2022-05-27 17:48:11,455 INFO [train.py:826] (5/8) Training started
2022-05-27 17:48:11,456 INFO [train.py:836] (5/8) Device: cuda:5
2022-05-27 17:48:11,506 INFO [train.py:846] (5/8) {'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, 'vgg_frontend': False, 'embedding_dim': 512, 'warm_step': 80000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.3.0.dev+missing.version.file', 'torch-version': '1.11.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'streaming-emformer-2022-05-27', 'icefall-git-sha1': 'c8c8645-dirty', 'icefall-git-date': 'Tue May 24 23:07:40 2022', 'icefall-path': '/ceph-fj/fangjun/open-source-2/icefall-streaming-2', 'k2-path': '/ceph-fj/fangjun/open-source-2/k2-multi-22/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-fj/fangjun/open-source-2/lhotse-master/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-6-0415002726-7dc5bf9fdc-w24k9', 'IP address': '10.177.28.71'}, 'world_size': 8, 'master_port': 12358, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 1, 'start_batch': 0, 'exp_dir': PosixPath('pruned_stateless_emformer_rnnt2/exp-full'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'lr_factor': 5.0, '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': 20, 'average_period': 100, 'use_fp16': False, 'attention_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 18, 'left_context_length': 128, 'segment_length': 8, 'right_context_length': 4, 'memory_size': 0, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 200, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'blank_id': 0, 'unk_id': 2, 'vocab_size': 500}
2022-05-27 17:48:11,506 INFO [train.py:848] (5/8) About to create model
2022-05-27 17:48:12,624 INFO [train.py:852] (5/8) Number of model parameters: 65390556
2022-05-27 17:48:18,159 INFO [train.py:867] (5/8) Using DDP
2022-05-27 17:48:19,232 INFO [asr_datamodule.py:392] (5/8) About to get train-clean-100 cuts
2022-05-27 17:48:28,004 INFO [asr_datamodule.py:399] (5/8) About to get train-clean-360 cuts
2022-05-27 17:49:02,880 INFO [asr_datamodule.py:406] (5/8) About to get train-other-500 cuts
2022-05-27 17:49:53,672 INFO [asr_datamodule.py:209] (5/8) Enable MUSAN
2022-05-27 17:49:53,672 INFO [asr_datamodule.py:210] (5/8) About to get Musan cuts
2022-05-27 17:50:03,033 INFO [asr_datamodule.py:238] (5/8) Enable SpecAugment
2022-05-27 17:50:03,033 INFO [asr_datamodule.py:239] (5/8) Time warp factor: 80
2022-05-27 17:50:03,033 INFO [asr_datamodule.py:251] (5/8) Num frame mask: 10
2022-05-27 17:50:03,034 INFO [asr_datamodule.py:264] (5/8) About to create train dataset
2022-05-27 17:50:03,034 INFO [asr_datamodule.py:292] (5/8) Using DynamicBucketingSampler.
2022-05-27 17:50:03,119 INFO [asr_datamodule.py:307] (5/8) About to create train dataloader
2022-05-27 17:50:03,119 INFO [asr_datamodule.py:413] (5/8) About to get dev-clean cuts
2022-05-27 17:50:03,321 INFO [asr_datamodule.py:418] (5/8) About to get dev-other cuts
2022-05-27 17:50:03,517 INFO [asr_datamodule.py:338] (5/8) About to create dev dataset
2022-05-27 17:50:03,523 INFO [asr_datamodule.py:357] (5/8) About to create dev dataloader
2022-05-27 17:50:03,523 INFO [train.py:986] (5/8) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
2022-05-27 17:51:21,528 INFO [distributed.py:948] (5/8) Reducer buckets have been rebuilt in this iteration.
2022-05-27 17:51:37,861 INFO [train.py:761] (5/8) Epoch 1, batch 0, loss[loss=10.55, simple_loss=7.095, pruned_loss=6.999, over 4990.00 frames.], tot_loss[loss=10.55, simple_loss=7.095, pruned_loss=6.999, over 4990.00 frames.], batch size: 26, lr: 6.84e-08
2022-05-27 17:52:15,836 INFO [train.py:761] (5/8) Epoch 1, batch 50, loss[loss=8.951, simple_loss=4.34, pruned_loss=6.781, over 4971.00 frames.], tot_loss[loss=10.01, simple_loss=6.006, pruned_loss=7.005, over 217451.76 frames.], batch size: 12, lr: 5.57e-07
2022-05-27 17:52:53,851 INFO [train.py:761] (5/8) Epoch 1, batch 100, loss[loss=7.624, simple_loss=2.95, pruned_loss=6.149, over 4853.00 frames.], tot_loss[loss=8.951, simple_loss=4.463, pruned_loss=6.72, over 383596.96 frames.], batch size: 14, lr: 1.04e-06
2022-05-27 17:53:31,913 INFO [train.py:761] (5/8) Epoch 1, batch 150, loss[loss=6.78, simple_loss=2.817, pruned_loss=5.371, over 4977.00 frames.], tot_loss[loss=8.186, simple_loss=3.794, pruned_loss=6.289, over 513419.30 frames.], batch size: 13, lr: 1.53e-06
2022-05-27 17:54:09,971 INFO [train.py:761] (5/8) Epoch 1, batch 200, loss[loss=6.322, simple_loss=2.847, pruned_loss=4.898, over 4676.00 frames.], tot_loss[loss=7.613, simple_loss=3.464, pruned_loss=5.881, over 613470.03 frames.], batch size: 13, lr: 2.02e-06
2022-05-27 17:54:47,962 INFO [train.py:761] (5/8) Epoch 1, batch 250, loss[loss=5.937, simple_loss=2.886, pruned_loss=4.493, over 4877.00 frames.], tot_loss[loss=7.14, simple_loss=3.271, pruned_loss=5.504, over 692176.93 frames.], batch size: 15, lr: 2.51e-06
2022-05-27 17:55:26,650 INFO [train.py:761] (5/8) Epoch 1, batch 300, loss[loss=5.247, simple_loss=2.695, pruned_loss=3.9, over 4828.00 frames.], tot_loss[loss=6.704, simple_loss=3.144, pruned_loss=5.132, over 753272.79 frames.], batch size: 11, lr: 3.00e-06
2022-05-27 17:56:04,434 INFO [train.py:761] (5/8) Epoch 1, batch 350, loss[loss=4.741, simple_loss=2.744, pruned_loss=3.369, over 4920.00 frames.], tot_loss[loss=6.274, simple_loss=3.058, pruned_loss=4.745, over 799764.58 frames.], batch size: 13, lr: 3.49e-06
2022-05-27 17:56:42,531 INFO [train.py:761] (5/8) Epoch 1, batch 400, loss[loss=4.386, simple_loss=2.934, pruned_loss=2.919, over 4884.00 frames.], tot_loss[loss=5.818, simple_loss=2.991, pruned_loss=4.323, over 836906.63 frames.], batch size: 17, lr: 3.97e-06
2022-05-27 17:57:20,652 INFO [train.py:761] (5/8) Epoch 1, batch 450, loss[loss=3.686, simple_loss=2.806, pruned_loss=2.283, over 4812.00 frames.], tot_loss[loss=5.352, simple_loss=2.947, pruned_loss=3.878, over 865363.74 frames.], batch size: 12, lr: 4.46e-06
2022-05-27 17:57:58,807 INFO [train.py:761] (5/8) Epoch 1, batch 500, loss[loss=3.098, simple_loss=2.722, pruned_loss=1.737, over 4923.00 frames.], tot_loss[loss=4.881, simple_loss=2.91, pruned_loss=3.426, over 887276.75 frames.], batch size: 13, lr: 4.95e-06
2022-05-27 17:58:36,580 INFO [train.py:761] (5/8) Epoch 1, batch 550, loss[loss=2.843, simple_loss=2.725, pruned_loss=1.48, over 4845.00 frames.], tot_loss[loss=4.436, simple_loss=2.875, pruned_loss=2.998, over 904362.16 frames.], batch size: 13, lr: 5.44e-06
2022-05-27 17:59:14,312 INFO [train.py:761] (5/8) Epoch 1, batch 600, loss[loss=2.785, simple_loss=2.751, pruned_loss=1.41, over 4614.00 frames.], tot_loss[loss=4.065, simple_loss=2.851, pruned_loss=2.639, over 917426.65 frames.], batch size: 12, lr: 5.93e-06
2022-05-27 17:59:52,257 INFO [train.py:761] (5/8) Epoch 1, batch 650, loss[loss=2.803, simple_loss=2.759, pruned_loss=1.424, over 4979.00 frames.], tot_loss[loss=3.769, simple_loss=2.829, pruned_loss=2.355, over 929175.82 frames.], batch size: 15, lr: 6.42e-06
2022-05-27 18:00:30,777 INFO [train.py:761] (5/8) Epoch 1, batch 700, loss[loss=2.385, simple_loss=2.462, pruned_loss=1.154, over 4828.00 frames.], tot_loss[loss=3.531, simple_loss=2.801, pruned_loss=2.131, over 937538.05 frames.], batch size: 11, lr: 6.90e-06
2022-05-27 18:01:07,996 INFO [train.py:761] (5/8) Epoch 1, batch 750, loss[loss=2.543, simple_loss=2.56, pruned_loss=1.263, over 4857.00 frames.], tot_loss[loss=3.341, simple_loss=2.771, pruned_loss=1.956, over 943992.86 frames.], batch size: 13, lr: 7.39e-06
2022-05-27 18:01:46,323 INFO [train.py:761] (5/8) Epoch 1, batch 800, loss[loss=2.744, simple_loss=2.668, pruned_loss=1.41, over 4909.00 frames.], tot_loss[loss=3.19, simple_loss=2.741, pruned_loss=1.819, over 949930.42 frames.], batch size: 14, lr: 7.88e-06
2022-05-27 18:02:24,027 INFO [train.py:761] (5/8) Epoch 1, batch 850, loss[loss=2.617, simple_loss=2.612, pruned_loss=1.311, over 4966.00 frames.], tot_loss[loss=3.063, simple_loss=2.709, pruned_loss=1.708, over 954732.59 frames.], batch size: 49, lr: 8.37e-06
2022-05-27 18:03:02,807 INFO [train.py:761] (5/8) Epoch 1, batch 900, loss[loss=2.594, simple_loss=2.563, pruned_loss=1.313, over 4898.00 frames.], tot_loss[loss=2.951, simple_loss=2.672, pruned_loss=1.615, over 957271.52 frames.], batch size: 15, lr: 8.86e-06
2022-05-27 18:03:40,733 INFO [train.py:761] (5/8) Epoch 1, batch 950, loss[loss=2.509, simple_loss=2.478, pruned_loss=1.27, over 4917.00 frames.], tot_loss[loss=2.86, simple_loss=2.636, pruned_loss=1.542, over 960464.47 frames.], batch size: 14, lr: 9.35e-06
2022-05-27 18:04:18,521 INFO [train.py:761] (5/8) Epoch 1, batch 1000, loss[loss=2.402, simple_loss=2.376, pruned_loss=1.214, over 4855.00 frames.], tot_loss[loss=2.788, simple_loss=2.604, pruned_loss=1.486, over 961770.54 frames.], batch size: 13, lr: 9.83e-06
2022-05-27 18:04:56,234 INFO [train.py:761] (5/8) Epoch 1, batch 1050, loss[loss=2.473, simple_loss=2.421, pruned_loss=1.263, over 4849.00 frames.], tot_loss[loss=2.724, simple_loss=2.567, pruned_loss=1.44, over 963523.51 frames.], batch size: 20, lr: 1.03e-05
2022-05-27 18:05:34,397 INFO [train.py:761] (5/8) Epoch 1, batch 1100, loss[loss=2.344, simple_loss=2.309, pruned_loss=1.189, over 4723.00 frames.], tot_loss[loss=2.663, simple_loss=2.528, pruned_loss=1.399, over 964539.81 frames.], batch size: 11, lr: 1.08e-05
2022-05-27 18:06:12,425 INFO [train.py:761] (5/8) Epoch 1, batch 1150, loss[loss=2.428, simple_loss=2.329, pruned_loss=1.264, over 4919.00 frames.], tot_loss[loss=2.619, simple_loss=2.494, pruned_loss=1.373, over 964762.26 frames.], batch size: 13, lr: 1.13e-05
2022-05-27 18:06:50,749 INFO [train.py:761] (5/8) Epoch 1, batch 1200, loss[loss=2.403, simple_loss=2.315, pruned_loss=1.246, over 4916.00 frames.], tot_loss[loss=2.579, simple_loss=2.458, pruned_loss=1.35, over 964778.99 frames.], batch size: 26, lr: 1.18e-05
2022-05-27 18:07:28,514 INFO [train.py:761] (5/8) Epoch 1, batch 1250, loss[loss=2.51, simple_loss=2.362, pruned_loss=1.329, over 4873.00 frames.], tot_loss[loss=2.546, simple_loss=2.423, pruned_loss=1.334, over 964949.28 frames.], batch size: 26, lr: 1.23e-05
2022-05-27 18:08:06,274 INFO [train.py:761] (5/8) Epoch 1, batch 1300, loss[loss=2.368, simple_loss=2.224, pruned_loss=1.256, over 4847.00 frames.], tot_loss[loss=2.519, simple_loss=2.391, pruned_loss=1.324, over 963891.68 frames.], batch size: 14, lr: 1.28e-05
2022-05-27 18:08:44,054 INFO [train.py:761] (5/8) Epoch 1, batch 1350, loss[loss=2.342, simple_loss=2.181, pruned_loss=1.252, over 4845.00 frames.], tot_loss[loss=2.489, simple_loss=2.354, pruned_loss=1.312, over 963324.14 frames.], batch size: 13, lr: 1.33e-05
2022-05-27 18:09:21,727 INFO [train.py:761] (5/8) Epoch 1, batch 1400, loss[loss=2.405, simple_loss=2.199, pruned_loss=1.306, over 4793.00 frames.], tot_loss[loss=2.469, simple_loss=2.322, pruned_loss=1.309, over 964707.26 frames.], batch size: 16, lr: 1.37e-05
2022-05-27 18:09:59,784 INFO [train.py:761] (5/8) Epoch 1, batch 1450, loss[loss=2.12, simple_loss=1.987, pruned_loss=1.127, over 4642.00 frames.], tot_loss[loss=2.443, simple_loss=2.283, pruned_loss=1.301, over 965491.84 frames.], batch size: 11, lr: 1.42e-05
2022-05-27 18:10:38,067 INFO [train.py:761] (5/8) Epoch 1, batch 1500, loss[loss=2.142, simple_loss=1.973, pruned_loss=1.156, over 4831.00 frames.], tot_loss[loss=2.411, simple_loss=2.241, pruned_loss=1.291, over 964535.63 frames.], batch size: 11, lr: 1.47e-05
2022-05-27 18:11:16,001 INFO [train.py:761] (5/8) Epoch 1, batch 1550, loss[loss=2.375, simple_loss=2.094, pruned_loss=1.328, over 4972.00 frames.], tot_loss[loss=2.381, simple_loss=2.198, pruned_loss=1.282, over 964731.20 frames.], batch size: 15, lr: 1.52e-05
2022-05-27 18:11:54,053 INFO [train.py:761] (5/8) Epoch 1, batch 1600, loss[loss=2.297, simple_loss=2.029, pruned_loss=1.283, over 4950.00 frames.], tot_loss[loss=2.356, simple_loss=2.158, pruned_loss=1.277, over 964995.20 frames.], batch size: 16, lr: 1.57e-05
2022-05-27 18:12:32,415 INFO [train.py:761] (5/8) Epoch 1, batch 1650, loss[loss=2.361, simple_loss=2.032, pruned_loss=1.344, over 4775.00 frames.], tot_loss[loss=2.338, simple_loss=2.121, pruned_loss=1.278, over 965948.87 frames.], batch size: 16, lr: 1.62e-05
2022-05-27 18:13:10,726 INFO [train.py:761] (5/8) Epoch 1, batch 1700, loss[loss=2.364, simple_loss=2.003, pruned_loss=1.363, over 4765.00 frames.], tot_loss[loss=2.311, simple_loss=2.076, pruned_loss=1.273, over 965353.94 frames.], batch size: 15, lr: 1.67e-05
2022-05-27 18:13:48,663 INFO [train.py:761] (5/8) Epoch 1, batch 1750, loss[loss=2.259, simple_loss=1.903, pruned_loss=1.308, over 4965.00 frames.], tot_loss[loss=2.293, simple_loss=2.036, pruned_loss=1.275, over 966966.75 frames.], batch size: 16, lr: 1.72e-05
2022-05-27 18:14:26,779 INFO [train.py:761] (5/8) Epoch 1, batch 1800, loss[loss=2.267, simple_loss=1.887, pruned_loss=1.324, over 4971.00 frames.], tot_loss[loss=2.272, simple_loss=1.993, pruned_loss=1.275, over 966951.13 frames.], batch size: 21, lr: 1.76e-05
2022-05-27 18:15:04,390 INFO [train.py:761] (5/8) Epoch 1, batch 1850, loss[loss=2.209, simple_loss=1.8, pruned_loss=1.309, over 4850.00 frames.], tot_loss[loss=2.248, simple_loss=1.948, pruned_loss=1.274, over 967858.00 frames.], batch size: 14, lr: 1.81e-05
2022-05-27 18:15:42,733 INFO [train.py:761] (5/8) Epoch 1, batch 1900, loss[loss=2.033, simple_loss=1.657, pruned_loss=1.204, over 4738.00 frames.], tot_loss[loss=2.226, simple_loss=1.905, pruned_loss=1.273, over 967191.96 frames.], batch size: 11, lr: 1.86e-05
2022-05-27 18:16:20,304 INFO [train.py:761] (5/8) Epoch 1, batch 1950, loss[loss=2.081, simple_loss=1.662, pruned_loss=1.25, over 4797.00 frames.], tot_loss[loss=2.202, simple_loss=1.859, pruned_loss=1.273, over 967012.04 frames.], batch size: 12, lr: 1.91e-05
2022-05-27 18:16:58,512 INFO [train.py:761] (5/8) Epoch 1, batch 2000, loss[loss=2.112, simple_loss=1.647, pruned_loss=1.288, over 4803.00 frames.], tot_loss[loss=2.179, simple_loss=1.813, pruned_loss=1.273, over 967232.84 frames.], batch size: 12, lr: 1.96e-05
2022-05-27 18:17:36,235 INFO [train.py:761] (5/8) Epoch 1, batch 2050, loss[loss=2.012, simple_loss=1.556, pruned_loss=1.234, over 4730.00 frames.], tot_loss[loss=2.157, simple_loss=1.768, pruned_loss=1.272, over 967478.61 frames.], batch size: 12, lr: 2.01e-05
2022-05-27 18:18:13,995 INFO [train.py:761] (5/8) Epoch 1, batch 2100, loss[loss=2.159, simple_loss=1.634, pruned_loss=1.342, over 4782.00 frames.], tot_loss[loss=2.137, simple_loss=1.725, pruned_loss=1.274, over 968228.40 frames.], batch size: 20, lr: 2.06e-05
2022-05-27 18:18:51,846 INFO [train.py:761] (5/8) Epoch 1, batch 2150, loss[loss=1.891, simple_loss=1.409, pruned_loss=1.186, over 4730.00 frames.], tot_loss[loss=2.112, simple_loss=1.679, pruned_loss=1.273, over 968026.61 frames.], batch size: 12, lr: 2.11e-05
2022-05-27 18:19:30,070 INFO [train.py:761] (5/8) Epoch 1, batch 2200, loss[loss=2.138, simple_loss=1.522, pruned_loss=1.377, over 4787.00 frames.], tot_loss[loss=2.093, simple_loss=1.636, pruned_loss=1.275, over 968626.87 frames.], batch size: 13, lr: 2.16e-05
2022-05-27 18:20:07,736 INFO [train.py:761] (5/8) Epoch 1, batch 2250, loss[loss=1.89, simple_loss=1.344, pruned_loss=1.218, over 4814.00 frames.], tot_loss[loss=2.068, simple_loss=1.589, pruned_loss=1.273, over 967010.28 frames.], batch size: 12, lr: 2.20e-05
2022-05-27 18:20:45,927 INFO [train.py:761] (5/8) Epoch 1, batch 2300, loss[loss=2.098, simple_loss=1.477, pruned_loss=1.359, over 4824.00 frames.], tot_loss[loss=2.044, simple_loss=1.545, pruned_loss=1.272, over 967197.62 frames.], batch size: 18, lr: 2.25e-05
2022-05-27 18:21:23,661 INFO [train.py:761] (5/8) Epoch 1, batch 2350, loss[loss=1.981, simple_loss=1.372, pruned_loss=1.295, over 4754.00 frames.], tot_loss[loss=2.019, simple_loss=1.501, pruned_loss=1.268, over 967641.32 frames.], batch size: 15, lr: 2.30e-05
2022-05-27 18:22:01,277 INFO [train.py:761] (5/8) Epoch 1, batch 2400, loss[loss=1.887, simple_loss=1.296, pruned_loss=1.239, over 4891.00 frames.], tot_loss[loss=1.997, simple_loss=1.462, pruned_loss=1.266, over 967142.05 frames.], batch size: 15, lr: 2.35e-05
2022-05-27 18:22:38,985 INFO [train.py:761] (5/8) Epoch 1, batch 2450, loss[loss=2.022, simple_loss=1.359, pruned_loss=1.343, over 4983.00 frames.], tot_loss[loss=1.978, simple_loss=1.427, pruned_loss=1.265, over 967186.26 frames.], batch size: 15, lr: 2.40e-05
2022-05-27 18:23:16,706 INFO [train.py:761] (5/8) Epoch 1, batch 2500, loss[loss=2.091, simple_loss=1.401, pruned_loss=1.39, over 4885.00 frames.], tot_loss[loss=1.965, simple_loss=1.397, pruned_loss=1.266, over 966979.14 frames.], batch size: 17, lr: 2.45e-05
2022-05-27 18:23:54,499 INFO [train.py:761] (5/8) Epoch 1, batch 2550, loss[loss=1.984, simple_loss=1.337, pruned_loss=1.316, over 4958.00 frames.], tot_loss[loss=1.945, simple_loss=1.365, pruned_loss=1.262, over 966192.35 frames.], batch size: 21, lr: 2.50e-05
2022-05-27 18:24:32,238 INFO [train.py:761] (5/8) Epoch 1, batch 2600, loss[loss=2.034, simple_loss=1.333, pruned_loss=1.367, over 4729.00 frames.], tot_loss[loss=1.926, simple_loss=1.336, pruned_loss=1.258, over 966052.24 frames.], batch size: 14, lr: 2.55e-05
2022-05-27 18:25:10,326 INFO [train.py:761] (5/8) Epoch 1, batch 2650, loss[loss=1.851, simple_loss=1.22, pruned_loss=1.241, over 4837.00 frames.], tot_loss[loss=1.906, simple_loss=1.307, pruned_loss=1.253, over 965701.90 frames.], batch size: 18, lr: 2.59e-05
2022-05-27 18:25:48,674 INFO [train.py:761] (5/8) Epoch 1, batch 2700, loss[loss=1.665, simple_loss=1.079, pruned_loss=1.125, over 4652.00 frames.], tot_loss[loss=1.889, simple_loss=1.28, pruned_loss=1.249, over 966399.69 frames.], batch size: 11, lr: 2.64e-05
2022-05-27 18:26:26,374 INFO [train.py:761] (5/8) Epoch 1, batch 2750, loss[loss=1.818, simple_loss=1.196, pruned_loss=1.221, over 4809.00 frames.], tot_loss[loss=1.88, simple_loss=1.262, pruned_loss=1.249, over 965801.02 frames.], batch size: 25, lr: 2.69e-05
2022-05-27 18:27:04,072 INFO [train.py:761] (5/8) Epoch 1, batch 2800, loss[loss=1.854, simple_loss=1.197, pruned_loss=1.255, over 4708.00 frames.], tot_loss[loss=1.867, simple_loss=1.245, pruned_loss=1.245, over 966028.59 frames.], batch size: 14, lr: 2.74e-05
2022-05-27 18:27:41,907 INFO [train.py:761] (5/8) Epoch 1, batch 2850, loss[loss=1.872, simple_loss=1.232, pruned_loss=1.256, over 4923.00 frames.], tot_loss[loss=1.858, simple_loss=1.232, pruned_loss=1.242, over 966255.77 frames.], batch size: 26, lr: 2.79e-05
2022-05-27 18:28:19,513 INFO [train.py:761] (5/8) Epoch 1, batch 2900, loss[loss=1.719, simple_loss=1.113, pruned_loss=1.162, over 4920.00 frames.], tot_loss[loss=1.839, simple_loss=1.214, pruned_loss=1.232, over 965716.49 frames.], batch size: 13, lr: 2.84e-05
2022-05-27 18:28:57,300 INFO [train.py:761] (5/8) Epoch 1, batch 2950, loss[loss=1.515, simple_loss=0.9761, pruned_loss=1.027, over 4568.00 frames.], tot_loss[loss=1.825, simple_loss=1.202, pruned_loss=1.224, over 965842.03 frames.], batch size: 10, lr: 2.89e-05
2022-05-27 18:29:35,425 INFO [train.py:761] (5/8) Epoch 1, batch 3000, loss[loss=1.88, simple_loss=1.232, pruned_loss=1.264, over 4965.00 frames.], tot_loss[loss=1.812, simple_loss=1.192, pruned_loss=1.217, over 965016.44 frames.], batch size: 14, lr: 2.94e-05
2022-05-27 18:29:35,426 INFO [train.py:781] (5/8) Computing validation loss
2022-05-27 18:29:45,394 INFO [train.py:790] (5/8) Epoch 1, validation: loss=1.786, simple_loss=1.18, pruned_loss=1.196, over 944034.00 frames.
2022-05-27 18:30:23,271 INFO [train.py:761] (5/8) Epoch 1, batch 3050, loss[loss=1.523, simple_loss=0.9915, pruned_loss=1.027, over 4737.00 frames.], tot_loss[loss=1.8, simple_loss=1.183, pruned_loss=1.209, over 965061.25 frames.], batch size: 11, lr: 2.99e-05
2022-05-27 18:31:01,748 INFO [train.py:761] (5/8) Epoch 1, batch 3100, loss[loss=1.767, simple_loss=1.181, pruned_loss=1.177, over 4882.00 frames.], tot_loss[loss=1.786, simple_loss=1.174, pruned_loss=1.2, over 964916.11 frames.], batch size: 45, lr: 3.03e-05
2022-05-27 18:31:39,481 INFO [train.py:761] (5/8) Epoch 1, batch 3150, loss[loss=1.677, simple_loss=1.106, pruned_loss=1.125, over 4969.00 frames.], tot_loss[loss=1.768, simple_loss=1.162, pruned_loss=1.187, over 964976.63 frames.], batch size: 16, lr: 3.08e-05
2022-05-27 18:32:17,751 INFO [train.py:761] (5/8) Epoch 1, batch 3200, loss[loss=1.794, simple_loss=1.189, pruned_loss=1.199, over 4803.00 frames.], tot_loss[loss=1.764, simple_loss=1.16, pruned_loss=1.184, over 965446.38 frames.], batch size: 16, lr: 3.13e-05
2022-05-27 18:32:56,158 INFO [train.py:761] (5/8) Epoch 1, batch 3250, loss[loss=1.699, simple_loss=1.125, pruned_loss=1.137, over 4971.00 frames.], tot_loss[loss=1.746, simple_loss=1.15, pruned_loss=1.171, over 966851.28 frames.], batch size: 15, lr: 3.18e-05
2022-05-27 18:33:34,552 INFO [train.py:761] (5/8) Epoch 1, batch 3300, loss[loss=1.707, simple_loss=1.139, pruned_loss=1.138, over 4801.00 frames.], tot_loss[loss=1.727, simple_loss=1.139, pruned_loss=1.157, over 966847.66 frames.], batch size: 20, lr: 3.23e-05
2022-05-27 18:34:12,517 INFO [train.py:761] (5/8) Epoch 1, batch 3350, loss[loss=1.511, simple_loss=1, pruned_loss=1.01, over 4839.00 frames.], tot_loss[loss=1.718, simple_loss=1.135, pruned_loss=1.151, over 968026.08 frames.], batch size: 11, lr: 3.28e-05
2022-05-27 18:34:50,239 INFO [train.py:761] (5/8) Epoch 1, batch 3400, loss[loss=1.632, simple_loss=1.081, pruned_loss=1.092, over 4735.00 frames.], tot_loss[loss=1.711, simple_loss=1.132, pruned_loss=1.145, over 967332.19 frames.], batch size: 12, lr: 3.33e-05
2022-05-27 18:35:28,009 INFO [train.py:761] (5/8) Epoch 1, batch 3450, loss[loss=1.676, simple_loss=1.122, pruned_loss=1.115, over 4726.00 frames.], tot_loss[loss=1.695, simple_loss=1.123, pruned_loss=1.133, over 966205.30 frames.], batch size: 13, lr: 3.38e-05
2022-05-27 18:36:05,847 INFO [train.py:761] (5/8) Epoch 1, batch 3500, loss[loss=1.58, simple_loss=1.062, pruned_loss=1.048, over 4945.00 frames.], tot_loss[loss=1.684, simple_loss=1.118, pruned_loss=1.125, over 966525.03 frames.], batch size: 47, lr: 3.42e-05
2022-05-27 18:36:43,103 INFO [train.py:761] (5/8) Epoch 1, batch 3550, loss[loss=1.657, simple_loss=1.112, pruned_loss=1.101, over 4923.00 frames.], tot_loss[loss=1.676, simple_loss=1.114, pruned_loss=1.119, over 967156.44 frames.], batch size: 13, lr: 3.47e-05
2022-05-27 18:37:21,444 INFO [train.py:761] (5/8) Epoch 1, batch 3600, loss[loss=1.705, simple_loss=1.149, pruned_loss=1.131, over 4965.00 frames.], tot_loss[loss=1.665, simple_loss=1.109, pruned_loss=1.111, over 967268.17 frames.], batch size: 16, lr: 3.52e-05
2022-05-27 18:37:59,646 INFO [train.py:761] (5/8) Epoch 1, batch 3650, loss[loss=1.647, simple_loss=1.105, pruned_loss=1.095, over 4770.00 frames.], tot_loss[loss=1.661, simple_loss=1.107, pruned_loss=1.107, over 967476.86 frames.], batch size: 15, lr: 3.57e-05
2022-05-27 18:38:38,281 INFO [train.py:761] (5/8) Epoch 1, batch 3700, loss[loss=1.689, simple_loss=1.126, pruned_loss=1.126, over 4890.00 frames.], tot_loss[loss=1.651, simple_loss=1.103, pruned_loss=1.1, over 967027.73 frames.], batch size: 15, lr: 3.62e-05
2022-05-27 18:39:16,351 INFO [train.py:761] (5/8) Epoch 1, batch 3750, loss[loss=1.69, simple_loss=1.14, pruned_loss=1.12, over 4918.00 frames.], tot_loss[loss=1.64, simple_loss=1.097, pruned_loss=1.092, over 966814.09 frames.], batch size: 14, lr: 3.67e-05
2022-05-27 18:39:54,182 INFO [train.py:761] (5/8) Epoch 1, batch 3800, loss[loss=1.561, simple_loss=1.054, pruned_loss=1.034, over 4917.00 frames.], tot_loss[loss=1.631, simple_loss=1.093, pruned_loss=1.085, over 965495.42 frames.], batch size: 13, lr: 3.72e-05
2022-05-27 18:40:32,204 INFO [train.py:761] (5/8) Epoch 1, batch 3850, loss[loss=1.417, simple_loss=0.9557, pruned_loss=0.9388, over 4805.00 frames.], tot_loss[loss=1.616, simple_loss=1.085, pruned_loss=1.073, over 965349.72 frames.], batch size: 12, lr: 3.77e-05
2022-05-27 18:41:10,098 INFO [train.py:761] (5/8) Epoch 1, batch 3900, loss[loss=1.697, simple_loss=1.14, pruned_loss=1.127, over 4977.00 frames.], tot_loss[loss=1.608, simple_loss=1.082, pruned_loss=1.067, over 966017.98 frames.], batch size: 14, lr: 3.82e-05
2022-05-27 18:41:48,091 INFO [train.py:761] (5/8) Epoch 1, batch 3950, loss[loss=1.421, simple_loss=0.9644, pruned_loss=0.9388, over 4809.00 frames.], tot_loss[loss=1.593, simple_loss=1.074, pruned_loss=1.056, over 964599.25 frames.], batch size: 11, lr: 3.86e-05
2022-05-27 18:42:26,292 INFO [train.py:761] (5/8) Epoch 1, batch 4000, loss[loss=1.683, simple_loss=1.14, pruned_loss=1.113, over 4798.00 frames.], tot_loss[loss=1.591, simple_loss=1.074, pruned_loss=1.054, over 965320.16 frames.], batch size: 14, lr: 3.91e-05
2022-05-27 18:43:04,686 INFO [train.py:761] (5/8) Epoch 1, batch 4050, loss[loss=1.341, simple_loss=0.91, pruned_loss=0.8864, over 4804.00 frames.], tot_loss[loss=1.588, simple_loss=1.074, pruned_loss=1.051, over 965558.89 frames.], batch size: 12, lr: 3.96e-05
2022-05-27 18:43:42,395 INFO [train.py:761] (5/8) Epoch 1, batch 4100, loss[loss=1.719, simple_loss=1.163, pruned_loss=1.138, over 4788.00 frames.], tot_loss[loss=1.578, simple_loss=1.069, pruned_loss=1.043, over 965487.91 frames.], batch size: 14, lr: 4.01e-05
2022-05-27 18:44:20,537 INFO [train.py:761] (5/8) Epoch 1, batch 4150, loss[loss=1.52, simple_loss=1.041, pruned_loss=1, over 4857.00 frames.], tot_loss[loss=1.574, simple_loss=1.068, pruned_loss=1.04, over 966353.78 frames.], batch size: 13, lr: 4.06e-05
2022-05-27 18:44:59,196 INFO [train.py:761] (5/8) Epoch 1, batch 4200, loss[loss=1.727, simple_loss=1.179, pruned_loss=1.138, over 4831.00 frames.], tot_loss[loss=1.573, simple_loss=1.069, pruned_loss=1.038, over 966631.91 frames.], batch size: 18, lr: 4.11e-05
2022-05-27 18:45:36,979 INFO [train.py:761] (5/8) Epoch 1, batch 4250, loss[loss=1.558, simple_loss=1.07, pruned_loss=1.023, over 4852.00 frames.], tot_loss[loss=1.566, simple_loss=1.067, pruned_loss=1.033, over 966856.90 frames.], batch size: 13, lr: 4.16e-05
2022-05-27 18:46:14,863 INFO [train.py:761] (5/8) Epoch 1, batch 4300, loss[loss=1.666, simple_loss=1.147, pruned_loss=1.092, over 4853.00 frames.], tot_loss[loss=1.555, simple_loss=1.062, pruned_loss=1.024, over 967309.96 frames.], batch size: 18, lr: 4.21e-05
2022-05-27 18:46:52,584 INFO [train.py:761] (5/8) Epoch 1, batch 4350, loss[loss=1.446, simple_loss=1.007, pruned_loss=0.9423, over 4918.00 frames.], tot_loss[loss=1.549, simple_loss=1.06, pruned_loss=1.019, over 966689.04 frames.], batch size: 14, lr: 4.25e-05
2022-05-27 18:47:31,049 INFO [train.py:761] (5/8) Epoch 1, batch 4400, loss[loss=1.607, simple_loss=1.105, pruned_loss=1.054, over 4786.00 frames.], tot_loss[loss=1.544, simple_loss=1.058, pruned_loss=1.014, over 967319.64 frames.], batch size: 14, lr: 4.30e-05
2022-05-27 18:48:08,993 INFO [train.py:761] (5/8) Epoch 1, batch 4450, loss[loss=1.464, simple_loss=1.017, pruned_loss=0.9555, over 4732.00 frames.], tot_loss[loss=1.534, simple_loss=1.054, pruned_loss=1.007, over 966762.73 frames.], batch size: 12, lr: 4.35e-05
2022-05-27 18:48:47,745 INFO [train.py:761] (5/8) Epoch 1, batch 4500, loss[loss=1.249, simple_loss=0.87, pruned_loss=0.8143, over 4834.00 frames.], tot_loss[loss=1.531, simple_loss=1.055, pruned_loss=1.004, over 966897.69 frames.], batch size: 11, lr: 4.40e-05
2022-05-27 18:49:25,497 INFO [train.py:761] (5/8) Epoch 1, batch 4550, loss[loss=1.664, simple_loss=1.165, pruned_loss=1.082, over 4792.00 frames.], tot_loss[loss=1.522, simple_loss=1.051, pruned_loss=0.9963, over 965737.67 frames.], batch size: 14, lr: 4.45e-05
2022-05-27 18:50:03,769 INFO [train.py:761] (5/8) Epoch 1, batch 4600, loss[loss=1.544, simple_loss=1.083, pruned_loss=1.003, over 4764.00 frames.], tot_loss[loss=1.516, simple_loss=1.05, pruned_loss=0.991, over 966234.60 frames.], batch size: 15, lr: 4.50e-05
2022-05-27 18:50:41,839 INFO [train.py:761] (5/8) Epoch 1, batch 4650, loss[loss=1.536, simple_loss=1.076, pruned_loss=0.998, over 4855.00 frames.], tot_loss[loss=1.501, simple_loss=1.043, pruned_loss=0.9795, over 966671.19 frames.], batch size: 13, lr: 4.55e-05
2022-05-27 18:51:20,346 INFO [train.py:761] (5/8) Epoch 1, batch 4700, loss[loss=1.348, simple_loss=0.943, pruned_loss=0.876, over 4662.00 frames.], tot_loss[loss=1.49, simple_loss=1.039, pruned_loss=0.971, over 966261.47 frames.], batch size: 12, lr: 4.60e-05
2022-05-27 18:51:58,888 INFO [train.py:761] (5/8) Epoch 1, batch 4750, loss[loss=1.524, simple_loss=1.072, pruned_loss=0.988, over 4670.00 frames.], tot_loss[loss=1.488, simple_loss=1.041, pruned_loss=0.9677, over 967987.32 frames.], batch size: 13, lr: 4.65e-05
2022-05-27 18:52:37,208 INFO [train.py:761] (5/8) Epoch 1, batch 4800, loss[loss=1.285, simple_loss=0.9151, pruned_loss=0.8276, over 4575.00 frames.], tot_loss[loss=1.479, simple_loss=1.039, pruned_loss=0.9598, over 967800.34 frames.], batch size: 10, lr: 4.69e-05
2022-05-27 18:53:14,968 INFO [train.py:761] (5/8) Epoch 1, batch 4850, loss[loss=1.538, simple_loss=1.109, pruned_loss=0.9838, over 4952.00 frames.], tot_loss[loss=1.471, simple_loss=1.037, pruned_loss=0.9526, over 966592.77 frames.], batch size: 16, lr: 4.74e-05
2022-05-27 18:53:53,411 INFO [train.py:761] (5/8) Epoch 1, batch 4900, loss[loss=1.412, simple_loss=1.009, pruned_loss=0.9075, over 4737.00 frames.], tot_loss[loss=1.458, simple_loss=1.033, pruned_loss=0.9418, over 966917.21 frames.], batch size: 12, lr: 4.79e-05
2022-05-27 18:54:31,755 INFO [train.py:761] (5/8) Epoch 1, batch 4950, loss[loss=1.457, simple_loss=1.069, pruned_loss=0.922, over 4766.00 frames.], tot_loss[loss=1.449, simple_loss=1.03, pruned_loss=0.9336, over 967228.05 frames.], batch size: 15, lr: 4.84e-05
2022-05-27 18:55:10,712 INFO [train.py:761] (5/8) Epoch 1, batch 5000, loss[loss=1.48, simple_loss=1.074, pruned_loss=0.9429, over 4783.00 frames.], tot_loss[loss=1.437, simple_loss=1.026, pruned_loss=0.9239, over 967547.47 frames.], batch size: 13, lr: 4.89e-05
2022-05-27 18:55:48,959 INFO [train.py:761] (5/8) Epoch 1, batch 5050, loss[loss=1.253, simple_loss=0.9137, pruned_loss=0.7966, over 4984.00 frames.], tot_loss[loss=1.421, simple_loss=1.019, pruned_loss=0.9113, over 968438.21 frames.], batch size: 13, lr: 4.94e-05
2022-05-27 18:56:27,153 INFO [train.py:761] (5/8) Epoch 1, batch 5100, loss[loss=1.366, simple_loss=0.9959, pruned_loss=0.8681, over 4666.00 frames.], tot_loss[loss=1.402, simple_loss=1.01, pruned_loss=0.8973, over 966776.40 frames.], batch size: 12, lr: 4.99e-05
2022-05-27 18:57:05,857 INFO [train.py:761] (5/8) Epoch 1, batch 5150, loss[loss=1.128, simple_loss=0.8433, pruned_loss=0.7065, over 4829.00 frames.], tot_loss[loss=1.393, simple_loss=1.008, pruned_loss=0.889, over 967241.73 frames.], batch size: 11, lr: 5.04e-05
2022-05-27 18:57:43,905 INFO [train.py:761] (5/8) Epoch 1, batch 5200, loss[loss=1.444, simple_loss=1.068, pruned_loss=0.9095, over 4882.00 frames.], tot_loss[loss=1.387, simple_loss=1.008, pruned_loss=0.8827, over 966686.81 frames.], batch size: 15, lr: 5.08e-05
2022-05-27 18:58:21,970 INFO [train.py:761] (5/8) Epoch 1, batch 5250, loss[loss=1.429, simple_loss=1.062, pruned_loss=0.8982, over 4869.00 frames.], tot_loss[loss=1.377, simple_loss=1.006, pruned_loss=0.8745, over 967069.90 frames.], batch size: 20, lr: 5.13e-05
2022-05-27 18:59:00,655 INFO [train.py:761] (5/8) Epoch 1, batch 5300, loss[loss=1.431, simple_loss=1.065, pruned_loss=0.8983, over 4796.00 frames.], tot_loss[loss=1.37, simple_loss=1.004, pruned_loss=0.8678, over 967001.75 frames.], batch size: 16, lr: 5.18e-05
2022-05-27 18:59:38,599 INFO [train.py:761] (5/8) Epoch 1, batch 5350, loss[loss=1.321, simple_loss=1.01, pruned_loss=0.816, over 4990.00 frames.], tot_loss[loss=1.357, simple_loss=0.9995, pruned_loss=0.857, over 966998.42 frames.], batch size: 13, lr: 5.23e-05
2022-05-27 19:00:17,295 INFO [train.py:761] (5/8) Epoch 1, batch 5400, loss[loss=1.435, simple_loss=1.079, pruned_loss=0.8954, over 4878.00 frames.], tot_loss[loss=1.344, simple_loss=0.9951, pruned_loss=0.8468, over 967950.89 frames.], batch size: 15, lr: 5.28e-05
2022-05-27 19:00:55,675 INFO [train.py:761] (5/8) Epoch 1, batch 5450, loss[loss=1.409, simple_loss=1.06, pruned_loss=0.879, over 4863.00 frames.], tot_loss[loss=1.333, simple_loss=0.9912, pruned_loss=0.8372, over 968109.13 frames.], batch size: 20, lr: 5.33e-05
2022-05-27 19:01:33,924 INFO [train.py:761] (5/8) Epoch 1, batch 5500, loss[loss=1.319, simple_loss=1.012, pruned_loss=0.8128, over 4850.00 frames.], tot_loss[loss=1.329, simple_loss=0.9923, pruned_loss=0.8325, over 967211.96 frames.], batch size: 18, lr: 5.38e-05
2022-05-27 19:02:11,785 INFO [train.py:761] (5/8) Epoch 1, batch 5550, loss[loss=1.33, simple_loss=1.023, pruned_loss=0.818, over 4893.00 frames.], tot_loss[loss=1.315, simple_loss=0.9867, pruned_loss=0.8221, over 967607.82 frames.], batch size: 15, lr: 5.43e-05
2022-05-27 19:02:50,113 INFO [train.py:761] (5/8) Epoch 1, batch 5600, loss[loss=1.235, simple_loss=0.9341, pruned_loss=0.7681, over 4847.00 frames.], tot_loss[loss=1.304, simple_loss=0.9821, pruned_loss=0.8132, over 967753.41 frames.], batch size: 13, lr: 5.48e-05
2022-05-27 19:03:28,247 INFO [train.py:761] (5/8) Epoch 1, batch 5650, loss[loss=1.139, simple_loss=0.8605, pruned_loss=0.7083, over 4636.00 frames.], tot_loss[loss=1.291, simple_loss=0.9765, pruned_loss=0.8029, over 967594.83 frames.], batch size: 11, lr: 5.52e-05
2022-05-27 19:04:06,412 INFO [train.py:761] (5/8) Epoch 1, batch 5700, loss[loss=1.295, simple_loss=0.9935, pruned_loss=0.7978, over 4704.00 frames.], tot_loss[loss=1.282, simple_loss=0.9736, pruned_loss=0.7952, over 967530.23 frames.], batch size: 14, lr: 5.57e-05
2022-05-27 19:04:44,164 INFO [train.py:761] (5/8) Epoch 1, batch 5750, loss[loss=1.161, simple_loss=0.8976, pruned_loss=0.7123, over 4926.00 frames.], tot_loss[loss=1.271, simple_loss=0.9688, pruned_loss=0.7865, over 967027.17 frames.], batch size: 13, lr: 5.62e-05
2022-05-27 19:05:22,844 INFO [train.py:761] (5/8) Epoch 1, batch 5800, loss[loss=1.194, simple_loss=0.9427, pruned_loss=0.7226, over 4855.00 frames.], tot_loss[loss=1.259, simple_loss=0.9647, pruned_loss=0.777, over 966739.42 frames.], batch size: 13, lr: 5.67e-05
2022-05-27 19:06:00,996 INFO [train.py:761] (5/8) Epoch 1, batch 5850, loss[loss=1.234, simple_loss=0.9747, pruned_loss=0.7468, over 4796.00 frames.], tot_loss[loss=1.248, simple_loss=0.9598, pruned_loss=0.7682, over 965908.05 frames.], batch size: 16, lr: 5.72e-05
2022-05-27 19:06:40,240 INFO [train.py:761] (5/8) Epoch 1, batch 5900, loss[loss=1.274, simple_loss=0.9878, pruned_loss=0.7805, over 4852.00 frames.], tot_loss[loss=1.238, simple_loss=0.956, pruned_loss=0.7601, over 967324.67 frames.], batch size: 21, lr: 5.77e-05
2022-05-27 19:07:18,081 INFO [train.py:761] (5/8) Epoch 1, batch 5950, loss[loss=1.214, simple_loss=0.955, pruned_loss=0.7364, over 4933.00 frames.], tot_loss[loss=1.228, simple_loss=0.9527, pruned_loss=0.752, over 967449.80 frames.], batch size: 26, lr: 5.82e-05
2022-05-27 19:07:56,487 INFO [train.py:761] (5/8) Epoch 1, batch 6000, loss[loss=1.162, simple_loss=0.9033, pruned_loss=0.7099, over 4877.00 frames.], tot_loss[loss=1.22, simple_loss=0.9493, pruned_loss=0.745, over 966994.78 frames.], batch size: 17, lr: 5.87e-05
2022-05-27 19:07:56,488 INFO [train.py:781] (5/8) Computing validation loss
2022-05-27 19:08:06,382 INFO [train.py:790] (5/8) Epoch 1, validation: loss=1.09, simple_loss=0.9281, pruned_loss=0.6261, over 944034.00 frames.
2022-05-27 19:08:44,639 INFO [train.py:761] (5/8) Epoch 1, batch 6050, loss[loss=1.097, simple_loss=0.8811, pruned_loss=0.6567, over 4986.00 frames.], tot_loss[loss=1.209, simple_loss=0.9443, pruned_loss=0.7368, over 968158.34 frames.], batch size: 13, lr: 5.92e-05
2022-05-27 19:09:23,437 INFO [train.py:761] (5/8) Epoch 1, batch 6100, loss[loss=1.097, simple_loss=0.89, pruned_loss=0.652, over 4790.00 frames.], tot_loss[loss=1.199, simple_loss=0.9403, pruned_loss=0.7294, over 967098.80 frames.], batch size: 13, lr: 5.96e-05
2022-05-27 19:10:01,597 INFO [train.py:761] (5/8) Epoch 1, batch 6150, loss[loss=1.189, simple_loss=0.9245, pruned_loss=0.7268, over 4789.00 frames.], tot_loss[loss=1.19, simple_loss=0.9362, pruned_loss=0.7219, over 966897.99 frames.], batch size: 13, lr: 6.01e-05
2022-05-27 19:10:39,917 INFO [train.py:761] (5/8) Epoch 1, batch 6200, loss[loss=1.096, simple_loss=0.8686, pruned_loss=0.6612, over 4743.00 frames.], tot_loss[loss=1.177, simple_loss=0.9297, pruned_loss=0.7125, over 966249.79 frames.], batch size: 12, lr: 6.06e-05
2022-05-27 19:11:17,965 INFO [train.py:761] (5/8) Epoch 1, batch 6250, loss[loss=1.187, simple_loss=0.9673, pruned_loss=0.703, over 4674.00 frames.], tot_loss[loss=1.172, simple_loss=0.9292, pruned_loss=0.7077, over 966892.52 frames.], batch size: 13, lr: 6.11e-05
2022-05-27 19:11:56,402 INFO [train.py:761] (5/8) Epoch 1, batch 6300, loss[loss=1.19, simple_loss=0.9491, pruned_loss=0.7158, over 4799.00 frames.], tot_loss[loss=1.162, simple_loss=0.9232, pruned_loss=0.7, over 966012.37 frames.], batch size: 25, lr: 6.16e-05
2022-05-27 19:12:34,393 INFO [train.py:761] (5/8) Epoch 1, batch 6350, loss[loss=0.9208, simple_loss=0.7595, pruned_loss=0.541, over 4821.00 frames.], tot_loss[loss=1.148, simple_loss=0.9154, pruned_loss=0.6903, over 965431.44 frames.], batch size: 11, lr: 6.21e-05
2022-05-27 19:13:12,574 INFO [train.py:761] (5/8) Epoch 1, batch 6400, loss[loss=1.194, simple_loss=0.972, pruned_loss=0.7077, over 4972.00 frames.], tot_loss[loss=1.139, simple_loss=0.9113, pruned_loss=0.6834, over 965224.31 frames.], batch size: 21, lr: 6.26e-05
2022-05-27 19:13:50,556 INFO [train.py:761] (5/8) Epoch 1, batch 6450, loss[loss=1.212, simple_loss=0.96, pruned_loss=0.732, over 4978.00 frames.], tot_loss[loss=1.13, simple_loss=0.9073, pruned_loss=0.6764, over 965401.19 frames.], batch size: 14, lr: 6.31e-05
2022-05-27 19:14:28,677 INFO [train.py:761] (5/8) Epoch 1, batch 6500, loss[loss=1.182, simple_loss=0.9561, pruned_loss=0.7044, over 4769.00 frames.], tot_loss[loss=1.125, simple_loss=0.9065, pruned_loss=0.6714, over 965180.14 frames.], batch size: 15, lr: 6.35e-05
2022-05-27 19:15:06,840 INFO [train.py:761] (5/8) Epoch 1, batch 6550, loss[loss=1.095, simple_loss=0.8498, pruned_loss=0.6696, over 4660.00 frames.], tot_loss[loss=1.115, simple_loss=0.9008, pruned_loss=0.6649, over 964728.60 frames.], batch size: 12, lr: 6.40e-05
2022-05-27 19:15:45,717 INFO [train.py:761] (5/8) Epoch 1, batch 6600, loss[loss=1.063, simple_loss=0.8725, pruned_loss=0.6264, over 4901.00 frames.], tot_loss[loss=1.109, simple_loss=0.8985, pruned_loss=0.6593, over 965491.44 frames.], batch size: 17, lr: 6.45e-05
2022-05-27 19:16:23,526 INFO [train.py:761] (5/8) Epoch 1, batch 6650, loss[loss=1.063, simple_loss=0.8687, pruned_loss=0.6283, over 4676.00 frames.], tot_loss[loss=1.098, simple_loss=0.8926, pruned_loss=0.6513, over 965265.68 frames.], batch size: 13, lr: 6.50e-05
2022-05-27 19:17:01,912 INFO [train.py:761] (5/8) Epoch 1, batch 6700, loss[loss=0.9809, simple_loss=0.8245, pruned_loss=0.5686, over 4776.00 frames.], tot_loss[loss=1.09, simple_loss=0.8892, pruned_loss=0.6449, over 965628.42 frames.], batch size: 14, lr: 6.55e-05
2022-05-27 19:17:57,085 INFO [train.py:761] (5/8) Epoch 2, batch 0, loss[loss=1.105, simple_loss=0.9297, pruned_loss=0.6397, over 4769.00 frames.], tot_loss[loss=1.105, simple_loss=0.9297, pruned_loss=0.6397, over 4769.00 frames.], batch size: 20, lr: 6.59e-05
2022-05-27 19:18:35,333 INFO [train.py:761] (5/8) Epoch 2, batch 50, loss[loss=0.968, simple_loss=0.8337, pruned_loss=0.5511, over 4801.00 frames.], tot_loss[loss=1.033, simple_loss=0.8787, pruned_loss=0.5936, over 218837.02 frames.], batch size: 12, lr: 6.64e-05
2022-05-27 19:19:13,518 INFO [train.py:761] (5/8) Epoch 2, batch 100, loss[loss=0.9037, simple_loss=0.7872, pruned_loss=0.5101, over 4724.00 frames.], tot_loss[loss=1.031, simple_loss=0.8775, pruned_loss=0.592, over 385086.89 frames.], batch size: 11, lr: 6.69e-05
2022-05-27 19:19:51,473 INFO [train.py:761] (5/8) Epoch 2, batch 150, loss[loss=1.009, simple_loss=0.8877, pruned_loss=0.5649, over 4768.00 frames.], tot_loss[loss=1.022, simple_loss=0.8749, pruned_loss=0.5842, over 514053.42 frames.], batch size: 15, lr: 6.74e-05
2022-05-27 19:20:29,902 INFO [train.py:761] (5/8) Epoch 2, batch 200, loss[loss=0.8508, simple_loss=0.7434, pruned_loss=0.4791, over 4822.00 frames.], tot_loss[loss=1.011, simple_loss=0.8697, pruned_loss=0.5764, over 615038.06 frames.], batch size: 11, lr: 6.79e-05
2022-05-27 19:21:07,316 INFO [train.py:761] (5/8) Epoch 2, batch 250, loss[loss=1.01, simple_loss=0.8821, pruned_loss=0.5693, over 4777.00 frames.], tot_loss[loss=0.9986, simple_loss=0.8611, pruned_loss=0.568, over 693628.31 frames.], batch size: 15, lr: 6.84e-05
2022-05-27 19:21:45,764 INFO [train.py:761] (5/8) Epoch 2, batch 300, loss[loss=0.9751, simple_loss=0.8421, pruned_loss=0.5541, over 4734.00 frames.], tot_loss[loss=0.9895, simple_loss=0.8557, pruned_loss=0.5617, over 754179.35 frames.], batch size: 12, lr: 6.89e-05
2022-05-27 19:22:23,607 INFO [train.py:761] (5/8) Epoch 2, batch 350, loss[loss=0.9005, simple_loss=0.7846, pruned_loss=0.5082, over 4645.00 frames.], tot_loss[loss=0.9778, simple_loss=0.848, pruned_loss=0.5538, over 799983.95 frames.], batch size: 11, lr: 6.94e-05
2022-05-27 19:23:02,043 INFO [train.py:761] (5/8) Epoch 2, batch 400, loss[loss=0.9421, simple_loss=0.8367, pruned_loss=0.5238, over 4711.00 frames.], tot_loss[loss=0.9696, simple_loss=0.8431, pruned_loss=0.5481, over 836746.88 frames.], batch size: 14, lr: 6.98e-05
2022-05-27 19:23:39,517 INFO [train.py:761] (5/8) Epoch 2, batch 450, loss[loss=0.8343, simple_loss=0.747, pruned_loss=0.4607, over 4791.00 frames.], tot_loss[loss=0.9605, simple_loss=0.8373, pruned_loss=0.5418, over 864923.42 frames.], batch size: 13, lr: 7.03e-05
2022-05-27 19:24:17,297 INFO [train.py:761] (5/8) Epoch 2, batch 500, loss[loss=1.041, simple_loss=0.9275, pruned_loss=0.5772, over 4871.00 frames.], tot_loss[loss=0.9542, simple_loss=0.8351, pruned_loss=0.5367, over 886784.43 frames.], batch size: 17, lr: 7.08e-05
2022-05-27 19:24:55,238 INFO [train.py:761] (5/8) Epoch 2, batch 550, loss[loss=1.103, simple_loss=0.9677, pruned_loss=0.6196, over 4787.00 frames.], tot_loss[loss=0.9554, simple_loss=0.8371, pruned_loss=0.5368, over 904391.23 frames.], batch size: 15, lr: 7.13e-05
2022-05-27 19:25:33,379 INFO [train.py:761] (5/8) Epoch 2, batch 600, loss[loss=0.8862, simple_loss=0.7517, pruned_loss=0.5104, over 4742.00 frames.], tot_loss[loss=0.9427, simple_loss=0.8296, pruned_loss=0.5279, over 918045.29 frames.], batch size: 11, lr: 7.18e-05
2022-05-27 19:26:11,242 INFO [train.py:761] (5/8) Epoch 2, batch 650, loss[loss=1.022, simple_loss=0.8857, pruned_loss=0.5788, over 4938.00 frames.], tot_loss[loss=0.9392, simple_loss=0.8286, pruned_loss=0.5249, over 929066.25 frames.], batch size: 16, lr: 7.23e-05
2022-05-27 19:26:49,465 INFO [train.py:761] (5/8) Epoch 2, batch 700, loss[loss=0.8778, simple_loss=0.8007, pruned_loss=0.4775, over 4946.00 frames.], tot_loss[loss=0.9331, simple_loss=0.8242, pruned_loss=0.521, over 938112.10 frames.], batch size: 16, lr: 7.28e-05
2022-05-27 19:27:27,411 INFO [train.py:761] (5/8) Epoch 2, batch 750, loss[loss=0.8527, simple_loss=0.7892, pruned_loss=0.4581, over 4916.00 frames.], tot_loss[loss=0.9225, simple_loss=0.8177, pruned_loss=0.5136, over 944515.72 frames.], batch size: 14, lr: 7.33e-05
2022-05-27 19:28:05,189 INFO [train.py:761] (5/8) Epoch 2, batch 800, loss[loss=0.8473, simple_loss=0.7479, pruned_loss=0.4734, over 4723.00 frames.], tot_loss[loss=0.9143, simple_loss=0.8119, pruned_loss=0.5083, over 947657.71 frames.], batch size: 12, lr: 7.38e-05
2022-05-27 19:28:43,215 INFO [train.py:761] (5/8) Epoch 2, batch 850, loss[loss=0.8251, simple_loss=0.7605, pruned_loss=0.4449, over 4664.00 frames.], tot_loss[loss=0.9046, simple_loss=0.8057, pruned_loss=0.5018, over 950747.62 frames.], batch size: 12, lr: 7.42e-05
2022-05-27 19:29:21,340 INFO [train.py:761] (5/8) Epoch 2, batch 900, loss[loss=0.9546, simple_loss=0.8574, pruned_loss=0.5259, over 4786.00 frames.], tot_loss[loss=0.9007, simple_loss=0.8041, pruned_loss=0.4987, over 953000.58 frames.], batch size: 13, lr: 7.47e-05
2022-05-27 19:29:59,007 INFO [train.py:761] (5/8) Epoch 2, batch 950, loss[loss=1.049, simple_loss=0.9068, pruned_loss=0.5956, over 4824.00 frames.], tot_loss[loss=0.8935, simple_loss=0.7994, pruned_loss=0.4938, over 956276.45 frames.], batch size: 16, lr: 7.52e-05
2022-05-27 19:30:36,916 INFO [train.py:761] (5/8) Epoch 2, batch 1000, loss[loss=0.7947, simple_loss=0.7287, pruned_loss=0.4304, over 4744.00 frames.], tot_loss[loss=0.8907, simple_loss=0.7987, pruned_loss=0.4914, over 958571.70 frames.], batch size: 11, lr: 7.57e-05
2022-05-27 19:31:14,874 INFO [train.py:761] (5/8) Epoch 2, batch 1050, loss[loss=0.897, simple_loss=0.8151, pruned_loss=0.4895, over 4779.00 frames.], tot_loss[loss=0.8845, simple_loss=0.7952, pruned_loss=0.4869, over 960157.39 frames.], batch size: 13, lr: 7.62e-05
2022-05-27 19:31:52,530 INFO [train.py:761] (5/8) Epoch 2, batch 1100, loss[loss=0.9172, simple_loss=0.8227, pruned_loss=0.5058, over 4783.00 frames.], tot_loss[loss=0.8748, simple_loss=0.7885, pruned_loss=0.4805, over 961839.10 frames.], batch size: 13, lr: 7.67e-05
2022-05-27 19:32:30,211 INFO [train.py:761] (5/8) Epoch 2, batch 1150, loss[loss=0.8865, simple_loss=0.8142, pruned_loss=0.4794, over 4711.00 frames.], tot_loss[loss=0.8713, simple_loss=0.7873, pruned_loss=0.4777, over 962494.84 frames.], batch size: 14, lr: 7.72e-05
2022-05-27 19:33:08,104 INFO [train.py:761] (5/8) Epoch 2, batch 1200, loss[loss=0.9389, simple_loss=0.8637, pruned_loss=0.507, over 4884.00 frames.], tot_loss[loss=0.8689, simple_loss=0.7862, pruned_loss=0.4758, over 963860.60 frames.], batch size: 15, lr: 7.77e-05
2022-05-27 19:33:45,525 INFO [train.py:761] (5/8) Epoch 2, batch 1250, loss[loss=0.7351, simple_loss=0.6747, pruned_loss=0.3978, over 4840.00 frames.], tot_loss[loss=0.8604, simple_loss=0.7807, pruned_loss=0.47, over 964977.12 frames.], batch size: 11, lr: 7.81e-05
2022-05-27 19:34:26,573 INFO [train.py:761] (5/8) Epoch 2, batch 1300, loss[loss=0.8009, simple_loss=0.7498, pruned_loss=0.426, over 4975.00 frames.], tot_loss[loss=0.8537, simple_loss=0.7767, pruned_loss=0.4653, over 964571.16 frames.], batch size: 14, lr: 7.86e-05
2022-05-27 19:35:04,358 INFO [train.py:761] (5/8) Epoch 2, batch 1350, loss[loss=0.8866, simple_loss=0.7916, pruned_loss=0.4908, over 4667.00 frames.], tot_loss[loss=0.8467, simple_loss=0.7718, pruned_loss=0.4608, over 966155.72 frames.], batch size: 13, lr: 7.91e-05
2022-05-27 19:35:42,518 INFO [train.py:761] (5/8) Epoch 2, batch 1400, loss[loss=0.9476, simple_loss=0.8341, pruned_loss=0.5306, over 4812.00 frames.], tot_loss[loss=0.8415, simple_loss=0.7693, pruned_loss=0.4569, over 966384.69 frames.], batch size: 16, lr: 7.96e-05
2022-05-27 19:36:20,341 INFO [train.py:761] (5/8) Epoch 2, batch 1450, loss[loss=0.8266, simple_loss=0.7336, pruned_loss=0.4598, over 4650.00 frames.], tot_loss[loss=0.8345, simple_loss=0.7648, pruned_loss=0.4521, over 965337.58 frames.], batch size: 11, lr: 8.01e-05
2022-05-27 19:36:58,355 INFO [train.py:761] (5/8) Epoch 2, batch 1500, loss[loss=0.7916, simple_loss=0.7178, pruned_loss=0.4326, over 4640.00 frames.], tot_loss[loss=0.8283, simple_loss=0.7608, pruned_loss=0.4479, over 965095.19 frames.], batch size: 11, lr: 8.06e-05
2022-05-27 19:37:36,304 INFO [train.py:761] (5/8) Epoch 2, batch 1550, loss[loss=0.7912, simple_loss=0.7431, pruned_loss=0.4197, over 4893.00 frames.], tot_loss[loss=0.8225, simple_loss=0.7565, pruned_loss=0.4442, over 965821.53 frames.], batch size: 15, lr: 8.11e-05
2022-05-27 19:38:13,989 INFO [train.py:761] (5/8) Epoch 2, batch 1600, loss[loss=0.6854, simple_loss=0.6618, pruned_loss=0.3545, over 4978.00 frames.], tot_loss[loss=0.8138, simple_loss=0.7507, pruned_loss=0.4385, over 965674.34 frames.], batch size: 13, lr: 8.16e-05
2022-05-27 19:38:52,138 INFO [train.py:761] (5/8) Epoch 2, batch 1650, loss[loss=0.7716, simple_loss=0.6986, pruned_loss=0.4223, over 4976.00 frames.], tot_loss[loss=0.8076, simple_loss=0.7465, pruned_loss=0.4344, over 966875.71 frames.], batch size: 12, lr: 8.21e-05
2022-05-27 19:39:30,209 INFO [train.py:761] (5/8) Epoch 2, batch 1700, loss[loss=0.7578, simple_loss=0.7127, pruned_loss=0.4014, over 4610.00 frames.], tot_loss[loss=0.8033, simple_loss=0.7438, pruned_loss=0.4314, over 967157.38 frames.], batch size: 10, lr: 8.25e-05
2022-05-27 19:40:07,814 INFO [train.py:761] (5/8) Epoch 2, batch 1750, loss[loss=0.8355, simple_loss=0.7554, pruned_loss=0.4578, over 4669.00 frames.], tot_loss[loss=0.8037, simple_loss=0.7456, pruned_loss=0.4309, over 967126.87 frames.], batch size: 12, lr: 8.30e-05
2022-05-27 19:40:45,870 INFO [train.py:761] (5/8) Epoch 2, batch 1800, loss[loss=0.6203, simple_loss=0.6073, pruned_loss=0.3167, over 4916.00 frames.], tot_loss[loss=0.7937, simple_loss=0.7392, pruned_loss=0.4241, over 966691.55 frames.], batch size: 13, lr: 8.35e-05
2022-05-27 19:41:23,413 INFO [train.py:761] (5/8) Epoch 2, batch 1850, loss[loss=0.799, simple_loss=0.7557, pruned_loss=0.4211, over 4837.00 frames.], tot_loss[loss=0.7864, simple_loss=0.7338, pruned_loss=0.4195, over 967075.65 frames.], batch size: 18, lr: 8.40e-05
2022-05-27 19:42:01,480 INFO [train.py:761] (5/8) Epoch 2, batch 1900, loss[loss=0.6481, simple_loss=0.6483, pruned_loss=0.3239, over 4639.00 frames.], tot_loss[loss=0.7857, simple_loss=0.7343, pruned_loss=0.4185, over 966760.08 frames.], batch size: 11, lr: 8.45e-05
2022-05-27 19:42:39,100 INFO [train.py:761] (5/8) Epoch 2, batch 1950, loss[loss=0.8196, simple_loss=0.7571, pruned_loss=0.4411, over 4783.00 frames.], tot_loss[loss=0.7815, simple_loss=0.7317, pruned_loss=0.4156, over 966399.25 frames.], batch size: 14, lr: 8.50e-05
2022-05-27 19:43:17,086 INFO [train.py:761] (5/8) Epoch 2, batch 2000, loss[loss=0.6991, simple_loss=0.6586, pruned_loss=0.3698, over 4723.00 frames.], tot_loss[loss=0.777, simple_loss=0.7288, pruned_loss=0.4126, over 965853.48 frames.], batch size: 13, lr: 8.55e-05
2022-05-27 19:43:55,179 INFO [train.py:761] (5/8) Epoch 2, batch 2050, loss[loss=0.8096, simple_loss=0.7714, pruned_loss=0.4239, over 4940.00 frames.], tot_loss[loss=0.7727, simple_loss=0.7263, pruned_loss=0.4095, over 965426.88 frames.], batch size: 20, lr: 8.60e-05
2022-05-27 19:44:33,543 INFO [train.py:761] (5/8) Epoch 2, batch 2100, loss[loss=0.8017, simple_loss=0.7611, pruned_loss=0.4212, over 4844.00 frames.], tot_loss[loss=0.7702, simple_loss=0.7248, pruned_loss=0.4078, over 965527.36 frames.], batch size: 26, lr: 8.64e-05
2022-05-27 19:45:11,267 INFO [train.py:761] (5/8) Epoch 2, batch 2150, loss[loss=0.814, simple_loss=0.7674, pruned_loss=0.4303, over 4781.00 frames.], tot_loss[loss=0.7668, simple_loss=0.7235, pruned_loss=0.405, over 966121.71 frames.], batch size: 15, lr: 8.69e-05
2022-05-27 19:45:49,703 INFO [train.py:761] (5/8) Epoch 2, batch 2200, loss[loss=0.6589, simple_loss=0.6436, pruned_loss=0.3371, over 4805.00 frames.], tot_loss[loss=0.7614, simple_loss=0.7195, pruned_loss=0.4017, over 964672.29 frames.], batch size: 12, lr: 8.74e-05
2022-05-27 19:46:27,409 INFO [train.py:761] (5/8) Epoch 2, batch 2250, loss[loss=0.7883, simple_loss=0.7482, pruned_loss=0.4141, over 4831.00 frames.], tot_loss[loss=0.755, simple_loss=0.7153, pruned_loss=0.3973, over 965514.15 frames.], batch size: 20, lr: 8.79e-05
2022-05-27 19:47:06,293 INFO [train.py:761] (5/8) Epoch 2, batch 2300, loss[loss=0.7058, simple_loss=0.681, pruned_loss=0.3653, over 4986.00 frames.], tot_loss[loss=0.7489, simple_loss=0.7108, pruned_loss=0.3935, over 965267.12 frames.], batch size: 13, lr: 8.84e-05
2022-05-27 19:47:44,040 INFO [train.py:761] (5/8) Epoch 2, batch 2350, loss[loss=0.6353, simple_loss=0.604, pruned_loss=0.3333, over 4969.00 frames.], tot_loss[loss=0.7452, simple_loss=0.7084, pruned_loss=0.391, over 966246.01 frames.], batch size: 12, lr: 8.89e-05
2022-05-27 19:48:22,236 INFO [train.py:761] (5/8) Epoch 2, batch 2400, loss[loss=0.7721, simple_loss=0.7255, pruned_loss=0.4094, over 4850.00 frames.], tot_loss[loss=0.7441, simple_loss=0.7083, pruned_loss=0.3899, over 966053.93 frames.], batch size: 14, lr: 8.94e-05
2022-05-27 19:48:59,830 INFO [train.py:761] (5/8) Epoch 2, batch 2450, loss[loss=0.6519, simple_loss=0.6541, pruned_loss=0.3248, over 4644.00 frames.], tot_loss[loss=0.7407, simple_loss=0.7059, pruned_loss=0.3878, over 966189.92 frames.], batch size: 11, lr: 8.99e-05
2022-05-27 19:49:37,934 INFO [train.py:761] (5/8) Epoch 2, batch 2500, loss[loss=0.7742, simple_loss=0.7457, pruned_loss=0.4014, over 4831.00 frames.], tot_loss[loss=0.7336, simple_loss=0.7009, pruned_loss=0.3832, over 966017.02 frames.], batch size: 18, lr: 9.04e-05
2022-05-27 19:50:15,471 INFO [train.py:761] (5/8) Epoch 2, batch 2550, loss[loss=0.7064, simple_loss=0.6913, pruned_loss=0.3608, over 4670.00 frames.], tot_loss[loss=0.7292, simple_loss=0.6977, pruned_loss=0.3804, over 966626.67 frames.], batch size: 13, lr: 9.08e-05
2022-05-27 19:50:53,794 INFO [train.py:761] (5/8) Epoch 2, batch 2600, loss[loss=0.7091, simple_loss=0.7082, pruned_loss=0.355, over 4982.00 frames.], tot_loss[loss=0.7213, simple_loss=0.6922, pruned_loss=0.3752, over 965818.50 frames.], batch size: 21, lr: 9.13e-05
2022-05-27 19:51:30,987 INFO [train.py:761] (5/8) Epoch 2, batch 2650, loss[loss=0.7279, simple_loss=0.7012, pruned_loss=0.3772, over 4862.00 frames.], tot_loss[loss=0.7183, simple_loss=0.691, pruned_loss=0.3728, over 965234.58 frames.], batch size: 13, lr: 9.18e-05
2022-05-27 19:52:09,147 INFO [train.py:761] (5/8) Epoch 2, batch 2700, loss[loss=0.6585, simple_loss=0.6201, pruned_loss=0.3485, over 4968.00 frames.], tot_loss[loss=0.7122, simple_loss=0.6872, pruned_loss=0.3686, over 964883.57 frames.], batch size: 12, lr: 9.23e-05
2022-05-27 19:52:47,311 INFO [train.py:761] (5/8) Epoch 2, batch 2750, loss[loss=0.8109, simple_loss=0.7606, pruned_loss=0.4306, over 4785.00 frames.], tot_loss[loss=0.7093, simple_loss=0.6848, pruned_loss=0.3669, over 965990.90 frames.], batch size: 14, lr: 9.28e-05
2022-05-27 19:53:25,354 INFO [train.py:761] (5/8) Epoch 2, batch 2800, loss[loss=0.6936, simple_loss=0.6718, pruned_loss=0.3577, over 4838.00 frames.], tot_loss[loss=0.7084, simple_loss=0.6844, pruned_loss=0.3662, over 967172.18 frames.], batch size: 26, lr: 9.33e-05
2022-05-27 19:54:03,500 INFO [train.py:761] (5/8) Epoch 2, batch 2850, loss[loss=0.596, simple_loss=0.5932, pruned_loss=0.2994, over 4835.00 frames.], tot_loss[loss=0.7013, simple_loss=0.679, pruned_loss=0.3618, over 966552.50 frames.], batch size: 11, lr: 9.38e-05
2022-05-27 19:54:41,311 INFO [train.py:761] (5/8) Epoch 2, batch 2900, loss[loss=0.6901, simple_loss=0.715, pruned_loss=0.3326, over 4758.00 frames.], tot_loss[loss=0.6972, simple_loss=0.6772, pruned_loss=0.3586, over 966178.88 frames.], batch size: 15, lr: 9.43e-05
2022-05-27 19:55:19,571 INFO [train.py:761] (5/8) Epoch 2, batch 2950, loss[loss=0.8389, simple_loss=0.7701, pruned_loss=0.4539, over 4768.00 frames.], tot_loss[loss=0.6961, simple_loss=0.6757, pruned_loss=0.3582, over 965942.31 frames.], batch size: 15, lr: 9.47e-05
2022-05-27 19:55:57,295 INFO [train.py:761] (5/8) Epoch 2, batch 3000, loss[loss=0.7009, simple_loss=0.7026, pruned_loss=0.3496, over 4862.00 frames.], tot_loss[loss=0.6956, simple_loss=0.6758, pruned_loss=0.3577, over 965467.86 frames.], batch size: 14, lr: 9.52e-05
2022-05-27 19:55:57,295 INFO [train.py:781] (5/8) Computing validation loss
2022-05-27 19:56:07,075 INFO [train.py:790] (5/8) Epoch 2, validation: loss=0.5819, simple_loss=0.6203, pruned_loss=0.2718, over 944034.00 frames.
2022-05-27 19:56:45,085 INFO [train.py:761] (5/8) Epoch 2, batch 3050, loss[loss=0.7342, simple_loss=0.7196, pruned_loss=0.3744, over 4932.00 frames.], tot_loss[loss=0.695, simple_loss=0.6752, pruned_loss=0.3574, over 966173.34 frames.], batch size: 26, lr: 9.57e-05
2022-05-27 19:57:22,611 INFO [train.py:761] (5/8) Epoch 2, batch 3100, loss[loss=0.617, simple_loss=0.5756, pruned_loss=0.3292, over 4891.00 frames.], tot_loss[loss=0.6935, simple_loss=0.6728, pruned_loss=0.3571, over 966233.03 frames.], batch size: 12, lr: 9.62e-05
2022-05-27 19:58:00,517 INFO [train.py:761] (5/8) Epoch 2, batch 3150, loss[loss=0.5966, simple_loss=0.6008, pruned_loss=0.2962, over 4978.00 frames.], tot_loss[loss=0.6912, simple_loss=0.6706, pruned_loss=0.3559, over 966629.68 frames.], batch size: 12, lr: 9.67e-05
2022-05-27 19:58:38,627 INFO [train.py:761] (5/8) Epoch 2, batch 3200, loss[loss=0.5619, simple_loss=0.5574, pruned_loss=0.2832, over 4970.00 frames.], tot_loss[loss=0.6896, simple_loss=0.6673, pruned_loss=0.356, over 966401.50 frames.], batch size: 12, lr: 9.72e-05
2022-05-27 19:59:16,746 INFO [train.py:761] (5/8) Epoch 2, batch 3250, loss[loss=0.6852, simple_loss=0.6515, pruned_loss=0.3595, over 4838.00 frames.], tot_loss[loss=0.6885, simple_loss=0.664, pruned_loss=0.3565, over 966703.82 frames.], batch size: 11, lr: 9.77e-05
2022-05-27 19:59:55,110 INFO [train.py:761] (5/8) Epoch 2, batch 3300, loss[loss=0.6466, simple_loss=0.6158, pruned_loss=0.3387, over 4982.00 frames.], tot_loss[loss=0.6933, simple_loss=0.6646, pruned_loss=0.361, over 967216.28 frames.], batch size: 13, lr: 9.82e-05
2022-05-27 20:00:32,753 INFO [train.py:761] (5/8) Epoch 2, batch 3350, loss[loss=0.7397, simple_loss=0.6636, pruned_loss=0.4079, over 4931.00 frames.], tot_loss[loss=0.6971, simple_loss=0.6651, pruned_loss=0.3646, over 966074.45 frames.], batch size: 13, lr: 9.87e-05
2022-05-27 20:01:10,635 INFO [train.py:761] (5/8) Epoch 2, batch 3400, loss[loss=0.6426, simple_loss=0.6334, pruned_loss=0.3259, over 4777.00 frames.], tot_loss[loss=0.7034, simple_loss=0.6682, pruned_loss=0.3694, over 965616.64 frames.], batch size: 13, lr: 9.91e-05
2022-05-27 20:01:48,328 INFO [train.py:761] (5/8) Epoch 2, batch 3450, loss[loss=0.7961, simple_loss=0.7405, pruned_loss=0.4259, over 4856.00 frames.], tot_loss[loss=0.707, simple_loss=0.6692, pruned_loss=0.3725, over 964771.71 frames.], batch size: 13, lr: 9.96e-05
2022-05-27 20:02:26,834 INFO [train.py:761] (5/8) Epoch 2, batch 3500, loss[loss=0.6882, simple_loss=0.6462, pruned_loss=0.3651, over 4792.00 frames.], tot_loss[loss=0.7084, simple_loss=0.6685, pruned_loss=0.3741, over 964550.90 frames.], batch size: 14, lr: 1.00e-04
2022-05-27 20:03:04,930 INFO [train.py:761] (5/8) Epoch 2, batch 3550, loss[loss=0.6778, simple_loss=0.652, pruned_loss=0.3519, over 4962.00 frames.], tot_loss[loss=0.7088, simple_loss=0.6684, pruned_loss=0.3746, over 965297.43 frames.], batch size: 16, lr: 1.01e-04
2022-05-27 20:03:42,882 INFO [train.py:761] (5/8) Epoch 2, batch 3600, loss[loss=0.6863, simple_loss=0.6592, pruned_loss=0.3567, over 4992.00 frames.], tot_loss[loss=0.7122, simple_loss=0.6695, pruned_loss=0.3775, over 966300.26 frames.], batch size: 13, lr: 1.01e-04
2022-05-27 20:04:20,622 INFO [train.py:761] (5/8) Epoch 2, batch 3650, loss[loss=0.7598, simple_loss=0.69, pruned_loss=0.4148, over 4994.00 frames.], tot_loss[loss=0.7123, simple_loss=0.6685, pruned_loss=0.3781, over 966857.15 frames.], batch size: 13, lr: 1.02e-04
2022-05-27 20:04:58,732 INFO [train.py:761] (5/8) Epoch 2, batch 3700, loss[loss=0.6582, simple_loss=0.6117, pruned_loss=0.3524, over 4832.00 frames.], tot_loss[loss=0.7099, simple_loss=0.6668, pruned_loss=0.3765, over 966279.47 frames.], batch size: 11, lr: 1.02e-04
2022-05-27 20:05:36,782 INFO [train.py:761] (5/8) Epoch 2, batch 3750, loss[loss=0.7901, simple_loss=0.7115, pruned_loss=0.4343, over 4848.00 frames.], tot_loss[loss=0.7097, simple_loss=0.6654, pruned_loss=0.377, over 966810.86 frames.], batch size: 14, lr: 1.03e-04
2022-05-27 20:06:15,004 INFO [train.py:761] (5/8) Epoch 2, batch 3800, loss[loss=0.6759, simple_loss=0.6557, pruned_loss=0.348, over 4913.00 frames.], tot_loss[loss=0.7062, simple_loss=0.6621, pruned_loss=0.3751, over 966433.88 frames.], batch size: 14, lr: 1.03e-04
2022-05-27 20:06:52,723 INFO [train.py:761] (5/8) Epoch 2, batch 3850, loss[loss=0.717, simple_loss=0.6749, pruned_loss=0.3795, over 4873.00 frames.], tot_loss[loss=0.7003, simple_loss=0.6579, pruned_loss=0.3714, over 965664.87 frames.], batch size: 15, lr: 1.04e-04
2022-05-27 20:07:30,594 INFO [train.py:761] (5/8) Epoch 2, batch 3900, loss[loss=0.6434, simple_loss=0.611, pruned_loss=0.3379, over 4735.00 frames.], tot_loss[loss=0.6999, simple_loss=0.6579, pruned_loss=0.3709, over 966615.31 frames.], batch size: 12, lr: 1.04e-04
2022-05-27 20:08:08,588 INFO [train.py:761] (5/8) Epoch 2, batch 3950, loss[loss=0.5735, simple_loss=0.5856, pruned_loss=0.2806, over 4747.00 frames.], tot_loss[loss=0.6992, simple_loss=0.6575, pruned_loss=0.3705, over 966877.85 frames.], batch size: 12, lr: 1.05e-04
2022-05-27 20:08:46,839 INFO [train.py:761] (5/8) Epoch 2, batch 4000, loss[loss=0.8191, simple_loss=0.7227, pruned_loss=0.4577, over 4975.00 frames.], tot_loss[loss=0.6967, simple_loss=0.6564, pruned_loss=0.3684, over 967674.49 frames.], batch size: 56, lr: 1.05e-04
2022-05-27 20:09:25,072 INFO [train.py:761] (5/8) Epoch 2, batch 4050, loss[loss=0.674, simple_loss=0.6293, pruned_loss=0.3594, over 4867.00 frames.], tot_loss[loss=0.6921, simple_loss=0.6534, pruned_loss=0.3654, over 967377.47 frames.], batch size: 17, lr: 1.05e-04
2022-05-27 20:10:03,164 INFO [train.py:761] (5/8) Epoch 2, batch 4100, loss[loss=0.5497, simple_loss=0.5472, pruned_loss=0.2761, over 4924.00 frames.], tot_loss[loss=0.6889, simple_loss=0.6513, pruned_loss=0.3632, over 967360.51 frames.], batch size: 14, lr: 1.06e-04
2022-05-27 20:10:41,639 INFO [train.py:761] (5/8) Epoch 2, batch 4150, loss[loss=0.7151, simple_loss=0.6861, pruned_loss=0.3721, over 4793.00 frames.], tot_loss[loss=0.6861, simple_loss=0.6484, pruned_loss=0.3619, over 967092.60 frames.], batch size: 14, lr: 1.06e-04
2022-05-27 20:11:19,495 INFO [train.py:761] (5/8) Epoch 2, batch 4200, loss[loss=0.6451, simple_loss=0.6153, pruned_loss=0.3375, over 4637.00 frames.], tot_loss[loss=0.6837, simple_loss=0.6463, pruned_loss=0.3605, over 966772.79 frames.], batch size: 11, lr: 1.07e-04
2022-05-27 20:11:57,359 INFO [train.py:761] (5/8) Epoch 2, batch 4250, loss[loss=0.6197, simple_loss=0.5908, pruned_loss=0.3243, over 4983.00 frames.], tot_loss[loss=0.685, simple_loss=0.6478, pruned_loss=0.3611, over 967179.74 frames.], batch size: 13, lr: 1.07e-04
2022-05-27 20:12:35,995 INFO [train.py:761] (5/8) Epoch 2, batch 4300, loss[loss=0.7008, simple_loss=0.6503, pruned_loss=0.3756, over 4853.00 frames.], tot_loss[loss=0.68, simple_loss=0.6448, pruned_loss=0.3576, over 967621.18 frames.], batch size: 13, lr: 1.08e-04
2022-05-27 20:13:14,330 INFO [train.py:761] (5/8) Epoch 2, batch 4350, loss[loss=0.6681, simple_loss=0.6474, pruned_loss=0.3445, over 4884.00 frames.], tot_loss[loss=0.6787, simple_loss=0.6438, pruned_loss=0.3568, over 967856.18 frames.], batch size: 15, lr: 1.08e-04
2022-05-27 20:13:52,611 INFO [train.py:761] (5/8) Epoch 2, batch 4400, loss[loss=0.7745, simple_loss=0.7055, pruned_loss=0.4217, over 4730.00 frames.], tot_loss[loss=0.6799, simple_loss=0.6444, pruned_loss=0.3577, over 967433.87 frames.], batch size: 13, lr: 1.09e-04
2022-05-27 20:14:31,162 INFO [train.py:761] (5/8) Epoch 2, batch 4450, loss[loss=0.8289, simple_loss=0.7392, pruned_loss=0.4593, over 4951.00 frames.], tot_loss[loss=0.6783, simple_loss=0.6436, pruned_loss=0.3566, over 967600.36 frames.], batch size: 16, lr: 1.09e-04
2022-05-27 20:15:09,489 INFO [train.py:761] (5/8) Epoch 2, batch 4500, loss[loss=0.51, simple_loss=0.5055, pruned_loss=0.2573, over 4732.00 frames.], tot_loss[loss=0.6776, simple_loss=0.6429, pruned_loss=0.3562, over 967671.91 frames.], batch size: 11, lr: 1.10e-04
2022-05-27 20:15:47,269 INFO [train.py:761] (5/8) Epoch 2, batch 4550, loss[loss=0.5495, simple_loss=0.5623, pruned_loss=0.2684, over 4780.00 frames.], tot_loss[loss=0.673, simple_loss=0.6397, pruned_loss=0.3531, over 968496.98 frames.], batch size: 13, lr: 1.10e-04
2022-05-27 20:16:25,834 INFO [train.py:761] (5/8) Epoch 2, batch 4600, loss[loss=0.686, simple_loss=0.6639, pruned_loss=0.3541, over 4767.00 frames.], tot_loss[loss=0.6721, simple_loss=0.6391, pruned_loss=0.3525, over 967576.62 frames.], batch size: 20, lr: 1.11e-04
2022-05-27 20:17:04,046 INFO [train.py:761] (5/8) Epoch 2, batch 4650, loss[loss=0.6238, simple_loss=0.6239, pruned_loss=0.3119, over 4736.00 frames.], tot_loss[loss=0.6676, simple_loss=0.6362, pruned_loss=0.3495, over 967111.09 frames.], batch size: 12, lr: 1.11e-04
2022-05-27 20:17:42,447 INFO [train.py:761] (5/8) Epoch 2, batch 4700, loss[loss=0.6538, simple_loss=0.6273, pruned_loss=0.3401, over 4789.00 frames.], tot_loss[loss=0.6667, simple_loss=0.6355, pruned_loss=0.349, over 966842.19 frames.], batch size: 20, lr: 1.12e-04
2022-05-27 20:18:20,288 INFO [train.py:761] (5/8) Epoch 2, batch 4750, loss[loss=0.6229, simple_loss=0.6255, pruned_loss=0.3102, over 4887.00 frames.], tot_loss[loss=0.6622, simple_loss=0.633, pruned_loss=0.3457, over 967073.52 frames.], batch size: 15, lr: 1.12e-04
2022-05-27 20:18:58,814 INFO [train.py:761] (5/8) Epoch 2, batch 4800, loss[loss=0.5724, simple_loss=0.5672, pruned_loss=0.2888, over 4874.00 frames.], tot_loss[loss=0.6586, simple_loss=0.6301, pruned_loss=0.3436, over 966927.48 frames.], batch size: 12, lr: 1.13e-04
2022-05-27 20:19:36,443 INFO [train.py:761] (5/8) Epoch 2, batch 4850, loss[loss=0.4952, simple_loss=0.5325, pruned_loss=0.2289, over 4737.00 frames.], tot_loss[loss=0.6517, simple_loss=0.6255, pruned_loss=0.3389, over 966042.44 frames.], batch size: 11, lr: 1.13e-04
2022-05-27 20:20:14,974 INFO [train.py:761] (5/8) Epoch 2, batch 4900, loss[loss=0.5751, simple_loss=0.5694, pruned_loss=0.2904, over 4743.00 frames.], tot_loss[loss=0.6492, simple_loss=0.6242, pruned_loss=0.3371, over 966895.11 frames.], batch size: 11, lr: 1.14e-04
2022-05-27 20:20:53,248 INFO [train.py:761] (5/8) Epoch 2, batch 4950, loss[loss=0.5019, simple_loss=0.5017, pruned_loss=0.251, over 4648.00 frames.], tot_loss[loss=0.6474, simple_loss=0.623, pruned_loss=0.3359, over 964916.80 frames.], batch size: 11, lr: 1.14e-04
2022-05-27 20:21:31,824 INFO [train.py:761] (5/8) Epoch 2, batch 5000, loss[loss=0.6571, simple_loss=0.6044, pruned_loss=0.3549, over 4730.00 frames.], tot_loss[loss=0.6515, simple_loss=0.6258, pruned_loss=0.3386, over 965759.84 frames.], batch size: 13, lr: 1.15e-04
2022-05-27 20:22:10,131 INFO [train.py:761] (5/8) Epoch 2, batch 5050, loss[loss=0.7467, simple_loss=0.6667, pruned_loss=0.4134, over 4805.00 frames.], tot_loss[loss=0.6526, simple_loss=0.6269, pruned_loss=0.3391, over 966110.50 frames.], batch size: 12, lr: 1.15e-04
2022-05-27 20:22:48,785 INFO [train.py:761] (5/8) Epoch 2, batch 5100, loss[loss=0.6711, simple_loss=0.6177, pruned_loss=0.3623, over 4884.00 frames.], tot_loss[loss=0.6458, simple_loss=0.6208, pruned_loss=0.3353, over 966512.75 frames.], batch size: 12, lr: 1.16e-04
2022-05-27 20:23:26,707 INFO [train.py:761] (5/8) Epoch 2, batch 5150, loss[loss=0.6963, simple_loss=0.6884, pruned_loss=0.3521, over 4714.00 frames.], tot_loss[loss=0.6413, simple_loss=0.6178, pruned_loss=0.3324, over 967051.96 frames.], batch size: 14, lr: 1.16e-04
2022-05-27 20:24:05,829 INFO [train.py:761] (5/8) Epoch 2, batch 5200, loss[loss=0.6304, simple_loss=0.5946, pruned_loss=0.3331, over 4913.00 frames.], tot_loss[loss=0.642, simple_loss=0.6185, pruned_loss=0.3327, over 968307.69 frames.], batch size: 13, lr: 1.17e-04
2022-05-27 20:24:43,403 INFO [train.py:761] (5/8) Epoch 2, batch 5250, loss[loss=0.6708, simple_loss=0.6561, pruned_loss=0.3428, over 4830.00 frames.], tot_loss[loss=0.6414, simple_loss=0.6184, pruned_loss=0.3322, over 967514.28 frames.], batch size: 25, lr: 1.17e-04
2022-05-27 20:25:22,051 INFO [train.py:761] (5/8) Epoch 2, batch 5300, loss[loss=0.5353, simple_loss=0.5611, pruned_loss=0.2548, over 4724.00 frames.], tot_loss[loss=0.6349, simple_loss=0.6135, pruned_loss=0.3281, over 966958.13 frames.], batch size: 12, lr: 1.18e-04
2022-05-27 20:26:00,220 INFO [train.py:761] (5/8) Epoch 2, batch 5350, loss[loss=0.4864, simple_loss=0.5023, pruned_loss=0.2353, over 4724.00 frames.], tot_loss[loss=0.6282, simple_loss=0.609, pruned_loss=0.3237, over 967400.79 frames.], batch size: 11, lr: 1.18e-04
2022-05-27 20:26:38,877 INFO [train.py:761] (5/8) Epoch 2, batch 5400, loss[loss=0.6614, simple_loss=0.6351, pruned_loss=0.3438, over 4908.00 frames.], tot_loss[loss=0.6262, simple_loss=0.6086, pruned_loss=0.3219, over 967997.52 frames.], batch size: 14, lr: 1.19e-04
2022-05-27 20:27:17,258 INFO [train.py:761] (5/8) Epoch 2, batch 5450, loss[loss=0.562, simple_loss=0.5539, pruned_loss=0.2851, over 4979.00 frames.], tot_loss[loss=0.6273, simple_loss=0.6102, pruned_loss=0.3222, over 967992.52 frames.], batch size: 12, lr: 1.19e-04
2022-05-27 20:27:55,472 INFO [train.py:761] (5/8) Epoch 2, batch 5500, loss[loss=0.5943, simple_loss=0.5803, pruned_loss=0.3042, over 4721.00 frames.], tot_loss[loss=0.6263, simple_loss=0.6093, pruned_loss=0.3217, over 967667.64 frames.], batch size: 13, lr: 1.20e-04
2022-05-27 20:28:33,527 INFO [train.py:761] (5/8) Epoch 2, batch 5550, loss[loss=0.5924, simple_loss=0.59, pruned_loss=0.2974, over 4854.00 frames.], tot_loss[loss=0.6182, simple_loss=0.6033, pruned_loss=0.3166, over 967408.30 frames.], batch size: 13, lr: 1.20e-04
2022-05-27 20:29:11,818 INFO [train.py:761] (5/8) Epoch 2, batch 5600, loss[loss=0.5151, simple_loss=0.512, pruned_loss=0.2591, over 4652.00 frames.], tot_loss[loss=0.6215, simple_loss=0.605, pruned_loss=0.319, over 967126.65 frames.], batch size: 11, lr: 1.21e-04
2022-05-27 20:29:50,321 INFO [train.py:761] (5/8) Epoch 2, batch 5650, loss[loss=0.6303, simple_loss=0.6223, pruned_loss=0.3192, over 4767.00 frames.], tot_loss[loss=0.618, simple_loss=0.6023, pruned_loss=0.3168, over 967816.74 frames.], batch size: 15, lr: 1.21e-04
2022-05-27 20:30:29,271 INFO [train.py:761] (5/8) Epoch 2, batch 5700, loss[loss=0.638, simple_loss=0.6224, pruned_loss=0.3268, over 4967.00 frames.], tot_loss[loss=0.6142, simple_loss=0.6005, pruned_loss=0.3139, over 968205.96 frames.], batch size: 14, lr: 1.22e-04
2022-05-27 20:31:07,400 INFO [train.py:761] (5/8) Epoch 2, batch 5750, loss[loss=0.5751, simple_loss=0.5448, pruned_loss=0.3026, over 4889.00 frames.], tot_loss[loss=0.6142, simple_loss=0.6005, pruned_loss=0.3139, over 967819.21 frames.], batch size: 12, lr: 1.22e-04
2022-05-27 20:31:45,761 INFO [train.py:761] (5/8) Epoch 2, batch 5800, loss[loss=0.8001, simple_loss=0.7394, pruned_loss=0.4304, over 4922.00 frames.], tot_loss[loss=0.6101, simple_loss=0.5974, pruned_loss=0.3114, over 966490.59 frames.], batch size: 13, lr: 1.23e-04
2022-05-27 20:32:24,154 INFO [train.py:761] (5/8) Epoch 2, batch 5850, loss[loss=0.7293, simple_loss=0.6726, pruned_loss=0.393, over 4942.00 frames.], tot_loss[loss=0.6099, simple_loss=0.5981, pruned_loss=0.3109, over 967079.07 frames.], batch size: 49, lr: 1.23e-04
2022-05-27 20:33:02,684 INFO [train.py:761] (5/8) Epoch 2, batch 5900, loss[loss=0.4825, simple_loss=0.5033, pruned_loss=0.2309, over 4555.00 frames.], tot_loss[loss=0.6102, simple_loss=0.5975, pruned_loss=0.3115, over 967338.34 frames.], batch size: 10, lr: 1.24e-04
2022-05-27 20:33:40,758 INFO [train.py:761] (5/8) Epoch 2, batch 5950, loss[loss=0.5869, simple_loss=0.6, pruned_loss=0.2869, over 4977.00 frames.], tot_loss[loss=0.6084, simple_loss=0.5955, pruned_loss=0.3107, over 967912.89 frames.], batch size: 16, lr: 1.24e-04
2022-05-27 20:34:19,406 INFO [train.py:761] (5/8) Epoch 2, batch 6000, loss[loss=0.5985, simple_loss=0.5759, pruned_loss=0.3106, over 4825.00 frames.], tot_loss[loss=0.6051, simple_loss=0.5932, pruned_loss=0.3085, over 966897.59 frames.], batch size: 11, lr: 1.25e-04
2022-05-27 20:34:19,407 INFO [train.py:781] (5/8) Computing validation loss
2022-05-27 20:34:29,532 INFO [train.py:790] (5/8) Epoch 2, validation: loss=0.4554, simple_loss=0.5259, pruned_loss=0.1925, over 944034.00 frames.
2022-05-27 20:35:07,985 INFO [train.py:761] (5/8) Epoch 2, batch 6050, loss[loss=0.621, simple_loss=0.6364, pruned_loss=0.3028, over 4954.00 frames.], tot_loss[loss=0.6024, simple_loss=0.5912, pruned_loss=0.3068, over 966520.36 frames.], batch size: 16, lr: 1.25e-04
2022-05-27 20:35:46,441 INFO [train.py:761] (5/8) Epoch 2, batch 6100, loss[loss=0.6812, simple_loss=0.6252, pruned_loss=0.3686, over 4942.00 frames.], tot_loss[loss=0.5993, simple_loss=0.5893, pruned_loss=0.3046, over 965908.55 frames.], batch size: 46, lr: 1.26e-04
2022-05-27 20:36:24,225 INFO [train.py:761] (5/8) Epoch 2, batch 6150, loss[loss=0.6104, simple_loss=0.5978, pruned_loss=0.3116, over 4794.00 frames.], tot_loss[loss=0.5978, simple_loss=0.5884, pruned_loss=0.3036, over 965350.71 frames.], batch size: 14, lr: 1.26e-04
2022-05-27 20:37:02,097 INFO [train.py:761] (5/8) Epoch 2, batch 6200, loss[loss=0.537, simple_loss=0.5359, pruned_loss=0.269, over 4877.00 frames.], tot_loss[loss=0.5952, simple_loss=0.5864, pruned_loss=0.302, over 966607.71 frames.], batch size: 15, lr: 1.26e-04
2022-05-27 20:37:40,095 INFO [train.py:761] (5/8) Epoch 2, batch 6250, loss[loss=0.6218, simple_loss=0.5966, pruned_loss=0.3235, over 4839.00 frames.], tot_loss[loss=0.5964, simple_loss=0.588, pruned_loss=0.3023, over 967502.09 frames.], batch size: 18, lr: 1.27e-04
2022-05-27 20:38:18,285 INFO [train.py:761] (5/8) Epoch 2, batch 6300, loss[loss=0.5882, simple_loss=0.5492, pruned_loss=0.3136, over 4647.00 frames.], tot_loss[loss=0.5926, simple_loss=0.5853, pruned_loss=0.2999, over 966658.87 frames.], batch size: 11, lr: 1.27e-04
2022-05-27 20:38:56,440 INFO [train.py:761] (5/8) Epoch 2, batch 6350, loss[loss=0.4488, simple_loss=0.4597, pruned_loss=0.2189, over 4748.00 frames.], tot_loss[loss=0.589, simple_loss=0.5817, pruned_loss=0.2981, over 966453.19 frames.], batch size: 11, lr: 1.28e-04
2022-05-27 20:39:34,736 INFO [train.py:761] (5/8) Epoch 2, batch 6400, loss[loss=0.6613, simple_loss=0.616, pruned_loss=0.3533, over 4855.00 frames.], tot_loss[loss=0.5882, simple_loss=0.5811, pruned_loss=0.2977, over 966525.97 frames.], batch size: 20, lr: 1.28e-04
2022-05-27 20:40:12,639 INFO [train.py:761] (5/8) Epoch 2, batch 6450, loss[loss=0.5832, simple_loss=0.5671, pruned_loss=0.2996, over 4672.00 frames.], tot_loss[loss=0.5849, simple_loss=0.5799, pruned_loss=0.295, over 966823.00 frames.], batch size: 12, lr: 1.29e-04
2022-05-27 20:40:51,164 INFO [train.py:761] (5/8) Epoch 2, batch 6500, loss[loss=0.5433, simple_loss=0.5678, pruned_loss=0.2594, over 4776.00 frames.], tot_loss[loss=0.5853, simple_loss=0.5795, pruned_loss=0.2955, over 967181.19 frames.], batch size: 15, lr: 1.29e-04
2022-05-27 20:41:29,794 INFO [train.py:761] (5/8) Epoch 2, batch 6550, loss[loss=0.6226, simple_loss=0.6193, pruned_loss=0.3129, over 4917.00 frames.], tot_loss[loss=0.5817, simple_loss=0.5771, pruned_loss=0.2931, over 968264.19 frames.], batch size: 14, lr: 1.30e-04
2022-05-27 20:42:08,153 INFO [train.py:761] (5/8) Epoch 2, batch 6600, loss[loss=0.6138, simple_loss=0.6184, pruned_loss=0.3046, over 4893.00 frames.], tot_loss[loss=0.5791, simple_loss=0.5751, pruned_loss=0.2915, over 968745.64 frames.], batch size: 20, lr: 1.30e-04
2022-05-27 20:42:46,208 INFO [train.py:761] (5/8) Epoch 2, batch 6650, loss[loss=0.5067, simple_loss=0.5326, pruned_loss=0.2404, over 4995.00 frames.], tot_loss[loss=0.5776, simple_loss=0.5745, pruned_loss=0.2904, over 967884.02 frames.], batch size: 13, lr: 1.31e-04
2022-05-27 20:43:24,451 INFO [train.py:761] (5/8) Epoch 2, batch 6700, loss[loss=0.6114, simple_loss=0.6085, pruned_loss=0.3072, over 4976.00 frames.], tot_loss[loss=0.5747, simple_loss=0.5728, pruned_loss=0.2883, over 966489.72 frames.], batch size: 15, lr: 1.31e-04
2022-05-27 20:44:20,934 INFO [train.py:761] (5/8) Epoch 3, batch 0, loss[loss=0.5384, simple_loss=0.589, pruned_loss=0.2439, over 4795.00 frames.], tot_loss[loss=0.5384, simple_loss=0.589, pruned_loss=0.2439, over 4795.00 frames.], batch size: 14, lr: 1.32e-04
2022-05-27 20:44:59,547 INFO [train.py:761] (5/8) Epoch 3, batch 50, loss[loss=0.5392, simple_loss=0.5629, pruned_loss=0.2578, over 4978.00 frames.], tot_loss[loss=0.519, simple_loss=0.5478, pruned_loss=0.2452, over 218136.54 frames.], batch size: 49, lr: 1.32e-04
2022-05-27 20:45:37,117 INFO [train.py:761] (5/8) Epoch 3, batch 100, loss[loss=0.5789, simple_loss=0.5987, pruned_loss=0.2796, over 4854.00 frames.], tot_loss[loss=0.5104, simple_loss=0.5438, pruned_loss=0.2385, over 384606.21 frames.], batch size: 14, lr: 1.33e-04
2022-05-27 20:46:14,923 INFO [train.py:761] (5/8) Epoch 3, batch 150, loss[loss=0.5783, simple_loss=0.5987, pruned_loss=0.2789, over 4673.00 frames.], tot_loss[loss=0.5074, simple_loss=0.5415, pruned_loss=0.2366, over 513648.77 frames.], batch size: 13, lr: 1.33e-04
2022-05-27 20:46:52,388 INFO [train.py:761] (5/8) Epoch 3, batch 200, loss[loss=0.4372, simple_loss=0.4881, pruned_loss=0.1931, over 4646.00 frames.], tot_loss[loss=0.5049, simple_loss=0.5402, pruned_loss=0.2348, over 613749.72 frames.], batch size: 11, lr: 1.34e-04
2022-05-27 20:47:30,576 INFO [train.py:761] (5/8) Epoch 3, batch 250, loss[loss=0.5398, simple_loss=0.5659, pruned_loss=0.2568, over 4982.00 frames.], tot_loss[loss=0.5016, simple_loss=0.5365, pruned_loss=0.2334, over 690999.94 frames.], batch size: 14, lr: 1.34e-04
2022-05-27 20:48:08,695 INFO [train.py:761] (5/8) Epoch 3, batch 300, loss[loss=0.5922, simple_loss=0.5979, pruned_loss=0.2933, over 4862.00 frames.], tot_loss[loss=0.5, simple_loss=0.5362, pruned_loss=0.2319, over 752494.11 frames.], batch size: 17, lr: 1.35e-04
2022-05-27 20:48:47,210 INFO [train.py:761] (5/8) Epoch 3, batch 350, loss[loss=0.5312, simple_loss=0.5648, pruned_loss=0.2488, over 4857.00 frames.], tot_loss[loss=0.4977, simple_loss=0.534, pruned_loss=0.2307, over 800011.22 frames.], batch size: 20, lr: 1.35e-04
2022-05-27 20:49:25,088 INFO [train.py:761] (5/8) Epoch 3, batch 400, loss[loss=0.6158, simple_loss=0.6147, pruned_loss=0.3085, over 4726.00 frames.], tot_loss[loss=0.4978, simple_loss=0.5346, pruned_loss=0.2305, over 835901.38 frames.], batch size: 13, lr: 1.36e-04
2022-05-27 20:50:02,859 INFO [train.py:761] (5/8) Epoch 3, batch 450, loss[loss=0.3888, simple_loss=0.4519, pruned_loss=0.1628, over 4638.00 frames.], tot_loss[loss=0.4919, simple_loss=0.5299, pruned_loss=0.2269, over 864187.41 frames.], batch size: 11, lr: 1.36e-04
2022-05-27 20:50:40,624 INFO [train.py:761] (5/8) Epoch 3, batch 500, loss[loss=0.4444, simple_loss=0.4897, pruned_loss=0.1996, over 4787.00 frames.], tot_loss[loss=0.4881, simple_loss=0.5279, pruned_loss=0.2242, over 887781.32 frames.], batch size: 13, lr: 1.37e-04
2022-05-27 20:51:18,165 INFO [train.py:761] (5/8) Epoch 3, batch 550, loss[loss=0.4072, simple_loss=0.4546, pruned_loss=0.1799, over 4735.00 frames.], tot_loss[loss=0.4843, simple_loss=0.5249, pruned_loss=0.2219, over 904609.33 frames.], batch size: 11, lr: 1.37e-04
2022-05-27 20:51:55,961 INFO [train.py:761] (5/8) Epoch 3, batch 600, loss[loss=0.5718, simple_loss=0.5823, pruned_loss=0.2806, over 4911.00 frames.], tot_loss[loss=0.4854, simple_loss=0.5253, pruned_loss=0.2228, over 918601.35 frames.], batch size: 44, lr: 1.38e-04
2022-05-27 20:52:33,986 INFO [train.py:761] (5/8) Epoch 3, batch 650, loss[loss=0.4758, simple_loss=0.5341, pruned_loss=0.2088, over 4915.00 frames.], tot_loss[loss=0.4878, simple_loss=0.5273, pruned_loss=0.2241, over 929346.85 frames.], batch size: 14, lr: 1.38e-04
2022-05-27 20:53:11,972 INFO [train.py:761] (5/8) Epoch 3, batch 700, loss[loss=0.5867, simple_loss=0.6013, pruned_loss=0.2861, over 4883.00 frames.], tot_loss[loss=0.4896, simple_loss=0.5277, pruned_loss=0.2257, over 937137.37 frames.], batch size: 15, lr: 1.39e-04
2022-05-27 20:53:49,349 INFO [train.py:761] (5/8) Epoch 3, batch 750, loss[loss=0.4692, simple_loss=0.518, pruned_loss=0.2102, over 4909.00 frames.], tot_loss[loss=0.4913, simple_loss=0.5288, pruned_loss=0.2269, over 943517.85 frames.], batch size: 14, lr: 1.39e-04
2022-05-27 20:54:27,267 INFO [train.py:761] (5/8) Epoch 3, batch 800, loss[loss=0.4875, simple_loss=0.5389, pruned_loss=0.2181, over 4782.00 frames.], tot_loss[loss=0.4896, simple_loss=0.5268, pruned_loss=0.2262, over 948455.17 frames.], batch size: 14, lr: 1.40e-04
2022-05-27 20:55:05,354 INFO [train.py:761] (5/8) Epoch 3, batch 850, loss[loss=0.4202, simple_loss=0.4719, pruned_loss=0.1843, over 4922.00 frames.], tot_loss[loss=0.4878, simple_loss=0.525, pruned_loss=0.2253, over 952274.96 frames.], batch size: 13, lr: 1.40e-04
2022-05-27 20:55:43,191 INFO [train.py:761] (5/8) Epoch 3, batch 900, loss[loss=0.5346, simple_loss=0.5702, pruned_loss=0.2495, over 4786.00 frames.], tot_loss[loss=0.4871, simple_loss=0.5244, pruned_loss=0.2249, over 955579.80 frames.], batch size: 15, lr: 1.41e-04
2022-05-27 20:56:21,447 INFO [train.py:761] (5/8) Epoch 3, batch 950, loss[loss=0.5756, simple_loss=0.5862, pruned_loss=0.2825, over 4902.00 frames.], tot_loss[loss=0.4845, simple_loss=0.5218, pruned_loss=0.2237, over 957537.38 frames.], batch size: 43, lr: 1.41e-04
2022-05-27 20:56:58,948 INFO [train.py:761] (5/8) Epoch 3, batch 1000, loss[loss=0.5107, simple_loss=0.5566, pruned_loss=0.2324, over 4948.00 frames.], tot_loss[loss=0.4882, simple_loss=0.525, pruned_loss=0.2258, over 960208.15 frames.], batch size: 16, lr: 1.42e-04
2022-05-27 20:57:37,672 INFO [train.py:761] (5/8) Epoch 3, batch 1050, loss[loss=0.4002, simple_loss=0.4568, pruned_loss=0.1718, over 4837.00 frames.], tot_loss[loss=0.4873, simple_loss=0.5251, pruned_loss=0.2247, over 961983.95 frames.], batch size: 11, lr: 1.42e-04
2022-05-27 20:58:15,318 INFO [train.py:761] (5/8) Epoch 3, batch 1100, loss[loss=0.4288, simple_loss=0.479, pruned_loss=0.1893, over 4733.00 frames.], tot_loss[loss=0.482, simple_loss=0.5213, pruned_loss=0.2213, over 963369.82 frames.], batch size: 12, lr: 1.43e-04
2022-05-27 20:58:53,891 INFO [train.py:761] (5/8) Epoch 3, batch 1150, loss[loss=0.3797, simple_loss=0.4321, pruned_loss=0.1637, over 4641.00 frames.], tot_loss[loss=0.4768, simple_loss=0.5191, pruned_loss=0.2173, over 963663.33 frames.], batch size: 11, lr: 1.43e-04
2022-05-27 20:59:31,961 INFO [train.py:761] (5/8) Epoch 3, batch 1200, loss[loss=0.4344, simple_loss=0.5129, pruned_loss=0.178, over 4720.00 frames.], tot_loss[loss=0.4782, simple_loss=0.5208, pruned_loss=0.2178, over 965712.11 frames.], batch size: 13, lr: 1.44e-04
2022-05-27 21:00:09,980 INFO [train.py:761] (5/8) Epoch 3, batch 1250, loss[loss=0.5461, simple_loss=0.5734, pruned_loss=0.2594, over 4880.00 frames.], tot_loss[loss=0.4741, simple_loss=0.5182, pruned_loss=0.215, over 965369.48 frames.], batch size: 25, lr: 1.44e-04
2022-05-27 21:00:48,136 INFO [train.py:761] (5/8) Epoch 3, batch 1300, loss[loss=0.3847, simple_loss=0.4552, pruned_loss=0.1571, over 4669.00 frames.], tot_loss[loss=0.4731, simple_loss=0.5175, pruned_loss=0.2143, over 964527.02 frames.], batch size: 12, lr: 1.45e-04
2022-05-27 21:01:26,411 INFO [train.py:761] (5/8) Epoch 3, batch 1350, loss[loss=0.3757, simple_loss=0.4431, pruned_loss=0.1542, over 4611.00 frames.], tot_loss[loss=0.4737, simple_loss=0.5188, pruned_loss=0.2143, over 963868.79 frames.], batch size: 12, lr: 1.45e-04
2022-05-27 21:02:03,828 INFO [train.py:761] (5/8) Epoch 3, batch 1400, loss[loss=0.5504, simple_loss=0.5906, pruned_loss=0.255, over 4964.00 frames.], tot_loss[loss=0.4735, simple_loss=0.5191, pruned_loss=0.214, over 964006.63 frames.], batch size: 16, lr: 1.45e-04
2022-05-27 21:02:42,169 INFO [train.py:761] (5/8) Epoch 3, batch 1450, loss[loss=0.4424, simple_loss=0.4793, pruned_loss=0.2027, over 4975.00 frames.], tot_loss[loss=0.4734, simple_loss=0.5191, pruned_loss=0.2139, over 964367.23 frames.], batch size: 12, lr: 1.46e-04
2022-05-27 21:03:19,962 INFO [train.py:761] (5/8) Epoch 3, batch 1500, loss[loss=0.4256, simple_loss=0.4672, pruned_loss=0.192, over 4830.00 frames.], tot_loss[loss=0.4733, simple_loss=0.5204, pruned_loss=0.213, over 964081.02 frames.], batch size: 11, lr: 1.46e-04
2022-05-27 21:03:57,782 INFO [train.py:761] (5/8) Epoch 3, batch 1550, loss[loss=0.4489, simple_loss=0.5123, pruned_loss=0.1927, over 4795.00 frames.], tot_loss[loss=0.4693, simple_loss=0.5174, pruned_loss=0.2106, over 964642.96 frames.], batch size: 14, lr: 1.47e-04
2022-05-27 21:04:35,576 INFO [train.py:761] (5/8) Epoch 3, batch 1600, loss[loss=0.4409, simple_loss=0.4962, pruned_loss=0.1928, over 4773.00 frames.], tot_loss[loss=0.4663, simple_loss=0.5147, pruned_loss=0.2089, over 965749.23 frames.], batch size: 15, lr: 1.47e-04
2022-05-27 21:05:13,912 INFO [train.py:761] (5/8) Epoch 3, batch 1650, loss[loss=0.4539, simple_loss=0.5257, pruned_loss=0.191, over 4785.00 frames.], tot_loss[loss=0.4645, simple_loss=0.5137, pruned_loss=0.2076, over 966143.27 frames.], batch size: 15, lr: 1.48e-04
2022-05-27 21:05:51,572 INFO [train.py:761] (5/8) Epoch 3, batch 1700, loss[loss=0.3868, simple_loss=0.4635, pruned_loss=0.155, over 4927.00 frames.], tot_loss[loss=0.4623, simple_loss=0.5117, pruned_loss=0.2064, over 966289.25 frames.], batch size: 13, lr: 1.48e-04
2022-05-27 21:06:29,686 INFO [train.py:761] (5/8) Epoch 3, batch 1750, loss[loss=0.5099, simple_loss=0.5709, pruned_loss=0.2244, over 4914.00 frames.], tot_loss[loss=0.4626, simple_loss=0.5121, pruned_loss=0.2066, over 966334.12 frames.], batch size: 14, lr: 1.49e-04
2022-05-27 21:07:07,564 INFO [train.py:761] (5/8) Epoch 3, batch 1800, loss[loss=0.3856, simple_loss=0.4362, pruned_loss=0.1674, over 4662.00 frames.], tot_loss[loss=0.4595, simple_loss=0.5101, pruned_loss=0.2045, over 966949.06 frames.], batch size: 12, lr: 1.49e-04
2022-05-27 21:07:45,553 INFO [train.py:761] (5/8) Epoch 3, batch 1850, loss[loss=0.4157, simple_loss=0.4862, pruned_loss=0.1726, over 4789.00 frames.], tot_loss[loss=0.4579, simple_loss=0.5087, pruned_loss=0.2036, over 966605.20 frames.], batch size: 13, lr: 1.50e-04
2022-05-27 21:08:23,415 INFO [train.py:761] (5/8) Epoch 3, batch 1900, loss[loss=0.3902, simple_loss=0.4506, pruned_loss=0.1649, over 4915.00 frames.], tot_loss[loss=0.4541, simple_loss=0.506, pruned_loss=0.2011, over 967321.32 frames.], batch size: 13, lr: 1.50e-04
2022-05-27 21:09:01,459 INFO [train.py:761] (5/8) Epoch 3, batch 1950, loss[loss=0.4249, simple_loss=0.4967, pruned_loss=0.1765, over 4900.00 frames.], tot_loss[loss=0.4541, simple_loss=0.5062, pruned_loss=0.201, over 966751.42 frames.], batch size: 17, lr: 1.51e-04
2022-05-27 21:09:39,370 INFO [train.py:761] (5/8) Epoch 3, batch 2000, loss[loss=0.49, simple_loss=0.5336, pruned_loss=0.2232, over 4853.00 frames.], tot_loss[loss=0.4554, simple_loss=0.5067, pruned_loss=0.2021, over 966240.96 frames.], batch size: 14, lr: 1.51e-04
2022-05-27 21:10:18,116 INFO [train.py:761] (5/8) Epoch 3, batch 2050, loss[loss=0.5746, simple_loss=0.5894, pruned_loss=0.2799, over 4951.00 frames.], tot_loss[loss=0.4536, simple_loss=0.5059, pruned_loss=0.2006, over 967430.15 frames.], batch size: 16, lr: 1.52e-04
2022-05-27 21:10:55,481 INFO [train.py:761] (5/8) Epoch 3, batch 2100, loss[loss=0.4763, simple_loss=0.5279, pruned_loss=0.2123, over 4932.00 frames.], tot_loss[loss=0.4542, simple_loss=0.5065, pruned_loss=0.201, over 966858.15 frames.], batch size: 26, lr: 1.52e-04
2022-05-27 21:11:33,439 INFO [train.py:761] (5/8) Epoch 3, batch 2150, loss[loss=0.4895, simple_loss=0.5272, pruned_loss=0.2259, over 4722.00 frames.], tot_loss[loss=0.4537, simple_loss=0.5055, pruned_loss=0.201, over 966581.84 frames.], batch size: 14, lr: 1.53e-04
2022-05-27 21:12:11,126 INFO [train.py:761] (5/8) Epoch 3, batch 2200, loss[loss=0.4332, simple_loss=0.4736, pruned_loss=0.1964, over 4994.00 frames.], tot_loss[loss=0.4529, simple_loss=0.5047, pruned_loss=0.2006, over 967438.12 frames.], batch size: 11, lr: 1.53e-04
2022-05-27 21:12:49,543 INFO [train.py:761] (5/8) Epoch 3, batch 2250, loss[loss=0.4357, simple_loss=0.5004, pruned_loss=0.1855, over 4918.00 frames.], tot_loss[loss=0.4505, simple_loss=0.5028, pruned_loss=0.1991, over 966938.82 frames.], batch size: 14, lr: 1.54e-04
2022-05-27 21:13:27,343 INFO [train.py:761] (5/8) Epoch 3, batch 2300, loss[loss=0.4072, simple_loss=0.471, pruned_loss=0.1717, over 4918.00 frames.], tot_loss[loss=0.4464, simple_loss=0.4996, pruned_loss=0.1967, over 966259.42 frames.], batch size: 13, lr: 1.54e-04
2022-05-27 21:14:05,614 INFO [train.py:761] (5/8) Epoch 3, batch 2350, loss[loss=0.3335, simple_loss=0.4077, pruned_loss=0.1297, over 4648.00 frames.], tot_loss[loss=0.4451, simple_loss=0.4985, pruned_loss=0.1958, over 965605.31 frames.], batch size: 11, lr: 1.55e-04
2022-05-27 21:14:42,769 INFO [train.py:761] (5/8) Epoch 3, batch 2400, loss[loss=0.4773, simple_loss=0.5242, pruned_loss=0.2152, over 4880.00 frames.], tot_loss[loss=0.4454, simple_loss=0.4988, pruned_loss=0.1959, over 965008.10 frames.], batch size: 18, lr: 1.55e-04
2022-05-27 21:15:20,261 INFO [train.py:761] (5/8) Epoch 3, batch 2450, loss[loss=0.5306, simple_loss=0.5608, pruned_loss=0.2501, over 4725.00 frames.], tot_loss[loss=0.4466, simple_loss=0.5003, pruned_loss=0.1964, over 965841.92 frames.], batch size: 13, lr: 1.56e-04
2022-05-27 21:15:57,785 INFO [train.py:761] (5/8) Epoch 3, batch 2500, loss[loss=0.357, simple_loss=0.4185, pruned_loss=0.1478, over 4731.00 frames.], tot_loss[loss=0.4464, simple_loss=0.5003, pruned_loss=0.1963, over 966269.88 frames.], batch size: 11, lr: 1.56e-04
2022-05-27 21:16:39,223 INFO [train.py:761] (5/8) Epoch 3, batch 2550, loss[loss=0.5402, simple_loss=0.557, pruned_loss=0.2616, over 4732.00 frames.], tot_loss[loss=0.4439, simple_loss=0.4984, pruned_loss=0.1947, over 966223.06 frames.], batch size: 13, lr: 1.57e-04
2022-05-27 21:17:16,834 INFO [train.py:761] (5/8) Epoch 3, batch 2600, loss[loss=0.3877, simple_loss=0.4717, pruned_loss=0.1519, over 4959.00 frames.], tot_loss[loss=0.441, simple_loss=0.4961, pruned_loss=0.193, over 965695.66 frames.], batch size: 15, lr: 1.57e-04
2022-05-27 21:17:54,752 INFO [train.py:761] (5/8) Epoch 3, batch 2650, loss[loss=0.4532, simple_loss=0.501, pruned_loss=0.2027, over 4958.00 frames.], tot_loss[loss=0.4416, simple_loss=0.4965, pruned_loss=0.1934, over 966341.64 frames.], batch size: 16, lr: 1.58e-04
2022-05-27 21:18:32,330 INFO [train.py:761] (5/8) Epoch 3, batch 2700, loss[loss=0.3954, simple_loss=0.4562, pruned_loss=0.1673, over 4645.00 frames.], tot_loss[loss=0.4385, simple_loss=0.4936, pruned_loss=0.1916, over 965873.12 frames.], batch size: 11, lr: 1.58e-04
2022-05-27 21:19:10,302 INFO [train.py:761] (5/8) Epoch 3, batch 2750, loss[loss=0.4191, simple_loss=0.4858, pruned_loss=0.1762, over 4725.00 frames.], tot_loss[loss=0.4391, simple_loss=0.4945, pruned_loss=0.1919, over 965539.31 frames.], batch size: 13, lr: 1.59e-04
2022-05-27 21:19:48,003 INFO [train.py:761] (5/8) Epoch 3, batch 2800, loss[loss=0.392, simple_loss=0.4665, pruned_loss=0.1587, over 4922.00 frames.], tot_loss[loss=0.4385, simple_loss=0.4932, pruned_loss=0.1919, over 965380.76 frames.], batch size: 14, lr: 1.59e-04
2022-05-27 21:20:25,826 INFO [train.py:761] (5/8) Epoch 3, batch 2850, loss[loss=0.4266, simple_loss=0.4831, pruned_loss=0.185, over 4799.00 frames.], tot_loss[loss=0.4374, simple_loss=0.4922, pruned_loss=0.1914, over 966827.50 frames.], batch size: 12, lr: 1.60e-04
2022-05-27 21:21:03,822 INFO [train.py:761] (5/8) Epoch 3, batch 2900, loss[loss=0.4543, simple_loss=0.5278, pruned_loss=0.1904, over 4855.00 frames.], tot_loss[loss=0.4352, simple_loss=0.4907, pruned_loss=0.1899, over 967045.57 frames.], batch size: 14, lr: 1.60e-04
2022-05-27 21:21:41,922 INFO [train.py:761] (5/8) Epoch 3, batch 2950, loss[loss=0.5003, simple_loss=0.5474, pruned_loss=0.2266, over 4774.00 frames.], tot_loss[loss=0.4378, simple_loss=0.4925, pruned_loss=0.1915, over 967598.19 frames.], batch size: 18, lr: 1.61e-04
2022-05-27 21:22:19,701 INFO [train.py:761] (5/8) Epoch 3, batch 3000, loss[loss=0.5051, simple_loss=0.5524, pruned_loss=0.2288, over 4820.00 frames.], tot_loss[loss=0.4377, simple_loss=0.4924, pruned_loss=0.1916, over 967549.60 frames.], batch size: 18, lr: 1.61e-04
2022-05-27 21:22:19,702 INFO [train.py:781] (5/8) Computing validation loss
2022-05-27 21:22:29,646 INFO [train.py:790] (5/8) Epoch 3, validation: loss=0.3638, simple_loss=0.4584, pruned_loss=0.1345, over 944034.00 frames.
2022-05-27 21:23:08,074 INFO [train.py:761] (5/8) Epoch 3, batch 3050, loss[loss=0.3778, simple_loss=0.4281, pruned_loss=0.1638, over 4801.00 frames.], tot_loss[loss=0.4351, simple_loss=0.4898, pruned_loss=0.1903, over 967631.57 frames.], batch size: 12, lr: 1.62e-04
2022-05-27 21:23:46,032 INFO [train.py:761] (5/8) Epoch 3, batch 3100, loss[loss=0.3803, simple_loss=0.423, pruned_loss=0.1689, over 4719.00 frames.], tot_loss[loss=0.4334, simple_loss=0.4876, pruned_loss=0.1896, over 966941.00 frames.], batch size: 11, lr: 1.62e-04
2022-05-27 21:24:24,095 INFO [train.py:761] (5/8) Epoch 3, batch 3150, loss[loss=0.4523, simple_loss=0.4945, pruned_loss=0.205, over 4613.00 frames.], tot_loss[loss=0.4394, simple_loss=0.4912, pruned_loss=0.1938, over 965942.31 frames.], batch size: 12, lr: 1.63e-04
2022-05-27 21:25:02,781 INFO [train.py:761] (5/8) Epoch 3, batch 3200, loss[loss=0.4716, simple_loss=0.5228, pruned_loss=0.2102, over 4725.00 frames.], tot_loss[loss=0.4417, simple_loss=0.4913, pruned_loss=0.1961, over 965319.28 frames.], batch size: 14, lr: 1.63e-04
2022-05-27 21:25:40,546 INFO [train.py:761] (5/8) Epoch 3, batch 3250, loss[loss=0.5521, simple_loss=0.5491, pruned_loss=0.2776, over 4767.00 frames.], tot_loss[loss=0.4462, simple_loss=0.4923, pruned_loss=0.2, over 965193.90 frames.], batch size: 15, lr: 1.64e-04
2022-05-27 21:26:18,927 INFO [train.py:761] (5/8) Epoch 3, batch 3300, loss[loss=0.5588, simple_loss=0.5689, pruned_loss=0.2744, over 4902.00 frames.], tot_loss[loss=0.4526, simple_loss=0.4952, pruned_loss=0.205, over 965250.41 frames.], batch size: 46, lr: 1.64e-04
2022-05-27 21:26:56,902 INFO [train.py:761] (5/8) Epoch 3, batch 3350, loss[loss=0.4285, simple_loss=0.4727, pruned_loss=0.1921, over 4975.00 frames.], tot_loss[loss=0.459, simple_loss=0.4978, pruned_loss=0.2101, over 965402.09 frames.], batch size: 12, lr: 1.65e-04
2022-05-27 21:27:34,668 INFO [train.py:761] (5/8) Epoch 3, batch 3400, loss[loss=0.4965, simple_loss=0.5107, pruned_loss=0.2411, over 4559.00 frames.], tot_loss[loss=0.4633, simple_loss=0.4996, pruned_loss=0.2134, over 966349.57 frames.], batch size: 10, lr: 1.65e-04
2022-05-27 21:28:12,193 INFO [train.py:761] (5/8) Epoch 3, batch 3450, loss[loss=0.4603, simple_loss=0.476, pruned_loss=0.2223, over 4985.00 frames.], tot_loss[loss=0.4677, simple_loss=0.5016, pruned_loss=0.2169, over 966529.66 frames.], batch size: 13, lr: 1.66e-04
2022-05-27 21:28:50,517 INFO [train.py:761] (5/8) Epoch 3, batch 3500, loss[loss=0.4856, simple_loss=0.5156, pruned_loss=0.2278, over 4980.00 frames.], tot_loss[loss=0.4733, simple_loss=0.5044, pruned_loss=0.2211, over 965376.57 frames.], batch size: 14, lr: 1.66e-04
2022-05-27 21:29:28,466 INFO [train.py:761] (5/8) Epoch 3, batch 3550, loss[loss=0.4087, simple_loss=0.4479, pruned_loss=0.1847, over 4641.00 frames.], tot_loss[loss=0.4754, simple_loss=0.5046, pruned_loss=0.2231, over 965204.39 frames.], batch size: 11, lr: 1.66e-04
2022-05-27 21:30:05,731 INFO [train.py:761] (5/8) Epoch 3, batch 3600, loss[loss=0.5348, simple_loss=0.5523, pruned_loss=0.2586, over 4770.00 frames.], tot_loss[loss=0.4792, simple_loss=0.5065, pruned_loss=0.2259, over 964594.59 frames.], batch size: 16, lr: 1.67e-04
2022-05-27 21:30:43,913 INFO [train.py:761] (5/8) Epoch 3, batch 3650, loss[loss=0.5483, simple_loss=0.561, pruned_loss=0.2678, over 4803.00 frames.], tot_loss[loss=0.4781, simple_loss=0.5055, pruned_loss=0.2253, over 965315.75 frames.], batch size: 16, lr: 1.67e-04
2022-05-27 21:31:22,025 INFO [train.py:761] (5/8) Epoch 3, batch 3700, loss[loss=0.5008, simple_loss=0.529, pruned_loss=0.2363, over 4674.00 frames.], tot_loss[loss=0.4792, simple_loss=0.5058, pruned_loss=0.2263, over 965567.17 frames.], batch size: 13, lr: 1.68e-04
2022-05-27 21:32:00,040 INFO [train.py:761] (5/8) Epoch 3, batch 3750, loss[loss=0.4313, simple_loss=0.458, pruned_loss=0.2023, over 4737.00 frames.], tot_loss[loss=0.4805, simple_loss=0.5071, pruned_loss=0.2269, over 966405.36 frames.], batch size: 12, lr: 1.68e-04
2022-05-27 21:32:37,182 INFO [train.py:761] (5/8) Epoch 3, batch 3800, loss[loss=0.4783, simple_loss=0.5193, pruned_loss=0.2186, over 4849.00 frames.], tot_loss[loss=0.4813, simple_loss=0.5074, pruned_loss=0.2276, over 966290.69 frames.], batch size: 14, lr: 1.69e-04
2022-05-27 21:33:15,329 INFO [train.py:761] (5/8) Epoch 3, batch 3850, loss[loss=0.4337, simple_loss=0.4697, pruned_loss=0.1989, over 4879.00 frames.], tot_loss[loss=0.4806, simple_loss=0.5061, pruned_loss=0.2276, over 967318.54 frames.], batch size: 12, lr: 1.69e-04
2022-05-27 21:33:53,695 INFO [train.py:761] (5/8) Epoch 3, batch 3900, loss[loss=0.3821, simple_loss=0.433, pruned_loss=0.1656, over 4813.00 frames.], tot_loss[loss=0.4824, simple_loss=0.5071, pruned_loss=0.2288, over 966648.72 frames.], batch size: 11, lr: 1.70e-04
2022-05-27 21:34:31,968 INFO [train.py:761] (5/8) Epoch 3, batch 3950, loss[loss=0.5074, simple_loss=0.5259, pruned_loss=0.2444, over 4907.00 frames.], tot_loss[loss=0.4824, simple_loss=0.5066, pruned_loss=0.229, over 967205.61 frames.], batch size: 27, lr: 1.70e-04
2022-05-27 21:35:10,320 INFO [train.py:761] (5/8) Epoch 3, batch 4000, loss[loss=0.3938, simple_loss=0.4355, pruned_loss=0.176, over 4976.00 frames.], tot_loss[loss=0.4834, simple_loss=0.5081, pruned_loss=0.2293, over 966466.09 frames.], batch size: 12, lr: 1.71e-04
2022-05-27 21:35:48,304 INFO [train.py:761] (5/8) Epoch 3, batch 4050, loss[loss=0.4965, simple_loss=0.521, pruned_loss=0.236, over 4946.00 frames.], tot_loss[loss=0.4836, simple_loss=0.5082, pruned_loss=0.2294, over 967150.95 frames.], batch size: 26, lr: 1.71e-04
2022-05-27 21:36:26,294 INFO [train.py:761] (5/8) Epoch 3, batch 4100, loss[loss=0.4284, simple_loss=0.4655, pruned_loss=0.1956, over 4847.00 frames.], tot_loss[loss=0.4821, simple_loss=0.5075, pruned_loss=0.2283, over 967828.66 frames.], batch size: 13, lr: 1.72e-04
2022-05-27 21:37:04,293 INFO [train.py:761] (5/8) Epoch 3, batch 4150, loss[loss=0.4165, simple_loss=0.4448, pruned_loss=0.1941, over 4987.00 frames.], tot_loss[loss=0.4814, simple_loss=0.5076, pruned_loss=0.2276, over 966950.38 frames.], batch size: 13, lr: 1.72e-04
2022-05-27 21:37:42,082 INFO [train.py:761] (5/8) Epoch 3, batch 4200, loss[loss=0.4155, simple_loss=0.4706, pruned_loss=0.1802, over 4716.00 frames.], tot_loss[loss=0.4786, simple_loss=0.5051, pruned_loss=0.2261, over 966964.55 frames.], batch size: 14, lr: 1.73e-04
2022-05-27 21:38:20,365 INFO [train.py:761] (5/8) Epoch 3, batch 4250, loss[loss=0.4196, simple_loss=0.4657, pruned_loss=0.1867, over 4789.00 frames.], tot_loss[loss=0.4745, simple_loss=0.5025, pruned_loss=0.2233, over 966513.11 frames.], batch size: 13, lr: 1.73e-04
2022-05-27 21:38:58,242 INFO [train.py:761] (5/8) Epoch 3, batch 4300, loss[loss=0.4168, simple_loss=0.4224, pruned_loss=0.2056, over 4637.00 frames.], tot_loss[loss=0.4698, simple_loss=0.499, pruned_loss=0.2204, over 966411.32 frames.], batch size: 11, lr: 1.74e-04
2022-05-27 21:39:36,989 INFO [train.py:761] (5/8) Epoch 3, batch 4350, loss[loss=0.4664, simple_loss=0.5148, pruned_loss=0.209, over 4849.00 frames.], tot_loss[loss=0.4737, simple_loss=0.502, pruned_loss=0.2227, over 967878.59 frames.], batch size: 14, lr: 1.74e-04
2022-05-27 21:40:14,820 INFO [train.py:761] (5/8) Epoch 3, batch 4400, loss[loss=0.4876, simple_loss=0.5393, pruned_loss=0.218, over 4937.00 frames.], tot_loss[loss=0.4734, simple_loss=0.5021, pruned_loss=0.2223, over 967509.68 frames.], batch size: 26, lr: 1.75e-04
2022-05-27 21:40:53,427 INFO [train.py:761] (5/8) Epoch 3, batch 4450, loss[loss=0.3767, simple_loss=0.4194, pruned_loss=0.167, over 4728.00 frames.], tot_loss[loss=0.471, simple_loss=0.4997, pruned_loss=0.2211, over 966075.15 frames.], batch size: 13, lr: 1.75e-04
2022-05-27 21:41:31,294 INFO [train.py:761] (5/8) Epoch 3, batch 4500, loss[loss=0.3817, simple_loss=0.427, pruned_loss=0.1682, over 4992.00 frames.], tot_loss[loss=0.4701, simple_loss=0.4984, pruned_loss=0.2209, over 965946.29 frames.], batch size: 13, lr: 1.76e-04
2022-05-27 21:42:09,708 INFO [train.py:761] (5/8) Epoch 3, batch 4550, loss[loss=0.4316, simple_loss=0.452, pruned_loss=0.2056, over 4563.00 frames.], tot_loss[loss=0.4642, simple_loss=0.4936, pruned_loss=0.2173, over 966149.88 frames.], batch size: 10, lr: 1.76e-04
2022-05-27 21:42:47,947 INFO [train.py:761] (5/8) Epoch 3, batch 4600, loss[loss=0.4726, simple_loss=0.5163, pruned_loss=0.2145, over 4846.00 frames.], tot_loss[loss=0.4624, simple_loss=0.4929, pruned_loss=0.216, over 966716.78 frames.], batch size: 14, lr: 1.77e-04
2022-05-27 21:43:26,360 INFO [train.py:761] (5/8) Epoch 3, batch 4650, loss[loss=0.4335, simple_loss=0.4584, pruned_loss=0.2042, over 4808.00 frames.], tot_loss[loss=0.4603, simple_loss=0.4912, pruned_loss=0.2147, over 966885.99 frames.], batch size: 12, lr: 1.77e-04
2022-05-27 21:44:04,286 INFO [train.py:761] (5/8) Epoch 3, batch 4700, loss[loss=0.5311, simple_loss=0.5343, pruned_loss=0.2639, over 4992.00 frames.], tot_loss[loss=0.4639, simple_loss=0.4941, pruned_loss=0.2168, over 967652.81 frames.], batch size: 13, lr: 1.78e-04
2022-05-27 21:44:42,454 INFO [train.py:761] (5/8) Epoch 3, batch 4750, loss[loss=0.4094, simple_loss=0.4383, pruned_loss=0.1902, over 4805.00 frames.], tot_loss[loss=0.4626, simple_loss=0.4934, pruned_loss=0.2159, over 966718.09 frames.], batch size: 12, lr: 1.78e-04
2022-05-27 21:45:20,558 INFO [train.py:761] (5/8) Epoch 3, batch 4800, loss[loss=0.5943, simple_loss=0.5948, pruned_loss=0.2968, over 4850.00 frames.], tot_loss[loss=0.4639, simple_loss=0.495, pruned_loss=0.2164, over 966397.03 frames.], batch size: 14, lr: 1.79e-04
2022-05-27 21:45:58,635 INFO [train.py:761] (5/8) Epoch 3, batch 4850, loss[loss=0.4889, simple_loss=0.5234, pruned_loss=0.2272, over 4847.00 frames.], tot_loss[loss=0.4629, simple_loss=0.4944, pruned_loss=0.2157, over 965960.07 frames.], batch size: 14, lr: 1.79e-04
2022-05-27 21:46:36,481 INFO [train.py:761] (5/8) Epoch 3, batch 4900, loss[loss=0.4764, simple_loss=0.524, pruned_loss=0.2144, over 4949.00 frames.], tot_loss[loss=0.4643, simple_loss=0.4959, pruned_loss=0.2163, over 965301.75 frames.], batch size: 16, lr: 1.80e-04
2022-05-27 21:47:14,569 INFO [train.py:761] (5/8) Epoch 3, batch 4950, loss[loss=0.4472, simple_loss=0.4896, pruned_loss=0.2024, over 4794.00 frames.], tot_loss[loss=0.4622, simple_loss=0.4945, pruned_loss=0.215, over 965824.26 frames.], batch size: 14, lr: 1.80e-04
2022-05-27 21:47:52,663 INFO [train.py:761] (5/8) Epoch 3, batch 5000, loss[loss=0.5003, simple_loss=0.496, pruned_loss=0.2523, over 4888.00 frames.], tot_loss[loss=0.4606, simple_loss=0.494, pruned_loss=0.2136, over 966060.81 frames.], batch size: 12, lr: 1.81e-04
2022-05-27 21:48:31,427 INFO [train.py:761] (5/8) Epoch 3, batch 5050, loss[loss=0.2879, simple_loss=0.3556, pruned_loss=0.1101, over 4737.00 frames.], tot_loss[loss=0.457, simple_loss=0.4907, pruned_loss=0.2116, over 965780.94 frames.], batch size: 11, lr: 1.81e-04
2022-05-27 21:49:09,212 INFO [train.py:761] (5/8) Epoch 3, batch 5100, loss[loss=0.4131, simple_loss=0.4646, pruned_loss=0.1808, over 4810.00 frames.], tot_loss[loss=0.4561, simple_loss=0.491, pruned_loss=0.2106, over 965623.15 frames.], batch size: 12, lr: 1.82e-04
2022-05-27 21:49:47,285 INFO [train.py:761] (5/8) Epoch 3, batch 5150, loss[loss=0.4094, simple_loss=0.4462, pruned_loss=0.1863, over 4922.00 frames.], tot_loss[loss=0.4525, simple_loss=0.4876, pruned_loss=0.2088, over 965702.39 frames.], batch size: 13, lr: 1.82e-04
2022-05-27 21:50:26,081 INFO [train.py:761] (5/8) Epoch 3, batch 5200, loss[loss=0.4735, simple_loss=0.5111, pruned_loss=0.2179, over 4963.00 frames.], tot_loss[loss=0.4527, simple_loss=0.4874, pruned_loss=0.209, over 965270.18 frames.], batch size: 14, lr: 1.83e-04
2022-05-27 21:51:04,248 INFO [train.py:761] (5/8) Epoch 3, batch 5250, loss[loss=0.4354, simple_loss=0.4942, pruned_loss=0.1883, over 4781.00 frames.], tot_loss[loss=0.4506, simple_loss=0.4861, pruned_loss=0.2075, over 966522.42 frames.], batch size: 15, lr: 1.83e-04
2022-05-27 21:51:43,376 INFO [train.py:761] (5/8) Epoch 3, batch 5300, loss[loss=0.4923, simple_loss=0.4987, pruned_loss=0.243, over 4806.00 frames.], tot_loss[loss=0.4539, simple_loss=0.4886, pruned_loss=0.2096, over 966891.47 frames.], batch size: 12, lr: 1.84e-04
2022-05-27 21:52:22,123 INFO [train.py:761] (5/8) Epoch 3, batch 5350, loss[loss=0.4229, simple_loss=0.483, pruned_loss=0.1814, over 4681.00 frames.], tot_loss[loss=0.4515, simple_loss=0.487, pruned_loss=0.208, over 966532.26 frames.], batch size: 13, lr: 1.84e-04
2022-05-27 21:53:00,283 INFO [train.py:761] (5/8) Epoch 3, batch 5400, loss[loss=0.4167, simple_loss=0.464, pruned_loss=0.1847, over 4898.00 frames.], tot_loss[loss=0.454, simple_loss=0.4884, pruned_loss=0.2098, over 967019.32 frames.], batch size: 12, lr: 1.85e-04
2022-05-27 21:53:38,787 INFO [train.py:761] (5/8) Epoch 3, batch 5450, loss[loss=0.3864, simple_loss=0.4455, pruned_loss=0.1636, over 4849.00 frames.], tot_loss[loss=0.4535, simple_loss=0.488, pruned_loss=0.2095, over 967836.94 frames.], batch size: 13, lr: 1.85e-04
2022-05-27 21:54:17,616 INFO [train.py:761] (5/8) Epoch 3, batch 5500, loss[loss=0.5207, simple_loss=0.5431, pruned_loss=0.2492, over 4718.00 frames.], tot_loss[loss=0.4507, simple_loss=0.4859, pruned_loss=0.2078, over 967229.62 frames.], batch size: 14, lr: 1.86e-04
2022-05-27 21:54:56,321 INFO [train.py:761] (5/8) Epoch 3, batch 5550, loss[loss=0.3713, simple_loss=0.4245, pruned_loss=0.159, over 4785.00 frames.], tot_loss[loss=0.4515, simple_loss=0.487, pruned_loss=0.208, over 967452.53 frames.], batch size: 13, lr: 1.86e-04
2022-05-27 21:55:34,268 INFO [train.py:761] (5/8) Epoch 3, batch 5600, loss[loss=0.4621, simple_loss=0.4835, pruned_loss=0.2204, over 4879.00 frames.], tot_loss[loss=0.4527, simple_loss=0.4871, pruned_loss=0.2091, over 966228.56 frames.], batch size: 15, lr: 1.87e-04
2022-05-27 21:56:12,126 INFO [train.py:761] (5/8) Epoch 3, batch 5650, loss[loss=0.4971, simple_loss=0.5307, pruned_loss=0.2318, over 4980.00 frames.], tot_loss[loss=0.4503, simple_loss=0.486, pruned_loss=0.2073, over 966065.49 frames.], batch size: 14, lr: 1.87e-04
2022-05-27 21:56:50,000 INFO [train.py:761] (5/8) Epoch 3, batch 5700, loss[loss=0.4392, simple_loss=0.4806, pruned_loss=0.1989, over 4973.00 frames.], tot_loss[loss=0.4467, simple_loss=0.4831, pruned_loss=0.2052, over 966088.78 frames.], batch size: 14, lr: 1.87e-04
2022-05-27 21:57:28,257 INFO [train.py:761] (5/8) Epoch 3, batch 5750, loss[loss=0.4611, simple_loss=0.498, pruned_loss=0.2121, over 4808.00 frames.], tot_loss[loss=0.4467, simple_loss=0.4829, pruned_loss=0.2052, over 966427.01 frames.], batch size: 20, lr: 1.88e-04
2022-05-27 21:58:06,611 INFO [train.py:761] (5/8) Epoch 3, batch 5800, loss[loss=0.5205, simple_loss=0.5312, pruned_loss=0.2549, over 4979.00 frames.], tot_loss[loss=0.4472, simple_loss=0.4834, pruned_loss=0.2055, over 966557.66 frames.], batch size: 53, lr: 1.88e-04
2022-05-27 21:58:45,242 INFO [train.py:761] (5/8) Epoch 3, batch 5850, loss[loss=0.4512, simple_loss=0.4669, pruned_loss=0.2177, over 4886.00 frames.], tot_loss[loss=0.444, simple_loss=0.4807, pruned_loss=0.2037, over 966948.12 frames.], batch size: 12, lr: 1.89e-04
2022-05-27 21:59:23,306 INFO [train.py:761] (5/8) Epoch 3, batch 5900, loss[loss=0.4277, simple_loss=0.459, pruned_loss=0.1982, over 4664.00 frames.], tot_loss[loss=0.4455, simple_loss=0.4821, pruned_loss=0.2044, over 966867.47 frames.], batch size: 13, lr: 1.89e-04
2022-05-27 22:00:01,519 INFO [train.py:761] (5/8) Epoch 3, batch 5950, loss[loss=0.4134, simple_loss=0.4286, pruned_loss=0.1991, over 4730.00 frames.], tot_loss[loss=0.4445, simple_loss=0.4818, pruned_loss=0.2037, over 967609.34 frames.], batch size: 11, lr: 1.90e-04
2022-05-27 22:00:39,595 INFO [train.py:761] (5/8) Epoch 3, batch 6000, loss[loss=0.3817, simple_loss=0.427, pruned_loss=0.1682, over 4733.00 frames.], tot_loss[loss=0.446, simple_loss=0.4832, pruned_loss=0.2044, over 968059.09 frames.], batch size: 12, lr: 1.90e-04
2022-05-27 22:00:39,596 INFO [train.py:781] (5/8) Computing validation loss
2022-05-27 22:00:49,392 INFO [train.py:790] (5/8) Epoch 3, validation: loss=0.3206, simple_loss=0.4277, pruned_loss=0.1068, over 944034.00 frames.
2022-05-27 22:01:28,322 INFO [train.py:761] (5/8) Epoch 3, batch 6050, loss[loss=0.4043, simple_loss=0.4704, pruned_loss=0.1691, over 4932.00 frames.], tot_loss[loss=0.445, simple_loss=0.4822, pruned_loss=0.2039, over 966990.86 frames.], batch size: 13, lr: 1.91e-04
2022-05-27 22:02:07,085 INFO [train.py:761] (5/8) Epoch 3, batch 6100, loss[loss=0.3816, simple_loss=0.4413, pruned_loss=0.161, over 4655.00 frames.], tot_loss[loss=0.4447, simple_loss=0.4818, pruned_loss=0.2038, over 966381.36 frames.], batch size: 12, lr: 1.91e-04
2022-05-27 22:02:45,187 INFO [train.py:761] (5/8) Epoch 3, batch 6150, loss[loss=0.4722, simple_loss=0.5138, pruned_loss=0.2153, over 4669.00 frames.], tot_loss[loss=0.4457, simple_loss=0.4825, pruned_loss=0.2045, over 967454.63 frames.], batch size: 12, lr: 1.92e-04
2022-05-27 22:03:23,251 INFO [train.py:761] (5/8) Epoch 3, batch 6200, loss[loss=0.4127, simple_loss=0.4741, pruned_loss=0.1757, over 4917.00 frames.], tot_loss[loss=0.4467, simple_loss=0.4833, pruned_loss=0.2051, over 967359.72 frames.], batch size: 14, lr: 1.92e-04
2022-05-27 22:04:02,073 INFO [train.py:761] (5/8) Epoch 3, batch 6250, loss[loss=0.3736, simple_loss=0.4288, pruned_loss=0.1592, over 4881.00 frames.], tot_loss[loss=0.4427, simple_loss=0.4795, pruned_loss=0.2029, over 967997.46 frames.], batch size: 12, lr: 1.93e-04
2022-05-27 22:04:40,271 INFO [train.py:761] (5/8) Epoch 3, batch 6300, loss[loss=0.481, simple_loss=0.519, pruned_loss=0.2215, over 4847.00 frames.], tot_loss[loss=0.4398, simple_loss=0.4776, pruned_loss=0.201, over 967415.85 frames.], batch size: 18, lr: 1.93e-04
2022-05-27 22:05:19,176 INFO [train.py:761] (5/8) Epoch 3, batch 6350, loss[loss=0.4176, simple_loss=0.4629, pruned_loss=0.1861, over 4979.00 frames.], tot_loss[loss=0.4396, simple_loss=0.4773, pruned_loss=0.201, over 967345.87 frames.], batch size: 14, lr: 1.94e-04
2022-05-27 22:05:57,392 INFO [train.py:761] (5/8) Epoch 3, batch 6400, loss[loss=0.5227, simple_loss=0.5256, pruned_loss=0.2599, over 4901.00 frames.], tot_loss[loss=0.4388, simple_loss=0.4771, pruned_loss=0.2002, over 967043.04 frames.], batch size: 48, lr: 1.94e-04
2022-05-27 22:06:35,359 INFO [train.py:761] (5/8) Epoch 3, batch 6450, loss[loss=0.5556, simple_loss=0.5842, pruned_loss=0.2635, over 4727.00 frames.], tot_loss[loss=0.4412, simple_loss=0.4793, pruned_loss=0.2016, over 966879.86 frames.], batch size: 13, lr: 1.95e-04
2022-05-27 22:07:13,688 INFO [train.py:761] (5/8) Epoch 3, batch 6500, loss[loss=0.4236, simple_loss=0.431, pruned_loss=0.2081, over 4545.00 frames.], tot_loss[loss=0.4399, simple_loss=0.4782, pruned_loss=0.2009, over 966071.33 frames.], batch size: 10, lr: 1.95e-04
2022-05-27 22:07:52,255 INFO [train.py:761] (5/8) Epoch 3, batch 6550, loss[loss=0.4474, simple_loss=0.4853, pruned_loss=0.2048, over 4806.00 frames.], tot_loss[loss=0.4362, simple_loss=0.4755, pruned_loss=0.1985, over 966669.98 frames.], batch size: 12, lr: 1.96e-04
2022-05-27 22:08:30,797 INFO [train.py:761] (5/8) Epoch 3, batch 6600, loss[loss=0.3666, simple_loss=0.4281, pruned_loss=0.1526, over 4927.00 frames.], tot_loss[loss=0.4367, simple_loss=0.4753, pruned_loss=0.199, over 966012.13 frames.], batch size: 13, lr: 1.96e-04
2022-05-27 22:09:08,829 INFO [train.py:761] (5/8) Epoch 3, batch 6650, loss[loss=0.5144, simple_loss=0.5271, pruned_loss=0.2508, over 4936.00 frames.], tot_loss[loss=0.4395, simple_loss=0.4774, pruned_loss=0.2008, over 966264.42 frames.], batch size: 47, lr: 1.97e-04
2022-05-27 22:09:46,823 INFO [train.py:761] (5/8) Epoch 3, batch 6700, loss[loss=0.5122, simple_loss=0.5408, pruned_loss=0.2418, over 4959.00 frames.], tot_loss[loss=0.4405, simple_loss=0.4778, pruned_loss=0.2016, over 967053.84 frames.], batch size: 16, lr: 1.97e-04
2022-05-27 22:10:42,598 INFO [train.py:761] (5/8) Epoch 4, batch 0, loss[loss=0.3679, simple_loss=0.4294, pruned_loss=0.1532, over 4582.00 frames.], tot_loss[loss=0.3679, simple_loss=0.4294, pruned_loss=0.1532, over 4582.00 frames.], batch size: 10, lr: 1.98e-04
2022-05-27 22:11:20,593 INFO [train.py:761] (5/8) Epoch 4, batch 50, loss[loss=0.3813, simple_loss=0.4491, pruned_loss=0.1567, over 4931.00 frames.], tot_loss[loss=0.3783, simple_loss=0.4435, pruned_loss=0.1566, over 216424.07 frames.], batch size: 13, lr: 1.98e-04
2022-05-27 22:11:58,584 INFO [train.py:761] (5/8) Epoch 4, batch 100, loss[loss=0.4404, simple_loss=0.5244, pruned_loss=0.1782, over 4842.00 frames.], tot_loss[loss=0.3777, simple_loss=0.4441, pruned_loss=0.1556, over 382085.11 frames.], batch size: 17, lr: 1.99e-04
2022-05-27 22:12:36,338 INFO [train.py:761] (5/8) Epoch 4, batch 150, loss[loss=0.4124, simple_loss=0.4803, pruned_loss=0.1723, over 4823.00 frames.], tot_loss[loss=0.385, simple_loss=0.4515, pruned_loss=0.1593, over 512012.64 frames.], batch size: 18, lr: 1.99e-04
2022-05-27 22:13:14,602 INFO [train.py:761] (5/8) Epoch 4, batch 200, loss[loss=0.3823, simple_loss=0.4648, pruned_loss=0.1499, over 4785.00 frames.], tot_loss[loss=0.3779, simple_loss=0.4468, pruned_loss=0.1545, over 612102.18 frames.], batch size: 15, lr: 2.00e-04
2022-05-27 22:13:51,924 INFO [train.py:761] (5/8) Epoch 4, batch 250, loss[loss=0.3225, simple_loss=0.3945, pruned_loss=0.1252, over 4837.00 frames.], tot_loss[loss=0.376, simple_loss=0.4449, pruned_loss=0.1536, over 691540.33 frames.], batch size: 11, lr: 2.00e-04
2022-05-27 22:14:29,412 INFO [train.py:761] (5/8) Epoch 4, batch 300, loss[loss=0.348, simple_loss=0.4339, pruned_loss=0.1311, over 4964.00 frames.], tot_loss[loss=0.3764, simple_loss=0.4463, pruned_loss=0.1533, over 751700.84 frames.], batch size: 16, lr: 2.01e-04
2022-05-27 22:15:07,360 INFO [train.py:761] (5/8) Epoch 4, batch 350, loss[loss=0.3434, simple_loss=0.4347, pruned_loss=0.126, over 4795.00 frames.], tot_loss[loss=0.3748, simple_loss=0.4452, pruned_loss=0.1522, over 799745.25 frames.], batch size: 16, lr: 2.01e-04
2022-05-27 22:15:45,785 INFO [train.py:761] (5/8) Epoch 4, batch 400, loss[loss=0.3574, simple_loss=0.4382, pruned_loss=0.1383, over 4726.00 frames.], tot_loss[loss=0.3729, simple_loss=0.4439, pruned_loss=0.151, over 836631.64 frames.], batch size: 12, lr: 2.02e-04
2022-05-27 22:16:23,677 INFO [train.py:761] (5/8) Epoch 4, batch 450, loss[loss=0.3896, simple_loss=0.4659, pruned_loss=0.1566, over 4975.00 frames.], tot_loss[loss=0.3715, simple_loss=0.4429, pruned_loss=0.15, over 866128.90 frames.], batch size: 21, lr: 2.02e-04
2022-05-27 22:17:01,900 INFO [train.py:761] (5/8) Epoch 4, batch 500, loss[loss=0.3962, simple_loss=0.4661, pruned_loss=0.1632, over 4724.00 frames.], tot_loss[loss=0.3715, simple_loss=0.4428, pruned_loss=0.1501, over 888534.34 frames.], batch size: 14, lr: 2.03e-04
2022-05-27 22:17:39,557 INFO [train.py:761] (5/8) Epoch 4, batch 550, loss[loss=0.3603, simple_loss=0.4464, pruned_loss=0.1371, over 4869.00 frames.], tot_loss[loss=0.3703, simple_loss=0.4422, pruned_loss=0.1492, over 904920.62 frames.], batch size: 17, lr: 2.03e-04
2022-05-27 22:18:17,465 INFO [train.py:761] (5/8) Epoch 4, batch 600, loss[loss=0.3285, simple_loss=0.3906, pruned_loss=0.1332, over 4678.00 frames.], tot_loss[loss=0.3712, simple_loss=0.4421, pruned_loss=0.1502, over 918179.75 frames.], batch size: 12, lr: 2.04e-04
2022-05-27 22:18:55,258 INFO [train.py:761] (5/8) Epoch 4, batch 650, loss[loss=0.3413, simple_loss=0.4221, pruned_loss=0.1303, over 4877.00 frames.], tot_loss[loss=0.3689, simple_loss=0.4398, pruned_loss=0.149, over 929572.88 frames.], batch size: 15, lr: 2.04e-04
2022-05-27 22:19:33,217 INFO [train.py:761] (5/8) Epoch 4, batch 700, loss[loss=0.4753, simple_loss=0.5275, pruned_loss=0.2116, over 4766.00 frames.], tot_loss[loss=0.3712, simple_loss=0.4415, pruned_loss=0.1505, over 937425.02 frames.], batch size: 15, lr: 2.05e-04
2022-05-27 22:20:11,455 INFO [train.py:761] (5/8) Epoch 4, batch 750, loss[loss=0.3916, simple_loss=0.4534, pruned_loss=0.165, over 4958.00 frames.], tot_loss[loss=0.3765, simple_loss=0.4454, pruned_loss=0.1538, over 944542.48 frames.], batch size: 21, lr: 2.05e-04
2022-05-27 22:20:49,667 INFO [train.py:761] (5/8) Epoch 4, batch 800, loss[loss=0.4378, simple_loss=0.4945, pruned_loss=0.1905, over 4808.00 frames.], tot_loss[loss=0.3764, simple_loss=0.4444, pruned_loss=0.1542, over 948295.48 frames.], batch size: 16, lr: 2.06e-04
2022-05-27 22:21:27,593 INFO [train.py:761] (5/8) Epoch 4, batch 850, loss[loss=0.4084, simple_loss=0.4626, pruned_loss=0.1771, over 4797.00 frames.], tot_loss[loss=0.3802, simple_loss=0.4473, pruned_loss=0.1565, over 952537.50 frames.], batch size: 13, lr: 2.06e-04
2022-05-27 22:22:06,092 INFO [train.py:761] (5/8) Epoch 4, batch 900, loss[loss=0.3749, simple_loss=0.4204, pruned_loss=0.1647, over 4630.00 frames.], tot_loss[loss=0.3811, simple_loss=0.4474, pruned_loss=0.1574, over 956381.40 frames.], batch size: 11, lr: 2.06e-04
2022-05-27 22:22:43,736 INFO [train.py:761] (5/8) Epoch 4, batch 950, loss[loss=0.4601, simple_loss=0.5162, pruned_loss=0.202, over 4782.00 frames.], tot_loss[loss=0.3824, simple_loss=0.4482, pruned_loss=0.1583, over 958780.56 frames.], batch size: 15, lr: 2.07e-04
2022-05-27 22:23:21,592 INFO [train.py:761] (5/8) Epoch 4, batch 1000, loss[loss=0.4877, simple_loss=0.5341, pruned_loss=0.2207, over 4819.00 frames.], tot_loss[loss=0.3811, simple_loss=0.4466, pruned_loss=0.1578, over 960499.47 frames.], batch size: 20, lr: 2.07e-04
2022-05-27 22:23:59,371 INFO [train.py:761] (5/8) Epoch 4, batch 1050, loss[loss=0.2843, simple_loss=0.3623, pruned_loss=0.1032, over 4892.00 frames.], tot_loss[loss=0.3772, simple_loss=0.4436, pruned_loss=0.1554, over 961719.85 frames.], batch size: 12, lr: 2.08e-04
2022-05-27 22:24:37,534 INFO [train.py:761] (5/8) Epoch 4, batch 1100, loss[loss=0.3824, simple_loss=0.4457, pruned_loss=0.1596, over 4673.00 frames.], tot_loss[loss=0.3783, simple_loss=0.4447, pruned_loss=0.156, over 963262.70 frames.], batch size: 13, lr: 2.08e-04
2022-05-27 22:25:14,969 INFO [train.py:761] (5/8) Epoch 4, batch 1150, loss[loss=0.3785, simple_loss=0.4495, pruned_loss=0.1538, over 4894.00 frames.], tot_loss[loss=0.3783, simple_loss=0.4447, pruned_loss=0.156, over 964349.04 frames.], batch size: 17, lr: 2.09e-04
2022-05-27 22:25:52,543 INFO [train.py:761] (5/8) Epoch 4, batch 1200, loss[loss=0.3923, simple_loss=0.4527, pruned_loss=0.166, over 4848.00 frames.], tot_loss[loss=0.3764, simple_loss=0.4426, pruned_loss=0.1551, over 964898.89 frames.], batch size: 14, lr: 2.09e-04
2022-05-27 22:26:30,254 INFO [train.py:761] (5/8) Epoch 4, batch 1250, loss[loss=0.3578, simple_loss=0.4262, pruned_loss=0.1447, over 4646.00 frames.], tot_loss[loss=0.3729, simple_loss=0.44, pruned_loss=0.1529, over 965134.62 frames.], batch size: 11, lr: 2.10e-04
2022-05-27 22:27:08,918 INFO [train.py:761] (5/8) Epoch 4, batch 1300, loss[loss=0.3785, simple_loss=0.4431, pruned_loss=0.157, over 4994.00 frames.], tot_loss[loss=0.3757, simple_loss=0.4425, pruned_loss=0.1545, over 966166.16 frames.], batch size: 13, lr: 2.10e-04
2022-05-27 22:27:46,706 INFO [train.py:761] (5/8) Epoch 4, batch 1350, loss[loss=0.4174, simple_loss=0.4852, pruned_loss=0.1748, over 4769.00 frames.], tot_loss[loss=0.3756, simple_loss=0.4424, pruned_loss=0.1544, over 965748.04 frames.], batch size: 16, lr: 2.11e-04
2022-05-27 22:28:24,700 INFO [train.py:761] (5/8) Epoch 4, batch 1400, loss[loss=0.3513, simple_loss=0.4078, pruned_loss=0.1474, over 4965.00 frames.], tot_loss[loss=0.3761, simple_loss=0.4431, pruned_loss=0.1545, over 966273.70 frames.], batch size: 11, lr: 2.11e-04
2022-05-27 22:29:02,499 INFO [train.py:761] (5/8) Epoch 4, batch 1450, loss[loss=0.2926, simple_loss=0.3695, pruned_loss=0.1079, over 4982.00 frames.], tot_loss[loss=0.3762, simple_loss=0.4435, pruned_loss=0.1544, over 967168.82 frames.], batch size: 13, lr: 2.12e-04
2022-05-27 22:29:40,591 INFO [train.py:761] (5/8) Epoch 4, batch 1500, loss[loss=0.421, simple_loss=0.4748, pruned_loss=0.1837, over 4980.00 frames.], tot_loss[loss=0.3739, simple_loss=0.4413, pruned_loss=0.1533, over 966670.68 frames.], batch size: 14, lr: 2.12e-04
2022-05-27 22:30:18,467 INFO [train.py:761] (5/8) Epoch 4, batch 1550, loss[loss=0.3772, simple_loss=0.4567, pruned_loss=0.1488, over 4721.00 frames.], tot_loss[loss=0.3736, simple_loss=0.4411, pruned_loss=0.1531, over 967526.53 frames.], batch size: 13, lr: 2.13e-04
2022-05-27 22:30:56,762 INFO [train.py:761] (5/8) Epoch 4, batch 1600, loss[loss=0.4176, simple_loss=0.4675, pruned_loss=0.1838, over 4951.00 frames.], tot_loss[loss=0.3724, simple_loss=0.4398, pruned_loss=0.1525, over 967666.46 frames.], batch size: 16, lr: 2.13e-04
2022-05-27 22:31:34,844 INFO [train.py:761] (5/8) Epoch 4, batch 1650, loss[loss=0.3096, simple_loss=0.3848, pruned_loss=0.1172, over 4642.00 frames.], tot_loss[loss=0.3718, simple_loss=0.439, pruned_loss=0.1523, over 967098.76 frames.], batch size: 11, lr: 2.14e-04
2022-05-27 22:32:13,138 INFO [train.py:761] (5/8) Epoch 4, batch 1700, loss[loss=0.3498, simple_loss=0.414, pruned_loss=0.1427, over 4977.00 frames.], tot_loss[loss=0.371, simple_loss=0.4384, pruned_loss=0.1518, over 967116.41 frames.], batch size: 12, lr: 2.14e-04
2022-05-27 22:32:50,669 INFO [train.py:761] (5/8) Epoch 4, batch 1750, loss[loss=0.3387, simple_loss=0.4136, pruned_loss=0.1319, over 4891.00 frames.], tot_loss[loss=0.3721, simple_loss=0.4392, pruned_loss=0.1525, over 967664.67 frames.], batch size: 17, lr: 2.15e-04
2022-05-27 22:33:28,910 INFO [train.py:761] (5/8) Epoch 4, batch 1800, loss[loss=0.3329, simple_loss=0.4098, pruned_loss=0.128, over 4722.00 frames.], tot_loss[loss=0.3705, simple_loss=0.4383, pruned_loss=0.1513, over 967660.18 frames.], batch size: 13, lr: 2.15e-04
2022-05-27 22:34:07,047 INFO [train.py:761] (5/8) Epoch 4, batch 1850, loss[loss=0.3785, simple_loss=0.4261, pruned_loss=0.1654, over 4889.00 frames.], tot_loss[loss=0.3692, simple_loss=0.4381, pruned_loss=0.1501, over 967499.92 frames.], batch size: 15, lr: 2.16e-04
2022-05-27 22:34:44,675 INFO [train.py:761] (5/8) Epoch 4, batch 1900, loss[loss=0.4039, simple_loss=0.4825, pruned_loss=0.1626, over 4792.00 frames.], tot_loss[loss=0.3685, simple_loss=0.4385, pruned_loss=0.1493, over 967799.58 frames.], batch size: 14, lr: 2.16e-04
2022-05-27 22:35:22,372 INFO [train.py:761] (5/8) Epoch 4, batch 1950, loss[loss=0.3998, simple_loss=0.461, pruned_loss=0.1693, over 4788.00 frames.], tot_loss[loss=0.371, simple_loss=0.4406, pruned_loss=0.1507, over 967081.33 frames.], batch size: 15, lr: 2.17e-04
2022-05-27 22:35:59,971 INFO [train.py:761] (5/8) Epoch 4, batch 2000, loss[loss=0.3236, simple_loss=0.4025, pruned_loss=0.1223, over 4858.00 frames.], tot_loss[loss=0.372, simple_loss=0.4415, pruned_loss=0.1513, over 968129.03 frames.], batch size: 13, lr: 2.17e-04
2022-05-27 22:36:38,004 INFO [train.py:761] (5/8) Epoch 4, batch 2050, loss[loss=0.33, simple_loss=0.4234, pruned_loss=0.1183, over 4976.00 frames.], tot_loss[loss=0.3696, simple_loss=0.4395, pruned_loss=0.1499, over 968558.28 frames.], batch size: 14, lr: 2.18e-04
2022-05-27 22:37:16,052 INFO [train.py:761] (5/8) Epoch 4, batch 2100, loss[loss=0.3236, simple_loss=0.4181, pruned_loss=0.1145, over 4718.00 frames.], tot_loss[loss=0.3709, simple_loss=0.4408, pruned_loss=0.1505, over 968069.63 frames.], batch size: 14, lr: 2.18e-04
2022-05-27 22:37:54,381 INFO [train.py:761] (5/8) Epoch 4, batch 2150, loss[loss=0.3796, simple_loss=0.4613, pruned_loss=0.1489, over 4890.00 frames.], tot_loss[loss=0.3696, simple_loss=0.4397, pruned_loss=0.1497, over 967771.30 frames.], batch size: 17, lr: 2.19e-04
2022-05-27 22:38:32,792 INFO [train.py:761] (5/8) Epoch 4, batch 2200, loss[loss=0.3342, simple_loss=0.4019, pruned_loss=0.1332, over 4886.00 frames.], tot_loss[loss=0.3686, simple_loss=0.4389, pruned_loss=0.1492, over 967367.68 frames.], batch size: 12, lr: 2.19e-04
2022-05-27 22:39:10,539 INFO [train.py:761] (5/8) Epoch 4, batch 2250, loss[loss=0.3081, simple_loss=0.3792, pruned_loss=0.1185, over 4751.00 frames.], tot_loss[loss=0.3683, simple_loss=0.4381, pruned_loss=0.1492, over 968095.57 frames.], batch size: 11, lr: 2.20e-04
2022-05-27 22:39:48,370 INFO [train.py:761] (5/8) Epoch 4, batch 2300, loss[loss=0.3952, simple_loss=0.4864, pruned_loss=0.152, over 4783.00 frames.], tot_loss[loss=0.3677, simple_loss=0.4375, pruned_loss=0.1489, over 969914.75 frames.], batch size: 20, lr: 2.20e-04
2022-05-27 22:40:26,394 INFO [train.py:761] (5/8) Epoch 4, batch 2350, loss[loss=0.4123, simple_loss=0.4823, pruned_loss=0.1711, over 4798.00 frames.], tot_loss[loss=0.3649, simple_loss=0.4348, pruned_loss=0.1475, over 969626.58 frames.], batch size: 16, lr: 2.21e-04
2022-05-27 22:41:03,887 INFO [train.py:761] (5/8) Epoch 4, batch 2400, loss[loss=0.3835, simple_loss=0.4268, pruned_loss=0.1701, over 4835.00 frames.], tot_loss[loss=0.3612, simple_loss=0.4323, pruned_loss=0.145, over 969058.03 frames.], batch size: 11, lr: 2.21e-04
2022-05-27 22:41:41,536 INFO [train.py:761] (5/8) Epoch 4, batch 2450, loss[loss=0.375, simple_loss=0.4474, pruned_loss=0.1512, over 4978.00 frames.], tot_loss[loss=0.3609, simple_loss=0.4316, pruned_loss=0.1451, over 967946.13 frames.], batch size: 26, lr: 2.22e-04
2022-05-27 22:42:19,811 INFO [train.py:761] (5/8) Epoch 4, batch 2500, loss[loss=0.4311, simple_loss=0.462, pruned_loss=0.2001, over 4810.00 frames.], tot_loss[loss=0.3618, simple_loss=0.4319, pruned_loss=0.1458, over 968415.82 frames.], batch size: 11, lr: 2.22e-04
2022-05-27 22:42:57,377 INFO [train.py:761] (5/8) Epoch 4, batch 2550, loss[loss=0.4138, simple_loss=0.4847, pruned_loss=0.1715, over 4962.00 frames.], tot_loss[loss=0.364, simple_loss=0.4332, pruned_loss=0.1474, over 968452.38 frames.], batch size: 16, lr: 2.23e-04
2022-05-27 22:43:35,205 INFO [train.py:761] (5/8) Epoch 4, batch 2600, loss[loss=0.3937, simple_loss=0.466, pruned_loss=0.1607, over 4863.00 frames.], tot_loss[loss=0.3637, simple_loss=0.4337, pruned_loss=0.1469, over 968227.08 frames.], batch size: 17, lr: 2.23e-04
2022-05-27 22:44:13,134 INFO [train.py:761] (5/8) Epoch 4, batch 2650, loss[loss=0.3298, simple_loss=0.4048, pruned_loss=0.1274, over 4877.00 frames.], tot_loss[loss=0.3606, simple_loss=0.4309, pruned_loss=0.1451, over 967022.31 frames.], batch size: 15, lr: 2.24e-04
2022-05-27 22:44:50,899 INFO [train.py:761] (5/8) Epoch 4, batch 2700, loss[loss=0.2687, simple_loss=0.3523, pruned_loss=0.09257, over 4889.00 frames.], tot_loss[loss=0.3587, simple_loss=0.4296, pruned_loss=0.1439, over 966637.27 frames.], batch size: 12, lr: 2.24e-04
2022-05-27 22:45:28,173 INFO [train.py:761] (5/8) Epoch 4, batch 2750, loss[loss=0.3609, simple_loss=0.4377, pruned_loss=0.142, over 4893.00 frames.], tot_loss[loss=0.3567, simple_loss=0.4279, pruned_loss=0.1428, over 966281.48 frames.], batch size: 27, lr: 2.25e-04
2022-05-27 22:46:06,272 INFO [train.py:761] (5/8) Epoch 4, batch 2800, loss[loss=0.3128, simple_loss=0.386, pruned_loss=0.1198, over 4926.00 frames.], tot_loss[loss=0.3556, simple_loss=0.4265, pruned_loss=0.1423, over 965962.84 frames.], batch size: 13, lr: 2.25e-04
2022-05-27 22:46:44,442 INFO [train.py:761] (5/8) Epoch 4, batch 2850, loss[loss=0.347, simple_loss=0.4315, pruned_loss=0.1313, over 4674.00 frames.], tot_loss[loss=0.356, simple_loss=0.4269, pruned_loss=0.1426, over 965478.32 frames.], batch size: 13, lr: 2.26e-04
2022-05-27 22:47:22,516 INFO [train.py:761] (5/8) Epoch 4, batch 2900, loss[loss=0.3307, simple_loss=0.4216, pruned_loss=0.1199, over 4850.00 frames.], tot_loss[loss=0.3577, simple_loss=0.4284, pruned_loss=0.1436, over 965914.85 frames.], batch size: 14, lr: 2.26e-04
2022-05-27 22:48:00,377 INFO [train.py:761] (5/8) Epoch 4, batch 2950, loss[loss=0.3486, simple_loss=0.4121, pruned_loss=0.1425, over 4733.00 frames.], tot_loss[loss=0.36, simple_loss=0.431, pruned_loss=0.1445, over 966167.51 frames.], batch size: 12, lr: 2.27e-04
2022-05-27 22:48:38,892 INFO [train.py:761] (5/8) Epoch 4, batch 3000, loss[loss=0.3985, simple_loss=0.4767, pruned_loss=0.1601, over 4890.00 frames.], tot_loss[loss=0.3623, simple_loss=0.4324, pruned_loss=0.1461, over 966352.07 frames.], batch size: 17, lr: 2.27e-04
2022-05-27 22:48:38,893 INFO [train.py:781] (5/8) Computing validation loss
2022-05-27 22:48:48,753 INFO [train.py:790] (5/8) Epoch 4, validation: loss=0.3056, simple_loss=0.407, pruned_loss=0.1021, over 944034.00 frames.
2022-05-27 22:49:26,327 INFO [train.py:761] (5/8) Epoch 4, batch 3050, loss[loss=0.3446, simple_loss=0.4135, pruned_loss=0.1379, over 4850.00 frames.], tot_loss[loss=0.3625, simple_loss=0.4328, pruned_loss=0.1462, over 966157.38 frames.], batch size: 13, lr: 2.27e-04
2022-05-27 22:50:04,538 INFO [train.py:761] (5/8) Epoch 4, batch 3100, loss[loss=0.3803, simple_loss=0.4448, pruned_loss=0.1579, over 4830.00 frames.], tot_loss[loss=0.3634, simple_loss=0.432, pruned_loss=0.1474, over 964620.66 frames.], batch size: 18, lr: 2.28e-04
2022-05-27 22:50:42,182 INFO [train.py:761] (5/8) Epoch 4, batch 3150, loss[loss=0.3658, simple_loss=0.4263, pruned_loss=0.1527, over 4785.00 frames.], tot_loss[loss=0.3694, simple_loss=0.4356, pruned_loss=0.1516, over 964670.76 frames.], batch size: 13, lr: 2.28e-04
2022-05-27 22:51:20,511 INFO [train.py:761] (5/8) Epoch 4, batch 3200, loss[loss=0.3932, simple_loss=0.4302, pruned_loss=0.1781, over 4728.00 frames.], tot_loss[loss=0.3745, simple_loss=0.4377, pruned_loss=0.1556, over 965336.31 frames.], batch size: 11, lr: 2.29e-04
2022-05-27 22:51:58,194 INFO [train.py:761] (5/8) Epoch 4, batch 3250, loss[loss=0.3419, simple_loss=0.4045, pruned_loss=0.1396, over 4804.00 frames.], tot_loss[loss=0.3792, simple_loss=0.4399, pruned_loss=0.1593, over 965385.48 frames.], batch size: 12, lr: 2.29e-04
2022-05-27 22:52:36,532 INFO [train.py:761] (5/8) Epoch 4, batch 3300, loss[loss=0.4759, simple_loss=0.5111, pruned_loss=0.2203, over 4969.00 frames.], tot_loss[loss=0.3826, simple_loss=0.4413, pruned_loss=0.1619, over 966069.44 frames.], batch size: 48, lr: 2.30e-04
2022-05-27 22:53:14,117 INFO [train.py:761] (5/8) Epoch 4, batch 3350, loss[loss=0.3996, simple_loss=0.4181, pruned_loss=0.1906, over 4824.00 frames.], tot_loss[loss=0.3896, simple_loss=0.4447, pruned_loss=0.1673, over 966931.95 frames.], batch size: 11, lr: 2.30e-04
2022-05-27 22:53:51,897 INFO [train.py:761] (5/8) Epoch 4, batch 3400, loss[loss=0.4174, simple_loss=0.471, pruned_loss=0.1819, over 4675.00 frames.], tot_loss[loss=0.3915, simple_loss=0.445, pruned_loss=0.169, over 967206.44 frames.], batch size: 13, lr: 2.31e-04
2022-05-27 22:54:30,125 INFO [train.py:761] (5/8) Epoch 4, batch 3450, loss[loss=0.3801, simple_loss=0.4435, pruned_loss=0.1584, over 4791.00 frames.], tot_loss[loss=0.3938, simple_loss=0.446, pruned_loss=0.1708, over 967111.33 frames.], batch size: 14, lr: 2.31e-04
2022-05-27 22:55:07,901 INFO [train.py:761] (5/8) Epoch 4, batch 3500, loss[loss=0.4468, simple_loss=0.4846, pruned_loss=0.2045, over 4723.00 frames.], tot_loss[loss=0.3963, simple_loss=0.4465, pruned_loss=0.173, over 966007.69 frames.], batch size: 14, lr: 2.32e-04
2022-05-27 22:55:45,612 INFO [train.py:761] (5/8) Epoch 4, batch 3550, loss[loss=0.3923, simple_loss=0.4381, pruned_loss=0.1733, over 4916.00 frames.], tot_loss[loss=0.3988, simple_loss=0.4476, pruned_loss=0.175, over 966068.03 frames.], batch size: 13, lr: 2.32e-04
2022-05-27 22:56:24,012 INFO [train.py:761] (5/8) Epoch 4, batch 3600, loss[loss=0.3746, simple_loss=0.4347, pruned_loss=0.1572, over 4813.00 frames.], tot_loss[loss=0.4017, simple_loss=0.4483, pruned_loss=0.1775, over 965219.57 frames.], batch size: 18, lr: 2.33e-04
2022-05-27 22:57:02,427 INFO [train.py:761] (5/8) Epoch 4, batch 3650, loss[loss=0.4561, simple_loss=0.5021, pruned_loss=0.2051, over 4928.00 frames.], tot_loss[loss=0.4037, simple_loss=0.4494, pruned_loss=0.179, over 964777.84 frames.], batch size: 21, lr: 2.33e-04
2022-05-27 22:57:40,677 INFO [train.py:761] (5/8) Epoch 4, batch 3700, loss[loss=0.4249, simple_loss=0.4809, pruned_loss=0.1844, over 4791.00 frames.], tot_loss[loss=0.4079, simple_loss=0.4526, pruned_loss=0.1816, over 964536.02 frames.], batch size: 16, lr: 2.34e-04
2022-05-27 22:58:18,819 INFO [train.py:761] (5/8) Epoch 4, batch 3750, loss[loss=0.39, simple_loss=0.4411, pruned_loss=0.1694, over 4915.00 frames.], tot_loss[loss=0.4092, simple_loss=0.4535, pruned_loss=0.1824, over 965478.41 frames.], batch size: 13, lr: 2.34e-04
2022-05-27 22:59:00,411 INFO [train.py:761] (5/8) Epoch 4, batch 3800, loss[loss=0.4264, simple_loss=0.4477, pruned_loss=0.2025, over 4726.00 frames.], tot_loss[loss=0.4076, simple_loss=0.4521, pruned_loss=0.1816, over 965441.51 frames.], batch size: 11, lr: 2.35e-04
2022-05-27 22:59:38,539 INFO [train.py:761] (5/8) Epoch 4, batch 3850, loss[loss=0.3954, simple_loss=0.4353, pruned_loss=0.1777, over 4928.00 frames.], tot_loss[loss=0.4077, simple_loss=0.4518, pruned_loss=0.1818, over 965648.80 frames.], batch size: 13, lr: 2.35e-04
2022-05-27 23:00:17,280 INFO [train.py:761] (5/8) Epoch 4, batch 3900, loss[loss=0.4028, simple_loss=0.4496, pruned_loss=0.1779, over 4776.00 frames.], tot_loss[loss=0.4062, simple_loss=0.4502, pruned_loss=0.1811, over 966492.77 frames.], batch size: 20, lr: 2.36e-04
2022-05-27 23:00:55,027 INFO [train.py:761] (5/8) Epoch 4, batch 3950, loss[loss=0.3907, simple_loss=0.4385, pruned_loss=0.1714, over 4795.00 frames.], tot_loss[loss=0.4092, simple_loss=0.4519, pruned_loss=0.1833, over 967285.29 frames.], batch size: 16, lr: 2.36e-04
2022-05-27 23:01:33,524 INFO [train.py:761] (5/8) Epoch 4, batch 4000, loss[loss=0.3684, simple_loss=0.4226, pruned_loss=0.1571, over 4910.00 frames.], tot_loss[loss=0.4044, simple_loss=0.4477, pruned_loss=0.1805, over 966242.87 frames.], batch size: 17, lr: 2.37e-04
2022-05-27 23:02:11,697 INFO [train.py:761] (5/8) Epoch 4, batch 4050, loss[loss=0.3711, simple_loss=0.4155, pruned_loss=0.1634, over 4902.00 frames.], tot_loss[loss=0.4061, simple_loss=0.449, pruned_loss=0.1817, over 965730.52 frames.], batch size: 12, lr: 2.37e-04
2022-05-27 23:02:49,773 INFO [train.py:761] (5/8) Epoch 4, batch 4100, loss[loss=0.4001, simple_loss=0.4475, pruned_loss=0.1764, over 4739.00 frames.], tot_loss[loss=0.405, simple_loss=0.4482, pruned_loss=0.1809, over 965064.78 frames.], batch size: 11, lr: 2.38e-04
2022-05-27 23:03:27,904 INFO [train.py:761] (5/8) Epoch 4, batch 4150, loss[loss=0.4788, simple_loss=0.4768, pruned_loss=0.2404, over 4789.00 frames.], tot_loss[loss=0.4058, simple_loss=0.4484, pruned_loss=0.1816, over 965578.75 frames.], batch size: 13, lr: 2.38e-04
2022-05-27 23:04:05,904 INFO [train.py:761] (5/8) Epoch 4, batch 4200, loss[loss=0.3293, simple_loss=0.3796, pruned_loss=0.1395, over 4820.00 frames.], tot_loss[loss=0.4046, simple_loss=0.4477, pruned_loss=0.1807, over 964849.49 frames.], batch size: 11, lr: 2.39e-04
2022-05-27 23:04:44,211 INFO [train.py:761] (5/8) Epoch 4, batch 4250, loss[loss=0.332, simple_loss=0.3932, pruned_loss=0.1354, over 4791.00 frames.], tot_loss[loss=0.4024, simple_loss=0.4459, pruned_loss=0.1795, over 964580.72 frames.], batch size: 13, lr: 2.39e-04
2022-05-27 23:05:22,976 INFO [train.py:761] (5/8) Epoch 4, batch 4300, loss[loss=0.3101, simple_loss=0.3661, pruned_loss=0.1271, over 4890.00 frames.], tot_loss[loss=0.4023, simple_loss=0.4464, pruned_loss=0.1791, over 965396.69 frames.], batch size: 12, lr: 2.40e-04
2022-05-27 23:06:01,112 INFO [train.py:761] (5/8) Epoch 4, batch 4350, loss[loss=0.4056, simple_loss=0.4393, pruned_loss=0.186, over 4803.00 frames.], tot_loss[loss=0.4023, simple_loss=0.4472, pruned_loss=0.1787, over 966040.78 frames.], batch size: 12, lr: 2.40e-04
2022-05-27 23:06:39,062 INFO [train.py:761] (5/8) Epoch 4, batch 4400, loss[loss=0.3589, simple_loss=0.4172, pruned_loss=0.1504, over 4808.00 frames.], tot_loss[loss=0.4029, simple_loss=0.4478, pruned_loss=0.179, over 965237.69 frames.], batch size: 12, lr: 2.41e-04
2022-05-27 23:07:16,905 INFO [train.py:761] (5/8) Epoch 4, batch 4450, loss[loss=0.3836, simple_loss=0.4372, pruned_loss=0.165, over 4675.00 frames.], tot_loss[loss=0.4042, simple_loss=0.449, pruned_loss=0.1797, over 964712.03 frames.], batch size: 13, lr: 2.41e-04
2022-05-27 23:07:55,016 INFO [train.py:761] (5/8) Epoch 4, batch 4500, loss[loss=0.3649, simple_loss=0.4473, pruned_loss=0.1413, over 4849.00 frames.], tot_loss[loss=0.4038, simple_loss=0.4492, pruned_loss=0.1791, over 966158.58 frames.], batch size: 14, lr: 2.42e-04
2022-05-27 23:08:32,960 INFO [train.py:761] (5/8) Epoch 4, batch 4550, loss[loss=0.4237, simple_loss=0.4678, pruned_loss=0.1898, over 4901.00 frames.], tot_loss[loss=0.4018, simple_loss=0.4474, pruned_loss=0.1781, over 965907.25 frames.], batch size: 44, lr: 2.42e-04
2022-05-27 23:09:11,431 INFO [train.py:761] (5/8) Epoch 4, batch 4600, loss[loss=0.4694, simple_loss=0.4987, pruned_loss=0.22, over 4919.00 frames.], tot_loss[loss=0.402, simple_loss=0.4471, pruned_loss=0.1785, over 965860.96 frames.], batch size: 21, lr: 2.43e-04
2022-05-27 23:09:49,868 INFO [train.py:761] (5/8) Epoch 4, batch 4650, loss[loss=0.3431, simple_loss=0.411, pruned_loss=0.1376, over 4573.00 frames.], tot_loss[loss=0.4032, simple_loss=0.4485, pruned_loss=0.1789, over 965888.17 frames.], batch size: 10, lr: 2.43e-04
2022-05-27 23:10:28,092 INFO [train.py:761] (5/8) Epoch 4, batch 4700, loss[loss=0.4068, simple_loss=0.4581, pruned_loss=0.1778, over 4675.00 frames.], tot_loss[loss=0.4028, simple_loss=0.448, pruned_loss=0.1788, over 966389.94 frames.], batch size: 13, lr: 2.44e-04
2022-05-27 23:11:06,108 INFO [train.py:761] (5/8) Epoch 4, batch 4750, loss[loss=0.4902, simple_loss=0.5057, pruned_loss=0.2373, over 4788.00 frames.], tot_loss[loss=0.4036, simple_loss=0.4483, pruned_loss=0.1794, over 966970.59 frames.], batch size: 14, lr: 2.44e-04
2022-05-27 23:11:44,949 INFO [train.py:761] (5/8) Epoch 4, batch 4800, loss[loss=0.3965, simple_loss=0.4454, pruned_loss=0.1738, over 4966.00 frames.], tot_loss[loss=0.4041, simple_loss=0.4478, pruned_loss=0.1802, over 966776.46 frames.], batch size: 16, lr: 2.45e-04
2022-05-27 23:12:22,825 INFO [train.py:761] (5/8) Epoch 4, batch 4850, loss[loss=0.3089, simple_loss=0.3882, pruned_loss=0.1148, over 4736.00 frames.], tot_loss[loss=0.4024, simple_loss=0.447, pruned_loss=0.1789, over 967622.46 frames.], batch size: 12, lr: 2.45e-04
2022-05-27 23:13:01,497 INFO [train.py:761] (5/8) Epoch 4, batch 4900, loss[loss=0.3421, simple_loss=0.4176, pruned_loss=0.1333, over 4822.00 frames.], tot_loss[loss=0.4019, simple_loss=0.4472, pruned_loss=0.1783, over 966399.88 frames.], batch size: 20, lr: 2.46e-04
2022-05-27 23:13:39,488 INFO [train.py:761] (5/8) Epoch 4, batch 4950, loss[loss=0.4528, simple_loss=0.4927, pruned_loss=0.2065, over 4951.00 frames.], tot_loss[loss=0.4018, simple_loss=0.447, pruned_loss=0.1783, over 966797.83 frames.], batch size: 16, lr: 2.46e-04
2022-05-27 23:14:18,104 INFO [train.py:761] (5/8) Epoch 4, batch 5000, loss[loss=0.312, simple_loss=0.377, pruned_loss=0.1235, over 4977.00 frames.], tot_loss[loss=0.4013, simple_loss=0.4469, pruned_loss=0.1778, over 967482.47 frames.], batch size: 12, lr: 2.47e-04
2022-05-27 23:14:56,021 INFO [train.py:761] (5/8) Epoch 4, batch 5050, loss[loss=0.4393, simple_loss=0.4808, pruned_loss=0.1989, over 4949.00 frames.], tot_loss[loss=0.3999, simple_loss=0.446, pruned_loss=0.1769, over 967583.38 frames.], batch size: 16, lr: 2.47e-04
2022-05-27 23:15:34,280 INFO [train.py:761] (5/8) Epoch 4, batch 5100, loss[loss=0.401, simple_loss=0.4067, pruned_loss=0.1976, over 4811.00 frames.], tot_loss[loss=0.3994, simple_loss=0.4452, pruned_loss=0.1768, over 968512.73 frames.], batch size: 12, lr: 2.47e-04
2022-05-27 23:16:12,464 INFO [train.py:761] (5/8) Epoch 4, batch 5150, loss[loss=0.3483, simple_loss=0.3956, pruned_loss=0.1505, over 4816.00 frames.], tot_loss[loss=0.3988, simple_loss=0.4448, pruned_loss=0.1764, over 967467.04 frames.], batch size: 12, lr: 2.48e-04
2022-05-27 23:16:50,063 INFO [train.py:761] (5/8) Epoch 4, batch 5200, loss[loss=0.4424, simple_loss=0.4807, pruned_loss=0.202, over 4860.00 frames.], tot_loss[loss=0.399, simple_loss=0.4455, pruned_loss=0.1763, over 967361.62 frames.], batch size: 49, lr: 2.48e-04
2022-05-27 23:17:28,119 INFO [train.py:761] (5/8) Epoch 4, batch 5250, loss[loss=0.4399, simple_loss=0.4755, pruned_loss=0.2022, over 4893.00 frames.], tot_loss[loss=0.3973, simple_loss=0.444, pruned_loss=0.1753, over 966264.34 frames.], batch size: 15, lr: 2.49e-04
2022-05-27 23:18:06,239 INFO [train.py:761] (5/8) Epoch 4, batch 5300, loss[loss=0.4019, simple_loss=0.4432, pruned_loss=0.1803, over 4776.00 frames.], tot_loss[loss=0.3949, simple_loss=0.4422, pruned_loss=0.1738, over 965275.44 frames.], batch size: 13, lr: 2.49e-04
2022-05-27 23:18:44,506 INFO [train.py:761] (5/8) Epoch 4, batch 5350, loss[loss=0.4742, simple_loss=0.5015, pruned_loss=0.2235, over 4965.00 frames.], tot_loss[loss=0.3946, simple_loss=0.442, pruned_loss=0.1736, over 966609.67 frames.], batch size: 15, lr: 2.50e-04
2022-05-27 23:19:22,930 INFO [train.py:761] (5/8) Epoch 4, batch 5400, loss[loss=0.4266, simple_loss=0.472, pruned_loss=0.1906, over 4877.00 frames.], tot_loss[loss=0.3931, simple_loss=0.441, pruned_loss=0.1726, over 965554.29 frames.], batch size: 15, lr: 2.50e-04
2022-05-27 23:20:01,256 INFO [train.py:761] (5/8) Epoch 4, batch 5450, loss[loss=0.4343, simple_loss=0.4661, pruned_loss=0.2012, over 4788.00 frames.], tot_loss[loss=0.3929, simple_loss=0.4414, pruned_loss=0.1722, over 965415.22 frames.], batch size: 14, lr: 2.51e-04
2022-05-27 23:20:39,597 INFO [train.py:761] (5/8) Epoch 4, batch 5500, loss[loss=0.4396, simple_loss=0.4738, pruned_loss=0.2026, over 4870.00 frames.], tot_loss[loss=0.3925, simple_loss=0.4405, pruned_loss=0.1723, over 966423.64 frames.], batch size: 15, lr: 2.51e-04
2022-05-27 23:21:17,135 INFO [train.py:761] (5/8) Epoch 4, batch 5550, loss[loss=0.4031, simple_loss=0.4481, pruned_loss=0.1791, over 4743.00 frames.], tot_loss[loss=0.3897, simple_loss=0.4382, pruned_loss=0.1706, over 967289.25 frames.], batch size: 12, lr: 2.52e-04
2022-05-27 23:21:55,571 INFO [train.py:761] (5/8) Epoch 4, batch 5600, loss[loss=0.4312, simple_loss=0.4881, pruned_loss=0.1872, over 4872.00 frames.], tot_loss[loss=0.3863, simple_loss=0.4355, pruned_loss=0.1686, over 967607.69 frames.], batch size: 26, lr: 2.52e-04
2022-05-27 23:22:33,841 INFO [train.py:761] (5/8) Epoch 4, batch 5650, loss[loss=0.4608, simple_loss=0.4782, pruned_loss=0.2217, over 4729.00 frames.], tot_loss[loss=0.3892, simple_loss=0.4384, pruned_loss=0.17, over 967979.86 frames.], batch size: 11, lr: 2.53e-04
2022-05-27 23:23:12,284 INFO [train.py:761] (5/8) Epoch 4, batch 5700, loss[loss=0.4269, simple_loss=0.4673, pruned_loss=0.1932, over 4830.00 frames.], tot_loss[loss=0.3902, simple_loss=0.4389, pruned_loss=0.1708, over 966951.88 frames.], batch size: 25, lr: 2.53e-04
2022-05-27 23:23:50,275 INFO [train.py:761] (5/8) Epoch 4, batch 5750, loss[loss=0.481, simple_loss=0.5189, pruned_loss=0.2215, over 4971.00 frames.], tot_loss[loss=0.3914, simple_loss=0.4397, pruned_loss=0.1716, over 967244.37 frames.], batch size: 15, lr: 2.54e-04
2022-05-27 23:24:28,916 INFO [train.py:761] (5/8) Epoch 4, batch 5800, loss[loss=0.3433, simple_loss=0.407, pruned_loss=0.1398, over 4834.00 frames.], tot_loss[loss=0.3926, simple_loss=0.4414, pruned_loss=0.1719, over 967097.54 frames.], batch size: 11, lr: 2.54e-04
2022-05-27 23:25:06,917 INFO [train.py:761] (5/8) Epoch 4, batch 5850, loss[loss=0.3548, simple_loss=0.4266, pruned_loss=0.1415, over 4977.00 frames.], tot_loss[loss=0.3942, simple_loss=0.4428, pruned_loss=0.1728, over 968043.52 frames.], batch size: 14, lr: 2.55e-04
2022-05-27 23:25:45,416 INFO [train.py:761] (5/8) Epoch 4, batch 5900, loss[loss=0.502, simple_loss=0.528, pruned_loss=0.238, over 4856.00 frames.], tot_loss[loss=0.3959, simple_loss=0.4441, pruned_loss=0.1738, over 967523.42 frames.], batch size: 18, lr: 2.55e-04
2022-05-27 23:26:23,132 INFO [train.py:761] (5/8) Epoch 4, batch 5950, loss[loss=0.4008, simple_loss=0.433, pruned_loss=0.1843, over 4713.00 frames.], tot_loss[loss=0.3948, simple_loss=0.4435, pruned_loss=0.1731, over 966636.47 frames.], batch size: 14, lr: 2.56e-04
2022-05-27 23:27:08,427 INFO [train.py:761] (5/8) Epoch 4, batch 6000, loss[loss=0.444, simple_loss=0.4914, pruned_loss=0.1983, over 4669.00 frames.], tot_loss[loss=0.3951, simple_loss=0.4434, pruned_loss=0.1733, over 967364.54 frames.], batch size: 13, lr: 2.56e-04
2022-05-27 23:27:08,428 INFO [train.py:781] (5/8) Computing validation loss
2022-05-27 23:27:18,235 INFO [train.py:790] (5/8) Epoch 4, validation: loss=0.283, simple_loss=0.3914, pruned_loss=0.08727, over 944034.00 frames.
2022-05-27 23:27:56,290 INFO [train.py:761] (5/8) Epoch 4, batch 6050, loss[loss=0.4394, simple_loss=0.4797, pruned_loss=0.1996, over 4858.00 frames.], tot_loss[loss=0.3945, simple_loss=0.4432, pruned_loss=0.1729, over 968294.16 frames.], batch size: 17, lr: 2.57e-04
2022-05-27 23:28:34,759 INFO [train.py:761] (5/8) Epoch 4, batch 6100, loss[loss=0.3628, simple_loss=0.4304, pruned_loss=0.1476, over 4819.00 frames.], tot_loss[loss=0.3943, simple_loss=0.4436, pruned_loss=0.1725, over 968024.90 frames.], batch size: 16, lr: 2.57e-04
2022-05-27 23:29:13,494 INFO [train.py:761] (5/8) Epoch 4, batch 6150, loss[loss=0.4749, simple_loss=0.5172, pruned_loss=0.2163, over 4818.00 frames.], tot_loss[loss=0.3943, simple_loss=0.4431, pruned_loss=0.1728, over 967951.20 frames.], batch size: 18, lr: 2.58e-04
2022-05-27 23:29:51,892 INFO [train.py:761] (5/8) Epoch 4, batch 6200, loss[loss=0.2669, simple_loss=0.3478, pruned_loss=0.09302, over 4845.00 frames.], tot_loss[loss=0.3957, simple_loss=0.4444, pruned_loss=0.1735, over 968239.28 frames.], batch size: 13, lr: 2.58e-04
2022-05-27 23:30:29,719 INFO [train.py:761] (5/8) Epoch 4, batch 6250, loss[loss=0.4512, simple_loss=0.4395, pruned_loss=0.2314, over 4648.00 frames.], tot_loss[loss=0.3922, simple_loss=0.4418, pruned_loss=0.1713, over 967132.37 frames.], batch size: 11, lr: 2.59e-04
2022-05-27 23:31:08,493 INFO [train.py:761] (5/8) Epoch 4, batch 6300, loss[loss=0.3513, simple_loss=0.4111, pruned_loss=0.1458, over 4914.00 frames.], tot_loss[loss=0.3929, simple_loss=0.4421, pruned_loss=0.1718, over 966481.42 frames.], batch size: 14, lr: 2.59e-04
2022-05-27 23:31:46,565 INFO [train.py:761] (5/8) Epoch 4, batch 6350, loss[loss=0.4131, simple_loss=0.4589, pruned_loss=0.1837, over 4982.00 frames.], tot_loss[loss=0.3903, simple_loss=0.4405, pruned_loss=0.17, over 966019.44 frames.], batch size: 21, lr: 2.60e-04
2022-05-27 23:32:25,440 INFO [train.py:761] (5/8) Epoch 4, batch 6400, loss[loss=0.3849, simple_loss=0.4161, pruned_loss=0.1769, over 4723.00 frames.], tot_loss[loss=0.3913, simple_loss=0.4409, pruned_loss=0.1708, over 966073.36 frames.], batch size: 11, lr: 2.60e-04
2022-05-27 23:33:03,404 INFO [train.py:761] (5/8) Epoch 4, batch 6450, loss[loss=0.5189, simple_loss=0.5248, pruned_loss=0.2565, over 4962.00 frames.], tot_loss[loss=0.3912, simple_loss=0.4408, pruned_loss=0.1708, over 966598.57 frames.], batch size: 26, lr: 2.61e-04
2022-05-27 23:33:42,055 INFO [train.py:761] (5/8) Epoch 4, batch 6500, loss[loss=0.3928, simple_loss=0.4457, pruned_loss=0.1699, over 4793.00 frames.], tot_loss[loss=0.392, simple_loss=0.4411, pruned_loss=0.1714, over 966434.64 frames.], batch size: 20, lr: 2.61e-04
2022-05-27 23:34:19,726 INFO [train.py:761] (5/8) Epoch 4, batch 6550, loss[loss=0.3189, simple_loss=0.3948, pruned_loss=0.1215, over 4901.00 frames.], tot_loss[loss=0.3906, simple_loss=0.4398, pruned_loss=0.1707, over 966991.94 frames.], batch size: 14, lr: 2.62e-04
2022-05-27 23:34:58,095 INFO [train.py:761] (5/8) Epoch 4, batch 6600, loss[loss=0.3047, simple_loss=0.3647, pruned_loss=0.1223, over 4988.00 frames.], tot_loss[loss=0.3861, simple_loss=0.437, pruned_loss=0.1676, over 967465.72 frames.], batch size: 12, lr: 2.62e-04
2022-05-27 23:35:36,183 INFO [train.py:761] (5/8) Epoch 4, batch 6650, loss[loss=0.3452, simple_loss=0.4, pruned_loss=0.1452, over 4974.00 frames.], tot_loss[loss=0.3865, simple_loss=0.4374, pruned_loss=0.1678, over 967383.90 frames.], batch size: 12, lr: 2.63e-04
2022-05-27 23:36:13,987 INFO [train.py:761] (5/8) Epoch 4, batch 6700, loss[loss=0.398, simple_loss=0.4523, pruned_loss=0.1719, over 4846.00 frames.], tot_loss[loss=0.3865, simple_loss=0.4374, pruned_loss=0.1678, over 966568.79 frames.], batch size: 14, lr: 2.63e-04
2022-05-27 23:37:10,704 INFO [train.py:761] (5/8) Epoch 5, batch 0, loss[loss=0.3247, simple_loss=0.401, pruned_loss=0.1242, over 4674.00 frames.], tot_loss[loss=0.3247, simple_loss=0.401, pruned_loss=0.1242, over 4674.00 frames.], batch size: 13, lr: 2.64e-04
2022-05-27 23:38:02,512 INFO [train.py:761] (5/8) Epoch 5, batch 50, loss[loss=0.2926, simple_loss=0.3609, pruned_loss=0.1121, over 4979.00 frames.], tot_loss[loss=0.3467, simple_loss=0.4214, pruned_loss=0.136, over 218641.73 frames.], batch size: 12, lr: 2.64e-04
2022-05-27 23:39:02,129 INFO [train.py:761] (5/8) Epoch 5, batch 100, loss[loss=0.3546, simple_loss=0.4303, pruned_loss=0.1394, over 4674.00 frames.], tot_loss[loss=0.339, simple_loss=0.4132, pruned_loss=0.1324, over 384214.69 frames.], batch size: 13, lr: 2.65e-04
2022-05-27 23:39:40,524 INFO [train.py:761] (5/8) Epoch 5, batch 150, loss[loss=0.3675, simple_loss=0.4423, pruned_loss=0.1463, over 4915.00 frames.], tot_loss[loss=0.341, simple_loss=0.4155, pruned_loss=0.1333, over 512174.47 frames.], batch size: 14, lr: 2.65e-04
2022-05-27 23:40:25,579 INFO [train.py:761] (5/8) Epoch 5, batch 200, loss[loss=0.3087, simple_loss=0.4001, pruned_loss=0.1087, over 4952.00 frames.], tot_loss[loss=0.3417, simple_loss=0.4154, pruned_loss=0.1339, over 612719.94 frames.], batch size: 16, lr: 2.66e-04
2022-05-27 23:41:03,606 INFO [train.py:761] (5/8) Epoch 5, batch 250, loss[loss=0.3199, simple_loss=0.3997, pruned_loss=0.12, over 4726.00 frames.], tot_loss[loss=0.3344, simple_loss=0.4101, pruned_loss=0.1293, over 691576.65 frames.], batch size: 13, lr: 2.66e-04
2022-05-27 23:41:40,946 INFO [train.py:761] (5/8) Epoch 5, batch 300, loss[loss=0.2791, simple_loss=0.3883, pruned_loss=0.08491, over 4782.00 frames.], tot_loss[loss=0.3336, simple_loss=0.41, pruned_loss=0.1286, over 752072.99 frames.], batch size: 13, lr: 2.66e-04
2022-05-27 23:42:18,684 INFO [train.py:761] (5/8) Epoch 5, batch 350, loss[loss=0.2869, simple_loss=0.3886, pruned_loss=0.09256, over 4670.00 frames.], tot_loss[loss=0.3327, simple_loss=0.41, pruned_loss=0.1277, over 799466.29 frames.], batch size: 13, lr: 2.67e-04
2022-05-27 23:42:56,142 INFO [train.py:761] (5/8) Epoch 5, batch 400, loss[loss=0.3004, simple_loss=0.3639, pruned_loss=0.1185, over 4727.00 frames.], tot_loss[loss=0.3296, simple_loss=0.4068, pruned_loss=0.1262, over 836681.70 frames.], batch size: 11, lr: 2.67e-04
2022-05-27 23:43:34,128 INFO [train.py:761] (5/8) Epoch 5, batch 450, loss[loss=0.3055, simple_loss=0.3858, pruned_loss=0.1126, over 4805.00 frames.], tot_loss[loss=0.3304, simple_loss=0.4079, pruned_loss=0.1265, over 866009.74 frames.], batch size: 12, lr: 2.68e-04
2022-05-27 23:44:11,954 INFO [train.py:761] (5/8) Epoch 5, batch 500, loss[loss=0.3487, simple_loss=0.403, pruned_loss=0.1472, over 4612.00 frames.], tot_loss[loss=0.3294, simple_loss=0.4073, pruned_loss=0.1257, over 888129.16 frames.], batch size: 12, lr: 2.68e-04
2022-05-27 23:44:50,035 INFO [train.py:761] (5/8) Epoch 5, batch 550, loss[loss=0.3292, simple_loss=0.4196, pruned_loss=0.1194, over 4886.00 frames.], tot_loss[loss=0.3299, simple_loss=0.4073, pruned_loss=0.1263, over 905360.83 frames.], batch size: 15, lr: 2.69e-04
2022-05-27 23:45:28,129 INFO [train.py:761] (5/8) Epoch 5, batch 600, loss[loss=0.3824, simple_loss=0.4284, pruned_loss=0.1682, over 4720.00 frames.], tot_loss[loss=0.3305, simple_loss=0.4081, pruned_loss=0.1265, over 918750.09 frames.], batch size: 13, lr: 2.69e-04
2022-05-27 23:46:05,920 INFO [train.py:761] (5/8) Epoch 5, batch 650, loss[loss=0.2752, simple_loss=0.3375, pruned_loss=0.1065, over 4984.00 frames.], tot_loss[loss=0.3309, simple_loss=0.4078, pruned_loss=0.1269, over 929025.72 frames.], batch size: 12, lr: 2.70e-04
2022-05-27 23:46:44,068 INFO [train.py:761] (5/8) Epoch 5, batch 700, loss[loss=0.3464, simple_loss=0.4119, pruned_loss=0.1405, over 4866.00 frames.], tot_loss[loss=0.3338, simple_loss=0.4094, pruned_loss=0.1291, over 936455.02 frames.], batch size: 13, lr: 2.70e-04
2022-05-27 23:47:22,017 INFO [train.py:761] (5/8) Epoch 5, batch 750, loss[loss=0.3637, simple_loss=0.4345, pruned_loss=0.1465, over 4759.00 frames.], tot_loss[loss=0.3364, simple_loss=0.4116, pruned_loss=0.1306, over 943593.58 frames.], batch size: 15, lr: 2.71e-04
2022-05-27 23:47:59,628 INFO [train.py:761] (5/8) Epoch 5, batch 800, loss[loss=0.2895, simple_loss=0.3699, pruned_loss=0.1045, over 4766.00 frames.], tot_loss[loss=0.336, simple_loss=0.4109, pruned_loss=0.1306, over 948437.65 frames.], batch size: 15, lr: 2.71e-04
2022-05-27 23:48:37,651 INFO [train.py:761] (5/8) Epoch 5, batch 850, loss[loss=0.3031, simple_loss=0.3951, pruned_loss=0.1055, over 4882.00 frames.], tot_loss[loss=0.3374, simple_loss=0.4113, pruned_loss=0.1317, over 953383.99 frames.], batch size: 17, lr: 2.72e-04
2022-05-27 23:49:15,284 INFO [train.py:761] (5/8) Epoch 5, batch 900, loss[loss=0.3635, simple_loss=0.4372, pruned_loss=0.1449, over 4792.00 frames.], tot_loss[loss=0.3384, simple_loss=0.4119, pruned_loss=0.1324, over 956853.31 frames.], batch size: 14, lr: 2.72e-04
2022-05-27 23:49:53,002 INFO [train.py:761] (5/8) Epoch 5, batch 950, loss[loss=0.2693, simple_loss=0.3645, pruned_loss=0.08709, over 4829.00 frames.], tot_loss[loss=0.3399, simple_loss=0.4129, pruned_loss=0.1334, over 958036.85 frames.], batch size: 11, lr: 2.73e-04
2022-05-27 23:50:30,665 INFO [train.py:761] (5/8) Epoch 5, batch 1000, loss[loss=0.4176, simple_loss=0.4871, pruned_loss=0.1741, over 4806.00 frames.], tot_loss[loss=0.3389, simple_loss=0.4122, pruned_loss=0.1328, over 959201.09 frames.], batch size: 20, lr: 2.73e-04
2022-05-27 23:51:08,940 INFO [train.py:761] (5/8) Epoch 5, batch 1050, loss[loss=0.3413, simple_loss=0.4163, pruned_loss=0.1331, over 4730.00 frames.], tot_loss[loss=0.3386, simple_loss=0.4113, pruned_loss=0.1329, over 960235.08 frames.], batch size: 12, lr: 2.74e-04
2022-05-27 23:51:47,030 INFO [train.py:761] (5/8) Epoch 5, batch 1100, loss[loss=0.2676, simple_loss=0.3335, pruned_loss=0.1008, over 4969.00 frames.], tot_loss[loss=0.3377, simple_loss=0.4104, pruned_loss=0.1324, over 962009.48 frames.], batch size: 12, lr: 2.74e-04
2022-05-27 23:52:24,886 INFO [train.py:761] (5/8) Epoch 5, batch 1150, loss[loss=0.3458, simple_loss=0.4271, pruned_loss=0.1323, over 4912.00 frames.], tot_loss[loss=0.3374, simple_loss=0.4105, pruned_loss=0.1321, over 961739.10 frames.], batch size: 14, lr: 2.75e-04
2022-05-27 23:53:03,296 INFO [train.py:761] (5/8) Epoch 5, batch 1200, loss[loss=0.3326, simple_loss=0.4198, pruned_loss=0.1228, over 4876.00 frames.], tot_loss[loss=0.3378, simple_loss=0.4116, pruned_loss=0.1319, over 962981.56 frames.], batch size: 47, lr: 2.75e-04
2022-05-27 23:53:41,657 INFO [train.py:761] (5/8) Epoch 5, batch 1250, loss[loss=0.3436, simple_loss=0.4292, pruned_loss=0.1291, over 4983.00 frames.], tot_loss[loss=0.3366, simple_loss=0.4109, pruned_loss=0.1312, over 963306.81 frames.], batch size: 27, lr: 2.76e-04
2022-05-27 23:54:19,642 INFO [train.py:761] (5/8) Epoch 5, batch 1300, loss[loss=0.2601, simple_loss=0.3416, pruned_loss=0.08927, over 4880.00 frames.], tot_loss[loss=0.338, simple_loss=0.4117, pruned_loss=0.1321, over 962397.36 frames.], batch size: 12, lr: 2.76e-04
2022-05-27 23:54:57,428 INFO [train.py:761] (5/8) Epoch 5, batch 1350, loss[loss=0.3736, simple_loss=0.4494, pruned_loss=0.1488, over 4847.00 frames.], tot_loss[loss=0.3383, simple_loss=0.4119, pruned_loss=0.1324, over 962958.26 frames.], batch size: 18, lr: 2.77e-04
2022-05-27 23:55:35,629 INFO [train.py:761] (5/8) Epoch 5, batch 1400, loss[loss=0.3466, simple_loss=0.4211, pruned_loss=0.1361, over 4866.00 frames.], tot_loss[loss=0.3393, simple_loss=0.4124, pruned_loss=0.1331, over 963734.71 frames.], batch size: 17, lr: 2.77e-04
2022-05-27 23:56:14,077 INFO [train.py:761] (5/8) Epoch 5, batch 1450, loss[loss=0.3352, simple_loss=0.4196, pruned_loss=0.1254, over 4845.00 frames.], tot_loss[loss=0.3383, simple_loss=0.4117, pruned_loss=0.1324, over 964925.76 frames.], batch size: 14, lr: 2.78e-04
2022-05-27 23:56:52,315 INFO [train.py:761] (5/8) Epoch 5, batch 1500, loss[loss=0.3111, simple_loss=0.3963, pruned_loss=0.113, over 4783.00 frames.], tot_loss[loss=0.3354, simple_loss=0.4093, pruned_loss=0.1308, over 965102.24 frames.], batch size: 13, lr: 2.78e-04
2022-05-27 23:57:30,129 INFO [train.py:761] (5/8) Epoch 5, batch 1550, loss[loss=0.3013, simple_loss=0.3638, pruned_loss=0.1194, over 4799.00 frames.], tot_loss[loss=0.3334, simple_loss=0.4073, pruned_loss=0.1298, over 964619.81 frames.], batch size: 12, lr: 2.79e-04
2022-05-27 23:58:08,385 INFO [train.py:761] (5/8) Epoch 5, batch 1600, loss[loss=0.3202, simple_loss=0.3959, pruned_loss=0.1223, over 4971.00 frames.], tot_loss[loss=0.3348, simple_loss=0.4086, pruned_loss=0.1304, over 965086.64 frames.], batch size: 15, lr: 2.79e-04
2022-05-27 23:58:46,322 INFO [train.py:761] (5/8) Epoch 5, batch 1650, loss[loss=0.2919, simple_loss=0.3696, pruned_loss=0.1071, over 4811.00 frames.], tot_loss[loss=0.3355, simple_loss=0.4095, pruned_loss=0.1307, over 965882.58 frames.], batch size: 12, lr: 2.80e-04
2022-05-27 23:59:23,708 INFO [train.py:761] (5/8) Epoch 5, batch 1700, loss[loss=0.2956, simple_loss=0.3744, pruned_loss=0.1084, over 4791.00 frames.], tot_loss[loss=0.3344, simple_loss=0.4088, pruned_loss=0.13, over 965772.27 frames.], batch size: 16, lr: 2.80e-04
2022-05-28 00:00:01,651 INFO [train.py:761] (5/8) Epoch 5, batch 1750, loss[loss=0.289, simple_loss=0.3786, pruned_loss=0.09974, over 4923.00 frames.], tot_loss[loss=0.3346, simple_loss=0.4092, pruned_loss=0.13, over 966118.09 frames.], batch size: 13, lr: 2.81e-04
2022-05-28 00:00:39,739 INFO [train.py:761] (5/8) Epoch 5, batch 1800, loss[loss=0.349, simple_loss=0.4233, pruned_loss=0.1373, over 4890.00 frames.], tot_loss[loss=0.3342, simple_loss=0.4087, pruned_loss=0.1299, over 966109.26 frames.], batch size: 15, lr: 2.81e-04
2022-05-28 00:01:17,574 INFO [train.py:761] (5/8) Epoch 5, batch 1850, loss[loss=0.2978, simple_loss=0.3929, pruned_loss=0.1014, over 4916.00 frames.], tot_loss[loss=0.3359, simple_loss=0.4097, pruned_loss=0.131, over 966565.18 frames.], batch size: 17, lr: 2.82e-04
2022-05-28 00:01:55,707 INFO [train.py:761] (5/8) Epoch 5, batch 1900, loss[loss=0.3497, simple_loss=0.4136, pruned_loss=0.1429, over 4880.00 frames.], tot_loss[loss=0.3335, simple_loss=0.4082, pruned_loss=0.1295, over 965977.47 frames.], batch size: 12, lr: 2.82e-04
2022-05-28 00:02:33,777 INFO [train.py:761] (5/8) Epoch 5, batch 1950, loss[loss=0.3828, simple_loss=0.4473, pruned_loss=0.1591, over 4679.00 frames.], tot_loss[loss=0.3322, simple_loss=0.4067, pruned_loss=0.1289, over 965887.09 frames.], batch size: 13, lr: 2.83e-04
2022-05-28 00:03:11,636 INFO [train.py:761] (5/8) Epoch 5, batch 2000, loss[loss=0.3325, simple_loss=0.3941, pruned_loss=0.1355, over 4654.00 frames.], tot_loss[loss=0.3323, simple_loss=0.4068, pruned_loss=0.1289, over 966467.27 frames.], batch size: 12, lr: 2.83e-04
2022-05-28 00:03:49,823 INFO [train.py:761] (5/8) Epoch 5, batch 2050, loss[loss=0.2714, simple_loss=0.3604, pruned_loss=0.09126, over 4568.00 frames.], tot_loss[loss=0.3309, simple_loss=0.4058, pruned_loss=0.128, over 967230.07 frames.], batch size: 10, lr: 2.84e-04
2022-05-28 00:04:27,721 INFO [train.py:761] (5/8) Epoch 5, batch 2100, loss[loss=0.3554, simple_loss=0.4296, pruned_loss=0.1406, over 4994.00 frames.], tot_loss[loss=0.3323, simple_loss=0.4069, pruned_loss=0.1289, over 966867.87 frames.], batch size: 21, lr: 2.84e-04
2022-05-28 00:05:05,834 INFO [train.py:761] (5/8) Epoch 5, batch 2150, loss[loss=0.3144, simple_loss=0.3834, pruned_loss=0.1227, over 4724.00 frames.], tot_loss[loss=0.3327, simple_loss=0.4074, pruned_loss=0.129, over 967822.99 frames.], batch size: 12, lr: 2.85e-04
2022-05-28 00:05:43,439 INFO [train.py:761] (5/8) Epoch 5, batch 2200, loss[loss=0.3842, simple_loss=0.444, pruned_loss=0.1622, over 4968.00 frames.], tot_loss[loss=0.3343, simple_loss=0.4086, pruned_loss=0.13, over 968456.02 frames.], batch size: 16, lr: 2.85e-04
2022-05-28 00:06:21,131 INFO [train.py:761] (5/8) Epoch 5, batch 2250, loss[loss=0.277, simple_loss=0.3566, pruned_loss=0.09868, over 4736.00 frames.], tot_loss[loss=0.3327, simple_loss=0.4076, pruned_loss=0.1289, over 967798.25 frames.], batch size: 11, lr: 2.86e-04
2022-05-28 00:06:58,794 INFO [train.py:761] (5/8) Epoch 5, batch 2300, loss[loss=0.3091, simple_loss=0.3979, pruned_loss=0.1101, over 4846.00 frames.], tot_loss[loss=0.3305, simple_loss=0.406, pruned_loss=0.1275, over 966878.12 frames.], batch size: 14, lr: 2.86e-04
2022-05-28 00:07:36,775 INFO [train.py:761] (5/8) Epoch 5, batch 2350, loss[loss=0.3286, simple_loss=0.3886, pruned_loss=0.1343, over 4671.00 frames.], tot_loss[loss=0.3323, simple_loss=0.4071, pruned_loss=0.1288, over 966200.38 frames.], batch size: 13, lr: 2.87e-04
2022-05-28 00:08:15,002 INFO [train.py:761] (5/8) Epoch 5, batch 2400, loss[loss=0.2802, simple_loss=0.3325, pruned_loss=0.1139, over 4728.00 frames.], tot_loss[loss=0.3304, simple_loss=0.4058, pruned_loss=0.1275, over 965893.46 frames.], batch size: 11, lr: 2.87e-04
2022-05-28 00:08:53,291 INFO [train.py:761] (5/8) Epoch 5, batch 2450, loss[loss=0.3462, simple_loss=0.3976, pruned_loss=0.1474, over 4669.00 frames.], tot_loss[loss=0.3318, simple_loss=0.4069, pruned_loss=0.1283, over 965408.83 frames.], batch size: 12, lr: 2.87e-04
2022-05-28 00:09:30,957 INFO [train.py:761] (5/8) Epoch 5, batch 2500, loss[loss=0.3237, simple_loss=0.3879, pruned_loss=0.1298, over 4889.00 frames.], tot_loss[loss=0.3315, simple_loss=0.4067, pruned_loss=0.1281, over 966018.51 frames.], batch size: 12, lr: 2.88e-04
2022-05-28 00:10:09,035 INFO [train.py:761] (5/8) Epoch 5, batch 2550, loss[loss=0.265, simple_loss=0.3566, pruned_loss=0.08674, over 4913.00 frames.], tot_loss[loss=0.3328, simple_loss=0.4078, pruned_loss=0.1289, over 965898.66 frames.], batch size: 13, lr: 2.88e-04
2022-05-28 00:10:46,871 INFO [train.py:761] (5/8) Epoch 5, batch 2600, loss[loss=0.3243, simple_loss=0.3938, pruned_loss=0.1274, over 4867.00 frames.], tot_loss[loss=0.3318, simple_loss=0.4065, pruned_loss=0.1286, over 966560.23 frames.], batch size: 15, lr: 2.89e-04
2022-05-28 00:11:24,639 INFO [train.py:761] (5/8) Epoch 5, batch 2650, loss[loss=0.2848, simple_loss=0.3819, pruned_loss=0.09383, over 4789.00 frames.], tot_loss[loss=0.3306, simple_loss=0.4059, pruned_loss=0.1277, over 967028.68 frames.], batch size: 14, lr: 2.89e-04
2022-05-28 00:12:02,696 INFO [train.py:761] (5/8) Epoch 5, batch 2700, loss[loss=0.3163, simple_loss=0.3749, pruned_loss=0.1289, over 4659.00 frames.], tot_loss[loss=0.3305, simple_loss=0.4057, pruned_loss=0.1276, over 966528.03 frames.], batch size: 12, lr: 2.90e-04
2022-05-28 00:12:40,028 INFO [train.py:761] (5/8) Epoch 5, batch 2750, loss[loss=0.3102, simple_loss=0.3789, pruned_loss=0.1208, over 4630.00 frames.], tot_loss[loss=0.3296, simple_loss=0.4052, pruned_loss=0.127, over 965936.44 frames.], batch size: 11, lr: 2.90e-04
2022-05-28 00:13:17,769 INFO [train.py:761] (5/8) Epoch 5, batch 2800, loss[loss=0.2761, simple_loss=0.3532, pruned_loss=0.09956, over 4975.00 frames.], tot_loss[loss=0.33, simple_loss=0.405, pruned_loss=0.1275, over 967411.99 frames.], batch size: 12, lr: 2.91e-04
2022-05-28 00:13:56,143 INFO [train.py:761] (5/8) Epoch 5, batch 2850, loss[loss=0.3621, simple_loss=0.4246, pruned_loss=0.1498, over 4728.00 frames.], tot_loss[loss=0.3305, simple_loss=0.4052, pruned_loss=0.1279, over 966465.11 frames.], batch size: 12, lr: 2.91e-04
2022-05-28 00:14:34,265 INFO [train.py:761] (5/8) Epoch 5, batch 2900, loss[loss=0.311, simple_loss=0.3865, pruned_loss=0.1177, over 4884.00 frames.], tot_loss[loss=0.3306, simple_loss=0.4058, pruned_loss=0.1277, over 966831.63 frames.], batch size: 17, lr: 2.92e-04
2022-05-28 00:15:12,183 INFO [train.py:761] (5/8) Epoch 5, batch 2950, loss[loss=0.2593, simple_loss=0.3323, pruned_loss=0.09313, over 4972.00 frames.], tot_loss[loss=0.3291, simple_loss=0.4047, pruned_loss=0.1267, over 966288.09 frames.], batch size: 12, lr: 2.92e-04
2022-05-28 00:15:50,180 INFO [train.py:761] (5/8) Epoch 5, batch 3000, loss[loss=0.3151, simple_loss=0.3899, pruned_loss=0.1201, over 4788.00 frames.], tot_loss[loss=0.3282, simple_loss=0.4035, pruned_loss=0.1264, over 966692.86 frames.], batch size: 16, lr: 2.93e-04
2022-05-28 00:15:50,181 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 00:15:59,809 INFO [train.py:790] (5/8) Epoch 5, validation: loss=0.2821, simple_loss=0.3843, pruned_loss=0.08992, over 944034.00 frames.
2022-05-28 00:16:37,959 INFO [train.py:761] (5/8) Epoch 5, batch 3050, loss[loss=0.3483, simple_loss=0.4122, pruned_loss=0.1422, over 4914.00 frames.], tot_loss[loss=0.3283, simple_loss=0.4037, pruned_loss=0.1264, over 967366.37 frames.], batch size: 14, lr: 2.93e-04
2022-05-28 00:17:15,817 INFO [train.py:761] (5/8) Epoch 5, batch 3100, loss[loss=0.3646, simple_loss=0.4172, pruned_loss=0.156, over 4885.00 frames.], tot_loss[loss=0.3309, simple_loss=0.4049, pruned_loss=0.1284, over 966497.52 frames.], batch size: 12, lr: 2.94e-04
2022-05-28 00:17:54,450 INFO [train.py:761] (5/8) Epoch 5, batch 3150, loss[loss=0.2999, simple_loss=0.4052, pruned_loss=0.09731, over 4796.00 frames.], tot_loss[loss=0.3345, simple_loss=0.4061, pruned_loss=0.1315, over 966882.81 frames.], batch size: 20, lr: 2.94e-04
2022-05-28 00:18:31,908 INFO [train.py:761] (5/8) Epoch 5, batch 3200, loss[loss=0.3243, simple_loss=0.3976, pruned_loss=0.1255, over 4790.00 frames.], tot_loss[loss=0.3395, simple_loss=0.4094, pruned_loss=0.1348, over 967467.14 frames.], batch size: 13, lr: 2.95e-04
2022-05-28 00:19:09,706 INFO [train.py:761] (5/8) Epoch 5, batch 3250, loss[loss=0.4459, simple_loss=0.4735, pruned_loss=0.2092, over 4973.00 frames.], tot_loss[loss=0.345, simple_loss=0.4116, pruned_loss=0.1392, over 966293.26 frames.], batch size: 16, lr: 2.95e-04
2022-05-28 00:19:46,947 INFO [train.py:761] (5/8) Epoch 5, batch 3300, loss[loss=0.3454, simple_loss=0.3901, pruned_loss=0.1504, over 4561.00 frames.], tot_loss[loss=0.3517, simple_loss=0.4154, pruned_loss=0.144, over 966585.71 frames.], batch size: 10, lr: 2.96e-04
2022-05-28 00:20:25,348 INFO [train.py:761] (5/8) Epoch 5, batch 3350, loss[loss=0.3025, simple_loss=0.3846, pruned_loss=0.1102, over 4727.00 frames.], tot_loss[loss=0.3547, simple_loss=0.4166, pruned_loss=0.1464, over 965843.71 frames.], batch size: 13, lr: 2.96e-04
2022-05-28 00:21:03,331 INFO [train.py:761] (5/8) Epoch 5, batch 3400, loss[loss=0.3233, simple_loss=0.394, pruned_loss=0.1263, over 4922.00 frames.], tot_loss[loss=0.3599, simple_loss=0.419, pruned_loss=0.1504, over 967656.48 frames.], batch size: 13, lr: 2.97e-04
2022-05-28 00:21:41,385 INFO [train.py:761] (5/8) Epoch 5, batch 3450, loss[loss=0.4457, simple_loss=0.4704, pruned_loss=0.2106, over 4974.00 frames.], tot_loss[loss=0.3641, simple_loss=0.4207, pruned_loss=0.1537, over 966301.96 frames.], batch size: 14, lr: 2.97e-04
2022-05-28 00:22:19,851 INFO [train.py:761] (5/8) Epoch 5, batch 3500, loss[loss=0.4863, simple_loss=0.4938, pruned_loss=0.2394, over 4970.00 frames.], tot_loss[loss=0.3661, simple_loss=0.4213, pruned_loss=0.1555, over 965606.40 frames.], batch size: 14, lr: 2.98e-04
2022-05-28 00:22:58,211 INFO [train.py:761] (5/8) Epoch 5, batch 3550, loss[loss=0.4352, simple_loss=0.466, pruned_loss=0.2021, over 4917.00 frames.], tot_loss[loss=0.3679, simple_loss=0.4228, pruned_loss=0.1566, over 965547.14 frames.], batch size: 14, lr: 2.98e-04
2022-05-28 00:23:36,233 INFO [train.py:761] (5/8) Epoch 5, batch 3600, loss[loss=0.4094, simple_loss=0.4522, pruned_loss=0.1833, over 4756.00 frames.], tot_loss[loss=0.3703, simple_loss=0.4238, pruned_loss=0.1584, over 965881.88 frames.], batch size: 15, lr: 2.99e-04
2022-05-28 00:24:14,653 INFO [train.py:761] (5/8) Epoch 5, batch 3650, loss[loss=0.5248, simple_loss=0.531, pruned_loss=0.2593, over 4768.00 frames.], tot_loss[loss=0.376, simple_loss=0.4274, pruned_loss=0.1623, over 966262.00 frames.], batch size: 15, lr: 2.99e-04
2022-05-28 00:24:52,665 INFO [train.py:761] (5/8) Epoch 5, batch 3700, loss[loss=0.5169, simple_loss=0.5201, pruned_loss=0.2568, over 4934.00 frames.], tot_loss[loss=0.3772, simple_loss=0.4278, pruned_loss=0.1633, over 966927.73 frames.], batch size: 47, lr: 3.00e-04
2022-05-28 00:25:31,450 INFO [train.py:761] (5/8) Epoch 5, batch 3750, loss[loss=0.4046, simple_loss=0.4559, pruned_loss=0.1767, over 4798.00 frames.], tot_loss[loss=0.3757, simple_loss=0.4273, pruned_loss=0.1621, over 966947.04 frames.], batch size: 16, lr: 3.00e-04
2022-05-28 00:26:09,714 INFO [train.py:761] (5/8) Epoch 5, batch 3800, loss[loss=0.352, simple_loss=0.4086, pruned_loss=0.1477, over 4721.00 frames.], tot_loss[loss=0.375, simple_loss=0.4266, pruned_loss=0.1617, over 967877.35 frames.], batch size: 13, lr: 3.01e-04
2022-05-28 00:26:48,014 INFO [train.py:761] (5/8) Epoch 5, batch 3850, loss[loss=0.3798, simple_loss=0.4309, pruned_loss=0.1643, over 4732.00 frames.], tot_loss[loss=0.3769, simple_loss=0.4277, pruned_loss=0.163, over 967818.78 frames.], batch size: 12, lr: 3.01e-04
2022-05-28 00:27:26,153 INFO [train.py:761] (5/8) Epoch 5, batch 3900, loss[loss=0.3823, simple_loss=0.4416, pruned_loss=0.1615, over 4670.00 frames.], tot_loss[loss=0.3769, simple_loss=0.4275, pruned_loss=0.1632, over 966111.78 frames.], batch size: 13, lr: 3.02e-04
2022-05-28 00:28:04,506 INFO [train.py:761] (5/8) Epoch 5, batch 3950, loss[loss=0.3068, simple_loss=0.3671, pruned_loss=0.1233, over 4918.00 frames.], tot_loss[loss=0.3765, simple_loss=0.4269, pruned_loss=0.163, over 966711.80 frames.], batch size: 13, lr: 3.02e-04
2022-05-28 00:28:42,430 INFO [train.py:761] (5/8) Epoch 5, batch 4000, loss[loss=0.325, simple_loss=0.3603, pruned_loss=0.1449, over 4728.00 frames.], tot_loss[loss=0.3736, simple_loss=0.4246, pruned_loss=0.1613, over 966228.21 frames.], batch size: 11, lr: 3.03e-04
2022-05-28 00:29:20,723 INFO [train.py:761] (5/8) Epoch 5, batch 4050, loss[loss=0.3025, simple_loss=0.353, pruned_loss=0.126, over 4723.00 frames.], tot_loss[loss=0.3726, simple_loss=0.4232, pruned_loss=0.1609, over 965745.51 frames.], batch size: 11, lr: 3.03e-04
2022-05-28 00:29:58,667 INFO [train.py:761] (5/8) Epoch 5, batch 4100, loss[loss=0.3459, simple_loss=0.4159, pruned_loss=0.1379, over 4778.00 frames.], tot_loss[loss=0.3715, simple_loss=0.422, pruned_loss=0.1604, over 965291.73 frames.], batch size: 14, lr: 3.04e-04
2022-05-28 00:30:37,072 INFO [train.py:761] (5/8) Epoch 5, batch 4150, loss[loss=0.4314, simple_loss=0.4689, pruned_loss=0.1969, over 4838.00 frames.], tot_loss[loss=0.3724, simple_loss=0.4229, pruned_loss=0.161, over 965746.78 frames.], batch size: 18, lr: 3.04e-04
2022-05-28 00:31:15,786 INFO [train.py:761] (5/8) Epoch 5, batch 4200, loss[loss=0.2894, simple_loss=0.3739, pruned_loss=0.1025, over 4785.00 frames.], tot_loss[loss=0.3699, simple_loss=0.4213, pruned_loss=0.1592, over 967217.52 frames.], batch size: 13, lr: 3.05e-04
2022-05-28 00:31:53,676 INFO [train.py:761] (5/8) Epoch 5, batch 4250, loss[loss=0.468, simple_loss=0.5, pruned_loss=0.218, over 4934.00 frames.], tot_loss[loss=0.3699, simple_loss=0.4208, pruned_loss=0.1595, over 966274.55 frames.], batch size: 46, lr: 3.05e-04
2022-05-28 00:32:31,713 INFO [train.py:761] (5/8) Epoch 5, batch 4300, loss[loss=0.3556, simple_loss=0.4273, pruned_loss=0.1419, over 4902.00 frames.], tot_loss[loss=0.3711, simple_loss=0.4224, pruned_loss=0.16, over 966784.32 frames.], batch size: 17, lr: 3.06e-04
2022-05-28 00:33:10,205 INFO [train.py:761] (5/8) Epoch 5, batch 4350, loss[loss=0.3778, simple_loss=0.4351, pruned_loss=0.1602, over 4845.00 frames.], tot_loss[loss=0.3719, simple_loss=0.4229, pruned_loss=0.1605, over 967160.19 frames.], batch size: 18, lr: 3.06e-04
2022-05-28 00:33:47,588 INFO [train.py:761] (5/8) Epoch 5, batch 4400, loss[loss=0.386, simple_loss=0.432, pruned_loss=0.1699, over 4804.00 frames.], tot_loss[loss=0.3719, simple_loss=0.4225, pruned_loss=0.1606, over 966351.39 frames.], batch size: 12, lr: 3.07e-04
2022-05-28 00:34:25,784 INFO [train.py:761] (5/8) Epoch 5, batch 4450, loss[loss=0.2746, simple_loss=0.3491, pruned_loss=0.1, over 4874.00 frames.], tot_loss[loss=0.3679, simple_loss=0.42, pruned_loss=0.1579, over 966619.03 frames.], batch size: 12, lr: 3.07e-04
2022-05-28 00:35:03,804 INFO [train.py:761] (5/8) Epoch 5, batch 4500, loss[loss=0.3219, simple_loss=0.3788, pruned_loss=0.1325, over 4952.00 frames.], tot_loss[loss=0.3663, simple_loss=0.4187, pruned_loss=0.1569, over 966311.74 frames.], batch size: 16, lr: 3.08e-04
2022-05-28 00:35:41,817 INFO [train.py:761] (5/8) Epoch 5, batch 4550, loss[loss=0.3519, simple_loss=0.4029, pruned_loss=0.1504, over 4883.00 frames.], tot_loss[loss=0.366, simple_loss=0.4191, pruned_loss=0.1565, over 965911.53 frames.], batch size: 15, lr: 3.08e-04
2022-05-28 00:36:20,094 INFO [train.py:761] (5/8) Epoch 5, batch 4600, loss[loss=0.3437, simple_loss=0.4176, pruned_loss=0.1349, over 4886.00 frames.], tot_loss[loss=0.3654, simple_loss=0.419, pruned_loss=0.1559, over 966446.08 frames.], batch size: 15, lr: 3.08e-04
2022-05-28 00:36:58,610 INFO [train.py:761] (5/8) Epoch 5, batch 4650, loss[loss=0.3624, simple_loss=0.4221, pruned_loss=0.1513, over 4741.00 frames.], tot_loss[loss=0.3636, simple_loss=0.4179, pruned_loss=0.1547, over 966086.13 frames.], batch size: 12, lr: 3.09e-04
2022-05-28 00:37:37,177 INFO [train.py:761] (5/8) Epoch 5, batch 4700, loss[loss=0.3243, simple_loss=0.3868, pruned_loss=0.1309, over 4659.00 frames.], tot_loss[loss=0.3668, simple_loss=0.4201, pruned_loss=0.1567, over 967426.00 frames.], batch size: 12, lr: 3.09e-04
2022-05-28 00:38:15,636 INFO [train.py:761] (5/8) Epoch 5, batch 4750, loss[loss=0.3868, simple_loss=0.4494, pruned_loss=0.1621, over 4988.00 frames.], tot_loss[loss=0.366, simple_loss=0.4192, pruned_loss=0.1564, over 966096.83 frames.], batch size: 21, lr: 3.10e-04
2022-05-28 00:38:54,123 INFO [train.py:761] (5/8) Epoch 5, batch 4800, loss[loss=0.4176, simple_loss=0.4685, pruned_loss=0.1833, over 4773.00 frames.], tot_loss[loss=0.3636, simple_loss=0.4174, pruned_loss=0.155, over 966229.05 frames.], batch size: 15, lr: 3.10e-04
2022-05-28 00:39:32,946 INFO [train.py:761] (5/8) Epoch 5, batch 4850, loss[loss=0.3384, simple_loss=0.4035, pruned_loss=0.1367, over 4955.00 frames.], tot_loss[loss=0.365, simple_loss=0.4179, pruned_loss=0.156, over 966109.12 frames.], batch size: 16, lr: 3.11e-04
2022-05-28 00:40:10,684 INFO [train.py:761] (5/8) Epoch 5, batch 4900, loss[loss=0.3203, simple_loss=0.3987, pruned_loss=0.1209, over 4974.00 frames.], tot_loss[loss=0.3635, simple_loss=0.4166, pruned_loss=0.1552, over 965066.93 frames.], batch size: 15, lr: 3.11e-04
2022-05-28 00:40:48,980 INFO [train.py:761] (5/8) Epoch 5, batch 4950, loss[loss=0.2614, simple_loss=0.3263, pruned_loss=0.09829, over 4827.00 frames.], tot_loss[loss=0.3626, simple_loss=0.4161, pruned_loss=0.1546, over 965644.00 frames.], batch size: 11, lr: 3.12e-04
2022-05-28 00:41:27,177 INFO [train.py:761] (5/8) Epoch 5, batch 5000, loss[loss=0.3916, simple_loss=0.4469, pruned_loss=0.1681, over 4909.00 frames.], tot_loss[loss=0.361, simple_loss=0.4149, pruned_loss=0.1535, over 966233.23 frames.], batch size: 14, lr: 3.12e-04
2022-05-28 00:42:08,434 INFO [train.py:761] (5/8) Epoch 5, batch 5050, loss[loss=0.327, simple_loss=0.3796, pruned_loss=0.1372, over 4978.00 frames.], tot_loss[loss=0.3637, simple_loss=0.4179, pruned_loss=0.1547, over 967062.05 frames.], batch size: 14, lr: 3.13e-04
2022-05-28 00:42:46,854 INFO [train.py:761] (5/8) Epoch 5, batch 5100, loss[loss=0.3578, simple_loss=0.4152, pruned_loss=0.1502, over 4918.00 frames.], tot_loss[loss=0.365, simple_loss=0.4193, pruned_loss=0.1553, over 966400.75 frames.], batch size: 14, lr: 3.13e-04
2022-05-28 00:43:25,064 INFO [train.py:761] (5/8) Epoch 5, batch 5150, loss[loss=0.3208, simple_loss=0.3821, pruned_loss=0.1298, over 4741.00 frames.], tot_loss[loss=0.3666, simple_loss=0.4205, pruned_loss=0.1564, over 966547.72 frames.], batch size: 12, lr: 3.14e-04
2022-05-28 00:44:03,758 INFO [train.py:761] (5/8) Epoch 5, batch 5200, loss[loss=0.4138, simple_loss=0.4544, pruned_loss=0.1865, over 4794.00 frames.], tot_loss[loss=0.3676, simple_loss=0.4214, pruned_loss=0.1569, over 966988.63 frames.], batch size: 16, lr: 3.14e-04
2022-05-28 00:44:42,888 INFO [train.py:761] (5/8) Epoch 5, batch 5250, loss[loss=0.4306, simple_loss=0.4766, pruned_loss=0.1923, over 4914.00 frames.], tot_loss[loss=0.3675, simple_loss=0.4209, pruned_loss=0.157, over 967422.98 frames.], batch size: 21, lr: 3.15e-04
2022-05-28 00:45:21,695 INFO [train.py:761] (5/8) Epoch 5, batch 5300, loss[loss=0.3644, simple_loss=0.4044, pruned_loss=0.1622, over 4882.00 frames.], tot_loss[loss=0.3683, simple_loss=0.4215, pruned_loss=0.1576, over 967752.90 frames.], batch size: 12, lr: 3.15e-04
2022-05-28 00:46:00,005 INFO [train.py:761] (5/8) Epoch 5, batch 5350, loss[loss=0.3459, simple_loss=0.4036, pruned_loss=0.1441, over 4719.00 frames.], tot_loss[loss=0.367, simple_loss=0.4205, pruned_loss=0.1567, over 967838.90 frames.], batch size: 14, lr: 3.16e-04
2022-05-28 00:46:38,046 INFO [train.py:761] (5/8) Epoch 5, batch 5400, loss[loss=0.402, simple_loss=0.455, pruned_loss=0.1745, over 4890.00 frames.], tot_loss[loss=0.3678, simple_loss=0.4211, pruned_loss=0.1572, over 967002.24 frames.], batch size: 17, lr: 3.16e-04
2022-05-28 00:47:16,784 INFO [train.py:761] (5/8) Epoch 5, batch 5450, loss[loss=0.2847, simple_loss=0.3533, pruned_loss=0.1081, over 4727.00 frames.], tot_loss[loss=0.3647, simple_loss=0.4189, pruned_loss=0.1552, over 966010.17 frames.], batch size: 12, lr: 3.17e-04
2022-05-28 00:47:54,230 INFO [train.py:761] (5/8) Epoch 5, batch 5500, loss[loss=0.3883, simple_loss=0.46, pruned_loss=0.1583, over 4952.00 frames.], tot_loss[loss=0.3644, simple_loss=0.4191, pruned_loss=0.1549, over 966545.79 frames.], batch size: 16, lr: 3.17e-04
2022-05-28 00:48:32,553 INFO [train.py:761] (5/8) Epoch 5, batch 5550, loss[loss=0.3232, simple_loss=0.3903, pruned_loss=0.128, over 4672.00 frames.], tot_loss[loss=0.3622, simple_loss=0.418, pruned_loss=0.1532, over 966841.80 frames.], batch size: 13, lr: 3.18e-04
2022-05-28 00:49:10,558 INFO [train.py:761] (5/8) Epoch 5, batch 5600, loss[loss=0.3254, simple_loss=0.4034, pruned_loss=0.1238, over 4953.00 frames.], tot_loss[loss=0.3624, simple_loss=0.4176, pruned_loss=0.1536, over 966887.01 frames.], batch size: 16, lr: 3.18e-04
2022-05-28 00:49:48,802 INFO [train.py:761] (5/8) Epoch 5, batch 5650, loss[loss=0.3295, simple_loss=0.3894, pruned_loss=0.1348, over 4792.00 frames.], tot_loss[loss=0.3628, simple_loss=0.4177, pruned_loss=0.1539, over 966677.41 frames.], batch size: 13, lr: 3.19e-04
2022-05-28 00:50:26,623 INFO [train.py:761] (5/8) Epoch 5, batch 5700, loss[loss=0.3946, simple_loss=0.4453, pruned_loss=0.1719, over 4935.00 frames.], tot_loss[loss=0.3608, simple_loss=0.416, pruned_loss=0.1528, over 964941.26 frames.], batch size: 26, lr: 3.19e-04
2022-05-28 00:51:05,452 INFO [train.py:761] (5/8) Epoch 5, batch 5750, loss[loss=0.3219, simple_loss=0.3793, pruned_loss=0.1322, over 4807.00 frames.], tot_loss[loss=0.3621, simple_loss=0.4169, pruned_loss=0.1537, over 966073.62 frames.], batch size: 12, lr: 3.20e-04
2022-05-28 00:51:44,114 INFO [train.py:761] (5/8) Epoch 5, batch 5800, loss[loss=0.3599, simple_loss=0.4291, pruned_loss=0.1453, over 4850.00 frames.], tot_loss[loss=0.3616, simple_loss=0.4161, pruned_loss=0.1535, over 965211.42 frames.], batch size: 14, lr: 3.20e-04
2022-05-28 00:52:22,306 INFO [train.py:761] (5/8) Epoch 5, batch 5850, loss[loss=0.3413, simple_loss=0.4067, pruned_loss=0.138, over 4922.00 frames.], tot_loss[loss=0.3616, simple_loss=0.4167, pruned_loss=0.1533, over 965953.67 frames.], batch size: 13, lr: 3.21e-04
2022-05-28 00:53:00,291 INFO [train.py:761] (5/8) Epoch 5, batch 5900, loss[loss=0.3017, simple_loss=0.3651, pruned_loss=0.1191, over 4810.00 frames.], tot_loss[loss=0.3576, simple_loss=0.4131, pruned_loss=0.151, over 965642.61 frames.], batch size: 12, lr: 3.21e-04
2022-05-28 00:53:38,498 INFO [train.py:761] (5/8) Epoch 5, batch 5950, loss[loss=0.4106, simple_loss=0.4566, pruned_loss=0.1823, over 4918.00 frames.], tot_loss[loss=0.3621, simple_loss=0.4167, pruned_loss=0.1537, over 965607.28 frames.], batch size: 14, lr: 3.22e-04
2022-05-28 00:54:16,279 INFO [train.py:761] (5/8) Epoch 5, batch 6000, loss[loss=0.366, simple_loss=0.4121, pruned_loss=0.16, over 4906.00 frames.], tot_loss[loss=0.3625, simple_loss=0.4178, pruned_loss=0.1536, over 965541.77 frames.], batch size: 25, lr: 3.22e-04
2022-05-28 00:54:16,280 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 00:54:28,437 INFO [train.py:790] (5/8) Epoch 5, validation: loss=0.2638, simple_loss=0.3727, pruned_loss=0.07743, over 944034.00 frames.
2022-05-28 00:55:07,230 INFO [train.py:761] (5/8) Epoch 5, batch 6050, loss[loss=0.3834, simple_loss=0.4407, pruned_loss=0.1631, over 4847.00 frames.], tot_loss[loss=0.3639, simple_loss=0.419, pruned_loss=0.1544, over 967201.67 frames.], batch size: 26, lr: 3.23e-04
2022-05-28 00:55:45,344 INFO [train.py:761] (5/8) Epoch 5, batch 6100, loss[loss=0.4001, simple_loss=0.4485, pruned_loss=0.1759, over 4826.00 frames.], tot_loss[loss=0.3646, simple_loss=0.4196, pruned_loss=0.1548, over 967406.66 frames.], batch size: 18, lr: 3.23e-04
2022-05-28 00:56:23,611 INFO [train.py:761] (5/8) Epoch 5, batch 6150, loss[loss=0.3226, simple_loss=0.3816, pruned_loss=0.1318, over 4799.00 frames.], tot_loss[loss=0.3612, simple_loss=0.4168, pruned_loss=0.1528, over 967814.97 frames.], batch size: 12, lr: 3.24e-04
2022-05-28 00:57:01,885 INFO [train.py:761] (5/8) Epoch 5, batch 6200, loss[loss=0.3558, simple_loss=0.427, pruned_loss=0.1423, over 4782.00 frames.], tot_loss[loss=0.3616, simple_loss=0.4169, pruned_loss=0.1532, over 967216.11 frames.], batch size: 13, lr: 3.24e-04
2022-05-28 00:57:39,992 INFO [train.py:761] (5/8) Epoch 5, batch 6250, loss[loss=0.3933, simple_loss=0.4291, pruned_loss=0.1787, over 4736.00 frames.], tot_loss[loss=0.3593, simple_loss=0.4152, pruned_loss=0.1517, over 966414.55 frames.], batch size: 13, lr: 3.25e-04
2022-05-28 00:58:18,527 INFO [train.py:761] (5/8) Epoch 5, batch 6300, loss[loss=0.3146, simple_loss=0.3733, pruned_loss=0.1279, over 4731.00 frames.], tot_loss[loss=0.3577, simple_loss=0.4135, pruned_loss=0.1509, over 965525.10 frames.], batch size: 13, lr: 3.25e-04
2022-05-28 00:58:56,690 INFO [train.py:761] (5/8) Epoch 5, batch 6350, loss[loss=0.3162, simple_loss=0.3728, pruned_loss=0.1298, over 4968.00 frames.], tot_loss[loss=0.358, simple_loss=0.414, pruned_loss=0.151, over 965484.95 frames.], batch size: 12, lr: 3.26e-04
2022-05-28 00:59:34,694 INFO [train.py:761] (5/8) Epoch 5, batch 6400, loss[loss=0.3677, simple_loss=0.4275, pruned_loss=0.154, over 4960.00 frames.], tot_loss[loss=0.3578, simple_loss=0.4136, pruned_loss=0.151, over 966709.95 frames.], batch size: 26, lr: 3.26e-04
2022-05-28 01:00:12,987 INFO [train.py:761] (5/8) Epoch 5, batch 6450, loss[loss=0.3269, simple_loss=0.4004, pruned_loss=0.1267, over 4793.00 frames.], tot_loss[loss=0.3583, simple_loss=0.4138, pruned_loss=0.1514, over 966972.88 frames.], batch size: 14, lr: 3.27e-04
2022-05-28 01:00:50,569 INFO [train.py:761] (5/8) Epoch 5, batch 6500, loss[loss=0.3451, simple_loss=0.394, pruned_loss=0.1482, over 4988.00 frames.], tot_loss[loss=0.3578, simple_loss=0.4137, pruned_loss=0.1509, over 967660.42 frames.], batch size: 13, lr: 3.27e-04
2022-05-28 01:01:28,653 INFO [train.py:761] (5/8) Epoch 5, batch 6550, loss[loss=0.4406, simple_loss=0.4996, pruned_loss=0.1908, over 4802.00 frames.], tot_loss[loss=0.3588, simple_loss=0.4143, pruned_loss=0.1516, over 967519.80 frames.], batch size: 16, lr: 3.28e-04
2022-05-28 01:02:06,760 INFO [train.py:761] (5/8) Epoch 5, batch 6600, loss[loss=0.3766, simple_loss=0.4381, pruned_loss=0.1576, over 4876.00 frames.], tot_loss[loss=0.3571, simple_loss=0.4123, pruned_loss=0.151, over 967011.08 frames.], batch size: 15, lr: 3.28e-04
2022-05-28 01:02:44,989 INFO [train.py:761] (5/8) Epoch 5, batch 6650, loss[loss=0.3444, simple_loss=0.395, pruned_loss=0.1469, over 4855.00 frames.], tot_loss[loss=0.3565, simple_loss=0.4122, pruned_loss=0.1504, over 966783.42 frames.], batch size: 13, lr: 3.29e-04
2022-05-28 01:03:23,256 INFO [train.py:761] (5/8) Epoch 5, batch 6700, loss[loss=0.3895, simple_loss=0.4551, pruned_loss=0.1619, over 4952.00 frames.], tot_loss[loss=0.3552, simple_loss=0.4112, pruned_loss=0.1496, over 966732.11 frames.], batch size: 16, lr: 3.29e-04
2022-05-28 01:04:18,190 INFO [train.py:761] (5/8) Epoch 6, batch 0, loss[loss=0.3175, simple_loss=0.3871, pruned_loss=0.124, over 4743.00 frames.], tot_loss[loss=0.3175, simple_loss=0.3871, pruned_loss=0.124, over 4743.00 frames.], batch size: 12, lr: 3.29e-04
2022-05-28 01:04:55,917 INFO [train.py:761] (5/8) Epoch 6, batch 50, loss[loss=0.336, simple_loss=0.4041, pruned_loss=0.134, over 4732.00 frames.], tot_loss[loss=0.3168, simple_loss=0.3911, pruned_loss=0.1212, over 218353.16 frames.], batch size: 12, lr: 3.30e-04
2022-05-28 01:05:34,353 INFO [train.py:761] (5/8) Epoch 6, batch 100, loss[loss=0.3728, simple_loss=0.453, pruned_loss=0.1463, over 4790.00 frames.], tot_loss[loss=0.3192, simple_loss=0.3953, pruned_loss=0.1216, over 384926.74 frames.], batch size: 16, lr: 3.30e-04
2022-05-28 01:06:12,303 INFO [train.py:761] (5/8) Epoch 6, batch 150, loss[loss=0.3239, simple_loss=0.4018, pruned_loss=0.123, over 4854.00 frames.], tot_loss[loss=0.3111, simple_loss=0.389, pruned_loss=0.1166, over 513050.76 frames.], batch size: 14, lr: 3.31e-04
2022-05-28 01:06:50,651 INFO [train.py:761] (5/8) Epoch 6, batch 200, loss[loss=0.2737, simple_loss=0.3418, pruned_loss=0.1029, over 4990.00 frames.], tot_loss[loss=0.3113, simple_loss=0.3892, pruned_loss=0.1167, over 613834.12 frames.], batch size: 13, lr: 3.31e-04
2022-05-28 01:07:28,479 INFO [train.py:761] (5/8) Epoch 6, batch 250, loss[loss=0.315, simple_loss=0.4056, pruned_loss=0.1122, over 4781.00 frames.], tot_loss[loss=0.3164, simple_loss=0.3949, pruned_loss=0.119, over 692876.76 frames.], batch size: 13, lr: 3.32e-04
2022-05-28 01:08:06,694 INFO [train.py:761] (5/8) Epoch 6, batch 300, loss[loss=0.3103, simple_loss=0.3888, pruned_loss=0.116, over 4850.00 frames.], tot_loss[loss=0.3151, simple_loss=0.3932, pruned_loss=0.1185, over 752697.22 frames.], batch size: 13, lr: 3.32e-04
2022-05-28 01:08:44,741 INFO [train.py:761] (5/8) Epoch 6, batch 350, loss[loss=0.3212, simple_loss=0.406, pruned_loss=0.1182, over 4966.00 frames.], tot_loss[loss=0.3138, simple_loss=0.3919, pruned_loss=0.1179, over 800599.72 frames.], batch size: 16, lr: 3.33e-04
2022-05-28 01:09:23,065 INFO [train.py:761] (5/8) Epoch 6, batch 400, loss[loss=0.3056, simple_loss=0.3946, pruned_loss=0.1083, over 4713.00 frames.], tot_loss[loss=0.3115, simple_loss=0.3902, pruned_loss=0.1164, over 837030.30 frames.], batch size: 14, lr: 3.33e-04
2022-05-28 01:10:00,908 INFO [train.py:761] (5/8) Epoch 6, batch 450, loss[loss=0.3128, simple_loss=0.3928, pruned_loss=0.1164, over 4855.00 frames.], tot_loss[loss=0.3094, simple_loss=0.3885, pruned_loss=0.1151, over 865094.23 frames.], batch size: 14, lr: 3.34e-04
2022-05-28 01:10:38,850 INFO [train.py:761] (5/8) Epoch 6, batch 500, loss[loss=0.319, simple_loss=0.3941, pruned_loss=0.122, over 4781.00 frames.], tot_loss[loss=0.3074, simple_loss=0.3865, pruned_loss=0.1142, over 887005.48 frames.], batch size: 20, lr: 3.34e-04
2022-05-28 01:11:16,872 INFO [train.py:761] (5/8) Epoch 6, batch 550, loss[loss=0.3386, simple_loss=0.392, pruned_loss=0.1426, over 4996.00 frames.], tot_loss[loss=0.3076, simple_loss=0.3862, pruned_loss=0.1145, over 903966.21 frames.], batch size: 11, lr: 3.35e-04
2022-05-28 01:11:54,940 INFO [train.py:761] (5/8) Epoch 6, batch 600, loss[loss=0.3192, simple_loss=0.3855, pruned_loss=0.1264, over 4790.00 frames.], tot_loss[loss=0.3084, simple_loss=0.387, pruned_loss=0.1149, over 917807.05 frames.], batch size: 16, lr: 3.35e-04
2022-05-28 01:12:32,257 INFO [train.py:761] (5/8) Epoch 6, batch 650, loss[loss=0.3132, simple_loss=0.4012, pruned_loss=0.1126, over 4774.00 frames.], tot_loss[loss=0.3091, simple_loss=0.3878, pruned_loss=0.1152, over 928309.27 frames.], batch size: 15, lr: 3.36e-04
2022-05-28 01:13:10,726 INFO [train.py:761] (5/8) Epoch 6, batch 700, loss[loss=0.3098, simple_loss=0.3813, pruned_loss=0.1191, over 4727.00 frames.], tot_loss[loss=0.3117, simple_loss=0.3897, pruned_loss=0.1168, over 936486.88 frames.], batch size: 13, lr: 3.36e-04
2022-05-28 01:13:48,257 INFO [train.py:761] (5/8) Epoch 6, batch 750, loss[loss=0.3382, simple_loss=0.4111, pruned_loss=0.1327, over 4967.00 frames.], tot_loss[loss=0.3128, simple_loss=0.39, pruned_loss=0.1178, over 943171.10 frames.], batch size: 15, lr: 3.37e-04
2022-05-28 01:14:27,014 INFO [train.py:761] (5/8) Epoch 6, batch 800, loss[loss=0.3181, simple_loss=0.3941, pruned_loss=0.121, over 4650.00 frames.], tot_loss[loss=0.3139, simple_loss=0.3908, pruned_loss=0.1185, over 948263.98 frames.], batch size: 11, lr: 3.37e-04
2022-05-28 01:15:05,201 INFO [train.py:761] (5/8) Epoch 6, batch 850, loss[loss=0.3604, simple_loss=0.4335, pruned_loss=0.1437, over 4976.00 frames.], tot_loss[loss=0.3141, simple_loss=0.391, pruned_loss=0.1186, over 953044.63 frames.], batch size: 15, lr: 3.38e-04
2022-05-28 01:15:42,957 INFO [train.py:761] (5/8) Epoch 6, batch 900, loss[loss=0.324, simple_loss=0.3919, pruned_loss=0.128, over 4923.00 frames.], tot_loss[loss=0.3162, simple_loss=0.3929, pruned_loss=0.1198, over 957618.22 frames.], batch size: 13, lr: 3.38e-04
2022-05-28 01:16:20,736 INFO [train.py:761] (5/8) Epoch 6, batch 950, loss[loss=0.2864, simple_loss=0.3658, pruned_loss=0.1035, over 4563.00 frames.], tot_loss[loss=0.3181, simple_loss=0.3949, pruned_loss=0.1206, over 960840.91 frames.], batch size: 10, lr: 3.39e-04
2022-05-28 01:16:59,136 INFO [train.py:761] (5/8) Epoch 6, batch 1000, loss[loss=0.2845, simple_loss=0.3457, pruned_loss=0.1116, over 4646.00 frames.], tot_loss[loss=0.3201, simple_loss=0.3961, pruned_loss=0.1221, over 961651.14 frames.], batch size: 11, lr: 3.39e-04
2022-05-28 01:17:36,744 INFO [train.py:761] (5/8) Epoch 6, batch 1050, loss[loss=0.3523, simple_loss=0.4401, pruned_loss=0.1323, over 4850.00 frames.], tot_loss[loss=0.3213, simple_loss=0.3967, pruned_loss=0.1229, over 962767.28 frames.], batch size: 14, lr: 3.40e-04
2022-05-28 01:18:14,804 INFO [train.py:761] (5/8) Epoch 6, batch 1100, loss[loss=0.3355, simple_loss=0.4079, pruned_loss=0.1315, over 4844.00 frames.], tot_loss[loss=0.3218, simple_loss=0.3974, pruned_loss=0.1231, over 963982.20 frames.], batch size: 14, lr: 3.40e-04
2022-05-28 01:18:52,924 INFO [train.py:761] (5/8) Epoch 6, batch 1150, loss[loss=0.2745, simple_loss=0.3563, pruned_loss=0.09633, over 4858.00 frames.], tot_loss[loss=0.3202, simple_loss=0.3959, pruned_loss=0.1222, over 965538.21 frames.], batch size: 13, lr: 3.41e-04
2022-05-28 01:19:30,996 INFO [train.py:761] (5/8) Epoch 6, batch 1200, loss[loss=0.3035, simple_loss=0.3941, pruned_loss=0.1064, over 4914.00 frames.], tot_loss[loss=0.3189, simple_loss=0.3954, pruned_loss=0.1212, over 965625.45 frames.], batch size: 17, lr: 3.41e-04
2022-05-28 01:20:09,098 INFO [train.py:761] (5/8) Epoch 6, batch 1250, loss[loss=0.2507, simple_loss=0.3308, pruned_loss=0.08533, over 4718.00 frames.], tot_loss[loss=0.3193, simple_loss=0.3946, pruned_loss=0.122, over 965183.22 frames.], batch size: 12, lr: 3.42e-04
2022-05-28 01:20:46,929 INFO [train.py:761] (5/8) Epoch 6, batch 1300, loss[loss=0.3142, simple_loss=0.3954, pruned_loss=0.1165, over 4873.00 frames.], tot_loss[loss=0.3188, simple_loss=0.3943, pruned_loss=0.1217, over 965841.88 frames.], batch size: 17, lr: 3.42e-04
2022-05-28 01:21:24,728 INFO [train.py:761] (5/8) Epoch 6, batch 1350, loss[loss=0.267, simple_loss=0.3333, pruned_loss=0.1004, over 4873.00 frames.], tot_loss[loss=0.3195, simple_loss=0.3947, pruned_loss=0.1221, over 966296.59 frames.], batch size: 12, lr: 3.43e-04
2022-05-28 01:22:03,235 INFO [train.py:761] (5/8) Epoch 6, batch 1400, loss[loss=0.3558, simple_loss=0.4224, pruned_loss=0.1446, over 4890.00 frames.], tot_loss[loss=0.3188, simple_loss=0.3941, pruned_loss=0.1218, over 965530.42 frames.], batch size: 17, lr: 3.43e-04
2022-05-28 01:22:40,782 INFO [train.py:761] (5/8) Epoch 6, batch 1450, loss[loss=0.3067, simple_loss=0.3738, pruned_loss=0.1198, over 4864.00 frames.], tot_loss[loss=0.3174, simple_loss=0.3934, pruned_loss=0.1207, over 965677.37 frames.], batch size: 13, lr: 3.44e-04
2022-05-28 01:23:18,851 INFO [train.py:761] (5/8) Epoch 6, batch 1500, loss[loss=0.3121, simple_loss=0.3877, pruned_loss=0.1182, over 4658.00 frames.], tot_loss[loss=0.3154, simple_loss=0.3916, pruned_loss=0.1196, over 964680.28 frames.], batch size: 12, lr: 3.44e-04
2022-05-28 01:23:56,551 INFO [train.py:761] (5/8) Epoch 6, batch 1550, loss[loss=0.3119, simple_loss=0.3916, pruned_loss=0.1161, over 4860.00 frames.], tot_loss[loss=0.3154, simple_loss=0.3914, pruned_loss=0.1197, over 966345.65 frames.], batch size: 14, lr: 3.45e-04
2022-05-28 01:24:34,719 INFO [train.py:761] (5/8) Epoch 6, batch 1600, loss[loss=0.3373, simple_loss=0.4101, pruned_loss=0.1322, over 4886.00 frames.], tot_loss[loss=0.3153, simple_loss=0.3912, pruned_loss=0.1197, over 966305.05 frames.], batch size: 17, lr: 3.45e-04
2022-05-28 01:25:12,660 INFO [train.py:761] (5/8) Epoch 6, batch 1650, loss[loss=0.3691, simple_loss=0.4409, pruned_loss=0.1487, over 4900.00 frames.], tot_loss[loss=0.3159, simple_loss=0.3918, pruned_loss=0.12, over 965228.96 frames.], batch size: 46, lr: 3.46e-04
2022-05-28 01:25:51,104 INFO [train.py:761] (5/8) Epoch 6, batch 1700, loss[loss=0.2588, simple_loss=0.3463, pruned_loss=0.08562, over 4723.00 frames.], tot_loss[loss=0.3159, simple_loss=0.3919, pruned_loss=0.12, over 965429.30 frames.], batch size: 12, lr: 3.46e-04
2022-05-28 01:26:28,922 INFO [train.py:761] (5/8) Epoch 6, batch 1750, loss[loss=0.2901, simple_loss=0.3802, pruned_loss=0.1, over 4728.00 frames.], tot_loss[loss=0.3155, simple_loss=0.3918, pruned_loss=0.1196, over 966039.10 frames.], batch size: 13, lr: 3.47e-04
2022-05-28 01:27:06,585 INFO [train.py:761] (5/8) Epoch 6, batch 1800, loss[loss=0.3899, simple_loss=0.4572, pruned_loss=0.1613, over 4767.00 frames.], tot_loss[loss=0.3156, simple_loss=0.3918, pruned_loss=0.1197, over 965731.26 frames.], batch size: 20, lr: 3.47e-04
2022-05-28 01:27:44,836 INFO [train.py:761] (5/8) Epoch 6, batch 1850, loss[loss=0.3069, simple_loss=0.3952, pruned_loss=0.1094, over 4913.00 frames.], tot_loss[loss=0.3166, simple_loss=0.3927, pruned_loss=0.1202, over 966677.96 frames.], batch size: 14, lr: 3.47e-04
2022-05-28 01:28:22,837 INFO [train.py:761] (5/8) Epoch 6, batch 1900, loss[loss=0.2904, simple_loss=0.3839, pruned_loss=0.09846, over 4925.00 frames.], tot_loss[loss=0.3152, simple_loss=0.3918, pruned_loss=0.1193, over 966389.07 frames.], batch size: 14, lr: 3.48e-04
2022-05-28 01:29:00,856 INFO [train.py:761] (5/8) Epoch 6, batch 1950, loss[loss=0.3455, simple_loss=0.4391, pruned_loss=0.126, over 4796.00 frames.], tot_loss[loss=0.3142, simple_loss=0.3902, pruned_loss=0.1191, over 967033.61 frames.], batch size: 16, lr: 3.48e-04
2022-05-28 01:29:38,520 INFO [train.py:761] (5/8) Epoch 6, batch 2000, loss[loss=0.2974, simple_loss=0.3818, pruned_loss=0.1065, over 4664.00 frames.], tot_loss[loss=0.3144, simple_loss=0.3905, pruned_loss=0.1192, over 966200.81 frames.], batch size: 13, lr: 3.49e-04
2022-05-28 01:30:16,680 INFO [train.py:761] (5/8) Epoch 6, batch 2050, loss[loss=0.264, simple_loss=0.3508, pruned_loss=0.08861, over 4673.00 frames.], tot_loss[loss=0.313, simple_loss=0.3899, pruned_loss=0.118, over 965530.98 frames.], batch size: 13, lr: 3.49e-04
2022-05-28 01:30:55,110 INFO [train.py:761] (5/8) Epoch 6, batch 2100, loss[loss=0.303, simple_loss=0.4048, pruned_loss=0.1006, over 4719.00 frames.], tot_loss[loss=0.3143, simple_loss=0.3916, pruned_loss=0.1185, over 965238.38 frames.], batch size: 14, lr: 3.50e-04
2022-05-28 01:31:32,984 INFO [train.py:761] (5/8) Epoch 6, batch 2150, loss[loss=0.334, simple_loss=0.4259, pruned_loss=0.1211, over 4767.00 frames.], tot_loss[loss=0.3139, simple_loss=0.3911, pruned_loss=0.1184, over 965425.27 frames.], batch size: 15, lr: 3.50e-04
2022-05-28 01:32:10,648 INFO [train.py:761] (5/8) Epoch 6, batch 2200, loss[loss=0.3273, simple_loss=0.4039, pruned_loss=0.1253, over 4771.00 frames.], tot_loss[loss=0.3113, simple_loss=0.3887, pruned_loss=0.1169, over 964762.80 frames.], batch size: 20, lr: 3.51e-04
2022-05-28 01:32:48,269 INFO [train.py:761] (5/8) Epoch 6, batch 2250, loss[loss=0.3278, simple_loss=0.4017, pruned_loss=0.127, over 4974.00 frames.], tot_loss[loss=0.3108, simple_loss=0.3882, pruned_loss=0.1167, over 966036.53 frames.], batch size: 14, lr: 3.51e-04
2022-05-28 01:33:26,034 INFO [train.py:761] (5/8) Epoch 6, batch 2300, loss[loss=0.2809, simple_loss=0.3555, pruned_loss=0.1032, over 4840.00 frames.], tot_loss[loss=0.3109, simple_loss=0.3882, pruned_loss=0.1168, over 965222.78 frames.], batch size: 18, lr: 3.52e-04
2022-05-28 01:34:03,318 INFO [train.py:761] (5/8) Epoch 6, batch 2350, loss[loss=0.3322, simple_loss=0.4051, pruned_loss=0.1296, over 4793.00 frames.], tot_loss[loss=0.3112, simple_loss=0.3889, pruned_loss=0.1168, over 966485.89 frames.], batch size: 16, lr: 3.52e-04
2022-05-28 01:34:41,301 INFO [train.py:761] (5/8) Epoch 6, batch 2400, loss[loss=0.306, simple_loss=0.3941, pruned_loss=0.109, over 4886.00 frames.], tot_loss[loss=0.3129, simple_loss=0.39, pruned_loss=0.1179, over 967324.06 frames.], batch size: 15, lr: 3.53e-04
2022-05-28 01:35:19,362 INFO [train.py:761] (5/8) Epoch 6, batch 2450, loss[loss=0.2465, simple_loss=0.336, pruned_loss=0.07851, over 4743.00 frames.], tot_loss[loss=0.3123, simple_loss=0.3899, pruned_loss=0.1174, over 967576.90 frames.], batch size: 11, lr: 3.53e-04
2022-05-28 01:35:57,472 INFO [train.py:761] (5/8) Epoch 6, batch 2500, loss[loss=0.3391, simple_loss=0.4176, pruned_loss=0.1303, over 4793.00 frames.], tot_loss[loss=0.3144, simple_loss=0.3907, pruned_loss=0.119, over 966248.75 frames.], batch size: 16, lr: 3.54e-04
2022-05-28 01:36:35,190 INFO [train.py:761] (5/8) Epoch 6, batch 2550, loss[loss=0.3598, simple_loss=0.434, pruned_loss=0.1428, over 4841.00 frames.], tot_loss[loss=0.312, simple_loss=0.3887, pruned_loss=0.1177, over 966646.57 frames.], batch size: 13, lr: 3.54e-04
2022-05-28 01:37:13,702 INFO [train.py:761] (5/8) Epoch 6, batch 2600, loss[loss=0.2787, simple_loss=0.3628, pruned_loss=0.09728, over 4969.00 frames.], tot_loss[loss=0.3132, simple_loss=0.3895, pruned_loss=0.1185, over 967368.83 frames.], batch size: 14, lr: 3.55e-04
2022-05-28 01:37:51,651 INFO [train.py:761] (5/8) Epoch 6, batch 2650, loss[loss=0.3357, simple_loss=0.4179, pruned_loss=0.1268, over 4851.00 frames.], tot_loss[loss=0.3136, simple_loss=0.3899, pruned_loss=0.1186, over 967748.65 frames.], batch size: 14, lr: 3.55e-04
2022-05-28 01:38:30,179 INFO [train.py:761] (5/8) Epoch 6, batch 2700, loss[loss=0.3117, simple_loss=0.394, pruned_loss=0.1147, over 4783.00 frames.], tot_loss[loss=0.3134, simple_loss=0.3898, pruned_loss=0.1185, over 967148.85 frames.], batch size: 14, lr: 3.56e-04
2022-05-28 01:39:07,990 INFO [train.py:761] (5/8) Epoch 6, batch 2750, loss[loss=0.257, simple_loss=0.3282, pruned_loss=0.09289, over 4628.00 frames.], tot_loss[loss=0.314, simple_loss=0.3902, pruned_loss=0.1189, over 966995.52 frames.], batch size: 11, lr: 3.56e-04
2022-05-28 01:39:45,783 INFO [train.py:761] (5/8) Epoch 6, batch 2800, loss[loss=0.2846, simple_loss=0.3791, pruned_loss=0.09506, over 4915.00 frames.], tot_loss[loss=0.3135, simple_loss=0.39, pruned_loss=0.1185, over 966917.56 frames.], batch size: 14, lr: 3.57e-04
2022-05-28 01:40:23,601 INFO [train.py:761] (5/8) Epoch 6, batch 2850, loss[loss=0.4139, simple_loss=0.4669, pruned_loss=0.1805, over 4796.00 frames.], tot_loss[loss=0.3145, simple_loss=0.3905, pruned_loss=0.1192, over 967006.92 frames.], batch size: 14, lr: 3.57e-04
2022-05-28 01:41:01,462 INFO [train.py:761] (5/8) Epoch 6, batch 2900, loss[loss=0.2997, simple_loss=0.3881, pruned_loss=0.1057, over 4775.00 frames.], tot_loss[loss=0.3126, simple_loss=0.3891, pruned_loss=0.1181, over 966359.36 frames.], batch size: 15, lr: 3.58e-04
2022-05-28 01:41:39,363 INFO [train.py:761] (5/8) Epoch 6, batch 2950, loss[loss=0.3067, simple_loss=0.3878, pruned_loss=0.1128, over 4890.00 frames.], tot_loss[loss=0.3099, simple_loss=0.3874, pruned_loss=0.1162, over 966342.48 frames.], batch size: 18, lr: 3.58e-04
2022-05-28 01:42:17,583 INFO [train.py:761] (5/8) Epoch 6, batch 3000, loss[loss=0.3707, simple_loss=0.44, pruned_loss=0.1507, over 4849.00 frames.], tot_loss[loss=0.3096, simple_loss=0.3875, pruned_loss=0.1158, over 966027.97 frames.], batch size: 14, lr: 3.59e-04
2022-05-28 01:42:17,583 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 01:42:27,496 INFO [train.py:790] (5/8) Epoch 6, validation: loss=0.2709, simple_loss=0.372, pruned_loss=0.0849, over 944034.00 frames.
2022-05-28 01:43:05,230 INFO [train.py:761] (5/8) Epoch 6, batch 3050, loss[loss=0.2818, simple_loss=0.3408, pruned_loss=0.1114, over 4887.00 frames.], tot_loss[loss=0.3096, simple_loss=0.3871, pruned_loss=0.116, over 965385.63 frames.], batch size: 12, lr: 3.59e-04
2022-05-28 01:43:43,647 INFO [train.py:761] (5/8) Epoch 6, batch 3100, loss[loss=0.3168, simple_loss=0.408, pruned_loss=0.1128, over 4817.00 frames.], tot_loss[loss=0.3113, simple_loss=0.3874, pruned_loss=0.1176, over 965794.74 frames.], batch size: 20, lr: 3.60e-04
2022-05-28 01:44:21,931 INFO [train.py:761] (5/8) Epoch 6, batch 3150, loss[loss=0.2947, simple_loss=0.3708, pruned_loss=0.1093, over 4789.00 frames.], tot_loss[loss=0.3154, simple_loss=0.39, pruned_loss=0.1204, over 965856.01 frames.], batch size: 13, lr: 3.60e-04
2022-05-28 01:44:59,943 INFO [train.py:761] (5/8) Epoch 6, batch 3200, loss[loss=0.297, simple_loss=0.3725, pruned_loss=0.1107, over 4856.00 frames.], tot_loss[loss=0.3198, simple_loss=0.3919, pruned_loss=0.1239, over 966918.12 frames.], batch size: 14, lr: 3.61e-04
2022-05-28 01:45:37,824 INFO [train.py:761] (5/8) Epoch 6, batch 3250, loss[loss=0.3195, simple_loss=0.372, pruned_loss=0.1335, over 4727.00 frames.], tot_loss[loss=0.3267, simple_loss=0.3953, pruned_loss=0.129, over 968263.02 frames.], batch size: 11, lr: 3.61e-04
2022-05-28 01:46:16,123 INFO [train.py:761] (5/8) Epoch 6, batch 3300, loss[loss=0.4222, simple_loss=0.4674, pruned_loss=0.1886, over 4892.00 frames.], tot_loss[loss=0.3341, simple_loss=0.3997, pruned_loss=0.1342, over 968805.21 frames.], batch size: 26, lr: 3.62e-04
2022-05-28 01:46:54,173 INFO [train.py:761] (5/8) Epoch 6, batch 3350, loss[loss=0.4384, simple_loss=0.4765, pruned_loss=0.2001, over 4726.00 frames.], tot_loss[loss=0.3365, simple_loss=0.401, pruned_loss=0.136, over 968562.67 frames.], batch size: 13, lr: 3.62e-04
2022-05-28 01:47:32,632 INFO [train.py:761] (5/8) Epoch 6, batch 3400, loss[loss=0.2949, simple_loss=0.3652, pruned_loss=0.1123, over 4804.00 frames.], tot_loss[loss=0.3395, simple_loss=0.4026, pruned_loss=0.1382, over 968195.61 frames.], batch size: 12, lr: 3.63e-04
2022-05-28 01:48:10,988 INFO [train.py:761] (5/8) Epoch 6, batch 3450, loss[loss=0.346, simple_loss=0.3991, pruned_loss=0.1465, over 4783.00 frames.], tot_loss[loss=0.3443, simple_loss=0.4053, pruned_loss=0.1417, over 968117.54 frames.], batch size: 14, lr: 3.63e-04
2022-05-28 01:48:49,312 INFO [train.py:761] (5/8) Epoch 6, batch 3500, loss[loss=0.3252, simple_loss=0.3849, pruned_loss=0.1327, over 4867.00 frames.], tot_loss[loss=0.3449, simple_loss=0.4054, pruned_loss=0.1422, over 967772.02 frames.], batch size: 17, lr: 3.64e-04
2022-05-28 01:49:27,245 INFO [train.py:761] (5/8) Epoch 6, batch 3550, loss[loss=0.3456, simple_loss=0.3872, pruned_loss=0.152, over 4799.00 frames.], tot_loss[loss=0.3437, simple_loss=0.4036, pruned_loss=0.1419, over 966142.48 frames.], batch size: 12, lr: 3.64e-04
2022-05-28 01:50:05,299 INFO [train.py:761] (5/8) Epoch 6, batch 3600, loss[loss=0.4216, simple_loss=0.4746, pruned_loss=0.1843, over 4810.00 frames.], tot_loss[loss=0.3473, simple_loss=0.4054, pruned_loss=0.1446, over 966578.66 frames.], batch size: 16, lr: 3.65e-04
2022-05-28 01:50:43,796 INFO [train.py:761] (5/8) Epoch 6, batch 3650, loss[loss=0.371, simple_loss=0.4274, pruned_loss=0.1572, over 4761.00 frames.], tot_loss[loss=0.348, simple_loss=0.4055, pruned_loss=0.1453, over 965944.00 frames.], batch size: 15, lr: 3.65e-04
2022-05-28 01:51:21,972 INFO [train.py:761] (5/8) Epoch 6, batch 3700, loss[loss=0.3228, simple_loss=0.3993, pruned_loss=0.1232, over 4672.00 frames.], tot_loss[loss=0.3518, simple_loss=0.4083, pruned_loss=0.1477, over 966156.95 frames.], batch size: 13, lr: 3.66e-04
2022-05-28 01:51:59,591 INFO [train.py:761] (5/8) Epoch 6, batch 3750, loss[loss=0.3535, simple_loss=0.4178, pruned_loss=0.1446, over 4826.00 frames.], tot_loss[loss=0.3544, simple_loss=0.4103, pruned_loss=0.1493, over 965688.43 frames.], batch size: 18, lr: 3.66e-04
2022-05-28 01:52:37,495 INFO [train.py:761] (5/8) Epoch 6, batch 3800, loss[loss=0.2611, simple_loss=0.319, pruned_loss=0.1016, over 4559.00 frames.], tot_loss[loss=0.3559, simple_loss=0.4112, pruned_loss=0.1503, over 965392.91 frames.], batch size: 10, lr: 3.67e-04
2022-05-28 01:53:15,562 INFO [train.py:761] (5/8) Epoch 6, batch 3850, loss[loss=0.3181, simple_loss=0.369, pruned_loss=0.1336, over 4661.00 frames.], tot_loss[loss=0.3566, simple_loss=0.4116, pruned_loss=0.1508, over 965184.20 frames.], batch size: 11, lr: 3.67e-04
2022-05-28 01:53:54,025 INFO [train.py:761] (5/8) Epoch 6, batch 3900, loss[loss=0.4272, simple_loss=0.456, pruned_loss=0.1992, over 4982.00 frames.], tot_loss[loss=0.3546, simple_loss=0.4096, pruned_loss=0.1498, over 965080.48 frames.], batch size: 21, lr: 3.68e-04
2022-05-28 01:54:31,917 INFO [train.py:761] (5/8) Epoch 6, batch 3950, loss[loss=0.3087, simple_loss=0.3673, pruned_loss=0.125, over 4678.00 frames.], tot_loss[loss=0.3576, simple_loss=0.4116, pruned_loss=0.1517, over 964214.54 frames.], batch size: 13, lr: 3.68e-04
2022-05-28 01:55:10,210 INFO [train.py:761] (5/8) Epoch 6, batch 4000, loss[loss=0.3312, simple_loss=0.4023, pruned_loss=0.13, over 4783.00 frames.], tot_loss[loss=0.3544, simple_loss=0.4098, pruned_loss=0.1495, over 965111.09 frames.], batch size: 15, lr: 3.68e-04
2022-05-28 01:55:48,006 INFO [train.py:761] (5/8) Epoch 6, batch 4050, loss[loss=0.3678, simple_loss=0.4403, pruned_loss=0.1476, over 4974.00 frames.], tot_loss[loss=0.353, simple_loss=0.4088, pruned_loss=0.1486, over 964732.71 frames.], batch size: 14, lr: 3.69e-04
2022-05-28 01:56:26,241 INFO [train.py:761] (5/8) Epoch 6, batch 4100, loss[loss=0.2998, simple_loss=0.352, pruned_loss=0.1238, over 4829.00 frames.], tot_loss[loss=0.3525, simple_loss=0.4082, pruned_loss=0.1484, over 964116.25 frames.], batch size: 11, lr: 3.69e-04
2022-05-28 01:57:04,677 INFO [train.py:761] (5/8) Epoch 6, batch 4150, loss[loss=0.3557, simple_loss=0.4176, pruned_loss=0.1469, over 4870.00 frames.], tot_loss[loss=0.3545, simple_loss=0.4097, pruned_loss=0.1497, over 964529.81 frames.], batch size: 15, lr: 3.70e-04
2022-05-28 01:57:42,300 INFO [train.py:761] (5/8) Epoch 6, batch 4200, loss[loss=0.3095, simple_loss=0.3842, pruned_loss=0.1174, over 4787.00 frames.], tot_loss[loss=0.3531, simple_loss=0.4084, pruned_loss=0.1489, over 965494.20 frames.], batch size: 13, lr: 3.70e-04
2022-05-28 01:58:20,597 INFO [train.py:761] (5/8) Epoch 6, batch 4250, loss[loss=0.3588, simple_loss=0.4232, pruned_loss=0.1472, over 4852.00 frames.], tot_loss[loss=0.3547, simple_loss=0.4096, pruned_loss=0.1499, over 967167.30 frames.], batch size: 14, lr: 3.71e-04
2022-05-28 01:58:59,442 INFO [train.py:761] (5/8) Epoch 6, batch 4300, loss[loss=0.3537, simple_loss=0.4187, pruned_loss=0.1443, over 4877.00 frames.], tot_loss[loss=0.352, simple_loss=0.4075, pruned_loss=0.1483, over 967173.51 frames.], batch size: 17, lr: 3.71e-04
2022-05-28 01:59:37,326 INFO [train.py:761] (5/8) Epoch 6, batch 4350, loss[loss=0.3428, simple_loss=0.412, pruned_loss=0.1368, over 4794.00 frames.], tot_loss[loss=0.352, simple_loss=0.4072, pruned_loss=0.1484, over 967720.78 frames.], batch size: 14, lr: 3.72e-04
2022-05-28 02:00:15,044 INFO [train.py:761] (5/8) Epoch 6, batch 4400, loss[loss=0.3202, simple_loss=0.4042, pruned_loss=0.1181, over 4726.00 frames.], tot_loss[loss=0.354, simple_loss=0.4086, pruned_loss=0.1497, over 967895.41 frames.], batch size: 14, lr: 3.72e-04
2022-05-28 02:00:53,449 INFO [train.py:761] (5/8) Epoch 6, batch 4450, loss[loss=0.2692, simple_loss=0.3423, pruned_loss=0.09804, over 4662.00 frames.], tot_loss[loss=0.3534, simple_loss=0.4081, pruned_loss=0.1493, over 967033.56 frames.], batch size: 12, lr: 3.73e-04
2022-05-28 02:01:31,336 INFO [train.py:761] (5/8) Epoch 6, batch 4500, loss[loss=0.3921, simple_loss=0.4358, pruned_loss=0.1741, over 4952.00 frames.], tot_loss[loss=0.357, simple_loss=0.4112, pruned_loss=0.1514, over 966713.78 frames.], batch size: 26, lr: 3.73e-04
2022-05-28 02:02:09,639 INFO [train.py:761] (5/8) Epoch 6, batch 4550, loss[loss=0.3729, simple_loss=0.4338, pruned_loss=0.156, over 4930.00 frames.], tot_loss[loss=0.3525, simple_loss=0.4081, pruned_loss=0.1484, over 965743.26 frames.], batch size: 13, lr: 3.74e-04
2022-05-28 02:02:48,032 INFO [train.py:761] (5/8) Epoch 6, batch 4600, loss[loss=0.308, simple_loss=0.3671, pruned_loss=0.1245, over 4654.00 frames.], tot_loss[loss=0.3508, simple_loss=0.4068, pruned_loss=0.1474, over 965471.00 frames.], batch size: 12, lr: 3.74e-04
2022-05-28 02:03:25,748 INFO [train.py:761] (5/8) Epoch 6, batch 4650, loss[loss=0.322, simple_loss=0.3924, pruned_loss=0.1258, over 4920.00 frames.], tot_loss[loss=0.3498, simple_loss=0.4061, pruned_loss=0.1467, over 965775.55 frames.], batch size: 14, lr: 3.75e-04
2022-05-28 02:04:03,853 INFO [train.py:761] (5/8) Epoch 6, batch 4700, loss[loss=0.3231, simple_loss=0.399, pruned_loss=0.1236, over 4768.00 frames.], tot_loss[loss=0.3503, simple_loss=0.4059, pruned_loss=0.1473, over 966744.97 frames.], batch size: 15, lr: 3.75e-04
2022-05-28 02:04:41,958 INFO [train.py:761] (5/8) Epoch 6, batch 4750, loss[loss=0.3774, simple_loss=0.4409, pruned_loss=0.157, over 4972.00 frames.], tot_loss[loss=0.3476, simple_loss=0.4042, pruned_loss=0.1455, over 967780.34 frames.], batch size: 15, lr: 3.76e-04
2022-05-28 02:05:19,846 INFO [train.py:761] (5/8) Epoch 6, batch 4800, loss[loss=0.3046, simple_loss=0.3532, pruned_loss=0.128, over 4854.00 frames.], tot_loss[loss=0.3463, simple_loss=0.4027, pruned_loss=0.145, over 966883.15 frames.], batch size: 13, lr: 3.76e-04
2022-05-28 02:05:57,893 INFO [train.py:761] (5/8) Epoch 6, batch 4850, loss[loss=0.3565, simple_loss=0.4191, pruned_loss=0.1469, over 4784.00 frames.], tot_loss[loss=0.3457, simple_loss=0.4021, pruned_loss=0.1446, over 965880.77 frames.], batch size: 14, lr: 3.77e-04
2022-05-28 02:06:36,057 INFO [train.py:761] (5/8) Epoch 6, batch 4900, loss[loss=0.4038, simple_loss=0.4415, pruned_loss=0.1831, over 4857.00 frames.], tot_loss[loss=0.344, simple_loss=0.4005, pruned_loss=0.1438, over 966820.13 frames.], batch size: 17, lr: 3.77e-04
2022-05-28 02:07:14,154 INFO [train.py:761] (5/8) Epoch 6, batch 4950, loss[loss=0.254, simple_loss=0.3172, pruned_loss=0.09536, over 4639.00 frames.], tot_loss[loss=0.3466, simple_loss=0.4032, pruned_loss=0.145, over 966873.66 frames.], batch size: 11, lr: 3.78e-04
2022-05-28 02:07:51,942 INFO [train.py:761] (5/8) Epoch 6, batch 5000, loss[loss=0.3513, simple_loss=0.4104, pruned_loss=0.1461, over 4874.00 frames.], tot_loss[loss=0.3456, simple_loss=0.4025, pruned_loss=0.1443, over 966356.36 frames.], batch size: 15, lr: 3.78e-04
2022-05-28 02:08:29,962 INFO [train.py:761] (5/8) Epoch 6, batch 5050, loss[loss=0.2869, simple_loss=0.3645, pruned_loss=0.1047, over 4611.00 frames.], tot_loss[loss=0.3465, simple_loss=0.403, pruned_loss=0.145, over 966143.77 frames.], batch size: 12, lr: 3.79e-04
2022-05-28 02:09:07,917 INFO [train.py:761] (5/8) Epoch 6, batch 5100, loss[loss=0.3772, simple_loss=0.4169, pruned_loss=0.1687, over 4858.00 frames.], tot_loss[loss=0.3486, simple_loss=0.4043, pruned_loss=0.1465, over 966375.46 frames.], batch size: 45, lr: 3.79e-04
2022-05-28 02:09:46,128 INFO [train.py:761] (5/8) Epoch 6, batch 5150, loss[loss=0.3375, simple_loss=0.3994, pruned_loss=0.1378, over 4898.00 frames.], tot_loss[loss=0.3501, simple_loss=0.4055, pruned_loss=0.1474, over 966547.33 frames.], batch size: 21, lr: 3.80e-04
2022-05-28 02:10:25,104 INFO [train.py:761] (5/8) Epoch 6, batch 5200, loss[loss=0.3461, simple_loss=0.4062, pruned_loss=0.143, over 4877.00 frames.], tot_loss[loss=0.3486, simple_loss=0.405, pruned_loss=0.1461, over 966258.69 frames.], batch size: 17, lr: 3.80e-04
2022-05-28 02:11:03,557 INFO [train.py:761] (5/8) Epoch 6, batch 5250, loss[loss=0.3431, simple_loss=0.3996, pruned_loss=0.1433, over 4975.00 frames.], tot_loss[loss=0.3473, simple_loss=0.4037, pruned_loss=0.1454, over 966235.60 frames.], batch size: 15, lr: 3.81e-04
2022-05-28 02:11:42,217 INFO [train.py:761] (5/8) Epoch 6, batch 5300, loss[loss=0.3105, simple_loss=0.3847, pruned_loss=0.1182, over 4860.00 frames.], tot_loss[loss=0.3475, simple_loss=0.4041, pruned_loss=0.1455, over 966416.56 frames.], batch size: 18, lr: 3.81e-04
2022-05-28 02:12:20,493 INFO [train.py:761] (5/8) Epoch 6, batch 5350, loss[loss=0.436, simple_loss=0.4663, pruned_loss=0.2028, over 4970.00 frames.], tot_loss[loss=0.3451, simple_loss=0.4023, pruned_loss=0.144, over 965598.24 frames.], batch size: 47, lr: 3.82e-04
2022-05-28 02:12:59,388 INFO [train.py:761] (5/8) Epoch 6, batch 5400, loss[loss=0.4543, simple_loss=0.4881, pruned_loss=0.2103, over 4958.00 frames.], tot_loss[loss=0.3473, simple_loss=0.4045, pruned_loss=0.1451, over 966323.91 frames.], batch size: 16, lr: 3.82e-04
2022-05-28 02:13:37,698 INFO [train.py:761] (5/8) Epoch 6, batch 5450, loss[loss=0.3822, simple_loss=0.4349, pruned_loss=0.1648, over 4785.00 frames.], tot_loss[loss=0.3476, simple_loss=0.4049, pruned_loss=0.1452, over 966976.18 frames.], batch size: 16, lr: 3.83e-04
2022-05-28 02:14:16,014 INFO [train.py:761] (5/8) Epoch 6, batch 5500, loss[loss=0.3354, simple_loss=0.4054, pruned_loss=0.1327, over 4879.00 frames.], tot_loss[loss=0.3458, simple_loss=0.4036, pruned_loss=0.144, over 966281.82 frames.], batch size: 17, lr: 3.83e-04
2022-05-28 02:14:53,466 INFO [train.py:761] (5/8) Epoch 6, batch 5550, loss[loss=0.3153, simple_loss=0.379, pruned_loss=0.1258, over 4729.00 frames.], tot_loss[loss=0.3451, simple_loss=0.403, pruned_loss=0.1436, over 965428.36 frames.], batch size: 12, lr: 3.84e-04
2022-05-28 02:15:31,667 INFO [train.py:761] (5/8) Epoch 6, batch 5600, loss[loss=0.3529, simple_loss=0.4172, pruned_loss=0.1444, over 4926.00 frames.], tot_loss[loss=0.3443, simple_loss=0.4023, pruned_loss=0.1431, over 965118.16 frames.], batch size: 13, lr: 3.84e-04
2022-05-28 02:16:10,259 INFO [train.py:761] (5/8) Epoch 6, batch 5650, loss[loss=0.3512, simple_loss=0.4152, pruned_loss=0.1436, over 4847.00 frames.], tot_loss[loss=0.342, simple_loss=0.401, pruned_loss=0.1416, over 965229.95 frames.], batch size: 18, lr: 3.85e-04
2022-05-28 02:16:48,514 INFO [train.py:761] (5/8) Epoch 6, batch 5700, loss[loss=0.2883, simple_loss=0.3503, pruned_loss=0.1132, over 4782.00 frames.], tot_loss[loss=0.3422, simple_loss=0.4009, pruned_loss=0.1417, over 965452.29 frames.], batch size: 13, lr: 3.85e-04
2022-05-28 02:17:26,848 INFO [train.py:761] (5/8) Epoch 6, batch 5750, loss[loss=0.2712, simple_loss=0.3501, pruned_loss=0.09613, over 4815.00 frames.], tot_loss[loss=0.3422, simple_loss=0.401, pruned_loss=0.1417, over 966341.03 frames.], batch size: 11, lr: 3.86e-04
2022-05-28 02:18:05,380 INFO [train.py:761] (5/8) Epoch 6, batch 5800, loss[loss=0.3342, simple_loss=0.4004, pruned_loss=0.134, over 4916.00 frames.], tot_loss[loss=0.3444, simple_loss=0.4023, pruned_loss=0.1433, over 966049.40 frames.], batch size: 14, lr: 3.86e-04
2022-05-28 02:18:43,622 INFO [train.py:761] (5/8) Epoch 6, batch 5850, loss[loss=0.3499, simple_loss=0.4004, pruned_loss=0.1497, over 4734.00 frames.], tot_loss[loss=0.3482, simple_loss=0.405, pruned_loss=0.1457, over 966899.08 frames.], batch size: 12, lr: 3.87e-04
2022-05-28 02:19:21,738 INFO [train.py:761] (5/8) Epoch 6, batch 5900, loss[loss=0.363, simple_loss=0.4145, pruned_loss=0.1558, over 4722.00 frames.], tot_loss[loss=0.3475, simple_loss=0.404, pruned_loss=0.1454, over 966397.36 frames.], batch size: 13, lr: 3.87e-04
2022-05-28 02:19:59,906 INFO [train.py:761] (5/8) Epoch 6, batch 5950, loss[loss=0.3305, simple_loss=0.3868, pruned_loss=0.1371, over 4733.00 frames.], tot_loss[loss=0.3489, simple_loss=0.4053, pruned_loss=0.1462, over 966602.26 frames.], batch size: 12, lr: 3.88e-04
2022-05-28 02:20:38,516 INFO [train.py:761] (5/8) Epoch 6, batch 6000, loss[loss=0.3176, simple_loss=0.3956, pruned_loss=0.1198, over 4721.00 frames.], tot_loss[loss=0.3497, simple_loss=0.4061, pruned_loss=0.1467, over 966646.22 frames.], batch size: 13, lr: 3.88e-04
2022-05-28 02:20:38,517 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 02:20:48,513 INFO [train.py:790] (5/8) Epoch 6, validation: loss=0.2544, simple_loss=0.362, pruned_loss=0.07338, over 944034.00 frames.
2022-05-28 02:21:26,627 INFO [train.py:761] (5/8) Epoch 6, batch 6050, loss[loss=0.3245, simple_loss=0.3593, pruned_loss=0.1449, over 4650.00 frames.], tot_loss[loss=0.35, simple_loss=0.4063, pruned_loss=0.1469, over 966987.06 frames.], batch size: 11, lr: 3.89e-04
2022-05-28 02:22:05,565 INFO [train.py:761] (5/8) Epoch 6, batch 6100, loss[loss=0.3441, simple_loss=0.4126, pruned_loss=0.1378, over 4905.00 frames.], tot_loss[loss=0.3495, simple_loss=0.406, pruned_loss=0.1465, over 966585.34 frames.], batch size: 14, lr: 3.89e-04
2022-05-28 02:22:43,390 INFO [train.py:761] (5/8) Epoch 6, batch 6150, loss[loss=0.3015, simple_loss=0.3726, pruned_loss=0.1152, over 4725.00 frames.], tot_loss[loss=0.3468, simple_loss=0.4045, pruned_loss=0.1446, over 967534.92 frames.], batch size: 12, lr: 3.89e-04
2022-05-28 02:23:22,082 INFO [train.py:761] (5/8) Epoch 6, batch 6200, loss[loss=0.2653, simple_loss=0.3386, pruned_loss=0.09603, over 4976.00 frames.], tot_loss[loss=0.3457, simple_loss=0.4034, pruned_loss=0.144, over 966184.68 frames.], batch size: 12, lr: 3.90e-04
2022-05-28 02:24:00,054 INFO [train.py:761] (5/8) Epoch 6, batch 6250, loss[loss=0.3034, simple_loss=0.3654, pruned_loss=0.1207, over 4876.00 frames.], tot_loss[loss=0.3454, simple_loss=0.4028, pruned_loss=0.144, over 967196.44 frames.], batch size: 12, lr: 3.90e-04
2022-05-28 02:24:41,777 INFO [train.py:761] (5/8) Epoch 6, batch 6300, loss[loss=0.33, simple_loss=0.3906, pruned_loss=0.1347, over 4951.00 frames.], tot_loss[loss=0.3466, simple_loss=0.4043, pruned_loss=0.1445, over 968152.66 frames.], batch size: 26, lr: 3.91e-04
2022-05-28 02:25:19,818 INFO [train.py:761] (5/8) Epoch 6, batch 6350, loss[loss=0.3269, simple_loss=0.3978, pruned_loss=0.128, over 4803.00 frames.], tot_loss[loss=0.346, simple_loss=0.404, pruned_loss=0.144, over 966596.20 frames.], batch size: 20, lr: 3.91e-04
2022-05-28 02:25:58,359 INFO [train.py:761] (5/8) Epoch 6, batch 6400, loss[loss=0.3669, simple_loss=0.4388, pruned_loss=0.1476, over 4976.00 frames.], tot_loss[loss=0.3468, simple_loss=0.405, pruned_loss=0.1443, over 966617.34 frames.], batch size: 15, lr: 3.92e-04
2022-05-28 02:26:36,590 INFO [train.py:761] (5/8) Epoch 6, batch 6450, loss[loss=0.3191, simple_loss=0.3698, pruned_loss=0.1342, over 4728.00 frames.], tot_loss[loss=0.3463, simple_loss=0.4045, pruned_loss=0.1441, over 966179.99 frames.], batch size: 11, lr: 3.92e-04
2022-05-28 02:27:15,409 INFO [train.py:761] (5/8) Epoch 6, batch 6500, loss[loss=0.3145, simple_loss=0.3698, pruned_loss=0.1296, over 4928.00 frames.], tot_loss[loss=0.3438, simple_loss=0.4019, pruned_loss=0.1429, over 966050.86 frames.], batch size: 13, lr: 3.93e-04
2022-05-28 02:27:53,631 INFO [train.py:761] (5/8) Epoch 6, batch 6550, loss[loss=0.2988, simple_loss=0.3574, pruned_loss=0.1201, over 4608.00 frames.], tot_loss[loss=0.3416, simple_loss=0.3997, pruned_loss=0.1418, over 966448.26 frames.], batch size: 10, lr: 3.93e-04
2022-05-28 02:28:31,380 INFO [train.py:761] (5/8) Epoch 6, batch 6600, loss[loss=0.3283, simple_loss=0.3926, pruned_loss=0.132, over 4822.00 frames.], tot_loss[loss=0.3407, simple_loss=0.3996, pruned_loss=0.141, over 965883.32 frames.], batch size: 20, lr: 3.94e-04
2022-05-28 02:29:09,654 INFO [train.py:761] (5/8) Epoch 6, batch 6650, loss[loss=0.2944, simple_loss=0.3491, pruned_loss=0.1198, over 4979.00 frames.], tot_loss[loss=0.34, simple_loss=0.3994, pruned_loss=0.1403, over 965444.43 frames.], batch size: 12, lr: 3.94e-04
2022-05-28 02:29:48,290 INFO [train.py:761] (5/8) Epoch 6, batch 6700, loss[loss=0.4324, simple_loss=0.4672, pruned_loss=0.1988, over 4855.00 frames.], tot_loss[loss=0.3424, simple_loss=0.401, pruned_loss=0.1419, over 965814.83 frames.], batch size: 18, lr: 3.95e-04
2022-05-28 02:30:42,275 INFO [train.py:761] (5/8) Epoch 7, batch 0, loss[loss=0.2772, simple_loss=0.3553, pruned_loss=0.09949, over 4883.00 frames.], tot_loss[loss=0.2772, simple_loss=0.3553, pruned_loss=0.09949, over 4883.00 frames.], batch size: 12, lr: 3.95e-04
2022-05-28 02:31:20,499 INFO [train.py:761] (5/8) Epoch 7, batch 50, loss[loss=0.2766, simple_loss=0.3787, pruned_loss=0.08727, over 4843.00 frames.], tot_loss[loss=0.3037, simple_loss=0.3806, pruned_loss=0.1134, over 219299.53 frames.], batch size: 14, lr: 3.96e-04
2022-05-28 02:31:58,766 INFO [train.py:761] (5/8) Epoch 7, batch 100, loss[loss=0.3164, simple_loss=0.4044, pruned_loss=0.1142, over 4853.00 frames.], tot_loss[loss=0.3014, simple_loss=0.3787, pruned_loss=0.112, over 386003.86 frames.], batch size: 18, lr: 3.96e-04
2022-05-28 02:32:37,094 INFO [train.py:761] (5/8) Epoch 7, batch 150, loss[loss=0.2861, simple_loss=0.3782, pruned_loss=0.09701, over 4762.00 frames.], tot_loss[loss=0.3015, simple_loss=0.3794, pruned_loss=0.1118, over 514669.66 frames.], batch size: 15, lr: 3.97e-04
2022-05-28 02:33:14,727 INFO [train.py:761] (5/8) Epoch 7, batch 200, loss[loss=0.2441, simple_loss=0.3255, pruned_loss=0.08135, over 4723.00 frames.], tot_loss[loss=0.3006, simple_loss=0.3789, pruned_loss=0.1111, over 614991.03 frames.], batch size: 11, lr: 3.97e-04
2022-05-28 02:33:53,286 INFO [train.py:761] (5/8) Epoch 7, batch 250, loss[loss=0.3703, simple_loss=0.4333, pruned_loss=0.1537, over 4960.00 frames.], tot_loss[loss=0.3014, simple_loss=0.3795, pruned_loss=0.1117, over 692743.57 frames.], batch size: 45, lr: 3.98e-04
2022-05-28 02:34:31,329 INFO [train.py:761] (5/8) Epoch 7, batch 300, loss[loss=0.3039, simple_loss=0.3833, pruned_loss=0.1122, over 4973.00 frames.], tot_loss[loss=0.3023, simple_loss=0.3812, pruned_loss=0.1117, over 753992.14 frames.], batch size: 15, lr: 3.98e-04
2022-05-28 02:35:09,434 INFO [train.py:761] (5/8) Epoch 7, batch 350, loss[loss=0.2572, simple_loss=0.3335, pruned_loss=0.09045, over 4720.00 frames.], tot_loss[loss=0.302, simple_loss=0.3807, pruned_loss=0.1116, over 801009.23 frames.], batch size: 11, lr: 3.99e-04
2022-05-28 02:35:46,925 INFO [train.py:761] (5/8) Epoch 7, batch 400, loss[loss=0.2728, simple_loss=0.3546, pruned_loss=0.0955, over 4984.00 frames.], tot_loss[loss=0.2994, simple_loss=0.3786, pruned_loss=0.1101, over 837204.61 frames.], batch size: 15, lr: 3.99e-04
2022-05-28 02:36:25,191 INFO [train.py:761] (5/8) Epoch 7, batch 450, loss[loss=0.2706, simple_loss=0.3629, pruned_loss=0.08915, over 4961.00 frames.], tot_loss[loss=0.2984, simple_loss=0.3779, pruned_loss=0.1095, over 866175.79 frames.], batch size: 21, lr: 4.00e-04
2022-05-28 02:37:02,640 INFO [train.py:761] (5/8) Epoch 7, batch 500, loss[loss=0.3725, simple_loss=0.4288, pruned_loss=0.1581, over 4788.00 frames.], tot_loss[loss=0.2966, simple_loss=0.3765, pruned_loss=0.1084, over 888340.10 frames.], batch size: 14, lr: 4.00e-04
2022-05-28 02:37:40,958 INFO [train.py:761] (5/8) Epoch 7, batch 550, loss[loss=0.2655, simple_loss=0.3239, pruned_loss=0.1035, over 4978.00 frames.], tot_loss[loss=0.2974, simple_loss=0.3772, pruned_loss=0.1088, over 905280.13 frames.], batch size: 12, lr: 4.01e-04
2022-05-28 02:38:18,912 INFO [train.py:761] (5/8) Epoch 7, batch 600, loss[loss=0.2977, simple_loss=0.3857, pruned_loss=0.1048, over 4838.00 frames.], tot_loss[loss=0.2958, simple_loss=0.3758, pruned_loss=0.1079, over 918218.12 frames.], batch size: 18, lr: 4.01e-04
2022-05-28 02:38:57,168 INFO [train.py:761] (5/8) Epoch 7, batch 650, loss[loss=0.3589, simple_loss=0.4307, pruned_loss=0.1436, over 4978.00 frames.], tot_loss[loss=0.2978, simple_loss=0.3774, pruned_loss=0.1092, over 929550.27 frames.], batch size: 14, lr: 4.02e-04
2022-05-28 02:39:35,255 INFO [train.py:761] (5/8) Epoch 7, batch 700, loss[loss=0.4173, simple_loss=0.4508, pruned_loss=0.1919, over 4968.00 frames.], tot_loss[loss=0.3, simple_loss=0.3785, pruned_loss=0.1107, over 938086.98 frames.], batch size: 46, lr: 4.02e-04
2022-05-28 02:40:13,119 INFO [train.py:761] (5/8) Epoch 7, batch 750, loss[loss=0.3147, simple_loss=0.3896, pruned_loss=0.1199, over 4984.00 frames.], tot_loss[loss=0.3007, simple_loss=0.3791, pruned_loss=0.1112, over 945571.88 frames.], batch size: 15, lr: 4.03e-04
2022-05-28 02:40:51,473 INFO [train.py:761] (5/8) Epoch 7, batch 800, loss[loss=0.3366, simple_loss=0.3946, pruned_loss=0.1393, over 4810.00 frames.], tot_loss[loss=0.3025, simple_loss=0.3797, pruned_loss=0.1127, over 950249.03 frames.], batch size: 12, lr: 4.03e-04
2022-05-28 02:41:29,752 INFO [train.py:761] (5/8) Epoch 7, batch 850, loss[loss=0.3911, simple_loss=0.4423, pruned_loss=0.1699, over 4978.00 frames.], tot_loss[loss=0.3052, simple_loss=0.382, pruned_loss=0.1143, over 955351.63 frames.], batch size: 26, lr: 4.04e-04
2022-05-28 02:42:07,408 INFO [train.py:761] (5/8) Epoch 7, batch 900, loss[loss=0.2794, simple_loss=0.3584, pruned_loss=0.1002, over 4667.00 frames.], tot_loss[loss=0.3074, simple_loss=0.3839, pruned_loss=0.1155, over 958919.67 frames.], batch size: 12, lr: 4.04e-04
2022-05-28 02:42:45,285 INFO [train.py:761] (5/8) Epoch 7, batch 950, loss[loss=0.2266, simple_loss=0.3168, pruned_loss=0.06817, over 4845.00 frames.], tot_loss[loss=0.3074, simple_loss=0.3843, pruned_loss=0.1152, over 960637.80 frames.], batch size: 13, lr: 4.05e-04
2022-05-28 02:43:23,046 INFO [train.py:761] (5/8) Epoch 7, batch 1000, loss[loss=0.3015, simple_loss=0.3779, pruned_loss=0.1125, over 4816.00 frames.], tot_loss[loss=0.3067, simple_loss=0.384, pruned_loss=0.1148, over 961044.06 frames.], batch size: 16, lr: 4.05e-04
2022-05-28 02:44:01,533 INFO [train.py:761] (5/8) Epoch 7, batch 1050, loss[loss=0.3173, simple_loss=0.3814, pruned_loss=0.1266, over 4922.00 frames.], tot_loss[loss=0.3044, simple_loss=0.382, pruned_loss=0.1134, over 962827.52 frames.], batch size: 13, lr: 4.06e-04
2022-05-28 02:44:39,303 INFO [train.py:761] (5/8) Epoch 7, batch 1100, loss[loss=0.316, simple_loss=0.3802, pruned_loss=0.1259, over 4668.00 frames.], tot_loss[loss=0.3023, simple_loss=0.3804, pruned_loss=0.1121, over 963418.08 frames.], batch size: 13, lr: 4.06e-04
2022-05-28 02:45:17,366 INFO [train.py:761] (5/8) Epoch 7, batch 1150, loss[loss=0.33, simple_loss=0.4122, pruned_loss=0.1239, over 4855.00 frames.], tot_loss[loss=0.3041, simple_loss=0.3817, pruned_loss=0.1133, over 964131.88 frames.], batch size: 18, lr: 4.07e-04
2022-05-28 02:45:55,527 INFO [train.py:761] (5/8) Epoch 7, batch 1200, loss[loss=0.3039, simple_loss=0.3825, pruned_loss=0.1126, over 4738.00 frames.], tot_loss[loss=0.3038, simple_loss=0.3811, pruned_loss=0.1132, over 963899.81 frames.], batch size: 12, lr: 4.07e-04
2022-05-28 02:46:33,550 INFO [train.py:761] (5/8) Epoch 7, batch 1250, loss[loss=0.3198, simple_loss=0.3995, pruned_loss=0.1201, over 4726.00 frames.], tot_loss[loss=0.302, simple_loss=0.3798, pruned_loss=0.1121, over 963859.87 frames.], batch size: 13, lr: 4.08e-04
2022-05-28 02:47:11,520 INFO [train.py:761] (5/8) Epoch 7, batch 1300, loss[loss=0.3058, simple_loss=0.3714, pruned_loss=0.12, over 4922.00 frames.], tot_loss[loss=0.3048, simple_loss=0.3821, pruned_loss=0.1138, over 964129.75 frames.], batch size: 13, lr: 4.08e-04
2022-05-28 02:47:49,247 INFO [train.py:761] (5/8) Epoch 7, batch 1350, loss[loss=0.291, simple_loss=0.3713, pruned_loss=0.1054, over 4671.00 frames.], tot_loss[loss=0.3034, simple_loss=0.3815, pruned_loss=0.1126, over 964305.35 frames.], batch size: 13, lr: 4.08e-04
2022-05-28 02:48:27,021 INFO [train.py:761] (5/8) Epoch 7, batch 1400, loss[loss=0.2819, simple_loss=0.3547, pruned_loss=0.1045, over 4788.00 frames.], tot_loss[loss=0.3013, simple_loss=0.3798, pruned_loss=0.1114, over 964843.21 frames.], batch size: 14, lr: 4.09e-04
2022-05-28 02:49:04,748 INFO [train.py:761] (5/8) Epoch 7, batch 1450, loss[loss=0.2649, simple_loss=0.3467, pruned_loss=0.09158, over 4937.00 frames.], tot_loss[loss=0.2998, simple_loss=0.3782, pruned_loss=0.1107, over 965126.26 frames.], batch size: 13, lr: 4.09e-04
2022-05-28 02:49:42,614 INFO [train.py:761] (5/8) Epoch 7, batch 1500, loss[loss=0.3368, simple_loss=0.4125, pruned_loss=0.1306, over 4939.00 frames.], tot_loss[loss=0.2986, simple_loss=0.3777, pruned_loss=0.1097, over 965024.72 frames.], batch size: 50, lr: 4.10e-04
2022-05-28 02:50:20,484 INFO [train.py:761] (5/8) Epoch 7, batch 1550, loss[loss=0.3501, simple_loss=0.4216, pruned_loss=0.1392, over 4937.00 frames.], tot_loss[loss=0.2989, simple_loss=0.3776, pruned_loss=0.1101, over 965045.00 frames.], batch size: 16, lr: 4.10e-04
2022-05-28 02:50:58,338 INFO [train.py:761] (5/8) Epoch 7, batch 1600, loss[loss=0.3459, simple_loss=0.4232, pruned_loss=0.1343, over 4894.00 frames.], tot_loss[loss=0.2991, simple_loss=0.3773, pruned_loss=0.1105, over 965004.24 frames.], batch size: 17, lr: 4.11e-04
2022-05-28 02:51:36,084 INFO [train.py:761] (5/8) Epoch 7, batch 1650, loss[loss=0.2634, simple_loss=0.3405, pruned_loss=0.09319, over 4852.00 frames.], tot_loss[loss=0.2978, simple_loss=0.3759, pruned_loss=0.1098, over 965894.30 frames.], batch size: 13, lr: 4.11e-04
2022-05-28 02:52:14,230 INFO [train.py:761] (5/8) Epoch 7, batch 1700, loss[loss=0.3364, simple_loss=0.4091, pruned_loss=0.1318, over 4992.00 frames.], tot_loss[loss=0.2989, simple_loss=0.376, pruned_loss=0.1109, over 966721.93 frames.], batch size: 21, lr: 4.12e-04
2022-05-28 02:52:52,475 INFO [train.py:761] (5/8) Epoch 7, batch 1750, loss[loss=0.3789, simple_loss=0.4604, pruned_loss=0.1487, over 4993.00 frames.], tot_loss[loss=0.2995, simple_loss=0.3775, pruned_loss=0.1107, over 966930.38 frames.], batch size: 21, lr: 4.12e-04
2022-05-28 02:53:30,186 INFO [train.py:761] (5/8) Epoch 7, batch 1800, loss[loss=0.3016, simple_loss=0.379, pruned_loss=0.1121, over 4972.00 frames.], tot_loss[loss=0.2997, simple_loss=0.3772, pruned_loss=0.111, over 966660.22 frames.], batch size: 15, lr: 4.13e-04
2022-05-28 02:54:08,075 INFO [train.py:761] (5/8) Epoch 7, batch 1850, loss[loss=0.3164, simple_loss=0.3987, pruned_loss=0.117, over 4973.00 frames.], tot_loss[loss=0.3013, simple_loss=0.3786, pruned_loss=0.112, over 966584.79 frames.], batch size: 15, lr: 4.13e-04
2022-05-28 02:54:45,490 INFO [train.py:761] (5/8) Epoch 7, batch 1900, loss[loss=0.3464, simple_loss=0.4225, pruned_loss=0.1352, over 4942.00 frames.], tot_loss[loss=0.3015, simple_loss=0.3792, pruned_loss=0.1119, over 966363.15 frames.], batch size: 16, lr: 4.14e-04
2022-05-28 02:55:23,161 INFO [train.py:761] (5/8) Epoch 7, batch 1950, loss[loss=0.3343, simple_loss=0.4082, pruned_loss=0.1302, over 4798.00 frames.], tot_loss[loss=0.3024, simple_loss=0.38, pruned_loss=0.1124, over 966678.01 frames.], batch size: 12, lr: 4.14e-04
2022-05-28 02:56:01,256 INFO [train.py:761] (5/8) Epoch 7, batch 2000, loss[loss=0.3038, simple_loss=0.3551, pruned_loss=0.1263, over 4734.00 frames.], tot_loss[loss=0.3004, simple_loss=0.3787, pruned_loss=0.1111, over 966684.94 frames.], batch size: 11, lr: 4.15e-04
2022-05-28 02:56:39,369 INFO [train.py:761] (5/8) Epoch 7, batch 2050, loss[loss=0.2748, simple_loss=0.3586, pruned_loss=0.09553, over 4787.00 frames.], tot_loss[loss=0.3004, simple_loss=0.3789, pruned_loss=0.1109, over 966654.15 frames.], batch size: 14, lr: 4.15e-04
2022-05-28 02:57:17,794 INFO [train.py:761] (5/8) Epoch 7, batch 2100, loss[loss=0.297, simple_loss=0.3816, pruned_loss=0.1062, over 4855.00 frames.], tot_loss[loss=0.3015, simple_loss=0.3803, pruned_loss=0.1114, over 966881.99 frames.], batch size: 13, lr: 4.16e-04
2022-05-28 02:57:55,413 INFO [train.py:761] (5/8) Epoch 7, batch 2150, loss[loss=0.2643, simple_loss=0.3495, pruned_loss=0.0895, over 4943.00 frames.], tot_loss[loss=0.2979, simple_loss=0.3773, pruned_loss=0.1093, over 966394.55 frames.], batch size: 16, lr: 4.16e-04
2022-05-28 02:58:33,091 INFO [train.py:761] (5/8) Epoch 7, batch 2200, loss[loss=0.3172, simple_loss=0.3903, pruned_loss=0.122, over 4861.00 frames.], tot_loss[loss=0.2982, simple_loss=0.3771, pruned_loss=0.1096, over 964876.83 frames.], batch size: 13, lr: 4.17e-04
2022-05-28 02:59:11,085 INFO [train.py:761] (5/8) Epoch 7, batch 2250, loss[loss=0.2647, simple_loss=0.3544, pruned_loss=0.08748, over 4788.00 frames.], tot_loss[loss=0.2989, simple_loss=0.378, pruned_loss=0.1099, over 965539.62 frames.], batch size: 13, lr: 4.17e-04
2022-05-28 02:59:48,873 INFO [train.py:761] (5/8) Epoch 7, batch 2300, loss[loss=0.3029, simple_loss=0.3966, pruned_loss=0.1046, over 4667.00 frames.], tot_loss[loss=0.2985, simple_loss=0.3774, pruned_loss=0.1098, over 964752.98 frames.], batch size: 13, lr: 4.18e-04
2022-05-28 03:00:26,599 INFO [train.py:761] (5/8) Epoch 7, batch 2350, loss[loss=0.309, simple_loss=0.3886, pruned_loss=0.1147, over 4791.00 frames.], tot_loss[loss=0.2968, simple_loss=0.3758, pruned_loss=0.1089, over 963976.02 frames.], batch size: 15, lr: 4.18e-04
2022-05-28 03:01:04,448 INFO [train.py:761] (5/8) Epoch 7, batch 2400, loss[loss=0.2237, simple_loss=0.3013, pruned_loss=0.07303, over 4737.00 frames.], tot_loss[loss=0.297, simple_loss=0.3759, pruned_loss=0.1091, over 964681.35 frames.], batch size: 11, lr: 4.19e-04
2022-05-28 03:01:42,674 INFO [train.py:761] (5/8) Epoch 7, batch 2450, loss[loss=0.2756, simple_loss=0.3339, pruned_loss=0.1086, over 4734.00 frames.], tot_loss[loss=0.2959, simple_loss=0.3744, pruned_loss=0.1087, over 965059.76 frames.], batch size: 11, lr: 4.19e-04
2022-05-28 03:02:21,362 INFO [train.py:761] (5/8) Epoch 7, batch 2500, loss[loss=0.3547, simple_loss=0.4356, pruned_loss=0.1369, over 4801.00 frames.], tot_loss[loss=0.2943, simple_loss=0.3731, pruned_loss=0.1077, over 964397.42 frames.], batch size: 16, lr: 4.20e-04
2022-05-28 03:02:59,677 INFO [train.py:761] (5/8) Epoch 7, batch 2550, loss[loss=0.3218, simple_loss=0.4041, pruned_loss=0.1197, over 4968.00 frames.], tot_loss[loss=0.2988, simple_loss=0.3773, pruned_loss=0.1101, over 965468.52 frames.], batch size: 14, lr: 4.20e-04
2022-05-28 03:03:37,401 INFO [train.py:761] (5/8) Epoch 7, batch 2600, loss[loss=0.3853, simple_loss=0.442, pruned_loss=0.1643, over 4754.00 frames.], tot_loss[loss=0.2988, simple_loss=0.3776, pruned_loss=0.11, over 965300.15 frames.], batch size: 20, lr: 4.21e-04
2022-05-28 03:04:15,600 INFO [train.py:761] (5/8) Epoch 7, batch 2650, loss[loss=0.2423, simple_loss=0.3353, pruned_loss=0.07459, over 4663.00 frames.], tot_loss[loss=0.2977, simple_loss=0.3761, pruned_loss=0.1096, over 965044.85 frames.], batch size: 12, lr: 4.21e-04
2022-05-28 03:04:53,365 INFO [train.py:761] (5/8) Epoch 7, batch 2700, loss[loss=0.2664, simple_loss=0.3333, pruned_loss=0.09973, over 4545.00 frames.], tot_loss[loss=0.2961, simple_loss=0.375, pruned_loss=0.1086, over 965693.54 frames.], batch size: 10, lr: 4.22e-04
2022-05-28 03:05:31,366 INFO [train.py:761] (5/8) Epoch 7, batch 2750, loss[loss=0.2595, simple_loss=0.3437, pruned_loss=0.08764, over 4991.00 frames.], tot_loss[loss=0.2946, simple_loss=0.3742, pruned_loss=0.1075, over 964878.22 frames.], batch size: 13, lr: 4.22e-04
2022-05-28 03:06:09,631 INFO [train.py:761] (5/8) Epoch 7, batch 2800, loss[loss=0.3041, simple_loss=0.3711, pruned_loss=0.1186, over 4799.00 frames.], tot_loss[loss=0.2963, simple_loss=0.3765, pruned_loss=0.1081, over 965186.47 frames.], batch size: 13, lr: 4.23e-04
2022-05-28 03:06:47,553 INFO [train.py:761] (5/8) Epoch 7, batch 2850, loss[loss=0.2598, simple_loss=0.3635, pruned_loss=0.07806, over 4790.00 frames.], tot_loss[loss=0.2956, simple_loss=0.376, pruned_loss=0.1076, over 965625.49 frames.], batch size: 14, lr: 4.23e-04
2022-05-28 03:07:25,265 INFO [train.py:761] (5/8) Epoch 7, batch 2900, loss[loss=0.2781, simple_loss=0.3663, pruned_loss=0.09495, over 4738.00 frames.], tot_loss[loss=0.2943, simple_loss=0.3746, pruned_loss=0.107, over 965344.04 frames.], batch size: 12, lr: 4.24e-04
2022-05-28 03:08:02,803 INFO [train.py:761] (5/8) Epoch 7, batch 2950, loss[loss=0.3485, simple_loss=0.4344, pruned_loss=0.1313, over 4831.00 frames.], tot_loss[loss=0.2947, simple_loss=0.3744, pruned_loss=0.1075, over 965649.99 frames.], batch size: 18, lr: 4.24e-04
2022-05-28 03:08:40,473 INFO [train.py:761] (5/8) Epoch 7, batch 3000, loss[loss=0.3379, simple_loss=0.421, pruned_loss=0.1274, over 4897.00 frames.], tot_loss[loss=0.2939, simple_loss=0.3738, pruned_loss=0.107, over 966109.10 frames.], batch size: 27, lr: 4.25e-04
2022-05-28 03:08:40,473 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 03:08:50,851 INFO [train.py:790] (5/8) Epoch 7, validation: loss=0.2597, simple_loss=0.3613, pruned_loss=0.07901, over 944034.00 frames.
2022-05-28 03:09:28,849 INFO [train.py:761] (5/8) Epoch 7, batch 3050, loss[loss=0.3106, simple_loss=0.4089, pruned_loss=0.1061, over 4794.00 frames.], tot_loss[loss=0.2966, simple_loss=0.3766, pruned_loss=0.1083, over 966688.72 frames.], batch size: 14, lr: 4.25e-04
2022-05-28 03:10:07,174 INFO [train.py:761] (5/8) Epoch 7, batch 3100, loss[loss=0.284, simple_loss=0.355, pruned_loss=0.1065, over 4980.00 frames.], tot_loss[loss=0.2988, simple_loss=0.3769, pruned_loss=0.1104, over 965769.09 frames.], batch size: 12, lr: 4.26e-04
2022-05-28 03:10:45,596 INFO [train.py:761] (5/8) Epoch 7, batch 3150, loss[loss=0.2484, simple_loss=0.3225, pruned_loss=0.08717, over 4802.00 frames.], tot_loss[loss=0.3023, simple_loss=0.3784, pruned_loss=0.1131, over 966105.26 frames.], batch size: 12, lr: 4.26e-04
2022-05-28 03:11:23,633 INFO [train.py:761] (5/8) Epoch 7, batch 3200, loss[loss=0.3297, simple_loss=0.3771, pruned_loss=0.1411, over 4872.00 frames.], tot_loss[loss=0.3051, simple_loss=0.3792, pruned_loss=0.1155, over 966657.74 frames.], batch size: 12, lr: 4.27e-04
2022-05-28 03:12:01,558 INFO [train.py:761] (5/8) Epoch 7, batch 3250, loss[loss=0.3758, simple_loss=0.435, pruned_loss=0.1583, over 4781.00 frames.], tot_loss[loss=0.3084, simple_loss=0.3801, pruned_loss=0.1184, over 966200.11 frames.], batch size: 25, lr: 4.27e-04
2022-05-28 03:12:39,236 INFO [train.py:761] (5/8) Epoch 7, batch 3300, loss[loss=0.3345, simple_loss=0.3766, pruned_loss=0.1462, over 4969.00 frames.], tot_loss[loss=0.3136, simple_loss=0.383, pruned_loss=0.1222, over 966801.81 frames.], batch size: 12, lr: 4.28e-04
2022-05-28 03:13:17,213 INFO [train.py:761] (5/8) Epoch 7, batch 3350, loss[loss=0.3772, simple_loss=0.4222, pruned_loss=0.1661, over 4918.00 frames.], tot_loss[loss=0.3178, simple_loss=0.3854, pruned_loss=0.1251, over 965129.06 frames.], batch size: 14, lr: 4.28e-04
2022-05-28 03:13:55,195 INFO [train.py:761] (5/8) Epoch 7, batch 3400, loss[loss=0.3475, simple_loss=0.396, pruned_loss=0.1495, over 4993.00 frames.], tot_loss[loss=0.3215, simple_loss=0.3876, pruned_loss=0.1277, over 965877.06 frames.], batch size: 13, lr: 4.29e-04
2022-05-28 03:14:33,392 INFO [train.py:761] (5/8) Epoch 7, batch 3450, loss[loss=0.2461, simple_loss=0.3193, pruned_loss=0.08649, over 4980.00 frames.], tot_loss[loss=0.3245, simple_loss=0.3891, pruned_loss=0.13, over 966182.82 frames.], batch size: 12, lr: 4.29e-04
2022-05-28 03:15:11,381 INFO [train.py:761] (5/8) Epoch 7, batch 3500, loss[loss=0.3657, simple_loss=0.4025, pruned_loss=0.1645, over 4991.00 frames.], tot_loss[loss=0.327, simple_loss=0.3906, pruned_loss=0.1317, over 966517.54 frames.], batch size: 13, lr: 4.29e-04
2022-05-28 03:15:49,353 INFO [train.py:761] (5/8) Epoch 7, batch 3550, loss[loss=0.3136, simple_loss=0.3719, pruned_loss=0.1276, over 4586.00 frames.], tot_loss[loss=0.3304, simple_loss=0.3919, pruned_loss=0.1344, over 967054.32 frames.], batch size: 10, lr: 4.30e-04
2022-05-28 03:16:27,083 INFO [train.py:761] (5/8) Epoch 7, batch 3600, loss[loss=0.2542, simple_loss=0.329, pruned_loss=0.08974, over 4889.00 frames.], tot_loss[loss=0.3346, simple_loss=0.3952, pruned_loss=0.1371, over 967187.22 frames.], batch size: 12, lr: 4.30e-04
2022-05-28 03:17:05,090 INFO [train.py:761] (5/8) Epoch 7, batch 3650, loss[loss=0.3619, simple_loss=0.4012, pruned_loss=0.1614, over 4777.00 frames.], tot_loss[loss=0.3366, simple_loss=0.3964, pruned_loss=0.1384, over 966744.97 frames.], batch size: 16, lr: 4.31e-04
2022-05-28 03:17:42,870 INFO [train.py:761] (5/8) Epoch 7, batch 3700, loss[loss=0.4093, simple_loss=0.4606, pruned_loss=0.1789, over 4797.00 frames.], tot_loss[loss=0.3385, simple_loss=0.3975, pruned_loss=0.1397, over 966071.10 frames.], batch size: 16, lr: 4.31e-04
2022-05-28 03:18:21,142 INFO [train.py:761] (5/8) Epoch 7, batch 3750, loss[loss=0.4329, simple_loss=0.4704, pruned_loss=0.1977, over 4988.00 frames.], tot_loss[loss=0.3412, simple_loss=0.399, pruned_loss=0.1417, over 967053.04 frames.], batch size: 26, lr: 4.32e-04
2022-05-28 03:18:58,610 INFO [train.py:761] (5/8) Epoch 7, batch 3800, loss[loss=0.3673, simple_loss=0.4105, pruned_loss=0.162, over 4854.00 frames.], tot_loss[loss=0.3414, simple_loss=0.3987, pruned_loss=0.142, over 966304.10 frames.], batch size: 17, lr: 4.32e-04
2022-05-28 03:19:36,508 INFO [train.py:761] (5/8) Epoch 7, batch 3850, loss[loss=0.3682, simple_loss=0.4215, pruned_loss=0.1575, over 4776.00 frames.], tot_loss[loss=0.3424, simple_loss=0.3991, pruned_loss=0.1429, over 965975.37 frames.], batch size: 15, lr: 4.33e-04
2022-05-28 03:20:14,708 INFO [train.py:761] (5/8) Epoch 7, batch 3900, loss[loss=0.2862, simple_loss=0.3342, pruned_loss=0.1191, over 4835.00 frames.], tot_loss[loss=0.3451, simple_loss=0.401, pruned_loss=0.1446, over 966735.70 frames.], batch size: 11, lr: 4.33e-04
2022-05-28 03:20:52,575 INFO [train.py:761] (5/8) Epoch 7, batch 3950, loss[loss=0.2848, simple_loss=0.3475, pruned_loss=0.1111, over 4977.00 frames.], tot_loss[loss=0.3419, simple_loss=0.3982, pruned_loss=0.1428, over 966265.17 frames.], batch size: 12, lr: 4.34e-04
2022-05-28 03:21:31,595 INFO [train.py:761] (5/8) Epoch 7, batch 4000, loss[loss=0.3053, simple_loss=0.3819, pruned_loss=0.1144, over 4890.00 frames.], tot_loss[loss=0.3417, simple_loss=0.3981, pruned_loss=0.1426, over 967112.60 frames.], batch size: 12, lr: 4.34e-04
2022-05-28 03:22:09,902 INFO [train.py:761] (5/8) Epoch 7, batch 4050, loss[loss=0.331, simple_loss=0.3809, pruned_loss=0.1405, over 4984.00 frames.], tot_loss[loss=0.3407, simple_loss=0.3973, pruned_loss=0.1421, over 966657.02 frames.], batch size: 12, lr: 4.35e-04
2022-05-28 03:22:47,881 INFO [train.py:761] (5/8) Epoch 7, batch 4100, loss[loss=0.2166, simple_loss=0.3008, pruned_loss=0.06617, over 4638.00 frames.], tot_loss[loss=0.3377, simple_loss=0.3952, pruned_loss=0.1401, over 965155.98 frames.], batch size: 11, lr: 4.35e-04
2022-05-28 03:23:25,965 INFO [train.py:761] (5/8) Epoch 7, batch 4150, loss[loss=0.3201, simple_loss=0.3826, pruned_loss=0.1288, over 4928.00 frames.], tot_loss[loss=0.3395, simple_loss=0.3967, pruned_loss=0.1412, over 965701.37 frames.], batch size: 13, lr: 4.36e-04
2022-05-28 03:24:04,368 INFO [train.py:761] (5/8) Epoch 7, batch 4200, loss[loss=0.4009, simple_loss=0.4394, pruned_loss=0.1812, over 4681.00 frames.], tot_loss[loss=0.34, simple_loss=0.3972, pruned_loss=0.1414, over 966134.77 frames.], batch size: 13, lr: 4.36e-04
2022-05-28 03:24:42,833 INFO [train.py:761] (5/8) Epoch 7, batch 4250, loss[loss=0.4287, simple_loss=0.4703, pruned_loss=0.1936, over 4933.00 frames.], tot_loss[loss=0.3385, simple_loss=0.396, pruned_loss=0.1405, over 966801.23 frames.], batch size: 26, lr: 4.37e-04
2022-05-28 03:25:20,767 INFO [train.py:761] (5/8) Epoch 7, batch 4300, loss[loss=0.3628, simple_loss=0.4108, pruned_loss=0.1573, over 4867.00 frames.], tot_loss[loss=0.337, simple_loss=0.3949, pruned_loss=0.1395, over 966555.93 frames.], batch size: 17, lr: 4.37e-04
2022-05-28 03:25:59,114 INFO [train.py:761] (5/8) Epoch 7, batch 4350, loss[loss=0.3835, simple_loss=0.4249, pruned_loss=0.171, over 4900.00 frames.], tot_loss[loss=0.3381, simple_loss=0.3962, pruned_loss=0.14, over 966940.13 frames.], batch size: 26, lr: 4.38e-04
2022-05-28 03:26:37,366 INFO [train.py:761] (5/8) Epoch 7, batch 4400, loss[loss=0.2839, simple_loss=0.338, pruned_loss=0.115, over 4534.00 frames.], tot_loss[loss=0.3374, simple_loss=0.3958, pruned_loss=0.1394, over 966447.38 frames.], batch size: 10, lr: 4.38e-04
2022-05-28 03:27:15,962 INFO [train.py:761] (5/8) Epoch 7, batch 4450, loss[loss=0.3322, simple_loss=0.3916, pruned_loss=0.1364, over 4914.00 frames.], tot_loss[loss=0.3364, simple_loss=0.3954, pruned_loss=0.1387, over 966250.39 frames.], batch size: 14, lr: 4.39e-04
2022-05-28 03:27:54,025 INFO [train.py:761] (5/8) Epoch 7, batch 4500, loss[loss=0.324, simple_loss=0.3923, pruned_loss=0.1278, over 4724.00 frames.], tot_loss[loss=0.3357, simple_loss=0.3947, pruned_loss=0.1383, over 965719.03 frames.], batch size: 14, lr: 4.39e-04
2022-05-28 03:28:32,376 INFO [train.py:761] (5/8) Epoch 7, batch 4550, loss[loss=0.2825, simple_loss=0.3553, pruned_loss=0.1048, over 4739.00 frames.], tot_loss[loss=0.3349, simple_loss=0.3939, pruned_loss=0.138, over 966256.46 frames.], batch size: 12, lr: 4.40e-04
2022-05-28 03:29:09,957 INFO [train.py:761] (5/8) Epoch 7, batch 4600, loss[loss=0.3198, simple_loss=0.3851, pruned_loss=0.1272, over 4859.00 frames.], tot_loss[loss=0.3328, simple_loss=0.393, pruned_loss=0.1363, over 966676.81 frames.], batch size: 13, lr: 4.40e-04
2022-05-28 03:29:48,282 INFO [train.py:761] (5/8) Epoch 7, batch 4650, loss[loss=0.3429, simple_loss=0.3774, pruned_loss=0.1542, over 4738.00 frames.], tot_loss[loss=0.332, simple_loss=0.3921, pruned_loss=0.1359, over 966758.35 frames.], batch size: 11, lr: 4.41e-04
2022-05-28 03:30:26,350 INFO [train.py:761] (5/8) Epoch 7, batch 4700, loss[loss=0.3914, simple_loss=0.4456, pruned_loss=0.1686, over 4955.00 frames.], tot_loss[loss=0.3339, simple_loss=0.3932, pruned_loss=0.1373, over 966731.88 frames.], batch size: 16, lr: 4.41e-04
2022-05-28 03:31:04,713 INFO [train.py:761] (5/8) Epoch 7, batch 4750, loss[loss=0.3651, simple_loss=0.3874, pruned_loss=0.1714, over 4894.00 frames.], tot_loss[loss=0.3341, simple_loss=0.3929, pruned_loss=0.1376, over 965586.50 frames.], batch size: 12, lr: 4.42e-04
2022-05-28 03:31:42,998 INFO [train.py:761] (5/8) Epoch 7, batch 4800, loss[loss=0.3395, simple_loss=0.3908, pruned_loss=0.1441, over 4803.00 frames.], tot_loss[loss=0.337, simple_loss=0.3952, pruned_loss=0.1394, over 965500.57 frames.], batch size: 16, lr: 4.42e-04
2022-05-28 03:32:21,436 INFO [train.py:761] (5/8) Epoch 7, batch 4850, loss[loss=0.3601, simple_loss=0.419, pruned_loss=0.1506, over 4971.00 frames.], tot_loss[loss=0.3369, simple_loss=0.3959, pruned_loss=0.139, over 965897.90 frames.], batch size: 15, lr: 4.43e-04
2022-05-28 03:32:59,699 INFO [train.py:761] (5/8) Epoch 7, batch 4900, loss[loss=0.3825, simple_loss=0.4322, pruned_loss=0.1664, over 4971.00 frames.], tot_loss[loss=0.3347, simple_loss=0.3938, pruned_loss=0.1379, over 966829.79 frames.], batch size: 26, lr: 4.43e-04
2022-05-28 03:33:37,813 INFO [train.py:761] (5/8) Epoch 7, batch 4950, loss[loss=0.3098, simple_loss=0.3824, pruned_loss=0.1186, over 4905.00 frames.], tot_loss[loss=0.3344, simple_loss=0.3936, pruned_loss=0.1376, over 966095.92 frames.], batch size: 14, lr: 4.44e-04
2022-05-28 03:34:15,670 INFO [train.py:761] (5/8) Epoch 7, batch 5000, loss[loss=0.2366, simple_loss=0.3158, pruned_loss=0.07871, over 4738.00 frames.], tot_loss[loss=0.3348, simple_loss=0.3934, pruned_loss=0.1381, over 966226.92 frames.], batch size: 11, lr: 4.44e-04
2022-05-28 03:34:53,819 INFO [train.py:761] (5/8) Epoch 7, batch 5050, loss[loss=0.2912, simple_loss=0.378, pruned_loss=0.1022, over 4773.00 frames.], tot_loss[loss=0.3344, simple_loss=0.3938, pruned_loss=0.1375, over 966280.51 frames.], batch size: 15, lr: 4.45e-04
2022-05-28 03:35:32,098 INFO [train.py:761] (5/8) Epoch 7, batch 5100, loss[loss=0.3616, simple_loss=0.4154, pruned_loss=0.1539, over 4987.00 frames.], tot_loss[loss=0.3333, simple_loss=0.3924, pruned_loss=0.1371, over 965772.56 frames.], batch size: 13, lr: 4.45e-04
2022-05-28 03:36:10,232 INFO [train.py:761] (5/8) Epoch 7, batch 5150, loss[loss=0.2883, simple_loss=0.3478, pruned_loss=0.1144, over 4813.00 frames.], tot_loss[loss=0.3324, simple_loss=0.392, pruned_loss=0.1364, over 964859.11 frames.], batch size: 12, lr: 4.46e-04
2022-05-28 03:36:48,558 INFO [train.py:761] (5/8) Epoch 7, batch 5200, loss[loss=0.3159, simple_loss=0.3749, pruned_loss=0.1284, over 4885.00 frames.], tot_loss[loss=0.3335, simple_loss=0.3936, pruned_loss=0.1367, over 966530.13 frames.], batch size: 15, lr: 4.46e-04
2022-05-28 03:37:27,042 INFO [train.py:761] (5/8) Epoch 7, batch 5250, loss[loss=0.4015, simple_loss=0.4366, pruned_loss=0.1832, over 4887.00 frames.], tot_loss[loss=0.3327, simple_loss=0.393, pruned_loss=0.1363, over 964982.80 frames.], batch size: 15, lr: 4.47e-04
2022-05-28 03:38:05,575 INFO [train.py:761] (5/8) Epoch 7, batch 5300, loss[loss=0.3478, simple_loss=0.3939, pruned_loss=0.1509, over 4914.00 frames.], tot_loss[loss=0.3316, simple_loss=0.3918, pruned_loss=0.1357, over 965837.78 frames.], batch size: 14, lr: 4.47e-04
2022-05-28 03:38:43,932 INFO [train.py:761] (5/8) Epoch 7, batch 5350, loss[loss=0.3301, simple_loss=0.4008, pruned_loss=0.1297, over 4661.00 frames.], tot_loss[loss=0.3302, simple_loss=0.3903, pruned_loss=0.135, over 965134.42 frames.], batch size: 13, lr: 4.48e-04
2022-05-28 03:39:21,725 INFO [train.py:761] (5/8) Epoch 7, batch 5400, loss[loss=0.3154, simple_loss=0.373, pruned_loss=0.1289, over 4812.00 frames.], tot_loss[loss=0.3297, simple_loss=0.3906, pruned_loss=0.1344, over 965831.05 frames.], batch size: 16, lr: 4.48e-04
2022-05-28 03:39:59,723 INFO [train.py:761] (5/8) Epoch 7, batch 5450, loss[loss=0.2859, simple_loss=0.3508, pruned_loss=0.1105, over 4648.00 frames.], tot_loss[loss=0.3281, simple_loss=0.389, pruned_loss=0.1336, over 965311.42 frames.], batch size: 11, lr: 4.49e-04
2022-05-28 03:40:37,920 INFO [train.py:761] (5/8) Epoch 7, batch 5500, loss[loss=0.4246, simple_loss=0.4573, pruned_loss=0.196, over 4829.00 frames.], tot_loss[loss=0.3268, simple_loss=0.3875, pruned_loss=0.1331, over 965263.93 frames.], batch size: 18, lr: 4.49e-04
2022-05-28 03:41:16,147 INFO [train.py:761] (5/8) Epoch 7, batch 5550, loss[loss=0.3594, simple_loss=0.4281, pruned_loss=0.1454, over 4727.00 frames.], tot_loss[loss=0.3283, simple_loss=0.389, pruned_loss=0.1338, over 966040.98 frames.], batch size: 13, lr: 4.50e-04
2022-05-28 03:41:54,623 INFO [train.py:761] (5/8) Epoch 7, batch 5600, loss[loss=0.3028, simple_loss=0.3833, pruned_loss=0.1111, over 4983.00 frames.], tot_loss[loss=0.3319, simple_loss=0.3924, pruned_loss=0.1357, over 967000.29 frames.], batch size: 15, lr: 4.50e-04
2022-05-28 03:42:32,960 INFO [train.py:761] (5/8) Epoch 7, batch 5650, loss[loss=0.3212, simple_loss=0.3617, pruned_loss=0.1403, over 4917.00 frames.], tot_loss[loss=0.3301, simple_loss=0.3904, pruned_loss=0.1349, over 968098.28 frames.], batch size: 13, lr: 4.50e-04
2022-05-28 03:43:11,159 INFO [train.py:761] (5/8) Epoch 7, batch 5700, loss[loss=0.3814, simple_loss=0.4441, pruned_loss=0.1594, over 4951.00 frames.], tot_loss[loss=0.3316, simple_loss=0.3915, pruned_loss=0.1359, over 968620.32 frames.], batch size: 16, lr: 4.51e-04
2022-05-28 03:43:49,239 INFO [train.py:761] (5/8) Epoch 7, batch 5750, loss[loss=0.3234, simple_loss=0.3836, pruned_loss=0.1316, over 4644.00 frames.], tot_loss[loss=0.3319, simple_loss=0.3918, pruned_loss=0.1361, over 967995.22 frames.], batch size: 11, lr: 4.51e-04
2022-05-28 03:44:27,533 INFO [train.py:761] (5/8) Epoch 7, batch 5800, loss[loss=0.2471, simple_loss=0.3287, pruned_loss=0.08279, over 4838.00 frames.], tot_loss[loss=0.3309, simple_loss=0.3904, pruned_loss=0.1357, over 968979.19 frames.], batch size: 11, lr: 4.52e-04
2022-05-28 03:45:06,327 INFO [train.py:761] (5/8) Epoch 7, batch 5850, loss[loss=0.3288, simple_loss=0.3669, pruned_loss=0.1453, over 4644.00 frames.], tot_loss[loss=0.3314, simple_loss=0.3911, pruned_loss=0.1358, over 968479.36 frames.], batch size: 11, lr: 4.52e-04
2022-05-28 03:45:44,348 INFO [train.py:761] (5/8) Epoch 7, batch 5900, loss[loss=0.4084, simple_loss=0.4498, pruned_loss=0.1835, over 4858.00 frames.], tot_loss[loss=0.3325, simple_loss=0.3916, pruned_loss=0.1367, over 967267.66 frames.], batch size: 13, lr: 4.53e-04
2022-05-28 03:46:22,312 INFO [train.py:761] (5/8) Epoch 7, batch 5950, loss[loss=0.3739, simple_loss=0.4295, pruned_loss=0.1592, over 4855.00 frames.], tot_loss[loss=0.3342, simple_loss=0.3935, pruned_loss=0.1375, over 965871.57 frames.], batch size: 14, lr: 4.53e-04
2022-05-28 03:46:59,988 INFO [train.py:761] (5/8) Epoch 7, batch 6000, loss[loss=0.2522, simple_loss=0.3474, pruned_loss=0.07855, over 4860.00 frames.], tot_loss[loss=0.3356, simple_loss=0.3949, pruned_loss=0.1381, over 965953.22 frames.], batch size: 13, lr: 4.54e-04
2022-05-28 03:46:59,989 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 03:47:09,726 INFO [train.py:790] (5/8) Epoch 7, validation: loss=0.244, simple_loss=0.3524, pruned_loss=0.06783, over 944034.00 frames.
2022-05-28 03:47:48,204 INFO [train.py:761] (5/8) Epoch 7, batch 6050, loss[loss=0.3122, simple_loss=0.3762, pruned_loss=0.1241, over 4723.00 frames.], tot_loss[loss=0.3338, simple_loss=0.3934, pruned_loss=0.1371, over 966405.77 frames.], batch size: 14, lr: 4.54e-04
2022-05-28 03:48:26,323 INFO [train.py:761] (5/8) Epoch 7, batch 6100, loss[loss=0.3781, simple_loss=0.4251, pruned_loss=0.1655, over 4926.00 frames.], tot_loss[loss=0.3351, simple_loss=0.3941, pruned_loss=0.138, over 966454.32 frames.], batch size: 14, lr: 4.55e-04
2022-05-28 03:49:04,763 INFO [train.py:761] (5/8) Epoch 7, batch 6150, loss[loss=0.3454, simple_loss=0.4156, pruned_loss=0.1376, over 4968.00 frames.], tot_loss[loss=0.3326, simple_loss=0.3917, pruned_loss=0.1367, over 966674.92 frames.], batch size: 15, lr: 4.55e-04
2022-05-28 03:49:42,971 INFO [train.py:761] (5/8) Epoch 7, batch 6200, loss[loss=0.2866, simple_loss=0.362, pruned_loss=0.1056, over 4858.00 frames.], tot_loss[loss=0.3323, simple_loss=0.3921, pruned_loss=0.1363, over 966373.90 frames.], batch size: 13, lr: 4.56e-04
2022-05-28 03:50:21,234 INFO [train.py:761] (5/8) Epoch 7, batch 6250, loss[loss=0.3749, simple_loss=0.4379, pruned_loss=0.1559, over 4806.00 frames.], tot_loss[loss=0.3294, simple_loss=0.3899, pruned_loss=0.1345, over 966098.36 frames.], batch size: 20, lr: 4.56e-04
2022-05-28 03:50:59,538 INFO [train.py:761] (5/8) Epoch 7, batch 6300, loss[loss=0.3554, simple_loss=0.4149, pruned_loss=0.148, over 4884.00 frames.], tot_loss[loss=0.3296, simple_loss=0.3901, pruned_loss=0.1346, over 966440.67 frames.], batch size: 17, lr: 4.57e-04
2022-05-28 03:51:38,106 INFO [train.py:761] (5/8) Epoch 7, batch 6350, loss[loss=0.346, simple_loss=0.3881, pruned_loss=0.1519, over 4810.00 frames.], tot_loss[loss=0.3278, simple_loss=0.3884, pruned_loss=0.1336, over 966312.76 frames.], batch size: 20, lr: 4.57e-04
2022-05-28 03:52:16,072 INFO [train.py:761] (5/8) Epoch 7, batch 6400, loss[loss=0.3421, simple_loss=0.3998, pruned_loss=0.1422, over 4797.00 frames.], tot_loss[loss=0.327, simple_loss=0.3878, pruned_loss=0.1331, over 965554.92 frames.], batch size: 13, lr: 4.58e-04
2022-05-28 03:52:54,590 INFO [train.py:761] (5/8) Epoch 7, batch 6450, loss[loss=0.3634, simple_loss=0.4123, pruned_loss=0.1572, over 4797.00 frames.], tot_loss[loss=0.3271, simple_loss=0.3879, pruned_loss=0.1331, over 965210.75 frames.], batch size: 12, lr: 4.58e-04
2022-05-28 03:53:32,203 INFO [train.py:761] (5/8) Epoch 7, batch 6500, loss[loss=0.2716, simple_loss=0.3256, pruned_loss=0.1088, over 4564.00 frames.], tot_loss[loss=0.3289, simple_loss=0.3893, pruned_loss=0.1342, over 965329.61 frames.], batch size: 10, lr: 4.59e-04
2022-05-28 03:54:10,659 INFO [train.py:761] (5/8) Epoch 7, batch 6550, loss[loss=0.3157, simple_loss=0.3671, pruned_loss=0.1322, over 4799.00 frames.], tot_loss[loss=0.331, simple_loss=0.3908, pruned_loss=0.1356, over 966249.11 frames.], batch size: 12, lr: 4.59e-04
2022-05-28 03:54:48,641 INFO [train.py:761] (5/8) Epoch 7, batch 6600, loss[loss=0.2861, simple_loss=0.3579, pruned_loss=0.1072, over 4790.00 frames.], tot_loss[loss=0.3298, simple_loss=0.3906, pruned_loss=0.1345, over 966079.97 frames.], batch size: 13, lr: 4.60e-04
2022-05-28 03:55:27,007 INFO [train.py:761] (5/8) Epoch 7, batch 6650, loss[loss=0.3557, simple_loss=0.4263, pruned_loss=0.1425, over 4873.00 frames.], tot_loss[loss=0.3292, simple_loss=0.3895, pruned_loss=0.1345, over 965660.27 frames.], batch size: 15, lr: 4.60e-04
2022-05-28 03:56:05,807 INFO [train.py:761] (5/8) Epoch 7, batch 6700, loss[loss=0.3549, simple_loss=0.4098, pruned_loss=0.15, over 4667.00 frames.], tot_loss[loss=0.3313, simple_loss=0.391, pruned_loss=0.1358, over 966513.99 frames.], batch size: 12, lr: 4.61e-04
2022-05-28 03:57:01,667 INFO [train.py:761] (5/8) Epoch 8, batch 0, loss[loss=0.2956, simple_loss=0.3729, pruned_loss=0.1092, over 4794.00 frames.], tot_loss[loss=0.2956, simple_loss=0.3729, pruned_loss=0.1092, over 4794.00 frames.], batch size: 20, lr: 4.61e-04
2022-05-28 03:57:39,385 INFO [train.py:761] (5/8) Epoch 8, batch 50, loss[loss=0.2965, simple_loss=0.3689, pruned_loss=0.112, over 4973.00 frames.], tot_loss[loss=0.3038, simple_loss=0.3829, pruned_loss=0.1123, over 218227.72 frames.], batch size: 12, lr: 4.62e-04
2022-05-28 03:58:17,832 INFO [train.py:761] (5/8) Epoch 8, batch 100, loss[loss=0.2749, simple_loss=0.3529, pruned_loss=0.09843, over 4986.00 frames.], tot_loss[loss=0.3006, simple_loss=0.3794, pruned_loss=0.1109, over 383956.31 frames.], batch size: 13, lr: 4.62e-04
2022-05-28 03:58:55,679 INFO [train.py:761] (5/8) Epoch 8, batch 150, loss[loss=0.2594, simple_loss=0.3328, pruned_loss=0.09297, over 4556.00 frames.], tot_loss[loss=0.2934, simple_loss=0.3721, pruned_loss=0.1073, over 512585.55 frames.], batch size: 10, lr: 4.63e-04
2022-05-28 03:59:33,807 INFO [train.py:761] (5/8) Epoch 8, batch 200, loss[loss=0.2585, simple_loss=0.351, pruned_loss=0.08296, over 4943.00 frames.], tot_loss[loss=0.2912, simple_loss=0.3713, pruned_loss=0.1056, over 612971.15 frames.], batch size: 16, lr: 4.63e-04
2022-05-28 04:00:11,584 INFO [train.py:761] (5/8) Epoch 8, batch 250, loss[loss=0.3418, simple_loss=0.4224, pruned_loss=0.1306, over 4767.00 frames.], tot_loss[loss=0.2899, simple_loss=0.3697, pruned_loss=0.1051, over 691970.17 frames.], batch size: 15, lr: 4.64e-04
2022-05-28 04:00:50,161 INFO [train.py:761] (5/8) Epoch 8, batch 300, loss[loss=0.2386, simple_loss=0.323, pruned_loss=0.07714, over 4737.00 frames.], tot_loss[loss=0.2875, simple_loss=0.3675, pruned_loss=0.1038, over 752070.90 frames.], batch size: 11, lr: 4.64e-04
2022-05-28 04:01:27,884 INFO [train.py:761] (5/8) Epoch 8, batch 350, loss[loss=0.2552, simple_loss=0.3438, pruned_loss=0.08326, over 4986.00 frames.], tot_loss[loss=0.2872, simple_loss=0.3676, pruned_loss=0.1034, over 798189.21 frames.], batch size: 13, lr: 4.65e-04
2022-05-28 04:02:06,010 INFO [train.py:761] (5/8) Epoch 8, batch 400, loss[loss=0.3643, simple_loss=0.4117, pruned_loss=0.1585, over 4738.00 frames.], tot_loss[loss=0.2872, simple_loss=0.3679, pruned_loss=0.1033, over 835327.80 frames.], batch size: 12, lr: 4.65e-04
2022-05-28 04:02:44,518 INFO [train.py:761] (5/8) Epoch 8, batch 450, loss[loss=0.2461, simple_loss=0.3379, pruned_loss=0.07714, over 4783.00 frames.], tot_loss[loss=0.286, simple_loss=0.3672, pruned_loss=0.1024, over 863102.63 frames.], batch size: 13, lr: 4.66e-04
2022-05-28 04:03:22,527 INFO [train.py:761] (5/8) Epoch 8, batch 500, loss[loss=0.2607, simple_loss=0.3318, pruned_loss=0.0948, over 4797.00 frames.], tot_loss[loss=0.2832, simple_loss=0.3649, pruned_loss=0.1008, over 884652.14 frames.], batch size: 12, lr: 4.66e-04
2022-05-28 04:04:00,669 INFO [train.py:761] (5/8) Epoch 8, batch 550, loss[loss=0.2751, simple_loss=0.3389, pruned_loss=0.1057, over 4896.00 frames.], tot_loss[loss=0.2825, simple_loss=0.364, pruned_loss=0.1005, over 902364.77 frames.], batch size: 12, lr: 4.67e-04
2022-05-28 04:04:38,479 INFO [train.py:761] (5/8) Epoch 8, batch 600, loss[loss=0.3581, simple_loss=0.431, pruned_loss=0.1426, over 4876.00 frames.], tot_loss[loss=0.2842, simple_loss=0.3653, pruned_loss=0.1015, over 916244.94 frames.], batch size: 15, lr: 4.67e-04
2022-05-28 04:05:16,371 INFO [train.py:761] (5/8) Epoch 8, batch 650, loss[loss=0.24, simple_loss=0.3181, pruned_loss=0.08097, over 4986.00 frames.], tot_loss[loss=0.2856, simple_loss=0.3663, pruned_loss=0.1024, over 927650.72 frames.], batch size: 12, lr: 4.68e-04
2022-05-28 04:05:54,962 INFO [train.py:761] (5/8) Epoch 8, batch 700, loss[loss=0.3647, simple_loss=0.4021, pruned_loss=0.1637, over 4615.00 frames.], tot_loss[loss=0.2867, simple_loss=0.3666, pruned_loss=0.1034, over 936234.50 frames.], batch size: 12, lr: 4.68e-04
2022-05-28 04:06:32,658 INFO [train.py:761] (5/8) Epoch 8, batch 750, loss[loss=0.3041, simple_loss=0.3691, pruned_loss=0.1195, over 4950.00 frames.], tot_loss[loss=0.2877, simple_loss=0.3672, pruned_loss=0.1041, over 942800.01 frames.], batch size: 16, lr: 4.69e-04
2022-05-28 04:07:13,330 INFO [train.py:761] (5/8) Epoch 8, batch 800, loss[loss=0.3589, simple_loss=0.4347, pruned_loss=0.1415, over 4914.00 frames.], tot_loss[loss=0.2906, simple_loss=0.3694, pruned_loss=0.1059, over 948428.15 frames.], batch size: 14, lr: 4.69e-04
2022-05-28 04:07:50,890 INFO [train.py:761] (5/8) Epoch 8, batch 850, loss[loss=0.2354, simple_loss=0.3231, pruned_loss=0.07386, over 4730.00 frames.], tot_loss[loss=0.2904, simple_loss=0.3695, pruned_loss=0.1057, over 953098.79 frames.], batch size: 12, lr: 4.69e-04
2022-05-28 04:08:28,958 INFO [train.py:761] (5/8) Epoch 8, batch 900, loss[loss=0.2761, simple_loss=0.3506, pruned_loss=0.1008, over 4986.00 frames.], tot_loss[loss=0.292, simple_loss=0.3708, pruned_loss=0.1066, over 956428.59 frames.], batch size: 13, lr: 4.70e-04
2022-05-28 04:09:07,143 INFO [train.py:761] (5/8) Epoch 8, batch 950, loss[loss=0.2925, simple_loss=0.3806, pruned_loss=0.1023, over 4675.00 frames.], tot_loss[loss=0.2938, simple_loss=0.3724, pruned_loss=0.1076, over 958358.75 frames.], batch size: 13, lr: 4.70e-04
2022-05-28 04:09:45,628 INFO [train.py:761] (5/8) Epoch 8, batch 1000, loss[loss=0.2681, simple_loss=0.3528, pruned_loss=0.09167, over 4766.00 frames.], tot_loss[loss=0.2969, simple_loss=0.375, pruned_loss=0.1094, over 960556.01 frames.], batch size: 20, lr: 4.71e-04
2022-05-28 04:10:23,165 INFO [train.py:761] (5/8) Epoch 8, batch 1050, loss[loss=0.2925, simple_loss=0.3813, pruned_loss=0.1018, over 4787.00 frames.], tot_loss[loss=0.2958, simple_loss=0.3736, pruned_loss=0.109, over 961629.78 frames.], batch size: 14, lr: 4.71e-04
2022-05-28 04:11:01,117 INFO [train.py:761] (5/8) Epoch 8, batch 1100, loss[loss=0.3064, simple_loss=0.396, pruned_loss=0.1084, over 4905.00 frames.], tot_loss[loss=0.2973, simple_loss=0.3747, pruned_loss=0.11, over 962817.26 frames.], batch size: 17, lr: 4.72e-04
2022-05-28 04:11:38,647 INFO [train.py:761] (5/8) Epoch 8, batch 1150, loss[loss=0.2773, simple_loss=0.344, pruned_loss=0.1053, over 4804.00 frames.], tot_loss[loss=0.2956, simple_loss=0.373, pruned_loss=0.1091, over 963723.15 frames.], batch size: 12, lr: 4.72e-04
2022-05-28 04:12:16,711 INFO [train.py:761] (5/8) Epoch 8, batch 1200, loss[loss=0.3776, simple_loss=0.4386, pruned_loss=0.1583, over 4902.00 frames.], tot_loss[loss=0.2961, simple_loss=0.3741, pruned_loss=0.1091, over 965487.14 frames.], batch size: 50, lr: 4.73e-04
2022-05-28 04:12:54,305 INFO [train.py:761] (5/8) Epoch 8, batch 1250, loss[loss=0.2811, simple_loss=0.3459, pruned_loss=0.1081, over 4722.00 frames.], tot_loss[loss=0.2948, simple_loss=0.3728, pruned_loss=0.1084, over 965464.18 frames.], batch size: 12, lr: 4.73e-04
2022-05-28 04:13:32,526 INFO [train.py:761] (5/8) Epoch 8, batch 1300, loss[loss=0.3236, simple_loss=0.3958, pruned_loss=0.1258, over 4985.00 frames.], tot_loss[loss=0.2961, simple_loss=0.3742, pruned_loss=0.109, over 966496.21 frames.], batch size: 15, lr: 4.74e-04
2022-05-28 04:14:09,980 INFO [train.py:761] (5/8) Epoch 8, batch 1350, loss[loss=0.2779, simple_loss=0.3514, pruned_loss=0.1022, over 4862.00 frames.], tot_loss[loss=0.2949, simple_loss=0.3729, pruned_loss=0.1085, over 966017.38 frames.], batch size: 13, lr: 4.74e-04
2022-05-28 04:14:48,213 INFO [train.py:761] (5/8) Epoch 8, batch 1400, loss[loss=0.2825, simple_loss=0.3716, pruned_loss=0.09668, over 4913.00 frames.], tot_loss[loss=0.2932, simple_loss=0.3715, pruned_loss=0.1074, over 966419.09 frames.], batch size: 14, lr: 4.75e-04
2022-05-28 04:15:25,685 INFO [train.py:761] (5/8) Epoch 8, batch 1450, loss[loss=0.3565, simple_loss=0.4226, pruned_loss=0.1452, over 4755.00 frames.], tot_loss[loss=0.2925, simple_loss=0.3708, pruned_loss=0.1071, over 965594.37 frames.], batch size: 15, lr: 4.75e-04
2022-05-28 04:16:03,666 INFO [train.py:761] (5/8) Epoch 8, batch 1500, loss[loss=0.252, simple_loss=0.339, pruned_loss=0.08249, over 4727.00 frames.], tot_loss[loss=0.2925, simple_loss=0.371, pruned_loss=0.107, over 966273.56 frames.], batch size: 12, lr: 4.76e-04
2022-05-28 04:16:41,292 INFO [train.py:761] (5/8) Epoch 8, batch 1550, loss[loss=0.2348, simple_loss=0.3236, pruned_loss=0.07301, over 4547.00 frames.], tot_loss[loss=0.2944, simple_loss=0.3728, pruned_loss=0.108, over 966126.08 frames.], batch size: 10, lr: 4.76e-04
2022-05-28 04:17:19,764 INFO [train.py:761] (5/8) Epoch 8, batch 1600, loss[loss=0.3079, simple_loss=0.3954, pruned_loss=0.1102, over 4914.00 frames.], tot_loss[loss=0.2931, simple_loss=0.3712, pruned_loss=0.1076, over 965869.61 frames.], batch size: 14, lr: 4.77e-04
2022-05-28 04:17:57,965 INFO [train.py:761] (5/8) Epoch 8, batch 1650, loss[loss=0.2475, simple_loss=0.3326, pruned_loss=0.08114, over 4722.00 frames.], tot_loss[loss=0.2914, simple_loss=0.3702, pruned_loss=0.1063, over 966061.66 frames.], batch size: 14, lr: 4.77e-04
2022-05-28 04:18:35,545 INFO [train.py:761] (5/8) Epoch 8, batch 1700, loss[loss=0.312, simple_loss=0.3923, pruned_loss=0.1158, over 4866.00 frames.], tot_loss[loss=0.2907, simple_loss=0.3698, pruned_loss=0.1058, over 966420.91 frames.], batch size: 18, lr: 4.78e-04
2022-05-28 04:19:13,257 INFO [train.py:761] (5/8) Epoch 8, batch 1750, loss[loss=0.2441, simple_loss=0.3221, pruned_loss=0.08304, over 4731.00 frames.], tot_loss[loss=0.2916, simple_loss=0.3707, pruned_loss=0.1063, over 966334.25 frames.], batch size: 11, lr: 4.78e-04
2022-05-28 04:19:50,590 INFO [train.py:761] (5/8) Epoch 8, batch 1800, loss[loss=0.2462, simple_loss=0.3234, pruned_loss=0.0845, over 4601.00 frames.], tot_loss[loss=0.2919, simple_loss=0.3709, pruned_loss=0.1065, over 966371.88 frames.], batch size: 10, lr: 4.79e-04
2022-05-28 04:20:28,266 INFO [train.py:761] (5/8) Epoch 8, batch 1850, loss[loss=0.2215, simple_loss=0.3009, pruned_loss=0.071, over 4726.00 frames.], tot_loss[loss=0.2907, simple_loss=0.3695, pruned_loss=0.106, over 966214.59 frames.], batch size: 11, lr: 4.79e-04
2022-05-28 04:21:06,300 INFO [train.py:761] (5/8) Epoch 8, batch 1900, loss[loss=0.3218, simple_loss=0.4114, pruned_loss=0.1161, over 4850.00 frames.], tot_loss[loss=0.29, simple_loss=0.3688, pruned_loss=0.1056, over 966398.84 frames.], batch size: 14, lr: 4.80e-04
2022-05-28 04:21:44,418 INFO [train.py:761] (5/8) Epoch 8, batch 1950, loss[loss=0.3669, simple_loss=0.429, pruned_loss=0.1524, over 4962.00 frames.], tot_loss[loss=0.2921, simple_loss=0.3701, pruned_loss=0.1071, over 967217.73 frames.], batch size: 47, lr: 4.80e-04
2022-05-28 04:22:22,562 INFO [train.py:761] (5/8) Epoch 8, batch 2000, loss[loss=0.2971, simple_loss=0.3871, pruned_loss=0.1036, over 4925.00 frames.], tot_loss[loss=0.2918, simple_loss=0.3705, pruned_loss=0.1065, over 968440.51 frames.], batch size: 14, lr: 4.81e-04
2022-05-28 04:23:00,500 INFO [train.py:761] (5/8) Epoch 8, batch 2050, loss[loss=0.2925, simple_loss=0.3729, pruned_loss=0.106, over 4846.00 frames.], tot_loss[loss=0.2919, simple_loss=0.3706, pruned_loss=0.1066, over 967627.67 frames.], batch size: 14, lr: 4.81e-04
2022-05-28 04:23:38,357 INFO [train.py:761] (5/8) Epoch 8, batch 2100, loss[loss=0.2925, simple_loss=0.3664, pruned_loss=0.1093, over 4985.00 frames.], tot_loss[loss=0.2918, simple_loss=0.3707, pruned_loss=0.1065, over 967503.26 frames.], batch size: 13, lr: 4.82e-04
2022-05-28 04:24:15,919 INFO [train.py:761] (5/8) Epoch 8, batch 2150, loss[loss=0.2974, simple_loss=0.3717, pruned_loss=0.1115, over 4722.00 frames.], tot_loss[loss=0.2898, simple_loss=0.3693, pruned_loss=0.1051, over 967329.61 frames.], batch size: 13, lr: 4.82e-04
2022-05-28 04:24:53,973 INFO [train.py:761] (5/8) Epoch 8, batch 2200, loss[loss=0.2888, simple_loss=0.3695, pruned_loss=0.1041, over 4850.00 frames.], tot_loss[loss=0.2898, simple_loss=0.3692, pruned_loss=0.1051, over 967063.26 frames.], batch size: 17, lr: 4.83e-04
2022-05-28 04:25:31,796 INFO [train.py:761] (5/8) Epoch 8, batch 2250, loss[loss=0.2681, simple_loss=0.3496, pruned_loss=0.09333, over 4780.00 frames.], tot_loss[loss=0.29, simple_loss=0.3695, pruned_loss=0.1052, over 966847.77 frames.], batch size: 13, lr: 4.83e-04
2022-05-28 04:26:09,596 INFO [train.py:761] (5/8) Epoch 8, batch 2300, loss[loss=0.2945, simple_loss=0.4016, pruned_loss=0.0937, over 4851.00 frames.], tot_loss[loss=0.2912, simple_loss=0.3713, pruned_loss=0.1055, over 966950.01 frames.], batch size: 14, lr: 4.84e-04
2022-05-28 04:26:47,602 INFO [train.py:761] (5/8) Epoch 8, batch 2350, loss[loss=0.218, simple_loss=0.2936, pruned_loss=0.07125, over 4820.00 frames.], tot_loss[loss=0.2914, simple_loss=0.3706, pruned_loss=0.1061, over 967786.49 frames.], batch size: 11, lr: 4.84e-04
2022-05-28 04:27:25,259 INFO [train.py:761] (5/8) Epoch 8, batch 2400, loss[loss=0.2365, simple_loss=0.3294, pruned_loss=0.07183, over 4968.00 frames.], tot_loss[loss=0.2904, simple_loss=0.37, pruned_loss=0.1054, over 968091.23 frames.], batch size: 15, lr: 4.85e-04
2022-05-28 04:28:02,817 INFO [train.py:761] (5/8) Epoch 8, batch 2450, loss[loss=0.3055, simple_loss=0.3875, pruned_loss=0.1118, over 4782.00 frames.], tot_loss[loss=0.2889, simple_loss=0.3687, pruned_loss=0.1046, over 967098.19 frames.], batch size: 15, lr: 4.85e-04
2022-05-28 04:28:41,064 INFO [train.py:761] (5/8) Epoch 8, batch 2500, loss[loss=0.3109, simple_loss=0.4005, pruned_loss=0.1107, over 4877.00 frames.], tot_loss[loss=0.2909, simple_loss=0.3701, pruned_loss=0.1059, over 966633.29 frames.], batch size: 15, lr: 4.86e-04
2022-05-28 04:29:18,892 INFO [train.py:761] (5/8) Epoch 8, batch 2550, loss[loss=0.2464, simple_loss=0.318, pruned_loss=0.08741, over 4678.00 frames.], tot_loss[loss=0.2901, simple_loss=0.3696, pruned_loss=0.1053, over 965792.68 frames.], batch size: 12, lr: 4.86e-04
2022-05-28 04:29:57,029 INFO [train.py:761] (5/8) Epoch 8, batch 2600, loss[loss=0.2361, simple_loss=0.3145, pruned_loss=0.0789, over 4655.00 frames.], tot_loss[loss=0.2885, simple_loss=0.3685, pruned_loss=0.1043, over 965963.75 frames.], batch size: 11, lr: 4.87e-04
2022-05-28 04:30:34,801 INFO [train.py:761] (5/8) Epoch 8, batch 2650, loss[loss=0.291, simple_loss=0.361, pruned_loss=0.1105, over 4972.00 frames.], tot_loss[loss=0.2889, simple_loss=0.3687, pruned_loss=0.1046, over 964539.75 frames.], batch size: 14, lr: 4.87e-04
2022-05-28 04:31:12,725 INFO [train.py:761] (5/8) Epoch 8, batch 2700, loss[loss=0.2786, simple_loss=0.3596, pruned_loss=0.09873, over 4965.00 frames.], tot_loss[loss=0.2888, simple_loss=0.3689, pruned_loss=0.1043, over 965720.03 frames.], batch size: 12, lr: 4.88e-04
2022-05-28 04:31:50,902 INFO [train.py:761] (5/8) Epoch 8, batch 2750, loss[loss=0.3216, simple_loss=0.3946, pruned_loss=0.1243, over 4849.00 frames.], tot_loss[loss=0.2883, simple_loss=0.3678, pruned_loss=0.1044, over 966715.66 frames.], batch size: 13, lr: 4.88e-04
2022-05-28 04:32:28,829 INFO [train.py:761] (5/8) Epoch 8, batch 2800, loss[loss=0.3516, simple_loss=0.4234, pruned_loss=0.14, over 4853.00 frames.], tot_loss[loss=0.2881, simple_loss=0.3681, pruned_loss=0.1041, over 965953.23 frames.], batch size: 14, lr: 4.89e-04
2022-05-28 04:33:06,637 INFO [train.py:761] (5/8) Epoch 8, batch 2850, loss[loss=0.3323, simple_loss=0.4012, pruned_loss=0.1317, over 4676.00 frames.], tot_loss[loss=0.2872, simple_loss=0.3672, pruned_loss=0.1035, over 965410.65 frames.], batch size: 13, lr: 4.89e-04
2022-05-28 04:33:44,890 INFO [train.py:761] (5/8) Epoch 8, batch 2900, loss[loss=0.3108, simple_loss=0.3801, pruned_loss=0.1207, over 4736.00 frames.], tot_loss[loss=0.2859, simple_loss=0.3662, pruned_loss=0.1028, over 965084.25 frames.], batch size: 12, lr: 4.90e-04
2022-05-28 04:34:22,757 INFO [train.py:761] (5/8) Epoch 8, batch 2950, loss[loss=0.3863, simple_loss=0.464, pruned_loss=0.1543, over 4770.00 frames.], tot_loss[loss=0.2867, simple_loss=0.3671, pruned_loss=0.1032, over 965344.31 frames.], batch size: 20, lr: 4.90e-04
2022-05-28 04:35:00,693 INFO [train.py:761] (5/8) Epoch 8, batch 3000, loss[loss=0.2745, simple_loss=0.351, pruned_loss=0.09896, over 4651.00 frames.], tot_loss[loss=0.2859, simple_loss=0.3667, pruned_loss=0.1026, over 965700.84 frames.], batch size: 11, lr: 4.90e-04
2022-05-28 04:35:00,693 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 04:35:10,690 INFO [train.py:790] (5/8) Epoch 8, validation: loss=0.2509, simple_loss=0.3531, pruned_loss=0.07439, over 944034.00 frames.
2022-05-28 04:35:48,449 INFO [train.py:761] (5/8) Epoch 8, batch 3050, loss[loss=0.2737, simple_loss=0.343, pruned_loss=0.1022, over 4742.00 frames.], tot_loss[loss=0.2859, simple_loss=0.3665, pruned_loss=0.1027, over 966095.54 frames.], batch size: 11, lr: 4.91e-04
2022-05-28 04:36:26,628 INFO [train.py:761] (5/8) Epoch 8, batch 3100, loss[loss=0.2997, simple_loss=0.3835, pruned_loss=0.1079, over 4858.00 frames.], tot_loss[loss=0.2895, simple_loss=0.369, pruned_loss=0.105, over 966846.25 frames.], batch size: 17, lr: 4.91e-04
2022-05-28 04:37:04,742 INFO [train.py:761] (5/8) Epoch 8, batch 3150, loss[loss=0.2843, simple_loss=0.354, pruned_loss=0.1072, over 4725.00 frames.], tot_loss[loss=0.2937, simple_loss=0.3718, pruned_loss=0.1078, over 965654.57 frames.], batch size: 13, lr: 4.92e-04
2022-05-28 04:37:42,656 INFO [train.py:761] (5/8) Epoch 8, batch 3200, loss[loss=0.3351, simple_loss=0.389, pruned_loss=0.1406, over 4795.00 frames.], tot_loss[loss=0.2999, simple_loss=0.375, pruned_loss=0.1124, over 965021.46 frames.], batch size: 20, lr: 4.92e-04
2022-05-28 04:38:20,619 INFO [train.py:761] (5/8) Epoch 8, batch 3250, loss[loss=0.3623, simple_loss=0.4127, pruned_loss=0.1559, over 4773.00 frames.], tot_loss[loss=0.304, simple_loss=0.3772, pruned_loss=0.1154, over 965066.43 frames.], batch size: 20, lr: 4.93e-04
2022-05-28 04:38:58,794 INFO [train.py:761] (5/8) Epoch 8, batch 3300, loss[loss=0.3461, simple_loss=0.4098, pruned_loss=0.1413, over 4881.00 frames.], tot_loss[loss=0.3072, simple_loss=0.3783, pruned_loss=0.1181, over 965977.46 frames.], batch size: 15, lr: 4.93e-04
2022-05-28 04:39:36,397 INFO [train.py:761] (5/8) Epoch 8, batch 3350, loss[loss=0.3707, simple_loss=0.4054, pruned_loss=0.1679, over 4640.00 frames.], tot_loss[loss=0.3105, simple_loss=0.3801, pruned_loss=0.1205, over 964815.45 frames.], batch size: 11, lr: 4.94e-04
2022-05-28 04:40:14,455 INFO [train.py:761] (5/8) Epoch 8, batch 3400, loss[loss=0.3038, simple_loss=0.3735, pruned_loss=0.117, over 4669.00 frames.], tot_loss[loss=0.3152, simple_loss=0.3824, pruned_loss=0.124, over 965195.89 frames.], batch size: 12, lr: 4.94e-04
2022-05-28 04:40:52,639 INFO [train.py:761] (5/8) Epoch 8, batch 3450, loss[loss=0.3371, simple_loss=0.3984, pruned_loss=0.138, over 4675.00 frames.], tot_loss[loss=0.3178, simple_loss=0.3828, pruned_loss=0.1264, over 964889.79 frames.], batch size: 13, lr: 4.95e-04
2022-05-28 04:41:31,122 INFO [train.py:761] (5/8) Epoch 8, batch 3500, loss[loss=0.3105, simple_loss=0.3678, pruned_loss=0.1266, over 4723.00 frames.], tot_loss[loss=0.3195, simple_loss=0.383, pruned_loss=0.128, over 964236.39 frames.], batch size: 14, lr: 4.95e-04
2022-05-28 04:42:09,346 INFO [train.py:761] (5/8) Epoch 8, batch 3550, loss[loss=0.2604, simple_loss=0.3252, pruned_loss=0.09773, over 4886.00 frames.], tot_loss[loss=0.3222, simple_loss=0.385, pruned_loss=0.1297, over 964403.84 frames.], batch size: 12, lr: 4.96e-04
2022-05-28 04:42:46,653 INFO [train.py:761] (5/8) Epoch 8, batch 3600, loss[loss=0.3105, simple_loss=0.3668, pruned_loss=0.1271, over 4976.00 frames.], tot_loss[loss=0.3227, simple_loss=0.3848, pruned_loss=0.1303, over 964274.51 frames.], batch size: 12, lr: 4.96e-04
2022-05-28 04:43:24,793 INFO [train.py:761] (5/8) Epoch 8, batch 3650, loss[loss=0.3037, simple_loss=0.3632, pruned_loss=0.1221, over 4662.00 frames.], tot_loss[loss=0.3223, simple_loss=0.3838, pruned_loss=0.1304, over 964008.18 frames.], batch size: 12, lr: 4.97e-04
2022-05-28 04:44:03,115 INFO [train.py:761] (5/8) Epoch 8, batch 3700, loss[loss=0.3948, simple_loss=0.4273, pruned_loss=0.1811, over 4775.00 frames.], tot_loss[loss=0.3234, simple_loss=0.3841, pruned_loss=0.1313, over 964615.17 frames.], batch size: 15, lr: 4.97e-04
2022-05-28 04:44:40,679 INFO [train.py:761] (5/8) Epoch 8, batch 3750, loss[loss=0.3258, simple_loss=0.3989, pruned_loss=0.1263, over 4848.00 frames.], tot_loss[loss=0.3255, simple_loss=0.3851, pruned_loss=0.1329, over 964489.12 frames.], batch size: 14, lr: 4.98e-04
2022-05-28 04:45:19,256 INFO [train.py:761] (5/8) Epoch 8, batch 3800, loss[loss=0.3779, simple_loss=0.4427, pruned_loss=0.1565, over 4882.00 frames.], tot_loss[loss=0.3294, simple_loss=0.3883, pruned_loss=0.1352, over 965068.54 frames.], batch size: 17, lr: 4.98e-04
2022-05-28 04:45:57,206 INFO [train.py:761] (5/8) Epoch 8, batch 3850, loss[loss=0.3246, simple_loss=0.3733, pruned_loss=0.138, over 4847.00 frames.], tot_loss[loss=0.3262, simple_loss=0.3852, pruned_loss=0.1336, over 964066.63 frames.], batch size: 11, lr: 4.99e-04
2022-05-28 04:46:34,743 INFO [train.py:761] (5/8) Epoch 8, batch 3900, loss[loss=0.3622, simple_loss=0.4193, pruned_loss=0.1525, over 4772.00 frames.], tot_loss[loss=0.3274, simple_loss=0.3866, pruned_loss=0.1341, over 963932.62 frames.], batch size: 15, lr: 4.99e-04
2022-05-28 04:47:12,661 INFO [train.py:761] (5/8) Epoch 8, batch 3950, loss[loss=0.3256, simple_loss=0.3978, pruned_loss=0.1267, over 4859.00 frames.], tot_loss[loss=0.3268, simple_loss=0.3854, pruned_loss=0.1341, over 964466.41 frames.], batch size: 17, lr: 5.00e-04
2022-05-28 04:47:51,419 INFO [train.py:761] (5/8) Epoch 8, batch 4000, loss[loss=0.33, simple_loss=0.3781, pruned_loss=0.1409, over 4738.00 frames.], tot_loss[loss=0.3292, simple_loss=0.3872, pruned_loss=0.1356, over 964725.94 frames.], batch size: 11, lr: 5.00e-04
2022-05-28 04:48:29,554 INFO [train.py:761] (5/8) Epoch 8, batch 4050, loss[loss=0.3134, simple_loss=0.3708, pruned_loss=0.128, over 4790.00 frames.], tot_loss[loss=0.3284, simple_loss=0.3868, pruned_loss=0.135, over 964042.10 frames.], batch size: 20, lr: 5.01e-04
2022-05-28 04:49:08,273 INFO [train.py:761] (5/8) Epoch 8, batch 4100, loss[loss=0.3205, simple_loss=0.3756, pruned_loss=0.1326, over 4892.00 frames.], tot_loss[loss=0.3281, simple_loss=0.3866, pruned_loss=0.1348, over 963435.86 frames.], batch size: 17, lr: 5.01e-04
2022-05-28 04:49:46,155 INFO [train.py:761] (5/8) Epoch 8, batch 4150, loss[loss=0.3558, simple_loss=0.4035, pruned_loss=0.1541, over 4785.00 frames.], tot_loss[loss=0.3289, simple_loss=0.3873, pruned_loss=0.1352, over 965513.92 frames.], batch size: 20, lr: 5.02e-04
2022-05-28 04:50:24,381 INFO [train.py:761] (5/8) Epoch 8, batch 4200, loss[loss=0.3681, simple_loss=0.4228, pruned_loss=0.1567, over 4852.00 frames.], tot_loss[loss=0.3278, simple_loss=0.3866, pruned_loss=0.1345, over 966019.22 frames.], batch size: 25, lr: 5.02e-04
2022-05-28 04:51:02,243 INFO [train.py:761] (5/8) Epoch 8, batch 4250, loss[loss=0.2916, simple_loss=0.3675, pruned_loss=0.1079, over 4849.00 frames.], tot_loss[loss=0.3299, simple_loss=0.3882, pruned_loss=0.1358, over 966039.10 frames.], batch size: 14, lr: 5.03e-04
2022-05-28 04:51:40,590 INFO [train.py:761] (5/8) Epoch 8, batch 4300, loss[loss=0.3029, simple_loss=0.3652, pruned_loss=0.1202, over 4976.00 frames.], tot_loss[loss=0.3308, simple_loss=0.3886, pruned_loss=0.1365, over 965723.94 frames.], batch size: 12, lr: 5.03e-04
2022-05-28 04:52:19,004 INFO [train.py:761] (5/8) Epoch 8, batch 4350, loss[loss=0.3746, simple_loss=0.4262, pruned_loss=0.1615, over 4949.00 frames.], tot_loss[loss=0.3306, simple_loss=0.3887, pruned_loss=0.1362, over 966212.22 frames.], batch size: 26, lr: 5.04e-04
2022-05-28 04:52:57,511 INFO [train.py:761] (5/8) Epoch 8, batch 4400, loss[loss=0.3049, simple_loss=0.3769, pruned_loss=0.1164, over 4979.00 frames.], tot_loss[loss=0.329, simple_loss=0.3881, pruned_loss=0.135, over 966433.89 frames.], batch size: 14, lr: 5.04e-04
2022-05-28 04:53:36,171 INFO [train.py:761] (5/8) Epoch 8, batch 4450, loss[loss=0.3143, simple_loss=0.382, pruned_loss=0.1233, over 4713.00 frames.], tot_loss[loss=0.3294, simple_loss=0.3881, pruned_loss=0.1353, over 965762.47 frames.], batch size: 14, lr: 5.05e-04
2022-05-28 04:54:14,313 INFO [train.py:761] (5/8) Epoch 8, batch 4500, loss[loss=0.3465, simple_loss=0.4029, pruned_loss=0.1451, over 4916.00 frames.], tot_loss[loss=0.3276, simple_loss=0.3871, pruned_loss=0.1341, over 966819.80 frames.], batch size: 14, lr: 5.05e-04
2022-05-28 04:54:52,100 INFO [train.py:761] (5/8) Epoch 8, batch 4550, loss[loss=0.3108, simple_loss=0.3588, pruned_loss=0.1314, over 4972.00 frames.], tot_loss[loss=0.3267, simple_loss=0.3865, pruned_loss=0.1334, over 967479.06 frames.], batch size: 12, lr: 5.06e-04
2022-05-28 04:55:30,610 INFO [train.py:761] (5/8) Epoch 8, batch 4600, loss[loss=0.2702, simple_loss=0.3561, pruned_loss=0.09218, over 4788.00 frames.], tot_loss[loss=0.3249, simple_loss=0.3856, pruned_loss=0.1321, over 967516.36 frames.], batch size: 13, lr: 5.06e-04
2022-05-28 04:56:08,672 INFO [train.py:761] (5/8) Epoch 8, batch 4650, loss[loss=0.3407, simple_loss=0.3874, pruned_loss=0.147, over 4958.00 frames.], tot_loss[loss=0.3246, simple_loss=0.3851, pruned_loss=0.132, over 968146.63 frames.], batch size: 16, lr: 5.07e-04
2022-05-28 04:56:47,102 INFO [train.py:761] (5/8) Epoch 8, batch 4700, loss[loss=0.3217, simple_loss=0.3985, pruned_loss=0.1224, over 4846.00 frames.], tot_loss[loss=0.3239, simple_loss=0.3844, pruned_loss=0.1317, over 968498.11 frames.], batch size: 13, lr: 5.07e-04
2022-05-28 04:57:25,644 INFO [train.py:761] (5/8) Epoch 8, batch 4750, loss[loss=0.3323, simple_loss=0.3924, pruned_loss=0.1361, over 4716.00 frames.], tot_loss[loss=0.3249, simple_loss=0.3856, pruned_loss=0.1321, over 967319.81 frames.], batch size: 14, lr: 5.08e-04
2022-05-28 04:58:03,763 INFO [train.py:761] (5/8) Epoch 8, batch 4800, loss[loss=0.4397, simple_loss=0.4557, pruned_loss=0.2118, over 4969.00 frames.], tot_loss[loss=0.3237, simple_loss=0.3844, pruned_loss=0.1315, over 968326.31 frames.], batch size: 45, lr: 5.08e-04
2022-05-28 04:58:41,831 INFO [train.py:761] (5/8) Epoch 8, batch 4850, loss[loss=0.3535, simple_loss=0.3773, pruned_loss=0.1649, over 4735.00 frames.], tot_loss[loss=0.3246, simple_loss=0.3843, pruned_loss=0.1324, over 967199.22 frames.], batch size: 12, lr: 5.09e-04
2022-05-28 04:59:19,965 INFO [train.py:761] (5/8) Epoch 8, batch 4900, loss[loss=0.4056, simple_loss=0.4379, pruned_loss=0.1867, over 4777.00 frames.], tot_loss[loss=0.3251, simple_loss=0.3849, pruned_loss=0.1326, over 966465.31 frames.], batch size: 15, lr: 5.09e-04
2022-05-28 04:59:58,397 INFO [train.py:761] (5/8) Epoch 8, batch 4950, loss[loss=0.2967, simple_loss=0.3498, pruned_loss=0.1218, over 4733.00 frames.], tot_loss[loss=0.3246, simple_loss=0.3846, pruned_loss=0.1323, over 965756.60 frames.], batch size: 12, lr: 5.10e-04
2022-05-28 05:00:36,807 INFO [train.py:761] (5/8) Epoch 8, batch 5000, loss[loss=0.3375, simple_loss=0.4056, pruned_loss=0.1347, over 4938.00 frames.], tot_loss[loss=0.3242, simple_loss=0.3846, pruned_loss=0.1319, over 966531.95 frames.], batch size: 27, lr: 5.10e-04
2022-05-28 05:01:14,874 INFO [train.py:761] (5/8) Epoch 8, batch 5050, loss[loss=0.3648, simple_loss=0.4044, pruned_loss=0.1627, over 4993.00 frames.], tot_loss[loss=0.3215, simple_loss=0.3817, pruned_loss=0.1306, over 965880.27 frames.], batch size: 13, lr: 5.10e-04
2022-05-28 05:01:53,601 INFO [train.py:761] (5/8) Epoch 8, batch 5100, loss[loss=0.3301, simple_loss=0.3752, pruned_loss=0.1425, over 4990.00 frames.], tot_loss[loss=0.3247, simple_loss=0.3842, pruned_loss=0.1327, over 967171.57 frames.], batch size: 13, lr: 5.11e-04
2022-05-28 05:02:31,517 INFO [train.py:761] (5/8) Epoch 8, batch 5150, loss[loss=0.2262, simple_loss=0.311, pruned_loss=0.07065, over 4639.00 frames.], tot_loss[loss=0.3231, simple_loss=0.3831, pruned_loss=0.1316, over 965505.67 frames.], batch size: 11, lr: 5.11e-04
2022-05-28 05:03:09,642 INFO [train.py:761] (5/8) Epoch 8, batch 5200, loss[loss=0.3058, simple_loss=0.3681, pruned_loss=0.1217, over 4798.00 frames.], tot_loss[loss=0.3247, simple_loss=0.3845, pruned_loss=0.1325, over 966175.84 frames.], batch size: 12, lr: 5.12e-04
2022-05-28 05:03:47,786 INFO [train.py:761] (5/8) Epoch 8, batch 5250, loss[loss=0.3014, simple_loss=0.3481, pruned_loss=0.1273, over 4735.00 frames.], tot_loss[loss=0.3243, simple_loss=0.3845, pruned_loss=0.1321, over 966493.24 frames.], batch size: 11, lr: 5.12e-04
2022-05-28 05:04:26,032 INFO [train.py:761] (5/8) Epoch 8, batch 5300, loss[loss=0.3027, simple_loss=0.373, pruned_loss=0.1162, over 4666.00 frames.], tot_loss[loss=0.3269, simple_loss=0.3869, pruned_loss=0.1335, over 966356.16 frames.], batch size: 13, lr: 5.13e-04
2022-05-28 05:05:04,282 INFO [train.py:761] (5/8) Epoch 8, batch 5350, loss[loss=0.3206, simple_loss=0.3769, pruned_loss=0.1322, over 4677.00 frames.], tot_loss[loss=0.3262, simple_loss=0.3859, pruned_loss=0.1332, over 966548.22 frames.], batch size: 13, lr: 5.13e-04
2022-05-28 05:05:42,485 INFO [train.py:761] (5/8) Epoch 8, batch 5400, loss[loss=0.3365, simple_loss=0.3952, pruned_loss=0.1389, over 4889.00 frames.], tot_loss[loss=0.3243, simple_loss=0.3842, pruned_loss=0.1322, over 966632.24 frames.], batch size: 15, lr: 5.14e-04
2022-05-28 05:06:21,138 INFO [train.py:761] (5/8) Epoch 8, batch 5450, loss[loss=0.3493, simple_loss=0.4006, pruned_loss=0.149, over 4976.00 frames.], tot_loss[loss=0.3219, simple_loss=0.3834, pruned_loss=0.1302, over 966667.22 frames.], batch size: 21, lr: 5.14e-04
2022-05-28 05:06:59,149 INFO [train.py:761] (5/8) Epoch 8, batch 5500, loss[loss=0.2989, simple_loss=0.3767, pruned_loss=0.1105, over 4826.00 frames.], tot_loss[loss=0.3219, simple_loss=0.3838, pruned_loss=0.13, over 966992.18 frames.], batch size: 20, lr: 5.15e-04
2022-05-28 05:07:37,633 INFO [train.py:761] (5/8) Epoch 8, batch 5550, loss[loss=0.2608, simple_loss=0.32, pruned_loss=0.1008, over 4829.00 frames.], tot_loss[loss=0.3207, simple_loss=0.3826, pruned_loss=0.1295, over 965936.38 frames.], batch size: 11, lr: 5.15e-04
2022-05-28 05:08:16,211 INFO [train.py:761] (5/8) Epoch 8, batch 5600, loss[loss=0.3447, simple_loss=0.3839, pruned_loss=0.1528, over 4640.00 frames.], tot_loss[loss=0.3219, simple_loss=0.3833, pruned_loss=0.1302, over 965949.61 frames.], batch size: 11, lr: 5.16e-04
2022-05-28 05:08:54,332 INFO [train.py:761] (5/8) Epoch 8, batch 5650, loss[loss=0.2806, simple_loss=0.3488, pruned_loss=0.1062, over 4788.00 frames.], tot_loss[loss=0.3202, simple_loss=0.3823, pruned_loss=0.129, over 966172.67 frames.], batch size: 13, lr: 5.16e-04
2022-05-28 05:09:32,570 INFO [train.py:761] (5/8) Epoch 8, batch 5700, loss[loss=0.3606, simple_loss=0.3902, pruned_loss=0.1655, over 4987.00 frames.], tot_loss[loss=0.3232, simple_loss=0.3844, pruned_loss=0.131, over 966825.85 frames.], batch size: 11, lr: 5.17e-04
2022-05-28 05:10:10,677 INFO [train.py:761] (5/8) Epoch 8, batch 5750, loss[loss=0.2971, simple_loss=0.3471, pruned_loss=0.1235, over 4643.00 frames.], tot_loss[loss=0.3233, simple_loss=0.3847, pruned_loss=0.1309, over 966011.09 frames.], batch size: 11, lr: 5.17e-04
2022-05-28 05:10:49,130 INFO [train.py:761] (5/8) Epoch 8, batch 5800, loss[loss=0.3597, simple_loss=0.4291, pruned_loss=0.1451, over 4724.00 frames.], tot_loss[loss=0.3241, simple_loss=0.3852, pruned_loss=0.1315, over 966245.70 frames.], batch size: 14, lr: 5.18e-04
2022-05-28 05:11:27,256 INFO [train.py:761] (5/8) Epoch 8, batch 5850, loss[loss=0.2982, simple_loss=0.3667, pruned_loss=0.1148, over 4908.00 frames.], tot_loss[loss=0.3228, simple_loss=0.3835, pruned_loss=0.131, over 965968.96 frames.], batch size: 14, lr: 5.18e-04
2022-05-28 05:12:05,091 INFO [train.py:761] (5/8) Epoch 8, batch 5900, loss[loss=0.3916, simple_loss=0.4286, pruned_loss=0.1773, over 4859.00 frames.], tot_loss[loss=0.3219, simple_loss=0.3827, pruned_loss=0.1305, over 966081.90 frames.], batch size: 18, lr: 5.19e-04
2022-05-28 05:12:43,120 INFO [train.py:761] (5/8) Epoch 8, batch 5950, loss[loss=0.2358, simple_loss=0.2967, pruned_loss=0.08748, over 4730.00 frames.], tot_loss[loss=0.3217, simple_loss=0.3827, pruned_loss=0.1303, over 965834.01 frames.], batch size: 11, lr: 5.19e-04
2022-05-28 05:13:21,353 INFO [train.py:761] (5/8) Epoch 8, batch 6000, loss[loss=0.3188, simple_loss=0.3923, pruned_loss=0.1226, over 4825.00 frames.], tot_loss[loss=0.3209, simple_loss=0.383, pruned_loss=0.1294, over 966436.30 frames.], batch size: 25, lr: 5.20e-04
2022-05-28 05:13:21,353 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 05:13:31,318 INFO [train.py:790] (5/8) Epoch 8, validation: loss=0.2395, simple_loss=0.3461, pruned_loss=0.06645, over 944034.00 frames.
2022-05-28 05:14:09,802 INFO [train.py:761] (5/8) Epoch 8, batch 6050, loss[loss=0.2829, simple_loss=0.3536, pruned_loss=0.1061, over 4644.00 frames.], tot_loss[loss=0.3183, simple_loss=0.3809, pruned_loss=0.1278, over 966075.71 frames.], batch size: 11, lr: 5.20e-04
2022-05-28 05:14:48,743 INFO [train.py:761] (5/8) Epoch 8, batch 6100, loss[loss=0.2956, simple_loss=0.3641, pruned_loss=0.1135, over 4663.00 frames.], tot_loss[loss=0.3182, simple_loss=0.381, pruned_loss=0.1277, over 966673.17 frames.], batch size: 12, lr: 5.21e-04
2022-05-28 05:15:26,834 INFO [train.py:761] (5/8) Epoch 8, batch 6150, loss[loss=0.2905, simple_loss=0.3575, pruned_loss=0.1117, over 4776.00 frames.], tot_loss[loss=0.3167, simple_loss=0.3795, pruned_loss=0.127, over 965971.71 frames.], batch size: 15, lr: 5.21e-04
2022-05-28 05:16:05,418 INFO [train.py:761] (5/8) Epoch 8, batch 6200, loss[loss=0.3701, simple_loss=0.4206, pruned_loss=0.1598, over 4787.00 frames.], tot_loss[loss=0.3154, simple_loss=0.3787, pruned_loss=0.1261, over 965121.45 frames.], batch size: 14, lr: 5.22e-04
2022-05-28 05:16:43,442 INFO [train.py:761] (5/8) Epoch 8, batch 6250, loss[loss=0.3235, simple_loss=0.3966, pruned_loss=0.1253, over 4849.00 frames.], tot_loss[loss=0.3164, simple_loss=0.3795, pruned_loss=0.1266, over 965384.91 frames.], batch size: 14, lr: 5.22e-04
2022-05-28 05:17:21,553 INFO [train.py:761] (5/8) Epoch 8, batch 6300, loss[loss=0.2888, simple_loss=0.3411, pruned_loss=0.1183, over 4889.00 frames.], tot_loss[loss=0.3181, simple_loss=0.3807, pruned_loss=0.1278, over 965716.86 frames.], batch size: 12, lr: 5.23e-04
2022-05-28 05:17:59,783 INFO [train.py:761] (5/8) Epoch 8, batch 6350, loss[loss=0.3556, simple_loss=0.3924, pruned_loss=0.1593, over 4889.00 frames.], tot_loss[loss=0.3169, simple_loss=0.3796, pruned_loss=0.1271, over 963970.48 frames.], batch size: 12, lr: 5.23e-04
2022-05-28 05:18:38,173 INFO [train.py:761] (5/8) Epoch 8, batch 6400, loss[loss=0.2356, simple_loss=0.3096, pruned_loss=0.08077, over 4662.00 frames.], tot_loss[loss=0.3175, simple_loss=0.3803, pruned_loss=0.1273, over 964463.02 frames.], batch size: 12, lr: 5.24e-04
2022-05-28 05:19:15,964 INFO [train.py:761] (5/8) Epoch 8, batch 6450, loss[loss=0.3084, simple_loss=0.372, pruned_loss=0.1223, over 4914.00 frames.], tot_loss[loss=0.3193, simple_loss=0.3812, pruned_loss=0.1287, over 964704.37 frames.], batch size: 14, lr: 5.24e-04
2022-05-28 05:19:54,740 INFO [train.py:761] (5/8) Epoch 8, batch 6500, loss[loss=0.3777, simple_loss=0.4327, pruned_loss=0.1614, over 4674.00 frames.], tot_loss[loss=0.3204, simple_loss=0.3825, pruned_loss=0.1292, over 963999.38 frames.], batch size: 12, lr: 5.25e-04
2022-05-28 05:20:33,251 INFO [train.py:761] (5/8) Epoch 8, batch 6550, loss[loss=0.2612, simple_loss=0.3468, pruned_loss=0.08776, over 4874.00 frames.], tot_loss[loss=0.32, simple_loss=0.3818, pruned_loss=0.1291, over 964954.49 frames.], batch size: 15, lr: 5.25e-04
2022-05-28 05:21:11,656 INFO [train.py:761] (5/8) Epoch 8, batch 6600, loss[loss=0.3467, simple_loss=0.4112, pruned_loss=0.1411, over 4913.00 frames.], tot_loss[loss=0.3215, simple_loss=0.3829, pruned_loss=0.13, over 964555.32 frames.], batch size: 14, lr: 5.26e-04
2022-05-28 05:21:50,257 INFO [train.py:761] (5/8) Epoch 8, batch 6650, loss[loss=0.328, simple_loss=0.3937, pruned_loss=0.1311, over 4786.00 frames.], tot_loss[loss=0.3191, simple_loss=0.3812, pruned_loss=0.1285, over 965472.30 frames.], batch size: 14, lr: 5.26e-04
2022-05-28 05:22:28,606 INFO [train.py:761] (5/8) Epoch 8, batch 6700, loss[loss=0.299, simple_loss=0.3616, pruned_loss=0.1182, over 4737.00 frames.], tot_loss[loss=0.318, simple_loss=0.3803, pruned_loss=0.1279, over 965454.70 frames.], batch size: 12, lr: 5.27e-04
2022-05-28 05:23:25,539 INFO [train.py:761] (5/8) Epoch 9, batch 0, loss[loss=0.2908, simple_loss=0.3811, pruned_loss=0.1002, over 4735.00 frames.], tot_loss[loss=0.2908, simple_loss=0.3811, pruned_loss=0.1002, over 4735.00 frames.], batch size: 12, lr: 5.27e-04
2022-05-28 05:24:10,978 INFO [train.py:761] (5/8) Epoch 9, batch 50, loss[loss=0.2803, simple_loss=0.3768, pruned_loss=0.09194, over 4872.00 frames.], tot_loss[loss=0.2828, simple_loss=0.3599, pruned_loss=0.1028, over 217280.42 frames.], batch size: 18, lr: 5.28e-04
2022-05-28 05:24:48,809 INFO [train.py:761] (5/8) Epoch 9, batch 100, loss[loss=0.3477, simple_loss=0.4177, pruned_loss=0.1389, over 4943.00 frames.], tot_loss[loss=0.2827, simple_loss=0.3611, pruned_loss=0.1021, over 382392.89 frames.], batch size: 43, lr: 5.28e-04
2022-05-28 05:25:27,080 INFO [train.py:761] (5/8) Epoch 9, batch 150, loss[loss=0.2623, simple_loss=0.326, pruned_loss=0.09933, over 4553.00 frames.], tot_loss[loss=0.2794, simple_loss=0.3587, pruned_loss=0.1001, over 509901.43 frames.], batch size: 10, lr: 5.29e-04
2022-05-28 05:26:05,320 INFO [train.py:761] (5/8) Epoch 9, batch 200, loss[loss=0.2511, simple_loss=0.3404, pruned_loss=0.08087, over 4796.00 frames.], tot_loss[loss=0.2789, simple_loss=0.3586, pruned_loss=0.09965, over 612354.18 frames.], batch size: 13, lr: 5.29e-04
2022-05-28 05:26:43,379 INFO [train.py:761] (5/8) Epoch 9, batch 250, loss[loss=0.3076, simple_loss=0.3838, pruned_loss=0.1157, over 4852.00 frames.], tot_loss[loss=0.2771, simple_loss=0.3572, pruned_loss=0.09852, over 691650.75 frames.], batch size: 14, lr: 5.30e-04
2022-05-28 05:27:21,091 INFO [train.py:761] (5/8) Epoch 9, batch 300, loss[loss=0.2842, simple_loss=0.3857, pruned_loss=0.09138, over 4861.00 frames.], tot_loss[loss=0.2766, simple_loss=0.3568, pruned_loss=0.09822, over 753405.45 frames.], batch size: 17, lr: 5.30e-04
2022-05-28 05:27:59,186 INFO [train.py:761] (5/8) Epoch 9, batch 350, loss[loss=0.32, simple_loss=0.4088, pruned_loss=0.1156, over 4670.00 frames.], tot_loss[loss=0.2778, simple_loss=0.3587, pruned_loss=0.09852, over 799716.19 frames.], batch size: 13, lr: 5.30e-04
2022-05-28 05:28:37,612 INFO [train.py:761] (5/8) Epoch 9, batch 400, loss[loss=0.3075, simple_loss=0.3912, pruned_loss=0.1119, over 4858.00 frames.], tot_loss[loss=0.2771, simple_loss=0.3585, pruned_loss=0.09782, over 836367.85 frames.], batch size: 14, lr: 5.31e-04
2022-05-28 05:29:15,934 INFO [train.py:761] (5/8) Epoch 9, batch 450, loss[loss=0.2861, simple_loss=0.3695, pruned_loss=0.1014, over 4976.00 frames.], tot_loss[loss=0.2759, simple_loss=0.3579, pruned_loss=0.09696, over 864997.34 frames.], batch size: 14, lr: 5.31e-04
2022-05-28 05:29:53,462 INFO [train.py:761] (5/8) Epoch 9, batch 500, loss[loss=0.2371, simple_loss=0.32, pruned_loss=0.07709, over 4582.00 frames.], tot_loss[loss=0.2758, simple_loss=0.3585, pruned_loss=0.09655, over 887766.50 frames.], batch size: 10, lr: 5.32e-04
2022-05-28 05:30:32,176 INFO [train.py:761] (5/8) Epoch 9, batch 550, loss[loss=0.2806, simple_loss=0.3655, pruned_loss=0.0979, over 4673.00 frames.], tot_loss[loss=0.2766, simple_loss=0.3595, pruned_loss=0.09682, over 905600.42 frames.], batch size: 13, lr: 5.32e-04
2022-05-28 05:31:10,354 INFO [train.py:761] (5/8) Epoch 9, batch 600, loss[loss=0.2736, simple_loss=0.3487, pruned_loss=0.09928, over 4978.00 frames.], tot_loss[loss=0.2767, simple_loss=0.3596, pruned_loss=0.09685, over 919302.45 frames.], batch size: 14, lr: 5.33e-04
2022-05-28 05:31:48,741 INFO [train.py:761] (5/8) Epoch 9, batch 650, loss[loss=0.3244, simple_loss=0.3877, pruned_loss=0.1305, over 4847.00 frames.], tot_loss[loss=0.2765, simple_loss=0.3589, pruned_loss=0.09706, over 929526.89 frames.], batch size: 14, lr: 5.33e-04
2022-05-28 05:32:26,843 INFO [train.py:761] (5/8) Epoch 9, batch 700, loss[loss=0.311, simple_loss=0.3803, pruned_loss=0.1209, over 4941.00 frames.], tot_loss[loss=0.278, simple_loss=0.3592, pruned_loss=0.09843, over 937746.42 frames.], batch size: 16, lr: 5.34e-04
2022-05-28 05:33:05,324 INFO [train.py:761] (5/8) Epoch 9, batch 750, loss[loss=0.2821, simple_loss=0.3711, pruned_loss=0.09659, over 4723.00 frames.], tot_loss[loss=0.2808, simple_loss=0.3617, pruned_loss=0.09996, over 944366.98 frames.], batch size: 13, lr: 5.34e-04
2022-05-28 05:33:43,229 INFO [train.py:761] (5/8) Epoch 9, batch 800, loss[loss=0.3001, simple_loss=0.3884, pruned_loss=0.1059, over 4887.00 frames.], tot_loss[loss=0.2824, simple_loss=0.3633, pruned_loss=0.1008, over 948446.59 frames.], batch size: 17, lr: 5.35e-04
2022-05-28 05:34:21,386 INFO [train.py:761] (5/8) Epoch 9, batch 850, loss[loss=0.2985, simple_loss=0.3773, pruned_loss=0.1098, over 4671.00 frames.], tot_loss[loss=0.2845, simple_loss=0.3642, pruned_loss=0.1025, over 951914.50 frames.], batch size: 13, lr: 5.35e-04
2022-05-28 05:34:59,572 INFO [train.py:761] (5/8) Epoch 9, batch 900, loss[loss=0.2444, simple_loss=0.3346, pruned_loss=0.07703, over 4922.00 frames.], tot_loss[loss=0.2853, simple_loss=0.3648, pruned_loss=0.1029, over 955542.52 frames.], batch size: 13, lr: 5.36e-04
2022-05-28 05:35:37,814 INFO [train.py:761] (5/8) Epoch 9, batch 950, loss[loss=0.3259, simple_loss=0.4081, pruned_loss=0.1219, over 4782.00 frames.], tot_loss[loss=0.2865, simple_loss=0.3655, pruned_loss=0.1037, over 958920.73 frames.], batch size: 14, lr: 5.36e-04
2022-05-28 05:36:14,989 INFO [train.py:761] (5/8) Epoch 9, batch 1000, loss[loss=0.2877, simple_loss=0.3724, pruned_loss=0.1015, over 4851.00 frames.], tot_loss[loss=0.2871, simple_loss=0.366, pruned_loss=0.104, over 961116.07 frames.], batch size: 14, lr: 5.37e-04
2022-05-28 05:36:53,321 INFO [train.py:761] (5/8) Epoch 9, batch 1050, loss[loss=0.2614, simple_loss=0.3589, pruned_loss=0.08199, over 4721.00 frames.], tot_loss[loss=0.2868, simple_loss=0.3663, pruned_loss=0.1037, over 962795.83 frames.], batch size: 14, lr: 5.37e-04
2022-05-28 05:37:30,928 INFO [train.py:761] (5/8) Epoch 9, batch 1100, loss[loss=0.2916, simple_loss=0.3963, pruned_loss=0.09344, over 4970.00 frames.], tot_loss[loss=0.286, simple_loss=0.3654, pruned_loss=0.1033, over 963908.97 frames.], batch size: 14, lr: 5.38e-04
2022-05-28 05:38:09,397 INFO [train.py:761] (5/8) Epoch 9, batch 1150, loss[loss=0.2954, simple_loss=0.3908, pruned_loss=0.09996, over 4786.00 frames.], tot_loss[loss=0.2859, simple_loss=0.3655, pruned_loss=0.1031, over 965215.21 frames.], batch size: 20, lr: 5.38e-04
2022-05-28 05:38:47,466 INFO [train.py:761] (5/8) Epoch 9, batch 1200, loss[loss=0.319, simple_loss=0.3852, pruned_loss=0.1264, over 4714.00 frames.], tot_loss[loss=0.2861, simple_loss=0.365, pruned_loss=0.1036, over 965326.65 frames.], batch size: 14, lr: 5.39e-04
2022-05-28 05:39:25,603 INFO [train.py:761] (5/8) Epoch 9, batch 1250, loss[loss=0.2669, simple_loss=0.3513, pruned_loss=0.09125, over 4886.00 frames.], tot_loss[loss=0.2847, simple_loss=0.3638, pruned_loss=0.1027, over 965315.88 frames.], batch size: 12, lr: 5.39e-04
2022-05-28 05:40:10,882 INFO [train.py:761] (5/8) Epoch 9, batch 1300, loss[loss=0.3102, simple_loss=0.3764, pruned_loss=0.122, over 4972.00 frames.], tot_loss[loss=0.2852, simple_loss=0.3642, pruned_loss=0.1031, over 965406.16 frames.], batch size: 15, lr: 5.40e-04
2022-05-28 05:41:10,268 INFO [train.py:761] (5/8) Epoch 9, batch 1350, loss[loss=0.3044, simple_loss=0.3851, pruned_loss=0.1119, over 4870.00 frames.], tot_loss[loss=0.2851, simple_loss=0.3642, pruned_loss=0.1031, over 966529.27 frames.], batch size: 15, lr: 5.40e-04
2022-05-28 05:41:48,389 INFO [train.py:761] (5/8) Epoch 9, batch 1400, loss[loss=0.2717, simple_loss=0.3556, pruned_loss=0.09389, over 4664.00 frames.], tot_loss[loss=0.2854, simple_loss=0.3646, pruned_loss=0.1031, over 966966.19 frames.], batch size: 12, lr: 5.41e-04
2022-05-28 05:42:26,170 INFO [train.py:761] (5/8) Epoch 9, batch 1450, loss[loss=0.2534, simple_loss=0.3555, pruned_loss=0.07566, over 4769.00 frames.], tot_loss[loss=0.2853, simple_loss=0.3648, pruned_loss=0.1029, over 966509.56 frames.], batch size: 15, lr: 5.41e-04
2022-05-28 05:43:11,687 INFO [train.py:761] (5/8) Epoch 9, batch 1500, loss[loss=0.3592, simple_loss=0.4413, pruned_loss=0.1386, over 4968.00 frames.], tot_loss[loss=0.286, simple_loss=0.3661, pruned_loss=0.1029, over 966958.33 frames.], batch size: 15, lr: 5.42e-04
2022-05-28 05:43:49,901 INFO [train.py:761] (5/8) Epoch 9, batch 1550, loss[loss=0.2296, simple_loss=0.3119, pruned_loss=0.07366, over 4813.00 frames.], tot_loss[loss=0.284, simple_loss=0.3644, pruned_loss=0.1018, over 967313.84 frames.], batch size: 12, lr: 5.42e-04
2022-05-28 05:44:27,554 INFO [train.py:761] (5/8) Epoch 9, batch 1600, loss[loss=0.2466, simple_loss=0.3459, pruned_loss=0.07363, over 4784.00 frames.], tot_loss[loss=0.2836, simple_loss=0.364, pruned_loss=0.1016, over 968016.23 frames.], batch size: 13, lr: 5.43e-04
2022-05-28 05:45:12,504 INFO [train.py:761] (5/8) Epoch 9, batch 1650, loss[loss=0.2901, simple_loss=0.355, pruned_loss=0.1126, over 4883.00 frames.], tot_loss[loss=0.2835, simple_loss=0.3633, pruned_loss=0.1019, over 967396.54 frames.], batch size: 12, lr: 5.43e-04
2022-05-28 05:45:50,004 INFO [train.py:761] (5/8) Epoch 9, batch 1700, loss[loss=0.28, simple_loss=0.3627, pruned_loss=0.09865, over 4726.00 frames.], tot_loss[loss=0.2829, simple_loss=0.3628, pruned_loss=0.1015, over 966728.08 frames.], batch size: 13, lr: 5.44e-04
2022-05-28 05:46:28,259 INFO [train.py:761] (5/8) Epoch 9, batch 1750, loss[loss=0.3098, simple_loss=0.371, pruned_loss=0.1243, over 4730.00 frames.], tot_loss[loss=0.2846, simple_loss=0.364, pruned_loss=0.1026, over 966833.38 frames.], batch size: 12, lr: 5.44e-04
2022-05-28 05:47:06,308 INFO [train.py:761] (5/8) Epoch 9, batch 1800, loss[loss=0.2946, simple_loss=0.3638, pruned_loss=0.1127, over 4650.00 frames.], tot_loss[loss=0.2829, simple_loss=0.3632, pruned_loss=0.1013, over 965696.64 frames.], batch size: 11, lr: 5.45e-04
2022-05-28 05:47:44,712 INFO [train.py:761] (5/8) Epoch 9, batch 1850, loss[loss=0.2429, simple_loss=0.3246, pruned_loss=0.0806, over 4916.00 frames.], tot_loss[loss=0.2847, simple_loss=0.3644, pruned_loss=0.1025, over 965678.47 frames.], batch size: 14, lr: 5.45e-04
2022-05-28 05:48:22,139 INFO [train.py:761] (5/8) Epoch 9, batch 1900, loss[loss=0.275, simple_loss=0.3627, pruned_loss=0.09359, over 4730.00 frames.], tot_loss[loss=0.2836, simple_loss=0.3635, pruned_loss=0.1019, over 965624.02 frames.], batch size: 13, lr: 5.46e-04
2022-05-28 05:49:00,115 INFO [train.py:761] (5/8) Epoch 9, batch 1950, loss[loss=0.2357, simple_loss=0.3357, pruned_loss=0.06784, over 4724.00 frames.], tot_loss[loss=0.2835, simple_loss=0.3638, pruned_loss=0.1016, over 966612.41 frames.], batch size: 13, lr: 5.46e-04
2022-05-28 05:49:37,373 INFO [train.py:761] (5/8) Epoch 9, batch 2000, loss[loss=0.262, simple_loss=0.3534, pruned_loss=0.08534, over 4829.00 frames.], tot_loss[loss=0.2839, simple_loss=0.3638, pruned_loss=0.102, over 965933.34 frames.], batch size: 26, lr: 5.47e-04
2022-05-28 05:50:18,097 INFO [train.py:761] (5/8) Epoch 9, batch 2050, loss[loss=0.2479, simple_loss=0.3562, pruned_loss=0.06985, over 4975.00 frames.], tot_loss[loss=0.2834, simple_loss=0.3637, pruned_loss=0.1016, over 966755.29 frames.], batch size: 15, lr: 5.47e-04
2022-05-28 05:50:55,988 INFO [train.py:761] (5/8) Epoch 9, batch 2100, loss[loss=0.2604, simple_loss=0.3467, pruned_loss=0.08707, over 4812.00 frames.], tot_loss[loss=0.2842, simple_loss=0.3641, pruned_loss=0.1022, over 966209.00 frames.], batch size: 20, lr: 5.48e-04
2022-05-28 05:51:33,787 INFO [train.py:761] (5/8) Epoch 9, batch 2150, loss[loss=0.3091, simple_loss=0.3648, pruned_loss=0.1267, over 4886.00 frames.], tot_loss[loss=0.2838, simple_loss=0.3636, pruned_loss=0.102, over 965801.18 frames.], batch size: 12, lr: 5.48e-04
2022-05-28 05:52:11,557 INFO [train.py:761] (5/8) Epoch 9, batch 2200, loss[loss=0.2963, simple_loss=0.3734, pruned_loss=0.1096, over 4729.00 frames.], tot_loss[loss=0.2827, simple_loss=0.3621, pruned_loss=0.1016, over 965881.35 frames.], batch size: 13, lr: 5.49e-04
2022-05-28 05:52:50,069 INFO [train.py:761] (5/8) Epoch 9, batch 2250, loss[loss=0.2549, simple_loss=0.3605, pruned_loss=0.0747, over 4795.00 frames.], tot_loss[loss=0.2812, simple_loss=0.3614, pruned_loss=0.1005, over 967020.90 frames.], batch size: 14, lr: 5.49e-04
2022-05-28 05:53:28,422 INFO [train.py:761] (5/8) Epoch 9, batch 2300, loss[loss=0.3455, simple_loss=0.4307, pruned_loss=0.1301, over 4779.00 frames.], tot_loss[loss=0.2826, simple_loss=0.3631, pruned_loss=0.101, over 967468.83 frames.], batch size: 16, lr: 5.50e-04
2022-05-28 05:54:06,476 INFO [train.py:761] (5/8) Epoch 9, batch 2350, loss[loss=0.2672, simple_loss=0.3436, pruned_loss=0.09539, over 4991.00 frames.], tot_loss[loss=0.2838, simple_loss=0.3641, pruned_loss=0.1018, over 966985.97 frames.], batch size: 13, lr: 5.50e-04
2022-05-28 05:54:44,298 INFO [train.py:761] (5/8) Epoch 9, batch 2400, loss[loss=0.3811, simple_loss=0.4294, pruned_loss=0.1664, over 4776.00 frames.], tot_loss[loss=0.2844, simple_loss=0.3642, pruned_loss=0.1023, over 966177.08 frames.], batch size: 15, lr: 5.50e-04
2022-05-28 05:55:22,742 INFO [train.py:761] (5/8) Epoch 9, batch 2450, loss[loss=0.2553, simple_loss=0.3283, pruned_loss=0.09115, over 4833.00 frames.], tot_loss[loss=0.2836, simple_loss=0.3633, pruned_loss=0.1019, over 966895.18 frames.], batch size: 11, lr: 5.51e-04
2022-05-28 05:56:00,750 INFO [train.py:761] (5/8) Epoch 9, batch 2500, loss[loss=0.2482, simple_loss=0.3388, pruned_loss=0.07881, over 4917.00 frames.], tot_loss[loss=0.2837, simple_loss=0.3632, pruned_loss=0.1021, over 967687.85 frames.], batch size: 14, lr: 5.51e-04
2022-05-28 05:56:38,822 INFO [train.py:761] (5/8) Epoch 9, batch 2550, loss[loss=0.2761, simple_loss=0.3479, pruned_loss=0.1021, over 4812.00 frames.], tot_loss[loss=0.2824, simple_loss=0.3621, pruned_loss=0.1014, over 967581.49 frames.], batch size: 12, lr: 5.52e-04
2022-05-28 05:57:16,617 INFO [train.py:761] (5/8) Epoch 9, batch 2600, loss[loss=0.2773, simple_loss=0.3723, pruned_loss=0.09113, over 4890.00 frames.], tot_loss[loss=0.2842, simple_loss=0.3633, pruned_loss=0.1026, over 966122.43 frames.], batch size: 15, lr: 5.52e-04
2022-05-28 05:57:54,603 INFO [train.py:761] (5/8) Epoch 9, batch 2650, loss[loss=0.2949, simple_loss=0.3872, pruned_loss=0.1013, over 4910.00 frames.], tot_loss[loss=0.2844, simple_loss=0.3642, pruned_loss=0.1023, over 966814.16 frames.], batch size: 14, lr: 5.53e-04
2022-05-28 05:58:32,521 INFO [train.py:761] (5/8) Epoch 9, batch 2700, loss[loss=0.2492, simple_loss=0.3116, pruned_loss=0.09338, over 4876.00 frames.], tot_loss[loss=0.2827, simple_loss=0.3631, pruned_loss=0.1012, over 967350.35 frames.], batch size: 12, lr: 5.53e-04
2022-05-28 05:59:10,404 INFO [train.py:761] (5/8) Epoch 9, batch 2750, loss[loss=0.3229, simple_loss=0.391, pruned_loss=0.1274, over 4894.00 frames.], tot_loss[loss=0.2812, simple_loss=0.3615, pruned_loss=0.1004, over 966589.61 frames.], batch size: 15, lr: 5.54e-04
2022-05-28 05:59:48,201 INFO [train.py:761] (5/8) Epoch 9, batch 2800, loss[loss=0.2911, simple_loss=0.367, pruned_loss=0.1076, over 4782.00 frames.], tot_loss[loss=0.2808, simple_loss=0.3613, pruned_loss=0.1001, over 966534.19 frames.], batch size: 15, lr: 5.54e-04
2022-05-28 06:00:26,265 INFO [train.py:761] (5/8) Epoch 9, batch 2850, loss[loss=0.2595, simple_loss=0.3366, pruned_loss=0.09119, over 4665.00 frames.], tot_loss[loss=0.279, simple_loss=0.3604, pruned_loss=0.09883, over 966629.70 frames.], batch size: 12, lr: 5.55e-04
2022-05-28 06:01:03,829 INFO [train.py:761] (5/8) Epoch 9, batch 2900, loss[loss=0.2875, simple_loss=0.3666, pruned_loss=0.1042, over 4920.00 frames.], tot_loss[loss=0.2791, simple_loss=0.3606, pruned_loss=0.09881, over 966773.43 frames.], batch size: 14, lr: 5.55e-04
2022-05-28 06:01:41,731 INFO [train.py:761] (5/8) Epoch 9, batch 2950, loss[loss=0.3541, simple_loss=0.4121, pruned_loss=0.1481, over 4784.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3595, pruned_loss=0.09831, over 966767.50 frames.], batch size: 14, lr: 5.56e-04
2022-05-28 06:02:19,454 INFO [train.py:761] (5/8) Epoch 9, batch 3000, loss[loss=0.2831, simple_loss=0.3578, pruned_loss=0.1042, over 4882.00 frames.], tot_loss[loss=0.2782, simple_loss=0.3596, pruned_loss=0.09838, over 966808.98 frames.], batch size: 15, lr: 5.56e-04
2022-05-28 06:02:19,454 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 06:02:29,886 INFO [train.py:790] (5/8) Epoch 9, validation: loss=0.2485, simple_loss=0.3485, pruned_loss=0.07419, over 944034.00 frames.
2022-05-28 06:03:08,247 INFO [train.py:761] (5/8) Epoch 9, batch 3050, loss[loss=0.2524, simple_loss=0.3337, pruned_loss=0.08557, over 4797.00 frames.], tot_loss[loss=0.279, simple_loss=0.3598, pruned_loss=0.09908, over 967841.71 frames.], batch size: 12, lr: 5.57e-04
2022-05-28 06:03:45,748 INFO [train.py:761] (5/8) Epoch 9, batch 3100, loss[loss=0.3083, simple_loss=0.3702, pruned_loss=0.1232, over 4669.00 frames.], tot_loss[loss=0.2818, simple_loss=0.3617, pruned_loss=0.101, over 967633.44 frames.], batch size: 13, lr: 5.57e-04
2022-05-28 06:04:24,309 INFO [train.py:761] (5/8) Epoch 9, batch 3150, loss[loss=0.3124, simple_loss=0.3855, pruned_loss=0.1196, over 4969.00 frames.], tot_loss[loss=0.2833, simple_loss=0.3621, pruned_loss=0.1023, over 967684.15 frames.], batch size: 16, lr: 5.58e-04
2022-05-28 06:05:01,823 INFO [train.py:761] (5/8) Epoch 9, batch 3200, loss[loss=0.3328, simple_loss=0.4078, pruned_loss=0.1289, over 4874.00 frames.], tot_loss[loss=0.286, simple_loss=0.3637, pruned_loss=0.1041, over 967906.84 frames.], batch size: 17, lr: 5.58e-04
2022-05-28 06:05:40,252 INFO [train.py:761] (5/8) Epoch 9, batch 3250, loss[loss=0.297, simple_loss=0.368, pruned_loss=0.113, over 4981.00 frames.], tot_loss[loss=0.2885, simple_loss=0.3634, pruned_loss=0.1068, over 968394.10 frames.], batch size: 14, lr: 5.59e-04
2022-05-28 06:06:18,336 INFO [train.py:761] (5/8) Epoch 9, batch 3300, loss[loss=0.2976, simple_loss=0.3699, pruned_loss=0.1127, over 4759.00 frames.], tot_loss[loss=0.2913, simple_loss=0.3647, pruned_loss=0.1089, over 967828.66 frames.], batch size: 15, lr: 5.59e-04
2022-05-28 06:06:56,820 INFO [train.py:761] (5/8) Epoch 9, batch 3350, loss[loss=0.2771, simple_loss=0.3483, pruned_loss=0.103, over 4670.00 frames.], tot_loss[loss=0.2976, simple_loss=0.3688, pruned_loss=0.1132, over 967011.49 frames.], batch size: 13, lr: 5.60e-04
2022-05-28 06:07:35,636 INFO [train.py:761] (5/8) Epoch 9, batch 3400, loss[loss=0.2958, simple_loss=0.3832, pruned_loss=0.1042, over 4883.00 frames.], tot_loss[loss=0.3015, simple_loss=0.3711, pruned_loss=0.116, over 966801.44 frames.], batch size: 15, lr: 5.60e-04
2022-05-28 06:08:14,176 INFO [train.py:761] (5/8) Epoch 9, batch 3450, loss[loss=0.2595, simple_loss=0.339, pruned_loss=0.08998, over 4846.00 frames.], tot_loss[loss=0.3058, simple_loss=0.3737, pruned_loss=0.1189, over 967462.65 frames.], batch size: 13, lr: 5.61e-04
2022-05-28 06:08:52,018 INFO [train.py:761] (5/8) Epoch 9, batch 3500, loss[loss=0.2623, simple_loss=0.3372, pruned_loss=0.09376, over 4718.00 frames.], tot_loss[loss=0.3086, simple_loss=0.3751, pruned_loss=0.1211, over 967896.05 frames.], batch size: 13, lr: 5.61e-04
2022-05-28 06:09:30,220 INFO [train.py:761] (5/8) Epoch 9, batch 3550, loss[loss=0.3114, simple_loss=0.3834, pruned_loss=0.1197, over 4818.00 frames.], tot_loss[loss=0.3116, simple_loss=0.3766, pruned_loss=0.1233, over 966924.54 frames.], batch size: 16, lr: 5.62e-04
2022-05-28 06:10:08,953 INFO [train.py:761] (5/8) Epoch 9, batch 3600, loss[loss=0.2914, simple_loss=0.3425, pruned_loss=0.1202, over 4820.00 frames.], tot_loss[loss=0.3129, simple_loss=0.3775, pruned_loss=0.1241, over 966894.65 frames.], batch size: 11, lr: 5.62e-04
2022-05-28 06:10:46,955 INFO [train.py:761] (5/8) Epoch 9, batch 3650, loss[loss=0.3479, simple_loss=0.4173, pruned_loss=0.1393, over 4782.00 frames.], tot_loss[loss=0.3144, simple_loss=0.3784, pruned_loss=0.1252, over 966281.45 frames.], batch size: 15, lr: 5.63e-04
2022-05-28 06:11:24,981 INFO [train.py:761] (5/8) Epoch 9, batch 3700, loss[loss=0.2871, simple_loss=0.3581, pruned_loss=0.1081, over 4783.00 frames.], tot_loss[loss=0.3159, simple_loss=0.3791, pruned_loss=0.1264, over 965278.45 frames.], batch size: 13, lr: 5.63e-04
2022-05-28 06:12:03,396 INFO [train.py:761] (5/8) Epoch 9, batch 3750, loss[loss=0.3813, simple_loss=0.4317, pruned_loss=0.1655, over 4945.00 frames.], tot_loss[loss=0.3164, simple_loss=0.3789, pruned_loss=0.1269, over 965095.41 frames.], batch size: 26, lr: 5.64e-04
2022-05-28 06:12:41,840 INFO [train.py:761] (5/8) Epoch 9, batch 3800, loss[loss=0.2897, simple_loss=0.3468, pruned_loss=0.1163, over 4972.00 frames.], tot_loss[loss=0.3162, simple_loss=0.3785, pruned_loss=0.127, over 964174.15 frames.], batch size: 12, lr: 5.64e-04
2022-05-28 06:13:20,412 INFO [train.py:761] (5/8) Epoch 9, batch 3850, loss[loss=0.2934, simple_loss=0.3501, pruned_loss=0.1183, over 4736.00 frames.], tot_loss[loss=0.3164, simple_loss=0.3783, pruned_loss=0.1273, over 964745.62 frames.], batch size: 12, lr: 5.65e-04
2022-05-28 06:13:58,512 INFO [train.py:761] (5/8) Epoch 9, batch 3900, loss[loss=0.3681, simple_loss=0.4149, pruned_loss=0.1607, over 4885.00 frames.], tot_loss[loss=0.3171, simple_loss=0.3788, pruned_loss=0.1277, over 964832.56 frames.], batch size: 17, lr: 5.65e-04
2022-05-28 06:14:36,770 INFO [train.py:761] (5/8) Epoch 9, batch 3950, loss[loss=0.3798, simple_loss=0.4252, pruned_loss=0.1671, over 4724.00 frames.], tot_loss[loss=0.3164, simple_loss=0.3778, pruned_loss=0.1275, over 964050.67 frames.], batch size: 14, lr: 5.66e-04
2022-05-28 06:15:14,777 INFO [train.py:761] (5/8) Epoch 9, batch 4000, loss[loss=0.2973, simple_loss=0.352, pruned_loss=0.1213, over 4788.00 frames.], tot_loss[loss=0.3183, simple_loss=0.3787, pruned_loss=0.1289, over 964902.06 frames.], batch size: 14, lr: 5.66e-04
2022-05-28 06:15:53,338 INFO [train.py:761] (5/8) Epoch 9, batch 4050, loss[loss=0.2693, simple_loss=0.3361, pruned_loss=0.1013, over 4847.00 frames.], tot_loss[loss=0.3188, simple_loss=0.3787, pruned_loss=0.1294, over 965431.76 frames.], batch size: 11, lr: 5.67e-04
2022-05-28 06:16:31,377 INFO [train.py:761] (5/8) Epoch 9, batch 4100, loss[loss=0.3205, simple_loss=0.385, pruned_loss=0.1281, over 4971.00 frames.], tot_loss[loss=0.3193, simple_loss=0.3794, pruned_loss=0.1296, over 965461.76 frames.], batch size: 14, lr: 5.67e-04
2022-05-28 06:17:09,432 INFO [train.py:761] (5/8) Epoch 9, batch 4150, loss[loss=0.3155, simple_loss=0.3908, pruned_loss=0.1201, over 4670.00 frames.], tot_loss[loss=0.3186, simple_loss=0.3793, pruned_loss=0.1289, over 965744.86 frames.], batch size: 13, lr: 5.68e-04
2022-05-28 06:17:46,913 INFO [train.py:761] (5/8) Epoch 9, batch 4200, loss[loss=0.2857, simple_loss=0.359, pruned_loss=0.1062, over 4860.00 frames.], tot_loss[loss=0.3187, simple_loss=0.3796, pruned_loss=0.1289, over 965801.64 frames.], batch size: 13, lr: 5.68e-04
2022-05-28 06:18:25,345 INFO [train.py:761] (5/8) Epoch 9, batch 4250, loss[loss=0.3138, simple_loss=0.3859, pruned_loss=0.1208, over 4841.00 frames.], tot_loss[loss=0.3174, simple_loss=0.379, pruned_loss=0.1279, over 966177.54 frames.], batch size: 20, lr: 5.69e-04
2022-05-28 06:19:03,752 INFO [train.py:761] (5/8) Epoch 9, batch 4300, loss[loss=0.3109, simple_loss=0.3794, pruned_loss=0.1212, over 4968.00 frames.], tot_loss[loss=0.3171, simple_loss=0.3789, pruned_loss=0.1277, over 967011.41 frames.], batch size: 15, lr: 5.69e-04
2022-05-28 06:19:41,781 INFO [train.py:761] (5/8) Epoch 9, batch 4350, loss[loss=0.2748, simple_loss=0.3337, pruned_loss=0.1079, over 4991.00 frames.], tot_loss[loss=0.3145, simple_loss=0.3763, pruned_loss=0.1264, over 966902.54 frames.], batch size: 11, lr: 5.70e-04
2022-05-28 06:20:19,836 INFO [train.py:761] (5/8) Epoch 9, batch 4400, loss[loss=0.3362, simple_loss=0.412, pruned_loss=0.1302, over 4911.00 frames.], tot_loss[loss=0.3152, simple_loss=0.3769, pruned_loss=0.1267, over 967243.30 frames.], batch size: 25, lr: 5.70e-04
2022-05-28 06:20:58,231 INFO [train.py:761] (5/8) Epoch 9, batch 4450, loss[loss=0.3313, simple_loss=0.379, pruned_loss=0.1418, over 4793.00 frames.], tot_loss[loss=0.3146, simple_loss=0.3765, pruned_loss=0.1263, over 966347.81 frames.], batch size: 12, lr: 5.71e-04
2022-05-28 06:21:36,647 INFO [train.py:761] (5/8) Epoch 9, batch 4500, loss[loss=0.2922, simple_loss=0.3674, pruned_loss=0.1085, over 4913.00 frames.], tot_loss[loss=0.316, simple_loss=0.3783, pruned_loss=0.1269, over 966293.63 frames.], batch size: 14, lr: 5.71e-04
2022-05-28 06:22:14,683 INFO [train.py:761] (5/8) Epoch 9, batch 4550, loss[loss=0.2542, simple_loss=0.3036, pruned_loss=0.1024, over 4832.00 frames.], tot_loss[loss=0.316, simple_loss=0.3781, pruned_loss=0.127, over 966236.93 frames.], batch size: 11, lr: 5.71e-04
2022-05-28 06:22:52,442 INFO [train.py:761] (5/8) Epoch 9, batch 4600, loss[loss=0.3477, simple_loss=0.3949, pruned_loss=0.1503, over 4991.00 frames.], tot_loss[loss=0.3141, simple_loss=0.3766, pruned_loss=0.1258, over 966569.55 frames.], batch size: 13, lr: 5.72e-04
2022-05-28 06:23:30,476 INFO [train.py:761] (5/8) Epoch 9, batch 4650, loss[loss=0.3852, simple_loss=0.4256, pruned_loss=0.1724, over 4663.00 frames.], tot_loss[loss=0.3154, simple_loss=0.3774, pruned_loss=0.1267, over 965861.07 frames.], batch size: 13, lr: 5.72e-04
2022-05-28 06:24:08,948 INFO [train.py:761] (5/8) Epoch 9, batch 4700, loss[loss=0.3343, simple_loss=0.3776, pruned_loss=0.1455, over 4669.00 frames.], tot_loss[loss=0.3144, simple_loss=0.3767, pruned_loss=0.1261, over 965634.34 frames.], batch size: 13, lr: 5.73e-04
2022-05-28 06:24:47,897 INFO [train.py:761] (5/8) Epoch 9, batch 4750, loss[loss=0.3669, simple_loss=0.4162, pruned_loss=0.1588, over 4785.00 frames.], tot_loss[loss=0.3135, simple_loss=0.3756, pruned_loss=0.1257, over 965892.09 frames.], batch size: 20, lr: 5.73e-04
2022-05-28 06:25:25,817 INFO [train.py:761] (5/8) Epoch 9, batch 4800, loss[loss=0.3327, simple_loss=0.4073, pruned_loss=0.129, over 4912.00 frames.], tot_loss[loss=0.3144, simple_loss=0.3765, pruned_loss=0.1262, over 965971.34 frames.], batch size: 14, lr: 5.74e-04
2022-05-28 06:26:03,970 INFO [train.py:761] (5/8) Epoch 9, batch 4850, loss[loss=0.2723, simple_loss=0.3575, pruned_loss=0.09358, over 4764.00 frames.], tot_loss[loss=0.3133, simple_loss=0.3752, pruned_loss=0.1257, over 965380.84 frames.], batch size: 15, lr: 5.74e-04
2022-05-28 06:26:42,530 INFO [train.py:761] (5/8) Epoch 9, batch 4900, loss[loss=0.354, simple_loss=0.4241, pruned_loss=0.1419, over 4953.00 frames.], tot_loss[loss=0.3136, simple_loss=0.3763, pruned_loss=0.1254, over 965676.56 frames.], batch size: 16, lr: 5.75e-04
2022-05-28 06:27:20,751 INFO [train.py:761] (5/8) Epoch 9, batch 4950, loss[loss=0.2833, simple_loss=0.3671, pruned_loss=0.0997, over 4974.00 frames.], tot_loss[loss=0.3138, simple_loss=0.3769, pruned_loss=0.1253, over 966204.18 frames.], batch size: 12, lr: 5.75e-04
2022-05-28 06:27:58,535 INFO [train.py:761] (5/8) Epoch 9, batch 5000, loss[loss=0.3432, simple_loss=0.4086, pruned_loss=0.1389, over 4919.00 frames.], tot_loss[loss=0.3149, simple_loss=0.3778, pruned_loss=0.126, over 965919.86 frames.], batch size: 14, lr: 5.76e-04
2022-05-28 06:28:36,901 INFO [train.py:761] (5/8) Epoch 9, batch 5050, loss[loss=0.3049, simple_loss=0.3745, pruned_loss=0.1176, over 4859.00 frames.], tot_loss[loss=0.3126, simple_loss=0.3758, pruned_loss=0.1247, over 965820.98 frames.], batch size: 18, lr: 5.76e-04
2022-05-28 06:29:14,614 INFO [train.py:761] (5/8) Epoch 9, batch 5100, loss[loss=0.2714, simple_loss=0.3251, pruned_loss=0.1089, over 4645.00 frames.], tot_loss[loss=0.3091, simple_loss=0.3729, pruned_loss=0.1226, over 965443.53 frames.], batch size: 11, lr: 5.77e-04
2022-05-28 06:29:53,032 INFO [train.py:761] (5/8) Epoch 9, batch 5150, loss[loss=0.2947, simple_loss=0.3486, pruned_loss=0.1204, over 4739.00 frames.], tot_loss[loss=0.3092, simple_loss=0.373, pruned_loss=0.1227, over 965211.40 frames.], batch size: 12, lr: 5.77e-04
2022-05-28 06:30:30,718 INFO [train.py:761] (5/8) Epoch 9, batch 5200, loss[loss=0.2527, simple_loss=0.3271, pruned_loss=0.08916, over 4649.00 frames.], tot_loss[loss=0.3098, simple_loss=0.3733, pruned_loss=0.1232, over 965797.61 frames.], batch size: 11, lr: 5.78e-04
2022-05-28 06:31:09,679 INFO [train.py:761] (5/8) Epoch 9, batch 5250, loss[loss=0.3615, simple_loss=0.412, pruned_loss=0.1555, over 4798.00 frames.], tot_loss[loss=0.31, simple_loss=0.3734, pruned_loss=0.1233, over 965369.45 frames.], batch size: 16, lr: 5.78e-04
2022-05-28 06:31:47,750 INFO [train.py:761] (5/8) Epoch 9, batch 5300, loss[loss=0.36, simple_loss=0.4215, pruned_loss=0.1493, over 4785.00 frames.], tot_loss[loss=0.3123, simple_loss=0.3753, pruned_loss=0.1246, over 965158.70 frames.], batch size: 13, lr: 5.79e-04
2022-05-28 06:32:26,203 INFO [train.py:761] (5/8) Epoch 9, batch 5350, loss[loss=0.3526, simple_loss=0.4151, pruned_loss=0.145, over 4802.00 frames.], tot_loss[loss=0.3116, simple_loss=0.3741, pruned_loss=0.1246, over 964647.32 frames.], batch size: 16, lr: 5.79e-04
2022-05-28 06:33:04,071 INFO [train.py:761] (5/8) Epoch 9, batch 5400, loss[loss=0.2592, simple_loss=0.3395, pruned_loss=0.08941, over 4756.00 frames.], tot_loss[loss=0.3116, simple_loss=0.3747, pruned_loss=0.1243, over 964493.39 frames.], batch size: 15, lr: 5.80e-04
2022-05-28 06:33:42,928 INFO [train.py:761] (5/8) Epoch 9, batch 5450, loss[loss=0.255, simple_loss=0.3253, pruned_loss=0.09239, over 4995.00 frames.], tot_loss[loss=0.3115, simple_loss=0.3746, pruned_loss=0.1242, over 964294.62 frames.], batch size: 11, lr: 5.80e-04
2022-05-28 06:34:20,747 INFO [train.py:761] (5/8) Epoch 9, batch 5500, loss[loss=0.3869, simple_loss=0.4384, pruned_loss=0.1677, over 4881.00 frames.], tot_loss[loss=0.3112, simple_loss=0.3741, pruned_loss=0.1241, over 963577.98 frames.], batch size: 15, lr: 5.81e-04
2022-05-28 06:34:59,009 INFO [train.py:761] (5/8) Epoch 9, batch 5550, loss[loss=0.2259, simple_loss=0.3081, pruned_loss=0.07184, over 4727.00 frames.], tot_loss[loss=0.309, simple_loss=0.3726, pruned_loss=0.1227, over 964356.99 frames.], batch size: 13, lr: 5.81e-04
2022-05-28 06:35:37,312 INFO [train.py:761] (5/8) Epoch 9, batch 5600, loss[loss=0.3598, simple_loss=0.4074, pruned_loss=0.1561, over 4670.00 frames.], tot_loss[loss=0.3092, simple_loss=0.3725, pruned_loss=0.123, over 964409.60 frames.], batch size: 12, lr: 5.82e-04
2022-05-28 06:36:15,379 INFO [train.py:761] (5/8) Epoch 9, batch 5650, loss[loss=0.2991, simple_loss=0.3697, pruned_loss=0.1143, over 4793.00 frames.], tot_loss[loss=0.3109, simple_loss=0.3741, pruned_loss=0.1239, over 965224.17 frames.], batch size: 16, lr: 5.82e-04
2022-05-28 06:36:53,390 INFO [train.py:761] (5/8) Epoch 9, batch 5700, loss[loss=0.2935, simple_loss=0.3586, pruned_loss=0.1142, over 4730.00 frames.], tot_loss[loss=0.3096, simple_loss=0.373, pruned_loss=0.1231, over 964314.58 frames.], batch size: 13, lr: 5.83e-04
2022-05-28 06:37:31,698 INFO [train.py:761] (5/8) Epoch 9, batch 5750, loss[loss=0.3191, simple_loss=0.3962, pruned_loss=0.121, over 4788.00 frames.], tot_loss[loss=0.3111, simple_loss=0.3744, pruned_loss=0.1239, over 965748.04 frames.], batch size: 14, lr: 5.83e-04
2022-05-28 06:38:10,279 INFO [train.py:761] (5/8) Epoch 9, batch 5800, loss[loss=0.3163, simple_loss=0.3969, pruned_loss=0.1179, over 4865.00 frames.], tot_loss[loss=0.313, simple_loss=0.3762, pruned_loss=0.1249, over 966696.26 frames.], batch size: 17, lr: 5.84e-04
2022-05-28 06:38:49,012 INFO [train.py:761] (5/8) Epoch 9, batch 5850, loss[loss=0.355, simple_loss=0.4172, pruned_loss=0.1464, over 4781.00 frames.], tot_loss[loss=0.3134, simple_loss=0.3766, pruned_loss=0.1251, over 966553.96 frames.], batch size: 15, lr: 5.84e-04
2022-05-28 06:39:27,388 INFO [train.py:761] (5/8) Epoch 9, batch 5900, loss[loss=0.3099, simple_loss=0.3899, pruned_loss=0.1149, over 4917.00 frames.], tot_loss[loss=0.311, simple_loss=0.3748, pruned_loss=0.1236, over 966868.35 frames.], batch size: 14, lr: 5.85e-04
2022-05-28 06:40:05,570 INFO [train.py:761] (5/8) Epoch 9, batch 5950, loss[loss=0.3197, simple_loss=0.3641, pruned_loss=0.1377, over 4740.00 frames.], tot_loss[loss=0.3108, simple_loss=0.3743, pruned_loss=0.1237, over 965808.26 frames.], batch size: 11, lr: 5.85e-04
2022-05-28 06:40:44,184 INFO [train.py:761] (5/8) Epoch 9, batch 6000, loss[loss=0.2892, simple_loss=0.3533, pruned_loss=0.1126, over 4804.00 frames.], tot_loss[loss=0.3115, simple_loss=0.3748, pruned_loss=0.1241, over 966423.61 frames.], batch size: 12, lr: 5.86e-04
2022-05-28 06:40:44,185 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 06:40:54,199 INFO [train.py:790] (5/8) Epoch 9, validation: loss=0.2327, simple_loss=0.34, pruned_loss=0.06269, over 944034.00 frames.
2022-05-28 06:41:32,594 INFO [train.py:761] (5/8) Epoch 9, batch 6050, loss[loss=0.2585, simple_loss=0.3312, pruned_loss=0.09287, over 4732.00 frames.], tot_loss[loss=0.311, simple_loss=0.3745, pruned_loss=0.1237, over 965582.99 frames.], batch size: 11, lr: 5.86e-04
2022-05-28 06:42:10,597 INFO [train.py:761] (5/8) Epoch 9, batch 6100, loss[loss=0.2892, simple_loss=0.3563, pruned_loss=0.111, over 4848.00 frames.], tot_loss[loss=0.3121, simple_loss=0.3752, pruned_loss=0.1245, over 966768.72 frames.], batch size: 14, lr: 5.87e-04
2022-05-28 06:42:48,852 INFO [train.py:761] (5/8) Epoch 9, batch 6150, loss[loss=0.2458, simple_loss=0.3151, pruned_loss=0.08827, over 4633.00 frames.], tot_loss[loss=0.3126, simple_loss=0.3752, pruned_loss=0.125, over 966759.23 frames.], batch size: 11, lr: 5.87e-04
2022-05-28 06:43:26,904 INFO [train.py:761] (5/8) Epoch 9, batch 6200, loss[loss=0.3074, simple_loss=0.3668, pruned_loss=0.124, over 4816.00 frames.], tot_loss[loss=0.3087, simple_loss=0.372, pruned_loss=0.1227, over 966714.95 frames.], batch size: 18, lr: 5.88e-04
2022-05-28 06:44:05,395 INFO [train.py:761] (5/8) Epoch 9, batch 6250, loss[loss=0.3447, simple_loss=0.4111, pruned_loss=0.1391, over 4929.00 frames.], tot_loss[loss=0.3086, simple_loss=0.3722, pruned_loss=0.1225, over 966414.14 frames.], batch size: 25, lr: 5.88e-04
2022-05-28 06:44:43,441 INFO [train.py:761] (5/8) Epoch 9, batch 6300, loss[loss=0.3203, simple_loss=0.3828, pruned_loss=0.1289, over 4783.00 frames.], tot_loss[loss=0.3082, simple_loss=0.3718, pruned_loss=0.1223, over 966254.15 frames.], batch size: 16, lr: 5.89e-04
2022-05-28 06:45:21,717 INFO [train.py:761] (5/8) Epoch 9, batch 6350, loss[loss=0.3388, simple_loss=0.4126, pruned_loss=0.1326, over 4967.00 frames.], tot_loss[loss=0.3065, simple_loss=0.3707, pruned_loss=0.1212, over 967001.49 frames.], batch size: 15, lr: 5.89e-04
2022-05-28 06:45:59,682 INFO [train.py:761] (5/8) Epoch 9, batch 6400, loss[loss=0.2924, simple_loss=0.3576, pruned_loss=0.1137, over 4882.00 frames.], tot_loss[loss=0.3043, simple_loss=0.3691, pruned_loss=0.1198, over 966841.28 frames.], batch size: 26, lr: 5.90e-04
2022-05-28 06:46:38,513 INFO [train.py:761] (5/8) Epoch 9, batch 6450, loss[loss=0.3645, simple_loss=0.4218, pruned_loss=0.1535, over 4761.00 frames.], tot_loss[loss=0.307, simple_loss=0.3712, pruned_loss=0.1214, over 966978.36 frames.], batch size: 15, lr: 5.90e-04
2022-05-28 06:47:16,428 INFO [train.py:761] (5/8) Epoch 9, batch 6500, loss[loss=0.3292, simple_loss=0.3985, pruned_loss=0.1299, over 4724.00 frames.], tot_loss[loss=0.3076, simple_loss=0.3716, pruned_loss=0.1218, over 965680.26 frames.], batch size: 13, lr: 5.91e-04
2022-05-28 06:47:55,181 INFO [train.py:761] (5/8) Epoch 9, batch 6550, loss[loss=0.272, simple_loss=0.3395, pruned_loss=0.1023, over 4978.00 frames.], tot_loss[loss=0.3067, simple_loss=0.3716, pruned_loss=0.1209, over 965683.04 frames.], batch size: 12, lr: 5.91e-04
2022-05-28 06:48:33,716 INFO [train.py:761] (5/8) Epoch 9, batch 6600, loss[loss=0.3765, simple_loss=0.4153, pruned_loss=0.1688, over 4915.00 frames.], tot_loss[loss=0.3061, simple_loss=0.3711, pruned_loss=0.1205, over 966961.61 frames.], batch size: 14, lr: 5.92e-04
2022-05-28 06:49:11,953 INFO [train.py:761] (5/8) Epoch 9, batch 6650, loss[loss=0.2839, simple_loss=0.3491, pruned_loss=0.1093, over 4983.00 frames.], tot_loss[loss=0.3061, simple_loss=0.371, pruned_loss=0.1206, over 966752.01 frames.], batch size: 14, lr: 5.92e-04
2022-05-28 06:49:49,828 INFO [train.py:761] (5/8) Epoch 9, batch 6700, loss[loss=0.3018, simple_loss=0.3661, pruned_loss=0.1188, over 4916.00 frames.], tot_loss[loss=0.3051, simple_loss=0.3702, pruned_loss=0.1199, over 967130.05 frames.], batch size: 14, lr: 5.92e-04
2022-05-28 06:50:46,963 INFO [train.py:761] (5/8) Epoch 10, batch 0, loss[loss=0.244, simple_loss=0.3466, pruned_loss=0.07069, over 4780.00 frames.], tot_loss[loss=0.244, simple_loss=0.3466, pruned_loss=0.07069, over 4780.00 frames.], batch size: 16, lr: 5.93e-04
2022-05-28 06:51:25,145 INFO [train.py:761] (5/8) Epoch 10, batch 50, loss[loss=0.2888, simple_loss=0.3626, pruned_loss=0.1075, over 4878.00 frames.], tot_loss[loss=0.2846, simple_loss=0.3633, pruned_loss=0.1029, over 218413.62 frames.], batch size: 18, lr: 5.93e-04
2022-05-28 06:52:03,334 INFO [train.py:761] (5/8) Epoch 10, batch 100, loss[loss=0.2912, simple_loss=0.3732, pruned_loss=0.1046, over 4977.00 frames.], tot_loss[loss=0.2807, simple_loss=0.3591, pruned_loss=0.1012, over 384413.58 frames.], batch size: 15, lr: 5.94e-04
2022-05-28 06:52:41,389 INFO [train.py:761] (5/8) Epoch 10, batch 150, loss[loss=0.3149, simple_loss=0.4037, pruned_loss=0.1131, over 4909.00 frames.], tot_loss[loss=0.283, simple_loss=0.3626, pruned_loss=0.1017, over 514336.91 frames.], batch size: 46, lr: 5.94e-04
2022-05-28 06:53:19,296 INFO [train.py:761] (5/8) Epoch 10, batch 200, loss[loss=0.2626, simple_loss=0.3536, pruned_loss=0.08579, over 4851.00 frames.], tot_loss[loss=0.2817, simple_loss=0.3619, pruned_loss=0.1008, over 614489.40 frames.], batch size: 14, lr: 5.95e-04
2022-05-28 06:53:57,315 INFO [train.py:761] (5/8) Epoch 10, batch 250, loss[loss=0.2773, simple_loss=0.3696, pruned_loss=0.09251, over 4875.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3581, pruned_loss=0.09909, over 691457.59 frames.], batch size: 17, lr: 5.95e-04
2022-05-28 06:54:35,112 INFO [train.py:761] (5/8) Epoch 10, batch 300, loss[loss=0.2238, simple_loss=0.3042, pruned_loss=0.07175, over 4820.00 frames.], tot_loss[loss=0.2763, simple_loss=0.3566, pruned_loss=0.09798, over 751743.31 frames.], batch size: 11, lr: 5.96e-04
2022-05-28 06:55:12,859 INFO [train.py:761] (5/8) Epoch 10, batch 350, loss[loss=0.3608, simple_loss=0.4322, pruned_loss=0.1447, over 4763.00 frames.], tot_loss[loss=0.2733, simple_loss=0.3551, pruned_loss=0.0957, over 799049.37 frames.], batch size: 18, lr: 5.96e-04
2022-05-28 06:55:50,866 INFO [train.py:761] (5/8) Epoch 10, batch 400, loss[loss=0.2682, simple_loss=0.3538, pruned_loss=0.09129, over 4991.00 frames.], tot_loss[loss=0.2698, simple_loss=0.3522, pruned_loss=0.09368, over 836164.04 frames.], batch size: 21, lr: 5.97e-04
2022-05-28 06:56:28,658 INFO [train.py:761] (5/8) Epoch 10, batch 450, loss[loss=0.3286, simple_loss=0.4062, pruned_loss=0.1255, over 4967.00 frames.], tot_loss[loss=0.2695, simple_loss=0.352, pruned_loss=0.09352, over 864780.85 frames.], batch size: 15, lr: 5.97e-04
2022-05-28 06:57:06,891 INFO [train.py:761] (5/8) Epoch 10, batch 500, loss[loss=0.257, simple_loss=0.343, pruned_loss=0.08553, over 4852.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3501, pruned_loss=0.09249, over 888209.05 frames.], batch size: 13, lr: 5.98e-04
2022-05-28 06:57:44,527 INFO [train.py:761] (5/8) Epoch 10, batch 550, loss[loss=0.2544, simple_loss=0.358, pruned_loss=0.07537, over 4716.00 frames.], tot_loss[loss=0.2682, simple_loss=0.3514, pruned_loss=0.0925, over 906035.48 frames.], batch size: 14, lr: 5.98e-04
2022-05-28 06:58:23,093 INFO [train.py:761] (5/8) Epoch 10, batch 600, loss[loss=0.2378, simple_loss=0.3151, pruned_loss=0.08024, over 4992.00 frames.], tot_loss[loss=0.2676, simple_loss=0.3509, pruned_loss=0.09209, over 919277.03 frames.], batch size: 13, lr: 5.99e-04
2022-05-28 06:59:01,015 INFO [train.py:761] (5/8) Epoch 10, batch 650, loss[loss=0.3469, simple_loss=0.4012, pruned_loss=0.1463, over 4787.00 frames.], tot_loss[loss=0.2685, simple_loss=0.3513, pruned_loss=0.09286, over 929276.01 frames.], batch size: 13, lr: 5.99e-04
2022-05-28 06:59:38,462 INFO [train.py:761] (5/8) Epoch 10, batch 700, loss[loss=0.3202, simple_loss=0.3943, pruned_loss=0.123, over 4673.00 frames.], tot_loss[loss=0.2713, simple_loss=0.3536, pruned_loss=0.09451, over 937966.67 frames.], batch size: 13, lr: 6.00e-04
2022-05-28 07:00:15,831 INFO [train.py:761] (5/8) Epoch 10, batch 750, loss[loss=0.2713, simple_loss=0.3421, pruned_loss=0.1003, over 4730.00 frames.], tot_loss[loss=0.2732, simple_loss=0.3551, pruned_loss=0.09561, over 943689.92 frames.], batch size: 12, lr: 6.00e-04
2022-05-28 07:00:53,905 INFO [train.py:761] (5/8) Epoch 10, batch 800, loss[loss=0.4048, simple_loss=0.4582, pruned_loss=0.1757, over 4961.00 frames.], tot_loss[loss=0.2753, simple_loss=0.3569, pruned_loss=0.09689, over 948537.29 frames.], batch size: 51, lr: 6.01e-04
2022-05-28 07:01:32,025 INFO [train.py:761] (5/8) Epoch 10, batch 850, loss[loss=0.2645, simple_loss=0.3486, pruned_loss=0.09024, over 4722.00 frames.], tot_loss[loss=0.2771, simple_loss=0.3583, pruned_loss=0.09798, over 952700.08 frames.], batch size: 14, lr: 6.01e-04
2022-05-28 07:02:10,589 INFO [train.py:761] (5/8) Epoch 10, batch 900, loss[loss=0.2847, simple_loss=0.3643, pruned_loss=0.1025, over 4852.00 frames.], tot_loss[loss=0.2779, simple_loss=0.3586, pruned_loss=0.09859, over 955155.84 frames.], batch size: 25, lr: 6.02e-04
2022-05-28 07:02:48,583 INFO [train.py:761] (5/8) Epoch 10, batch 950, loss[loss=0.2825, simple_loss=0.3628, pruned_loss=0.1011, over 4928.00 frames.], tot_loss[loss=0.2774, simple_loss=0.3575, pruned_loss=0.09865, over 957818.38 frames.], batch size: 13, lr: 6.02e-04
2022-05-28 07:03:26,723 INFO [train.py:761] (5/8) Epoch 10, batch 1000, loss[loss=0.2822, simple_loss=0.3799, pruned_loss=0.09223, over 4729.00 frames.], tot_loss[loss=0.2784, simple_loss=0.3581, pruned_loss=0.09931, over 959103.55 frames.], batch size: 14, lr: 6.03e-04
2022-05-28 07:04:04,607 INFO [train.py:761] (5/8) Epoch 10, batch 1050, loss[loss=0.3046, simple_loss=0.3758, pruned_loss=0.1167, over 4850.00 frames.], tot_loss[loss=0.2793, simple_loss=0.359, pruned_loss=0.09976, over 961467.31 frames.], batch size: 13, lr: 6.03e-04
2022-05-28 07:04:42,384 INFO [train.py:761] (5/8) Epoch 10, batch 1100, loss[loss=0.3172, simple_loss=0.4019, pruned_loss=0.1163, over 4782.00 frames.], tot_loss[loss=0.279, simple_loss=0.3586, pruned_loss=0.09973, over 961984.95 frames.], batch size: 25, lr: 6.04e-04
2022-05-28 07:05:20,256 INFO [train.py:761] (5/8) Epoch 10, batch 1150, loss[loss=0.3045, simple_loss=0.382, pruned_loss=0.1135, over 4717.00 frames.], tot_loss[loss=0.2785, simple_loss=0.3581, pruned_loss=0.09944, over 962891.57 frames.], batch size: 14, lr: 6.04e-04
2022-05-28 07:05:58,037 INFO [train.py:761] (5/8) Epoch 10, batch 1200, loss[loss=0.274, simple_loss=0.3765, pruned_loss=0.08579, over 4849.00 frames.], tot_loss[loss=0.279, simple_loss=0.3588, pruned_loss=0.09964, over 964251.95 frames.], batch size: 20, lr: 6.05e-04
2022-05-28 07:06:35,744 INFO [train.py:761] (5/8) Epoch 10, batch 1250, loss[loss=0.2449, simple_loss=0.3348, pruned_loss=0.07744, over 4865.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3578, pruned_loss=0.09915, over 963633.87 frames.], batch size: 18, lr: 6.05e-04
2022-05-28 07:07:13,683 INFO [train.py:761] (5/8) Epoch 10, batch 1300, loss[loss=0.2694, simple_loss=0.3516, pruned_loss=0.09362, over 4787.00 frames.], tot_loss[loss=0.2792, simple_loss=0.3588, pruned_loss=0.09975, over 964481.87 frames.], batch size: 13, lr: 6.06e-04
2022-05-28 07:07:51,836 INFO [train.py:761] (5/8) Epoch 10, batch 1350, loss[loss=0.2919, simple_loss=0.365, pruned_loss=0.1094, over 4778.00 frames.], tot_loss[loss=0.2787, simple_loss=0.3584, pruned_loss=0.09947, over 964437.57 frames.], batch size: 16, lr: 6.06e-04
2022-05-28 07:08:29,790 INFO [train.py:761] (5/8) Epoch 10, batch 1400, loss[loss=0.3062, simple_loss=0.3976, pruned_loss=0.1074, over 4899.00 frames.], tot_loss[loss=0.2799, simple_loss=0.3589, pruned_loss=0.1005, over 965115.89 frames.], batch size: 15, lr: 6.07e-04
2022-05-28 07:09:07,888 INFO [train.py:761] (5/8) Epoch 10, batch 1450, loss[loss=0.2584, simple_loss=0.3537, pruned_loss=0.08149, over 4918.00 frames.], tot_loss[loss=0.2774, simple_loss=0.3568, pruned_loss=0.09897, over 965205.00 frames.], batch size: 13, lr: 6.07e-04
2022-05-28 07:09:45,483 INFO [train.py:761] (5/8) Epoch 10, batch 1500, loss[loss=0.3086, simple_loss=0.3997, pruned_loss=0.1087, over 4819.00 frames.], tot_loss[loss=0.2768, simple_loss=0.3566, pruned_loss=0.09852, over 965054.99 frames.], batch size: 20, lr: 6.08e-04
2022-05-28 07:10:23,396 INFO [train.py:761] (5/8) Epoch 10, batch 1550, loss[loss=0.2467, simple_loss=0.35, pruned_loss=0.07169, over 4931.00 frames.], tot_loss[loss=0.2766, simple_loss=0.3564, pruned_loss=0.09835, over 966207.93 frames.], batch size: 16, lr: 6.08e-04
2022-05-28 07:11:01,147 INFO [train.py:761] (5/8) Epoch 10, batch 1600, loss[loss=0.3237, simple_loss=0.3987, pruned_loss=0.1244, over 4769.00 frames.], tot_loss[loss=0.2763, simple_loss=0.3562, pruned_loss=0.09821, over 966597.42 frames.], batch size: 20, lr: 6.09e-04
2022-05-28 07:11:38,782 INFO [train.py:761] (5/8) Epoch 10, batch 1650, loss[loss=0.2729, simple_loss=0.3377, pruned_loss=0.104, over 4832.00 frames.], tot_loss[loss=0.2773, simple_loss=0.3574, pruned_loss=0.09857, over 965847.54 frames.], batch size: 11, lr: 6.09e-04
2022-05-28 07:12:17,458 INFO [train.py:761] (5/8) Epoch 10, batch 1700, loss[loss=0.2722, simple_loss=0.3216, pruned_loss=0.1114, over 4638.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3578, pruned_loss=0.09876, over 966053.77 frames.], batch size: 11, lr: 6.10e-04
2022-05-28 07:12:55,493 INFO [train.py:761] (5/8) Epoch 10, batch 1750, loss[loss=0.2547, simple_loss=0.3375, pruned_loss=0.08594, over 4885.00 frames.], tot_loss[loss=0.2761, simple_loss=0.3564, pruned_loss=0.09789, over 966655.53 frames.], batch size: 15, lr: 6.10e-04
2022-05-28 07:13:33,871 INFO [train.py:761] (5/8) Epoch 10, batch 1800, loss[loss=0.3408, simple_loss=0.4432, pruned_loss=0.1192, over 4788.00 frames.], tot_loss[loss=0.2776, simple_loss=0.3576, pruned_loss=0.09883, over 965987.18 frames.], batch size: 15, lr: 6.11e-04
2022-05-28 07:14:12,064 INFO [train.py:761] (5/8) Epoch 10, batch 1850, loss[loss=0.2759, simple_loss=0.3704, pruned_loss=0.09073, over 4714.00 frames.], tot_loss[loss=0.2773, simple_loss=0.3574, pruned_loss=0.09862, over 965396.38 frames.], batch size: 14, lr: 6.11e-04
2022-05-28 07:14:50,256 INFO [train.py:761] (5/8) Epoch 10, batch 1900, loss[loss=0.2984, simple_loss=0.3692, pruned_loss=0.1138, over 4657.00 frames.], tot_loss[loss=0.2744, simple_loss=0.3556, pruned_loss=0.09656, over 965702.02 frames.], batch size: 12, lr: 6.11e-04
2022-05-28 07:15:27,957 INFO [train.py:761] (5/8) Epoch 10, batch 1950, loss[loss=0.2497, simple_loss=0.337, pruned_loss=0.08123, over 4994.00 frames.], tot_loss[loss=0.2738, simple_loss=0.3553, pruned_loss=0.09613, over 964977.73 frames.], batch size: 13, lr: 6.12e-04
2022-05-28 07:16:05,871 INFO [train.py:761] (5/8) Epoch 10, batch 2000, loss[loss=0.2685, simple_loss=0.3607, pruned_loss=0.08819, over 4946.00 frames.], tot_loss[loss=0.2737, simple_loss=0.3551, pruned_loss=0.09616, over 966070.34 frames.], batch size: 26, lr: 6.12e-04
2022-05-28 07:16:43,825 INFO [train.py:761] (5/8) Epoch 10, batch 2050, loss[loss=0.2605, simple_loss=0.3313, pruned_loss=0.09487, over 4717.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3561, pruned_loss=0.0963, over 966458.19 frames.], batch size: 12, lr: 6.13e-04
2022-05-28 07:17:21,333 INFO [train.py:761] (5/8) Epoch 10, batch 2100, loss[loss=0.2274, simple_loss=0.3113, pruned_loss=0.07178, over 4986.00 frames.], tot_loss[loss=0.2752, simple_loss=0.3564, pruned_loss=0.09699, over 966616.13 frames.], batch size: 13, lr: 6.13e-04
2022-05-28 07:17:58,962 INFO [train.py:761] (5/8) Epoch 10, batch 2150, loss[loss=0.1947, simple_loss=0.2649, pruned_loss=0.06226, over 4895.00 frames.], tot_loss[loss=0.2724, simple_loss=0.3539, pruned_loss=0.09543, over 966788.30 frames.], batch size: 12, lr: 6.14e-04
2022-05-28 07:18:37,357 INFO [train.py:761] (5/8) Epoch 10, batch 2200, loss[loss=0.3052, simple_loss=0.3718, pruned_loss=0.1193, over 4966.00 frames.], tot_loss[loss=0.2729, simple_loss=0.3548, pruned_loss=0.09552, over 966691.76 frames.], batch size: 12, lr: 6.14e-04
2022-05-28 07:19:15,013 INFO [train.py:761] (5/8) Epoch 10, batch 2250, loss[loss=0.2507, simple_loss=0.3275, pruned_loss=0.08691, over 4819.00 frames.], tot_loss[loss=0.2723, simple_loss=0.3543, pruned_loss=0.09511, over 965834.14 frames.], batch size: 11, lr: 6.15e-04
2022-05-28 07:19:52,907 INFO [train.py:761] (5/8) Epoch 10, batch 2300, loss[loss=0.3073, simple_loss=0.3779, pruned_loss=0.1183, over 4822.00 frames.], tot_loss[loss=0.2722, simple_loss=0.354, pruned_loss=0.09514, over 964854.32 frames.], batch size: 16, lr: 6.15e-04
2022-05-28 07:20:30,971 INFO [train.py:761] (5/8) Epoch 10, batch 2350, loss[loss=0.288, simple_loss=0.3621, pruned_loss=0.107, over 4893.00 frames.], tot_loss[loss=0.2732, simple_loss=0.355, pruned_loss=0.09569, over 965702.39 frames.], batch size: 25, lr: 6.16e-04
2022-05-28 07:21:09,320 INFO [train.py:761] (5/8) Epoch 10, batch 2400, loss[loss=0.2536, simple_loss=0.3262, pruned_loss=0.09047, over 4857.00 frames.], tot_loss[loss=0.2726, simple_loss=0.3546, pruned_loss=0.09527, over 965403.96 frames.], batch size: 13, lr: 6.16e-04
2022-05-28 07:21:47,592 INFO [train.py:761] (5/8) Epoch 10, batch 2450, loss[loss=0.3082, simple_loss=0.3851, pruned_loss=0.1157, over 4947.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3555, pruned_loss=0.09577, over 965750.19 frames.], batch size: 44, lr: 6.17e-04
2022-05-28 07:22:25,773 INFO [train.py:761] (5/8) Epoch 10, batch 2500, loss[loss=0.3031, simple_loss=0.3863, pruned_loss=0.11, over 4719.00 frames.], tot_loss[loss=0.2784, simple_loss=0.3585, pruned_loss=0.09918, over 966697.44 frames.], batch size: 14, lr: 6.17e-04
2022-05-28 07:23:03,999 INFO [train.py:761] (5/8) Epoch 10, batch 2550, loss[loss=0.2707, simple_loss=0.3439, pruned_loss=0.09876, over 4734.00 frames.], tot_loss[loss=0.2774, simple_loss=0.3579, pruned_loss=0.09849, over 967165.32 frames.], batch size: 12, lr: 6.18e-04
2022-05-28 07:23:42,106 INFO [train.py:761] (5/8) Epoch 10, batch 2600, loss[loss=0.2993, simple_loss=0.3714, pruned_loss=0.1136, over 4967.00 frames.], tot_loss[loss=0.2758, simple_loss=0.3564, pruned_loss=0.09765, over 967946.40 frames.], batch size: 16, lr: 6.18e-04
2022-05-28 07:24:19,882 INFO [train.py:761] (5/8) Epoch 10, batch 2650, loss[loss=0.335, simple_loss=0.4074, pruned_loss=0.1313, over 4974.00 frames.], tot_loss[loss=0.2742, simple_loss=0.3546, pruned_loss=0.09689, over 968605.05 frames.], batch size: 15, lr: 6.19e-04
2022-05-28 07:24:58,122 INFO [train.py:761] (5/8) Epoch 10, batch 2700, loss[loss=0.3391, simple_loss=0.4235, pruned_loss=0.1273, over 4855.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3558, pruned_loss=0.0977, over 968590.84 frames.], batch size: 14, lr: 6.19e-04
2022-05-28 07:25:35,597 INFO [train.py:761] (5/8) Epoch 10, batch 2750, loss[loss=0.2366, simple_loss=0.3182, pruned_loss=0.07752, over 4855.00 frames.], tot_loss[loss=0.2738, simple_loss=0.3545, pruned_loss=0.09653, over 968219.93 frames.], batch size: 13, lr: 6.20e-04
2022-05-28 07:26:13,832 INFO [train.py:761] (5/8) Epoch 10, batch 2800, loss[loss=0.2657, simple_loss=0.3535, pruned_loss=0.08896, over 4741.00 frames.], tot_loss[loss=0.2738, simple_loss=0.3548, pruned_loss=0.09636, over 968643.26 frames.], batch size: 12, lr: 6.20e-04
2022-05-28 07:26:51,235 INFO [train.py:761] (5/8) Epoch 10, batch 2850, loss[loss=0.2244, simple_loss=0.2963, pruned_loss=0.07624, over 4995.00 frames.], tot_loss[loss=0.2722, simple_loss=0.3534, pruned_loss=0.09547, over 968305.74 frames.], batch size: 11, lr: 6.21e-04
2022-05-28 07:27:28,827 INFO [train.py:761] (5/8) Epoch 10, batch 2900, loss[loss=0.2785, simple_loss=0.3611, pruned_loss=0.098, over 4847.00 frames.], tot_loss[loss=0.2696, simple_loss=0.3515, pruned_loss=0.09385, over 969074.29 frames.], batch size: 25, lr: 6.21e-04
2022-05-28 07:28:06,375 INFO [train.py:761] (5/8) Epoch 10, batch 2950, loss[loss=0.216, simple_loss=0.2869, pruned_loss=0.07259, over 4822.00 frames.], tot_loss[loss=0.2703, simple_loss=0.3521, pruned_loss=0.09425, over 967580.76 frames.], batch size: 11, lr: 6.22e-04
2022-05-28 07:28:44,646 INFO [train.py:761] (5/8) Epoch 10, batch 3000, loss[loss=0.2916, simple_loss=0.3778, pruned_loss=0.1027, over 4877.00 frames.], tot_loss[loss=0.2713, simple_loss=0.3532, pruned_loss=0.09465, over 966951.38 frames.], batch size: 17, lr: 6.22e-04
2022-05-28 07:28:44,647 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 07:28:54,709 INFO [train.py:790] (5/8) Epoch 10, validation: loss=0.239, simple_loss=0.3414, pruned_loss=0.06836, over 944034.00 frames.
2022-05-28 07:29:32,556 INFO [train.py:761] (5/8) Epoch 10, batch 3050, loss[loss=0.3233, simple_loss=0.3989, pruned_loss=0.1239, over 4802.00 frames.], tot_loss[loss=0.2733, simple_loss=0.3547, pruned_loss=0.09597, over 966302.97 frames.], batch size: 25, lr: 6.23e-04
2022-05-28 07:30:10,720 INFO [train.py:761] (5/8) Epoch 10, batch 3100, loss[loss=0.3263, simple_loss=0.4043, pruned_loss=0.1242, over 4819.00 frames.], tot_loss[loss=0.2765, simple_loss=0.3568, pruned_loss=0.09812, over 966728.17 frames.], batch size: 16, lr: 6.23e-04
2022-05-28 07:30:48,150 INFO [train.py:761] (5/8) Epoch 10, batch 3150, loss[loss=0.271, simple_loss=0.3689, pruned_loss=0.08657, over 4718.00 frames.], tot_loss[loss=0.2817, simple_loss=0.3601, pruned_loss=0.1017, over 966190.31 frames.], batch size: 14, lr: 6.24e-04
2022-05-28 07:31:26,517 INFO [train.py:761] (5/8) Epoch 10, batch 3200, loss[loss=0.2371, simple_loss=0.33, pruned_loss=0.07215, over 4726.00 frames.], tot_loss[loss=0.2839, simple_loss=0.3611, pruned_loss=0.1034, over 966048.93 frames.], batch size: 13, lr: 6.24e-04
2022-05-28 07:32:04,973 INFO [train.py:761] (5/8) Epoch 10, batch 3250, loss[loss=0.2742, simple_loss=0.3386, pruned_loss=0.1049, over 4883.00 frames.], tot_loss[loss=0.2891, simple_loss=0.3638, pruned_loss=0.1072, over 965563.47 frames.], batch size: 12, lr: 6.25e-04
2022-05-28 07:32:46,024 INFO [train.py:761] (5/8) Epoch 10, batch 3300, loss[loss=0.2432, simple_loss=0.3135, pruned_loss=0.08639, over 4728.00 frames.], tot_loss[loss=0.2931, simple_loss=0.3654, pruned_loss=0.1104, over 965151.19 frames.], batch size: 11, lr: 6.25e-04
2022-05-28 07:33:23,898 INFO [train.py:761] (5/8) Epoch 10, batch 3350, loss[loss=0.3379, simple_loss=0.3994, pruned_loss=0.1382, over 4788.00 frames.], tot_loss[loss=0.2955, simple_loss=0.3656, pruned_loss=0.1127, over 964729.94 frames.], batch size: 14, lr: 6.26e-04
2022-05-28 07:34:02,099 INFO [train.py:761] (5/8) Epoch 10, batch 3400, loss[loss=0.3274, simple_loss=0.3913, pruned_loss=0.1318, over 4838.00 frames.], tot_loss[loss=0.2984, simple_loss=0.3673, pruned_loss=0.1148, over 965375.48 frames.], batch size: 18, lr: 6.26e-04
2022-05-28 07:34:39,651 INFO [train.py:761] (5/8) Epoch 10, batch 3450, loss[loss=0.3424, simple_loss=0.383, pruned_loss=0.1508, over 4791.00 frames.], tot_loss[loss=0.2993, simple_loss=0.3677, pruned_loss=0.1154, over 964142.52 frames.], batch size: 12, lr: 6.27e-04
2022-05-28 07:35:18,339 INFO [train.py:761] (5/8) Epoch 10, batch 3500, loss[loss=0.3582, simple_loss=0.4076, pruned_loss=0.1544, over 4943.00 frames.], tot_loss[loss=0.3019, simple_loss=0.3689, pruned_loss=0.1175, over 965113.09 frames.], batch size: 51, lr: 6.27e-04
2022-05-28 07:35:55,885 INFO [train.py:761] (5/8) Epoch 10, batch 3550, loss[loss=0.3558, simple_loss=0.4024, pruned_loss=0.1546, over 4969.00 frames.], tot_loss[loss=0.3059, simple_loss=0.3714, pruned_loss=0.1202, over 965784.45 frames.], batch size: 16, lr: 6.28e-04
2022-05-28 07:36:34,277 INFO [train.py:761] (5/8) Epoch 10, batch 3600, loss[loss=0.3679, simple_loss=0.4102, pruned_loss=0.1628, over 4972.00 frames.], tot_loss[loss=0.3093, simple_loss=0.3735, pruned_loss=0.1226, over 967213.52 frames.], batch size: 15, lr: 6.28e-04
2022-05-28 07:37:12,058 INFO [train.py:761] (5/8) Epoch 10, batch 3650, loss[loss=0.357, simple_loss=0.4186, pruned_loss=0.1477, over 4937.00 frames.], tot_loss[loss=0.3116, simple_loss=0.375, pruned_loss=0.1241, over 967276.66 frames.], batch size: 21, lr: 6.29e-04
2022-05-28 07:37:50,056 INFO [train.py:761] (5/8) Epoch 10, batch 3700, loss[loss=0.3113, simple_loss=0.3872, pruned_loss=0.1177, over 4719.00 frames.], tot_loss[loss=0.3104, simple_loss=0.3742, pruned_loss=0.1233, over 965998.39 frames.], batch size: 14, lr: 6.29e-04
2022-05-28 07:38:27,952 INFO [train.py:761] (5/8) Epoch 10, batch 3750, loss[loss=0.2596, simple_loss=0.3282, pruned_loss=0.09551, over 4803.00 frames.], tot_loss[loss=0.3113, simple_loss=0.3746, pruned_loss=0.124, over 965763.61 frames.], batch size: 12, lr: 6.30e-04
2022-05-28 07:39:06,109 INFO [train.py:761] (5/8) Epoch 10, batch 3800, loss[loss=0.2816, simple_loss=0.3408, pruned_loss=0.1112, over 4912.00 frames.], tot_loss[loss=0.3098, simple_loss=0.3734, pruned_loss=0.1231, over 966636.54 frames.], batch size: 14, lr: 6.30e-04
2022-05-28 07:39:43,850 INFO [train.py:761] (5/8) Epoch 10, batch 3850, loss[loss=0.2312, simple_loss=0.3113, pruned_loss=0.07552, over 4650.00 frames.], tot_loss[loss=0.3082, simple_loss=0.3722, pruned_loss=0.1221, over 966244.11 frames.], batch size: 11, lr: 6.31e-04
2022-05-28 07:40:22,135 INFO [train.py:761] (5/8) Epoch 10, batch 3900, loss[loss=0.3132, simple_loss=0.3746, pruned_loss=0.126, over 4799.00 frames.], tot_loss[loss=0.3074, simple_loss=0.3712, pruned_loss=0.1218, over 966712.00 frames.], batch size: 16, lr: 6.31e-04
2022-05-28 07:41:00,274 INFO [train.py:761] (5/8) Epoch 10, batch 3950, loss[loss=0.2748, simple_loss=0.3336, pruned_loss=0.108, over 4843.00 frames.], tot_loss[loss=0.3088, simple_loss=0.372, pruned_loss=0.1228, over 966282.70 frames.], batch size: 11, lr: 6.32e-04
2022-05-28 07:41:38,169 INFO [train.py:761] (5/8) Epoch 10, batch 4000, loss[loss=0.3013, simple_loss=0.3634, pruned_loss=0.1196, over 4925.00 frames.], tot_loss[loss=0.3117, simple_loss=0.3733, pruned_loss=0.125, over 965731.82 frames.], batch size: 13, lr: 6.32e-04
2022-05-28 07:42:16,243 INFO [train.py:761] (5/8) Epoch 10, batch 4050, loss[loss=0.2783, simple_loss=0.35, pruned_loss=0.1033, over 4726.00 frames.], tot_loss[loss=0.3106, simple_loss=0.3724, pruned_loss=0.1244, over 965809.08 frames.], batch size: 12, lr: 6.32e-04
2022-05-28 07:42:54,365 INFO [train.py:761] (5/8) Epoch 10, batch 4100, loss[loss=0.3207, simple_loss=0.3881, pruned_loss=0.1266, over 4794.00 frames.], tot_loss[loss=0.3071, simple_loss=0.37, pruned_loss=0.1221, over 965792.36 frames.], batch size: 16, lr: 6.33e-04
2022-05-28 07:43:32,567 INFO [train.py:761] (5/8) Epoch 10, batch 4150, loss[loss=0.2883, simple_loss=0.3513, pruned_loss=0.1126, over 4782.00 frames.], tot_loss[loss=0.3071, simple_loss=0.37, pruned_loss=0.1221, over 966992.85 frames.], batch size: 13, lr: 6.33e-04
2022-05-28 07:44:10,946 INFO [train.py:761] (5/8) Epoch 10, batch 4200, loss[loss=0.3029, simple_loss=0.3727, pruned_loss=0.1165, over 4980.00 frames.], tot_loss[loss=0.3084, simple_loss=0.3715, pruned_loss=0.1227, over 967556.25 frames.], batch size: 26, lr: 6.34e-04
2022-05-28 07:44:48,629 INFO [train.py:761] (5/8) Epoch 10, batch 4250, loss[loss=0.2349, simple_loss=0.3057, pruned_loss=0.082, over 4847.00 frames.], tot_loss[loss=0.3079, simple_loss=0.3704, pruned_loss=0.1227, over 966412.35 frames.], batch size: 11, lr: 6.34e-04
2022-05-28 07:45:27,164 INFO [train.py:761] (5/8) Epoch 10, batch 4300, loss[loss=0.3559, simple_loss=0.4257, pruned_loss=0.143, over 4726.00 frames.], tot_loss[loss=0.3078, simple_loss=0.3707, pruned_loss=0.1224, over 966843.80 frames.], batch size: 13, lr: 6.35e-04
2022-05-28 07:46:05,325 INFO [train.py:761] (5/8) Epoch 10, batch 4350, loss[loss=0.3323, simple_loss=0.4011, pruned_loss=0.1317, over 4720.00 frames.], tot_loss[loss=0.3079, simple_loss=0.371, pruned_loss=0.1224, over 965831.87 frames.], batch size: 14, lr: 6.35e-04
2022-05-28 07:46:43,891 INFO [train.py:761] (5/8) Epoch 10, batch 4400, loss[loss=0.2314, simple_loss=0.2894, pruned_loss=0.08671, over 4739.00 frames.], tot_loss[loss=0.3055, simple_loss=0.3693, pruned_loss=0.1209, over 965336.64 frames.], batch size: 11, lr: 6.36e-04
2022-05-28 07:47:22,993 INFO [train.py:761] (5/8) Epoch 10, batch 4450, loss[loss=0.3136, simple_loss=0.3867, pruned_loss=0.1202, over 4797.00 frames.], tot_loss[loss=0.3065, simple_loss=0.3699, pruned_loss=0.1215, over 965342.00 frames.], batch size: 13, lr: 6.36e-04
2022-05-28 07:48:01,613 INFO [train.py:761] (5/8) Epoch 10, batch 4500, loss[loss=0.2728, simple_loss=0.3302, pruned_loss=0.1077, over 4979.00 frames.], tot_loss[loss=0.3053, simple_loss=0.3687, pruned_loss=0.1209, over 964814.09 frames.], batch size: 15, lr: 6.37e-04
2022-05-28 07:48:39,978 INFO [train.py:761] (5/8) Epoch 10, batch 4550, loss[loss=0.3318, simple_loss=0.382, pruned_loss=0.1408, over 4758.00 frames.], tot_loss[loss=0.3047, simple_loss=0.3684, pruned_loss=0.1205, over 965601.09 frames.], batch size: 15, lr: 6.37e-04
2022-05-28 07:49:18,400 INFO [train.py:761] (5/8) Epoch 10, batch 4600, loss[loss=0.3304, simple_loss=0.379, pruned_loss=0.1409, over 4919.00 frames.], tot_loss[loss=0.3023, simple_loss=0.3664, pruned_loss=0.1191, over 964941.70 frames.], batch size: 13, lr: 6.38e-04
2022-05-28 07:49:56,095 INFO [train.py:761] (5/8) Epoch 10, batch 4650, loss[loss=0.2876, simple_loss=0.3493, pruned_loss=0.1129, over 4834.00 frames.], tot_loss[loss=0.3022, simple_loss=0.3663, pruned_loss=0.1191, over 964533.24 frames.], batch size: 18, lr: 6.38e-04
2022-05-28 07:50:34,495 INFO [train.py:761] (5/8) Epoch 10, batch 4700, loss[loss=0.3405, simple_loss=0.4085, pruned_loss=0.1362, over 4846.00 frames.], tot_loss[loss=0.3038, simple_loss=0.3672, pruned_loss=0.1202, over 964774.17 frames.], batch size: 17, lr: 6.39e-04
2022-05-28 07:51:12,274 INFO [train.py:761] (5/8) Epoch 10, batch 4750, loss[loss=0.2794, simple_loss=0.3459, pruned_loss=0.1064, over 4853.00 frames.], tot_loss[loss=0.3031, simple_loss=0.3664, pruned_loss=0.1198, over 964833.63 frames.], batch size: 13, lr: 6.39e-04
2022-05-28 07:51:50,877 INFO [train.py:761] (5/8) Epoch 10, batch 4800, loss[loss=0.29, simple_loss=0.3629, pruned_loss=0.1085, over 4842.00 frames.], tot_loss[loss=0.3048, simple_loss=0.3681, pruned_loss=0.1207, over 966212.82 frames.], batch size: 13, lr: 6.40e-04
2022-05-28 07:52:28,721 INFO [train.py:761] (5/8) Epoch 10, batch 4850, loss[loss=0.3484, simple_loss=0.3953, pruned_loss=0.1507, over 4783.00 frames.], tot_loss[loss=0.305, simple_loss=0.3685, pruned_loss=0.1208, over 966727.45 frames.], batch size: 14, lr: 6.40e-04
2022-05-28 07:53:06,862 INFO [train.py:761] (5/8) Epoch 10, batch 4900, loss[loss=0.2873, simple_loss=0.3553, pruned_loss=0.1097, over 4852.00 frames.], tot_loss[loss=0.3035, simple_loss=0.3673, pruned_loss=0.1199, over 966292.95 frames.], batch size: 13, lr: 6.41e-04
2022-05-28 07:53:45,252 INFO [train.py:761] (5/8) Epoch 10, batch 4950, loss[loss=0.3565, simple_loss=0.3954, pruned_loss=0.1588, over 4949.00 frames.], tot_loss[loss=0.3039, simple_loss=0.3675, pruned_loss=0.1202, over 966555.01 frames.], batch size: 16, lr: 6.41e-04
2022-05-28 07:54:23,467 INFO [train.py:761] (5/8) Epoch 10, batch 5000, loss[loss=0.347, simple_loss=0.4098, pruned_loss=0.1421, over 4838.00 frames.], tot_loss[loss=0.3028, simple_loss=0.3667, pruned_loss=0.1194, over 965580.81 frames.], batch size: 18, lr: 6.42e-04
2022-05-28 07:55:01,621 INFO [train.py:761] (5/8) Epoch 10, batch 5050, loss[loss=0.2611, simple_loss=0.3278, pruned_loss=0.09721, over 4849.00 frames.], tot_loss[loss=0.3041, simple_loss=0.3678, pruned_loss=0.1202, over 965655.67 frames.], batch size: 13, lr: 6.42e-04
2022-05-28 07:55:40,241 INFO [train.py:761] (5/8) Epoch 10, batch 5100, loss[loss=0.3183, simple_loss=0.3764, pruned_loss=0.1301, over 4879.00 frames.], tot_loss[loss=0.3069, simple_loss=0.3701, pruned_loss=0.1219, over 966378.40 frames.], batch size: 25, lr: 6.43e-04
2022-05-28 07:56:18,220 INFO [train.py:761] (5/8) Epoch 10, batch 5150, loss[loss=0.3341, simple_loss=0.3997, pruned_loss=0.1343, over 4861.00 frames.], tot_loss[loss=0.3047, simple_loss=0.3679, pruned_loss=0.1207, over 966726.41 frames.], batch size: 25, lr: 6.43e-04
2022-05-28 07:56:56,212 INFO [train.py:761] (5/8) Epoch 10, batch 5200, loss[loss=0.2968, simple_loss=0.391, pruned_loss=0.1013, over 4789.00 frames.], tot_loss[loss=0.3025, simple_loss=0.3669, pruned_loss=0.119, over 966801.53 frames.], batch size: 14, lr: 6.44e-04
2022-05-28 07:57:34,185 INFO [train.py:761] (5/8) Epoch 10, batch 5250, loss[loss=0.325, simple_loss=0.3933, pruned_loss=0.1283, over 4868.00 frames.], tot_loss[loss=0.3028, simple_loss=0.3681, pruned_loss=0.1187, over 966301.39 frames.], batch size: 48, lr: 6.44e-04
2022-05-28 07:58:12,262 INFO [train.py:761] (5/8) Epoch 10, batch 5300, loss[loss=0.2954, simple_loss=0.3703, pruned_loss=0.1103, over 4786.00 frames.], tot_loss[loss=0.3013, simple_loss=0.3671, pruned_loss=0.1178, over 965605.17 frames.], batch size: 13, lr: 6.45e-04
2022-05-28 07:58:50,929 INFO [train.py:761] (5/8) Epoch 10, batch 5350, loss[loss=0.2822, simple_loss=0.359, pruned_loss=0.1027, over 4789.00 frames.], tot_loss[loss=0.3008, simple_loss=0.3667, pruned_loss=0.1174, over 965946.53 frames.], batch size: 14, lr: 6.45e-04
2022-05-28 07:59:29,418 INFO [train.py:761] (5/8) Epoch 10, batch 5400, loss[loss=0.3184, simple_loss=0.3875, pruned_loss=0.1247, over 4877.00 frames.], tot_loss[loss=0.3019, simple_loss=0.3678, pruned_loss=0.118, over 965928.54 frames.], batch size: 18, lr: 6.46e-04
2022-05-28 08:00:07,926 INFO [train.py:761] (5/8) Epoch 10, batch 5450, loss[loss=0.3101, simple_loss=0.3819, pruned_loss=0.1192, over 4855.00 frames.], tot_loss[loss=0.3024, simple_loss=0.3682, pruned_loss=0.1184, over 965625.83 frames.], batch size: 13, lr: 6.46e-04
2022-05-28 08:00:46,498 INFO [train.py:761] (5/8) Epoch 10, batch 5500, loss[loss=0.2988, simple_loss=0.3863, pruned_loss=0.1057, over 4668.00 frames.], tot_loss[loss=0.3006, simple_loss=0.3671, pruned_loss=0.1171, over 965279.41 frames.], batch size: 13, lr: 6.47e-04
2022-05-28 08:01:24,474 INFO [train.py:761] (5/8) Epoch 10, batch 5550, loss[loss=0.2613, simple_loss=0.3327, pruned_loss=0.09499, over 4907.00 frames.], tot_loss[loss=0.2999, simple_loss=0.366, pruned_loss=0.117, over 966148.05 frames.], batch size: 14, lr: 6.47e-04
2022-05-28 08:02:03,052 INFO [train.py:761] (5/8) Epoch 10, batch 5600, loss[loss=0.3349, simple_loss=0.4017, pruned_loss=0.134, over 4853.00 frames.], tot_loss[loss=0.3, simple_loss=0.3662, pruned_loss=0.1169, over 966904.62 frames.], batch size: 18, lr: 6.48e-04
2022-05-28 08:02:40,383 INFO [train.py:761] (5/8) Epoch 10, batch 5650, loss[loss=0.304, simple_loss=0.3445, pruned_loss=0.1317, over 4656.00 frames.], tot_loss[loss=0.2999, simple_loss=0.3656, pruned_loss=0.1171, over 966481.88 frames.], batch size: 11, lr: 6.48e-04
2022-05-28 08:03:18,770 INFO [train.py:761] (5/8) Epoch 10, batch 5700, loss[loss=0.2414, simple_loss=0.3092, pruned_loss=0.08676, over 4978.00 frames.], tot_loss[loss=0.301, simple_loss=0.3666, pruned_loss=0.1177, over 965871.89 frames.], batch size: 12, lr: 6.49e-04
2022-05-28 08:03:57,009 INFO [train.py:761] (5/8) Epoch 10, batch 5750, loss[loss=0.315, simple_loss=0.3639, pruned_loss=0.133, over 4796.00 frames.], tot_loss[loss=0.3027, simple_loss=0.3672, pruned_loss=0.119, over 966222.66 frames.], batch size: 16, lr: 6.49e-04
2022-05-28 08:04:35,593 INFO [train.py:761] (5/8) Epoch 10, batch 5800, loss[loss=0.3383, simple_loss=0.4039, pruned_loss=0.1363, over 4856.00 frames.], tot_loss[loss=0.3012, simple_loss=0.366, pruned_loss=0.1182, over 965696.51 frames.], batch size: 14, lr: 6.50e-04
2022-05-28 08:05:13,790 INFO [train.py:761] (5/8) Epoch 10, batch 5850, loss[loss=0.2959, simple_loss=0.3352, pruned_loss=0.1283, over 4992.00 frames.], tot_loss[loss=0.3027, simple_loss=0.367, pruned_loss=0.1192, over 966285.27 frames.], batch size: 13, lr: 6.50e-04
2022-05-28 08:05:52,954 INFO [train.py:761] (5/8) Epoch 10, batch 5900, loss[loss=0.2744, simple_loss=0.3544, pruned_loss=0.09715, over 4846.00 frames.], tot_loss[loss=0.3025, simple_loss=0.3674, pruned_loss=0.1188, over 966839.57 frames.], batch size: 14, lr: 6.51e-04
2022-05-28 08:06:31,741 INFO [train.py:761] (5/8) Epoch 10, batch 5950, loss[loss=0.3274, simple_loss=0.3935, pruned_loss=0.1306, over 4940.00 frames.], tot_loss[loss=0.3048, simple_loss=0.3692, pruned_loss=0.1202, over 966322.43 frames.], batch size: 16, lr: 6.51e-04
2022-05-28 08:07:10,239 INFO [train.py:761] (5/8) Epoch 10, batch 6000, loss[loss=0.2628, simple_loss=0.3315, pruned_loss=0.09704, over 4928.00 frames.], tot_loss[loss=0.3034, simple_loss=0.368, pruned_loss=0.1194, over 965655.93 frames.], batch size: 13, lr: 6.52e-04
2022-05-28 08:07:10,239 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 08:07:20,129 INFO [train.py:790] (5/8) Epoch 10, validation: loss=0.231, simple_loss=0.3365, pruned_loss=0.06277, over 944034.00 frames.
2022-05-28 08:07:57,855 INFO [train.py:761] (5/8) Epoch 10, batch 6050, loss[loss=0.2987, simple_loss=0.3512, pruned_loss=0.1231, over 4595.00 frames.], tot_loss[loss=0.3047, simple_loss=0.369, pruned_loss=0.1202, over 965495.35 frames.], batch size: 10, lr: 6.52e-04
2022-05-28 08:08:36,155 INFO [train.py:761] (5/8) Epoch 10, batch 6100, loss[loss=0.3714, simple_loss=0.436, pruned_loss=0.1534, over 4945.00 frames.], tot_loss[loss=0.3047, simple_loss=0.3691, pruned_loss=0.1202, over 964804.61 frames.], batch size: 45, lr: 6.53e-04
2022-05-28 08:09:14,820 INFO [train.py:761] (5/8) Epoch 10, batch 6150, loss[loss=0.2704, simple_loss=0.3455, pruned_loss=0.09766, over 4782.00 frames.], tot_loss[loss=0.3064, simple_loss=0.3706, pruned_loss=0.1211, over 965036.46 frames.], batch size: 13, lr: 6.53e-04
2022-05-28 08:09:53,572 INFO [train.py:761] (5/8) Epoch 10, batch 6200, loss[loss=0.2446, simple_loss=0.3199, pruned_loss=0.08464, over 4546.00 frames.], tot_loss[loss=0.3058, simple_loss=0.3697, pruned_loss=0.121, over 964498.56 frames.], batch size: 10, lr: 6.53e-04
2022-05-28 08:10:31,725 INFO [train.py:761] (5/8) Epoch 10, batch 6250, loss[loss=0.306, simple_loss=0.374, pruned_loss=0.119, over 4862.00 frames.], tot_loss[loss=0.3044, simple_loss=0.3683, pruned_loss=0.1202, over 964883.99 frames.], batch size: 13, lr: 6.54e-04
2022-05-28 08:11:09,703 INFO [train.py:761] (5/8) Epoch 10, batch 6300, loss[loss=0.3257, simple_loss=0.3798, pruned_loss=0.1358, over 4787.00 frames.], tot_loss[loss=0.3023, simple_loss=0.3668, pruned_loss=0.1189, over 965205.25 frames.], batch size: 16, lr: 6.54e-04
2022-05-28 08:11:48,372 INFO [train.py:761] (5/8) Epoch 10, batch 6350, loss[loss=0.3451, simple_loss=0.4012, pruned_loss=0.1445, over 4715.00 frames.], tot_loss[loss=0.302, simple_loss=0.3668, pruned_loss=0.1186, over 965545.81 frames.], batch size: 14, lr: 6.55e-04
2022-05-28 08:12:26,395 INFO [train.py:761] (5/8) Epoch 10, batch 6400, loss[loss=0.2827, simple_loss=0.3506, pruned_loss=0.1074, over 4848.00 frames.], tot_loss[loss=0.3043, simple_loss=0.3691, pruned_loss=0.1197, over 965533.84 frames.], batch size: 18, lr: 6.55e-04
2022-05-28 08:13:04,475 INFO [train.py:761] (5/8) Epoch 10, batch 6450, loss[loss=0.3464, simple_loss=0.3986, pruned_loss=0.1471, over 4810.00 frames.], tot_loss[loss=0.3052, simple_loss=0.3693, pruned_loss=0.1206, over 965322.89 frames.], batch size: 16, lr: 6.56e-04
2022-05-28 08:13:42,555 INFO [train.py:761] (5/8) Epoch 10, batch 6500, loss[loss=0.2822, simple_loss=0.3415, pruned_loss=0.1115, over 4749.00 frames.], tot_loss[loss=0.3042, simple_loss=0.3686, pruned_loss=0.1199, over 966326.06 frames.], batch size: 11, lr: 6.56e-04
2022-05-28 08:14:20,672 INFO [train.py:761] (5/8) Epoch 10, batch 6550, loss[loss=0.298, simple_loss=0.3616, pruned_loss=0.1171, over 4782.00 frames.], tot_loss[loss=0.3014, simple_loss=0.3664, pruned_loss=0.1182, over 965146.34 frames.], batch size: 13, lr: 6.57e-04
2022-05-28 08:14:59,198 INFO [train.py:761] (5/8) Epoch 10, batch 6600, loss[loss=0.2446, simple_loss=0.3125, pruned_loss=0.08835, over 4789.00 frames.], tot_loss[loss=0.3013, simple_loss=0.3663, pruned_loss=0.1181, over 964297.10 frames.], batch size: 12, lr: 6.57e-04
2022-05-28 08:15:37,595 INFO [train.py:761] (5/8) Epoch 10, batch 6650, loss[loss=0.3127, simple_loss=0.3871, pruned_loss=0.1192, over 4733.00 frames.], tot_loss[loss=0.3004, simple_loss=0.3661, pruned_loss=0.1174, over 964622.38 frames.], batch size: 13, lr: 6.58e-04
2022-05-28 08:16:16,672 INFO [train.py:761] (5/8) Epoch 10, batch 6700, loss[loss=0.3342, simple_loss=0.388, pruned_loss=0.1402, over 4864.00 frames.], tot_loss[loss=0.3013, simple_loss=0.3668, pruned_loss=0.1179, over 964808.05 frames.], batch size: 13, lr: 6.58e-04
2022-05-28 08:17:12,613 INFO [train.py:761] (5/8) Epoch 11, batch 0, loss[loss=0.3232, simple_loss=0.3929, pruned_loss=0.1267, over 4936.00 frames.], tot_loss[loss=0.3232, simple_loss=0.3929, pruned_loss=0.1267, over 4936.00 frames.], batch size: 45, lr: 6.59e-04
2022-05-28 08:17:50,244 INFO [train.py:761] (5/8) Epoch 11, batch 50, loss[loss=0.2493, simple_loss=0.3451, pruned_loss=0.07674, over 4851.00 frames.], tot_loss[loss=0.274, simple_loss=0.3522, pruned_loss=0.09791, over 218287.18 frames.], batch size: 13, lr: 6.59e-04
2022-05-28 08:18:28,003 INFO [train.py:761] (5/8) Epoch 11, batch 100, loss[loss=0.3055, simple_loss=0.3764, pruned_loss=0.1173, over 4722.00 frames.], tot_loss[loss=0.2732, simple_loss=0.3519, pruned_loss=0.09728, over 384421.99 frames.], batch size: 14, lr: 6.60e-04
2022-05-28 08:19:06,053 INFO [train.py:761] (5/8) Epoch 11, batch 150, loss[loss=0.2538, simple_loss=0.3205, pruned_loss=0.09352, over 4849.00 frames.], tot_loss[loss=0.2676, simple_loss=0.3479, pruned_loss=0.09366, over 512761.00 frames.], batch size: 11, lr: 6.60e-04
2022-05-28 08:19:44,056 INFO [train.py:761] (5/8) Epoch 11, batch 200, loss[loss=0.2233, simple_loss=0.301, pruned_loss=0.07284, over 4887.00 frames.], tot_loss[loss=0.267, simple_loss=0.3475, pruned_loss=0.09326, over 612888.20 frames.], batch size: 12, lr: 6.61e-04
2022-05-28 08:20:22,235 INFO [train.py:761] (5/8) Epoch 11, batch 250, loss[loss=0.2801, simple_loss=0.3634, pruned_loss=0.09837, over 4851.00 frames.], tot_loss[loss=0.2673, simple_loss=0.3493, pruned_loss=0.09261, over 692006.71 frames.], batch size: 14, lr: 6.61e-04
2022-05-28 08:20:59,880 INFO [train.py:761] (5/8) Epoch 11, batch 300, loss[loss=0.2985, simple_loss=0.3752, pruned_loss=0.1109, over 4936.00 frames.], tot_loss[loss=0.266, simple_loss=0.3482, pruned_loss=0.09191, over 752787.84 frames.], batch size: 16, lr: 6.62e-04
2022-05-28 08:21:37,887 INFO [train.py:761] (5/8) Epoch 11, batch 350, loss[loss=0.2759, simple_loss=0.3512, pruned_loss=0.1003, over 4860.00 frames.], tot_loss[loss=0.2649, simple_loss=0.347, pruned_loss=0.09137, over 800473.09 frames.], batch size: 14, lr: 6.62e-04
2022-05-28 08:22:15,516 INFO [train.py:761] (5/8) Epoch 11, batch 400, loss[loss=0.2306, simple_loss=0.3233, pruned_loss=0.06889, over 4888.00 frames.], tot_loss[loss=0.2616, simple_loss=0.3444, pruned_loss=0.08935, over 837282.40 frames.], batch size: 12, lr: 6.63e-04
2022-05-28 08:22:53,801 INFO [train.py:761] (5/8) Epoch 11, batch 450, loss[loss=0.2024, simple_loss=0.2971, pruned_loss=0.05387, over 4733.00 frames.], tot_loss[loss=0.2606, simple_loss=0.3441, pruned_loss=0.08852, over 865890.73 frames.], batch size: 12, lr: 6.63e-04
2022-05-28 08:23:31,481 INFO [train.py:761] (5/8) Epoch 11, batch 500, loss[loss=0.2793, simple_loss=0.3568, pruned_loss=0.1009, over 4988.00 frames.], tot_loss[loss=0.2613, simple_loss=0.3444, pruned_loss=0.08915, over 888103.79 frames.], batch size: 13, lr: 6.64e-04
2022-05-28 08:24:09,636 INFO [train.py:761] (5/8) Epoch 11, batch 550, loss[loss=0.2963, simple_loss=0.3797, pruned_loss=0.1064, over 4840.00 frames.], tot_loss[loss=0.2608, simple_loss=0.3447, pruned_loss=0.08845, over 906973.22 frames.], batch size: 18, lr: 6.64e-04
2022-05-28 08:24:47,133 INFO [train.py:761] (5/8) Epoch 11, batch 600, loss[loss=0.2393, simple_loss=0.3182, pruned_loss=0.08015, over 4733.00 frames.], tot_loss[loss=0.2598, simple_loss=0.3438, pruned_loss=0.08792, over 920002.73 frames.], batch size: 12, lr: 6.65e-04
2022-05-28 08:25:25,356 INFO [train.py:761] (5/8) Epoch 11, batch 650, loss[loss=0.2363, simple_loss=0.3343, pruned_loss=0.06915, over 4813.00 frames.], tot_loss[loss=0.2598, simple_loss=0.3436, pruned_loss=0.088, over 930962.74 frames.], batch size: 18, lr: 6.65e-04
2022-05-28 08:26:02,677 INFO [train.py:761] (5/8) Epoch 11, batch 700, loss[loss=0.2942, simple_loss=0.3654, pruned_loss=0.1115, over 4783.00 frames.], tot_loss[loss=0.2604, simple_loss=0.3441, pruned_loss=0.08839, over 938680.15 frames.], batch size: 13, lr: 6.66e-04
2022-05-28 08:26:40,509 INFO [train.py:761] (5/8) Epoch 11, batch 750, loss[loss=0.2852, simple_loss=0.3728, pruned_loss=0.09875, over 4851.00 frames.], tot_loss[loss=0.2617, simple_loss=0.3442, pruned_loss=0.08957, over 943841.12 frames.], batch size: 14, lr: 6.66e-04
2022-05-28 08:27:18,467 INFO [train.py:761] (5/8) Epoch 11, batch 800, loss[loss=0.3122, simple_loss=0.3861, pruned_loss=0.1191, over 4673.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3449, pruned_loss=0.09116, over 948010.84 frames.], batch size: 13, lr: 6.67e-04
2022-05-28 08:27:56,673 INFO [train.py:761] (5/8) Epoch 11, batch 850, loss[loss=0.3289, simple_loss=0.4014, pruned_loss=0.1282, over 4953.00 frames.], tot_loss[loss=0.2654, simple_loss=0.347, pruned_loss=0.09187, over 952297.53 frames.], batch size: 16, lr: 6.67e-04
2022-05-28 08:28:34,474 INFO [train.py:761] (5/8) Epoch 11, batch 900, loss[loss=0.2723, simple_loss=0.3378, pruned_loss=0.1034, over 4560.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3485, pruned_loss=0.09309, over 955528.47 frames.], batch size: 10, lr: 6.68e-04
2022-05-28 08:29:12,599 INFO [train.py:761] (5/8) Epoch 11, batch 950, loss[loss=0.3589, simple_loss=0.4267, pruned_loss=0.1456, over 4858.00 frames.], tot_loss[loss=0.2696, simple_loss=0.3499, pruned_loss=0.09471, over 957708.41 frames.], batch size: 18, lr: 6.68e-04
2022-05-28 08:29:50,021 INFO [train.py:761] (5/8) Epoch 11, batch 1000, loss[loss=0.3211, simple_loss=0.4072, pruned_loss=0.1176, over 4856.00 frames.], tot_loss[loss=0.2711, simple_loss=0.3512, pruned_loss=0.09549, over 958831.72 frames.], batch size: 17, lr: 6.69e-04
2022-05-28 08:30:28,020 INFO [train.py:761] (5/8) Epoch 11, batch 1050, loss[loss=0.2686, simple_loss=0.3543, pruned_loss=0.09141, over 4978.00 frames.], tot_loss[loss=0.2719, simple_loss=0.3516, pruned_loss=0.09611, over 961395.15 frames.], batch size: 15, lr: 6.69e-04
2022-05-28 08:31:05,599 INFO [train.py:761] (5/8) Epoch 11, batch 1100, loss[loss=0.3001, simple_loss=0.3918, pruned_loss=0.1042, over 4810.00 frames.], tot_loss[loss=0.2715, simple_loss=0.3519, pruned_loss=0.0955, over 962082.19 frames.], batch size: 25, lr: 6.70e-04
2022-05-28 08:31:43,671 INFO [train.py:761] (5/8) Epoch 11, batch 1150, loss[loss=0.2895, simple_loss=0.374, pruned_loss=0.1025, over 4790.00 frames.], tot_loss[loss=0.2721, simple_loss=0.3528, pruned_loss=0.09575, over 963390.70 frames.], batch size: 13, lr: 6.70e-04
2022-05-28 08:32:21,848 INFO [train.py:761] (5/8) Epoch 11, batch 1200, loss[loss=0.2108, simple_loss=0.3044, pruned_loss=0.05859, over 4982.00 frames.], tot_loss[loss=0.272, simple_loss=0.3528, pruned_loss=0.09564, over 964853.15 frames.], batch size: 12, lr: 6.71e-04
2022-05-28 08:32:59,745 INFO [train.py:761] (5/8) Epoch 11, batch 1250, loss[loss=0.2867, simple_loss=0.3664, pruned_loss=0.1035, over 4822.00 frames.], tot_loss[loss=0.2688, simple_loss=0.3496, pruned_loss=0.09396, over 965222.71 frames.], batch size: 20, lr: 6.71e-04
2022-05-28 08:33:38,008 INFO [train.py:761] (5/8) Epoch 11, batch 1300, loss[loss=0.2423, simple_loss=0.325, pruned_loss=0.07974, over 4669.00 frames.], tot_loss[loss=0.2686, simple_loss=0.3494, pruned_loss=0.09396, over 964692.76 frames.], batch size: 13, lr: 6.72e-04
2022-05-28 08:34:16,058 INFO [train.py:761] (5/8) Epoch 11, batch 1350, loss[loss=0.2082, simple_loss=0.305, pruned_loss=0.05572, over 4883.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3482, pruned_loss=0.09306, over 966893.14 frames.], batch size: 12, lr: 6.72e-04
2022-05-28 08:34:53,714 INFO [train.py:761] (5/8) Epoch 11, batch 1400, loss[loss=0.2489, simple_loss=0.3158, pruned_loss=0.09103, over 4984.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3484, pruned_loss=0.09332, over 965921.41 frames.], batch size: 11, lr: 6.72e-04
2022-05-28 08:35:31,889 INFO [train.py:761] (5/8) Epoch 11, batch 1450, loss[loss=0.2489, simple_loss=0.3451, pruned_loss=0.07633, over 4790.00 frames.], tot_loss[loss=0.2686, simple_loss=0.3495, pruned_loss=0.09386, over 966612.56 frames.], batch size: 14, lr: 6.73e-04
2022-05-28 08:36:09,901 INFO [train.py:761] (5/8) Epoch 11, batch 1500, loss[loss=0.3138, simple_loss=0.3753, pruned_loss=0.1261, over 4768.00 frames.], tot_loss[loss=0.2699, simple_loss=0.3506, pruned_loss=0.09458, over 966739.16 frames.], batch size: 20, lr: 6.73e-04
2022-05-28 08:36:48,157 INFO [train.py:761] (5/8) Epoch 11, batch 1550, loss[loss=0.2477, simple_loss=0.3344, pruned_loss=0.08045, over 4651.00 frames.], tot_loss[loss=0.2703, simple_loss=0.3511, pruned_loss=0.09473, over 965985.91 frames.], batch size: 11, lr: 6.74e-04
2022-05-28 08:37:26,498 INFO [train.py:761] (5/8) Epoch 11, batch 1600, loss[loss=0.2471, simple_loss=0.3285, pruned_loss=0.08279, over 4934.00 frames.], tot_loss[loss=0.2696, simple_loss=0.3514, pruned_loss=0.0939, over 967421.58 frames.], batch size: 25, lr: 6.74e-04
2022-05-28 08:38:04,817 INFO [train.py:761] (5/8) Epoch 11, batch 1650, loss[loss=0.2316, simple_loss=0.3088, pruned_loss=0.07722, over 4858.00 frames.], tot_loss[loss=0.2689, simple_loss=0.351, pruned_loss=0.09338, over 967779.80 frames.], batch size: 11, lr: 6.75e-04
2022-05-28 08:38:42,390 INFO [train.py:761] (5/8) Epoch 11, batch 1700, loss[loss=0.3044, simple_loss=0.3791, pruned_loss=0.1149, over 4989.00 frames.], tot_loss[loss=0.2687, simple_loss=0.3506, pruned_loss=0.0934, over 968715.19 frames.], batch size: 21, lr: 6.75e-04
2022-05-28 08:39:19,566 INFO [train.py:761] (5/8) Epoch 11, batch 1750, loss[loss=0.2445, simple_loss=0.3315, pruned_loss=0.07879, over 4849.00 frames.], tot_loss[loss=0.27, simple_loss=0.3513, pruned_loss=0.09433, over 967957.95 frames.], batch size: 13, lr: 6.76e-04
2022-05-28 08:39:57,193 INFO [train.py:761] (5/8) Epoch 11, batch 1800, loss[loss=0.3224, simple_loss=0.3753, pruned_loss=0.1348, over 4783.00 frames.], tot_loss[loss=0.2697, simple_loss=0.3511, pruned_loss=0.09416, over 968510.39 frames.], batch size: 14, lr: 6.76e-04
2022-05-28 08:40:35,182 INFO [train.py:761] (5/8) Epoch 11, batch 1850, loss[loss=0.2669, simple_loss=0.3561, pruned_loss=0.08888, over 4917.00 frames.], tot_loss[loss=0.2695, simple_loss=0.3509, pruned_loss=0.09404, over 968608.00 frames.], batch size: 14, lr: 6.77e-04
2022-05-28 08:41:13,184 INFO [train.py:761] (5/8) Epoch 11, batch 1900, loss[loss=0.2532, simple_loss=0.3356, pruned_loss=0.08544, over 4788.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3488, pruned_loss=0.09275, over 966544.84 frames.], batch size: 15, lr: 6.77e-04
2022-05-28 08:41:51,264 INFO [train.py:761] (5/8) Epoch 11, batch 1950, loss[loss=0.2657, simple_loss=0.3669, pruned_loss=0.08221, over 4908.00 frames.], tot_loss[loss=0.2661, simple_loss=0.348, pruned_loss=0.09215, over 967851.55 frames.], batch size: 14, lr: 6.78e-04
2022-05-28 08:42:28,791 INFO [train.py:761] (5/8) Epoch 11, batch 2000, loss[loss=0.2946, simple_loss=0.3518, pruned_loss=0.1186, over 4894.00 frames.], tot_loss[loss=0.267, simple_loss=0.3483, pruned_loss=0.09288, over 966907.65 frames.], batch size: 12, lr: 6.78e-04
2022-05-28 08:43:06,833 INFO [train.py:761] (5/8) Epoch 11, batch 2050, loss[loss=0.3522, simple_loss=0.432, pruned_loss=0.1362, over 4818.00 frames.], tot_loss[loss=0.2671, simple_loss=0.3486, pruned_loss=0.09279, over 966756.19 frames.], batch size: 20, lr: 6.79e-04
2022-05-28 08:43:44,602 INFO [train.py:761] (5/8) Epoch 11, batch 2100, loss[loss=0.2975, simple_loss=0.3851, pruned_loss=0.1049, over 4891.00 frames.], tot_loss[loss=0.2673, simple_loss=0.3491, pruned_loss=0.09276, over 967000.70 frames.], batch size: 44, lr: 6.79e-04
2022-05-28 08:44:23,299 INFO [train.py:761] (5/8) Epoch 11, batch 2150, loss[loss=0.2544, simple_loss=0.3342, pruned_loss=0.08724, over 4659.00 frames.], tot_loss[loss=0.267, simple_loss=0.3483, pruned_loss=0.09282, over 966979.32 frames.], batch size: 11, lr: 6.80e-04
2022-05-28 08:45:00,961 INFO [train.py:761] (5/8) Epoch 11, batch 2200, loss[loss=0.3767, simple_loss=0.4231, pruned_loss=0.1651, over 4943.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3469, pruned_loss=0.09177, over 965741.51 frames.], batch size: 45, lr: 6.80e-04
2022-05-28 08:45:38,957 INFO [train.py:761] (5/8) Epoch 11, batch 2250, loss[loss=0.26, simple_loss=0.3484, pruned_loss=0.08581, over 4908.00 frames.], tot_loss[loss=0.2659, simple_loss=0.3474, pruned_loss=0.09221, over 966151.99 frames.], batch size: 14, lr: 6.81e-04
2022-05-28 08:46:16,949 INFO [train.py:761] (5/8) Epoch 11, batch 2300, loss[loss=0.2222, simple_loss=0.3042, pruned_loss=0.07011, over 4628.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3487, pruned_loss=0.09303, over 966900.35 frames.], batch size: 11, lr: 6.81e-04
2022-05-28 08:46:55,113 INFO [train.py:761] (5/8) Epoch 11, batch 2350, loss[loss=0.2771, simple_loss=0.3498, pruned_loss=0.1022, over 4996.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3489, pruned_loss=0.09277, over 966828.64 frames.], batch size: 13, lr: 6.82e-04
2022-05-28 08:47:33,207 INFO [train.py:761] (5/8) Epoch 11, batch 2400, loss[loss=0.2295, simple_loss=0.3152, pruned_loss=0.07185, over 4735.00 frames.], tot_loss[loss=0.2662, simple_loss=0.3476, pruned_loss=0.09237, over 966654.72 frames.], batch size: 12, lr: 6.82e-04
2022-05-28 08:48:11,255 INFO [train.py:761] (5/8) Epoch 11, batch 2450, loss[loss=0.2314, simple_loss=0.3036, pruned_loss=0.0796, over 4741.00 frames.], tot_loss[loss=0.2665, simple_loss=0.3481, pruned_loss=0.09242, over 967038.68 frames.], batch size: 11, lr: 6.83e-04
2022-05-28 08:48:49,166 INFO [train.py:761] (5/8) Epoch 11, batch 2500, loss[loss=0.2741, simple_loss=0.3316, pruned_loss=0.1083, over 4959.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3491, pruned_loss=0.09298, over 966378.80 frames.], batch size: 12, lr: 6.83e-04
2022-05-28 08:49:27,066 INFO [train.py:761] (5/8) Epoch 11, batch 2550, loss[loss=0.2387, simple_loss=0.3313, pruned_loss=0.07306, over 4838.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3483, pruned_loss=0.09276, over 966033.60 frames.], batch size: 18, lr: 6.84e-04
2022-05-28 08:50:05,055 INFO [train.py:761] (5/8) Epoch 11, batch 2600, loss[loss=0.2351, simple_loss=0.3265, pruned_loss=0.07184, over 4882.00 frames.], tot_loss[loss=0.265, simple_loss=0.3463, pruned_loss=0.09182, over 966712.99 frames.], batch size: 12, lr: 6.84e-04
2022-05-28 08:50:43,845 INFO [train.py:761] (5/8) Epoch 11, batch 2650, loss[loss=0.2594, simple_loss=0.3448, pruned_loss=0.08698, over 4729.00 frames.], tot_loss[loss=0.2666, simple_loss=0.3478, pruned_loss=0.0927, over 966929.77 frames.], batch size: 11, lr: 6.85e-04
2022-05-28 08:51:21,756 INFO [train.py:761] (5/8) Epoch 11, batch 2700, loss[loss=0.2445, simple_loss=0.3218, pruned_loss=0.08362, over 4967.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3478, pruned_loss=0.093, over 966926.43 frames.], batch size: 12, lr: 6.85e-04
2022-05-28 08:51:59,452 INFO [train.py:761] (5/8) Epoch 11, batch 2750, loss[loss=0.3325, simple_loss=0.4058, pruned_loss=0.1296, over 4711.00 frames.], tot_loss[loss=0.2664, simple_loss=0.3477, pruned_loss=0.09252, over 966656.37 frames.], batch size: 14, lr: 6.86e-04
2022-05-28 08:52:37,044 INFO [train.py:761] (5/8) Epoch 11, batch 2800, loss[loss=0.2439, simple_loss=0.3337, pruned_loss=0.0771, over 4908.00 frames.], tot_loss[loss=0.2666, simple_loss=0.3479, pruned_loss=0.09266, over 965849.54 frames.], batch size: 26, lr: 6.86e-04
2022-05-28 08:53:15,029 INFO [train.py:761] (5/8) Epoch 11, batch 2850, loss[loss=0.2769, simple_loss=0.37, pruned_loss=0.09189, over 4792.00 frames.], tot_loss[loss=0.2693, simple_loss=0.3503, pruned_loss=0.09417, over 965945.50 frames.], batch size: 16, lr: 6.87e-04
2022-05-28 08:53:52,422 INFO [train.py:761] (5/8) Epoch 11, batch 2900, loss[loss=0.3449, simple_loss=0.4005, pruned_loss=0.1447, over 4975.00 frames.], tot_loss[loss=0.2695, simple_loss=0.3505, pruned_loss=0.09424, over 966563.16 frames.], batch size: 14, lr: 6.87e-04
2022-05-28 08:54:30,644 INFO [train.py:761] (5/8) Epoch 11, batch 2950, loss[loss=0.2641, simple_loss=0.3578, pruned_loss=0.08519, over 4865.00 frames.], tot_loss[loss=0.2683, simple_loss=0.3501, pruned_loss=0.09321, over 966202.95 frames.], batch size: 25, lr: 6.88e-04
2022-05-28 08:55:08,961 INFO [train.py:761] (5/8) Epoch 11, batch 3000, loss[loss=0.2353, simple_loss=0.3156, pruned_loss=0.07748, over 4976.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3497, pruned_loss=0.09325, over 967876.29 frames.], batch size: 13, lr: 6.88e-04
2022-05-28 08:55:08,962 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 08:55:18,929 INFO [train.py:790] (5/8) Epoch 11, validation: loss=0.2353, simple_loss=0.3369, pruned_loss=0.06682, over 944034.00 frames.
2022-05-28 08:55:56,312 INFO [train.py:761] (5/8) Epoch 11, batch 3050, loss[loss=0.2233, simple_loss=0.3068, pruned_loss=0.06991, over 4911.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3495, pruned_loss=0.09333, over 966757.56 frames.], batch size: 13, lr: 6.89e-04
2022-05-28 08:56:34,471 INFO [train.py:761] (5/8) Epoch 11, batch 3100, loss[loss=0.2477, simple_loss=0.3347, pruned_loss=0.0804, over 4728.00 frames.], tot_loss[loss=0.2714, simple_loss=0.3514, pruned_loss=0.09571, over 966705.66 frames.], batch size: 13, lr: 6.89e-04
2022-05-28 08:57:12,902 INFO [train.py:761] (5/8) Epoch 11, batch 3150, loss[loss=0.2394, simple_loss=0.3267, pruned_loss=0.07601, over 4974.00 frames.], tot_loss[loss=0.2734, simple_loss=0.3523, pruned_loss=0.09723, over 968347.73 frames.], batch size: 15, lr: 6.90e-04
2022-05-28 08:57:50,920 INFO [train.py:761] (5/8) Epoch 11, batch 3200, loss[loss=0.3045, simple_loss=0.3684, pruned_loss=0.1203, over 4816.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3533, pruned_loss=0.09903, over 970041.85 frames.], batch size: 16, lr: 6.90e-04
2022-05-28 08:58:29,227 INFO [train.py:761] (5/8) Epoch 11, batch 3250, loss[loss=0.2344, simple_loss=0.2989, pruned_loss=0.08495, over 4747.00 frames.], tot_loss[loss=0.2786, simple_loss=0.3548, pruned_loss=0.1012, over 968833.30 frames.], batch size: 11, lr: 6.91e-04
2022-05-28 08:59:07,485 INFO [train.py:761] (5/8) Epoch 11, batch 3300, loss[loss=0.3437, simple_loss=0.3804, pruned_loss=0.1535, over 4790.00 frames.], tot_loss[loss=0.2814, simple_loss=0.3557, pruned_loss=0.1036, over 967263.31 frames.], batch size: 12, lr: 6.91e-04
2022-05-28 08:59:46,074 INFO [train.py:761] (5/8) Epoch 11, batch 3350, loss[loss=0.2918, simple_loss=0.3545, pruned_loss=0.1145, over 4855.00 frames.], tot_loss[loss=0.2873, simple_loss=0.3595, pruned_loss=0.1075, over 967545.85 frames.], batch size: 14, lr: 6.92e-04
2022-05-28 09:00:24,210 INFO [train.py:761] (5/8) Epoch 11, batch 3400, loss[loss=0.2592, simple_loss=0.3222, pruned_loss=0.09809, over 4925.00 frames.], tot_loss[loss=0.289, simple_loss=0.3597, pruned_loss=0.1092, over 966544.65 frames.], batch size: 13, lr: 6.92e-04
2022-05-28 09:01:02,762 INFO [train.py:761] (5/8) Epoch 11, batch 3450, loss[loss=0.2335, simple_loss=0.3157, pruned_loss=0.07564, over 4843.00 frames.], tot_loss[loss=0.289, simple_loss=0.3592, pruned_loss=0.1095, over 964867.25 frames.], batch size: 11, lr: 6.93e-04
2022-05-28 09:01:40,991 INFO [train.py:761] (5/8) Epoch 11, batch 3500, loss[loss=0.2821, simple_loss=0.3401, pruned_loss=0.112, over 4975.00 frames.], tot_loss[loss=0.2927, simple_loss=0.3612, pruned_loss=0.1121, over 965534.75 frames.], batch size: 12, lr: 6.93e-04
2022-05-28 09:02:19,462 INFO [train.py:761] (5/8) Epoch 11, batch 3550, loss[loss=0.3601, simple_loss=0.4166, pruned_loss=0.1518, over 4886.00 frames.], tot_loss[loss=0.2951, simple_loss=0.3626, pruned_loss=0.1138, over 966372.92 frames.], batch size: 15, lr: 6.93e-04
2022-05-28 09:02:57,884 INFO [train.py:761] (5/8) Epoch 11, batch 3600, loss[loss=0.3282, simple_loss=0.3846, pruned_loss=0.1358, over 4766.00 frames.], tot_loss[loss=0.2975, simple_loss=0.3639, pruned_loss=0.1155, over 966777.34 frames.], batch size: 15, lr: 6.94e-04
2022-05-28 09:03:35,465 INFO [train.py:761] (5/8) Epoch 11, batch 3650, loss[loss=0.3326, simple_loss=0.3966, pruned_loss=0.1343, over 4923.00 frames.], tot_loss[loss=0.2984, simple_loss=0.3634, pruned_loss=0.1167, over 966625.46 frames.], batch size: 13, lr: 6.94e-04
2022-05-28 09:04:12,836 INFO [train.py:761] (5/8) Epoch 11, batch 3700, loss[loss=0.3077, simple_loss=0.3797, pruned_loss=0.1178, over 4722.00 frames.], tot_loss[loss=0.2986, simple_loss=0.3641, pruned_loss=0.1165, over 966138.89 frames.], batch size: 13, lr: 6.95e-04
2022-05-28 09:04:51,122 INFO [train.py:761] (5/8) Epoch 11, batch 3750, loss[loss=0.2268, simple_loss=0.2915, pruned_loss=0.08105, over 4993.00 frames.], tot_loss[loss=0.2996, simple_loss=0.3651, pruned_loss=0.1171, over 966003.78 frames.], batch size: 13, lr: 6.95e-04
2022-05-28 09:05:28,956 INFO [train.py:761] (5/8) Epoch 11, batch 3800, loss[loss=0.2864, simple_loss=0.36, pruned_loss=0.1064, over 4667.00 frames.], tot_loss[loss=0.3011, simple_loss=0.3665, pruned_loss=0.1179, over 965688.01 frames.], batch size: 12, lr: 6.96e-04
2022-05-28 09:06:07,449 INFO [train.py:761] (5/8) Epoch 11, batch 3850, loss[loss=0.3094, simple_loss=0.386, pruned_loss=0.1164, over 4794.00 frames.], tot_loss[loss=0.3, simple_loss=0.3656, pruned_loss=0.1172, over 967264.54 frames.], batch size: 16, lr: 6.96e-04
2022-05-28 09:06:45,154 INFO [train.py:761] (5/8) Epoch 11, batch 3900, loss[loss=0.3138, simple_loss=0.3729, pruned_loss=0.1274, over 4777.00 frames.], tot_loss[loss=0.3008, simple_loss=0.3661, pruned_loss=0.1178, over 966412.90 frames.], batch size: 15, lr: 6.97e-04
2022-05-28 09:07:23,410 INFO [train.py:761] (5/8) Epoch 11, batch 3950, loss[loss=0.2919, simple_loss=0.3634, pruned_loss=0.1102, over 4846.00 frames.], tot_loss[loss=0.2981, simple_loss=0.364, pruned_loss=0.1161, over 965924.96 frames.], batch size: 13, lr: 6.97e-04
2022-05-28 09:08:02,400 INFO [train.py:761] (5/8) Epoch 11, batch 4000, loss[loss=0.3483, simple_loss=0.3982, pruned_loss=0.1492, over 4856.00 frames.], tot_loss[loss=0.2975, simple_loss=0.3631, pruned_loss=0.116, over 966935.76 frames.], batch size: 25, lr: 6.98e-04
2022-05-28 09:08:40,560 INFO [train.py:761] (5/8) Epoch 11, batch 4050, loss[loss=0.3584, simple_loss=0.3985, pruned_loss=0.1591, over 4977.00 frames.], tot_loss[loss=0.3005, simple_loss=0.3649, pruned_loss=0.1181, over 966756.10 frames.], batch size: 45, lr: 6.98e-04
2022-05-28 09:09:17,971 INFO [train.py:761] (5/8) Epoch 11, batch 4100, loss[loss=0.3442, simple_loss=0.4076, pruned_loss=0.1404, over 4904.00 frames.], tot_loss[loss=0.3006, simple_loss=0.3651, pruned_loss=0.1181, over 966411.19 frames.], batch size: 14, lr: 6.99e-04
2022-05-28 09:09:56,817 INFO [train.py:761] (5/8) Epoch 11, batch 4150, loss[loss=0.2678, simple_loss=0.3513, pruned_loss=0.09214, over 4803.00 frames.], tot_loss[loss=0.3006, simple_loss=0.3652, pruned_loss=0.118, over 966257.76 frames.], batch size: 12, lr: 6.99e-04
2022-05-28 09:10:34,971 INFO [train.py:761] (5/8) Epoch 11, batch 4200, loss[loss=0.3397, simple_loss=0.3888, pruned_loss=0.1453, over 4786.00 frames.], tot_loss[loss=0.3006, simple_loss=0.3653, pruned_loss=0.118, over 965518.10 frames.], batch size: 13, lr: 7.00e-04
2022-05-28 09:11:13,664 INFO [train.py:761] (5/8) Epoch 11, batch 4250, loss[loss=0.2779, simple_loss=0.3358, pruned_loss=0.1101, over 4980.00 frames.], tot_loss[loss=0.3027, simple_loss=0.3669, pruned_loss=0.1192, over 966643.52 frames.], batch size: 13, lr: 7.00e-04
2022-05-28 09:11:52,463 INFO [train.py:761] (5/8) Epoch 11, batch 4300, loss[loss=0.2769, simple_loss=0.3494, pruned_loss=0.1022, over 4788.00 frames.], tot_loss[loss=0.302, simple_loss=0.3658, pruned_loss=0.1191, over 965874.64 frames.], batch size: 13, lr: 7.01e-04
2022-05-28 09:12:31,083 INFO [train.py:761] (5/8) Epoch 11, batch 4350, loss[loss=0.3114, simple_loss=0.3692, pruned_loss=0.1268, over 4664.00 frames.], tot_loss[loss=0.302, simple_loss=0.3659, pruned_loss=0.1191, over 965614.37 frames.], batch size: 12, lr: 7.01e-04
2022-05-28 09:13:09,180 INFO [train.py:761] (5/8) Epoch 11, batch 4400, loss[loss=0.321, simple_loss=0.3808, pruned_loss=0.1306, over 4976.00 frames.], tot_loss[loss=0.3017, simple_loss=0.3651, pruned_loss=0.1191, over 965340.96 frames.], batch size: 15, lr: 7.02e-04
2022-05-28 09:13:47,489 INFO [train.py:761] (5/8) Epoch 11, batch 4450, loss[loss=0.3268, simple_loss=0.3847, pruned_loss=0.1344, over 4728.00 frames.], tot_loss[loss=0.301, simple_loss=0.3646, pruned_loss=0.1187, over 965248.92 frames.], batch size: 12, lr: 7.02e-04
2022-05-28 09:14:25,599 INFO [train.py:761] (5/8) Epoch 11, batch 4500, loss[loss=0.3039, simple_loss=0.3609, pruned_loss=0.1235, over 4971.00 frames.], tot_loss[loss=0.3003, simple_loss=0.3637, pruned_loss=0.1184, over 965357.55 frames.], batch size: 14, lr: 7.03e-04
2022-05-28 09:15:07,050 INFO [train.py:761] (5/8) Epoch 11, batch 4550, loss[loss=0.2344, simple_loss=0.3105, pruned_loss=0.07912, over 4926.00 frames.], tot_loss[loss=0.2985, simple_loss=0.3628, pruned_loss=0.1171, over 964772.60 frames.], batch size: 13, lr: 7.03e-04
2022-05-28 09:15:44,421 INFO [train.py:761] (5/8) Epoch 11, batch 4600, loss[loss=0.2722, simple_loss=0.3591, pruned_loss=0.0927, over 4865.00 frames.], tot_loss[loss=0.3006, simple_loss=0.3648, pruned_loss=0.1182, over 965072.94 frames.], batch size: 20, lr: 7.04e-04
2022-05-28 09:16:22,793 INFO [train.py:761] (5/8) Epoch 11, batch 4650, loss[loss=0.2115, simple_loss=0.2869, pruned_loss=0.06806, over 4651.00 frames.], tot_loss[loss=0.3009, simple_loss=0.3651, pruned_loss=0.1184, over 965509.55 frames.], batch size: 11, lr: 7.04e-04
2022-05-28 09:17:00,846 INFO [train.py:761] (5/8) Epoch 11, batch 4700, loss[loss=0.2821, simple_loss=0.3531, pruned_loss=0.1055, over 4732.00 frames.], tot_loss[loss=0.2993, simple_loss=0.3638, pruned_loss=0.1174, over 965858.55 frames.], batch size: 13, lr: 7.05e-04
2022-05-28 09:17:38,957 INFO [train.py:761] (5/8) Epoch 11, batch 4750, loss[loss=0.253, simple_loss=0.3298, pruned_loss=0.08806, over 4568.00 frames.], tot_loss[loss=0.3001, simple_loss=0.3645, pruned_loss=0.1178, over 966207.06 frames.], batch size: 10, lr: 7.05e-04
2022-05-28 09:18:17,223 INFO [train.py:761] (5/8) Epoch 11, batch 4800, loss[loss=0.3595, simple_loss=0.4113, pruned_loss=0.1538, over 4967.00 frames.], tot_loss[loss=0.3004, simple_loss=0.3643, pruned_loss=0.1183, over 964817.67 frames.], batch size: 16, lr: 7.06e-04
2022-05-28 09:18:55,465 INFO [train.py:761] (5/8) Epoch 11, batch 4850, loss[loss=0.3157, simple_loss=0.3763, pruned_loss=0.1275, over 4852.00 frames.], tot_loss[loss=0.2995, simple_loss=0.3633, pruned_loss=0.1178, over 965121.57 frames.], batch size: 14, lr: 7.06e-04
2022-05-28 09:19:33,842 INFO [train.py:761] (5/8) Epoch 11, batch 4900, loss[loss=0.291, simple_loss=0.3534, pruned_loss=0.1143, over 4979.00 frames.], tot_loss[loss=0.2996, simple_loss=0.3636, pruned_loss=0.1178, over 964877.06 frames.], batch size: 13, lr: 7.07e-04
2022-05-28 09:20:12,516 INFO [train.py:761] (5/8) Epoch 11, batch 4950, loss[loss=0.3206, simple_loss=0.3875, pruned_loss=0.1269, over 4855.00 frames.], tot_loss[loss=0.2997, simple_loss=0.3638, pruned_loss=0.1178, over 965565.26 frames.], batch size: 14, lr: 7.07e-04
2022-05-28 09:20:50,828 INFO [train.py:761] (5/8) Epoch 11, batch 5000, loss[loss=0.3098, simple_loss=0.3792, pruned_loss=0.1202, over 4877.00 frames.], tot_loss[loss=0.299, simple_loss=0.3634, pruned_loss=0.1173, over 965748.18 frames.], batch size: 15, lr: 7.08e-04
2022-05-28 09:21:29,336 INFO [train.py:761] (5/8) Epoch 11, batch 5050, loss[loss=0.2644, simple_loss=0.3403, pruned_loss=0.09428, over 4978.00 frames.], tot_loss[loss=0.299, simple_loss=0.3639, pruned_loss=0.117, over 967190.92 frames.], batch size: 14, lr: 7.08e-04
2022-05-28 09:22:07,600 INFO [train.py:761] (5/8) Epoch 11, batch 5100, loss[loss=0.2632, simple_loss=0.3144, pruned_loss=0.106, over 4739.00 frames.], tot_loss[loss=0.2977, simple_loss=0.3625, pruned_loss=0.1164, over 967867.73 frames.], batch size: 11, lr: 7.09e-04
2022-05-28 09:22:45,694 INFO [train.py:761] (5/8) Epoch 11, batch 5150, loss[loss=0.3844, simple_loss=0.4239, pruned_loss=0.1724, over 4880.00 frames.], tot_loss[loss=0.2978, simple_loss=0.3624, pruned_loss=0.1166, over 966335.82 frames.], batch size: 45, lr: 7.09e-04
2022-05-28 09:23:24,118 INFO [train.py:761] (5/8) Epoch 11, batch 5200, loss[loss=0.3546, simple_loss=0.4168, pruned_loss=0.1462, over 4796.00 frames.], tot_loss[loss=0.2994, simple_loss=0.3633, pruned_loss=0.1177, over 966317.44 frames.], batch size: 20, lr: 7.10e-04
2022-05-28 09:24:02,469 INFO [train.py:761] (5/8) Epoch 11, batch 5250, loss[loss=0.3299, simple_loss=0.3872, pruned_loss=0.1363, over 4984.00 frames.], tot_loss[loss=0.2976, simple_loss=0.3614, pruned_loss=0.1169, over 966383.18 frames.], batch size: 15, lr: 7.10e-04
2022-05-28 09:24:41,603 INFO [train.py:761] (5/8) Epoch 11, batch 5300, loss[loss=0.2901, simple_loss=0.3757, pruned_loss=0.1023, over 4984.00 frames.], tot_loss[loss=0.2969, simple_loss=0.3608, pruned_loss=0.1165, over 966575.01 frames.], batch size: 15, lr: 7.11e-04
2022-05-28 09:25:19,432 INFO [train.py:761] (5/8) Epoch 11, batch 5350, loss[loss=0.2945, simple_loss=0.3385, pruned_loss=0.1253, over 4645.00 frames.], tot_loss[loss=0.2956, simple_loss=0.3602, pruned_loss=0.1155, over 965843.44 frames.], batch size: 11, lr: 7.11e-04
2022-05-28 09:25:57,813 INFO [train.py:761] (5/8) Epoch 11, batch 5400, loss[loss=0.2471, simple_loss=0.3222, pruned_loss=0.08598, over 4631.00 frames.], tot_loss[loss=0.2974, simple_loss=0.3621, pruned_loss=0.1163, over 965744.44 frames.], batch size: 11, lr: 7.12e-04
2022-05-28 09:26:35,414 INFO [train.py:761] (5/8) Epoch 11, batch 5450, loss[loss=0.2618, simple_loss=0.3579, pruned_loss=0.08283, over 4913.00 frames.], tot_loss[loss=0.2941, simple_loss=0.3591, pruned_loss=0.1145, over 965622.10 frames.], batch size: 14, lr: 7.12e-04
2022-05-28 09:27:13,512 INFO [train.py:761] (5/8) Epoch 11, batch 5500, loss[loss=0.2601, simple_loss=0.3503, pruned_loss=0.08499, over 4846.00 frames.], tot_loss[loss=0.2938, simple_loss=0.3589, pruned_loss=0.1144, over 966125.60 frames.], batch size: 14, lr: 7.13e-04
2022-05-28 09:27:51,546 INFO [train.py:761] (5/8) Epoch 11, batch 5550, loss[loss=0.3099, simple_loss=0.3667, pruned_loss=0.1265, over 4735.00 frames.], tot_loss[loss=0.2952, simple_loss=0.3602, pruned_loss=0.1151, over 967321.97 frames.], batch size: 12, lr: 7.13e-04
2022-05-28 09:28:29,643 INFO [train.py:761] (5/8) Epoch 11, batch 5600, loss[loss=0.2567, simple_loss=0.3229, pruned_loss=0.09522, over 4973.00 frames.], tot_loss[loss=0.294, simple_loss=0.3597, pruned_loss=0.1142, over 966863.08 frames.], batch size: 12, lr: 7.14e-04
2022-05-28 09:29:07,831 INFO [train.py:761] (5/8) Epoch 11, batch 5650, loss[loss=0.3512, simple_loss=0.3739, pruned_loss=0.1642, over 4556.00 frames.], tot_loss[loss=0.2951, simple_loss=0.3608, pruned_loss=0.1147, over 965919.21 frames.], batch size: 10, lr: 7.14e-04
2022-05-28 09:29:46,140 INFO [train.py:761] (5/8) Epoch 11, batch 5700, loss[loss=0.3091, simple_loss=0.3769, pruned_loss=0.1206, over 4964.00 frames.], tot_loss[loss=0.2964, simple_loss=0.3618, pruned_loss=0.1155, over 965734.88 frames.], batch size: 14, lr: 7.14e-04
2022-05-28 09:30:24,286 INFO [train.py:761] (5/8) Epoch 11, batch 5750, loss[loss=0.332, simple_loss=0.3814, pruned_loss=0.1413, over 4609.00 frames.], tot_loss[loss=0.2957, simple_loss=0.3615, pruned_loss=0.1149, over 964118.43 frames.], batch size: 12, lr: 7.15e-04
2022-05-28 09:31:02,836 INFO [train.py:761] (5/8) Epoch 11, batch 5800, loss[loss=0.2889, simple_loss=0.3678, pruned_loss=0.105, over 4876.00 frames.], tot_loss[loss=0.2937, simple_loss=0.3602, pruned_loss=0.1135, over 964822.30 frames.], batch size: 15, lr: 7.15e-04
2022-05-28 09:31:41,095 INFO [train.py:761] (5/8) Epoch 11, batch 5850, loss[loss=0.2266, simple_loss=0.2918, pruned_loss=0.08067, over 4837.00 frames.], tot_loss[loss=0.2936, simple_loss=0.3595, pruned_loss=0.1139, over 964762.89 frames.], batch size: 11, lr: 7.16e-04
2022-05-28 09:32:19,526 INFO [train.py:761] (5/8) Epoch 11, batch 5900, loss[loss=0.3118, simple_loss=0.3757, pruned_loss=0.1239, over 4837.00 frames.], tot_loss[loss=0.2936, simple_loss=0.3595, pruned_loss=0.1139, over 964512.40 frames.], batch size: 25, lr: 7.16e-04
2022-05-28 09:32:57,311 INFO [train.py:761] (5/8) Epoch 11, batch 5950, loss[loss=0.2541, simple_loss=0.3298, pruned_loss=0.08923, over 4881.00 frames.], tot_loss[loss=0.294, simple_loss=0.3598, pruned_loss=0.1141, over 964502.75 frames.], batch size: 18, lr: 7.17e-04
2022-05-28 09:33:35,301 INFO [train.py:761] (5/8) Epoch 11, batch 6000, loss[loss=0.3336, simple_loss=0.3902, pruned_loss=0.1385, over 4915.00 frames.], tot_loss[loss=0.2938, simple_loss=0.3601, pruned_loss=0.1137, over 965264.68 frames.], batch size: 14, lr: 7.17e-04
2022-05-28 09:33:35,301 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 09:33:45,257 INFO [train.py:790] (5/8) Epoch 11, validation: loss=0.2236, simple_loss=0.3311, pruned_loss=0.05801, over 944034.00 frames.
2022-05-28 09:34:23,566 INFO [train.py:761] (5/8) Epoch 11, batch 6050, loss[loss=0.3158, simple_loss=0.3841, pruned_loss=0.1238, over 4783.00 frames.], tot_loss[loss=0.2921, simple_loss=0.3588, pruned_loss=0.1128, over 965843.59 frames.], batch size: 14, lr: 7.18e-04
2022-05-28 09:35:02,070 INFO [train.py:761] (5/8) Epoch 11, batch 6100, loss[loss=0.2766, simple_loss=0.354, pruned_loss=0.09958, over 4890.00 frames.], tot_loss[loss=0.2928, simple_loss=0.3596, pruned_loss=0.113, over 966230.07 frames.], batch size: 12, lr: 7.18e-04
2022-05-28 09:35:40,248 INFO [train.py:761] (5/8) Epoch 11, batch 6150, loss[loss=0.3038, simple_loss=0.3755, pruned_loss=0.1161, over 4773.00 frames.], tot_loss[loss=0.2929, simple_loss=0.3595, pruned_loss=0.1132, over 965960.25 frames.], batch size: 20, lr: 7.19e-04
2022-05-28 09:36:18,374 INFO [train.py:761] (5/8) Epoch 11, batch 6200, loss[loss=0.2892, simple_loss=0.3603, pruned_loss=0.109, over 4969.00 frames.], tot_loss[loss=0.295, simple_loss=0.3609, pruned_loss=0.1145, over 966844.82 frames.], batch size: 14, lr: 7.19e-04
2022-05-28 09:36:56,989 INFO [train.py:761] (5/8) Epoch 11, batch 6250, loss[loss=0.2429, simple_loss=0.3162, pruned_loss=0.08486, over 4986.00 frames.], tot_loss[loss=0.2935, simple_loss=0.3596, pruned_loss=0.1137, over 966569.27 frames.], batch size: 13, lr: 7.20e-04
2022-05-28 09:37:35,002 INFO [train.py:761] (5/8) Epoch 11, batch 6300, loss[loss=0.2866, simple_loss=0.3739, pruned_loss=0.09965, over 4971.00 frames.], tot_loss[loss=0.2921, simple_loss=0.3591, pruned_loss=0.1125, over 966418.99 frames.], batch size: 14, lr: 7.20e-04
2022-05-28 09:38:13,124 INFO [train.py:761] (5/8) Epoch 11, batch 6350, loss[loss=0.3439, simple_loss=0.4067, pruned_loss=0.1406, over 4752.00 frames.], tot_loss[loss=0.2908, simple_loss=0.3582, pruned_loss=0.1117, over 966152.92 frames.], batch size: 15, lr: 7.21e-04
2022-05-28 09:38:51,051 INFO [train.py:761] (5/8) Epoch 11, batch 6400, loss[loss=0.2701, simple_loss=0.3447, pruned_loss=0.09776, over 4858.00 frames.], tot_loss[loss=0.2934, simple_loss=0.3597, pruned_loss=0.1135, over 965901.58 frames.], batch size: 13, lr: 7.21e-04
2022-05-28 09:39:29,427 INFO [train.py:761] (5/8) Epoch 11, batch 6450, loss[loss=0.2897, simple_loss=0.3458, pruned_loss=0.1168, over 4559.00 frames.], tot_loss[loss=0.2923, simple_loss=0.3586, pruned_loss=0.113, over 965339.31 frames.], batch size: 10, lr: 7.22e-04
2022-05-28 09:40:07,502 INFO [train.py:761] (5/8) Epoch 11, batch 6500, loss[loss=0.2167, simple_loss=0.2831, pruned_loss=0.07513, over 4669.00 frames.], tot_loss[loss=0.2905, simple_loss=0.3567, pruned_loss=0.1121, over 965857.98 frames.], batch size: 12, lr: 7.22e-04
2022-05-28 09:40:46,693 INFO [train.py:761] (5/8) Epoch 11, batch 6550, loss[loss=0.291, simple_loss=0.346, pruned_loss=0.118, over 4985.00 frames.], tot_loss[loss=0.2887, simple_loss=0.3554, pruned_loss=0.111, over 965341.75 frames.], batch size: 13, lr: 7.23e-04
2022-05-28 09:41:25,314 INFO [train.py:761] (5/8) Epoch 11, batch 6600, loss[loss=0.288, simple_loss=0.362, pruned_loss=0.107, over 4724.00 frames.], tot_loss[loss=0.2897, simple_loss=0.3561, pruned_loss=0.1117, over 964935.41 frames.], batch size: 13, lr: 7.23e-04
2022-05-28 09:42:03,771 INFO [train.py:761] (5/8) Epoch 11, batch 6650, loss[loss=0.2395, simple_loss=0.3147, pruned_loss=0.08213, over 4846.00 frames.], tot_loss[loss=0.2924, simple_loss=0.3581, pruned_loss=0.1133, over 965234.56 frames.], batch size: 13, lr: 7.24e-04
2022-05-28 09:42:42,207 INFO [train.py:761] (5/8) Epoch 11, batch 6700, loss[loss=0.3809, simple_loss=0.4224, pruned_loss=0.1697, over 4975.00 frames.], tot_loss[loss=0.2948, simple_loss=0.3605, pruned_loss=0.1146, over 965798.55 frames.], batch size: 45, lr: 7.24e-04
2022-05-28 09:43:38,279 INFO [train.py:761] (5/8) Epoch 12, batch 0, loss[loss=0.284, simple_loss=0.3575, pruned_loss=0.1053, over 4891.00 frames.], tot_loss[loss=0.284, simple_loss=0.3575, pruned_loss=0.1053, over 4891.00 frames.], batch size: 12, lr: 7.25e-04
2022-05-28 09:44:16,658 INFO [train.py:761] (5/8) Epoch 12, batch 50, loss[loss=0.2221, simple_loss=0.304, pruned_loss=0.07007, over 4994.00 frames.], tot_loss[loss=0.2637, simple_loss=0.3464, pruned_loss=0.0905, over 218178.22 frames.], batch size: 13, lr: 7.25e-04
2022-05-28 09:44:55,326 INFO [train.py:761] (5/8) Epoch 12, batch 100, loss[loss=0.2253, simple_loss=0.3081, pruned_loss=0.0713, over 4669.00 frames.], tot_loss[loss=0.2579, simple_loss=0.3412, pruned_loss=0.08725, over 384990.37 frames.], batch size: 12, lr: 7.26e-04
2022-05-28 09:45:33,022 INFO [train.py:761] (5/8) Epoch 12, batch 150, loss[loss=0.2516, simple_loss=0.332, pruned_loss=0.08557, over 4717.00 frames.], tot_loss[loss=0.2616, simple_loss=0.3445, pruned_loss=0.08931, over 514937.24 frames.], batch size: 14, lr: 7.26e-04
2022-05-28 09:46:11,828 INFO [train.py:761] (5/8) Epoch 12, batch 200, loss[loss=0.213, simple_loss=0.3178, pruned_loss=0.05409, over 4967.00 frames.], tot_loss[loss=0.2585, simple_loss=0.3419, pruned_loss=0.08754, over 615350.11 frames.], batch size: 14, lr: 7.27e-04
2022-05-28 09:46:49,707 INFO [train.py:761] (5/8) Epoch 12, batch 250, loss[loss=0.2715, simple_loss=0.356, pruned_loss=0.09347, over 4954.00 frames.], tot_loss[loss=0.2593, simple_loss=0.343, pruned_loss=0.08777, over 693552.27 frames.], batch size: 16, lr: 7.27e-04
2022-05-28 09:47:27,543 INFO [train.py:761] (5/8) Epoch 12, batch 300, loss[loss=0.2555, simple_loss=0.3413, pruned_loss=0.08486, over 4971.00 frames.], tot_loss[loss=0.2565, simple_loss=0.3403, pruned_loss=0.08628, over 753338.94 frames.], batch size: 14, lr: 7.28e-04
2022-05-28 09:48:04,993 INFO [train.py:761] (5/8) Epoch 12, batch 350, loss[loss=0.2293, simple_loss=0.3222, pruned_loss=0.06822, over 4984.00 frames.], tot_loss[loss=0.2578, simple_loss=0.3415, pruned_loss=0.08701, over 800424.49 frames.], batch size: 13, lr: 7.28e-04
2022-05-28 09:48:43,459 INFO [train.py:761] (5/8) Epoch 12, batch 400, loss[loss=0.2728, simple_loss=0.3558, pruned_loss=0.09492, over 4786.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3419, pruned_loss=0.0872, over 837591.89 frames.], batch size: 13, lr: 7.29e-04
2022-05-28 09:49:21,096 INFO [train.py:761] (5/8) Epoch 12, batch 450, loss[loss=0.2268, simple_loss=0.3069, pruned_loss=0.07333, over 4848.00 frames.], tot_loss[loss=0.2566, simple_loss=0.3406, pruned_loss=0.08628, over 866517.84 frames.], batch size: 13, lr: 7.29e-04
2022-05-28 09:49:58,721 INFO [train.py:761] (5/8) Epoch 12, batch 500, loss[loss=0.1766, simple_loss=0.2576, pruned_loss=0.04775, over 4817.00 frames.], tot_loss[loss=0.2543, simple_loss=0.3392, pruned_loss=0.0847, over 888925.34 frames.], batch size: 11, lr: 7.30e-04
2022-05-28 09:50:36,750 INFO [train.py:761] (5/8) Epoch 12, batch 550, loss[loss=0.2442, simple_loss=0.3345, pruned_loss=0.07701, over 4923.00 frames.], tot_loss[loss=0.2548, simple_loss=0.3392, pruned_loss=0.08525, over 906251.63 frames.], batch size: 25, lr: 7.30e-04
2022-05-28 09:51:14,899 INFO [train.py:761] (5/8) Epoch 12, batch 600, loss[loss=0.2441, simple_loss=0.3134, pruned_loss=0.08744, over 4757.00 frames.], tot_loss[loss=0.2558, simple_loss=0.3402, pruned_loss=0.08571, over 919210.00 frames.], batch size: 15, lr: 7.31e-04
2022-05-28 09:51:53,043 INFO [train.py:761] (5/8) Epoch 12, batch 650, loss[loss=0.3293, simple_loss=0.3959, pruned_loss=0.1314, over 4913.00 frames.], tot_loss[loss=0.2582, simple_loss=0.342, pruned_loss=0.0872, over 929755.88 frames.], batch size: 49, lr: 7.31e-04
2022-05-28 09:52:31,245 INFO [train.py:761] (5/8) Epoch 12, batch 700, loss[loss=0.2307, simple_loss=0.3101, pruned_loss=0.07562, over 4664.00 frames.], tot_loss[loss=0.2617, simple_loss=0.3442, pruned_loss=0.08955, over 937881.96 frames.], batch size: 11, lr: 7.32e-04
2022-05-28 09:53:08,441 INFO [train.py:761] (5/8) Epoch 12, batch 750, loss[loss=0.238, simple_loss=0.3056, pruned_loss=0.08524, over 4897.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3452, pruned_loss=0.08999, over 944411.65 frames.], batch size: 12, lr: 7.32e-04
2022-05-28 09:53:46,624 INFO [train.py:761] (5/8) Epoch 12, batch 800, loss[loss=0.2783, simple_loss=0.3447, pruned_loss=0.1059, over 4582.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3466, pruned_loss=0.09189, over 948391.29 frames.], batch size: 10, lr: 7.32e-04
2022-05-28 09:54:24,296 INFO [train.py:761] (5/8) Epoch 12, batch 850, loss[loss=0.2508, simple_loss=0.3295, pruned_loss=0.08598, over 4663.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3465, pruned_loss=0.09192, over 951791.83 frames.], batch size: 12, lr: 7.33e-04
2022-05-28 09:55:02,725 INFO [train.py:761] (5/8) Epoch 12, batch 900, loss[loss=0.3138, simple_loss=0.3943, pruned_loss=0.1166, over 4792.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3475, pruned_loss=0.0929, over 955526.62 frames.], batch size: 16, lr: 7.33e-04
2022-05-28 09:55:40,436 INFO [train.py:761] (5/8) Epoch 12, batch 950, loss[loss=0.252, simple_loss=0.3409, pruned_loss=0.08152, over 4880.00 frames.], tot_loss[loss=0.2671, simple_loss=0.3478, pruned_loss=0.09314, over 958306.60 frames.], batch size: 15, lr: 7.34e-04
2022-05-28 09:56:18,639 INFO [train.py:761] (5/8) Epoch 12, batch 1000, loss[loss=0.2896, simple_loss=0.382, pruned_loss=0.09858, over 4846.00 frames.], tot_loss[loss=0.2679, simple_loss=0.3484, pruned_loss=0.09374, over 960003.25 frames.], batch size: 14, lr: 7.34e-04
2022-05-28 09:56:56,284 INFO [train.py:761] (5/8) Epoch 12, batch 1050, loss[loss=0.2147, simple_loss=0.2909, pruned_loss=0.0693, over 4665.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3475, pruned_loss=0.09311, over 960229.97 frames.], batch size: 12, lr: 7.35e-04
2022-05-28 09:57:34,163 INFO [train.py:761] (5/8) Epoch 12, batch 1100, loss[loss=0.2101, simple_loss=0.2947, pruned_loss=0.06277, over 4891.00 frames.], tot_loss[loss=0.2665, simple_loss=0.3473, pruned_loss=0.09288, over 962221.63 frames.], batch size: 12, lr: 7.35e-04
2022-05-28 09:58:12,141 INFO [train.py:761] (5/8) Epoch 12, batch 1150, loss[loss=0.2341, simple_loss=0.3336, pruned_loss=0.06728, over 4989.00 frames.], tot_loss[loss=0.2684, simple_loss=0.3492, pruned_loss=0.0938, over 962520.06 frames.], batch size: 15, lr: 7.36e-04
2022-05-28 09:58:50,430 INFO [train.py:761] (5/8) Epoch 12, batch 1200, loss[loss=0.2452, simple_loss=0.3234, pruned_loss=0.08351, over 4973.00 frames.], tot_loss[loss=0.2656, simple_loss=0.3471, pruned_loss=0.09206, over 963543.74 frames.], batch size: 14, lr: 7.36e-04
2022-05-28 09:59:28,905 INFO [train.py:761] (5/8) Epoch 12, batch 1250, loss[loss=0.2641, simple_loss=0.3504, pruned_loss=0.08887, over 4677.00 frames.], tot_loss[loss=0.2631, simple_loss=0.345, pruned_loss=0.09057, over 964770.02 frames.], batch size: 13, lr: 7.37e-04
2022-05-28 10:00:06,971 INFO [train.py:761] (5/8) Epoch 12, batch 1300, loss[loss=0.2024, simple_loss=0.2831, pruned_loss=0.06082, over 4735.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3459, pruned_loss=0.09032, over 965915.48 frames.], batch size: 11, lr: 7.37e-04
2022-05-28 10:00:44,876 INFO [train.py:761] (5/8) Epoch 12, batch 1350, loss[loss=0.2981, simple_loss=0.3744, pruned_loss=0.1109, over 4837.00 frames.], tot_loss[loss=0.264, simple_loss=0.346, pruned_loss=0.09104, over 966591.15 frames.], batch size: 26, lr: 7.38e-04
2022-05-28 10:01:22,925 INFO [train.py:761] (5/8) Epoch 12, batch 1400, loss[loss=0.3211, simple_loss=0.3858, pruned_loss=0.1282, over 4966.00 frames.], tot_loss[loss=0.2655, simple_loss=0.3474, pruned_loss=0.09175, over 967643.35 frames.], batch size: 47, lr: 7.38e-04
2022-05-28 10:02:00,827 INFO [train.py:761] (5/8) Epoch 12, batch 1450, loss[loss=0.2702, simple_loss=0.3315, pruned_loss=0.1045, over 4648.00 frames.], tot_loss[loss=0.2668, simple_loss=0.3484, pruned_loss=0.09257, over 966877.79 frames.], batch size: 11, lr: 7.39e-04
2022-05-28 10:02:39,132 INFO [train.py:761] (5/8) Epoch 12, batch 1500, loss[loss=0.2846, simple_loss=0.3557, pruned_loss=0.1067, over 4976.00 frames.], tot_loss[loss=0.2683, simple_loss=0.3497, pruned_loss=0.09347, over 966364.23 frames.], batch size: 14, lr: 7.39e-04
2022-05-28 10:03:16,795 INFO [train.py:761] (5/8) Epoch 12, batch 1550, loss[loss=0.2803, simple_loss=0.3497, pruned_loss=0.1054, over 4889.00 frames.], tot_loss[loss=0.2659, simple_loss=0.3475, pruned_loss=0.09212, over 965475.90 frames.], batch size: 15, lr: 7.40e-04
2022-05-28 10:03:54,760 INFO [train.py:761] (5/8) Epoch 12, batch 1600, loss[loss=0.2653, simple_loss=0.3498, pruned_loss=0.09038, over 4933.00 frames.], tot_loss[loss=0.2665, simple_loss=0.3481, pruned_loss=0.09242, over 965827.99 frames.], batch size: 16, lr: 7.40e-04
2022-05-28 10:04:32,657 INFO [train.py:761] (5/8) Epoch 12, batch 1650, loss[loss=0.2295, simple_loss=0.3183, pruned_loss=0.07033, over 4969.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3486, pruned_loss=0.09261, over 966333.55 frames.], batch size: 14, lr: 7.41e-04
2022-05-28 10:05:10,803 INFO [train.py:761] (5/8) Epoch 12, batch 1700, loss[loss=0.2143, simple_loss=0.2911, pruned_loss=0.06874, over 4805.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3465, pruned_loss=0.09162, over 965644.89 frames.], batch size: 12, lr: 7.41e-04
2022-05-28 10:05:48,783 INFO [train.py:761] (5/8) Epoch 12, batch 1750, loss[loss=0.2307, simple_loss=0.3154, pruned_loss=0.07299, over 4791.00 frames.], tot_loss[loss=0.2656, simple_loss=0.3467, pruned_loss=0.09226, over 965742.95 frames.], batch size: 14, lr: 7.42e-04
2022-05-28 10:06:26,189 INFO [train.py:761] (5/8) Epoch 12, batch 1800, loss[loss=0.2778, simple_loss=0.3587, pruned_loss=0.09845, over 4972.00 frames.], tot_loss[loss=0.2639, simple_loss=0.3455, pruned_loss=0.09117, over 966210.00 frames.], batch size: 14, lr: 7.42e-04
2022-05-28 10:07:03,472 INFO [train.py:761] (5/8) Epoch 12, batch 1850, loss[loss=0.2157, simple_loss=0.3146, pruned_loss=0.05844, over 4836.00 frames.], tot_loss[loss=0.2642, simple_loss=0.3467, pruned_loss=0.09085, over 966179.64 frames.], batch size: 11, lr: 7.43e-04
2022-05-28 10:07:41,377 INFO [train.py:761] (5/8) Epoch 12, batch 1900, loss[loss=0.2138, simple_loss=0.2954, pruned_loss=0.06614, over 4878.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3451, pruned_loss=0.09011, over 965395.59 frames.], batch size: 12, lr: 7.43e-04
2022-05-28 10:08:19,753 INFO [train.py:761] (5/8) Epoch 12, batch 1950, loss[loss=0.2476, simple_loss=0.3473, pruned_loss=0.07394, over 4848.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3462, pruned_loss=0.09009, over 965655.15 frames.], batch size: 14, lr: 7.44e-04
2022-05-28 10:08:57,827 INFO [train.py:761] (5/8) Epoch 12, batch 2000, loss[loss=0.2242, simple_loss=0.2953, pruned_loss=0.07656, over 4992.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3459, pruned_loss=0.08978, over 966494.78 frames.], batch size: 11, lr: 7.44e-04
2022-05-28 10:09:35,230 INFO [train.py:761] (5/8) Epoch 12, batch 2050, loss[loss=0.2383, simple_loss=0.3411, pruned_loss=0.06777, over 4770.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3461, pruned_loss=0.08967, over 966397.07 frames.], batch size: 20, lr: 7.45e-04
2022-05-28 10:10:13,581 INFO [train.py:761] (5/8) Epoch 12, batch 2100, loss[loss=0.2718, simple_loss=0.3714, pruned_loss=0.08607, over 4968.00 frames.], tot_loss[loss=0.2622, simple_loss=0.3458, pruned_loss=0.08928, over 966333.62 frames.], batch size: 15, lr: 7.45e-04
2022-05-28 10:10:51,369 INFO [train.py:761] (5/8) Epoch 12, batch 2150, loss[loss=0.2431, simple_loss=0.3202, pruned_loss=0.083, over 4893.00 frames.], tot_loss[loss=0.2617, simple_loss=0.3454, pruned_loss=0.08902, over 965894.21 frames.], batch size: 12, lr: 7.46e-04
2022-05-28 10:11:29,876 INFO [train.py:761] (5/8) Epoch 12, batch 2200, loss[loss=0.2155, simple_loss=0.3218, pruned_loss=0.05463, over 4786.00 frames.], tot_loss[loss=0.2622, simple_loss=0.3455, pruned_loss=0.08942, over 966472.10 frames.], batch size: 14, lr: 7.46e-04
2022-05-28 10:12:08,034 INFO [train.py:761] (5/8) Epoch 12, batch 2250, loss[loss=0.234, simple_loss=0.32, pruned_loss=0.074, over 4864.00 frames.], tot_loss[loss=0.2653, simple_loss=0.3484, pruned_loss=0.09112, over 966340.19 frames.], batch size: 12, lr: 7.47e-04
2022-05-28 10:12:46,285 INFO [train.py:761] (5/8) Epoch 12, batch 2300, loss[loss=0.2323, simple_loss=0.3159, pruned_loss=0.07434, over 4988.00 frames.], tot_loss[loss=0.2658, simple_loss=0.3478, pruned_loss=0.09186, over 966751.63 frames.], batch size: 13, lr: 7.47e-04
2022-05-28 10:13:24,549 INFO [train.py:761] (5/8) Epoch 12, batch 2350, loss[loss=0.2443, simple_loss=0.329, pruned_loss=0.07984, over 4786.00 frames.], tot_loss[loss=0.2659, simple_loss=0.3475, pruned_loss=0.09217, over 966295.79 frames.], batch size: 14, lr: 7.48e-04
2022-05-28 10:14:02,760 INFO [train.py:761] (5/8) Epoch 12, batch 2400, loss[loss=0.2498, simple_loss=0.3242, pruned_loss=0.08767, over 4796.00 frames.], tot_loss[loss=0.2639, simple_loss=0.3454, pruned_loss=0.09127, over 966028.71 frames.], batch size: 13, lr: 7.48e-04
2022-05-28 10:14:40,330 INFO [train.py:761] (5/8) Epoch 12, batch 2450, loss[loss=0.3096, simple_loss=0.3943, pruned_loss=0.1125, over 4725.00 frames.], tot_loss[loss=0.2648, simple_loss=0.3463, pruned_loss=0.09172, over 966239.51 frames.], batch size: 13, lr: 7.49e-04
2022-05-28 10:15:18,589 INFO [train.py:761] (5/8) Epoch 12, batch 2500, loss[loss=0.2961, simple_loss=0.3747, pruned_loss=0.1087, over 4798.00 frames.], tot_loss[loss=0.2634, simple_loss=0.3446, pruned_loss=0.09112, over 965793.65 frames.], batch size: 20, lr: 7.49e-04
2022-05-28 10:15:56,277 INFO [train.py:761] (5/8) Epoch 12, batch 2550, loss[loss=0.2962, simple_loss=0.3653, pruned_loss=0.1136, over 4952.00 frames.], tot_loss[loss=0.262, simple_loss=0.3436, pruned_loss=0.09017, over 966726.88 frames.], batch size: 16, lr: 7.50e-04
2022-05-28 10:16:33,918 INFO [train.py:761] (5/8) Epoch 12, batch 2600, loss[loss=0.2819, simple_loss=0.3711, pruned_loss=0.09634, over 4794.00 frames.], tot_loss[loss=0.2611, simple_loss=0.343, pruned_loss=0.08961, over 966439.08 frames.], batch size: 16, lr: 7.50e-04
2022-05-28 10:17:11,790 INFO [train.py:761] (5/8) Epoch 12, batch 2650, loss[loss=0.3022, simple_loss=0.3773, pruned_loss=0.1136, over 4949.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3436, pruned_loss=0.08999, over 966220.98 frames.], batch size: 26, lr: 7.51e-04
2022-05-28 10:17:49,601 INFO [train.py:761] (5/8) Epoch 12, batch 2700, loss[loss=0.2011, simple_loss=0.2941, pruned_loss=0.0541, over 4973.00 frames.], tot_loss[loss=0.2612, simple_loss=0.3438, pruned_loss=0.0893, over 966664.18 frames.], batch size: 12, lr: 7.51e-04
2022-05-28 10:18:27,029 INFO [train.py:761] (5/8) Epoch 12, batch 2750, loss[loss=0.2309, simple_loss=0.329, pruned_loss=0.06643, over 4674.00 frames.], tot_loss[loss=0.2599, simple_loss=0.3423, pruned_loss=0.0888, over 966403.57 frames.], batch size: 13, lr: 7.52e-04
2022-05-28 10:19:05,007 INFO [train.py:761] (5/8) Epoch 12, batch 2800, loss[loss=0.2293, simple_loss=0.3087, pruned_loss=0.0749, over 4741.00 frames.], tot_loss[loss=0.26, simple_loss=0.3424, pruned_loss=0.08884, over 964524.20 frames.], batch size: 12, lr: 7.52e-04
2022-05-28 10:19:43,358 INFO [train.py:761] (5/8) Epoch 12, batch 2850, loss[loss=0.2809, simple_loss=0.3632, pruned_loss=0.09924, over 4832.00 frames.], tot_loss[loss=0.259, simple_loss=0.3416, pruned_loss=0.08821, over 965323.16 frames.], batch size: 18, lr: 7.53e-04
2022-05-28 10:20:22,073 INFO [train.py:761] (5/8) Epoch 12, batch 2900, loss[loss=0.2264, simple_loss=0.3283, pruned_loss=0.06229, over 4723.00 frames.], tot_loss[loss=0.2599, simple_loss=0.3425, pruned_loss=0.08869, over 964982.40 frames.], batch size: 14, lr: 7.53e-04
2022-05-28 10:21:00,088 INFO [train.py:761] (5/8) Epoch 12, batch 2950, loss[loss=0.2181, simple_loss=0.2892, pruned_loss=0.07348, over 4969.00 frames.], tot_loss[loss=0.2585, simple_loss=0.3416, pruned_loss=0.08772, over 965562.96 frames.], batch size: 12, lr: 7.53e-04
2022-05-28 10:21:38,307 INFO [train.py:761] (5/8) Epoch 12, batch 3000, loss[loss=0.2638, simple_loss=0.3476, pruned_loss=0.08995, over 4711.00 frames.], tot_loss[loss=0.2582, simple_loss=0.3411, pruned_loss=0.08769, over 965365.84 frames.], batch size: 14, lr: 7.54e-04
2022-05-28 10:21:38,307 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 10:21:48,263 INFO [train.py:790] (5/8) Epoch 12, validation: loss=0.2314, simple_loss=0.3336, pruned_loss=0.06464, over 944034.00 frames.
2022-05-28 10:22:26,360 INFO [train.py:761] (5/8) Epoch 12, batch 3050, loss[loss=0.3308, simple_loss=0.4078, pruned_loss=0.1269, over 4828.00 frames.], tot_loss[loss=0.2597, simple_loss=0.342, pruned_loss=0.08867, over 965116.97 frames.], batch size: 25, lr: 7.54e-04
2022-05-28 10:23:04,183 INFO [train.py:761] (5/8) Epoch 12, batch 3100, loss[loss=0.3533, simple_loss=0.4179, pruned_loss=0.1443, over 4676.00 frames.], tot_loss[loss=0.2615, simple_loss=0.3432, pruned_loss=0.08986, over 965138.06 frames.], batch size: 13, lr: 7.55e-04
2022-05-28 10:23:41,992 INFO [train.py:761] (5/8) Epoch 12, batch 3150, loss[loss=0.2511, simple_loss=0.354, pruned_loss=0.07409, over 4799.00 frames.], tot_loss[loss=0.2646, simple_loss=0.3452, pruned_loss=0.092, over 964269.48 frames.], batch size: 20, lr: 7.55e-04
2022-05-28 10:24:19,626 INFO [train.py:761] (5/8) Epoch 12, batch 3200, loss[loss=0.2576, simple_loss=0.3336, pruned_loss=0.09083, over 4790.00 frames.], tot_loss[loss=0.2698, simple_loss=0.3483, pruned_loss=0.09569, over 964169.26 frames.], batch size: 13, lr: 7.56e-04
2022-05-28 10:24:56,887 INFO [train.py:761] (5/8) Epoch 12, batch 3250, loss[loss=0.3151, simple_loss=0.3807, pruned_loss=0.1248, over 4776.00 frames.], tot_loss[loss=0.2738, simple_loss=0.3504, pruned_loss=0.09861, over 963368.68 frames.], batch size: 15, lr: 7.56e-04
2022-05-28 10:25:34,842 INFO [train.py:761] (5/8) Epoch 12, batch 3300, loss[loss=0.335, simple_loss=0.3878, pruned_loss=0.1411, over 4798.00 frames.], tot_loss[loss=0.2788, simple_loss=0.3531, pruned_loss=0.1022, over 963827.49 frames.], batch size: 16, lr: 7.57e-04
2022-05-28 10:26:13,109 INFO [train.py:761] (5/8) Epoch 12, batch 3350, loss[loss=0.2644, simple_loss=0.3441, pruned_loss=0.09234, over 4874.00 frames.], tot_loss[loss=0.2787, simple_loss=0.3523, pruned_loss=0.1025, over 963050.39 frames.], batch size: 18, lr: 7.57e-04
2022-05-28 10:26:51,731 INFO [train.py:761] (5/8) Epoch 12, batch 3400, loss[loss=0.3228, simple_loss=0.3867, pruned_loss=0.1294, over 4717.00 frames.], tot_loss[loss=0.28, simple_loss=0.3523, pruned_loss=0.1039, over 962857.12 frames.], batch size: 14, lr: 7.58e-04
2022-05-28 10:27:30,203 INFO [train.py:761] (5/8) Epoch 12, batch 3450, loss[loss=0.3607, simple_loss=0.4079, pruned_loss=0.1568, over 4948.00 frames.], tot_loss[loss=0.2821, simple_loss=0.3528, pruned_loss=0.1058, over 963801.45 frames.], batch size: 16, lr: 7.58e-04
2022-05-28 10:28:08,856 INFO [train.py:761] (5/8) Epoch 12, batch 3500, loss[loss=0.3186, simple_loss=0.3739, pruned_loss=0.1317, over 4783.00 frames.], tot_loss[loss=0.2828, simple_loss=0.3529, pruned_loss=0.1064, over 963328.50 frames.], batch size: 15, lr: 7.59e-04
2022-05-28 10:28:47,316 INFO [train.py:761] (5/8) Epoch 12, batch 3550, loss[loss=0.2953, simple_loss=0.3647, pruned_loss=0.113, over 4848.00 frames.], tot_loss[loss=0.2866, simple_loss=0.3551, pruned_loss=0.1091, over 964461.02 frames.], batch size: 18, lr: 7.59e-04
2022-05-28 10:29:24,578 INFO [train.py:761] (5/8) Epoch 12, batch 3600, loss[loss=0.2354, simple_loss=0.3048, pruned_loss=0.083, over 4976.00 frames.], tot_loss[loss=0.2866, simple_loss=0.3544, pruned_loss=0.1094, over 965981.97 frames.], batch size: 12, lr: 7.60e-04
2022-05-28 10:30:02,210 INFO [train.py:761] (5/8) Epoch 12, batch 3650, loss[loss=0.3184, simple_loss=0.3826, pruned_loss=0.1271, over 4966.00 frames.], tot_loss[loss=0.2907, simple_loss=0.3572, pruned_loss=0.1121, over 966117.44 frames.], batch size: 15, lr: 7.60e-04
2022-05-28 10:30:40,408 INFO [train.py:761] (5/8) Epoch 12, batch 3700, loss[loss=0.2883, simple_loss=0.3731, pruned_loss=0.1017, over 4796.00 frames.], tot_loss[loss=0.2924, simple_loss=0.3583, pruned_loss=0.1133, over 966061.61 frames.], batch size: 16, lr: 7.61e-04
2022-05-28 10:31:18,303 INFO [train.py:761] (5/8) Epoch 12, batch 3750, loss[loss=0.2677, simple_loss=0.3451, pruned_loss=0.09513, over 4784.00 frames.], tot_loss[loss=0.2933, simple_loss=0.3583, pruned_loss=0.1141, over 966602.92 frames.], batch size: 14, lr: 7.61e-04
2022-05-28 10:31:56,088 INFO [train.py:761] (5/8) Epoch 12, batch 3800, loss[loss=0.2833, simple_loss=0.3577, pruned_loss=0.1045, over 4946.00 frames.], tot_loss[loss=0.2939, simple_loss=0.3581, pruned_loss=0.1149, over 965887.73 frames.], batch size: 16, lr: 7.62e-04
2022-05-28 10:32:34,158 INFO [train.py:761] (5/8) Epoch 12, batch 3850, loss[loss=0.2478, simple_loss=0.3248, pruned_loss=0.08544, over 4980.00 frames.], tot_loss[loss=0.2937, simple_loss=0.3575, pruned_loss=0.115, over 965909.75 frames.], batch size: 12, lr: 7.62e-04
2022-05-28 10:33:12,316 INFO [train.py:761] (5/8) Epoch 12, batch 3900, loss[loss=0.2178, simple_loss=0.2895, pruned_loss=0.07304, over 4737.00 frames.], tot_loss[loss=0.2962, simple_loss=0.3599, pruned_loss=0.1162, over 965418.41 frames.], batch size: 11, lr: 7.63e-04
2022-05-28 10:33:50,678 INFO [train.py:761] (5/8) Epoch 12, batch 3950, loss[loss=0.2916, simple_loss=0.368, pruned_loss=0.1076, over 4804.00 frames.], tot_loss[loss=0.2947, simple_loss=0.3592, pruned_loss=0.1151, over 966440.71 frames.], batch size: 20, lr: 7.63e-04
2022-05-28 10:34:29,042 INFO [train.py:761] (5/8) Epoch 12, batch 4000, loss[loss=0.3, simple_loss=0.3762, pruned_loss=0.1119, over 4772.00 frames.], tot_loss[loss=0.2943, simple_loss=0.359, pruned_loss=0.1148, over 965632.06 frames.], batch size: 16, lr: 7.64e-04
2022-05-28 10:35:07,266 INFO [train.py:761] (5/8) Epoch 12, batch 4050, loss[loss=0.3397, simple_loss=0.3998, pruned_loss=0.1398, over 4838.00 frames.], tot_loss[loss=0.2946, simple_loss=0.3589, pruned_loss=0.1151, over 964242.82 frames.], batch size: 20, lr: 7.64e-04
2022-05-28 10:35:45,549 INFO [train.py:761] (5/8) Epoch 12, batch 4100, loss[loss=0.2436, simple_loss=0.3191, pruned_loss=0.08408, over 4848.00 frames.], tot_loss[loss=0.2938, simple_loss=0.3584, pruned_loss=0.1146, over 964649.65 frames.], batch size: 13, lr: 7.65e-04
2022-05-28 10:36:23,573 INFO [train.py:761] (5/8) Epoch 12, batch 4150, loss[loss=0.2948, simple_loss=0.3609, pruned_loss=0.1144, over 4910.00 frames.], tot_loss[loss=0.2934, simple_loss=0.3582, pruned_loss=0.1143, over 964346.63 frames.], batch size: 13, lr: 7.65e-04
2022-05-28 10:37:01,871 INFO [train.py:761] (5/8) Epoch 12, batch 4200, loss[loss=0.3006, simple_loss=0.3746, pruned_loss=0.1133, over 4976.00 frames.], tot_loss[loss=0.2935, simple_loss=0.3591, pruned_loss=0.114, over 965020.91 frames.], batch size: 14, lr: 7.66e-04
2022-05-28 10:37:39,621 INFO [train.py:761] (5/8) Epoch 12, batch 4250, loss[loss=0.2206, simple_loss=0.2932, pruned_loss=0.07395, over 4806.00 frames.], tot_loss[loss=0.2919, simple_loss=0.3575, pruned_loss=0.1131, over 965241.49 frames.], batch size: 12, lr: 7.66e-04
2022-05-28 10:38:18,303 INFO [train.py:761] (5/8) Epoch 12, batch 4300, loss[loss=0.3085, simple_loss=0.3599, pruned_loss=0.1285, over 4840.00 frames.], tot_loss[loss=0.2919, simple_loss=0.3572, pruned_loss=0.1134, over 965421.90 frames.], batch size: 26, lr: 7.67e-04
2022-05-28 10:38:56,717 INFO [train.py:761] (5/8) Epoch 12, batch 4350, loss[loss=0.2692, simple_loss=0.3319, pruned_loss=0.1033, over 4800.00 frames.], tot_loss[loss=0.2916, simple_loss=0.3572, pruned_loss=0.113, over 966003.98 frames.], batch size: 12, lr: 7.67e-04
2022-05-28 10:39:34,837 INFO [train.py:761] (5/8) Epoch 12, batch 4400, loss[loss=0.2919, simple_loss=0.3559, pruned_loss=0.1139, over 4790.00 frames.], tot_loss[loss=0.292, simple_loss=0.3579, pruned_loss=0.113, over 966819.23 frames.], batch size: 14, lr: 7.68e-04
2022-05-28 10:40:12,997 INFO [train.py:761] (5/8) Epoch 12, batch 4450, loss[loss=0.3323, simple_loss=0.3904, pruned_loss=0.1371, over 4841.00 frames.], tot_loss[loss=0.2928, simple_loss=0.3579, pruned_loss=0.1139, over 965999.78 frames.], batch size: 20, lr: 7.68e-04
2022-05-28 10:40:51,449 INFO [train.py:761] (5/8) Epoch 12, batch 4500, loss[loss=0.3229, simple_loss=0.3893, pruned_loss=0.1283, over 4947.00 frames.], tot_loss[loss=0.2957, simple_loss=0.36, pruned_loss=0.1157, over 965607.04 frames.], batch size: 52, lr: 7.69e-04
2022-05-28 10:41:28,902 INFO [train.py:761] (5/8) Epoch 12, batch 4550, loss[loss=0.2774, simple_loss=0.3285, pruned_loss=0.1132, over 4535.00 frames.], tot_loss[loss=0.2945, simple_loss=0.3592, pruned_loss=0.1149, over 965750.54 frames.], batch size: 10, lr: 7.69e-04
2022-05-28 10:42:08,011 INFO [train.py:761] (5/8) Epoch 12, batch 4600, loss[loss=0.2954, simple_loss=0.3697, pruned_loss=0.1105, over 4772.00 frames.], tot_loss[loss=0.2959, simple_loss=0.3604, pruned_loss=0.1157, over 966894.19 frames.], batch size: 15, lr: 7.70e-04
2022-05-28 10:42:45,885 INFO [train.py:761] (5/8) Epoch 12, batch 4650, loss[loss=0.2324, simple_loss=0.3015, pruned_loss=0.0816, over 4591.00 frames.], tot_loss[loss=0.295, simple_loss=0.3595, pruned_loss=0.1152, over 966363.56 frames.], batch size: 10, lr: 7.70e-04
2022-05-28 10:43:24,574 INFO [train.py:761] (5/8) Epoch 12, batch 4700, loss[loss=0.3096, simple_loss=0.3539, pruned_loss=0.1327, over 4987.00 frames.], tot_loss[loss=0.2976, simple_loss=0.3622, pruned_loss=0.1166, over 967012.70 frames.], batch size: 13, lr: 7.71e-04
2022-05-28 10:44:02,369 INFO [train.py:761] (5/8) Epoch 12, batch 4750, loss[loss=0.3137, simple_loss=0.3788, pruned_loss=0.1243, over 4976.00 frames.], tot_loss[loss=0.2994, simple_loss=0.3632, pruned_loss=0.1178, over 966762.81 frames.], batch size: 14, lr: 7.71e-04
2022-05-28 10:44:40,569 INFO [train.py:761] (5/8) Epoch 12, batch 4800, loss[loss=0.2823, simple_loss=0.3555, pruned_loss=0.1046, over 4670.00 frames.], tot_loss[loss=0.2975, simple_loss=0.3619, pruned_loss=0.1165, over 966546.39 frames.], batch size: 13, lr: 7.72e-04
2022-05-28 10:45:18,703 INFO [train.py:761] (5/8) Epoch 12, batch 4850, loss[loss=0.3678, simple_loss=0.4084, pruned_loss=0.1636, over 4878.00 frames.], tot_loss[loss=0.2954, simple_loss=0.36, pruned_loss=0.1154, over 966848.15 frames.], batch size: 17, lr: 7.72e-04
2022-05-28 10:45:57,544 INFO [train.py:761] (5/8) Epoch 12, batch 4900, loss[loss=0.2585, simple_loss=0.3295, pruned_loss=0.09378, over 4840.00 frames.], tot_loss[loss=0.2955, simple_loss=0.36, pruned_loss=0.1155, over 966441.12 frames.], batch size: 11, lr: 7.73e-04
2022-05-28 10:46:35,778 INFO [train.py:761] (5/8) Epoch 12, batch 4950, loss[loss=0.2985, simple_loss=0.3737, pruned_loss=0.1116, over 4987.00 frames.], tot_loss[loss=0.2936, simple_loss=0.3586, pruned_loss=0.1143, over 966414.47 frames.], batch size: 26, lr: 7.73e-04
2022-05-28 10:47:13,782 INFO [train.py:761] (5/8) Epoch 12, batch 5000, loss[loss=0.2798, simple_loss=0.3551, pruned_loss=0.1022, over 4845.00 frames.], tot_loss[loss=0.2922, simple_loss=0.3576, pruned_loss=0.1134, over 967024.25 frames.], batch size: 20, lr: 7.74e-04
2022-05-28 10:47:51,684 INFO [train.py:761] (5/8) Epoch 12, batch 5050, loss[loss=0.367, simple_loss=0.4193, pruned_loss=0.1574, over 4941.00 frames.], tot_loss[loss=0.2933, simple_loss=0.3586, pruned_loss=0.1139, over 965776.42 frames.], batch size: 45, lr: 7.74e-04
2022-05-28 10:48:29,914 INFO [train.py:761] (5/8) Epoch 12, batch 5100, loss[loss=0.35, simple_loss=0.3886, pruned_loss=0.1557, over 4661.00 frames.], tot_loss[loss=0.2911, simple_loss=0.3568, pruned_loss=0.1127, over 964561.28 frames.], batch size: 12, lr: 7.74e-04
2022-05-28 10:49:08,071 INFO [train.py:761] (5/8) Epoch 12, batch 5150, loss[loss=0.2865, simple_loss=0.3535, pruned_loss=0.1097, over 4979.00 frames.], tot_loss[loss=0.2901, simple_loss=0.3566, pruned_loss=0.1118, over 965590.25 frames.], batch size: 21, lr: 7.75e-04
2022-05-28 10:49:46,564 INFO [train.py:761] (5/8) Epoch 12, batch 5200, loss[loss=0.2606, simple_loss=0.3341, pruned_loss=0.09349, over 4720.00 frames.], tot_loss[loss=0.2908, simple_loss=0.3573, pruned_loss=0.1121, over 966035.25 frames.], batch size: 14, lr: 7.75e-04
2022-05-28 10:50:24,854 INFO [train.py:761] (5/8) Epoch 12, batch 5250, loss[loss=0.2737, simple_loss=0.3694, pruned_loss=0.08907, over 4882.00 frames.], tot_loss[loss=0.2906, simple_loss=0.3577, pruned_loss=0.1117, over 966209.32 frames.], batch size: 15, lr: 7.76e-04
2022-05-28 10:51:03,104 INFO [train.py:761] (5/8) Epoch 12, batch 5300, loss[loss=0.3512, simple_loss=0.4272, pruned_loss=0.1376, over 4928.00 frames.], tot_loss[loss=0.2928, simple_loss=0.3596, pruned_loss=0.113, over 967243.58 frames.], batch size: 43, lr: 7.76e-04
2022-05-28 10:51:41,852 INFO [train.py:761] (5/8) Epoch 12, batch 5350, loss[loss=0.3288, simple_loss=0.3865, pruned_loss=0.1356, over 4931.00 frames.], tot_loss[loss=0.2907, simple_loss=0.3578, pruned_loss=0.1118, over 966536.61 frames.], batch size: 47, lr: 7.77e-04
2022-05-28 10:52:20,171 INFO [train.py:761] (5/8) Epoch 12, batch 5400, loss[loss=0.2524, simple_loss=0.3215, pruned_loss=0.09166, over 4889.00 frames.], tot_loss[loss=0.2908, simple_loss=0.3576, pruned_loss=0.1119, over 966339.14 frames.], batch size: 12, lr: 7.77e-04
2022-05-28 10:52:58,568 INFO [train.py:761] (5/8) Epoch 12, batch 5450, loss[loss=0.2494, simple_loss=0.3281, pruned_loss=0.08538, over 4930.00 frames.], tot_loss[loss=0.2889, simple_loss=0.3559, pruned_loss=0.1109, over 965457.22 frames.], batch size: 13, lr: 7.78e-04
2022-05-28 10:53:37,425 INFO [train.py:761] (5/8) Epoch 12, batch 5500, loss[loss=0.2801, simple_loss=0.3625, pruned_loss=0.0988, over 4975.00 frames.], tot_loss[loss=0.2879, simple_loss=0.3552, pruned_loss=0.1103, over 964196.13 frames.], batch size: 14, lr: 7.78e-04
2022-05-28 10:54:15,926 INFO [train.py:761] (5/8) Epoch 12, batch 5550, loss[loss=0.3071, simple_loss=0.3824, pruned_loss=0.1159, over 4784.00 frames.], tot_loss[loss=0.2905, simple_loss=0.3571, pruned_loss=0.1119, over 964693.15 frames.], batch size: 20, lr: 7.79e-04
2022-05-28 10:54:54,898 INFO [train.py:761] (5/8) Epoch 12, batch 5600, loss[loss=0.2617, simple_loss=0.3441, pruned_loss=0.08967, over 4661.00 frames.], tot_loss[loss=0.2899, simple_loss=0.3564, pruned_loss=0.1117, over 964653.41 frames.], batch size: 12, lr: 7.79e-04
2022-05-28 10:55:32,839 INFO [train.py:761] (5/8) Epoch 12, batch 5650, loss[loss=0.2944, simple_loss=0.3642, pruned_loss=0.1123, over 4960.00 frames.], tot_loss[loss=0.2895, simple_loss=0.3557, pruned_loss=0.1117, over 965172.17 frames.], batch size: 16, lr: 7.80e-04
2022-05-28 10:56:11,552 INFO [train.py:761] (5/8) Epoch 12, batch 5700, loss[loss=0.3198, simple_loss=0.391, pruned_loss=0.1243, over 4972.00 frames.], tot_loss[loss=0.2891, simple_loss=0.3553, pruned_loss=0.1114, over 965877.05 frames.], batch size: 14, lr: 7.80e-04
2022-05-28 10:56:50,060 INFO [train.py:761] (5/8) Epoch 12, batch 5750, loss[loss=0.3326, simple_loss=0.3914, pruned_loss=0.1369, over 4674.00 frames.], tot_loss[loss=0.2898, simple_loss=0.3562, pruned_loss=0.1117, over 964900.86 frames.], batch size: 13, lr: 7.81e-04
2022-05-28 10:57:31,426 INFO [train.py:761] (5/8) Epoch 12, batch 5800, loss[loss=0.2465, simple_loss=0.305, pruned_loss=0.09398, over 4739.00 frames.], tot_loss[loss=0.29, simple_loss=0.3566, pruned_loss=0.1117, over 965057.64 frames.], batch size: 11, lr: 7.81e-04
2022-05-28 10:58:10,133 INFO [train.py:761] (5/8) Epoch 12, batch 5850, loss[loss=0.265, simple_loss=0.3222, pruned_loss=0.1039, over 4727.00 frames.], tot_loss[loss=0.29, simple_loss=0.3565, pruned_loss=0.1117, over 965169.98 frames.], batch size: 12, lr: 7.81e-04
2022-05-28 10:58:48,232 INFO [train.py:761] (5/8) Epoch 12, batch 5900, loss[loss=0.3018, simple_loss=0.3685, pruned_loss=0.1176, over 4781.00 frames.], tot_loss[loss=0.2858, simple_loss=0.353, pruned_loss=0.1093, over 965588.74 frames.], batch size: 16, lr: 7.81e-04
2022-05-28 10:59:26,247 INFO [train.py:761] (5/8) Epoch 12, batch 5950, loss[loss=0.3377, simple_loss=0.4094, pruned_loss=0.1331, over 4969.00 frames.], tot_loss[loss=0.2858, simple_loss=0.3532, pruned_loss=0.1093, over 965776.93 frames.], batch size: 16, lr: 7.80e-04
2022-05-28 11:00:04,348 INFO [train.py:761] (5/8) Epoch 12, batch 6000, loss[loss=0.2788, simple_loss=0.3537, pruned_loss=0.102, over 4949.00 frames.], tot_loss[loss=0.2881, simple_loss=0.3548, pruned_loss=0.1107, over 966342.75 frames.], batch size: 16, lr: 7.80e-04
2022-05-28 11:00:04,349 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 11:00:14,259 INFO [train.py:790] (5/8) Epoch 12, validation: loss=0.2223, simple_loss=0.3282, pruned_loss=0.05821, over 944034.00 frames.
2022-05-28 11:00:52,278 INFO [train.py:761] (5/8) Epoch 12, batch 6050, loss[loss=0.3032, simple_loss=0.3884, pruned_loss=0.1091, over 4876.00 frames.], tot_loss[loss=0.2884, simple_loss=0.3549, pruned_loss=0.111, over 966093.82 frames.], batch size: 15, lr: 7.80e-04
2022-05-28 11:01:30,701 INFO [train.py:761] (5/8) Epoch 12, batch 6100, loss[loss=0.2948, simple_loss=0.3652, pruned_loss=0.1122, over 4880.00 frames.], tot_loss[loss=0.2904, simple_loss=0.3566, pruned_loss=0.1121, over 966893.67 frames.], batch size: 17, lr: 7.80e-04
2022-05-28 11:02:08,643 INFO [train.py:761] (5/8) Epoch 12, batch 6150, loss[loss=0.2917, simple_loss=0.3562, pruned_loss=0.1136, over 4921.00 frames.], tot_loss[loss=0.2889, simple_loss=0.3552, pruned_loss=0.1113, over 967030.97 frames.], batch size: 17, lr: 7.80e-04
2022-05-28 11:02:47,116 INFO [train.py:761] (5/8) Epoch 12, batch 6200, loss[loss=0.2867, simple_loss=0.3535, pruned_loss=0.1099, over 4768.00 frames.], tot_loss[loss=0.2872, simple_loss=0.3545, pruned_loss=0.11, over 967660.41 frames.], batch size: 15, lr: 7.79e-04
2022-05-28 11:03:25,325 INFO [train.py:761] (5/8) Epoch 12, batch 6250, loss[loss=0.3059, simple_loss=0.3785, pruned_loss=0.1166, over 4788.00 frames.], tot_loss[loss=0.2874, simple_loss=0.3543, pruned_loss=0.1103, over 968312.17 frames.], batch size: 14, lr: 7.79e-04
2022-05-28 11:04:03,158 INFO [train.py:761] (5/8) Epoch 12, batch 6300, loss[loss=0.2611, simple_loss=0.3269, pruned_loss=0.09769, over 4662.00 frames.], tot_loss[loss=0.2869, simple_loss=0.3539, pruned_loss=0.1099, over 966742.06 frames.], batch size: 12, lr: 7.79e-04
2022-05-28 11:04:40,731 INFO [train.py:761] (5/8) Epoch 12, batch 6350, loss[loss=0.2233, simple_loss=0.2966, pruned_loss=0.07501, over 4831.00 frames.], tot_loss[loss=0.2869, simple_loss=0.3539, pruned_loss=0.11, over 966369.49 frames.], batch size: 11, lr: 7.79e-04
2022-05-28 11:05:19,305 INFO [train.py:761] (5/8) Epoch 12, batch 6400, loss[loss=0.2682, simple_loss=0.341, pruned_loss=0.09774, over 4913.00 frames.], tot_loss[loss=0.2886, simple_loss=0.3555, pruned_loss=0.1109, over 965541.01 frames.], batch size: 14, lr: 7.78e-04
2022-05-28 11:05:57,117 INFO [train.py:761] (5/8) Epoch 12, batch 6450, loss[loss=0.2479, simple_loss=0.326, pruned_loss=0.0849, over 4703.00 frames.], tot_loss[loss=0.2875, simple_loss=0.3547, pruned_loss=0.1102, over 965501.12 frames.], batch size: 14, lr: 7.78e-04
2022-05-28 11:06:35,750 INFO [train.py:761] (5/8) Epoch 12, batch 6500, loss[loss=0.2997, simple_loss=0.3503, pruned_loss=0.1245, over 4918.00 frames.], tot_loss[loss=0.2876, simple_loss=0.3551, pruned_loss=0.11, over 965548.32 frames.], batch size: 13, lr: 7.78e-04
2022-05-28 11:07:13,714 INFO [train.py:761] (5/8) Epoch 12, batch 6550, loss[loss=0.2479, simple_loss=0.3212, pruned_loss=0.08732, over 4882.00 frames.], tot_loss[loss=0.2864, simple_loss=0.3538, pruned_loss=0.1095, over 964647.99 frames.], batch size: 12, lr: 7.78e-04
2022-05-28 11:07:52,129 INFO [train.py:761] (5/8) Epoch 12, batch 6600, loss[loss=0.2543, simple_loss=0.3315, pruned_loss=0.0885, over 4767.00 frames.], tot_loss[loss=0.286, simple_loss=0.3531, pruned_loss=0.1094, over 966252.53 frames.], batch size: 20, lr: 7.77e-04
2022-05-28 11:08:30,182 INFO [train.py:761] (5/8) Epoch 12, batch 6650, loss[loss=0.2909, simple_loss=0.3702, pruned_loss=0.1058, over 4877.00 frames.], tot_loss[loss=0.2855, simple_loss=0.3528, pruned_loss=0.1091, over 966128.32 frames.], batch size: 17, lr: 7.77e-04
2022-05-28 11:09:09,056 INFO [train.py:761] (5/8) Epoch 12, batch 6700, loss[loss=0.2395, simple_loss=0.3272, pruned_loss=0.07586, over 4726.00 frames.], tot_loss[loss=0.2851, simple_loss=0.3528, pruned_loss=0.1087, over 965590.86 frames.], batch size: 12, lr: 7.77e-04
2022-05-28 11:10:03,615 INFO [train.py:761] (5/8) Epoch 13, batch 0, loss[loss=0.2639, simple_loss=0.3492, pruned_loss=0.08931, over 4787.00 frames.], tot_loss[loss=0.2639, simple_loss=0.3492, pruned_loss=0.08931, over 4787.00 frames.], batch size: 14, lr: 7.77e-04
2022-05-28 11:10:41,641 INFO [train.py:761] (5/8) Epoch 13, batch 50, loss[loss=0.3387, simple_loss=0.3965, pruned_loss=0.1404, over 4931.00 frames.], tot_loss[loss=0.2598, simple_loss=0.3394, pruned_loss=0.09005, over 218668.48 frames.], batch size: 46, lr: 7.76e-04
2022-05-28 11:11:19,504 INFO [train.py:761] (5/8) Epoch 13, batch 100, loss[loss=0.2236, simple_loss=0.3203, pruned_loss=0.06341, over 4669.00 frames.], tot_loss[loss=0.2548, simple_loss=0.3361, pruned_loss=0.08674, over 384226.42 frames.], batch size: 13, lr: 7.76e-04
2022-05-28 11:11:57,397 INFO [train.py:761] (5/8) Epoch 13, batch 150, loss[loss=0.2639, simple_loss=0.345, pruned_loss=0.09144, over 4850.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3343, pruned_loss=0.08541, over 513170.22 frames.], batch size: 14, lr: 7.76e-04
2022-05-28 11:12:36,087 INFO [train.py:761] (5/8) Epoch 13, batch 200, loss[loss=0.2606, simple_loss=0.3477, pruned_loss=0.08673, over 4976.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3341, pruned_loss=0.08545, over 613810.65 frames.], batch size: 14, lr: 7.76e-04
2022-05-28 11:13:13,839 INFO [train.py:761] (5/8) Epoch 13, batch 250, loss[loss=0.2282, simple_loss=0.3212, pruned_loss=0.06755, over 4670.00 frames.], tot_loss[loss=0.2515, simple_loss=0.3338, pruned_loss=0.08461, over 691395.57 frames.], batch size: 12, lr: 7.75e-04
2022-05-28 11:13:52,120 INFO [train.py:761] (5/8) Epoch 13, batch 300, loss[loss=0.2515, simple_loss=0.3412, pruned_loss=0.08088, over 4981.00 frames.], tot_loss[loss=0.2509, simple_loss=0.3334, pruned_loss=0.08422, over 752774.86 frames.], batch size: 15, lr: 7.75e-04
2022-05-28 11:14:37,356 INFO [train.py:761] (5/8) Epoch 13, batch 350, loss[loss=0.2371, simple_loss=0.3314, pruned_loss=0.07135, over 4886.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3346, pruned_loss=0.08389, over 800739.06 frames.], batch size: 15, lr: 7.75e-04
2022-05-28 11:15:14,737 INFO [train.py:761] (5/8) Epoch 13, batch 400, loss[loss=0.2553, simple_loss=0.3224, pruned_loss=0.09407, over 4855.00 frames.], tot_loss[loss=0.2505, simple_loss=0.334, pruned_loss=0.08348, over 837339.62 frames.], batch size: 11, lr: 7.75e-04
2022-05-28 11:15:52,964 INFO [train.py:761] (5/8) Epoch 13, batch 450, loss[loss=0.2388, simple_loss=0.3264, pruned_loss=0.07566, over 4979.00 frames.], tot_loss[loss=0.252, simple_loss=0.3353, pruned_loss=0.08436, over 867031.09 frames.], batch size: 15, lr: 7.74e-04
2022-05-28 11:16:31,008 INFO [train.py:761] (5/8) Epoch 13, batch 500, loss[loss=0.2448, simple_loss=0.3253, pruned_loss=0.08217, over 4785.00 frames.], tot_loss[loss=0.251, simple_loss=0.3351, pruned_loss=0.0835, over 888655.08 frames.], batch size: 14, lr: 7.74e-04
2022-05-28 11:17:08,583 INFO [train.py:761] (5/8) Epoch 13, batch 550, loss[loss=0.3156, simple_loss=0.3853, pruned_loss=0.123, over 4849.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3349, pruned_loss=0.0834, over 906356.08 frames.], batch size: 14, lr: 7.74e-04
2022-05-28 11:17:47,175 INFO [train.py:761] (5/8) Epoch 13, batch 600, loss[loss=0.2904, simple_loss=0.3685, pruned_loss=0.1061, over 4782.00 frames.], tot_loss[loss=0.2513, simple_loss=0.3359, pruned_loss=0.08336, over 919142.76 frames.], batch size: 16, lr: 7.74e-04
2022-05-28 11:18:25,228 INFO [train.py:761] (5/8) Epoch 13, batch 650, loss[loss=0.2879, simple_loss=0.3776, pruned_loss=0.09909, over 4974.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3375, pruned_loss=0.08449, over 929906.78 frames.], batch size: 15, lr: 7.74e-04
2022-05-28 11:19:03,276 INFO [train.py:761] (5/8) Epoch 13, batch 700, loss[loss=0.2971, simple_loss=0.3616, pruned_loss=0.1163, over 4893.00 frames.], tot_loss[loss=0.2552, simple_loss=0.3393, pruned_loss=0.08552, over 938899.97 frames.], batch size: 18, lr: 7.73e-04
2022-05-28 11:19:40,713 INFO [train.py:761] (5/8) Epoch 13, batch 750, loss[loss=0.27, simple_loss=0.3505, pruned_loss=0.09473, over 4807.00 frames.], tot_loss[loss=0.2558, simple_loss=0.3397, pruned_loss=0.08595, over 944886.49 frames.], batch size: 12, lr: 7.73e-04
2022-05-28 11:20:19,321 INFO [train.py:761] (5/8) Epoch 13, batch 800, loss[loss=0.2821, simple_loss=0.3459, pruned_loss=0.1091, over 4849.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3395, pruned_loss=0.08644, over 949919.40 frames.], batch size: 13, lr: 7.73e-04
2022-05-28 11:20:57,298 INFO [train.py:761] (5/8) Epoch 13, batch 850, loss[loss=0.2738, simple_loss=0.3528, pruned_loss=0.09743, over 4787.00 frames.], tot_loss[loss=0.2572, simple_loss=0.3399, pruned_loss=0.08728, over 952813.09 frames.], batch size: 14, lr: 7.73e-04
2022-05-28 11:21:35,469 INFO [train.py:761] (5/8) Epoch 13, batch 900, loss[loss=0.2658, simple_loss=0.3573, pruned_loss=0.08718, over 4977.00 frames.], tot_loss[loss=0.2592, simple_loss=0.3417, pruned_loss=0.08835, over 956078.28 frames.], batch size: 14, lr: 7.72e-04
2022-05-28 11:22:13,521 INFO [train.py:761] (5/8) Epoch 13, batch 950, loss[loss=0.3148, simple_loss=0.3844, pruned_loss=0.1226, over 4931.00 frames.], tot_loss[loss=0.2586, simple_loss=0.341, pruned_loss=0.08809, over 958627.11 frames.], batch size: 46, lr: 7.72e-04
2022-05-28 11:22:51,449 INFO [train.py:761] (5/8) Epoch 13, batch 1000, loss[loss=0.2492, simple_loss=0.3408, pruned_loss=0.07877, over 4788.00 frames.], tot_loss[loss=0.2577, simple_loss=0.3404, pruned_loss=0.08752, over 961441.19 frames.], batch size: 14, lr: 7.72e-04
2022-05-28 11:23:28,950 INFO [train.py:761] (5/8) Epoch 13, batch 1050, loss[loss=0.2698, simple_loss=0.3514, pruned_loss=0.0941, over 4614.00 frames.], tot_loss[loss=0.2586, simple_loss=0.341, pruned_loss=0.08808, over 963429.64 frames.], batch size: 12, lr: 7.72e-04
2022-05-28 11:24:06,599 INFO [train.py:761] (5/8) Epoch 13, batch 1100, loss[loss=0.2368, simple_loss=0.324, pruned_loss=0.07487, over 4723.00 frames.], tot_loss[loss=0.2599, simple_loss=0.342, pruned_loss=0.08893, over 963629.67 frames.], batch size: 13, lr: 7.71e-04
2022-05-28 11:24:44,897 INFO [train.py:761] (5/8) Epoch 13, batch 1150, loss[loss=0.287, simple_loss=0.3584, pruned_loss=0.1078, over 4786.00 frames.], tot_loss[loss=0.2582, simple_loss=0.3405, pruned_loss=0.08796, over 964048.74 frames.], batch size: 13, lr: 7.71e-04
2022-05-28 11:25:22,910 INFO [train.py:761] (5/8) Epoch 13, batch 1200, loss[loss=0.2336, simple_loss=0.3085, pruned_loss=0.07938, over 4827.00 frames.], tot_loss[loss=0.2591, simple_loss=0.341, pruned_loss=0.08864, over 964660.04 frames.], batch size: 11, lr: 7.71e-04
2022-05-28 11:26:00,869 INFO [train.py:761] (5/8) Epoch 13, batch 1250, loss[loss=0.2546, simple_loss=0.3468, pruned_loss=0.08124, over 4842.00 frames.], tot_loss[loss=0.2585, simple_loss=0.3401, pruned_loss=0.08841, over 964180.73 frames.], batch size: 14, lr: 7.71e-04
2022-05-28 11:26:39,507 INFO [train.py:761] (5/8) Epoch 13, batch 1300, loss[loss=0.2624, simple_loss=0.3541, pruned_loss=0.08541, over 4707.00 frames.], tot_loss[loss=0.258, simple_loss=0.3401, pruned_loss=0.088, over 965617.55 frames.], batch size: 14, lr: 7.70e-04
2022-05-28 11:27:17,186 INFO [train.py:761] (5/8) Epoch 13, batch 1350, loss[loss=0.2581, simple_loss=0.3518, pruned_loss=0.08216, over 4893.00 frames.], tot_loss[loss=0.2583, simple_loss=0.3401, pruned_loss=0.08824, over 965296.78 frames.], batch size: 17, lr: 7.70e-04
2022-05-28 11:27:55,182 INFO [train.py:761] (5/8) Epoch 13, batch 1400, loss[loss=0.2574, simple_loss=0.3504, pruned_loss=0.08216, over 4905.00 frames.], tot_loss[loss=0.2604, simple_loss=0.3424, pruned_loss=0.08922, over 965943.79 frames.], batch size: 14, lr: 7.70e-04
2022-05-28 11:28:32,700 INFO [train.py:761] (5/8) Epoch 13, batch 1450, loss[loss=0.2604, simple_loss=0.343, pruned_loss=0.08884, over 4886.00 frames.], tot_loss[loss=0.2602, simple_loss=0.3419, pruned_loss=0.08926, over 965947.97 frames.], batch size: 12, lr: 7.70e-04
2022-05-28 11:29:10,548 INFO [train.py:761] (5/8) Epoch 13, batch 1500, loss[loss=0.2437, simple_loss=0.3253, pruned_loss=0.08105, over 4814.00 frames.], tot_loss[loss=0.2596, simple_loss=0.3408, pruned_loss=0.0892, over 965796.53 frames.], batch size: 12, lr: 7.70e-04
2022-05-28 11:29:48,929 INFO [train.py:761] (5/8) Epoch 13, batch 1550, loss[loss=0.2997, simple_loss=0.3938, pruned_loss=0.1028, over 4716.00 frames.], tot_loss[loss=0.2601, simple_loss=0.3417, pruned_loss=0.08922, over 966646.09 frames.], batch size: 14, lr: 7.69e-04
2022-05-28 11:30:27,037 INFO [train.py:761] (5/8) Epoch 13, batch 1600, loss[loss=0.2287, simple_loss=0.3229, pruned_loss=0.06723, over 4790.00 frames.], tot_loss[loss=0.2592, simple_loss=0.3414, pruned_loss=0.08847, over 966442.30 frames.], batch size: 14, lr: 7.69e-04
2022-05-28 11:31:04,703 INFO [train.py:761] (5/8) Epoch 13, batch 1650, loss[loss=0.2229, simple_loss=0.2947, pruned_loss=0.0756, over 4636.00 frames.], tot_loss[loss=0.2594, simple_loss=0.3419, pruned_loss=0.08844, over 967295.30 frames.], batch size: 11, lr: 7.69e-04
2022-05-28 11:31:42,871 INFO [train.py:761] (5/8) Epoch 13, batch 1700, loss[loss=0.2309, simple_loss=0.298, pruned_loss=0.08193, over 4715.00 frames.], tot_loss[loss=0.2606, simple_loss=0.3428, pruned_loss=0.08919, over 966934.66 frames.], batch size: 11, lr: 7.69e-04
2022-05-28 11:32:20,820 INFO [train.py:761] (5/8) Epoch 13, batch 1750, loss[loss=0.2678, simple_loss=0.3578, pruned_loss=0.08895, over 4835.00 frames.], tot_loss[loss=0.2596, simple_loss=0.3418, pruned_loss=0.08866, over 967211.09 frames.], batch size: 18, lr: 7.68e-04
2022-05-28 11:32:58,774 INFO [train.py:761] (5/8) Epoch 13, batch 1800, loss[loss=0.2526, simple_loss=0.3445, pruned_loss=0.08033, over 4727.00 frames.], tot_loss[loss=0.258, simple_loss=0.3399, pruned_loss=0.08809, over 966588.24 frames.], batch size: 14, lr: 7.68e-04
2022-05-28 11:33:36,234 INFO [train.py:761] (5/8) Epoch 13, batch 1850, loss[loss=0.2034, simple_loss=0.2883, pruned_loss=0.05925, over 4798.00 frames.], tot_loss[loss=0.2579, simple_loss=0.3402, pruned_loss=0.08774, over 968150.31 frames.], batch size: 12, lr: 7.68e-04
2022-05-28 11:34:14,679 INFO [train.py:761] (5/8) Epoch 13, batch 1900, loss[loss=0.2525, simple_loss=0.3362, pruned_loss=0.08441, over 4957.00 frames.], tot_loss[loss=0.2565, simple_loss=0.3391, pruned_loss=0.08701, over 968400.43 frames.], batch size: 16, lr: 7.68e-04
2022-05-28 11:34:52,302 INFO [train.py:761] (5/8) Epoch 13, batch 1950, loss[loss=0.2598, simple_loss=0.3423, pruned_loss=0.08864, over 4779.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3379, pruned_loss=0.08612, over 966295.46 frames.], batch size: 15, lr: 7.67e-04
2022-05-28 11:35:29,924 INFO [train.py:761] (5/8) Epoch 13, batch 2000, loss[loss=0.3015, simple_loss=0.3768, pruned_loss=0.1132, over 4780.00 frames.], tot_loss[loss=0.2538, simple_loss=0.3362, pruned_loss=0.08569, over 965867.37 frames.], batch size: 16, lr: 7.67e-04
2022-05-28 11:36:07,615 INFO [train.py:761] (5/8) Epoch 13, batch 2050, loss[loss=0.3138, simple_loss=0.3919, pruned_loss=0.1178, over 4908.00 frames.], tot_loss[loss=0.2554, simple_loss=0.338, pruned_loss=0.08633, over 966417.90 frames.], batch size: 44, lr: 7.67e-04
2022-05-28 11:36:45,688 INFO [train.py:761] (5/8) Epoch 13, batch 2100, loss[loss=0.2175, simple_loss=0.3024, pruned_loss=0.06633, over 4976.00 frames.], tot_loss[loss=0.2547, simple_loss=0.3375, pruned_loss=0.08592, over 967362.81 frames.], batch size: 12, lr: 7.67e-04
2022-05-28 11:37:24,555 INFO [train.py:761] (5/8) Epoch 13, batch 2150, loss[loss=0.2686, simple_loss=0.3427, pruned_loss=0.09731, over 4972.00 frames.], tot_loss[loss=0.2544, simple_loss=0.3373, pruned_loss=0.08573, over 967066.93 frames.], batch size: 16, lr: 7.67e-04
2022-05-28 11:38:03,069 INFO [train.py:761] (5/8) Epoch 13, batch 2200, loss[loss=0.2535, simple_loss=0.3583, pruned_loss=0.07433, over 4917.00 frames.], tot_loss[loss=0.2539, simple_loss=0.3368, pruned_loss=0.08552, over 968238.19 frames.], batch size: 14, lr: 7.66e-04
2022-05-28 11:38:41,258 INFO [train.py:761] (5/8) Epoch 13, batch 2250, loss[loss=0.2287, simple_loss=0.3296, pruned_loss=0.06396, over 4788.00 frames.], tot_loss[loss=0.2549, simple_loss=0.3377, pruned_loss=0.08607, over 967963.99 frames.], batch size: 13, lr: 7.66e-04
2022-05-28 11:39:19,640 INFO [train.py:761] (5/8) Epoch 13, batch 2300, loss[loss=0.258, simple_loss=0.3463, pruned_loss=0.08486, over 4908.00 frames.], tot_loss[loss=0.2552, simple_loss=0.3381, pruned_loss=0.08612, over 967459.56 frames.], batch size: 13, lr: 7.66e-04
2022-05-28 11:39:57,445 INFO [train.py:761] (5/8) Epoch 13, batch 2350, loss[loss=0.2137, simple_loss=0.3038, pruned_loss=0.06181, over 4910.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3363, pruned_loss=0.08509, over 965877.40 frames.], batch size: 13, lr: 7.66e-04
2022-05-28 11:40:42,916 INFO [train.py:761] (5/8) Epoch 13, batch 2400, loss[loss=0.1953, simple_loss=0.2836, pruned_loss=0.05348, over 4823.00 frames.], tot_loss[loss=0.2531, simple_loss=0.3365, pruned_loss=0.08483, over 965521.39 frames.], batch size: 11, lr: 7.65e-04
2022-05-28 11:41:20,790 INFO [train.py:761] (5/8) Epoch 13, batch 2450, loss[loss=0.2245, simple_loss=0.3233, pruned_loss=0.06278, over 4847.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3362, pruned_loss=0.08441, over 965299.25 frames.], batch size: 14, lr: 7.65e-04
2022-05-28 11:42:06,034 INFO [train.py:761] (5/8) Epoch 13, batch 2500, loss[loss=0.2228, simple_loss=0.3139, pruned_loss=0.06585, over 4882.00 frames.], tot_loss[loss=0.2529, simple_loss=0.3366, pruned_loss=0.08461, over 965886.03 frames.], batch size: 15, lr: 7.65e-04
2022-05-28 11:42:51,196 INFO [train.py:761] (5/8) Epoch 13, batch 2550, loss[loss=0.2527, simple_loss=0.3527, pruned_loss=0.0763, over 4794.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3374, pruned_loss=0.085, over 965683.65 frames.], batch size: 16, lr: 7.65e-04
2022-05-28 11:43:36,751 INFO [train.py:761] (5/8) Epoch 13, batch 2600, loss[loss=0.2273, simple_loss=0.309, pruned_loss=0.07284, over 4815.00 frames.], tot_loss[loss=0.2545, simple_loss=0.3381, pruned_loss=0.08544, over 966541.01 frames.], batch size: 12, lr: 7.64e-04
2022-05-28 11:44:14,697 INFO [train.py:761] (5/8) Epoch 13, batch 2650, loss[loss=0.2064, simple_loss=0.2948, pruned_loss=0.05897, over 4721.00 frames.], tot_loss[loss=0.2536, simple_loss=0.3375, pruned_loss=0.08481, over 966273.81 frames.], batch size: 11, lr: 7.64e-04
2022-05-28 11:44:52,579 INFO [train.py:761] (5/8) Epoch 13, batch 2700, loss[loss=0.2198, simple_loss=0.2935, pruned_loss=0.07307, over 4641.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3369, pruned_loss=0.08431, over 965661.02 frames.], batch size: 11, lr: 7.64e-04
2022-05-28 11:45:38,060 INFO [train.py:761] (5/8) Epoch 13, batch 2750, loss[loss=0.2257, simple_loss=0.3258, pruned_loss=0.06282, over 4853.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3358, pruned_loss=0.08346, over 966039.31 frames.], batch size: 14, lr: 7.64e-04
2022-05-28 11:46:15,553 INFO [train.py:761] (5/8) Epoch 13, batch 2800, loss[loss=0.2504, simple_loss=0.3299, pruned_loss=0.08549, over 4736.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3352, pruned_loss=0.08381, over 965973.62 frames.], batch size: 11, lr: 7.64e-04
2022-05-28 11:46:53,604 INFO [train.py:761] (5/8) Epoch 13, batch 2850, loss[loss=0.2983, simple_loss=0.3874, pruned_loss=0.1046, over 4714.00 frames.], tot_loss[loss=0.251, simple_loss=0.3351, pruned_loss=0.0835, over 965867.90 frames.], batch size: 14, lr: 7.63e-04
2022-05-28 11:47:38,646 INFO [train.py:761] (5/8) Epoch 13, batch 2900, loss[loss=0.1904, simple_loss=0.273, pruned_loss=0.05389, over 4634.00 frames.], tot_loss[loss=0.2509, simple_loss=0.3352, pruned_loss=0.08331, over 966295.30 frames.], batch size: 11, lr: 7.63e-04
2022-05-28 11:48:16,574 INFO [train.py:761] (5/8) Epoch 13, batch 2950, loss[loss=0.2545, simple_loss=0.3456, pruned_loss=0.08176, over 4848.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3371, pruned_loss=0.08409, over 967045.75 frames.], batch size: 13, lr: 7.63e-04
2022-05-28 11:48:54,316 INFO [train.py:761] (5/8) Epoch 13, batch 3000, loss[loss=0.3056, simple_loss=0.389, pruned_loss=0.1111, over 4802.00 frames.], tot_loss[loss=0.2539, simple_loss=0.3384, pruned_loss=0.08473, over 966687.92 frames.], batch size: 18, lr: 7.63e-04
2022-05-28 11:48:54,317 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 11:49:04,602 INFO [train.py:790] (5/8) Epoch 13, validation: loss=0.228, simple_loss=0.3294, pruned_loss=0.06337, over 944034.00 frames.
2022-05-28 11:49:42,255 INFO [train.py:761] (5/8) Epoch 13, batch 3050, loss[loss=0.1984, simple_loss=0.2957, pruned_loss=0.05054, over 4853.00 frames.], tot_loss[loss=0.2549, simple_loss=0.339, pruned_loss=0.08539, over 966568.15 frames.], batch size: 13, lr: 7.62e-04
2022-05-28 11:50:21,434 INFO [train.py:761] (5/8) Epoch 13, batch 3100, loss[loss=0.2201, simple_loss=0.3062, pruned_loss=0.06704, over 4737.00 frames.], tot_loss[loss=0.2564, simple_loss=0.339, pruned_loss=0.08692, over 966337.70 frames.], batch size: 12, lr: 7.62e-04
2022-05-28 11:50:59,023 INFO [train.py:761] (5/8) Epoch 13, batch 3150, loss[loss=0.2457, simple_loss=0.3331, pruned_loss=0.07909, over 4920.00 frames.], tot_loss[loss=0.2587, simple_loss=0.34, pruned_loss=0.08865, over 966054.32 frames.], batch size: 13, lr: 7.62e-04
2022-05-28 11:51:36,948 INFO [train.py:761] (5/8) Epoch 13, batch 3200, loss[loss=0.2866, simple_loss=0.3434, pruned_loss=0.1149, over 4786.00 frames.], tot_loss[loss=0.263, simple_loss=0.343, pruned_loss=0.09148, over 965727.88 frames.], batch size: 13, lr: 7.62e-04
2022-05-28 11:52:15,572 INFO [train.py:761] (5/8) Epoch 13, batch 3250, loss[loss=0.2464, simple_loss=0.3073, pruned_loss=0.09273, over 4536.00 frames.], tot_loss[loss=0.2653, simple_loss=0.3434, pruned_loss=0.09363, over 966311.81 frames.], batch size: 10, lr: 7.62e-04
2022-05-28 11:53:00,966 INFO [train.py:761] (5/8) Epoch 13, batch 3300, loss[loss=0.2483, simple_loss=0.3305, pruned_loss=0.08307, over 4847.00 frames.], tot_loss[loss=0.2698, simple_loss=0.3458, pruned_loss=0.09687, over 966202.87 frames.], batch size: 13, lr: 7.61e-04
2022-05-28 11:53:38,838 INFO [train.py:761] (5/8) Epoch 13, batch 3350, loss[loss=0.2904, simple_loss=0.3472, pruned_loss=0.1168, over 4986.00 frames.], tot_loss[loss=0.2715, simple_loss=0.3461, pruned_loss=0.09848, over 965683.66 frames.], batch size: 13, lr: 7.61e-04
2022-05-28 11:54:17,338 INFO [train.py:761] (5/8) Epoch 13, batch 3400, loss[loss=0.2606, simple_loss=0.3247, pruned_loss=0.09823, over 4812.00 frames.], tot_loss[loss=0.2748, simple_loss=0.3475, pruned_loss=0.101, over 966530.83 frames.], batch size: 12, lr: 7.61e-04
2022-05-28 11:54:56,144 INFO [train.py:761] (5/8) Epoch 13, batch 3450, loss[loss=0.2097, simple_loss=0.2992, pruned_loss=0.06006, over 4850.00 frames.], tot_loss[loss=0.2776, simple_loss=0.3492, pruned_loss=0.103, over 967498.04 frames.], batch size: 13, lr: 7.61e-04
2022-05-28 11:55:34,263 INFO [train.py:761] (5/8) Epoch 13, batch 3500, loss[loss=0.2917, simple_loss=0.3597, pruned_loss=0.1119, over 4980.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3487, pruned_loss=0.1037, over 967634.50 frames.], batch size: 13, lr: 7.60e-04
2022-05-28 11:56:11,947 INFO [train.py:761] (5/8) Epoch 13, batch 3550, loss[loss=0.311, simple_loss=0.3758, pruned_loss=0.1231, over 4780.00 frames.], tot_loss[loss=0.2784, simple_loss=0.3484, pruned_loss=0.1042, over 966345.92 frames.], batch size: 16, lr: 7.60e-04
2022-05-28 11:56:50,541 INFO [train.py:761] (5/8) Epoch 13, batch 3600, loss[loss=0.298, simple_loss=0.3634, pruned_loss=0.1164, over 4769.00 frames.], tot_loss[loss=0.2814, simple_loss=0.3507, pruned_loss=0.1061, over 967004.79 frames.], batch size: 16, lr: 7.60e-04
2022-05-28 11:57:28,646 INFO [train.py:761] (5/8) Epoch 13, batch 3650, loss[loss=0.275, simple_loss=0.3535, pruned_loss=0.09827, over 4960.00 frames.], tot_loss[loss=0.2838, simple_loss=0.3519, pruned_loss=0.1078, over 966018.27 frames.], batch size: 16, lr: 7.60e-04
2022-05-28 11:58:07,025 INFO [train.py:761] (5/8) Epoch 13, batch 3700, loss[loss=0.2562, simple_loss=0.3282, pruned_loss=0.09205, over 4980.00 frames.], tot_loss[loss=0.2843, simple_loss=0.3518, pruned_loss=0.1084, over 965778.97 frames.], batch size: 13, lr: 7.59e-04
2022-05-28 11:58:44,720 INFO [train.py:761] (5/8) Epoch 13, batch 3750, loss[loss=0.278, simple_loss=0.3387, pruned_loss=0.1086, over 4784.00 frames.], tot_loss[loss=0.2851, simple_loss=0.352, pruned_loss=0.1091, over 965910.32 frames.], batch size: 14, lr: 7.59e-04
2022-05-28 11:59:23,318 INFO [train.py:761] (5/8) Epoch 13, batch 3800, loss[loss=0.3797, simple_loss=0.4253, pruned_loss=0.167, over 4671.00 frames.], tot_loss[loss=0.2862, simple_loss=0.3529, pruned_loss=0.1098, over 965776.92 frames.], batch size: 13, lr: 7.59e-04
2022-05-28 12:00:01,650 INFO [train.py:761] (5/8) Epoch 13, batch 3850, loss[loss=0.254, simple_loss=0.35, pruned_loss=0.07898, over 4716.00 frames.], tot_loss[loss=0.2846, simple_loss=0.3515, pruned_loss=0.1089, over 965621.26 frames.], batch size: 14, lr: 7.59e-04
2022-05-28 12:00:39,487 INFO [train.py:761] (5/8) Epoch 13, batch 3900, loss[loss=0.3042, simple_loss=0.3826, pruned_loss=0.1129, over 4944.00 frames.], tot_loss[loss=0.2851, simple_loss=0.3516, pruned_loss=0.1094, over 965429.30 frames.], batch size: 16, lr: 7.59e-04
2022-05-28 12:01:17,758 INFO [train.py:761] (5/8) Epoch 13, batch 3950, loss[loss=0.3471, simple_loss=0.3962, pruned_loss=0.149, over 4913.00 frames.], tot_loss[loss=0.2857, simple_loss=0.3519, pruned_loss=0.1098, over 965240.71 frames.], batch size: 49, lr: 7.58e-04
2022-05-28 12:01:55,802 INFO [train.py:761] (5/8) Epoch 13, batch 4000, loss[loss=0.2305, simple_loss=0.3278, pruned_loss=0.06666, over 4721.00 frames.], tot_loss[loss=0.2875, simple_loss=0.3535, pruned_loss=0.1107, over 965412.48 frames.], batch size: 14, lr: 7.58e-04
2022-05-28 12:02:34,621 INFO [train.py:761] (5/8) Epoch 13, batch 4050, loss[loss=0.3063, simple_loss=0.3724, pruned_loss=0.1201, over 4876.00 frames.], tot_loss[loss=0.2856, simple_loss=0.3522, pruned_loss=0.1095, over 965441.55 frames.], batch size: 15, lr: 7.58e-04
2022-05-28 12:03:13,153 INFO [train.py:761] (5/8) Epoch 13, batch 4100, loss[loss=0.212, simple_loss=0.2954, pruned_loss=0.06434, over 4912.00 frames.], tot_loss[loss=0.2865, simple_loss=0.3529, pruned_loss=0.1101, over 965753.61 frames.], batch size: 14, lr: 7.58e-04
2022-05-28 12:03:50,699 INFO [train.py:761] (5/8) Epoch 13, batch 4150, loss[loss=0.2488, simple_loss=0.3027, pruned_loss=0.09745, over 4852.00 frames.], tot_loss[loss=0.2851, simple_loss=0.3517, pruned_loss=0.1092, over 965877.05 frames.], batch size: 11, lr: 7.57e-04
2022-05-28 12:04:29,253 INFO [train.py:761] (5/8) Epoch 13, batch 4200, loss[loss=0.2666, simple_loss=0.3514, pruned_loss=0.09087, over 4858.00 frames.], tot_loss[loss=0.2839, simple_loss=0.3515, pruned_loss=0.1082, over 966597.65 frames.], batch size: 13, lr: 7.57e-04
2022-05-28 12:05:07,291 INFO [train.py:761] (5/8) Epoch 13, batch 4250, loss[loss=0.2356, simple_loss=0.2976, pruned_loss=0.08681, over 4804.00 frames.], tot_loss[loss=0.2822, simple_loss=0.3503, pruned_loss=0.107, over 966751.90 frames.], batch size: 12, lr: 7.57e-04
2022-05-28 12:05:45,464 INFO [train.py:761] (5/8) Epoch 13, batch 4300, loss[loss=0.2431, simple_loss=0.3082, pruned_loss=0.08897, over 4671.00 frames.], tot_loss[loss=0.2822, simple_loss=0.3503, pruned_loss=0.1071, over 966614.44 frames.], batch size: 12, lr: 7.57e-04
2022-05-28 12:06:23,820 INFO [train.py:761] (5/8) Epoch 13, batch 4350, loss[loss=0.2317, simple_loss=0.306, pruned_loss=0.07872, over 4550.00 frames.], tot_loss[loss=0.2846, simple_loss=0.3518, pruned_loss=0.1087, over 966505.27 frames.], batch size: 10, lr: 7.57e-04
2022-05-28 12:07:02,057 INFO [train.py:761] (5/8) Epoch 13, batch 4400, loss[loss=0.2564, simple_loss=0.3258, pruned_loss=0.09349, over 4809.00 frames.], tot_loss[loss=0.2836, simple_loss=0.3509, pruned_loss=0.1081, over 966032.31 frames.], batch size: 12, lr: 7.56e-04
2022-05-28 12:07:39,476 INFO [train.py:761] (5/8) Epoch 13, batch 4450, loss[loss=0.2713, simple_loss=0.3236, pruned_loss=0.1095, over 4665.00 frames.], tot_loss[loss=0.2831, simple_loss=0.3502, pruned_loss=0.108, over 965411.02 frames.], batch size: 12, lr: 7.56e-04
2022-05-28 12:08:17,379 INFO [train.py:761] (5/8) Epoch 13, batch 4500, loss[loss=0.235, simple_loss=0.3239, pruned_loss=0.07305, over 4847.00 frames.], tot_loss[loss=0.2838, simple_loss=0.3505, pruned_loss=0.1086, over 966137.07 frames.], batch size: 11, lr: 7.56e-04
2022-05-28 12:08:55,587 INFO [train.py:761] (5/8) Epoch 13, batch 4550, loss[loss=0.282, simple_loss=0.3492, pruned_loss=0.1074, over 4887.00 frames.], tot_loss[loss=0.2863, simple_loss=0.3527, pruned_loss=0.1099, over 966093.87 frames.], batch size: 15, lr: 7.56e-04
2022-05-28 12:09:33,993 INFO [train.py:761] (5/8) Epoch 13, batch 4600, loss[loss=0.2363, simple_loss=0.3243, pruned_loss=0.07413, over 4857.00 frames.], tot_loss[loss=0.2839, simple_loss=0.351, pruned_loss=0.1084, over 966393.81 frames.], batch size: 13, lr: 7.55e-04
2022-05-28 12:10:11,921 INFO [train.py:761] (5/8) Epoch 13, batch 4650, loss[loss=0.2815, simple_loss=0.3419, pruned_loss=0.1106, over 4924.00 frames.], tot_loss[loss=0.2832, simple_loss=0.3505, pruned_loss=0.108, over 966030.32 frames.], batch size: 13, lr: 7.55e-04
2022-05-28 12:10:50,144 INFO [train.py:761] (5/8) Epoch 13, batch 4700, loss[loss=0.2403, simple_loss=0.3167, pruned_loss=0.08196, over 4655.00 frames.], tot_loss[loss=0.2839, simple_loss=0.3508, pruned_loss=0.1085, over 966857.63 frames.], batch size: 11, lr: 7.55e-04
2022-05-28 12:11:28,027 INFO [train.py:761] (5/8) Epoch 13, batch 4750, loss[loss=0.2935, simple_loss=0.3691, pruned_loss=0.1089, over 4911.00 frames.], tot_loss[loss=0.2847, simple_loss=0.352, pruned_loss=0.1087, over 966846.76 frames.], batch size: 26, lr: 7.55e-04
2022-05-28 12:12:06,334 INFO [train.py:761] (5/8) Epoch 13, batch 4800, loss[loss=0.2725, simple_loss=0.3205, pruned_loss=0.1123, over 4716.00 frames.], tot_loss[loss=0.2841, simple_loss=0.3513, pruned_loss=0.1085, over 966467.50 frames.], batch size: 11, lr: 7.55e-04
2022-05-28 12:12:44,596 INFO [train.py:761] (5/8) Epoch 13, batch 4850, loss[loss=0.283, simple_loss=0.3241, pruned_loss=0.121, over 4660.00 frames.], tot_loss[loss=0.2828, simple_loss=0.3501, pruned_loss=0.1077, over 966710.95 frames.], batch size: 12, lr: 7.54e-04
2022-05-28 12:13:23,313 INFO [train.py:761] (5/8) Epoch 13, batch 4900, loss[loss=0.259, simple_loss=0.3145, pruned_loss=0.1017, over 4838.00 frames.], tot_loss[loss=0.2827, simple_loss=0.3505, pruned_loss=0.1075, over 966160.07 frames.], batch size: 11, lr: 7.54e-04
2022-05-28 12:14:01,492 INFO [train.py:761] (5/8) Epoch 13, batch 4950, loss[loss=0.3227, simple_loss=0.3849, pruned_loss=0.1302, over 4845.00 frames.], tot_loss[loss=0.2818, simple_loss=0.3494, pruned_loss=0.1071, over 966708.49 frames.], batch size: 20, lr: 7.54e-04
2022-05-28 12:14:39,406 INFO [train.py:761] (5/8) Epoch 13, batch 5000, loss[loss=0.3604, simple_loss=0.4122, pruned_loss=0.1543, over 4980.00 frames.], tot_loss[loss=0.2819, simple_loss=0.3498, pruned_loss=0.107, over 966392.08 frames.], batch size: 45, lr: 7.54e-04
2022-05-28 12:15:17,641 INFO [train.py:761] (5/8) Epoch 13, batch 5050, loss[loss=0.2833, simple_loss=0.3341, pruned_loss=0.1162, over 4893.00 frames.], tot_loss[loss=0.2811, simple_loss=0.3494, pruned_loss=0.1064, over 967249.73 frames.], batch size: 12, lr: 7.53e-04
2022-05-28 12:15:55,908 INFO [train.py:761] (5/8) Epoch 13, batch 5100, loss[loss=0.2974, simple_loss=0.3794, pruned_loss=0.1077, over 4985.00 frames.], tot_loss[loss=0.2806, simple_loss=0.3491, pruned_loss=0.1061, over 968030.30 frames.], batch size: 15, lr: 7.53e-04
2022-05-28 12:16:34,506 INFO [train.py:761] (5/8) Epoch 13, batch 5150, loss[loss=0.2815, simple_loss=0.3516, pruned_loss=0.1057, over 4796.00 frames.], tot_loss[loss=0.2797, simple_loss=0.3489, pruned_loss=0.1053, over 966542.98 frames.], batch size: 16, lr: 7.53e-04
2022-05-28 12:17:12,621 INFO [train.py:761] (5/8) Epoch 13, batch 5200, loss[loss=0.2768, simple_loss=0.346, pruned_loss=0.1038, over 4791.00 frames.], tot_loss[loss=0.2808, simple_loss=0.3498, pruned_loss=0.1059, over 965330.01 frames.], batch size: 14, lr: 7.53e-04
2022-05-28 12:17:50,926 INFO [train.py:761] (5/8) Epoch 13, batch 5250, loss[loss=0.3453, simple_loss=0.4055, pruned_loss=0.1426, over 4890.00 frames.], tot_loss[loss=0.2807, simple_loss=0.3495, pruned_loss=0.106, over 965439.39 frames.], batch size: 15, lr: 7.53e-04
2022-05-28 12:18:29,269 INFO [train.py:761] (5/8) Epoch 13, batch 5300, loss[loss=0.2786, simple_loss=0.3435, pruned_loss=0.1068, over 4836.00 frames.], tot_loss[loss=0.2799, simple_loss=0.3491, pruned_loss=0.1054, over 966094.08 frames.], batch size: 11, lr: 7.52e-04
2022-05-28 12:19:07,130 INFO [train.py:761] (5/8) Epoch 13, batch 5350, loss[loss=0.3444, simple_loss=0.4008, pruned_loss=0.144, over 4796.00 frames.], tot_loss[loss=0.2797, simple_loss=0.3491, pruned_loss=0.1051, over 966304.93 frames.], batch size: 14, lr: 7.52e-04
2022-05-28 12:19:44,769 INFO [train.py:761] (5/8) Epoch 13, batch 5400, loss[loss=0.3055, simple_loss=0.3825, pruned_loss=0.1143, over 4917.00 frames.], tot_loss[loss=0.278, simple_loss=0.3481, pruned_loss=0.104, over 965403.08 frames.], batch size: 14, lr: 7.52e-04
2022-05-28 12:20:23,329 INFO [train.py:761] (5/8) Epoch 13, batch 5450, loss[loss=0.3176, simple_loss=0.3687, pruned_loss=0.1333, over 4849.00 frames.], tot_loss[loss=0.2787, simple_loss=0.3484, pruned_loss=0.1045, over 966221.07 frames.], batch size: 13, lr: 7.52e-04
2022-05-28 12:21:01,705 INFO [train.py:761] (5/8) Epoch 13, batch 5500, loss[loss=0.333, simple_loss=0.3908, pruned_loss=0.1377, over 4981.00 frames.], tot_loss[loss=0.2808, simple_loss=0.35, pruned_loss=0.1058, over 967567.42 frames.], batch size: 15, lr: 7.52e-04
2022-05-28 12:21:40,041 INFO [train.py:761] (5/8) Epoch 13, batch 5550, loss[loss=0.2506, simple_loss=0.3262, pruned_loss=0.08745, over 4833.00 frames.], tot_loss[loss=0.2811, simple_loss=0.3501, pruned_loss=0.1061, over 967974.08 frames.], batch size: 11, lr: 7.51e-04
2022-05-28 12:22:18,737 INFO [train.py:761] (5/8) Epoch 13, batch 5600, loss[loss=0.3368, simple_loss=0.3883, pruned_loss=0.1427, over 4889.00 frames.], tot_loss[loss=0.2831, simple_loss=0.351, pruned_loss=0.1076, over 967671.63 frames.], batch size: 15, lr: 7.51e-04
2022-05-28 12:22:56,855 INFO [train.py:761] (5/8) Epoch 13, batch 5650, loss[loss=0.2457, simple_loss=0.2956, pruned_loss=0.09786, over 4840.00 frames.], tot_loss[loss=0.2811, simple_loss=0.3492, pruned_loss=0.1065, over 966979.35 frames.], batch size: 11, lr: 7.51e-04
2022-05-28 12:23:35,071 INFO [train.py:761] (5/8) Epoch 13, batch 5700, loss[loss=0.2809, simple_loss=0.3566, pruned_loss=0.1026, over 4851.00 frames.], tot_loss[loss=0.281, simple_loss=0.3488, pruned_loss=0.1066, over 965928.71 frames.], batch size: 14, lr: 7.51e-04
2022-05-28 12:24:13,250 INFO [train.py:761] (5/8) Epoch 13, batch 5750, loss[loss=0.2532, simple_loss=0.3267, pruned_loss=0.08988, over 4974.00 frames.], tot_loss[loss=0.2798, simple_loss=0.3487, pruned_loss=0.1054, over 966039.58 frames.], batch size: 12, lr: 7.50e-04
2022-05-28 12:24:51,576 INFO [train.py:761] (5/8) Epoch 13, batch 5800, loss[loss=0.2973, simple_loss=0.3646, pruned_loss=0.115, over 4846.00 frames.], tot_loss[loss=0.2819, simple_loss=0.3506, pruned_loss=0.1066, over 966395.95 frames.], batch size: 18, lr: 7.50e-04
2022-05-28 12:25:29,328 INFO [train.py:761] (5/8) Epoch 13, batch 5850, loss[loss=0.3069, simple_loss=0.3719, pruned_loss=0.121, over 4840.00 frames.], tot_loss[loss=0.2822, simple_loss=0.3511, pruned_loss=0.1066, over 966895.96 frames.], batch size: 18, lr: 7.50e-04
2022-05-28 12:26:07,510 INFO [train.py:761] (5/8) Epoch 13, batch 5900, loss[loss=0.2505, simple_loss=0.3313, pruned_loss=0.0848, over 4858.00 frames.], tot_loss[loss=0.2833, simple_loss=0.352, pruned_loss=0.1073, over 966581.80 frames.], batch size: 13, lr: 7.50e-04
2022-05-28 12:26:45,431 INFO [train.py:761] (5/8) Epoch 13, batch 5950, loss[loss=0.3548, simple_loss=0.4185, pruned_loss=0.1455, over 4666.00 frames.], tot_loss[loss=0.2827, simple_loss=0.3518, pruned_loss=0.1068, over 966634.28 frames.], batch size: 13, lr: 7.50e-04
2022-05-28 12:27:23,992 INFO [train.py:761] (5/8) Epoch 13, batch 6000, loss[loss=0.3013, simple_loss=0.3647, pruned_loss=0.1189, over 4769.00 frames.], tot_loss[loss=0.2814, simple_loss=0.3506, pruned_loss=0.1061, over 966544.67 frames.], batch size: 15, lr: 7.49e-04
2022-05-28 12:27:23,992 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 12:27:33,933 INFO [train.py:790] (5/8) Epoch 13, validation: loss=0.2157, simple_loss=0.3223, pruned_loss=0.05454, over 944034.00 frames.
2022-05-28 12:28:11,946 INFO [train.py:761] (5/8) Epoch 13, batch 6050, loss[loss=0.2712, simple_loss=0.3499, pruned_loss=0.09626, over 4875.00 frames.], tot_loss[loss=0.2818, simple_loss=0.3509, pruned_loss=0.1064, over 965850.61 frames.], batch size: 15, lr: 7.49e-04
2022-05-28 12:28:50,099 INFO [train.py:761] (5/8) Epoch 13, batch 6100, loss[loss=0.3177, simple_loss=0.3803, pruned_loss=0.1275, over 4964.00 frames.], tot_loss[loss=0.2817, simple_loss=0.3508, pruned_loss=0.1063, over 965421.89 frames.], batch size: 26, lr: 7.49e-04
2022-05-28 12:29:28,444 INFO [train.py:761] (5/8) Epoch 13, batch 6150, loss[loss=0.2648, simple_loss=0.3342, pruned_loss=0.09769, over 4874.00 frames.], tot_loss[loss=0.2834, simple_loss=0.3522, pruned_loss=0.1073, over 966503.78 frames.], batch size: 15, lr: 7.49e-04
2022-05-28 12:30:06,713 INFO [train.py:761] (5/8) Epoch 13, batch 6200, loss[loss=0.2916, simple_loss=0.3589, pruned_loss=0.1122, over 4819.00 frames.], tot_loss[loss=0.2834, simple_loss=0.3515, pruned_loss=0.1076, over 966151.45 frames.], batch size: 26, lr: 7.49e-04
2022-05-28 12:30:44,971 INFO [train.py:761] (5/8) Epoch 13, batch 6250, loss[loss=0.2749, simple_loss=0.3535, pruned_loss=0.09813, over 4911.00 frames.], tot_loss[loss=0.2826, simple_loss=0.3512, pruned_loss=0.107, over 967549.29 frames.], batch size: 14, lr: 7.48e-04
2022-05-28 12:31:23,914 INFO [train.py:761] (5/8) Epoch 13, batch 6300, loss[loss=0.2633, simple_loss=0.3436, pruned_loss=0.09146, over 4915.00 frames.], tot_loss[loss=0.2824, simple_loss=0.3514, pruned_loss=0.1067, over 966769.57 frames.], batch size: 14, lr: 7.48e-04
2022-05-28 12:32:02,147 INFO [train.py:761] (5/8) Epoch 13, batch 6350, loss[loss=0.3017, simple_loss=0.348, pruned_loss=0.1277, over 4655.00 frames.], tot_loss[loss=0.2826, simple_loss=0.3514, pruned_loss=0.1069, over 967107.82 frames.], batch size: 12, lr: 7.48e-04
2022-05-28 12:32:40,804 INFO [train.py:761] (5/8) Epoch 13, batch 6400, loss[loss=0.3091, simple_loss=0.3753, pruned_loss=0.1215, over 4964.00 frames.], tot_loss[loss=0.2829, simple_loss=0.3519, pruned_loss=0.107, over 967069.50 frames.], batch size: 26, lr: 7.48e-04
2022-05-28 12:33:19,082 INFO [train.py:761] (5/8) Epoch 13, batch 6450, loss[loss=0.2973, simple_loss=0.3691, pruned_loss=0.1127, over 4846.00 frames.], tot_loss[loss=0.2819, simple_loss=0.3506, pruned_loss=0.1066, over 967100.20 frames.], batch size: 25, lr: 7.47e-04
2022-05-28 12:33:57,541 INFO [train.py:761] (5/8) Epoch 13, batch 6500, loss[loss=0.2948, simple_loss=0.3603, pruned_loss=0.1146, over 4780.00 frames.], tot_loss[loss=0.2819, simple_loss=0.3505, pruned_loss=0.1067, over 967120.42 frames.], batch size: 13, lr: 7.47e-04
2022-05-28 12:34:36,177 INFO [train.py:761] (5/8) Epoch 13, batch 6550, loss[loss=0.2565, simple_loss=0.3183, pruned_loss=0.09741, over 4733.00 frames.], tot_loss[loss=0.2808, simple_loss=0.3498, pruned_loss=0.1059, over 966184.67 frames.], batch size: 11, lr: 7.47e-04
2022-05-28 12:35:14,993 INFO [train.py:761] (5/8) Epoch 13, batch 6600, loss[loss=0.297, simple_loss=0.3672, pruned_loss=0.1134, over 4829.00 frames.], tot_loss[loss=0.281, simple_loss=0.3502, pruned_loss=0.1059, over 965820.90 frames.], batch size: 20, lr: 7.47e-04
2022-05-28 12:35:52,831 INFO [train.py:761] (5/8) Epoch 13, batch 6650, loss[loss=0.2757, simple_loss=0.3449, pruned_loss=0.1033, over 4916.00 frames.], tot_loss[loss=0.2804, simple_loss=0.3499, pruned_loss=0.1055, over 966625.40 frames.], batch size: 13, lr: 7.47e-04
2022-05-28 12:36:31,101 INFO [train.py:761] (5/8) Epoch 13, batch 6700, loss[loss=0.2362, simple_loss=0.3057, pruned_loss=0.08334, over 4735.00 frames.], tot_loss[loss=0.2797, simple_loss=0.349, pruned_loss=0.1052, over 965481.54 frames.], batch size: 11, lr: 7.46e-04
2022-05-28 12:37:26,661 INFO [train.py:761] (5/8) Epoch 14, batch 0, loss[loss=0.2192, simple_loss=0.2943, pruned_loss=0.07205, over 4978.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2943, pruned_loss=0.07205, over 4978.00 frames.], batch size: 12, lr: 7.46e-04
2022-05-28 12:38:04,489 INFO [train.py:761] (5/8) Epoch 14, batch 50, loss[loss=0.2609, simple_loss=0.3469, pruned_loss=0.08749, over 4679.00 frames.], tot_loss[loss=0.2531, simple_loss=0.3356, pruned_loss=0.0853, over 218708.18 frames.], batch size: 13, lr: 7.46e-04
2022-05-28 12:38:42,802 INFO [train.py:761] (5/8) Epoch 14, batch 100, loss[loss=0.2472, simple_loss=0.3301, pruned_loss=0.08215, over 4915.00 frames.], tot_loss[loss=0.2546, simple_loss=0.3377, pruned_loss=0.08572, over 384733.51 frames.], batch size: 26, lr: 7.46e-04
2022-05-28 12:39:21,562 INFO [train.py:761] (5/8) Epoch 14, batch 150, loss[loss=0.2015, simple_loss=0.2897, pruned_loss=0.05667, over 4884.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3326, pruned_loss=0.0822, over 514027.30 frames.], batch size: 12, lr: 7.46e-04
2022-05-28 12:39:59,651 INFO [train.py:761] (5/8) Epoch 14, batch 200, loss[loss=0.2325, simple_loss=0.3368, pruned_loss=0.06413, over 4782.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3308, pruned_loss=0.07992, over 613426.52 frames.], batch size: 20, lr: 7.45e-04
2022-05-28 12:40:37,137 INFO [train.py:761] (5/8) Epoch 14, batch 250, loss[loss=0.2094, simple_loss=0.2975, pruned_loss=0.06069, over 4590.00 frames.], tot_loss[loss=0.2446, simple_loss=0.3298, pruned_loss=0.07968, over 690616.74 frames.], batch size: 10, lr: 7.45e-04
2022-05-28 12:41:14,751 INFO [train.py:761] (5/8) Epoch 14, batch 300, loss[loss=0.2328, simple_loss=0.3172, pruned_loss=0.07426, over 4668.00 frames.], tot_loss[loss=0.2442, simple_loss=0.3294, pruned_loss=0.07948, over 752439.26 frames.], batch size: 12, lr: 7.45e-04
2022-05-28 12:41:56,327 INFO [train.py:761] (5/8) Epoch 14, batch 350, loss[loss=0.235, simple_loss=0.3325, pruned_loss=0.06874, over 4784.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3301, pruned_loss=0.07977, over 799736.13 frames.], batch size: 16, lr: 7.45e-04
2022-05-28 12:42:34,045 INFO [train.py:761] (5/8) Epoch 14, batch 400, loss[loss=0.1943, simple_loss=0.291, pruned_loss=0.04879, over 4667.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3301, pruned_loss=0.07973, over 836293.69 frames.], batch size: 13, lr: 7.44e-04
2022-05-28 12:43:11,852 INFO [train.py:761] (5/8) Epoch 14, batch 450, loss[loss=0.2515, simple_loss=0.3509, pruned_loss=0.07608, over 4800.00 frames.], tot_loss[loss=0.2424, simple_loss=0.328, pruned_loss=0.07834, over 865073.04 frames.], batch size: 16, lr: 7.44e-04
2022-05-28 12:43:50,192 INFO [train.py:761] (5/8) Epoch 14, batch 500, loss[loss=0.2562, simple_loss=0.3445, pruned_loss=0.0839, over 4919.00 frames.], tot_loss[loss=0.2432, simple_loss=0.3288, pruned_loss=0.07875, over 888462.95 frames.], batch size: 13, lr: 7.44e-04
2022-05-28 12:44:28,776 INFO [train.py:761] (5/8) Epoch 14, batch 550, loss[loss=0.2554, simple_loss=0.3435, pruned_loss=0.08363, over 4975.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3287, pruned_loss=0.07876, over 905407.79 frames.], batch size: 15, lr: 7.44e-04
2022-05-28 12:45:06,746 INFO [train.py:761] (5/8) Epoch 14, batch 600, loss[loss=0.2177, simple_loss=0.3189, pruned_loss=0.05824, over 4989.00 frames.], tot_loss[loss=0.245, simple_loss=0.3307, pruned_loss=0.07965, over 919590.20 frames.], batch size: 21, lr: 7.44e-04
2022-05-28 12:45:44,405 INFO [train.py:761] (5/8) Epoch 14, batch 650, loss[loss=0.2318, simple_loss=0.3267, pruned_loss=0.06852, over 4709.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3304, pruned_loss=0.08008, over 929048.54 frames.], batch size: 14, lr: 7.43e-04
2022-05-28 12:46:22,038 INFO [train.py:761] (5/8) Epoch 14, batch 700, loss[loss=0.2556, simple_loss=0.35, pruned_loss=0.08061, over 4871.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3298, pruned_loss=0.08029, over 937534.92 frames.], batch size: 15, lr: 7.43e-04
2022-05-28 12:47:00,201 INFO [train.py:761] (5/8) Epoch 14, batch 750, loss[loss=0.3125, simple_loss=0.3906, pruned_loss=0.1172, over 4774.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3322, pruned_loss=0.08143, over 943690.20 frames.], batch size: 16, lr: 7.43e-04
2022-05-28 12:47:38,711 INFO [train.py:761] (5/8) Epoch 14, batch 800, loss[loss=0.2612, simple_loss=0.3383, pruned_loss=0.09201, over 4842.00 frames.], tot_loss[loss=0.2511, simple_loss=0.335, pruned_loss=0.08361, over 948728.57 frames.], batch size: 13, lr: 7.43e-04
2022-05-28 12:48:17,113 INFO [train.py:761] (5/8) Epoch 14, batch 850, loss[loss=0.2759, simple_loss=0.3413, pruned_loss=0.1052, over 4730.00 frames.], tot_loss[loss=0.2528, simple_loss=0.3364, pruned_loss=0.08463, over 953182.15 frames.], batch size: 12, lr: 7.43e-04
2022-05-28 12:48:54,612 INFO [train.py:761] (5/8) Epoch 14, batch 900, loss[loss=0.2735, simple_loss=0.3604, pruned_loss=0.09327, over 4984.00 frames.], tot_loss[loss=0.2541, simple_loss=0.3379, pruned_loss=0.08516, over 956251.48 frames.], batch size: 15, lr: 7.42e-04
2022-05-28 12:49:32,427 INFO [train.py:761] (5/8) Epoch 14, batch 950, loss[loss=0.2786, simple_loss=0.3607, pruned_loss=0.0982, over 4931.00 frames.], tot_loss[loss=0.2547, simple_loss=0.3382, pruned_loss=0.08562, over 958111.93 frames.], batch size: 16, lr: 7.42e-04
2022-05-28 12:50:10,716 INFO [train.py:761] (5/8) Epoch 14, batch 1000, loss[loss=0.2346, simple_loss=0.3069, pruned_loss=0.08111, over 4642.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3389, pruned_loss=0.08567, over 960353.67 frames.], batch size: 11, lr: 7.42e-04
2022-05-28 12:50:48,378 INFO [train.py:761] (5/8) Epoch 14, batch 1050, loss[loss=0.2325, simple_loss=0.3072, pruned_loss=0.07887, over 4734.00 frames.], tot_loss[loss=0.2543, simple_loss=0.3375, pruned_loss=0.08556, over 961597.72 frames.], batch size: 12, lr: 7.42e-04
2022-05-28 12:51:26,339 INFO [train.py:761] (5/8) Epoch 14, batch 1100, loss[loss=0.3471, simple_loss=0.4215, pruned_loss=0.1364, over 4967.00 frames.], tot_loss[loss=0.2544, simple_loss=0.3381, pruned_loss=0.08538, over 963207.24 frames.], batch size: 49, lr: 7.42e-04
2022-05-28 12:52:04,452 INFO [train.py:761] (5/8) Epoch 14, batch 1150, loss[loss=0.2234, simple_loss=0.3233, pruned_loss=0.06174, over 4983.00 frames.], tot_loss[loss=0.2534, simple_loss=0.3371, pruned_loss=0.08488, over 964422.14 frames.], batch size: 15, lr: 7.41e-04
2022-05-28 12:52:42,270 INFO [train.py:761] (5/8) Epoch 14, batch 1200, loss[loss=0.2657, simple_loss=0.3532, pruned_loss=0.08914, over 4785.00 frames.], tot_loss[loss=0.2534, simple_loss=0.3369, pruned_loss=0.08492, over 964186.51 frames.], batch size: 14, lr: 7.41e-04
2022-05-28 12:53:20,386 INFO [train.py:761] (5/8) Epoch 14, batch 1250, loss[loss=0.2516, simple_loss=0.3325, pruned_loss=0.08532, over 4804.00 frames.], tot_loss[loss=0.2523, simple_loss=0.3363, pruned_loss=0.0841, over 963951.91 frames.], batch size: 12, lr: 7.41e-04
2022-05-28 12:53:58,131 INFO [train.py:761] (5/8) Epoch 14, batch 1300, loss[loss=0.2485, simple_loss=0.3229, pruned_loss=0.08699, over 4852.00 frames.], tot_loss[loss=0.2522, simple_loss=0.3363, pruned_loss=0.08402, over 964926.09 frames.], batch size: 13, lr: 7.41e-04
2022-05-28 12:54:36,319 INFO [train.py:761] (5/8) Epoch 14, batch 1350, loss[loss=0.2839, simple_loss=0.378, pruned_loss=0.09491, over 4775.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3351, pruned_loss=0.08308, over 965292.95 frames.], batch size: 15, lr: 7.40e-04
2022-05-28 12:55:14,310 INFO [train.py:761] (5/8) Epoch 14, batch 1400, loss[loss=0.2439, simple_loss=0.3309, pruned_loss=0.07843, over 4805.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3362, pruned_loss=0.08366, over 966343.80 frames.], batch size: 12, lr: 7.40e-04
2022-05-28 12:55:52,725 INFO [train.py:761] (5/8) Epoch 14, batch 1450, loss[loss=0.19, simple_loss=0.2685, pruned_loss=0.05569, over 4574.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3348, pruned_loss=0.08307, over 966197.47 frames.], batch size: 10, lr: 7.40e-04
2022-05-28 12:56:31,043 INFO [train.py:761] (5/8) Epoch 14, batch 1500, loss[loss=0.2568, simple_loss=0.3457, pruned_loss=0.08398, over 4784.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3354, pruned_loss=0.08306, over 965933.57 frames.], batch size: 13, lr: 7.40e-04
2022-05-28 12:57:09,384 INFO [train.py:761] (5/8) Epoch 14, batch 1550, loss[loss=0.2736, simple_loss=0.364, pruned_loss=0.09156, over 4850.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3347, pruned_loss=0.08322, over 965271.66 frames.], batch size: 18, lr: 7.40e-04
2022-05-28 12:57:47,397 INFO [train.py:761] (5/8) Epoch 14, batch 1600, loss[loss=0.2371, simple_loss=0.3148, pruned_loss=0.07974, over 4786.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3335, pruned_loss=0.0823, over 964632.30 frames.], batch size: 13, lr: 7.39e-04
2022-05-28 12:58:25,260 INFO [train.py:761] (5/8) Epoch 14, batch 1650, loss[loss=0.2257, simple_loss=0.3142, pruned_loss=0.06857, over 4799.00 frames.], tot_loss[loss=0.2488, simple_loss=0.3335, pruned_loss=0.08207, over 964644.06 frames.], batch size: 12, lr: 7.39e-04
2022-05-28 12:59:03,060 INFO [train.py:761] (5/8) Epoch 14, batch 1700, loss[loss=0.2667, simple_loss=0.3601, pruned_loss=0.08663, over 4856.00 frames.], tot_loss[loss=0.2494, simple_loss=0.3344, pruned_loss=0.08219, over 965480.40 frames.], batch size: 14, lr: 7.39e-04
2022-05-28 12:59:41,282 INFO [train.py:761] (5/8) Epoch 14, batch 1750, loss[loss=0.2236, simple_loss=0.3121, pruned_loss=0.06758, over 4920.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3341, pruned_loss=0.08266, over 966105.64 frames.], batch size: 13, lr: 7.39e-04
2022-05-28 13:00:18,939 INFO [train.py:761] (5/8) Epoch 14, batch 1800, loss[loss=0.2312, simple_loss=0.3216, pruned_loss=0.07037, over 4986.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3333, pruned_loss=0.08223, over 965820.80 frames.], batch size: 14, lr: 7.39e-04
2022-05-28 13:00:56,847 INFO [train.py:761] (5/8) Epoch 14, batch 1850, loss[loss=0.2028, simple_loss=0.2766, pruned_loss=0.06451, over 4976.00 frames.], tot_loss[loss=0.2483, simple_loss=0.333, pruned_loss=0.08175, over 966143.21 frames.], batch size: 12, lr: 7.38e-04
2022-05-28 13:01:34,789 INFO [train.py:761] (5/8) Epoch 14, batch 1900, loss[loss=0.2457, simple_loss=0.3308, pruned_loss=0.08036, over 4854.00 frames.], tot_loss[loss=0.2469, simple_loss=0.332, pruned_loss=0.08092, over 966010.47 frames.], batch size: 14, lr: 7.38e-04
2022-05-28 13:02:12,436 INFO [train.py:761] (5/8) Epoch 14, batch 1950, loss[loss=0.1846, simple_loss=0.2715, pruned_loss=0.04892, over 4793.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3317, pruned_loss=0.08069, over 966429.85 frames.], batch size: 13, lr: 7.38e-04
2022-05-28 13:02:50,261 INFO [train.py:761] (5/8) Epoch 14, batch 2000, loss[loss=0.255, simple_loss=0.3603, pruned_loss=0.07482, over 4777.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3321, pruned_loss=0.08059, over 966907.79 frames.], batch size: 15, lr: 7.38e-04
2022-05-28 13:03:28,212 INFO [train.py:761] (5/8) Epoch 14, batch 2050, loss[loss=0.2881, simple_loss=0.3629, pruned_loss=0.1067, over 4906.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3321, pruned_loss=0.08076, over 964950.36 frames.], batch size: 48, lr: 7.38e-04
2022-05-28 13:04:06,272 INFO [train.py:761] (5/8) Epoch 14, batch 2100, loss[loss=0.2401, simple_loss=0.3337, pruned_loss=0.07322, over 4975.00 frames.], tot_loss[loss=0.246, simple_loss=0.3311, pruned_loss=0.08048, over 965521.28 frames.], batch size: 14, lr: 7.37e-04
2022-05-28 13:04:44,195 INFO [train.py:761] (5/8) Epoch 14, batch 2150, loss[loss=0.2432, simple_loss=0.3374, pruned_loss=0.07445, over 4915.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3334, pruned_loss=0.08161, over 965111.21 frames.], batch size: 14, lr: 7.37e-04
2022-05-28 13:05:22,087 INFO [train.py:761] (5/8) Epoch 14, batch 2200, loss[loss=0.2559, simple_loss=0.3336, pruned_loss=0.08916, over 4845.00 frames.], tot_loss[loss=0.2484, simple_loss=0.3334, pruned_loss=0.08168, over 965710.06 frames.], batch size: 11, lr: 7.37e-04
2022-05-28 13:06:00,185 INFO [train.py:761] (5/8) Epoch 14, batch 2250, loss[loss=0.2557, simple_loss=0.3506, pruned_loss=0.08038, over 4896.00 frames.], tot_loss[loss=0.2492, simple_loss=0.334, pruned_loss=0.08217, over 966058.53 frames.], batch size: 17, lr: 7.37e-04
2022-05-28 13:06:38,148 INFO [train.py:761] (5/8) Epoch 14, batch 2300, loss[loss=0.2303, simple_loss=0.3312, pruned_loss=0.06463, over 4741.00 frames.], tot_loss[loss=0.2503, simple_loss=0.3348, pruned_loss=0.08284, over 967291.30 frames.], batch size: 12, lr: 7.37e-04
2022-05-28 13:07:16,502 INFO [train.py:761] (5/8) Epoch 14, batch 2350, loss[loss=0.2193, simple_loss=0.3167, pruned_loss=0.06093, over 4807.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3344, pruned_loss=0.08269, over 967792.01 frames.], batch size: 16, lr: 7.36e-04
2022-05-28 13:07:54,191 INFO [train.py:761] (5/8) Epoch 14, batch 2400, loss[loss=0.2403, simple_loss=0.3248, pruned_loss=0.07794, over 4661.00 frames.], tot_loss[loss=0.2492, simple_loss=0.3342, pruned_loss=0.08208, over 968086.58 frames.], batch size: 12, lr: 7.36e-04
2022-05-28 13:08:32,183 INFO [train.py:761] (5/8) Epoch 14, batch 2450, loss[loss=0.2125, simple_loss=0.313, pruned_loss=0.05601, over 4888.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3329, pruned_loss=0.08099, over 968238.81 frames.], batch size: 15, lr: 7.36e-04
2022-05-28 13:09:09,461 INFO [train.py:761] (5/8) Epoch 14, batch 2500, loss[loss=0.2599, simple_loss=0.355, pruned_loss=0.08241, over 4847.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3334, pruned_loss=0.08083, over 968223.87 frames.], batch size: 18, lr: 7.36e-04
2022-05-28 13:09:47,785 INFO [train.py:761] (5/8) Epoch 14, batch 2550, loss[loss=0.2614, simple_loss=0.3434, pruned_loss=0.08976, over 4779.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3309, pruned_loss=0.07984, over 966582.72 frames.], batch size: 13, lr: 7.36e-04
2022-05-28 13:10:25,842 INFO [train.py:761] (5/8) Epoch 14, batch 2600, loss[loss=0.2891, simple_loss=0.3704, pruned_loss=0.1039, over 4845.00 frames.], tot_loss[loss=0.2454, simple_loss=0.3313, pruned_loss=0.07978, over 966524.57 frames.], batch size: 14, lr: 7.35e-04
2022-05-28 13:11:04,043 INFO [train.py:761] (5/8) Epoch 14, batch 2650, loss[loss=0.2974, simple_loss=0.3661, pruned_loss=0.1144, over 4837.00 frames.], tot_loss[loss=0.2479, simple_loss=0.3334, pruned_loss=0.08121, over 966940.63 frames.], batch size: 20, lr: 7.35e-04
2022-05-28 13:11:42,133 INFO [train.py:761] (5/8) Epoch 14, batch 2700, loss[loss=0.2289, simple_loss=0.3138, pruned_loss=0.07201, over 4898.00 frames.], tot_loss[loss=0.2467, simple_loss=0.3326, pruned_loss=0.08046, over 967672.17 frames.], batch size: 12, lr: 7.35e-04
2022-05-28 13:12:20,038 INFO [train.py:761] (5/8) Epoch 14, batch 2750, loss[loss=0.2693, simple_loss=0.3579, pruned_loss=0.09034, over 4977.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3317, pruned_loss=0.07973, over 968042.06 frames.], batch size: 15, lr: 7.35e-04
2022-05-28 13:12:57,911 INFO [train.py:761] (5/8) Epoch 14, batch 2800, loss[loss=0.2657, simple_loss=0.3103, pruned_loss=0.1106, over 4559.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3325, pruned_loss=0.08053, over 967213.31 frames.], batch size: 10, lr: 7.35e-04
2022-05-28 13:13:36,075 INFO [train.py:761] (5/8) Epoch 14, batch 2850, loss[loss=0.2559, simple_loss=0.351, pruned_loss=0.08034, over 4808.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3314, pruned_loss=0.07986, over 966652.19 frames.], batch size: 18, lr: 7.34e-04
2022-05-28 13:14:13,630 INFO [train.py:761] (5/8) Epoch 14, batch 2900, loss[loss=0.2458, simple_loss=0.3402, pruned_loss=0.07567, over 4771.00 frames.], tot_loss[loss=0.2463, simple_loss=0.332, pruned_loss=0.08032, over 966587.83 frames.], batch size: 16, lr: 7.34e-04
2022-05-28 13:14:51,574 INFO [train.py:761] (5/8) Epoch 14, batch 2950, loss[loss=0.2145, simple_loss=0.3198, pruned_loss=0.05462, over 4982.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3313, pruned_loss=0.08025, over 966611.34 frames.], batch size: 13, lr: 7.34e-04
2022-05-28 13:15:30,195 INFO [train.py:761] (5/8) Epoch 14, batch 3000, loss[loss=0.242, simple_loss=0.3348, pruned_loss=0.0746, over 4914.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3314, pruned_loss=0.0804, over 966136.31 frames.], batch size: 14, lr: 7.34e-04
2022-05-28 13:15:30,195 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 13:15:40,062 INFO [train.py:790] (5/8) Epoch 14, validation: loss=0.2247, simple_loss=0.3258, pruned_loss=0.06185, over 944034.00 frames.
2022-05-28 13:16:18,288 INFO [train.py:761] (5/8) Epoch 14, batch 3050, loss[loss=0.2466, simple_loss=0.345, pruned_loss=0.07406, over 4877.00 frames.], tot_loss[loss=0.2472, simple_loss=0.3323, pruned_loss=0.08111, over 967021.93 frames.], batch size: 15, lr: 7.34e-04
2022-05-28 13:16:56,505 INFO [train.py:761] (5/8) Epoch 14, batch 3100, loss[loss=0.2312, simple_loss=0.313, pruned_loss=0.07468, over 4800.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3346, pruned_loss=0.08256, over 968082.96 frames.], batch size: 12, lr: 7.33e-04
2022-05-28 13:17:33,873 INFO [train.py:761] (5/8) Epoch 14, batch 3150, loss[loss=0.313, simple_loss=0.3837, pruned_loss=0.1212, over 4956.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3355, pruned_loss=0.08477, over 967571.03 frames.], batch size: 27, lr: 7.33e-04
2022-05-28 13:18:11,671 INFO [train.py:761] (5/8) Epoch 14, batch 3200, loss[loss=0.2677, simple_loss=0.3511, pruned_loss=0.0922, over 4953.00 frames.], tot_loss[loss=0.2573, simple_loss=0.3384, pruned_loss=0.08806, over 968497.03 frames.], batch size: 16, lr: 7.33e-04
2022-05-28 13:18:49,945 INFO [train.py:761] (5/8) Epoch 14, batch 3250, loss[loss=0.2788, simple_loss=0.3618, pruned_loss=0.09792, over 4833.00 frames.], tot_loss[loss=0.2588, simple_loss=0.3389, pruned_loss=0.08934, over 968203.08 frames.], batch size: 20, lr: 7.33e-04
2022-05-28 13:19:27,696 INFO [train.py:761] (5/8) Epoch 14, batch 3300, loss[loss=0.323, simple_loss=0.3896, pruned_loss=0.1281, over 4937.00 frames.], tot_loss[loss=0.2628, simple_loss=0.341, pruned_loss=0.09232, over 967617.46 frames.], batch size: 21, lr: 7.33e-04
2022-05-28 13:20:05,480 INFO [train.py:761] (5/8) Epoch 14, batch 3350, loss[loss=0.2327, simple_loss=0.3191, pruned_loss=0.07312, over 4853.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3419, pruned_loss=0.09399, over 967401.24 frames.], batch size: 13, lr: 7.32e-04
2022-05-28 13:20:43,503 INFO [train.py:761] (5/8) Epoch 14, batch 3400, loss[loss=0.3268, simple_loss=0.3817, pruned_loss=0.1359, over 4866.00 frames.], tot_loss[loss=0.2654, simple_loss=0.3417, pruned_loss=0.09452, over 966581.43 frames.], batch size: 17, lr: 7.32e-04
2022-05-28 13:21:21,605 INFO [train.py:761] (5/8) Epoch 14, batch 3450, loss[loss=0.3064, simple_loss=0.3671, pruned_loss=0.1229, over 4972.00 frames.], tot_loss[loss=0.2673, simple_loss=0.342, pruned_loss=0.09624, over 965761.63 frames.], batch size: 16, lr: 7.32e-04
2022-05-28 13:21:59,653 INFO [train.py:761] (5/8) Epoch 14, batch 3500, loss[loss=0.2599, simple_loss=0.3366, pruned_loss=0.09158, over 4914.00 frames.], tot_loss[loss=0.2684, simple_loss=0.3423, pruned_loss=0.09722, over 966265.82 frames.], batch size: 14, lr: 7.32e-04
2022-05-28 13:22:38,008 INFO [train.py:761] (5/8) Epoch 14, batch 3550, loss[loss=0.284, simple_loss=0.3552, pruned_loss=0.1064, over 4727.00 frames.], tot_loss[loss=0.2701, simple_loss=0.343, pruned_loss=0.09863, over 965295.32 frames.], batch size: 13, lr: 7.32e-04
2022-05-28 13:23:16,008 INFO [train.py:761] (5/8) Epoch 14, batch 3600, loss[loss=0.3407, simple_loss=0.3963, pruned_loss=0.1425, over 4898.00 frames.], tot_loss[loss=0.2717, simple_loss=0.3438, pruned_loss=0.09984, over 965023.52 frames.], batch size: 46, lr: 7.31e-04
2022-05-28 13:23:53,818 INFO [train.py:761] (5/8) Epoch 14, batch 3650, loss[loss=0.2974, simple_loss=0.3622, pruned_loss=0.1163, over 4916.00 frames.], tot_loss[loss=0.273, simple_loss=0.3444, pruned_loss=0.1008, over 964761.20 frames.], batch size: 14, lr: 7.31e-04
2022-05-28 13:24:31,703 INFO [train.py:761] (5/8) Epoch 14, batch 3700, loss[loss=0.241, simple_loss=0.3331, pruned_loss=0.07447, over 4853.00 frames.], tot_loss[loss=0.2732, simple_loss=0.3439, pruned_loss=0.1013, over 965355.37 frames.], batch size: 14, lr: 7.31e-04
2022-05-28 13:25:09,928 INFO [train.py:761] (5/8) Epoch 14, batch 3750, loss[loss=0.2834, simple_loss=0.3522, pruned_loss=0.1073, over 4670.00 frames.], tot_loss[loss=0.2748, simple_loss=0.3446, pruned_loss=0.1025, over 966090.54 frames.], batch size: 13, lr: 7.31e-04
2022-05-28 13:25:48,305 INFO [train.py:761] (5/8) Epoch 14, batch 3800, loss[loss=0.2689, simple_loss=0.351, pruned_loss=0.09335, over 4858.00 frames.], tot_loss[loss=0.277, simple_loss=0.3465, pruned_loss=0.1037, over 966183.35 frames.], batch size: 14, lr: 7.31e-04
2022-05-28 13:26:26,661 INFO [train.py:761] (5/8) Epoch 14, batch 3850, loss[loss=0.2669, simple_loss=0.3404, pruned_loss=0.09676, over 4911.00 frames.], tot_loss[loss=0.278, simple_loss=0.3472, pruned_loss=0.1044, over 966444.08 frames.], batch size: 14, lr: 7.30e-04
2022-05-28 13:27:04,256 INFO [train.py:761] (5/8) Epoch 14, batch 3900, loss[loss=0.2648, simple_loss=0.3414, pruned_loss=0.09413, over 4790.00 frames.], tot_loss[loss=0.276, simple_loss=0.3459, pruned_loss=0.103, over 965594.85 frames.], batch size: 16, lr: 7.30e-04
2022-05-28 13:27:42,518 INFO [train.py:761] (5/8) Epoch 14, batch 3950, loss[loss=0.2506, simple_loss=0.3427, pruned_loss=0.07927, over 4977.00 frames.], tot_loss[loss=0.2759, simple_loss=0.3461, pruned_loss=0.1029, over 966167.98 frames.], batch size: 14, lr: 7.30e-04
2022-05-28 13:28:20,507 INFO [train.py:761] (5/8) Epoch 14, batch 4000, loss[loss=0.261, simple_loss=0.3364, pruned_loss=0.09279, over 4768.00 frames.], tot_loss[loss=0.2769, simple_loss=0.3472, pruned_loss=0.1034, over 966846.04 frames.], batch size: 15, lr: 7.30e-04
2022-05-28 13:28:59,000 INFO [train.py:761] (5/8) Epoch 14, batch 4050, loss[loss=0.2591, simple_loss=0.3361, pruned_loss=0.09106, over 4970.00 frames.], tot_loss[loss=0.2769, simple_loss=0.3471, pruned_loss=0.1034, over 966442.95 frames.], batch size: 15, lr: 7.30e-04
2022-05-28 13:29:37,315 INFO [train.py:761] (5/8) Epoch 14, batch 4100, loss[loss=0.3316, simple_loss=0.3841, pruned_loss=0.1396, over 4918.00 frames.], tot_loss[loss=0.2763, simple_loss=0.3463, pruned_loss=0.1032, over 966767.47 frames.], batch size: 14, lr: 7.29e-04
2022-05-28 13:30:15,547 INFO [train.py:761] (5/8) Epoch 14, batch 4150, loss[loss=0.2633, simple_loss=0.3362, pruned_loss=0.09524, over 4784.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3476, pruned_loss=0.1039, over 966384.49 frames.], batch size: 13, lr: 7.29e-04
2022-05-28 13:30:53,601 INFO [train.py:761] (5/8) Epoch 14, batch 4200, loss[loss=0.2181, simple_loss=0.2901, pruned_loss=0.07299, over 4801.00 frames.], tot_loss[loss=0.2784, simple_loss=0.3485, pruned_loss=0.1042, over 966120.71 frames.], batch size: 12, lr: 7.29e-04
2022-05-28 13:31:31,759 INFO [train.py:761] (5/8) Epoch 14, batch 4250, loss[loss=0.3298, simple_loss=0.3785, pruned_loss=0.1405, over 4735.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3478, pruned_loss=0.1038, over 966398.22 frames.], batch size: 12, lr: 7.29e-04
2022-05-28 13:32:09,615 INFO [train.py:761] (5/8) Epoch 14, batch 4300, loss[loss=0.2843, simple_loss=0.3675, pruned_loss=0.1005, over 4775.00 frames.], tot_loss[loss=0.2806, simple_loss=0.3504, pruned_loss=0.1054, over 966215.32 frames.], batch size: 15, lr: 7.29e-04
2022-05-28 13:32:48,620 INFO [train.py:761] (5/8) Epoch 14, batch 4350, loss[loss=0.256, simple_loss=0.3265, pruned_loss=0.09272, over 4944.00 frames.], tot_loss[loss=0.2786, simple_loss=0.3481, pruned_loss=0.1045, over 965866.85 frames.], batch size: 26, lr: 7.28e-04
2022-05-28 13:33:26,919 INFO [train.py:761] (5/8) Epoch 14, batch 4400, loss[loss=0.2904, simple_loss=0.3563, pruned_loss=0.1122, over 4789.00 frames.], tot_loss[loss=0.2775, simple_loss=0.3474, pruned_loss=0.1038, over 966958.47 frames.], batch size: 13, lr: 7.28e-04
2022-05-28 13:34:04,600 INFO [train.py:761] (5/8) Epoch 14, batch 4450, loss[loss=0.2029, simple_loss=0.2885, pruned_loss=0.05867, over 4879.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3461, pruned_loss=0.1027, over 966794.45 frames.], batch size: 12, lr: 7.28e-04
2022-05-28 13:34:42,662 INFO [train.py:761] (5/8) Epoch 14, batch 4500, loss[loss=0.3017, simple_loss=0.3744, pruned_loss=0.1145, over 4873.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3461, pruned_loss=0.1026, over 967185.39 frames.], batch size: 17, lr: 7.28e-04
2022-05-28 13:35:21,004 INFO [train.py:761] (5/8) Epoch 14, batch 4550, loss[loss=0.3001, simple_loss=0.3488, pruned_loss=0.1257, over 4975.00 frames.], tot_loss[loss=0.276, simple_loss=0.346, pruned_loss=0.103, over 967366.58 frames.], batch size: 14, lr: 7.28e-04
2022-05-28 13:35:58,974 INFO [train.py:761] (5/8) Epoch 14, batch 4600, loss[loss=0.2351, simple_loss=0.3167, pruned_loss=0.07671, over 4770.00 frames.], tot_loss[loss=0.2728, simple_loss=0.3431, pruned_loss=0.1013, over 966721.96 frames.], batch size: 15, lr: 7.27e-04
2022-05-28 13:36:36,805 INFO [train.py:761] (5/8) Epoch 14, batch 4650, loss[loss=0.2862, simple_loss=0.3729, pruned_loss=0.09969, over 4954.00 frames.], tot_loss[loss=0.2741, simple_loss=0.344, pruned_loss=0.102, over 966535.81 frames.], batch size: 26, lr: 7.27e-04
2022-05-28 13:37:15,456 INFO [train.py:761] (5/8) Epoch 14, batch 4700, loss[loss=0.3382, simple_loss=0.3826, pruned_loss=0.1469, over 4710.00 frames.], tot_loss[loss=0.2739, simple_loss=0.3439, pruned_loss=0.102, over 967051.27 frames.], batch size: 14, lr: 7.27e-04
2022-05-28 13:37:53,517 INFO [train.py:761] (5/8) Epoch 14, batch 4750, loss[loss=0.2371, simple_loss=0.3092, pruned_loss=0.08252, over 4980.00 frames.], tot_loss[loss=0.2734, simple_loss=0.3434, pruned_loss=0.1017, over 967013.37 frames.], batch size: 12, lr: 7.27e-04
2022-05-28 13:38:31,206 INFO [train.py:761] (5/8) Epoch 14, batch 4800, loss[loss=0.2274, simple_loss=0.2967, pruned_loss=0.07905, over 4640.00 frames.], tot_loss[loss=0.2718, simple_loss=0.342, pruned_loss=0.1008, over 968315.43 frames.], batch size: 11, lr: 7.27e-04
2022-05-28 13:39:10,177 INFO [train.py:761] (5/8) Epoch 14, batch 4850, loss[loss=0.249, simple_loss=0.3133, pruned_loss=0.09236, over 4667.00 frames.], tot_loss[loss=0.2726, simple_loss=0.3429, pruned_loss=0.1012, over 967704.42 frames.], batch size: 12, lr: 7.26e-04
2022-05-28 13:39:47,890 INFO [train.py:761] (5/8) Epoch 14, batch 4900, loss[loss=0.2583, simple_loss=0.3269, pruned_loss=0.09484, over 4830.00 frames.], tot_loss[loss=0.2728, simple_loss=0.3431, pruned_loss=0.1013, over 968547.27 frames.], batch size: 11, lr: 7.26e-04
2022-05-28 13:40:26,219 INFO [train.py:761] (5/8) Epoch 14, batch 4950, loss[loss=0.2515, simple_loss=0.3215, pruned_loss=0.09079, over 4913.00 frames.], tot_loss[loss=0.2701, simple_loss=0.3409, pruned_loss=0.09967, over 967762.05 frames.], batch size: 14, lr: 7.26e-04
2022-05-28 13:41:04,811 INFO [train.py:761] (5/8) Epoch 14, batch 5000, loss[loss=0.2569, simple_loss=0.3425, pruned_loss=0.08564, over 4857.00 frames.], tot_loss[loss=0.2704, simple_loss=0.342, pruned_loss=0.09945, over 967120.10 frames.], batch size: 17, lr: 7.26e-04
2022-05-28 13:41:42,999 INFO [train.py:761] (5/8) Epoch 14, batch 5050, loss[loss=0.2836, simple_loss=0.3576, pruned_loss=0.1049, over 4782.00 frames.], tot_loss[loss=0.2714, simple_loss=0.3432, pruned_loss=0.09975, over 967272.96 frames.], batch size: 15, lr: 7.26e-04
2022-05-28 13:42:21,522 INFO [train.py:761] (5/8) Epoch 14, batch 5100, loss[loss=0.2682, simple_loss=0.3334, pruned_loss=0.1015, over 4773.00 frames.], tot_loss[loss=0.272, simple_loss=0.343, pruned_loss=0.1005, over 967118.30 frames.], batch size: 20, lr: 7.25e-04
2022-05-28 13:42:59,686 INFO [train.py:761] (5/8) Epoch 14, batch 5150, loss[loss=0.2691, simple_loss=0.3415, pruned_loss=0.09831, over 4844.00 frames.], tot_loss[loss=0.2728, simple_loss=0.3436, pruned_loss=0.101, over 966770.45 frames.], batch size: 18, lr: 7.25e-04
2022-05-28 13:43:37,795 INFO [train.py:761] (5/8) Epoch 14, batch 5200, loss[loss=0.2447, simple_loss=0.3211, pruned_loss=0.08417, over 4724.00 frames.], tot_loss[loss=0.2726, simple_loss=0.343, pruned_loss=0.1011, over 966618.15 frames.], batch size: 12, lr: 7.25e-04
2022-05-28 13:44:16,420 INFO [train.py:761] (5/8) Epoch 14, batch 5250, loss[loss=0.2555, simple_loss=0.335, pruned_loss=0.08806, over 4993.00 frames.], tot_loss[loss=0.2736, simple_loss=0.3436, pruned_loss=0.1018, over 967288.11 frames.], batch size: 13, lr: 7.25e-04
2022-05-28 13:44:55,415 INFO [train.py:761] (5/8) Epoch 14, batch 5300, loss[loss=0.2982, simple_loss=0.372, pruned_loss=0.1122, over 4790.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3438, pruned_loss=0.1016, over 966650.52 frames.], batch size: 16, lr: 7.25e-04
2022-05-28 13:45:33,365 INFO [train.py:761] (5/8) Epoch 14, batch 5350, loss[loss=0.2145, simple_loss=0.2857, pruned_loss=0.07165, over 4726.00 frames.], tot_loss[loss=0.2723, simple_loss=0.343, pruned_loss=0.1008, over 966040.76 frames.], batch size: 11, lr: 7.24e-04
2022-05-28 13:46:11,779 INFO [train.py:761] (5/8) Epoch 14, batch 5400, loss[loss=0.2432, simple_loss=0.3183, pruned_loss=0.08406, over 4672.00 frames.], tot_loss[loss=0.2736, simple_loss=0.3436, pruned_loss=0.1018, over 965889.24 frames.], batch size: 12, lr: 7.24e-04
2022-05-28 13:46:50,402 INFO [train.py:761] (5/8) Epoch 14, batch 5450, loss[loss=0.2946, simple_loss=0.3722, pruned_loss=0.1086, over 4976.00 frames.], tot_loss[loss=0.272, simple_loss=0.3423, pruned_loss=0.1009, over 965857.44 frames.], batch size: 15, lr: 7.24e-04
2022-05-28 13:47:28,201 INFO [train.py:761] (5/8) Epoch 14, batch 5500, loss[loss=0.2772, simple_loss=0.35, pruned_loss=0.1023, over 4952.00 frames.], tot_loss[loss=0.2719, simple_loss=0.3424, pruned_loss=0.1007, over 965657.80 frames.], batch size: 16, lr: 7.24e-04
2022-05-28 13:48:06,579 INFO [train.py:761] (5/8) Epoch 14, batch 5550, loss[loss=0.23, simple_loss=0.2997, pruned_loss=0.08013, over 4984.00 frames.], tot_loss[loss=0.2724, simple_loss=0.3429, pruned_loss=0.101, over 965357.93 frames.], batch size: 11, lr: 7.24e-04
2022-05-28 13:48:44,531 INFO [train.py:761] (5/8) Epoch 14, batch 5600, loss[loss=0.2526, simple_loss=0.3382, pruned_loss=0.0835, over 4773.00 frames.], tot_loss[loss=0.2718, simple_loss=0.3431, pruned_loss=0.1003, over 965943.88 frames.], batch size: 16, lr: 7.23e-04
2022-05-28 13:49:22,104 INFO [train.py:761] (5/8) Epoch 14, batch 5650, loss[loss=0.296, simple_loss=0.3722, pruned_loss=0.1099, over 4786.00 frames.], tot_loss[loss=0.2724, simple_loss=0.3431, pruned_loss=0.1009, over 965992.02 frames.], batch size: 13, lr: 7.23e-04
2022-05-28 13:50:00,270 INFO [train.py:761] (5/8) Epoch 14, batch 5700, loss[loss=0.3043, simple_loss=0.3692, pruned_loss=0.1197, over 4678.00 frames.], tot_loss[loss=0.2716, simple_loss=0.3422, pruned_loss=0.1005, over 966230.31 frames.], batch size: 13, lr: 7.23e-04
2022-05-28 13:50:38,731 INFO [train.py:761] (5/8) Epoch 14, batch 5750, loss[loss=0.2711, simple_loss=0.3466, pruned_loss=0.09785, over 4724.00 frames.], tot_loss[loss=0.2701, simple_loss=0.3409, pruned_loss=0.09958, over 965721.48 frames.], batch size: 13, lr: 7.23e-04
2022-05-28 13:51:16,677 INFO [train.py:761] (5/8) Epoch 14, batch 5800, loss[loss=0.2559, simple_loss=0.3425, pruned_loss=0.08468, over 4730.00 frames.], tot_loss[loss=0.2697, simple_loss=0.3408, pruned_loss=0.09929, over 966260.40 frames.], batch size: 14, lr: 7.23e-04
2022-05-28 13:51:55,390 INFO [train.py:761] (5/8) Epoch 14, batch 5850, loss[loss=0.3142, simple_loss=0.391, pruned_loss=0.1187, over 4849.00 frames.], tot_loss[loss=0.2705, simple_loss=0.3414, pruned_loss=0.09977, over 966219.19 frames.], batch size: 14, lr: 7.22e-04
2022-05-28 13:52:33,221 INFO [train.py:761] (5/8) Epoch 14, batch 5900, loss[loss=0.2727, simple_loss=0.3563, pruned_loss=0.09452, over 4978.00 frames.], tot_loss[loss=0.2708, simple_loss=0.3425, pruned_loss=0.0995, over 966300.76 frames.], batch size: 14, lr: 7.22e-04
2022-05-28 13:53:11,754 INFO [train.py:761] (5/8) Epoch 14, batch 5950, loss[loss=0.2623, simple_loss=0.3219, pruned_loss=0.1014, over 4662.00 frames.], tot_loss[loss=0.272, simple_loss=0.3434, pruned_loss=0.1004, over 966058.00 frames.], batch size: 12, lr: 7.22e-04
2022-05-28 13:53:50,450 INFO [train.py:761] (5/8) Epoch 14, batch 6000, loss[loss=0.2682, simple_loss=0.3607, pruned_loss=0.08784, over 4785.00 frames.], tot_loss[loss=0.2727, simple_loss=0.344, pruned_loss=0.1007, over 967074.34 frames.], batch size: 15, lr: 7.22e-04
2022-05-28 13:53:50,451 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 13:54:00,247 INFO [train.py:790] (5/8) Epoch 14, validation: loss=0.2163, simple_loss=0.3211, pruned_loss=0.05573, over 944034.00 frames.
2022-05-28 13:54:38,373 INFO [train.py:761] (5/8) Epoch 14, batch 6050, loss[loss=0.2942, simple_loss=0.3619, pruned_loss=0.1132, over 4944.00 frames.], tot_loss[loss=0.2725, simple_loss=0.3434, pruned_loss=0.1008, over 966813.70 frames.], batch size: 16, lr: 7.22e-04
2022-05-28 13:55:16,749 INFO [train.py:761] (5/8) Epoch 14, batch 6100, loss[loss=0.2761, simple_loss=0.3605, pruned_loss=0.09587, over 4911.00 frames.], tot_loss[loss=0.274, simple_loss=0.3446, pruned_loss=0.1017, over 967124.25 frames.], batch size: 14, lr: 7.22e-04
2022-05-28 13:55:55,627 INFO [train.py:761] (5/8) Epoch 14, batch 6150, loss[loss=0.2546, simple_loss=0.3511, pruned_loss=0.07904, over 4912.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3443, pruned_loss=0.1014, over 966776.61 frames.], batch size: 14, lr: 7.21e-04
2022-05-28 13:56:33,773 INFO [train.py:761] (5/8) Epoch 14, batch 6200, loss[loss=0.2701, simple_loss=0.3478, pruned_loss=0.0962, over 4906.00 frames.], tot_loss[loss=0.2723, simple_loss=0.3427, pruned_loss=0.101, over 966800.49 frames.], batch size: 14, lr: 7.21e-04
2022-05-28 13:57:12,381 INFO [train.py:761] (5/8) Epoch 14, batch 6250, loss[loss=0.2703, simple_loss=0.345, pruned_loss=0.09784, over 4921.00 frames.], tot_loss[loss=0.2717, simple_loss=0.3417, pruned_loss=0.1009, over 967013.15 frames.], batch size: 13, lr: 7.21e-04
2022-05-28 13:57:50,233 INFO [train.py:761] (5/8) Epoch 14, batch 6300, loss[loss=0.2621, simple_loss=0.3539, pruned_loss=0.08516, over 4780.00 frames.], tot_loss[loss=0.2712, simple_loss=0.3417, pruned_loss=0.1004, over 965888.81 frames.], batch size: 13, lr: 7.21e-04
2022-05-28 13:58:28,376 INFO [train.py:761] (5/8) Epoch 14, batch 6350, loss[loss=0.2245, simple_loss=0.303, pruned_loss=0.07295, over 4711.00 frames.], tot_loss[loss=0.2715, simple_loss=0.3424, pruned_loss=0.1003, over 965533.59 frames.], batch size: 14, lr: 7.21e-04
2022-05-28 13:59:06,725 INFO [train.py:761] (5/8) Epoch 14, batch 6400, loss[loss=0.2684, simple_loss=0.334, pruned_loss=0.1014, over 4736.00 frames.], tot_loss[loss=0.2697, simple_loss=0.3407, pruned_loss=0.09938, over 964460.26 frames.], batch size: 12, lr: 7.20e-04
2022-05-28 13:59:45,173 INFO [train.py:761] (5/8) Epoch 14, batch 6450, loss[loss=0.2982, simple_loss=0.3676, pruned_loss=0.1144, over 4870.00 frames.], tot_loss[loss=0.2694, simple_loss=0.3399, pruned_loss=0.09949, over 964617.59 frames.], batch size: 18, lr: 7.20e-04
2022-05-28 14:00:23,206 INFO [train.py:761] (5/8) Epoch 14, batch 6500, loss[loss=0.2383, simple_loss=0.3248, pruned_loss=0.07589, over 4856.00 frames.], tot_loss[loss=0.2687, simple_loss=0.34, pruned_loss=0.09866, over 964875.84 frames.], batch size: 17, lr: 7.20e-04
2022-05-28 14:01:01,720 INFO [train.py:761] (5/8) Epoch 14, batch 6550, loss[loss=0.2604, simple_loss=0.3279, pruned_loss=0.09647, over 4809.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3396, pruned_loss=0.09832, over 964884.37 frames.], batch size: 12, lr: 7.20e-04
2022-05-28 14:01:39,763 INFO [train.py:761] (5/8) Epoch 14, batch 6600, loss[loss=0.2308, simple_loss=0.3212, pruned_loss=0.07016, over 4977.00 frames.], tot_loss[loss=0.269, simple_loss=0.3407, pruned_loss=0.09868, over 965596.57 frames.], batch size: 14, lr: 7.20e-04
2022-05-28 14:02:18,290 INFO [train.py:761] (5/8) Epoch 14, batch 6650, loss[loss=0.3015, simple_loss=0.3695, pruned_loss=0.1167, over 4976.00 frames.], tot_loss[loss=0.2708, simple_loss=0.3421, pruned_loss=0.09975, over 966646.94 frames.], batch size: 15, lr: 7.19e-04
2022-05-28 14:02:56,768 INFO [train.py:761] (5/8) Epoch 14, batch 6700, loss[loss=0.2838, simple_loss=0.3637, pruned_loss=0.1019, over 4966.00 frames.], tot_loss[loss=0.2721, simple_loss=0.3439, pruned_loss=0.1002, over 967896.73 frames.], batch size: 16, lr: 7.19e-04
2022-05-28 14:03:50,389 INFO [train.py:761] (5/8) Epoch 15, batch 0, loss[loss=0.2355, simple_loss=0.3218, pruned_loss=0.07457, over 4727.00 frames.], tot_loss[loss=0.2355, simple_loss=0.3218, pruned_loss=0.07457, over 4727.00 frames.], batch size: 13, lr: 7.19e-04
2022-05-28 14:04:28,680 INFO [train.py:761] (5/8) Epoch 15, batch 50, loss[loss=0.2497, simple_loss=0.3408, pruned_loss=0.07934, over 4843.00 frames.], tot_loss[loss=0.2482, simple_loss=0.3339, pruned_loss=0.08119, over 218294.48 frames.], batch size: 18, lr: 7.19e-04
2022-05-28 14:05:06,928 INFO [train.py:761] (5/8) Epoch 15, batch 100, loss[loss=0.2555, simple_loss=0.3402, pruned_loss=0.0854, over 4669.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3315, pruned_loss=0.0804, over 383476.11 frames.], batch size: 13, lr: 7.19e-04
2022-05-28 14:05:44,990 INFO [train.py:761] (5/8) Epoch 15, batch 150, loss[loss=0.2206, simple_loss=0.3161, pruned_loss=0.06252, over 4932.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3303, pruned_loss=0.07893, over 512142.92 frames.], batch size: 26, lr: 7.18e-04
2022-05-28 14:06:23,261 INFO [train.py:761] (5/8) Epoch 15, batch 200, loss[loss=0.2131, simple_loss=0.3039, pruned_loss=0.06111, over 4974.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3278, pruned_loss=0.07802, over 611932.02 frames.], batch size: 12, lr: 7.18e-04
2022-05-28 14:07:00,569 INFO [train.py:761] (5/8) Epoch 15, batch 250, loss[loss=0.2355, simple_loss=0.3205, pruned_loss=0.07527, over 4892.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3285, pruned_loss=0.07835, over 691849.99 frames.], batch size: 15, lr: 7.18e-04
2022-05-28 14:07:38,980 INFO [train.py:761] (5/8) Epoch 15, batch 300, loss[loss=0.2389, simple_loss=0.3326, pruned_loss=0.07256, over 4769.00 frames.], tot_loss[loss=0.2438, simple_loss=0.3297, pruned_loss=0.07895, over 753569.63 frames.], batch size: 15, lr: 7.18e-04
2022-05-28 14:08:16,684 INFO [train.py:761] (5/8) Epoch 15, batch 350, loss[loss=0.2465, simple_loss=0.343, pruned_loss=0.07503, over 4904.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3284, pruned_loss=0.07819, over 800400.68 frames.], batch size: 17, lr: 7.18e-04
2022-05-28 14:08:55,003 INFO [train.py:761] (5/8) Epoch 15, batch 400, loss[loss=0.2158, simple_loss=0.2978, pruned_loss=0.06687, over 4722.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3265, pruned_loss=0.07746, over 838228.04 frames.], batch size: 14, lr: 7.18e-04
2022-05-28 14:09:32,921 INFO [train.py:761] (5/8) Epoch 15, batch 450, loss[loss=0.2604, simple_loss=0.3411, pruned_loss=0.08991, over 4785.00 frames.], tot_loss[loss=0.2395, simple_loss=0.3254, pruned_loss=0.07683, over 866834.23 frames.], batch size: 16, lr: 7.17e-04
2022-05-28 14:10:11,412 INFO [train.py:761] (5/8) Epoch 15, batch 500, loss[loss=0.2466, simple_loss=0.3476, pruned_loss=0.07283, over 4787.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3248, pruned_loss=0.07609, over 888250.30 frames.], batch size: 14, lr: 7.17e-04
2022-05-28 14:10:49,588 INFO [train.py:761] (5/8) Epoch 15, batch 550, loss[loss=0.1989, simple_loss=0.3082, pruned_loss=0.0448, over 4911.00 frames.], tot_loss[loss=0.2362, simple_loss=0.3228, pruned_loss=0.07482, over 905546.82 frames.], batch size: 14, lr: 7.17e-04
2022-05-28 14:11:26,989 INFO [train.py:761] (5/8) Epoch 15, batch 600, loss[loss=0.2245, simple_loss=0.3176, pruned_loss=0.06566, over 4919.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3221, pruned_loss=0.07417, over 919039.49 frames.], batch size: 13, lr: 7.17e-04
2022-05-28 14:12:04,756 INFO [train.py:761] (5/8) Epoch 15, batch 650, loss[loss=0.1977, simple_loss=0.2721, pruned_loss=0.06168, over 4562.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3235, pruned_loss=0.07401, over 930616.08 frames.], batch size: 10, lr: 7.17e-04
2022-05-28 14:12:43,123 INFO [train.py:761] (5/8) Epoch 15, batch 700, loss[loss=0.2695, simple_loss=0.3608, pruned_loss=0.08909, over 4725.00 frames.], tot_loss[loss=0.2373, simple_loss=0.3242, pruned_loss=0.07521, over 937974.32 frames.], batch size: 14, lr: 7.16e-04
2022-05-28 14:13:20,733 INFO [train.py:761] (5/8) Epoch 15, batch 750, loss[loss=0.2373, simple_loss=0.3056, pruned_loss=0.08446, over 4647.00 frames.], tot_loss[loss=0.2408, simple_loss=0.3268, pruned_loss=0.07746, over 943274.15 frames.], batch size: 11, lr: 7.16e-04
2022-05-28 14:13:58,582 INFO [train.py:761] (5/8) Epoch 15, batch 800, loss[loss=0.2219, simple_loss=0.2969, pruned_loss=0.07341, over 4806.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3287, pruned_loss=0.07855, over 949537.25 frames.], batch size: 12, lr: 7.16e-04
2022-05-28 14:14:36,252 INFO [train.py:761] (5/8) Epoch 15, batch 850, loss[loss=0.284, simple_loss=0.3811, pruned_loss=0.09347, over 4769.00 frames.], tot_loss[loss=0.2445, simple_loss=0.33, pruned_loss=0.07951, over 954655.03 frames.], batch size: 15, lr: 7.16e-04
2022-05-28 14:15:14,310 INFO [train.py:761] (5/8) Epoch 15, batch 900, loss[loss=0.2101, simple_loss=0.2883, pruned_loss=0.0659, over 4732.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3294, pruned_loss=0.07926, over 956185.68 frames.], batch size: 11, lr: 7.16e-04
2022-05-28 14:15:51,984 INFO [train.py:761] (5/8) Epoch 15, batch 950, loss[loss=0.2598, simple_loss=0.3446, pruned_loss=0.08752, over 4966.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3303, pruned_loss=0.08012, over 959304.65 frames.], batch size: 14, lr: 7.15e-04
2022-05-28 14:16:30,062 INFO [train.py:761] (5/8) Epoch 15, batch 1000, loss[loss=0.22, simple_loss=0.3029, pruned_loss=0.06857, over 4980.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3313, pruned_loss=0.0805, over 959867.08 frames.], batch size: 12, lr: 7.15e-04
2022-05-28 14:17:08,321 INFO [train.py:761] (5/8) Epoch 15, batch 1050, loss[loss=0.2773, simple_loss=0.3644, pruned_loss=0.09514, over 4905.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3309, pruned_loss=0.08008, over 960978.11 frames.], batch size: 14, lr: 7.15e-04
2022-05-28 14:17:45,698 INFO [train.py:761] (5/8) Epoch 15, batch 1100, loss[loss=0.2197, simple_loss=0.3123, pruned_loss=0.06355, over 4724.00 frames.], tot_loss[loss=0.2458, simple_loss=0.3313, pruned_loss=0.0802, over 962328.38 frames.], batch size: 14, lr: 7.15e-04
2022-05-28 14:18:23,653 INFO [train.py:761] (5/8) Epoch 15, batch 1150, loss[loss=0.2991, simple_loss=0.3797, pruned_loss=0.1092, over 4771.00 frames.], tot_loss[loss=0.2432, simple_loss=0.329, pruned_loss=0.07872, over 963467.60 frames.], batch size: 15, lr: 7.15e-04
2022-05-28 14:19:01,891 INFO [train.py:761] (5/8) Epoch 15, batch 1200, loss[loss=0.2155, simple_loss=0.3023, pruned_loss=0.06436, over 4800.00 frames.], tot_loss[loss=0.2427, simple_loss=0.3286, pruned_loss=0.07841, over 963496.47 frames.], batch size: 12, lr: 7.15e-04
2022-05-28 14:19:39,641 INFO [train.py:761] (5/8) Epoch 15, batch 1250, loss[loss=0.2695, simple_loss=0.3455, pruned_loss=0.09679, over 4856.00 frames.], tot_loss[loss=0.2443, simple_loss=0.3295, pruned_loss=0.07949, over 964434.12 frames.], batch size: 13, lr: 7.14e-04
2022-05-28 14:20:17,921 INFO [train.py:761] (5/8) Epoch 15, batch 1300, loss[loss=0.2428, simple_loss=0.3281, pruned_loss=0.07876, over 4791.00 frames.], tot_loss[loss=0.2446, simple_loss=0.3298, pruned_loss=0.07974, over 966078.24 frames.], batch size: 13, lr: 7.14e-04
2022-05-28 14:20:56,276 INFO [train.py:761] (5/8) Epoch 15, batch 1350, loss[loss=0.2732, simple_loss=0.349, pruned_loss=0.09868, over 4826.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3307, pruned_loss=0.08016, over 966372.65 frames.], batch size: 18, lr: 7.14e-04
2022-05-28 14:21:34,481 INFO [train.py:761] (5/8) Epoch 15, batch 1400, loss[loss=0.2386, simple_loss=0.3273, pruned_loss=0.07493, over 4847.00 frames.], tot_loss[loss=0.246, simple_loss=0.3313, pruned_loss=0.08033, over 967323.81 frames.], batch size: 13, lr: 7.14e-04
2022-05-28 14:22:12,308 INFO [train.py:761] (5/8) Epoch 15, batch 1450, loss[loss=0.2459, simple_loss=0.3388, pruned_loss=0.07648, over 4794.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3304, pruned_loss=0.07959, over 967977.94 frames.], batch size: 14, lr: 7.14e-04
2022-05-28 14:22:50,567 INFO [train.py:761] (5/8) Epoch 15, batch 1500, loss[loss=0.2596, simple_loss=0.3423, pruned_loss=0.08843, over 4893.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3321, pruned_loss=0.08026, over 968087.05 frames.], batch size: 15, lr: 7.13e-04
2022-05-28 14:23:28,785 INFO [train.py:761] (5/8) Epoch 15, batch 1550, loss[loss=0.2058, simple_loss=0.2935, pruned_loss=0.05899, over 4819.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3319, pruned_loss=0.08038, over 967401.12 frames.], batch size: 12, lr: 7.13e-04
2022-05-28 14:24:09,595 INFO [train.py:761] (5/8) Epoch 15, batch 1600, loss[loss=0.2274, simple_loss=0.3095, pruned_loss=0.0727, over 4779.00 frames.], tot_loss[loss=0.246, simple_loss=0.332, pruned_loss=0.07993, over 967460.43 frames.], batch size: 13, lr: 7.13e-04
2022-05-28 14:24:47,463 INFO [train.py:761] (5/8) Epoch 15, batch 1650, loss[loss=0.1924, simple_loss=0.2862, pruned_loss=0.04929, over 4990.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3289, pruned_loss=0.07908, over 967448.97 frames.], batch size: 13, lr: 7.13e-04
2022-05-28 14:25:25,479 INFO [train.py:761] (5/8) Epoch 15, batch 1700, loss[loss=0.2934, simple_loss=0.3551, pruned_loss=0.1158, over 4760.00 frames.], tot_loss[loss=0.2454, simple_loss=0.3304, pruned_loss=0.08019, over 967393.76 frames.], batch size: 15, lr: 7.13e-04
2022-05-28 14:26:03,596 INFO [train.py:761] (5/8) Epoch 15, batch 1750, loss[loss=0.2408, simple_loss=0.3383, pruned_loss=0.0717, over 4874.00 frames.], tot_loss[loss=0.2465, simple_loss=0.3321, pruned_loss=0.08046, over 967451.42 frames.], batch size: 15, lr: 7.12e-04
2022-05-28 14:26:41,715 INFO [train.py:761] (5/8) Epoch 15, batch 1800, loss[loss=0.2222, simple_loss=0.3035, pruned_loss=0.07045, over 4734.00 frames.], tot_loss[loss=0.246, simple_loss=0.3319, pruned_loss=0.08012, over 968270.80 frames.], batch size: 12, lr: 7.12e-04
2022-05-28 14:27:19,504 INFO [train.py:761] (5/8) Epoch 15, batch 1850, loss[loss=0.2318, simple_loss=0.3302, pruned_loss=0.06669, over 4784.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3319, pruned_loss=0.08032, over 967642.84 frames.], batch size: 15, lr: 7.12e-04
2022-05-28 14:27:57,245 INFO [train.py:761] (5/8) Epoch 15, batch 1900, loss[loss=0.2684, simple_loss=0.3501, pruned_loss=0.09333, over 4787.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3322, pruned_loss=0.08015, over 968111.80 frames.], batch size: 16, lr: 7.12e-04
2022-05-28 14:28:35,021 INFO [train.py:761] (5/8) Epoch 15, batch 1950, loss[loss=0.1964, simple_loss=0.2755, pruned_loss=0.05865, over 4973.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3329, pruned_loss=0.0802, over 967995.63 frames.], batch size: 12, lr: 7.12e-04
2022-05-28 14:29:12,731 INFO [train.py:761] (5/8) Epoch 15, batch 2000, loss[loss=0.2346, simple_loss=0.3251, pruned_loss=0.07206, over 4734.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3308, pruned_loss=0.07937, over 967237.88 frames.], batch size: 13, lr: 7.12e-04
2022-05-28 14:29:50,796 INFO [train.py:761] (5/8) Epoch 15, batch 2050, loss[loss=0.2181, simple_loss=0.3023, pruned_loss=0.06689, over 4911.00 frames.], tot_loss[loss=0.2432, simple_loss=0.3299, pruned_loss=0.07825, over 966893.83 frames.], batch size: 13, lr: 7.11e-04
2022-05-28 14:30:29,074 INFO [train.py:761] (5/8) Epoch 15, batch 2100, loss[loss=0.2595, simple_loss=0.3384, pruned_loss=0.09029, over 4778.00 frames.], tot_loss[loss=0.2443, simple_loss=0.3311, pruned_loss=0.07872, over 967195.40 frames.], batch size: 15, lr: 7.11e-04
2022-05-28 14:31:06,654 INFO [train.py:761] (5/8) Epoch 15, batch 2150, loss[loss=0.2488, simple_loss=0.3341, pruned_loss=0.08177, over 4915.00 frames.], tot_loss[loss=0.2438, simple_loss=0.3306, pruned_loss=0.07848, over 966619.92 frames.], batch size: 14, lr: 7.11e-04
2022-05-28 14:31:44,912 INFO [train.py:761] (5/8) Epoch 15, batch 2200, loss[loss=0.2341, simple_loss=0.339, pruned_loss=0.06459, over 4978.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3294, pruned_loss=0.07789, over 965726.64 frames.], batch size: 15, lr: 7.11e-04
2022-05-28 14:32:23,345 INFO [train.py:761] (5/8) Epoch 15, batch 2250, loss[loss=0.2076, simple_loss=0.2905, pruned_loss=0.0624, over 4985.00 frames.], tot_loss[loss=0.2425, simple_loss=0.3292, pruned_loss=0.07794, over 966269.43 frames.], batch size: 12, lr: 7.11e-04
2022-05-28 14:33:01,498 INFO [train.py:761] (5/8) Epoch 15, batch 2300, loss[loss=0.2222, simple_loss=0.3287, pruned_loss=0.05787, over 4918.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3286, pruned_loss=0.07725, over 966767.89 frames.], batch size: 14, lr: 7.10e-04
2022-05-28 14:33:38,938 INFO [train.py:761] (5/8) Epoch 15, batch 2350, loss[loss=0.2512, simple_loss=0.3309, pruned_loss=0.08577, over 4872.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3287, pruned_loss=0.07711, over 967036.47 frames.], batch size: 17, lr: 7.10e-04
2022-05-28 14:34:16,820 INFO [train.py:761] (5/8) Epoch 15, batch 2400, loss[loss=0.1794, simple_loss=0.2596, pruned_loss=0.04963, over 4633.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3288, pruned_loss=0.07752, over 967069.19 frames.], batch size: 11, lr: 7.10e-04
2022-05-28 14:34:54,850 INFO [train.py:761] (5/8) Epoch 15, batch 2450, loss[loss=0.2456, simple_loss=0.3289, pruned_loss=0.08118, over 4820.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3287, pruned_loss=0.07775, over 966733.41 frames.], batch size: 18, lr: 7.10e-04
2022-05-28 14:35:32,823 INFO [train.py:761] (5/8) Epoch 15, batch 2500, loss[loss=0.2284, simple_loss=0.328, pruned_loss=0.06442, over 4852.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3284, pruned_loss=0.07756, over 967288.30 frames.], batch size: 18, lr: 7.10e-04
2022-05-28 14:36:10,802 INFO [train.py:761] (5/8) Epoch 15, batch 2550, loss[loss=0.2507, simple_loss=0.3428, pruned_loss=0.07927, over 4888.00 frames.], tot_loss[loss=0.2409, simple_loss=0.3274, pruned_loss=0.07724, over 966349.43 frames.], batch size: 17, lr: 7.10e-04
2022-05-28 14:36:48,846 INFO [train.py:761] (5/8) Epoch 15, batch 2600, loss[loss=0.214, simple_loss=0.2959, pruned_loss=0.06605, over 4962.00 frames.], tot_loss[loss=0.2416, simple_loss=0.328, pruned_loss=0.07761, over 966958.61 frames.], batch size: 12, lr: 7.09e-04
2022-05-28 14:37:26,851 INFO [train.py:761] (5/8) Epoch 15, batch 2650, loss[loss=0.2542, simple_loss=0.3446, pruned_loss=0.08187, over 4989.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3291, pruned_loss=0.07776, over 967165.81 frames.], batch size: 21, lr: 7.09e-04
2022-05-28 14:38:04,664 INFO [train.py:761] (5/8) Epoch 15, batch 2700, loss[loss=0.2684, simple_loss=0.346, pruned_loss=0.09542, over 4866.00 frames.], tot_loss[loss=0.2416, simple_loss=0.3287, pruned_loss=0.07731, over 967004.04 frames.], batch size: 17, lr: 7.09e-04
2022-05-28 14:38:42,849 INFO [train.py:761] (5/8) Epoch 15, batch 2750, loss[loss=0.2692, simple_loss=0.3445, pruned_loss=0.09695, over 4793.00 frames.], tot_loss[loss=0.241, simple_loss=0.3283, pruned_loss=0.07683, over 966772.66 frames.], batch size: 16, lr: 7.09e-04
2022-05-28 14:39:20,690 INFO [train.py:761] (5/8) Epoch 15, batch 2800, loss[loss=0.213, simple_loss=0.3169, pruned_loss=0.05451, over 4803.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3277, pruned_loss=0.07657, over 965826.18 frames.], batch size: 12, lr: 7.09e-04
2022-05-28 14:39:58,861 INFO [train.py:761] (5/8) Epoch 15, batch 2850, loss[loss=0.213, simple_loss=0.3106, pruned_loss=0.05775, over 4811.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3283, pruned_loss=0.07655, over 966625.80 frames.], batch size: 16, lr: 7.08e-04
2022-05-28 14:40:36,582 INFO [train.py:761] (5/8) Epoch 15, batch 2900, loss[loss=0.2016, simple_loss=0.2906, pruned_loss=0.05637, over 4978.00 frames.], tot_loss[loss=0.2394, simple_loss=0.3267, pruned_loss=0.07606, over 965672.45 frames.], batch size: 12, lr: 7.08e-04
2022-05-28 14:41:14,492 INFO [train.py:761] (5/8) Epoch 15, batch 2950, loss[loss=0.259, simple_loss=0.3504, pruned_loss=0.08378, over 4805.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3272, pruned_loss=0.07662, over 966725.49 frames.], batch size: 20, lr: 7.08e-04
2022-05-28 14:41:52,599 INFO [train.py:761] (5/8) Epoch 15, batch 3000, loss[loss=0.2697, simple_loss=0.3586, pruned_loss=0.09034, over 4919.00 frames.], tot_loss[loss=0.24, simple_loss=0.3269, pruned_loss=0.07657, over 966931.67 frames.], batch size: 26, lr: 7.08e-04
2022-05-28 14:41:52,600 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 14:42:02,612 INFO [train.py:790] (5/8) Epoch 15, validation: loss=0.2173, simple_loss=0.3203, pruned_loss=0.05712, over 944034.00 frames.
2022-05-28 14:42:40,034 INFO [train.py:761] (5/8) Epoch 15, batch 3050, loss[loss=0.302, simple_loss=0.3464, pruned_loss=0.1288, over 4992.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3266, pruned_loss=0.07653, over 966960.37 frames.], batch size: 12, lr: 7.08e-04
2022-05-28 14:43:18,602 INFO [train.py:761] (5/8) Epoch 15, batch 3100, loss[loss=0.2467, simple_loss=0.3313, pruned_loss=0.08099, over 4673.00 frames.], tot_loss[loss=0.2413, simple_loss=0.3276, pruned_loss=0.07743, over 966748.53 frames.], batch size: 13, lr: 7.08e-04
2022-05-28 14:43:56,524 INFO [train.py:761] (5/8) Epoch 15, batch 3150, loss[loss=0.2666, simple_loss=0.3575, pruned_loss=0.08784, over 4774.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3298, pruned_loss=0.07998, over 966874.62 frames.], batch size: 15, lr: 7.07e-04
2022-05-28 14:44:34,820 INFO [train.py:761] (5/8) Epoch 15, batch 3200, loss[loss=0.2933, simple_loss=0.3589, pruned_loss=0.1139, over 4913.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3331, pruned_loss=0.08363, over 966090.09 frames.], batch size: 14, lr: 7.07e-04
2022-05-28 14:45:12,615 INFO [train.py:761] (5/8) Epoch 15, batch 3250, loss[loss=0.2639, simple_loss=0.3286, pruned_loss=0.09965, over 4973.00 frames.], tot_loss[loss=0.253, simple_loss=0.3345, pruned_loss=0.08581, over 965379.69 frames.], batch size: 14, lr: 7.07e-04
2022-05-28 14:45:50,556 INFO [train.py:761] (5/8) Epoch 15, batch 3300, loss[loss=0.2273, simple_loss=0.2963, pruned_loss=0.07917, over 4826.00 frames.], tot_loss[loss=0.2556, simple_loss=0.3357, pruned_loss=0.08781, over 966580.57 frames.], batch size: 11, lr: 7.07e-04
2022-05-28 14:46:28,373 INFO [train.py:761] (5/8) Epoch 15, batch 3350, loss[loss=0.2215, simple_loss=0.2906, pruned_loss=0.07621, over 4891.00 frames.], tot_loss[loss=0.2564, simple_loss=0.335, pruned_loss=0.08894, over 967303.31 frames.], batch size: 12, lr: 7.07e-04
2022-05-28 14:47:06,448 INFO [train.py:761] (5/8) Epoch 15, batch 3400, loss[loss=0.295, simple_loss=0.3541, pruned_loss=0.118, over 4656.00 frames.], tot_loss[loss=0.2607, simple_loss=0.3378, pruned_loss=0.09179, over 966599.50 frames.], batch size: 12, lr: 7.06e-04
2022-05-28 14:47:44,496 INFO [train.py:761] (5/8) Epoch 15, batch 3450, loss[loss=0.2805, simple_loss=0.3623, pruned_loss=0.09937, over 4882.00 frames.], tot_loss[loss=0.261, simple_loss=0.3373, pruned_loss=0.09238, over 965584.44 frames.], batch size: 15, lr: 7.06e-04
2022-05-28 14:48:23,097 INFO [train.py:761] (5/8) Epoch 15, batch 3500, loss[loss=0.2857, simple_loss=0.356, pruned_loss=0.1077, over 4760.00 frames.], tot_loss[loss=0.2617, simple_loss=0.3368, pruned_loss=0.09326, over 964859.83 frames.], batch size: 15, lr: 7.06e-04
2022-05-28 14:49:01,331 INFO [train.py:761] (5/8) Epoch 15, batch 3550, loss[loss=0.2821, simple_loss=0.356, pruned_loss=0.1041, over 4799.00 frames.], tot_loss[loss=0.2605, simple_loss=0.3356, pruned_loss=0.09267, over 964871.33 frames.], batch size: 20, lr: 7.06e-04
2022-05-28 14:49:39,579 INFO [train.py:761] (5/8) Epoch 15, batch 3600, loss[loss=0.2693, simple_loss=0.3289, pruned_loss=0.1049, over 4818.00 frames.], tot_loss[loss=0.2633, simple_loss=0.337, pruned_loss=0.09476, over 965617.46 frames.], batch size: 11, lr: 7.06e-04
2022-05-28 14:50:17,274 INFO [train.py:761] (5/8) Epoch 15, batch 3650, loss[loss=0.2256, simple_loss=0.2898, pruned_loss=0.08069, over 4870.00 frames.], tot_loss[loss=0.264, simple_loss=0.337, pruned_loss=0.09552, over 964583.08 frames.], batch size: 12, lr: 7.06e-04
2022-05-28 14:50:56,016 INFO [train.py:761] (5/8) Epoch 15, batch 3700, loss[loss=0.3748, simple_loss=0.4066, pruned_loss=0.1715, over 4972.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3379, pruned_loss=0.09627, over 964847.60 frames.], batch size: 15, lr: 7.05e-04
2022-05-28 14:51:34,026 INFO [train.py:761] (5/8) Epoch 15, batch 3750, loss[loss=0.2569, simple_loss=0.3305, pruned_loss=0.09164, over 4917.00 frames.], tot_loss[loss=0.2658, simple_loss=0.3385, pruned_loss=0.09656, over 965972.35 frames.], batch size: 14, lr: 7.05e-04
2022-05-28 14:52:12,092 INFO [train.py:761] (5/8) Epoch 15, batch 3800, loss[loss=0.2423, simple_loss=0.3197, pruned_loss=0.08247, over 4639.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3398, pruned_loss=0.09754, over 965354.00 frames.], batch size: 11, lr: 7.05e-04
2022-05-28 14:52:49,883 INFO [train.py:761] (5/8) Epoch 15, batch 3850, loss[loss=0.2364, simple_loss=0.2953, pruned_loss=0.08873, over 4804.00 frames.], tot_loss[loss=0.2666, simple_loss=0.3387, pruned_loss=0.09722, over 966256.35 frames.], batch size: 12, lr: 7.05e-04
2022-05-28 14:53:28,430 INFO [train.py:761] (5/8) Epoch 15, batch 3900, loss[loss=0.2863, simple_loss=0.3453, pruned_loss=0.1136, over 4854.00 frames.], tot_loss[loss=0.2668, simple_loss=0.3387, pruned_loss=0.09748, over 966504.47 frames.], batch size: 13, lr: 7.05e-04
2022-05-28 14:54:06,566 INFO [train.py:761] (5/8) Epoch 15, batch 3950, loss[loss=0.2529, simple_loss=0.3175, pruned_loss=0.09418, over 4663.00 frames.], tot_loss[loss=0.2682, simple_loss=0.3392, pruned_loss=0.09857, over 965956.41 frames.], batch size: 12, lr: 7.04e-04
2022-05-28 14:54:44,431 INFO [train.py:761] (5/8) Epoch 15, batch 4000, loss[loss=0.2858, simple_loss=0.3425, pruned_loss=0.1146, over 4912.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3397, pruned_loss=0.09907, over 965562.01 frames.], batch size: 13, lr: 7.04e-04
2022-05-28 14:55:22,986 INFO [train.py:761] (5/8) Epoch 15, batch 4050, loss[loss=0.2497, simple_loss=0.33, pruned_loss=0.08471, over 4914.00 frames.], tot_loss[loss=0.2683, simple_loss=0.3391, pruned_loss=0.09876, over 965343.10 frames.], batch size: 13, lr: 7.04e-04
2022-05-28 14:56:01,845 INFO [train.py:761] (5/8) Epoch 15, batch 4100, loss[loss=0.2395, simple_loss=0.334, pruned_loss=0.07249, over 4791.00 frames.], tot_loss[loss=0.2688, simple_loss=0.3398, pruned_loss=0.09885, over 965878.71 frames.], batch size: 14, lr: 7.04e-04
2022-05-28 14:56:39,928 INFO [train.py:761] (5/8) Epoch 15, batch 4150, loss[loss=0.2616, simple_loss=0.3235, pruned_loss=0.09989, over 4717.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3397, pruned_loss=0.09903, over 965977.34 frames.], batch size: 12, lr: 7.04e-04
2022-05-28 14:57:18,556 INFO [train.py:761] (5/8) Epoch 15, batch 4200, loss[loss=0.2364, simple_loss=0.3057, pruned_loss=0.08361, over 4970.00 frames.], tot_loss[loss=0.268, simple_loss=0.3393, pruned_loss=0.09836, over 967041.16 frames.], batch size: 11, lr: 7.04e-04
2022-05-28 14:57:56,309 INFO [train.py:761] (5/8) Epoch 15, batch 4250, loss[loss=0.2426, simple_loss=0.3253, pruned_loss=0.08, over 4657.00 frames.], tot_loss[loss=0.2671, simple_loss=0.3387, pruned_loss=0.09769, over 966369.35 frames.], batch size: 12, lr: 7.03e-04
2022-05-28 14:58:34,642 INFO [train.py:761] (5/8) Epoch 15, batch 4300, loss[loss=0.326, simple_loss=0.3963, pruned_loss=0.1278, over 4946.00 frames.], tot_loss[loss=0.2673, simple_loss=0.3394, pruned_loss=0.09763, over 967018.55 frames.], batch size: 49, lr: 7.03e-04
2022-05-28 14:59:12,361 INFO [train.py:761] (5/8) Epoch 15, batch 4350, loss[loss=0.3411, simple_loss=0.4033, pruned_loss=0.1395, over 4845.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3383, pruned_loss=0.09753, over 966806.01 frames.], batch size: 14, lr: 7.03e-04
2022-05-28 14:59:50,596 INFO [train.py:761] (5/8) Epoch 15, batch 4400, loss[loss=0.2738, simple_loss=0.3531, pruned_loss=0.09724, over 4952.00 frames.], tot_loss[loss=0.2671, simple_loss=0.3383, pruned_loss=0.09799, over 966643.56 frames.], batch size: 16, lr: 7.03e-04
2022-05-28 15:00:28,708 INFO [train.py:761] (5/8) Epoch 15, batch 4450, loss[loss=0.2987, simple_loss=0.3666, pruned_loss=0.1154, over 4788.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3382, pruned_loss=0.09755, over 966402.34 frames.], batch size: 16, lr: 7.03e-04
2022-05-28 15:01:06,820 INFO [train.py:761] (5/8) Epoch 15, batch 4500, loss[loss=0.2997, simple_loss=0.3627, pruned_loss=0.1183, over 4778.00 frames.], tot_loss[loss=0.2656, simple_loss=0.3376, pruned_loss=0.09682, over 966229.28 frames.], batch size: 16, lr: 7.02e-04
2022-05-28 15:01:44,497 INFO [train.py:761] (5/8) Epoch 15, batch 4550, loss[loss=0.2577, simple_loss=0.3359, pruned_loss=0.08975, over 4790.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3371, pruned_loss=0.09638, over 966901.78 frames.], batch size: 14, lr: 7.02e-04
2022-05-28 15:02:23,033 INFO [train.py:761] (5/8) Epoch 15, batch 4600, loss[loss=0.3184, simple_loss=0.3908, pruned_loss=0.123, over 4925.00 frames.], tot_loss[loss=0.2658, simple_loss=0.3377, pruned_loss=0.09697, over 967125.40 frames.], batch size: 51, lr: 7.02e-04
2022-05-28 15:03:01,239 INFO [train.py:761] (5/8) Epoch 15, batch 4650, loss[loss=0.203, simple_loss=0.2723, pruned_loss=0.06685, over 4842.00 frames.], tot_loss[loss=0.2655, simple_loss=0.3377, pruned_loss=0.09659, over 967027.64 frames.], batch size: 11, lr: 7.02e-04
2022-05-28 15:03:40,035 INFO [train.py:761] (5/8) Epoch 15, batch 4700, loss[loss=0.2067, simple_loss=0.2813, pruned_loss=0.06601, over 4979.00 frames.], tot_loss[loss=0.265, simple_loss=0.3375, pruned_loss=0.09627, over 967618.72 frames.], batch size: 12, lr: 7.02e-04
2022-05-28 15:04:18,432 INFO [train.py:761] (5/8) Epoch 15, batch 4750, loss[loss=0.2276, simple_loss=0.3045, pruned_loss=0.07539, over 4989.00 frames.], tot_loss[loss=0.2666, simple_loss=0.3382, pruned_loss=0.09749, over 966568.72 frames.], batch size: 13, lr: 7.02e-04
2022-05-28 15:04:56,347 INFO [train.py:761] (5/8) Epoch 15, batch 4800, loss[loss=0.2975, simple_loss=0.379, pruned_loss=0.108, over 4787.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3378, pruned_loss=0.09631, over 967023.45 frames.], batch size: 14, lr: 7.01e-04
2022-05-28 15:05:34,625 INFO [train.py:761] (5/8) Epoch 15, batch 4850, loss[loss=0.2658, simple_loss=0.3434, pruned_loss=0.09414, over 4770.00 frames.], tot_loss[loss=0.2658, simple_loss=0.3378, pruned_loss=0.09691, over 966687.76 frames.], batch size: 14, lr: 7.01e-04
2022-05-28 15:06:13,255 INFO [train.py:761] (5/8) Epoch 15, batch 4900, loss[loss=0.2729, simple_loss=0.3538, pruned_loss=0.096, over 4812.00 frames.], tot_loss[loss=0.2662, simple_loss=0.3378, pruned_loss=0.09725, over 965960.66 frames.], batch size: 20, lr: 7.01e-04
2022-05-28 15:06:51,416 INFO [train.py:761] (5/8) Epoch 15, batch 4950, loss[loss=0.2573, simple_loss=0.3463, pruned_loss=0.08414, over 4894.00 frames.], tot_loss[loss=0.2664, simple_loss=0.3382, pruned_loss=0.09729, over 966234.84 frames.], batch size: 20, lr: 7.01e-04
2022-05-28 15:07:30,105 INFO [train.py:761] (5/8) Epoch 15, batch 5000, loss[loss=0.3199, simple_loss=0.3924, pruned_loss=0.1236, over 4721.00 frames.], tot_loss[loss=0.2656, simple_loss=0.338, pruned_loss=0.09657, over 966295.73 frames.], batch size: 14, lr: 7.01e-04
2022-05-28 15:08:08,331 INFO [train.py:761] (5/8) Epoch 15, batch 5050, loss[loss=0.297, simple_loss=0.3721, pruned_loss=0.111, over 4894.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3394, pruned_loss=0.09721, over 966360.33 frames.], batch size: 26, lr: 7.01e-04
2022-05-28 15:08:46,638 INFO [train.py:761] (5/8) Epoch 15, batch 5100, loss[loss=0.2733, simple_loss=0.3432, pruned_loss=0.1017, over 4720.00 frames.], tot_loss[loss=0.2666, simple_loss=0.3391, pruned_loss=0.09705, over 966357.61 frames.], batch size: 14, lr: 7.00e-04
2022-05-28 15:09:24,588 INFO [train.py:761] (5/8) Epoch 15, batch 5150, loss[loss=0.2359, simple_loss=0.318, pruned_loss=0.07693, over 4802.00 frames.], tot_loss[loss=0.2664, simple_loss=0.3389, pruned_loss=0.09698, over 966512.49 frames.], batch size: 12, lr: 7.00e-04
2022-05-28 15:10:02,071 INFO [train.py:761] (5/8) Epoch 15, batch 5200, loss[loss=0.2561, simple_loss=0.346, pruned_loss=0.08314, over 4855.00 frames.], tot_loss[loss=0.2654, simple_loss=0.3382, pruned_loss=0.09635, over 965945.40 frames.], batch size: 18, lr: 7.00e-04
2022-05-28 15:10:40,335 INFO [train.py:761] (5/8) Epoch 15, batch 5250, loss[loss=0.2563, simple_loss=0.3366, pruned_loss=0.08804, over 4889.00 frames.], tot_loss[loss=0.2654, simple_loss=0.3383, pruned_loss=0.0962, over 965334.19 frames.], batch size: 17, lr: 7.00e-04
2022-05-28 15:11:19,040 INFO [train.py:761] (5/8) Epoch 15, batch 5300, loss[loss=0.2641, simple_loss=0.3303, pruned_loss=0.09897, over 4645.00 frames.], tot_loss[loss=0.2653, simple_loss=0.3377, pruned_loss=0.09643, over 966282.01 frames.], batch size: 11, lr: 7.00e-04
2022-05-28 15:11:57,405 INFO [train.py:761] (5/8) Epoch 15, batch 5350, loss[loss=0.303, simple_loss=0.3732, pruned_loss=0.1164, over 4721.00 frames.], tot_loss[loss=0.2641, simple_loss=0.3364, pruned_loss=0.09591, over 965111.41 frames.], batch size: 14, lr: 6.99e-04
2022-05-28 15:12:36,102 INFO [train.py:761] (5/8) Epoch 15, batch 5400, loss[loss=0.2569, simple_loss=0.3281, pruned_loss=0.09283, over 4666.00 frames.], tot_loss[loss=0.2617, simple_loss=0.3348, pruned_loss=0.09433, over 966343.41 frames.], batch size: 12, lr: 6.99e-04
2022-05-28 15:13:14,221 INFO [train.py:761] (5/8) Epoch 15, batch 5450, loss[loss=0.3218, simple_loss=0.3794, pruned_loss=0.132, over 4953.00 frames.], tot_loss[loss=0.2629, simple_loss=0.3357, pruned_loss=0.09505, over 966744.77 frames.], batch size: 47, lr: 6.99e-04
2022-05-28 15:13:52,503 INFO [train.py:761] (5/8) Epoch 15, batch 5500, loss[loss=0.1954, simple_loss=0.2764, pruned_loss=0.05725, over 4976.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3377, pruned_loss=0.09636, over 967602.86 frames.], batch size: 12, lr: 6.99e-04
2022-05-28 15:14:30,808 INFO [train.py:761] (5/8) Epoch 15, batch 5550, loss[loss=0.2134, simple_loss=0.2905, pruned_loss=0.06819, over 4633.00 frames.], tot_loss[loss=0.2655, simple_loss=0.3381, pruned_loss=0.09648, over 967078.73 frames.], batch size: 11, lr: 6.99e-04
2022-05-28 15:15:09,270 INFO [train.py:761] (5/8) Epoch 15, batch 5600, loss[loss=0.2092, simple_loss=0.2841, pruned_loss=0.06712, over 4829.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3378, pruned_loss=0.09599, over 967535.57 frames.], batch size: 11, lr: 6.99e-04
2022-05-28 15:15:47,671 INFO [train.py:761] (5/8) Epoch 15, batch 5650, loss[loss=0.2282, simple_loss=0.3098, pruned_loss=0.07329, over 4978.00 frames.], tot_loss[loss=0.2645, simple_loss=0.3373, pruned_loss=0.09585, over 967556.11 frames.], batch size: 12, lr: 6.98e-04
2022-05-28 15:16:26,519 INFO [train.py:761] (5/8) Epoch 15, batch 5700, loss[loss=0.2549, simple_loss=0.3348, pruned_loss=0.08755, over 4791.00 frames.], tot_loss[loss=0.2635, simple_loss=0.3367, pruned_loss=0.09518, over 967825.27 frames.], batch size: 16, lr: 6.98e-04
2022-05-28 15:17:04,670 INFO [train.py:761] (5/8) Epoch 15, batch 5750, loss[loss=0.2364, simple_loss=0.3226, pruned_loss=0.07507, over 4924.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3382, pruned_loss=0.09605, over 967488.37 frames.], batch size: 13, lr: 6.98e-04
2022-05-28 15:17:42,806 INFO [train.py:761] (5/8) Epoch 15, batch 5800, loss[loss=0.2713, simple_loss=0.3485, pruned_loss=0.09707, over 4898.00 frames.], tot_loss[loss=0.2639, simple_loss=0.337, pruned_loss=0.09543, over 966943.91 frames.], batch size: 17, lr: 6.98e-04
2022-05-28 15:18:21,384 INFO [train.py:761] (5/8) Epoch 15, batch 5850, loss[loss=0.328, simple_loss=0.3851, pruned_loss=0.1354, over 4885.00 frames.], tot_loss[loss=0.2637, simple_loss=0.3363, pruned_loss=0.09552, over 965803.87 frames.], batch size: 17, lr: 6.98e-04
2022-05-28 15:19:00,239 INFO [train.py:761] (5/8) Epoch 15, batch 5900, loss[loss=0.3497, simple_loss=0.4113, pruned_loss=0.1441, over 4867.00 frames.], tot_loss[loss=0.2651, simple_loss=0.3377, pruned_loss=0.09628, over 966483.85 frames.], batch size: 17, lr: 6.98e-04
2022-05-28 15:19:38,235 INFO [train.py:761] (5/8) Epoch 15, batch 5950, loss[loss=0.2556, simple_loss=0.3448, pruned_loss=0.08323, over 4859.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3376, pruned_loss=0.0961, over 966365.55 frames.], batch size: 18, lr: 6.97e-04
2022-05-28 15:20:16,728 INFO [train.py:761] (5/8) Epoch 15, batch 6000, loss[loss=0.2339, simple_loss=0.3282, pruned_loss=0.0698, over 4796.00 frames.], tot_loss[loss=0.2656, simple_loss=0.3386, pruned_loss=0.09629, over 966524.49 frames.], batch size: 14, lr: 6.97e-04
2022-05-28 15:20:16,728 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 15:20:26,647 INFO [train.py:790] (5/8) Epoch 15, validation: loss=0.21, simple_loss=0.3164, pruned_loss=0.0518, over 944034.00 frames.
2022-05-28 15:21:04,403 INFO [train.py:761] (5/8) Epoch 15, batch 6050, loss[loss=0.2639, simple_loss=0.3304, pruned_loss=0.09876, over 4744.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3394, pruned_loss=0.09722, over 966811.81 frames.], batch size: 12, lr: 6.97e-04
2022-05-28 15:21:43,053 INFO [train.py:761] (5/8) Epoch 15, batch 6100, loss[loss=0.2281, simple_loss=0.3131, pruned_loss=0.07159, over 4671.00 frames.], tot_loss[loss=0.267, simple_loss=0.3394, pruned_loss=0.09736, over 966598.44 frames.], batch size: 13, lr: 6.97e-04
2022-05-28 15:22:21,866 INFO [train.py:761] (5/8) Epoch 15, batch 6150, loss[loss=0.2757, simple_loss=0.3433, pruned_loss=0.1041, over 4881.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3375, pruned_loss=0.09611, over 966624.29 frames.], batch size: 15, lr: 6.97e-04
2022-05-28 15:23:00,794 INFO [train.py:761] (5/8) Epoch 15, batch 6200, loss[loss=0.249, simple_loss=0.3254, pruned_loss=0.08626, over 4721.00 frames.], tot_loss[loss=0.2651, simple_loss=0.337, pruned_loss=0.0966, over 966061.43 frames.], batch size: 13, lr: 6.97e-04
2022-05-28 15:23:38,946 INFO [train.py:761] (5/8) Epoch 15, batch 6250, loss[loss=0.2146, simple_loss=0.2929, pruned_loss=0.06816, over 4877.00 frames.], tot_loss[loss=0.264, simple_loss=0.3362, pruned_loss=0.09594, over 966636.55 frames.], batch size: 12, lr: 6.96e-04
2022-05-28 15:24:17,638 INFO [train.py:761] (5/8) Epoch 15, batch 6300, loss[loss=0.2811, simple_loss=0.3752, pruned_loss=0.09354, over 4968.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3379, pruned_loss=0.09625, over 966788.32 frames.], batch size: 14, lr: 6.96e-04
2022-05-28 15:24:55,737 INFO [train.py:761] (5/8) Epoch 15, batch 6350, loss[loss=0.2275, simple_loss=0.3075, pruned_loss=0.07376, over 4883.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3371, pruned_loss=0.09527, over 966493.35 frames.], batch size: 12, lr: 6.96e-04
2022-05-28 15:25:34,372 INFO [train.py:761] (5/8) Epoch 15, batch 6400, loss[loss=0.2957, simple_loss=0.3608, pruned_loss=0.1153, over 4781.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3367, pruned_loss=0.09522, over 966304.01 frames.], batch size: 14, lr: 6.96e-04
2022-05-28 15:26:12,759 INFO [train.py:761] (5/8) Epoch 15, batch 6450, loss[loss=0.2349, simple_loss=0.314, pruned_loss=0.07795, over 4772.00 frames.], tot_loss[loss=0.2648, simple_loss=0.3381, pruned_loss=0.09577, over 965441.28 frames.], batch size: 15, lr: 6.96e-04
2022-05-28 15:26:51,032 INFO [train.py:761] (5/8) Epoch 15, batch 6500, loss[loss=0.2982, simple_loss=0.3518, pruned_loss=0.1222, over 4790.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3365, pruned_loss=0.0943, over 966724.61 frames.], batch size: 16, lr: 6.95e-04
2022-05-28 15:27:28,459 INFO [train.py:761] (5/8) Epoch 15, batch 6550, loss[loss=0.3173, simple_loss=0.3769, pruned_loss=0.1289, over 4783.00 frames.], tot_loss[loss=0.264, simple_loss=0.338, pruned_loss=0.095, over 966640.32 frames.], batch size: 16, lr: 6.95e-04
2022-05-28 15:28:07,360 INFO [train.py:761] (5/8) Epoch 15, batch 6600, loss[loss=0.212, simple_loss=0.2877, pruned_loss=0.06818, over 4546.00 frames.], tot_loss[loss=0.264, simple_loss=0.338, pruned_loss=0.09497, over 965869.77 frames.], batch size: 10, lr: 6.95e-04
2022-05-28 15:28:46,018 INFO [train.py:761] (5/8) Epoch 15, batch 6650, loss[loss=0.2071, simple_loss=0.2941, pruned_loss=0.06002, over 4782.00 frames.], tot_loss[loss=0.2613, simple_loss=0.3358, pruned_loss=0.0934, over 967509.58 frames.], batch size: 13, lr: 6.95e-04
2022-05-28 15:29:24,770 INFO [train.py:761] (5/8) Epoch 15, batch 6700, loss[loss=0.2229, simple_loss=0.3169, pruned_loss=0.06445, over 4718.00 frames.], tot_loss[loss=0.2619, simple_loss=0.336, pruned_loss=0.09391, over 967880.70 frames.], batch size: 14, lr: 6.95e-04
2022-05-28 15:30:20,520 INFO [train.py:761] (5/8) Epoch 16, batch 0, loss[loss=0.2586, simple_loss=0.3541, pruned_loss=0.08152, over 4807.00 frames.], tot_loss[loss=0.2586, simple_loss=0.3541, pruned_loss=0.08152, over 4807.00 frames.], batch size: 16, lr: 6.95e-04
2022-05-28 15:30:59,017 INFO [train.py:761] (5/8) Epoch 16, batch 50, loss[loss=0.2271, simple_loss=0.3056, pruned_loss=0.07431, over 4662.00 frames.], tot_loss[loss=0.2403, simple_loss=0.3233, pruned_loss=0.07865, over 218372.56 frames.], batch size: 12, lr: 6.94e-04
2022-05-28 15:31:36,621 INFO [train.py:761] (5/8) Epoch 16, batch 100, loss[loss=0.2343, simple_loss=0.3364, pruned_loss=0.06609, over 4831.00 frames.], tot_loss[loss=0.2409, simple_loss=0.326, pruned_loss=0.07789, over 384030.57 frames.], batch size: 20, lr: 6.94e-04
2022-05-28 15:32:15,065 INFO [train.py:761] (5/8) Epoch 16, batch 150, loss[loss=0.191, simple_loss=0.2753, pruned_loss=0.05338, over 4967.00 frames.], tot_loss[loss=0.237, simple_loss=0.3223, pruned_loss=0.07583, over 513068.32 frames.], batch size: 12, lr: 6.94e-04
2022-05-28 15:32:53,005 INFO [train.py:761] (5/8) Epoch 16, batch 200, loss[loss=0.2062, simple_loss=0.2968, pruned_loss=0.05779, over 4734.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3219, pruned_loss=0.07438, over 612980.88 frames.], batch size: 12, lr: 6.94e-04
2022-05-28 15:33:30,931 INFO [train.py:761] (5/8) Epoch 16, batch 250, loss[loss=0.2113, simple_loss=0.287, pruned_loss=0.06786, over 4641.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3213, pruned_loss=0.07394, over 691097.55 frames.], batch size: 11, lr: 6.94e-04
2022-05-28 15:34:09,743 INFO [train.py:761] (5/8) Epoch 16, batch 300, loss[loss=0.2152, simple_loss=0.319, pruned_loss=0.05577, over 4973.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3206, pruned_loss=0.07362, over 752172.14 frames.], batch size: 15, lr: 6.94e-04
2022-05-28 15:34:47,682 INFO [train.py:761] (5/8) Epoch 16, batch 350, loss[loss=0.2029, simple_loss=0.2869, pruned_loss=0.05943, over 4790.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3215, pruned_loss=0.07403, over 799308.55 frames.], batch size: 12, lr: 6.93e-04
2022-05-28 15:35:25,500 INFO [train.py:761] (5/8) Epoch 16, batch 400, loss[loss=0.2852, simple_loss=0.3678, pruned_loss=0.1013, over 4850.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3216, pruned_loss=0.07354, over 836632.20 frames.], batch size: 14, lr: 6.93e-04
2022-05-28 15:36:03,376 INFO [train.py:761] (5/8) Epoch 16, batch 450, loss[loss=0.3111, simple_loss=0.3912, pruned_loss=0.1156, over 4961.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3215, pruned_loss=0.073, over 865608.08 frames.], batch size: 49, lr: 6.93e-04
2022-05-28 15:36:41,390 INFO [train.py:761] (5/8) Epoch 16, batch 500, loss[loss=0.2489, simple_loss=0.3318, pruned_loss=0.08301, over 4612.00 frames.], tot_loss[loss=0.2332, simple_loss=0.321, pruned_loss=0.07267, over 886146.57 frames.], batch size: 12, lr: 6.93e-04
2022-05-28 15:37:19,480 INFO [train.py:761] (5/8) Epoch 16, batch 550, loss[loss=0.215, simple_loss=0.2878, pruned_loss=0.07108, over 4806.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3199, pruned_loss=0.07222, over 903185.31 frames.], batch size: 12, lr: 6.93e-04
2022-05-28 15:37:56,908 INFO [train.py:761] (5/8) Epoch 16, batch 600, loss[loss=0.3305, simple_loss=0.3874, pruned_loss=0.1368, over 4952.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3198, pruned_loss=0.07228, over 916384.51 frames.], batch size: 45, lr: 6.93e-04
2022-05-28 15:38:34,867 INFO [train.py:761] (5/8) Epoch 16, batch 650, loss[loss=0.2288, simple_loss=0.3254, pruned_loss=0.06613, over 4671.00 frames.], tot_loss[loss=0.234, simple_loss=0.3214, pruned_loss=0.07332, over 927139.59 frames.], batch size: 13, lr: 6.92e-04
2022-05-28 15:39:12,595 INFO [train.py:761] (5/8) Epoch 16, batch 700, loss[loss=0.2197, simple_loss=0.3013, pruned_loss=0.06905, over 4734.00 frames.], tot_loss[loss=0.2346, simple_loss=0.322, pruned_loss=0.07358, over 936500.71 frames.], batch size: 11, lr: 6.92e-04
2022-05-28 15:39:50,850 INFO [train.py:761] (5/8) Epoch 16, batch 750, loss[loss=0.2078, simple_loss=0.2835, pruned_loss=0.06607, over 4735.00 frames.], tot_loss[loss=0.2373, simple_loss=0.324, pruned_loss=0.07527, over 942502.32 frames.], batch size: 12, lr: 6.92e-04
2022-05-28 15:40:28,913 INFO [train.py:761] (5/8) Epoch 16, batch 800, loss[loss=0.2883, simple_loss=0.3711, pruned_loss=0.1028, over 4970.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3235, pruned_loss=0.07504, over 947177.76 frames.], batch size: 46, lr: 6.92e-04
2022-05-28 15:41:06,620 INFO [train.py:761] (5/8) Epoch 16, batch 850, loss[loss=0.258, simple_loss=0.3419, pruned_loss=0.08704, over 4815.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3227, pruned_loss=0.07455, over 950135.89 frames.], batch size: 18, lr: 6.92e-04
2022-05-28 15:41:44,706 INFO [train.py:761] (5/8) Epoch 16, batch 900, loss[loss=0.2293, simple_loss=0.3297, pruned_loss=0.06443, over 4926.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3234, pruned_loss=0.07503, over 953886.61 frames.], batch size: 13, lr: 6.92e-04
2022-05-28 15:42:22,921 INFO [train.py:761] (5/8) Epoch 16, batch 950, loss[loss=0.2449, simple_loss=0.3402, pruned_loss=0.07483, over 4967.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3241, pruned_loss=0.07589, over 956582.30 frames.], batch size: 15, lr: 6.91e-04
2022-05-28 15:43:00,173 INFO [train.py:761] (5/8) Epoch 16, batch 1000, loss[loss=0.2256, simple_loss=0.3348, pruned_loss=0.05821, over 4716.00 frames.], tot_loss[loss=0.237, simple_loss=0.3236, pruned_loss=0.07526, over 958235.14 frames.], batch size: 14, lr: 6.91e-04
2022-05-28 15:43:38,156 INFO [train.py:761] (5/8) Epoch 16, batch 1050, loss[loss=0.1935, simple_loss=0.2835, pruned_loss=0.05179, over 4803.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3247, pruned_loss=0.0762, over 959941.41 frames.], batch size: 12, lr: 6.91e-04
2022-05-28 15:44:16,218 INFO [train.py:761] (5/8) Epoch 16, batch 1100, loss[loss=0.2485, simple_loss=0.3386, pruned_loss=0.07922, over 4980.00 frames.], tot_loss[loss=0.239, simple_loss=0.3254, pruned_loss=0.07633, over 961191.49 frames.], batch size: 15, lr: 6.91e-04
2022-05-28 15:44:54,631 INFO [train.py:761] (5/8) Epoch 16, batch 1150, loss[loss=0.2223, simple_loss=0.3108, pruned_loss=0.06686, over 4946.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3244, pruned_loss=0.0763, over 963543.41 frames.], batch size: 16, lr: 6.91e-04
2022-05-28 15:45:33,149 INFO [train.py:761] (5/8) Epoch 16, batch 1200, loss[loss=0.2171, simple_loss=0.2988, pruned_loss=0.06774, over 4797.00 frames.], tot_loss[loss=0.2394, simple_loss=0.3254, pruned_loss=0.07674, over 964022.90 frames.], batch size: 12, lr: 6.91e-04
2022-05-28 15:46:11,321 INFO [train.py:761] (5/8) Epoch 16, batch 1250, loss[loss=0.2532, simple_loss=0.333, pruned_loss=0.08672, over 4670.00 frames.], tot_loss[loss=0.2405, simple_loss=0.3261, pruned_loss=0.07749, over 965239.11 frames.], batch size: 13, lr: 6.90e-04
2022-05-28 15:46:48,598 INFO [train.py:761] (5/8) Epoch 16, batch 1300, loss[loss=0.2523, simple_loss=0.3173, pruned_loss=0.0937, over 4972.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3258, pruned_loss=0.07747, over 964866.08 frames.], batch size: 11, lr: 6.90e-04
2022-05-28 15:47:26,699 INFO [train.py:761] (5/8) Epoch 16, batch 1350, loss[loss=0.2215, simple_loss=0.3116, pruned_loss=0.06566, over 4972.00 frames.], tot_loss[loss=0.2389, simple_loss=0.3241, pruned_loss=0.07681, over 964969.10 frames.], batch size: 12, lr: 6.90e-04
2022-05-28 15:48:04,499 INFO [train.py:761] (5/8) Epoch 16, batch 1400, loss[loss=0.2483, simple_loss=0.3354, pruned_loss=0.08059, over 4961.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3234, pruned_loss=0.07614, over 965862.36 frames.], batch size: 16, lr: 6.90e-04
2022-05-28 15:48:42,574 INFO [train.py:761] (5/8) Epoch 16, batch 1450, loss[loss=0.2154, simple_loss=0.316, pruned_loss=0.05737, over 4850.00 frames.], tot_loss[loss=0.2389, simple_loss=0.3246, pruned_loss=0.07663, over 966009.15 frames.], batch size: 14, lr: 6.90e-04
2022-05-28 15:49:20,380 INFO [train.py:761] (5/8) Epoch 16, batch 1500, loss[loss=0.261, simple_loss=0.3328, pruned_loss=0.09461, over 4852.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3242, pruned_loss=0.07644, over 965618.27 frames.], batch size: 13, lr: 6.90e-04
2022-05-28 15:49:58,567 INFO [train.py:761] (5/8) Epoch 16, batch 1550, loss[loss=0.2264, simple_loss=0.3076, pruned_loss=0.07257, over 4985.00 frames.], tot_loss[loss=0.2395, simple_loss=0.3251, pruned_loss=0.07692, over 965050.61 frames.], batch size: 13, lr: 6.89e-04
2022-05-28 15:50:36,664 INFO [train.py:761] (5/8) Epoch 16, batch 1600, loss[loss=0.3194, simple_loss=0.3932, pruned_loss=0.1228, over 4762.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3248, pruned_loss=0.07621, over 965039.47 frames.], batch size: 15, lr: 6.89e-04
2022-05-28 15:51:14,878 INFO [train.py:761] (5/8) Epoch 16, batch 1650, loss[loss=0.2729, simple_loss=0.3473, pruned_loss=0.09922, over 4879.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3248, pruned_loss=0.07619, over 965449.84 frames.], batch size: 15, lr: 6.89e-04
2022-05-28 15:51:52,623 INFO [train.py:761] (5/8) Epoch 16, batch 1700, loss[loss=0.3027, simple_loss=0.3879, pruned_loss=0.1087, over 4789.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3253, pruned_loss=0.07658, over 965281.76 frames.], batch size: 20, lr: 6.89e-04
2022-05-28 15:52:30,571 INFO [train.py:761] (5/8) Epoch 16, batch 1750, loss[loss=0.1747, simple_loss=0.2605, pruned_loss=0.04447, over 4881.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3242, pruned_loss=0.07579, over 966691.21 frames.], batch size: 12, lr: 6.89e-04
2022-05-28 15:53:08,347 INFO [train.py:761] (5/8) Epoch 16, batch 1800, loss[loss=0.2544, simple_loss=0.3403, pruned_loss=0.08425, over 4658.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3237, pruned_loss=0.07499, over 967294.68 frames.], batch size: 12, lr: 6.89e-04
2022-05-28 15:53:46,431 INFO [train.py:761] (5/8) Epoch 16, batch 1850, loss[loss=0.2435, simple_loss=0.3181, pruned_loss=0.08442, over 4657.00 frames.], tot_loss[loss=0.2373, simple_loss=0.3242, pruned_loss=0.07514, over 967793.15 frames.], batch size: 12, lr: 6.88e-04
2022-05-28 15:54:24,190 INFO [train.py:761] (5/8) Epoch 16, batch 1900, loss[loss=0.2275, simple_loss=0.3141, pruned_loss=0.07043, over 4656.00 frames.], tot_loss[loss=0.237, simple_loss=0.3247, pruned_loss=0.07462, over 967351.47 frames.], batch size: 12, lr: 6.88e-04
2022-05-28 15:55:01,924 INFO [train.py:761] (5/8) Epoch 16, batch 1950, loss[loss=0.2277, simple_loss=0.308, pruned_loss=0.07375, over 4734.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3259, pruned_loss=0.07464, over 966820.68 frames.], batch size: 12, lr: 6.88e-04
2022-05-28 15:55:40,097 INFO [train.py:761] (5/8) Epoch 16, batch 2000, loss[loss=0.2372, simple_loss=0.3337, pruned_loss=0.07032, over 4867.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3273, pruned_loss=0.07558, over 967433.02 frames.], batch size: 17, lr: 6.88e-04
2022-05-28 15:56:17,790 INFO [train.py:761] (5/8) Epoch 16, batch 2050, loss[loss=0.2314, simple_loss=0.3293, pruned_loss=0.06675, over 4901.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3265, pruned_loss=0.076, over 966998.02 frames.], batch size: 14, lr: 6.88e-04
2022-05-28 15:56:55,740 INFO [train.py:761] (5/8) Epoch 16, batch 2100, loss[loss=0.2481, simple_loss=0.3382, pruned_loss=0.07899, over 4875.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3265, pruned_loss=0.07539, over 965544.82 frames.], batch size: 26, lr: 6.88e-04
2022-05-28 15:57:33,563 INFO [train.py:761] (5/8) Epoch 16, batch 2150, loss[loss=0.2125, simple_loss=0.311, pruned_loss=0.05698, over 4675.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3231, pruned_loss=0.07422, over 965198.89 frames.], batch size: 13, lr: 6.87e-04
2022-05-28 15:58:12,069 INFO [train.py:761] (5/8) Epoch 16, batch 2200, loss[loss=0.2356, simple_loss=0.3279, pruned_loss=0.07162, over 4781.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3227, pruned_loss=0.07433, over 965458.66 frames.], batch size: 15, lr: 6.87e-04
2022-05-28 15:58:50,511 INFO [train.py:761] (5/8) Epoch 16, batch 2250, loss[loss=0.2018, simple_loss=0.2934, pruned_loss=0.05504, over 4961.00 frames.], tot_loss[loss=0.2369, simple_loss=0.324, pruned_loss=0.07483, over 965662.94 frames.], batch size: 12, lr: 6.87e-04
2022-05-28 15:59:28,389 INFO [train.py:761] (5/8) Epoch 16, batch 2300, loss[loss=0.2209, simple_loss=0.3214, pruned_loss=0.06015, over 4781.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3233, pruned_loss=0.07415, over 965947.80 frames.], batch size: 14, lr: 6.87e-04
2022-05-28 16:00:06,390 INFO [train.py:761] (5/8) Epoch 16, batch 2350, loss[loss=0.2383, simple_loss=0.3303, pruned_loss=0.07316, over 4865.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3229, pruned_loss=0.07372, over 965928.08 frames.], batch size: 15, lr: 6.87e-04
2022-05-28 16:00:44,102 INFO [train.py:761] (5/8) Epoch 16, batch 2400, loss[loss=0.2274, simple_loss=0.3225, pruned_loss=0.06616, over 4971.00 frames.], tot_loss[loss=0.2354, simple_loss=0.323, pruned_loss=0.07392, over 965945.32 frames.], batch size: 12, lr: 6.87e-04
2022-05-28 16:01:22,894 INFO [train.py:761] (5/8) Epoch 16, batch 2450, loss[loss=0.2137, simple_loss=0.2939, pruned_loss=0.0667, over 4669.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3244, pruned_loss=0.07521, over 965868.05 frames.], batch size: 12, lr: 6.86e-04
2022-05-28 16:02:00,543 INFO [train.py:761] (5/8) Epoch 16, batch 2500, loss[loss=0.2539, simple_loss=0.3403, pruned_loss=0.08379, over 4670.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3245, pruned_loss=0.07518, over 964921.60 frames.], batch size: 13, lr: 6.86e-04
2022-05-28 16:02:38,658 INFO [train.py:761] (5/8) Epoch 16, batch 2550, loss[loss=0.2648, simple_loss=0.3595, pruned_loss=0.08506, over 4875.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3255, pruned_loss=0.07529, over 964866.53 frames.], batch size: 18, lr: 6.86e-04
2022-05-28 16:03:15,928 INFO [train.py:761] (5/8) Epoch 16, batch 2600, loss[loss=0.2233, simple_loss=0.3112, pruned_loss=0.06769, over 4798.00 frames.], tot_loss[loss=0.2377, simple_loss=0.3252, pruned_loss=0.0751, over 964498.03 frames.], batch size: 12, lr: 6.86e-04
2022-05-28 16:03:54,288 INFO [train.py:761] (5/8) Epoch 16, batch 2650, loss[loss=0.2557, simple_loss=0.358, pruned_loss=0.07672, over 4892.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3245, pruned_loss=0.07483, over 964813.54 frames.], batch size: 15, lr: 6.86e-04
2022-05-28 16:04:31,793 INFO [train.py:761] (5/8) Epoch 16, batch 2700, loss[loss=0.2582, simple_loss=0.3334, pruned_loss=0.09155, over 4916.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3242, pruned_loss=0.07482, over 966530.34 frames.], batch size: 13, lr: 6.86e-04
2022-05-28 16:05:09,580 INFO [train.py:761] (5/8) Epoch 16, batch 2750, loss[loss=0.2503, simple_loss=0.3214, pruned_loss=0.08958, over 4919.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3229, pruned_loss=0.07399, over 965948.23 frames.], batch size: 13, lr: 6.85e-04
2022-05-28 16:05:48,131 INFO [train.py:761] (5/8) Epoch 16, batch 2800, loss[loss=0.208, simple_loss=0.2962, pruned_loss=0.05988, over 4803.00 frames.], tot_loss[loss=0.2372, simple_loss=0.324, pruned_loss=0.07517, over 965909.92 frames.], batch size: 12, lr: 6.85e-04
2022-05-28 16:06:29,504 INFO [train.py:761] (5/8) Epoch 16, batch 2850, loss[loss=0.309, simple_loss=0.3921, pruned_loss=0.113, over 4887.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3238, pruned_loss=0.07484, over 965535.48 frames.], batch size: 15, lr: 6.85e-04
2022-05-28 16:07:07,994 INFO [train.py:761] (5/8) Epoch 16, batch 2900, loss[loss=0.1913, simple_loss=0.2793, pruned_loss=0.05169, over 4978.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3233, pruned_loss=0.07426, over 965409.81 frames.], batch size: 11, lr: 6.85e-04
2022-05-28 16:07:46,245 INFO [train.py:761] (5/8) Epoch 16, batch 2950, loss[loss=0.2374, simple_loss=0.3288, pruned_loss=0.07304, over 4795.00 frames.], tot_loss[loss=0.2355, simple_loss=0.3228, pruned_loss=0.0741, over 966442.10 frames.], batch size: 12, lr: 6.85e-04
2022-05-28 16:08:24,284 INFO [train.py:761] (5/8) Epoch 16, batch 3000, loss[loss=0.2494, simple_loss=0.3537, pruned_loss=0.07255, over 4766.00 frames.], tot_loss[loss=0.2344, simple_loss=0.322, pruned_loss=0.07345, over 967025.57 frames.], batch size: 15, lr: 6.85e-04
2022-05-28 16:08:24,284 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 16:08:34,194 INFO [train.py:790] (5/8) Epoch 16, validation: loss=0.2148, simple_loss=0.3176, pruned_loss=0.05598, over 944034.00 frames.
2022-05-28 16:09:12,373 INFO [train.py:761] (5/8) Epoch 16, batch 3050, loss[loss=0.2338, simple_loss=0.325, pruned_loss=0.07123, over 4853.00 frames.], tot_loss[loss=0.2343, simple_loss=0.322, pruned_loss=0.0733, over 967247.52 frames.], batch size: 14, lr: 6.84e-04
2022-05-28 16:09:50,811 INFO [train.py:761] (5/8) Epoch 16, batch 3100, loss[loss=0.2132, simple_loss=0.2927, pruned_loss=0.06683, over 4739.00 frames.], tot_loss[loss=0.235, simple_loss=0.3215, pruned_loss=0.07429, over 965984.18 frames.], batch size: 12, lr: 6.84e-04
2022-05-28 16:10:28,740 INFO [train.py:761] (5/8) Epoch 16, batch 3150, loss[loss=0.2267, simple_loss=0.3113, pruned_loss=0.07103, over 4789.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3231, pruned_loss=0.07631, over 964936.59 frames.], batch size: 13, lr: 6.84e-04
2022-05-28 16:11:06,899 INFO [train.py:761] (5/8) Epoch 16, batch 3200, loss[loss=0.1842, simple_loss=0.2723, pruned_loss=0.04811, over 4719.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3245, pruned_loss=0.07894, over 965522.08 frames.], batch size: 11, lr: 6.84e-04
2022-05-28 16:11:45,124 INFO [train.py:761] (5/8) Epoch 16, batch 3250, loss[loss=0.3252, simple_loss=0.386, pruned_loss=0.1322, over 4865.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3259, pruned_loss=0.08117, over 965769.07 frames.], batch size: 17, lr: 6.84e-04
2022-05-28 16:12:23,394 INFO [train.py:761] (5/8) Epoch 16, batch 3300, loss[loss=0.2276, simple_loss=0.3254, pruned_loss=0.06486, over 4787.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3278, pruned_loss=0.08358, over 965462.71 frames.], batch size: 14, lr: 6.84e-04
2022-05-28 16:13:01,366 INFO [train.py:761] (5/8) Epoch 16, batch 3350, loss[loss=0.2629, simple_loss=0.3447, pruned_loss=0.09053, over 4976.00 frames.], tot_loss[loss=0.2487, simple_loss=0.3285, pruned_loss=0.08448, over 966562.84 frames.], batch size: 14, lr: 6.83e-04
2022-05-28 16:13:39,444 INFO [train.py:761] (5/8) Epoch 16, batch 3400, loss[loss=0.2436, simple_loss=0.3179, pruned_loss=0.08461, over 4988.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3302, pruned_loss=0.08682, over 966682.88 frames.], batch size: 13, lr: 6.83e-04
2022-05-28 16:14:17,433 INFO [train.py:761] (5/8) Epoch 16, batch 3450, loss[loss=0.2419, simple_loss=0.3198, pruned_loss=0.08198, over 4963.00 frames.], tot_loss[loss=0.2549, simple_loss=0.3324, pruned_loss=0.08874, over 966891.96 frames.], batch size: 15, lr: 6.83e-04
2022-05-28 16:14:55,713 INFO [train.py:761] (5/8) Epoch 16, batch 3500, loss[loss=0.3144, simple_loss=0.3891, pruned_loss=0.1198, over 4977.00 frames.], tot_loss[loss=0.2573, simple_loss=0.3342, pruned_loss=0.0902, over 968433.14 frames.], batch size: 15, lr: 6.83e-04
2022-05-28 16:15:34,209 INFO [train.py:761] (5/8) Epoch 16, batch 3550, loss[loss=0.3051, simple_loss=0.3537, pruned_loss=0.1283, over 4553.00 frames.], tot_loss[loss=0.2591, simple_loss=0.3349, pruned_loss=0.09166, over 967628.37 frames.], batch size: 10, lr: 6.83e-04
2022-05-28 16:16:11,939 INFO [train.py:761] (5/8) Epoch 16, batch 3600, loss[loss=0.2819, simple_loss=0.3564, pruned_loss=0.1037, over 4952.00 frames.], tot_loss[loss=0.2604, simple_loss=0.3353, pruned_loss=0.09278, over 968046.94 frames.], batch size: 16, lr: 6.83e-04
2022-05-28 16:16:49,687 INFO [train.py:761] (5/8) Epoch 16, batch 3650, loss[loss=0.2018, simple_loss=0.2903, pruned_loss=0.05663, over 4786.00 frames.], tot_loss[loss=0.262, simple_loss=0.3363, pruned_loss=0.09391, over 968652.54 frames.], batch size: 13, lr: 6.82e-04
2022-05-28 16:17:28,562 INFO [train.py:761] (5/8) Epoch 16, batch 3700, loss[loss=0.2722, simple_loss=0.3481, pruned_loss=0.09814, over 4789.00 frames.], tot_loss[loss=0.2612, simple_loss=0.3353, pruned_loss=0.09353, over 968226.52 frames.], batch size: 14, lr: 6.82e-04
2022-05-28 16:18:06,862 INFO [train.py:761] (5/8) Epoch 16, batch 3750, loss[loss=0.2467, simple_loss=0.3466, pruned_loss=0.07336, over 4952.00 frames.], tot_loss[loss=0.2602, simple_loss=0.3343, pruned_loss=0.09303, over 968106.82 frames.], batch size: 16, lr: 6.82e-04
2022-05-28 16:18:44,833 INFO [train.py:761] (5/8) Epoch 16, batch 3800, loss[loss=0.2751, simple_loss=0.3579, pruned_loss=0.09613, over 4851.00 frames.], tot_loss[loss=0.2634, simple_loss=0.3368, pruned_loss=0.09499, over 967050.10 frames.], batch size: 14, lr: 6.82e-04
2022-05-28 16:19:23,743 INFO [train.py:761] (5/8) Epoch 16, batch 3850, loss[loss=0.2621, simple_loss=0.3453, pruned_loss=0.08946, over 4857.00 frames.], tot_loss[loss=0.2643, simple_loss=0.3378, pruned_loss=0.09542, over 966741.00 frames.], batch size: 18, lr: 6.82e-04
2022-05-28 16:20:02,335 INFO [train.py:761] (5/8) Epoch 16, batch 3900, loss[loss=0.2448, simple_loss=0.3089, pruned_loss=0.09032, over 4730.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3378, pruned_loss=0.09602, over 966377.86 frames.], batch size: 11, lr: 6.82e-04
2022-05-28 16:20:40,206 INFO [train.py:761] (5/8) Epoch 16, batch 3950, loss[loss=0.256, simple_loss=0.3279, pruned_loss=0.09207, over 4730.00 frames.], tot_loss[loss=0.264, simple_loss=0.3362, pruned_loss=0.09586, over 966656.19 frames.], batch size: 12, lr: 6.81e-04
2022-05-28 16:21:18,595 INFO [train.py:761] (5/8) Epoch 16, batch 4000, loss[loss=0.27, simple_loss=0.3553, pruned_loss=0.09235, over 4970.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3361, pruned_loss=0.09557, over 966402.84 frames.], batch size: 15, lr: 6.81e-04
2022-05-28 16:21:56,331 INFO [train.py:761] (5/8) Epoch 16, batch 4050, loss[loss=0.3188, simple_loss=0.3625, pruned_loss=0.1376, over 4888.00 frames.], tot_loss[loss=0.2652, simple_loss=0.3372, pruned_loss=0.09659, over 967448.22 frames.], batch size: 12, lr: 6.81e-04
2022-05-28 16:22:34,288 INFO [train.py:761] (5/8) Epoch 16, batch 4100, loss[loss=0.2182, simple_loss=0.2925, pruned_loss=0.07194, over 4836.00 frames.], tot_loss[loss=0.2658, simple_loss=0.3379, pruned_loss=0.09682, over 965491.90 frames.], batch size: 11, lr: 6.81e-04
2022-05-28 16:23:12,714 INFO [train.py:761] (5/8) Epoch 16, batch 4150, loss[loss=0.35, simple_loss=0.4022, pruned_loss=0.1489, over 4951.00 frames.], tot_loss[loss=0.2663, simple_loss=0.3386, pruned_loss=0.09698, over 966236.54 frames.], batch size: 45, lr: 6.81e-04
2022-05-28 16:23:50,826 INFO [train.py:761] (5/8) Epoch 16, batch 4200, loss[loss=0.3202, simple_loss=0.3578, pruned_loss=0.1413, over 4790.00 frames.], tot_loss[loss=0.266, simple_loss=0.3389, pruned_loss=0.09653, over 965706.11 frames.], batch size: 13, lr: 6.81e-04
2022-05-28 16:24:29,491 INFO [train.py:761] (5/8) Epoch 16, batch 4250, loss[loss=0.3006, simple_loss=0.3566, pruned_loss=0.1223, over 4811.00 frames.], tot_loss[loss=0.2658, simple_loss=0.3389, pruned_loss=0.09633, over 965934.79 frames.], batch size: 18, lr: 6.81e-04
2022-05-28 16:25:07,674 INFO [train.py:761] (5/8) Epoch 16, batch 4300, loss[loss=0.2184, simple_loss=0.289, pruned_loss=0.07384, over 4637.00 frames.], tot_loss[loss=0.2651, simple_loss=0.338, pruned_loss=0.09613, over 966234.62 frames.], batch size: 11, lr: 6.80e-04
2022-05-28 16:25:46,376 INFO [train.py:761] (5/8) Epoch 16, batch 4350, loss[loss=0.2278, simple_loss=0.3004, pruned_loss=0.07764, over 4738.00 frames.], tot_loss[loss=0.2648, simple_loss=0.3375, pruned_loss=0.09602, over 966209.54 frames.], batch size: 11, lr: 6.80e-04
2022-05-28 16:26:24,775 INFO [train.py:761] (5/8) Epoch 16, batch 4400, loss[loss=0.2568, simple_loss=0.3305, pruned_loss=0.09159, over 4919.00 frames.], tot_loss[loss=0.264, simple_loss=0.3369, pruned_loss=0.09556, over 966055.61 frames.], batch size: 14, lr: 6.80e-04
2022-05-28 16:27:03,763 INFO [train.py:761] (5/8) Epoch 16, batch 4450, loss[loss=0.3401, simple_loss=0.3991, pruned_loss=0.1406, over 4895.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3365, pruned_loss=0.09538, over 966103.33 frames.], batch size: 46, lr: 6.80e-04
2022-05-28 16:27:41,783 INFO [train.py:761] (5/8) Epoch 16, batch 4500, loss[loss=0.2912, simple_loss=0.3529, pruned_loss=0.1147, over 4980.00 frames.], tot_loss[loss=0.261, simple_loss=0.3346, pruned_loss=0.09376, over 966319.60 frames.], batch size: 21, lr: 6.80e-04
2022-05-28 16:28:19,708 INFO [train.py:761] (5/8) Epoch 16, batch 4550, loss[loss=0.2905, simple_loss=0.3448, pruned_loss=0.1181, over 4912.00 frames.], tot_loss[loss=0.2607, simple_loss=0.3338, pruned_loss=0.09379, over 966972.63 frames.], batch size: 14, lr: 6.80e-04
2022-05-28 16:28:57,684 INFO [train.py:761] (5/8) Epoch 16, batch 4600, loss[loss=0.25, simple_loss=0.328, pruned_loss=0.08596, over 4942.00 frames.], tot_loss[loss=0.2601, simple_loss=0.3334, pruned_loss=0.09339, over 966583.05 frames.], batch size: 16, lr: 6.79e-04
2022-05-28 16:29:36,226 INFO [train.py:761] (5/8) Epoch 16, batch 4650, loss[loss=0.2295, simple_loss=0.3247, pruned_loss=0.06714, over 4793.00 frames.], tot_loss[loss=0.2596, simple_loss=0.3335, pruned_loss=0.09287, over 966638.54 frames.], batch size: 14, lr: 6.79e-04
2022-05-28 16:30:14,311 INFO [train.py:761] (5/8) Epoch 16, batch 4700, loss[loss=0.2103, simple_loss=0.2891, pruned_loss=0.06579, over 4854.00 frames.], tot_loss[loss=0.2599, simple_loss=0.3338, pruned_loss=0.093, over 967152.65 frames.], batch size: 13, lr: 6.79e-04
2022-05-28 16:30:52,636 INFO [train.py:761] (5/8) Epoch 16, batch 4750, loss[loss=0.2607, simple_loss=0.3337, pruned_loss=0.09381, over 4859.00 frames.], tot_loss[loss=0.261, simple_loss=0.3337, pruned_loss=0.09415, over 966678.85 frames.], batch size: 17, lr: 6.79e-04
2022-05-28 16:31:30,338 INFO [train.py:761] (5/8) Epoch 16, batch 4800, loss[loss=0.1699, simple_loss=0.2487, pruned_loss=0.04553, over 4735.00 frames.], tot_loss[loss=0.261, simple_loss=0.3342, pruned_loss=0.09388, over 966105.82 frames.], batch size: 11, lr: 6.79e-04
2022-05-28 16:32:09,090 INFO [train.py:761] (5/8) Epoch 16, batch 4850, loss[loss=0.2057, simple_loss=0.2821, pruned_loss=0.06464, over 4849.00 frames.], tot_loss[loss=0.2608, simple_loss=0.3333, pruned_loss=0.09415, over 965213.87 frames.], batch size: 13, lr: 6.79e-04
2022-05-28 16:32:47,008 INFO [train.py:761] (5/8) Epoch 16, batch 4900, loss[loss=0.2423, simple_loss=0.3327, pruned_loss=0.07595, over 4786.00 frames.], tot_loss[loss=0.2609, simple_loss=0.3333, pruned_loss=0.09426, over 964523.13 frames.], batch size: 14, lr: 6.78e-04
2022-05-28 16:33:25,328 INFO [train.py:761] (5/8) Epoch 16, batch 4950, loss[loss=0.2874, simple_loss=0.3595, pruned_loss=0.1077, over 4807.00 frames.], tot_loss[loss=0.2608, simple_loss=0.3335, pruned_loss=0.09407, over 964204.12 frames.], batch size: 16, lr: 6.78e-04
2022-05-28 16:34:03,447 INFO [train.py:761] (5/8) Epoch 16, batch 5000, loss[loss=0.2644, simple_loss=0.3334, pruned_loss=0.09768, over 4806.00 frames.], tot_loss[loss=0.2605, simple_loss=0.3336, pruned_loss=0.09374, over 965147.07 frames.], batch size: 12, lr: 6.78e-04
2022-05-28 16:34:41,940 INFO [train.py:761] (5/8) Epoch 16, batch 5050, loss[loss=0.2356, simple_loss=0.3286, pruned_loss=0.07127, over 4714.00 frames.], tot_loss[loss=0.2592, simple_loss=0.3327, pruned_loss=0.09289, over 965670.89 frames.], batch size: 14, lr: 6.78e-04
2022-05-28 16:35:20,097 INFO [train.py:761] (5/8) Epoch 16, batch 5100, loss[loss=0.2564, simple_loss=0.326, pruned_loss=0.09346, over 4667.00 frames.], tot_loss[loss=0.2585, simple_loss=0.3321, pruned_loss=0.09245, over 966305.99 frames.], batch size: 13, lr: 6.78e-04
2022-05-28 16:35:58,498 INFO [train.py:761] (5/8) Epoch 16, batch 5150, loss[loss=0.2511, simple_loss=0.2927, pruned_loss=0.1048, over 4830.00 frames.], tot_loss[loss=0.2594, simple_loss=0.3327, pruned_loss=0.09311, over 966282.14 frames.], batch size: 11, lr: 6.78e-04
2022-05-28 16:36:36,882 INFO [train.py:761] (5/8) Epoch 16, batch 5200, loss[loss=0.3116, simple_loss=0.37, pruned_loss=0.1266, over 4919.00 frames.], tot_loss[loss=0.2591, simple_loss=0.3323, pruned_loss=0.09295, over 966631.10 frames.], batch size: 18, lr: 6.77e-04
2022-05-28 16:37:15,807 INFO [train.py:761] (5/8) Epoch 16, batch 5250, loss[loss=0.2705, simple_loss=0.3462, pruned_loss=0.09734, over 4973.00 frames.], tot_loss[loss=0.2571, simple_loss=0.3311, pruned_loss=0.09153, over 966966.19 frames.], batch size: 14, lr: 6.77e-04
2022-05-28 16:37:53,580 INFO [train.py:761] (5/8) Epoch 16, batch 5300, loss[loss=0.2436, simple_loss=0.3206, pruned_loss=0.08334, over 4835.00 frames.], tot_loss[loss=0.2569, simple_loss=0.3307, pruned_loss=0.09157, over 967197.70 frames.], batch size: 25, lr: 6.77e-04
2022-05-28 16:38:31,910 INFO [train.py:761] (5/8) Epoch 16, batch 5350, loss[loss=0.2775, simple_loss=0.3496, pruned_loss=0.1027, over 4673.00 frames.], tot_loss[loss=0.256, simple_loss=0.33, pruned_loss=0.09097, over 965298.06 frames.], batch size: 13, lr: 6.77e-04
2022-05-28 16:39:10,007 INFO [train.py:761] (5/8) Epoch 16, batch 5400, loss[loss=0.3104, simple_loss=0.3693, pruned_loss=0.1258, over 4953.00 frames.], tot_loss[loss=0.2549, simple_loss=0.3292, pruned_loss=0.09032, over 967352.89 frames.], batch size: 49, lr: 6.77e-04
2022-05-28 16:39:48,330 INFO [train.py:761] (5/8) Epoch 16, batch 5450, loss[loss=0.2472, simple_loss=0.3369, pruned_loss=0.07877, over 4772.00 frames.], tot_loss[loss=0.2544, simple_loss=0.329, pruned_loss=0.08994, over 967500.58 frames.], batch size: 15, lr: 6.77e-04
2022-05-28 16:40:26,307 INFO [train.py:761] (5/8) Epoch 16, batch 5500, loss[loss=0.2118, simple_loss=0.281, pruned_loss=0.07124, over 4540.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3306, pruned_loss=0.09089, over 966740.26 frames.], batch size: 10, lr: 6.77e-04
2022-05-28 16:41:04,345 INFO [train.py:761] (5/8) Epoch 16, batch 5550, loss[loss=0.2281, simple_loss=0.3067, pruned_loss=0.07477, over 4972.00 frames.], tot_loss[loss=0.2563, simple_loss=0.3308, pruned_loss=0.09089, over 965732.03 frames.], batch size: 15, lr: 6.76e-04
2022-05-28 16:41:42,986 INFO [train.py:761] (5/8) Epoch 16, batch 5600, loss[loss=0.204, simple_loss=0.2746, pruned_loss=0.0667, over 4880.00 frames.], tot_loss[loss=0.2552, simple_loss=0.3297, pruned_loss=0.09031, over 965919.86 frames.], batch size: 12, lr: 6.76e-04
2022-05-28 16:42:21,959 INFO [train.py:761] (5/8) Epoch 16, batch 5650, loss[loss=0.2491, simple_loss=0.3314, pruned_loss=0.08342, over 4810.00 frames.], tot_loss[loss=0.2555, simple_loss=0.3301, pruned_loss=0.09041, over 965344.12 frames.], batch size: 25, lr: 6.76e-04
2022-05-28 16:43:07,550 INFO [train.py:761] (5/8) Epoch 16, batch 5700, loss[loss=0.2319, simple_loss=0.3133, pruned_loss=0.0753, over 4670.00 frames.], tot_loss[loss=0.2548, simple_loss=0.329, pruned_loss=0.09032, over 964406.59 frames.], batch size: 13, lr: 6.76e-04
2022-05-28 16:43:55,945 INFO [train.py:761] (5/8) Epoch 16, batch 5750, loss[loss=0.2616, simple_loss=0.3404, pruned_loss=0.0914, over 4722.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3301, pruned_loss=0.09115, over 964525.86 frames.], batch size: 14, lr: 6.76e-04
2022-05-28 16:44:44,767 INFO [train.py:761] (5/8) Epoch 16, batch 5800, loss[loss=0.2195, simple_loss=0.2852, pruned_loss=0.07685, over 4969.00 frames.], tot_loss[loss=0.2566, simple_loss=0.3307, pruned_loss=0.09126, over 965073.96 frames.], batch size: 12, lr: 6.76e-04
2022-05-28 16:45:34,367 INFO [train.py:761] (5/8) Epoch 16, batch 5850, loss[loss=0.2329, simple_loss=0.3127, pruned_loss=0.07654, over 4960.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3321, pruned_loss=0.09203, over 965474.55 frames.], batch size: 12, lr: 6.75e-04
2022-05-28 16:46:16,361 INFO [train.py:761] (5/8) Epoch 16, batch 5900, loss[loss=0.2688, simple_loss=0.3405, pruned_loss=0.09855, over 4785.00 frames.], tot_loss[loss=0.2589, simple_loss=0.333, pruned_loss=0.09244, over 966434.35 frames.], batch size: 14, lr: 6.75e-04
2022-05-28 16:47:05,224 INFO [train.py:761] (5/8) Epoch 16, batch 5950, loss[loss=0.233, simple_loss=0.3114, pruned_loss=0.0773, over 4722.00 frames.], tot_loss[loss=0.2585, simple_loss=0.3326, pruned_loss=0.09217, over 966311.36 frames.], batch size: 13, lr: 6.75e-04
2022-05-28 16:47:53,981 INFO [train.py:761] (5/8) Epoch 16, batch 6000, loss[loss=0.2189, simple_loss=0.2759, pruned_loss=0.08099, over 4957.00 frames.], tot_loss[loss=0.2582, simple_loss=0.3324, pruned_loss=0.09204, over 966857.41 frames.], batch size: 11, lr: 6.75e-04
2022-05-28 16:47:53,981 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 16:48:06,502 INFO [train.py:790] (5/8) Epoch 16, validation: loss=0.2074, simple_loss=0.3141, pruned_loss=0.05028, over 944034.00 frames.
2022-05-28 16:48:54,442 INFO [train.py:761] (5/8) Epoch 16, batch 6050, loss[loss=0.2414, simple_loss=0.3231, pruned_loss=0.07987, over 4889.00 frames.], tot_loss[loss=0.258, simple_loss=0.333, pruned_loss=0.09149, over 966698.63 frames.], batch size: 12, lr: 6.75e-04
2022-05-28 16:49:37,547 INFO [train.py:761] (5/8) Epoch 16, batch 6100, loss[loss=0.305, simple_loss=0.37, pruned_loss=0.12, over 4913.00 frames.], tot_loss[loss=0.2595, simple_loss=0.334, pruned_loss=0.09248, over 967128.77 frames.], batch size: 49, lr: 6.75e-04
2022-05-28 16:50:26,808 INFO [train.py:761] (5/8) Epoch 16, batch 6150, loss[loss=0.2272, simple_loss=0.3023, pruned_loss=0.07608, over 4918.00 frames.], tot_loss[loss=0.2592, simple_loss=0.334, pruned_loss=0.09222, over 966806.95 frames.], batch size: 13, lr: 6.74e-04
2022-05-28 16:51:16,327 INFO [train.py:761] (5/8) Epoch 16, batch 6200, loss[loss=0.2892, simple_loss=0.3681, pruned_loss=0.1051, over 4781.00 frames.], tot_loss[loss=0.2599, simple_loss=0.3342, pruned_loss=0.09283, over 965984.94 frames.], batch size: 16, lr: 6.74e-04
2022-05-28 16:52:06,225 INFO [train.py:761] (5/8) Epoch 16, batch 6250, loss[loss=0.2725, simple_loss=0.3387, pruned_loss=0.1031, over 4859.00 frames.], tot_loss[loss=0.261, simple_loss=0.3348, pruned_loss=0.09358, over 964983.78 frames.], batch size: 13, lr: 6.74e-04
2022-05-28 16:52:46,727 INFO [train.py:761] (5/8) Epoch 16, batch 6300, loss[loss=0.231, simple_loss=0.3183, pruned_loss=0.07185, over 4719.00 frames.], tot_loss[loss=0.2608, simple_loss=0.3346, pruned_loss=0.09351, over 966161.64 frames.], batch size: 13, lr: 6.74e-04
2022-05-28 16:53:25,426 INFO [train.py:761] (5/8) Epoch 16, batch 6350, loss[loss=0.2234, simple_loss=0.3056, pruned_loss=0.07058, over 4799.00 frames.], tot_loss[loss=0.2592, simple_loss=0.3333, pruned_loss=0.09253, over 966692.92 frames.], batch size: 12, lr: 6.74e-04
2022-05-28 16:54:04,168 INFO [train.py:761] (5/8) Epoch 16, batch 6400, loss[loss=0.2743, simple_loss=0.3577, pruned_loss=0.09543, over 4719.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3329, pruned_loss=0.09169, over 966609.35 frames.], batch size: 14, lr: 6.74e-04
2022-05-28 16:54:42,392 INFO [train.py:761] (5/8) Epoch 16, batch 6450, loss[loss=0.2179, simple_loss=0.301, pruned_loss=0.06736, over 4969.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3329, pruned_loss=0.09169, over 966049.75 frames.], batch size: 15, lr: 6.74e-04
2022-05-28 16:55:20,737 INFO [train.py:761] (5/8) Epoch 16, batch 6500, loss[loss=0.2656, simple_loss=0.3603, pruned_loss=0.08539, over 4762.00 frames.], tot_loss[loss=0.2574, simple_loss=0.3318, pruned_loss=0.09153, over 965940.74 frames.], batch size: 20, lr: 6.73e-04
2022-05-28 16:56:09,107 INFO [train.py:761] (5/8) Epoch 16, batch 6550, loss[loss=0.2505, simple_loss=0.3403, pruned_loss=0.08036, over 4968.00 frames.], tot_loss[loss=0.2585, simple_loss=0.333, pruned_loss=0.09199, over 965435.57 frames.], batch size: 15, lr: 6.73e-04
2022-05-28 16:56:57,702 INFO [train.py:761] (5/8) Epoch 16, batch 6600, loss[loss=0.2996, simple_loss=0.3688, pruned_loss=0.1151, over 4783.00 frames.], tot_loss[loss=0.2591, simple_loss=0.3331, pruned_loss=0.09254, over 965677.58 frames.], batch size: 13, lr: 6.73e-04
2022-05-28 16:57:48,341 INFO [train.py:761] (5/8) Epoch 16, batch 6650, loss[loss=0.3345, simple_loss=0.3889, pruned_loss=0.1401, over 4670.00 frames.], tot_loss[loss=0.2587, simple_loss=0.3329, pruned_loss=0.09228, over 966396.18 frames.], batch size: 13, lr: 6.73e-04
2022-05-28 16:58:34,142 INFO [train.py:761] (5/8) Epoch 16, batch 6700, loss[loss=0.1923, simple_loss=0.2973, pruned_loss=0.04363, over 4985.00 frames.], tot_loss[loss=0.2573, simple_loss=0.3314, pruned_loss=0.09163, over 965719.76 frames.], batch size: 13, lr: 6.73e-04
2022-05-28 16:59:29,832 INFO [train.py:761] (5/8) Epoch 17, batch 0, loss[loss=0.2567, simple_loss=0.3425, pruned_loss=0.08549, over 4772.00 frames.], tot_loss[loss=0.2567, simple_loss=0.3425, pruned_loss=0.08549, over 4772.00 frames.], batch size: 15, lr: 6.73e-04
2022-05-28 17:00:07,703 INFO [train.py:761] (5/8) Epoch 17, batch 50, loss[loss=0.2326, simple_loss=0.328, pruned_loss=0.06858, over 4952.00 frames.], tot_loss[loss=0.237, simple_loss=0.3234, pruned_loss=0.07536, over 218249.00 frames.], batch size: 16, lr: 6.72e-04
2022-05-28 17:00:46,563 INFO [train.py:761] (5/8) Epoch 17, batch 100, loss[loss=0.2754, simple_loss=0.3539, pruned_loss=0.09842, over 4790.00 frames.], tot_loss[loss=0.2408, simple_loss=0.3272, pruned_loss=0.07722, over 384784.39 frames.], batch size: 16, lr: 6.72e-04
2022-05-28 17:01:24,058 INFO [train.py:761] (5/8) Epoch 17, batch 150, loss[loss=0.2422, simple_loss=0.3214, pruned_loss=0.08148, over 4843.00 frames.], tot_loss[loss=0.2395, simple_loss=0.3258, pruned_loss=0.07657, over 513888.96 frames.], batch size: 14, lr: 6.72e-04
2022-05-28 17:02:02,370 INFO [train.py:761] (5/8) Epoch 17, batch 200, loss[loss=0.1746, simple_loss=0.2779, pruned_loss=0.03565, over 4990.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3246, pruned_loss=0.07507, over 614513.03 frames.], batch size: 13, lr: 6.72e-04
2022-05-28 17:02:39,976 INFO [train.py:761] (5/8) Epoch 17, batch 250, loss[loss=0.2552, simple_loss=0.3439, pruned_loss=0.08325, over 4831.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3247, pruned_loss=0.0745, over 693188.96 frames.], batch size: 16, lr: 6.72e-04
2022-05-28 17:03:18,133 INFO [train.py:761] (5/8) Epoch 17, batch 300, loss[loss=0.1901, simple_loss=0.285, pruned_loss=0.04763, over 4976.00 frames.], tot_loss[loss=0.2362, simple_loss=0.3238, pruned_loss=0.07427, over 753839.44 frames.], batch size: 12, lr: 6.72e-04
2022-05-28 17:03:56,213 INFO [train.py:761] (5/8) Epoch 17, batch 350, loss[loss=0.2321, simple_loss=0.3299, pruned_loss=0.06716, over 4775.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3216, pruned_loss=0.07359, over 799968.52 frames.], batch size: 20, lr: 6.72e-04
2022-05-28 17:04:34,618 INFO [train.py:761] (5/8) Epoch 17, batch 400, loss[loss=0.2384, simple_loss=0.325, pruned_loss=0.0759, over 4715.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3204, pruned_loss=0.07273, over 836600.63 frames.], batch size: 14, lr: 6.71e-04
2022-05-28 17:05:12,121 INFO [train.py:761] (5/8) Epoch 17, batch 450, loss[loss=0.2365, simple_loss=0.3221, pruned_loss=0.07543, over 4988.00 frames.], tot_loss[loss=0.232, simple_loss=0.3197, pruned_loss=0.07213, over 865462.61 frames.], batch size: 13, lr: 6.71e-04
2022-05-28 17:05:49,775 INFO [train.py:761] (5/8) Epoch 17, batch 500, loss[loss=0.2655, simple_loss=0.3498, pruned_loss=0.09058, over 4792.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3189, pruned_loss=0.07151, over 887787.81 frames.], batch size: 13, lr: 6.71e-04
2022-05-28 17:06:27,864 INFO [train.py:761] (5/8) Epoch 17, batch 550, loss[loss=0.175, simple_loss=0.2543, pruned_loss=0.04785, over 4975.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3165, pruned_loss=0.0701, over 905801.35 frames.], batch size: 12, lr: 6.71e-04
2022-05-28 17:07:05,536 INFO [train.py:761] (5/8) Epoch 17, batch 600, loss[loss=0.2594, simple_loss=0.3351, pruned_loss=0.09183, over 4917.00 frames.], tot_loss[loss=0.23, simple_loss=0.3182, pruned_loss=0.07096, over 919658.73 frames.], batch size: 13, lr: 6.71e-04
2022-05-28 17:07:43,776 INFO [train.py:761] (5/8) Epoch 17, batch 650, loss[loss=0.2791, simple_loss=0.3573, pruned_loss=0.1004, over 4655.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3187, pruned_loss=0.07143, over 929200.37 frames.], batch size: 12, lr: 6.71e-04
2022-05-28 17:08:22,056 INFO [train.py:761] (5/8) Epoch 17, batch 700, loss[loss=0.1905, simple_loss=0.2812, pruned_loss=0.04992, over 4666.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3182, pruned_loss=0.0717, over 937007.62 frames.], batch size: 13, lr: 6.70e-04
2022-05-28 17:08:59,869 INFO [train.py:761] (5/8) Epoch 17, batch 750, loss[loss=0.1932, simple_loss=0.2855, pruned_loss=0.05048, over 4840.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3199, pruned_loss=0.0727, over 942917.82 frames.], batch size: 13, lr: 6.70e-04
2022-05-28 17:09:37,957 INFO [train.py:761] (5/8) Epoch 17, batch 800, loss[loss=0.2575, simple_loss=0.3528, pruned_loss=0.08107, over 4909.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3219, pruned_loss=0.07388, over 949393.17 frames.], batch size: 17, lr: 6.70e-04
2022-05-28 17:10:15,631 INFO [train.py:761] (5/8) Epoch 17, batch 850, loss[loss=0.2635, simple_loss=0.3566, pruned_loss=0.08522, over 4902.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3227, pruned_loss=0.07443, over 953776.22 frames.], batch size: 26, lr: 6.70e-04
2022-05-28 17:10:53,741 INFO [train.py:761] (5/8) Epoch 17, batch 900, loss[loss=0.2167, simple_loss=0.3148, pruned_loss=0.05933, over 4774.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3222, pruned_loss=0.0741, over 957727.08 frames.], batch size: 15, lr: 6.70e-04
2022-05-28 17:11:31,139 INFO [train.py:761] (5/8) Epoch 17, batch 950, loss[loss=0.2107, simple_loss=0.2992, pruned_loss=0.06114, over 4780.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3213, pruned_loss=0.07359, over 960051.59 frames.], batch size: 14, lr: 6.70e-04
2022-05-28 17:12:16,960 INFO [train.py:761] (5/8) Epoch 17, batch 1000, loss[loss=0.2479, simple_loss=0.3357, pruned_loss=0.08004, over 4846.00 frames.], tot_loss[loss=0.2361, simple_loss=0.3227, pruned_loss=0.07471, over 961931.09 frames.], batch size: 14, lr: 6.70e-04
2022-05-28 17:12:54,968 INFO [train.py:761] (5/8) Epoch 17, batch 1050, loss[loss=0.338, simple_loss=0.3932, pruned_loss=0.1414, over 4877.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3234, pruned_loss=0.07517, over 962261.46 frames.], batch size: 44, lr: 6.69e-04
2022-05-28 17:13:32,952 INFO [train.py:761] (5/8) Epoch 17, batch 1100, loss[loss=0.1786, simple_loss=0.259, pruned_loss=0.04913, over 4970.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3235, pruned_loss=0.07475, over 963242.82 frames.], batch size: 12, lr: 6.69e-04
2022-05-28 17:14:11,165 INFO [train.py:761] (5/8) Epoch 17, batch 1150, loss[loss=0.2281, simple_loss=0.3211, pruned_loss=0.06756, over 4913.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3237, pruned_loss=0.07478, over 963406.52 frames.], batch size: 17, lr: 6.69e-04
2022-05-28 17:14:48,956 INFO [train.py:761] (5/8) Epoch 17, batch 1200, loss[loss=0.2676, simple_loss=0.3494, pruned_loss=0.09286, over 4916.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3237, pruned_loss=0.07461, over 963937.13 frames.], batch size: 14, lr: 6.69e-04
2022-05-28 17:15:26,624 INFO [train.py:761] (5/8) Epoch 17, batch 1250, loss[loss=0.2536, simple_loss=0.3282, pruned_loss=0.08944, over 4786.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3231, pruned_loss=0.07424, over 963622.28 frames.], batch size: 13, lr: 6.69e-04
2022-05-28 17:16:04,738 INFO [train.py:761] (5/8) Epoch 17, batch 1300, loss[loss=0.2773, simple_loss=0.3602, pruned_loss=0.09718, over 4979.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3221, pruned_loss=0.07388, over 964945.61 frames.], batch size: 21, lr: 6.69e-04
2022-05-28 17:16:42,738 INFO [train.py:761] (5/8) Epoch 17, batch 1350, loss[loss=0.2011, simple_loss=0.2779, pruned_loss=0.06208, over 4644.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3208, pruned_loss=0.07315, over 964853.21 frames.], batch size: 11, lr: 6.68e-04
2022-05-28 17:17:21,237 INFO [train.py:761] (5/8) Epoch 17, batch 1400, loss[loss=0.2241, simple_loss=0.3164, pruned_loss=0.06587, over 4667.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3204, pruned_loss=0.07294, over 965080.59 frames.], batch size: 13, lr: 6.68e-04
2022-05-28 17:17:59,203 INFO [train.py:761] (5/8) Epoch 17, batch 1450, loss[loss=0.2567, simple_loss=0.3376, pruned_loss=0.08787, over 4844.00 frames.], tot_loss[loss=0.235, simple_loss=0.3221, pruned_loss=0.07401, over 965093.38 frames.], batch size: 14, lr: 6.68e-04
2022-05-28 17:18:37,878 INFO [train.py:761] (5/8) Epoch 17, batch 1500, loss[loss=0.2359, simple_loss=0.3195, pruned_loss=0.07618, over 4807.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3227, pruned_loss=0.07419, over 965464.16 frames.], batch size: 12, lr: 6.68e-04
2022-05-28 17:19:16,187 INFO [train.py:761] (5/8) Epoch 17, batch 1550, loss[loss=0.2253, simple_loss=0.3037, pruned_loss=0.07349, over 4990.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3218, pruned_loss=0.07325, over 964924.45 frames.], batch size: 13, lr: 6.68e-04
2022-05-28 17:19:54,213 INFO [train.py:761] (5/8) Epoch 17, batch 1600, loss[loss=0.2269, simple_loss=0.3242, pruned_loss=0.0648, over 4845.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3214, pruned_loss=0.07292, over 964791.32 frames.], batch size: 14, lr: 6.68e-04
2022-05-28 17:20:32,375 INFO [train.py:761] (5/8) Epoch 17, batch 1650, loss[loss=0.3052, simple_loss=0.385, pruned_loss=0.1127, over 4878.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3235, pruned_loss=0.07397, over 965485.57 frames.], batch size: 25, lr: 6.68e-04
2022-05-28 17:21:10,192 INFO [train.py:761] (5/8) Epoch 17, batch 1700, loss[loss=0.2429, simple_loss=0.3168, pruned_loss=0.08444, over 4666.00 frames.], tot_loss[loss=0.2361, simple_loss=0.3242, pruned_loss=0.07399, over 965545.34 frames.], batch size: 12, lr: 6.67e-04
2022-05-28 17:21:48,157 INFO [train.py:761] (5/8) Epoch 17, batch 1750, loss[loss=0.244, simple_loss=0.3331, pruned_loss=0.07744, over 4852.00 frames.], tot_loss[loss=0.2361, simple_loss=0.3239, pruned_loss=0.07408, over 965080.92 frames.], batch size: 14, lr: 6.67e-04
2022-05-28 17:22:25,981 INFO [train.py:761] (5/8) Epoch 17, batch 1800, loss[loss=0.2824, simple_loss=0.3686, pruned_loss=0.09807, over 4863.00 frames.], tot_loss[loss=0.2361, simple_loss=0.3239, pruned_loss=0.07421, over 965592.37 frames.], batch size: 18, lr: 6.67e-04
2022-05-28 17:23:04,293 INFO [train.py:761] (5/8) Epoch 17, batch 1850, loss[loss=0.2031, simple_loss=0.2985, pruned_loss=0.05381, over 4663.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3209, pruned_loss=0.07341, over 966364.68 frames.], batch size: 12, lr: 6.67e-04
2022-05-28 17:23:42,575 INFO [train.py:761] (5/8) Epoch 17, batch 1900, loss[loss=0.2578, simple_loss=0.3554, pruned_loss=0.08015, over 4722.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3208, pruned_loss=0.07343, over 964587.23 frames.], batch size: 13, lr: 6.67e-04
2022-05-28 17:24:20,301 INFO [train.py:761] (5/8) Epoch 17, batch 1950, loss[loss=0.1846, simple_loss=0.286, pruned_loss=0.04155, over 4677.00 frames.], tot_loss[loss=0.234, simple_loss=0.3213, pruned_loss=0.07336, over 965815.28 frames.], batch size: 13, lr: 6.67e-04
2022-05-28 17:24:57,844 INFO [train.py:761] (5/8) Epoch 17, batch 2000, loss[loss=0.2594, simple_loss=0.3489, pruned_loss=0.08492, over 4785.00 frames.], tot_loss[loss=0.235, simple_loss=0.3221, pruned_loss=0.07392, over 965910.49 frames.], batch size: 14, lr: 6.66e-04
2022-05-28 17:25:35,559 INFO [train.py:761] (5/8) Epoch 17, batch 2050, loss[loss=0.2014, simple_loss=0.2897, pruned_loss=0.05661, over 4789.00 frames.], tot_loss[loss=0.236, simple_loss=0.3233, pruned_loss=0.07438, over 965673.79 frames.], batch size: 13, lr: 6.66e-04
2022-05-28 17:26:13,332 INFO [train.py:761] (5/8) Epoch 17, batch 2100, loss[loss=0.1925, simple_loss=0.2809, pruned_loss=0.05209, over 4784.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3229, pruned_loss=0.07394, over 966050.29 frames.], batch size: 13, lr: 6.66e-04
2022-05-28 17:26:51,649 INFO [train.py:761] (5/8) Epoch 17, batch 2150, loss[loss=0.2241, simple_loss=0.3149, pruned_loss=0.06667, over 4852.00 frames.], tot_loss[loss=0.2356, simple_loss=0.323, pruned_loss=0.07409, over 965879.17 frames.], batch size: 13, lr: 6.66e-04
2022-05-28 17:27:29,998 INFO [train.py:761] (5/8) Epoch 17, batch 2200, loss[loss=0.2672, simple_loss=0.3445, pruned_loss=0.09496, over 4941.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3218, pruned_loss=0.07351, over 964394.69 frames.], batch size: 45, lr: 6.66e-04
2022-05-28 17:28:08,126 INFO [train.py:761] (5/8) Epoch 17, batch 2250, loss[loss=0.2296, simple_loss=0.324, pruned_loss=0.06762, over 4842.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3216, pruned_loss=0.07333, over 963958.92 frames.], batch size: 13, lr: 6.66e-04
2022-05-28 17:28:46,550 INFO [train.py:761] (5/8) Epoch 17, batch 2300, loss[loss=0.2026, simple_loss=0.2914, pruned_loss=0.0569, over 4786.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3232, pruned_loss=0.07397, over 964868.96 frames.], batch size: 13, lr: 6.66e-04
2022-05-28 17:29:24,180 INFO [train.py:761] (5/8) Epoch 17, batch 2350, loss[loss=0.2173, simple_loss=0.3095, pruned_loss=0.06256, over 4971.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3243, pruned_loss=0.07469, over 966343.43 frames.], batch size: 15, lr: 6.65e-04
2022-05-28 17:30:01,996 INFO [train.py:761] (5/8) Epoch 17, batch 2400, loss[loss=0.2261, simple_loss=0.3134, pruned_loss=0.0694, over 4964.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3232, pruned_loss=0.07395, over 966615.93 frames.], batch size: 14, lr: 6.65e-04
2022-05-28 17:30:39,562 INFO [train.py:761] (5/8) Epoch 17, batch 2450, loss[loss=0.2208, simple_loss=0.3161, pruned_loss=0.06274, over 4725.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3226, pruned_loss=0.07321, over 966216.97 frames.], batch size: 12, lr: 6.65e-04
2022-05-28 17:31:18,066 INFO [train.py:761] (5/8) Epoch 17, batch 2500, loss[loss=0.1935, simple_loss=0.2897, pruned_loss=0.04867, over 4853.00 frames.], tot_loss[loss=0.2347, simple_loss=0.3228, pruned_loss=0.0733, over 966092.41 frames.], batch size: 14, lr: 6.65e-04
2022-05-28 17:31:55,221 INFO [train.py:761] (5/8) Epoch 17, batch 2550, loss[loss=0.2164, simple_loss=0.3157, pruned_loss=0.05861, over 4838.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3217, pruned_loss=0.07251, over 965301.47 frames.], batch size: 25, lr: 6.65e-04
2022-05-28 17:32:33,655 INFO [train.py:761] (5/8) Epoch 17, batch 2600, loss[loss=0.1881, simple_loss=0.2835, pruned_loss=0.04633, over 4814.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3217, pruned_loss=0.07229, over 965938.59 frames.], batch size: 11, lr: 6.65e-04
2022-05-28 17:33:10,898 INFO [train.py:761] (5/8) Epoch 17, batch 2650, loss[loss=0.198, simple_loss=0.2772, pruned_loss=0.05938, over 4978.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3216, pruned_loss=0.07194, over 966021.46 frames.], batch size: 11, lr: 6.64e-04
2022-05-28 17:33:49,010 INFO [train.py:761] (5/8) Epoch 17, batch 2700, loss[loss=0.2212, simple_loss=0.3241, pruned_loss=0.05909, over 4984.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3214, pruned_loss=0.07201, over 965828.84 frames.], batch size: 15, lr: 6.64e-04
2022-05-28 17:34:26,829 INFO [train.py:761] (5/8) Epoch 17, batch 2750, loss[loss=0.2482, simple_loss=0.3249, pruned_loss=0.08577, over 4958.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3201, pruned_loss=0.07151, over 965335.01 frames.], batch size: 16, lr: 6.64e-04
2022-05-28 17:35:04,503 INFO [train.py:761] (5/8) Epoch 17, batch 2800, loss[loss=0.2285, simple_loss=0.3275, pruned_loss=0.06474, over 4862.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3206, pruned_loss=0.07162, over 964514.48 frames.], batch size: 17, lr: 6.64e-04
2022-05-28 17:35:42,326 INFO [train.py:761] (5/8) Epoch 17, batch 2850, loss[loss=0.2484, simple_loss=0.3403, pruned_loss=0.07828, over 4881.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3195, pruned_loss=0.07141, over 963778.27 frames.], batch size: 43, lr: 6.64e-04
2022-05-28 17:36:20,678 INFO [train.py:761] (5/8) Epoch 17, batch 2900, loss[loss=0.2794, simple_loss=0.3661, pruned_loss=0.09629, over 4938.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3201, pruned_loss=0.07174, over 963466.31 frames.], batch size: 47, lr: 6.64e-04
2022-05-28 17:36:58,425 INFO [train.py:761] (5/8) Epoch 17, batch 2950, loss[loss=0.2448, simple_loss=0.3312, pruned_loss=0.07923, over 4796.00 frames.], tot_loss[loss=0.231, simple_loss=0.3191, pruned_loss=0.07143, over 963703.76 frames.], batch size: 18, lr: 6.64e-04
2022-05-28 17:37:36,150 INFO [train.py:761] (5/8) Epoch 17, batch 3000, loss[loss=0.2358, simple_loss=0.3058, pruned_loss=0.08285, over 4964.00 frames.], tot_loss[loss=0.2327, simple_loss=0.32, pruned_loss=0.07266, over 965003.64 frames.], batch size: 11, lr: 6.63e-04
2022-05-28 17:37:36,151 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 17:37:46,120 INFO [train.py:790] (5/8) Epoch 17, validation: loss=0.2141, simple_loss=0.3162, pruned_loss=0.05601, over 944034.00 frames.
2022-05-28 17:38:23,917 INFO [train.py:761] (5/8) Epoch 17, batch 3050, loss[loss=0.2005, simple_loss=0.2856, pruned_loss=0.05771, over 4927.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3205, pruned_loss=0.07309, over 965247.37 frames.], batch size: 13, lr: 6.63e-04
2022-05-28 17:39:02,018 INFO [train.py:761] (5/8) Epoch 17, batch 3100, loss[loss=0.2281, simple_loss=0.3128, pruned_loss=0.07174, over 4662.00 frames.], tot_loss[loss=0.236, simple_loss=0.3219, pruned_loss=0.07509, over 964912.99 frames.], batch size: 13, lr: 6.63e-04
2022-05-28 17:39:39,896 INFO [train.py:761] (5/8) Epoch 17, batch 3150, loss[loss=0.2589, simple_loss=0.3426, pruned_loss=0.08763, over 4786.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3231, pruned_loss=0.07652, over 965501.88 frames.], batch size: 13, lr: 6.63e-04
2022-05-28 17:40:17,288 INFO [train.py:761] (5/8) Epoch 17, batch 3200, loss[loss=0.2366, simple_loss=0.3107, pruned_loss=0.08128, over 4984.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3236, pruned_loss=0.07805, over 964276.61 frames.], batch size: 13, lr: 6.63e-04
2022-05-28 17:40:55,084 INFO [train.py:761] (5/8) Epoch 17, batch 3250, loss[loss=0.2027, simple_loss=0.2797, pruned_loss=0.06282, over 4845.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3256, pruned_loss=0.08061, over 963669.05 frames.], batch size: 11, lr: 6.63e-04
2022-05-28 17:41:33,190 INFO [train.py:761] (5/8) Epoch 17, batch 3300, loss[loss=0.2186, simple_loss=0.2944, pruned_loss=0.07142, over 4827.00 frames.], tot_loss[loss=0.2434, simple_loss=0.324, pruned_loss=0.08136, over 964200.39 frames.], batch size: 11, lr: 6.63e-04
2022-05-28 17:42:11,573 INFO [train.py:761] (5/8) Epoch 17, batch 3350, loss[loss=0.2804, simple_loss=0.3547, pruned_loss=0.103, over 4980.00 frames.], tot_loss[loss=0.247, simple_loss=0.3263, pruned_loss=0.08384, over 964143.31 frames.], batch size: 13, lr: 6.62e-04
2022-05-28 17:42:49,733 INFO [train.py:761] (5/8) Epoch 17, batch 3400, loss[loss=0.2851, simple_loss=0.3527, pruned_loss=0.1087, over 4836.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3269, pruned_loss=0.08546, over 965602.57 frames.], batch size: 20, lr: 6.62e-04
2022-05-28 17:43:27,624 INFO [train.py:761] (5/8) Epoch 17, batch 3450, loss[loss=0.1813, simple_loss=0.2631, pruned_loss=0.04974, over 4865.00 frames.], tot_loss[loss=0.2515, simple_loss=0.3289, pruned_loss=0.08706, over 964800.26 frames.], batch size: 13, lr: 6.62e-04
2022-05-28 17:44:06,356 INFO [train.py:761] (5/8) Epoch 17, batch 3500, loss[loss=0.2387, simple_loss=0.3249, pruned_loss=0.07627, over 4716.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3283, pruned_loss=0.08763, over 965759.12 frames.], batch size: 14, lr: 6.62e-04
2022-05-28 17:44:44,238 INFO [train.py:761] (5/8) Epoch 17, batch 3550, loss[loss=0.2825, simple_loss=0.3595, pruned_loss=0.1028, over 4969.00 frames.], tot_loss[loss=0.2558, simple_loss=0.3309, pruned_loss=0.09031, over 965668.08 frames.], batch size: 15, lr: 6.62e-04
2022-05-28 17:45:29,352 INFO [train.py:761] (5/8) Epoch 17, batch 3600, loss[loss=0.2799, simple_loss=0.36, pruned_loss=0.09985, over 4793.00 frames.], tot_loss[loss=0.2593, simple_loss=0.3335, pruned_loss=0.09255, over 966428.90 frames.], batch size: 14, lr: 6.62e-04
2022-05-28 17:46:07,640 INFO [train.py:761] (5/8) Epoch 17, batch 3650, loss[loss=0.2373, simple_loss=0.3159, pruned_loss=0.0793, over 4775.00 frames.], tot_loss[loss=0.2587, simple_loss=0.3323, pruned_loss=0.09252, over 966169.57 frames.], batch size: 15, lr: 6.62e-04
2022-05-28 17:46:45,717 INFO [train.py:761] (5/8) Epoch 17, batch 3700, loss[loss=0.2292, simple_loss=0.3014, pruned_loss=0.0785, over 4980.00 frames.], tot_loss[loss=0.2579, simple_loss=0.3318, pruned_loss=0.09199, over 965541.89 frames.], batch size: 12, lr: 6.61e-04
2022-05-28 17:47:23,516 INFO [train.py:761] (5/8) Epoch 17, batch 3750, loss[loss=0.2914, simple_loss=0.3631, pruned_loss=0.1099, over 4772.00 frames.], tot_loss[loss=0.2569, simple_loss=0.3315, pruned_loss=0.09121, over 966091.07 frames.], batch size: 15, lr: 6.61e-04
2022-05-28 17:48:02,525 INFO [train.py:761] (5/8) Epoch 17, batch 3800, loss[loss=0.2732, simple_loss=0.3493, pruned_loss=0.0985, over 4920.00 frames.], tot_loss[loss=0.2587, simple_loss=0.3329, pruned_loss=0.09223, over 966961.80 frames.], batch size: 14, lr: 6.61e-04
2022-05-28 17:48:40,576 INFO [train.py:761] (5/8) Epoch 17, batch 3850, loss[loss=0.2367, simple_loss=0.327, pruned_loss=0.07326, over 4855.00 frames.], tot_loss[loss=0.2588, simple_loss=0.3331, pruned_loss=0.09226, over 966720.49 frames.], batch size: 13, lr: 6.61e-04
2022-05-28 17:49:26,058 INFO [train.py:761] (5/8) Epoch 17, batch 3900, loss[loss=0.224, simple_loss=0.3005, pruned_loss=0.0737, over 4677.00 frames.], tot_loss[loss=0.2594, simple_loss=0.3331, pruned_loss=0.09285, over 966411.15 frames.], batch size: 12, lr: 6.61e-04
2022-05-28 17:50:11,102 INFO [train.py:761] (5/8) Epoch 17, batch 3950, loss[loss=0.2147, simple_loss=0.2918, pruned_loss=0.0688, over 4886.00 frames.], tot_loss[loss=0.2599, simple_loss=0.3334, pruned_loss=0.09314, over 966509.05 frames.], batch size: 12, lr: 6.61e-04
2022-05-28 17:50:50,287 INFO [train.py:761] (5/8) Epoch 17, batch 4000, loss[loss=0.2221, simple_loss=0.2965, pruned_loss=0.07381, over 4552.00 frames.], tot_loss[loss=0.2588, simple_loss=0.3322, pruned_loss=0.09268, over 965718.45 frames.], batch size: 10, lr: 6.60e-04
2022-05-28 17:51:35,275 INFO [train.py:761] (5/8) Epoch 17, batch 4050, loss[loss=0.2613, simple_loss=0.3405, pruned_loss=0.09111, over 4891.00 frames.], tot_loss[loss=0.2567, simple_loss=0.3308, pruned_loss=0.09133, over 966845.97 frames.], batch size: 26, lr: 6.60e-04
2022-05-28 17:52:16,490 INFO [train.py:761] (5/8) Epoch 17, batch 4100, loss[loss=0.2593, simple_loss=0.3335, pruned_loss=0.09258, over 4861.00 frames.], tot_loss[loss=0.2556, simple_loss=0.3296, pruned_loss=0.09077, over 966824.26 frames.], batch size: 17, lr: 6.60e-04
2022-05-28 17:52:54,555 INFO [train.py:761] (5/8) Epoch 17, batch 4150, loss[loss=0.2518, simple_loss=0.3165, pruned_loss=0.09352, over 4900.00 frames.], tot_loss[loss=0.2549, simple_loss=0.329, pruned_loss=0.09043, over 966855.51 frames.], batch size: 12, lr: 6.60e-04
2022-05-28 17:53:32,553 INFO [train.py:761] (5/8) Epoch 17, batch 4200, loss[loss=0.2531, simple_loss=0.3296, pruned_loss=0.0883, over 4914.00 frames.], tot_loss[loss=0.2546, simple_loss=0.3288, pruned_loss=0.09023, over 966572.89 frames.], batch size: 14, lr: 6.60e-04
2022-05-28 17:54:10,556 INFO [train.py:761] (5/8) Epoch 17, batch 4250, loss[loss=0.285, simple_loss=0.3839, pruned_loss=0.09306, over 4974.00 frames.], tot_loss[loss=0.2563, simple_loss=0.3302, pruned_loss=0.09117, over 966747.84 frames.], batch size: 15, lr: 6.60e-04
2022-05-28 17:54:48,634 INFO [train.py:761] (5/8) Epoch 17, batch 4300, loss[loss=0.2292, simple_loss=0.3087, pruned_loss=0.07486, over 4723.00 frames.], tot_loss[loss=0.2579, simple_loss=0.332, pruned_loss=0.09194, over 967085.40 frames.], batch size: 13, lr: 6.60e-04
2022-05-28 17:55:27,171 INFO [train.py:761] (5/8) Epoch 17, batch 4350, loss[loss=0.2047, simple_loss=0.2714, pruned_loss=0.06893, over 4729.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3291, pruned_loss=0.09056, over 966522.25 frames.], batch size: 11, lr: 6.59e-04
2022-05-28 17:56:12,749 INFO [train.py:761] (5/8) Epoch 17, batch 4400, loss[loss=0.2086, simple_loss=0.2896, pruned_loss=0.06378, over 4842.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3278, pruned_loss=0.08934, over 965708.30 frames.], batch size: 14, lr: 6.59e-04
2022-05-28 17:56:51,007 INFO [train.py:761] (5/8) Epoch 17, batch 4450, loss[loss=0.3067, simple_loss=0.3635, pruned_loss=0.1249, over 4718.00 frames.], tot_loss[loss=0.2547, simple_loss=0.3293, pruned_loss=0.09008, over 966097.03 frames.], batch size: 13, lr: 6.59e-04
2022-05-28 17:57:29,029 INFO [train.py:761] (5/8) Epoch 17, batch 4500, loss[loss=0.282, simple_loss=0.3619, pruned_loss=0.1011, over 4722.00 frames.], tot_loss[loss=0.2542, simple_loss=0.3286, pruned_loss=0.08989, over 966030.95 frames.], batch size: 14, lr: 6.59e-04
2022-05-28 17:58:06,942 INFO [train.py:761] (5/8) Epoch 17, batch 4550, loss[loss=0.2951, simple_loss=0.3581, pruned_loss=0.116, over 4939.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3281, pruned_loss=0.0893, over 965849.10 frames.], batch size: 16, lr: 6.59e-04
2022-05-28 17:58:52,542 INFO [train.py:761] (5/8) Epoch 17, batch 4600, loss[loss=0.2054, simple_loss=0.2697, pruned_loss=0.07057, over 4647.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3276, pruned_loss=0.08882, over 965157.73 frames.], batch size: 11, lr: 6.59e-04
2022-05-28 17:59:30,913 INFO [train.py:761] (5/8) Epoch 17, batch 4650, loss[loss=0.2556, simple_loss=0.3348, pruned_loss=0.08819, over 4974.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3277, pruned_loss=0.08868, over 965913.05 frames.], batch size: 27, lr: 6.59e-04
2022-05-28 18:00:08,732 INFO [train.py:761] (5/8) Epoch 17, batch 4700, loss[loss=0.3183, simple_loss=0.3878, pruned_loss=0.1244, over 4910.00 frames.], tot_loss[loss=0.2555, simple_loss=0.33, pruned_loss=0.09046, over 967322.64 frames.], batch size: 47, lr: 6.58e-04
2022-05-28 18:00:46,360 INFO [train.py:761] (5/8) Epoch 17, batch 4750, loss[loss=0.2417, simple_loss=0.3197, pruned_loss=0.08183, over 4765.00 frames.], tot_loss[loss=0.2556, simple_loss=0.3303, pruned_loss=0.09046, over 967913.19 frames.], batch size: 15, lr: 6.58e-04
2022-05-28 18:01:24,813 INFO [train.py:761] (5/8) Epoch 17, batch 4800, loss[loss=0.191, simple_loss=0.2583, pruned_loss=0.06187, over 4996.00 frames.], tot_loss[loss=0.255, simple_loss=0.3293, pruned_loss=0.09037, over 967841.68 frames.], batch size: 11, lr: 6.58e-04
2022-05-28 18:02:02,913 INFO [train.py:761] (5/8) Epoch 17, batch 4850, loss[loss=0.2403, simple_loss=0.3062, pruned_loss=0.08721, over 4669.00 frames.], tot_loss[loss=0.2563, simple_loss=0.3305, pruned_loss=0.09104, over 967003.95 frames.], batch size: 12, lr: 6.58e-04
2022-05-28 18:02:41,328 INFO [train.py:761] (5/8) Epoch 17, batch 4900, loss[loss=0.3148, simple_loss=0.3776, pruned_loss=0.126, over 4881.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3306, pruned_loss=0.0909, over 966142.70 frames.], batch size: 15, lr: 6.58e-04
2022-05-28 18:03:19,577 INFO [train.py:761] (5/8) Epoch 17, batch 4950, loss[loss=0.2372, simple_loss=0.301, pruned_loss=0.08672, over 4728.00 frames.], tot_loss[loss=0.2556, simple_loss=0.3305, pruned_loss=0.09038, over 967133.39 frames.], batch size: 12, lr: 6.58e-04
2022-05-28 18:04:05,112 INFO [train.py:761] (5/8) Epoch 17, batch 5000, loss[loss=0.2842, simple_loss=0.3433, pruned_loss=0.1125, over 4674.00 frames.], tot_loss[loss=0.255, simple_loss=0.3294, pruned_loss=0.09027, over 965617.13 frames.], batch size: 13, lr: 6.58e-04
2022-05-28 18:04:42,720 INFO [train.py:761] (5/8) Epoch 17, batch 5050, loss[loss=0.2851, simple_loss=0.3608, pruned_loss=0.1047, over 4834.00 frames.], tot_loss[loss=0.2575, simple_loss=0.3319, pruned_loss=0.09153, over 965573.17 frames.], batch size: 17, lr: 6.57e-04
2022-05-28 18:05:21,375 INFO [train.py:761] (5/8) Epoch 17, batch 5100, loss[loss=0.2441, simple_loss=0.317, pruned_loss=0.08555, over 4908.00 frames.], tot_loss[loss=0.2563, simple_loss=0.3313, pruned_loss=0.09063, over 964728.96 frames.], batch size: 14, lr: 6.57e-04
2022-05-28 18:05:59,524 INFO [train.py:761] (5/8) Epoch 17, batch 5150, loss[loss=0.3305, simple_loss=0.3794, pruned_loss=0.1407, over 4670.00 frames.], tot_loss[loss=0.2577, simple_loss=0.3326, pruned_loss=0.09137, over 963807.72 frames.], batch size: 12, lr: 6.57e-04
2022-05-28 18:06:37,810 INFO [train.py:761] (5/8) Epoch 17, batch 5200, loss[loss=0.2913, simple_loss=0.3692, pruned_loss=0.1067, over 4782.00 frames.], tot_loss[loss=0.257, simple_loss=0.3319, pruned_loss=0.09103, over 965129.48 frames.], batch size: 20, lr: 6.57e-04
2022-05-28 18:07:16,326 INFO [train.py:761] (5/8) Epoch 17, batch 5250, loss[loss=0.2417, simple_loss=0.3379, pruned_loss=0.07275, over 4760.00 frames.], tot_loss[loss=0.2569, simple_loss=0.3321, pruned_loss=0.09084, over 965867.85 frames.], batch size: 15, lr: 6.57e-04
2022-05-28 18:07:55,174 INFO [train.py:761] (5/8) Epoch 17, batch 5300, loss[loss=0.2699, simple_loss=0.352, pruned_loss=0.09387, over 4781.00 frames.], tot_loss[loss=0.2549, simple_loss=0.3305, pruned_loss=0.08967, over 965682.67 frames.], batch size: 13, lr: 6.57e-04
2022-05-28 18:08:33,330 INFO [train.py:761] (5/8) Epoch 17, batch 5350, loss[loss=0.2256, simple_loss=0.3118, pruned_loss=0.06976, over 4734.00 frames.], tot_loss[loss=0.2543, simple_loss=0.33, pruned_loss=0.08935, over 965480.17 frames.], batch size: 13, lr: 6.57e-04
2022-05-28 18:09:11,927 INFO [train.py:761] (5/8) Epoch 17, batch 5400, loss[loss=0.2719, simple_loss=0.3531, pruned_loss=0.09538, over 4854.00 frames.], tot_loss[loss=0.254, simple_loss=0.3297, pruned_loss=0.08915, over 965642.44 frames.], batch size: 13, lr: 6.56e-04
2022-05-28 18:09:50,256 INFO [train.py:761] (5/8) Epoch 17, batch 5450, loss[loss=0.235, simple_loss=0.3069, pruned_loss=0.08153, over 4654.00 frames.], tot_loss[loss=0.2547, simple_loss=0.3304, pruned_loss=0.08948, over 966323.29 frames.], batch size: 11, lr: 6.56e-04
2022-05-28 18:10:28,600 INFO [train.py:761] (5/8) Epoch 17, batch 5500, loss[loss=0.2885, simple_loss=0.3627, pruned_loss=0.1071, over 4796.00 frames.], tot_loss[loss=0.254, simple_loss=0.33, pruned_loss=0.08902, over 966560.61 frames.], batch size: 16, lr: 6.56e-04
2022-05-28 18:11:06,680 INFO [train.py:761] (5/8) Epoch 17, batch 5550, loss[loss=0.2853, simple_loss=0.3638, pruned_loss=0.1034, over 4852.00 frames.], tot_loss[loss=0.2529, simple_loss=0.3291, pruned_loss=0.08836, over 967351.35 frames.], batch size: 14, lr: 6.56e-04
2022-05-28 18:11:45,294 INFO [train.py:761] (5/8) Epoch 17, batch 5600, loss[loss=0.2898, simple_loss=0.3611, pruned_loss=0.1093, over 4774.00 frames.], tot_loss[loss=0.2538, simple_loss=0.3297, pruned_loss=0.08897, over 967014.77 frames.], batch size: 16, lr: 6.56e-04
2022-05-28 18:12:23,228 INFO [train.py:761] (5/8) Epoch 17, batch 5650, loss[loss=0.258, simple_loss=0.337, pruned_loss=0.0895, over 4973.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3303, pruned_loss=0.08991, over 966216.21 frames.], batch size: 15, lr: 6.56e-04
2022-05-28 18:13:01,980 INFO [train.py:761] (5/8) Epoch 17, batch 5700, loss[loss=0.246, simple_loss=0.3305, pruned_loss=0.08075, over 4909.00 frames.], tot_loss[loss=0.2554, simple_loss=0.3307, pruned_loss=0.09006, over 965530.12 frames.], batch size: 14, lr: 6.56e-04
2022-05-28 18:13:40,037 INFO [train.py:761] (5/8) Epoch 17, batch 5750, loss[loss=0.254, simple_loss=0.3369, pruned_loss=0.08558, over 4718.00 frames.], tot_loss[loss=0.2553, simple_loss=0.3307, pruned_loss=0.08993, over 965296.39 frames.], batch size: 14, lr: 6.55e-04
2022-05-28 18:14:18,398 INFO [train.py:761] (5/8) Epoch 17, batch 5800, loss[loss=0.2798, simple_loss=0.3635, pruned_loss=0.09805, over 4890.00 frames.], tot_loss[loss=0.2569, simple_loss=0.332, pruned_loss=0.0909, over 965869.25 frames.], batch size: 17, lr: 6.55e-04
2022-05-28 18:14:56,890 INFO [train.py:761] (5/8) Epoch 17, batch 5850, loss[loss=0.2521, simple_loss=0.3196, pruned_loss=0.09232, over 4801.00 frames.], tot_loss[loss=0.2572, simple_loss=0.3321, pruned_loss=0.09112, over 966684.55 frames.], batch size: 16, lr: 6.55e-04
2022-05-28 18:15:35,525 INFO [train.py:761] (5/8) Epoch 17, batch 5900, loss[loss=0.2571, simple_loss=0.3181, pruned_loss=0.09809, over 4810.00 frames.], tot_loss[loss=0.2559, simple_loss=0.3313, pruned_loss=0.09027, over 965759.01 frames.], batch size: 12, lr: 6.55e-04
2022-05-28 18:16:13,726 INFO [train.py:761] (5/8) Epoch 17, batch 5950, loss[loss=0.2682, simple_loss=0.3449, pruned_loss=0.09575, over 4842.00 frames.], tot_loss[loss=0.2553, simple_loss=0.3307, pruned_loss=0.08995, over 965026.35 frames.], batch size: 18, lr: 6.55e-04
2022-05-28 18:16:52,434 INFO [train.py:761] (5/8) Epoch 17, batch 6000, loss[loss=0.2805, simple_loss=0.3496, pruned_loss=0.1057, over 4936.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3284, pruned_loss=0.0891, over 965678.88 frames.], batch size: 26, lr: 6.55e-04
2022-05-28 18:16:52,435 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 18:17:02,094 INFO [train.py:790] (5/8) Epoch 17, validation: loss=0.2061, simple_loss=0.312, pruned_loss=0.05012, over 944034.00 frames.
2022-05-28 18:17:40,363 INFO [train.py:761] (5/8) Epoch 17, batch 6050, loss[loss=0.2095, simple_loss=0.2903, pruned_loss=0.06435, over 4993.00 frames.], tot_loss[loss=0.2532, simple_loss=0.3286, pruned_loss=0.0889, over 967373.91 frames.], batch size: 13, lr: 6.55e-04
2022-05-28 18:18:18,552 INFO [train.py:761] (5/8) Epoch 17, batch 6100, loss[loss=0.2301, simple_loss=0.3144, pruned_loss=0.07293, over 4731.00 frames.], tot_loss[loss=0.2538, simple_loss=0.3293, pruned_loss=0.08913, over 967822.65 frames.], batch size: 11, lr: 6.54e-04
2022-05-28 18:18:56,643 INFO [train.py:761] (5/8) Epoch 17, batch 6150, loss[loss=0.2223, simple_loss=0.3198, pruned_loss=0.06239, over 4966.00 frames.], tot_loss[loss=0.2546, simple_loss=0.3297, pruned_loss=0.08979, over 967442.97 frames.], batch size: 14, lr: 6.54e-04
2022-05-28 18:19:34,856 INFO [train.py:761] (5/8) Epoch 17, batch 6200, loss[loss=0.2956, simple_loss=0.3641, pruned_loss=0.1136, over 4947.00 frames.], tot_loss[loss=0.2551, simple_loss=0.3303, pruned_loss=0.08998, over 967258.60 frames.], batch size: 16, lr: 6.54e-04
2022-05-28 18:20:12,986 INFO [train.py:761] (5/8) Epoch 17, batch 6250, loss[loss=0.2159, simple_loss=0.2823, pruned_loss=0.0747, over 4554.00 frames.], tot_loss[loss=0.2534, simple_loss=0.329, pruned_loss=0.08894, over 966585.90 frames.], batch size: 10, lr: 6.54e-04
2022-05-28 18:20:51,636 INFO [train.py:761] (5/8) Epoch 17, batch 6300, loss[loss=0.2217, simple_loss=0.289, pruned_loss=0.07723, over 4978.00 frames.], tot_loss[loss=0.251, simple_loss=0.3265, pruned_loss=0.08771, over 966845.02 frames.], batch size: 12, lr: 6.54e-04
2022-05-28 18:21:29,883 INFO [train.py:761] (5/8) Epoch 17, batch 6350, loss[loss=0.2534, simple_loss=0.3267, pruned_loss=0.09002, over 4723.00 frames.], tot_loss[loss=0.2511, simple_loss=0.327, pruned_loss=0.08765, over 966708.47 frames.], batch size: 13, lr: 6.54e-04
2022-05-28 18:22:08,759 INFO [train.py:761] (5/8) Epoch 17, batch 6400, loss[loss=0.2438, simple_loss=0.3302, pruned_loss=0.07872, over 4976.00 frames.], tot_loss[loss=0.253, simple_loss=0.3289, pruned_loss=0.08855, over 966770.26 frames.], batch size: 14, lr: 6.54e-04
2022-05-28 18:22:46,871 INFO [train.py:761] (5/8) Epoch 17, batch 6450, loss[loss=0.1962, simple_loss=0.2746, pruned_loss=0.05886, over 4727.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3282, pruned_loss=0.08842, over 967185.11 frames.], batch size: 11, lr: 6.53e-04
2022-05-28 18:23:24,900 INFO [train.py:761] (5/8) Epoch 17, batch 6500, loss[loss=0.281, simple_loss=0.3607, pruned_loss=0.1007, over 4953.00 frames.], tot_loss[loss=0.2532, simple_loss=0.329, pruned_loss=0.08869, over 965781.86 frames.], batch size: 21, lr: 6.53e-04
2022-05-28 18:24:03,108 INFO [train.py:761] (5/8) Epoch 17, batch 6550, loss[loss=0.2751, simple_loss=0.3442, pruned_loss=0.103, over 4914.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3277, pruned_loss=0.08791, over 966082.43 frames.], batch size: 14, lr: 6.53e-04
2022-05-28 18:24:41,354 INFO [train.py:761] (5/8) Epoch 17, batch 6600, loss[loss=0.2686, simple_loss=0.3439, pruned_loss=0.09663, over 4783.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3273, pruned_loss=0.08789, over 966548.49 frames.], batch size: 13, lr: 6.53e-04
2022-05-28 18:25:20,148 INFO [train.py:761] (5/8) Epoch 17, batch 6650, loss[loss=0.2491, simple_loss=0.3094, pruned_loss=0.09435, over 4970.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3288, pruned_loss=0.08925, over 965648.11 frames.], batch size: 12, lr: 6.53e-04
2022-05-28 18:25:59,013 INFO [train.py:761] (5/8) Epoch 17, batch 6700, loss[loss=0.2715, simple_loss=0.3312, pruned_loss=0.1059, over 4730.00 frames.], tot_loss[loss=0.2534, simple_loss=0.3286, pruned_loss=0.08911, over 965684.90 frames.], batch size: 11, lr: 6.53e-04
2022-05-28 18:26:55,415 INFO [train.py:761] (5/8) Epoch 18, batch 0, loss[loss=0.2295, simple_loss=0.3328, pruned_loss=0.06313, over 4976.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3328, pruned_loss=0.06313, over 4976.00 frames.], batch size: 15, lr: 6.53e-04
2022-05-28 18:27:33,878 INFO [train.py:761] (5/8) Epoch 18, batch 50, loss[loss=0.201, simple_loss=0.2784, pruned_loss=0.06179, over 4834.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3181, pruned_loss=0.07253, over 217988.62 frames.], batch size: 11, lr: 6.52e-04
2022-05-28 18:28:11,574 INFO [train.py:761] (5/8) Epoch 18, batch 100, loss[loss=0.2772, simple_loss=0.35, pruned_loss=0.1022, over 4769.00 frames.], tot_loss[loss=0.2288, simple_loss=0.3173, pruned_loss=0.07012, over 384041.37 frames.], batch size: 15, lr: 6.52e-04
2022-05-28 18:28:50,165 INFO [train.py:761] (5/8) Epoch 18, batch 150, loss[loss=0.1504, simple_loss=0.2272, pruned_loss=0.03677, over 4556.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3158, pruned_loss=0.06983, over 512636.43 frames.], batch size: 10, lr: 6.52e-04
2022-05-28 18:29:27,923 INFO [train.py:761] (5/8) Epoch 18, batch 200, loss[loss=0.1993, simple_loss=0.2761, pruned_loss=0.06119, over 4837.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3171, pruned_loss=0.06991, over 613858.96 frames.], batch size: 11, lr: 6.52e-04
2022-05-28 18:30:06,123 INFO [train.py:761] (5/8) Epoch 18, batch 250, loss[loss=0.2603, simple_loss=0.3501, pruned_loss=0.08527, over 4862.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3166, pruned_loss=0.06935, over 691253.22 frames.], batch size: 48, lr: 6.52e-04
2022-05-28 18:30:44,148 INFO [train.py:761] (5/8) Epoch 18, batch 300, loss[loss=0.2154, simple_loss=0.3088, pruned_loss=0.06101, over 4793.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3157, pruned_loss=0.06906, over 751241.60 frames.], batch size: 14, lr: 6.52e-04
2022-05-28 18:31:22,743 INFO [train.py:761] (5/8) Epoch 18, batch 350, loss[loss=0.2358, simple_loss=0.3328, pruned_loss=0.06946, over 4890.00 frames.], tot_loss[loss=0.227, simple_loss=0.3157, pruned_loss=0.06914, over 797890.71 frames.], batch size: 17, lr: 6.52e-04
2022-05-28 18:32:00,424 INFO [train.py:761] (5/8) Epoch 18, batch 400, loss[loss=0.2219, simple_loss=0.3275, pruned_loss=0.05815, over 4816.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3131, pruned_loss=0.06755, over 835277.15 frames.], batch size: 25, lr: 6.51e-04
2022-05-28 18:32:37,949 INFO [train.py:761] (5/8) Epoch 18, batch 450, loss[loss=0.2768, simple_loss=0.3579, pruned_loss=0.09784, over 4976.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3139, pruned_loss=0.06736, over 864352.08 frames.], batch size: 15, lr: 6.51e-04
2022-05-28 18:33:15,822 INFO [train.py:761] (5/8) Epoch 18, batch 500, loss[loss=0.2114, simple_loss=0.3101, pruned_loss=0.0563, over 4874.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3146, pruned_loss=0.06818, over 886976.16 frames.], batch size: 15, lr: 6.51e-04
2022-05-28 18:33:54,025 INFO [train.py:761] (5/8) Epoch 18, batch 550, loss[loss=0.233, simple_loss=0.3311, pruned_loss=0.06744, over 4851.00 frames.], tot_loss[loss=0.224, simple_loss=0.313, pruned_loss=0.06753, over 904891.24 frames.], batch size: 14, lr: 6.51e-04
2022-05-28 18:34:32,031 INFO [train.py:761] (5/8) Epoch 18, batch 600, loss[loss=0.2556, simple_loss=0.3301, pruned_loss=0.09051, over 4742.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3129, pruned_loss=0.0674, over 919078.56 frames.], batch size: 11, lr: 6.51e-04
2022-05-28 18:35:09,368 INFO [train.py:761] (5/8) Epoch 18, batch 650, loss[loss=0.2343, simple_loss=0.3155, pruned_loss=0.07652, over 4819.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3143, pruned_loss=0.06818, over 930245.11 frames.], batch size: 20, lr: 6.51e-04
2022-05-28 18:35:46,636 INFO [train.py:761] (5/8) Epoch 18, batch 700, loss[loss=0.2304, simple_loss=0.3296, pruned_loss=0.06559, over 4974.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3148, pruned_loss=0.06871, over 939007.54 frames.], batch size: 15, lr: 6.51e-04
2022-05-28 18:36:24,480 INFO [train.py:761] (5/8) Epoch 18, batch 750, loss[loss=0.1925, simple_loss=0.2933, pruned_loss=0.04591, over 4668.00 frames.], tot_loss[loss=0.2279, simple_loss=0.3163, pruned_loss=0.06973, over 945518.25 frames.], batch size: 12, lr: 6.50e-04
2022-05-28 18:37:02,521 INFO [train.py:761] (5/8) Epoch 18, batch 800, loss[loss=0.2137, simple_loss=0.2986, pruned_loss=0.06437, over 4807.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3166, pruned_loss=0.07079, over 949255.34 frames.], batch size: 12, lr: 6.50e-04
2022-05-28 18:37:40,490 INFO [train.py:761] (5/8) Epoch 18, batch 850, loss[loss=0.2358, simple_loss=0.3218, pruned_loss=0.07492, over 4664.00 frames.], tot_loss[loss=0.2295, simple_loss=0.317, pruned_loss=0.07095, over 952894.86 frames.], batch size: 12, lr: 6.50e-04
2022-05-28 18:38:18,103 INFO [train.py:761] (5/8) Epoch 18, batch 900, loss[loss=0.2191, simple_loss=0.3127, pruned_loss=0.06271, over 4945.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3183, pruned_loss=0.07234, over 956109.17 frames.], batch size: 16, lr: 6.50e-04
2022-05-28 18:38:56,184 INFO [train.py:761] (5/8) Epoch 18, batch 950, loss[loss=0.2126, simple_loss=0.2988, pruned_loss=0.06319, over 4791.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3191, pruned_loss=0.07287, over 958814.80 frames.], batch size: 13, lr: 6.50e-04
2022-05-28 18:39:34,264 INFO [train.py:761] (5/8) Epoch 18, batch 1000, loss[loss=0.208, simple_loss=0.2948, pruned_loss=0.06064, over 4992.00 frames.], tot_loss[loss=0.2322, simple_loss=0.319, pruned_loss=0.07267, over 960289.17 frames.], batch size: 13, lr: 6.50e-04
2022-05-28 18:40:11,852 INFO [train.py:761] (5/8) Epoch 18, batch 1050, loss[loss=0.2256, simple_loss=0.3238, pruned_loss=0.06372, over 4988.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3196, pruned_loss=0.0727, over 962365.88 frames.], batch size: 13, lr: 6.50e-04
2022-05-28 18:40:49,595 INFO [train.py:761] (5/8) Epoch 18, batch 1100, loss[loss=0.2669, simple_loss=0.3467, pruned_loss=0.09349, over 4990.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3203, pruned_loss=0.07291, over 962184.38 frames.], batch size: 21, lr: 6.49e-04
2022-05-28 18:41:27,841 INFO [train.py:761] (5/8) Epoch 18, batch 1150, loss[loss=0.2079, simple_loss=0.3194, pruned_loss=0.04816, over 4967.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3207, pruned_loss=0.07292, over 963272.82 frames.], batch size: 14, lr: 6.49e-04
2022-05-28 18:42:05,675 INFO [train.py:761] (5/8) Epoch 18, batch 1200, loss[loss=0.2915, simple_loss=0.374, pruned_loss=0.1045, over 4865.00 frames.], tot_loss[loss=0.231, simple_loss=0.3193, pruned_loss=0.07134, over 963880.99 frames.], batch size: 15, lr: 6.49e-04
2022-05-28 18:42:43,876 INFO [train.py:761] (5/8) Epoch 18, batch 1250, loss[loss=0.1917, simple_loss=0.2762, pruned_loss=0.05362, over 4793.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3194, pruned_loss=0.0718, over 964519.07 frames.], batch size: 12, lr: 6.49e-04
2022-05-28 18:43:21,538 INFO [train.py:761] (5/8) Epoch 18, batch 1300, loss[loss=0.2919, simple_loss=0.3725, pruned_loss=0.1056, over 4789.00 frames.], tot_loss[loss=0.2336, simple_loss=0.321, pruned_loss=0.0731, over 964545.44 frames.], batch size: 20, lr: 6.49e-04
2022-05-28 18:44:00,118 INFO [train.py:761] (5/8) Epoch 18, batch 1350, loss[loss=0.2718, simple_loss=0.36, pruned_loss=0.09181, over 4963.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3199, pruned_loss=0.07253, over 964738.34 frames.], batch size: 16, lr: 6.49e-04
2022-05-28 18:44:37,944 INFO [train.py:761] (5/8) Epoch 18, batch 1400, loss[loss=0.1887, simple_loss=0.2789, pruned_loss=0.04927, over 4723.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3199, pruned_loss=0.07251, over 963714.98 frames.], batch size: 11, lr: 6.49e-04
2022-05-28 18:45:16,124 INFO [train.py:761] (5/8) Epoch 18, batch 1450, loss[loss=0.1946, simple_loss=0.2862, pruned_loss=0.05153, over 4668.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3214, pruned_loss=0.07308, over 964696.33 frames.], batch size: 12, lr: 6.48e-04
2022-05-28 18:45:54,039 INFO [train.py:761] (5/8) Epoch 18, batch 1500, loss[loss=0.2422, simple_loss=0.333, pruned_loss=0.07573, over 4788.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3229, pruned_loss=0.07347, over 965411.11 frames.], batch size: 13, lr: 6.48e-04
2022-05-28 18:46:32,473 INFO [train.py:761] (5/8) Epoch 18, batch 1550, loss[loss=0.2369, simple_loss=0.3199, pruned_loss=0.07698, over 4923.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3232, pruned_loss=0.07413, over 965403.30 frames.], batch size: 13, lr: 6.48e-04
2022-05-28 18:47:10,833 INFO [train.py:761] (5/8) Epoch 18, batch 1600, loss[loss=0.2768, simple_loss=0.3689, pruned_loss=0.09235, over 4889.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3242, pruned_loss=0.07472, over 966311.98 frames.], batch size: 50, lr: 6.48e-04
2022-05-28 18:47:49,170 INFO [train.py:761] (5/8) Epoch 18, batch 1650, loss[loss=0.2977, simple_loss=0.3784, pruned_loss=0.1085, over 4790.00 frames.], tot_loss[loss=0.2372, simple_loss=0.3247, pruned_loss=0.07481, over 967697.25 frames.], batch size: 20, lr: 6.48e-04
2022-05-28 18:48:27,433 INFO [train.py:761] (5/8) Epoch 18, batch 1700, loss[loss=0.1863, simple_loss=0.2819, pruned_loss=0.04533, over 4880.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3223, pruned_loss=0.07369, over 967093.72 frames.], batch size: 12, lr: 6.48e-04
2022-05-28 18:49:05,516 INFO [train.py:761] (5/8) Epoch 18, batch 1750, loss[loss=0.2443, simple_loss=0.3247, pruned_loss=0.082, over 4935.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3219, pruned_loss=0.07356, over 966170.42 frames.], batch size: 13, lr: 6.48e-04
2022-05-28 18:49:43,047 INFO [train.py:761] (5/8) Epoch 18, batch 1800, loss[loss=0.2235, simple_loss=0.3032, pruned_loss=0.07186, over 4782.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3197, pruned_loss=0.07255, over 966309.92 frames.], batch size: 16, lr: 6.47e-04
2022-05-28 18:50:20,982 INFO [train.py:761] (5/8) Epoch 18, batch 1850, loss[loss=0.2422, simple_loss=0.3327, pruned_loss=0.07591, over 4857.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3202, pruned_loss=0.0725, over 966720.21 frames.], batch size: 17, lr: 6.47e-04
2022-05-28 18:50:59,127 INFO [train.py:761] (5/8) Epoch 18, batch 1900, loss[loss=0.2537, simple_loss=0.3432, pruned_loss=0.08206, over 4790.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3183, pruned_loss=0.07179, over 966101.06 frames.], batch size: 16, lr: 6.47e-04
2022-05-28 18:51:37,176 INFO [train.py:761] (5/8) Epoch 18, batch 1950, loss[loss=0.2581, simple_loss=0.3412, pruned_loss=0.08752, over 4784.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3196, pruned_loss=0.07257, over 966235.47 frames.], batch size: 14, lr: 6.47e-04
2022-05-28 18:52:15,018 INFO [train.py:761] (5/8) Epoch 18, batch 2000, loss[loss=0.1934, simple_loss=0.2803, pruned_loss=0.05323, over 4781.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3185, pruned_loss=0.07262, over 966221.15 frames.], batch size: 13, lr: 6.47e-04
2022-05-28 18:52:53,553 INFO [train.py:761] (5/8) Epoch 18, batch 2050, loss[loss=0.2479, simple_loss=0.3474, pruned_loss=0.07419, over 4973.00 frames.], tot_loss[loss=0.2337, simple_loss=0.3207, pruned_loss=0.07337, over 967073.34 frames.], batch size: 14, lr: 6.47e-04
2022-05-28 18:53:31,188 INFO [train.py:761] (5/8) Epoch 18, batch 2100, loss[loss=0.1912, simple_loss=0.2809, pruned_loss=0.05071, over 4807.00 frames.], tot_loss[loss=0.233, simple_loss=0.3208, pruned_loss=0.07259, over 967585.88 frames.], batch size: 12, lr: 6.47e-04
2022-05-28 18:54:09,594 INFO [train.py:761] (5/8) Epoch 18, batch 2150, loss[loss=0.2335, simple_loss=0.3115, pruned_loss=0.07774, over 4963.00 frames.], tot_loss[loss=0.2333, simple_loss=0.321, pruned_loss=0.07279, over 968327.35 frames.], batch size: 12, lr: 6.46e-04
2022-05-28 18:54:47,793 INFO [train.py:761] (5/8) Epoch 18, batch 2200, loss[loss=0.1867, simple_loss=0.288, pruned_loss=0.04266, over 4672.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3204, pruned_loss=0.07249, over 967371.19 frames.], batch size: 13, lr: 6.46e-04
2022-05-28 18:55:25,825 INFO [train.py:761] (5/8) Epoch 18, batch 2250, loss[loss=0.2405, simple_loss=0.3326, pruned_loss=0.07418, over 4818.00 frames.], tot_loss[loss=0.234, simple_loss=0.3218, pruned_loss=0.07309, over 968625.07 frames.], batch size: 20, lr: 6.46e-04
2022-05-28 18:56:03,648 INFO [train.py:761] (5/8) Epoch 18, batch 2300, loss[loss=0.2534, simple_loss=0.3488, pruned_loss=0.07895, over 4862.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3218, pruned_loss=0.07259, over 968238.95 frames.], batch size: 15, lr: 6.46e-04
2022-05-28 18:56:42,129 INFO [train.py:761] (5/8) Epoch 18, batch 2350, loss[loss=0.2031, simple_loss=0.2962, pruned_loss=0.055, over 4785.00 frames.], tot_loss[loss=0.234, simple_loss=0.3222, pruned_loss=0.07286, over 968451.82 frames.], batch size: 14, lr: 6.46e-04
2022-05-28 18:57:20,037 INFO [train.py:761] (5/8) Epoch 18, batch 2400, loss[loss=0.2454, simple_loss=0.3397, pruned_loss=0.07556, over 4888.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3219, pruned_loss=0.07319, over 967943.08 frames.], batch size: 15, lr: 6.46e-04
2022-05-28 18:57:57,812 INFO [train.py:761] (5/8) Epoch 18, batch 2450, loss[loss=0.2055, simple_loss=0.3025, pruned_loss=0.05426, over 4656.00 frames.], tot_loss[loss=0.2342, simple_loss=0.322, pruned_loss=0.07321, over 967262.41 frames.], batch size: 12, lr: 6.46e-04
2022-05-28 18:58:35,768 INFO [train.py:761] (5/8) Epoch 18, batch 2500, loss[loss=0.2341, simple_loss=0.3152, pruned_loss=0.07644, over 4996.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3215, pruned_loss=0.07247, over 967074.20 frames.], batch size: 13, lr: 6.46e-04
2022-05-28 18:59:13,655 INFO [train.py:761] (5/8) Epoch 18, batch 2550, loss[loss=0.2083, simple_loss=0.3084, pruned_loss=0.05406, over 4844.00 frames.], tot_loss[loss=0.232, simple_loss=0.3205, pruned_loss=0.07175, over 966199.29 frames.], batch size: 14, lr: 6.45e-04
2022-05-28 18:59:51,841 INFO [train.py:761] (5/8) Epoch 18, batch 2600, loss[loss=0.2551, simple_loss=0.3367, pruned_loss=0.08671, over 4777.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3193, pruned_loss=0.07108, over 966508.37 frames.], batch size: 15, lr: 6.45e-04
2022-05-28 19:00:30,163 INFO [train.py:761] (5/8) Epoch 18, batch 2650, loss[loss=0.2303, simple_loss=0.3037, pruned_loss=0.07844, over 4981.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3199, pruned_loss=0.07167, over 966771.79 frames.], batch size: 13, lr: 6.45e-04
2022-05-28 19:01:07,874 INFO [train.py:761] (5/8) Epoch 18, batch 2700, loss[loss=0.1773, simple_loss=0.2536, pruned_loss=0.05057, over 4734.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3172, pruned_loss=0.06996, over 966034.60 frames.], batch size: 11, lr: 6.45e-04
2022-05-28 19:01:45,947 INFO [train.py:761] (5/8) Epoch 18, batch 2750, loss[loss=0.2697, simple_loss=0.3269, pruned_loss=0.1063, over 4663.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3188, pruned_loss=0.07075, over 966579.16 frames.], batch size: 12, lr: 6.45e-04
2022-05-28 19:02:23,718 INFO [train.py:761] (5/8) Epoch 18, batch 2800, loss[loss=0.224, simple_loss=0.3255, pruned_loss=0.06129, over 4727.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3184, pruned_loss=0.07037, over 966278.54 frames.], batch size: 13, lr: 6.45e-04
2022-05-28 19:03:01,780 INFO [train.py:761] (5/8) Epoch 18, batch 2850, loss[loss=0.1843, simple_loss=0.2807, pruned_loss=0.0439, over 4987.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3166, pruned_loss=0.06951, over 966121.94 frames.], batch size: 13, lr: 6.45e-04
2022-05-28 19:03:39,864 INFO [train.py:761] (5/8) Epoch 18, batch 2900, loss[loss=0.2354, simple_loss=0.3336, pruned_loss=0.06859, over 4787.00 frames.], tot_loss[loss=0.2279, simple_loss=0.3169, pruned_loss=0.0695, over 965877.78 frames.], batch size: 16, lr: 6.44e-04
2022-05-28 19:04:17,880 INFO [train.py:761] (5/8) Epoch 18, batch 2950, loss[loss=0.2796, simple_loss=0.36, pruned_loss=0.09957, over 4991.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3187, pruned_loss=0.07105, over 967386.35 frames.], batch size: 21, lr: 6.44e-04
2022-05-28 19:04:55,818 INFO [train.py:761] (5/8) Epoch 18, batch 3000, loss[loss=0.2342, simple_loss=0.3363, pruned_loss=0.0661, over 4759.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3186, pruned_loss=0.07055, over 966580.63 frames.], batch size: 15, lr: 6.44e-04
2022-05-28 19:04:55,818 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 19:05:05,949 INFO [train.py:790] (5/8) Epoch 18, validation: loss=0.2127, simple_loss=0.3144, pruned_loss=0.05552, over 944034.00 frames.
2022-05-28 19:05:43,708 INFO [train.py:761] (5/8) Epoch 18, batch 3050, loss[loss=0.2149, simple_loss=0.3219, pruned_loss=0.05388, over 4728.00 frames.], tot_loss[loss=0.2299, simple_loss=0.3187, pruned_loss=0.07061, over 966118.46 frames.], batch size: 13, lr: 6.44e-04
2022-05-28 19:06:22,013 INFO [train.py:761] (5/8) Epoch 18, batch 3100, loss[loss=0.2591, simple_loss=0.3389, pruned_loss=0.08967, over 4664.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3191, pruned_loss=0.07209, over 965938.98 frames.], batch size: 13, lr: 6.44e-04
2022-05-28 19:07:00,065 INFO [train.py:761] (5/8) Epoch 18, batch 3150, loss[loss=0.2213, simple_loss=0.3209, pruned_loss=0.06088, over 4728.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3211, pruned_loss=0.07422, over 965128.96 frames.], batch size: 13, lr: 6.44e-04
2022-05-28 19:07:37,904 INFO [train.py:761] (5/8) Epoch 18, batch 3200, loss[loss=0.2449, simple_loss=0.3421, pruned_loss=0.07386, over 4775.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3216, pruned_loss=0.07512, over 965207.20 frames.], batch size: 15, lr: 6.44e-04
2022-05-28 19:08:16,506 INFO [train.py:761] (5/8) Epoch 18, batch 3250, loss[loss=0.2191, simple_loss=0.3104, pruned_loss=0.06386, over 4923.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3225, pruned_loss=0.07733, over 966640.05 frames.], batch size: 13, lr: 6.43e-04
2022-05-28 19:08:54,392 INFO [train.py:761] (5/8) Epoch 18, batch 3300, loss[loss=0.1925, simple_loss=0.2654, pruned_loss=0.05986, over 4626.00 frames.], tot_loss[loss=0.2401, simple_loss=0.3229, pruned_loss=0.07865, over 965693.79 frames.], batch size: 11, lr: 6.43e-04
2022-05-28 19:09:32,677 INFO [train.py:761] (5/8) Epoch 18, batch 3350, loss[loss=0.3053, simple_loss=0.3685, pruned_loss=0.1211, over 4910.00 frames.], tot_loss[loss=0.2436, simple_loss=0.3248, pruned_loss=0.0812, over 966178.14 frames.], batch size: 14, lr: 6.43e-04
2022-05-28 19:10:10,771 INFO [train.py:761] (5/8) Epoch 18, batch 3400, loss[loss=0.2678, simple_loss=0.3357, pruned_loss=0.1, over 4720.00 frames.], tot_loss[loss=0.2467, simple_loss=0.3262, pruned_loss=0.08355, over 966798.85 frames.], batch size: 13, lr: 6.43e-04
2022-05-28 19:10:50,001 INFO [train.py:761] (5/8) Epoch 18, batch 3450, loss[loss=0.2659, simple_loss=0.3379, pruned_loss=0.0969, over 4785.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3276, pruned_loss=0.08526, over 965873.68 frames.], batch size: 14, lr: 6.43e-04
2022-05-28 19:11:28,228 INFO [train.py:761] (5/8) Epoch 18, batch 3500, loss[loss=0.2641, simple_loss=0.3497, pruned_loss=0.08926, over 4989.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3285, pruned_loss=0.08656, over 966376.62 frames.], batch size: 21, lr: 6.43e-04
2022-05-28 19:12:06,465 INFO [train.py:761] (5/8) Epoch 18, batch 3550, loss[loss=0.2428, simple_loss=0.3175, pruned_loss=0.08408, over 4671.00 frames.], tot_loss[loss=0.2515, simple_loss=0.3284, pruned_loss=0.08729, over 965198.61 frames.], batch size: 13, lr: 6.43e-04
2022-05-28 19:12:44,538 INFO [train.py:761] (5/8) Epoch 18, batch 3600, loss[loss=0.2423, simple_loss=0.3345, pruned_loss=0.07504, over 4954.00 frames.], tot_loss[loss=0.2553, simple_loss=0.3306, pruned_loss=0.09004, over 966950.19 frames.], batch size: 21, lr: 6.43e-04
2022-05-28 19:13:22,630 INFO [train.py:761] (5/8) Epoch 18, batch 3650, loss[loss=0.2508, simple_loss=0.3132, pruned_loss=0.09418, over 4723.00 frames.], tot_loss[loss=0.2541, simple_loss=0.3291, pruned_loss=0.08954, over 965897.94 frames.], batch size: 11, lr: 6.42e-04
2022-05-28 19:14:00,661 INFO [train.py:761] (5/8) Epoch 18, batch 3700, loss[loss=0.2499, simple_loss=0.3413, pruned_loss=0.07928, over 4786.00 frames.], tot_loss[loss=0.2555, simple_loss=0.3303, pruned_loss=0.09039, over 966422.70 frames.], batch size: 14, lr: 6.42e-04
2022-05-28 19:14:38,633 INFO [train.py:761] (5/8) Epoch 18, batch 3750, loss[loss=0.2548, simple_loss=0.3364, pruned_loss=0.08666, over 4658.00 frames.], tot_loss[loss=0.2571, simple_loss=0.3317, pruned_loss=0.09124, over 966394.12 frames.], batch size: 12, lr: 6.42e-04
2022-05-28 19:15:16,783 INFO [train.py:761] (5/8) Epoch 18, batch 3800, loss[loss=0.2523, simple_loss=0.325, pruned_loss=0.0898, over 4719.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3305, pruned_loss=0.09091, over 966771.62 frames.], batch size: 13, lr: 6.42e-04
2022-05-28 19:15:55,133 INFO [train.py:761] (5/8) Epoch 18, batch 3850, loss[loss=0.2397, simple_loss=0.3124, pruned_loss=0.08352, over 4988.00 frames.], tot_loss[loss=0.2569, simple_loss=0.3311, pruned_loss=0.09136, over 966693.22 frames.], batch size: 13, lr: 6.42e-04
2022-05-28 19:16:33,875 INFO [train.py:761] (5/8) Epoch 18, batch 3900, loss[loss=0.2902, simple_loss=0.3655, pruned_loss=0.1074, over 4927.00 frames.], tot_loss[loss=0.2565, simple_loss=0.3309, pruned_loss=0.09106, over 966941.02 frames.], batch size: 47, lr: 6.42e-04
2022-05-28 19:17:11,858 INFO [train.py:761] (5/8) Epoch 18, batch 3950, loss[loss=0.2541, simple_loss=0.3305, pruned_loss=0.08889, over 4875.00 frames.], tot_loss[loss=0.2554, simple_loss=0.3298, pruned_loss=0.09049, over 966477.63 frames.], batch size: 17, lr: 6.42e-04
2022-05-28 19:17:49,989 INFO [train.py:761] (5/8) Epoch 18, batch 4000, loss[loss=0.247, simple_loss=0.3103, pruned_loss=0.09188, over 4832.00 frames.], tot_loss[loss=0.2549, simple_loss=0.33, pruned_loss=0.08992, over 965970.58 frames.], batch size: 11, lr: 6.41e-04
2022-05-28 19:18:28,192 INFO [train.py:761] (5/8) Epoch 18, batch 4050, loss[loss=0.2252, simple_loss=0.311, pruned_loss=0.06965, over 4882.00 frames.], tot_loss[loss=0.2539, simple_loss=0.3291, pruned_loss=0.0894, over 966455.36 frames.], batch size: 15, lr: 6.41e-04
2022-05-28 19:19:06,064 INFO [train.py:761] (5/8) Epoch 18, batch 4100, loss[loss=0.2928, simple_loss=0.3484, pruned_loss=0.1186, over 4804.00 frames.], tot_loss[loss=0.2513, simple_loss=0.3265, pruned_loss=0.08805, over 965707.85 frames.], batch size: 16, lr: 6.41e-04
2022-05-28 19:19:44,270 INFO [train.py:761] (5/8) Epoch 18, batch 4150, loss[loss=0.2818, simple_loss=0.34, pruned_loss=0.1118, over 4943.00 frames.], tot_loss[loss=0.252, simple_loss=0.3278, pruned_loss=0.08817, over 966396.52 frames.], batch size: 21, lr: 6.41e-04
2022-05-28 19:20:22,995 INFO [train.py:761] (5/8) Epoch 18, batch 4200, loss[loss=0.2515, simple_loss=0.332, pruned_loss=0.08548, over 4891.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3282, pruned_loss=0.08859, over 966275.59 frames.], batch size: 17, lr: 6.41e-04
2022-05-28 19:21:00,906 INFO [train.py:761] (5/8) Epoch 18, batch 4250, loss[loss=0.3421, simple_loss=0.3923, pruned_loss=0.1459, over 4729.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3281, pruned_loss=0.08855, over 965549.88 frames.], batch size: 12, lr: 6.41e-04
2022-05-28 19:21:38,793 INFO [train.py:761] (5/8) Epoch 18, batch 4300, loss[loss=0.2904, simple_loss=0.3445, pruned_loss=0.1182, over 4979.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3282, pruned_loss=0.08859, over 966300.25 frames.], batch size: 12, lr: 6.41e-04
2022-05-28 19:22:17,491 INFO [train.py:761] (5/8) Epoch 18, batch 4350, loss[loss=0.2273, simple_loss=0.3104, pruned_loss=0.07212, over 4971.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3272, pruned_loss=0.08826, over 967133.28 frames.], batch size: 15, lr: 6.40e-04
2022-05-28 19:22:55,664 INFO [train.py:761] (5/8) Epoch 18, batch 4400, loss[loss=0.2996, simple_loss=0.3696, pruned_loss=0.1148, over 4851.00 frames.], tot_loss[loss=0.2534, simple_loss=0.3287, pruned_loss=0.0891, over 967274.97 frames.], batch size: 26, lr: 6.40e-04
2022-05-28 19:23:33,931 INFO [train.py:761] (5/8) Epoch 18, batch 4450, loss[loss=0.2543, simple_loss=0.3104, pruned_loss=0.09914, over 4972.00 frames.], tot_loss[loss=0.2549, simple_loss=0.3299, pruned_loss=0.08994, over 967563.74 frames.], batch size: 11, lr: 6.40e-04
2022-05-28 19:24:12,119 INFO [train.py:761] (5/8) Epoch 18, batch 4500, loss[loss=0.2243, simple_loss=0.2902, pruned_loss=0.07922, over 4811.00 frames.], tot_loss[loss=0.2536, simple_loss=0.3286, pruned_loss=0.08925, over 967316.92 frames.], batch size: 12, lr: 6.40e-04
2022-05-28 19:24:50,991 INFO [train.py:761] (5/8) Epoch 18, batch 4550, loss[loss=0.2157, simple_loss=0.2842, pruned_loss=0.07355, over 4833.00 frames.], tot_loss[loss=0.2528, simple_loss=0.3277, pruned_loss=0.0889, over 966023.01 frames.], batch size: 11, lr: 6.40e-04
2022-05-28 19:25:29,176 INFO [train.py:761] (5/8) Epoch 18, batch 4600, loss[loss=0.2621, simple_loss=0.3306, pruned_loss=0.09684, over 4737.00 frames.], tot_loss[loss=0.2528, simple_loss=0.3274, pruned_loss=0.08908, over 965578.69 frames.], batch size: 12, lr: 6.40e-04
2022-05-28 19:26:07,300 INFO [train.py:761] (5/8) Epoch 18, batch 4650, loss[loss=0.2439, simple_loss=0.3394, pruned_loss=0.07423, over 4793.00 frames.], tot_loss[loss=0.2531, simple_loss=0.3279, pruned_loss=0.08915, over 965939.58 frames.], batch size: 14, lr: 6.40e-04
2022-05-28 19:26:45,416 INFO [train.py:761] (5/8) Epoch 18, batch 4700, loss[loss=0.2288, simple_loss=0.2837, pruned_loss=0.08691, over 4830.00 frames.], tot_loss[loss=0.2528, simple_loss=0.3277, pruned_loss=0.08896, over 965584.40 frames.], batch size: 11, lr: 6.40e-04
2022-05-28 19:27:23,478 INFO [train.py:761] (5/8) Epoch 18, batch 4750, loss[loss=0.2368, simple_loss=0.318, pruned_loss=0.07776, over 4951.00 frames.], tot_loss[loss=0.2546, simple_loss=0.3295, pruned_loss=0.08985, over 966111.31 frames.], batch size: 16, lr: 6.39e-04
2022-05-28 19:28:02,153 INFO [train.py:761] (5/8) Epoch 18, batch 4800, loss[loss=0.2328, simple_loss=0.3044, pruned_loss=0.08059, over 4882.00 frames.], tot_loss[loss=0.254, simple_loss=0.3289, pruned_loss=0.08956, over 965777.70 frames.], batch size: 12, lr: 6.39e-04
2022-05-28 19:28:40,686 INFO [train.py:761] (5/8) Epoch 18, batch 4850, loss[loss=0.261, simple_loss=0.3563, pruned_loss=0.08283, over 4946.00 frames.], tot_loss[loss=0.2523, simple_loss=0.3278, pruned_loss=0.0884, over 965191.95 frames.], batch size: 16, lr: 6.39e-04
2022-05-28 19:29:18,843 INFO [train.py:761] (5/8) Epoch 18, batch 4900, loss[loss=0.2242, simple_loss=0.309, pruned_loss=0.06965, over 4911.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3283, pruned_loss=0.08854, over 965756.12 frames.], batch size: 13, lr: 6.39e-04
2022-05-28 19:29:57,217 INFO [train.py:761] (5/8) Epoch 18, batch 4950, loss[loss=0.269, simple_loss=0.3465, pruned_loss=0.09573, over 4668.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3282, pruned_loss=0.08848, over 964322.20 frames.], batch size: 13, lr: 6.39e-04
2022-05-28 19:30:35,337 INFO [train.py:761] (5/8) Epoch 18, batch 5000, loss[loss=0.2096, simple_loss=0.2799, pruned_loss=0.06969, over 4826.00 frames.], tot_loss[loss=0.251, simple_loss=0.3269, pruned_loss=0.0875, over 965340.76 frames.], batch size: 11, lr: 6.39e-04
2022-05-28 19:31:13,464 INFO [train.py:761] (5/8) Epoch 18, batch 5050, loss[loss=0.3031, simple_loss=0.3672, pruned_loss=0.1195, over 4714.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3272, pruned_loss=0.08756, over 965340.25 frames.], batch size: 14, lr: 6.39e-04
2022-05-28 19:31:51,874 INFO [train.py:761] (5/8) Epoch 18, batch 5100, loss[loss=0.2337, simple_loss=0.3146, pruned_loss=0.07645, over 4884.00 frames.], tot_loss[loss=0.2544, simple_loss=0.33, pruned_loss=0.08942, over 966182.34 frames.], batch size: 12, lr: 6.38e-04
2022-05-28 19:32:30,253 INFO [train.py:761] (5/8) Epoch 18, batch 5150, loss[loss=0.2471, simple_loss=0.3319, pruned_loss=0.08112, over 4729.00 frames.], tot_loss[loss=0.2539, simple_loss=0.3294, pruned_loss=0.0892, over 966243.86 frames.], batch size: 13, lr: 6.38e-04
2022-05-28 19:33:08,284 INFO [train.py:761] (5/8) Epoch 18, batch 5200, loss[loss=0.2337, simple_loss=0.315, pruned_loss=0.07615, over 4669.00 frames.], tot_loss[loss=0.251, simple_loss=0.3271, pruned_loss=0.08746, over 966777.46 frames.], batch size: 12, lr: 6.38e-04
2022-05-28 19:33:47,323 INFO [train.py:761] (5/8) Epoch 18, batch 5250, loss[loss=0.2337, simple_loss=0.3331, pruned_loss=0.06714, over 4941.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3279, pruned_loss=0.0879, over 967680.52 frames.], batch size: 16, lr: 6.38e-04
2022-05-28 19:34:25,762 INFO [train.py:761] (5/8) Epoch 18, batch 5300, loss[loss=0.2454, simple_loss=0.3347, pruned_loss=0.07806, over 4862.00 frames.], tot_loss[loss=0.252, simple_loss=0.3281, pruned_loss=0.08793, over 966582.81 frames.], batch size: 13, lr: 6.38e-04
2022-05-28 19:35:07,743 INFO [train.py:761] (5/8) Epoch 18, batch 5350, loss[loss=0.2349, simple_loss=0.3202, pruned_loss=0.07479, over 4850.00 frames.], tot_loss[loss=0.2518, simple_loss=0.328, pruned_loss=0.08781, over 966369.01 frames.], batch size: 14, lr: 6.38e-04
2022-05-28 19:35:46,170 INFO [train.py:761] (5/8) Epoch 18, batch 5400, loss[loss=0.2733, simple_loss=0.3713, pruned_loss=0.08771, over 4877.00 frames.], tot_loss[loss=0.2515, simple_loss=0.3285, pruned_loss=0.08725, over 966666.53 frames.], batch size: 17, lr: 6.38e-04
2022-05-28 19:36:23,854 INFO [train.py:761] (5/8) Epoch 18, batch 5450, loss[loss=0.2494, simple_loss=0.3286, pruned_loss=0.08511, over 4994.00 frames.], tot_loss[loss=0.2516, simple_loss=0.328, pruned_loss=0.08756, over 966188.17 frames.], batch size: 13, lr: 6.38e-04
2022-05-28 19:37:01,842 INFO [train.py:761] (5/8) Epoch 18, batch 5500, loss[loss=0.311, simple_loss=0.3632, pruned_loss=0.1295, over 4885.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3271, pruned_loss=0.08682, over 964857.37 frames.], batch size: 12, lr: 6.37e-04
2022-05-28 19:37:39,794 INFO [train.py:761] (5/8) Epoch 18, batch 5550, loss[loss=0.2521, simple_loss=0.3072, pruned_loss=0.09846, over 4560.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3262, pruned_loss=0.08671, over 963853.15 frames.], batch size: 10, lr: 6.37e-04
2022-05-28 19:38:17,888 INFO [train.py:761] (5/8) Epoch 18, batch 5600, loss[loss=0.2452, simple_loss=0.3257, pruned_loss=0.08236, over 4986.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3256, pruned_loss=0.08708, over 963974.50 frames.], batch size: 21, lr: 6.37e-04
2022-05-28 19:38:55,908 INFO [train.py:761] (5/8) Epoch 18, batch 5650, loss[loss=0.2307, simple_loss=0.3011, pruned_loss=0.08013, over 4881.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3254, pruned_loss=0.08717, over 964819.11 frames.], batch size: 12, lr: 6.37e-04
2022-05-28 19:39:34,173 INFO [train.py:761] (5/8) Epoch 18, batch 5700, loss[loss=0.2933, simple_loss=0.358, pruned_loss=0.1143, over 4885.00 frames.], tot_loss[loss=0.25, simple_loss=0.3257, pruned_loss=0.08714, over 965278.91 frames.], batch size: 15, lr: 6.37e-04
2022-05-28 19:40:12,214 INFO [train.py:761] (5/8) Epoch 18, batch 5750, loss[loss=0.1874, simple_loss=0.2786, pruned_loss=0.04812, over 4838.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3239, pruned_loss=0.08589, over 965030.45 frames.], batch size: 11, lr: 6.37e-04
2022-05-28 19:40:50,686 INFO [train.py:761] (5/8) Epoch 18, batch 5800, loss[loss=0.3634, simple_loss=0.4086, pruned_loss=0.1591, over 4959.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3245, pruned_loss=0.08626, over 964678.03 frames.], batch size: 48, lr: 6.37e-04
2022-05-28 19:41:29,711 INFO [train.py:761] (5/8) Epoch 18, batch 5850, loss[loss=0.2552, simple_loss=0.3316, pruned_loss=0.08946, over 4855.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3266, pruned_loss=0.08738, over 965972.02 frames.], batch size: 13, lr: 6.36e-04
2022-05-28 19:42:07,934 INFO [train.py:761] (5/8) Epoch 18, batch 5900, loss[loss=0.2308, simple_loss=0.3119, pruned_loss=0.07486, over 4846.00 frames.], tot_loss[loss=0.2501, simple_loss=0.3261, pruned_loss=0.08709, over 966572.47 frames.], batch size: 13, lr: 6.36e-04
2022-05-28 19:42:46,191 INFO [train.py:761] (5/8) Epoch 18, batch 5950, loss[loss=0.2647, simple_loss=0.3337, pruned_loss=0.09784, over 4974.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3258, pruned_loss=0.08731, over 967330.51 frames.], batch size: 14, lr: 6.36e-04
2022-05-28 19:43:24,124 INFO [train.py:761] (5/8) Epoch 18, batch 6000, loss[loss=0.2515, simple_loss=0.3318, pruned_loss=0.08561, over 4849.00 frames.], tot_loss[loss=0.251, simple_loss=0.3267, pruned_loss=0.08764, over 967721.11 frames.], batch size: 18, lr: 6.36e-04
2022-05-28 19:43:24,125 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 19:43:34,065 INFO [train.py:790] (5/8) Epoch 18, validation: loss=0.2033, simple_loss=0.31, pruned_loss=0.04834, over 944034.00 frames.
2022-05-28 19:44:12,832 INFO [train.py:761] (5/8) Epoch 18, batch 6050, loss[loss=0.2663, simple_loss=0.3349, pruned_loss=0.0989, over 4784.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3273, pruned_loss=0.08779, over 967192.28 frames.], batch size: 20, lr: 6.36e-04
2022-05-28 19:44:51,159 INFO [train.py:761] (5/8) Epoch 18, batch 6100, loss[loss=0.2632, simple_loss=0.3395, pruned_loss=0.09349, over 4772.00 frames.], tot_loss[loss=0.2531, simple_loss=0.3289, pruned_loss=0.08861, over 968192.73 frames.], batch size: 16, lr: 6.36e-04
2022-05-28 19:45:29,574 INFO [train.py:761] (5/8) Epoch 18, batch 6150, loss[loss=0.215, simple_loss=0.2907, pruned_loss=0.06966, over 4972.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3279, pruned_loss=0.08797, over 968109.39 frames.], batch size: 12, lr: 6.36e-04
2022-05-28 19:46:08,008 INFO [train.py:761] (5/8) Epoch 18, batch 6200, loss[loss=0.2666, simple_loss=0.3487, pruned_loss=0.09228, over 4918.00 frames.], tot_loss[loss=0.2522, simple_loss=0.3278, pruned_loss=0.08828, over 967641.28 frames.], batch size: 14, lr: 6.36e-04
2022-05-28 19:46:46,130 INFO [train.py:761] (5/8) Epoch 18, batch 6250, loss[loss=0.2555, simple_loss=0.3239, pruned_loss=0.09355, over 4986.00 frames.], tot_loss[loss=0.2519, simple_loss=0.328, pruned_loss=0.08789, over 967464.28 frames.], batch size: 12, lr: 6.35e-04
2022-05-28 19:47:24,424 INFO [train.py:761] (5/8) Epoch 18, batch 6300, loss[loss=0.2331, simple_loss=0.3268, pruned_loss=0.06971, over 4793.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3271, pruned_loss=0.08708, over 967588.46 frames.], batch size: 14, lr: 6.35e-04
2022-05-28 19:48:02,962 INFO [train.py:761] (5/8) Epoch 18, batch 6350, loss[loss=0.2524, simple_loss=0.3359, pruned_loss=0.08446, over 4786.00 frames.], tot_loss[loss=0.2503, simple_loss=0.3268, pruned_loss=0.08687, over 966838.93 frames.], batch size: 14, lr: 6.35e-04
2022-05-28 19:48:41,275 INFO [train.py:761] (5/8) Epoch 18, batch 6400, loss[loss=0.2193, simple_loss=0.2893, pruned_loss=0.07461, over 4985.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3263, pruned_loss=0.08659, over 967404.51 frames.], batch size: 12, lr: 6.35e-04
2022-05-28 19:49:19,812 INFO [train.py:761] (5/8) Epoch 18, batch 6450, loss[loss=0.2349, simple_loss=0.3194, pruned_loss=0.0752, over 4855.00 frames.], tot_loss[loss=0.2501, simple_loss=0.327, pruned_loss=0.08659, over 967707.52 frames.], batch size: 14, lr: 6.35e-04
2022-05-28 19:49:58,399 INFO [train.py:761] (5/8) Epoch 18, batch 6500, loss[loss=0.2991, simple_loss=0.3669, pruned_loss=0.1156, over 4908.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3269, pruned_loss=0.0872, over 968451.18 frames.], batch size: 14, lr: 6.35e-04
2022-05-28 19:50:36,787 INFO [train.py:761] (5/8) Epoch 18, batch 6550, loss[loss=0.2114, simple_loss=0.292, pruned_loss=0.06533, over 4808.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3261, pruned_loss=0.0873, over 967312.83 frames.], batch size: 12, lr: 6.35e-04
2022-05-28 19:51:14,563 INFO [train.py:761] (5/8) Epoch 18, batch 6600, loss[loss=0.2191, simple_loss=0.3026, pruned_loss=0.06776, over 4918.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3258, pruned_loss=0.08766, over 966959.97 frames.], batch size: 13, lr: 6.35e-04
2022-05-28 19:51:53,325 INFO [train.py:761] (5/8) Epoch 18, batch 6650, loss[loss=0.2724, simple_loss=0.3375, pruned_loss=0.1037, over 4880.00 frames.], tot_loss[loss=0.2504, simple_loss=0.326, pruned_loss=0.08742, over 967056.18 frames.], batch size: 15, lr: 6.34e-04
2022-05-28 19:52:31,082 INFO [train.py:761] (5/8) Epoch 18, batch 6700, loss[loss=0.2528, simple_loss=0.3377, pruned_loss=0.08391, over 4917.00 frames.], tot_loss[loss=0.2486, simple_loss=0.3244, pruned_loss=0.08642, over 967230.20 frames.], batch size: 14, lr: 6.34e-04
2022-05-28 19:53:28,529 INFO [train.py:761] (5/8) Epoch 19, batch 0, loss[loss=0.2292, simple_loss=0.3166, pruned_loss=0.07093, over 4776.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3166, pruned_loss=0.07093, over 4776.00 frames.], batch size: 15, lr: 6.34e-04
2022-05-28 19:54:06,437 INFO [train.py:761] (5/8) Epoch 19, batch 50, loss[loss=0.2489, simple_loss=0.3295, pruned_loss=0.08415, over 4663.00 frames.], tot_loss[loss=0.232, simple_loss=0.317, pruned_loss=0.07349, over 217830.17 frames.], batch size: 12, lr: 6.34e-04
2022-05-28 19:54:44,605 INFO [train.py:761] (5/8) Epoch 19, batch 100, loss[loss=0.2247, simple_loss=0.3236, pruned_loss=0.06288, over 4714.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3169, pruned_loss=0.07074, over 383697.68 frames.], batch size: 14, lr: 6.34e-04
2022-05-28 19:55:22,144 INFO [train.py:761] (5/8) Epoch 19, batch 150, loss[loss=0.2083, simple_loss=0.2948, pruned_loss=0.06096, over 4667.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3151, pruned_loss=0.06989, over 512233.74 frames.], batch size: 12, lr: 6.34e-04
2022-05-28 19:56:00,318 INFO [train.py:761] (5/8) Epoch 19, batch 200, loss[loss=0.1963, simple_loss=0.2763, pruned_loss=0.05815, over 4811.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3138, pruned_loss=0.06957, over 613292.06 frames.], batch size: 12, lr: 6.34e-04
2022-05-28 19:56:38,241 INFO [train.py:761] (5/8) Epoch 19, batch 250, loss[loss=0.2043, simple_loss=0.2875, pruned_loss=0.06057, over 4975.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3129, pruned_loss=0.06884, over 691864.90 frames.], batch size: 12, lr: 6.33e-04
2022-05-28 19:57:16,714 INFO [train.py:761] (5/8) Epoch 19, batch 300, loss[loss=0.1962, simple_loss=0.2717, pruned_loss=0.06038, over 4986.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3128, pruned_loss=0.06844, over 753819.73 frames.], batch size: 11, lr: 6.33e-04
2022-05-28 19:57:54,214 INFO [train.py:761] (5/8) Epoch 19, batch 350, loss[loss=0.1794, simple_loss=0.258, pruned_loss=0.05038, over 4746.00 frames.], tot_loss[loss=0.2218, simple_loss=0.31, pruned_loss=0.0668, over 800473.24 frames.], batch size: 11, lr: 6.33e-04
2022-05-28 19:58:32,139 INFO [train.py:761] (5/8) Epoch 19, batch 400, loss[loss=0.2331, simple_loss=0.3352, pruned_loss=0.06552, over 4723.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3113, pruned_loss=0.06657, over 837736.90 frames.], batch size: 13, lr: 6.33e-04
2022-05-28 19:59:10,071 INFO [train.py:761] (5/8) Epoch 19, batch 450, loss[loss=0.231, simple_loss=0.3269, pruned_loss=0.0675, over 4894.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3125, pruned_loss=0.06639, over 866042.51 frames.], batch size: 15, lr: 6.33e-04
2022-05-28 19:59:48,798 INFO [train.py:761] (5/8) Epoch 19, batch 500, loss[loss=0.1946, simple_loss=0.2936, pruned_loss=0.04777, over 4855.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3106, pruned_loss=0.06583, over 889293.42 frames.], batch size: 14, lr: 6.33e-04
2022-05-28 20:00:26,608 INFO [train.py:761] (5/8) Epoch 19, batch 550, loss[loss=0.225, simple_loss=0.302, pruned_loss=0.07402, over 4883.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3129, pruned_loss=0.06678, over 906468.22 frames.], batch size: 15, lr: 6.33e-04
2022-05-28 20:01:04,785 INFO [train.py:761] (5/8) Epoch 19, batch 600, loss[loss=0.2284, simple_loss=0.308, pruned_loss=0.07437, over 4773.00 frames.], tot_loss[loss=0.2215, simple_loss=0.311, pruned_loss=0.066, over 919611.82 frames.], batch size: 13, lr: 6.33e-04
2022-05-28 20:01:42,505 INFO [train.py:761] (5/8) Epoch 19, batch 650, loss[loss=0.2046, simple_loss=0.2824, pruned_loss=0.0634, over 4994.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3128, pruned_loss=0.06694, over 930448.63 frames.], batch size: 13, lr: 6.32e-04
2022-05-28 20:02:20,285 INFO [train.py:761] (5/8) Epoch 19, batch 700, loss[loss=0.1853, simple_loss=0.2846, pruned_loss=0.043, over 4666.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3139, pruned_loss=0.06757, over 938066.57 frames.], batch size: 12, lr: 6.32e-04
2022-05-28 20:02:57,919 INFO [train.py:761] (5/8) Epoch 19, batch 750, loss[loss=0.2625, simple_loss=0.3608, pruned_loss=0.08204, over 4753.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3138, pruned_loss=0.06834, over 944073.39 frames.], batch size: 15, lr: 6.32e-04
2022-05-28 20:03:35,890 INFO [train.py:761] (5/8) Epoch 19, batch 800, loss[loss=0.2034, simple_loss=0.2958, pruned_loss=0.05552, over 4990.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3157, pruned_loss=0.06952, over 949107.76 frames.], batch size: 13, lr: 6.32e-04
2022-05-28 20:04:13,460 INFO [train.py:761] (5/8) Epoch 19, batch 850, loss[loss=0.2386, simple_loss=0.3254, pruned_loss=0.07584, over 4955.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3158, pruned_loss=0.0697, over 953074.17 frames.], batch size: 16, lr: 6.32e-04
2022-05-28 20:04:51,898 INFO [train.py:761] (5/8) Epoch 19, batch 900, loss[loss=0.2785, simple_loss=0.3604, pruned_loss=0.09836, over 4803.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3172, pruned_loss=0.07078, over 956111.59 frames.], batch size: 16, lr: 6.32e-04
2022-05-28 20:05:29,888 INFO [train.py:761] (5/8) Epoch 19, batch 950, loss[loss=0.1854, simple_loss=0.2649, pruned_loss=0.05293, over 4728.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3188, pruned_loss=0.07146, over 958900.48 frames.], batch size: 11, lr: 6.32e-04
2022-05-28 20:06:08,053 INFO [train.py:761] (5/8) Epoch 19, batch 1000, loss[loss=0.2346, simple_loss=0.3219, pruned_loss=0.07362, over 4672.00 frames.], tot_loss[loss=0.2307, simple_loss=0.319, pruned_loss=0.07119, over 960502.51 frames.], batch size: 13, lr: 6.32e-04
2022-05-28 20:06:45,599 INFO [train.py:761] (5/8) Epoch 19, batch 1050, loss[loss=0.2353, simple_loss=0.3372, pruned_loss=0.06667, over 4976.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3163, pruned_loss=0.07002, over 961339.65 frames.], batch size: 14, lr: 6.31e-04
2022-05-28 20:07:23,807 INFO [train.py:761] (5/8) Epoch 19, batch 1100, loss[loss=0.2167, simple_loss=0.3233, pruned_loss=0.0551, over 4789.00 frames.], tot_loss[loss=0.229, simple_loss=0.3166, pruned_loss=0.07064, over 961965.39 frames.], batch size: 16, lr: 6.31e-04
2022-05-28 20:08:01,432 INFO [train.py:761] (5/8) Epoch 19, batch 1150, loss[loss=0.2078, simple_loss=0.2983, pruned_loss=0.05867, over 4839.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3165, pruned_loss=0.07025, over 963400.73 frames.], batch size: 11, lr: 6.31e-04
2022-05-28 20:08:40,181 INFO [train.py:761] (5/8) Epoch 19, batch 1200, loss[loss=0.1966, simple_loss=0.2762, pruned_loss=0.05847, over 4973.00 frames.], tot_loss[loss=0.2282, simple_loss=0.316, pruned_loss=0.07025, over 963084.98 frames.], batch size: 12, lr: 6.31e-04
2022-05-28 20:09:18,332 INFO [train.py:761] (5/8) Epoch 19, batch 1250, loss[loss=0.2715, simple_loss=0.3533, pruned_loss=0.0948, over 4973.00 frames.], tot_loss[loss=0.2282, simple_loss=0.316, pruned_loss=0.07022, over 963198.88 frames.], batch size: 14, lr: 6.31e-04
2022-05-28 20:09:56,088 INFO [train.py:761] (5/8) Epoch 19, batch 1300, loss[loss=0.1984, simple_loss=0.2869, pruned_loss=0.05493, over 4667.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3172, pruned_loss=0.07089, over 964652.75 frames.], batch size: 12, lr: 6.31e-04
2022-05-28 20:10:33,749 INFO [train.py:761] (5/8) Epoch 19, batch 1350, loss[loss=0.2204, simple_loss=0.3222, pruned_loss=0.05929, over 4725.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3167, pruned_loss=0.07027, over 964984.51 frames.], batch size: 13, lr: 6.31e-04
2022-05-28 20:11:12,179 INFO [train.py:761] (5/8) Epoch 19, batch 1400, loss[loss=0.251, simple_loss=0.3427, pruned_loss=0.07964, over 4980.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3184, pruned_loss=0.071, over 965351.10 frames.], batch size: 14, lr: 6.31e-04
2022-05-28 20:11:50,616 INFO [train.py:761] (5/8) Epoch 19, batch 1450, loss[loss=0.2398, simple_loss=0.3235, pruned_loss=0.078, over 4979.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3184, pruned_loss=0.07065, over 966842.78 frames.], batch size: 14, lr: 6.30e-04
2022-05-28 20:12:28,734 INFO [train.py:761] (5/8) Epoch 19, batch 1500, loss[loss=0.2102, simple_loss=0.2869, pruned_loss=0.06672, over 4893.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3189, pruned_loss=0.07085, over 966557.56 frames.], batch size: 12, lr: 6.30e-04
2022-05-28 20:13:06,131 INFO [train.py:761] (5/8) Epoch 19, batch 1550, loss[loss=0.248, simple_loss=0.3484, pruned_loss=0.07375, over 4790.00 frames.], tot_loss[loss=0.23, simple_loss=0.3188, pruned_loss=0.07061, over 966315.45 frames.], batch size: 20, lr: 6.30e-04
2022-05-28 20:13:44,329 INFO [train.py:761] (5/8) Epoch 19, batch 1600, loss[loss=0.2442, simple_loss=0.3398, pruned_loss=0.07435, over 4975.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3164, pruned_loss=0.06949, over 966906.19 frames.], batch size: 14, lr: 6.30e-04
2022-05-28 20:14:22,685 INFO [train.py:761] (5/8) Epoch 19, batch 1650, loss[loss=0.2938, simple_loss=0.3605, pruned_loss=0.1135, over 4842.00 frames.], tot_loss[loss=0.2271, simple_loss=0.3153, pruned_loss=0.06945, over 965959.51 frames.], batch size: 18, lr: 6.30e-04
2022-05-28 20:15:00,827 INFO [train.py:761] (5/8) Epoch 19, batch 1700, loss[loss=0.1879, simple_loss=0.2771, pruned_loss=0.04935, over 4733.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3155, pruned_loss=0.06965, over 965418.68 frames.], batch size: 11, lr: 6.30e-04
2022-05-28 20:15:38,453 INFO [train.py:761] (5/8) Epoch 19, batch 1750, loss[loss=0.1938, simple_loss=0.2843, pruned_loss=0.05166, over 4981.00 frames.], tot_loss[loss=0.228, simple_loss=0.3163, pruned_loss=0.06978, over 966830.86 frames.], batch size: 13, lr: 6.30e-04
2022-05-28 20:16:15,966 INFO [train.py:761] (5/8) Epoch 19, batch 1800, loss[loss=0.2275, simple_loss=0.3416, pruned_loss=0.05675, over 4871.00 frames.], tot_loss[loss=0.228, simple_loss=0.3165, pruned_loss=0.06969, over 966457.43 frames.], batch size: 15, lr: 6.29e-04
2022-05-28 20:16:53,991 INFO [train.py:761] (5/8) Epoch 19, batch 1850, loss[loss=0.1938, simple_loss=0.2808, pruned_loss=0.05337, over 4995.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3157, pruned_loss=0.06881, over 966036.40 frames.], batch size: 13, lr: 6.29e-04
2022-05-28 20:17:32,066 INFO [train.py:761] (5/8) Epoch 19, batch 1900, loss[loss=0.214, simple_loss=0.2896, pruned_loss=0.06924, over 4742.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3167, pruned_loss=0.06903, over 965419.76 frames.], batch size: 11, lr: 6.29e-04
2022-05-28 20:18:09,849 INFO [train.py:761] (5/8) Epoch 19, batch 1950, loss[loss=0.2349, simple_loss=0.3109, pruned_loss=0.07945, over 4849.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3172, pruned_loss=0.0689, over 966688.54 frames.], batch size: 13, lr: 6.29e-04
2022-05-28 20:18:48,418 INFO [train.py:761] (5/8) Epoch 19, batch 2000, loss[loss=0.2446, simple_loss=0.3364, pruned_loss=0.07639, over 4992.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3172, pruned_loss=0.06891, over 967119.84 frames.], batch size: 13, lr: 6.29e-04
2022-05-28 20:19:27,003 INFO [train.py:761] (5/8) Epoch 19, batch 2050, loss[loss=0.2038, simple_loss=0.3003, pruned_loss=0.05368, over 4668.00 frames.], tot_loss[loss=0.2282, simple_loss=0.318, pruned_loss=0.06926, over 966584.51 frames.], batch size: 12, lr: 6.29e-04
2022-05-28 20:20:04,989 INFO [train.py:761] (5/8) Epoch 19, batch 2100, loss[loss=0.2746, simple_loss=0.3614, pruned_loss=0.09388, over 4859.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3179, pruned_loss=0.06957, over 966079.86 frames.], batch size: 14, lr: 6.29e-04
2022-05-28 20:20:43,360 INFO [train.py:761] (5/8) Epoch 19, batch 2150, loss[loss=0.1815, simple_loss=0.2853, pruned_loss=0.03888, over 4967.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3164, pruned_loss=0.06944, over 965320.33 frames.], batch size: 15, lr: 6.29e-04
2022-05-28 20:21:21,556 INFO [train.py:761] (5/8) Epoch 19, batch 2200, loss[loss=0.2806, simple_loss=0.363, pruned_loss=0.09907, over 4946.00 frames.], tot_loss[loss=0.228, simple_loss=0.3165, pruned_loss=0.0697, over 966029.02 frames.], batch size: 16, lr: 6.28e-04
2022-05-28 20:21:59,569 INFO [train.py:761] (5/8) Epoch 19, batch 2250, loss[loss=0.2002, simple_loss=0.2884, pruned_loss=0.05598, over 4882.00 frames.], tot_loss[loss=0.2273, simple_loss=0.316, pruned_loss=0.06934, over 968057.86 frames.], batch size: 15, lr: 6.28e-04
2022-05-28 20:22:37,947 INFO [train.py:761] (5/8) Epoch 19, batch 2300, loss[loss=0.2269, simple_loss=0.3241, pruned_loss=0.06489, over 4789.00 frames.], tot_loss[loss=0.2262, simple_loss=0.315, pruned_loss=0.06874, over 967481.00 frames.], batch size: 14, lr: 6.28e-04
2022-05-28 20:23:15,538 INFO [train.py:761] (5/8) Epoch 19, batch 2350, loss[loss=0.1654, simple_loss=0.2596, pruned_loss=0.03559, over 4974.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3156, pruned_loss=0.06874, over 966782.12 frames.], batch size: 12, lr: 6.28e-04
2022-05-28 20:23:53,786 INFO [train.py:761] (5/8) Epoch 19, batch 2400, loss[loss=0.2893, simple_loss=0.3717, pruned_loss=0.1035, over 4908.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3153, pruned_loss=0.06825, over 967474.36 frames.], batch size: 48, lr: 6.28e-04
2022-05-28 20:24:31,998 INFO [train.py:761] (5/8) Epoch 19, batch 2450, loss[loss=0.193, simple_loss=0.2817, pruned_loss=0.05216, over 4881.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3144, pruned_loss=0.06773, over 966574.25 frames.], batch size: 12, lr: 6.28e-04
2022-05-28 20:25:09,651 INFO [train.py:761] (5/8) Epoch 19, batch 2500, loss[loss=0.1933, simple_loss=0.302, pruned_loss=0.04228, over 4855.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3147, pruned_loss=0.06831, over 967159.07 frames.], batch size: 14, lr: 6.28e-04
2022-05-28 20:25:47,491 INFO [train.py:761] (5/8) Epoch 19, batch 2550, loss[loss=0.212, simple_loss=0.2993, pruned_loss=0.06236, over 4948.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3141, pruned_loss=0.06815, over 967699.75 frames.], batch size: 16, lr: 6.28e-04
2022-05-28 20:26:25,923 INFO [train.py:761] (5/8) Epoch 19, batch 2600, loss[loss=0.2113, simple_loss=0.2937, pruned_loss=0.06438, over 4963.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3151, pruned_loss=0.06789, over 967041.75 frames.], batch size: 12, lr: 6.27e-04
2022-05-28 20:27:03,257 INFO [train.py:761] (5/8) Epoch 19, batch 2650, loss[loss=0.2183, simple_loss=0.3211, pruned_loss=0.05777, over 4717.00 frames.], tot_loss[loss=0.2257, simple_loss=0.316, pruned_loss=0.06771, over 966529.61 frames.], batch size: 14, lr: 6.27e-04
2022-05-28 20:27:41,724 INFO [train.py:761] (5/8) Epoch 19, batch 2700, loss[loss=0.243, simple_loss=0.3147, pruned_loss=0.08559, over 4734.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3167, pruned_loss=0.06848, over 967922.27 frames.], batch size: 12, lr: 6.27e-04
2022-05-28 20:28:19,286 INFO [train.py:761] (5/8) Epoch 19, batch 2750, loss[loss=0.2262, simple_loss=0.3175, pruned_loss=0.06746, over 4849.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3174, pruned_loss=0.06946, over 966695.90 frames.], batch size: 14, lr: 6.27e-04
2022-05-28 20:28:57,437 INFO [train.py:761] (5/8) Epoch 19, batch 2800, loss[loss=0.26, simple_loss=0.3447, pruned_loss=0.08765, over 4975.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3175, pruned_loss=0.06937, over 967257.01 frames.], batch size: 15, lr: 6.27e-04
2022-05-28 20:29:35,028 INFO [train.py:761] (5/8) Epoch 19, batch 2850, loss[loss=0.2732, simple_loss=0.3544, pruned_loss=0.09595, over 4860.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3169, pruned_loss=0.0696, over 966835.54 frames.], batch size: 26, lr: 6.27e-04
2022-05-28 20:30:13,416 INFO [train.py:761] (5/8) Epoch 19, batch 2900, loss[loss=0.1785, simple_loss=0.2746, pruned_loss=0.04122, over 4887.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3166, pruned_loss=0.06926, over 967855.16 frames.], batch size: 12, lr: 6.27e-04
2022-05-28 20:30:51,543 INFO [train.py:761] (5/8) Epoch 19, batch 2950, loss[loss=0.1933, simple_loss=0.2688, pruned_loss=0.05891, over 4817.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3162, pruned_loss=0.06929, over 966758.53 frames.], batch size: 11, lr: 6.27e-04
2022-05-28 20:31:29,280 INFO [train.py:761] (5/8) Epoch 19, batch 3000, loss[loss=0.2178, simple_loss=0.3021, pruned_loss=0.06678, over 4792.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3128, pruned_loss=0.06769, over 966584.55 frames.], batch size: 13, lr: 6.26e-04
2022-05-28 20:31:29,280 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 20:31:39,467 INFO [train.py:790] (5/8) Epoch 19, validation: loss=0.2107, simple_loss=0.3123, pruned_loss=0.05461, over 944034.00 frames.
2022-05-28 20:32:17,765 INFO [train.py:761] (5/8) Epoch 19, batch 3050, loss[loss=0.2028, simple_loss=0.3002, pruned_loss=0.05266, over 4985.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3152, pruned_loss=0.06916, over 966749.96 frames.], batch size: 13, lr: 6.26e-04
2022-05-28 20:32:55,883 INFO [train.py:761] (5/8) Epoch 19, batch 3100, loss[loss=0.2058, simple_loss=0.2946, pruned_loss=0.0585, over 4670.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3149, pruned_loss=0.06941, over 965899.52 frames.], batch size: 12, lr: 6.26e-04
2022-05-28 20:33:33,712 INFO [train.py:761] (5/8) Epoch 19, batch 3150, loss[loss=0.2246, simple_loss=0.3193, pruned_loss=0.06496, over 4921.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3155, pruned_loss=0.07064, over 966278.74 frames.], batch size: 14, lr: 6.26e-04
2022-05-28 20:34:11,777 INFO [train.py:761] (5/8) Epoch 19, batch 3200, loss[loss=0.2341, simple_loss=0.3186, pruned_loss=0.07477, over 4667.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3181, pruned_loss=0.07313, over 966156.51 frames.], batch size: 13, lr: 6.26e-04
2022-05-28 20:34:49,325 INFO [train.py:761] (5/8) Epoch 19, batch 3250, loss[loss=0.223, simple_loss=0.3012, pruned_loss=0.07243, over 4800.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3187, pruned_loss=0.07446, over 966194.85 frames.], batch size: 12, lr: 6.26e-04
2022-05-28 20:35:27,441 INFO [train.py:761] (5/8) Epoch 19, batch 3300, loss[loss=0.2004, simple_loss=0.2975, pruned_loss=0.05166, over 4827.00 frames.], tot_loss[loss=0.2382, simple_loss=0.3217, pruned_loss=0.07737, over 967790.95 frames.], batch size: 20, lr: 6.26e-04
2022-05-28 20:36:05,166 INFO [train.py:761] (5/8) Epoch 19, batch 3350, loss[loss=0.2827, simple_loss=0.3508, pruned_loss=0.1073, over 4981.00 frames.], tot_loss[loss=0.2409, simple_loss=0.3232, pruned_loss=0.07925, over 966540.77 frames.], batch size: 26, lr: 6.26e-04
2022-05-28 20:36:42,915 INFO [train.py:761] (5/8) Epoch 19, batch 3400, loss[loss=0.2999, simple_loss=0.3571, pruned_loss=0.1214, over 4763.00 frames.], tot_loss[loss=0.2433, simple_loss=0.324, pruned_loss=0.08124, over 966223.07 frames.], batch size: 20, lr: 6.25e-04
2022-05-28 20:37:20,909 INFO [train.py:761] (5/8) Epoch 19, batch 3450, loss[loss=0.2836, simple_loss=0.3495, pruned_loss=0.1089, over 4989.00 frames.], tot_loss[loss=0.2458, simple_loss=0.325, pruned_loss=0.08328, over 965706.15 frames.], batch size: 13, lr: 6.25e-04
2022-05-28 20:37:59,110 INFO [train.py:761] (5/8) Epoch 19, batch 3500, loss[loss=0.1837, simple_loss=0.2791, pruned_loss=0.0441, over 4784.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3249, pruned_loss=0.08386, over 964943.57 frames.], batch size: 16, lr: 6.25e-04
2022-05-28 20:38:37,584 INFO [train.py:761] (5/8) Epoch 19, batch 3550, loss[loss=0.2356, simple_loss=0.2968, pruned_loss=0.08718, over 4749.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3259, pruned_loss=0.08464, over 966063.58 frames.], batch size: 11, lr: 6.25e-04
2022-05-28 20:39:16,348 INFO [train.py:761] (5/8) Epoch 19, batch 3600, loss[loss=0.2642, simple_loss=0.3298, pruned_loss=0.09932, over 4987.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3257, pruned_loss=0.08499, over 965759.03 frames.], batch size: 13, lr: 6.25e-04
2022-05-28 20:39:54,450 INFO [train.py:761] (5/8) Epoch 19, batch 3650, loss[loss=0.2552, simple_loss=0.3364, pruned_loss=0.08698, over 4970.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3263, pruned_loss=0.08577, over 966870.96 frames.], batch size: 15, lr: 6.25e-04
2022-05-28 20:40:33,065 INFO [train.py:761] (5/8) Epoch 19, batch 3700, loss[loss=0.2634, simple_loss=0.3414, pruned_loss=0.09265, over 4776.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3264, pruned_loss=0.08535, over 967123.40 frames.], batch size: 16, lr: 6.25e-04
2022-05-28 20:41:11,418 INFO [train.py:761] (5/8) Epoch 19, batch 3750, loss[loss=0.2578, simple_loss=0.3312, pruned_loss=0.09217, over 4855.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3261, pruned_loss=0.08606, over 965745.71 frames.], batch size: 13, lr: 6.25e-04
2022-05-28 20:41:49,541 INFO [train.py:761] (5/8) Epoch 19, batch 3800, loss[loss=0.2372, simple_loss=0.3216, pruned_loss=0.07638, over 4671.00 frames.], tot_loss[loss=0.251, simple_loss=0.3276, pruned_loss=0.08722, over 965604.78 frames.], batch size: 13, lr: 6.24e-04
2022-05-28 20:42:27,542 INFO [train.py:761] (5/8) Epoch 19, batch 3850, loss[loss=0.2053, simple_loss=0.2952, pruned_loss=0.05771, over 4781.00 frames.], tot_loss[loss=0.25, simple_loss=0.3264, pruned_loss=0.08686, over 964623.30 frames.], batch size: 13, lr: 6.24e-04
2022-05-28 20:43:05,686 INFO [train.py:761] (5/8) Epoch 19, batch 3900, loss[loss=0.2389, simple_loss=0.3138, pruned_loss=0.08198, over 4984.00 frames.], tot_loss[loss=0.2511, simple_loss=0.3267, pruned_loss=0.08777, over 965299.63 frames.], batch size: 15, lr: 6.24e-04
2022-05-28 20:43:43,730 INFO [train.py:761] (5/8) Epoch 19, batch 3950, loss[loss=0.2658, simple_loss=0.3301, pruned_loss=0.1007, over 4837.00 frames.], tot_loss[loss=0.2517, simple_loss=0.3271, pruned_loss=0.08808, over 964864.60 frames.], batch size: 18, lr: 6.24e-04
2022-05-28 20:44:21,703 INFO [train.py:761] (5/8) Epoch 19, batch 4000, loss[loss=0.223, simple_loss=0.3135, pruned_loss=0.06623, over 4675.00 frames.], tot_loss[loss=0.252, simple_loss=0.3274, pruned_loss=0.08835, over 964453.51 frames.], batch size: 13, lr: 6.24e-04
2022-05-28 20:44:59,211 INFO [train.py:761] (5/8) Epoch 19, batch 4050, loss[loss=0.2394, simple_loss=0.3254, pruned_loss=0.07672, over 4672.00 frames.], tot_loss[loss=0.2534, simple_loss=0.3287, pruned_loss=0.08903, over 964960.46 frames.], batch size: 13, lr: 6.24e-04
2022-05-28 20:45:37,467 INFO [train.py:761] (5/8) Epoch 19, batch 4100, loss[loss=0.2052, simple_loss=0.2849, pruned_loss=0.0628, over 4729.00 frames.], tot_loss[loss=0.2543, simple_loss=0.3295, pruned_loss=0.08955, over 965727.86 frames.], batch size: 13, lr: 6.24e-04
2022-05-28 20:46:15,628 INFO [train.py:761] (5/8) Epoch 19, batch 4150, loss[loss=0.2528, simple_loss=0.3404, pruned_loss=0.08258, over 4965.00 frames.], tot_loss[loss=0.2534, simple_loss=0.3288, pruned_loss=0.08904, over 965605.74 frames.], batch size: 12, lr: 6.24e-04
2022-05-28 20:46:54,047 INFO [train.py:761] (5/8) Epoch 19, batch 4200, loss[loss=0.2587, simple_loss=0.3152, pruned_loss=0.1011, over 4736.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3272, pruned_loss=0.08826, over 966267.94 frames.], batch size: 11, lr: 6.23e-04
2022-05-28 20:47:32,012 INFO [train.py:761] (5/8) Epoch 19, batch 4250, loss[loss=0.24, simple_loss=0.323, pruned_loss=0.07848, over 4666.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3265, pruned_loss=0.08746, over 964948.61 frames.], batch size: 13, lr: 6.23e-04
2022-05-28 20:48:10,000 INFO [train.py:761] (5/8) Epoch 19, batch 4300, loss[loss=0.2399, simple_loss=0.324, pruned_loss=0.07791, over 4778.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3258, pruned_loss=0.08704, over 965648.94 frames.], batch size: 20, lr: 6.23e-04
2022-05-28 20:48:48,429 INFO [train.py:761] (5/8) Epoch 19, batch 4350, loss[loss=0.2196, simple_loss=0.2969, pruned_loss=0.07118, over 4808.00 frames.], tot_loss[loss=0.2479, simple_loss=0.3237, pruned_loss=0.08598, over 965499.71 frames.], batch size: 12, lr: 6.23e-04
2022-05-28 20:49:26,218 INFO [train.py:761] (5/8) Epoch 19, batch 4400, loss[loss=0.2666, simple_loss=0.3205, pruned_loss=0.1063, over 4992.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3232, pruned_loss=0.08525, over 965007.66 frames.], batch size: 13, lr: 6.23e-04
2022-05-28 20:50:04,149 INFO [train.py:761] (5/8) Epoch 19, batch 4450, loss[loss=0.3003, simple_loss=0.3586, pruned_loss=0.121, over 4887.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3225, pruned_loss=0.08489, over 964597.34 frames.], batch size: 26, lr: 6.23e-04
2022-05-28 20:50:42,061 INFO [train.py:761] (5/8) Epoch 19, batch 4500, loss[loss=0.258, simple_loss=0.3534, pruned_loss=0.08132, over 4729.00 frames.], tot_loss[loss=0.2464, simple_loss=0.3231, pruned_loss=0.08488, over 964200.63 frames.], batch size: 14, lr: 6.23e-04
2022-05-28 20:51:20,406 INFO [train.py:761] (5/8) Epoch 19, batch 4550, loss[loss=0.2466, simple_loss=0.3217, pruned_loss=0.08572, over 4920.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3222, pruned_loss=0.08445, over 964874.03 frames.], batch size: 13, lr: 6.23e-04
2022-05-28 20:51:59,091 INFO [train.py:761] (5/8) Epoch 19, batch 4600, loss[loss=0.2325, simple_loss=0.2973, pruned_loss=0.08385, over 4892.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3232, pruned_loss=0.08521, over 964666.73 frames.], batch size: 12, lr: 6.22e-04
2022-05-28 20:52:37,473 INFO [train.py:761] (5/8) Epoch 19, batch 4650, loss[loss=0.2582, simple_loss=0.3349, pruned_loss=0.09074, over 4792.00 frames.], tot_loss[loss=0.2458, simple_loss=0.3217, pruned_loss=0.08491, over 966082.22 frames.], batch size: 15, lr: 6.22e-04
2022-05-28 20:53:16,294 INFO [train.py:761] (5/8) Epoch 19, batch 4700, loss[loss=0.2084, simple_loss=0.2898, pruned_loss=0.06348, over 4668.00 frames.], tot_loss[loss=0.2458, simple_loss=0.3216, pruned_loss=0.08501, over 967751.52 frames.], batch size: 12, lr: 6.22e-04
2022-05-28 20:53:54,380 INFO [train.py:761] (5/8) Epoch 19, batch 4750, loss[loss=0.2028, simple_loss=0.2923, pruned_loss=0.05664, over 4831.00 frames.], tot_loss[loss=0.2465, simple_loss=0.3224, pruned_loss=0.08529, over 966598.20 frames.], batch size: 11, lr: 6.22e-04
2022-05-28 20:54:32,806 INFO [train.py:761] (5/8) Epoch 19, batch 4800, loss[loss=0.2224, simple_loss=0.2872, pruned_loss=0.07875, over 4633.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3218, pruned_loss=0.08519, over 966192.90 frames.], batch size: 11, lr: 6.22e-04
2022-05-28 20:55:10,788 INFO [train.py:761] (5/8) Epoch 19, batch 4850, loss[loss=0.2041, simple_loss=0.2716, pruned_loss=0.06827, over 4655.00 frames.], tot_loss[loss=0.2458, simple_loss=0.3217, pruned_loss=0.08498, over 965389.54 frames.], batch size: 11, lr: 6.22e-04
2022-05-28 20:55:49,007 INFO [train.py:761] (5/8) Epoch 19, batch 4900, loss[loss=0.2115, simple_loss=0.2886, pruned_loss=0.06716, over 4978.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3212, pruned_loss=0.0846, over 966115.70 frames.], batch size: 12, lr: 6.22e-04
2022-05-28 20:56:27,371 INFO [train.py:761] (5/8) Epoch 19, batch 4950, loss[loss=0.2329, simple_loss=0.3127, pruned_loss=0.07657, over 4717.00 frames.], tot_loss[loss=0.244, simple_loss=0.3205, pruned_loss=0.08375, over 966032.04 frames.], batch size: 13, lr: 6.22e-04
2022-05-28 20:57:05,873 INFO [train.py:761] (5/8) Epoch 19, batch 5000, loss[loss=0.2353, simple_loss=0.3022, pruned_loss=0.08423, over 4729.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3213, pruned_loss=0.08426, over 965813.23 frames.], batch size: 11, lr: 6.21e-04
2022-05-28 20:57:43,515 INFO [train.py:761] (5/8) Epoch 19, batch 5050, loss[loss=0.2127, simple_loss=0.2969, pruned_loss=0.06425, over 4975.00 frames.], tot_loss[loss=0.2465, simple_loss=0.3224, pruned_loss=0.08533, over 966645.46 frames.], batch size: 15, lr: 6.21e-04
2022-05-28 20:58:21,998 INFO [train.py:761] (5/8) Epoch 19, batch 5100, loss[loss=0.276, simple_loss=0.3458, pruned_loss=0.1031, over 4665.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3246, pruned_loss=0.08658, over 966018.15 frames.], batch size: 13, lr: 6.21e-04
2022-05-28 20:59:00,014 INFO [train.py:761] (5/8) Epoch 19, batch 5150, loss[loss=0.189, simple_loss=0.2778, pruned_loss=0.05007, over 4801.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3254, pruned_loss=0.08708, over 967197.98 frames.], batch size: 12, lr: 6.21e-04
2022-05-28 20:59:38,413 INFO [train.py:761] (5/8) Epoch 19, batch 5200, loss[loss=0.2171, simple_loss=0.2998, pruned_loss=0.0672, over 4663.00 frames.], tot_loss[loss=0.2497, simple_loss=0.325, pruned_loss=0.08714, over 966062.72 frames.], batch size: 12, lr: 6.21e-04
2022-05-28 21:00:17,325 INFO [train.py:761] (5/8) Epoch 19, batch 5250, loss[loss=0.2699, simple_loss=0.35, pruned_loss=0.09493, over 4791.00 frames.], tot_loss[loss=0.2483, simple_loss=0.324, pruned_loss=0.08636, over 966094.23 frames.], batch size: 20, lr: 6.21e-04
2022-05-28 21:00:55,817 INFO [train.py:761] (5/8) Epoch 19, batch 5300, loss[loss=0.2284, simple_loss=0.3101, pruned_loss=0.07335, over 4770.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3241, pruned_loss=0.08579, over 966686.49 frames.], batch size: 15, lr: 6.21e-04
2022-05-28 21:01:34,036 INFO [train.py:761] (5/8) Epoch 19, batch 5350, loss[loss=0.2172, simple_loss=0.3256, pruned_loss=0.05439, over 4732.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3231, pruned_loss=0.08465, over 966629.10 frames.], batch size: 14, lr: 6.21e-04
2022-05-28 21:02:11,923 INFO [train.py:761] (5/8) Epoch 19, batch 5400, loss[loss=0.2478, simple_loss=0.3295, pruned_loss=0.08303, over 4858.00 frames.], tot_loss[loss=0.2458, simple_loss=0.3225, pruned_loss=0.08449, over 966249.78 frames.], batch size: 14, lr: 6.20e-04
2022-05-28 21:02:50,148 INFO [train.py:761] (5/8) Epoch 19, batch 5450, loss[loss=0.2494, simple_loss=0.3283, pruned_loss=0.08518, over 4775.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3222, pruned_loss=0.08442, over 965242.51 frames.], batch size: 20, lr: 6.20e-04
2022-05-28 21:03:28,723 INFO [train.py:761] (5/8) Epoch 19, batch 5500, loss[loss=0.2399, simple_loss=0.3063, pruned_loss=0.08674, over 4974.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3227, pruned_loss=0.08491, over 966307.51 frames.], batch size: 13, lr: 6.20e-04
2022-05-28 21:04:06,694 INFO [train.py:761] (5/8) Epoch 19, batch 5550, loss[loss=0.2902, simple_loss=0.3506, pruned_loss=0.1149, over 4714.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3228, pruned_loss=0.08572, over 967153.44 frames.], batch size: 14, lr: 6.20e-04
2022-05-28 21:04:45,414 INFO [train.py:761] (5/8) Epoch 19, batch 5600, loss[loss=0.2102, simple_loss=0.2737, pruned_loss=0.07337, over 4645.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3241, pruned_loss=0.08626, over 966362.88 frames.], batch size: 11, lr: 6.20e-04
2022-05-28 21:05:23,508 INFO [train.py:761] (5/8) Epoch 19, batch 5650, loss[loss=0.2053, simple_loss=0.2793, pruned_loss=0.06563, over 4843.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3241, pruned_loss=0.08624, over 966470.59 frames.], batch size: 11, lr: 6.20e-04
2022-05-28 21:06:01,873 INFO [train.py:761] (5/8) Epoch 19, batch 5700, loss[loss=0.2349, simple_loss=0.3146, pruned_loss=0.07762, over 4881.00 frames.], tot_loss[loss=0.2464, simple_loss=0.3227, pruned_loss=0.08505, over 966012.16 frames.], batch size: 15, lr: 6.20e-04
2022-05-28 21:06:40,303 INFO [train.py:761] (5/8) Epoch 19, batch 5750, loss[loss=0.228, simple_loss=0.2836, pruned_loss=0.08622, over 4591.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3234, pruned_loss=0.08604, over 965565.13 frames.], batch size: 10, lr: 6.20e-04
2022-05-28 21:07:18,615 INFO [train.py:761] (5/8) Epoch 19, batch 5800, loss[loss=0.2276, simple_loss=0.304, pruned_loss=0.07558, over 4967.00 frames.], tot_loss[loss=0.2486, simple_loss=0.3239, pruned_loss=0.08661, over 965043.83 frames.], batch size: 16, lr: 6.20e-04
2022-05-28 21:07:57,320 INFO [train.py:761] (5/8) Epoch 19, batch 5850, loss[loss=0.2396, simple_loss=0.3147, pruned_loss=0.08227, over 4727.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3224, pruned_loss=0.08585, over 965456.09 frames.], batch size: 13, lr: 6.19e-04
2022-05-28 21:08:35,595 INFO [train.py:761] (5/8) Epoch 19, batch 5900, loss[loss=0.2509, simple_loss=0.3277, pruned_loss=0.08706, over 4799.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3252, pruned_loss=0.08714, over 965987.29 frames.], batch size: 16, lr: 6.19e-04
2022-05-28 21:09:14,179 INFO [train.py:761] (5/8) Epoch 19, batch 5950, loss[loss=0.2349, simple_loss=0.3299, pruned_loss=0.07, over 4975.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3248, pruned_loss=0.08647, over 967393.71 frames.], batch size: 15, lr: 6.19e-04
2022-05-28 21:09:52,484 INFO [train.py:761] (5/8) Epoch 19, batch 6000, loss[loss=0.2136, simple_loss=0.2801, pruned_loss=0.07352, over 4755.00 frames.], tot_loss[loss=0.2494, simple_loss=0.3253, pruned_loss=0.08676, over 967048.39 frames.], batch size: 11, lr: 6.19e-04
2022-05-28 21:09:52,484 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 21:10:02,318 INFO [train.py:790] (5/8) Epoch 19, validation: loss=0.2025, simple_loss=0.3085, pruned_loss=0.04825, over 944034.00 frames.
2022-05-28 21:10:40,132 INFO [train.py:761] (5/8) Epoch 19, batch 6050, loss[loss=0.2357, simple_loss=0.3222, pruned_loss=0.07461, over 4795.00 frames.], tot_loss[loss=0.2479, simple_loss=0.3241, pruned_loss=0.08592, over 967142.47 frames.], batch size: 14, lr: 6.19e-04
2022-05-28 21:11:19,106 INFO [train.py:761] (5/8) Epoch 19, batch 6100, loss[loss=0.2426, simple_loss=0.3264, pruned_loss=0.07937, over 4732.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3251, pruned_loss=0.08652, over 967471.13 frames.], batch size: 13, lr: 6.19e-04
2022-05-28 21:11:57,216 INFO [train.py:761] (5/8) Epoch 19, batch 6150, loss[loss=0.2848, simple_loss=0.3569, pruned_loss=0.1064, over 4772.00 frames.], tot_loss[loss=0.2501, simple_loss=0.3264, pruned_loss=0.08695, over 967874.72 frames.], batch size: 15, lr: 6.19e-04
2022-05-28 21:12:35,811 INFO [train.py:761] (5/8) Epoch 19, batch 6200, loss[loss=0.262, simple_loss=0.3282, pruned_loss=0.09786, over 4792.00 frames.], tot_loss[loss=0.2494, simple_loss=0.3254, pruned_loss=0.08675, over 968050.90 frames.], batch size: 13, lr: 6.19e-04
2022-05-28 21:13:13,645 INFO [train.py:761] (5/8) Epoch 19, batch 6250, loss[loss=0.2478, simple_loss=0.329, pruned_loss=0.08333, over 4802.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3248, pruned_loss=0.08592, over 967638.01 frames.], batch size: 12, lr: 6.18e-04
2022-05-28 21:13:52,295 INFO [train.py:761] (5/8) Epoch 19, batch 6300, loss[loss=0.2469, simple_loss=0.3118, pruned_loss=0.09101, over 4857.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3247, pruned_loss=0.08619, over 968332.64 frames.], batch size: 13, lr: 6.18e-04
2022-05-28 21:14:30,759 INFO [train.py:761] (5/8) Epoch 19, batch 6350, loss[loss=0.2766, simple_loss=0.3579, pruned_loss=0.09766, over 4911.00 frames.], tot_loss[loss=0.2494, simple_loss=0.3259, pruned_loss=0.08645, over 967665.69 frames.], batch size: 14, lr: 6.18e-04
2022-05-28 21:15:09,100 INFO [train.py:761] (5/8) Epoch 19, batch 6400, loss[loss=0.2427, simple_loss=0.3196, pruned_loss=0.08286, over 4813.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3243, pruned_loss=0.08522, over 967674.32 frames.], batch size: 26, lr: 6.18e-04
2022-05-28 21:15:47,784 INFO [train.py:761] (5/8) Epoch 19, batch 6450, loss[loss=0.2904, simple_loss=0.3684, pruned_loss=0.1062, over 4940.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3243, pruned_loss=0.08529, over 967552.07 frames.], batch size: 48, lr: 6.18e-04
2022-05-28 21:16:26,323 INFO [train.py:761] (5/8) Epoch 19, batch 6500, loss[loss=0.2488, simple_loss=0.306, pruned_loss=0.0958, over 4827.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3242, pruned_loss=0.08573, over 967278.17 frames.], batch size: 11, lr: 6.18e-04
2022-05-28 21:17:04,096 INFO [train.py:761] (5/8) Epoch 19, batch 6550, loss[loss=0.2275, simple_loss=0.3103, pruned_loss=0.0723, over 4965.00 frames.], tot_loss[loss=0.2472, simple_loss=0.3242, pruned_loss=0.08512, over 967432.01 frames.], batch size: 15, lr: 6.18e-04
2022-05-28 21:17:46,103 INFO [train.py:761] (5/8) Epoch 19, batch 6600, loss[loss=0.235, simple_loss=0.313, pruned_loss=0.0785, over 4994.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3242, pruned_loss=0.08498, over 967607.89 frames.], batch size: 13, lr: 6.18e-04
2022-05-28 21:18:24,364 INFO [train.py:761] (5/8) Epoch 19, batch 6650, loss[loss=0.3021, simple_loss=0.369, pruned_loss=0.1176, over 4968.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3237, pruned_loss=0.08444, over 968122.67 frames.], batch size: 45, lr: 6.17e-04
2022-05-28 21:19:02,836 INFO [train.py:761] (5/8) Epoch 19, batch 6700, loss[loss=0.2553, simple_loss=0.3274, pruned_loss=0.09156, over 4796.00 frames.], tot_loss[loss=0.247, simple_loss=0.3245, pruned_loss=0.08473, over 967896.83 frames.], batch size: 12, lr: 6.17e-04
2022-05-28 21:19:57,489 INFO [train.py:761] (5/8) Epoch 20, batch 0, loss[loss=0.2263, simple_loss=0.3203, pruned_loss=0.06613, over 4863.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3203, pruned_loss=0.06613, over 4863.00 frames.], batch size: 18, lr: 6.17e-04
2022-05-28 21:20:35,045 INFO [train.py:761] (5/8) Epoch 20, batch 50, loss[loss=0.2586, simple_loss=0.3558, pruned_loss=0.08073, over 4878.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3121, pruned_loss=0.06825, over 219163.78 frames.], batch size: 15, lr: 6.17e-04
2022-05-28 21:21:13,148 INFO [train.py:761] (5/8) Epoch 20, batch 100, loss[loss=0.2448, simple_loss=0.3336, pruned_loss=0.07803, over 4973.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3098, pruned_loss=0.06721, over 384366.19 frames.], batch size: 15, lr: 6.17e-04
2022-05-28 21:21:51,224 INFO [train.py:761] (5/8) Epoch 20, batch 150, loss[loss=0.1805, simple_loss=0.2746, pruned_loss=0.04315, over 4921.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3106, pruned_loss=0.06698, over 514291.99 frames.], batch size: 13, lr: 6.17e-04
2022-05-28 21:22:29,032 INFO [train.py:761] (5/8) Epoch 20, batch 200, loss[loss=0.1824, simple_loss=0.2838, pruned_loss=0.04048, over 4727.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3141, pruned_loss=0.06852, over 614793.19 frames.], batch size: 12, lr: 6.17e-04
2022-05-28 21:23:07,009 INFO [train.py:761] (5/8) Epoch 20, batch 250, loss[loss=0.2152, simple_loss=0.2808, pruned_loss=0.07483, over 4838.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3135, pruned_loss=0.06782, over 693228.08 frames.], batch size: 11, lr: 6.17e-04
2022-05-28 21:23:44,820 INFO [train.py:761] (5/8) Epoch 20, batch 300, loss[loss=0.2034, simple_loss=0.2922, pruned_loss=0.05733, over 4565.00 frames.], tot_loss[loss=0.223, simple_loss=0.312, pruned_loss=0.06699, over 752918.60 frames.], batch size: 10, lr: 6.17e-04
2022-05-28 21:24:22,480 INFO [train.py:761] (5/8) Epoch 20, batch 350, loss[loss=0.1801, simple_loss=0.2641, pruned_loss=0.0481, over 4734.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3121, pruned_loss=0.06619, over 799973.03 frames.], batch size: 11, lr: 6.16e-04
2022-05-28 21:25:00,073 INFO [train.py:761] (5/8) Epoch 20, batch 400, loss[loss=0.1983, simple_loss=0.3043, pruned_loss=0.04611, over 4869.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3107, pruned_loss=0.06594, over 836120.47 frames.], batch size: 17, lr: 6.16e-04
2022-05-28 21:25:37,828 INFO [train.py:761] (5/8) Epoch 20, batch 450, loss[loss=0.1556, simple_loss=0.2484, pruned_loss=0.03144, over 4667.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3105, pruned_loss=0.06539, over 865045.01 frames.], batch size: 12, lr: 6.16e-04
2022-05-28 21:26:15,908 INFO [train.py:761] (5/8) Epoch 20, batch 500, loss[loss=0.2162, simple_loss=0.2932, pruned_loss=0.0696, over 4735.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3113, pruned_loss=0.06594, over 888222.24 frames.], batch size: 12, lr: 6.16e-04
2022-05-28 21:26:54,455 INFO [train.py:761] (5/8) Epoch 20, batch 550, loss[loss=0.2499, simple_loss=0.3399, pruned_loss=0.07993, over 4783.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3098, pruned_loss=0.06543, over 906623.40 frames.], batch size: 14, lr: 6.16e-04
2022-05-28 21:27:32,410 INFO [train.py:761] (5/8) Epoch 20, batch 600, loss[loss=0.1765, simple_loss=0.2638, pruned_loss=0.0446, over 4969.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3091, pruned_loss=0.06514, over 919787.82 frames.], batch size: 12, lr: 6.16e-04
2022-05-28 21:28:10,665 INFO [train.py:761] (5/8) Epoch 20, batch 650, loss[loss=0.2148, simple_loss=0.2925, pruned_loss=0.06855, over 4643.00 frames.], tot_loss[loss=0.2208, simple_loss=0.31, pruned_loss=0.06579, over 929256.63 frames.], batch size: 11, lr: 6.16e-04
2022-05-28 21:28:48,884 INFO [train.py:761] (5/8) Epoch 20, batch 700, loss[loss=0.2127, simple_loss=0.3023, pruned_loss=0.06158, over 4970.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3124, pruned_loss=0.06699, over 938801.44 frames.], batch size: 12, lr: 6.16e-04
2022-05-28 21:29:27,067 INFO [train.py:761] (5/8) Epoch 20, batch 750, loss[loss=0.2293, simple_loss=0.327, pruned_loss=0.06585, over 4963.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3126, pruned_loss=0.06707, over 944831.62 frames.], batch size: 15, lr: 6.15e-04
2022-05-28 21:30:04,690 INFO [train.py:761] (5/8) Epoch 20, batch 800, loss[loss=0.198, simple_loss=0.2927, pruned_loss=0.05164, over 4856.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3149, pruned_loss=0.06863, over 950388.50 frames.], batch size: 13, lr: 6.15e-04
2022-05-28 21:30:42,518 INFO [train.py:761] (5/8) Epoch 20, batch 850, loss[loss=0.2368, simple_loss=0.3165, pruned_loss=0.07852, over 4717.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3152, pruned_loss=0.06908, over 952632.28 frames.], batch size: 14, lr: 6.15e-04
2022-05-28 21:31:20,147 INFO [train.py:761] (5/8) Epoch 20, batch 900, loss[loss=0.1936, simple_loss=0.272, pruned_loss=0.0576, over 4975.00 frames.], tot_loss[loss=0.2271, simple_loss=0.3151, pruned_loss=0.06955, over 956724.90 frames.], batch size: 11, lr: 6.15e-04
2022-05-28 21:31:57,722 INFO [train.py:761] (5/8) Epoch 20, batch 950, loss[loss=0.1783, simple_loss=0.2686, pruned_loss=0.04403, over 4976.00 frames.], tot_loss[loss=0.2271, simple_loss=0.3148, pruned_loss=0.06968, over 959226.68 frames.], batch size: 15, lr: 6.15e-04
2022-05-28 21:32:35,529 INFO [train.py:761] (5/8) Epoch 20, batch 1000, loss[loss=0.2353, simple_loss=0.3183, pruned_loss=0.07617, over 4971.00 frames.], tot_loss[loss=0.2271, simple_loss=0.3147, pruned_loss=0.06971, over 959817.90 frames.], batch size: 16, lr: 6.15e-04
2022-05-28 21:33:13,605 INFO [train.py:761] (5/8) Epoch 20, batch 1050, loss[loss=0.2848, simple_loss=0.3703, pruned_loss=0.09968, over 4777.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3151, pruned_loss=0.06974, over 960220.88 frames.], batch size: 14, lr: 6.15e-04
2022-05-28 21:33:51,182 INFO [train.py:761] (5/8) Epoch 20, batch 1100, loss[loss=0.2766, simple_loss=0.3558, pruned_loss=0.09872, over 4781.00 frames.], tot_loss[loss=0.228, simple_loss=0.3162, pruned_loss=0.06988, over 961168.72 frames.], batch size: 13, lr: 6.15e-04
2022-05-28 21:34:29,645 INFO [train.py:761] (5/8) Epoch 20, batch 1150, loss[loss=0.2337, simple_loss=0.3393, pruned_loss=0.06404, over 4720.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3153, pruned_loss=0.06904, over 962039.13 frames.], batch size: 14, lr: 6.14e-04
2022-05-28 21:35:07,748 INFO [train.py:761] (5/8) Epoch 20, batch 1200, loss[loss=0.2185, simple_loss=0.3185, pruned_loss=0.05925, over 4786.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3153, pruned_loss=0.06923, over 963103.10 frames.], batch size: 16, lr: 6.14e-04
2022-05-28 21:35:46,348 INFO [train.py:761] (5/8) Epoch 20, batch 1250, loss[loss=0.2202, simple_loss=0.306, pruned_loss=0.06717, over 4830.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3158, pruned_loss=0.06931, over 964285.51 frames.], batch size: 18, lr: 6.14e-04
2022-05-28 21:36:24,013 INFO [train.py:761] (5/8) Epoch 20, batch 1300, loss[loss=0.2511, simple_loss=0.339, pruned_loss=0.0816, over 4783.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3155, pruned_loss=0.06887, over 964424.35 frames.], batch size: 15, lr: 6.14e-04
2022-05-28 21:37:02,764 INFO [train.py:761] (5/8) Epoch 20, batch 1350, loss[loss=0.2396, simple_loss=0.337, pruned_loss=0.07105, over 4753.00 frames.], tot_loss[loss=0.2267, simple_loss=0.316, pruned_loss=0.06869, over 965442.55 frames.], batch size: 15, lr: 6.14e-04
2022-05-28 21:37:40,893 INFO [train.py:761] (5/8) Epoch 20, batch 1400, loss[loss=0.2242, simple_loss=0.3217, pruned_loss=0.06333, over 4953.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3128, pruned_loss=0.06749, over 965556.95 frames.], batch size: 16, lr: 6.14e-04
2022-05-28 21:38:18,817 INFO [train.py:761] (5/8) Epoch 20, batch 1450, loss[loss=0.2058, simple_loss=0.2884, pruned_loss=0.06157, over 4984.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3125, pruned_loss=0.06731, over 965826.15 frames.], batch size: 12, lr: 6.14e-04
2022-05-28 21:38:56,898 INFO [train.py:761] (5/8) Epoch 20, batch 1500, loss[loss=0.2831, simple_loss=0.3521, pruned_loss=0.1071, over 4823.00 frames.], tot_loss[loss=0.2232, simple_loss=0.312, pruned_loss=0.06716, over 964841.29 frames.], batch size: 25, lr: 6.14e-04
2022-05-28 21:39:34,753 INFO [train.py:761] (5/8) Epoch 20, batch 1550, loss[loss=0.242, simple_loss=0.3401, pruned_loss=0.07192, over 4818.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3114, pruned_loss=0.06705, over 963300.22 frames.], batch size: 18, lr: 6.14e-04
2022-05-28 21:40:12,943 INFO [train.py:761] (5/8) Epoch 20, batch 1600, loss[loss=0.2101, simple_loss=0.3111, pruned_loss=0.05459, over 4734.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3116, pruned_loss=0.06701, over 963723.84 frames.], batch size: 13, lr: 6.13e-04
2022-05-28 21:40:50,747 INFO [train.py:761] (5/8) Epoch 20, batch 1650, loss[loss=0.2205, simple_loss=0.3197, pruned_loss=0.06068, over 4789.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3106, pruned_loss=0.06685, over 963458.22 frames.], batch size: 14, lr: 6.13e-04
2022-05-28 21:41:28,579 INFO [train.py:761] (5/8) Epoch 20, batch 1700, loss[loss=0.2805, simple_loss=0.3513, pruned_loss=0.1049, over 4935.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3118, pruned_loss=0.06726, over 963963.03 frames.], batch size: 27, lr: 6.13e-04
2022-05-28 21:42:06,570 INFO [train.py:761] (5/8) Epoch 20, batch 1750, loss[loss=0.246, simple_loss=0.3266, pruned_loss=0.08273, over 4674.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3131, pruned_loss=0.06774, over 964656.69 frames.], batch size: 13, lr: 6.13e-04
2022-05-28 21:42:44,283 INFO [train.py:761] (5/8) Epoch 20, batch 1800, loss[loss=0.2267, simple_loss=0.3171, pruned_loss=0.0682, over 4778.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3131, pruned_loss=0.06758, over 965421.19 frames.], batch size: 16, lr: 6.13e-04
2022-05-28 21:43:22,658 INFO [train.py:761] (5/8) Epoch 20, batch 1850, loss[loss=0.2543, simple_loss=0.3369, pruned_loss=0.0859, over 4922.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3122, pruned_loss=0.06704, over 965315.75 frames.], batch size: 14, lr: 6.13e-04
2022-05-28 21:44:00,742 INFO [train.py:761] (5/8) Epoch 20, batch 1900, loss[loss=0.2357, simple_loss=0.3366, pruned_loss=0.06737, over 4889.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3133, pruned_loss=0.06793, over 965295.10 frames.], batch size: 17, lr: 6.13e-04
2022-05-28 21:44:38,226 INFO [train.py:761] (5/8) Epoch 20, batch 1950, loss[loss=0.251, simple_loss=0.3336, pruned_loss=0.08416, over 4851.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3132, pruned_loss=0.06677, over 964941.00 frames.], batch size: 13, lr: 6.13e-04
2022-05-28 21:45:15,692 INFO [train.py:761] (5/8) Epoch 20, batch 2000, loss[loss=0.2223, simple_loss=0.304, pruned_loss=0.07029, over 4790.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3149, pruned_loss=0.06763, over 964801.80 frames.], batch size: 14, lr: 6.12e-04
2022-05-28 21:45:53,292 INFO [train.py:761] (5/8) Epoch 20, batch 2050, loss[loss=0.2476, simple_loss=0.3072, pruned_loss=0.09398, over 4971.00 frames.], tot_loss[loss=0.2262, simple_loss=0.316, pruned_loss=0.06818, over 965805.06 frames.], batch size: 12, lr: 6.12e-04
2022-05-28 21:46:31,668 INFO [train.py:761] (5/8) Epoch 20, batch 2100, loss[loss=0.2347, simple_loss=0.3353, pruned_loss=0.06701, over 4874.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3142, pruned_loss=0.0675, over 965982.66 frames.], batch size: 15, lr: 6.12e-04
2022-05-28 21:47:09,817 INFO [train.py:761] (5/8) Epoch 20, batch 2150, loss[loss=0.1932, simple_loss=0.2801, pruned_loss=0.05313, over 4737.00 frames.], tot_loss[loss=0.2247, simple_loss=0.314, pruned_loss=0.06774, over 965924.90 frames.], batch size: 12, lr: 6.12e-04
2022-05-28 21:47:47,732 INFO [train.py:761] (5/8) Epoch 20, batch 2200, loss[loss=0.2123, simple_loss=0.2996, pruned_loss=0.06251, over 4732.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3145, pruned_loss=0.06808, over 965427.84 frames.], batch size: 11, lr: 6.12e-04
2022-05-28 21:48:26,064 INFO [train.py:761] (5/8) Epoch 20, batch 2250, loss[loss=0.1724, simple_loss=0.2528, pruned_loss=0.04605, over 4888.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3138, pruned_loss=0.06727, over 964486.27 frames.], batch size: 12, lr: 6.12e-04
2022-05-28 21:49:04,138 INFO [train.py:761] (5/8) Epoch 20, batch 2300, loss[loss=0.1958, simple_loss=0.2845, pruned_loss=0.05355, over 4847.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3125, pruned_loss=0.06653, over 965848.50 frames.], batch size: 13, lr: 6.12e-04
2022-05-28 21:49:42,139 INFO [train.py:761] (5/8) Epoch 20, batch 2350, loss[loss=0.2216, simple_loss=0.3119, pruned_loss=0.06565, over 4819.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3137, pruned_loss=0.06666, over 966179.76 frames.], batch size: 20, lr: 6.12e-04
2022-05-28 21:50:19,619 INFO [train.py:761] (5/8) Epoch 20, batch 2400, loss[loss=0.2635, simple_loss=0.345, pruned_loss=0.09103, over 4784.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3127, pruned_loss=0.06685, over 967223.03 frames.], batch size: 14, lr: 6.12e-04
2022-05-28 21:50:57,287 INFO [train.py:761] (5/8) Epoch 20, batch 2450, loss[loss=0.2139, simple_loss=0.3078, pruned_loss=0.05999, over 4723.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3138, pruned_loss=0.06765, over 967468.84 frames.], batch size: 12, lr: 6.11e-04
2022-05-28 21:51:35,423 INFO [train.py:761] (5/8) Epoch 20, batch 2500, loss[loss=0.1834, simple_loss=0.2907, pruned_loss=0.03808, over 4847.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3141, pruned_loss=0.06759, over 966754.52 frames.], batch size: 13, lr: 6.11e-04
2022-05-28 21:52:13,804 INFO [train.py:761] (5/8) Epoch 20, batch 2550, loss[loss=0.2352, simple_loss=0.335, pruned_loss=0.06774, over 4868.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3136, pruned_loss=0.06807, over 967110.68 frames.], batch size: 20, lr: 6.11e-04
2022-05-28 21:52:51,980 INFO [train.py:761] (5/8) Epoch 20, batch 2600, loss[loss=0.2277, simple_loss=0.3294, pruned_loss=0.06299, over 4977.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3136, pruned_loss=0.06814, over 967393.35 frames.], batch size: 15, lr: 6.11e-04
2022-05-28 21:53:29,901 INFO [train.py:761] (5/8) Epoch 20, batch 2650, loss[loss=0.1963, simple_loss=0.2802, pruned_loss=0.05623, over 4975.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3145, pruned_loss=0.06842, over 968204.01 frames.], batch size: 11, lr: 6.11e-04
2022-05-28 21:54:08,181 INFO [train.py:761] (5/8) Epoch 20, batch 2700, loss[loss=0.2293, simple_loss=0.3189, pruned_loss=0.06986, over 4983.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3145, pruned_loss=0.0679, over 966161.23 frames.], batch size: 13, lr: 6.11e-04
2022-05-28 21:54:45,937 INFO [train.py:761] (5/8) Epoch 20, batch 2750, loss[loss=0.2532, simple_loss=0.3373, pruned_loss=0.08455, over 4811.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3144, pruned_loss=0.06798, over 966500.57 frames.], batch size: 25, lr: 6.11e-04
2022-05-28 21:55:24,504 INFO [train.py:761] (5/8) Epoch 20, batch 2800, loss[loss=0.1982, simple_loss=0.2986, pruned_loss=0.04885, over 4865.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3153, pruned_loss=0.06798, over 966728.38 frames.], batch size: 17, lr: 6.11e-04
2022-05-28 21:56:02,505 INFO [train.py:761] (5/8) Epoch 20, batch 2850, loss[loss=0.1926, simple_loss=0.3012, pruned_loss=0.04203, over 4769.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3142, pruned_loss=0.06762, over 966309.97 frames.], batch size: 15, lr: 6.10e-04
2022-05-28 21:56:39,941 INFO [train.py:761] (5/8) Epoch 20, batch 2900, loss[loss=0.1717, simple_loss=0.2649, pruned_loss=0.03926, over 4834.00 frames.], tot_loss[loss=0.224, simple_loss=0.3136, pruned_loss=0.0672, over 966259.63 frames.], batch size: 11, lr: 6.10e-04
2022-05-28 21:57:18,027 INFO [train.py:761] (5/8) Epoch 20, batch 2950, loss[loss=0.2018, simple_loss=0.2826, pruned_loss=0.06046, over 4978.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3129, pruned_loss=0.06703, over 966456.41 frames.], batch size: 11, lr: 6.10e-04
2022-05-28 21:57:55,820 INFO [train.py:761] (5/8) Epoch 20, batch 3000, loss[loss=0.2035, simple_loss=0.282, pruned_loss=0.06252, over 4745.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3125, pruned_loss=0.06722, over 966514.53 frames.], batch size: 11, lr: 6.10e-04
2022-05-28 21:57:55,820 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 21:58:05,763 INFO [train.py:790] (5/8) Epoch 20, validation: loss=0.21, simple_loss=0.3123, pruned_loss=0.05382, over 944034.00 frames.
2022-05-28 21:58:44,201 INFO [train.py:761] (5/8) Epoch 20, batch 3050, loss[loss=0.1924, simple_loss=0.2876, pruned_loss=0.04858, over 4673.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3144, pruned_loss=0.06794, over 966834.05 frames.], batch size: 13, lr: 6.10e-04
2022-05-28 21:59:22,113 INFO [train.py:761] (5/8) Epoch 20, batch 3100, loss[loss=0.2527, simple_loss=0.3488, pruned_loss=0.07829, over 4878.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3158, pruned_loss=0.06886, over 966190.49 frames.], batch size: 17, lr: 6.10e-04
2022-05-28 22:00:00,103 INFO [train.py:761] (5/8) Epoch 20, batch 3150, loss[loss=0.2375, simple_loss=0.3461, pruned_loss=0.06442, over 4880.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3171, pruned_loss=0.07058, over 966364.38 frames.], batch size: 15, lr: 6.10e-04
2022-05-28 22:00:37,783 INFO [train.py:761] (5/8) Epoch 20, batch 3200, loss[loss=0.2447, simple_loss=0.331, pruned_loss=0.07925, over 4898.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3179, pruned_loss=0.07195, over 966083.80 frames.], batch size: 15, lr: 6.10e-04
2022-05-28 22:01:15,947 INFO [train.py:761] (5/8) Epoch 20, batch 3250, loss[loss=0.2676, simple_loss=0.3591, pruned_loss=0.08804, over 4757.00 frames.], tot_loss[loss=0.2349, simple_loss=0.32, pruned_loss=0.07486, over 966147.40 frames.], batch size: 15, lr: 6.10e-04
2022-05-28 22:01:54,272 INFO [train.py:761] (5/8) Epoch 20, batch 3300, loss[loss=0.3263, simple_loss=0.3891, pruned_loss=0.1317, over 4882.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3209, pruned_loss=0.07737, over 965617.15 frames.], batch size: 50, lr: 6.09e-04
2022-05-28 22:02:32,788 INFO [train.py:761] (5/8) Epoch 20, batch 3350, loss[loss=0.2412, simple_loss=0.3285, pruned_loss=0.07698, over 4949.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3221, pruned_loss=0.07871, over 966420.54 frames.], batch size: 21, lr: 6.09e-04
2022-05-28 22:03:10,498 INFO [train.py:761] (5/8) Epoch 20, batch 3400, loss[loss=0.2762, simple_loss=0.3343, pruned_loss=0.1091, over 4973.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3226, pruned_loss=0.08058, over 966877.38 frames.], batch size: 15, lr: 6.09e-04
2022-05-28 22:03:48,875 INFO [train.py:761] (5/8) Epoch 20, batch 3450, loss[loss=0.2352, simple_loss=0.3048, pruned_loss=0.08279, over 4728.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3244, pruned_loss=0.08229, over 967770.90 frames.], batch size: 12, lr: 6.09e-04
2022-05-28 22:04:26,811 INFO [train.py:761] (5/8) Epoch 20, batch 3500, loss[loss=0.3396, simple_loss=0.3948, pruned_loss=0.1422, over 4904.00 frames.], tot_loss[loss=0.2434, simple_loss=0.323, pruned_loss=0.08195, over 966375.09 frames.], batch size: 51, lr: 6.09e-04
2022-05-28 22:05:04,382 INFO [train.py:761] (5/8) Epoch 20, batch 3550, loss[loss=0.2045, simple_loss=0.2906, pruned_loss=0.05921, over 4989.00 frames.], tot_loss[loss=0.2425, simple_loss=0.322, pruned_loss=0.08147, over 965472.70 frames.], batch size: 13, lr: 6.09e-04
2022-05-28 22:05:43,060 INFO [train.py:761] (5/8) Epoch 20, batch 3600, loss[loss=0.2931, simple_loss=0.3599, pruned_loss=0.1132, over 4669.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3229, pruned_loss=0.08247, over 965797.88 frames.], batch size: 13, lr: 6.09e-04
2022-05-28 22:06:21,013 INFO [train.py:761] (5/8) Epoch 20, batch 3650, loss[loss=0.2726, simple_loss=0.3532, pruned_loss=0.09597, over 4918.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3242, pruned_loss=0.0841, over 964897.51 frames.], batch size: 14, lr: 6.09e-04
2022-05-28 22:06:59,325 INFO [train.py:761] (5/8) Epoch 20, batch 3700, loss[loss=0.2851, simple_loss=0.3517, pruned_loss=0.1093, over 4721.00 frames.], tot_loss[loss=0.2459, simple_loss=0.323, pruned_loss=0.08436, over 964402.10 frames.], batch size: 13, lr: 6.09e-04
2022-05-28 22:07:37,186 INFO [train.py:761] (5/8) Epoch 20, batch 3750, loss[loss=0.2282, simple_loss=0.3121, pruned_loss=0.07214, over 4663.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3243, pruned_loss=0.08533, over 965581.91 frames.], batch size: 12, lr: 6.08e-04
2022-05-28 22:08:14,759 INFO [train.py:761] (5/8) Epoch 20, batch 3800, loss[loss=0.2969, simple_loss=0.3521, pruned_loss=0.1209, over 4826.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3243, pruned_loss=0.08524, over 964722.66 frames.], batch size: 16, lr: 6.08e-04
2022-05-28 22:08:53,151 INFO [train.py:761] (5/8) Epoch 20, batch 3850, loss[loss=0.2099, simple_loss=0.2831, pruned_loss=0.06829, over 4670.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3223, pruned_loss=0.08472, over 964616.02 frames.], batch size: 12, lr: 6.08e-04
2022-05-28 22:09:31,182 INFO [train.py:761] (5/8) Epoch 20, batch 3900, loss[loss=0.231, simple_loss=0.2984, pruned_loss=0.08179, over 4719.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3224, pruned_loss=0.08487, over 965082.43 frames.], batch size: 11, lr: 6.08e-04
2022-05-28 22:10:09,490 INFO [train.py:761] (5/8) Epoch 20, batch 3950, loss[loss=0.32, simple_loss=0.3838, pruned_loss=0.1281, over 4780.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3226, pruned_loss=0.08432, over 965686.21 frames.], batch size: 16, lr: 6.08e-04
2022-05-28 22:10:47,109 INFO [train.py:761] (5/8) Epoch 20, batch 4000, loss[loss=0.2214, simple_loss=0.2967, pruned_loss=0.07299, over 4735.00 frames.], tot_loss[loss=0.2454, simple_loss=0.3224, pruned_loss=0.08423, over 966560.95 frames.], batch size: 11, lr: 6.08e-04
2022-05-28 22:11:25,605 INFO [train.py:761] (5/8) Epoch 20, batch 4050, loss[loss=0.2244, simple_loss=0.3064, pruned_loss=0.07118, over 4812.00 frames.], tot_loss[loss=0.2454, simple_loss=0.3224, pruned_loss=0.0842, over 965392.91 frames.], batch size: 12, lr: 6.08e-04
2022-05-28 22:12:03,443 INFO [train.py:761] (5/8) Epoch 20, batch 4100, loss[loss=0.2112, simple_loss=0.2832, pruned_loss=0.06958, over 4880.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3221, pruned_loss=0.08409, over 965476.11 frames.], batch size: 12, lr: 6.08e-04
2022-05-28 22:12:41,963 INFO [train.py:761] (5/8) Epoch 20, batch 4150, loss[loss=0.2251, simple_loss=0.3232, pruned_loss=0.06353, over 4677.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3238, pruned_loss=0.08441, over 966408.98 frames.], batch size: 13, lr: 6.07e-04
2022-05-28 22:13:19,513 INFO [train.py:761] (5/8) Epoch 20, batch 4200, loss[loss=0.2598, simple_loss=0.3177, pruned_loss=0.1009, over 4639.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3226, pruned_loss=0.08363, over 965799.19 frames.], batch size: 11, lr: 6.07e-04
2022-05-28 22:13:57,686 INFO [train.py:761] (5/8) Epoch 20, batch 4250, loss[loss=0.2728, simple_loss=0.3435, pruned_loss=0.101, over 4872.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3228, pruned_loss=0.08452, over 964913.85 frames.], batch size: 15, lr: 6.07e-04
2022-05-28 22:14:36,211 INFO [train.py:761] (5/8) Epoch 20, batch 4300, loss[loss=0.2205, simple_loss=0.3135, pruned_loss=0.06379, over 4954.00 frames.], tot_loss[loss=0.247, simple_loss=0.3238, pruned_loss=0.08514, over 965830.79 frames.], batch size: 16, lr: 6.07e-04
2022-05-28 22:15:14,656 INFO [train.py:761] (5/8) Epoch 20, batch 4350, loss[loss=0.2368, simple_loss=0.3142, pruned_loss=0.07972, over 4728.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3239, pruned_loss=0.08542, over 964636.69 frames.], batch size: 13, lr: 6.07e-04
2022-05-28 22:15:52,815 INFO [train.py:761] (5/8) Epoch 20, batch 4400, loss[loss=0.2569, simple_loss=0.322, pruned_loss=0.09591, over 4930.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3239, pruned_loss=0.08509, over 964820.07 frames.], batch size: 13, lr: 6.07e-04
2022-05-28 22:16:31,319 INFO [train.py:761] (5/8) Epoch 20, batch 4450, loss[loss=0.2632, simple_loss=0.3094, pruned_loss=0.1085, over 4649.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3242, pruned_loss=0.08533, over 964014.34 frames.], batch size: 11, lr: 6.07e-04
2022-05-28 22:17:08,973 INFO [train.py:761] (5/8) Epoch 20, batch 4500, loss[loss=0.1995, simple_loss=0.2785, pruned_loss=0.06024, over 4662.00 frames.], tot_loss[loss=0.2473, simple_loss=0.3242, pruned_loss=0.08526, over 964512.01 frames.], batch size: 12, lr: 6.07e-04
2022-05-28 22:17:47,554 INFO [train.py:761] (5/8) Epoch 20, batch 4550, loss[loss=0.2908, simple_loss=0.3578, pruned_loss=0.1119, over 4810.00 frames.], tot_loss[loss=0.2469, simple_loss=0.3237, pruned_loss=0.08508, over 964700.55 frames.], batch size: 16, lr: 6.07e-04
2022-05-28 22:18:25,950 INFO [train.py:761] (5/8) Epoch 20, batch 4600, loss[loss=0.2021, simple_loss=0.2862, pruned_loss=0.05905, over 4979.00 frames.], tot_loss[loss=0.2443, simple_loss=0.321, pruned_loss=0.08383, over 963512.24 frames.], batch size: 12, lr: 6.06e-04
2022-05-28 22:19:04,860 INFO [train.py:761] (5/8) Epoch 20, batch 4650, loss[loss=0.2023, simple_loss=0.2772, pruned_loss=0.06366, over 4954.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3209, pruned_loss=0.08399, over 964573.06 frames.], batch size: 11, lr: 6.06e-04
2022-05-28 22:19:42,958 INFO [train.py:761] (5/8) Epoch 20, batch 4700, loss[loss=0.2895, simple_loss=0.375, pruned_loss=0.102, over 4788.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3219, pruned_loss=0.08465, over 964814.04 frames.], batch size: 14, lr: 6.06e-04
2022-05-28 22:20:21,132 INFO [train.py:761] (5/8) Epoch 20, batch 4750, loss[loss=0.2765, simple_loss=0.3516, pruned_loss=0.1007, over 4916.00 frames.], tot_loss[loss=0.2471, simple_loss=0.323, pruned_loss=0.08555, over 965715.38 frames.], batch size: 18, lr: 6.06e-04
2022-05-28 22:21:00,189 INFO [train.py:761] (5/8) Epoch 20, batch 4800, loss[loss=0.2529, simple_loss=0.3107, pruned_loss=0.09755, over 4822.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3231, pruned_loss=0.08521, over 965980.63 frames.], batch size: 11, lr: 6.06e-04
2022-05-28 22:21:38,610 INFO [train.py:761] (5/8) Epoch 20, batch 4850, loss[loss=0.2637, simple_loss=0.3413, pruned_loss=0.09301, over 4798.00 frames.], tot_loss[loss=0.2472, simple_loss=0.3235, pruned_loss=0.0854, over 966666.48 frames.], batch size: 20, lr: 6.06e-04
2022-05-28 22:22:16,668 INFO [train.py:761] (5/8) Epoch 20, batch 4900, loss[loss=0.2966, simple_loss=0.366, pruned_loss=0.1136, over 4954.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3241, pruned_loss=0.0857, over 966588.92 frames.], batch size: 16, lr: 6.06e-04
2022-05-28 22:22:55,206 INFO [train.py:761] (5/8) Epoch 20, batch 4950, loss[loss=0.2098, simple_loss=0.279, pruned_loss=0.07032, over 4850.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3225, pruned_loss=0.08532, over 966267.75 frames.], batch size: 13, lr: 6.06e-04
2022-05-28 22:23:33,070 INFO [train.py:761] (5/8) Epoch 20, batch 5000, loss[loss=0.2863, simple_loss=0.3529, pruned_loss=0.1098, over 4800.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3232, pruned_loss=0.08502, over 965540.33 frames.], batch size: 16, lr: 6.06e-04
2022-05-28 22:24:12,032 INFO [train.py:761] (5/8) Epoch 20, batch 5050, loss[loss=0.3186, simple_loss=0.3821, pruned_loss=0.1276, over 4914.00 frames.], tot_loss[loss=0.2454, simple_loss=0.3223, pruned_loss=0.08428, over 966583.38 frames.], batch size: 49, lr: 6.05e-04
2022-05-28 22:24:50,785 INFO [train.py:761] (5/8) Epoch 20, batch 5100, loss[loss=0.2909, simple_loss=0.3708, pruned_loss=0.1056, over 4985.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3217, pruned_loss=0.08384, over 966406.93 frames.], batch size: 26, lr: 6.05e-04
2022-05-28 22:25:29,222 INFO [train.py:761] (5/8) Epoch 20, batch 5150, loss[loss=0.2154, simple_loss=0.2937, pruned_loss=0.06849, over 4611.00 frames.], tot_loss[loss=0.245, simple_loss=0.322, pruned_loss=0.08398, over 966814.50 frames.], batch size: 12, lr: 6.05e-04
2022-05-28 22:26:07,302 INFO [train.py:761] (5/8) Epoch 20, batch 5200, loss[loss=0.2439, simple_loss=0.309, pruned_loss=0.0894, over 4810.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3222, pruned_loss=0.08423, over 966393.89 frames.], batch size: 12, lr: 6.05e-04
2022-05-28 22:26:46,053 INFO [train.py:761] (5/8) Epoch 20, batch 5250, loss[loss=0.2595, simple_loss=0.3315, pruned_loss=0.09373, over 4891.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3219, pruned_loss=0.08396, over 965857.70 frames.], batch size: 26, lr: 6.05e-04
2022-05-28 22:27:24,361 INFO [train.py:761] (5/8) Epoch 20, batch 5300, loss[loss=0.2469, simple_loss=0.3206, pruned_loss=0.08666, over 4848.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3212, pruned_loss=0.08329, over 965832.19 frames.], batch size: 14, lr: 6.05e-04
2022-05-28 22:28:02,959 INFO [train.py:761] (5/8) Epoch 20, batch 5350, loss[loss=0.2037, simple_loss=0.2877, pruned_loss=0.05989, over 4665.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3203, pruned_loss=0.08224, over 965954.50 frames.], batch size: 13, lr: 6.05e-04
2022-05-28 22:28:40,385 INFO [train.py:761] (5/8) Epoch 20, batch 5400, loss[loss=0.2327, simple_loss=0.3149, pruned_loss=0.07525, over 4881.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3201, pruned_loss=0.08226, over 966491.67 frames.], batch size: 15, lr: 6.05e-04
2022-05-28 22:29:18,864 INFO [train.py:761] (5/8) Epoch 20, batch 5450, loss[loss=0.2327, simple_loss=0.3201, pruned_loss=0.07267, over 4979.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3207, pruned_loss=0.08303, over 967327.85 frames.], batch size: 15, lr: 6.05e-04
2022-05-28 22:29:57,245 INFO [train.py:761] (5/8) Epoch 20, batch 5500, loss[loss=0.2766, simple_loss=0.3713, pruned_loss=0.09094, over 4953.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3204, pruned_loss=0.08295, over 967798.10 frames.], batch size: 16, lr: 6.04e-04
2022-05-28 22:30:35,599 INFO [train.py:761] (5/8) Epoch 20, batch 5550, loss[loss=0.224, simple_loss=0.3277, pruned_loss=0.06018, over 4851.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3199, pruned_loss=0.08292, over 967543.53 frames.], batch size: 14, lr: 6.04e-04
2022-05-28 22:31:13,423 INFO [train.py:761] (5/8) Epoch 20, batch 5600, loss[loss=0.2782, simple_loss=0.3227, pruned_loss=0.1169, over 4548.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3211, pruned_loss=0.08359, over 966555.07 frames.], batch size: 10, lr: 6.04e-04
2022-05-28 22:31:51,708 INFO [train.py:761] (5/8) Epoch 20, batch 5650, loss[loss=0.2336, simple_loss=0.3257, pruned_loss=0.0707, over 4971.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3218, pruned_loss=0.0844, over 966520.97 frames.], batch size: 14, lr: 6.04e-04
2022-05-28 22:32:30,180 INFO [train.py:761] (5/8) Epoch 20, batch 5700, loss[loss=0.2456, simple_loss=0.319, pruned_loss=0.08608, over 4802.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3216, pruned_loss=0.08409, over 967125.73 frames.], batch size: 16, lr: 6.04e-04
2022-05-28 22:33:08,515 INFO [train.py:761] (5/8) Epoch 20, batch 5750, loss[loss=0.2265, simple_loss=0.2999, pruned_loss=0.07655, over 4806.00 frames.], tot_loss[loss=0.245, simple_loss=0.3221, pruned_loss=0.084, over 966883.48 frames.], batch size: 12, lr: 6.04e-04
2022-05-28 22:33:46,967 INFO [train.py:761] (5/8) Epoch 20, batch 5800, loss[loss=0.2628, simple_loss=0.336, pruned_loss=0.09482, over 4793.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3233, pruned_loss=0.08463, over 968353.68 frames.], batch size: 13, lr: 6.04e-04
2022-05-28 22:34:25,174 INFO [train.py:761] (5/8) Epoch 20, batch 5850, loss[loss=0.2616, simple_loss=0.3181, pruned_loss=0.1026, over 4991.00 frames.], tot_loss[loss=0.245, simple_loss=0.3219, pruned_loss=0.08408, over 966863.37 frames.], batch size: 13, lr: 6.04e-04
2022-05-28 22:35:03,169 INFO [train.py:761] (5/8) Epoch 20, batch 5900, loss[loss=0.2606, simple_loss=0.3183, pruned_loss=0.1015, over 4583.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3221, pruned_loss=0.08418, over 966923.89 frames.], batch size: 10, lr: 6.03e-04
2022-05-28 22:35:41,188 INFO [train.py:761] (5/8) Epoch 20, batch 5950, loss[loss=0.3258, simple_loss=0.3683, pruned_loss=0.1417, over 4851.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3217, pruned_loss=0.08442, over 966638.77 frames.], batch size: 14, lr: 6.03e-04
2022-05-28 22:36:20,420 INFO [train.py:761] (5/8) Epoch 20, batch 6000, loss[loss=0.2562, simple_loss=0.3293, pruned_loss=0.09154, over 4903.00 frames.], tot_loss[loss=0.2436, simple_loss=0.3206, pruned_loss=0.08331, over 967191.78 frames.], batch size: 17, lr: 6.03e-04
2022-05-28 22:36:20,420 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 22:36:30,524 INFO [train.py:790] (5/8) Epoch 20, validation: loss=0.2047, simple_loss=0.3091, pruned_loss=0.05018, over 944034.00 frames.
2022-05-28 22:37:08,754 INFO [train.py:761] (5/8) Epoch 20, batch 6050, loss[loss=0.2168, simple_loss=0.2886, pruned_loss=0.07248, over 4886.00 frames.], tot_loss[loss=0.2454, simple_loss=0.3223, pruned_loss=0.08425, over 966701.71 frames.], batch size: 12, lr: 6.03e-04
2022-05-28 22:37:47,039 INFO [train.py:761] (5/8) Epoch 20, batch 6100, loss[loss=0.2659, simple_loss=0.3343, pruned_loss=0.09877, over 4878.00 frames.], tot_loss[loss=0.245, simple_loss=0.3222, pruned_loss=0.08394, over 967256.80 frames.], batch size: 15, lr: 6.03e-04
2022-05-28 22:38:25,502 INFO [train.py:761] (5/8) Epoch 20, batch 6150, loss[loss=0.1939, simple_loss=0.2659, pruned_loss=0.061, over 4549.00 frames.], tot_loss[loss=0.245, simple_loss=0.3223, pruned_loss=0.08385, over 966895.44 frames.], batch size: 10, lr: 6.03e-04
2022-05-28 22:39:03,834 INFO [train.py:761] (5/8) Epoch 20, batch 6200, loss[loss=0.2134, simple_loss=0.3069, pruned_loss=0.05996, over 4861.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3223, pruned_loss=0.08378, over 967839.39 frames.], batch size: 14, lr: 6.03e-04
2022-05-28 22:39:42,284 INFO [train.py:761] (5/8) Epoch 20, batch 6250, loss[loss=0.2405, simple_loss=0.3276, pruned_loss=0.0767, over 4764.00 frames.], tot_loss[loss=0.2442, simple_loss=0.3213, pruned_loss=0.08357, over 967228.39 frames.], batch size: 15, lr: 6.03e-04
2022-05-28 22:40:21,063 INFO [train.py:761] (5/8) Epoch 20, batch 6300, loss[loss=0.3296, simple_loss=0.3858, pruned_loss=0.1367, over 4792.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3202, pruned_loss=0.08298, over 967049.11 frames.], batch size: 16, lr: 6.03e-04
2022-05-28 22:40:59,647 INFO [train.py:761] (5/8) Epoch 20, batch 6350, loss[loss=0.3262, simple_loss=0.3719, pruned_loss=0.1402, over 4925.00 frames.], tot_loss[loss=0.2411, simple_loss=0.3185, pruned_loss=0.0818, over 965885.62 frames.], batch size: 46, lr: 6.02e-04
2022-05-28 22:41:38,020 INFO [train.py:761] (5/8) Epoch 20, batch 6400, loss[loss=0.3097, simple_loss=0.3725, pruned_loss=0.1235, over 4886.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3201, pruned_loss=0.08278, over 966505.05 frames.], batch size: 15, lr: 6.02e-04
2022-05-28 22:42:15,856 INFO [train.py:761] (5/8) Epoch 20, batch 6450, loss[loss=0.2364, simple_loss=0.3183, pruned_loss=0.07726, over 4783.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3196, pruned_loss=0.08262, over 965518.09 frames.], batch size: 15, lr: 6.02e-04
2022-05-28 22:42:53,724 INFO [train.py:761] (5/8) Epoch 20, batch 6500, loss[loss=0.2698, simple_loss=0.3428, pruned_loss=0.0984, over 4670.00 frames.], tot_loss[loss=0.2438, simple_loss=0.3206, pruned_loss=0.08345, over 965456.08 frames.], batch size: 12, lr: 6.02e-04
2022-05-28 22:43:32,674 INFO [train.py:761] (5/8) Epoch 20, batch 6550, loss[loss=0.2326, simple_loss=0.2973, pruned_loss=0.08396, over 4646.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3209, pruned_loss=0.08402, over 965677.07 frames.], batch size: 11, lr: 6.02e-04
2022-05-28 22:44:11,055 INFO [train.py:761] (5/8) Epoch 20, batch 6600, loss[loss=0.2748, simple_loss=0.3513, pruned_loss=0.09912, over 4894.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3207, pruned_loss=0.0841, over 967244.21 frames.], batch size: 17, lr: 6.02e-04
2022-05-28 22:44:49,562 INFO [train.py:761] (5/8) Epoch 20, batch 6650, loss[loss=0.2907, simple_loss=0.3671, pruned_loss=0.1071, over 4933.00 frames.], tot_loss[loss=0.2451, simple_loss=0.3224, pruned_loss=0.08387, over 967507.92 frames.], batch size: 50, lr: 6.02e-04
2022-05-28 22:45:28,112 INFO [train.py:761] (5/8) Epoch 20, batch 6700, loss[loss=0.306, simple_loss=0.3757, pruned_loss=0.1181, over 4899.00 frames.], tot_loss[loss=0.2451, simple_loss=0.322, pruned_loss=0.08413, over 966813.30 frames.], batch size: 48, lr: 6.02e-04
2022-05-28 22:46:22,082 INFO [train.py:761] (5/8) Epoch 21, batch 0, loss[loss=0.18, simple_loss=0.2662, pruned_loss=0.04696, over 4824.00 frames.], tot_loss[loss=0.18, simple_loss=0.2662, pruned_loss=0.04696, over 4824.00 frames.], batch size: 11, lr: 6.02e-04
2022-05-28 22:47:00,229 INFO [train.py:761] (5/8) Epoch 21, batch 50, loss[loss=0.2269, simple_loss=0.3245, pruned_loss=0.06468, over 4781.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3142, pruned_loss=0.06757, over 218468.53 frames.], batch size: 16, lr: 6.01e-04
2022-05-28 22:47:38,777 INFO [train.py:761] (5/8) Epoch 21, batch 100, loss[loss=0.233, simple_loss=0.3105, pruned_loss=0.07777, over 4833.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3142, pruned_loss=0.06676, over 384478.43 frames.], batch size: 18, lr: 6.01e-04
2022-05-28 22:48:16,741 INFO [train.py:761] (5/8) Epoch 21, batch 150, loss[loss=0.2076, simple_loss=0.2841, pruned_loss=0.06553, over 4838.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3122, pruned_loss=0.06686, over 514299.16 frames.], batch size: 11, lr: 6.01e-04
2022-05-28 22:48:54,533 INFO [train.py:761] (5/8) Epoch 21, batch 200, loss[loss=0.2477, simple_loss=0.3403, pruned_loss=0.07757, over 4971.00 frames.], tot_loss[loss=0.2234, simple_loss=0.312, pruned_loss=0.06741, over 614554.95 frames.], batch size: 15, lr: 6.01e-04
2022-05-28 22:49:32,374 INFO [train.py:761] (5/8) Epoch 21, batch 250, loss[loss=0.2205, simple_loss=0.3278, pruned_loss=0.05657, over 4828.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3121, pruned_loss=0.06663, over 692156.46 frames.], batch size: 18, lr: 6.01e-04
2022-05-28 22:50:10,450 INFO [train.py:761] (5/8) Epoch 21, batch 300, loss[loss=0.2281, simple_loss=0.3134, pruned_loss=0.07139, over 4917.00 frames.], tot_loss[loss=0.2204, simple_loss=0.31, pruned_loss=0.06536, over 752033.61 frames.], batch size: 13, lr: 6.01e-04
2022-05-28 22:50:48,304 INFO [train.py:761] (5/8) Epoch 21, batch 350, loss[loss=0.1939, simple_loss=0.2878, pruned_loss=0.05001, over 4774.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3095, pruned_loss=0.06443, over 799769.32 frames.], batch size: 13, lr: 6.01e-04
2022-05-28 22:51:26,980 INFO [train.py:761] (5/8) Epoch 21, batch 400, loss[loss=0.1904, simple_loss=0.2985, pruned_loss=0.04117, over 4721.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3093, pruned_loss=0.06465, over 836158.21 frames.], batch size: 13, lr: 6.01e-04
2022-05-28 22:52:05,195 INFO [train.py:761] (5/8) Epoch 21, batch 450, loss[loss=0.2241, simple_loss=0.3308, pruned_loss=0.05871, over 4975.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3109, pruned_loss=0.0651, over 865846.74 frames.], batch size: 14, lr: 6.01e-04
2022-05-28 22:52:43,230 INFO [train.py:761] (5/8) Epoch 21, batch 500, loss[loss=0.2918, simple_loss=0.3582, pruned_loss=0.1127, over 4980.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3109, pruned_loss=0.06527, over 887432.50 frames.], batch size: 12, lr: 6.00e-04
2022-05-28 22:53:21,037 INFO [train.py:761] (5/8) Epoch 21, batch 550, loss[loss=0.198, simple_loss=0.2909, pruned_loss=0.05259, over 4670.00 frames.], tot_loss[loss=0.2201, simple_loss=0.3102, pruned_loss=0.06497, over 905037.11 frames.], batch size: 12, lr: 6.00e-04
2022-05-28 22:53:59,617 INFO [train.py:761] (5/8) Epoch 21, batch 600, loss[loss=0.1753, simple_loss=0.2628, pruned_loss=0.04388, over 4847.00 frames.], tot_loss[loss=0.219, simple_loss=0.309, pruned_loss=0.06452, over 919123.01 frames.], batch size: 11, lr: 6.00e-04
2022-05-28 22:54:37,475 INFO [train.py:761] (5/8) Epoch 21, batch 650, loss[loss=0.1769, simple_loss=0.2682, pruned_loss=0.04284, over 4738.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3086, pruned_loss=0.06492, over 929388.27 frames.], batch size: 11, lr: 6.00e-04
2022-05-28 22:55:15,536 INFO [train.py:761] (5/8) Epoch 21, batch 700, loss[loss=0.2133, simple_loss=0.3133, pruned_loss=0.05659, over 4967.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3107, pruned_loss=0.06583, over 938228.51 frames.], batch size: 15, lr: 6.00e-04
2022-05-28 22:55:52,972 INFO [train.py:761] (5/8) Epoch 21, batch 750, loss[loss=0.2061, simple_loss=0.2924, pruned_loss=0.05987, over 4784.00 frames.], tot_loss[loss=0.2221, simple_loss=0.311, pruned_loss=0.06655, over 943454.44 frames.], batch size: 13, lr: 6.00e-04
2022-05-28 22:56:30,461 INFO [train.py:761] (5/8) Epoch 21, batch 800, loss[loss=0.2481, simple_loss=0.342, pruned_loss=0.07713, over 4764.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3114, pruned_loss=0.06742, over 948744.12 frames.], batch size: 20, lr: 6.00e-04
2022-05-28 22:57:08,124 INFO [train.py:761] (5/8) Epoch 21, batch 850, loss[loss=0.225, simple_loss=0.3093, pruned_loss=0.0703, over 4723.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3112, pruned_loss=0.06732, over 952325.80 frames.], batch size: 13, lr: 6.00e-04
2022-05-28 22:57:46,072 INFO [train.py:761] (5/8) Epoch 21, batch 900, loss[loss=0.2066, simple_loss=0.285, pruned_loss=0.06412, over 4840.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3113, pruned_loss=0.0671, over 954926.87 frames.], batch size: 11, lr: 6.00e-04
2022-05-28 22:58:24,495 INFO [train.py:761] (5/8) Epoch 21, batch 950, loss[loss=0.2252, simple_loss=0.3137, pruned_loss=0.06833, over 4728.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3116, pruned_loss=0.06738, over 957060.38 frames.], batch size: 12, lr: 5.99e-04
2022-05-28 22:59:02,069 INFO [train.py:761] (5/8) Epoch 21, batch 1000, loss[loss=0.2402, simple_loss=0.3133, pruned_loss=0.08358, over 4958.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3113, pruned_loss=0.06766, over 958593.20 frames.], batch size: 12, lr: 5.99e-04
2022-05-28 22:59:39,588 INFO [train.py:761] (5/8) Epoch 21, batch 1050, loss[loss=0.1946, simple_loss=0.2885, pruned_loss=0.05036, over 4807.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3103, pruned_loss=0.06693, over 960815.01 frames.], batch size: 12, lr: 5.99e-04
2022-05-28 23:00:21,447 INFO [train.py:761] (5/8) Epoch 21, batch 1100, loss[loss=0.2471, simple_loss=0.3288, pruned_loss=0.08263, over 4794.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3115, pruned_loss=0.06748, over 961859.72 frames.], batch size: 16, lr: 5.99e-04
2022-05-28 23:00:59,576 INFO [train.py:761] (5/8) Epoch 21, batch 1150, loss[loss=0.2283, simple_loss=0.3292, pruned_loss=0.06371, over 4853.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3109, pruned_loss=0.06679, over 962667.94 frames.], batch size: 17, lr: 5.99e-04
2022-05-28 23:01:37,744 INFO [train.py:761] (5/8) Epoch 21, batch 1200, loss[loss=0.2308, simple_loss=0.3123, pruned_loss=0.07471, over 4915.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3128, pruned_loss=0.06811, over 965432.18 frames.], batch size: 14, lr: 5.99e-04
2022-05-28 23:02:16,005 INFO [train.py:761] (5/8) Epoch 21, batch 1250, loss[loss=0.2581, simple_loss=0.3509, pruned_loss=0.08262, over 4666.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3136, pruned_loss=0.06831, over 965798.29 frames.], batch size: 13, lr: 5.99e-04
2022-05-28 23:02:54,032 INFO [train.py:761] (5/8) Epoch 21, batch 1300, loss[loss=0.2167, simple_loss=0.2995, pruned_loss=0.06699, over 4885.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3133, pruned_loss=0.06871, over 965416.63 frames.], batch size: 15, lr: 5.99e-04
2022-05-28 23:03:31,836 INFO [train.py:761] (5/8) Epoch 21, batch 1350, loss[loss=0.2363, simple_loss=0.3228, pruned_loss=0.07488, over 4786.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3133, pruned_loss=0.06824, over 965331.99 frames.], batch size: 14, lr: 5.99e-04
2022-05-28 23:04:17,205 INFO [train.py:761] (5/8) Epoch 21, batch 1400, loss[loss=0.2857, simple_loss=0.3694, pruned_loss=0.101, over 4781.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3139, pruned_loss=0.06856, over 966158.60 frames.], batch size: 15, lr: 5.98e-04
2022-05-28 23:04:55,477 INFO [train.py:761] (5/8) Epoch 21, batch 1450, loss[loss=0.2572, simple_loss=0.3365, pruned_loss=0.08893, over 4872.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3151, pruned_loss=0.06885, over 965659.28 frames.], batch size: 48, lr: 5.98e-04
2022-05-28 23:05:33,406 INFO [train.py:761] (5/8) Epoch 21, batch 1500, loss[loss=0.238, simple_loss=0.3123, pruned_loss=0.08187, over 4802.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3159, pruned_loss=0.06984, over 967341.64 frames.], batch size: 12, lr: 5.98e-04
2022-05-28 23:06:10,955 INFO [train.py:761] (5/8) Epoch 21, batch 1550, loss[loss=0.2383, simple_loss=0.3262, pruned_loss=0.07521, over 4783.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3156, pruned_loss=0.06944, over 966473.64 frames.], batch size: 13, lr: 5.98e-04
2022-05-28 23:06:49,176 INFO [train.py:761] (5/8) Epoch 21, batch 1600, loss[loss=0.2165, simple_loss=0.3091, pruned_loss=0.06191, over 4991.00 frames.], tot_loss[loss=0.2276, simple_loss=0.316, pruned_loss=0.06965, over 967184.01 frames.], batch size: 12, lr: 5.98e-04
2022-05-28 23:07:27,048 INFO [train.py:761] (5/8) Epoch 21, batch 1650, loss[loss=0.2224, simple_loss=0.3104, pruned_loss=0.06716, over 4893.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3154, pruned_loss=0.06893, over 966384.26 frames.], batch size: 21, lr: 5.98e-04
2022-05-28 23:08:05,177 INFO [train.py:761] (5/8) Epoch 21, batch 1700, loss[loss=0.225, simple_loss=0.3254, pruned_loss=0.06236, over 4977.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3154, pruned_loss=0.06821, over 966892.58 frames.], batch size: 26, lr: 5.98e-04
2022-05-28 23:08:42,669 INFO [train.py:761] (5/8) Epoch 21, batch 1750, loss[loss=0.2846, simple_loss=0.374, pruned_loss=0.09756, over 4807.00 frames.], tot_loss[loss=0.2262, simple_loss=0.3157, pruned_loss=0.06836, over 966347.05 frames.], batch size: 16, lr: 5.98e-04
2022-05-28 23:09:20,530 INFO [train.py:761] (5/8) Epoch 21, batch 1800, loss[loss=0.2401, simple_loss=0.3405, pruned_loss=0.06985, over 4895.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3146, pruned_loss=0.06749, over 965918.86 frames.], batch size: 15, lr: 5.98e-04
2022-05-28 23:09:58,553 INFO [train.py:761] (5/8) Epoch 21, batch 1850, loss[loss=0.2514, simple_loss=0.3382, pruned_loss=0.08224, over 4948.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3145, pruned_loss=0.0676, over 965027.32 frames.], batch size: 16, lr: 5.98e-04
2022-05-28 23:10:36,722 INFO [train.py:761] (5/8) Epoch 21, batch 1900, loss[loss=0.2159, simple_loss=0.3144, pruned_loss=0.05872, over 4782.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3128, pruned_loss=0.06697, over 965245.31 frames.], batch size: 13, lr: 5.97e-04
2022-05-28 23:11:14,359 INFO [train.py:761] (5/8) Epoch 21, batch 1950, loss[loss=0.2201, simple_loss=0.3177, pruned_loss=0.0613, over 4786.00 frames.], tot_loss[loss=0.224, simple_loss=0.3134, pruned_loss=0.06731, over 966379.89 frames.], batch size: 14, lr: 5.97e-04
2022-05-28 23:11:52,685 INFO [train.py:761] (5/8) Epoch 21, batch 2000, loss[loss=0.2275, simple_loss=0.3242, pruned_loss=0.06538, over 4783.00 frames.], tot_loss[loss=0.225, simple_loss=0.3137, pruned_loss=0.0681, over 966017.75 frames.], batch size: 13, lr: 5.97e-04
2022-05-28 23:12:30,884 INFO [train.py:761] (5/8) Epoch 21, batch 2050, loss[loss=0.1902, simple_loss=0.284, pruned_loss=0.04822, over 4859.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3123, pruned_loss=0.06749, over 966420.42 frames.], batch size: 13, lr: 5.97e-04
2022-05-28 23:13:09,563 INFO [train.py:761] (5/8) Epoch 21, batch 2100, loss[loss=0.2318, simple_loss=0.3291, pruned_loss=0.06719, over 4773.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3126, pruned_loss=0.06699, over 966468.63 frames.], batch size: 15, lr: 5.97e-04
2022-05-28 23:13:47,310 INFO [train.py:761] (5/8) Epoch 21, batch 2150, loss[loss=0.2225, simple_loss=0.3143, pruned_loss=0.06532, over 4960.00 frames.], tot_loss[loss=0.223, simple_loss=0.3123, pruned_loss=0.06679, over 967073.00 frames.], batch size: 16, lr: 5.97e-04
2022-05-28 23:14:24,919 INFO [train.py:761] (5/8) Epoch 21, batch 2200, loss[loss=0.2092, simple_loss=0.3156, pruned_loss=0.05139, over 4968.00 frames.], tot_loss[loss=0.223, simple_loss=0.3126, pruned_loss=0.06669, over 966445.44 frames.], batch size: 15, lr: 5.97e-04
2022-05-28 23:15:02,761 INFO [train.py:761] (5/8) Epoch 21, batch 2250, loss[loss=0.2592, simple_loss=0.3488, pruned_loss=0.08478, over 4917.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3127, pruned_loss=0.06698, over 966706.17 frames.], batch size: 26, lr: 5.97e-04
2022-05-28 23:15:40,671 INFO [train.py:761] (5/8) Epoch 21, batch 2300, loss[loss=0.2315, simple_loss=0.3251, pruned_loss=0.069, over 4803.00 frames.], tot_loss[loss=0.221, simple_loss=0.3106, pruned_loss=0.06571, over 964801.08 frames.], batch size: 16, lr: 5.97e-04
2022-05-28 23:16:18,321 INFO [train.py:761] (5/8) Epoch 21, batch 2350, loss[loss=0.252, simple_loss=0.3359, pruned_loss=0.08399, over 4878.00 frames.], tot_loss[loss=0.22, simple_loss=0.3094, pruned_loss=0.06531, over 965139.15 frames.], batch size: 15, lr: 5.96e-04
2022-05-28 23:16:56,184 INFO [train.py:761] (5/8) Epoch 21, batch 2400, loss[loss=0.2054, simple_loss=0.3027, pruned_loss=0.05405, over 4969.00 frames.], tot_loss[loss=0.2198, simple_loss=0.3094, pruned_loss=0.06507, over 964971.06 frames.], batch size: 14, lr: 5.96e-04
2022-05-28 23:17:34,500 INFO [train.py:761] (5/8) Epoch 21, batch 2450, loss[loss=0.2098, simple_loss=0.298, pruned_loss=0.06082, over 4714.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3107, pruned_loss=0.06577, over 964565.91 frames.], batch size: 14, lr: 5.96e-04
2022-05-28 23:18:12,143 INFO [train.py:761] (5/8) Epoch 21, batch 2500, loss[loss=0.2197, simple_loss=0.3164, pruned_loss=0.06147, over 4989.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3108, pruned_loss=0.06578, over 964025.67 frames.], batch size: 13, lr: 5.96e-04
2022-05-28 23:18:49,680 INFO [train.py:761] (5/8) Epoch 21, batch 2550, loss[loss=0.2274, simple_loss=0.3129, pruned_loss=0.07096, over 4785.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3109, pruned_loss=0.06568, over 965359.20 frames.], batch size: 14, lr: 5.96e-04
2022-05-28 23:19:27,553 INFO [train.py:761] (5/8) Epoch 21, batch 2600, loss[loss=0.259, simple_loss=0.3507, pruned_loss=0.08361, over 4965.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3095, pruned_loss=0.06483, over 966455.34 frames.], batch size: 14, lr: 5.96e-04
2022-05-28 23:20:05,373 INFO [train.py:761] (5/8) Epoch 21, batch 2650, loss[loss=0.2232, simple_loss=0.3202, pruned_loss=0.06304, over 4712.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3106, pruned_loss=0.06597, over 965814.20 frames.], batch size: 14, lr: 5.96e-04
2022-05-28 23:20:43,662 INFO [train.py:761] (5/8) Epoch 21, batch 2700, loss[loss=0.2247, simple_loss=0.3036, pruned_loss=0.07295, over 4667.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3093, pruned_loss=0.0649, over 966173.84 frames.], batch size: 12, lr: 5.96e-04
2022-05-28 23:21:21,370 INFO [train.py:761] (5/8) Epoch 21, batch 2750, loss[loss=0.276, simple_loss=0.3382, pruned_loss=0.1069, over 4818.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3099, pruned_loss=0.06532, over 965150.47 frames.], batch size: 12, lr: 5.96e-04
2022-05-28 23:21:59,329 INFO [train.py:761] (5/8) Epoch 21, batch 2800, loss[loss=0.2034, simple_loss=0.2983, pruned_loss=0.05425, over 4782.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3085, pruned_loss=0.06438, over 964902.77 frames.], batch size: 13, lr: 5.95e-04
2022-05-28 23:22:37,928 INFO [train.py:761] (5/8) Epoch 21, batch 2850, loss[loss=0.2168, simple_loss=0.3053, pruned_loss=0.06413, over 4971.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3091, pruned_loss=0.06468, over 965459.30 frames.], batch size: 14, lr: 5.95e-04
2022-05-28 23:23:15,965 INFO [train.py:761] (5/8) Epoch 21, batch 2900, loss[loss=0.2238, simple_loss=0.3136, pruned_loss=0.06697, over 4793.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3096, pruned_loss=0.06494, over 965106.40 frames.], batch size: 15, lr: 5.95e-04
2022-05-28 23:23:53,532 INFO [train.py:761] (5/8) Epoch 21, batch 2950, loss[loss=0.2252, simple_loss=0.3243, pruned_loss=0.06306, over 4860.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3095, pruned_loss=0.06477, over 964676.99 frames.], batch size: 14, lr: 5.95e-04
2022-05-28 23:24:31,349 INFO [train.py:761] (5/8) Epoch 21, batch 3000, loss[loss=0.2416, simple_loss=0.32, pruned_loss=0.08161, over 4856.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3094, pruned_loss=0.06489, over 964835.49 frames.], batch size: 13, lr: 5.95e-04
2022-05-28 23:24:31,350 INFO [train.py:781] (5/8) Computing validation loss
2022-05-28 23:24:41,418 INFO [train.py:790] (5/8) Epoch 21, validation: loss=0.2079, simple_loss=0.3097, pruned_loss=0.05307, over 944034.00 frames.
2022-05-28 23:25:19,593 INFO [train.py:761] (5/8) Epoch 21, batch 3050, loss[loss=0.2609, simple_loss=0.3225, pruned_loss=0.09968, over 4912.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3099, pruned_loss=0.06537, over 964780.91 frames.], batch size: 14, lr: 5.95e-04
2022-05-28 23:25:57,775 INFO [train.py:761] (5/8) Epoch 21, batch 3100, loss[loss=0.1885, simple_loss=0.2788, pruned_loss=0.04909, over 4884.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3104, pruned_loss=0.06595, over 965665.81 frames.], batch size: 12, lr: 5.95e-04
2022-05-28 23:26:35,539 INFO [train.py:761] (5/8) Epoch 21, batch 3150, loss[loss=0.2061, simple_loss=0.2872, pruned_loss=0.06249, over 4729.00 frames.], tot_loss[loss=0.2216, simple_loss=0.31, pruned_loss=0.06657, over 965774.62 frames.], batch size: 13, lr: 5.95e-04
2022-05-28 23:27:13,667 INFO [train.py:761] (5/8) Epoch 21, batch 3200, loss[loss=0.2405, simple_loss=0.3231, pruned_loss=0.07897, over 4663.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3138, pruned_loss=0.06989, over 965704.71 frames.], batch size: 12, lr: 5.95e-04
2022-05-28 23:27:51,626 INFO [train.py:761] (5/8) Epoch 21, batch 3250, loss[loss=0.2672, simple_loss=0.3469, pruned_loss=0.09374, over 4839.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3151, pruned_loss=0.07192, over 965726.61 frames.], batch size: 13, lr: 5.94e-04
2022-05-28 23:28:29,914 INFO [train.py:761] (5/8) Epoch 21, batch 3300, loss[loss=0.1894, simple_loss=0.2674, pruned_loss=0.05566, over 4648.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3131, pruned_loss=0.07234, over 965801.75 frames.], batch size: 11, lr: 5.94e-04
2022-05-28 23:29:07,897 INFO [train.py:761] (5/8) Epoch 21, batch 3350, loss[loss=0.2618, simple_loss=0.3441, pruned_loss=0.08978, over 4851.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3153, pruned_loss=0.07511, over 966060.31 frames.], batch size: 17, lr: 5.94e-04
2022-05-28 23:29:46,219 INFO [train.py:761] (5/8) Epoch 21, batch 3400, loss[loss=0.2621, simple_loss=0.3362, pruned_loss=0.094, over 4834.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3162, pruned_loss=0.0763, over 966550.76 frames.], batch size: 11, lr: 5.94e-04
2022-05-28 23:30:23,618 INFO [train.py:761] (5/8) Epoch 21, batch 3450, loss[loss=0.2522, simple_loss=0.3262, pruned_loss=0.08911, over 4720.00 frames.], tot_loss[loss=0.238, simple_loss=0.3193, pruned_loss=0.07832, over 966841.66 frames.], batch size: 13, lr: 5.94e-04
2022-05-28 23:31:01,658 INFO [train.py:761] (5/8) Epoch 21, batch 3500, loss[loss=0.2777, simple_loss=0.3393, pruned_loss=0.1081, over 4942.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3202, pruned_loss=0.07981, over 966983.86 frames.], batch size: 27, lr: 5.94e-04
2022-05-28 23:31:38,934 INFO [train.py:761] (5/8) Epoch 21, batch 3550, loss[loss=0.2511, simple_loss=0.3129, pruned_loss=0.09463, over 4741.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3217, pruned_loss=0.08178, over 966706.21 frames.], batch size: 11, lr: 5.94e-04
2022-05-28 23:32:16,782 INFO [train.py:761] (5/8) Epoch 21, batch 3600, loss[loss=0.2753, simple_loss=0.3374, pruned_loss=0.1066, over 4775.00 frames.], tot_loss[loss=0.2432, simple_loss=0.3214, pruned_loss=0.08248, over 967149.61 frames.], batch size: 13, lr: 5.94e-04
2022-05-28 23:32:54,853 INFO [train.py:761] (5/8) Epoch 21, batch 3650, loss[loss=0.2914, simple_loss=0.357, pruned_loss=0.1129, over 4967.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3216, pruned_loss=0.08293, over 966808.35 frames.], batch size: 45, lr: 5.94e-04
2022-05-28 23:33:32,909 INFO [train.py:761] (5/8) Epoch 21, batch 3700, loss[loss=0.3093, simple_loss=0.3804, pruned_loss=0.1191, over 4981.00 frames.], tot_loss[loss=0.2446, simple_loss=0.322, pruned_loss=0.0836, over 967173.78 frames.], batch size: 47, lr: 5.94e-04
2022-05-28 23:34:10,866 INFO [train.py:761] (5/8) Epoch 21, batch 3750, loss[loss=0.2268, simple_loss=0.2976, pruned_loss=0.07796, over 4820.00 frames.], tot_loss[loss=0.2464, simple_loss=0.3232, pruned_loss=0.08476, over 967364.42 frames.], batch size: 11, lr: 5.93e-04
2022-05-28 23:34:49,200 INFO [train.py:761] (5/8) Epoch 21, batch 3800, loss[loss=0.2272, simple_loss=0.3037, pruned_loss=0.07533, over 4926.00 frames.], tot_loss[loss=0.2465, simple_loss=0.3236, pruned_loss=0.08473, over 967421.36 frames.], batch size: 13, lr: 5.93e-04
2022-05-28 23:35:26,865 INFO [train.py:761] (5/8) Epoch 21, batch 3850, loss[loss=0.2253, simple_loss=0.3054, pruned_loss=0.07259, over 4921.00 frames.], tot_loss[loss=0.2451, simple_loss=0.3229, pruned_loss=0.08365, over 967293.69 frames.], batch size: 13, lr: 5.93e-04
2022-05-28 23:36:05,380 INFO [train.py:761] (5/8) Epoch 21, batch 3900, loss[loss=0.2418, simple_loss=0.3309, pruned_loss=0.07631, over 4876.00 frames.], tot_loss[loss=0.2467, simple_loss=0.3243, pruned_loss=0.08458, over 967169.43 frames.], batch size: 15, lr: 5.93e-04
2022-05-28 23:36:43,897 INFO [train.py:761] (5/8) Epoch 21, batch 3950, loss[loss=0.2837, simple_loss=0.3666, pruned_loss=0.1004, over 4851.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3224, pruned_loss=0.08399, over 967224.87 frames.], batch size: 26, lr: 5.93e-04
2022-05-28 23:37:22,077 INFO [train.py:761] (5/8) Epoch 21, batch 4000, loss[loss=0.2268, simple_loss=0.3176, pruned_loss=0.06801, over 4669.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3219, pruned_loss=0.08398, over 966791.27 frames.], batch size: 12, lr: 5.93e-04
2022-05-28 23:38:00,253 INFO [train.py:761] (5/8) Epoch 21, batch 4050, loss[loss=0.248, simple_loss=0.3285, pruned_loss=0.08378, over 4929.00 frames.], tot_loss[loss=0.246, simple_loss=0.3231, pruned_loss=0.08442, over 966351.18 frames.], batch size: 13, lr: 5.93e-04
2022-05-28 23:38:39,117 INFO [train.py:761] (5/8) Epoch 21, batch 4100, loss[loss=0.1784, simple_loss=0.2709, pruned_loss=0.04294, over 4731.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3227, pruned_loss=0.08415, over 965290.60 frames.], batch size: 12, lr: 5.93e-04
2022-05-28 23:39:17,300 INFO [train.py:761] (5/8) Epoch 21, batch 4150, loss[loss=0.2577, simple_loss=0.3327, pruned_loss=0.09136, over 4900.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3218, pruned_loss=0.08318, over 965680.67 frames.], batch size: 14, lr: 5.93e-04
2022-05-28 23:39:55,671 INFO [train.py:761] (5/8) Epoch 21, batch 4200, loss[loss=0.272, simple_loss=0.3453, pruned_loss=0.09935, over 4785.00 frames.], tot_loss[loss=0.2427, simple_loss=0.3204, pruned_loss=0.08251, over 966007.65 frames.], batch size: 14, lr: 5.92e-04
2022-05-28 23:40:33,489 INFO [train.py:761] (5/8) Epoch 21, batch 4250, loss[loss=0.2954, simple_loss=0.3548, pruned_loss=0.118, over 4975.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3216, pruned_loss=0.08409, over 966289.19 frames.], batch size: 50, lr: 5.92e-04
2022-05-28 23:41:12,319 INFO [train.py:761] (5/8) Epoch 21, batch 4300, loss[loss=0.2151, simple_loss=0.29, pruned_loss=0.07012, over 4893.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3228, pruned_loss=0.08521, over 966035.40 frames.], batch size: 12, lr: 5.92e-04
2022-05-28 23:41:50,175 INFO [train.py:761] (5/8) Epoch 21, batch 4350, loss[loss=0.215, simple_loss=0.3041, pruned_loss=0.06301, over 4718.00 frames.], tot_loss[loss=0.2465, simple_loss=0.3224, pruned_loss=0.08525, over 966793.96 frames.], batch size: 14, lr: 5.92e-04
2022-05-28 23:42:28,377 INFO [train.py:761] (5/8) Epoch 21, batch 4400, loss[loss=0.2701, simple_loss=0.3436, pruned_loss=0.09834, over 4884.00 frames.], tot_loss[loss=0.247, simple_loss=0.3234, pruned_loss=0.08529, over 967708.61 frames.], batch size: 15, lr: 5.92e-04
2022-05-28 23:43:05,733 INFO [train.py:761] (5/8) Epoch 21, batch 4450, loss[loss=0.2351, simple_loss=0.3162, pruned_loss=0.07696, over 4883.00 frames.], tot_loss[loss=0.246, simple_loss=0.3228, pruned_loss=0.08461, over 967152.49 frames.], batch size: 15, lr: 5.92e-04
2022-05-28 23:43:44,398 INFO [train.py:761] (5/8) Epoch 21, batch 4500, loss[loss=0.3538, simple_loss=0.3976, pruned_loss=0.155, over 4949.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3219, pruned_loss=0.08432, over 966729.78 frames.], batch size: 48, lr: 5.92e-04
2022-05-28 23:44:22,566 INFO [train.py:761] (5/8) Epoch 21, batch 4550, loss[loss=0.2915, simple_loss=0.3615, pruned_loss=0.1108, over 4787.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3221, pruned_loss=0.08372, over 965683.35 frames.], batch size: 16, lr: 5.92e-04
2022-05-28 23:45:07,667 INFO [train.py:761] (5/8) Epoch 21, batch 4600, loss[loss=0.2787, simple_loss=0.3592, pruned_loss=0.09908, over 4912.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3224, pruned_loss=0.08348, over 965376.98 frames.], batch size: 48, lr: 5.92e-04
2022-05-28 23:45:45,857 INFO [train.py:761] (5/8) Epoch 21, batch 4650, loss[loss=0.2256, simple_loss=0.3052, pruned_loss=0.07293, over 4731.00 frames.], tot_loss[loss=0.2446, simple_loss=0.3219, pruned_loss=0.08361, over 966797.24 frames.], batch size: 12, lr: 5.91e-04
2022-05-28 23:46:24,237 INFO [train.py:761] (5/8) Epoch 21, batch 4700, loss[loss=0.2916, simple_loss=0.3646, pruned_loss=0.1093, over 4935.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3214, pruned_loss=0.08374, over 965243.02 frames.], batch size: 26, lr: 5.91e-04
2022-05-28 23:47:02,520 INFO [train.py:761] (5/8) Epoch 21, batch 4750, loss[loss=0.2044, simple_loss=0.3041, pruned_loss=0.0523, over 4984.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3211, pruned_loss=0.08398, over 965385.15 frames.], batch size: 13, lr: 5.91e-04
2022-05-28 23:47:40,569 INFO [train.py:761] (5/8) Epoch 21, batch 4800, loss[loss=0.2358, simple_loss=0.3161, pruned_loss=0.07774, over 4915.00 frames.], tot_loss[loss=0.2443, simple_loss=0.3214, pruned_loss=0.08354, over 965603.59 frames.], batch size: 14, lr: 5.91e-04
2022-05-28 23:48:19,050 INFO [train.py:761] (5/8) Epoch 21, batch 4850, loss[loss=0.2283, simple_loss=0.2937, pruned_loss=0.08142, over 4792.00 frames.], tot_loss[loss=0.2454, simple_loss=0.3223, pruned_loss=0.08423, over 965711.59 frames.], batch size: 12, lr: 5.91e-04
2022-05-28 23:48:57,280 INFO [train.py:761] (5/8) Epoch 21, batch 4900, loss[loss=0.2431, simple_loss=0.3139, pruned_loss=0.0862, over 4727.00 frames.], tot_loss[loss=0.2432, simple_loss=0.3201, pruned_loss=0.08312, over 965220.71 frames.], batch size: 12, lr: 5.91e-04
2022-05-28 23:49:35,451 INFO [train.py:761] (5/8) Epoch 21, batch 4950, loss[loss=0.2486, simple_loss=0.3354, pruned_loss=0.08086, over 4851.00 frames.], tot_loss[loss=0.2413, simple_loss=0.3184, pruned_loss=0.0821, over 964788.59 frames.], batch size: 13, lr: 5.91e-04
2022-05-28 23:50:13,911 INFO [train.py:761] (5/8) Epoch 21, batch 5000, loss[loss=0.2662, simple_loss=0.3368, pruned_loss=0.0978, over 4721.00 frames.], tot_loss[loss=0.2405, simple_loss=0.3176, pruned_loss=0.0817, over 965103.16 frames.], batch size: 14, lr: 5.91e-04
2022-05-28 23:50:51,860 INFO [train.py:761] (5/8) Epoch 21, batch 5050, loss[loss=0.2799, simple_loss=0.3455, pruned_loss=0.1072, over 4768.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3175, pruned_loss=0.08107, over 964757.24 frames.], batch size: 20, lr: 5.91e-04
2022-05-28 23:51:30,442 INFO [train.py:761] (5/8) Epoch 21, batch 5100, loss[loss=0.283, simple_loss=0.3659, pruned_loss=0.1, over 4853.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3205, pruned_loss=0.08311, over 965263.43 frames.], batch size: 14, lr: 5.91e-04
2022-05-28 23:52:15,516 INFO [train.py:761] (5/8) Epoch 21, batch 5150, loss[loss=0.2642, simple_loss=0.3452, pruned_loss=0.09167, over 4901.00 frames.], tot_loss[loss=0.2436, simple_loss=0.3211, pruned_loss=0.08307, over 966022.49 frames.], batch size: 18, lr: 5.90e-04
2022-05-28 23:52:53,855 INFO [train.py:761] (5/8) Epoch 21, batch 5200, loss[loss=0.2477, simple_loss=0.3395, pruned_loss=0.07798, over 4788.00 frames.], tot_loss[loss=0.2418, simple_loss=0.3193, pruned_loss=0.08218, over 965822.35 frames.], batch size: 14, lr: 5.90e-04
2022-05-28 23:53:32,210 INFO [train.py:761] (5/8) Epoch 21, batch 5250, loss[loss=0.2913, simple_loss=0.3579, pruned_loss=0.1123, over 4972.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3192, pruned_loss=0.08254, over 965074.19 frames.], batch size: 49, lr: 5.90e-04
2022-05-28 23:54:11,001 INFO [train.py:761] (5/8) Epoch 21, batch 5300, loss[loss=0.3229, simple_loss=0.3928, pruned_loss=0.1265, over 4981.00 frames.], tot_loss[loss=0.2428, simple_loss=0.32, pruned_loss=0.08282, over 965706.99 frames.], batch size: 49, lr: 5.90e-04
2022-05-28 23:54:48,786 INFO [train.py:761] (5/8) Epoch 21, batch 5350, loss[loss=0.1897, simple_loss=0.2721, pruned_loss=0.05362, over 4729.00 frames.], tot_loss[loss=0.2413, simple_loss=0.319, pruned_loss=0.08186, over 964774.67 frames.], batch size: 12, lr: 5.90e-04
2022-05-28 23:55:27,239 INFO [train.py:761] (5/8) Epoch 21, batch 5400, loss[loss=0.2625, simple_loss=0.3505, pruned_loss=0.08723, over 4967.00 frames.], tot_loss[loss=0.2412, simple_loss=0.319, pruned_loss=0.08166, over 965446.75 frames.], batch size: 21, lr: 5.90e-04
2022-05-28 23:56:12,542 INFO [train.py:761] (5/8) Epoch 21, batch 5450, loss[loss=0.2278, simple_loss=0.2986, pruned_loss=0.07851, over 4738.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3195, pruned_loss=0.08173, over 965596.78 frames.], batch size: 11, lr: 5.90e-04
2022-05-28 23:56:57,755 INFO [train.py:761] (5/8) Epoch 21, batch 5500, loss[loss=0.2438, simple_loss=0.3119, pruned_loss=0.08786, over 4909.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3197, pruned_loss=0.08201, over 964587.35 frames.], batch size: 14, lr: 5.90e-04
2022-05-28 23:57:35,565 INFO [train.py:761] (5/8) Epoch 21, batch 5550, loss[loss=0.2423, simple_loss=0.315, pruned_loss=0.08483, over 4870.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3209, pruned_loss=0.0829, over 964876.84 frames.], batch size: 12, lr: 5.90e-04
2022-05-28 23:58:14,036 INFO [train.py:761] (5/8) Epoch 21, batch 5600, loss[loss=0.2383, simple_loss=0.3139, pruned_loss=0.08136, over 4793.00 frames.], tot_loss[loss=0.2414, simple_loss=0.3187, pruned_loss=0.08201, over 964274.93 frames.], batch size: 12, lr: 5.89e-04
2022-05-28 23:58:52,200 INFO [train.py:761] (5/8) Epoch 21, batch 5650, loss[loss=0.1913, simple_loss=0.2678, pruned_loss=0.05741, over 4976.00 frames.], tot_loss[loss=0.2411, simple_loss=0.3189, pruned_loss=0.08168, over 963556.45 frames.], batch size: 12, lr: 5.89e-04
2022-05-28 23:59:30,182 INFO [train.py:761] (5/8) Epoch 21, batch 5700, loss[loss=0.1946, simple_loss=0.2746, pruned_loss=0.05729, over 4850.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3197, pruned_loss=0.08189, over 964506.47 frames.], batch size: 13, lr: 5.89e-04
2022-05-29 00:00:15,897 INFO [train.py:761] (5/8) Epoch 21, batch 5750, loss[loss=0.2561, simple_loss=0.3302, pruned_loss=0.09099, over 4846.00 frames.], tot_loss[loss=0.2409, simple_loss=0.3186, pruned_loss=0.08155, over 964284.09 frames.], batch size: 14, lr: 5.89e-04
2022-05-29 00:00:54,875 INFO [train.py:761] (5/8) Epoch 21, batch 5800, loss[loss=0.1895, simple_loss=0.2742, pruned_loss=0.05241, over 4672.00 frames.], tot_loss[loss=0.2417, simple_loss=0.319, pruned_loss=0.08219, over 964232.35 frames.], batch size: 12, lr: 5.89e-04
2022-05-29 00:01:32,960 INFO [train.py:761] (5/8) Epoch 21, batch 5850, loss[loss=0.2584, simple_loss=0.3315, pruned_loss=0.09267, over 4786.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3179, pruned_loss=0.08173, over 963785.50 frames.], batch size: 20, lr: 5.89e-04
2022-05-29 00:02:11,373 INFO [train.py:761] (5/8) Epoch 21, batch 5900, loss[loss=0.2635, simple_loss=0.3443, pruned_loss=0.09136, over 4921.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3206, pruned_loss=0.08312, over 964466.27 frames.], batch size: 14, lr: 5.89e-04
2022-05-29 00:02:49,607 INFO [train.py:761] (5/8) Epoch 21, batch 5950, loss[loss=0.3144, simple_loss=0.3756, pruned_loss=0.1266, over 4896.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3217, pruned_loss=0.08436, over 965843.44 frames.], batch size: 18, lr: 5.89e-04
2022-05-29 00:03:28,119 INFO [train.py:761] (5/8) Epoch 21, batch 6000, loss[loss=0.2072, simple_loss=0.2874, pruned_loss=0.06351, over 4854.00 frames.], tot_loss[loss=0.2434, simple_loss=0.321, pruned_loss=0.08293, over 966576.68 frames.], batch size: 13, lr: 5.89e-04
2022-05-29 00:03:28,120 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 00:03:45,059 INFO [train.py:790] (5/8) Epoch 21, validation: loss=0.2017, simple_loss=0.3067, pruned_loss=0.04836, over 944034.00 frames.
2022-05-29 00:04:23,312 INFO [train.py:761] (5/8) Epoch 21, batch 6050, loss[loss=0.2108, simple_loss=0.2965, pruned_loss=0.06256, over 4992.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3195, pruned_loss=0.08174, over 968002.56 frames.], batch size: 11, lr: 5.89e-04
2022-05-29 00:05:02,154 INFO [train.py:761] (5/8) Epoch 21, batch 6100, loss[loss=0.216, simple_loss=0.2904, pruned_loss=0.07085, over 4920.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3212, pruned_loss=0.08253, over 967546.06 frames.], batch size: 13, lr: 5.88e-04
2022-05-29 00:05:41,191 INFO [train.py:761] (5/8) Epoch 21, batch 6150, loss[loss=0.227, simple_loss=0.3151, pruned_loss=0.06947, over 4883.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3217, pruned_loss=0.0825, over 967023.28 frames.], batch size: 15, lr: 5.88e-04
2022-05-29 00:06:19,234 INFO [train.py:761] (5/8) Epoch 21, batch 6200, loss[loss=0.2549, simple_loss=0.3407, pruned_loss=0.08461, over 4969.00 frames.], tot_loss[loss=0.2427, simple_loss=0.3214, pruned_loss=0.08198, over 967288.76 frames.], batch size: 15, lr: 5.88e-04
2022-05-29 00:06:57,686 INFO [train.py:761] (5/8) Epoch 21, batch 6250, loss[loss=0.2267, simple_loss=0.3178, pruned_loss=0.06782, over 4861.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3197, pruned_loss=0.08053, over 966589.06 frames.], batch size: 14, lr: 5.88e-04
2022-05-29 00:07:36,074 INFO [train.py:761] (5/8) Epoch 21, batch 6300, loss[loss=0.2529, simple_loss=0.3312, pruned_loss=0.08728, over 4809.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3214, pruned_loss=0.08162, over 966786.32 frames.], batch size: 16, lr: 5.88e-04
2022-05-29 00:08:14,226 INFO [train.py:761] (5/8) Epoch 21, batch 6350, loss[loss=0.2666, simple_loss=0.334, pruned_loss=0.09957, over 4834.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3206, pruned_loss=0.08144, over 966362.79 frames.], batch size: 26, lr: 5.88e-04
2022-05-29 00:08:52,316 INFO [train.py:761] (5/8) Epoch 21, batch 6400, loss[loss=0.1957, simple_loss=0.2841, pruned_loss=0.05365, over 4669.00 frames.], tot_loss[loss=0.2424, simple_loss=0.321, pruned_loss=0.0819, over 965930.84 frames.], batch size: 13, lr: 5.88e-04
2022-05-29 00:09:30,776 INFO [train.py:761] (5/8) Epoch 21, batch 6450, loss[loss=0.2674, simple_loss=0.3358, pruned_loss=0.09954, over 4660.00 frames.], tot_loss[loss=0.2425, simple_loss=0.3207, pruned_loss=0.08219, over 966179.85 frames.], batch size: 13, lr: 5.88e-04
2022-05-29 00:10:08,855 INFO [train.py:761] (5/8) Epoch 21, batch 6500, loss[loss=0.238, simple_loss=0.3301, pruned_loss=0.073, over 4782.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3197, pruned_loss=0.08187, over 966801.98 frames.], batch size: 20, lr: 5.88e-04
2022-05-29 00:10:54,544 INFO [train.py:761] (5/8) Epoch 21, batch 6550, loss[loss=0.1841, simple_loss=0.2517, pruned_loss=0.05823, over 4651.00 frames.], tot_loss[loss=0.2405, simple_loss=0.3182, pruned_loss=0.08138, over 966910.60 frames.], batch size: 11, lr: 5.88e-04
2022-05-29 00:11:32,939 INFO [train.py:761] (5/8) Epoch 21, batch 6600, loss[loss=0.2402, simple_loss=0.3262, pruned_loss=0.07706, over 4981.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3185, pruned_loss=0.0814, over 966038.47 frames.], batch size: 26, lr: 5.87e-04
2022-05-29 00:12:11,367 INFO [train.py:761] (5/8) Epoch 21, batch 6650, loss[loss=0.2447, simple_loss=0.3265, pruned_loss=0.08145, over 4928.00 frames.], tot_loss[loss=0.24, simple_loss=0.3176, pruned_loss=0.08122, over 966226.57 frames.], batch size: 13, lr: 5.87e-04
2022-05-29 00:12:50,266 INFO [train.py:761] (5/8) Epoch 21, batch 6700, loss[loss=0.2, simple_loss=0.2844, pruned_loss=0.05777, over 4802.00 frames.], tot_loss[loss=0.2408, simple_loss=0.3183, pruned_loss=0.08162, over 966167.01 frames.], batch size: 12, lr: 5.87e-04
2022-05-29 00:13:44,515 INFO [train.py:761] (5/8) Epoch 22, batch 0, loss[loss=0.2115, simple_loss=0.3106, pruned_loss=0.05615, over 4980.00 frames.], tot_loss[loss=0.2115, simple_loss=0.3106, pruned_loss=0.05615, over 4980.00 frames.], batch size: 15, lr: 5.87e-04
2022-05-29 00:14:22,887 INFO [train.py:761] (5/8) Epoch 22, batch 50, loss[loss=0.2638, simple_loss=0.3475, pruned_loss=0.09, over 4755.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3096, pruned_loss=0.06371, over 217620.02 frames.], batch size: 15, lr: 5.87e-04
2022-05-29 00:15:00,599 INFO [train.py:761] (5/8) Epoch 22, batch 100, loss[loss=0.3171, simple_loss=0.3923, pruned_loss=0.121, over 4890.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3115, pruned_loss=0.06548, over 383959.13 frames.], batch size: 43, lr: 5.87e-04
2022-05-29 00:15:38,939 INFO [train.py:761] (5/8) Epoch 22, batch 150, loss[loss=0.1987, simple_loss=0.278, pruned_loss=0.05964, over 4666.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3108, pruned_loss=0.06569, over 512521.93 frames.], batch size: 12, lr: 5.87e-04
2022-05-29 00:16:16,723 INFO [train.py:761] (5/8) Epoch 22, batch 200, loss[loss=0.225, simple_loss=0.314, pruned_loss=0.06799, over 4943.00 frames.], tot_loss[loss=0.2203, simple_loss=0.31, pruned_loss=0.06527, over 613044.61 frames.], batch size: 16, lr: 5.87e-04
2022-05-29 00:16:54,808 INFO [train.py:761] (5/8) Epoch 22, batch 250, loss[loss=0.2542, simple_loss=0.3458, pruned_loss=0.08125, over 4887.00 frames.], tot_loss[loss=0.2223, simple_loss=0.312, pruned_loss=0.06627, over 691418.88 frames.], batch size: 15, lr: 5.87e-04
2022-05-29 00:17:32,987 INFO [train.py:761] (5/8) Epoch 22, batch 300, loss[loss=0.2502, simple_loss=0.3269, pruned_loss=0.08675, over 4853.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3105, pruned_loss=0.06634, over 753118.67 frames.], batch size: 13, lr: 5.86e-04
2022-05-29 00:18:11,276 INFO [train.py:761] (5/8) Epoch 22, batch 350, loss[loss=0.1501, simple_loss=0.25, pruned_loss=0.0251, over 4964.00 frames.], tot_loss[loss=0.22, simple_loss=0.3093, pruned_loss=0.06541, over 800988.90 frames.], batch size: 12, lr: 5.86e-04
2022-05-29 00:18:48,993 INFO [train.py:761] (5/8) Epoch 22, batch 400, loss[loss=0.2187, simple_loss=0.3097, pruned_loss=0.06378, over 4765.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3081, pruned_loss=0.0645, over 837418.91 frames.], batch size: 20, lr: 5.86e-04
2022-05-29 00:19:27,025 INFO [train.py:761] (5/8) Epoch 22, batch 450, loss[loss=0.18, simple_loss=0.2918, pruned_loss=0.03413, over 4852.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3082, pruned_loss=0.06377, over 866539.89 frames.], batch size: 14, lr: 5.86e-04
2022-05-29 00:20:04,480 INFO [train.py:761] (5/8) Epoch 22, batch 500, loss[loss=0.2032, simple_loss=0.298, pruned_loss=0.05418, over 4808.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3086, pruned_loss=0.06332, over 889339.04 frames.], batch size: 12, lr: 5.86e-04
2022-05-29 00:20:42,802 INFO [train.py:761] (5/8) Epoch 22, batch 550, loss[loss=0.2095, simple_loss=0.2838, pruned_loss=0.06767, over 4938.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3075, pruned_loss=0.06281, over 907491.81 frames.], batch size: 11, lr: 5.86e-04
2022-05-29 00:21:20,699 INFO [train.py:761] (5/8) Epoch 22, batch 600, loss[loss=0.2039, simple_loss=0.2772, pruned_loss=0.06524, over 4804.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3078, pruned_loss=0.0629, over 920240.88 frames.], batch size: 12, lr: 5.86e-04
2022-05-29 00:21:59,448 INFO [train.py:761] (5/8) Epoch 22, batch 650, loss[loss=0.2022, simple_loss=0.3075, pruned_loss=0.04846, over 4790.00 frames.], tot_loss[loss=0.2168, simple_loss=0.307, pruned_loss=0.06328, over 929998.59 frames.], batch size: 14, lr: 5.86e-04
2022-05-29 00:22:37,388 INFO [train.py:761] (5/8) Epoch 22, batch 700, loss[loss=0.204, simple_loss=0.2931, pruned_loss=0.05741, over 4728.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3077, pruned_loss=0.06351, over 938070.15 frames.], batch size: 12, lr: 5.86e-04
2022-05-29 00:23:15,136 INFO [train.py:761] (5/8) Epoch 22, batch 750, loss[loss=0.23, simple_loss=0.323, pruned_loss=0.06852, over 4728.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3085, pruned_loss=0.0639, over 944434.68 frames.], batch size: 12, lr: 5.86e-04
2022-05-29 00:23:53,004 INFO [train.py:761] (5/8) Epoch 22, batch 800, loss[loss=0.2382, simple_loss=0.3331, pruned_loss=0.07168, over 4801.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3075, pruned_loss=0.06381, over 948462.80 frames.], batch size: 16, lr: 5.85e-04
2022-05-29 00:24:31,420 INFO [train.py:761] (5/8) Epoch 22, batch 850, loss[loss=0.165, simple_loss=0.2642, pruned_loss=0.03291, over 4636.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3099, pruned_loss=0.06571, over 952984.22 frames.], batch size: 11, lr: 5.85e-04
2022-05-29 00:25:09,323 INFO [train.py:761] (5/8) Epoch 22, batch 900, loss[loss=0.2567, simple_loss=0.3433, pruned_loss=0.08504, over 4943.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3123, pruned_loss=0.06715, over 957263.98 frames.], batch size: 21, lr: 5.85e-04
2022-05-29 00:25:47,506 INFO [train.py:761] (5/8) Epoch 22, batch 950, loss[loss=0.2479, simple_loss=0.3238, pruned_loss=0.086, over 4993.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3132, pruned_loss=0.0676, over 958630.32 frames.], batch size: 13, lr: 5.85e-04
2022-05-29 00:26:26,298 INFO [train.py:761] (5/8) Epoch 22, batch 1000, loss[loss=0.1808, simple_loss=0.2805, pruned_loss=0.04049, over 4799.00 frames.], tot_loss[loss=0.224, simple_loss=0.3134, pruned_loss=0.06727, over 961328.52 frames.], batch size: 12, lr: 5.85e-04
2022-05-29 00:27:04,333 INFO [train.py:761] (5/8) Epoch 22, batch 1050, loss[loss=0.1943, simple_loss=0.2929, pruned_loss=0.04784, over 4959.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3135, pruned_loss=0.0675, over 963242.23 frames.], batch size: 21, lr: 5.85e-04
2022-05-29 00:27:42,538 INFO [train.py:761] (5/8) Epoch 22, batch 1100, loss[loss=0.259, simple_loss=0.3463, pruned_loss=0.08583, over 4888.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3139, pruned_loss=0.06822, over 964519.20 frames.], batch size: 18, lr: 5.85e-04
2022-05-29 00:28:20,290 INFO [train.py:761] (5/8) Epoch 22, batch 1150, loss[loss=0.1763, simple_loss=0.2595, pruned_loss=0.04659, over 4978.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3148, pruned_loss=0.06779, over 964855.21 frames.], batch size: 12, lr: 5.85e-04
2022-05-29 00:28:57,906 INFO [train.py:761] (5/8) Epoch 22, batch 1200, loss[loss=0.2145, simple_loss=0.3003, pruned_loss=0.06439, over 4718.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3135, pruned_loss=0.06701, over 966168.93 frames.], batch size: 11, lr: 5.85e-04
2022-05-29 00:29:36,027 INFO [train.py:761] (5/8) Epoch 22, batch 1250, loss[loss=0.2086, simple_loss=0.3178, pruned_loss=0.04975, over 4974.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3126, pruned_loss=0.06658, over 965830.60 frames.], batch size: 16, lr: 5.85e-04
2022-05-29 00:30:14,494 INFO [train.py:761] (5/8) Epoch 22, batch 1300, loss[loss=0.2587, simple_loss=0.3528, pruned_loss=0.08229, over 4976.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3132, pruned_loss=0.06715, over 966272.31 frames.], batch size: 46, lr: 5.84e-04
2022-05-29 00:30:52,599 INFO [train.py:761] (5/8) Epoch 22, batch 1350, loss[loss=0.1946, simple_loss=0.2787, pruned_loss=0.05528, over 4819.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3133, pruned_loss=0.06716, over 966504.05 frames.], batch size: 11, lr: 5.84e-04
2022-05-29 00:31:29,875 INFO [train.py:761] (5/8) Epoch 22, batch 1400, loss[loss=0.1976, simple_loss=0.298, pruned_loss=0.04862, over 4670.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3123, pruned_loss=0.0665, over 965563.07 frames.], batch size: 13, lr: 5.84e-04
2022-05-29 00:32:07,893 INFO [train.py:761] (5/8) Epoch 22, batch 1450, loss[loss=0.2515, simple_loss=0.3307, pruned_loss=0.08612, over 4677.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3117, pruned_loss=0.06637, over 965234.36 frames.], batch size: 13, lr: 5.84e-04
2022-05-29 00:32:45,987 INFO [train.py:761] (5/8) Epoch 22, batch 1500, loss[loss=0.2114, simple_loss=0.3087, pruned_loss=0.05701, over 4794.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3124, pruned_loss=0.06629, over 964759.66 frames.], batch size: 16, lr: 5.84e-04
2022-05-29 00:33:24,334 INFO [train.py:761] (5/8) Epoch 22, batch 1550, loss[loss=0.2065, simple_loss=0.2949, pruned_loss=0.059, over 4980.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3121, pruned_loss=0.06655, over 965130.73 frames.], batch size: 12, lr: 5.84e-04
2022-05-29 00:34:02,407 INFO [train.py:761] (5/8) Epoch 22, batch 1600, loss[loss=0.2404, simple_loss=0.331, pruned_loss=0.07493, over 4792.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3123, pruned_loss=0.06692, over 965676.86 frames.], batch size: 13, lr: 5.84e-04
2022-05-29 00:34:40,457 INFO [train.py:761] (5/8) Epoch 22, batch 1650, loss[loss=0.2125, simple_loss=0.3189, pruned_loss=0.05301, over 4990.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3114, pruned_loss=0.06661, over 966344.80 frames.], batch size: 15, lr: 5.84e-04
2022-05-29 00:35:18,106 INFO [train.py:761] (5/8) Epoch 22, batch 1700, loss[loss=0.2597, simple_loss=0.3606, pruned_loss=0.07938, over 4720.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3115, pruned_loss=0.06659, over 966131.07 frames.], batch size: 14, lr: 5.84e-04
2022-05-29 00:35:55,884 INFO [train.py:761] (5/8) Epoch 22, batch 1750, loss[loss=0.2481, simple_loss=0.3401, pruned_loss=0.07805, over 4788.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3115, pruned_loss=0.06647, over 966478.57 frames.], batch size: 16, lr: 5.84e-04
2022-05-29 00:36:34,180 INFO [train.py:761] (5/8) Epoch 22, batch 1800, loss[loss=0.2206, simple_loss=0.3245, pruned_loss=0.05835, over 4900.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3111, pruned_loss=0.06615, over 965937.24 frames.], batch size: 18, lr: 5.83e-04
2022-05-29 00:37:11,855 INFO [train.py:761] (5/8) Epoch 22, batch 1850, loss[loss=0.1853, simple_loss=0.2627, pruned_loss=0.05392, over 4972.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3103, pruned_loss=0.06558, over 965864.10 frames.], batch size: 12, lr: 5.83e-04
2022-05-29 00:37:50,076 INFO [train.py:761] (5/8) Epoch 22, batch 1900, loss[loss=0.2627, simple_loss=0.3443, pruned_loss=0.09056, over 4942.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3102, pruned_loss=0.06581, over 966250.83 frames.], batch size: 26, lr: 5.83e-04
2022-05-29 00:38:28,178 INFO [train.py:761] (5/8) Epoch 22, batch 1950, loss[loss=0.2374, simple_loss=0.3345, pruned_loss=0.07012, over 4965.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3111, pruned_loss=0.06619, over 967738.82 frames.], batch size: 16, lr: 5.83e-04
2022-05-29 00:39:05,735 INFO [train.py:761] (5/8) Epoch 22, batch 2000, loss[loss=0.2206, simple_loss=0.3237, pruned_loss=0.05872, over 4971.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3122, pruned_loss=0.06657, over 968960.03 frames.], batch size: 15, lr: 5.83e-04
2022-05-29 00:39:43,391 INFO [train.py:761] (5/8) Epoch 22, batch 2050, loss[loss=0.174, simple_loss=0.2579, pruned_loss=0.04505, over 4634.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3109, pruned_loss=0.06582, over 968676.83 frames.], batch size: 11, lr: 5.83e-04
2022-05-29 00:40:21,339 INFO [train.py:761] (5/8) Epoch 22, batch 2100, loss[loss=0.2455, simple_loss=0.3241, pruned_loss=0.08347, over 4884.00 frames.], tot_loss[loss=0.221, simple_loss=0.3105, pruned_loss=0.0657, over 968174.12 frames.], batch size: 15, lr: 5.83e-04
2022-05-29 00:40:59,367 INFO [train.py:761] (5/8) Epoch 22, batch 2150, loss[loss=0.2387, simple_loss=0.3315, pruned_loss=0.07293, over 4856.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3108, pruned_loss=0.06546, over 967784.74 frames.], batch size: 20, lr: 5.83e-04
2022-05-29 00:41:37,376 INFO [train.py:761] (5/8) Epoch 22, batch 2200, loss[loss=0.1677, simple_loss=0.2613, pruned_loss=0.03703, over 4888.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3102, pruned_loss=0.06525, over 967552.28 frames.], batch size: 12, lr: 5.83e-04
2022-05-29 00:42:15,281 INFO [train.py:761] (5/8) Epoch 22, batch 2250, loss[loss=0.2273, simple_loss=0.3287, pruned_loss=0.063, over 4716.00 frames.], tot_loss[loss=0.2206, simple_loss=0.311, pruned_loss=0.06508, over 966943.80 frames.], batch size: 13, lr: 5.82e-04
2022-05-29 00:42:53,343 INFO [train.py:761] (5/8) Epoch 22, batch 2300, loss[loss=0.2337, simple_loss=0.3359, pruned_loss=0.06578, over 4890.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3112, pruned_loss=0.06493, over 967424.94 frames.], batch size: 15, lr: 5.82e-04
2022-05-29 00:43:34,343 INFO [train.py:761] (5/8) Epoch 22, batch 2350, loss[loss=0.1664, simple_loss=0.2656, pruned_loss=0.03354, over 4734.00 frames.], tot_loss[loss=0.2212, simple_loss=0.312, pruned_loss=0.06518, over 966361.09 frames.], batch size: 11, lr: 5.82e-04
2022-05-29 00:44:12,385 INFO [train.py:761] (5/8) Epoch 22, batch 2400, loss[loss=0.2455, simple_loss=0.3377, pruned_loss=0.07669, over 4959.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3109, pruned_loss=0.06497, over 966396.03 frames.], batch size: 49, lr: 5.82e-04
2022-05-29 00:44:50,257 INFO [train.py:761] (5/8) Epoch 22, batch 2450, loss[loss=0.2274, simple_loss=0.3107, pruned_loss=0.072, over 4911.00 frames.], tot_loss[loss=0.22, simple_loss=0.3101, pruned_loss=0.06492, over 965622.05 frames.], batch size: 14, lr: 5.82e-04
2022-05-29 00:45:28,217 INFO [train.py:761] (5/8) Epoch 22, batch 2500, loss[loss=0.2002, simple_loss=0.291, pruned_loss=0.05473, over 4723.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3098, pruned_loss=0.06465, over 965569.96 frames.], batch size: 11, lr: 5.82e-04
2022-05-29 00:46:06,453 INFO [train.py:761] (5/8) Epoch 22, batch 2550, loss[loss=0.197, simple_loss=0.283, pruned_loss=0.05551, over 4799.00 frames.], tot_loss[loss=0.2181, simple_loss=0.309, pruned_loss=0.06359, over 966327.91 frames.], batch size: 13, lr: 5.82e-04
2022-05-29 00:46:43,950 INFO [train.py:761] (5/8) Epoch 22, batch 2600, loss[loss=0.2162, simple_loss=0.3127, pruned_loss=0.0599, over 4805.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3089, pruned_loss=0.06321, over 965617.57 frames.], batch size: 20, lr: 5.82e-04
2022-05-29 00:47:22,094 INFO [train.py:761] (5/8) Epoch 22, batch 2650, loss[loss=0.236, simple_loss=0.3248, pruned_loss=0.07363, over 4666.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3086, pruned_loss=0.06357, over 965471.31 frames.], batch size: 13, lr: 5.82e-04
2022-05-29 00:48:00,465 INFO [train.py:761] (5/8) Epoch 22, batch 2700, loss[loss=0.2057, simple_loss=0.3126, pruned_loss=0.04945, over 4852.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3087, pruned_loss=0.06355, over 966287.52 frames.], batch size: 14, lr: 5.82e-04
2022-05-29 00:48:38,272 INFO [train.py:761] (5/8) Epoch 22, batch 2750, loss[loss=0.2396, simple_loss=0.346, pruned_loss=0.0666, over 4815.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3089, pruned_loss=0.0633, over 966572.28 frames.], batch size: 16, lr: 5.81e-04
2022-05-29 00:49:15,945 INFO [train.py:761] (5/8) Epoch 22, batch 2800, loss[loss=0.2251, simple_loss=0.3124, pruned_loss=0.06888, over 4821.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3089, pruned_loss=0.06372, over 966121.72 frames.], batch size: 11, lr: 5.81e-04
2022-05-29 00:49:53,965 INFO [train.py:761] (5/8) Epoch 22, batch 2850, loss[loss=0.2584, simple_loss=0.3427, pruned_loss=0.0871, over 4889.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3102, pruned_loss=0.06522, over 965338.71 frames.], batch size: 46, lr: 5.81e-04
2022-05-29 00:50:31,965 INFO [train.py:761] (5/8) Epoch 22, batch 2900, loss[loss=0.2246, simple_loss=0.3082, pruned_loss=0.0705, over 4787.00 frames.], tot_loss[loss=0.2201, simple_loss=0.3099, pruned_loss=0.06514, over 965946.72 frames.], batch size: 13, lr: 5.81e-04
2022-05-29 00:51:10,178 INFO [train.py:761] (5/8) Epoch 22, batch 2950, loss[loss=0.1953, simple_loss=0.2946, pruned_loss=0.04796, over 4851.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3105, pruned_loss=0.06512, over 966990.64 frames.], batch size: 14, lr: 5.81e-04
2022-05-29 00:51:48,201 INFO [train.py:761] (5/8) Epoch 22, batch 3000, loss[loss=0.23, simple_loss=0.3212, pruned_loss=0.06939, over 4885.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3097, pruned_loss=0.06439, over 967715.80 frames.], batch size: 15, lr: 5.81e-04
2022-05-29 00:51:48,201 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 00:51:58,458 INFO [train.py:790] (5/8) Epoch 22, validation: loss=0.2084, simple_loss=0.3096, pruned_loss=0.0536, over 944034.00 frames.
2022-05-29 00:52:37,008 INFO [train.py:761] (5/8) Epoch 22, batch 3050, loss[loss=0.2389, simple_loss=0.3241, pruned_loss=0.07688, over 4980.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3103, pruned_loss=0.06444, over 967234.86 frames.], batch size: 15, lr: 5.81e-04
2022-05-29 00:53:15,120 INFO [train.py:761] (5/8) Epoch 22, batch 3100, loss[loss=0.247, simple_loss=0.3435, pruned_loss=0.07529, over 4811.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3107, pruned_loss=0.06538, over 966593.89 frames.], batch size: 20, lr: 5.81e-04
2022-05-29 00:53:53,414 INFO [train.py:761] (5/8) Epoch 22, batch 3150, loss[loss=0.2542, simple_loss=0.3461, pruned_loss=0.08116, over 4720.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3133, pruned_loss=0.06751, over 966376.20 frames.], batch size: 14, lr: 5.81e-04
2022-05-29 00:54:31,237 INFO [train.py:761] (5/8) Epoch 22, batch 3200, loss[loss=0.224, simple_loss=0.3024, pruned_loss=0.07283, over 4783.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3144, pruned_loss=0.06942, over 965857.59 frames.], batch size: 13, lr: 5.81e-04
2022-05-29 00:55:09,308 INFO [train.py:761] (5/8) Epoch 22, batch 3250, loss[loss=0.2307, simple_loss=0.3054, pruned_loss=0.07804, over 4734.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3168, pruned_loss=0.07227, over 966026.88 frames.], batch size: 11, lr: 5.80e-04
2022-05-29 00:55:47,744 INFO [train.py:761] (5/8) Epoch 22, batch 3300, loss[loss=0.2063, simple_loss=0.2727, pruned_loss=0.06994, over 4551.00 frames.], tot_loss[loss=0.23, simple_loss=0.3149, pruned_loss=0.07254, over 964779.27 frames.], batch size: 10, lr: 5.80e-04
2022-05-29 00:56:25,636 INFO [train.py:761] (5/8) Epoch 22, batch 3350, loss[loss=0.2722, simple_loss=0.3528, pruned_loss=0.09577, over 4719.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3159, pruned_loss=0.07491, over 963989.67 frames.], batch size: 14, lr: 5.80e-04
2022-05-29 00:57:03,379 INFO [train.py:761] (5/8) Epoch 22, batch 3400, loss[loss=0.2525, simple_loss=0.3281, pruned_loss=0.08842, over 4986.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3165, pruned_loss=0.07612, over 963969.57 frames.], batch size: 21, lr: 5.80e-04
2022-05-29 00:57:41,577 INFO [train.py:761] (5/8) Epoch 22, batch 3450, loss[loss=0.2449, simple_loss=0.3109, pruned_loss=0.08947, over 4631.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3167, pruned_loss=0.07677, over 964345.37 frames.], batch size: 11, lr: 5.80e-04
2022-05-29 00:58:19,563 INFO [train.py:761] (5/8) Epoch 22, batch 3500, loss[loss=0.2229, simple_loss=0.3015, pruned_loss=0.07212, over 4896.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3165, pruned_loss=0.07707, over 964166.08 frames.], batch size: 12, lr: 5.80e-04
2022-05-29 00:58:57,926 INFO [train.py:761] (5/8) Epoch 22, batch 3550, loss[loss=0.2335, simple_loss=0.3193, pruned_loss=0.07387, over 4771.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3173, pruned_loss=0.07874, over 965554.36 frames.], batch size: 15, lr: 5.80e-04
2022-05-29 00:59:36,184 INFO [train.py:761] (5/8) Epoch 22, batch 3600, loss[loss=0.2113, simple_loss=0.3038, pruned_loss=0.05937, over 4777.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3175, pruned_loss=0.07916, over 965761.48 frames.], batch size: 13, lr: 5.80e-04
2022-05-29 01:00:14,389 INFO [train.py:761] (5/8) Epoch 22, batch 3650, loss[loss=0.214, simple_loss=0.3093, pruned_loss=0.05938, over 4778.00 frames.], tot_loss[loss=0.2391, simple_loss=0.3185, pruned_loss=0.07989, over 965729.23 frames.], batch size: 13, lr: 5.80e-04
2022-05-29 01:00:52,338 INFO [train.py:761] (5/8) Epoch 22, batch 3700, loss[loss=0.2509, simple_loss=0.3266, pruned_loss=0.08755, over 4736.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3189, pruned_loss=0.08071, over 964684.31 frames.], batch size: 13, lr: 5.80e-04
2022-05-29 01:01:30,348 INFO [train.py:761] (5/8) Epoch 22, batch 3750, loss[loss=0.2358, simple_loss=0.3095, pruned_loss=0.08101, over 4972.00 frames.], tot_loss[loss=0.2416, simple_loss=0.32, pruned_loss=0.08156, over 966036.91 frames.], batch size: 12, lr: 5.79e-04
2022-05-29 01:02:08,455 INFO [train.py:761] (5/8) Epoch 22, batch 3800, loss[loss=0.2679, simple_loss=0.3361, pruned_loss=0.09982, over 4951.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3201, pruned_loss=0.08208, over 966231.42 frames.], batch size: 16, lr: 5.79e-04
2022-05-29 01:02:46,730 INFO [train.py:761] (5/8) Epoch 22, batch 3850, loss[loss=0.3462, simple_loss=0.395, pruned_loss=0.1488, over 4922.00 frames.], tot_loss[loss=0.2427, simple_loss=0.3206, pruned_loss=0.0824, over 967087.88 frames.], batch size: 47, lr: 5.79e-04
2022-05-29 01:03:24,627 INFO [train.py:761] (5/8) Epoch 22, batch 3900, loss[loss=0.2376, simple_loss=0.3215, pruned_loss=0.07681, over 4985.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3208, pruned_loss=0.08187, over 967054.42 frames.], batch size: 13, lr: 5.79e-04
2022-05-29 01:04:02,985 INFO [train.py:761] (5/8) Epoch 22, batch 3950, loss[loss=0.3136, simple_loss=0.3781, pruned_loss=0.1246, over 4949.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3221, pruned_loss=0.08265, over 967219.61 frames.], batch size: 50, lr: 5.79e-04
2022-05-29 01:04:40,783 INFO [train.py:761] (5/8) Epoch 22, batch 4000, loss[loss=0.2116, simple_loss=0.2887, pruned_loss=0.0673, over 4732.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3208, pruned_loss=0.08239, over 967905.18 frames.], batch size: 12, lr: 5.79e-04
2022-05-29 01:05:19,249 INFO [train.py:761] (5/8) Epoch 22, batch 4050, loss[loss=0.1871, simple_loss=0.2758, pruned_loss=0.04921, over 4809.00 frames.], tot_loss[loss=0.2413, simple_loss=0.3192, pruned_loss=0.08168, over 967153.65 frames.], batch size: 12, lr: 5.79e-04
2022-05-29 01:05:56,780 INFO [train.py:761] (5/8) Epoch 22, batch 4100, loss[loss=0.269, simple_loss=0.3421, pruned_loss=0.09792, over 4954.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3186, pruned_loss=0.08194, over 967194.34 frames.], batch size: 16, lr: 5.79e-04
2022-05-29 01:06:34,930 INFO [train.py:761] (5/8) Epoch 22, batch 4150, loss[loss=0.2266, simple_loss=0.306, pruned_loss=0.07364, over 4928.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3191, pruned_loss=0.08305, over 967711.76 frames.], batch size: 13, lr: 5.79e-04
2022-05-29 01:07:13,685 INFO [train.py:761] (5/8) Epoch 22, batch 4200, loss[loss=0.2678, simple_loss=0.3517, pruned_loss=0.09195, over 4887.00 frames.], tot_loss[loss=0.2405, simple_loss=0.3178, pruned_loss=0.08157, over 966908.59 frames.], batch size: 15, lr: 5.79e-04
2022-05-29 01:07:51,696 INFO [train.py:761] (5/8) Epoch 22, batch 4250, loss[loss=0.1914, simple_loss=0.2644, pruned_loss=0.05918, over 4656.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3155, pruned_loss=0.07987, over 965820.24 frames.], batch size: 12, lr: 5.78e-04
2022-05-29 01:08:29,876 INFO [train.py:761] (5/8) Epoch 22, batch 4300, loss[loss=0.2377, simple_loss=0.3089, pruned_loss=0.08324, over 4990.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3147, pruned_loss=0.07932, over 965787.27 frames.], batch size: 13, lr: 5.78e-04
2022-05-29 01:09:07,870 INFO [train.py:761] (5/8) Epoch 22, batch 4350, loss[loss=0.2331, simple_loss=0.3277, pruned_loss=0.06931, over 4852.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3169, pruned_loss=0.08015, over 966781.34 frames.], batch size: 14, lr: 5.78e-04
2022-05-29 01:09:45,989 INFO [train.py:761] (5/8) Epoch 22, batch 4400, loss[loss=0.2908, simple_loss=0.3659, pruned_loss=0.1078, over 4880.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3168, pruned_loss=0.08022, over 966128.98 frames.], batch size: 18, lr: 5.78e-04
2022-05-29 01:10:24,417 INFO [train.py:761] (5/8) Epoch 22, batch 4450, loss[loss=0.205, simple_loss=0.2877, pruned_loss=0.06113, over 4806.00 frames.], tot_loss[loss=0.239, simple_loss=0.3169, pruned_loss=0.08055, over 965498.47 frames.], batch size: 12, lr: 5.78e-04
2022-05-29 01:11:02,564 INFO [train.py:761] (5/8) Epoch 22, batch 4500, loss[loss=0.2522, simple_loss=0.3382, pruned_loss=0.0831, over 4792.00 frames.], tot_loss[loss=0.2388, simple_loss=0.317, pruned_loss=0.0803, over 964973.14 frames.], batch size: 16, lr: 5.78e-04
2022-05-29 01:11:41,054 INFO [train.py:761] (5/8) Epoch 22, batch 4550, loss[loss=0.2737, simple_loss=0.342, pruned_loss=0.1027, over 4771.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3174, pruned_loss=0.0798, over 964726.36 frames.], batch size: 20, lr: 5.78e-04
2022-05-29 01:12:19,053 INFO [train.py:761] (5/8) Epoch 22, batch 4600, loss[loss=0.235, simple_loss=0.3089, pruned_loss=0.08053, over 4881.00 frames.], tot_loss[loss=0.2394, simple_loss=0.3184, pruned_loss=0.08023, over 965187.11 frames.], batch size: 12, lr: 5.78e-04
2022-05-29 01:12:57,321 INFO [train.py:761] (5/8) Epoch 22, batch 4650, loss[loss=0.2104, simple_loss=0.2993, pruned_loss=0.06079, over 4741.00 frames.], tot_loss[loss=0.2406, simple_loss=0.3194, pruned_loss=0.08092, over 965049.02 frames.], batch size: 13, lr: 5.78e-04
2022-05-29 01:13:35,685 INFO [train.py:761] (5/8) Epoch 22, batch 4700, loss[loss=0.2099, simple_loss=0.2892, pruned_loss=0.06533, over 4794.00 frames.], tot_loss[loss=0.2418, simple_loss=0.3202, pruned_loss=0.0817, over 965795.38 frames.], batch size: 13, lr: 5.78e-04
2022-05-29 01:14:13,840 INFO [train.py:761] (5/8) Epoch 22, batch 4750, loss[loss=0.212, simple_loss=0.293, pruned_loss=0.06557, over 4853.00 frames.], tot_loss[loss=0.2438, simple_loss=0.3217, pruned_loss=0.08293, over 966214.18 frames.], batch size: 13, lr: 5.77e-04
2022-05-29 01:14:51,583 INFO [train.py:761] (5/8) Epoch 22, batch 4800, loss[loss=0.3008, simple_loss=0.3634, pruned_loss=0.1191, over 4968.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3206, pruned_loss=0.08314, over 966293.98 frames.], batch size: 48, lr: 5.77e-04
2022-05-29 01:15:30,152 INFO [train.py:761] (5/8) Epoch 22, batch 4850, loss[loss=0.2228, simple_loss=0.305, pruned_loss=0.07025, over 4783.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3188, pruned_loss=0.08244, over 965965.62 frames.], batch size: 13, lr: 5.77e-04
2022-05-29 01:16:08,366 INFO [train.py:761] (5/8) Epoch 22, batch 4900, loss[loss=0.2323, simple_loss=0.2986, pruned_loss=0.08296, over 4672.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3182, pruned_loss=0.08282, over 966802.23 frames.], batch size: 13, lr: 5.77e-04
2022-05-29 01:16:46,399 INFO [train.py:761] (5/8) Epoch 22, batch 4950, loss[loss=0.2382, simple_loss=0.3259, pruned_loss=0.07522, over 4781.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3188, pruned_loss=0.08275, over 967849.72 frames.], batch size: 14, lr: 5.77e-04
2022-05-29 01:17:24,799 INFO [train.py:761] (5/8) Epoch 22, batch 5000, loss[loss=0.2289, simple_loss=0.3141, pruned_loss=0.07187, over 4892.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3188, pruned_loss=0.08289, over 967450.26 frames.], batch size: 15, lr: 5.77e-04
2022-05-29 01:18:03,037 INFO [train.py:761] (5/8) Epoch 22, batch 5050, loss[loss=0.2456, simple_loss=0.3241, pruned_loss=0.08358, over 4781.00 frames.], tot_loss[loss=0.2418, simple_loss=0.3192, pruned_loss=0.08223, over 966648.83 frames.], batch size: 14, lr: 5.77e-04
2022-05-29 01:18:41,090 INFO [train.py:761] (5/8) Epoch 22, batch 5100, loss[loss=0.1912, simple_loss=0.2654, pruned_loss=0.0585, over 4921.00 frames.], tot_loss[loss=0.2408, simple_loss=0.3186, pruned_loss=0.08153, over 966832.69 frames.], batch size: 13, lr: 5.77e-04
2022-05-29 01:19:19,363 INFO [train.py:761] (5/8) Epoch 22, batch 5150, loss[loss=0.2028, simple_loss=0.2911, pruned_loss=0.05722, over 4914.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3199, pruned_loss=0.08195, over 966999.27 frames.], batch size: 13, lr: 5.77e-04
2022-05-29 01:19:57,456 INFO [train.py:761] (5/8) Epoch 22, batch 5200, loss[loss=0.2244, simple_loss=0.3034, pruned_loss=0.07269, over 4734.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3202, pruned_loss=0.08275, over 967719.45 frames.], batch size: 12, lr: 5.77e-04
2022-05-29 01:20:35,825 INFO [train.py:761] (5/8) Epoch 22, batch 5250, loss[loss=0.1786, simple_loss=0.255, pruned_loss=0.05111, over 4888.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3194, pruned_loss=0.08184, over 966786.63 frames.], batch size: 12, lr: 5.77e-04
2022-05-29 01:21:14,272 INFO [train.py:761] (5/8) Epoch 22, batch 5300, loss[loss=0.2005, simple_loss=0.2802, pruned_loss=0.06038, over 4732.00 frames.], tot_loss[loss=0.2414, simple_loss=0.3192, pruned_loss=0.08177, over 966651.40 frames.], batch size: 11, lr: 5.76e-04
2022-05-29 01:21:52,590 INFO [train.py:761] (5/8) Epoch 22, batch 5350, loss[loss=0.2966, simple_loss=0.3676, pruned_loss=0.1128, over 4945.00 frames.], tot_loss[loss=0.2413, simple_loss=0.3192, pruned_loss=0.08167, over 965704.02 frames.], batch size: 26, lr: 5.76e-04
2022-05-29 01:22:31,331 INFO [train.py:761] (5/8) Epoch 22, batch 5400, loss[loss=0.2356, simple_loss=0.3289, pruned_loss=0.07118, over 4813.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3195, pruned_loss=0.08097, over 965808.40 frames.], batch size: 16, lr: 5.76e-04
2022-05-29 01:23:10,201 INFO [train.py:761] (5/8) Epoch 22, batch 5450, loss[loss=0.2174, simple_loss=0.2935, pruned_loss=0.07062, over 4666.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3193, pruned_loss=0.08105, over 966725.59 frames.], batch size: 13, lr: 5.76e-04
2022-05-29 01:23:48,284 INFO [train.py:761] (5/8) Epoch 22, batch 5500, loss[loss=0.2911, simple_loss=0.3622, pruned_loss=0.11, over 4836.00 frames.], tot_loss[loss=0.2401, simple_loss=0.3186, pruned_loss=0.08077, over 966438.23 frames.], batch size: 26, lr: 5.76e-04
2022-05-29 01:24:26,638 INFO [train.py:761] (5/8) Epoch 22, batch 5550, loss[loss=0.2315, simple_loss=0.2994, pruned_loss=0.08177, over 4837.00 frames.], tot_loss[loss=0.2389, simple_loss=0.3176, pruned_loss=0.08011, over 966338.13 frames.], batch size: 11, lr: 5.76e-04
2022-05-29 01:25:05,189 INFO [train.py:761] (5/8) Epoch 22, batch 5600, loss[loss=0.2426, simple_loss=0.3154, pruned_loss=0.08494, over 4927.00 frames.], tot_loss[loss=0.2391, simple_loss=0.3173, pruned_loss=0.08042, over 965872.08 frames.], batch size: 26, lr: 5.76e-04
2022-05-29 01:25:43,802 INFO [train.py:761] (5/8) Epoch 22, batch 5650, loss[loss=0.2445, simple_loss=0.3315, pruned_loss=0.07874, over 4806.00 frames.], tot_loss[loss=0.2387, simple_loss=0.3174, pruned_loss=0.08, over 965360.88 frames.], batch size: 20, lr: 5.76e-04
2022-05-29 01:26:22,373 INFO [train.py:761] (5/8) Epoch 22, batch 5700, loss[loss=0.2401, simple_loss=0.3311, pruned_loss=0.07457, over 4949.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3179, pruned_loss=0.08082, over 965253.55 frames.], batch size: 16, lr: 5.76e-04
2022-05-29 01:27:01,239 INFO [train.py:761] (5/8) Epoch 22, batch 5750, loss[loss=0.2907, simple_loss=0.3568, pruned_loss=0.1123, over 4991.00 frames.], tot_loss[loss=0.2391, simple_loss=0.3173, pruned_loss=0.08046, over 966001.02 frames.], batch size: 13, lr: 5.76e-04
2022-05-29 01:27:38,980 INFO [train.py:761] (5/8) Epoch 22, batch 5800, loss[loss=0.2245, simple_loss=0.3196, pruned_loss=0.06473, over 4966.00 frames.], tot_loss[loss=0.24, simple_loss=0.3183, pruned_loss=0.08083, over 967222.25 frames.], batch size: 14, lr: 5.75e-04
2022-05-29 01:28:17,504 INFO [train.py:761] (5/8) Epoch 22, batch 5850, loss[loss=0.2616, simple_loss=0.324, pruned_loss=0.09959, over 4667.00 frames.], tot_loss[loss=0.2403, simple_loss=0.3182, pruned_loss=0.08126, over 966772.23 frames.], batch size: 12, lr: 5.75e-04
2022-05-29 01:28:55,284 INFO [train.py:761] (5/8) Epoch 22, batch 5900, loss[loss=0.2399, simple_loss=0.2994, pruned_loss=0.09018, over 4670.00 frames.], tot_loss[loss=0.2411, simple_loss=0.3188, pruned_loss=0.08174, over 966713.20 frames.], batch size: 12, lr: 5.75e-04
2022-05-29 01:29:33,787 INFO [train.py:761] (5/8) Epoch 22, batch 5950, loss[loss=0.2232, simple_loss=0.3038, pruned_loss=0.07129, over 4802.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3176, pruned_loss=0.08086, over 966387.81 frames.], batch size: 20, lr: 5.75e-04
2022-05-29 01:30:11,411 INFO [train.py:761] (5/8) Epoch 22, batch 6000, loss[loss=0.2029, simple_loss=0.2842, pruned_loss=0.06076, over 4885.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3179, pruned_loss=0.0812, over 966234.79 frames.], batch size: 12, lr: 5.75e-04
2022-05-29 01:30:11,412 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 01:30:21,354 INFO [train.py:790] (5/8) Epoch 22, validation: loss=0.2013, simple_loss=0.3062, pruned_loss=0.04819, over 944034.00 frames.
2022-05-29 01:31:00,180 INFO [train.py:761] (5/8) Epoch 22, batch 6050, loss[loss=0.2133, simple_loss=0.3036, pruned_loss=0.06146, over 4978.00 frames.], tot_loss[loss=0.2406, simple_loss=0.3187, pruned_loss=0.08127, over 966482.69 frames.], batch size: 15, lr: 5.75e-04
2022-05-29 01:31:38,687 INFO [train.py:761] (5/8) Epoch 22, batch 6100, loss[loss=0.2671, simple_loss=0.3466, pruned_loss=0.09382, over 4861.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3205, pruned_loss=0.08254, over 965382.06 frames.], batch size: 17, lr: 5.75e-04
2022-05-29 01:32:16,615 INFO [train.py:761] (5/8) Epoch 22, batch 6150, loss[loss=0.2139, simple_loss=0.3129, pruned_loss=0.05748, over 4716.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3197, pruned_loss=0.08207, over 965575.58 frames.], batch size: 14, lr: 5.75e-04
2022-05-29 01:32:55,017 INFO [train.py:761] (5/8) Epoch 22, batch 6200, loss[loss=0.2565, simple_loss=0.331, pruned_loss=0.09096, over 4806.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3193, pruned_loss=0.0823, over 965486.31 frames.], batch size: 16, lr: 5.75e-04
2022-05-29 01:33:33,400 INFO [train.py:761] (5/8) Epoch 22, batch 6250, loss[loss=0.2525, simple_loss=0.3411, pruned_loss=0.08195, over 4980.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3207, pruned_loss=0.0831, over 966182.61 frames.], batch size: 27, lr: 5.75e-04
2022-05-29 01:34:11,195 INFO [train.py:761] (5/8) Epoch 22, batch 6300, loss[loss=0.219, simple_loss=0.295, pruned_loss=0.07155, over 4665.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3182, pruned_loss=0.08128, over 965683.97 frames.], batch size: 12, lr: 5.74e-04
2022-05-29 01:34:49,223 INFO [train.py:761] (5/8) Epoch 22, batch 6350, loss[loss=0.2434, simple_loss=0.3449, pruned_loss=0.07099, over 4976.00 frames.], tot_loss[loss=0.241, simple_loss=0.3189, pruned_loss=0.08151, over 965320.86 frames.], batch size: 15, lr: 5.74e-04
2022-05-29 01:35:27,309 INFO [train.py:761] (5/8) Epoch 22, batch 6400, loss[loss=0.2243, simple_loss=0.3109, pruned_loss=0.06883, over 4875.00 frames.], tot_loss[loss=0.2405, simple_loss=0.3179, pruned_loss=0.0816, over 965466.95 frames.], batch size: 17, lr: 5.74e-04
2022-05-29 01:36:05,755 INFO [train.py:761] (5/8) Epoch 22, batch 6450, loss[loss=0.2871, simple_loss=0.3618, pruned_loss=0.1062, over 4886.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3172, pruned_loss=0.08117, over 965923.86 frames.], batch size: 17, lr: 5.74e-04
2022-05-29 01:36:44,374 INFO [train.py:761] (5/8) Epoch 22, batch 6500, loss[loss=0.2375, simple_loss=0.3189, pruned_loss=0.07808, over 4983.00 frames.], tot_loss[loss=0.2383, simple_loss=0.3165, pruned_loss=0.08, over 965236.50 frames.], batch size: 15, lr: 5.74e-04
2022-05-29 01:37:23,454 INFO [train.py:761] (5/8) Epoch 22, batch 6550, loss[loss=0.1995, simple_loss=0.2783, pruned_loss=0.06034, over 4734.00 frames.], tot_loss[loss=0.2387, simple_loss=0.3168, pruned_loss=0.08027, over 965631.62 frames.], batch size: 11, lr: 5.74e-04
2022-05-29 01:38:01,967 INFO [train.py:761] (5/8) Epoch 22, batch 6600, loss[loss=0.1951, simple_loss=0.2761, pruned_loss=0.0571, over 4804.00 frames.], tot_loss[loss=0.2382, simple_loss=0.3164, pruned_loss=0.08, over 964830.90 frames.], batch size: 12, lr: 5.74e-04
2022-05-29 01:38:40,388 INFO [train.py:761] (5/8) Epoch 22, batch 6650, loss[loss=0.2699, simple_loss=0.3485, pruned_loss=0.09568, over 4775.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3168, pruned_loss=0.08006, over 965121.34 frames.], batch size: 20, lr: 5.74e-04
2022-05-29 01:39:17,785 INFO [train.py:761] (5/8) Epoch 22, batch 6700, loss[loss=0.2553, simple_loss=0.3405, pruned_loss=0.08507, over 4829.00 frames.], tot_loss[loss=0.239, simple_loss=0.3174, pruned_loss=0.08024, over 963927.56 frames.], batch size: 20, lr: 5.74e-04
2022-05-29 01:40:13,329 INFO [train.py:761] (5/8) Epoch 23, batch 0, loss[loss=0.2084, simple_loss=0.3074, pruned_loss=0.05471, over 4977.00 frames.], tot_loss[loss=0.2084, simple_loss=0.3074, pruned_loss=0.05471, over 4977.00 frames.], batch size: 14, lr: 5.74e-04
2022-05-29 01:40:51,448 INFO [train.py:761] (5/8) Epoch 23, batch 50, loss[loss=0.2494, simple_loss=0.3189, pruned_loss=0.08993, over 4659.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3154, pruned_loss=0.06877, over 219046.28 frames.], batch size: 12, lr: 5.74e-04
2022-05-29 01:41:29,256 INFO [train.py:761] (5/8) Epoch 23, batch 100, loss[loss=0.1752, simple_loss=0.2834, pruned_loss=0.03347, over 4917.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3111, pruned_loss=0.06594, over 384640.63 frames.], batch size: 13, lr: 5.73e-04
2022-05-29 01:42:07,176 INFO [train.py:761] (5/8) Epoch 23, batch 150, loss[loss=0.1953, simple_loss=0.3054, pruned_loss=0.04255, over 4788.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3102, pruned_loss=0.06522, over 513476.83 frames.], batch size: 13, lr: 5.73e-04
2022-05-29 01:42:45,639 INFO [train.py:761] (5/8) Epoch 23, batch 200, loss[loss=0.2086, simple_loss=0.2865, pruned_loss=0.06538, over 4576.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3108, pruned_loss=0.06544, over 613892.75 frames.], batch size: 11, lr: 5.73e-04
2022-05-29 01:43:24,059 INFO [train.py:761] (5/8) Epoch 23, batch 250, loss[loss=0.2332, simple_loss=0.3343, pruned_loss=0.0661, over 4712.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3087, pruned_loss=0.06428, over 692697.33 frames.], batch size: 14, lr: 5.73e-04
2022-05-29 01:44:02,271 INFO [train.py:761] (5/8) Epoch 23, batch 300, loss[loss=0.2097, simple_loss=0.311, pruned_loss=0.05421, over 4908.00 frames.], tot_loss[loss=0.218, simple_loss=0.308, pruned_loss=0.06404, over 752462.10 frames.], batch size: 14, lr: 5.73e-04
2022-05-29 01:44:40,281 INFO [train.py:761] (5/8) Epoch 23, batch 350, loss[loss=0.216, simple_loss=0.3059, pruned_loss=0.06302, over 4802.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3067, pruned_loss=0.06348, over 799560.53 frames.], batch size: 12, lr: 5.73e-04
2022-05-29 01:45:17,833 INFO [train.py:761] (5/8) Epoch 23, batch 400, loss[loss=0.2067, simple_loss=0.3153, pruned_loss=0.04908, over 4974.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3064, pruned_loss=0.06309, over 836688.26 frames.], batch size: 14, lr: 5.73e-04
2022-05-29 01:45:55,685 INFO [train.py:761] (5/8) Epoch 23, batch 450, loss[loss=0.2111, simple_loss=0.3002, pruned_loss=0.06103, over 4979.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3067, pruned_loss=0.06319, over 865591.46 frames.], batch size: 15, lr: 5.73e-04
2022-05-29 01:46:33,752 INFO [train.py:761] (5/8) Epoch 23, batch 500, loss[loss=0.2152, simple_loss=0.3127, pruned_loss=0.05888, over 4707.00 frames.], tot_loss[loss=0.2175, simple_loss=0.3078, pruned_loss=0.06361, over 887585.07 frames.], batch size: 14, lr: 5.73e-04
2022-05-29 01:47:11,656 INFO [train.py:761] (5/8) Epoch 23, batch 550, loss[loss=0.2177, simple_loss=0.329, pruned_loss=0.05315, over 4853.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3071, pruned_loss=0.06333, over 905541.30 frames.], batch size: 14, lr: 5.73e-04
2022-05-29 01:47:49,951 INFO [train.py:761] (5/8) Epoch 23, batch 600, loss[loss=0.2335, simple_loss=0.3215, pruned_loss=0.07279, over 4934.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3081, pruned_loss=0.06336, over 919440.22 frames.], batch size: 13, lr: 5.72e-04
2022-05-29 01:48:27,653 INFO [train.py:761] (5/8) Epoch 23, batch 650, loss[loss=0.2144, simple_loss=0.3051, pruned_loss=0.06184, over 4803.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3075, pruned_loss=0.06302, over 930128.11 frames.], batch size: 12, lr: 5.72e-04
2022-05-29 01:49:05,087 INFO [train.py:761] (5/8) Epoch 23, batch 700, loss[loss=0.2083, simple_loss=0.2787, pruned_loss=0.06895, over 4830.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3066, pruned_loss=0.06253, over 938421.45 frames.], batch size: 11, lr: 5.72e-04
2022-05-29 01:49:43,458 INFO [train.py:761] (5/8) Epoch 23, batch 750, loss[loss=0.2146, simple_loss=0.2973, pruned_loss=0.0659, over 4796.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3078, pruned_loss=0.0635, over 943383.82 frames.], batch size: 12, lr: 5.72e-04
2022-05-29 01:50:21,400 INFO [train.py:761] (5/8) Epoch 23, batch 800, loss[loss=0.2406, simple_loss=0.3246, pruned_loss=0.07828, over 4786.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3092, pruned_loss=0.06433, over 948553.53 frames.], batch size: 13, lr: 5.72e-04
2022-05-29 01:50:59,154 INFO [train.py:761] (5/8) Epoch 23, batch 850, loss[loss=0.1942, simple_loss=0.2813, pruned_loss=0.05358, over 4808.00 frames.], tot_loss[loss=0.22, simple_loss=0.3097, pruned_loss=0.06516, over 952769.04 frames.], batch size: 12, lr: 5.72e-04
2022-05-29 01:51:37,312 INFO [train.py:761] (5/8) Epoch 23, batch 900, loss[loss=0.2321, simple_loss=0.3185, pruned_loss=0.07288, over 4875.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3098, pruned_loss=0.06554, over 955869.28 frames.], batch size: 17, lr: 5.72e-04
2022-05-29 01:52:15,696 INFO [train.py:761] (5/8) Epoch 23, batch 950, loss[loss=0.2622, simple_loss=0.338, pruned_loss=0.09322, over 4830.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3095, pruned_loss=0.06569, over 957382.29 frames.], batch size: 18, lr: 5.72e-04
2022-05-29 01:52:53,609 INFO [train.py:761] (5/8) Epoch 23, batch 1000, loss[loss=0.1929, simple_loss=0.2856, pruned_loss=0.05012, over 4717.00 frames.], tot_loss[loss=0.22, simple_loss=0.3092, pruned_loss=0.06547, over 958950.07 frames.], batch size: 14, lr: 5.72e-04
2022-05-29 01:53:31,848 INFO [train.py:761] (5/8) Epoch 23, batch 1050, loss[loss=0.2367, simple_loss=0.3277, pruned_loss=0.07281, over 4946.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3106, pruned_loss=0.06576, over 961171.58 frames.], batch size: 16, lr: 5.72e-04
2022-05-29 01:54:09,950 INFO [train.py:761] (5/8) Epoch 23, batch 1100, loss[loss=0.1924, simple_loss=0.2701, pruned_loss=0.05736, over 4976.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3115, pruned_loss=0.06636, over 962313.88 frames.], batch size: 12, lr: 5.71e-04
2022-05-29 01:54:48,165 INFO [train.py:761] (5/8) Epoch 23, batch 1150, loss[loss=0.2105, simple_loss=0.2853, pruned_loss=0.06787, over 4892.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3117, pruned_loss=0.06656, over 962634.24 frames.], batch size: 12, lr: 5.71e-04
2022-05-29 01:55:25,964 INFO [train.py:761] (5/8) Epoch 23, batch 1200, loss[loss=0.2156, simple_loss=0.2976, pruned_loss=0.06681, over 4985.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3117, pruned_loss=0.06605, over 963748.10 frames.], batch size: 13, lr: 5.71e-04
2022-05-29 01:56:03,898 INFO [train.py:761] (5/8) Epoch 23, batch 1250, loss[loss=0.2284, simple_loss=0.3116, pruned_loss=0.07258, over 4876.00 frames.], tot_loss[loss=0.22, simple_loss=0.3102, pruned_loss=0.0649, over 963713.54 frames.], batch size: 15, lr: 5.71e-04
2022-05-29 01:56:41,705 INFO [train.py:761] (5/8) Epoch 23, batch 1300, loss[loss=0.185, simple_loss=0.273, pruned_loss=0.04846, over 4810.00 frames.], tot_loss[loss=0.2191, simple_loss=0.3092, pruned_loss=0.06447, over 963587.65 frames.], batch size: 12, lr: 5.71e-04
2022-05-29 01:57:20,153 INFO [train.py:761] (5/8) Epoch 23, batch 1350, loss[loss=0.2132, simple_loss=0.3042, pruned_loss=0.06106, over 4856.00 frames.], tot_loss[loss=0.218, simple_loss=0.3077, pruned_loss=0.06413, over 964499.41 frames.], batch size: 14, lr: 5.71e-04
2022-05-29 01:57:58,199 INFO [train.py:761] (5/8) Epoch 23, batch 1400, loss[loss=0.2508, simple_loss=0.326, pruned_loss=0.08781, over 4917.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3087, pruned_loss=0.06459, over 965653.12 frames.], batch size: 14, lr: 5.71e-04
2022-05-29 01:58:36,143 INFO [train.py:761] (5/8) Epoch 23, batch 1450, loss[loss=0.2384, simple_loss=0.3383, pruned_loss=0.06928, over 4887.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3082, pruned_loss=0.06432, over 964848.64 frames.], batch size: 15, lr: 5.71e-04
2022-05-29 01:59:13,587 INFO [train.py:761] (5/8) Epoch 23, batch 1500, loss[loss=0.2307, simple_loss=0.3152, pruned_loss=0.0731, over 4875.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3096, pruned_loss=0.06505, over 964654.66 frames.], batch size: 18, lr: 5.71e-04
2022-05-29 01:59:51,603 INFO [train.py:761] (5/8) Epoch 23, batch 1550, loss[loss=0.2141, simple_loss=0.3201, pruned_loss=0.05409, over 4855.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3098, pruned_loss=0.06551, over 964644.02 frames.], batch size: 14, lr: 5.71e-04
2022-05-29 02:00:29,812 INFO [train.py:761] (5/8) Epoch 23, batch 1600, loss[loss=0.2366, simple_loss=0.3152, pruned_loss=0.079, over 4664.00 frames.], tot_loss[loss=0.2208, simple_loss=0.3098, pruned_loss=0.0659, over 965856.90 frames.], batch size: 12, lr: 5.71e-04
2022-05-29 02:01:07,851 INFO [train.py:761] (5/8) Epoch 23, batch 1650, loss[loss=0.1933, simple_loss=0.2793, pruned_loss=0.05361, over 4986.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3087, pruned_loss=0.06531, over 965615.58 frames.], batch size: 13, lr: 5.70e-04
2022-05-29 02:01:45,653 INFO [train.py:761] (5/8) Epoch 23, batch 1700, loss[loss=0.2197, simple_loss=0.3239, pruned_loss=0.05778, over 4725.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3066, pruned_loss=0.06444, over 966568.60 frames.], batch size: 13, lr: 5.70e-04
2022-05-29 02:02:23,775 INFO [train.py:761] (5/8) Epoch 23, batch 1750, loss[loss=0.206, simple_loss=0.2969, pruned_loss=0.05758, over 4919.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3061, pruned_loss=0.06378, over 965732.77 frames.], batch size: 13, lr: 5.70e-04
2022-05-29 02:03:01,663 INFO [train.py:761] (5/8) Epoch 23, batch 1800, loss[loss=0.244, simple_loss=0.3283, pruned_loss=0.07981, over 4868.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3059, pruned_loss=0.06315, over 965295.72 frames.], batch size: 15, lr: 5.70e-04
2022-05-29 02:03:39,940 INFO [train.py:761] (5/8) Epoch 23, batch 1850, loss[loss=0.2099, simple_loss=0.3048, pruned_loss=0.05749, over 4804.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3078, pruned_loss=0.06425, over 965447.72 frames.], batch size: 12, lr: 5.70e-04
2022-05-29 02:04:17,557 INFO [train.py:761] (5/8) Epoch 23, batch 1900, loss[loss=0.1721, simple_loss=0.2554, pruned_loss=0.04438, over 4558.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3084, pruned_loss=0.06372, over 965292.83 frames.], batch size: 10, lr: 5.70e-04
2022-05-29 02:04:55,579 INFO [train.py:761] (5/8) Epoch 23, batch 1950, loss[loss=0.1541, simple_loss=0.2469, pruned_loss=0.03069, over 4828.00 frames.], tot_loss[loss=0.218, simple_loss=0.3087, pruned_loss=0.06366, over 966375.44 frames.], batch size: 11, lr: 5.70e-04
2022-05-29 02:05:33,141 INFO [train.py:761] (5/8) Epoch 23, batch 2000, loss[loss=0.1948, simple_loss=0.2999, pruned_loss=0.04481, over 4666.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3094, pruned_loss=0.06361, over 967346.31 frames.], batch size: 12, lr: 5.70e-04
2022-05-29 02:06:11,282 INFO [train.py:761] (5/8) Epoch 23, batch 2050, loss[loss=0.1771, simple_loss=0.2664, pruned_loss=0.04392, over 4840.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3102, pruned_loss=0.06355, over 966893.08 frames.], batch size: 11, lr: 5.70e-04
2022-05-29 02:06:49,385 INFO [train.py:761] (5/8) Epoch 23, batch 2100, loss[loss=0.2229, simple_loss=0.3124, pruned_loss=0.06666, over 4781.00 frames.], tot_loss[loss=0.2193, simple_loss=0.311, pruned_loss=0.06375, over 966255.08 frames.], batch size: 13, lr: 5.70e-04
2022-05-29 02:07:27,541 INFO [train.py:761] (5/8) Epoch 23, batch 2150, loss[loss=0.2306, simple_loss=0.326, pruned_loss=0.0676, over 4879.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3103, pruned_loss=0.06339, over 966201.21 frames.], batch size: 15, lr: 5.69e-04
2022-05-29 02:08:05,792 INFO [train.py:761] (5/8) Epoch 23, batch 2200, loss[loss=0.2217, simple_loss=0.3021, pruned_loss=0.07059, over 4630.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3104, pruned_loss=0.06405, over 965482.78 frames.], batch size: 11, lr: 5.69e-04
2022-05-29 02:08:44,458 INFO [train.py:761] (5/8) Epoch 23, batch 2250, loss[loss=0.1948, simple_loss=0.2706, pruned_loss=0.05954, over 4728.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3103, pruned_loss=0.06405, over 965643.75 frames.], batch size: 11, lr: 5.69e-04
2022-05-29 02:09:22,148 INFO [train.py:761] (5/8) Epoch 23, batch 2300, loss[loss=0.2401, simple_loss=0.3249, pruned_loss=0.07768, over 4838.00 frames.], tot_loss[loss=0.2198, simple_loss=0.311, pruned_loss=0.06426, over 965127.32 frames.], batch size: 18, lr: 5.69e-04
2022-05-29 02:10:00,542 INFO [train.py:761] (5/8) Epoch 23, batch 2350, loss[loss=0.195, simple_loss=0.2727, pruned_loss=0.05862, over 4894.00 frames.], tot_loss[loss=0.2197, simple_loss=0.311, pruned_loss=0.06418, over 965556.76 frames.], batch size: 12, lr: 5.69e-04
2022-05-29 02:10:38,429 INFO [train.py:761] (5/8) Epoch 23, batch 2400, loss[loss=0.2275, simple_loss=0.2997, pruned_loss=0.0776, over 4738.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3106, pruned_loss=0.06403, over 965194.95 frames.], batch size: 12, lr: 5.69e-04
2022-05-29 02:11:16,499 INFO [train.py:761] (5/8) Epoch 23, batch 2450, loss[loss=0.2044, simple_loss=0.3074, pruned_loss=0.0507, over 4820.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3096, pruned_loss=0.0634, over 965068.10 frames.], batch size: 20, lr: 5.69e-04
2022-05-29 02:11:54,687 INFO [train.py:761] (5/8) Epoch 23, batch 2500, loss[loss=0.2392, simple_loss=0.3358, pruned_loss=0.07133, over 4886.00 frames.], tot_loss[loss=0.218, simple_loss=0.3092, pruned_loss=0.0634, over 964929.31 frames.], batch size: 17, lr: 5.69e-04
2022-05-29 02:12:32,930 INFO [train.py:761] (5/8) Epoch 23, batch 2550, loss[loss=0.1712, simple_loss=0.2587, pruned_loss=0.04188, over 4588.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3092, pruned_loss=0.06362, over 965830.13 frames.], batch size: 10, lr: 5.69e-04
2022-05-29 02:13:10,457 INFO [train.py:761] (5/8) Epoch 23, batch 2600, loss[loss=0.2174, simple_loss=0.302, pruned_loss=0.0664, over 4673.00 frames.], tot_loss[loss=0.218, simple_loss=0.309, pruned_loss=0.06352, over 966333.08 frames.], batch size: 13, lr: 5.69e-04
2022-05-29 02:13:48,310 INFO [train.py:761] (5/8) Epoch 23, batch 2650, loss[loss=0.238, simple_loss=0.3462, pruned_loss=0.06486, over 4767.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3075, pruned_loss=0.06285, over 966191.44 frames.], batch size: 15, lr: 5.69e-04
2022-05-29 02:14:25,993 INFO [train.py:761] (5/8) Epoch 23, batch 2700, loss[loss=0.2054, simple_loss=0.2967, pruned_loss=0.05705, over 4801.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3084, pruned_loss=0.0634, over 966587.70 frames.], batch size: 16, lr: 5.68e-04
2022-05-29 02:15:03,537 INFO [train.py:761] (5/8) Epoch 23, batch 2750, loss[loss=0.2247, simple_loss=0.3119, pruned_loss=0.0687, over 4784.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3076, pruned_loss=0.06284, over 966465.18 frames.], batch size: 13, lr: 5.68e-04
2022-05-29 02:15:42,249 INFO [train.py:761] (5/8) Epoch 23, batch 2800, loss[loss=0.2347, simple_loss=0.3205, pruned_loss=0.07445, over 4989.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3096, pruned_loss=0.06371, over 965805.89 frames.], batch size: 26, lr: 5.68e-04
2022-05-29 02:16:20,454 INFO [train.py:761] (5/8) Epoch 23, batch 2850, loss[loss=0.2055, simple_loss=0.2836, pruned_loss=0.06364, over 4876.00 frames.], tot_loss[loss=0.219, simple_loss=0.3098, pruned_loss=0.06406, over 966865.16 frames.], batch size: 12, lr: 5.68e-04
2022-05-29 02:16:58,667 INFO [train.py:761] (5/8) Epoch 23, batch 2900, loss[loss=0.2216, simple_loss=0.3111, pruned_loss=0.06607, over 4846.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3087, pruned_loss=0.06408, over 966595.50 frames.], batch size: 14, lr: 5.68e-04
2022-05-29 02:17:36,989 INFO [train.py:761] (5/8) Epoch 23, batch 2950, loss[loss=0.1818, simple_loss=0.2582, pruned_loss=0.05274, over 4923.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3088, pruned_loss=0.0638, over 967034.32 frames.], batch size: 13, lr: 5.68e-04
2022-05-29 02:18:14,804 INFO [train.py:761] (5/8) Epoch 23, batch 3000, loss[loss=0.1543, simple_loss=0.2404, pruned_loss=0.03412, over 4829.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3076, pruned_loss=0.06386, over 966320.06 frames.], batch size: 11, lr: 5.68e-04
2022-05-29 02:18:14,805 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 02:18:24,916 INFO [train.py:790] (5/8) Epoch 23, validation: loss=0.2104, simple_loss=0.3101, pruned_loss=0.05539, over 944034.00 frames.
2022-05-29 02:19:03,206 INFO [train.py:761] (5/8) Epoch 23, batch 3050, loss[loss=0.2796, simple_loss=0.3667, pruned_loss=0.09623, over 4840.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3095, pruned_loss=0.06473, over 967181.16 frames.], batch size: 20, lr: 5.68e-04
2022-05-29 02:19:40,740 INFO [train.py:761] (5/8) Epoch 23, batch 3100, loss[loss=0.2049, simple_loss=0.2983, pruned_loss=0.05572, over 4925.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3077, pruned_loss=0.06438, over 965828.18 frames.], batch size: 13, lr: 5.68e-04
2022-05-29 02:20:19,089 INFO [train.py:761] (5/8) Epoch 23, batch 3150, loss[loss=0.2882, simple_loss=0.357, pruned_loss=0.1097, over 4725.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3086, pruned_loss=0.06602, over 966904.81 frames.], batch size: 13, lr: 5.68e-04
2022-05-29 02:20:57,017 INFO [train.py:761] (5/8) Epoch 23, batch 3200, loss[loss=0.2444, simple_loss=0.3236, pruned_loss=0.08265, over 4922.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3098, pruned_loss=0.0679, over 966583.60 frames.], batch size: 13, lr: 5.68e-04
2022-05-29 02:21:34,771 INFO [train.py:761] (5/8) Epoch 23, batch 3250, loss[loss=0.2286, simple_loss=0.3146, pruned_loss=0.0713, over 4660.00 frames.], tot_loss[loss=0.225, simple_loss=0.3111, pruned_loss=0.06942, over 966753.54 frames.], batch size: 12, lr: 5.67e-04
2022-05-29 02:22:12,681 INFO [train.py:761] (5/8) Epoch 23, batch 3300, loss[loss=0.232, simple_loss=0.3103, pruned_loss=0.07685, over 4791.00 frames.], tot_loss[loss=0.2262, simple_loss=0.3115, pruned_loss=0.07048, over 966521.08 frames.], batch size: 13, lr: 5.67e-04
2022-05-29 02:22:51,161 INFO [train.py:761] (5/8) Epoch 23, batch 3350, loss[loss=0.2389, simple_loss=0.3164, pruned_loss=0.08075, over 4855.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3133, pruned_loss=0.07241, over 965958.08 frames.], batch size: 13, lr: 5.67e-04
2022-05-29 02:23:29,273 INFO [train.py:761] (5/8) Epoch 23, batch 3400, loss[loss=0.2742, simple_loss=0.3397, pruned_loss=0.1043, over 4871.00 frames.], tot_loss[loss=0.2317, simple_loss=0.314, pruned_loss=0.07475, over 967005.89 frames.], batch size: 44, lr: 5.67e-04
2022-05-29 02:24:07,892 INFO [train.py:761] (5/8) Epoch 23, batch 3450, loss[loss=0.3173, simple_loss=0.3883, pruned_loss=0.1232, over 4918.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3156, pruned_loss=0.07663, over 967981.51 frames.], batch size: 47, lr: 5.67e-04
2022-05-29 02:24:45,737 INFO [train.py:761] (5/8) Epoch 23, batch 3500, loss[loss=0.2404, simple_loss=0.3195, pruned_loss=0.08065, over 4784.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3153, pruned_loss=0.0768, over 966273.96 frames.], batch size: 15, lr: 5.67e-04
2022-05-29 02:25:23,618 INFO [train.py:761] (5/8) Epoch 23, batch 3550, loss[loss=0.2077, simple_loss=0.2946, pruned_loss=0.06041, over 4663.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3166, pruned_loss=0.07837, over 965354.78 frames.], batch size: 12, lr: 5.67e-04
2022-05-29 02:26:01,589 INFO [train.py:761] (5/8) Epoch 23, batch 3600, loss[loss=0.1719, simple_loss=0.2508, pruned_loss=0.04653, over 4732.00 frames.], tot_loss[loss=0.2369, simple_loss=0.316, pruned_loss=0.07886, over 965227.29 frames.], batch size: 11, lr: 5.67e-04
2022-05-29 02:26:43,382 INFO [train.py:761] (5/8) Epoch 23, batch 3650, loss[loss=0.1775, simple_loss=0.2576, pruned_loss=0.04874, over 4744.00 frames.], tot_loss[loss=0.2372, simple_loss=0.3163, pruned_loss=0.07906, over 965926.18 frames.], batch size: 11, lr: 5.67e-04
2022-05-29 02:27:21,250 INFO [train.py:761] (5/8) Epoch 23, batch 3700, loss[loss=0.2154, simple_loss=0.3005, pruned_loss=0.06514, over 4726.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3165, pruned_loss=0.07882, over 964392.31 frames.], batch size: 14, lr: 5.67e-04
2022-05-29 02:27:59,342 INFO [train.py:761] (5/8) Epoch 23, batch 3750, loss[loss=0.3191, simple_loss=0.3907, pruned_loss=0.1237, over 4979.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3162, pruned_loss=0.07929, over 964460.57 frames.], batch size: 46, lr: 5.66e-04
2022-05-29 02:28:37,658 INFO [train.py:761] (5/8) Epoch 23, batch 3800, loss[loss=0.2701, simple_loss=0.3505, pruned_loss=0.09481, over 4787.00 frames.], tot_loss[loss=0.2393, simple_loss=0.3174, pruned_loss=0.08066, over 965766.27 frames.], batch size: 20, lr: 5.66e-04
2022-05-29 02:29:16,284 INFO [train.py:761] (5/8) Epoch 23, batch 3850, loss[loss=0.2655, simple_loss=0.3442, pruned_loss=0.09337, over 4711.00 frames.], tot_loss[loss=0.2392, simple_loss=0.317, pruned_loss=0.08067, over 966288.67 frames.], batch size: 14, lr: 5.66e-04
2022-05-29 02:29:54,494 INFO [train.py:761] (5/8) Epoch 23, batch 3900, loss[loss=0.214, simple_loss=0.2898, pruned_loss=0.06913, over 4813.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3174, pruned_loss=0.08122, over 967296.68 frames.], batch size: 12, lr: 5.66e-04
2022-05-29 02:30:32,511 INFO [train.py:761] (5/8) Epoch 23, batch 3950, loss[loss=0.2885, simple_loss=0.3683, pruned_loss=0.1043, over 4885.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3162, pruned_loss=0.08105, over 966585.78 frames.], batch size: 15, lr: 5.66e-04
2022-05-29 02:31:10,623 INFO [train.py:761] (5/8) Epoch 23, batch 4000, loss[loss=0.1784, simple_loss=0.255, pruned_loss=0.05094, over 4729.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3185, pruned_loss=0.08225, over 966365.35 frames.], batch size: 12, lr: 5.66e-04
2022-05-29 02:31:49,089 INFO [train.py:761] (5/8) Epoch 23, batch 4050, loss[loss=0.206, simple_loss=0.2798, pruned_loss=0.06613, over 4576.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3174, pruned_loss=0.08096, over 965319.24 frames.], batch size: 10, lr: 5.66e-04
2022-05-29 02:32:26,989 INFO [train.py:761] (5/8) Epoch 23, batch 4100, loss[loss=0.2212, simple_loss=0.2839, pruned_loss=0.07927, over 4628.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3176, pruned_loss=0.0811, over 966261.41 frames.], batch size: 11, lr: 5.66e-04
2022-05-29 02:33:05,152 INFO [train.py:761] (5/8) Epoch 23, batch 4150, loss[loss=0.1934, simple_loss=0.2737, pruned_loss=0.05656, over 4915.00 frames.], tot_loss[loss=0.2384, simple_loss=0.3163, pruned_loss=0.08025, over 966154.87 frames.], batch size: 13, lr: 5.66e-04
2022-05-29 02:33:43,041 INFO [train.py:761] (5/8) Epoch 23, batch 4200, loss[loss=0.2595, simple_loss=0.3221, pruned_loss=0.0984, over 4728.00 frames.], tot_loss[loss=0.2409, simple_loss=0.3188, pruned_loss=0.08152, over 966842.47 frames.], batch size: 11, lr: 5.66e-04
2022-05-29 02:34:21,422 INFO [train.py:761] (5/8) Epoch 23, batch 4250, loss[loss=0.2484, simple_loss=0.3246, pruned_loss=0.08612, over 4919.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3196, pruned_loss=0.08192, over 966810.94 frames.], batch size: 13, lr: 5.66e-04
2022-05-29 02:34:59,166 INFO [train.py:761] (5/8) Epoch 23, batch 4300, loss[loss=0.191, simple_loss=0.2876, pruned_loss=0.04721, over 4784.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3192, pruned_loss=0.0819, over 966080.81 frames.], batch size: 13, lr: 5.65e-04
2022-05-29 02:35:38,154 INFO [train.py:761] (5/8) Epoch 23, batch 4350, loss[loss=0.2457, simple_loss=0.3359, pruned_loss=0.0778, over 4720.00 frames.], tot_loss[loss=0.2425, simple_loss=0.3201, pruned_loss=0.0825, over 967868.89 frames.], batch size: 14, lr: 5.65e-04
2022-05-29 02:36:15,699 INFO [train.py:761] (5/8) Epoch 23, batch 4400, loss[loss=0.2073, simple_loss=0.2832, pruned_loss=0.06567, over 4922.00 frames.], tot_loss[loss=0.2413, simple_loss=0.3191, pruned_loss=0.08174, over 967000.15 frames.], batch size: 13, lr: 5.65e-04
2022-05-29 02:36:54,375 INFO [train.py:761] (5/8) Epoch 23, batch 4450, loss[loss=0.2391, simple_loss=0.3256, pruned_loss=0.07627, over 4903.00 frames.], tot_loss[loss=0.2391, simple_loss=0.317, pruned_loss=0.08062, over 966485.48 frames.], batch size: 17, lr: 5.65e-04
2022-05-29 02:37:32,619 INFO [train.py:761] (5/8) Epoch 23, batch 4500, loss[loss=0.2196, simple_loss=0.292, pruned_loss=0.0736, over 4718.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3177, pruned_loss=0.08096, over 966318.36 frames.], batch size: 14, lr: 5.65e-04
2022-05-29 02:38:10,613 INFO [train.py:761] (5/8) Epoch 23, batch 4550, loss[loss=0.2718, simple_loss=0.3503, pruned_loss=0.09663, over 4941.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3172, pruned_loss=0.08063, over 967292.26 frames.], batch size: 21, lr: 5.65e-04
2022-05-29 02:38:48,440 INFO [train.py:761] (5/8) Epoch 23, batch 4600, loss[loss=0.2362, simple_loss=0.3076, pruned_loss=0.08241, over 4854.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3168, pruned_loss=0.08019, over 965950.20 frames.], batch size: 17, lr: 5.65e-04
2022-05-29 02:39:26,654 INFO [train.py:761] (5/8) Epoch 23, batch 4650, loss[loss=0.216, simple_loss=0.2878, pruned_loss=0.07207, over 4730.00 frames.], tot_loss[loss=0.2382, simple_loss=0.3163, pruned_loss=0.08002, over 967530.74 frames.], batch size: 11, lr: 5.65e-04
2022-05-29 02:40:04,843 INFO [train.py:761] (5/8) Epoch 23, batch 4700, loss[loss=0.1918, simple_loss=0.2801, pruned_loss=0.05179, over 4724.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3167, pruned_loss=0.07975, over 966390.91 frames.], batch size: 14, lr: 5.65e-04
2022-05-29 02:40:43,148 INFO [train.py:761] (5/8) Epoch 23, batch 4750, loss[loss=0.2445, simple_loss=0.323, pruned_loss=0.08305, over 4734.00 frames.], tot_loss[loss=0.2396, simple_loss=0.318, pruned_loss=0.08065, over 966205.72 frames.], batch size: 12, lr: 5.65e-04
2022-05-29 02:41:21,504 INFO [train.py:761] (5/8) Epoch 23, batch 4800, loss[loss=0.2486, simple_loss=0.3204, pruned_loss=0.0884, over 4880.00 frames.], tot_loss[loss=0.2397, simple_loss=0.318, pruned_loss=0.08073, over 965999.88 frames.], batch size: 17, lr: 5.65e-04
2022-05-29 02:41:59,951 INFO [train.py:761] (5/8) Epoch 23, batch 4850, loss[loss=0.31, simple_loss=0.372, pruned_loss=0.124, over 4910.00 frames.], tot_loss[loss=0.24, simple_loss=0.3179, pruned_loss=0.08105, over 966735.48 frames.], batch size: 46, lr: 5.64e-04
2022-05-29 02:42:37,901 INFO [train.py:761] (5/8) Epoch 23, batch 4900, loss[loss=0.2172, simple_loss=0.3012, pruned_loss=0.06663, over 4549.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3183, pruned_loss=0.0811, over 966910.25 frames.], batch size: 10, lr: 5.64e-04
2022-05-29 02:43:16,290 INFO [train.py:761] (5/8) Epoch 23, batch 4950, loss[loss=0.212, simple_loss=0.2888, pruned_loss=0.06756, over 4733.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3184, pruned_loss=0.08098, over 966379.70 frames.], batch size: 11, lr: 5.64e-04
2022-05-29 02:43:54,594 INFO [train.py:761] (5/8) Epoch 23, batch 5000, loss[loss=0.2733, simple_loss=0.3433, pruned_loss=0.1016, over 4968.00 frames.], tot_loss[loss=0.2393, simple_loss=0.3176, pruned_loss=0.08045, over 967520.58 frames.], batch size: 26, lr: 5.64e-04
2022-05-29 02:44:33,025 INFO [train.py:761] (5/8) Epoch 23, batch 5050, loss[loss=0.1858, simple_loss=0.2667, pruned_loss=0.0524, over 4731.00 frames.], tot_loss[loss=0.2384, simple_loss=0.3167, pruned_loss=0.08009, over 967531.81 frames.], batch size: 11, lr: 5.64e-04
2022-05-29 02:45:11,677 INFO [train.py:761] (5/8) Epoch 23, batch 5100, loss[loss=0.2445, simple_loss=0.3253, pruned_loss=0.08182, over 4962.00 frames.], tot_loss[loss=0.2377, simple_loss=0.3156, pruned_loss=0.07992, over 966596.50 frames.], batch size: 21, lr: 5.64e-04
2022-05-29 02:45:50,006 INFO [train.py:761] (5/8) Epoch 23, batch 5150, loss[loss=0.2453, simple_loss=0.3406, pruned_loss=0.07504, over 4884.00 frames.], tot_loss[loss=0.237, simple_loss=0.3149, pruned_loss=0.07952, over 965277.41 frames.], batch size: 17, lr: 5.64e-04
2022-05-29 02:46:28,013 INFO [train.py:761] (5/8) Epoch 23, batch 5200, loss[loss=0.2482, simple_loss=0.3244, pruned_loss=0.08602, over 4789.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3148, pruned_loss=0.07937, over 965041.51 frames.], batch size: 16, lr: 5.64e-04
2022-05-29 02:47:06,040 INFO [train.py:761] (5/8) Epoch 23, batch 5250, loss[loss=0.2653, simple_loss=0.3531, pruned_loss=0.08873, over 4856.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3147, pruned_loss=0.07903, over 964655.27 frames.], batch size: 14, lr: 5.64e-04
2022-05-29 02:47:44,223 INFO [train.py:761] (5/8) Epoch 23, batch 5300, loss[loss=0.2262, simple_loss=0.3194, pruned_loss=0.06651, over 4796.00 frames.], tot_loss[loss=0.2382, simple_loss=0.3164, pruned_loss=0.07996, over 966614.15 frames.], batch size: 14, lr: 5.64e-04
2022-05-29 02:48:22,366 INFO [train.py:761] (5/8) Epoch 23, batch 5350, loss[loss=0.2334, simple_loss=0.3312, pruned_loss=0.06779, over 4782.00 frames.], tot_loss[loss=0.2372, simple_loss=0.3157, pruned_loss=0.07932, over 966937.86 frames.], batch size: 15, lr: 5.64e-04
2022-05-29 02:49:00,751 INFO [train.py:761] (5/8) Epoch 23, batch 5400, loss[loss=0.2034, simple_loss=0.2894, pruned_loss=0.05869, over 4788.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3147, pruned_loss=0.07853, over 966256.16 frames.], batch size: 14, lr: 5.63e-04
2022-05-29 02:49:38,912 INFO [train.py:761] (5/8) Epoch 23, batch 5450, loss[loss=0.2144, simple_loss=0.3049, pruned_loss=0.06191, over 4854.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3155, pruned_loss=0.07937, over 965213.53 frames.], batch size: 13, lr: 5.63e-04
2022-05-29 02:50:16,724 INFO [train.py:761] (5/8) Epoch 23, batch 5500, loss[loss=0.2948, simple_loss=0.365, pruned_loss=0.1122, over 4780.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3173, pruned_loss=0.0806, over 964861.07 frames.], batch size: 15, lr: 5.63e-04
2022-05-29 02:50:55,407 INFO [train.py:761] (5/8) Epoch 23, batch 5550, loss[loss=0.2431, simple_loss=0.3303, pruned_loss=0.07798, over 4863.00 frames.], tot_loss[loss=0.2396, simple_loss=0.3174, pruned_loss=0.08092, over 965112.45 frames.], batch size: 14, lr: 5.63e-04
2022-05-29 02:51:33,092 INFO [train.py:761] (5/8) Epoch 23, batch 5600, loss[loss=0.2085, simple_loss=0.289, pruned_loss=0.06402, over 4781.00 frames.], tot_loss[loss=0.2382, simple_loss=0.3171, pruned_loss=0.07962, over 965707.35 frames.], batch size: 13, lr: 5.63e-04
2022-05-29 02:52:11,496 INFO [train.py:761] (5/8) Epoch 23, batch 5650, loss[loss=0.2466, simple_loss=0.3296, pruned_loss=0.08184, over 4871.00 frames.], tot_loss[loss=0.239, simple_loss=0.3179, pruned_loss=0.08007, over 966321.49 frames.], batch size: 17, lr: 5.63e-04
2022-05-29 02:52:49,319 INFO [train.py:761] (5/8) Epoch 23, batch 5700, loss[loss=0.3082, simple_loss=0.3634, pruned_loss=0.1265, over 4856.00 frames.], tot_loss[loss=0.2388, simple_loss=0.3174, pruned_loss=0.08015, over 966956.90 frames.], batch size: 14, lr: 5.63e-04
2022-05-29 02:53:28,393 INFO [train.py:761] (5/8) Epoch 23, batch 5750, loss[loss=0.2874, simple_loss=0.3591, pruned_loss=0.1079, over 4866.00 frames.], tot_loss[loss=0.241, simple_loss=0.3187, pruned_loss=0.08161, over 967146.39 frames.], batch size: 18, lr: 5.63e-04
2022-05-29 02:54:07,000 INFO [train.py:761] (5/8) Epoch 23, batch 5800, loss[loss=0.248, simple_loss=0.3243, pruned_loss=0.08585, over 4955.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3171, pruned_loss=0.08066, over 967560.95 frames.], batch size: 16, lr: 5.63e-04
2022-05-29 02:54:45,562 INFO [train.py:761] (5/8) Epoch 23, batch 5850, loss[loss=0.259, simple_loss=0.3282, pruned_loss=0.09493, over 4989.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3184, pruned_loss=0.08121, over 967725.07 frames.], batch size: 13, lr: 5.63e-04
2022-05-29 02:55:23,416 INFO [train.py:761] (5/8) Epoch 23, batch 5900, loss[loss=0.2416, simple_loss=0.3247, pruned_loss=0.07922, over 4843.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3179, pruned_loss=0.08096, over 968243.35 frames.], batch size: 18, lr: 5.63e-04
2022-05-29 02:56:01,933 INFO [train.py:761] (5/8) Epoch 23, batch 5950, loss[loss=0.2792, simple_loss=0.3516, pruned_loss=0.1034, over 4964.00 frames.], tot_loss[loss=0.2395, simple_loss=0.3173, pruned_loss=0.08081, over 968501.91 frames.], batch size: 49, lr: 5.62e-04
2022-05-29 02:56:40,036 INFO [train.py:761] (5/8) Epoch 23, batch 6000, loss[loss=0.2133, simple_loss=0.2991, pruned_loss=0.06373, over 4981.00 frames.], tot_loss[loss=0.2384, simple_loss=0.3167, pruned_loss=0.07999, over 968875.35 frames.], batch size: 15, lr: 5.62e-04
2022-05-29 02:56:40,037 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 02:56:49,922 INFO [train.py:790] (5/8) Epoch 23, validation: loss=0.2002, simple_loss=0.3049, pruned_loss=0.04778, over 944034.00 frames.
2022-05-29 02:57:27,836 INFO [train.py:761] (5/8) Epoch 23, batch 6050, loss[loss=0.3012, simple_loss=0.378, pruned_loss=0.1122, over 4940.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3181, pruned_loss=0.08075, over 969252.22 frames.], batch size: 47, lr: 5.62e-04
2022-05-29 02:58:06,001 INFO [train.py:761] (5/8) Epoch 23, batch 6100, loss[loss=0.202, simple_loss=0.277, pruned_loss=0.06352, over 4556.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3178, pruned_loss=0.08095, over 968552.13 frames.], batch size: 10, lr: 5.62e-04
2022-05-29 02:58:44,504 INFO [train.py:761] (5/8) Epoch 23, batch 6150, loss[loss=0.2571, simple_loss=0.3199, pruned_loss=0.09718, over 4780.00 frames.], tot_loss[loss=0.2393, simple_loss=0.3176, pruned_loss=0.08046, over 968018.91 frames.], batch size: 13, lr: 5.62e-04
2022-05-29 02:59:22,950 INFO [train.py:761] (5/8) Epoch 23, batch 6200, loss[loss=0.2474, simple_loss=0.3382, pruned_loss=0.07836, over 4932.00 frames.], tot_loss[loss=0.238, simple_loss=0.3167, pruned_loss=0.07966, over 967874.19 frames.], batch size: 16, lr: 5.62e-04
2022-05-29 03:00:01,677 INFO [train.py:761] (5/8) Epoch 23, batch 6250, loss[loss=0.2543, simple_loss=0.3361, pruned_loss=0.08624, over 4833.00 frames.], tot_loss[loss=0.2375, simple_loss=0.3168, pruned_loss=0.07911, over 967200.13 frames.], batch size: 16, lr: 5.62e-04
2022-05-29 03:00:39,731 INFO [train.py:761] (5/8) Epoch 23, batch 6300, loss[loss=0.2224, simple_loss=0.2914, pruned_loss=0.07666, over 4660.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3177, pruned_loss=0.07961, over 967395.66 frames.], batch size: 12, lr: 5.62e-04
2022-05-29 03:01:17,676 INFO [train.py:761] (5/8) Epoch 23, batch 6350, loss[loss=0.2579, simple_loss=0.3384, pruned_loss=0.08868, over 4843.00 frames.], tot_loss[loss=0.2389, simple_loss=0.3182, pruned_loss=0.07981, over 967671.20 frames.], batch size: 18, lr: 5.62e-04
2022-05-29 03:01:55,954 INFO [train.py:761] (5/8) Epoch 23, batch 6400, loss[loss=0.2252, simple_loss=0.304, pruned_loss=0.07314, over 4925.00 frames.], tot_loss[loss=0.2383, simple_loss=0.3176, pruned_loss=0.07955, over 967013.61 frames.], batch size: 13, lr: 5.62e-04
2022-05-29 03:02:33,729 INFO [train.py:761] (5/8) Epoch 23, batch 6450, loss[loss=0.1852, simple_loss=0.2601, pruned_loss=0.05515, over 4712.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3177, pruned_loss=0.07979, over 967321.13 frames.], batch size: 11, lr: 5.62e-04
2022-05-29 03:03:12,169 INFO [train.py:761] (5/8) Epoch 23, batch 6500, loss[loss=0.3042, simple_loss=0.3744, pruned_loss=0.117, over 4872.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3156, pruned_loss=0.07891, over 966891.53 frames.], batch size: 17, lr: 5.61e-04
2022-05-29 03:03:50,552 INFO [train.py:761] (5/8) Epoch 23, batch 6550, loss[loss=0.2785, simple_loss=0.3511, pruned_loss=0.103, over 4716.00 frames.], tot_loss[loss=0.2373, simple_loss=0.316, pruned_loss=0.0793, over 965411.98 frames.], batch size: 14, lr: 5.61e-04
2022-05-29 03:04:28,788 INFO [train.py:761] (5/8) Epoch 23, batch 6600, loss[loss=0.2056, simple_loss=0.3029, pruned_loss=0.05416, over 4669.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3142, pruned_loss=0.07863, over 965360.53 frames.], batch size: 12, lr: 5.61e-04
2022-05-29 03:05:07,702 INFO [train.py:761] (5/8) Epoch 23, batch 6650, loss[loss=0.2218, simple_loss=0.2909, pruned_loss=0.07631, over 4986.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3146, pruned_loss=0.07932, over 964890.67 frames.], batch size: 13, lr: 5.61e-04
2022-05-29 03:05:45,407 INFO [train.py:761] (5/8) Epoch 23, batch 6700, loss[loss=0.2467, simple_loss=0.3263, pruned_loss=0.08357, over 4766.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3149, pruned_loss=0.0792, over 964915.13 frames.], batch size: 20, lr: 5.61e-04
2022-05-29 03:06:41,790 INFO [train.py:761] (5/8) Epoch 24, batch 0, loss[loss=0.2238, simple_loss=0.3268, pruned_loss=0.06045, over 4780.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3268, pruned_loss=0.06045, over 4780.00 frames.], batch size: 20, lr: 5.61e-04
2022-05-29 03:07:19,801 INFO [train.py:761] (5/8) Epoch 24, batch 50, loss[loss=0.2118, simple_loss=0.3113, pruned_loss=0.05615, over 4777.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3121, pruned_loss=0.0671, over 219909.77 frames.], batch size: 15, lr: 5.61e-04
2022-05-29 03:07:58,026 INFO [train.py:761] (5/8) Epoch 24, batch 100, loss[loss=0.2203, simple_loss=0.317, pruned_loss=0.06173, over 4978.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3081, pruned_loss=0.06419, over 385730.57 frames.], batch size: 15, lr: 5.61e-04
2022-05-29 03:08:35,900 INFO [train.py:761] (5/8) Epoch 24, batch 150, loss[loss=0.2298, simple_loss=0.3116, pruned_loss=0.07399, over 4967.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3055, pruned_loss=0.06309, over 513798.09 frames.], batch size: 16, lr: 5.61e-04
2022-05-29 03:09:14,194 INFO [train.py:761] (5/8) Epoch 24, batch 200, loss[loss=0.2204, simple_loss=0.3185, pruned_loss=0.06117, over 4790.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3055, pruned_loss=0.06268, over 614329.83 frames.], batch size: 20, lr: 5.61e-04
2022-05-29 03:09:52,153 INFO [train.py:761] (5/8) Epoch 24, batch 250, loss[loss=0.2194, simple_loss=0.307, pruned_loss=0.06589, over 4854.00 frames.], tot_loss[loss=0.2141, simple_loss=0.3044, pruned_loss=0.06193, over 692920.84 frames.], batch size: 14, lr: 5.61e-04
2022-05-29 03:10:30,560 INFO [train.py:761] (5/8) Epoch 24, batch 300, loss[loss=0.2365, simple_loss=0.3198, pruned_loss=0.07666, over 4618.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3053, pruned_loss=0.0625, over 754033.64 frames.], batch size: 12, lr: 5.60e-04
2022-05-29 03:11:08,530 INFO [train.py:761] (5/8) Epoch 24, batch 350, loss[loss=0.2253, simple_loss=0.301, pruned_loss=0.07478, over 4792.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3043, pruned_loss=0.06151, over 802368.31 frames.], batch size: 14, lr: 5.60e-04
2022-05-29 03:11:46,999 INFO [train.py:761] (5/8) Epoch 24, batch 400, loss[loss=0.2041, simple_loss=0.2948, pruned_loss=0.05665, over 4973.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3054, pruned_loss=0.0616, over 837983.73 frames.], batch size: 15, lr: 5.60e-04
2022-05-29 03:12:24,913 INFO [train.py:761] (5/8) Epoch 24, batch 450, loss[loss=0.2143, simple_loss=0.3003, pruned_loss=0.06414, over 4786.00 frames.], tot_loss[loss=0.215, simple_loss=0.3057, pruned_loss=0.06218, over 867140.07 frames.], batch size: 16, lr: 5.60e-04
2022-05-29 03:13:02,970 INFO [train.py:761] (5/8) Epoch 24, batch 500, loss[loss=0.2131, simple_loss=0.2966, pruned_loss=0.0648, over 4730.00 frames.], tot_loss[loss=0.2144, simple_loss=0.3049, pruned_loss=0.06189, over 890346.76 frames.], batch size: 11, lr: 5.60e-04
2022-05-29 03:13:40,855 INFO [train.py:761] (5/8) Epoch 24, batch 550, loss[loss=0.2121, simple_loss=0.3051, pruned_loss=0.05956, over 4975.00 frames.], tot_loss[loss=0.2127, simple_loss=0.3036, pruned_loss=0.0609, over 907910.56 frames.], batch size: 15, lr: 5.60e-04
2022-05-29 03:14:18,732 INFO [train.py:761] (5/8) Epoch 24, batch 600, loss[loss=0.1982, simple_loss=0.3015, pruned_loss=0.04746, over 4983.00 frames.], tot_loss[loss=0.2143, simple_loss=0.305, pruned_loss=0.06179, over 921697.06 frames.], batch size: 14, lr: 5.60e-04
2022-05-29 03:14:56,635 INFO [train.py:761] (5/8) Epoch 24, batch 650, loss[loss=0.2252, simple_loss=0.3033, pruned_loss=0.07358, over 4990.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3052, pruned_loss=0.0616, over 931848.98 frames.], batch size: 13, lr: 5.60e-04
2022-05-29 03:15:34,675 INFO [train.py:761] (5/8) Epoch 24, batch 700, loss[loss=0.2247, simple_loss=0.3074, pruned_loss=0.07096, over 4664.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3069, pruned_loss=0.06268, over 939001.13 frames.], batch size: 12, lr: 5.60e-04
2022-05-29 03:16:12,772 INFO [train.py:761] (5/8) Epoch 24, batch 750, loss[loss=0.2043, simple_loss=0.2876, pruned_loss=0.06052, over 4670.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3073, pruned_loss=0.06325, over 945363.70 frames.], batch size: 12, lr: 5.60e-04
2022-05-29 03:16:51,248 INFO [train.py:761] (5/8) Epoch 24, batch 800, loss[loss=0.2275, simple_loss=0.332, pruned_loss=0.06147, over 4863.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3063, pruned_loss=0.06292, over 950401.37 frames.], batch size: 15, lr: 5.60e-04
2022-05-29 03:17:29,082 INFO [train.py:761] (5/8) Epoch 24, batch 850, loss[loss=0.2633, simple_loss=0.342, pruned_loss=0.09228, over 4853.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3079, pruned_loss=0.06364, over 953692.55 frames.], batch size: 13, lr: 5.59e-04
2022-05-29 03:18:06,683 INFO [train.py:761] (5/8) Epoch 24, batch 900, loss[loss=0.2096, simple_loss=0.2902, pruned_loss=0.0645, over 4776.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3075, pruned_loss=0.06381, over 955147.80 frames.], batch size: 13, lr: 5.59e-04
2022-05-29 03:18:44,250 INFO [train.py:761] (5/8) Epoch 24, batch 950, loss[loss=0.226, simple_loss=0.3104, pruned_loss=0.07079, over 4810.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3073, pruned_loss=0.06376, over 957375.97 frames.], batch size: 20, lr: 5.59e-04
2022-05-29 03:19:22,090 INFO [train.py:761] (5/8) Epoch 24, batch 1000, loss[loss=0.2289, simple_loss=0.32, pruned_loss=0.06888, over 4874.00 frames.], tot_loss[loss=0.2192, simple_loss=0.309, pruned_loss=0.06472, over 960091.66 frames.], batch size: 18, lr: 5.59e-04
2022-05-29 03:19:59,895 INFO [train.py:761] (5/8) Epoch 24, batch 1050, loss[loss=0.2065, simple_loss=0.2867, pruned_loss=0.06316, over 4669.00 frames.], tot_loss[loss=0.2191, simple_loss=0.3088, pruned_loss=0.06467, over 961094.35 frames.], batch size: 12, lr: 5.59e-04
2022-05-29 03:20:37,687 INFO [train.py:761] (5/8) Epoch 24, batch 1100, loss[loss=0.255, simple_loss=0.3602, pruned_loss=0.07489, over 4890.00 frames.], tot_loss[loss=0.2191, simple_loss=0.309, pruned_loss=0.06465, over 962967.03 frames.], batch size: 15, lr: 5.59e-04
2022-05-29 03:21:15,804 INFO [train.py:761] (5/8) Epoch 24, batch 1150, loss[loss=0.1911, simple_loss=0.2729, pruned_loss=0.0547, over 4801.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3083, pruned_loss=0.06443, over 963763.09 frames.], batch size: 12, lr: 5.59e-04
2022-05-29 03:21:53,749 INFO [train.py:761] (5/8) Epoch 24, batch 1200, loss[loss=0.1741, simple_loss=0.256, pruned_loss=0.04612, over 4736.00 frames.], tot_loss[loss=0.2198, simple_loss=0.3095, pruned_loss=0.06504, over 964418.64 frames.], batch size: 11, lr: 5.59e-04
2022-05-29 03:22:31,622 INFO [train.py:761] (5/8) Epoch 24, batch 1250, loss[loss=0.2755, simple_loss=0.3501, pruned_loss=0.1004, over 4880.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3084, pruned_loss=0.06439, over 964236.64 frames.], batch size: 15, lr: 5.59e-04
2022-05-29 03:23:10,392 INFO [train.py:761] (5/8) Epoch 24, batch 1300, loss[loss=0.1905, simple_loss=0.2789, pruned_loss=0.05109, over 4953.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3069, pruned_loss=0.06383, over 964578.52 frames.], batch size: 11, lr: 5.59e-04
2022-05-29 03:23:48,658 INFO [train.py:761] (5/8) Epoch 24, batch 1350, loss[loss=0.2201, simple_loss=0.3092, pruned_loss=0.0655, over 4889.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3083, pruned_loss=0.06419, over 965355.75 frames.], batch size: 17, lr: 5.59e-04
2022-05-29 03:24:26,814 INFO [train.py:761] (5/8) Epoch 24, batch 1400, loss[loss=0.2194, simple_loss=0.3032, pruned_loss=0.06775, over 4808.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3089, pruned_loss=0.06424, over 964441.67 frames.], batch size: 16, lr: 5.58e-04
2022-05-29 03:25:04,662 INFO [train.py:761] (5/8) Epoch 24, batch 1450, loss[loss=0.1741, simple_loss=0.2663, pruned_loss=0.04096, over 4883.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3087, pruned_loss=0.06417, over 965680.17 frames.], batch size: 12, lr: 5.58e-04
2022-05-29 03:25:43,001 INFO [train.py:761] (5/8) Epoch 24, batch 1500, loss[loss=0.2107, simple_loss=0.2929, pruned_loss=0.06427, over 4740.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3087, pruned_loss=0.06394, over 965615.56 frames.], batch size: 12, lr: 5.58e-04
2022-05-29 03:26:21,307 INFO [train.py:761] (5/8) Epoch 24, batch 1550, loss[loss=0.1847, simple_loss=0.2656, pruned_loss=0.05184, over 4829.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3082, pruned_loss=0.06373, over 965473.71 frames.], batch size: 11, lr: 5.58e-04
2022-05-29 03:26:59,740 INFO [train.py:761] (5/8) Epoch 24, batch 1600, loss[loss=0.2024, simple_loss=0.3041, pruned_loss=0.05039, over 4792.00 frames.], tot_loss[loss=0.2191, simple_loss=0.309, pruned_loss=0.06456, over 965203.50 frames.], batch size: 14, lr: 5.58e-04
2022-05-29 03:27:37,875 INFO [train.py:761] (5/8) Epoch 24, batch 1650, loss[loss=0.2261, simple_loss=0.3167, pruned_loss=0.06773, over 4922.00 frames.], tot_loss[loss=0.2204, simple_loss=0.31, pruned_loss=0.0654, over 964956.78 frames.], batch size: 14, lr: 5.58e-04
2022-05-29 03:28:16,814 INFO [train.py:761] (5/8) Epoch 24, batch 1700, loss[loss=0.2587, simple_loss=0.3238, pruned_loss=0.09681, over 4911.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3101, pruned_loss=0.06521, over 965726.57 frames.], batch size: 13, lr: 5.58e-04
2022-05-29 03:28:55,259 INFO [train.py:761] (5/8) Epoch 24, batch 1750, loss[loss=0.2013, simple_loss=0.2792, pruned_loss=0.06169, over 4732.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3105, pruned_loss=0.06506, over 966520.10 frames.], batch size: 11, lr: 5.58e-04
2022-05-29 03:29:33,042 INFO [train.py:761] (5/8) Epoch 24, batch 1800, loss[loss=0.205, simple_loss=0.2992, pruned_loss=0.05543, over 4806.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3095, pruned_loss=0.06485, over 966887.85 frames.], batch size: 12, lr: 5.58e-04
2022-05-29 03:30:11,010 INFO [train.py:761] (5/8) Epoch 24, batch 1850, loss[loss=0.2117, simple_loss=0.3022, pruned_loss=0.06059, over 4733.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3113, pruned_loss=0.06575, over 967637.47 frames.], batch size: 12, lr: 5.58e-04
2022-05-29 03:30:48,776 INFO [train.py:761] (5/8) Epoch 24, batch 1900, loss[loss=0.192, simple_loss=0.2946, pruned_loss=0.04476, over 4979.00 frames.], tot_loss[loss=0.2198, simple_loss=0.3098, pruned_loss=0.0649, over 967449.12 frames.], batch size: 16, lr: 5.58e-04
2022-05-29 03:31:26,365 INFO [train.py:761] (5/8) Epoch 24, batch 1950, loss[loss=0.2306, simple_loss=0.3191, pruned_loss=0.07101, over 4787.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3101, pruned_loss=0.06523, over 966858.69 frames.], batch size: 14, lr: 5.58e-04
2022-05-29 03:32:04,748 INFO [train.py:761] (5/8) Epoch 24, batch 2000, loss[loss=0.2325, simple_loss=0.318, pruned_loss=0.07355, over 4725.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3094, pruned_loss=0.06477, over 967014.04 frames.], batch size: 12, lr: 5.57e-04
2022-05-29 03:32:42,206 INFO [train.py:761] (5/8) Epoch 24, batch 2050, loss[loss=0.2076, simple_loss=0.2862, pruned_loss=0.06452, over 4652.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3102, pruned_loss=0.06534, over 967264.77 frames.], batch size: 11, lr: 5.57e-04
2022-05-29 03:33:20,472 INFO [train.py:761] (5/8) Epoch 24, batch 2100, loss[loss=0.2322, simple_loss=0.2972, pruned_loss=0.08362, over 4831.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3091, pruned_loss=0.06474, over 965371.44 frames.], batch size: 11, lr: 5.57e-04
2022-05-29 03:33:58,444 INFO [train.py:761] (5/8) Epoch 24, batch 2150, loss[loss=0.1747, simple_loss=0.2521, pruned_loss=0.04863, over 4726.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3068, pruned_loss=0.06343, over 964677.31 frames.], batch size: 11, lr: 5.57e-04
2022-05-29 03:34:36,012 INFO [train.py:761] (5/8) Epoch 24, batch 2200, loss[loss=0.2145, simple_loss=0.3192, pruned_loss=0.05486, over 4831.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3073, pruned_loss=0.06348, over 965169.33 frames.], batch size: 18, lr: 5.57e-04
2022-05-29 03:35:14,012 INFO [train.py:761] (5/8) Epoch 24, batch 2250, loss[loss=0.232, simple_loss=0.3194, pruned_loss=0.07231, over 4773.00 frames.], tot_loss[loss=0.2175, simple_loss=0.3077, pruned_loss=0.06362, over 965962.89 frames.], batch size: 15, lr: 5.57e-04
2022-05-29 03:35:52,139 INFO [train.py:761] (5/8) Epoch 24, batch 2300, loss[loss=0.2411, simple_loss=0.3373, pruned_loss=0.07238, over 4670.00 frames.], tot_loss[loss=0.218, simple_loss=0.3086, pruned_loss=0.06372, over 965637.94 frames.], batch size: 13, lr: 5.57e-04
2022-05-29 03:36:30,046 INFO [train.py:761] (5/8) Epoch 24, batch 2350, loss[loss=0.2284, simple_loss=0.3164, pruned_loss=0.0702, over 4826.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3075, pruned_loss=0.06353, over 966073.26 frames.], batch size: 18, lr: 5.57e-04
2022-05-29 03:37:07,968 INFO [train.py:761] (5/8) Epoch 24, batch 2400, loss[loss=0.198, simple_loss=0.2974, pruned_loss=0.04934, over 4978.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3053, pruned_loss=0.0618, over 966759.64 frames.], batch size: 15, lr: 5.57e-04
2022-05-29 03:37:45,699 INFO [train.py:761] (5/8) Epoch 24, batch 2450, loss[loss=0.2139, simple_loss=0.3056, pruned_loss=0.06107, over 4672.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3058, pruned_loss=0.0618, over 966845.63 frames.], batch size: 13, lr: 5.57e-04
2022-05-29 03:38:23,884 INFO [train.py:761] (5/8) Epoch 24, batch 2500, loss[loss=0.2272, simple_loss=0.3069, pruned_loss=0.07378, over 4971.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3068, pruned_loss=0.06228, over 966996.34 frames.], batch size: 12, lr: 5.57e-04
2022-05-29 03:39:01,640 INFO [train.py:761] (5/8) Epoch 24, batch 2550, loss[loss=0.1642, simple_loss=0.249, pruned_loss=0.03966, over 4891.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3064, pruned_loss=0.06263, over 967703.06 frames.], batch size: 12, lr: 5.56e-04
2022-05-29 03:39:40,306 INFO [train.py:761] (5/8) Epoch 24, batch 2600, loss[loss=0.2451, simple_loss=0.3402, pruned_loss=0.07495, over 4890.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3076, pruned_loss=0.06287, over 968069.48 frames.], batch size: 17, lr: 5.56e-04
2022-05-29 03:40:17,860 INFO [train.py:761] (5/8) Epoch 24, batch 2650, loss[loss=0.1939, simple_loss=0.2819, pruned_loss=0.05295, over 4743.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3068, pruned_loss=0.06267, over 967901.87 frames.], batch size: 11, lr: 5.56e-04
2022-05-29 03:40:55,519 INFO [train.py:761] (5/8) Epoch 24, batch 2700, loss[loss=0.226, simple_loss=0.305, pruned_loss=0.07352, over 4732.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3077, pruned_loss=0.06356, over 967515.41 frames.], batch size: 12, lr: 5.56e-04
2022-05-29 03:41:33,272 INFO [train.py:761] (5/8) Epoch 24, batch 2750, loss[loss=0.2003, simple_loss=0.2751, pruned_loss=0.06274, over 4809.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3073, pruned_loss=0.06311, over 967306.75 frames.], batch size: 12, lr: 5.56e-04
2022-05-29 03:42:11,490 INFO [train.py:761] (5/8) Epoch 24, batch 2800, loss[loss=0.2117, simple_loss=0.3187, pruned_loss=0.05233, over 4711.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3073, pruned_loss=0.0628, over 968102.99 frames.], batch size: 14, lr: 5.56e-04
2022-05-29 03:42:49,858 INFO [train.py:761] (5/8) Epoch 24, batch 2850, loss[loss=0.2226, simple_loss=0.3115, pruned_loss=0.0669, over 4664.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3058, pruned_loss=0.06182, over 966890.08 frames.], batch size: 12, lr: 5.56e-04
2022-05-29 03:43:27,710 INFO [train.py:761] (5/8) Epoch 24, batch 2900, loss[loss=0.1866, simple_loss=0.2792, pruned_loss=0.04696, over 4852.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3056, pruned_loss=0.06172, over 967296.94 frames.], batch size: 13, lr: 5.56e-04
2022-05-29 03:44:05,730 INFO [train.py:761] (5/8) Epoch 24, batch 2950, loss[loss=0.2333, simple_loss=0.3309, pruned_loss=0.06789, over 4848.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3068, pruned_loss=0.06234, over 967463.63 frames.], batch size: 14, lr: 5.56e-04
2022-05-29 03:44:43,546 INFO [train.py:761] (5/8) Epoch 24, batch 3000, loss[loss=0.1892, simple_loss=0.2819, pruned_loss=0.04828, over 4786.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3071, pruned_loss=0.06202, over 965950.43 frames.], batch size: 16, lr: 5.56e-04
2022-05-29 03:44:43,546 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 03:44:53,570 INFO [train.py:790] (5/8) Epoch 24, validation: loss=0.2056, simple_loss=0.3068, pruned_loss=0.05216, over 944034.00 frames.
2022-05-29 03:45:31,846 INFO [train.py:761] (5/8) Epoch 24, batch 3050, loss[loss=0.2232, simple_loss=0.303, pruned_loss=0.07168, over 4990.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3071, pruned_loss=0.06225, over 966676.85 frames.], batch size: 13, lr: 5.56e-04
2022-05-29 03:46:09,898 INFO [train.py:761] (5/8) Epoch 24, batch 3100, loss[loss=0.2068, simple_loss=0.2905, pruned_loss=0.06153, over 4573.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3078, pruned_loss=0.06289, over 965229.62 frames.], batch size: 10, lr: 5.55e-04
2022-05-29 03:46:47,476 INFO [train.py:761] (5/8) Epoch 24, batch 3150, loss[loss=0.2116, simple_loss=0.2968, pruned_loss=0.06317, over 4676.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3077, pruned_loss=0.06459, over 965362.99 frames.], batch size: 13, lr: 5.55e-04
2022-05-29 03:47:25,941 INFO [train.py:761] (5/8) Epoch 24, batch 3200, loss[loss=0.2146, simple_loss=0.3286, pruned_loss=0.05034, over 4964.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3099, pruned_loss=0.06672, over 966132.37 frames.], batch size: 16, lr: 5.55e-04
2022-05-29 03:48:03,595 INFO [train.py:761] (5/8) Epoch 24, batch 3250, loss[loss=0.3229, simple_loss=0.3898, pruned_loss=0.128, over 4956.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3114, pruned_loss=0.06901, over 965580.88 frames.], batch size: 16, lr: 5.55e-04
2022-05-29 03:48:41,217 INFO [train.py:761] (5/8) Epoch 24, batch 3300, loss[loss=0.2713, simple_loss=0.3507, pruned_loss=0.09594, over 4853.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3138, pruned_loss=0.07127, over 965406.36 frames.], batch size: 13, lr: 5.55e-04
2022-05-29 03:49:18,897 INFO [train.py:761] (5/8) Epoch 24, batch 3350, loss[loss=0.1839, simple_loss=0.2655, pruned_loss=0.05108, over 4803.00 frames.], tot_loss[loss=0.2288, simple_loss=0.3134, pruned_loss=0.07206, over 965064.99 frames.], batch size: 12, lr: 5.55e-04
2022-05-29 03:49:57,446 INFO [train.py:761] (5/8) Epoch 24, batch 3400, loss[loss=0.237, simple_loss=0.3102, pruned_loss=0.08192, over 4667.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3144, pruned_loss=0.07394, over 965758.53 frames.], batch size: 12, lr: 5.55e-04
2022-05-29 03:50:35,522 INFO [train.py:761] (5/8) Epoch 24, batch 3450, loss[loss=0.2039, simple_loss=0.3061, pruned_loss=0.05079, over 4783.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3147, pruned_loss=0.07527, over 965381.35 frames.], batch size: 13, lr: 5.55e-04
2022-05-29 03:51:13,779 INFO [train.py:761] (5/8) Epoch 24, batch 3500, loss[loss=0.2168, simple_loss=0.3121, pruned_loss=0.06079, over 4979.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3168, pruned_loss=0.07689, over 965137.03 frames.], batch size: 14, lr: 5.55e-04
2022-05-29 03:51:51,474 INFO [train.py:761] (5/8) Epoch 24, batch 3550, loss[loss=0.2235, simple_loss=0.3104, pruned_loss=0.06834, over 4672.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3174, pruned_loss=0.07773, over 965856.53 frames.], batch size: 12, lr: 5.55e-04
2022-05-29 03:52:29,763 INFO [train.py:761] (5/8) Epoch 24, batch 3600, loss[loss=0.2132, simple_loss=0.2859, pruned_loss=0.07025, over 4832.00 frames.], tot_loss[loss=0.2377, simple_loss=0.3179, pruned_loss=0.07871, over 966079.36 frames.], batch size: 11, lr: 5.55e-04
2022-05-29 03:53:07,301 INFO [train.py:761] (5/8) Epoch 24, batch 3650, loss[loss=0.1712, simple_loss=0.2531, pruned_loss=0.04468, over 4727.00 frames.], tot_loss[loss=0.2373, simple_loss=0.3172, pruned_loss=0.07869, over 966034.43 frames.], batch size: 11, lr: 5.55e-04
2022-05-29 03:53:45,634 INFO [train.py:761] (5/8) Epoch 24, batch 3700, loss[loss=0.2355, simple_loss=0.2933, pruned_loss=0.08883, over 4730.00 frames.], tot_loss[loss=0.2393, simple_loss=0.3179, pruned_loss=0.08038, over 966224.40 frames.], batch size: 11, lr: 5.54e-04
2022-05-29 03:54:23,247 INFO [train.py:761] (5/8) Epoch 24, batch 3750, loss[loss=0.2154, simple_loss=0.3083, pruned_loss=0.06121, over 4972.00 frames.], tot_loss[loss=0.241, simple_loss=0.3194, pruned_loss=0.08126, over 966396.48 frames.], batch size: 14, lr: 5.54e-04
2022-05-29 03:55:01,336 INFO [train.py:761] (5/8) Epoch 24, batch 3800, loss[loss=0.2104, simple_loss=0.3023, pruned_loss=0.05919, over 4726.00 frames.], tot_loss[loss=0.2425, simple_loss=0.3209, pruned_loss=0.0821, over 965470.11 frames.], batch size: 13, lr: 5.54e-04
2022-05-29 03:55:39,509 INFO [train.py:761] (5/8) Epoch 24, batch 3850, loss[loss=0.1948, simple_loss=0.2759, pruned_loss=0.05688, over 4732.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3181, pruned_loss=0.08082, over 964703.73 frames.], batch size: 12, lr: 5.54e-04
2022-05-29 03:56:17,644 INFO [train.py:761] (5/8) Epoch 24, batch 3900, loss[loss=0.2459, simple_loss=0.3317, pruned_loss=0.08003, over 4881.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3169, pruned_loss=0.08008, over 966360.85 frames.], batch size: 17, lr: 5.54e-04
2022-05-29 03:56:55,824 INFO [train.py:761] (5/8) Epoch 24, batch 3950, loss[loss=0.2411, simple_loss=0.3019, pruned_loss=0.09017, over 4716.00 frames.], tot_loss[loss=0.2382, simple_loss=0.3167, pruned_loss=0.07984, over 966499.57 frames.], batch size: 11, lr: 5.54e-04
2022-05-29 03:57:34,605 INFO [train.py:761] (5/8) Epoch 24, batch 4000, loss[loss=0.2634, simple_loss=0.3234, pruned_loss=0.1017, over 4917.00 frames.], tot_loss[loss=0.2389, simple_loss=0.3168, pruned_loss=0.08053, over 967297.10 frames.], batch size: 13, lr: 5.54e-04
2022-05-29 03:58:12,923 INFO [train.py:761] (5/8) Epoch 24, batch 4050, loss[loss=0.2606, simple_loss=0.3325, pruned_loss=0.09432, over 4963.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3154, pruned_loss=0.08017, over 966072.45 frames.], batch size: 21, lr: 5.54e-04
2022-05-29 03:58:51,325 INFO [train.py:761] (5/8) Epoch 24, batch 4100, loss[loss=0.2351, simple_loss=0.3174, pruned_loss=0.07639, over 4950.00 frames.], tot_loss[loss=0.237, simple_loss=0.3156, pruned_loss=0.07926, over 967295.16 frames.], batch size: 16, lr: 5.54e-04
2022-05-29 03:59:29,264 INFO [train.py:761] (5/8) Epoch 24, batch 4150, loss[loss=0.2473, simple_loss=0.3288, pruned_loss=0.08288, over 4829.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3149, pruned_loss=0.07881, over 966850.95 frames.], batch size: 25, lr: 5.54e-04
2022-05-29 04:00:07,739 INFO [train.py:761] (5/8) Epoch 24, batch 4200, loss[loss=0.2509, simple_loss=0.3407, pruned_loss=0.08054, over 4783.00 frames.], tot_loss[loss=0.236, simple_loss=0.3148, pruned_loss=0.07862, over 966738.70 frames.], batch size: 14, lr: 5.54e-04
2022-05-29 04:00:46,337 INFO [train.py:761] (5/8) Epoch 24, batch 4250, loss[loss=0.3462, simple_loss=0.397, pruned_loss=0.1477, over 4840.00 frames.], tot_loss[loss=0.2364, simple_loss=0.315, pruned_loss=0.07891, over 968123.99 frames.], batch size: 51, lr: 5.53e-04
2022-05-29 04:01:23,923 INFO [train.py:761] (5/8) Epoch 24, batch 4300, loss[loss=0.2583, simple_loss=0.3269, pruned_loss=0.09487, over 4891.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3143, pruned_loss=0.07832, over 968847.05 frames.], batch size: 17, lr: 5.53e-04
2022-05-29 04:02:02,646 INFO [train.py:761] (5/8) Epoch 24, batch 4350, loss[loss=0.2599, simple_loss=0.3318, pruned_loss=0.09404, over 4837.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3146, pruned_loss=0.07849, over 967540.32 frames.], batch size: 25, lr: 5.53e-04
2022-05-29 04:02:41,273 INFO [train.py:761] (5/8) Epoch 24, batch 4400, loss[loss=0.2476, simple_loss=0.3267, pruned_loss=0.08429, over 4709.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3155, pruned_loss=0.07985, over 966769.61 frames.], batch size: 14, lr: 5.53e-04
2022-05-29 04:03:19,217 INFO [train.py:761] (5/8) Epoch 24, batch 4450, loss[loss=0.2456, simple_loss=0.3233, pruned_loss=0.08397, over 4913.00 frames.], tot_loss[loss=0.2368, simple_loss=0.315, pruned_loss=0.0793, over 967421.79 frames.], batch size: 17, lr: 5.53e-04
2022-05-29 04:03:57,599 INFO [train.py:761] (5/8) Epoch 24, batch 4500, loss[loss=0.222, simple_loss=0.2891, pruned_loss=0.07743, over 4808.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3136, pruned_loss=0.07809, over 966486.51 frames.], batch size: 12, lr: 5.53e-04
2022-05-29 04:04:35,455 INFO [train.py:761] (5/8) Epoch 24, batch 4550, loss[loss=0.2201, simple_loss=0.3088, pruned_loss=0.06575, over 4813.00 frames.], tot_loss[loss=0.2348, simple_loss=0.314, pruned_loss=0.07777, over 966154.92 frames.], batch size: 18, lr: 5.53e-04
2022-05-29 04:05:13,753 INFO [train.py:761] (5/8) Epoch 24, batch 4600, loss[loss=0.1898, simple_loss=0.2673, pruned_loss=0.05613, over 4843.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3144, pruned_loss=0.0777, over 965871.42 frames.], batch size: 11, lr: 5.53e-04
2022-05-29 04:05:52,159 INFO [train.py:761] (5/8) Epoch 24, batch 4650, loss[loss=0.2308, simple_loss=0.311, pruned_loss=0.07532, over 4779.00 frames.], tot_loss[loss=0.2365, simple_loss=0.316, pruned_loss=0.07851, over 965759.80 frames.], batch size: 13, lr: 5.53e-04
2022-05-29 04:06:30,203 INFO [train.py:761] (5/8) Epoch 24, batch 4700, loss[loss=0.2259, simple_loss=0.3054, pruned_loss=0.0732, over 4726.00 frames.], tot_loss[loss=0.2373, simple_loss=0.3154, pruned_loss=0.07957, over 964770.61 frames.], batch size: 12, lr: 5.53e-04
2022-05-29 04:07:08,001 INFO [train.py:761] (5/8) Epoch 24, batch 4750, loss[loss=0.2265, simple_loss=0.3168, pruned_loss=0.06814, over 4669.00 frames.], tot_loss[loss=0.2387, simple_loss=0.3168, pruned_loss=0.08026, over 964740.05 frames.], batch size: 13, lr: 5.53e-04
2022-05-29 04:07:46,684 INFO [train.py:761] (5/8) Epoch 24, batch 4800, loss[loss=0.2711, simple_loss=0.3439, pruned_loss=0.0992, over 4936.00 frames.], tot_loss[loss=0.2398, simple_loss=0.318, pruned_loss=0.08081, over 966258.93 frames.], batch size: 16, lr: 5.53e-04
2022-05-29 04:08:24,703 INFO [train.py:761] (5/8) Epoch 24, batch 4850, loss[loss=0.2167, simple_loss=0.3015, pruned_loss=0.06599, over 4730.00 frames.], tot_loss[loss=0.2387, simple_loss=0.3172, pruned_loss=0.08009, over 966502.36 frames.], batch size: 12, lr: 5.52e-04
2022-05-29 04:09:06,509 INFO [train.py:761] (5/8) Epoch 24, batch 4900, loss[loss=0.2494, simple_loss=0.3171, pruned_loss=0.09085, over 4809.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3177, pruned_loss=0.08033, over 965972.66 frames.], batch size: 12, lr: 5.52e-04
2022-05-29 04:09:43,875 INFO [train.py:761] (5/8) Epoch 24, batch 4950, loss[loss=0.2552, simple_loss=0.3236, pruned_loss=0.09337, over 4954.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3176, pruned_loss=0.07973, over 966313.79 frames.], batch size: 21, lr: 5.52e-04
2022-05-29 04:10:21,881 INFO [train.py:761] (5/8) Epoch 24, batch 5000, loss[loss=0.2225, simple_loss=0.2904, pruned_loss=0.07733, over 4881.00 frames.], tot_loss[loss=0.2394, simple_loss=0.3183, pruned_loss=0.08026, over 965896.47 frames.], batch size: 15, lr: 5.52e-04
2022-05-29 04:11:00,116 INFO [train.py:761] (5/8) Epoch 24, batch 5050, loss[loss=0.2458, simple_loss=0.3339, pruned_loss=0.07887, over 4786.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3171, pruned_loss=0.07958, over 965939.21 frames.], batch size: 14, lr: 5.52e-04
2022-05-29 04:11:38,030 INFO [train.py:761] (5/8) Epoch 24, batch 5100, loss[loss=0.2972, simple_loss=0.3566, pruned_loss=0.1189, over 4872.00 frames.], tot_loss[loss=0.2383, simple_loss=0.3175, pruned_loss=0.07956, over 966455.92 frames.], batch size: 17, lr: 5.52e-04
2022-05-29 04:12:16,404 INFO [train.py:761] (5/8) Epoch 24, batch 5150, loss[loss=0.2755, simple_loss=0.3404, pruned_loss=0.1053, over 4963.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3159, pruned_loss=0.07883, over 965724.42 frames.], batch size: 16, lr: 5.52e-04
2022-05-29 04:12:55,133 INFO [train.py:761] (5/8) Epoch 24, batch 5200, loss[loss=0.2355, simple_loss=0.3052, pruned_loss=0.08294, over 4992.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3155, pruned_loss=0.07863, over 966525.29 frames.], batch size: 13, lr: 5.52e-04
2022-05-29 04:13:33,651 INFO [train.py:761] (5/8) Epoch 24, batch 5250, loss[loss=0.2324, simple_loss=0.2934, pruned_loss=0.0857, over 4813.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3154, pruned_loss=0.07824, over 966756.26 frames.], batch size: 12, lr: 5.52e-04
2022-05-29 04:14:12,327 INFO [train.py:761] (5/8) Epoch 24, batch 5300, loss[loss=0.2453, simple_loss=0.3218, pruned_loss=0.08439, over 4792.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3146, pruned_loss=0.07855, over 966699.69 frames.], batch size: 14, lr: 5.52e-04
2022-05-29 04:14:50,858 INFO [train.py:761] (5/8) Epoch 24, batch 5350, loss[loss=0.1996, simple_loss=0.2745, pruned_loss=0.06232, over 4991.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3138, pruned_loss=0.07797, over 966755.88 frames.], batch size: 13, lr: 5.52e-04
2022-05-29 04:15:28,726 INFO [train.py:761] (5/8) Epoch 24, batch 5400, loss[loss=0.2562, simple_loss=0.3256, pruned_loss=0.09337, over 4978.00 frames.], tot_loss[loss=0.234, simple_loss=0.3126, pruned_loss=0.07771, over 966213.95 frames.], batch size: 14, lr: 5.51e-04
2022-05-29 04:16:07,228 INFO [train.py:761] (5/8) Epoch 24, batch 5450, loss[loss=0.223, simple_loss=0.3098, pruned_loss=0.06812, over 4813.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3138, pruned_loss=0.07833, over 966942.11 frames.], batch size: 16, lr: 5.51e-04
2022-05-29 04:16:45,744 INFO [train.py:761] (5/8) Epoch 24, batch 5500, loss[loss=0.2494, simple_loss=0.3217, pruned_loss=0.08861, over 4915.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3141, pruned_loss=0.0784, over 966795.74 frames.], batch size: 14, lr: 5.51e-04
2022-05-29 04:17:23,364 INFO [train.py:761] (5/8) Epoch 24, batch 5550, loss[loss=0.2422, simple_loss=0.3257, pruned_loss=0.07936, over 4842.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3136, pruned_loss=0.07808, over 966319.19 frames.], batch size: 13, lr: 5.51e-04
2022-05-29 04:18:01,785 INFO [train.py:761] (5/8) Epoch 24, batch 5600, loss[loss=0.2202, simple_loss=0.3033, pruned_loss=0.06853, over 4812.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3137, pruned_loss=0.07775, over 965582.30 frames.], batch size: 16, lr: 5.51e-04
2022-05-29 04:18:40,248 INFO [train.py:761] (5/8) Epoch 24, batch 5650, loss[loss=0.2312, simple_loss=0.3195, pruned_loss=0.07139, over 4973.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3153, pruned_loss=0.07868, over 965675.97 frames.], batch size: 14, lr: 5.51e-04
2022-05-29 04:19:18,059 INFO [train.py:761] (5/8) Epoch 24, batch 5700, loss[loss=0.2548, simple_loss=0.3349, pruned_loss=0.08736, over 4948.00 frames.], tot_loss[loss=0.2357, simple_loss=0.315, pruned_loss=0.07824, over 966360.65 frames.], batch size: 16, lr: 5.51e-04
2022-05-29 04:19:56,209 INFO [train.py:761] (5/8) Epoch 24, batch 5750, loss[loss=0.1978, simple_loss=0.2805, pruned_loss=0.0576, over 4851.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3145, pruned_loss=0.07793, over 965317.19 frames.], batch size: 14, lr: 5.51e-04
2022-05-29 04:20:34,781 INFO [train.py:761] (5/8) Epoch 24, batch 5800, loss[loss=0.3109, simple_loss=0.3802, pruned_loss=0.1208, over 4937.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3159, pruned_loss=0.07837, over 965473.67 frames.], batch size: 47, lr: 5.51e-04
2022-05-29 04:21:12,428 INFO [train.py:761] (5/8) Epoch 24, batch 5850, loss[loss=0.185, simple_loss=0.2728, pruned_loss=0.04853, over 4991.00 frames.], tot_loss[loss=0.236, simple_loss=0.3159, pruned_loss=0.0781, over 965601.77 frames.], batch size: 13, lr: 5.51e-04
2022-05-29 04:21:50,747 INFO [train.py:761] (5/8) Epoch 24, batch 5900, loss[loss=0.2498, simple_loss=0.3223, pruned_loss=0.08869, over 4977.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3154, pruned_loss=0.07789, over 964937.50 frames.], batch size: 14, lr: 5.51e-04
2022-05-29 04:22:28,528 INFO [train.py:761] (5/8) Epoch 24, batch 5950, loss[loss=0.2327, simple_loss=0.3324, pruned_loss=0.06646, over 4847.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3152, pruned_loss=0.07748, over 964524.23 frames.], batch size: 18, lr: 5.51e-04
2022-05-29 04:23:06,919 INFO [train.py:761] (5/8) Epoch 24, batch 6000, loss[loss=0.2165, simple_loss=0.31, pruned_loss=0.06153, over 4732.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3159, pruned_loss=0.07792, over 965590.18 frames.], batch size: 12, lr: 5.50e-04
2022-05-29 04:23:06,919 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 04:23:16,883 INFO [train.py:790] (5/8) Epoch 24, validation: loss=0.1992, simple_loss=0.3041, pruned_loss=0.04714, over 944034.00 frames.
2022-05-29 04:23:55,118 INFO [train.py:761] (5/8) Epoch 24, batch 6050, loss[loss=0.1845, simple_loss=0.2676, pruned_loss=0.05073, over 4974.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3159, pruned_loss=0.07784, over 965734.49 frames.], batch size: 11, lr: 5.50e-04
2022-05-29 04:24:34,066 INFO [train.py:761] (5/8) Epoch 24, batch 6100, loss[loss=0.2714, simple_loss=0.3389, pruned_loss=0.1019, over 4897.00 frames.], tot_loss[loss=0.236, simple_loss=0.316, pruned_loss=0.07796, over 965412.22 frames.], batch size: 48, lr: 5.50e-04
2022-05-29 04:25:13,382 INFO [train.py:761] (5/8) Epoch 24, batch 6150, loss[loss=0.1983, simple_loss=0.2913, pruned_loss=0.0527, over 4918.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3142, pruned_loss=0.07734, over 965341.88 frames.], batch size: 13, lr: 5.50e-04
2022-05-29 04:25:51,591 INFO [train.py:761] (5/8) Epoch 24, batch 6200, loss[loss=0.2239, simple_loss=0.2883, pruned_loss=0.07973, over 4542.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3143, pruned_loss=0.07791, over 964550.64 frames.], batch size: 10, lr: 5.50e-04
2022-05-29 04:26:29,234 INFO [train.py:761] (5/8) Epoch 24, batch 6250, loss[loss=0.2462, simple_loss=0.3281, pruned_loss=0.08218, over 4921.00 frames.], tot_loss[loss=0.2359, simple_loss=0.315, pruned_loss=0.07839, over 965164.31 frames.], batch size: 13, lr: 5.50e-04
2022-05-29 04:27:07,464 INFO [train.py:761] (5/8) Epoch 24, batch 6300, loss[loss=0.2254, simple_loss=0.3064, pruned_loss=0.07223, over 4679.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3163, pruned_loss=0.07896, over 965706.31 frames.], batch size: 13, lr: 5.50e-04
2022-05-29 04:27:45,175 INFO [train.py:761] (5/8) Epoch 24, batch 6350, loss[loss=0.2308, simple_loss=0.3254, pruned_loss=0.06809, over 4780.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3157, pruned_loss=0.07844, over 965615.10 frames.], batch size: 14, lr: 5.50e-04
2022-05-29 04:28:23,670 INFO [train.py:761] (5/8) Epoch 24, batch 6400, loss[loss=0.2238, simple_loss=0.3202, pruned_loss=0.06372, over 4791.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3153, pruned_loss=0.07802, over 965685.94 frames.], batch size: 13, lr: 5.50e-04
2022-05-29 04:29:01,576 INFO [train.py:761] (5/8) Epoch 24, batch 6450, loss[loss=0.2018, simple_loss=0.2826, pruned_loss=0.06057, over 4931.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3135, pruned_loss=0.07705, over 966006.59 frames.], batch size: 13, lr: 5.50e-04
2022-05-29 04:29:40,050 INFO [train.py:761] (5/8) Epoch 24, batch 6500, loss[loss=0.281, simple_loss=0.347, pruned_loss=0.1075, over 4730.00 frames.], tot_loss[loss=0.236, simple_loss=0.3152, pruned_loss=0.07838, over 965951.37 frames.], batch size: 12, lr: 5.50e-04
2022-05-29 04:30:18,289 INFO [train.py:761] (5/8) Epoch 24, batch 6550, loss[loss=0.2001, simple_loss=0.2821, pruned_loss=0.05912, over 4737.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3141, pruned_loss=0.07818, over 966277.96 frames.], batch size: 11, lr: 5.50e-04
2022-05-29 04:30:56,746 INFO [train.py:761] (5/8) Epoch 24, batch 6600, loss[loss=0.192, simple_loss=0.2742, pruned_loss=0.05489, over 4852.00 frames.], tot_loss[loss=0.236, simple_loss=0.3151, pruned_loss=0.07845, over 965691.18 frames.], batch size: 13, lr: 5.49e-04
2022-05-29 04:31:35,643 INFO [train.py:761] (5/8) Epoch 24, batch 6650, loss[loss=0.2288, simple_loss=0.3117, pruned_loss=0.07291, over 4674.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3161, pruned_loss=0.07852, over 965851.86 frames.], batch size: 13, lr: 5.49e-04
2022-05-29 04:32:13,846 INFO [train.py:761] (5/8) Epoch 24, batch 6700, loss[loss=0.238, simple_loss=0.3142, pruned_loss=0.0809, over 4845.00 frames.], tot_loss[loss=0.2379, simple_loss=0.317, pruned_loss=0.07941, over 965711.29 frames.], batch size: 13, lr: 5.49e-04
2022-05-29 04:33:09,055 INFO [train.py:761] (5/8) Epoch 25, batch 0, loss[loss=0.2088, simple_loss=0.3099, pruned_loss=0.05381, over 4955.00 frames.], tot_loss[loss=0.2088, simple_loss=0.3099, pruned_loss=0.05381, over 4955.00 frames.], batch size: 16, lr: 5.49e-04
2022-05-29 04:33:47,325 INFO [train.py:761] (5/8) Epoch 25, batch 50, loss[loss=0.1704, simple_loss=0.2671, pruned_loss=0.03683, over 4919.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3078, pruned_loss=0.06482, over 218629.74 frames.], batch size: 13, lr: 5.49e-04
2022-05-29 04:34:25,146 INFO [train.py:761] (5/8) Epoch 25, batch 100, loss[loss=0.1764, simple_loss=0.266, pruned_loss=0.04334, over 4737.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3015, pruned_loss=0.06144, over 383265.51 frames.], batch size: 11, lr: 5.49e-04
2022-05-29 04:35:03,143 INFO [train.py:761] (5/8) Epoch 25, batch 150, loss[loss=0.2066, simple_loss=0.3048, pruned_loss=0.05423, over 4993.00 frames.], tot_loss[loss=0.2114, simple_loss=0.3013, pruned_loss=0.06079, over 512899.16 frames.], batch size: 13, lr: 5.49e-04
2022-05-29 04:35:41,604 INFO [train.py:761] (5/8) Epoch 25, batch 200, loss[loss=0.2464, simple_loss=0.338, pruned_loss=0.07738, over 4971.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3027, pruned_loss=0.06151, over 613076.97 frames.], batch size: 15, lr: 5.49e-04
2022-05-29 04:36:19,441 INFO [train.py:761] (5/8) Epoch 25, batch 250, loss[loss=0.1982, simple_loss=0.285, pruned_loss=0.05572, over 4729.00 frames.], tot_loss[loss=0.2125, simple_loss=0.3027, pruned_loss=0.06121, over 691995.77 frames.], batch size: 12, lr: 5.49e-04
2022-05-29 04:36:57,852 INFO [train.py:761] (5/8) Epoch 25, batch 300, loss[loss=0.1761, simple_loss=0.2722, pruned_loss=0.04002, over 4801.00 frames.], tot_loss[loss=0.2111, simple_loss=0.3015, pruned_loss=0.06037, over 752149.47 frames.], batch size: 12, lr: 5.49e-04
2022-05-29 04:37:36,283 INFO [train.py:761] (5/8) Epoch 25, batch 350, loss[loss=0.2077, simple_loss=0.2968, pruned_loss=0.05924, over 4865.00 frames.], tot_loss[loss=0.2102, simple_loss=0.3007, pruned_loss=0.05982, over 799993.84 frames.], batch size: 26, lr: 5.49e-04
2022-05-29 04:38:13,584 INFO [train.py:761] (5/8) Epoch 25, batch 400, loss[loss=0.2002, simple_loss=0.2799, pruned_loss=0.06029, over 4978.00 frames.], tot_loss[loss=0.2102, simple_loss=0.3006, pruned_loss=0.05995, over 837274.29 frames.], batch size: 12, lr: 5.49e-04
2022-05-29 04:38:51,507 INFO [train.py:761] (5/8) Epoch 25, batch 450, loss[loss=0.1973, simple_loss=0.2854, pruned_loss=0.0546, over 4783.00 frames.], tot_loss[loss=0.2106, simple_loss=0.3015, pruned_loss=0.05989, over 865844.96 frames.], batch size: 15, lr: 5.48e-04
2022-05-29 04:39:29,317 INFO [train.py:761] (5/8) Epoch 25, batch 500, loss[loss=0.1973, simple_loss=0.2887, pruned_loss=0.05294, over 4840.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3013, pruned_loss=0.05945, over 888652.45 frames.], batch size: 13, lr: 5.48e-04
2022-05-29 04:40:07,846 INFO [train.py:761] (5/8) Epoch 25, batch 550, loss[loss=0.2037, simple_loss=0.3023, pruned_loss=0.05258, over 4902.00 frames.], tot_loss[loss=0.2124, simple_loss=0.3037, pruned_loss=0.06054, over 906664.22 frames.], batch size: 14, lr: 5.48e-04
2022-05-29 04:40:45,318 INFO [train.py:761] (5/8) Epoch 25, batch 600, loss[loss=0.1977, simple_loss=0.2893, pruned_loss=0.05303, over 4840.00 frames.], tot_loss[loss=0.2118, simple_loss=0.303, pruned_loss=0.0603, over 920178.43 frames.], batch size: 18, lr: 5.48e-04
2022-05-29 04:41:23,450 INFO [train.py:761] (5/8) Epoch 25, batch 650, loss[loss=0.1867, simple_loss=0.2667, pruned_loss=0.0533, over 4838.00 frames.], tot_loss[loss=0.2126, simple_loss=0.3039, pruned_loss=0.06064, over 930817.60 frames.], batch size: 11, lr: 5.48e-04
2022-05-29 04:42:01,612 INFO [train.py:761] (5/8) Epoch 25, batch 700, loss[loss=0.2604, simple_loss=0.3503, pruned_loss=0.08521, over 4851.00 frames.], tot_loss[loss=0.2128, simple_loss=0.3039, pruned_loss=0.06088, over 939140.67 frames.], batch size: 18, lr: 5.48e-04
2022-05-29 04:42:39,597 INFO [train.py:761] (5/8) Epoch 25, batch 750, loss[loss=0.2097, simple_loss=0.3063, pruned_loss=0.05655, over 4974.00 frames.], tot_loss[loss=0.213, simple_loss=0.3041, pruned_loss=0.06097, over 945976.82 frames.], batch size: 26, lr: 5.48e-04
2022-05-29 04:43:17,552 INFO [train.py:761] (5/8) Epoch 25, batch 800, loss[loss=0.1949, simple_loss=0.2885, pruned_loss=0.05067, over 4932.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3058, pruned_loss=0.06202, over 950451.15 frames.], batch size: 13, lr: 5.48e-04
2022-05-29 04:43:55,388 INFO [train.py:761] (5/8) Epoch 25, batch 850, loss[loss=0.2055, simple_loss=0.2682, pruned_loss=0.07141, over 4738.00 frames.], tot_loss[loss=0.2156, simple_loss=0.306, pruned_loss=0.06255, over 954833.00 frames.], batch size: 11, lr: 5.48e-04
2022-05-29 04:44:32,859 INFO [train.py:761] (5/8) Epoch 25, batch 900, loss[loss=0.2103, simple_loss=0.3063, pruned_loss=0.05713, over 4874.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3063, pruned_loss=0.06262, over 958331.08 frames.], batch size: 17, lr: 5.48e-04
2022-05-29 04:45:10,310 INFO [train.py:761] (5/8) Epoch 25, batch 950, loss[loss=0.1945, simple_loss=0.2818, pruned_loss=0.05358, over 4721.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3061, pruned_loss=0.06305, over 960071.89 frames.], batch size: 12, lr: 5.48e-04
2022-05-29 04:45:47,974 INFO [train.py:761] (5/8) Epoch 25, batch 1000, loss[loss=0.2602, simple_loss=0.3493, pruned_loss=0.08551, over 4855.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3063, pruned_loss=0.06305, over 961046.10 frames.], batch size: 14, lr: 5.47e-04
2022-05-29 04:46:26,167 INFO [train.py:761] (5/8) Epoch 25, batch 1050, loss[loss=0.2184, simple_loss=0.3017, pruned_loss=0.06757, over 4669.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3074, pruned_loss=0.06357, over 962201.88 frames.], batch size: 12, lr: 5.47e-04
2022-05-29 04:47:03,732 INFO [train.py:761] (5/8) Epoch 25, batch 1100, loss[loss=0.2188, simple_loss=0.3099, pruned_loss=0.0639, over 4921.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3086, pruned_loss=0.06458, over 962799.98 frames.], batch size: 13, lr: 5.47e-04
2022-05-29 04:47:41,743 INFO [train.py:761] (5/8) Epoch 25, batch 1150, loss[loss=0.2612, simple_loss=0.3539, pruned_loss=0.08423, over 4892.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3082, pruned_loss=0.06396, over 962858.16 frames.], batch size: 49, lr: 5.47e-04
2022-05-29 04:48:19,350 INFO [train.py:761] (5/8) Epoch 25, batch 1200, loss[loss=0.2046, simple_loss=0.3014, pruned_loss=0.05392, over 4976.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3075, pruned_loss=0.063, over 962861.92 frames.], batch size: 15, lr: 5.47e-04
2022-05-29 04:48:58,026 INFO [train.py:761] (5/8) Epoch 25, batch 1250, loss[loss=0.2367, simple_loss=0.3173, pruned_loss=0.07811, over 4988.00 frames.], tot_loss[loss=0.2175, simple_loss=0.308, pruned_loss=0.06347, over 964311.39 frames.], batch size: 13, lr: 5.47e-04
2022-05-29 04:49:35,596 INFO [train.py:761] (5/8) Epoch 25, batch 1300, loss[loss=0.2167, simple_loss=0.2874, pruned_loss=0.07303, over 4808.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3075, pruned_loss=0.06362, over 964805.41 frames.], batch size: 12, lr: 5.47e-04
2022-05-29 04:50:13,633 INFO [train.py:761] (5/8) Epoch 25, batch 1350, loss[loss=0.2864, simple_loss=0.3669, pruned_loss=0.103, over 4919.00 frames.], tot_loss[loss=0.218, simple_loss=0.3082, pruned_loss=0.06386, over 966457.62 frames.], batch size: 49, lr: 5.47e-04
2022-05-29 04:50:51,594 INFO [train.py:761] (5/8) Epoch 25, batch 1400, loss[loss=0.2082, simple_loss=0.2872, pruned_loss=0.06463, over 4985.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3083, pruned_loss=0.06377, over 966779.81 frames.], batch size: 11, lr: 5.47e-04
2022-05-29 04:51:29,746 INFO [train.py:761] (5/8) Epoch 25, batch 1450, loss[loss=0.1997, simple_loss=0.2894, pruned_loss=0.05493, over 4908.00 frames.], tot_loss[loss=0.2175, simple_loss=0.308, pruned_loss=0.06354, over 966838.96 frames.], batch size: 14, lr: 5.47e-04
2022-05-29 04:52:07,576 INFO [train.py:761] (5/8) Epoch 25, batch 1500, loss[loss=0.1687, simple_loss=0.2502, pruned_loss=0.04364, over 4849.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3076, pruned_loss=0.06346, over 966495.32 frames.], batch size: 11, lr: 5.47e-04
2022-05-29 04:52:45,227 INFO [train.py:761] (5/8) Epoch 25, batch 1550, loss[loss=0.2188, simple_loss=0.3199, pruned_loss=0.05882, over 4861.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3083, pruned_loss=0.06355, over 966988.88 frames.], batch size: 17, lr: 5.47e-04
2022-05-29 04:53:22,947 INFO [train.py:761] (5/8) Epoch 25, batch 1600, loss[loss=0.1824, simple_loss=0.2752, pruned_loss=0.04477, over 4855.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3091, pruned_loss=0.06407, over 967650.96 frames.], batch size: 13, lr: 5.46e-04
2022-05-29 04:54:01,149 INFO [train.py:761] (5/8) Epoch 25, batch 1650, loss[loss=0.249, simple_loss=0.3389, pruned_loss=0.07953, over 4799.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3092, pruned_loss=0.06395, over 967032.55 frames.], batch size: 16, lr: 5.46e-04
2022-05-29 04:54:38,977 INFO [train.py:761] (5/8) Epoch 25, batch 1700, loss[loss=0.2371, simple_loss=0.3198, pruned_loss=0.07718, over 4927.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3102, pruned_loss=0.06447, over 965882.88 frames.], batch size: 13, lr: 5.46e-04
2022-05-29 04:55:17,033 INFO [train.py:761] (5/8) Epoch 25, batch 1750, loss[loss=0.1903, simple_loss=0.2928, pruned_loss=0.04389, over 4974.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3102, pruned_loss=0.0642, over 965776.49 frames.], batch size: 14, lr: 5.46e-04
2022-05-29 04:55:55,181 INFO [train.py:761] (5/8) Epoch 25, batch 1800, loss[loss=0.1974, simple_loss=0.2944, pruned_loss=0.05014, over 4659.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3102, pruned_loss=0.06421, over 965580.78 frames.], batch size: 12, lr: 5.46e-04
2022-05-29 04:56:40,485 INFO [train.py:761] (5/8) Epoch 25, batch 1850, loss[loss=0.197, simple_loss=0.2881, pruned_loss=0.0529, over 4868.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3092, pruned_loss=0.06326, over 966917.92 frames.], batch size: 17, lr: 5.46e-04
2022-05-29 04:57:18,928 INFO [train.py:761] (5/8) Epoch 25, batch 1900, loss[loss=0.2141, simple_loss=0.3119, pruned_loss=0.0581, over 4674.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3086, pruned_loss=0.06292, over 966018.86 frames.], batch size: 13, lr: 5.46e-04
2022-05-29 04:57:57,184 INFO [train.py:761] (5/8) Epoch 25, batch 1950, loss[loss=0.2055, simple_loss=0.3014, pruned_loss=0.05479, over 4916.00 frames.], tot_loss[loss=0.217, simple_loss=0.3081, pruned_loss=0.06295, over 966310.06 frames.], batch size: 14, lr: 5.46e-04
2022-05-29 04:58:35,282 INFO [train.py:761] (5/8) Epoch 25, batch 2000, loss[loss=0.2297, simple_loss=0.3105, pruned_loss=0.07439, over 4862.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3086, pruned_loss=0.06357, over 966706.49 frames.], batch size: 14, lr: 5.46e-04
2022-05-29 04:59:13,458 INFO [train.py:761] (5/8) Epoch 25, batch 2050, loss[loss=0.1999, simple_loss=0.293, pruned_loss=0.05337, over 4984.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3085, pruned_loss=0.06346, over 966975.99 frames.], batch size: 13, lr: 5.46e-04
2022-05-29 04:59:51,620 INFO [train.py:761] (5/8) Epoch 25, batch 2100, loss[loss=0.218, simple_loss=0.315, pruned_loss=0.06047, over 4782.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3091, pruned_loss=0.06371, over 967029.86 frames.], batch size: 14, lr: 5.46e-04
2022-05-29 05:00:30,004 INFO [train.py:761] (5/8) Epoch 25, batch 2150, loss[loss=0.2119, simple_loss=0.3169, pruned_loss=0.05343, over 4976.00 frames.], tot_loss[loss=0.2172, simple_loss=0.308, pruned_loss=0.06317, over 968073.10 frames.], batch size: 14, lr: 5.46e-04
2022-05-29 05:01:07,939 INFO [train.py:761] (5/8) Epoch 25, batch 2200, loss[loss=0.2642, simple_loss=0.3364, pruned_loss=0.09597, over 4834.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3058, pruned_loss=0.06299, over 967372.78 frames.], batch size: 20, lr: 5.45e-04
2022-05-29 05:01:45,802 INFO [train.py:761] (5/8) Epoch 25, batch 2250, loss[loss=0.1922, simple_loss=0.2848, pruned_loss=0.04983, over 4619.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3064, pruned_loss=0.0631, over 966412.87 frames.], batch size: 12, lr: 5.45e-04
2022-05-29 05:02:23,872 INFO [train.py:761] (5/8) Epoch 25, batch 2300, loss[loss=0.1952, simple_loss=0.2889, pruned_loss=0.05076, over 4806.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3055, pruned_loss=0.06252, over 967061.02 frames.], batch size: 12, lr: 5.45e-04
2022-05-29 05:03:02,190 INFO [train.py:761] (5/8) Epoch 25, batch 2350, loss[loss=0.186, simple_loss=0.2829, pruned_loss=0.04457, over 4856.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3058, pruned_loss=0.06304, over 967526.96 frames.], batch size: 14, lr: 5.45e-04
2022-05-29 05:03:39,971 INFO [train.py:761] (5/8) Epoch 25, batch 2400, loss[loss=0.213, simple_loss=0.3063, pruned_loss=0.05988, over 4933.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3063, pruned_loss=0.0633, over 967068.48 frames.], batch size: 13, lr: 5.45e-04
2022-05-29 05:04:18,114 INFO [train.py:761] (5/8) Epoch 25, batch 2450, loss[loss=0.2065, simple_loss=0.2901, pruned_loss=0.06144, over 4854.00 frames.], tot_loss[loss=0.215, simple_loss=0.3055, pruned_loss=0.06232, over 966399.42 frames.], batch size: 13, lr: 5.45e-04
2022-05-29 05:04:56,139 INFO [train.py:761] (5/8) Epoch 25, batch 2500, loss[loss=0.2411, simple_loss=0.3373, pruned_loss=0.07247, over 4907.00 frames.], tot_loss[loss=0.2155, simple_loss=0.306, pruned_loss=0.06249, over 966033.87 frames.], batch size: 17, lr: 5.45e-04
2022-05-29 05:05:33,949 INFO [train.py:761] (5/8) Epoch 25, batch 2550, loss[loss=0.1921, simple_loss=0.281, pruned_loss=0.05165, over 4663.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3061, pruned_loss=0.0627, over 966675.61 frames.], batch size: 12, lr: 5.45e-04
2022-05-29 05:06:11,455 INFO [train.py:761] (5/8) Epoch 25, batch 2600, loss[loss=0.2524, simple_loss=0.3427, pruned_loss=0.08107, over 4867.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3055, pruned_loss=0.06282, over 966115.04 frames.], batch size: 20, lr: 5.45e-04
2022-05-29 05:06:49,867 INFO [train.py:761] (5/8) Epoch 25, batch 2650, loss[loss=0.229, simple_loss=0.3182, pruned_loss=0.06991, over 4915.00 frames.], tot_loss[loss=0.2141, simple_loss=0.3043, pruned_loss=0.06197, over 966854.19 frames.], batch size: 14, lr: 5.45e-04
2022-05-29 05:07:27,796 INFO [train.py:761] (5/8) Epoch 25, batch 2700, loss[loss=0.2158, simple_loss=0.325, pruned_loss=0.05325, over 4888.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3049, pruned_loss=0.06222, over 965846.99 frames.], batch size: 15, lr: 5.45e-04
2022-05-29 05:08:05,977 INFO [train.py:761] (5/8) Epoch 25, batch 2750, loss[loss=0.2388, simple_loss=0.3086, pruned_loss=0.08448, over 4915.00 frames.], tot_loss[loss=0.215, simple_loss=0.3053, pruned_loss=0.06238, over 966099.95 frames.], batch size: 13, lr: 5.45e-04
2022-05-29 05:08:43,597 INFO [train.py:761] (5/8) Epoch 25, batch 2800, loss[loss=0.2416, simple_loss=0.3332, pruned_loss=0.07494, over 4781.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3067, pruned_loss=0.06259, over 966969.76 frames.], batch size: 15, lr: 5.44e-04
2022-05-29 05:09:21,612 INFO [train.py:761] (5/8) Epoch 25, batch 2850, loss[loss=0.1905, simple_loss=0.2828, pruned_loss=0.04907, over 4852.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3066, pruned_loss=0.0624, over 967606.54 frames.], batch size: 13, lr: 5.44e-04
2022-05-29 05:09:59,142 INFO [train.py:761] (5/8) Epoch 25, batch 2900, loss[loss=0.2055, simple_loss=0.3124, pruned_loss=0.04933, over 4796.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3066, pruned_loss=0.06196, over 967347.63 frames.], batch size: 14, lr: 5.44e-04
2022-05-29 05:10:36,931 INFO [train.py:761] (5/8) Epoch 25, batch 2950, loss[loss=0.2048, simple_loss=0.3053, pruned_loss=0.05214, over 4974.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3067, pruned_loss=0.06151, over 967189.89 frames.], batch size: 14, lr: 5.44e-04
2022-05-29 05:11:14,548 INFO [train.py:761] (5/8) Epoch 25, batch 3000, loss[loss=0.186, simple_loss=0.2866, pruned_loss=0.04268, over 4792.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3063, pruned_loss=0.06113, over 966037.39 frames.], batch size: 13, lr: 5.44e-04
2022-05-29 05:11:14,548 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 05:11:24,457 INFO [train.py:790] (5/8) Epoch 25, validation: loss=0.2072, simple_loss=0.3074, pruned_loss=0.05351, over 944034.00 frames.
2022-05-29 05:12:02,789 INFO [train.py:761] (5/8) Epoch 25, batch 3050, loss[loss=0.249, simple_loss=0.3328, pruned_loss=0.08261, over 4968.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3065, pruned_loss=0.06202, over 967101.65 frames.], batch size: 47, lr: 5.44e-04
2022-05-29 05:12:41,323 INFO [train.py:761] (5/8) Epoch 25, batch 3100, loss[loss=0.2063, simple_loss=0.301, pruned_loss=0.05581, over 4919.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3086, pruned_loss=0.06442, over 966791.42 frames.], batch size: 13, lr: 5.44e-04
2022-05-29 05:13:18,944 INFO [train.py:761] (5/8) Epoch 25, batch 3150, loss[loss=0.211, simple_loss=0.2899, pruned_loss=0.06611, over 4927.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3086, pruned_loss=0.0654, over 966923.78 frames.], batch size: 13, lr: 5.44e-04
2022-05-29 05:13:57,126 INFO [train.py:761] (5/8) Epoch 25, batch 3200, loss[loss=0.2898, simple_loss=0.3613, pruned_loss=0.1092, over 4787.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3096, pruned_loss=0.06679, over 967002.89 frames.], batch size: 16, lr: 5.44e-04
2022-05-29 05:14:36,031 INFO [train.py:761] (5/8) Epoch 25, batch 3250, loss[loss=0.2236, simple_loss=0.3209, pruned_loss=0.06311, over 4810.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3113, pruned_loss=0.06928, over 966792.72 frames.], batch size: 18, lr: 5.44e-04
2022-05-29 05:15:14,039 INFO [train.py:761] (5/8) Epoch 25, batch 3300, loss[loss=0.2132, simple_loss=0.2834, pruned_loss=0.07149, over 4641.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3118, pruned_loss=0.06989, over 965559.41 frames.], batch size: 11, lr: 5.44e-04
2022-05-29 05:15:51,968 INFO [train.py:761] (5/8) Epoch 25, batch 3350, loss[loss=0.2404, simple_loss=0.3209, pruned_loss=0.07994, over 4975.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3122, pruned_loss=0.0714, over 965603.21 frames.], batch size: 14, lr: 5.44e-04
2022-05-29 05:16:30,401 INFO [train.py:761] (5/8) Epoch 25, batch 3400, loss[loss=0.1994, simple_loss=0.2744, pruned_loss=0.0622, over 4731.00 frames.], tot_loss[loss=0.2275, simple_loss=0.311, pruned_loss=0.07198, over 965671.78 frames.], batch size: 12, lr: 5.44e-04
2022-05-29 05:17:08,546 INFO [train.py:761] (5/8) Epoch 25, batch 3450, loss[loss=0.245, simple_loss=0.3246, pruned_loss=0.08272, over 4990.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3116, pruned_loss=0.07279, over 964861.06 frames.], batch size: 13, lr: 5.43e-04
2022-05-29 05:17:46,070 INFO [train.py:761] (5/8) Epoch 25, batch 3500, loss[loss=0.243, simple_loss=0.3221, pruned_loss=0.08197, over 4842.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3131, pruned_loss=0.07412, over 965537.65 frames.], batch size: 18, lr: 5.43e-04
2022-05-29 05:18:23,833 INFO [train.py:761] (5/8) Epoch 25, batch 3550, loss[loss=0.2555, simple_loss=0.3442, pruned_loss=0.08336, over 4794.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3123, pruned_loss=0.07422, over 965950.84 frames.], batch size: 16, lr: 5.43e-04
2022-05-29 05:19:01,243 INFO [train.py:761] (5/8) Epoch 25, batch 3600, loss[loss=0.2267, simple_loss=0.3157, pruned_loss=0.06883, over 4770.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3134, pruned_loss=0.07484, over 965709.02 frames.], batch size: 16, lr: 5.43e-04
2022-05-29 05:19:39,298 INFO [train.py:761] (5/8) Epoch 25, batch 3650, loss[loss=0.2345, simple_loss=0.3291, pruned_loss=0.06998, over 4988.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3141, pruned_loss=0.07619, over 965009.66 frames.], batch size: 21, lr: 5.43e-04
2022-05-29 05:20:17,314 INFO [train.py:761] (5/8) Epoch 25, batch 3700, loss[loss=0.2321, simple_loss=0.3125, pruned_loss=0.07584, over 4791.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3139, pruned_loss=0.0763, over 965191.24 frames.], batch size: 14, lr: 5.43e-04
2022-05-29 05:20:55,584 INFO [train.py:761] (5/8) Epoch 25, batch 3750, loss[loss=0.2368, simple_loss=0.3228, pruned_loss=0.07537, over 4709.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3146, pruned_loss=0.07752, over 966342.86 frames.], batch size: 14, lr: 5.43e-04
2022-05-29 05:21:33,809 INFO [train.py:761] (5/8) Epoch 25, batch 3800, loss[loss=0.3195, simple_loss=0.3923, pruned_loss=0.1233, over 4850.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3161, pruned_loss=0.07841, over 965771.55 frames.], batch size: 17, lr: 5.43e-04
2022-05-29 05:22:12,075 INFO [train.py:761] (5/8) Epoch 25, batch 3850, loss[loss=0.2366, simple_loss=0.2893, pruned_loss=0.09192, over 4826.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3161, pruned_loss=0.07857, over 964733.97 frames.], batch size: 11, lr: 5.43e-04
2022-05-29 05:22:50,188 INFO [train.py:761] (5/8) Epoch 25, batch 3900, loss[loss=0.2877, simple_loss=0.3681, pruned_loss=0.1036, over 4921.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3155, pruned_loss=0.0788, over 965988.20 frames.], batch size: 51, lr: 5.43e-04
2022-05-29 05:23:28,044 INFO [train.py:761] (5/8) Epoch 25, batch 3950, loss[loss=0.2115, simple_loss=0.3098, pruned_loss=0.05662, over 4828.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3155, pruned_loss=0.07933, over 966371.11 frames.], batch size: 20, lr: 5.43e-04
2022-05-29 05:24:06,057 INFO [train.py:761] (5/8) Epoch 25, batch 4000, loss[loss=0.2671, simple_loss=0.3366, pruned_loss=0.09886, over 4665.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3155, pruned_loss=0.07936, over 966622.50 frames.], batch size: 12, lr: 5.43e-04
2022-05-29 05:24:44,234 INFO [train.py:761] (5/8) Epoch 25, batch 4050, loss[loss=0.2405, simple_loss=0.329, pruned_loss=0.07603, over 4776.00 frames.], tot_loss[loss=0.2382, simple_loss=0.3165, pruned_loss=0.07994, over 966398.54 frames.], batch size: 15, lr: 5.42e-04
2022-05-29 05:25:22,442 INFO [train.py:761] (5/8) Epoch 25, batch 4100, loss[loss=0.2781, simple_loss=0.351, pruned_loss=0.1026, over 4946.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3159, pruned_loss=0.07915, over 967250.56 frames.], batch size: 16, lr: 5.42e-04
2022-05-29 05:26:00,662 INFO [train.py:761] (5/8) Epoch 25, batch 4150, loss[loss=0.2787, simple_loss=0.3628, pruned_loss=0.09725, over 4845.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3175, pruned_loss=0.07985, over 966968.47 frames.], batch size: 26, lr: 5.42e-04
2022-05-29 05:26:38,628 INFO [train.py:761] (5/8) Epoch 25, batch 4200, loss[loss=0.2629, simple_loss=0.3474, pruned_loss=0.08914, over 4954.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3168, pruned_loss=0.0795, over 966324.11 frames.], batch size: 16, lr: 5.42e-04
2022-05-29 05:27:17,087 INFO [train.py:761] (5/8) Epoch 25, batch 4250, loss[loss=0.204, simple_loss=0.2876, pruned_loss=0.06024, over 4791.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3161, pruned_loss=0.07954, over 965965.43 frames.], batch size: 14, lr: 5.42e-04
2022-05-29 05:27:54,905 INFO [train.py:761] (5/8) Epoch 25, batch 4300, loss[loss=0.2429, simple_loss=0.3285, pruned_loss=0.07867, over 4791.00 frames.], tot_loss[loss=0.2361, simple_loss=0.315, pruned_loss=0.07858, over 964971.49 frames.], batch size: 14, lr: 5.42e-04
2022-05-29 05:28:33,187 INFO [train.py:761] (5/8) Epoch 25, batch 4350, loss[loss=0.2096, simple_loss=0.3037, pruned_loss=0.05781, over 4947.00 frames.], tot_loss[loss=0.235, simple_loss=0.3135, pruned_loss=0.07828, over 965023.98 frames.], batch size: 26, lr: 5.42e-04
2022-05-29 05:29:11,243 INFO [train.py:761] (5/8) Epoch 25, batch 4400, loss[loss=0.2049, simple_loss=0.2791, pruned_loss=0.06537, over 4849.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3124, pruned_loss=0.07792, over 965322.07 frames.], batch size: 11, lr: 5.42e-04
2022-05-29 05:29:49,269 INFO [train.py:761] (5/8) Epoch 25, batch 4450, loss[loss=0.2149, simple_loss=0.2967, pruned_loss=0.06651, over 4860.00 frames.], tot_loss[loss=0.2337, simple_loss=0.3126, pruned_loss=0.07741, over 965554.03 frames.], batch size: 13, lr: 5.42e-04
2022-05-29 05:30:27,176 INFO [train.py:761] (5/8) Epoch 25, batch 4500, loss[loss=0.182, simple_loss=0.2588, pruned_loss=0.05259, over 4643.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3115, pruned_loss=0.07653, over 966182.26 frames.], batch size: 11, lr: 5.42e-04
2022-05-29 05:31:06,082 INFO [train.py:761] (5/8) Epoch 25, batch 4550, loss[loss=0.2237, simple_loss=0.2967, pruned_loss=0.07532, over 4986.00 frames.], tot_loss[loss=0.232, simple_loss=0.3123, pruned_loss=0.07583, over 965564.59 frames.], batch size: 12, lr: 5.42e-04
2022-05-29 05:31:43,560 INFO [train.py:761] (5/8) Epoch 25, batch 4600, loss[loss=0.2307, simple_loss=0.3192, pruned_loss=0.0711, over 4673.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3133, pruned_loss=0.07674, over 966377.97 frames.], batch size: 13, lr: 5.42e-04
2022-05-29 05:32:21,981 INFO [train.py:761] (5/8) Epoch 25, batch 4650, loss[loss=0.2041, simple_loss=0.2935, pruned_loss=0.0574, over 4735.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3129, pruned_loss=0.07695, over 965546.41 frames.], batch size: 12, lr: 5.41e-04
2022-05-29 05:32:59,998 INFO [train.py:761] (5/8) Epoch 25, batch 4700, loss[loss=0.2359, simple_loss=0.31, pruned_loss=0.08089, over 4887.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3117, pruned_loss=0.07606, over 966651.90 frames.], batch size: 15, lr: 5.41e-04
2022-05-29 05:33:38,312 INFO [train.py:761] (5/8) Epoch 25, batch 4750, loss[loss=0.2332, simple_loss=0.3268, pruned_loss=0.0698, over 4779.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3113, pruned_loss=0.07563, over 965727.30 frames.], batch size: 14, lr: 5.41e-04
2022-05-29 05:34:17,131 INFO [train.py:761] (5/8) Epoch 25, batch 4800, loss[loss=0.2298, simple_loss=0.33, pruned_loss=0.06476, over 4848.00 frames.], tot_loss[loss=0.2333, simple_loss=0.313, pruned_loss=0.07679, over 966064.49 frames.], batch size: 14, lr: 5.41e-04
2022-05-29 05:34:54,964 INFO [train.py:761] (5/8) Epoch 25, batch 4850, loss[loss=0.2093, simple_loss=0.2749, pruned_loss=0.07181, over 4976.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3129, pruned_loss=0.07749, over 966564.58 frames.], batch size: 12, lr: 5.41e-04
2022-05-29 05:35:33,163 INFO [train.py:761] (5/8) Epoch 25, batch 4900, loss[loss=0.2482, simple_loss=0.3246, pruned_loss=0.08589, over 4774.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3124, pruned_loss=0.07664, over 966146.23 frames.], batch size: 15, lr: 5.41e-04
2022-05-29 05:36:10,936 INFO [train.py:761] (5/8) Epoch 25, batch 4950, loss[loss=0.239, simple_loss=0.3246, pruned_loss=0.07669, over 4974.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3125, pruned_loss=0.07685, over 965837.67 frames.], batch size: 15, lr: 5.41e-04
2022-05-29 05:36:48,770 INFO [train.py:761] (5/8) Epoch 25, batch 5000, loss[loss=0.1933, simple_loss=0.2641, pruned_loss=0.06129, over 4746.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3125, pruned_loss=0.07645, over 965159.21 frames.], batch size: 12, lr: 5.41e-04
2022-05-29 05:37:26,656 INFO [train.py:761] (5/8) Epoch 25, batch 5050, loss[loss=0.228, simple_loss=0.2983, pruned_loss=0.07886, over 4732.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3108, pruned_loss=0.07552, over 966024.33 frames.], batch size: 11, lr: 5.41e-04
2022-05-29 05:38:05,106 INFO [train.py:761] (5/8) Epoch 25, batch 5100, loss[loss=0.2043, simple_loss=0.2772, pruned_loss=0.0657, over 4990.00 frames.], tot_loss[loss=0.2323, simple_loss=0.312, pruned_loss=0.07626, over 966510.43 frames.], batch size: 11, lr: 5.41e-04
2022-05-29 05:38:43,588 INFO [train.py:761] (5/8) Epoch 25, batch 5150, loss[loss=0.2926, simple_loss=0.3512, pruned_loss=0.117, over 4909.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3123, pruned_loss=0.07697, over 966513.82 frames.], batch size: 26, lr: 5.41e-04
2022-05-29 05:39:22,184 INFO [train.py:761] (5/8) Epoch 25, batch 5200, loss[loss=0.2233, simple_loss=0.3086, pruned_loss=0.06902, over 4723.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3136, pruned_loss=0.07761, over 967617.44 frames.], batch size: 14, lr: 5.41e-04
2022-05-29 05:40:00,594 INFO [train.py:761] (5/8) Epoch 25, batch 5250, loss[loss=0.2636, simple_loss=0.3378, pruned_loss=0.09468, over 4870.00 frames.], tot_loss[loss=0.2337, simple_loss=0.313, pruned_loss=0.07722, over 967222.49 frames.], batch size: 15, lr: 5.40e-04
2022-05-29 05:40:39,269 INFO [train.py:761] (5/8) Epoch 25, batch 5300, loss[loss=0.2545, simple_loss=0.3148, pruned_loss=0.0971, over 4711.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3126, pruned_loss=0.07721, over 967489.65 frames.], batch size: 14, lr: 5.40e-04
2022-05-29 05:41:18,057 INFO [train.py:761] (5/8) Epoch 25, batch 5350, loss[loss=0.211, simple_loss=0.2897, pruned_loss=0.06609, over 4886.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3122, pruned_loss=0.07718, over 967359.37 frames.], batch size: 12, lr: 5.40e-04
2022-05-29 05:41:56,226 INFO [train.py:761] (5/8) Epoch 25, batch 5400, loss[loss=0.2215, simple_loss=0.2981, pruned_loss=0.0724, over 4883.00 frames.], tot_loss[loss=0.231, simple_loss=0.3104, pruned_loss=0.07582, over 966867.03 frames.], batch size: 12, lr: 5.40e-04
2022-05-29 05:42:34,440 INFO [train.py:761] (5/8) Epoch 25, batch 5450, loss[loss=0.2311, simple_loss=0.3093, pruned_loss=0.07641, over 4906.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3099, pruned_loss=0.07547, over 966450.92 frames.], batch size: 14, lr: 5.40e-04
2022-05-29 05:43:12,654 INFO [train.py:761] (5/8) Epoch 25, batch 5500, loss[loss=0.2271, simple_loss=0.3216, pruned_loss=0.06631, over 4724.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3117, pruned_loss=0.07643, over 967281.45 frames.], batch size: 14, lr: 5.40e-04
2022-05-29 05:43:50,828 INFO [train.py:761] (5/8) Epoch 25, batch 5550, loss[loss=0.2049, simple_loss=0.2916, pruned_loss=0.05913, over 4727.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3119, pruned_loss=0.07617, over 966575.41 frames.], batch size: 12, lr: 5.40e-04
2022-05-29 05:44:28,849 INFO [train.py:761] (5/8) Epoch 25, batch 5600, loss[loss=0.2194, simple_loss=0.3007, pruned_loss=0.06904, over 4736.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3109, pruned_loss=0.07571, over 965985.93 frames.], batch size: 12, lr: 5.40e-04
2022-05-29 05:45:07,233 INFO [train.py:761] (5/8) Epoch 25, batch 5650, loss[loss=0.2244, simple_loss=0.2988, pruned_loss=0.07505, over 4642.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3105, pruned_loss=0.07509, over 967128.37 frames.], batch size: 11, lr: 5.40e-04
2022-05-29 05:45:44,900 INFO [train.py:761] (5/8) Epoch 25, batch 5700, loss[loss=0.2429, simple_loss=0.3265, pruned_loss=0.07966, over 4798.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3111, pruned_loss=0.07485, over 968556.07 frames.], batch size: 26, lr: 5.40e-04
2022-05-29 05:46:23,480 INFO [train.py:761] (5/8) Epoch 25, batch 5750, loss[loss=0.2168, simple_loss=0.3108, pruned_loss=0.06138, over 4673.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3128, pruned_loss=0.07592, over 968819.63 frames.], batch size: 13, lr: 5.40e-04
2022-05-29 05:47:01,724 INFO [train.py:761] (5/8) Epoch 25, batch 5800, loss[loss=0.2936, simple_loss=0.3666, pruned_loss=0.1103, over 4824.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3122, pruned_loss=0.07581, over 968577.21 frames.], batch size: 25, lr: 5.40e-04
2022-05-29 05:47:40,811 INFO [train.py:761] (5/8) Epoch 25, batch 5850, loss[loss=0.2005, simple_loss=0.2853, pruned_loss=0.05787, over 4969.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3114, pruned_loss=0.0758, over 968570.67 frames.], batch size: 12, lr: 5.40e-04
2022-05-29 05:48:18,938 INFO [train.py:761] (5/8) Epoch 25, batch 5900, loss[loss=0.3083, simple_loss=0.3738, pruned_loss=0.1214, over 4822.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3129, pruned_loss=0.07688, over 968054.85 frames.], batch size: 18, lr: 5.39e-04
2022-05-29 05:49:04,921 INFO [train.py:761] (5/8) Epoch 25, batch 5950, loss[loss=0.2176, simple_loss=0.3012, pruned_loss=0.06704, over 4761.00 frames.], tot_loss[loss=0.2334, simple_loss=0.313, pruned_loss=0.07685, over 969036.75 frames.], batch size: 20, lr: 5.39e-04
2022-05-29 05:49:43,129 INFO [train.py:761] (5/8) Epoch 25, batch 6000, loss[loss=0.2872, simple_loss=0.3612, pruned_loss=0.1066, over 4931.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3121, pruned_loss=0.07649, over 969055.32 frames.], batch size: 49, lr: 5.39e-04
2022-05-29 05:49:43,130 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 05:49:53,018 INFO [train.py:790] (5/8) Epoch 25, validation: loss=0.1994, simple_loss=0.3038, pruned_loss=0.04748, over 944034.00 frames.
2022-05-29 05:50:31,558 INFO [train.py:761] (5/8) Epoch 25, batch 6050, loss[loss=0.2541, simple_loss=0.3258, pruned_loss=0.09122, over 4820.00 frames.], tot_loss[loss=0.232, simple_loss=0.3123, pruned_loss=0.07581, over 968982.15 frames.], batch size: 16, lr: 5.39e-04
2022-05-29 05:51:09,946 INFO [train.py:761] (5/8) Epoch 25, batch 6100, loss[loss=0.2614, simple_loss=0.3288, pruned_loss=0.097, over 4977.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3132, pruned_loss=0.07663, over 968573.14 frames.], batch size: 15, lr: 5.39e-04
2022-05-29 05:51:51,409 INFO [train.py:761] (5/8) Epoch 25, batch 6150, loss[loss=0.3091, simple_loss=0.3692, pruned_loss=0.1245, over 4919.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3129, pruned_loss=0.07684, over 967670.16 frames.], batch size: 21, lr: 5.39e-04
2022-05-29 05:52:29,585 INFO [train.py:761] (5/8) Epoch 25, batch 6200, loss[loss=0.211, simple_loss=0.2786, pruned_loss=0.07166, over 4741.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3123, pruned_loss=0.07677, over 966863.97 frames.], batch size: 11, lr: 5.39e-04
2022-05-29 05:53:07,844 INFO [train.py:761] (5/8) Epoch 25, batch 6250, loss[loss=0.2268, simple_loss=0.3102, pruned_loss=0.0717, over 4984.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3123, pruned_loss=0.07675, over 967273.69 frames.], batch size: 15, lr: 5.39e-04
2022-05-29 05:53:46,619 INFO [train.py:761] (5/8) Epoch 25, batch 6300, loss[loss=0.27, simple_loss=0.3588, pruned_loss=0.09062, over 4893.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3134, pruned_loss=0.07721, over 967657.72 frames.], batch size: 17, lr: 5.39e-04
2022-05-29 05:54:25,003 INFO [train.py:761] (5/8) Epoch 25, batch 6350, loss[loss=0.22, simple_loss=0.2879, pruned_loss=0.07603, over 4540.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3129, pruned_loss=0.07704, over 966977.64 frames.], batch size: 10, lr: 5.39e-04
2022-05-29 05:55:03,094 INFO [train.py:761] (5/8) Epoch 25, batch 6400, loss[loss=0.236, simple_loss=0.3143, pruned_loss=0.07886, over 4711.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3133, pruned_loss=0.07679, over 966483.14 frames.], batch size: 14, lr: 5.39e-04
2022-05-29 05:55:41,411 INFO [train.py:761] (5/8) Epoch 25, batch 6450, loss[loss=0.2221, simple_loss=0.3048, pruned_loss=0.06976, over 4788.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3129, pruned_loss=0.077, over 966840.77 frames.], batch size: 14, lr: 5.39e-04
2022-05-29 05:56:19,802 INFO [train.py:761] (5/8) Epoch 25, batch 6500, loss[loss=0.2128, simple_loss=0.2953, pruned_loss=0.06517, over 4745.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3132, pruned_loss=0.07691, over 966849.25 frames.], batch size: 12, lr: 5.38e-04
2022-05-29 05:57:05,531 INFO [train.py:761] (5/8) Epoch 25, batch 6550, loss[loss=0.2067, simple_loss=0.3039, pruned_loss=0.05473, over 4727.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3126, pruned_loss=0.07653, over 966893.27 frames.], batch size: 13, lr: 5.38e-04
2022-05-29 05:57:43,694 INFO [train.py:761] (5/8) Epoch 25, batch 6600, loss[loss=0.2775, simple_loss=0.3609, pruned_loss=0.09699, over 4782.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3128, pruned_loss=0.07686, over 966787.13 frames.], batch size: 14, lr: 5.38e-04
2022-05-29 05:58:22,346 INFO [train.py:761] (5/8) Epoch 25, batch 6650, loss[loss=0.238, simple_loss=0.3189, pruned_loss=0.07858, over 4968.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3131, pruned_loss=0.07696, over 967544.19 frames.], batch size: 14, lr: 5.38e-04
2022-05-29 05:59:00,576 INFO [train.py:761] (5/8) Epoch 25, batch 6700, loss[loss=0.2485, simple_loss=0.328, pruned_loss=0.08447, over 4986.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3127, pruned_loss=0.07677, over 967801.55 frames.], batch size: 26, lr: 5.38e-04
2022-05-29 06:00:01,401 INFO [train.py:761] (5/8) Epoch 26, batch 0, loss[loss=0.3123, simple_loss=0.3842, pruned_loss=0.1202, over 4983.00 frames.], tot_loss[loss=0.3123, simple_loss=0.3842, pruned_loss=0.1202, over 4983.00 frames.], batch size: 46, lr: 5.38e-04
2022-05-29 06:00:39,082 INFO [train.py:761] (5/8) Epoch 26, batch 50, loss[loss=0.1986, simple_loss=0.2934, pruned_loss=0.05194, over 4724.00 frames.], tot_loss[loss=0.22, simple_loss=0.31, pruned_loss=0.06503, over 218039.87 frames.], batch size: 14, lr: 5.38e-04
2022-05-29 06:01:17,681 INFO [train.py:761] (5/8) Epoch 26, batch 100, loss[loss=0.2369, simple_loss=0.3344, pruned_loss=0.0697, over 4857.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3063, pruned_loss=0.0626, over 384155.52 frames.], batch size: 17, lr: 5.38e-04
2022-05-29 06:01:55,300 INFO [train.py:761] (5/8) Epoch 26, batch 150, loss[loss=0.2097, simple_loss=0.31, pruned_loss=0.05467, over 4803.00 frames.], tot_loss[loss=0.2128, simple_loss=0.3047, pruned_loss=0.06045, over 514279.24 frames.], batch size: 16, lr: 5.38e-04
2022-05-29 06:02:32,855 INFO [train.py:761] (5/8) Epoch 26, batch 200, loss[loss=0.222, simple_loss=0.3088, pruned_loss=0.06758, over 4663.00 frames.], tot_loss[loss=0.2128, simple_loss=0.3044, pruned_loss=0.06057, over 615803.50 frames.], batch size: 12, lr: 5.38e-04
2022-05-29 06:03:10,834 INFO [train.py:761] (5/8) Epoch 26, batch 250, loss[loss=0.2545, simple_loss=0.346, pruned_loss=0.08147, over 4957.00 frames.], tot_loss[loss=0.2124, simple_loss=0.3041, pruned_loss=0.06029, over 692838.37 frames.], batch size: 48, lr: 5.38e-04
2022-05-29 06:03:49,175 INFO [train.py:761] (5/8) Epoch 26, batch 300, loss[loss=0.186, simple_loss=0.2679, pruned_loss=0.05202, over 4963.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3018, pruned_loss=0.0592, over 752468.30 frames.], batch size: 12, lr: 5.38e-04
2022-05-29 06:04:27,172 INFO [train.py:761] (5/8) Epoch 26, batch 350, loss[loss=0.1852, simple_loss=0.261, pruned_loss=0.05471, over 4832.00 frames.], tot_loss[loss=0.2097, simple_loss=0.3013, pruned_loss=0.0591, over 799418.55 frames.], batch size: 11, lr: 5.38e-04
2022-05-29 06:05:12,692 INFO [train.py:761] (5/8) Epoch 26, batch 400, loss[loss=0.2327, simple_loss=0.3178, pruned_loss=0.07384, over 4974.00 frames.], tot_loss[loss=0.2106, simple_loss=0.3021, pruned_loss=0.05951, over 838238.39 frames.], batch size: 14, lr: 5.37e-04
2022-05-29 06:05:50,609 INFO [train.py:761] (5/8) Epoch 26, batch 450, loss[loss=0.26, simple_loss=0.3458, pruned_loss=0.08714, over 4722.00 frames.], tot_loss[loss=0.2094, simple_loss=0.3005, pruned_loss=0.0591, over 865536.76 frames.], batch size: 14, lr: 5.37e-04
2022-05-29 06:06:29,303 INFO [train.py:761] (5/8) Epoch 26, batch 500, loss[loss=0.2779, simple_loss=0.3659, pruned_loss=0.0949, over 4885.00 frames.], tot_loss[loss=0.2092, simple_loss=0.3011, pruned_loss=0.05866, over 888844.02 frames.], batch size: 15, lr: 5.37e-04
2022-05-29 06:07:07,215 INFO [train.py:761] (5/8) Epoch 26, batch 550, loss[loss=0.2186, simple_loss=0.2906, pruned_loss=0.07332, over 4740.00 frames.], tot_loss[loss=0.2099, simple_loss=0.3019, pruned_loss=0.059, over 905891.19 frames.], batch size: 12, lr: 5.37e-04
2022-05-29 06:07:52,938 INFO [train.py:761] (5/8) Epoch 26, batch 600, loss[loss=0.246, simple_loss=0.3277, pruned_loss=0.08215, over 4815.00 frames.], tot_loss[loss=0.2094, simple_loss=0.3007, pruned_loss=0.05905, over 919549.97 frames.], batch size: 12, lr: 5.37e-04
2022-05-29 06:08:38,670 INFO [train.py:761] (5/8) Epoch 26, batch 650, loss[loss=0.2131, simple_loss=0.2947, pruned_loss=0.06571, over 4982.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2997, pruned_loss=0.05885, over 930027.93 frames.], batch size: 15, lr: 5.37e-04
2022-05-29 06:09:16,387 INFO [train.py:761] (5/8) Epoch 26, batch 700, loss[loss=0.2143, simple_loss=0.3044, pruned_loss=0.06205, over 4972.00 frames.], tot_loss[loss=0.2095, simple_loss=0.3009, pruned_loss=0.05903, over 937943.98 frames.], batch size: 14, lr: 5.37e-04
2022-05-29 06:09:54,023 INFO [train.py:761] (5/8) Epoch 26, batch 750, loss[loss=0.242, simple_loss=0.3329, pruned_loss=0.07561, over 4975.00 frames.], tot_loss[loss=0.2122, simple_loss=0.304, pruned_loss=0.06022, over 945180.25 frames.], batch size: 15, lr: 5.37e-04
2022-05-29 06:10:31,741 INFO [train.py:761] (5/8) Epoch 26, batch 800, loss[loss=0.2298, simple_loss=0.3079, pruned_loss=0.07586, over 4980.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3047, pruned_loss=0.06103, over 949874.52 frames.], batch size: 12, lr: 5.37e-04
2022-05-29 06:11:16,986 INFO [train.py:761] (5/8) Epoch 26, batch 850, loss[loss=0.18, simple_loss=0.2643, pruned_loss=0.04791, over 4732.00 frames.], tot_loss[loss=0.2122, simple_loss=0.303, pruned_loss=0.06072, over 951726.78 frames.], batch size: 12, lr: 5.37e-04
2022-05-29 06:11:55,036 INFO [train.py:761] (5/8) Epoch 26, batch 900, loss[loss=0.1826, simple_loss=0.2568, pruned_loss=0.05419, over 4655.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3033, pruned_loss=0.06065, over 954956.18 frames.], batch size: 11, lr: 5.37e-04
2022-05-29 06:12:32,665 INFO [train.py:761] (5/8) Epoch 26, batch 950, loss[loss=0.2063, simple_loss=0.2997, pruned_loss=0.05642, over 4844.00 frames.], tot_loss[loss=0.2119, simple_loss=0.3028, pruned_loss=0.06049, over 956771.99 frames.], batch size: 13, lr: 5.37e-04
2022-05-29 06:13:10,735 INFO [train.py:761] (5/8) Epoch 26, batch 1000, loss[loss=0.2234, simple_loss=0.3122, pruned_loss=0.06734, over 4672.00 frames.], tot_loss[loss=0.2119, simple_loss=0.3029, pruned_loss=0.0605, over 959146.56 frames.], batch size: 13, lr: 5.36e-04
2022-05-29 06:13:48,634 INFO [train.py:761] (5/8) Epoch 26, batch 1050, loss[loss=0.2418, simple_loss=0.3242, pruned_loss=0.07964, over 4842.00 frames.], tot_loss[loss=0.2128, simple_loss=0.303, pruned_loss=0.06129, over 960827.17 frames.], batch size: 20, lr: 5.36e-04
2022-05-29 06:14:26,535 INFO [train.py:761] (5/8) Epoch 26, batch 1100, loss[loss=0.2078, simple_loss=0.2909, pruned_loss=0.06233, over 4675.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3041, pruned_loss=0.06126, over 961948.59 frames.], batch size: 12, lr: 5.36e-04
2022-05-29 06:15:04,241 INFO [train.py:761] (5/8) Epoch 26, batch 1150, loss[loss=0.2442, simple_loss=0.3175, pruned_loss=0.08545, over 4991.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3044, pruned_loss=0.06115, over 961964.82 frames.], batch size: 13, lr: 5.36e-04
2022-05-29 06:15:42,555 INFO [train.py:761] (5/8) Epoch 26, batch 1200, loss[loss=0.1815, simple_loss=0.286, pruned_loss=0.03852, over 4724.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3043, pruned_loss=0.0611, over 963276.98 frames.], batch size: 14, lr: 5.36e-04
2022-05-29 06:16:20,605 INFO [train.py:761] (5/8) Epoch 26, batch 1250, loss[loss=0.1951, simple_loss=0.3032, pruned_loss=0.04351, over 4720.00 frames.], tot_loss[loss=0.214, simple_loss=0.3046, pruned_loss=0.06171, over 963415.14 frames.], batch size: 14, lr: 5.36e-04
2022-05-29 06:16:58,517 INFO [train.py:761] (5/8) Epoch 26, batch 1300, loss[loss=0.2645, simple_loss=0.3572, pruned_loss=0.08586, over 4974.00 frames.], tot_loss[loss=0.2158, simple_loss=0.307, pruned_loss=0.06231, over 965030.76 frames.], batch size: 46, lr: 5.36e-04
2022-05-29 06:17:36,272 INFO [train.py:761] (5/8) Epoch 26, batch 1350, loss[loss=0.2251, simple_loss=0.312, pruned_loss=0.06907, over 4774.00 frames.], tot_loss[loss=0.2161, simple_loss=0.307, pruned_loss=0.06255, over 964300.79 frames.], batch size: 14, lr: 5.36e-04
2022-05-29 06:18:14,276 INFO [train.py:761] (5/8) Epoch 26, batch 1400, loss[loss=0.2417, simple_loss=0.3239, pruned_loss=0.07979, over 4779.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3074, pruned_loss=0.06311, over 964078.80 frames.], batch size: 14, lr: 5.36e-04
2022-05-29 06:18:52,477 INFO [train.py:761] (5/8) Epoch 26, batch 1450, loss[loss=0.205, simple_loss=0.2864, pruned_loss=0.06183, over 4728.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3069, pruned_loss=0.06305, over 964246.19 frames.], batch size: 11, lr: 5.36e-04
2022-05-29 06:19:31,122 INFO [train.py:761] (5/8) Epoch 26, batch 1500, loss[loss=0.2278, simple_loss=0.3209, pruned_loss=0.06733, over 4973.00 frames.], tot_loss[loss=0.217, simple_loss=0.3074, pruned_loss=0.06325, over 964674.27 frames.], batch size: 15, lr: 5.36e-04
2022-05-29 06:20:08,680 INFO [train.py:761] (5/8) Epoch 26, batch 1550, loss[loss=0.2092, simple_loss=0.3057, pruned_loss=0.05633, over 4891.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3075, pruned_loss=0.06353, over 965365.68 frames.], batch size: 12, lr: 5.36e-04
2022-05-29 06:20:47,385 INFO [train.py:761] (5/8) Epoch 26, batch 1600, loss[loss=0.2176, simple_loss=0.3159, pruned_loss=0.0596, over 4912.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3074, pruned_loss=0.06366, over 965827.73 frames.], batch size: 14, lr: 5.36e-04
2022-05-29 06:21:25,401 INFO [train.py:761] (5/8) Epoch 26, batch 1650, loss[loss=0.2436, simple_loss=0.3408, pruned_loss=0.07318, over 4912.00 frames.], tot_loss[loss=0.2169, simple_loss=0.307, pruned_loss=0.06338, over 966208.80 frames.], batch size: 14, lr: 5.35e-04
2022-05-29 06:22:03,193 INFO [train.py:761] (5/8) Epoch 26, batch 1700, loss[loss=0.2336, simple_loss=0.3322, pruned_loss=0.0675, over 4976.00 frames.], tot_loss[loss=0.216, simple_loss=0.3063, pruned_loss=0.06286, over 967279.57 frames.], batch size: 14, lr: 5.35e-04
2022-05-29 06:22:41,353 INFO [train.py:761] (5/8) Epoch 26, batch 1750, loss[loss=0.2079, simple_loss=0.305, pruned_loss=0.05537, over 4910.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3069, pruned_loss=0.06333, over 967867.86 frames.], batch size: 14, lr: 5.35e-04
2022-05-29 06:23:19,163 INFO [train.py:761] (5/8) Epoch 26, batch 1800, loss[loss=0.2003, simple_loss=0.2843, pruned_loss=0.05818, over 4813.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3073, pruned_loss=0.06288, over 966890.39 frames.], batch size: 12, lr: 5.35e-04
2022-05-29 06:23:56,938 INFO [train.py:761] (5/8) Epoch 26, batch 1850, loss[loss=0.2375, simple_loss=0.3189, pruned_loss=0.07811, over 4919.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3059, pruned_loss=0.06266, over 966844.25 frames.], batch size: 13, lr: 5.35e-04
2022-05-29 06:24:35,332 INFO [train.py:761] (5/8) Epoch 26, batch 1900, loss[loss=0.2096, simple_loss=0.273, pruned_loss=0.07313, over 4986.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3058, pruned_loss=0.06326, over 967650.73 frames.], batch size: 12, lr: 5.35e-04
2022-05-29 06:25:13,256 INFO [train.py:761] (5/8) Epoch 26, batch 1950, loss[loss=0.2576, simple_loss=0.3383, pruned_loss=0.08842, over 4787.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3061, pruned_loss=0.06322, over 966677.69 frames.], batch size: 20, lr: 5.35e-04
2022-05-29 06:25:51,438 INFO [train.py:761] (5/8) Epoch 26, batch 2000, loss[loss=0.2176, simple_loss=0.3133, pruned_loss=0.06098, over 4798.00 frames.], tot_loss[loss=0.216, simple_loss=0.306, pruned_loss=0.06305, over 966586.02 frames.], batch size: 16, lr: 5.35e-04
2022-05-29 06:26:29,299 INFO [train.py:761] (5/8) Epoch 26, batch 2050, loss[loss=0.2152, simple_loss=0.2944, pruned_loss=0.06797, over 4670.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3068, pruned_loss=0.06328, over 966089.33 frames.], batch size: 13, lr: 5.35e-04
2022-05-29 06:27:08,181 INFO [train.py:761] (5/8) Epoch 26, batch 2100, loss[loss=0.1783, simple_loss=0.2735, pruned_loss=0.04151, over 4860.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3062, pruned_loss=0.06266, over 965437.25 frames.], batch size: 13, lr: 5.35e-04
2022-05-29 06:27:45,973 INFO [train.py:761] (5/8) Epoch 26, batch 2150, loss[loss=0.2137, simple_loss=0.2933, pruned_loss=0.06701, over 4920.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3056, pruned_loss=0.06268, over 965756.24 frames.], batch size: 13, lr: 5.35e-04
2022-05-29 06:28:24,334 INFO [train.py:761] (5/8) Epoch 26, batch 2200, loss[loss=0.1854, simple_loss=0.2645, pruned_loss=0.05313, over 4978.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3056, pruned_loss=0.06229, over 966432.82 frames.], batch size: 12, lr: 5.35e-04
2022-05-29 06:29:02,451 INFO [train.py:761] (5/8) Epoch 26, batch 2250, loss[loss=0.173, simple_loss=0.2728, pruned_loss=0.03656, over 4788.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3052, pruned_loss=0.06199, over 967100.09 frames.], batch size: 13, lr: 5.35e-04
2022-05-29 06:29:40,215 INFO [train.py:761] (5/8) Epoch 26, batch 2300, loss[loss=0.1735, simple_loss=0.2653, pruned_loss=0.04087, over 4879.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3048, pruned_loss=0.0618, over 966775.53 frames.], batch size: 12, lr: 5.34e-04
2022-05-29 06:30:17,757 INFO [train.py:761] (5/8) Epoch 26, batch 2350, loss[loss=0.2031, simple_loss=0.2909, pruned_loss=0.05764, over 4562.00 frames.], tot_loss[loss=0.2144, simple_loss=0.3052, pruned_loss=0.06176, over 966264.98 frames.], batch size: 10, lr: 5.34e-04
2022-05-29 06:30:55,720 INFO [train.py:761] (5/8) Epoch 26, batch 2400, loss[loss=0.1979, simple_loss=0.2863, pruned_loss=0.05475, over 4884.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3055, pruned_loss=0.06215, over 966268.54 frames.], batch size: 12, lr: 5.34e-04
2022-05-29 06:31:33,938 INFO [train.py:761] (5/8) Epoch 26, batch 2450, loss[loss=0.2142, simple_loss=0.2897, pruned_loss=0.06931, over 4577.00 frames.], tot_loss[loss=0.214, simple_loss=0.3052, pruned_loss=0.06139, over 966300.63 frames.], batch size: 10, lr: 5.34e-04
2022-05-29 06:32:11,830 INFO [train.py:761] (5/8) Epoch 26, batch 2500, loss[loss=0.2087, simple_loss=0.3023, pruned_loss=0.05753, over 4887.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3048, pruned_loss=0.06107, over 965905.02 frames.], batch size: 15, lr: 5.34e-04
2022-05-29 06:32:50,143 INFO [train.py:761] (5/8) Epoch 26, batch 2550, loss[loss=0.2182, simple_loss=0.3045, pruned_loss=0.06595, over 4863.00 frames.], tot_loss[loss=0.2139, simple_loss=0.305, pruned_loss=0.06136, over 966145.87 frames.], batch size: 13, lr: 5.34e-04
2022-05-29 06:33:27,867 INFO [train.py:761] (5/8) Epoch 26, batch 2600, loss[loss=0.1956, simple_loss=0.2892, pruned_loss=0.05097, over 4992.00 frames.], tot_loss[loss=0.2131, simple_loss=0.3043, pruned_loss=0.06097, over 966316.69 frames.], batch size: 13, lr: 5.34e-04
2022-05-29 06:34:05,381 INFO [train.py:761] (5/8) Epoch 26, batch 2650, loss[loss=0.2776, simple_loss=0.3458, pruned_loss=0.1047, over 4870.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3045, pruned_loss=0.06095, over 965737.16 frames.], batch size: 15, lr: 5.34e-04
2022-05-29 06:34:43,785 INFO [train.py:761] (5/8) Epoch 26, batch 2700, loss[loss=0.2154, simple_loss=0.3139, pruned_loss=0.05844, over 4848.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3054, pruned_loss=0.06119, over 965704.19 frames.], batch size: 18, lr: 5.34e-04
2022-05-29 06:35:21,778 INFO [train.py:761] (5/8) Epoch 26, batch 2750, loss[loss=0.2127, simple_loss=0.3072, pruned_loss=0.05914, over 4868.00 frames.], tot_loss[loss=0.2141, simple_loss=0.3055, pruned_loss=0.06139, over 965229.72 frames.], batch size: 26, lr: 5.34e-04
2022-05-29 06:35:59,710 INFO [train.py:761] (5/8) Epoch 26, batch 2800, loss[loss=0.2416, simple_loss=0.3274, pruned_loss=0.07789, over 4871.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3066, pruned_loss=0.06177, over 965215.68 frames.], batch size: 15, lr: 5.34e-04
2022-05-29 06:36:37,957 INFO [train.py:761] (5/8) Epoch 26, batch 2850, loss[loss=0.1844, simple_loss=0.2844, pruned_loss=0.04222, over 4780.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3056, pruned_loss=0.06151, over 965806.37 frames.], batch size: 13, lr: 5.34e-04
2022-05-29 06:37:15,575 INFO [train.py:761] (5/8) Epoch 26, batch 2900, loss[loss=0.1826, simple_loss=0.2765, pruned_loss=0.04435, over 4829.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3056, pruned_loss=0.06115, over 966360.15 frames.], batch size: 11, lr: 5.34e-04
2022-05-29 06:37:53,208 INFO [train.py:761] (5/8) Epoch 26, batch 2950, loss[loss=0.209, simple_loss=0.2902, pruned_loss=0.0639, over 4799.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3051, pruned_loss=0.06065, over 965972.54 frames.], batch size: 12, lr: 5.33e-04
2022-05-29 06:38:30,808 INFO [train.py:761] (5/8) Epoch 26, batch 3000, loss[loss=0.1928, simple_loss=0.2797, pruned_loss=0.05294, over 4882.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3051, pruned_loss=0.0603, over 966138.57 frames.], batch size: 12, lr: 5.33e-04
2022-05-29 06:38:30,808 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 06:38:40,607 INFO [train.py:790] (5/8) Epoch 26, validation: loss=0.2057, simple_loss=0.3065, pruned_loss=0.05244, over 944034.00 frames.
2022-05-29 06:39:18,356 INFO [train.py:761] (5/8) Epoch 26, batch 3050, loss[loss=0.2125, simple_loss=0.3106, pruned_loss=0.05714, over 4663.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3046, pruned_loss=0.0598, over 966292.67 frames.], batch size: 12, lr: 5.33e-04
2022-05-29 06:39:56,735 INFO [train.py:761] (5/8) Epoch 26, batch 3100, loss[loss=0.1803, simple_loss=0.2683, pruned_loss=0.04616, over 4744.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3048, pruned_loss=0.06047, over 967049.40 frames.], batch size: 11, lr: 5.33e-04
2022-05-29 06:40:34,361 INFO [train.py:761] (5/8) Epoch 26, batch 3150, loss[loss=0.2451, simple_loss=0.32, pruned_loss=0.08506, over 4667.00 frames.], tot_loss[loss=0.2145, simple_loss=0.305, pruned_loss=0.06197, over 966817.42 frames.], batch size: 12, lr: 5.33e-04
2022-05-29 06:41:13,165 INFO [train.py:761] (5/8) Epoch 26, batch 3200, loss[loss=0.2301, simple_loss=0.3292, pruned_loss=0.06548, over 4959.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3076, pruned_loss=0.06494, over 966546.24 frames.], batch size: 16, lr: 5.33e-04
2022-05-29 06:41:50,955 INFO [train.py:761] (5/8) Epoch 26, batch 3250, loss[loss=0.231, simple_loss=0.322, pruned_loss=0.07003, over 4788.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3087, pruned_loss=0.06701, over 966127.55 frames.], batch size: 13, lr: 5.33e-04
2022-05-29 06:42:28,990 INFO [train.py:761] (5/8) Epoch 26, batch 3300, loss[loss=0.1999, simple_loss=0.2857, pruned_loss=0.05704, over 4730.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3086, pruned_loss=0.06817, over 965556.84 frames.], batch size: 11, lr: 5.33e-04
2022-05-29 06:43:07,500 INFO [train.py:761] (5/8) Epoch 26, batch 3350, loss[loss=0.2902, simple_loss=0.3475, pruned_loss=0.1165, over 4851.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3087, pruned_loss=0.06952, over 966813.17 frames.], batch size: 18, lr: 5.33e-04
2022-05-29 06:43:45,885 INFO [train.py:761] (5/8) Epoch 26, batch 3400, loss[loss=0.1745, simple_loss=0.2753, pruned_loss=0.03683, over 4811.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3091, pruned_loss=0.07114, over 967160.33 frames.], batch size: 12, lr: 5.33e-04
2022-05-29 06:44:24,249 INFO [train.py:761] (5/8) Epoch 26, batch 3450, loss[loss=0.2345, simple_loss=0.3174, pruned_loss=0.07582, over 4787.00 frames.], tot_loss[loss=0.227, simple_loss=0.3092, pruned_loss=0.07233, over 966824.24 frames.], batch size: 16, lr: 5.33e-04
2022-05-29 06:45:02,621 INFO [train.py:761] (5/8) Epoch 26, batch 3500, loss[loss=0.2622, simple_loss=0.3383, pruned_loss=0.09301, over 4913.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3107, pruned_loss=0.07382, over 967538.92 frames.], batch size: 25, lr: 5.33e-04
2022-05-29 06:45:40,630 INFO [train.py:761] (5/8) Epoch 26, batch 3550, loss[loss=0.2448, simple_loss=0.338, pruned_loss=0.07587, over 4880.00 frames.], tot_loss[loss=0.23, simple_loss=0.3114, pruned_loss=0.07427, over 967636.43 frames.], batch size: 17, lr: 5.33e-04
2022-05-29 06:46:19,131 INFO [train.py:761] (5/8) Epoch 26, batch 3600, loss[loss=0.2403, simple_loss=0.3282, pruned_loss=0.07621, over 4868.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3116, pruned_loss=0.0746, over 967024.17 frames.], batch size: 17, lr: 5.32e-04
2022-05-29 06:46:57,197 INFO [train.py:761] (5/8) Epoch 26, batch 3650, loss[loss=0.2282, simple_loss=0.3092, pruned_loss=0.07357, over 4737.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3127, pruned_loss=0.07573, over 965392.41 frames.], batch size: 11, lr: 5.32e-04
2022-05-29 06:47:35,718 INFO [train.py:761] (5/8) Epoch 26, batch 3700, loss[loss=0.2613, simple_loss=0.3479, pruned_loss=0.0873, over 4815.00 frames.], tot_loss[loss=0.2337, simple_loss=0.314, pruned_loss=0.07667, over 965811.87 frames.], batch size: 18, lr: 5.32e-04
2022-05-29 06:48:14,239 INFO [train.py:761] (5/8) Epoch 26, batch 3750, loss[loss=0.2743, simple_loss=0.3423, pruned_loss=0.1031, over 4943.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3136, pruned_loss=0.07675, over 964849.73 frames.], batch size: 48, lr: 5.32e-04
2022-05-29 06:48:52,393 INFO [train.py:761] (5/8) Epoch 26, batch 3800, loss[loss=0.2383, simple_loss=0.3136, pruned_loss=0.08147, over 4720.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3147, pruned_loss=0.07742, over 965344.22 frames.], batch size: 13, lr: 5.32e-04
2022-05-29 06:49:29,811 INFO [train.py:761] (5/8) Epoch 26, batch 3850, loss[loss=0.2018, simple_loss=0.2788, pruned_loss=0.06243, over 4789.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3148, pruned_loss=0.07751, over 964976.52 frames.], batch size: 13, lr: 5.32e-04
2022-05-29 06:50:08,479 INFO [train.py:761] (5/8) Epoch 26, batch 3900, loss[loss=0.2257, simple_loss=0.3059, pruned_loss=0.07269, over 4782.00 frames.], tot_loss[loss=0.2332, simple_loss=0.313, pruned_loss=0.07674, over 964312.91 frames.], batch size: 13, lr: 5.32e-04
2022-05-29 06:50:46,887 INFO [train.py:761] (5/8) Epoch 26, batch 3950, loss[loss=0.2021, simple_loss=0.2806, pruned_loss=0.06182, over 4632.00 frames.], tot_loss[loss=0.233, simple_loss=0.3123, pruned_loss=0.07681, over 965128.42 frames.], batch size: 10, lr: 5.32e-04
2022-05-29 06:51:24,966 INFO [train.py:761] (5/8) Epoch 26, batch 4000, loss[loss=0.2393, simple_loss=0.3232, pruned_loss=0.07767, over 4824.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3114, pruned_loss=0.07634, over 965267.37 frames.], batch size: 18, lr: 5.32e-04
2022-05-29 06:52:02,911 INFO [train.py:761] (5/8) Epoch 26, batch 4050, loss[loss=0.1864, simple_loss=0.2698, pruned_loss=0.05149, over 4575.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3122, pruned_loss=0.07681, over 964924.28 frames.], batch size: 10, lr: 5.32e-04
2022-05-29 06:52:41,248 INFO [train.py:761] (5/8) Epoch 26, batch 4100, loss[loss=0.2524, simple_loss=0.3416, pruned_loss=0.08158, over 4762.00 frames.], tot_loss[loss=0.234, simple_loss=0.3131, pruned_loss=0.07749, over 965663.61 frames.], batch size: 15, lr: 5.32e-04
2022-05-29 06:53:19,070 INFO [train.py:761] (5/8) Epoch 26, batch 4150, loss[loss=0.1826, simple_loss=0.2585, pruned_loss=0.05334, over 4642.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3127, pruned_loss=0.07693, over 965569.99 frames.], batch size: 11, lr: 5.32e-04
2022-05-29 06:53:57,025 INFO [train.py:761] (5/8) Epoch 26, batch 4200, loss[loss=0.2387, simple_loss=0.2891, pruned_loss=0.09416, over 4828.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3125, pruned_loss=0.07635, over 965079.32 frames.], batch size: 11, lr: 5.32e-04
2022-05-29 06:54:35,287 INFO [train.py:761] (5/8) Epoch 26, batch 4250, loss[loss=0.2143, simple_loss=0.3004, pruned_loss=0.0641, over 4793.00 frames.], tot_loss[loss=0.2343, simple_loss=0.314, pruned_loss=0.07731, over 964867.14 frames.], batch size: 14, lr: 5.31e-04
2022-05-29 06:55:13,943 INFO [train.py:761] (5/8) Epoch 26, batch 4300, loss[loss=0.286, simple_loss=0.3395, pruned_loss=0.1162, over 4850.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3122, pruned_loss=0.0764, over 964478.84 frames.], batch size: 13, lr: 5.31e-04
2022-05-29 06:55:51,443 INFO [train.py:761] (5/8) Epoch 26, batch 4350, loss[loss=0.2393, simple_loss=0.3382, pruned_loss=0.07022, over 4983.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3132, pruned_loss=0.07633, over 965738.34 frames.], batch size: 21, lr: 5.31e-04
2022-05-29 06:56:29,548 INFO [train.py:761] (5/8) Epoch 26, batch 4400, loss[loss=0.2871, simple_loss=0.3619, pruned_loss=0.1062, over 4902.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3122, pruned_loss=0.07559, over 966241.35 frames.], batch size: 26, lr: 5.31e-04
2022-05-29 06:57:07,623 INFO [train.py:761] (5/8) Epoch 26, batch 4450, loss[loss=0.2031, simple_loss=0.2708, pruned_loss=0.06768, over 4655.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3132, pruned_loss=0.07673, over 967979.66 frames.], batch size: 11, lr: 5.31e-04
2022-05-29 06:57:45,664 INFO [train.py:761] (5/8) Epoch 26, batch 4500, loss[loss=0.1536, simple_loss=0.2361, pruned_loss=0.03552, over 4885.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3127, pruned_loss=0.07623, over 968345.28 frames.], batch size: 12, lr: 5.31e-04
2022-05-29 06:58:24,271 INFO [train.py:761] (5/8) Epoch 26, batch 4550, loss[loss=0.2371, simple_loss=0.3174, pruned_loss=0.07844, over 4914.00 frames.], tot_loss[loss=0.233, simple_loss=0.3123, pruned_loss=0.07685, over 967592.61 frames.], batch size: 14, lr: 5.31e-04
2022-05-29 06:59:02,340 INFO [train.py:761] (5/8) Epoch 26, batch 4600, loss[loss=0.221, simple_loss=0.3151, pruned_loss=0.06347, over 4723.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3143, pruned_loss=0.07811, over 968406.27 frames.], batch size: 14, lr: 5.31e-04
2022-05-29 06:59:40,443 INFO [train.py:761] (5/8) Epoch 26, batch 4650, loss[loss=0.2481, simple_loss=0.3361, pruned_loss=0.08003, over 4913.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3128, pruned_loss=0.07719, over 967560.67 frames.], batch size: 14, lr: 5.31e-04
2022-05-29 07:00:18,918 INFO [train.py:761] (5/8) Epoch 26, batch 4700, loss[loss=0.2617, simple_loss=0.3376, pruned_loss=0.09292, over 4982.00 frames.], tot_loss[loss=0.2334, simple_loss=0.312, pruned_loss=0.07743, over 968104.67 frames.], batch size: 15, lr: 5.31e-04
2022-05-29 07:00:57,173 INFO [train.py:761] (5/8) Epoch 26, batch 4750, loss[loss=0.2459, simple_loss=0.3199, pruned_loss=0.08601, over 4980.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3112, pruned_loss=0.0768, over 966513.80 frames.], batch size: 15, lr: 5.31e-04
2022-05-29 07:01:35,835 INFO [train.py:761] (5/8) Epoch 26, batch 4800, loss[loss=0.2393, simple_loss=0.3148, pruned_loss=0.08195, over 4887.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3111, pruned_loss=0.07687, over 965938.65 frames.], batch size: 15, lr: 5.31e-04
2022-05-29 07:02:14,291 INFO [train.py:761] (5/8) Epoch 26, batch 4850, loss[loss=0.2271, simple_loss=0.292, pruned_loss=0.08114, over 4728.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3107, pruned_loss=0.07646, over 965671.70 frames.], batch size: 12, lr: 5.31e-04
2022-05-29 07:02:52,591 INFO [train.py:761] (5/8) Epoch 26, batch 4900, loss[loss=0.2635, simple_loss=0.3171, pruned_loss=0.105, over 4674.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3108, pruned_loss=0.07618, over 965879.09 frames.], batch size: 13, lr: 5.30e-04
2022-05-29 07:03:30,226 INFO [train.py:761] (5/8) Epoch 26, batch 4950, loss[loss=0.2129, simple_loss=0.2962, pruned_loss=0.06482, over 4788.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3105, pruned_loss=0.07554, over 965610.98 frames.], batch size: 14, lr: 5.30e-04
2022-05-29 07:04:08,671 INFO [train.py:761] (5/8) Epoch 26, batch 5000, loss[loss=0.2374, simple_loss=0.299, pruned_loss=0.08787, over 4987.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3091, pruned_loss=0.07528, over 965067.52 frames.], batch size: 13, lr: 5.30e-04
2022-05-29 07:04:46,421 INFO [train.py:761] (5/8) Epoch 26, batch 5050, loss[loss=0.2912, simple_loss=0.3831, pruned_loss=0.09969, over 4909.00 frames.], tot_loss[loss=0.2297, simple_loss=0.3094, pruned_loss=0.07503, over 965058.43 frames.], batch size: 26, lr: 5.30e-04
2022-05-29 07:05:25,197 INFO [train.py:761] (5/8) Epoch 26, batch 5100, loss[loss=0.1759, simple_loss=0.2661, pruned_loss=0.04281, over 4989.00 frames.], tot_loss[loss=0.2308, simple_loss=0.311, pruned_loss=0.07526, over 965713.37 frames.], batch size: 13, lr: 5.30e-04
2022-05-29 07:06:03,284 INFO [train.py:761] (5/8) Epoch 26, batch 5150, loss[loss=0.2138, simple_loss=0.2934, pruned_loss=0.06711, over 4848.00 frames.], tot_loss[loss=0.231, simple_loss=0.3107, pruned_loss=0.07564, over 967101.67 frames.], batch size: 13, lr: 5.30e-04
2022-05-29 07:06:41,752 INFO [train.py:761] (5/8) Epoch 26, batch 5200, loss[loss=0.2213, simple_loss=0.307, pruned_loss=0.06782, over 4797.00 frames.], tot_loss[loss=0.232, simple_loss=0.3121, pruned_loss=0.07601, over 966091.16 frames.], batch size: 16, lr: 5.30e-04
2022-05-29 07:07:20,283 INFO [train.py:761] (5/8) Epoch 26, batch 5250, loss[loss=0.2947, simple_loss=0.3705, pruned_loss=0.1095, over 4931.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3132, pruned_loss=0.07694, over 967225.07 frames.], batch size: 47, lr: 5.30e-04
2022-05-29 07:07:58,717 INFO [train.py:761] (5/8) Epoch 26, batch 5300, loss[loss=0.2006, simple_loss=0.2967, pruned_loss=0.0523, over 4791.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3128, pruned_loss=0.07683, over 968209.16 frames.], batch size: 14, lr: 5.30e-04
2022-05-29 07:08:37,110 INFO [train.py:761] (5/8) Epoch 26, batch 5350, loss[loss=0.2631, simple_loss=0.3389, pruned_loss=0.09361, over 4792.00 frames.], tot_loss[loss=0.2334, simple_loss=0.313, pruned_loss=0.07685, over 967193.36 frames.], batch size: 20, lr: 5.30e-04
2022-05-29 07:09:16,268 INFO [train.py:761] (5/8) Epoch 26, batch 5400, loss[loss=0.2349, simple_loss=0.3147, pruned_loss=0.07749, over 4726.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3148, pruned_loss=0.0782, over 967098.06 frames.], batch size: 12, lr: 5.30e-04
2022-05-29 07:09:54,960 INFO [train.py:761] (5/8) Epoch 26, batch 5450, loss[loss=0.186, simple_loss=0.2742, pruned_loss=0.04892, over 4725.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3125, pruned_loss=0.07694, over 966490.12 frames.], batch size: 12, lr: 5.30e-04
2022-05-29 07:10:33,411 INFO [train.py:761] (5/8) Epoch 26, batch 5500, loss[loss=0.1948, simple_loss=0.2804, pruned_loss=0.05458, over 4723.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3107, pruned_loss=0.07545, over 965134.52 frames.], batch size: 12, lr: 5.30e-04
2022-05-29 07:11:11,842 INFO [train.py:761] (5/8) Epoch 26, batch 5550, loss[loss=0.2302, simple_loss=0.2836, pruned_loss=0.08844, over 4883.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3118, pruned_loss=0.07627, over 965118.73 frames.], batch size: 12, lr: 5.29e-04
2022-05-29 07:11:49,972 INFO [train.py:761] (5/8) Epoch 26, batch 5600, loss[loss=0.2682, simple_loss=0.335, pruned_loss=0.1007, over 4727.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3112, pruned_loss=0.07588, over 963992.45 frames.], batch size: 13, lr: 5.29e-04
2022-05-29 07:12:28,525 INFO [train.py:761] (5/8) Epoch 26, batch 5650, loss[loss=0.24, simple_loss=0.3252, pruned_loss=0.07745, over 4778.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3109, pruned_loss=0.07586, over 964896.50 frames.], batch size: 20, lr: 5.29e-04
2022-05-29 07:13:06,931 INFO [train.py:761] (5/8) Epoch 26, batch 5700, loss[loss=0.2254, simple_loss=0.2927, pruned_loss=0.07902, over 4762.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3119, pruned_loss=0.0763, over 965365.68 frames.], batch size: 15, lr: 5.29e-04
2022-05-29 07:13:45,216 INFO [train.py:761] (5/8) Epoch 26, batch 5750, loss[loss=0.1784, simple_loss=0.2781, pruned_loss=0.03929, over 4968.00 frames.], tot_loss[loss=0.231, simple_loss=0.3107, pruned_loss=0.07563, over 967069.20 frames.], batch size: 12, lr: 5.29e-04
2022-05-29 07:14:23,439 INFO [train.py:761] (5/8) Epoch 26, batch 5800, loss[loss=0.3192, simple_loss=0.3818, pruned_loss=0.1283, over 4937.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3108, pruned_loss=0.07552, over 966502.65 frames.], batch size: 45, lr: 5.29e-04
2022-05-29 07:15:01,356 INFO [train.py:761] (5/8) Epoch 26, batch 5850, loss[loss=0.236, simple_loss=0.3112, pruned_loss=0.08035, over 4915.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3095, pruned_loss=0.07442, over 965404.02 frames.], batch size: 13, lr: 5.29e-04
2022-05-29 07:15:39,693 INFO [train.py:761] (5/8) Epoch 26, batch 5900, loss[loss=0.2215, simple_loss=0.31, pruned_loss=0.06649, over 4953.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3116, pruned_loss=0.07538, over 965234.12 frames.], batch size: 16, lr: 5.29e-04
2022-05-29 07:16:17,370 INFO [train.py:761] (5/8) Epoch 26, batch 5950, loss[loss=0.2345, simple_loss=0.3208, pruned_loss=0.07411, over 4777.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3141, pruned_loss=0.07648, over 966267.34 frames.], batch size: 15, lr: 5.29e-04
2022-05-29 07:16:55,971 INFO [train.py:761] (5/8) Epoch 26, batch 6000, loss[loss=0.2186, simple_loss=0.3128, pruned_loss=0.06223, over 4972.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3142, pruned_loss=0.07681, over 967650.40 frames.], batch size: 14, lr: 5.29e-04
2022-05-29 07:16:55,972 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 07:17:05,798 INFO [train.py:790] (5/8) Epoch 26, validation: loss=0.1987, simple_loss=0.3027, pruned_loss=0.04737, over 944034.00 frames.
2022-05-29 07:17:44,132 INFO [train.py:761] (5/8) Epoch 26, batch 6050, loss[loss=0.2494, simple_loss=0.3261, pruned_loss=0.08631, over 4847.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3134, pruned_loss=0.07648, over 967687.57 frames.], batch size: 14, lr: 5.29e-04
2022-05-29 07:18:23,199 INFO [train.py:761] (5/8) Epoch 26, batch 6100, loss[loss=0.2418, simple_loss=0.3067, pruned_loss=0.08849, over 4780.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3126, pruned_loss=0.07647, over 967676.43 frames.], batch size: 13, lr: 5.29e-04
2022-05-29 07:19:00,957 INFO [train.py:761] (5/8) Epoch 26, batch 6150, loss[loss=0.2352, simple_loss=0.3128, pruned_loss=0.07876, over 4781.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3123, pruned_loss=0.07667, over 966553.69 frames.], batch size: 13, lr: 5.29e-04
2022-05-29 07:19:39,829 INFO [train.py:761] (5/8) Epoch 26, batch 6200, loss[loss=0.2392, simple_loss=0.3246, pruned_loss=0.07694, over 4869.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3126, pruned_loss=0.07686, over 966394.20 frames.], batch size: 18, lr: 5.28e-04
2022-05-29 07:20:18,182 INFO [train.py:761] (5/8) Epoch 26, batch 6250, loss[loss=0.2427, simple_loss=0.3259, pruned_loss=0.07972, over 4787.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3131, pruned_loss=0.07687, over 967204.08 frames.], batch size: 14, lr: 5.28e-04
2022-05-29 07:20:55,660 INFO [train.py:761] (5/8) Epoch 26, batch 6300, loss[loss=0.2522, simple_loss=0.3284, pruned_loss=0.08801, over 4916.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3129, pruned_loss=0.07677, over 967350.16 frames.], batch size: 14, lr: 5.28e-04
2022-05-29 07:21:34,058 INFO [train.py:761] (5/8) Epoch 26, batch 6350, loss[loss=0.2486, simple_loss=0.3353, pruned_loss=0.08098, over 4994.00 frames.], tot_loss[loss=0.232, simple_loss=0.3123, pruned_loss=0.07586, over 967922.23 frames.], batch size: 13, lr: 5.28e-04
2022-05-29 07:22:12,568 INFO [train.py:761] (5/8) Epoch 26, batch 6400, loss[loss=0.2004, simple_loss=0.2948, pruned_loss=0.05304, over 4722.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3122, pruned_loss=0.07595, over 968142.14 frames.], batch size: 14, lr: 5.28e-04
2022-05-29 07:22:51,425 INFO [train.py:761] (5/8) Epoch 26, batch 6450, loss[loss=0.2337, simple_loss=0.3239, pruned_loss=0.07173, over 4772.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3099, pruned_loss=0.07426, over 967652.78 frames.], batch size: 16, lr: 5.28e-04
2022-05-29 07:23:30,068 INFO [train.py:761] (5/8) Epoch 26, batch 6500, loss[loss=0.1672, simple_loss=0.2441, pruned_loss=0.04515, over 4734.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3092, pruned_loss=0.07383, over 968047.99 frames.], batch size: 11, lr: 5.28e-04
2022-05-29 07:24:08,013 INFO [train.py:761] (5/8) Epoch 26, batch 6550, loss[loss=0.2375, simple_loss=0.3274, pruned_loss=0.07382, over 4955.00 frames.], tot_loss[loss=0.2287, simple_loss=0.3098, pruned_loss=0.0738, over 967441.28 frames.], batch size: 16, lr: 5.28e-04
2022-05-29 07:24:46,969 INFO [train.py:761] (5/8) Epoch 26, batch 6600, loss[loss=0.24, simple_loss=0.3208, pruned_loss=0.07958, over 4668.00 frames.], tot_loss[loss=0.2301, simple_loss=0.3107, pruned_loss=0.07473, over 967721.53 frames.], batch size: 13, lr: 5.28e-04
2022-05-29 07:25:25,403 INFO [train.py:761] (5/8) Epoch 26, batch 6650, loss[loss=0.2325, simple_loss=0.3195, pruned_loss=0.07277, over 4673.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3111, pruned_loss=0.07522, over 966707.51 frames.], batch size: 13, lr: 5.28e-04
2022-05-29 07:26:03,490 INFO [train.py:761] (5/8) Epoch 26, batch 6700, loss[loss=0.2345, simple_loss=0.3225, pruned_loss=0.07327, over 4938.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3113, pruned_loss=0.07543, over 966178.60 frames.], batch size: 16, lr: 5.28e-04
2022-05-29 07:26:58,449 INFO [train.py:761] (5/8) Epoch 27, batch 0, loss[loss=0.2235, simple_loss=0.3235, pruned_loss=0.06181, over 4909.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3235, pruned_loss=0.06181, over 4909.00 frames.], batch size: 14, lr: 5.28e-04
2022-05-29 07:27:36,556 INFO [train.py:761] (5/8) Epoch 27, batch 50, loss[loss=0.2592, simple_loss=0.3495, pruned_loss=0.08443, over 4973.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3053, pruned_loss=0.06277, over 219427.94 frames.], batch size: 14, lr: 5.28e-04
2022-05-29 07:28:14,105 INFO [train.py:761] (5/8) Epoch 27, batch 100, loss[loss=0.2025, simple_loss=0.3078, pruned_loss=0.04863, over 4863.00 frames.], tot_loss[loss=0.214, simple_loss=0.3045, pruned_loss=0.0618, over 385071.35 frames.], batch size: 18, lr: 5.27e-04
2022-05-29 07:28:51,991 INFO [train.py:761] (5/8) Epoch 27, batch 150, loss[loss=0.1855, simple_loss=0.2653, pruned_loss=0.05285, over 4514.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3042, pruned_loss=0.06118, over 513016.83 frames.], batch size: 10, lr: 5.27e-04
2022-05-29 07:29:30,137 INFO [train.py:761] (5/8) Epoch 27, batch 200, loss[loss=0.1889, simple_loss=0.2851, pruned_loss=0.04633, over 4804.00 frames.], tot_loss[loss=0.2124, simple_loss=0.304, pruned_loss=0.06034, over 613908.20 frames.], batch size: 16, lr: 5.27e-04
2022-05-29 07:30:07,961 INFO [train.py:761] (5/8) Epoch 27, batch 250, loss[loss=0.179, simple_loss=0.2672, pruned_loss=0.04535, over 4983.00 frames.], tot_loss[loss=0.2106, simple_loss=0.3018, pruned_loss=0.05972, over 693255.85 frames.], batch size: 13, lr: 5.27e-04
2022-05-29 07:30:45,180 INFO [train.py:761] (5/8) Epoch 27, batch 300, loss[loss=0.1645, simple_loss=0.2538, pruned_loss=0.03763, over 4640.00 frames.], tot_loss[loss=0.2105, simple_loss=0.3016, pruned_loss=0.05963, over 753541.48 frames.], batch size: 11, lr: 5.27e-04
2022-05-29 07:31:23,217 INFO [train.py:761] (5/8) Epoch 27, batch 350, loss[loss=0.2356, simple_loss=0.3291, pruned_loss=0.07103, over 4726.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2999, pruned_loss=0.0594, over 800240.79 frames.], batch size: 13, lr: 5.27e-04
2022-05-29 07:32:01,263 INFO [train.py:761] (5/8) Epoch 27, batch 400, loss[loss=0.1852, simple_loss=0.2955, pruned_loss=0.03739, over 4917.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2998, pruned_loss=0.05933, over 837097.99 frames.], batch size: 13, lr: 5.27e-04
2022-05-29 07:32:39,918 INFO [train.py:761] (5/8) Epoch 27, batch 450, loss[loss=0.1837, simple_loss=0.2876, pruned_loss=0.03995, over 4724.00 frames.], tot_loss[loss=0.2091, simple_loss=0.3004, pruned_loss=0.05894, over 865666.85 frames.], batch size: 12, lr: 5.27e-04
2022-05-29 07:33:18,206 INFO [train.py:761] (5/8) Epoch 27, batch 500, loss[loss=0.2045, simple_loss=0.3047, pruned_loss=0.05217, over 4736.00 frames.], tot_loss[loss=0.2089, simple_loss=0.3001, pruned_loss=0.0588, over 888380.97 frames.], batch size: 13, lr: 5.27e-04
2022-05-29 07:33:56,465 INFO [train.py:761] (5/8) Epoch 27, batch 550, loss[loss=0.175, simple_loss=0.2794, pruned_loss=0.03534, over 4783.00 frames.], tot_loss[loss=0.2088, simple_loss=0.3002, pruned_loss=0.05872, over 906193.21 frames.], batch size: 14, lr: 5.27e-04
2022-05-29 07:34:34,182 INFO [train.py:761] (5/8) Epoch 27, batch 600, loss[loss=0.1815, simple_loss=0.2709, pruned_loss=0.04607, over 4740.00 frames.], tot_loss[loss=0.2091, simple_loss=0.3007, pruned_loss=0.05874, over 919688.10 frames.], batch size: 12, lr: 5.27e-04
2022-05-29 07:35:15,201 INFO [train.py:761] (5/8) Epoch 27, batch 650, loss[loss=0.2282, simple_loss=0.3157, pruned_loss=0.07034, over 4978.00 frames.], tot_loss[loss=0.2095, simple_loss=0.3009, pruned_loss=0.05911, over 930892.77 frames.], batch size: 15, lr: 5.27e-04
2022-05-29 07:35:53,251 INFO [train.py:761] (5/8) Epoch 27, batch 700, loss[loss=0.2432, simple_loss=0.3152, pruned_loss=0.08565, over 4884.00 frames.], tot_loss[loss=0.2114, simple_loss=0.3021, pruned_loss=0.06037, over 939473.89 frames.], batch size: 12, lr: 5.27e-04
2022-05-29 07:36:31,959 INFO [train.py:761] (5/8) Epoch 27, batch 750, loss[loss=0.2253, simple_loss=0.3283, pruned_loss=0.0611, over 4912.00 frames.], tot_loss[loss=0.212, simple_loss=0.3027, pruned_loss=0.06064, over 944961.97 frames.], batch size: 14, lr: 5.27e-04
2022-05-29 07:37:10,289 INFO [train.py:761] (5/8) Epoch 27, batch 800, loss[loss=0.2042, simple_loss=0.2902, pruned_loss=0.05912, over 4879.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3044, pruned_loss=0.06175, over 950053.65 frames.], batch size: 15, lr: 5.26e-04
2022-05-29 07:37:47,931 INFO [train.py:761] (5/8) Epoch 27, batch 850, loss[loss=0.1835, simple_loss=0.2654, pruned_loss=0.05085, over 4843.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3048, pruned_loss=0.06242, over 952845.77 frames.], batch size: 11, lr: 5.26e-04
2022-05-29 07:38:26,061 INFO [train.py:761] (5/8) Epoch 27, batch 900, loss[loss=0.187, simple_loss=0.264, pruned_loss=0.05504, over 4653.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3052, pruned_loss=0.06308, over 955767.96 frames.], batch size: 11, lr: 5.26e-04
2022-05-29 07:39:04,003 INFO [train.py:761] (5/8) Epoch 27, batch 950, loss[loss=0.1871, simple_loss=0.2698, pruned_loss=0.05222, over 4664.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3048, pruned_loss=0.06253, over 956692.99 frames.], batch size: 12, lr: 5.26e-04
2022-05-29 07:39:42,441 INFO [train.py:761] (5/8) Epoch 27, batch 1000, loss[loss=0.2242, simple_loss=0.3051, pruned_loss=0.07168, over 4996.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3066, pruned_loss=0.06304, over 958667.46 frames.], batch size: 13, lr: 5.26e-04
2022-05-29 07:40:20,279 INFO [train.py:761] (5/8) Epoch 27, batch 1050, loss[loss=0.1624, simple_loss=0.2588, pruned_loss=0.03296, over 4852.00 frames.], tot_loss[loss=0.215, simple_loss=0.3058, pruned_loss=0.06212, over 959604.03 frames.], batch size: 13, lr: 5.26e-04
2022-05-29 07:40:57,645 INFO [train.py:761] (5/8) Epoch 27, batch 1100, loss[loss=0.1854, simple_loss=0.2766, pruned_loss=0.0471, over 4636.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3059, pruned_loss=0.06172, over 961025.02 frames.], batch size: 11, lr: 5.26e-04
2022-05-29 07:41:35,246 INFO [train.py:761] (5/8) Epoch 27, batch 1150, loss[loss=0.1752, simple_loss=0.2517, pruned_loss=0.04935, over 4576.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3063, pruned_loss=0.06191, over 961624.31 frames.], batch size: 10, lr: 5.26e-04
2022-05-29 07:42:12,931 INFO [train.py:761] (5/8) Epoch 27, batch 1200, loss[loss=0.1893, simple_loss=0.2681, pruned_loss=0.05524, over 4660.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3046, pruned_loss=0.06116, over 962379.70 frames.], batch size: 12, lr: 5.26e-04
2022-05-29 07:42:50,433 INFO [train.py:761] (5/8) Epoch 27, batch 1250, loss[loss=0.1895, simple_loss=0.2787, pruned_loss=0.05009, over 4799.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3062, pruned_loss=0.06229, over 962650.41 frames.], batch size: 12, lr: 5.26e-04
2022-05-29 07:43:28,485 INFO [train.py:761] (5/8) Epoch 27, batch 1300, loss[loss=0.2124, simple_loss=0.3201, pruned_loss=0.05238, over 4671.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3062, pruned_loss=0.06238, over 961890.68 frames.], batch size: 13, lr: 5.26e-04
2022-05-29 07:44:06,903 INFO [train.py:761] (5/8) Epoch 27, batch 1350, loss[loss=0.156, simple_loss=0.2381, pruned_loss=0.03693, over 4832.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3068, pruned_loss=0.06267, over 963390.57 frames.], batch size: 11, lr: 5.26e-04
2022-05-29 07:44:44,946 INFO [train.py:761] (5/8) Epoch 27, batch 1400, loss[loss=0.1902, simple_loss=0.279, pruned_loss=0.0507, over 4836.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3066, pruned_loss=0.06223, over 963640.15 frames.], batch size: 11, lr: 5.26e-04
2022-05-29 07:45:23,331 INFO [train.py:761] (5/8) Epoch 27, batch 1450, loss[loss=0.1945, simple_loss=0.2829, pruned_loss=0.05302, over 4721.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3071, pruned_loss=0.06229, over 963764.46 frames.], batch size: 13, lr: 5.25e-04
2022-05-29 07:46:01,523 INFO [train.py:761] (5/8) Epoch 27, batch 1500, loss[loss=0.2223, simple_loss=0.3301, pruned_loss=0.05723, over 4912.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3062, pruned_loss=0.06181, over 964977.02 frames.], batch size: 14, lr: 5.25e-04
2022-05-29 07:46:39,554 INFO [train.py:761] (5/8) Epoch 27, batch 1550, loss[loss=0.2632, simple_loss=0.3597, pruned_loss=0.08339, over 4872.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3062, pruned_loss=0.06169, over 963969.42 frames.], batch size: 15, lr: 5.25e-04
2022-05-29 07:47:17,084 INFO [train.py:761] (5/8) Epoch 27, batch 1600, loss[loss=0.1891, simple_loss=0.2836, pruned_loss=0.04733, over 4725.00 frames.], tot_loss[loss=0.2147, simple_loss=0.306, pruned_loss=0.06167, over 964163.49 frames.], batch size: 12, lr: 5.25e-04
2022-05-29 07:47:55,782 INFO [train.py:761] (5/8) Epoch 27, batch 1650, loss[loss=0.1552, simple_loss=0.2482, pruned_loss=0.03112, over 4650.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3044, pruned_loss=0.06134, over 965349.34 frames.], batch size: 11, lr: 5.25e-04
2022-05-29 07:48:33,621 INFO [train.py:761] (5/8) Epoch 27, batch 1700, loss[loss=0.2064, simple_loss=0.2909, pruned_loss=0.06092, over 4973.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3046, pruned_loss=0.06158, over 965147.74 frames.], batch size: 12, lr: 5.25e-04
2022-05-29 07:49:11,499 INFO [train.py:761] (5/8) Epoch 27, batch 1750, loss[loss=0.2284, simple_loss=0.3202, pruned_loss=0.06826, over 4776.00 frames.], tot_loss[loss=0.214, simple_loss=0.305, pruned_loss=0.06146, over 965143.59 frames.], batch size: 16, lr: 5.25e-04
2022-05-29 07:49:49,571 INFO [train.py:761] (5/8) Epoch 27, batch 1800, loss[loss=0.2397, simple_loss=0.334, pruned_loss=0.07268, over 4790.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3049, pruned_loss=0.06129, over 965575.35 frames.], batch size: 14, lr: 5.25e-04
2022-05-29 07:50:27,550 INFO [train.py:761] (5/8) Epoch 27, batch 1850, loss[loss=0.2009, simple_loss=0.2936, pruned_loss=0.05409, over 4723.00 frames.], tot_loss[loss=0.2128, simple_loss=0.304, pruned_loss=0.06085, over 965762.56 frames.], batch size: 13, lr: 5.25e-04
2022-05-29 07:51:05,750 INFO [train.py:761] (5/8) Epoch 27, batch 1900, loss[loss=0.2184, simple_loss=0.3129, pruned_loss=0.06199, over 4849.00 frames.], tot_loss[loss=0.2126, simple_loss=0.3045, pruned_loss=0.06032, over 965029.20 frames.], batch size: 18, lr: 5.25e-04
2022-05-29 07:51:43,564 INFO [train.py:761] (5/8) Epoch 27, batch 1950, loss[loss=0.219, simple_loss=0.305, pruned_loss=0.06647, over 4670.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3038, pruned_loss=0.06016, over 964409.96 frames.], batch size: 12, lr: 5.25e-04
2022-05-29 07:52:21,335 INFO [train.py:761] (5/8) Epoch 27, batch 2000, loss[loss=0.2406, simple_loss=0.3429, pruned_loss=0.06913, over 4879.00 frames.], tot_loss[loss=0.2125, simple_loss=0.304, pruned_loss=0.06051, over 966363.30 frames.], batch size: 15, lr: 5.25e-04
2022-05-29 07:52:59,320 INFO [train.py:761] (5/8) Epoch 27, batch 2050, loss[loss=0.1786, simple_loss=0.2654, pruned_loss=0.04586, over 4885.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3051, pruned_loss=0.06129, over 965796.96 frames.], batch size: 12, lr: 5.25e-04
2022-05-29 07:53:37,031 INFO [train.py:761] (5/8) Epoch 27, batch 2100, loss[loss=0.2582, simple_loss=0.3415, pruned_loss=0.08747, over 4846.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3044, pruned_loss=0.06066, over 966150.84 frames.], batch size: 14, lr: 5.25e-04
2022-05-29 07:54:14,873 INFO [train.py:761] (5/8) Epoch 27, batch 2150, loss[loss=0.2342, simple_loss=0.3223, pruned_loss=0.07303, over 4715.00 frames.], tot_loss[loss=0.2129, simple_loss=0.304, pruned_loss=0.06089, over 965879.67 frames.], batch size: 14, lr: 5.24e-04
2022-05-29 07:54:53,299 INFO [train.py:761] (5/8) Epoch 27, batch 2200, loss[loss=0.1964, simple_loss=0.2759, pruned_loss=0.05842, over 4711.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3045, pruned_loss=0.06137, over 966305.84 frames.], batch size: 11, lr: 5.24e-04
2022-05-29 07:55:31,545 INFO [train.py:761] (5/8) Epoch 27, batch 2250, loss[loss=0.2011, simple_loss=0.2899, pruned_loss=0.05617, over 4781.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3048, pruned_loss=0.06144, over 966123.17 frames.], batch size: 14, lr: 5.24e-04
2022-05-29 07:56:09,424 INFO [train.py:761] (5/8) Epoch 27, batch 2300, loss[loss=0.2321, simple_loss=0.3315, pruned_loss=0.06639, over 4862.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3054, pruned_loss=0.06115, over 965305.04 frames.], batch size: 21, lr: 5.24e-04
2022-05-29 07:56:47,442 INFO [train.py:761] (5/8) Epoch 27, batch 2350, loss[loss=0.2092, simple_loss=0.3028, pruned_loss=0.05776, over 4665.00 frames.], tot_loss[loss=0.2135, simple_loss=0.305, pruned_loss=0.06096, over 965432.66 frames.], batch size: 13, lr: 5.24e-04
2022-05-29 07:57:25,292 INFO [train.py:761] (5/8) Epoch 27, batch 2400, loss[loss=0.2535, simple_loss=0.3454, pruned_loss=0.08076, over 4811.00 frames.], tot_loss[loss=0.2127, simple_loss=0.3041, pruned_loss=0.06066, over 964844.24 frames.], batch size: 18, lr: 5.24e-04
2022-05-29 07:58:02,793 INFO [train.py:761] (5/8) Epoch 27, batch 2450, loss[loss=0.1779, simple_loss=0.2769, pruned_loss=0.0395, over 4658.00 frames.], tot_loss[loss=0.213, simple_loss=0.3043, pruned_loss=0.06087, over 964655.05 frames.], batch size: 12, lr: 5.24e-04
2022-05-29 07:58:40,890 INFO [train.py:761] (5/8) Epoch 27, batch 2500, loss[loss=0.201, simple_loss=0.2969, pruned_loss=0.05254, over 4857.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3049, pruned_loss=0.06099, over 965698.35 frames.], batch size: 13, lr: 5.24e-04
2022-05-29 07:59:19,686 INFO [train.py:761] (5/8) Epoch 27, batch 2550, loss[loss=0.1595, simple_loss=0.2502, pruned_loss=0.03436, over 4831.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3048, pruned_loss=0.06123, over 965464.75 frames.], batch size: 11, lr: 5.24e-04
2022-05-29 07:59:58,136 INFO [train.py:761] (5/8) Epoch 27, batch 2600, loss[loss=0.2249, simple_loss=0.3152, pruned_loss=0.06733, over 4919.00 frames.], tot_loss[loss=0.2125, simple_loss=0.3038, pruned_loss=0.06055, over 967336.46 frames.], batch size: 13, lr: 5.24e-04
2022-05-29 08:00:36,330 INFO [train.py:761] (5/8) Epoch 27, batch 2650, loss[loss=0.2099, simple_loss=0.3051, pruned_loss=0.05732, over 4769.00 frames.], tot_loss[loss=0.2119, simple_loss=0.3035, pruned_loss=0.06008, over 965992.25 frames.], batch size: 20, lr: 5.24e-04
2022-05-29 08:01:14,817 INFO [train.py:761] (5/8) Epoch 27, batch 2700, loss[loss=0.2051, simple_loss=0.3152, pruned_loss=0.04747, over 4846.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3038, pruned_loss=0.06026, over 967415.11 frames.], batch size: 26, lr: 5.24e-04
2022-05-29 08:01:53,168 INFO [train.py:761] (5/8) Epoch 27, batch 2750, loss[loss=0.2342, simple_loss=0.3387, pruned_loss=0.06486, over 4968.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3048, pruned_loss=0.06078, over 967024.31 frames.], batch size: 15, lr: 5.24e-04
2022-05-29 08:02:30,468 INFO [train.py:761] (5/8) Epoch 27, batch 2800, loss[loss=0.2089, simple_loss=0.2847, pruned_loss=0.06654, over 4893.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3047, pruned_loss=0.06056, over 966444.40 frames.], batch size: 12, lr: 5.23e-04
2022-05-29 08:03:08,419 INFO [train.py:761] (5/8) Epoch 27, batch 2850, loss[loss=0.1846, simple_loss=0.2729, pruned_loss=0.04816, over 4838.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3033, pruned_loss=0.0604, over 966126.38 frames.], batch size: 11, lr: 5.23e-04
2022-05-29 08:03:46,356 INFO [train.py:761] (5/8) Epoch 27, batch 2900, loss[loss=0.2104, simple_loss=0.3046, pruned_loss=0.05814, over 4895.00 frames.], tot_loss[loss=0.2131, simple_loss=0.3044, pruned_loss=0.06096, over 965839.85 frames.], batch size: 15, lr: 5.23e-04
2022-05-29 08:04:24,559 INFO [train.py:761] (5/8) Epoch 27, batch 2950, loss[loss=0.2003, simple_loss=0.2901, pruned_loss=0.05531, over 4783.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3037, pruned_loss=0.06022, over 964591.12 frames.], batch size: 15, lr: 5.23e-04
2022-05-29 08:05:02,233 INFO [train.py:761] (5/8) Epoch 27, batch 3000, loss[loss=0.1592, simple_loss=0.2557, pruned_loss=0.03135, over 4970.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3041, pruned_loss=0.06025, over 964734.40 frames.], batch size: 12, lr: 5.23e-04
2022-05-29 08:05:02,233 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 08:05:12,260 INFO [train.py:790] (5/8) Epoch 27, validation: loss=0.205, simple_loss=0.3057, pruned_loss=0.05214, over 944034.00 frames.
2022-05-29 08:05:50,368 INFO [train.py:761] (5/8) Epoch 27, batch 3050, loss[loss=0.2487, simple_loss=0.3333, pruned_loss=0.0821, over 4838.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3036, pruned_loss=0.06043, over 965004.67 frames.], batch size: 20, lr: 5.23e-04
2022-05-29 08:06:28,506 INFO [train.py:761] (5/8) Epoch 27, batch 3100, loss[loss=0.2146, simple_loss=0.3111, pruned_loss=0.05899, over 4970.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3045, pruned_loss=0.06116, over 965262.96 frames.], batch size: 14, lr: 5.23e-04
2022-05-29 08:07:06,599 INFO [train.py:761] (5/8) Epoch 27, batch 3150, loss[loss=0.1662, simple_loss=0.2639, pruned_loss=0.03429, over 4882.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3042, pruned_loss=0.06172, over 964098.63 frames.], batch size: 12, lr: 5.23e-04
2022-05-29 08:07:44,295 INFO [train.py:761] (5/8) Epoch 27, batch 3200, loss[loss=0.2344, simple_loss=0.3062, pruned_loss=0.08136, over 4664.00 frames.], tot_loss[loss=0.216, simple_loss=0.3046, pruned_loss=0.06374, over 963432.81 frames.], batch size: 12, lr: 5.23e-04
2022-05-29 08:08:22,566 INFO [train.py:761] (5/8) Epoch 27, batch 3250, loss[loss=0.1703, simple_loss=0.2527, pruned_loss=0.04392, over 4649.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3049, pruned_loss=0.06568, over 964342.22 frames.], batch size: 11, lr: 5.23e-04
2022-05-29 08:09:00,332 INFO [train.py:761] (5/8) Epoch 27, batch 3300, loss[loss=0.2222, simple_loss=0.3274, pruned_loss=0.05848, over 4840.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3069, pruned_loss=0.06795, over 965103.58 frames.], batch size: 20, lr: 5.23e-04
2022-05-29 08:09:37,901 INFO [train.py:761] (5/8) Epoch 27, batch 3350, loss[loss=0.2514, simple_loss=0.3307, pruned_loss=0.08611, over 4791.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3072, pruned_loss=0.06923, over 966354.65 frames.], batch size: 13, lr: 5.23e-04
2022-05-29 08:10:15,777 INFO [train.py:761] (5/8) Epoch 27, batch 3400, loss[loss=0.2296, simple_loss=0.3059, pruned_loss=0.07662, over 4783.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3083, pruned_loss=0.07056, over 966210.16 frames.], batch size: 14, lr: 5.23e-04
2022-05-29 08:10:54,358 INFO [train.py:761] (5/8) Epoch 27, batch 3450, loss[loss=0.2353, simple_loss=0.3073, pruned_loss=0.08165, over 4662.00 frames.], tot_loss[loss=0.226, simple_loss=0.3081, pruned_loss=0.07191, over 966423.61 frames.], batch size: 13, lr: 5.23e-04
2022-05-29 08:11:32,341 INFO [train.py:761] (5/8) Epoch 27, batch 3500, loss[loss=0.2262, simple_loss=0.3058, pruned_loss=0.0733, over 4926.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3106, pruned_loss=0.07382, over 966420.62 frames.], batch size: 13, lr: 5.22e-04
2022-05-29 08:12:10,649 INFO [train.py:761] (5/8) Epoch 27, batch 3550, loss[loss=0.2698, simple_loss=0.3414, pruned_loss=0.09905, over 4904.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3101, pruned_loss=0.07422, over 966323.24 frames.], batch size: 14, lr: 5.22e-04
2022-05-29 08:12:48,831 INFO [train.py:761] (5/8) Epoch 27, batch 3600, loss[loss=0.1794, simple_loss=0.2645, pruned_loss=0.04711, over 4733.00 frames.], tot_loss[loss=0.2297, simple_loss=0.3105, pruned_loss=0.07443, over 965720.82 frames.], batch size: 12, lr: 5.22e-04
2022-05-29 08:13:27,333 INFO [train.py:761] (5/8) Epoch 27, batch 3650, loss[loss=0.2786, simple_loss=0.3517, pruned_loss=0.1027, over 4895.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3131, pruned_loss=0.07601, over 966288.71 frames.], batch size: 15, lr: 5.22e-04
2022-05-29 08:14:05,851 INFO [train.py:761] (5/8) Epoch 27, batch 3700, loss[loss=0.1878, simple_loss=0.2719, pruned_loss=0.05191, over 4981.00 frames.], tot_loss[loss=0.2315, simple_loss=0.312, pruned_loss=0.07548, over 965805.53 frames.], batch size: 12, lr: 5.22e-04
2022-05-29 08:14:44,584 INFO [train.py:761] (5/8) Epoch 27, batch 3750, loss[loss=0.2242, simple_loss=0.3319, pruned_loss=0.05825, over 4726.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3132, pruned_loss=0.07663, over 966675.43 frames.], batch size: 14, lr: 5.22e-04
2022-05-29 08:15:22,614 INFO [train.py:761] (5/8) Epoch 27, batch 3800, loss[loss=0.2246, simple_loss=0.2924, pruned_loss=0.0784, over 4974.00 frames.], tot_loss[loss=0.232, simple_loss=0.3116, pruned_loss=0.07624, over 965754.67 frames.], batch size: 12, lr: 5.22e-04
2022-05-29 08:16:01,006 INFO [train.py:761] (5/8) Epoch 27, batch 3850, loss[loss=0.232, simple_loss=0.3147, pruned_loss=0.07466, over 4775.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3133, pruned_loss=0.07721, over 965857.84 frames.], batch size: 13, lr: 5.22e-04
2022-05-29 08:16:38,648 INFO [train.py:761] (5/8) Epoch 27, batch 3900, loss[loss=0.2496, simple_loss=0.3407, pruned_loss=0.07923, over 4889.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3124, pruned_loss=0.07685, over 966086.30 frames.], batch size: 15, lr: 5.22e-04
2022-05-29 08:17:16,885 INFO [train.py:761] (5/8) Epoch 27, batch 3950, loss[loss=0.224, simple_loss=0.2961, pruned_loss=0.07597, over 4801.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3122, pruned_loss=0.07681, over 966643.48 frames.], batch size: 12, lr: 5.22e-04
2022-05-29 08:17:55,099 INFO [train.py:761] (5/8) Epoch 27, batch 4000, loss[loss=0.2518, simple_loss=0.32, pruned_loss=0.09176, over 4772.00 frames.], tot_loss[loss=0.2329, simple_loss=0.312, pruned_loss=0.07692, over 965874.25 frames.], batch size: 15, lr: 5.22e-04
2022-05-29 08:18:33,542 INFO [train.py:761] (5/8) Epoch 27, batch 4050, loss[loss=0.2445, simple_loss=0.321, pruned_loss=0.08402, over 4914.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3112, pruned_loss=0.07668, over 966324.04 frames.], batch size: 14, lr: 5.22e-04
2022-05-29 08:19:11,885 INFO [train.py:761] (5/8) Epoch 27, batch 4100, loss[loss=0.2074, simple_loss=0.2904, pruned_loss=0.06224, over 4919.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3119, pruned_loss=0.07709, over 966343.99 frames.], batch size: 14, lr: 5.22e-04
2022-05-29 08:19:49,870 INFO [train.py:761] (5/8) Epoch 27, batch 4150, loss[loss=0.2478, simple_loss=0.3374, pruned_loss=0.07915, over 4971.00 frames.], tot_loss[loss=0.232, simple_loss=0.3111, pruned_loss=0.07648, over 966368.64 frames.], batch size: 14, lr: 5.22e-04
2022-05-29 08:20:28,953 INFO [train.py:761] (5/8) Epoch 27, batch 4200, loss[loss=0.259, simple_loss=0.3276, pruned_loss=0.09524, over 4977.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3114, pruned_loss=0.07666, over 965896.63 frames.], batch size: 15, lr: 5.21e-04
2022-05-29 08:21:07,246 INFO [train.py:761] (5/8) Epoch 27, batch 4250, loss[loss=0.2319, simple_loss=0.3302, pruned_loss=0.06682, over 4954.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3134, pruned_loss=0.07755, over 965184.07 frames.], batch size: 26, lr: 5.21e-04
2022-05-29 08:21:45,210 INFO [train.py:761] (5/8) Epoch 27, batch 4300, loss[loss=0.175, simple_loss=0.2494, pruned_loss=0.05029, over 4968.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3122, pruned_loss=0.07664, over 966299.00 frames.], batch size: 12, lr: 5.21e-04
2022-05-29 08:22:23,403 INFO [train.py:761] (5/8) Epoch 27, batch 4350, loss[loss=0.2712, simple_loss=0.3501, pruned_loss=0.09612, over 4899.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3127, pruned_loss=0.07693, over 966671.13 frames.], batch size: 26, lr: 5.21e-04
2022-05-29 08:23:01,223 INFO [train.py:761] (5/8) Epoch 27, batch 4400, loss[loss=0.192, simple_loss=0.2646, pruned_loss=0.0597, over 4812.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3132, pruned_loss=0.07721, over 966647.02 frames.], batch size: 12, lr: 5.21e-04
2022-05-29 08:23:39,897 INFO [train.py:761] (5/8) Epoch 27, batch 4450, loss[loss=0.2088, simple_loss=0.2871, pruned_loss=0.06526, over 4972.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3135, pruned_loss=0.07754, over 966976.30 frames.], batch size: 12, lr: 5.21e-04
2022-05-29 08:24:18,302 INFO [train.py:761] (5/8) Epoch 27, batch 4500, loss[loss=0.2399, simple_loss=0.3267, pruned_loss=0.07659, over 4951.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3134, pruned_loss=0.07765, over 966826.07 frames.], batch size: 16, lr: 5.21e-04
2022-05-29 08:24:56,198 INFO [train.py:761] (5/8) Epoch 27, batch 4550, loss[loss=0.208, simple_loss=0.3019, pruned_loss=0.05707, over 4988.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3132, pruned_loss=0.07733, over 967503.72 frames.], batch size: 15, lr: 5.21e-04
2022-05-29 08:25:34,671 INFO [train.py:761] (5/8) Epoch 27, batch 4600, loss[loss=0.2457, simple_loss=0.3239, pruned_loss=0.08377, over 4908.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3134, pruned_loss=0.07661, over 967629.65 frames.], batch size: 14, lr: 5.21e-04
2022-05-29 08:26:13,236 INFO [train.py:761] (5/8) Epoch 27, batch 4650, loss[loss=0.2789, simple_loss=0.3713, pruned_loss=0.09324, over 4802.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3127, pruned_loss=0.07642, over 967014.48 frames.], batch size: 16, lr: 5.21e-04
2022-05-29 08:26:51,196 INFO [train.py:761] (5/8) Epoch 27, batch 4700, loss[loss=0.2034, simple_loss=0.2838, pruned_loss=0.06146, over 4824.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3116, pruned_loss=0.07611, over 967282.60 frames.], batch size: 11, lr: 5.21e-04
2022-05-29 08:27:29,977 INFO [train.py:761] (5/8) Epoch 27, batch 4750, loss[loss=0.2533, simple_loss=0.3342, pruned_loss=0.08619, over 4718.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3131, pruned_loss=0.07673, over 967370.83 frames.], batch size: 14, lr: 5.21e-04
2022-05-29 08:28:07,830 INFO [train.py:761] (5/8) Epoch 27, batch 4800, loss[loss=0.2294, simple_loss=0.2965, pruned_loss=0.08116, over 4925.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3128, pruned_loss=0.07627, over 966397.67 frames.], batch size: 13, lr: 5.21e-04
2022-05-29 08:28:45,885 INFO [train.py:761] (5/8) Epoch 27, batch 4850, loss[loss=0.1875, simple_loss=0.2719, pruned_loss=0.05155, over 4989.00 frames.], tot_loss[loss=0.232, simple_loss=0.312, pruned_loss=0.07597, over 967392.22 frames.], batch size: 11, lr: 5.20e-04
2022-05-29 08:29:24,096 INFO [train.py:761] (5/8) Epoch 27, batch 4900, loss[loss=0.2728, simple_loss=0.3352, pruned_loss=0.1052, over 4817.00 frames.], tot_loss[loss=0.2332, simple_loss=0.313, pruned_loss=0.07674, over 966677.31 frames.], batch size: 18, lr: 5.20e-04
2022-05-29 08:30:02,441 INFO [train.py:761] (5/8) Epoch 27, batch 4950, loss[loss=0.2195, simple_loss=0.3028, pruned_loss=0.06813, over 4672.00 frames.], tot_loss[loss=0.2337, simple_loss=0.3139, pruned_loss=0.07675, over 966874.78 frames.], batch size: 12, lr: 5.20e-04
2022-05-29 08:30:40,598 INFO [train.py:761] (5/8) Epoch 27, batch 5000, loss[loss=0.2096, simple_loss=0.3071, pruned_loss=0.05601, over 4846.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3121, pruned_loss=0.0758, over 966069.02 frames.], batch size: 14, lr: 5.20e-04
2022-05-29 08:31:18,861 INFO [train.py:761] (5/8) Epoch 27, batch 5050, loss[loss=0.2168, simple_loss=0.2968, pruned_loss=0.06843, over 4726.00 frames.], tot_loss[loss=0.232, simple_loss=0.3125, pruned_loss=0.07575, over 967567.19 frames.], batch size: 13, lr: 5.20e-04
2022-05-29 08:31:56,938 INFO [train.py:761] (5/8) Epoch 27, batch 5100, loss[loss=0.194, simple_loss=0.2753, pruned_loss=0.05637, over 4820.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3121, pruned_loss=0.0757, over 967209.65 frames.], batch size: 11, lr: 5.20e-04
2022-05-29 08:32:35,520 INFO [train.py:761] (5/8) Epoch 27, batch 5150, loss[loss=0.197, simple_loss=0.2858, pruned_loss=0.05408, over 4980.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3128, pruned_loss=0.07623, over 966465.96 frames.], batch size: 14, lr: 5.20e-04
2022-05-29 08:33:13,517 INFO [train.py:761] (5/8) Epoch 27, batch 5200, loss[loss=0.2388, simple_loss=0.3158, pruned_loss=0.08089, over 4872.00 frames.], tot_loss[loss=0.2312, simple_loss=0.312, pruned_loss=0.07521, over 966367.36 frames.], batch size: 15, lr: 5.20e-04
2022-05-29 08:33:52,330 INFO [train.py:761] (5/8) Epoch 27, batch 5250, loss[loss=0.2315, simple_loss=0.3209, pruned_loss=0.07103, over 4773.00 frames.], tot_loss[loss=0.2312, simple_loss=0.312, pruned_loss=0.07522, over 966394.21 frames.], batch size: 15, lr: 5.20e-04
2022-05-29 08:34:29,826 INFO [train.py:761] (5/8) Epoch 27, batch 5300, loss[loss=0.1984, simple_loss=0.2816, pruned_loss=0.05761, over 4787.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3104, pruned_loss=0.07462, over 965677.53 frames.], batch size: 13, lr: 5.20e-04
2022-05-29 08:35:08,040 INFO [train.py:761] (5/8) Epoch 27, batch 5350, loss[loss=0.1783, simple_loss=0.2747, pruned_loss=0.0409, over 4800.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3109, pruned_loss=0.07499, over 964306.90 frames.], batch size: 12, lr: 5.20e-04
2022-05-29 08:35:46,443 INFO [train.py:761] (5/8) Epoch 27, batch 5400, loss[loss=0.2304, simple_loss=0.3147, pruned_loss=0.07309, over 4854.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3128, pruned_loss=0.07522, over 965136.80 frames.], batch size: 14, lr: 5.20e-04
2022-05-29 08:36:24,865 INFO [train.py:761] (5/8) Epoch 27, batch 5450, loss[loss=0.2215, simple_loss=0.3048, pruned_loss=0.06911, over 4669.00 frames.], tot_loss[loss=0.2305, simple_loss=0.3122, pruned_loss=0.07442, over 966139.26 frames.], batch size: 12, lr: 5.20e-04
2022-05-29 08:37:03,432 INFO [train.py:761] (5/8) Epoch 27, batch 5500, loss[loss=0.2171, simple_loss=0.2933, pruned_loss=0.07043, over 4742.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3133, pruned_loss=0.07486, over 965524.02 frames.], batch size: 11, lr: 5.20e-04
2022-05-29 08:37:41,302 INFO [train.py:761] (5/8) Epoch 27, batch 5550, loss[loss=0.2061, simple_loss=0.2903, pruned_loss=0.06101, over 4929.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3118, pruned_loss=0.07438, over 966595.73 frames.], batch size: 13, lr: 5.19e-04
2022-05-29 08:38:19,970 INFO [train.py:761] (5/8) Epoch 27, batch 5600, loss[loss=0.2404, simple_loss=0.3196, pruned_loss=0.08062, over 4848.00 frames.], tot_loss[loss=0.2301, simple_loss=0.3112, pruned_loss=0.07452, over 966047.95 frames.], batch size: 13, lr: 5.19e-04
2022-05-29 08:38:58,576 INFO [train.py:761] (5/8) Epoch 27, batch 5650, loss[loss=0.2694, simple_loss=0.3502, pruned_loss=0.09435, over 4789.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3121, pruned_loss=0.07478, over 966748.91 frames.], batch size: 20, lr: 5.19e-04
2022-05-29 08:39:37,007 INFO [train.py:761] (5/8) Epoch 27, batch 5700, loss[loss=0.2668, simple_loss=0.3485, pruned_loss=0.09257, over 4840.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3116, pruned_loss=0.07502, over 966186.18 frames.], batch size: 20, lr: 5.19e-04
2022-05-29 08:40:14,891 INFO [train.py:761] (5/8) Epoch 27, batch 5750, loss[loss=0.2312, simple_loss=0.2979, pruned_loss=0.08226, over 4717.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3123, pruned_loss=0.07523, over 966166.33 frames.], batch size: 13, lr: 5.19e-04
2022-05-29 08:40:53,348 INFO [train.py:761] (5/8) Epoch 27, batch 5800, loss[loss=0.2353, simple_loss=0.3138, pruned_loss=0.07835, over 4945.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3124, pruned_loss=0.07534, over 966886.28 frames.], batch size: 21, lr: 5.19e-04
2022-05-29 08:41:31,555 INFO [train.py:761] (5/8) Epoch 27, batch 5850, loss[loss=0.2159, simple_loss=0.2868, pruned_loss=0.07248, over 4730.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3117, pruned_loss=0.07544, over 966603.57 frames.], batch size: 12, lr: 5.19e-04
2022-05-29 08:42:09,924 INFO [train.py:761] (5/8) Epoch 27, batch 5900, loss[loss=0.2253, simple_loss=0.2996, pruned_loss=0.07549, over 4799.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3116, pruned_loss=0.0757, over 966252.47 frames.], batch size: 12, lr: 5.19e-04
2022-05-29 08:42:48,321 INFO [train.py:761] (5/8) Epoch 27, batch 5950, loss[loss=0.2087, simple_loss=0.2994, pruned_loss=0.05894, over 4971.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3117, pruned_loss=0.07574, over 965747.49 frames.], batch size: 14, lr: 5.19e-04
2022-05-29 08:43:26,365 INFO [train.py:761] (5/8) Epoch 27, batch 6000, loss[loss=0.214, simple_loss=0.2971, pruned_loss=0.06544, over 4797.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3118, pruned_loss=0.07542, over 965635.52 frames.], batch size: 14, lr: 5.19e-04
2022-05-29 08:43:26,365 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 08:43:36,420 INFO [train.py:790] (5/8) Epoch 27, validation: loss=0.1994, simple_loss=0.3032, pruned_loss=0.04781, over 944034.00 frames.
2022-05-29 08:44:14,430 INFO [train.py:761] (5/8) Epoch 27, batch 6050, loss[loss=0.2286, simple_loss=0.3172, pruned_loss=0.06995, over 4787.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3106, pruned_loss=0.07507, over 964587.80 frames.], batch size: 14, lr: 5.19e-04
2022-05-29 08:44:52,284 INFO [train.py:761] (5/8) Epoch 27, batch 6100, loss[loss=0.2361, simple_loss=0.3176, pruned_loss=0.07725, over 4792.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3105, pruned_loss=0.0749, over 964683.66 frames.], batch size: 13, lr: 5.19e-04
2022-05-29 08:45:30,785 INFO [train.py:761] (5/8) Epoch 27, batch 6150, loss[loss=0.2006, simple_loss=0.2851, pruned_loss=0.05804, over 4736.00 frames.], tot_loss[loss=0.2301, simple_loss=0.3105, pruned_loss=0.07491, over 964138.27 frames.], batch size: 12, lr: 5.19e-04
2022-05-29 08:46:09,156 INFO [train.py:761] (5/8) Epoch 27, batch 6200, loss[loss=0.2176, simple_loss=0.3119, pruned_loss=0.06165, over 4911.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3109, pruned_loss=0.07492, over 965597.10 frames.], batch size: 14, lr: 5.19e-04
2022-05-29 08:46:47,931 INFO [train.py:761] (5/8) Epoch 27, batch 6250, loss[loss=0.183, simple_loss=0.2679, pruned_loss=0.0491, over 4991.00 frames.], tot_loss[loss=0.2305, simple_loss=0.3106, pruned_loss=0.07525, over 966269.88 frames.], batch size: 12, lr: 5.18e-04
2022-05-29 08:47:26,198 INFO [train.py:761] (5/8) Epoch 27, batch 6300, loss[loss=0.2246, simple_loss=0.2969, pruned_loss=0.07616, over 4671.00 frames.], tot_loss[loss=0.229, simple_loss=0.3094, pruned_loss=0.0743, over 966441.56 frames.], batch size: 13, lr: 5.18e-04
2022-05-29 08:48:04,645 INFO [train.py:761] (5/8) Epoch 27, batch 6350, loss[loss=0.2308, simple_loss=0.3183, pruned_loss=0.07163, over 4886.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3098, pruned_loss=0.07468, over 965995.37 frames.], batch size: 15, lr: 5.18e-04
2022-05-29 08:48:42,851 INFO [train.py:761] (5/8) Epoch 27, batch 6400, loss[loss=0.2634, simple_loss=0.3329, pruned_loss=0.0969, over 4715.00 frames.], tot_loss[loss=0.2287, simple_loss=0.309, pruned_loss=0.07418, over 966223.94 frames.], batch size: 13, lr: 5.18e-04
2022-05-29 08:49:21,507 INFO [train.py:761] (5/8) Epoch 27, batch 6450, loss[loss=0.2555, simple_loss=0.3144, pruned_loss=0.09827, over 4846.00 frames.], tot_loss[loss=0.23, simple_loss=0.3102, pruned_loss=0.07486, over 966384.94 frames.], batch size: 13, lr: 5.18e-04
2022-05-29 08:49:59,580 INFO [train.py:761] (5/8) Epoch 27, batch 6500, loss[loss=0.2698, simple_loss=0.3585, pruned_loss=0.09055, over 4717.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3117, pruned_loss=0.07482, over 965761.91 frames.], batch size: 14, lr: 5.18e-04
2022-05-29 08:50:37,884 INFO [train.py:761] (5/8) Epoch 27, batch 6550, loss[loss=0.2056, simple_loss=0.2894, pruned_loss=0.06091, over 4782.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3106, pruned_loss=0.07405, over 965881.07 frames.], batch size: 13, lr: 5.18e-04
2022-05-29 08:51:15,711 INFO [train.py:761] (5/8) Epoch 27, batch 6600, loss[loss=0.2838, simple_loss=0.3557, pruned_loss=0.106, over 4788.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3103, pruned_loss=0.07426, over 966987.20 frames.], batch size: 14, lr: 5.18e-04
2022-05-29 08:51:54,012 INFO [train.py:761] (5/8) Epoch 27, batch 6650, loss[loss=0.2671, simple_loss=0.3492, pruned_loss=0.09251, over 4716.00 frames.], tot_loss[loss=0.2279, simple_loss=0.3088, pruned_loss=0.07346, over 966440.80 frames.], batch size: 14, lr: 5.18e-04
2022-05-29 08:52:32,663 INFO [train.py:761] (5/8) Epoch 27, batch 6700, loss[loss=0.2507, simple_loss=0.3309, pruned_loss=0.08529, over 4836.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3087, pruned_loss=0.07379, over 965387.62 frames.], batch size: 20, lr: 5.18e-04
2022-05-29 08:53:24,490 INFO [train.py:761] (5/8) Epoch 28, batch 0, loss[loss=0.2222, simple_loss=0.3252, pruned_loss=0.05961, over 4955.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3252, pruned_loss=0.05961, over 4955.00 frames.], batch size: 16, lr: 5.18e-04
2022-05-29 08:54:02,294 INFO [train.py:761] (5/8) Epoch 28, batch 50, loss[loss=0.2258, simple_loss=0.3196, pruned_loss=0.06604, over 4883.00 frames.], tot_loss[loss=0.2118, simple_loss=0.3025, pruned_loss=0.06053, over 217382.56 frames.], batch size: 15, lr: 5.18e-04
2022-05-29 08:54:40,614 INFO [train.py:761] (5/8) Epoch 28, batch 100, loss[loss=0.2316, simple_loss=0.3262, pruned_loss=0.06849, over 4729.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2996, pruned_loss=0.05941, over 382957.74 frames.], batch size: 13, lr: 5.18e-04
2022-05-29 08:55:18,407 INFO [train.py:761] (5/8) Epoch 28, batch 150, loss[loss=0.222, simple_loss=0.3107, pruned_loss=0.06661, over 4789.00 frames.], tot_loss[loss=0.2115, simple_loss=0.3016, pruned_loss=0.06067, over 512007.81 frames.], batch size: 16, lr: 5.18e-04
2022-05-29 08:55:56,670 INFO [train.py:761] (5/8) Epoch 28, batch 200, loss[loss=0.1885, simple_loss=0.2583, pruned_loss=0.05933, over 4726.00 frames.], tot_loss[loss=0.2099, simple_loss=0.3, pruned_loss=0.05987, over 611825.25 frames.], batch size: 11, lr: 5.17e-04
2022-05-29 08:56:34,123 INFO [train.py:761] (5/8) Epoch 28, batch 250, loss[loss=0.2011, simple_loss=0.2832, pruned_loss=0.05954, over 4854.00 frames.], tot_loss[loss=0.2102, simple_loss=0.3009, pruned_loss=0.05977, over 690706.55 frames.], batch size: 13, lr: 5.17e-04
2022-05-29 08:57:12,083 INFO [train.py:761] (5/8) Epoch 28, batch 300, loss[loss=0.2081, simple_loss=0.3091, pruned_loss=0.05359, over 4978.00 frames.], tot_loss[loss=0.2105, simple_loss=0.3014, pruned_loss=0.0598, over 752329.28 frames.], batch size: 14, lr: 5.17e-04
2022-05-29 08:57:50,181 INFO [train.py:761] (5/8) Epoch 28, batch 350, loss[loss=0.2439, simple_loss=0.3242, pruned_loss=0.08179, over 4767.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2999, pruned_loss=0.05869, over 799801.54 frames.], batch size: 15, lr: 5.17e-04
2022-05-29 08:58:28,031 INFO [train.py:761] (5/8) Epoch 28, batch 400, loss[loss=0.2069, simple_loss=0.2902, pruned_loss=0.06186, over 4732.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2989, pruned_loss=0.05815, over 837121.39 frames.], batch size: 12, lr: 5.17e-04
2022-05-29 08:59:06,194 INFO [train.py:761] (5/8) Epoch 28, batch 450, loss[loss=0.1812, simple_loss=0.2672, pruned_loss=0.04761, over 4789.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2997, pruned_loss=0.05858, over 865400.20 frames.], batch size: 13, lr: 5.17e-04
2022-05-29 08:59:44,121 INFO [train.py:761] (5/8) Epoch 28, batch 500, loss[loss=0.1816, simple_loss=0.2742, pruned_loss=0.04451, over 4797.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2992, pruned_loss=0.05826, over 887995.21 frames.], batch size: 13, lr: 5.17e-04
2022-05-29 09:00:22,038 INFO [train.py:761] (5/8) Epoch 28, batch 550, loss[loss=0.1961, simple_loss=0.2859, pruned_loss=0.0532, over 4723.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2997, pruned_loss=0.0585, over 904500.37 frames.], batch size: 11, lr: 5.17e-04
2022-05-29 09:01:00,423 INFO [train.py:761] (5/8) Epoch 28, batch 600, loss[loss=0.2154, simple_loss=0.3149, pruned_loss=0.058, over 4868.00 frames.], tot_loss[loss=0.2083, simple_loss=0.3, pruned_loss=0.0583, over 918245.67 frames.], batch size: 17, lr: 5.17e-04
2022-05-29 09:01:38,529 INFO [train.py:761] (5/8) Epoch 28, batch 650, loss[loss=0.2667, simple_loss=0.364, pruned_loss=0.08475, over 4954.00 frames.], tot_loss[loss=0.2095, simple_loss=0.3014, pruned_loss=0.05883, over 928526.79 frames.], batch size: 16, lr: 5.17e-04
2022-05-29 09:02:16,533 INFO [train.py:761] (5/8) Epoch 28, batch 700, loss[loss=0.2277, simple_loss=0.3242, pruned_loss=0.06557, over 4790.00 frames.], tot_loss[loss=0.211, simple_loss=0.3018, pruned_loss=0.0601, over 936172.90 frames.], batch size: 20, lr: 5.17e-04
2022-05-29 09:02:53,872 INFO [train.py:761] (5/8) Epoch 28, batch 750, loss[loss=0.2101, simple_loss=0.3152, pruned_loss=0.05254, over 4981.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3015, pruned_loss=0.06085, over 942768.47 frames.], batch size: 15, lr: 5.17e-04
2022-05-29 09:03:33,126 INFO [train.py:761] (5/8) Epoch 28, batch 800, loss[loss=0.1774, simple_loss=0.2717, pruned_loss=0.04154, over 4724.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3037, pruned_loss=0.06177, over 949283.41 frames.], batch size: 12, lr: 5.17e-04
2022-05-29 09:04:11,091 INFO [train.py:761] (5/8) Epoch 28, batch 850, loss[loss=0.2054, simple_loss=0.3068, pruned_loss=0.05195, over 4777.00 frames.], tot_loss[loss=0.2126, simple_loss=0.3035, pruned_loss=0.06091, over 952465.95 frames.], batch size: 14, lr: 5.17e-04
2022-05-29 09:04:49,553 INFO [train.py:761] (5/8) Epoch 28, batch 900, loss[loss=0.2209, simple_loss=0.3257, pruned_loss=0.05809, over 4777.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3026, pruned_loss=0.06085, over 954898.81 frames.], batch size: 15, lr: 5.17e-04
2022-05-29 09:05:26,945 INFO [train.py:761] (5/8) Epoch 28, batch 950, loss[loss=0.232, simple_loss=0.3275, pruned_loss=0.06826, over 4864.00 frames.], tot_loss[loss=0.2124, simple_loss=0.3027, pruned_loss=0.061, over 957998.60 frames.], batch size: 17, lr: 5.16e-04
2022-05-29 09:06:05,350 INFO [train.py:761] (5/8) Epoch 28, batch 1000, loss[loss=0.2088, simple_loss=0.2992, pruned_loss=0.05919, over 4870.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3047, pruned_loss=0.06198, over 961324.49 frames.], batch size: 15, lr: 5.16e-04
2022-05-29 09:06:43,399 INFO [train.py:761] (5/8) Epoch 28, batch 1050, loss[loss=0.1864, simple_loss=0.288, pruned_loss=0.04238, over 4978.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3041, pruned_loss=0.06168, over 962647.33 frames.], batch size: 15, lr: 5.16e-04
2022-05-29 09:07:21,377 INFO [train.py:761] (5/8) Epoch 28, batch 1100, loss[loss=0.247, simple_loss=0.3422, pruned_loss=0.07588, over 4875.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3038, pruned_loss=0.06131, over 963671.01 frames.], batch size: 17, lr: 5.16e-04
2022-05-29 09:07:59,460 INFO [train.py:761] (5/8) Epoch 28, batch 1150, loss[loss=0.1991, simple_loss=0.3032, pruned_loss=0.04748, over 4906.00 frames.], tot_loss[loss=0.213, simple_loss=0.3041, pruned_loss=0.06099, over 964766.18 frames.], batch size: 14, lr: 5.16e-04
2022-05-29 09:08:37,363 INFO [train.py:761] (5/8) Epoch 28, batch 1200, loss[loss=0.1687, simple_loss=0.2629, pruned_loss=0.03723, over 4976.00 frames.], tot_loss[loss=0.2125, simple_loss=0.3036, pruned_loss=0.0607, over 965298.50 frames.], batch size: 12, lr: 5.16e-04
2022-05-29 09:09:15,528 INFO [train.py:761] (5/8) Epoch 28, batch 1250, loss[loss=0.1713, simple_loss=0.2649, pruned_loss=0.03884, over 4652.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3046, pruned_loss=0.06142, over 967050.34 frames.], batch size: 11, lr: 5.16e-04
2022-05-29 09:09:53,399 INFO [train.py:761] (5/8) Epoch 28, batch 1300, loss[loss=0.1883, simple_loss=0.2997, pruned_loss=0.03845, over 4850.00 frames.], tot_loss[loss=0.2131, simple_loss=0.3042, pruned_loss=0.06102, over 967099.61 frames.], batch size: 14, lr: 5.16e-04
2022-05-29 09:10:30,951 INFO [train.py:761] (5/8) Epoch 28, batch 1350, loss[loss=0.2005, simple_loss=0.2951, pruned_loss=0.05288, over 4917.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3058, pruned_loss=0.06141, over 966833.86 frames.], batch size: 14, lr: 5.16e-04
2022-05-29 09:11:09,098 INFO [train.py:761] (5/8) Epoch 28, batch 1400, loss[loss=0.2173, simple_loss=0.2985, pruned_loss=0.06807, over 4668.00 frames.], tot_loss[loss=0.2125, simple_loss=0.3039, pruned_loss=0.06053, over 966683.67 frames.], batch size: 12, lr: 5.16e-04
2022-05-29 09:11:47,094 INFO [train.py:761] (5/8) Epoch 28, batch 1450, loss[loss=0.2498, simple_loss=0.3379, pruned_loss=0.08087, over 4908.00 frames.], tot_loss[loss=0.2127, simple_loss=0.3038, pruned_loss=0.06079, over 966364.00 frames.], batch size: 14, lr: 5.16e-04
2022-05-29 09:12:25,423 INFO [train.py:761] (5/8) Epoch 28, batch 1500, loss[loss=0.2082, simple_loss=0.2894, pruned_loss=0.06351, over 4722.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3032, pruned_loss=0.06074, over 967186.17 frames.], batch size: 11, lr: 5.16e-04
2022-05-29 09:13:03,137 INFO [train.py:761] (5/8) Epoch 28, batch 1550, loss[loss=0.1798, simple_loss=0.2793, pruned_loss=0.04021, over 4784.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3033, pruned_loss=0.06046, over 967032.26 frames.], batch size: 13, lr: 5.16e-04
2022-05-29 09:13:41,640 INFO [train.py:761] (5/8) Epoch 28, batch 1600, loss[loss=0.1995, simple_loss=0.2976, pruned_loss=0.0507, over 4672.00 frames.], tot_loss[loss=0.2124, simple_loss=0.3037, pruned_loss=0.0605, over 966561.60 frames.], batch size: 12, lr: 5.16e-04
2022-05-29 09:14:19,521 INFO [train.py:761] (5/8) Epoch 28, batch 1650, loss[loss=0.2146, simple_loss=0.3144, pruned_loss=0.05737, over 4852.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3051, pruned_loss=0.06123, over 966513.93 frames.], batch size: 18, lr: 5.15e-04
2022-05-29 09:14:57,716 INFO [train.py:761] (5/8) Epoch 28, batch 1700, loss[loss=0.1674, simple_loss=0.2447, pruned_loss=0.0451, over 4747.00 frames.], tot_loss[loss=0.2128, simple_loss=0.3044, pruned_loss=0.06063, over 965801.74 frames.], batch size: 11, lr: 5.15e-04
2022-05-29 09:15:35,688 INFO [train.py:761] (5/8) Epoch 28, batch 1750, loss[loss=0.2609, simple_loss=0.3319, pruned_loss=0.09499, over 4726.00 frames.], tot_loss[loss=0.2118, simple_loss=0.303, pruned_loss=0.06032, over 965572.08 frames.], batch size: 13, lr: 5.15e-04
2022-05-29 09:16:13,179 INFO [train.py:761] (5/8) Epoch 28, batch 1800, loss[loss=0.223, simple_loss=0.3222, pruned_loss=0.06189, over 4809.00 frames.], tot_loss[loss=0.212, simple_loss=0.3032, pruned_loss=0.0604, over 966009.63 frames.], batch size: 16, lr: 5.15e-04
2022-05-29 09:16:50,872 INFO [train.py:761] (5/8) Epoch 28, batch 1850, loss[loss=0.2718, simple_loss=0.3609, pruned_loss=0.09134, over 4850.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3042, pruned_loss=0.06078, over 966036.95 frames.], batch size: 14, lr: 5.15e-04
2022-05-29 09:17:32,333 INFO [train.py:761] (5/8) Epoch 28, batch 1900, loss[loss=0.2038, simple_loss=0.2758, pruned_loss=0.06587, over 4723.00 frames.], tot_loss[loss=0.2109, simple_loss=0.3027, pruned_loss=0.05959, over 966464.37 frames.], batch size: 11, lr: 5.15e-04
2022-05-29 09:18:10,395 INFO [train.py:761] (5/8) Epoch 28, batch 1950, loss[loss=0.258, simple_loss=0.3519, pruned_loss=0.08208, over 4668.00 frames.], tot_loss[loss=0.2124, simple_loss=0.3039, pruned_loss=0.06043, over 965582.71 frames.], batch size: 13, lr: 5.15e-04
2022-05-29 09:18:49,505 INFO [train.py:761] (5/8) Epoch 28, batch 2000, loss[loss=0.1967, simple_loss=0.293, pruned_loss=0.05022, over 4677.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3052, pruned_loss=0.06106, over 965252.52 frames.], batch size: 13, lr: 5.15e-04
2022-05-29 09:19:27,386 INFO [train.py:761] (5/8) Epoch 28, batch 2050, loss[loss=0.2226, simple_loss=0.3116, pruned_loss=0.06681, over 4894.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3054, pruned_loss=0.06056, over 964707.22 frames.], batch size: 17, lr: 5.15e-04
2022-05-29 09:20:05,454 INFO [train.py:761] (5/8) Epoch 28, batch 2100, loss[loss=0.2007, simple_loss=0.2985, pruned_loss=0.05143, over 4720.00 frames.], tot_loss[loss=0.2127, simple_loss=0.3048, pruned_loss=0.06028, over 966038.47 frames.], batch size: 13, lr: 5.15e-04
2022-05-29 09:20:43,424 INFO [train.py:761] (5/8) Epoch 28, batch 2150, loss[loss=0.2095, simple_loss=0.305, pruned_loss=0.05703, over 4735.00 frames.], tot_loss[loss=0.213, simple_loss=0.3049, pruned_loss=0.06056, over 965867.46 frames.], batch size: 12, lr: 5.15e-04
2022-05-29 09:21:21,252 INFO [train.py:761] (5/8) Epoch 28, batch 2200, loss[loss=0.1802, simple_loss=0.2781, pruned_loss=0.04117, over 4980.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3041, pruned_loss=0.06012, over 966374.28 frames.], batch size: 13, lr: 5.15e-04
2022-05-29 09:21:59,316 INFO [train.py:761] (5/8) Epoch 28, batch 2250, loss[loss=0.2365, simple_loss=0.3165, pruned_loss=0.07823, over 4800.00 frames.], tot_loss[loss=0.211, simple_loss=0.303, pruned_loss=0.05949, over 966069.88 frames.], batch size: 12, lr: 5.15e-04
2022-05-29 09:22:37,195 INFO [train.py:761] (5/8) Epoch 28, batch 2300, loss[loss=0.2196, simple_loss=0.3104, pruned_loss=0.06435, over 4804.00 frames.], tot_loss[loss=0.21, simple_loss=0.3024, pruned_loss=0.05878, over 965270.08 frames.], batch size: 12, lr: 5.15e-04
2022-05-29 09:23:15,078 INFO [train.py:761] (5/8) Epoch 28, batch 2350, loss[loss=0.1996, simple_loss=0.2936, pruned_loss=0.05281, over 4977.00 frames.], tot_loss[loss=0.2104, simple_loss=0.3027, pruned_loss=0.05901, over 965678.66 frames.], batch size: 14, lr: 5.14e-04
2022-05-29 09:23:53,599 INFO [train.py:761] (5/8) Epoch 28, batch 2400, loss[loss=0.2194, simple_loss=0.3249, pruned_loss=0.05696, over 4879.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3023, pruned_loss=0.0589, over 966418.86 frames.], batch size: 17, lr: 5.14e-04
2022-05-29 09:24:31,822 INFO [train.py:761] (5/8) Epoch 28, batch 2450, loss[loss=0.2391, simple_loss=0.339, pruned_loss=0.06956, over 4978.00 frames.], tot_loss[loss=0.2103, simple_loss=0.3024, pruned_loss=0.05905, over 966823.69 frames.], batch size: 15, lr: 5.14e-04
2022-05-29 09:25:09,640 INFO [train.py:761] (5/8) Epoch 28, batch 2500, loss[loss=0.1493, simple_loss=0.237, pruned_loss=0.03077, over 4992.00 frames.], tot_loss[loss=0.2107, simple_loss=0.3032, pruned_loss=0.0591, over 966613.58 frames.], batch size: 12, lr: 5.14e-04
2022-05-29 09:25:47,464 INFO [train.py:761] (5/8) Epoch 28, batch 2550, loss[loss=0.2176, simple_loss=0.3082, pruned_loss=0.06354, over 4839.00 frames.], tot_loss[loss=0.2113, simple_loss=0.3038, pruned_loss=0.05944, over 966841.33 frames.], batch size: 20, lr: 5.14e-04
2022-05-29 09:26:25,409 INFO [train.py:761] (5/8) Epoch 28, batch 2600, loss[loss=0.2671, simple_loss=0.3761, pruned_loss=0.07904, over 4939.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3043, pruned_loss=0.05998, over 966206.51 frames.], batch size: 16, lr: 5.14e-04
2022-05-29 09:27:03,166 INFO [train.py:761] (5/8) Epoch 28, batch 2650, loss[loss=0.2352, simple_loss=0.3066, pruned_loss=0.0819, over 4917.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3043, pruned_loss=0.05994, over 966071.97 frames.], batch size: 13, lr: 5.14e-04
2022-05-29 09:27:41,503 INFO [train.py:761] (5/8) Epoch 28, batch 2700, loss[loss=0.2385, simple_loss=0.3356, pruned_loss=0.07066, over 4917.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3024, pruned_loss=0.05886, over 964779.34 frames.], batch size: 14, lr: 5.14e-04
2022-05-29 09:28:19,463 INFO [train.py:761] (5/8) Epoch 28, batch 2750, loss[loss=0.2062, simple_loss=0.308, pruned_loss=0.0522, over 4847.00 frames.], tot_loss[loss=0.2096, simple_loss=0.3016, pruned_loss=0.05886, over 964427.52 frames.], batch size: 18, lr: 5.14e-04
2022-05-29 09:28:57,647 INFO [train.py:761] (5/8) Epoch 28, batch 2800, loss[loss=0.2034, simple_loss=0.3008, pruned_loss=0.05303, over 4878.00 frames.], tot_loss[loss=0.2103, simple_loss=0.3024, pruned_loss=0.05909, over 965868.93 frames.], batch size: 26, lr: 5.14e-04
2022-05-29 09:29:35,622 INFO [train.py:761] (5/8) Epoch 28, batch 2850, loss[loss=0.1988, simple_loss=0.2921, pruned_loss=0.05279, over 4970.00 frames.], tot_loss[loss=0.2098, simple_loss=0.3014, pruned_loss=0.0591, over 965625.96 frames.], batch size: 12, lr: 5.14e-04
2022-05-29 09:30:13,094 INFO [train.py:761] (5/8) Epoch 28, batch 2900, loss[loss=0.2503, simple_loss=0.3386, pruned_loss=0.08105, over 4896.00 frames.], tot_loss[loss=0.2097, simple_loss=0.3015, pruned_loss=0.05896, over 965160.32 frames.], batch size: 17, lr: 5.14e-04
2022-05-29 09:30:50,799 INFO [train.py:761] (5/8) Epoch 28, batch 2950, loss[loss=0.2268, simple_loss=0.3161, pruned_loss=0.06881, over 4967.00 frames.], tot_loss[loss=0.212, simple_loss=0.3036, pruned_loss=0.06021, over 964873.32 frames.], batch size: 14, lr: 5.14e-04
2022-05-29 09:31:28,908 INFO [train.py:761] (5/8) Epoch 28, batch 3000, loss[loss=0.2041, simple_loss=0.2993, pruned_loss=0.05443, over 4947.00 frames.], tot_loss[loss=0.2116, simple_loss=0.303, pruned_loss=0.06011, over 965749.83 frames.], batch size: 16, lr: 5.14e-04
2022-05-29 09:31:28,909 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 09:31:38,979 INFO [train.py:790] (5/8) Epoch 28, validation: loss=0.206, simple_loss=0.3055, pruned_loss=0.05326, over 944034.00 frames.
2022-05-29 09:32:16,987 INFO [train.py:761] (5/8) Epoch 28, batch 3050, loss[loss=0.1675, simple_loss=0.2619, pruned_loss=0.0366, over 4808.00 frames.], tot_loss[loss=0.2115, simple_loss=0.3027, pruned_loss=0.06018, over 965363.48 frames.], batch size: 12, lr: 5.13e-04
2022-05-29 09:32:55,678 INFO [train.py:761] (5/8) Epoch 28, batch 3100, loss[loss=0.2264, simple_loss=0.3113, pruned_loss=0.07078, over 4828.00 frames.], tot_loss[loss=0.212, simple_loss=0.3031, pruned_loss=0.06048, over 964958.28 frames.], batch size: 18, lr: 5.13e-04
2022-05-29 09:33:33,869 INFO [train.py:761] (5/8) Epoch 28, batch 3150, loss[loss=0.2317, simple_loss=0.3205, pruned_loss=0.07141, over 4904.00 frames.], tot_loss[loss=0.2138, simple_loss=0.304, pruned_loss=0.06179, over 965066.47 frames.], batch size: 25, lr: 5.13e-04
2022-05-29 09:34:12,250 INFO [train.py:761] (5/8) Epoch 28, batch 3200, loss[loss=0.2245, simple_loss=0.3109, pruned_loss=0.06906, over 4797.00 frames.], tot_loss[loss=0.2161, simple_loss=0.305, pruned_loss=0.06358, over 965404.67 frames.], batch size: 14, lr: 5.13e-04
2022-05-29 09:34:50,329 INFO [train.py:761] (5/8) Epoch 28, batch 3250, loss[loss=0.2499, simple_loss=0.3284, pruned_loss=0.08568, over 4784.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3062, pruned_loss=0.06519, over 964868.59 frames.], batch size: 13, lr: 5.13e-04
2022-05-29 09:35:28,952 INFO [train.py:761] (5/8) Epoch 28, batch 3300, loss[loss=0.2046, simple_loss=0.2758, pruned_loss=0.06668, over 4804.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3071, pruned_loss=0.06717, over 966542.60 frames.], batch size: 12, lr: 5.13e-04
2022-05-29 09:36:06,884 INFO [train.py:761] (5/8) Epoch 28, batch 3350, loss[loss=0.2396, simple_loss=0.3172, pruned_loss=0.08103, over 4870.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3086, pruned_loss=0.06985, over 966991.88 frames.], batch size: 18, lr: 5.13e-04
2022-05-29 09:36:45,446 INFO [train.py:761] (5/8) Epoch 28, batch 3400, loss[loss=0.2019, simple_loss=0.2918, pruned_loss=0.05597, over 4856.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3072, pruned_loss=0.06925, over 966765.49 frames.], batch size: 13, lr: 5.13e-04
2022-05-29 09:37:23,212 INFO [train.py:761] (5/8) Epoch 28, batch 3450, loss[loss=0.2159, simple_loss=0.3049, pruned_loss=0.06343, over 4948.00 frames.], tot_loss[loss=0.224, simple_loss=0.3075, pruned_loss=0.07028, over 966001.56 frames.], batch size: 16, lr: 5.13e-04
2022-05-29 09:38:01,447 INFO [train.py:761] (5/8) Epoch 28, batch 3500, loss[loss=0.2335, simple_loss=0.3185, pruned_loss=0.07423, over 4853.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3064, pruned_loss=0.07038, over 964878.23 frames.], batch size: 14, lr: 5.13e-04
2022-05-29 09:38:39,514 INFO [train.py:761] (5/8) Epoch 28, batch 3550, loss[loss=0.2278, simple_loss=0.3317, pruned_loss=0.0619, over 4758.00 frames.], tot_loss[loss=0.2237, simple_loss=0.306, pruned_loss=0.07073, over 964826.77 frames.], batch size: 20, lr: 5.13e-04
2022-05-29 09:39:17,327 INFO [train.py:761] (5/8) Epoch 28, batch 3600, loss[loss=0.2119, simple_loss=0.2953, pruned_loss=0.06422, over 4986.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3065, pruned_loss=0.07132, over 966264.50 frames.], batch size: 13, lr: 5.13e-04
2022-05-29 09:39:55,386 INFO [train.py:761] (5/8) Epoch 28, batch 3650, loss[loss=0.2162, simple_loss=0.322, pruned_loss=0.05515, over 4780.00 frames.], tot_loss[loss=0.2251, simple_loss=0.307, pruned_loss=0.07161, over 966845.13 frames.], batch size: 14, lr: 5.13e-04
2022-05-29 09:40:33,542 INFO [train.py:761] (5/8) Epoch 28, batch 3700, loss[loss=0.2422, simple_loss=0.3166, pruned_loss=0.08386, over 4726.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3058, pruned_loss=0.07183, over 966918.14 frames.], batch size: 13, lr: 5.13e-04
2022-05-29 09:41:11,457 INFO [train.py:761] (5/8) Epoch 28, batch 3750, loss[loss=0.2303, simple_loss=0.3181, pruned_loss=0.07127, over 4720.00 frames.], tot_loss[loss=0.2275, simple_loss=0.308, pruned_loss=0.07353, over 967122.72 frames.], batch size: 14, lr: 5.13e-04
2022-05-29 09:41:49,884 INFO [train.py:761] (5/8) Epoch 28, batch 3800, loss[loss=0.2385, simple_loss=0.3347, pruned_loss=0.07118, over 4876.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3091, pruned_loss=0.07472, over 966996.10 frames.], batch size: 17, lr: 5.12e-04
2022-05-29 09:42:27,817 INFO [train.py:761] (5/8) Epoch 28, batch 3850, loss[loss=0.2194, simple_loss=0.2983, pruned_loss=0.07031, over 4927.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3078, pruned_loss=0.07462, over 967109.58 frames.], batch size: 13, lr: 5.12e-04
2022-05-29 09:43:06,123 INFO [train.py:761] (5/8) Epoch 28, batch 3900, loss[loss=0.2349, simple_loss=0.3233, pruned_loss=0.07328, over 4945.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3102, pruned_loss=0.07551, over 967271.59 frames.], batch size: 16, lr: 5.12e-04
2022-05-29 09:43:44,373 INFO [train.py:761] (5/8) Epoch 28, batch 3950, loss[loss=0.2421, simple_loss=0.3411, pruned_loss=0.0715, over 4738.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3101, pruned_loss=0.07564, over 966849.71 frames.], batch size: 13, lr: 5.12e-04
2022-05-29 09:44:22,176 INFO [train.py:761] (5/8) Epoch 28, batch 4000, loss[loss=0.2912, simple_loss=0.3569, pruned_loss=0.1127, over 4964.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3112, pruned_loss=0.07599, over 966643.53 frames.], batch size: 49, lr: 5.12e-04
2022-05-29 09:44:59,826 INFO [train.py:761] (5/8) Epoch 28, batch 4050, loss[loss=0.2815, simple_loss=0.3548, pruned_loss=0.1041, over 4883.00 frames.], tot_loss[loss=0.2324, simple_loss=0.312, pruned_loss=0.07642, over 967599.41 frames.], batch size: 26, lr: 5.12e-04
2022-05-29 09:45:38,437 INFO [train.py:761] (5/8) Epoch 28, batch 4100, loss[loss=0.188, simple_loss=0.2692, pruned_loss=0.05339, over 4892.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3118, pruned_loss=0.07669, over 967272.65 frames.], batch size: 12, lr: 5.12e-04
2022-05-29 09:46:16,354 INFO [train.py:761] (5/8) Epoch 28, batch 4150, loss[loss=0.2656, simple_loss=0.3379, pruned_loss=0.09667, over 4794.00 frames.], tot_loss[loss=0.232, simple_loss=0.3116, pruned_loss=0.07624, over 966544.48 frames.], batch size: 16, lr: 5.12e-04
2022-05-29 09:46:54,707 INFO [train.py:761] (5/8) Epoch 28, batch 4200, loss[loss=0.2049, simple_loss=0.2822, pruned_loss=0.06385, over 4558.00 frames.], tot_loss[loss=0.23, simple_loss=0.31, pruned_loss=0.075, over 966762.89 frames.], batch size: 10, lr: 5.12e-04
2022-05-29 09:47:32,361 INFO [train.py:761] (5/8) Epoch 28, batch 4250, loss[loss=0.248, simple_loss=0.327, pruned_loss=0.08453, over 4839.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3108, pruned_loss=0.07555, over 966246.88 frames.], batch size: 18, lr: 5.12e-04
2022-05-29 09:48:11,220 INFO [train.py:761] (5/8) Epoch 28, batch 4300, loss[loss=0.229, simple_loss=0.3265, pruned_loss=0.06575, over 4717.00 frames.], tot_loss[loss=0.23, simple_loss=0.3104, pruned_loss=0.0748, over 965123.03 frames.], batch size: 14, lr: 5.12e-04
2022-05-29 09:48:49,841 INFO [train.py:761] (5/8) Epoch 28, batch 4350, loss[loss=0.2352, simple_loss=0.316, pruned_loss=0.07716, over 4854.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3107, pruned_loss=0.07483, over 965264.12 frames.], batch size: 14, lr: 5.12e-04
2022-05-29 09:49:28,193 INFO [train.py:761] (5/8) Epoch 28, batch 4400, loss[loss=0.2113, simple_loss=0.28, pruned_loss=0.07126, over 4899.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3085, pruned_loss=0.07384, over 964347.59 frames.], batch size: 12, lr: 5.12e-04
2022-05-29 09:50:06,275 INFO [train.py:761] (5/8) Epoch 28, batch 4450, loss[loss=0.1728, simple_loss=0.2696, pruned_loss=0.03797, over 4988.00 frames.], tot_loss[loss=0.2286, simple_loss=0.309, pruned_loss=0.07407, over 965186.16 frames.], batch size: 13, lr: 5.12e-04
2022-05-29 09:50:44,230 INFO [train.py:761] (5/8) Epoch 28, batch 4500, loss[loss=0.2331, simple_loss=0.3222, pruned_loss=0.07199, over 4951.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3084, pruned_loss=0.07388, over 965399.46 frames.], batch size: 26, lr: 5.11e-04
2022-05-29 09:51:22,626 INFO [train.py:761] (5/8) Epoch 28, batch 4550, loss[loss=0.218, simple_loss=0.3007, pruned_loss=0.06766, over 4890.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3085, pruned_loss=0.07434, over 965147.99 frames.], batch size: 26, lr: 5.11e-04
2022-05-29 09:52:00,828 INFO [train.py:761] (5/8) Epoch 28, batch 4600, loss[loss=0.2214, simple_loss=0.2981, pruned_loss=0.07229, over 4790.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3085, pruned_loss=0.07424, over 965883.22 frames.], batch size: 13, lr: 5.11e-04
2022-05-29 09:52:38,958 INFO [train.py:761] (5/8) Epoch 28, batch 4650, loss[loss=0.1807, simple_loss=0.2571, pruned_loss=0.05216, over 4974.00 frames.], tot_loss[loss=0.229, simple_loss=0.3087, pruned_loss=0.07463, over 966049.14 frames.], batch size: 12, lr: 5.11e-04
2022-05-29 09:53:17,611 INFO [train.py:761] (5/8) Epoch 28, batch 4700, loss[loss=0.1951, simple_loss=0.276, pruned_loss=0.05707, over 4672.00 frames.], tot_loss[loss=0.229, simple_loss=0.3088, pruned_loss=0.07465, over 966942.00 frames.], batch size: 12, lr: 5.11e-04
2022-05-29 09:53:55,462 INFO [train.py:761] (5/8) Epoch 28, batch 4750, loss[loss=0.2554, simple_loss=0.3536, pruned_loss=0.07856, over 4859.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3086, pruned_loss=0.07381, over 967137.61 frames.], batch size: 26, lr: 5.11e-04
2022-05-29 09:54:33,670 INFO [train.py:761] (5/8) Epoch 28, batch 4800, loss[loss=0.2399, simple_loss=0.3299, pruned_loss=0.07491, over 4732.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3089, pruned_loss=0.07444, over 966545.81 frames.], batch size: 13, lr: 5.11e-04
2022-05-29 09:55:12,027 INFO [train.py:761] (5/8) Epoch 28, batch 4850, loss[loss=0.2192, simple_loss=0.3023, pruned_loss=0.06802, over 4854.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3083, pruned_loss=0.07429, over 966046.81 frames.], batch size: 14, lr: 5.11e-04
2022-05-29 09:55:50,529 INFO [train.py:761] (5/8) Epoch 28, batch 4900, loss[loss=0.2186, simple_loss=0.3102, pruned_loss=0.06349, over 4886.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3088, pruned_loss=0.07472, over 966007.64 frames.], batch size: 17, lr: 5.11e-04
2022-05-29 09:56:28,473 INFO [train.py:761] (5/8) Epoch 28, batch 4950, loss[loss=0.2184, simple_loss=0.2983, pruned_loss=0.0693, over 4677.00 frames.], tot_loss[loss=0.2291, simple_loss=0.309, pruned_loss=0.0746, over 965779.95 frames.], batch size: 13, lr: 5.11e-04
2022-05-29 09:57:06,872 INFO [train.py:761] (5/8) Epoch 28, batch 5000, loss[loss=0.2091, simple_loss=0.3014, pruned_loss=0.05841, over 4920.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3089, pruned_loss=0.07389, over 966765.20 frames.], batch size: 13, lr: 5.11e-04
2022-05-29 09:57:45,375 INFO [train.py:761] (5/8) Epoch 28, batch 5050, loss[loss=0.2275, simple_loss=0.3108, pruned_loss=0.07215, over 4921.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3096, pruned_loss=0.07456, over 966130.52 frames.], batch size: 13, lr: 5.11e-04
2022-05-29 09:58:23,546 INFO [train.py:761] (5/8) Epoch 28, batch 5100, loss[loss=0.2162, simple_loss=0.294, pruned_loss=0.06927, over 4856.00 frames.], tot_loss[loss=0.2305, simple_loss=0.3107, pruned_loss=0.07509, over 966112.91 frames.], batch size: 13, lr: 5.11e-04
2022-05-29 09:59:01,674 INFO [train.py:761] (5/8) Epoch 28, batch 5150, loss[loss=0.227, simple_loss=0.3078, pruned_loss=0.07312, over 4992.00 frames.], tot_loss[loss=0.229, simple_loss=0.3093, pruned_loss=0.07432, over 966887.59 frames.], batch size: 13, lr: 5.11e-04
2022-05-29 09:59:39,865 INFO [train.py:761] (5/8) Epoch 28, batch 5200, loss[loss=0.2431, simple_loss=0.3312, pruned_loss=0.07745, over 4971.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3082, pruned_loss=0.07417, over 966362.65 frames.], batch size: 15, lr: 5.11e-04
2022-05-29 10:00:18,491 INFO [train.py:761] (5/8) Epoch 28, batch 5250, loss[loss=0.2421, simple_loss=0.3367, pruned_loss=0.07374, over 4717.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3088, pruned_loss=0.0741, over 966239.85 frames.], batch size: 14, lr: 5.10e-04
2022-05-29 10:00:56,998 INFO [train.py:761] (5/8) Epoch 28, batch 5300, loss[loss=0.2514, simple_loss=0.3258, pruned_loss=0.08853, over 4972.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3084, pruned_loss=0.0736, over 966740.72 frames.], batch size: 15, lr: 5.10e-04
2022-05-29 10:01:35,103 INFO [train.py:761] (5/8) Epoch 28, batch 5350, loss[loss=0.235, simple_loss=0.3206, pruned_loss=0.07466, over 4918.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3081, pruned_loss=0.07323, over 967288.60 frames.], batch size: 13, lr: 5.10e-04
2022-05-29 10:02:13,271 INFO [train.py:761] (5/8) Epoch 28, batch 5400, loss[loss=0.2037, simple_loss=0.2778, pruned_loss=0.0648, over 4808.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3069, pruned_loss=0.07225, over 967088.21 frames.], batch size: 12, lr: 5.10e-04
2022-05-29 10:02:51,263 INFO [train.py:761] (5/8) Epoch 28, batch 5450, loss[loss=0.2315, simple_loss=0.314, pruned_loss=0.07452, over 4977.00 frames.], tot_loss[loss=0.228, simple_loss=0.3091, pruned_loss=0.07348, over 966286.06 frames.], batch size: 14, lr: 5.10e-04
2022-05-29 10:03:30,300 INFO [train.py:761] (5/8) Epoch 28, batch 5500, loss[loss=0.2495, simple_loss=0.3297, pruned_loss=0.08465, over 4972.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3101, pruned_loss=0.07451, over 965988.62 frames.], batch size: 16, lr: 5.10e-04
2022-05-29 10:04:08,882 INFO [train.py:761] (5/8) Epoch 28, batch 5550, loss[loss=0.2429, simple_loss=0.3196, pruned_loss=0.08309, over 4923.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3099, pruned_loss=0.07466, over 966267.19 frames.], batch size: 13, lr: 5.10e-04
2022-05-29 10:04:46,773 INFO [train.py:761] (5/8) Epoch 28, batch 5600, loss[loss=0.2436, simple_loss=0.3441, pruned_loss=0.07153, over 4727.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3117, pruned_loss=0.07522, over 965792.49 frames.], batch size: 13, lr: 5.10e-04
2022-05-29 10:05:24,760 INFO [train.py:761] (5/8) Epoch 28, batch 5650, loss[loss=0.1945, simple_loss=0.2656, pruned_loss=0.06165, over 4968.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3111, pruned_loss=0.07486, over 965692.28 frames.], batch size: 11, lr: 5.10e-04
2022-05-29 10:06:02,834 INFO [train.py:761] (5/8) Epoch 28, batch 5700, loss[loss=0.2632, simple_loss=0.353, pruned_loss=0.08668, over 4804.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3119, pruned_loss=0.0754, over 966530.97 frames.], batch size: 16, lr: 5.10e-04
2022-05-29 10:06:41,342 INFO [train.py:761] (5/8) Epoch 28, batch 5750, loss[loss=0.2268, simple_loss=0.3143, pruned_loss=0.06966, over 4793.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3126, pruned_loss=0.07578, over 966336.35 frames.], batch size: 20, lr: 5.10e-04
2022-05-29 10:07:19,925 INFO [train.py:761] (5/8) Epoch 28, batch 5800, loss[loss=0.2568, simple_loss=0.3412, pruned_loss=0.08622, over 4855.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3108, pruned_loss=0.07483, over 966699.67 frames.], batch size: 13, lr: 5.10e-04
2022-05-29 10:07:58,189 INFO [train.py:761] (5/8) Epoch 28, batch 5850, loss[loss=0.2049, simple_loss=0.2821, pruned_loss=0.06384, over 4809.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3097, pruned_loss=0.07402, over 966348.67 frames.], batch size: 12, lr: 5.10e-04
2022-05-29 10:08:36,326 INFO [train.py:761] (5/8) Epoch 28, batch 5900, loss[loss=0.2504, simple_loss=0.3187, pruned_loss=0.09105, over 4975.00 frames.], tot_loss[loss=0.2267, simple_loss=0.308, pruned_loss=0.0727, over 966453.85 frames.], batch size: 15, lr: 5.10e-04
2022-05-29 10:09:14,503 INFO [train.py:761] (5/8) Epoch 28, batch 5950, loss[loss=0.3003, simple_loss=0.3666, pruned_loss=0.117, over 4938.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3087, pruned_loss=0.073, over 966941.60 frames.], batch size: 52, lr: 5.10e-04
2022-05-29 10:09:53,168 INFO [train.py:761] (5/8) Epoch 28, batch 6000, loss[loss=0.219, simple_loss=0.3177, pruned_loss=0.06016, over 4778.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3078, pruned_loss=0.07243, over 965362.79 frames.], batch size: 15, lr: 5.09e-04
2022-05-29 10:09:53,169 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 10:10:03,324 INFO [train.py:790] (5/8) Epoch 28, validation: loss=0.1978, simple_loss=0.3017, pruned_loss=0.04702, over 944034.00 frames.
2022-05-29 10:10:41,975 INFO [train.py:761] (5/8) Epoch 28, batch 6050, loss[loss=0.2234, simple_loss=0.3121, pruned_loss=0.06729, over 4813.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3075, pruned_loss=0.07283, over 964727.81 frames.], batch size: 20, lr: 5.09e-04
2022-05-29 10:11:20,470 INFO [train.py:761] (5/8) Epoch 28, batch 6100, loss[loss=0.2431, simple_loss=0.3324, pruned_loss=0.07691, over 4952.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3077, pruned_loss=0.07284, over 964990.36 frames.], batch size: 21, lr: 5.09e-04
2022-05-29 10:11:58,707 INFO [train.py:761] (5/8) Epoch 28, batch 6150, loss[loss=0.1971, simple_loss=0.2888, pruned_loss=0.05273, over 4919.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3079, pruned_loss=0.07325, over 966093.35 frames.], batch size: 13, lr: 5.09e-04
2022-05-29 10:12:37,562 INFO [train.py:761] (5/8) Epoch 28, batch 6200, loss[loss=0.2034, simple_loss=0.2796, pruned_loss=0.06363, over 4880.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3081, pruned_loss=0.0736, over 966118.20 frames.], batch size: 12, lr: 5.09e-04
2022-05-29 10:13:15,712 INFO [train.py:761] (5/8) Epoch 28, batch 6250, loss[loss=0.2475, simple_loss=0.3313, pruned_loss=0.08189, over 4822.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3108, pruned_loss=0.0752, over 966420.12 frames.], batch size: 18, lr: 5.09e-04
2022-05-29 10:13:54,071 INFO [train.py:761] (5/8) Epoch 28, batch 6300, loss[loss=0.2236, simple_loss=0.2955, pruned_loss=0.0759, over 4798.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3109, pruned_loss=0.07484, over 967048.20 frames.], batch size: 16, lr: 5.09e-04
2022-05-29 10:14:32,188 INFO [train.py:761] (5/8) Epoch 28, batch 6350, loss[loss=0.2079, simple_loss=0.2961, pruned_loss=0.0599, over 4848.00 frames.], tot_loss[loss=0.231, simple_loss=0.3115, pruned_loss=0.07524, over 967182.96 frames.], batch size: 17, lr: 5.09e-04
2022-05-29 10:15:10,449 INFO [train.py:761] (5/8) Epoch 28, batch 6400, loss[loss=0.2338, simple_loss=0.3104, pruned_loss=0.07858, over 4869.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3103, pruned_loss=0.0743, over 967139.15 frames.], batch size: 18, lr: 5.09e-04
2022-05-29 10:15:49,060 INFO [train.py:761] (5/8) Epoch 28, batch 6450, loss[loss=0.2308, simple_loss=0.2978, pruned_loss=0.08188, over 4742.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3099, pruned_loss=0.07409, over 967276.61 frames.], batch size: 11, lr: 5.09e-04
2022-05-29 10:16:27,192 INFO [train.py:761] (5/8) Epoch 28, batch 6500, loss[loss=0.2309, simple_loss=0.3149, pruned_loss=0.07349, over 4785.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3102, pruned_loss=0.07408, over 966763.68 frames.], batch size: 13, lr: 5.09e-04
2022-05-29 10:17:05,454 INFO [train.py:761] (5/8) Epoch 28, batch 6550, loss[loss=0.2242, simple_loss=0.3002, pruned_loss=0.07409, over 4811.00 frames.], tot_loss[loss=0.2286, simple_loss=0.31, pruned_loss=0.0736, over 967577.06 frames.], batch size: 24, lr: 5.09e-04
2022-05-29 10:17:43,346 INFO [train.py:761] (5/8) Epoch 28, batch 6600, loss[loss=0.1727, simple_loss=0.2505, pruned_loss=0.04742, over 4875.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3099, pruned_loss=0.07341, over 967866.50 frames.], batch size: 12, lr: 5.09e-04
2022-05-29 10:18:21,785 INFO [train.py:761] (5/8) Epoch 28, batch 6650, loss[loss=0.2262, simple_loss=0.3115, pruned_loss=0.07043, over 4883.00 frames.], tot_loss[loss=0.2283, simple_loss=0.31, pruned_loss=0.07331, over 968476.00 frames.], batch size: 15, lr: 5.09e-04
2022-05-29 10:19:00,815 INFO [train.py:761] (5/8) Epoch 28, batch 6700, loss[loss=0.2115, simple_loss=0.3022, pruned_loss=0.0604, over 4920.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3103, pruned_loss=0.07372, over 967554.49 frames.], batch size: 13, lr: 5.09e-04
2022-05-29 10:19:55,100 INFO [train.py:761] (5/8) Epoch 29, batch 0, loss[loss=0.1888, simple_loss=0.2802, pruned_loss=0.0487, over 4733.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2802, pruned_loss=0.0487, over 4733.00 frames.], batch size: 12, lr: 5.08e-04
2022-05-29 10:20:32,918 INFO [train.py:761] (5/8) Epoch 29, batch 50, loss[loss=0.2279, simple_loss=0.3236, pruned_loss=0.06613, over 4882.00 frames.], tot_loss[loss=0.214, simple_loss=0.3055, pruned_loss=0.06125, over 217289.46 frames.], batch size: 15, lr: 5.08e-04
2022-05-29 10:21:11,239 INFO [train.py:761] (5/8) Epoch 29, batch 100, loss[loss=0.2571, simple_loss=0.3287, pruned_loss=0.09275, over 4800.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3046, pruned_loss=0.06135, over 384043.61 frames.], batch size: 16, lr: 5.08e-04
2022-05-29 10:21:48,976 INFO [train.py:761] (5/8) Epoch 29, batch 150, loss[loss=0.2315, simple_loss=0.3394, pruned_loss=0.06183, over 4887.00 frames.], tot_loss[loss=0.2125, simple_loss=0.3039, pruned_loss=0.06057, over 513605.62 frames.], batch size: 18, lr: 5.08e-04
2022-05-29 10:22:27,076 INFO [train.py:761] (5/8) Epoch 29, batch 200, loss[loss=0.1833, simple_loss=0.2801, pruned_loss=0.04332, over 4670.00 frames.], tot_loss[loss=0.2127, simple_loss=0.304, pruned_loss=0.06076, over 613981.82 frames.], batch size: 13, lr: 5.08e-04
2022-05-29 10:23:04,917 INFO [train.py:761] (5/8) Epoch 29, batch 250, loss[loss=0.212, simple_loss=0.2927, pruned_loss=0.0657, over 4907.00 frames.], tot_loss[loss=0.2107, simple_loss=0.3018, pruned_loss=0.05978, over 691941.47 frames.], batch size: 14, lr: 5.08e-04
2022-05-29 10:23:42,705 INFO [train.py:761] (5/8) Epoch 29, batch 300, loss[loss=0.2327, simple_loss=0.3332, pruned_loss=0.06613, over 4966.00 frames.], tot_loss[loss=0.2107, simple_loss=0.3018, pruned_loss=0.05979, over 753918.61 frames.], batch size: 45, lr: 5.08e-04
2022-05-29 10:24:21,361 INFO [train.py:761] (5/8) Epoch 29, batch 350, loss[loss=0.2316, simple_loss=0.3141, pruned_loss=0.07448, over 4655.00 frames.], tot_loss[loss=0.2102, simple_loss=0.3016, pruned_loss=0.05939, over 800895.00 frames.], batch size: 12, lr: 5.08e-04
2022-05-29 10:24:58,908 INFO [train.py:761] (5/8) Epoch 29, batch 400, loss[loss=0.2307, simple_loss=0.3307, pruned_loss=0.06536, over 4787.00 frames.], tot_loss[loss=0.2094, simple_loss=0.3005, pruned_loss=0.05913, over 836468.09 frames.], batch size: 14, lr: 5.08e-04
2022-05-29 10:25:37,074 INFO [train.py:761] (5/8) Epoch 29, batch 450, loss[loss=0.2222, simple_loss=0.3209, pruned_loss=0.06173, over 4948.00 frames.], tot_loss[loss=0.2094, simple_loss=0.3, pruned_loss=0.05939, over 864821.27 frames.], batch size: 16, lr: 5.08e-04
2022-05-29 10:26:14,473 INFO [train.py:761] (5/8) Epoch 29, batch 500, loss[loss=0.222, simple_loss=0.3208, pruned_loss=0.06156, over 4721.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2989, pruned_loss=0.05799, over 886994.68 frames.], batch size: 13, lr: 5.08e-04
2022-05-29 10:26:52,043 INFO [train.py:761] (5/8) Epoch 29, batch 550, loss[loss=0.1876, simple_loss=0.2801, pruned_loss=0.04755, over 4673.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2997, pruned_loss=0.05793, over 904694.02 frames.], batch size: 13, lr: 5.08e-04
2022-05-29 10:27:29,612 INFO [train.py:761] (5/8) Epoch 29, batch 600, loss[loss=0.1897, simple_loss=0.297, pruned_loss=0.04115, over 4984.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2988, pruned_loss=0.05712, over 918622.49 frames.], batch size: 13, lr: 5.08e-04
2022-05-29 10:28:07,417 INFO [train.py:761] (5/8) Epoch 29, batch 650, loss[loss=0.1823, simple_loss=0.2684, pruned_loss=0.04804, over 4966.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2982, pruned_loss=0.05701, over 929053.67 frames.], batch size: 11, lr: 5.08e-04
2022-05-29 10:28:45,339 INFO [train.py:761] (5/8) Epoch 29, batch 700, loss[loss=0.2189, simple_loss=0.3141, pruned_loss=0.06184, over 4848.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2994, pruned_loss=0.05755, over 937818.01 frames.], batch size: 14, lr: 5.08e-04
2022-05-29 10:29:23,704 INFO [train.py:761] (5/8) Epoch 29, batch 750, loss[loss=0.1875, simple_loss=0.292, pruned_loss=0.04149, over 4861.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2996, pruned_loss=0.05756, over 945177.35 frames.], batch size: 14, lr: 5.07e-04
2022-05-29 10:30:01,845 INFO [train.py:761] (5/8) Epoch 29, batch 800, loss[loss=0.1738, simple_loss=0.2629, pruned_loss=0.04234, over 4849.00 frames.], tot_loss[loss=0.2095, simple_loss=0.3012, pruned_loss=0.0589, over 949779.23 frames.], batch size: 13, lr: 5.07e-04
2022-05-29 10:30:39,972 INFO [train.py:761] (5/8) Epoch 29, batch 850, loss[loss=0.2327, simple_loss=0.3247, pruned_loss=0.07039, over 4858.00 frames.], tot_loss[loss=0.2103, simple_loss=0.3021, pruned_loss=0.05927, over 953473.26 frames.], batch size: 17, lr: 5.07e-04
2022-05-29 10:31:18,151 INFO [train.py:761] (5/8) Epoch 29, batch 900, loss[loss=0.1959, simple_loss=0.2693, pruned_loss=0.06129, over 4643.00 frames.], tot_loss[loss=0.2106, simple_loss=0.3018, pruned_loss=0.05971, over 956026.53 frames.], batch size: 11, lr: 5.07e-04
2022-05-29 10:31:56,327 INFO [train.py:761] (5/8) Epoch 29, batch 950, loss[loss=0.1895, simple_loss=0.2821, pruned_loss=0.04849, over 4788.00 frames.], tot_loss[loss=0.2102, simple_loss=0.3015, pruned_loss=0.05948, over 956956.42 frames.], batch size: 13, lr: 5.07e-04
2022-05-29 10:32:33,996 INFO [train.py:761] (5/8) Epoch 29, batch 1000, loss[loss=0.2155, simple_loss=0.3159, pruned_loss=0.0576, over 4893.00 frames.], tot_loss[loss=0.2097, simple_loss=0.3011, pruned_loss=0.05917, over 958788.12 frames.], batch size: 15, lr: 5.07e-04
2022-05-29 10:33:11,849 INFO [train.py:761] (5/8) Epoch 29, batch 1050, loss[loss=0.2472, simple_loss=0.3447, pruned_loss=0.07492, over 4947.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3033, pruned_loss=0.05994, over 960647.83 frames.], batch size: 16, lr: 5.07e-04
2022-05-29 10:33:48,979 INFO [train.py:761] (5/8) Epoch 29, batch 1100, loss[loss=0.218, simple_loss=0.3155, pruned_loss=0.06025, over 4881.00 frames.], tot_loss[loss=0.2128, simple_loss=0.3043, pruned_loss=0.06062, over 960957.52 frames.], batch size: 15, lr: 5.07e-04
2022-05-29 10:34:26,986 INFO [train.py:761] (5/8) Epoch 29, batch 1150, loss[loss=0.2325, simple_loss=0.3074, pruned_loss=0.07876, over 4839.00 frames.], tot_loss[loss=0.2128, simple_loss=0.3039, pruned_loss=0.06086, over 963277.79 frames.], batch size: 11, lr: 5.07e-04
2022-05-29 10:35:05,062 INFO [train.py:761] (5/8) Epoch 29, batch 1200, loss[loss=0.2047, simple_loss=0.3021, pruned_loss=0.05361, over 4669.00 frames.], tot_loss[loss=0.2115, simple_loss=0.3024, pruned_loss=0.06027, over 963900.66 frames.], batch size: 13, lr: 5.07e-04
2022-05-29 10:35:43,733 INFO [train.py:761] (5/8) Epoch 29, batch 1250, loss[loss=0.2199, simple_loss=0.3067, pruned_loss=0.06654, over 4961.00 frames.], tot_loss[loss=0.214, simple_loss=0.3046, pruned_loss=0.06172, over 965438.25 frames.], batch size: 16, lr: 5.07e-04
2022-05-29 10:36:21,351 INFO [train.py:761] (5/8) Epoch 29, batch 1300, loss[loss=0.1936, simple_loss=0.263, pruned_loss=0.06213, over 4976.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3045, pruned_loss=0.06204, over 965727.71 frames.], batch size: 12, lr: 5.07e-04
2022-05-29 10:36:59,633 INFO [train.py:761] (5/8) Epoch 29, batch 1350, loss[loss=0.2506, simple_loss=0.3514, pruned_loss=0.07492, over 4786.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3052, pruned_loss=0.06199, over 965921.68 frames.], batch size: 16, lr: 5.07e-04
2022-05-29 10:37:37,232 INFO [train.py:761] (5/8) Epoch 29, batch 1400, loss[loss=0.2566, simple_loss=0.3492, pruned_loss=0.08206, over 4874.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3051, pruned_loss=0.062, over 965720.32 frames.], batch size: 17, lr: 5.07e-04
2022-05-29 10:38:15,775 INFO [train.py:761] (5/8) Epoch 29, batch 1450, loss[loss=0.226, simple_loss=0.3136, pruned_loss=0.06923, over 4812.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3057, pruned_loss=0.06229, over 965903.50 frames.], batch size: 16, lr: 5.07e-04
2022-05-29 10:38:53,310 INFO [train.py:761] (5/8) Epoch 29, batch 1500, loss[loss=0.186, simple_loss=0.2678, pruned_loss=0.05207, over 4830.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3046, pruned_loss=0.06149, over 966133.29 frames.], batch size: 11, lr: 5.06e-04
2022-05-29 10:39:31,407 INFO [train.py:761] (5/8) Epoch 29, batch 1550, loss[loss=0.2304, simple_loss=0.3173, pruned_loss=0.07171, over 4671.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3052, pruned_loss=0.06232, over 965706.71 frames.], batch size: 13, lr: 5.06e-04
2022-05-29 10:40:09,221 INFO [train.py:761] (5/8) Epoch 29, batch 1600, loss[loss=0.2236, simple_loss=0.3063, pruned_loss=0.07039, over 4834.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3048, pruned_loss=0.06189, over 966191.07 frames.], batch size: 18, lr: 5.06e-04
2022-05-29 10:40:47,362 INFO [train.py:761] (5/8) Epoch 29, batch 1650, loss[loss=0.1902, simple_loss=0.2752, pruned_loss=0.05266, over 4641.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3053, pruned_loss=0.06191, over 965711.28 frames.], batch size: 11, lr: 5.06e-04
2022-05-29 10:41:25,612 INFO [train.py:761] (5/8) Epoch 29, batch 1700, loss[loss=0.1996, simple_loss=0.2957, pruned_loss=0.05181, over 4919.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3049, pruned_loss=0.06168, over 966136.98 frames.], batch size: 13, lr: 5.06e-04
2022-05-29 10:42:03,950 INFO [train.py:761] (5/8) Epoch 29, batch 1750, loss[loss=0.2117, simple_loss=0.3045, pruned_loss=0.05951, over 4679.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3055, pruned_loss=0.06209, over 965910.26 frames.], batch size: 13, lr: 5.06e-04
2022-05-29 10:42:42,155 INFO [train.py:761] (5/8) Epoch 29, batch 1800, loss[loss=0.1708, simple_loss=0.2625, pruned_loss=0.03956, over 4982.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3066, pruned_loss=0.06209, over 966487.06 frames.], batch size: 12, lr: 5.06e-04
2022-05-29 10:43:20,228 INFO [train.py:761] (5/8) Epoch 29, batch 1850, loss[loss=0.2173, simple_loss=0.3142, pruned_loss=0.06019, over 4851.00 frames.], tot_loss[loss=0.2141, simple_loss=0.3052, pruned_loss=0.06154, over 966010.05 frames.], batch size: 14, lr: 5.06e-04
2022-05-29 10:43:57,946 INFO [train.py:761] (5/8) Epoch 29, batch 1900, loss[loss=0.1645, simple_loss=0.2519, pruned_loss=0.0385, over 4557.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3047, pruned_loss=0.06081, over 964984.81 frames.], batch size: 10, lr: 5.06e-04
2022-05-29 10:44:44,084 INFO [train.py:761] (5/8) Epoch 29, batch 1950, loss[loss=0.1895, simple_loss=0.272, pruned_loss=0.05349, over 4641.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3036, pruned_loss=0.0605, over 965077.93 frames.], batch size: 11, lr: 5.06e-04
2022-05-29 10:45:21,661 INFO [train.py:761] (5/8) Epoch 29, batch 2000, loss[loss=0.1937, simple_loss=0.2936, pruned_loss=0.04689, over 4612.00 frames.], tot_loss[loss=0.2123, simple_loss=0.304, pruned_loss=0.06024, over 965210.83 frames.], batch size: 12, lr: 5.06e-04
2022-05-29 10:45:59,870 INFO [train.py:761] (5/8) Epoch 29, batch 2050, loss[loss=0.216, simple_loss=0.3034, pruned_loss=0.06426, over 4726.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3041, pruned_loss=0.06022, over 964786.72 frames.], batch size: 12, lr: 5.06e-04
2022-05-29 10:46:37,561 INFO [train.py:761] (5/8) Epoch 29, batch 2100, loss[loss=0.2293, simple_loss=0.3314, pruned_loss=0.06358, over 4771.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3051, pruned_loss=0.06111, over 964958.21 frames.], batch size: 15, lr: 5.06e-04
2022-05-29 10:47:16,366 INFO [train.py:761] (5/8) Epoch 29, batch 2150, loss[loss=0.2096, simple_loss=0.3179, pruned_loss=0.05069, over 4888.00 frames.], tot_loss[loss=0.2127, simple_loss=0.3041, pruned_loss=0.06066, over 965478.62 frames.], batch size: 15, lr: 5.06e-04
2022-05-29 10:47:53,810 INFO [train.py:761] (5/8) Epoch 29, batch 2200, loss[loss=0.2688, simple_loss=0.3468, pruned_loss=0.09542, over 4919.00 frames.], tot_loss[loss=0.213, simple_loss=0.3045, pruned_loss=0.06075, over 966571.97 frames.], batch size: 48, lr: 5.06e-04
2022-05-29 10:48:31,541 INFO [train.py:761] (5/8) Epoch 29, batch 2250, loss[loss=0.1662, simple_loss=0.2519, pruned_loss=0.04029, over 4645.00 frames.], tot_loss[loss=0.2125, simple_loss=0.3048, pruned_loss=0.06011, over 966944.36 frames.], batch size: 11, lr: 5.05e-04
2022-05-29 10:49:09,855 INFO [train.py:761] (5/8) Epoch 29, batch 2300, loss[loss=0.1535, simple_loss=0.2648, pruned_loss=0.02113, over 4741.00 frames.], tot_loss[loss=0.2112, simple_loss=0.303, pruned_loss=0.05967, over 966680.83 frames.], batch size: 12, lr: 5.05e-04
2022-05-29 10:49:47,972 INFO [train.py:761] (5/8) Epoch 29, batch 2350, loss[loss=0.1742, simple_loss=0.2759, pruned_loss=0.03627, over 4848.00 frames.], tot_loss[loss=0.2115, simple_loss=0.3034, pruned_loss=0.05976, over 967439.46 frames.], batch size: 14, lr: 5.05e-04
2022-05-29 10:50:25,788 INFO [train.py:761] (5/8) Epoch 29, batch 2400, loss[loss=0.2377, simple_loss=0.315, pruned_loss=0.08018, over 4898.00 frames.], tot_loss[loss=0.2103, simple_loss=0.3022, pruned_loss=0.05917, over 966504.83 frames.], batch size: 49, lr: 5.05e-04
2022-05-29 10:51:03,649 INFO [train.py:761] (5/8) Epoch 29, batch 2450, loss[loss=0.2298, simple_loss=0.3249, pruned_loss=0.06738, over 4783.00 frames.], tot_loss[loss=0.212, simple_loss=0.3041, pruned_loss=0.05994, over 966076.20 frames.], batch size: 15, lr: 5.05e-04
2022-05-29 10:51:41,385 INFO [train.py:761] (5/8) Epoch 29, batch 2500, loss[loss=0.2122, simple_loss=0.2957, pruned_loss=0.06431, over 4658.00 frames.], tot_loss[loss=0.2118, simple_loss=0.3036, pruned_loss=0.05998, over 966123.54 frames.], batch size: 12, lr: 5.05e-04
2022-05-29 10:52:19,533 INFO [train.py:761] (5/8) Epoch 29, batch 2550, loss[loss=0.194, simple_loss=0.2711, pruned_loss=0.05847, over 4836.00 frames.], tot_loss[loss=0.2122, simple_loss=0.304, pruned_loss=0.0602, over 965610.62 frames.], batch size: 11, lr: 5.05e-04
2022-05-29 10:52:57,575 INFO [train.py:761] (5/8) Epoch 29, batch 2600, loss[loss=0.2061, simple_loss=0.2987, pruned_loss=0.05679, over 4665.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3042, pruned_loss=0.06025, over 965920.03 frames.], batch size: 13, lr: 5.05e-04
2022-05-29 10:53:35,968 INFO [train.py:761] (5/8) Epoch 29, batch 2650, loss[loss=0.2147, simple_loss=0.3205, pruned_loss=0.05442, over 4781.00 frames.], tot_loss[loss=0.2126, simple_loss=0.3047, pruned_loss=0.06023, over 965635.55 frames.], batch size: 14, lr: 5.05e-04
2022-05-29 10:54:13,777 INFO [train.py:761] (5/8) Epoch 29, batch 2700, loss[loss=0.2222, simple_loss=0.3277, pruned_loss=0.05834, over 4909.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3052, pruned_loss=0.06064, over 965363.94 frames.], batch size: 26, lr: 5.05e-04
2022-05-29 10:54:52,035 INFO [train.py:761] (5/8) Epoch 29, batch 2750, loss[loss=0.1753, simple_loss=0.2574, pruned_loss=0.04654, over 4828.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3039, pruned_loss=0.06013, over 965679.63 frames.], batch size: 11, lr: 5.05e-04
2022-05-29 10:55:29,950 INFO [train.py:761] (5/8) Epoch 29, batch 2800, loss[loss=0.2102, simple_loss=0.3074, pruned_loss=0.05645, over 4735.00 frames.], tot_loss[loss=0.2105, simple_loss=0.3023, pruned_loss=0.05938, over 966087.47 frames.], batch size: 13, lr: 5.05e-04
2022-05-29 10:56:08,047 INFO [train.py:761] (5/8) Epoch 29, batch 2850, loss[loss=0.2179, simple_loss=0.3101, pruned_loss=0.06285, over 4830.00 frames.], tot_loss[loss=0.2093, simple_loss=0.3012, pruned_loss=0.05872, over 965895.75 frames.], batch size: 18, lr: 5.05e-04
2022-05-29 10:56:45,766 INFO [train.py:761] (5/8) Epoch 29, batch 2900, loss[loss=0.2327, simple_loss=0.3295, pruned_loss=0.06789, over 4963.00 frames.], tot_loss[loss=0.209, simple_loss=0.3012, pruned_loss=0.05844, over 965510.45 frames.], batch size: 26, lr: 5.05e-04
2022-05-29 10:57:24,048 INFO [train.py:761] (5/8) Epoch 29, batch 2950, loss[loss=0.1846, simple_loss=0.2798, pruned_loss=0.04465, over 4851.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2993, pruned_loss=0.05779, over 965019.40 frames.], batch size: 14, lr: 5.05e-04
2022-05-29 10:58:01,837 INFO [train.py:761] (5/8) Epoch 29, batch 3000, loss[loss=0.2187, simple_loss=0.3104, pruned_loss=0.06344, over 4973.00 frames.], tot_loss[loss=0.2084, simple_loss=0.3004, pruned_loss=0.05822, over 965212.40 frames.], batch size: 12, lr: 5.04e-04
2022-05-29 10:58:01,837 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 10:58:11,630 INFO [train.py:790] (5/8) Epoch 29, validation: loss=0.2043, simple_loss=0.3043, pruned_loss=0.05213, over 944034.00 frames.
2022-05-29 10:58:49,741 INFO [train.py:761] (5/8) Epoch 29, batch 3050, loss[loss=0.2745, simple_loss=0.354, pruned_loss=0.09747, over 4806.00 frames.], tot_loss[loss=0.2092, simple_loss=0.3011, pruned_loss=0.05867, over 964630.81 frames.], batch size: 25, lr: 5.04e-04
2022-05-29 10:59:27,547 INFO [train.py:761] (5/8) Epoch 29, batch 3100, loss[loss=0.2024, simple_loss=0.3023, pruned_loss=0.05127, over 4965.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3033, pruned_loss=0.06062, over 964589.50 frames.], batch size: 26, lr: 5.04e-04
2022-05-29 11:00:08,701 INFO [train.py:761] (5/8) Epoch 29, batch 3150, loss[loss=0.2204, simple_loss=0.3067, pruned_loss=0.06707, over 4675.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3046, pruned_loss=0.062, over 965166.40 frames.], batch size: 13, lr: 5.04e-04
2022-05-29 11:00:46,365 INFO [train.py:761] (5/8) Epoch 29, batch 3200, loss[loss=0.295, simple_loss=0.3575, pruned_loss=0.1162, over 4953.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3061, pruned_loss=0.06416, over 965687.67 frames.], batch size: 49, lr: 5.04e-04
2022-05-29 11:01:24,558 INFO [train.py:761] (5/8) Epoch 29, batch 3250, loss[loss=0.2651, simple_loss=0.3534, pruned_loss=0.08842, over 4954.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3069, pruned_loss=0.06572, over 966320.17 frames.], batch size: 16, lr: 5.04e-04
2022-05-29 11:02:03,086 INFO [train.py:761] (5/8) Epoch 29, batch 3300, loss[loss=0.312, simple_loss=0.3879, pruned_loss=0.118, over 4899.00 frames.], tot_loss[loss=0.222, simple_loss=0.3085, pruned_loss=0.06779, over 967255.12 frames.], batch size: 48, lr: 5.04e-04
2022-05-29 11:02:41,705 INFO [train.py:761] (5/8) Epoch 29, batch 3350, loss[loss=0.2815, simple_loss=0.3588, pruned_loss=0.1021, over 4915.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3103, pruned_loss=0.07022, over 967187.47 frames.], batch size: 47, lr: 5.04e-04
2022-05-29 11:03:20,086 INFO [train.py:761] (5/8) Epoch 29, batch 3400, loss[loss=0.2238, simple_loss=0.2973, pruned_loss=0.07514, over 4990.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3097, pruned_loss=0.07072, over 966753.41 frames.], batch size: 13, lr: 5.04e-04
2022-05-29 11:03:58,483 INFO [train.py:761] (5/8) Epoch 29, batch 3450, loss[loss=0.2084, simple_loss=0.2827, pruned_loss=0.06705, over 4967.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3092, pruned_loss=0.07062, over 968066.88 frames.], batch size: 12, lr: 5.04e-04
2022-05-29 11:04:36,396 INFO [train.py:761] (5/8) Epoch 29, batch 3500, loss[loss=0.2104, simple_loss=0.2849, pruned_loss=0.06791, over 4787.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3092, pruned_loss=0.07132, over 967245.87 frames.], batch size: 13, lr: 5.04e-04
2022-05-29 11:05:14,539 INFO [train.py:761] (5/8) Epoch 29, batch 3550, loss[loss=0.187, simple_loss=0.2774, pruned_loss=0.04826, over 4997.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3114, pruned_loss=0.07316, over 967680.17 frames.], batch size: 13, lr: 5.04e-04
2022-05-29 11:05:51,861 INFO [train.py:761] (5/8) Epoch 29, batch 3600, loss[loss=0.2621, simple_loss=0.3465, pruned_loss=0.08888, over 4886.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3108, pruned_loss=0.07348, over 968047.50 frames.], batch size: 18, lr: 5.04e-04
2022-05-29 11:06:30,164 INFO [train.py:761] (5/8) Epoch 29, batch 3650, loss[loss=0.1935, simple_loss=0.2613, pruned_loss=0.06282, over 4841.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3095, pruned_loss=0.07303, over 967769.19 frames.], batch size: 11, lr: 5.04e-04
2022-05-29 11:07:08,137 INFO [train.py:761] (5/8) Epoch 29, batch 3700, loss[loss=0.1957, simple_loss=0.2821, pruned_loss=0.0546, over 4894.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3092, pruned_loss=0.07294, over 967352.93 frames.], batch size: 12, lr: 5.04e-04
2022-05-29 11:07:46,459 INFO [train.py:761] (5/8) Epoch 29, batch 3750, loss[loss=0.3237, simple_loss=0.387, pruned_loss=0.1302, over 4935.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3092, pruned_loss=0.07389, over 966264.69 frames.], batch size: 49, lr: 5.03e-04
2022-05-29 11:08:24,611 INFO [train.py:761] (5/8) Epoch 29, batch 3800, loss[loss=0.2289, simple_loss=0.3186, pruned_loss=0.06962, over 4900.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3095, pruned_loss=0.07455, over 964827.10 frames.], batch size: 15, lr: 5.03e-04
2022-05-29 11:09:03,053 INFO [train.py:761] (5/8) Epoch 29, batch 3850, loss[loss=0.2491, simple_loss=0.3076, pruned_loss=0.09528, over 4977.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3077, pruned_loss=0.07348, over 964878.49 frames.], batch size: 12, lr: 5.03e-04
2022-05-29 11:09:41,012 INFO [train.py:761] (5/8) Epoch 29, batch 3900, loss[loss=0.2037, simple_loss=0.3003, pruned_loss=0.05357, over 4732.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3082, pruned_loss=0.07334, over 965646.55 frames.], batch size: 12, lr: 5.03e-04
2022-05-29 11:10:19,225 INFO [train.py:761] (5/8) Epoch 29, batch 3950, loss[loss=0.2557, simple_loss=0.3274, pruned_loss=0.09197, over 4930.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3088, pruned_loss=0.07378, over 966658.47 frames.], batch size: 13, lr: 5.03e-04
2022-05-29 11:10:57,708 INFO [train.py:761] (5/8) Epoch 29, batch 4000, loss[loss=0.2384, simple_loss=0.3102, pruned_loss=0.08327, over 4905.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3098, pruned_loss=0.0747, over 966742.60 frames.], batch size: 17, lr: 5.03e-04
2022-05-29 11:11:35,911 INFO [train.py:761] (5/8) Epoch 29, batch 4050, loss[loss=0.2183, simple_loss=0.2955, pruned_loss=0.07055, over 4792.00 frames.], tot_loss[loss=0.23, simple_loss=0.3097, pruned_loss=0.07512, over 966424.17 frames.], batch size: 13, lr: 5.03e-04
2022-05-29 11:12:13,648 INFO [train.py:761] (5/8) Epoch 29, batch 4100, loss[loss=0.2643, simple_loss=0.3519, pruned_loss=0.08835, over 4783.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3102, pruned_loss=0.07549, over 966437.89 frames.], batch size: 20, lr: 5.03e-04
2022-05-29 11:12:51,618 INFO [train.py:761] (5/8) Epoch 29, batch 4150, loss[loss=0.2281, simple_loss=0.3026, pruned_loss=0.07678, over 4798.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3096, pruned_loss=0.07464, over 967309.66 frames.], batch size: 16, lr: 5.03e-04
2022-05-29 11:13:29,435 INFO [train.py:761] (5/8) Epoch 29, batch 4200, loss[loss=0.2633, simple_loss=0.3385, pruned_loss=0.09404, over 4760.00 frames.], tot_loss[loss=0.229, simple_loss=0.309, pruned_loss=0.07453, over 966781.74 frames.], batch size: 20, lr: 5.03e-04
2022-05-29 11:14:07,602 INFO [train.py:761] (5/8) Epoch 29, batch 4250, loss[loss=0.2472, simple_loss=0.3311, pruned_loss=0.08171, over 4835.00 frames.], tot_loss[loss=0.2297, simple_loss=0.3096, pruned_loss=0.07489, over 967501.36 frames.], batch size: 25, lr: 5.03e-04
2022-05-29 11:14:46,423 INFO [train.py:761] (5/8) Epoch 29, batch 4300, loss[loss=0.2463, simple_loss=0.3246, pruned_loss=0.08403, over 4783.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3093, pruned_loss=0.0745, over 966954.34 frames.], batch size: 13, lr: 5.03e-04
2022-05-29 11:15:24,778 INFO [train.py:761] (5/8) Epoch 29, batch 4350, loss[loss=0.2317, simple_loss=0.3162, pruned_loss=0.07363, over 4851.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3089, pruned_loss=0.07378, over 967699.05 frames.], batch size: 14, lr: 5.03e-04
2022-05-29 11:16:02,796 INFO [train.py:761] (5/8) Epoch 29, batch 4400, loss[loss=0.2877, simple_loss=0.356, pruned_loss=0.1097, over 4970.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3082, pruned_loss=0.07349, over 966989.44 frames.], batch size: 15, lr: 5.03e-04
2022-05-29 11:16:41,452 INFO [train.py:761] (5/8) Epoch 29, batch 4450, loss[loss=0.2608, simple_loss=0.3408, pruned_loss=0.09038, over 4889.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3091, pruned_loss=0.07387, over 967819.91 frames.], batch size: 15, lr: 5.03e-04
2022-05-29 11:17:19,653 INFO [train.py:761] (5/8) Epoch 29, batch 4500, loss[loss=0.2497, simple_loss=0.3323, pruned_loss=0.08354, over 4975.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3087, pruned_loss=0.07372, over 966641.31 frames.], batch size: 15, lr: 5.02e-04
2022-05-29 11:17:58,179 INFO [train.py:761] (5/8) Epoch 29, batch 4550, loss[loss=0.1942, simple_loss=0.2762, pruned_loss=0.05607, over 4882.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3062, pruned_loss=0.07236, over 966725.96 frames.], batch size: 12, lr: 5.02e-04
2022-05-29 11:18:36,082 INFO [train.py:761] (5/8) Epoch 29, batch 4600, loss[loss=0.1993, simple_loss=0.2881, pruned_loss=0.05525, over 4971.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3066, pruned_loss=0.07231, over 966334.98 frames.], batch size: 14, lr: 5.02e-04
2022-05-29 11:19:14,295 INFO [train.py:761] (5/8) Epoch 29, batch 4650, loss[loss=0.2588, simple_loss=0.3439, pruned_loss=0.08684, over 4946.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3073, pruned_loss=0.07323, over 966215.24 frames.], batch size: 16, lr: 5.02e-04
2022-05-29 11:19:52,506 INFO [train.py:761] (5/8) Epoch 29, batch 4700, loss[loss=0.2073, simple_loss=0.2982, pruned_loss=0.05822, over 4946.00 frames.], tot_loss[loss=0.228, simple_loss=0.3082, pruned_loss=0.07391, over 966253.31 frames.], batch size: 16, lr: 5.02e-04
2022-05-29 11:20:30,616 INFO [train.py:761] (5/8) Epoch 29, batch 4750, loss[loss=0.2364, simple_loss=0.3286, pruned_loss=0.0721, over 4881.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3083, pruned_loss=0.07369, over 965903.70 frames.], batch size: 17, lr: 5.02e-04
2022-05-29 11:21:09,139 INFO [train.py:761] (5/8) Epoch 29, batch 4800, loss[loss=0.2095, simple_loss=0.2929, pruned_loss=0.06307, over 4828.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3075, pruned_loss=0.07361, over 966711.73 frames.], batch size: 18, lr: 5.02e-04
2022-05-29 11:21:47,484 INFO [train.py:761] (5/8) Epoch 29, batch 4850, loss[loss=0.24, simple_loss=0.3246, pruned_loss=0.07774, over 4990.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3084, pruned_loss=0.0736, over 966716.94 frames.], batch size: 13, lr: 5.02e-04
2022-05-29 11:22:25,866 INFO [train.py:761] (5/8) Epoch 29, batch 4900, loss[loss=0.2026, simple_loss=0.2956, pruned_loss=0.05477, over 4957.00 frames.], tot_loss[loss=0.227, simple_loss=0.3075, pruned_loss=0.0733, over 966357.99 frames.], batch size: 16, lr: 5.02e-04
2022-05-29 11:23:04,964 INFO [train.py:761] (5/8) Epoch 29, batch 4950, loss[loss=0.2516, simple_loss=0.3305, pruned_loss=0.08629, over 4953.00 frames.], tot_loss[loss=0.228, simple_loss=0.3085, pruned_loss=0.07371, over 966541.18 frames.], batch size: 16, lr: 5.02e-04
2022-05-29 11:23:42,860 INFO [train.py:761] (5/8) Epoch 29, batch 5000, loss[loss=0.228, simple_loss=0.3067, pruned_loss=0.07463, over 4962.00 frames.], tot_loss[loss=0.2263, simple_loss=0.307, pruned_loss=0.07276, over 966279.07 frames.], batch size: 26, lr: 5.02e-04
2022-05-29 11:24:21,266 INFO [train.py:761] (5/8) Epoch 29, batch 5050, loss[loss=0.2288, simple_loss=0.299, pruned_loss=0.07933, over 4995.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3064, pruned_loss=0.07288, over 966645.72 frames.], batch size: 13, lr: 5.02e-04
2022-05-29 11:24:59,030 INFO [train.py:761] (5/8) Epoch 29, batch 5100, loss[loss=0.1902, simple_loss=0.2803, pruned_loss=0.05006, over 4913.00 frames.], tot_loss[loss=0.226, simple_loss=0.306, pruned_loss=0.07296, over 966760.40 frames.], batch size: 13, lr: 5.02e-04
2022-05-29 11:25:37,334 INFO [train.py:761] (5/8) Epoch 29, batch 5150, loss[loss=0.3202, simple_loss=0.372, pruned_loss=0.1342, over 4936.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3066, pruned_loss=0.07351, over 965617.71 frames.], batch size: 46, lr: 5.02e-04
2022-05-29 11:26:15,301 INFO [train.py:761] (5/8) Epoch 29, batch 5200, loss[loss=0.2626, simple_loss=0.35, pruned_loss=0.08763, over 4782.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3069, pruned_loss=0.07374, over 966081.05 frames.], batch size: 14, lr: 5.02e-04
2022-05-29 11:26:53,897 INFO [train.py:761] (5/8) Epoch 29, batch 5250, loss[loss=0.2794, simple_loss=0.3622, pruned_loss=0.09826, over 4874.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3078, pruned_loss=0.07388, over 965662.38 frames.], batch size: 47, lr: 5.02e-04
2022-05-29 11:27:31,758 INFO [train.py:761] (5/8) Epoch 29, batch 5300, loss[loss=0.205, simple_loss=0.2883, pruned_loss=0.06083, over 4921.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3095, pruned_loss=0.07507, over 966537.10 frames.], batch size: 13, lr: 5.01e-04
2022-05-29 11:28:09,964 INFO [train.py:761] (5/8) Epoch 29, batch 5350, loss[loss=0.2777, simple_loss=0.3472, pruned_loss=0.1041, over 4877.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3093, pruned_loss=0.07462, over 965412.18 frames.], batch size: 51, lr: 5.01e-04
2022-05-29 11:28:48,648 INFO [train.py:761] (5/8) Epoch 29, batch 5400, loss[loss=0.2171, simple_loss=0.3104, pruned_loss=0.06189, over 4762.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3114, pruned_loss=0.07506, over 965609.00 frames.], batch size: 15, lr: 5.01e-04
2022-05-29 11:29:26,579 INFO [train.py:761] (5/8) Epoch 29, batch 5450, loss[loss=0.2572, simple_loss=0.3429, pruned_loss=0.08568, over 4877.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3089, pruned_loss=0.07392, over 965543.41 frames.], batch size: 17, lr: 5.01e-04
2022-05-29 11:30:04,240 INFO [train.py:761] (5/8) Epoch 29, batch 5500, loss[loss=0.2238, simple_loss=0.289, pruned_loss=0.0793, over 4985.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3078, pruned_loss=0.07282, over 964592.18 frames.], batch size: 13, lr: 5.01e-04
2022-05-29 11:30:42,415 INFO [train.py:761] (5/8) Epoch 29, batch 5550, loss[loss=0.2141, simple_loss=0.2856, pruned_loss=0.07128, over 4976.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3075, pruned_loss=0.07233, over 965450.53 frames.], batch size: 12, lr: 5.01e-04
2022-05-29 11:31:20,918 INFO [train.py:761] (5/8) Epoch 29, batch 5600, loss[loss=0.2282, simple_loss=0.3156, pruned_loss=0.07043, over 4793.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3068, pruned_loss=0.07168, over 965131.44 frames.], batch size: 20, lr: 5.01e-04
2022-05-29 11:31:59,355 INFO [train.py:761] (5/8) Epoch 29, batch 5650, loss[loss=0.2579, simple_loss=0.3356, pruned_loss=0.09011, over 4968.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3062, pruned_loss=0.07137, over 966100.68 frames.], batch size: 15, lr: 5.01e-04
2022-05-29 11:32:37,927 INFO [train.py:761] (5/8) Epoch 29, batch 5700, loss[loss=0.2061, simple_loss=0.293, pruned_loss=0.05955, over 4790.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3063, pruned_loss=0.07192, over 965457.15 frames.], batch size: 13, lr: 5.01e-04
2022-05-29 11:33:16,627 INFO [train.py:761] (5/8) Epoch 29, batch 5750, loss[loss=0.2589, simple_loss=0.3366, pruned_loss=0.09055, over 4768.00 frames.], tot_loss[loss=0.226, simple_loss=0.3075, pruned_loss=0.07223, over 964920.67 frames.], batch size: 20, lr: 5.01e-04
2022-05-29 11:33:54,751 INFO [train.py:761] (5/8) Epoch 29, batch 5800, loss[loss=0.196, simple_loss=0.2857, pruned_loss=0.05311, over 4768.00 frames.], tot_loss[loss=0.2271, simple_loss=0.3085, pruned_loss=0.07286, over 965477.46 frames.], batch size: 20, lr: 5.01e-04
2022-05-29 11:34:33,072 INFO [train.py:761] (5/8) Epoch 29, batch 5850, loss[loss=0.2211, simple_loss=0.284, pruned_loss=0.07909, over 4567.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3074, pruned_loss=0.07209, over 965305.43 frames.], batch size: 10, lr: 5.01e-04
2022-05-29 11:35:11,352 INFO [train.py:761] (5/8) Epoch 29, batch 5900, loss[loss=0.2421, simple_loss=0.3188, pruned_loss=0.08269, over 4845.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3074, pruned_loss=0.07204, over 964821.80 frames.], batch size: 13, lr: 5.01e-04
2022-05-29 11:35:49,614 INFO [train.py:761] (5/8) Epoch 29, batch 5950, loss[loss=0.2217, simple_loss=0.2986, pruned_loss=0.07238, over 4884.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3082, pruned_loss=0.07278, over 965139.89 frames.], batch size: 15, lr: 5.01e-04
2022-05-29 11:36:27,988 INFO [train.py:761] (5/8) Epoch 29, batch 6000, loss[loss=0.2993, simple_loss=0.3633, pruned_loss=0.1176, over 4927.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3083, pruned_loss=0.07319, over 965268.72 frames.], batch size: 13, lr: 5.01e-04
2022-05-29 11:36:27,988 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 11:36:37,720 INFO [train.py:790] (5/8) Epoch 29, validation: loss=0.2003, simple_loss=0.3024, pruned_loss=0.04913, over 944034.00 frames.
2022-05-29 11:37:16,227 INFO [train.py:761] (5/8) Epoch 29, batch 6050, loss[loss=0.2122, simple_loss=0.2814, pruned_loss=0.07148, over 4726.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3077, pruned_loss=0.07309, over 966223.07 frames.], batch size: 12, lr: 5.00e-04
2022-05-29 11:37:54,280 INFO [train.py:761] (5/8) Epoch 29, batch 6100, loss[loss=0.2062, simple_loss=0.2947, pruned_loss=0.05889, over 4886.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3079, pruned_loss=0.07378, over 965659.03 frames.], batch size: 12, lr: 5.00e-04
2022-05-29 11:38:33,300 INFO [train.py:761] (5/8) Epoch 29, batch 6150, loss[loss=0.2016, simple_loss=0.2846, pruned_loss=0.05929, over 4848.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3081, pruned_loss=0.07372, over 965261.89 frames.], batch size: 13, lr: 5.00e-04
2022-05-29 11:39:11,785 INFO [train.py:761] (5/8) Epoch 29, batch 6200, loss[loss=0.2455, simple_loss=0.318, pruned_loss=0.0865, over 4714.00 frames.], tot_loss[loss=0.2278, simple_loss=0.308, pruned_loss=0.0738, over 964949.36 frames.], batch size: 14, lr: 5.00e-04
2022-05-29 11:39:50,408 INFO [train.py:761] (5/8) Epoch 29, batch 6250, loss[loss=0.2364, simple_loss=0.3129, pruned_loss=0.07999, over 4967.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3081, pruned_loss=0.07364, over 965499.68 frames.], batch size: 14, lr: 5.00e-04
2022-05-29 11:40:28,976 INFO [train.py:761] (5/8) Epoch 29, batch 6300, loss[loss=0.2509, simple_loss=0.3296, pruned_loss=0.08613, over 4978.00 frames.], tot_loss[loss=0.227, simple_loss=0.3074, pruned_loss=0.07324, over 966134.59 frames.], batch size: 14, lr: 5.00e-04
2022-05-29 11:41:07,234 INFO [train.py:761] (5/8) Epoch 29, batch 6350, loss[loss=0.2508, simple_loss=0.3097, pruned_loss=0.09597, over 4803.00 frames.], tot_loss[loss=0.2268, simple_loss=0.308, pruned_loss=0.07287, over 966819.47 frames.], batch size: 12, lr: 5.00e-04
2022-05-29 11:41:45,737 INFO [train.py:761] (5/8) Epoch 29, batch 6400, loss[loss=0.2532, simple_loss=0.337, pruned_loss=0.08468, over 4857.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3078, pruned_loss=0.07252, over 967177.38 frames.], batch size: 14, lr: 5.00e-04
2022-05-29 11:42:24,222 INFO [train.py:761] (5/8) Epoch 29, batch 6450, loss[loss=0.1807, simple_loss=0.2693, pruned_loss=0.04609, over 4640.00 frames.], tot_loss[loss=0.226, simple_loss=0.3076, pruned_loss=0.07222, over 966465.25 frames.], batch size: 11, lr: 5.00e-04
2022-05-29 11:43:02,871 INFO [train.py:761] (5/8) Epoch 29, batch 6500, loss[loss=0.2122, simple_loss=0.2856, pruned_loss=0.06943, over 4808.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3085, pruned_loss=0.0725, over 965862.23 frames.], batch size: 12, lr: 5.00e-04
2022-05-29 11:43:41,157 INFO [train.py:761] (5/8) Epoch 29, batch 6550, loss[loss=0.2802, simple_loss=0.3436, pruned_loss=0.1084, over 4936.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3095, pruned_loss=0.07298, over 966514.06 frames.], batch size: 46, lr: 5.00e-04
2022-05-29 11:44:19,331 INFO [train.py:761] (5/8) Epoch 29, batch 6600, loss[loss=0.212, simple_loss=0.2933, pruned_loss=0.06535, over 4866.00 frames.], tot_loss[loss=0.2272, simple_loss=0.309, pruned_loss=0.0727, over 966276.89 frames.], batch size: 18, lr: 5.00e-04
2022-05-29 11:44:57,964 INFO [train.py:761] (5/8) Epoch 29, batch 6650, loss[loss=0.2075, simple_loss=0.2988, pruned_loss=0.05808, over 4795.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3088, pruned_loss=0.07225, over 966452.22 frames.], batch size: 16, lr: 5.00e-04
2022-05-29 11:45:35,920 INFO [train.py:761] (5/8) Epoch 29, batch 6700, loss[loss=0.2448, simple_loss=0.3192, pruned_loss=0.08519, over 4768.00 frames.], tot_loss[loss=0.227, simple_loss=0.3087, pruned_loss=0.07258, over 966341.66 frames.], batch size: 15, lr: 5.00e-04
2022-05-29 11:46:30,204 INFO [train.py:761] (5/8) Epoch 30, batch 0, loss[loss=0.1954, simple_loss=0.2896, pruned_loss=0.05054, over 4921.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2896, pruned_loss=0.05054, over 4921.00 frames.], batch size: 13, lr: 5.00e-04
2022-05-29 11:47:08,234 INFO [train.py:761] (5/8) Epoch 30, batch 50, loss[loss=0.2426, simple_loss=0.3451, pruned_loss=0.07009, over 4668.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2993, pruned_loss=0.05792, over 217729.67 frames.], batch size: 13, lr: 5.00e-04
2022-05-29 11:47:54,592 INFO [train.py:761] (5/8) Epoch 30, batch 100, loss[loss=0.2041, simple_loss=0.2774, pruned_loss=0.06542, over 4646.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2991, pruned_loss=0.05829, over 383360.08 frames.], batch size: 11, lr: 4.99e-04
2022-05-29 11:48:32,274 INFO [train.py:761] (5/8) Epoch 30, batch 150, loss[loss=0.2141, simple_loss=0.2946, pruned_loss=0.06676, over 4792.00 frames.], tot_loss[loss=0.2115, simple_loss=0.303, pruned_loss=0.06003, over 514178.76 frames.], batch size: 13, lr: 4.99e-04
2022-05-29 11:49:11,021 INFO [train.py:761] (5/8) Epoch 30, batch 200, loss[loss=0.2162, simple_loss=0.3126, pruned_loss=0.05987, over 4888.00 frames.], tot_loss[loss=0.2104, simple_loss=0.3022, pruned_loss=0.0593, over 614052.14 frames.], batch size: 12, lr: 4.99e-04
2022-05-29 11:49:48,869 INFO [train.py:761] (5/8) Epoch 30, batch 250, loss[loss=0.1592, simple_loss=0.2551, pruned_loss=0.0317, over 4662.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2987, pruned_loss=0.05746, over 691010.12 frames.], batch size: 12, lr: 4.99e-04
2022-05-29 11:50:27,120 INFO [train.py:761] (5/8) Epoch 30, batch 300, loss[loss=0.1734, simple_loss=0.2864, pruned_loss=0.03015, over 4987.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2971, pruned_loss=0.05684, over 752845.00 frames.], batch size: 21, lr: 4.99e-04
2022-05-29 11:51:04,899 INFO [train.py:761] (5/8) Epoch 30, batch 350, loss[loss=0.1837, simple_loss=0.2753, pruned_loss=0.04607, over 4731.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2991, pruned_loss=0.05729, over 799773.44 frames.], batch size: 11, lr: 4.99e-04
2022-05-29 11:51:42,879 INFO [train.py:761] (5/8) Epoch 30, batch 400, loss[loss=0.2274, simple_loss=0.3259, pruned_loss=0.06447, over 4983.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2983, pruned_loss=0.05693, over 836974.04 frames.], batch size: 49, lr: 4.99e-04
2022-05-29 11:52:20,469 INFO [train.py:761] (5/8) Epoch 30, batch 450, loss[loss=0.2139, simple_loss=0.2932, pruned_loss=0.06734, over 4992.00 frames.], tot_loss[loss=0.2057, simple_loss=0.298, pruned_loss=0.05673, over 865832.34 frames.], batch size: 13, lr: 4.99e-04
2022-05-29 11:52:58,567 INFO [train.py:761] (5/8) Epoch 30, batch 500, loss[loss=0.173, simple_loss=0.2664, pruned_loss=0.0398, over 4895.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2978, pruned_loss=0.05701, over 887841.04 frames.], batch size: 12, lr: 4.99e-04
2022-05-29 11:53:36,379 INFO [train.py:761] (5/8) Epoch 30, batch 550, loss[loss=0.1977, simple_loss=0.3021, pruned_loss=0.04664, over 4785.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2962, pruned_loss=0.05613, over 905556.95 frames.], batch size: 14, lr: 4.99e-04
2022-05-29 11:54:21,359 INFO [train.py:761] (5/8) Epoch 30, batch 600, loss[loss=0.2216, simple_loss=0.3316, pruned_loss=0.05583, over 4774.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2969, pruned_loss=0.05668, over 917742.15 frames.], batch size: 14, lr: 4.99e-04
2022-05-29 11:54:59,544 INFO [train.py:761] (5/8) Epoch 30, batch 650, loss[loss=0.1979, simple_loss=0.2938, pruned_loss=0.05096, over 4767.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2962, pruned_loss=0.0562, over 928357.16 frames.], batch size: 15, lr: 4.99e-04
2022-05-29 11:55:37,668 INFO [train.py:761] (5/8) Epoch 30, batch 700, loss[loss=0.2021, simple_loss=0.2985, pruned_loss=0.05289, over 4727.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2981, pruned_loss=0.05742, over 936231.76 frames.], batch size: 13, lr: 4.99e-04
2022-05-29 11:56:15,362 INFO [train.py:761] (5/8) Epoch 30, batch 750, loss[loss=0.1714, simple_loss=0.2602, pruned_loss=0.04131, over 4819.00 frames.], tot_loss[loss=0.2073, simple_loss=0.299, pruned_loss=0.05779, over 943032.10 frames.], batch size: 11, lr: 4.99e-04
2022-05-29 11:57:00,747 INFO [train.py:761] (5/8) Epoch 30, batch 800, loss[loss=0.2128, simple_loss=0.3095, pruned_loss=0.05802, over 4731.00 frames.], tot_loss[loss=0.2089, simple_loss=0.3008, pruned_loss=0.05849, over 947647.15 frames.], batch size: 12, lr: 4.99e-04
2022-05-29 11:57:38,494 INFO [train.py:761] (5/8) Epoch 30, batch 850, loss[loss=0.1765, simple_loss=0.264, pruned_loss=0.04449, over 4882.00 frames.], tot_loss[loss=0.2091, simple_loss=0.3005, pruned_loss=0.05888, over 949896.76 frames.], batch size: 12, lr: 4.99e-04
2022-05-29 11:58:17,174 INFO [train.py:761] (5/8) Epoch 30, batch 900, loss[loss=0.1765, simple_loss=0.2714, pruned_loss=0.04076, over 4722.00 frames.], tot_loss[loss=0.2097, simple_loss=0.3008, pruned_loss=0.05927, over 953250.10 frames.], batch size: 11, lr: 4.98e-04
2022-05-29 11:58:55,017 INFO [train.py:761] (5/8) Epoch 30, batch 950, loss[loss=0.2128, simple_loss=0.3007, pruned_loss=0.06246, over 4983.00 frames.], tot_loss[loss=0.2102, simple_loss=0.3016, pruned_loss=0.05939, over 955730.05 frames.], batch size: 13, lr: 4.98e-04
2022-05-29 11:59:33,443 INFO [train.py:761] (5/8) Epoch 30, batch 1000, loss[loss=0.2169, simple_loss=0.3139, pruned_loss=0.05988, over 4849.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2999, pruned_loss=0.0588, over 957596.92 frames.], batch size: 18, lr: 4.98e-04
2022-05-29 12:00:11,475 INFO [train.py:761] (5/8) Epoch 30, batch 1050, loss[loss=0.1969, simple_loss=0.2909, pruned_loss=0.05147, over 4830.00 frames.], tot_loss[loss=0.2094, simple_loss=0.3001, pruned_loss=0.05932, over 960597.25 frames.], batch size: 20, lr: 4.98e-04
2022-05-29 12:00:49,544 INFO [train.py:761] (5/8) Epoch 30, batch 1100, loss[loss=0.2402, simple_loss=0.3331, pruned_loss=0.07364, over 4799.00 frames.], tot_loss[loss=0.2098, simple_loss=0.3007, pruned_loss=0.0594, over 961537.09 frames.], batch size: 18, lr: 4.98e-04
2022-05-29 12:01:27,663 INFO [train.py:761] (5/8) Epoch 30, batch 1150, loss[loss=0.1777, simple_loss=0.2722, pruned_loss=0.04158, over 4668.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2993, pruned_loss=0.05854, over 963203.18 frames.], batch size: 12, lr: 4.98e-04
2022-05-29 12:02:06,169 INFO [train.py:761] (5/8) Epoch 30, batch 1200, loss[loss=0.201, simple_loss=0.291, pruned_loss=0.05555, over 4780.00 frames.], tot_loss[loss=0.2096, simple_loss=0.3005, pruned_loss=0.0594, over 965050.97 frames.], batch size: 15, lr: 4.98e-04
2022-05-29 12:02:51,328 INFO [train.py:761] (5/8) Epoch 30, batch 1250, loss[loss=0.1896, simple_loss=0.2917, pruned_loss=0.04375, over 4766.00 frames.], tot_loss[loss=0.2098, simple_loss=0.3009, pruned_loss=0.05937, over 965707.28 frames.], batch size: 15, lr: 4.98e-04
2022-05-29 12:03:29,116 INFO [train.py:761] (5/8) Epoch 30, batch 1300, loss[loss=0.2231, simple_loss=0.3188, pruned_loss=0.06368, over 4673.00 frames.], tot_loss[loss=0.2096, simple_loss=0.3009, pruned_loss=0.05921, over 965360.75 frames.], batch size: 13, lr: 4.98e-04
2022-05-29 12:04:14,188 INFO [train.py:761] (5/8) Epoch 30, batch 1350, loss[loss=0.2091, simple_loss=0.3086, pruned_loss=0.05479, over 4666.00 frames.], tot_loss[loss=0.2095, simple_loss=0.3008, pruned_loss=0.05905, over 966388.11 frames.], batch size: 13, lr: 4.98e-04
2022-05-29 12:04:52,251 INFO [train.py:761] (5/8) Epoch 30, batch 1400, loss[loss=0.2763, simple_loss=0.3559, pruned_loss=0.0983, over 4792.00 frames.], tot_loss[loss=0.2096, simple_loss=0.3006, pruned_loss=0.05926, over 965724.21 frames.], batch size: 14, lr: 4.98e-04
2022-05-29 12:05:29,986 INFO [train.py:761] (5/8) Epoch 30, batch 1450, loss[loss=0.2101, simple_loss=0.2954, pruned_loss=0.06245, over 4919.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2998, pruned_loss=0.0585, over 965897.08 frames.], batch size: 13, lr: 4.98e-04
2022-05-29 12:06:07,830 INFO [train.py:761] (5/8) Epoch 30, batch 1500, loss[loss=0.2645, simple_loss=0.3499, pruned_loss=0.08955, over 4890.00 frames.], tot_loss[loss=0.2095, simple_loss=0.3008, pruned_loss=0.05912, over 965836.19 frames.], batch size: 45, lr: 4.98e-04
2022-05-29 12:06:45,507 INFO [train.py:761] (5/8) Epoch 30, batch 1550, loss[loss=0.2222, simple_loss=0.3153, pruned_loss=0.06459, over 4976.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3018, pruned_loss=0.0592, over 966526.86 frames.], batch size: 15, lr: 4.98e-04
2022-05-29 12:07:23,294 INFO [train.py:761] (5/8) Epoch 30, batch 1600, loss[loss=0.2418, simple_loss=0.3158, pruned_loss=0.08391, over 4947.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3036, pruned_loss=0.06045, over 967371.76 frames.], batch size: 16, lr: 4.98e-04
2022-05-29 12:08:08,743 INFO [train.py:761] (5/8) Epoch 30, batch 1650, loss[loss=0.1916, simple_loss=0.2726, pruned_loss=0.05533, over 4969.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3036, pruned_loss=0.06039, over 967590.82 frames.], batch size: 12, lr: 4.98e-04
2022-05-29 12:08:46,111 INFO [train.py:761] (5/8) Epoch 30, batch 1700, loss[loss=0.2182, simple_loss=0.315, pruned_loss=0.06069, over 4674.00 frames.], tot_loss[loss=0.2104, simple_loss=0.3019, pruned_loss=0.05945, over 965320.33 frames.], batch size: 13, lr: 4.97e-04
2022-05-29 12:09:24,042 INFO [train.py:761] (5/8) Epoch 30, batch 1750, loss[loss=0.2256, simple_loss=0.3139, pruned_loss=0.0686, over 4850.00 frames.], tot_loss[loss=0.2102, simple_loss=0.3018, pruned_loss=0.05927, over 966207.64 frames.], batch size: 18, lr: 4.97e-04
2022-05-29 12:10:01,902 INFO [train.py:761] (5/8) Epoch 30, batch 1800, loss[loss=0.1928, simple_loss=0.2915, pruned_loss=0.04704, over 4724.00 frames.], tot_loss[loss=0.2111, simple_loss=0.3029, pruned_loss=0.0597, over 966596.54 frames.], batch size: 13, lr: 4.97e-04
2022-05-29 12:10:39,689 INFO [train.py:761] (5/8) Epoch 30, batch 1850, loss[loss=0.2204, simple_loss=0.3099, pruned_loss=0.06544, over 4796.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3044, pruned_loss=0.06072, over 966017.69 frames.], batch size: 14, lr: 4.97e-04
2022-05-29 12:11:18,193 INFO [train.py:761] (5/8) Epoch 30, batch 1900, loss[loss=0.1749, simple_loss=0.2769, pruned_loss=0.0364, over 4987.00 frames.], tot_loss[loss=0.2126, simple_loss=0.3043, pruned_loss=0.06044, over 965907.95 frames.], batch size: 13, lr: 4.97e-04
2022-05-29 12:11:55,376 INFO [train.py:761] (5/8) Epoch 30, batch 1950, loss[loss=0.2412, simple_loss=0.3347, pruned_loss=0.07382, over 4810.00 frames.], tot_loss[loss=0.2124, simple_loss=0.3043, pruned_loss=0.06026, over 966613.99 frames.], batch size: 18, lr: 4.97e-04
2022-05-29 12:12:33,485 INFO [train.py:761] (5/8) Epoch 30, batch 2000, loss[loss=0.2552, simple_loss=0.3483, pruned_loss=0.08106, over 4919.00 frames.], tot_loss[loss=0.2128, simple_loss=0.3047, pruned_loss=0.06048, over 967112.97 frames.], batch size: 49, lr: 4.97e-04
2022-05-29 12:13:11,064 INFO [train.py:761] (5/8) Epoch 30, batch 2050, loss[loss=0.1938, simple_loss=0.2911, pruned_loss=0.0483, over 4725.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3039, pruned_loss=0.06014, over 967793.18 frames.], batch size: 13, lr: 4.97e-04
2022-05-29 12:13:49,037 INFO [train.py:761] (5/8) Epoch 30, batch 2100, loss[loss=0.2002, simple_loss=0.2957, pruned_loss=0.05239, over 4957.00 frames.], tot_loss[loss=0.2107, simple_loss=0.3024, pruned_loss=0.0595, over 967488.06 frames.], batch size: 26, lr: 4.97e-04
2022-05-29 12:14:34,400 INFO [train.py:761] (5/8) Epoch 30, batch 2150, loss[loss=0.2418, simple_loss=0.3393, pruned_loss=0.07212, over 4725.00 frames.], tot_loss[loss=0.2117, simple_loss=0.304, pruned_loss=0.05965, over 966692.50 frames.], batch size: 14, lr: 4.97e-04
2022-05-29 12:15:12,658 INFO [train.py:761] (5/8) Epoch 30, batch 2200, loss[loss=0.1822, simple_loss=0.2884, pruned_loss=0.03803, over 4794.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3038, pruned_loss=0.0597, over 968210.82 frames.], batch size: 13, lr: 4.97e-04
2022-05-29 12:15:50,208 INFO [train.py:761] (5/8) Epoch 30, batch 2250, loss[loss=0.2176, simple_loss=0.3168, pruned_loss=0.05923, over 4782.00 frames.], tot_loss[loss=0.2111, simple_loss=0.303, pruned_loss=0.05956, over 967583.93 frames.], batch size: 16, lr: 4.97e-04
2022-05-29 12:16:28,465 INFO [train.py:761] (5/8) Epoch 30, batch 2300, loss[loss=0.2311, simple_loss=0.3158, pruned_loss=0.07325, over 4776.00 frames.], tot_loss[loss=0.2104, simple_loss=0.3016, pruned_loss=0.05958, over 968083.07 frames.], batch size: 15, lr: 4.97e-04
2022-05-29 12:17:06,473 INFO [train.py:761] (5/8) Epoch 30, batch 2350, loss[loss=0.2055, simple_loss=0.3034, pruned_loss=0.05382, over 4790.00 frames.], tot_loss[loss=0.2088, simple_loss=0.3004, pruned_loss=0.05864, over 968456.52 frames.], batch size: 14, lr: 4.97e-04
2022-05-29 12:17:45,216 INFO [train.py:761] (5/8) Epoch 30, batch 2400, loss[loss=0.2177, simple_loss=0.3088, pruned_loss=0.06325, over 4669.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2992, pruned_loss=0.05828, over 967443.76 frames.], batch size: 13, lr: 4.97e-04
2022-05-29 12:18:23,347 INFO [train.py:761] (5/8) Epoch 30, batch 2450, loss[loss=0.1714, simple_loss=0.2688, pruned_loss=0.03702, over 4730.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2999, pruned_loss=0.05885, over 965303.96 frames.], batch size: 11, lr: 4.97e-04
2022-05-29 12:19:01,802 INFO [train.py:761] (5/8) Epoch 30, batch 2500, loss[loss=0.2045, simple_loss=0.3051, pruned_loss=0.05195, over 4877.00 frames.], tot_loss[loss=0.2096, simple_loss=0.3012, pruned_loss=0.05898, over 965944.41 frames.], batch size: 15, lr: 4.96e-04
2022-05-29 12:19:40,232 INFO [train.py:761] (5/8) Epoch 30, batch 2550, loss[loss=0.1711, simple_loss=0.2539, pruned_loss=0.04414, over 4740.00 frames.], tot_loss[loss=0.2103, simple_loss=0.3016, pruned_loss=0.05948, over 967128.76 frames.], batch size: 11, lr: 4.96e-04
2022-05-29 12:20:18,489 INFO [train.py:761] (5/8) Epoch 30, batch 2600, loss[loss=0.2837, simple_loss=0.3664, pruned_loss=0.1005, over 4933.00 frames.], tot_loss[loss=0.21, simple_loss=0.3019, pruned_loss=0.05907, over 967032.28 frames.], batch size: 16, lr: 4.96e-04
2022-05-29 12:20:56,533 INFO [train.py:761] (5/8) Epoch 30, batch 2650, loss[loss=0.1992, simple_loss=0.287, pruned_loss=0.0557, over 4982.00 frames.], tot_loss[loss=0.2098, simple_loss=0.3018, pruned_loss=0.05894, over 967641.62 frames.], batch size: 13, lr: 4.96e-04
2022-05-29 12:21:34,817 INFO [train.py:761] (5/8) Epoch 30, batch 2700, loss[loss=0.1653, simple_loss=0.2511, pruned_loss=0.03974, over 4806.00 frames.], tot_loss[loss=0.2085, simple_loss=0.3005, pruned_loss=0.05831, over 967254.54 frames.], batch size: 12, lr: 4.96e-04
2022-05-29 12:22:12,433 INFO [train.py:761] (5/8) Epoch 30, batch 2750, loss[loss=0.2241, simple_loss=0.3096, pruned_loss=0.06933, over 4861.00 frames.], tot_loss[loss=0.2089, simple_loss=0.3012, pruned_loss=0.05832, over 966678.77 frames.], batch size: 18, lr: 4.96e-04
2022-05-29 12:22:50,407 INFO [train.py:761] (5/8) Epoch 30, batch 2800, loss[loss=0.2502, simple_loss=0.3494, pruned_loss=0.07547, over 4761.00 frames.], tot_loss[loss=0.2094, simple_loss=0.3021, pruned_loss=0.05837, over 966139.96 frames.], batch size: 15, lr: 4.96e-04
2022-05-29 12:23:28,209 INFO [train.py:761] (5/8) Epoch 30, batch 2850, loss[loss=0.1857, simple_loss=0.2842, pruned_loss=0.04362, over 4984.00 frames.], tot_loss[loss=0.208, simple_loss=0.3005, pruned_loss=0.05777, over 965742.58 frames.], batch size: 14, lr: 4.96e-04
2022-05-29 12:24:06,238 INFO [train.py:761] (5/8) Epoch 30, batch 2900, loss[loss=0.1795, simple_loss=0.2726, pruned_loss=0.04316, over 4716.00 frames.], tot_loss[loss=0.2093, simple_loss=0.302, pruned_loss=0.05834, over 966127.04 frames.], batch size: 12, lr: 4.96e-04
2022-05-29 12:24:44,132 INFO [train.py:761] (5/8) Epoch 30, batch 2950, loss[loss=0.2235, simple_loss=0.3215, pruned_loss=0.06272, over 4919.00 frames.], tot_loss[loss=0.2086, simple_loss=0.3013, pruned_loss=0.05797, over 967656.45 frames.], batch size: 47, lr: 4.96e-04
2022-05-29 12:25:22,043 INFO [train.py:761] (5/8) Epoch 30, batch 3000, loss[loss=0.2115, simple_loss=0.3167, pruned_loss=0.05311, over 4971.00 frames.], tot_loss[loss=0.209, simple_loss=0.3016, pruned_loss=0.05819, over 967635.23 frames.], batch size: 16, lr: 4.96e-04
2022-05-29 12:25:22,043 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 12:25:31,903 INFO [train.py:790] (5/8) Epoch 30, validation: loss=0.2073, simple_loss=0.3053, pruned_loss=0.05463, over 944034.00 frames.
2022-05-29 12:26:09,418 INFO [train.py:761] (5/8) Epoch 30, batch 3050, loss[loss=0.1907, simple_loss=0.2867, pruned_loss=0.04734, over 4735.00 frames.], tot_loss[loss=0.2081, simple_loss=0.3003, pruned_loss=0.05797, over 967197.09 frames.], batch size: 12, lr: 4.96e-04
2022-05-29 12:26:47,979 INFO [train.py:761] (5/8) Epoch 30, batch 3100, loss[loss=0.1819, simple_loss=0.276, pruned_loss=0.04391, over 4847.00 frames.], tot_loss[loss=0.2093, simple_loss=0.301, pruned_loss=0.05874, over 966577.87 frames.], batch size: 14, lr: 4.96e-04
2022-05-29 12:27:26,403 INFO [train.py:761] (5/8) Epoch 30, batch 3150, loss[loss=0.2391, simple_loss=0.3337, pruned_loss=0.07223, over 4779.00 frames.], tot_loss[loss=0.2105, simple_loss=0.3013, pruned_loss=0.05983, over 966156.36 frames.], batch size: 15, lr: 4.96e-04
2022-05-29 12:28:04,806 INFO [train.py:761] (5/8) Epoch 30, batch 3200, loss[loss=0.2301, simple_loss=0.3087, pruned_loss=0.07577, over 4722.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3028, pruned_loss=0.06205, over 965852.81 frames.], batch size: 13, lr: 4.96e-04
2022-05-29 12:28:42,724 INFO [train.py:761] (5/8) Epoch 30, batch 3250, loss[loss=0.195, simple_loss=0.2757, pruned_loss=0.05716, over 4642.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3031, pruned_loss=0.06305, over 964619.72 frames.], batch size: 11, lr: 4.96e-04
2022-05-29 12:29:20,830 INFO [train.py:761] (5/8) Epoch 30, batch 3300, loss[loss=0.2052, simple_loss=0.3015, pruned_loss=0.05449, over 4976.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3041, pruned_loss=0.06429, over 965157.58 frames.], batch size: 14, lr: 4.95e-04
2022-05-29 12:29:59,002 INFO [train.py:761] (5/8) Epoch 30, batch 3350, loss[loss=0.2324, simple_loss=0.3036, pruned_loss=0.08061, over 4974.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3057, pruned_loss=0.06637, over 964612.54 frames.], batch size: 12, lr: 4.95e-04
2022-05-29 12:30:37,507 INFO [train.py:761] (5/8) Epoch 30, batch 3400, loss[loss=0.2206, simple_loss=0.304, pruned_loss=0.06858, over 4714.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3063, pruned_loss=0.06752, over 963985.22 frames.], batch size: 14, lr: 4.95e-04
2022-05-29 12:31:14,940 INFO [train.py:761] (5/8) Epoch 30, batch 3450, loss[loss=0.2156, simple_loss=0.2826, pruned_loss=0.07432, over 4993.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3072, pruned_loss=0.06886, over 963138.30 frames.], batch size: 13, lr: 4.95e-04
2022-05-29 12:31:53,387 INFO [train.py:761] (5/8) Epoch 30, batch 3500, loss[loss=0.1789, simple_loss=0.2701, pruned_loss=0.04381, over 4725.00 frames.], tot_loss[loss=0.223, simple_loss=0.3073, pruned_loss=0.06931, over 963420.17 frames.], batch size: 12, lr: 4.95e-04
2022-05-29 12:32:31,485 INFO [train.py:761] (5/8) Epoch 30, batch 3550, loss[loss=0.2122, simple_loss=0.2863, pruned_loss=0.06903, over 4634.00 frames.], tot_loss[loss=0.225, simple_loss=0.3082, pruned_loss=0.07094, over 964516.25 frames.], batch size: 11, lr: 4.95e-04
2022-05-29 12:33:09,650 INFO [train.py:761] (5/8) Epoch 30, batch 3600, loss[loss=0.1872, simple_loss=0.2652, pruned_loss=0.05455, over 4728.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3091, pruned_loss=0.07223, over 964753.74 frames.], batch size: 11, lr: 4.95e-04
2022-05-29 12:33:47,845 INFO [train.py:761] (5/8) Epoch 30, batch 3650, loss[loss=0.2352, simple_loss=0.3275, pruned_loss=0.07148, over 4893.00 frames.], tot_loss[loss=0.227, simple_loss=0.3087, pruned_loss=0.07267, over 965258.07 frames.], batch size: 15, lr: 4.95e-04
2022-05-29 12:34:25,999 INFO [train.py:761] (5/8) Epoch 30, batch 3700, loss[loss=0.203, simple_loss=0.2852, pruned_loss=0.06041, over 4985.00 frames.], tot_loss[loss=0.2262, simple_loss=0.3076, pruned_loss=0.07238, over 964975.20 frames.], batch size: 13, lr: 4.95e-04
2022-05-29 12:35:03,996 INFO [train.py:761] (5/8) Epoch 30, batch 3750, loss[loss=0.1761, simple_loss=0.2686, pruned_loss=0.04184, over 4651.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3099, pruned_loss=0.07341, over 965104.67 frames.], batch size: 11, lr: 4.95e-04
2022-05-29 12:35:41,633 INFO [train.py:761] (5/8) Epoch 30, batch 3800, loss[loss=0.225, simple_loss=0.3087, pruned_loss=0.07064, over 4725.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3087, pruned_loss=0.07324, over 965042.60 frames.], batch size: 13, lr: 4.95e-04
2022-05-29 12:36:19,062 INFO [train.py:761] (5/8) Epoch 30, batch 3850, loss[loss=0.1906, simple_loss=0.2702, pruned_loss=0.05549, over 4665.00 frames.], tot_loss[loss=0.229, simple_loss=0.3098, pruned_loss=0.07413, over 965480.50 frames.], batch size: 12, lr: 4.95e-04
2022-05-29 12:36:57,089 INFO [train.py:761] (5/8) Epoch 30, batch 3900, loss[loss=0.1741, simple_loss=0.253, pruned_loss=0.04754, over 4731.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3093, pruned_loss=0.07389, over 965160.05 frames.], batch size: 11, lr: 4.95e-04
2022-05-29 12:37:35,155 INFO [train.py:761] (5/8) Epoch 30, batch 3950, loss[loss=0.2457, simple_loss=0.3102, pruned_loss=0.09063, over 4986.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3089, pruned_loss=0.07411, over 965102.03 frames.], batch size: 13, lr: 4.95e-04
2022-05-29 12:38:13,430 INFO [train.py:761] (5/8) Epoch 30, batch 4000, loss[loss=0.2325, simple_loss=0.3213, pruned_loss=0.07178, over 4766.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3089, pruned_loss=0.07362, over 966058.99 frames.], batch size: 15, lr: 4.95e-04
2022-05-29 12:38:51,302 INFO [train.py:761] (5/8) Epoch 30, batch 4050, loss[loss=0.2997, simple_loss=0.3677, pruned_loss=0.1158, over 4848.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3085, pruned_loss=0.07361, over 965889.41 frames.], batch size: 18, lr: 4.95e-04
2022-05-29 12:39:29,529 INFO [train.py:761] (5/8) Epoch 30, batch 4100, loss[loss=0.2061, simple_loss=0.288, pruned_loss=0.06215, over 4888.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3077, pruned_loss=0.07289, over 966114.56 frames.], batch size: 12, lr: 4.94e-04
2022-05-29 12:40:08,102 INFO [train.py:761] (5/8) Epoch 30, batch 4150, loss[loss=0.232, simple_loss=0.3186, pruned_loss=0.07266, over 4789.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3078, pruned_loss=0.0726, over 964726.88 frames.], batch size: 14, lr: 4.94e-04
2022-05-29 12:40:46,620 INFO [train.py:761] (5/8) Epoch 30, batch 4200, loss[loss=0.1844, simple_loss=0.2718, pruned_loss=0.0485, over 4987.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3076, pruned_loss=0.07246, over 966427.07 frames.], batch size: 13, lr: 4.94e-04
2022-05-29 12:41:25,107 INFO [train.py:761] (5/8) Epoch 30, batch 4250, loss[loss=0.2806, simple_loss=0.3593, pruned_loss=0.1009, over 4885.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3087, pruned_loss=0.07415, over 966259.48 frames.], batch size: 15, lr: 4.94e-04
2022-05-29 12:42:03,085 INFO [train.py:761] (5/8) Epoch 30, batch 4300, loss[loss=0.234, simple_loss=0.3222, pruned_loss=0.07287, over 4972.00 frames.], tot_loss[loss=0.2287, simple_loss=0.3093, pruned_loss=0.07401, over 966936.47 frames.], batch size: 15, lr: 4.94e-04
2022-05-29 12:42:41,285 INFO [train.py:761] (5/8) Epoch 30, batch 4350, loss[loss=0.262, simple_loss=0.325, pruned_loss=0.09955, over 4805.00 frames.], tot_loss[loss=0.2305, simple_loss=0.3106, pruned_loss=0.07523, over 966586.49 frames.], batch size: 12, lr: 4.94e-04
2022-05-29 12:43:23,641 INFO [train.py:761] (5/8) Epoch 30, batch 4400, loss[loss=0.2061, simple_loss=0.2794, pruned_loss=0.06637, over 4637.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3087, pruned_loss=0.07402, over 966926.81 frames.], batch size: 11, lr: 4.94e-04
2022-05-29 12:44:02,284 INFO [train.py:761] (5/8) Epoch 30, batch 4450, loss[loss=0.276, simple_loss=0.3601, pruned_loss=0.09593, over 4843.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3081, pruned_loss=0.07353, over 966452.05 frames.], batch size: 26, lr: 4.94e-04
2022-05-29 12:44:40,439 INFO [train.py:761] (5/8) Epoch 30, batch 4500, loss[loss=0.1961, simple_loss=0.2748, pruned_loss=0.05873, over 4722.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3072, pruned_loss=0.0727, over 966210.61 frames.], batch size: 14, lr: 4.94e-04
2022-05-29 12:45:18,468 INFO [train.py:761] (5/8) Epoch 30, batch 4550, loss[loss=0.2329, simple_loss=0.3251, pruned_loss=0.07034, over 4983.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3085, pruned_loss=0.07339, over 966983.21 frames.], batch size: 44, lr: 4.94e-04
2022-05-29 12:45:57,134 INFO [train.py:761] (5/8) Epoch 30, batch 4600, loss[loss=0.188, simple_loss=0.2816, pruned_loss=0.04723, over 4913.00 frames.], tot_loss[loss=0.226, simple_loss=0.3072, pruned_loss=0.07243, over 966655.09 frames.], batch size: 14, lr: 4.94e-04
2022-05-29 12:46:35,244 INFO [train.py:761] (5/8) Epoch 30, batch 4650, loss[loss=0.2646, simple_loss=0.3481, pruned_loss=0.09056, over 4873.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3092, pruned_loss=0.07369, over 967170.81 frames.], batch size: 15, lr: 4.94e-04
2022-05-29 12:47:13,952 INFO [train.py:761] (5/8) Epoch 30, batch 4700, loss[loss=0.2405, simple_loss=0.321, pruned_loss=0.07998, over 4940.00 frames.], tot_loss[loss=0.229, simple_loss=0.3098, pruned_loss=0.07411, over 967513.48 frames.], batch size: 16, lr: 4.94e-04
2022-05-29 12:47:51,953 INFO [train.py:761] (5/8) Epoch 30, batch 4750, loss[loss=0.2298, simple_loss=0.3157, pruned_loss=0.07195, over 4959.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3098, pruned_loss=0.07425, over 966040.81 frames.], batch size: 16, lr: 4.94e-04
2022-05-29 12:48:30,164 INFO [train.py:761] (5/8) Epoch 30, batch 4800, loss[loss=0.2226, simple_loss=0.3175, pruned_loss=0.06391, over 4796.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3095, pruned_loss=0.07436, over 965157.16 frames.], batch size: 16, lr: 4.94e-04
2022-05-29 12:49:08,116 INFO [train.py:761] (5/8) Epoch 30, batch 4850, loss[loss=0.2869, simple_loss=0.3584, pruned_loss=0.1077, over 4924.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3096, pruned_loss=0.07476, over 964793.76 frames.], batch size: 44, lr: 4.94e-04
2022-05-29 12:49:46,254 INFO [train.py:761] (5/8) Epoch 30, batch 4900, loss[loss=0.233, simple_loss=0.3118, pruned_loss=0.07717, over 4786.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3092, pruned_loss=0.07426, over 965094.99 frames.], batch size: 13, lr: 4.93e-04
2022-05-29 12:50:24,534 INFO [train.py:761] (5/8) Epoch 30, batch 4950, loss[loss=0.2059, simple_loss=0.3001, pruned_loss=0.05582, over 4786.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3084, pruned_loss=0.07302, over 964624.10 frames.], batch size: 13, lr: 4.93e-04
2022-05-29 12:51:02,548 INFO [train.py:761] (5/8) Epoch 30, batch 5000, loss[loss=0.2178, simple_loss=0.2914, pruned_loss=0.07211, over 4800.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3082, pruned_loss=0.07261, over 965634.68 frames.], batch size: 16, lr: 4.93e-04
2022-05-29 12:51:40,836 INFO [train.py:761] (5/8) Epoch 30, batch 5050, loss[loss=0.234, simple_loss=0.3263, pruned_loss=0.07084, over 4990.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3087, pruned_loss=0.07315, over 965735.78 frames.], batch size: 13, lr: 4.93e-04
2022-05-29 12:52:19,583 INFO [train.py:761] (5/8) Epoch 30, batch 5100, loss[loss=0.2142, simple_loss=0.3108, pruned_loss=0.05885, over 4670.00 frames.], tot_loss[loss=0.228, simple_loss=0.3088, pruned_loss=0.07357, over 965659.12 frames.], batch size: 13, lr: 4.93e-04
2022-05-29 12:52:57,943 INFO [train.py:761] (5/8) Epoch 30, batch 5150, loss[loss=0.2254, simple_loss=0.3126, pruned_loss=0.06907, over 4793.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3092, pruned_loss=0.07369, over 965966.54 frames.], batch size: 18, lr: 4.93e-04
2022-05-29 12:53:36,602 INFO [train.py:761] (5/8) Epoch 30, batch 5200, loss[loss=0.2441, simple_loss=0.3316, pruned_loss=0.0783, over 4788.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3087, pruned_loss=0.07346, over 965859.78 frames.], batch size: 13, lr: 4.93e-04
2022-05-29 12:54:14,206 INFO [train.py:761] (5/8) Epoch 30, batch 5250, loss[loss=0.247, simple_loss=0.3227, pruned_loss=0.08564, over 4718.00 frames.], tot_loss[loss=0.2262, simple_loss=0.3075, pruned_loss=0.07246, over 965890.82 frames.], batch size: 14, lr: 4.93e-04
2022-05-29 12:54:52,577 INFO [train.py:761] (5/8) Epoch 30, batch 5300, loss[loss=0.2346, simple_loss=0.308, pruned_loss=0.08058, over 4785.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3085, pruned_loss=0.07331, over 966175.54 frames.], batch size: 14, lr: 4.93e-04
2022-05-29 12:55:31,364 INFO [train.py:761] (5/8) Epoch 30, batch 5350, loss[loss=0.2003, simple_loss=0.3099, pruned_loss=0.04532, over 4774.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3087, pruned_loss=0.07312, over 965920.24 frames.], batch size: 20, lr: 4.93e-04
2022-05-29 12:56:09,419 INFO [train.py:761] (5/8) Epoch 30, batch 5400, loss[loss=0.2171, simple_loss=0.2981, pruned_loss=0.06803, over 4563.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3071, pruned_loss=0.07168, over 965449.63 frames.], batch size: 10, lr: 4.93e-04
2022-05-29 12:56:47,822 INFO [train.py:761] (5/8) Epoch 30, batch 5450, loss[loss=0.2382, simple_loss=0.3314, pruned_loss=0.07248, over 4779.00 frames.], tot_loss[loss=0.227, simple_loss=0.3089, pruned_loss=0.07255, over 966536.19 frames.], batch size: 14, lr: 4.93e-04
2022-05-29 12:57:26,186 INFO [train.py:761] (5/8) Epoch 30, batch 5500, loss[loss=0.1954, simple_loss=0.2871, pruned_loss=0.05189, over 4922.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3081, pruned_loss=0.07223, over 966814.72 frames.], batch size: 13, lr: 4.93e-04
2022-05-29 12:58:04,168 INFO [train.py:761] (5/8) Epoch 30, batch 5550, loss[loss=0.2286, simple_loss=0.3141, pruned_loss=0.0716, over 4720.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3075, pruned_loss=0.07209, over 966269.26 frames.], batch size: 14, lr: 4.93e-04
2022-05-29 12:58:42,691 INFO [train.py:761] (5/8) Epoch 30, batch 5600, loss[loss=0.2076, simple_loss=0.3087, pruned_loss=0.05327, over 4949.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3083, pruned_loss=0.07274, over 965451.72 frames.], batch size: 16, lr: 4.93e-04
2022-05-29 12:59:20,692 INFO [train.py:761] (5/8) Epoch 30, batch 5650, loss[loss=0.2455, simple_loss=0.3296, pruned_loss=0.08072, over 4719.00 frames.], tot_loss[loss=0.226, simple_loss=0.3074, pruned_loss=0.07228, over 963952.70 frames.], batch size: 12, lr: 4.93e-04
2022-05-29 12:59:59,028 INFO [train.py:761] (5/8) Epoch 30, batch 5700, loss[loss=0.1848, simple_loss=0.2664, pruned_loss=0.05164, over 4646.00 frames.], tot_loss[loss=0.227, simple_loss=0.308, pruned_loss=0.07296, over 963841.16 frames.], batch size: 11, lr: 4.92e-04
2022-05-29 13:00:37,358 INFO [train.py:761] (5/8) Epoch 30, batch 5750, loss[loss=0.2189, simple_loss=0.318, pruned_loss=0.05993, over 4724.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3072, pruned_loss=0.07216, over 964148.49 frames.], batch size: 13, lr: 4.92e-04
2022-05-29 13:01:15,754 INFO [train.py:761] (5/8) Epoch 30, batch 5800, loss[loss=0.2319, simple_loss=0.3226, pruned_loss=0.07059, over 4667.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3079, pruned_loss=0.07243, over 964515.78 frames.], batch size: 13, lr: 4.92e-04
2022-05-29 13:01:54,189 INFO [train.py:761] (5/8) Epoch 30, batch 5850, loss[loss=0.2601, simple_loss=0.3475, pruned_loss=0.08633, over 4768.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3075, pruned_loss=0.07178, over 964323.02 frames.], batch size: 15, lr: 4.92e-04
2022-05-29 13:02:32,688 INFO [train.py:761] (5/8) Epoch 30, batch 5900, loss[loss=0.2466, simple_loss=0.3195, pruned_loss=0.08686, over 4828.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3078, pruned_loss=0.07269, over 964602.28 frames.], batch size: 25, lr: 4.92e-04
2022-05-29 13:03:10,922 INFO [train.py:761] (5/8) Epoch 30, batch 5950, loss[loss=0.2319, simple_loss=0.317, pruned_loss=0.07338, over 4971.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3088, pruned_loss=0.07312, over 966742.78 frames.], batch size: 16, lr: 4.92e-04
2022-05-29 13:03:49,525 INFO [train.py:761] (5/8) Epoch 30, batch 6000, loss[loss=0.2283, simple_loss=0.2998, pruned_loss=0.0784, over 4585.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3077, pruned_loss=0.07307, over 966027.27 frames.], batch size: 10, lr: 4.92e-04
2022-05-29 13:03:49,525 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 13:03:59,566 INFO [train.py:790] (5/8) Epoch 30, validation: loss=0.198, simple_loss=0.3012, pruned_loss=0.04734, over 944034.00 frames.
2022-05-29 13:04:36,953 INFO [train.py:761] (5/8) Epoch 30, batch 6050, loss[loss=0.2565, simple_loss=0.3245, pruned_loss=0.09422, over 4981.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3071, pruned_loss=0.07259, over 965869.20 frames.], batch size: 27, lr: 4.92e-04
2022-05-29 13:05:15,771 INFO [train.py:761] (5/8) Epoch 30, batch 6100, loss[loss=0.2012, simple_loss=0.2803, pruned_loss=0.061, over 4980.00 frames.], tot_loss[loss=0.226, simple_loss=0.3067, pruned_loss=0.07267, over 966407.30 frames.], batch size: 14, lr: 4.92e-04
2022-05-29 13:05:53,733 INFO [train.py:761] (5/8) Epoch 30, batch 6150, loss[loss=0.2435, simple_loss=0.323, pruned_loss=0.08203, over 4766.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3065, pruned_loss=0.07265, over 967196.74 frames.], batch size: 20, lr: 4.92e-04
2022-05-29 13:06:32,076 INFO [train.py:761] (5/8) Epoch 30, batch 6200, loss[loss=0.1919, simple_loss=0.282, pruned_loss=0.05085, over 4862.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3063, pruned_loss=0.07237, over 966140.97 frames.], batch size: 20, lr: 4.92e-04
2022-05-29 13:07:10,302 INFO [train.py:761] (5/8) Epoch 30, batch 6250, loss[loss=0.2343, simple_loss=0.292, pruned_loss=0.0883, over 4831.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3061, pruned_loss=0.07211, over 965221.34 frames.], batch size: 11, lr: 4.92e-04
2022-05-29 13:07:48,819 INFO [train.py:761] (5/8) Epoch 30, batch 6300, loss[loss=0.2237, simple_loss=0.3108, pruned_loss=0.06825, over 4895.00 frames.], tot_loss[loss=0.2268, simple_loss=0.308, pruned_loss=0.07283, over 965940.28 frames.], batch size: 15, lr: 4.92e-04
2022-05-29 13:08:27,215 INFO [train.py:761] (5/8) Epoch 30, batch 6350, loss[loss=0.268, simple_loss=0.3536, pruned_loss=0.09124, over 4830.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3079, pruned_loss=0.07236, over 965248.86 frames.], batch size: 26, lr: 4.92e-04
2022-05-29 13:09:05,173 INFO [train.py:761] (5/8) Epoch 30, batch 6400, loss[loss=0.1627, simple_loss=0.2374, pruned_loss=0.04403, over 4558.00 frames.], tot_loss[loss=0.226, simple_loss=0.3072, pruned_loss=0.07234, over 965142.09 frames.], batch size: 10, lr: 4.92e-04
2022-05-29 13:09:43,533 INFO [train.py:761] (5/8) Epoch 30, batch 6450, loss[loss=0.2014, simple_loss=0.2951, pruned_loss=0.05389, over 4852.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3074, pruned_loss=0.07241, over 964568.17 frames.], batch size: 14, lr: 4.92e-04
2022-05-29 13:10:21,907 INFO [train.py:761] (5/8) Epoch 30, batch 6500, loss[loss=0.3101, simple_loss=0.3818, pruned_loss=0.1192, over 4925.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3066, pruned_loss=0.07158, over 964195.75 frames.], batch size: 50, lr: 4.92e-04
2022-05-29 13:11:00,355 INFO [train.py:761] (5/8) Epoch 30, batch 6550, loss[loss=0.2877, simple_loss=0.3431, pruned_loss=0.1162, over 4893.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3068, pruned_loss=0.07099, over 964629.54 frames.], batch size: 26, lr: 4.91e-04
2022-05-29 13:11:38,640 INFO [train.py:761] (5/8) Epoch 30, batch 6600, loss[loss=0.1685, simple_loss=0.2517, pruned_loss=0.04261, over 4804.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3059, pruned_loss=0.07089, over 965798.73 frames.], batch size: 12, lr: 4.91e-04
2022-05-29 13:12:16,596 INFO [train.py:761] (5/8) Epoch 30, batch 6650, loss[loss=0.2314, simple_loss=0.3232, pruned_loss=0.06982, over 4970.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3071, pruned_loss=0.07175, over 966332.59 frames.], batch size: 14, lr: 4.91e-04
2022-05-29 13:12:54,954 INFO [train.py:761] (5/8) Epoch 30, batch 6700, loss[loss=0.2131, simple_loss=0.3031, pruned_loss=0.06154, over 4856.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3069, pruned_loss=0.07085, over 965615.15 frames.], batch size: 25, lr: 4.91e-04
2022-05-29 13:13:48,245 INFO [train.py:761] (5/8) Epoch 31, batch 0, loss[loss=0.206, simple_loss=0.2951, pruned_loss=0.05843, over 4928.00 frames.], tot_loss[loss=0.206, simple_loss=0.2951, pruned_loss=0.05843, over 4928.00 frames.], batch size: 13, lr: 4.91e-04
2022-05-29 13:14:26,749 INFO [train.py:761] (5/8) Epoch 31, batch 50, loss[loss=0.1816, simple_loss=0.2738, pruned_loss=0.04471, over 4661.00 frames.], tot_loss[loss=0.217, simple_loss=0.3072, pruned_loss=0.06342, over 218331.30 frames.], batch size: 12, lr: 4.91e-04
2022-05-29 13:15:04,811 INFO [train.py:761] (5/8) Epoch 31, batch 100, loss[loss=0.205, simple_loss=0.3004, pruned_loss=0.05485, over 4674.00 frames.], tot_loss[loss=0.2105, simple_loss=0.3011, pruned_loss=0.05993, over 383274.85 frames.], batch size: 13, lr: 4.91e-04
2022-05-29 13:15:43,143 INFO [train.py:761] (5/8) Epoch 31, batch 150, loss[loss=0.1736, simple_loss=0.2654, pruned_loss=0.04092, over 4650.00 frames.], tot_loss[loss=0.2088, simple_loss=0.3, pruned_loss=0.05887, over 512607.09 frames.], batch size: 11, lr: 4.91e-04
2022-05-29 13:16:20,828 INFO [train.py:761] (5/8) Epoch 31, batch 200, loss[loss=0.2342, simple_loss=0.3326, pruned_loss=0.06789, over 4974.00 frames.], tot_loss[loss=0.209, simple_loss=0.3009, pruned_loss=0.05854, over 613823.01 frames.], batch size: 14, lr: 4.91e-04
2022-05-29 13:16:58,953 INFO [train.py:761] (5/8) Epoch 31, batch 250, loss[loss=0.1901, simple_loss=0.2916, pruned_loss=0.04424, over 4796.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2997, pruned_loss=0.05704, over 692309.74 frames.], batch size: 16, lr: 4.91e-04
2022-05-29 13:17:36,667 INFO [train.py:761] (5/8) Epoch 31, batch 300, loss[loss=0.1994, simple_loss=0.2807, pruned_loss=0.05907, over 4781.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2995, pruned_loss=0.05748, over 752973.74 frames.], batch size: 13, lr: 4.91e-04
2022-05-29 13:18:14,853 INFO [train.py:761] (5/8) Epoch 31, batch 350, loss[loss=0.1858, simple_loss=0.274, pruned_loss=0.04882, over 4901.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2991, pruned_loss=0.05784, over 800277.58 frames.], batch size: 12, lr: 4.91e-04
2022-05-29 13:18:52,885 INFO [train.py:761] (5/8) Epoch 31, batch 400, loss[loss=0.1967, simple_loss=0.3121, pruned_loss=0.04066, over 4787.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2978, pruned_loss=0.05693, over 837700.08 frames.], batch size: 14, lr: 4.91e-04
2022-05-29 13:19:30,352 INFO [train.py:761] (5/8) Epoch 31, batch 450, loss[loss=0.1764, simple_loss=0.2619, pruned_loss=0.04542, over 4829.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2981, pruned_loss=0.05732, over 866016.75 frames.], batch size: 11, lr: 4.91e-04
2022-05-29 13:20:08,017 INFO [train.py:761] (5/8) Epoch 31, batch 500, loss[loss=0.2143, simple_loss=0.2991, pruned_loss=0.06478, over 4926.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2973, pruned_loss=0.05686, over 888423.38 frames.], batch size: 13, lr: 4.91e-04
2022-05-29 13:20:45,630 INFO [train.py:761] (5/8) Epoch 31, batch 550, loss[loss=0.143, simple_loss=0.2403, pruned_loss=0.02286, over 4976.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2971, pruned_loss=0.05687, over 905843.71 frames.], batch size: 12, lr: 4.91e-04
2022-05-29 13:21:23,537 INFO [train.py:761] (5/8) Epoch 31, batch 600, loss[loss=0.1772, simple_loss=0.2797, pruned_loss=0.03741, over 4931.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2969, pruned_loss=0.05626, over 920314.06 frames.], batch size: 13, lr: 4.90e-04
2022-05-29 13:22:01,641 INFO [train.py:761] (5/8) Epoch 31, batch 650, loss[loss=0.1976, simple_loss=0.2958, pruned_loss=0.04969, over 4792.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2979, pruned_loss=0.05674, over 930843.91 frames.], batch size: 14, lr: 4.90e-04
2022-05-29 13:22:40,166 INFO [train.py:761] (5/8) Epoch 31, batch 700, loss[loss=0.21, simple_loss=0.2999, pruned_loss=0.06009, over 4972.00 frames.], tot_loss[loss=0.205, simple_loss=0.2968, pruned_loss=0.05658, over 938774.41 frames.], batch size: 15, lr: 4.90e-04
2022-05-29 13:23:18,481 INFO [train.py:761] (5/8) Epoch 31, batch 750, loss[loss=0.1675, simple_loss=0.2568, pruned_loss=0.03911, over 4964.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2975, pruned_loss=0.05667, over 944914.59 frames.], batch size: 12, lr: 4.90e-04
2022-05-29 13:23:55,862 INFO [train.py:761] (5/8) Epoch 31, batch 800, loss[loss=0.2369, simple_loss=0.3445, pruned_loss=0.0646, over 4966.00 frames.], tot_loss[loss=0.207, simple_loss=0.299, pruned_loss=0.05753, over 950539.87 frames.], batch size: 15, lr: 4.90e-04
2022-05-29 13:24:34,058 INFO [train.py:761] (5/8) Epoch 31, batch 850, loss[loss=0.2219, simple_loss=0.3215, pruned_loss=0.06116, over 4671.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2986, pruned_loss=0.05763, over 954950.27 frames.], batch size: 13, lr: 4.90e-04
2022-05-29 13:25:13,057 INFO [train.py:761] (5/8) Epoch 31, batch 900, loss[loss=0.2197, simple_loss=0.3103, pruned_loss=0.06459, over 4764.00 frames.], tot_loss[loss=0.2081, simple_loss=0.3001, pruned_loss=0.05803, over 956442.71 frames.], batch size: 15, lr: 4.90e-04
2022-05-29 13:25:51,150 INFO [train.py:761] (5/8) Epoch 31, batch 950, loss[loss=0.1912, simple_loss=0.2705, pruned_loss=0.05592, over 4991.00 frames.], tot_loss[loss=0.2099, simple_loss=0.3018, pruned_loss=0.05898, over 959810.77 frames.], batch size: 13, lr: 4.90e-04
2022-05-29 13:26:29,217 INFO [train.py:761] (5/8) Epoch 31, batch 1000, loss[loss=0.2005, simple_loss=0.2964, pruned_loss=0.05226, over 4910.00 frames.], tot_loss[loss=0.2108, simple_loss=0.3022, pruned_loss=0.05969, over 962625.15 frames.], batch size: 13, lr: 4.90e-04
2022-05-29 13:27:07,075 INFO [train.py:761] (5/8) Epoch 31, batch 1050, loss[loss=0.1792, simple_loss=0.2732, pruned_loss=0.04256, over 4923.00 frames.], tot_loss[loss=0.2106, simple_loss=0.3024, pruned_loss=0.05936, over 964130.19 frames.], batch size: 13, lr: 4.90e-04
2022-05-29 13:27:45,170 INFO [train.py:761] (5/8) Epoch 31, batch 1100, loss[loss=0.1778, simple_loss=0.2727, pruned_loss=0.04143, over 4558.00 frames.], tot_loss[loss=0.2096, simple_loss=0.3017, pruned_loss=0.05878, over 964458.90 frames.], batch size: 10, lr: 4.90e-04
2022-05-29 13:28:23,291 INFO [train.py:761] (5/8) Epoch 31, batch 1150, loss[loss=0.2272, simple_loss=0.3218, pruned_loss=0.06627, over 4785.00 frames.], tot_loss[loss=0.2092, simple_loss=0.3014, pruned_loss=0.05848, over 965308.01 frames.], batch size: 13, lr: 4.90e-04
2022-05-29 13:29:01,277 INFO [train.py:761] (5/8) Epoch 31, batch 1200, loss[loss=0.1774, simple_loss=0.2731, pruned_loss=0.04087, over 4786.00 frames.], tot_loss[loss=0.2089, simple_loss=0.3011, pruned_loss=0.0583, over 965850.03 frames.], batch size: 13, lr: 4.90e-04
2022-05-29 13:29:38,727 INFO [train.py:761] (5/8) Epoch 31, batch 1250, loss[loss=0.2072, simple_loss=0.3116, pruned_loss=0.05137, over 4910.00 frames.], tot_loss[loss=0.2089, simple_loss=0.301, pruned_loss=0.0584, over 965517.19 frames.], batch size: 14, lr: 4.90e-04
2022-05-29 13:30:16,934 INFO [train.py:761] (5/8) Epoch 31, batch 1300, loss[loss=0.2342, simple_loss=0.3178, pruned_loss=0.07535, over 4795.00 frames.], tot_loss[loss=0.2093, simple_loss=0.3012, pruned_loss=0.05866, over 965188.90 frames.], batch size: 16, lr: 4.90e-04
2022-05-29 13:30:54,772 INFO [train.py:761] (5/8) Epoch 31, batch 1350, loss[loss=0.2172, simple_loss=0.3195, pruned_loss=0.05748, over 4877.00 frames.], tot_loss[loss=0.2083, simple_loss=0.3004, pruned_loss=0.05812, over 965473.92 frames.], batch size: 26, lr: 4.90e-04
2022-05-29 13:31:32,938 INFO [train.py:761] (5/8) Epoch 31, batch 1400, loss[loss=0.1997, simple_loss=0.2836, pruned_loss=0.05786, over 4988.00 frames.], tot_loss[loss=0.2091, simple_loss=0.3012, pruned_loss=0.05851, over 965634.02 frames.], batch size: 12, lr: 4.90e-04
2022-05-29 13:32:11,458 INFO [train.py:761] (5/8) Epoch 31, batch 1450, loss[loss=0.2465, simple_loss=0.3415, pruned_loss=0.07578, over 4864.00 frames.], tot_loss[loss=0.2096, simple_loss=0.3017, pruned_loss=0.05873, over 966310.00 frames.], batch size: 26, lr: 4.89e-04
2022-05-29 13:32:49,227 INFO [train.py:761] (5/8) Epoch 31, batch 1500, loss[loss=0.1688, simple_loss=0.2619, pruned_loss=0.0379, over 4824.00 frames.], tot_loss[loss=0.2105, simple_loss=0.3029, pruned_loss=0.05905, over 966215.76 frames.], batch size: 11, lr: 4.89e-04
2022-05-29 13:33:27,123 INFO [train.py:761] (5/8) Epoch 31, batch 1550, loss[loss=0.1891, simple_loss=0.2792, pruned_loss=0.04953, over 4727.00 frames.], tot_loss[loss=0.2097, simple_loss=0.302, pruned_loss=0.05868, over 966709.20 frames.], batch size: 14, lr: 4.89e-04
2022-05-29 13:34:05,216 INFO [train.py:761] (5/8) Epoch 31, batch 1600, loss[loss=0.1966, simple_loss=0.2815, pruned_loss=0.05585, over 4665.00 frames.], tot_loss[loss=0.2104, simple_loss=0.3024, pruned_loss=0.0592, over 966144.73 frames.], batch size: 12, lr: 4.89e-04
2022-05-29 13:34:43,282 INFO [train.py:761] (5/8) Epoch 31, batch 1650, loss[loss=0.2, simple_loss=0.2972, pruned_loss=0.05135, over 4850.00 frames.], tot_loss[loss=0.2088, simple_loss=0.3009, pruned_loss=0.05834, over 966895.66 frames.], batch size: 26, lr: 4.89e-04
2022-05-29 13:35:21,229 INFO [train.py:761] (5/8) Epoch 31, batch 1700, loss[loss=0.187, simple_loss=0.2712, pruned_loss=0.0514, over 4548.00 frames.], tot_loss[loss=0.2091, simple_loss=0.3008, pruned_loss=0.05868, over 966487.06 frames.], batch size: 10, lr: 4.89e-04
2022-05-29 13:35:59,429 INFO [train.py:761] (5/8) Epoch 31, batch 1750, loss[loss=0.1893, simple_loss=0.2663, pruned_loss=0.05612, over 4647.00 frames.], tot_loss[loss=0.2098, simple_loss=0.3011, pruned_loss=0.05921, over 966592.26 frames.], batch size: 11, lr: 4.89e-04
2022-05-29 13:36:37,623 INFO [train.py:761] (5/8) Epoch 31, batch 1800, loss[loss=0.1726, simple_loss=0.2611, pruned_loss=0.04206, over 4632.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2992, pruned_loss=0.05762, over 965816.31 frames.], batch size: 11, lr: 4.89e-04
2022-05-29 13:37:15,496 INFO [train.py:761] (5/8) Epoch 31, batch 1850, loss[loss=0.2236, simple_loss=0.3414, pruned_loss=0.05287, over 4891.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2998, pruned_loss=0.05826, over 965975.28 frames.], batch size: 17, lr: 4.89e-04
2022-05-29 13:37:53,284 INFO [train.py:761] (5/8) Epoch 31, batch 1900, loss[loss=0.1582, simple_loss=0.2453, pruned_loss=0.03555, over 4741.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2981, pruned_loss=0.05767, over 965775.39 frames.], batch size: 11, lr: 4.89e-04
2022-05-29 13:38:31,200 INFO [train.py:761] (5/8) Epoch 31, batch 1950, loss[loss=0.1828, simple_loss=0.2754, pruned_loss=0.04511, over 4727.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2994, pruned_loss=0.05773, over 965538.43 frames.], batch size: 13, lr: 4.89e-04
2022-05-29 13:39:09,114 INFO [train.py:761] (5/8) Epoch 31, batch 2000, loss[loss=0.2244, simple_loss=0.3188, pruned_loss=0.06497, over 4671.00 frames.], tot_loss[loss=0.2086, simple_loss=0.3006, pruned_loss=0.05832, over 965101.80 frames.], batch size: 13, lr: 4.89e-04
2022-05-29 13:39:46,899 INFO [train.py:761] (5/8) Epoch 31, batch 2050, loss[loss=0.2191, simple_loss=0.3181, pruned_loss=0.06005, over 4763.00 frames.], tot_loss[loss=0.2084, simple_loss=0.3001, pruned_loss=0.05832, over 965713.27 frames.], batch size: 15, lr: 4.89e-04
2022-05-29 13:40:24,512 INFO [train.py:761] (5/8) Epoch 31, batch 2100, loss[loss=0.2456, simple_loss=0.3553, pruned_loss=0.06799, over 4783.00 frames.], tot_loss[loss=0.2099, simple_loss=0.3016, pruned_loss=0.05915, over 966278.00 frames.], batch size: 16, lr: 4.89e-04
2022-05-29 13:41:02,653 INFO [train.py:761] (5/8) Epoch 31, batch 2150, loss[loss=0.2052, simple_loss=0.2851, pruned_loss=0.0626, over 4737.00 frames.], tot_loss[loss=0.2105, simple_loss=0.3022, pruned_loss=0.05938, over 964473.27 frames.], batch size: 12, lr: 4.89e-04
2022-05-29 13:41:40,064 INFO [train.py:761] (5/8) Epoch 31, batch 2200, loss[loss=0.2342, simple_loss=0.3259, pruned_loss=0.07128, over 4779.00 frames.], tot_loss[loss=0.2104, simple_loss=0.3017, pruned_loss=0.05958, over 964472.88 frames.], batch size: 15, lr: 4.89e-04
2022-05-29 13:42:18,258 INFO [train.py:761] (5/8) Epoch 31, batch 2250, loss[loss=0.2163, simple_loss=0.295, pruned_loss=0.06876, over 4641.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3012, pruned_loss=0.05945, over 965292.45 frames.], batch size: 11, lr: 4.88e-04
2022-05-29 13:42:56,011 INFO [train.py:761] (5/8) Epoch 31, batch 2300, loss[loss=0.2174, simple_loss=0.3052, pruned_loss=0.06476, over 4911.00 frames.], tot_loss[loss=0.209, simple_loss=0.3006, pruned_loss=0.05872, over 965997.58 frames.], batch size: 14, lr: 4.88e-04
2022-05-29 13:43:33,788 INFO [train.py:761] (5/8) Epoch 31, batch 2350, loss[loss=0.2023, simple_loss=0.2766, pruned_loss=0.06405, over 4736.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2996, pruned_loss=0.05872, over 965692.44 frames.], batch size: 11, lr: 4.88e-04
2022-05-29 13:44:11,908 INFO [train.py:761] (5/8) Epoch 31, batch 2400, loss[loss=0.253, simple_loss=0.3283, pruned_loss=0.08884, over 4914.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2999, pruned_loss=0.05927, over 967081.11 frames.], batch size: 14, lr: 4.88e-04
2022-05-29 13:44:49,989 INFO [train.py:761] (5/8) Epoch 31, batch 2450, loss[loss=0.1798, simple_loss=0.284, pruned_loss=0.03783, over 4795.00 frames.], tot_loss[loss=0.209, simple_loss=0.3003, pruned_loss=0.05885, over 967265.60 frames.], batch size: 13, lr: 4.88e-04
2022-05-29 13:45:27,700 INFO [train.py:761] (5/8) Epoch 31, batch 2500, loss[loss=0.1857, simple_loss=0.2656, pruned_loss=0.05287, over 4836.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2995, pruned_loss=0.05885, over 965991.70 frames.], batch size: 11, lr: 4.88e-04
2022-05-29 13:46:05,758 INFO [train.py:761] (5/8) Epoch 31, batch 2550, loss[loss=0.2359, simple_loss=0.3482, pruned_loss=0.06174, over 4965.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3013, pruned_loss=0.05945, over 966219.19 frames.], batch size: 15, lr: 4.88e-04
2022-05-29 13:46:43,987 INFO [train.py:761] (5/8) Epoch 31, batch 2600, loss[loss=0.1961, simple_loss=0.2664, pruned_loss=0.0629, over 4726.00 frames.], tot_loss[loss=0.2106, simple_loss=0.3017, pruned_loss=0.05969, over 966263.30 frames.], batch size: 11, lr: 4.88e-04
2022-05-29 13:47:21,976 INFO [train.py:761] (5/8) Epoch 31, batch 2650, loss[loss=0.1742, simple_loss=0.2807, pruned_loss=0.03388, over 4868.00 frames.], tot_loss[loss=0.209, simple_loss=0.3005, pruned_loss=0.05872, over 965940.75 frames.], batch size: 15, lr: 4.88e-04
2022-05-29 13:47:59,320 INFO [train.py:761] (5/8) Epoch 31, batch 2700, loss[loss=0.1562, simple_loss=0.2366, pruned_loss=0.03784, over 4823.00 frames.], tot_loss[loss=0.2087, simple_loss=0.3007, pruned_loss=0.05837, over 966206.33 frames.], batch size: 11, lr: 4.88e-04
2022-05-29 13:48:37,161 INFO [train.py:761] (5/8) Epoch 31, batch 2750, loss[loss=0.2043, simple_loss=0.2822, pruned_loss=0.06321, over 4644.00 frames.], tot_loss[loss=0.2078, simple_loss=0.3002, pruned_loss=0.05766, over 966899.82 frames.], batch size: 11, lr: 4.88e-04
2022-05-29 13:49:15,107 INFO [train.py:761] (5/8) Epoch 31, batch 2800, loss[loss=0.261, simple_loss=0.361, pruned_loss=0.08051, over 4901.00 frames.], tot_loss[loss=0.2081, simple_loss=0.3003, pruned_loss=0.05788, over 968024.32 frames.], batch size: 47, lr: 4.88e-04
2022-05-29 13:49:53,206 INFO [train.py:761] (5/8) Epoch 31, batch 2850, loss[loss=0.1894, simple_loss=0.2853, pruned_loss=0.04677, over 4778.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2983, pruned_loss=0.05743, over 968364.14 frames.], batch size: 15, lr: 4.88e-04
2022-05-29 13:50:30,746 INFO [train.py:761] (5/8) Epoch 31, batch 2900, loss[loss=0.2184, simple_loss=0.3189, pruned_loss=0.05899, over 4886.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2988, pruned_loss=0.05731, over 968603.86 frames.], batch size: 15, lr: 4.88e-04
2022-05-29 13:51:08,885 INFO [train.py:761] (5/8) Epoch 31, batch 2950, loss[loss=0.221, simple_loss=0.3063, pruned_loss=0.0678, over 4855.00 frames.], tot_loss[loss=0.207, simple_loss=0.299, pruned_loss=0.0575, over 968745.84 frames.], batch size: 13, lr: 4.88e-04
2022-05-29 13:51:46,947 INFO [train.py:761] (5/8) Epoch 31, batch 3000, loss[loss=0.1737, simple_loss=0.2625, pruned_loss=0.04244, over 4961.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2984, pruned_loss=0.05754, over 967454.26 frames.], batch size: 11, lr: 4.88e-04
2022-05-29 13:51:46,947 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 13:51:56,810 INFO [train.py:790] (5/8) Epoch 31, validation: loss=0.2033, simple_loss=0.3033, pruned_loss=0.05164, over 944034.00 frames.
2022-05-29 13:52:34,846 INFO [train.py:761] (5/8) Epoch 31, batch 3050, loss[loss=0.1909, simple_loss=0.2782, pruned_loss=0.05182, over 4782.00 frames.], tot_loss[loss=0.2064, simple_loss=0.298, pruned_loss=0.05737, over 967155.06 frames.], batch size: 13, lr: 4.88e-04
2022-05-29 13:53:11,993 INFO [train.py:761] (5/8) Epoch 31, batch 3100, loss[loss=0.1662, simple_loss=0.2543, pruned_loss=0.03905, over 4824.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2985, pruned_loss=0.05813, over 967196.37 frames.], batch size: 11, lr: 4.87e-04
2022-05-29 13:53:49,998 INFO [train.py:761] (5/8) Epoch 31, batch 3150, loss[loss=0.2353, simple_loss=0.3282, pruned_loss=0.07113, over 4886.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2986, pruned_loss=0.05886, over 966587.28 frames.], batch size: 17, lr: 4.87e-04
2022-05-29 13:54:27,861 INFO [train.py:761] (5/8) Epoch 31, batch 3200, loss[loss=0.1904, simple_loss=0.2933, pruned_loss=0.04372, over 4890.00 frames.], tot_loss[loss=0.2109, simple_loss=0.3004, pruned_loss=0.06071, over 966763.23 frames.], batch size: 26, lr: 4.87e-04
2022-05-29 13:55:05,937 INFO [train.py:761] (5/8) Epoch 31, batch 3250, loss[loss=0.198, simple_loss=0.2731, pruned_loss=0.06142, over 4986.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3016, pruned_loss=0.06274, over 966866.02 frames.], batch size: 12, lr: 4.87e-04
2022-05-29 13:55:44,092 INFO [train.py:761] (5/8) Epoch 31, batch 3300, loss[loss=0.2433, simple_loss=0.3304, pruned_loss=0.07809, over 4960.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3028, pruned_loss=0.06393, over 965531.10 frames.], batch size: 21, lr: 4.87e-04
2022-05-29 13:56:22,000 INFO [train.py:761] (5/8) Epoch 31, batch 3350, loss[loss=0.2399, simple_loss=0.3348, pruned_loss=0.07255, over 4906.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3029, pruned_loss=0.06467, over 965310.68 frames.], batch size: 17, lr: 4.87e-04
2022-05-29 13:57:00,177 INFO [train.py:761] (5/8) Epoch 31, batch 3400, loss[loss=0.2046, simple_loss=0.2963, pruned_loss=0.05643, over 4729.00 frames.], tot_loss[loss=0.2175, simple_loss=0.3028, pruned_loss=0.06611, over 965571.57 frames.], batch size: 13, lr: 4.87e-04
2022-05-29 13:57:38,799 INFO [train.py:761] (5/8) Epoch 31, batch 3450, loss[loss=0.2039, simple_loss=0.3019, pruned_loss=0.05291, over 4731.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3043, pruned_loss=0.06734, over 964903.28 frames.], batch size: 14, lr: 4.87e-04
2022-05-29 13:58:16,744 INFO [train.py:761] (5/8) Epoch 31, batch 3500, loss[loss=0.2512, simple_loss=0.3329, pruned_loss=0.08481, over 4973.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3046, pruned_loss=0.0684, over 964410.98 frames.], batch size: 14, lr: 4.87e-04
2022-05-29 13:58:55,368 INFO [train.py:761] (5/8) Epoch 31, batch 3550, loss[loss=0.2279, simple_loss=0.2955, pruned_loss=0.08011, over 4793.00 frames.], tot_loss[loss=0.2236, simple_loss=0.306, pruned_loss=0.07064, over 964575.67 frames.], batch size: 12, lr: 4.87e-04
2022-05-29 13:59:33,862 INFO [train.py:761] (5/8) Epoch 31, batch 3600, loss[loss=0.2385, simple_loss=0.3169, pruned_loss=0.08012, over 4795.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3049, pruned_loss=0.07018, over 964329.28 frames.], batch size: 14, lr: 4.87e-04
2022-05-29 14:00:12,143 INFO [train.py:761] (5/8) Epoch 31, batch 3650, loss[loss=0.1693, simple_loss=0.2457, pruned_loss=0.04643, over 4648.00 frames.], tot_loss[loss=0.222, simple_loss=0.304, pruned_loss=0.07004, over 963620.19 frames.], batch size: 11, lr: 4.87e-04
2022-05-29 14:00:50,201 INFO [train.py:761] (5/8) Epoch 31, batch 3700, loss[loss=0.2227, simple_loss=0.2984, pruned_loss=0.07345, over 4672.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3049, pruned_loss=0.07062, over 964498.32 frames.], batch size: 12, lr: 4.87e-04
2022-05-29 14:01:28,979 INFO [train.py:761] (5/8) Epoch 31, batch 3750, loss[loss=0.224, simple_loss=0.3065, pruned_loss=0.0708, over 4801.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3064, pruned_loss=0.07098, over 964664.85 frames.], batch size: 12, lr: 4.87e-04
2022-05-29 14:02:07,543 INFO [train.py:761] (5/8) Epoch 31, batch 3800, loss[loss=0.2348, simple_loss=0.3128, pruned_loss=0.07844, over 4887.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3058, pruned_loss=0.0707, over 964199.87 frames.], batch size: 17, lr: 4.87e-04
2022-05-29 14:02:45,461 INFO [train.py:761] (5/8) Epoch 31, batch 3850, loss[loss=0.2549, simple_loss=0.335, pruned_loss=0.08738, over 4713.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3057, pruned_loss=0.07133, over 963610.72 frames.], batch size: 14, lr: 4.87e-04
2022-05-29 14:03:24,013 INFO [train.py:761] (5/8) Epoch 31, batch 3900, loss[loss=0.18, simple_loss=0.2554, pruned_loss=0.05224, over 4996.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3075, pruned_loss=0.07228, over 964469.12 frames.], batch size: 13, lr: 4.87e-04
2022-05-29 14:04:02,618 INFO [train.py:761] (5/8) Epoch 31, batch 3950, loss[loss=0.2184, simple_loss=0.3185, pruned_loss=0.05916, over 4910.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3076, pruned_loss=0.07179, over 965865.79 frames.], batch size: 14, lr: 4.86e-04
2022-05-29 14:04:41,240 INFO [train.py:761] (5/8) Epoch 31, batch 4000, loss[loss=0.2801, simple_loss=0.3593, pruned_loss=0.1005, over 4966.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3074, pruned_loss=0.07236, over 967148.62 frames.], batch size: 27, lr: 4.86e-04
2022-05-29 14:05:19,245 INFO [train.py:761] (5/8) Epoch 31, batch 4050, loss[loss=0.2064, simple_loss=0.3047, pruned_loss=0.05409, over 4878.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3071, pruned_loss=0.07236, over 967407.55 frames.], batch size: 18, lr: 4.86e-04
2022-05-29 14:05:57,337 INFO [train.py:761] (5/8) Epoch 31, batch 4100, loss[loss=0.2318, simple_loss=0.3184, pruned_loss=0.0726, over 4809.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3083, pruned_loss=0.07332, over 966830.31 frames.], batch size: 12, lr: 4.86e-04
2022-05-29 14:06:35,370 INFO [train.py:761] (5/8) Epoch 31, batch 4150, loss[loss=0.2586, simple_loss=0.347, pruned_loss=0.08509, over 4969.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3077, pruned_loss=0.07267, over 966447.61 frames.], batch size: 14, lr: 4.86e-04
2022-05-29 14:07:13,710 INFO [train.py:761] (5/8) Epoch 31, batch 4200, loss[loss=0.2174, simple_loss=0.298, pruned_loss=0.06836, over 4783.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3079, pruned_loss=0.0734, over 966540.78 frames.], batch size: 13, lr: 4.86e-04
2022-05-29 14:07:51,427 INFO [train.py:761] (5/8) Epoch 31, batch 4250, loss[loss=0.219, simple_loss=0.2858, pruned_loss=0.07608, over 4804.00 frames.], tot_loss[loss=0.228, simple_loss=0.3082, pruned_loss=0.07393, over 966892.97 frames.], batch size: 12, lr: 4.86e-04
2022-05-29 14:08:29,176 INFO [train.py:761] (5/8) Epoch 31, batch 4300, loss[loss=0.2398, simple_loss=0.3228, pruned_loss=0.07845, over 4724.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3087, pruned_loss=0.07345, over 966640.59 frames.], batch size: 13, lr: 4.86e-04
2022-05-29 14:09:07,675 INFO [train.py:761] (5/8) Epoch 31, batch 4350, loss[loss=0.1903, simple_loss=0.2843, pruned_loss=0.04811, over 4717.00 frames.], tot_loss[loss=0.2264, simple_loss=0.307, pruned_loss=0.07293, over 966710.70 frames.], batch size: 14, lr: 4.86e-04
2022-05-29 14:09:45,744 INFO [train.py:761] (5/8) Epoch 31, batch 4400, loss[loss=0.2854, simple_loss=0.36, pruned_loss=0.1054, over 4721.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3081, pruned_loss=0.07373, over 965295.55 frames.], batch size: 14, lr: 4.86e-04
2022-05-29 14:10:24,113 INFO [train.py:761] (5/8) Epoch 31, batch 4450, loss[loss=0.2584, simple_loss=0.327, pruned_loss=0.09484, over 4772.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3074, pruned_loss=0.07286, over 965664.67 frames.], batch size: 15, lr: 4.86e-04
2022-05-29 14:11:02,626 INFO [train.py:761] (5/8) Epoch 31, batch 4500, loss[loss=0.2189, simple_loss=0.3038, pruned_loss=0.06701, over 4774.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3075, pruned_loss=0.07252, over 965411.33 frames.], batch size: 15, lr: 4.86e-04
2022-05-29 14:11:41,362 INFO [train.py:761] (5/8) Epoch 31, batch 4550, loss[loss=0.2152, simple_loss=0.2979, pruned_loss=0.06628, over 4790.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3069, pruned_loss=0.07221, over 966852.17 frames.], batch size: 13, lr: 4.86e-04
2022-05-29 14:12:19,328 INFO [train.py:761] (5/8) Epoch 31, batch 4600, loss[loss=0.2564, simple_loss=0.3321, pruned_loss=0.09031, over 4951.00 frames.], tot_loss[loss=0.225, simple_loss=0.3062, pruned_loss=0.07194, over 967345.76 frames.], batch size: 16, lr: 4.86e-04
2022-05-29 14:12:58,079 INFO [train.py:761] (5/8) Epoch 31, batch 4650, loss[loss=0.2492, simple_loss=0.3119, pruned_loss=0.09326, over 4736.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3064, pruned_loss=0.07202, over 967062.55 frames.], batch size: 12, lr: 4.86e-04
2022-05-29 14:13:36,660 INFO [train.py:761] (5/8) Epoch 31, batch 4700, loss[loss=0.27, simple_loss=0.3484, pruned_loss=0.09582, over 4881.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3061, pruned_loss=0.0722, over 967961.08 frames.], batch size: 17, lr: 4.86e-04
2022-05-29 14:14:15,101 INFO [train.py:761] (5/8) Epoch 31, batch 4750, loss[loss=0.1827, simple_loss=0.2591, pruned_loss=0.05315, over 4739.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3056, pruned_loss=0.07209, over 968927.17 frames.], batch size: 11, lr: 4.86e-04
2022-05-29 14:14:53,907 INFO [train.py:761] (5/8) Epoch 31, batch 4800, loss[loss=0.1784, simple_loss=0.2569, pruned_loss=0.04995, over 4663.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3065, pruned_loss=0.07281, over 967672.22 frames.], batch size: 12, lr: 4.85e-04
2022-05-29 14:15:32,200 INFO [train.py:761] (5/8) Epoch 31, batch 4850, loss[loss=0.2379, simple_loss=0.3293, pruned_loss=0.07323, over 4975.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3066, pruned_loss=0.07246, over 967036.06 frames.], batch size: 14, lr: 4.85e-04
2022-05-29 14:16:09,803 INFO [train.py:761] (5/8) Epoch 31, batch 4900, loss[loss=0.2143, simple_loss=0.2991, pruned_loss=0.06475, over 4914.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3065, pruned_loss=0.07254, over 967215.43 frames.], batch size: 14, lr: 4.85e-04
2022-05-29 14:16:49,001 INFO [train.py:761] (5/8) Epoch 31, batch 4950, loss[loss=0.2465, simple_loss=0.3275, pruned_loss=0.08272, over 4915.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3077, pruned_loss=0.07299, over 968704.11 frames.], batch size: 18, lr: 4.85e-04
2022-05-29 14:17:27,372 INFO [train.py:761] (5/8) Epoch 31, batch 5000, loss[loss=0.2199, simple_loss=0.307, pruned_loss=0.06638, over 4958.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3083, pruned_loss=0.07299, over 968572.72 frames.], batch size: 26, lr: 4.85e-04
2022-05-29 14:18:06,184 INFO [train.py:761] (5/8) Epoch 31, batch 5050, loss[loss=0.3162, simple_loss=0.3872, pruned_loss=0.1226, over 4919.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3094, pruned_loss=0.0736, over 968055.85 frames.], batch size: 48, lr: 4.85e-04
2022-05-29 14:18:44,469 INFO [train.py:761] (5/8) Epoch 31, batch 5100, loss[loss=0.2455, simple_loss=0.3215, pruned_loss=0.08478, over 4954.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3076, pruned_loss=0.07299, over 967575.29 frames.], batch size: 21, lr: 4.85e-04
2022-05-29 14:19:23,471 INFO [train.py:761] (5/8) Epoch 31, batch 5150, loss[loss=0.1823, simple_loss=0.2662, pruned_loss=0.04926, over 4981.00 frames.], tot_loss[loss=0.2274, simple_loss=0.308, pruned_loss=0.07343, over 966863.90 frames.], batch size: 12, lr: 4.85e-04
2022-05-29 14:20:01,223 INFO [train.py:761] (5/8) Epoch 31, batch 5200, loss[loss=0.314, simple_loss=0.3835, pruned_loss=0.1222, over 4991.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3077, pruned_loss=0.07274, over 967397.57 frames.], batch size: 21, lr: 4.85e-04
2022-05-29 14:20:40,121 INFO [train.py:761] (5/8) Epoch 31, batch 5250, loss[loss=0.2271, simple_loss=0.3027, pruned_loss=0.07576, over 4914.00 frames.], tot_loss[loss=0.227, simple_loss=0.3083, pruned_loss=0.07284, over 966581.64 frames.], batch size: 14, lr: 4.85e-04
2022-05-29 14:21:18,243 INFO [train.py:761] (5/8) Epoch 31, batch 5300, loss[loss=0.1988, simple_loss=0.2937, pruned_loss=0.05201, over 4879.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3071, pruned_loss=0.07213, over 966012.37 frames.], batch size: 15, lr: 4.85e-04
2022-05-29 14:21:56,443 INFO [train.py:761] (5/8) Epoch 31, batch 5350, loss[loss=0.1903, simple_loss=0.2793, pruned_loss=0.05062, over 4908.00 frames.], tot_loss[loss=0.2275, simple_loss=0.3092, pruned_loss=0.07292, over 967100.51 frames.], batch size: 14, lr: 4.85e-04
2022-05-29 14:22:34,749 INFO [train.py:761] (5/8) Epoch 31, batch 5400, loss[loss=0.2029, simple_loss=0.2866, pruned_loss=0.05958, over 4972.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3082, pruned_loss=0.07243, over 967080.71 frames.], batch size: 14, lr: 4.85e-04
2022-05-29 14:23:12,667 INFO [train.py:761] (5/8) Epoch 31, batch 5450, loss[loss=0.2356, simple_loss=0.3278, pruned_loss=0.07175, over 4816.00 frames.], tot_loss[loss=0.225, simple_loss=0.3073, pruned_loss=0.07137, over 967129.74 frames.], batch size: 20, lr: 4.85e-04
2022-05-29 14:23:50,220 INFO [train.py:761] (5/8) Epoch 31, batch 5500, loss[loss=0.2304, simple_loss=0.3204, pruned_loss=0.0702, over 4901.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3072, pruned_loss=0.07171, over 966479.81 frames.], batch size: 26, lr: 4.85e-04
2022-05-29 14:24:28,297 INFO [train.py:761] (5/8) Epoch 31, batch 5550, loss[loss=0.2447, simple_loss=0.3168, pruned_loss=0.08629, over 4808.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3062, pruned_loss=0.07119, over 966475.57 frames.], batch size: 16, lr: 4.85e-04
2022-05-29 14:25:06,331 INFO [train.py:761] (5/8) Epoch 31, batch 5600, loss[loss=0.203, simple_loss=0.2678, pruned_loss=0.06907, over 4662.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3059, pruned_loss=0.07086, over 966979.01 frames.], batch size: 12, lr: 4.85e-04
2022-05-29 14:25:48,089 INFO [train.py:761] (5/8) Epoch 31, batch 5650, loss[loss=0.2153, simple_loss=0.2927, pruned_loss=0.06897, over 4639.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3061, pruned_loss=0.07185, over 967526.05 frames.], batch size: 11, lr: 4.84e-04
2022-05-29 14:26:26,243 INFO [train.py:761] (5/8) Epoch 31, batch 5700, loss[loss=0.1933, simple_loss=0.2683, pruned_loss=0.05912, over 4805.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3073, pruned_loss=0.07298, over 968278.20 frames.], batch size: 12, lr: 4.84e-04
2022-05-29 14:27:04,461 INFO [train.py:761] (5/8) Epoch 31, batch 5750, loss[loss=0.1903, simple_loss=0.2595, pruned_loss=0.06057, over 4895.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3058, pruned_loss=0.07234, over 966883.85 frames.], batch size: 12, lr: 4.84e-04
2022-05-29 14:27:42,471 INFO [train.py:761] (5/8) Epoch 31, batch 5800, loss[loss=0.2001, simple_loss=0.2803, pruned_loss=0.05995, over 4988.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3052, pruned_loss=0.07206, over 966362.99 frames.], batch size: 11, lr: 4.84e-04
2022-05-29 14:28:20,986 INFO [train.py:761] (5/8) Epoch 31, batch 5850, loss[loss=0.2379, simple_loss=0.3226, pruned_loss=0.07659, over 4775.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3057, pruned_loss=0.0723, over 967424.24 frames.], batch size: 18, lr: 4.84e-04
2022-05-29 14:28:58,603 INFO [train.py:761] (5/8) Epoch 31, batch 5900, loss[loss=0.2376, simple_loss=0.3339, pruned_loss=0.07067, over 4926.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3051, pruned_loss=0.07173, over 967499.63 frames.], batch size: 13, lr: 4.84e-04
2022-05-29 14:29:36,699 INFO [train.py:761] (5/8) Epoch 31, batch 5950, loss[loss=0.2515, simple_loss=0.3249, pruned_loss=0.08908, over 4985.00 frames.], tot_loss[loss=0.2262, simple_loss=0.307, pruned_loss=0.0727, over 967932.36 frames.], batch size: 14, lr: 4.84e-04
2022-05-29 14:30:14,963 INFO [train.py:761] (5/8) Epoch 31, batch 6000, loss[loss=0.2182, simple_loss=0.3132, pruned_loss=0.06161, over 4855.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3093, pruned_loss=0.07402, over 968731.25 frames.], batch size: 14, lr: 4.84e-04
2022-05-29 14:30:14,963 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 14:30:24,867 INFO [train.py:790] (5/8) Epoch 31, validation: loss=0.1974, simple_loss=0.3009, pruned_loss=0.04693, over 944034.00 frames.
2022-05-29 14:31:02,972 INFO [train.py:761] (5/8) Epoch 31, batch 6050, loss[loss=0.2554, simple_loss=0.3391, pruned_loss=0.08585, over 4719.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3092, pruned_loss=0.07359, over 967977.26 frames.], batch size: 14, lr: 4.84e-04
2022-05-29 14:31:40,811 INFO [train.py:761] (5/8) Epoch 31, batch 6100, loss[loss=0.2182, simple_loss=0.3102, pruned_loss=0.06314, over 4882.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3088, pruned_loss=0.07289, over 968522.65 frames.], batch size: 15, lr: 4.84e-04
2022-05-29 14:32:19,563 INFO [train.py:761] (5/8) Epoch 31, batch 6150, loss[loss=0.199, simple_loss=0.2904, pruned_loss=0.05382, over 4929.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3077, pruned_loss=0.07199, over 968855.52 frames.], batch size: 13, lr: 4.84e-04
2022-05-29 14:32:57,399 INFO [train.py:761] (5/8) Epoch 31, batch 6200, loss[loss=0.2023, simple_loss=0.2998, pruned_loss=0.05239, over 4863.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3073, pruned_loss=0.07122, over 967804.54 frames.], batch size: 17, lr: 4.84e-04
2022-05-29 14:33:35,973 INFO [train.py:761] (5/8) Epoch 31, batch 6250, loss[loss=0.2128, simple_loss=0.2947, pruned_loss=0.06541, over 4724.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3069, pruned_loss=0.07213, over 967697.13 frames.], batch size: 13, lr: 4.84e-04
2022-05-29 14:34:13,952 INFO [train.py:761] (5/8) Epoch 31, batch 6300, loss[loss=0.2486, simple_loss=0.3403, pruned_loss=0.07844, over 4921.00 frames.], tot_loss[loss=0.2245, simple_loss=0.306, pruned_loss=0.07152, over 967055.46 frames.], batch size: 26, lr: 4.84e-04
2022-05-29 14:34:52,275 INFO [train.py:761] (5/8) Epoch 31, batch 6350, loss[loss=0.2139, simple_loss=0.3012, pruned_loss=0.06335, over 4718.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3062, pruned_loss=0.07217, over 966257.20 frames.], batch size: 14, lr: 4.84e-04
2022-05-29 14:35:30,255 INFO [train.py:761] (5/8) Epoch 31, batch 6400, loss[loss=0.2404, simple_loss=0.3148, pruned_loss=0.08303, over 4892.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3054, pruned_loss=0.0722, over 966865.37 frames.], batch size: 15, lr: 4.84e-04
2022-05-29 14:36:08,494 INFO [train.py:761] (5/8) Epoch 31, batch 6450, loss[loss=0.2096, simple_loss=0.3112, pruned_loss=0.05399, over 4926.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3059, pruned_loss=0.07247, over 967781.67 frames.], batch size: 21, lr: 4.84e-04
2022-05-29 14:36:46,687 INFO [train.py:761] (5/8) Epoch 31, batch 6500, loss[loss=0.2052, simple_loss=0.2799, pruned_loss=0.06524, over 4813.00 frames.], tot_loss[loss=0.2251, simple_loss=0.306, pruned_loss=0.07212, over 968025.55 frames.], batch size: 12, lr: 4.84e-04
2022-05-29 14:37:25,194 INFO [train.py:761] (5/8) Epoch 31, batch 6550, loss[loss=0.2525, simple_loss=0.3356, pruned_loss=0.08473, over 4853.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3045, pruned_loss=0.0715, over 967694.84 frames.], batch size: 20, lr: 4.83e-04
2022-05-29 14:38:03,530 INFO [train.py:761] (5/8) Epoch 31, batch 6600, loss[loss=0.2107, simple_loss=0.2909, pruned_loss=0.06525, over 4910.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3037, pruned_loss=0.07066, over 967766.57 frames.], batch size: 14, lr: 4.83e-04
2022-05-29 14:38:42,127 INFO [train.py:761] (5/8) Epoch 31, batch 6650, loss[loss=0.2, simple_loss=0.2858, pruned_loss=0.05707, over 4820.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3034, pruned_loss=0.07047, over 968044.93 frames.], batch size: 20, lr: 4.83e-04
2022-05-29 14:39:20,281 INFO [train.py:761] (5/8) Epoch 31, batch 6700, loss[loss=0.2356, simple_loss=0.3159, pruned_loss=0.07768, over 4963.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3032, pruned_loss=0.0705, over 967444.92 frames.], batch size: 16, lr: 4.83e-04
2022-05-29 14:40:15,684 INFO [train.py:761] (5/8) Epoch 32, batch 0, loss[loss=0.1915, simple_loss=0.3015, pruned_loss=0.04079, over 4879.00 frames.], tot_loss[loss=0.1915, simple_loss=0.3015, pruned_loss=0.04079, over 4879.00 frames.], batch size: 17, lr: 4.83e-04
2022-05-29 14:40:53,151 INFO [train.py:761] (5/8) Epoch 32, batch 50, loss[loss=0.1919, simple_loss=0.2694, pruned_loss=0.05717, over 4963.00 frames.], tot_loss[loss=0.2141, simple_loss=0.3043, pruned_loss=0.06197, over 217854.88 frames.], batch size: 12, lr: 4.83e-04
2022-05-29 14:41:31,124 INFO [train.py:761] (5/8) Epoch 32, batch 100, loss[loss=0.2775, simple_loss=0.3483, pruned_loss=0.1033, over 4776.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2973, pruned_loss=0.05788, over 383923.80 frames.], batch size: 15, lr: 4.83e-04
2022-05-29 14:42:08,505 INFO [train.py:761] (5/8) Epoch 32, batch 150, loss[loss=0.195, simple_loss=0.2944, pruned_loss=0.0478, over 4727.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2977, pruned_loss=0.05698, over 512509.55 frames.], batch size: 13, lr: 4.83e-04
2022-05-29 14:42:47,093 INFO [train.py:761] (5/8) Epoch 32, batch 200, loss[loss=0.2299, simple_loss=0.3267, pruned_loss=0.06653, over 4847.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2979, pruned_loss=0.0575, over 613873.81 frames.], batch size: 13, lr: 4.83e-04
2022-05-29 14:43:25,384 INFO [train.py:761] (5/8) Epoch 32, batch 250, loss[loss=0.1706, simple_loss=0.2536, pruned_loss=0.04377, over 4991.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2965, pruned_loss=0.0566, over 691103.50 frames.], batch size: 12, lr: 4.83e-04
2022-05-29 14:44:03,532 INFO [train.py:761] (5/8) Epoch 32, batch 300, loss[loss=0.1761, simple_loss=0.2689, pruned_loss=0.04164, over 4731.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2971, pruned_loss=0.05677, over 752358.28 frames.], batch size: 11, lr: 4.83e-04
2022-05-29 14:44:41,424 INFO [train.py:761] (5/8) Epoch 32, batch 350, loss[loss=0.2026, simple_loss=0.2918, pruned_loss=0.05674, over 4983.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2966, pruned_loss=0.05648, over 799885.27 frames.], batch size: 15, lr: 4.83e-04
2022-05-29 14:45:19,787 INFO [train.py:761] (5/8) Epoch 32, batch 400, loss[loss=0.1754, simple_loss=0.2756, pruned_loss=0.03762, over 4850.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2966, pruned_loss=0.05624, over 836416.77 frames.], batch size: 13, lr: 4.83e-04
2022-05-29 14:45:57,395 INFO [train.py:761] (5/8) Epoch 32, batch 450, loss[loss=0.2198, simple_loss=0.311, pruned_loss=0.06435, over 4888.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2967, pruned_loss=0.056, over 865123.76 frames.], batch size: 17, lr: 4.83e-04
2022-05-29 14:46:35,516 INFO [train.py:761] (5/8) Epoch 32, batch 500, loss[loss=0.1666, simple_loss=0.2444, pruned_loss=0.04441, over 4638.00 frames.], tot_loss[loss=0.2034, simple_loss=0.296, pruned_loss=0.05539, over 887702.76 frames.], batch size: 11, lr: 4.83e-04
2022-05-29 14:47:13,259 INFO [train.py:761] (5/8) Epoch 32, batch 550, loss[loss=0.1965, simple_loss=0.2937, pruned_loss=0.04962, over 4846.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2953, pruned_loss=0.05525, over 905010.38 frames.], batch size: 13, lr: 4.83e-04
2022-05-29 14:47:51,637 INFO [train.py:761] (5/8) Epoch 32, batch 600, loss[loss=0.2776, simple_loss=0.3603, pruned_loss=0.09749, over 4765.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2948, pruned_loss=0.05497, over 918462.06 frames.], batch size: 15, lr: 4.83e-04
2022-05-29 14:48:29,641 INFO [train.py:761] (5/8) Epoch 32, batch 650, loss[loss=0.2052, simple_loss=0.3075, pruned_loss=0.05144, over 4970.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2948, pruned_loss=0.05565, over 928325.94 frames.], batch size: 15, lr: 4.82e-04
2022-05-29 14:49:07,789 INFO [train.py:761] (5/8) Epoch 32, batch 700, loss[loss=0.2236, simple_loss=0.3264, pruned_loss=0.06034, over 4785.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2966, pruned_loss=0.05613, over 936731.05 frames.], batch size: 13, lr: 4.82e-04
2022-05-29 14:49:46,222 INFO [train.py:761] (5/8) Epoch 32, batch 750, loss[loss=0.2263, simple_loss=0.3166, pruned_loss=0.06796, over 4890.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2996, pruned_loss=0.0578, over 943410.49 frames.], batch size: 15, lr: 4.82e-04
2022-05-29 14:50:24,417 INFO [train.py:761] (5/8) Epoch 32, batch 800, loss[loss=0.2487, simple_loss=0.3403, pruned_loss=0.07849, over 4942.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2994, pruned_loss=0.05773, over 949078.28 frames.], batch size: 49, lr: 4.82e-04
2022-05-29 14:51:02,302 INFO [train.py:761] (5/8) Epoch 32, batch 850, loss[loss=0.2141, simple_loss=0.3185, pruned_loss=0.05485, over 4965.00 frames.], tot_loss[loss=0.2082, simple_loss=0.3002, pruned_loss=0.05804, over 953701.26 frames.], batch size: 14, lr: 4.82e-04
2022-05-29 14:51:39,677 INFO [train.py:761] (5/8) Epoch 32, batch 900, loss[loss=0.2046, simple_loss=0.3009, pruned_loss=0.05419, over 4786.00 frames.], tot_loss[loss=0.208, simple_loss=0.2997, pruned_loss=0.05812, over 955714.96 frames.], batch size: 13, lr: 4.82e-04
2022-05-29 14:52:17,838 INFO [train.py:761] (5/8) Epoch 32, batch 950, loss[loss=0.1747, simple_loss=0.2552, pruned_loss=0.04712, over 4713.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2979, pruned_loss=0.05762, over 957671.00 frames.], batch size: 11, lr: 4.82e-04
2022-05-29 14:52:56,176 INFO [train.py:761] (5/8) Epoch 32, batch 1000, loss[loss=0.178, simple_loss=0.2523, pruned_loss=0.05181, over 4737.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2994, pruned_loss=0.05857, over 958889.23 frames.], batch size: 11, lr: 4.82e-04
2022-05-29 14:53:33,829 INFO [train.py:761] (5/8) Epoch 32, batch 1050, loss[loss=0.2036, simple_loss=0.2906, pruned_loss=0.05825, over 4675.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2993, pruned_loss=0.05818, over 961329.20 frames.], batch size: 13, lr: 4.82e-04
2022-05-29 14:54:11,831 INFO [train.py:761] (5/8) Epoch 32, batch 1100, loss[loss=0.2391, simple_loss=0.3307, pruned_loss=0.07375, over 4959.00 frames.], tot_loss[loss=0.2086, simple_loss=0.3001, pruned_loss=0.05857, over 962484.34 frames.], batch size: 16, lr: 4.82e-04
2022-05-29 14:54:49,735 INFO [train.py:761] (5/8) Epoch 32, batch 1150, loss[loss=0.2004, simple_loss=0.2926, pruned_loss=0.05413, over 4918.00 frames.], tot_loss[loss=0.2087, simple_loss=0.3006, pruned_loss=0.05842, over 963873.43 frames.], batch size: 14, lr: 4.82e-04
2022-05-29 14:55:27,453 INFO [train.py:761] (5/8) Epoch 32, batch 1200, loss[loss=0.2165, simple_loss=0.3134, pruned_loss=0.05986, over 4981.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2993, pruned_loss=0.05802, over 964990.53 frames.], batch size: 26, lr: 4.82e-04
2022-05-29 14:56:05,471 INFO [train.py:761] (5/8) Epoch 32, batch 1250, loss[loss=0.2011, simple_loss=0.3022, pruned_loss=0.05003, over 4853.00 frames.], tot_loss[loss=0.2078, simple_loss=0.299, pruned_loss=0.05828, over 965139.40 frames.], batch size: 14, lr: 4.82e-04
2022-05-29 14:56:43,395 INFO [train.py:761] (5/8) Epoch 32, batch 1300, loss[loss=0.2615, simple_loss=0.355, pruned_loss=0.08397, over 4982.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2984, pruned_loss=0.05803, over 964593.00 frames.], batch size: 15, lr: 4.82e-04
2022-05-29 14:57:21,064 INFO [train.py:761] (5/8) Epoch 32, batch 1350, loss[loss=0.2105, simple_loss=0.3099, pruned_loss=0.05556, over 4894.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2998, pruned_loss=0.05873, over 965480.36 frames.], batch size: 15, lr: 4.82e-04
2022-05-29 14:57:58,578 INFO [train.py:761] (5/8) Epoch 32, batch 1400, loss[loss=0.1647, simple_loss=0.2453, pruned_loss=0.04208, over 4824.00 frames.], tot_loss[loss=0.207, simple_loss=0.2983, pruned_loss=0.05779, over 964963.36 frames.], batch size: 11, lr: 4.82e-04
2022-05-29 14:58:36,402 INFO [train.py:761] (5/8) Epoch 32, batch 1450, loss[loss=0.1634, simple_loss=0.2558, pruned_loss=0.03548, over 4825.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2981, pruned_loss=0.05777, over 964494.83 frames.], batch size: 11, lr: 4.82e-04
2022-05-29 14:59:14,612 INFO [train.py:761] (5/8) Epoch 32, batch 1500, loss[loss=0.1945, simple_loss=0.3008, pruned_loss=0.0441, over 4974.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2978, pruned_loss=0.05777, over 963075.24 frames.], batch size: 14, lr: 4.81e-04
2022-05-29 14:59:52,580 INFO [train.py:761] (5/8) Epoch 32, batch 1550, loss[loss=0.2332, simple_loss=0.315, pruned_loss=0.07571, over 4918.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2987, pruned_loss=0.05803, over 963253.60 frames.], batch size: 14, lr: 4.81e-04
2022-05-29 15:00:30,662 INFO [train.py:761] (5/8) Epoch 32, batch 1600, loss[loss=0.1984, simple_loss=0.2976, pruned_loss=0.04958, over 4875.00 frames.], tot_loss[loss=0.2074, simple_loss=0.299, pruned_loss=0.05785, over 963221.42 frames.], batch size: 17, lr: 4.81e-04
2022-05-29 15:01:08,581 INFO [train.py:761] (5/8) Epoch 32, batch 1650, loss[loss=0.2062, simple_loss=0.2893, pruned_loss=0.06156, over 4994.00 frames.], tot_loss[loss=0.2085, simple_loss=0.3003, pruned_loss=0.05833, over 964350.73 frames.], batch size: 13, lr: 4.81e-04
2022-05-29 15:01:46,570 INFO [train.py:761] (5/8) Epoch 32, batch 1700, loss[loss=0.2421, simple_loss=0.3345, pruned_loss=0.07486, over 4982.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2999, pruned_loss=0.05812, over 964566.61 frames.], batch size: 26, lr: 4.81e-04
2022-05-29 15:02:24,663 INFO [train.py:761] (5/8) Epoch 32, batch 1750, loss[loss=0.1941, simple_loss=0.2918, pruned_loss=0.04822, over 4725.00 frames.], tot_loss[loss=0.2084, simple_loss=0.3003, pruned_loss=0.05822, over 965272.03 frames.], batch size: 14, lr: 4.81e-04
2022-05-29 15:03:03,119 INFO [train.py:761] (5/8) Epoch 32, batch 1800, loss[loss=0.1804, simple_loss=0.2788, pruned_loss=0.04101, over 4674.00 frames.], tot_loss[loss=0.2081, simple_loss=0.3002, pruned_loss=0.05802, over 965909.80 frames.], batch size: 12, lr: 4.81e-04
2022-05-29 15:03:41,250 INFO [train.py:761] (5/8) Epoch 32, batch 1850, loss[loss=0.2758, simple_loss=0.3556, pruned_loss=0.09802, over 4945.00 frames.], tot_loss[loss=0.21, simple_loss=0.302, pruned_loss=0.05897, over 966417.54 frames.], batch size: 43, lr: 4.81e-04
2022-05-29 15:04:19,613 INFO [train.py:761] (5/8) Epoch 32, batch 1900, loss[loss=0.2104, simple_loss=0.3095, pruned_loss=0.05568, over 4790.00 frames.], tot_loss[loss=0.2092, simple_loss=0.3011, pruned_loss=0.05864, over 966723.31 frames.], batch size: 16, lr: 4.81e-04
2022-05-29 15:04:57,288 INFO [train.py:761] (5/8) Epoch 32, batch 1950, loss[loss=0.2166, simple_loss=0.3125, pruned_loss=0.06034, over 4935.00 frames.], tot_loss[loss=0.2077, simple_loss=0.3001, pruned_loss=0.05764, over 966621.81 frames.], batch size: 26, lr: 4.81e-04
2022-05-29 15:05:34,943 INFO [train.py:761] (5/8) Epoch 32, batch 2000, loss[loss=0.1866, simple_loss=0.2811, pruned_loss=0.04604, over 4804.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2996, pruned_loss=0.05748, over 966641.01 frames.], batch size: 12, lr: 4.81e-04
2022-05-29 15:06:12,666 INFO [train.py:761] (5/8) Epoch 32, batch 2050, loss[loss=0.2103, simple_loss=0.3045, pruned_loss=0.058, over 4770.00 frames.], tot_loss[loss=0.2079, simple_loss=0.3004, pruned_loss=0.05773, over 967619.33 frames.], batch size: 20, lr: 4.81e-04
2022-05-29 15:06:51,820 INFO [train.py:761] (5/8) Epoch 32, batch 2100, loss[loss=0.1929, simple_loss=0.2752, pruned_loss=0.05529, over 4989.00 frames.], tot_loss[loss=0.2082, simple_loss=0.3006, pruned_loss=0.05792, over 966957.73 frames.], batch size: 13, lr: 4.81e-04
2022-05-29 15:07:29,218 INFO [train.py:761] (5/8) Epoch 32, batch 2150, loss[loss=0.1986, simple_loss=0.297, pruned_loss=0.05005, over 4788.00 frames.], tot_loss[loss=0.2075, simple_loss=0.3004, pruned_loss=0.05729, over 966039.12 frames.], batch size: 14, lr: 4.81e-04
2022-05-29 15:08:07,412 INFO [train.py:761] (5/8) Epoch 32, batch 2200, loss[loss=0.2315, simple_loss=0.3173, pruned_loss=0.07283, over 4806.00 frames.], tot_loss[loss=0.2093, simple_loss=0.3022, pruned_loss=0.05819, over 965488.22 frames.], batch size: 12, lr: 4.81e-04
2022-05-29 15:08:45,555 INFO [train.py:761] (5/8) Epoch 32, batch 2250, loss[loss=0.1886, simple_loss=0.2806, pruned_loss=0.04828, over 4852.00 frames.], tot_loss[loss=0.2079, simple_loss=0.3007, pruned_loss=0.05751, over 965420.47 frames.], batch size: 13, lr: 4.81e-04
2022-05-29 15:09:23,447 INFO [train.py:761] (5/8) Epoch 32, batch 2300, loss[loss=0.2125, simple_loss=0.3125, pruned_loss=0.05623, over 4812.00 frames.], tot_loss[loss=0.2091, simple_loss=0.3017, pruned_loss=0.05824, over 964875.85 frames.], batch size: 12, lr: 4.81e-04
2022-05-29 15:10:01,632 INFO [train.py:761] (5/8) Epoch 32, batch 2350, loss[loss=0.2349, simple_loss=0.3295, pruned_loss=0.07016, over 4883.00 frames.], tot_loss[loss=0.2091, simple_loss=0.3017, pruned_loss=0.05828, over 966085.83 frames.], batch size: 17, lr: 4.81e-04
2022-05-29 15:10:39,614 INFO [train.py:761] (5/8) Epoch 32, batch 2400, loss[loss=0.2046, simple_loss=0.3243, pruned_loss=0.04243, over 4712.00 frames.], tot_loss[loss=0.2085, simple_loss=0.3006, pruned_loss=0.05823, over 966027.79 frames.], batch size: 14, lr: 4.80e-04
2022-05-29 15:11:17,921 INFO [train.py:761] (5/8) Epoch 32, batch 2450, loss[loss=0.1895, simple_loss=0.2829, pruned_loss=0.04808, over 4669.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2998, pruned_loss=0.05778, over 966547.69 frames.], batch size: 12, lr: 4.80e-04
2022-05-29 15:11:55,777 INFO [train.py:761] (5/8) Epoch 32, batch 2500, loss[loss=0.196, simple_loss=0.2728, pruned_loss=0.05962, over 4645.00 frames.], tot_loss[loss=0.2084, simple_loss=0.3007, pruned_loss=0.05806, over 965462.28 frames.], batch size: 11, lr: 4.80e-04
2022-05-29 15:12:33,325 INFO [train.py:761] (5/8) Epoch 32, batch 2550, loss[loss=0.1913, simple_loss=0.2988, pruned_loss=0.04188, over 4966.00 frames.], tot_loss[loss=0.2086, simple_loss=0.3009, pruned_loss=0.05813, over 966077.73 frames.], batch size: 16, lr: 4.80e-04
2022-05-29 15:13:11,179 INFO [train.py:761] (5/8) Epoch 32, batch 2600, loss[loss=0.1796, simple_loss=0.2715, pruned_loss=0.04387, over 4862.00 frames.], tot_loss[loss=0.2082, simple_loss=0.3001, pruned_loss=0.05819, over 965720.97 frames.], batch size: 13, lr: 4.80e-04
2022-05-29 15:13:48,831 INFO [train.py:761] (5/8) Epoch 32, batch 2650, loss[loss=0.2024, simple_loss=0.3026, pruned_loss=0.05112, over 4664.00 frames.], tot_loss[loss=0.209, simple_loss=0.301, pruned_loss=0.05853, over 965512.85 frames.], batch size: 13, lr: 4.80e-04
2022-05-29 15:14:27,315 INFO [train.py:761] (5/8) Epoch 32, batch 2700, loss[loss=0.2154, simple_loss=0.3088, pruned_loss=0.06105, over 4670.00 frames.], tot_loss[loss=0.2096, simple_loss=0.3019, pruned_loss=0.05866, over 966480.02 frames.], batch size: 12, lr: 4.80e-04
2022-05-29 15:15:05,574 INFO [train.py:761] (5/8) Epoch 32, batch 2750, loss[loss=0.17, simple_loss=0.2546, pruned_loss=0.04274, over 4968.00 frames.], tot_loss[loss=0.2085, simple_loss=0.3012, pruned_loss=0.05791, over 966897.16 frames.], batch size: 12, lr: 4.80e-04
2022-05-29 15:15:43,647 INFO [train.py:761] (5/8) Epoch 32, batch 2800, loss[loss=0.2082, simple_loss=0.3029, pruned_loss=0.05677, over 4756.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2997, pruned_loss=0.05807, over 965851.28 frames.], batch size: 15, lr: 4.80e-04
2022-05-29 15:16:21,889 INFO [train.py:761] (5/8) Epoch 32, batch 2850, loss[loss=0.2089, simple_loss=0.2987, pruned_loss=0.05956, over 4760.00 frames.], tot_loss[loss=0.207, simple_loss=0.2988, pruned_loss=0.05757, over 964666.47 frames.], batch size: 15, lr: 4.80e-04
2022-05-29 15:16:59,665 INFO [train.py:761] (5/8) Epoch 32, batch 2900, loss[loss=0.2273, simple_loss=0.3175, pruned_loss=0.06853, over 4776.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2978, pruned_loss=0.05688, over 963871.50 frames.], batch size: 20, lr: 4.80e-04
2022-05-29 15:17:37,514 INFO [train.py:761] (5/8) Epoch 32, batch 2950, loss[loss=0.2174, simple_loss=0.3297, pruned_loss=0.0525, over 4717.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2988, pruned_loss=0.05702, over 963141.07 frames.], batch size: 14, lr: 4.80e-04
2022-05-29 15:18:15,857 INFO [train.py:761] (5/8) Epoch 32, batch 3000, loss[loss=0.1789, simple_loss=0.2789, pruned_loss=0.03948, over 4849.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2997, pruned_loss=0.05778, over 965415.22 frames.], batch size: 14, lr: 4.80e-04
2022-05-29 15:18:15,857 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 15:18:25,996 INFO [train.py:790] (5/8) Epoch 32, validation: loss=0.2054, simple_loss=0.3043, pruned_loss=0.05326, over 944034.00 frames.
2022-05-29 15:19:04,194 INFO [train.py:761] (5/8) Epoch 32, batch 3050, loss[loss=0.2331, simple_loss=0.3266, pruned_loss=0.06983, over 4829.00 frames.], tot_loss[loss=0.2084, simple_loss=0.3004, pruned_loss=0.05818, over 966223.87 frames.], batch size: 45, lr: 4.80e-04
2022-05-29 15:19:42,683 INFO [train.py:761] (5/8) Epoch 32, batch 3100, loss[loss=0.1989, simple_loss=0.2863, pruned_loss=0.05576, over 4722.00 frames.], tot_loss[loss=0.2108, simple_loss=0.3023, pruned_loss=0.05964, over 965556.74 frames.], batch size: 12, lr: 4.80e-04
2022-05-29 15:20:20,558 INFO [train.py:761] (5/8) Epoch 32, batch 3150, loss[loss=0.2053, simple_loss=0.3032, pruned_loss=0.05375, over 4852.00 frames.], tot_loss[loss=0.2119, simple_loss=0.3027, pruned_loss=0.0605, over 965892.43 frames.], batch size: 13, lr: 4.80e-04
2022-05-29 15:20:58,789 INFO [train.py:761] (5/8) Epoch 32, batch 3200, loss[loss=0.2385, simple_loss=0.3202, pruned_loss=0.07839, over 4887.00 frames.], tot_loss[loss=0.213, simple_loss=0.3024, pruned_loss=0.06179, over 964381.12 frames.], batch size: 15, lr: 4.80e-04
2022-05-29 15:21:37,006 INFO [train.py:761] (5/8) Epoch 32, batch 3250, loss[loss=0.201, simple_loss=0.2882, pruned_loss=0.0569, over 4983.00 frames.], tot_loss[loss=0.214, simple_loss=0.3026, pruned_loss=0.06272, over 964803.68 frames.], batch size: 13, lr: 4.80e-04
2022-05-29 15:22:14,793 INFO [train.py:761] (5/8) Epoch 32, batch 3300, loss[loss=0.2367, simple_loss=0.3292, pruned_loss=0.07209, over 4989.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3063, pruned_loss=0.0657, over 965718.87 frames.], batch size: 27, lr: 4.79e-04
2022-05-29 15:22:52,882 INFO [train.py:761] (5/8) Epoch 32, batch 3350, loss[loss=0.2095, simple_loss=0.3042, pruned_loss=0.05739, over 4970.00 frames.], tot_loss[loss=0.2197, simple_loss=0.306, pruned_loss=0.06674, over 965381.50 frames.], batch size: 15, lr: 4.79e-04
2022-05-29 15:23:30,821 INFO [train.py:761] (5/8) Epoch 32, batch 3400, loss[loss=0.2236, simple_loss=0.3152, pruned_loss=0.06605, over 4850.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3056, pruned_loss=0.06745, over 966024.95 frames.], batch size: 14, lr: 4.79e-04
2022-05-29 15:24:09,551 INFO [train.py:761] (5/8) Epoch 32, batch 3450, loss[loss=0.2292, simple_loss=0.3206, pruned_loss=0.06888, over 4980.00 frames.], tot_loss[loss=0.2205, simple_loss=0.305, pruned_loss=0.06801, over 967195.65 frames.], batch size: 15, lr: 4.79e-04
2022-05-29 15:24:47,702 INFO [train.py:761] (5/8) Epoch 32, batch 3500, loss[loss=0.2073, simple_loss=0.3035, pruned_loss=0.05556, over 4967.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3056, pruned_loss=0.06884, over 967059.78 frames.], batch size: 15, lr: 4.79e-04
2022-05-29 15:25:26,007 INFO [train.py:761] (5/8) Epoch 32, batch 3550, loss[loss=0.2294, simple_loss=0.3087, pruned_loss=0.0751, over 4857.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3057, pruned_loss=0.06959, over 966868.50 frames.], batch size: 18, lr: 4.79e-04
2022-05-29 15:26:03,965 INFO [train.py:761] (5/8) Epoch 32, batch 3600, loss[loss=0.2039, simple_loss=0.2842, pruned_loss=0.06174, over 4856.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3063, pruned_loss=0.07008, over 967210.64 frames.], batch size: 13, lr: 4.79e-04
2022-05-29 15:26:41,521 INFO [train.py:761] (5/8) Epoch 32, batch 3650, loss[loss=0.2263, simple_loss=0.3034, pruned_loss=0.07455, over 4845.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3045, pruned_loss=0.0691, over 966263.47 frames.], batch size: 14, lr: 4.79e-04
2022-05-29 15:27:19,520 INFO [train.py:761] (5/8) Epoch 32, batch 3700, loss[loss=0.2281, simple_loss=0.3099, pruned_loss=0.07311, over 4886.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3042, pruned_loss=0.06941, over 966848.79 frames.], batch size: 12, lr: 4.79e-04
2022-05-29 15:27:57,217 INFO [train.py:761] (5/8) Epoch 32, batch 3750, loss[loss=0.1993, simple_loss=0.279, pruned_loss=0.05978, over 4850.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3046, pruned_loss=0.06956, over 966722.75 frames.], batch size: 13, lr: 4.79e-04
2022-05-29 15:28:35,898 INFO [train.py:761] (5/8) Epoch 32, batch 3800, loss[loss=0.2307, simple_loss=0.3023, pruned_loss=0.07951, over 4807.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3043, pruned_loss=0.06999, over 967025.10 frames.], batch size: 12, lr: 4.79e-04
2022-05-29 15:29:13,727 INFO [train.py:761] (5/8) Epoch 32, batch 3850, loss[loss=0.2006, simple_loss=0.2723, pruned_loss=0.06441, over 4733.00 frames.], tot_loss[loss=0.223, simple_loss=0.3048, pruned_loss=0.07064, over 966255.71 frames.], batch size: 11, lr: 4.79e-04
2022-05-29 15:29:52,277 INFO [train.py:761] (5/8) Epoch 32, batch 3900, loss[loss=0.2663, simple_loss=0.3489, pruned_loss=0.09185, over 4876.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3052, pruned_loss=0.07057, over 966777.29 frames.], batch size: 15, lr: 4.79e-04
2022-05-29 15:30:29,959 INFO [train.py:761] (5/8) Epoch 32, batch 3950, loss[loss=0.2491, simple_loss=0.334, pruned_loss=0.08212, over 4882.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3053, pruned_loss=0.07013, over 966767.59 frames.], batch size: 17, lr: 4.79e-04
2022-05-29 15:31:09,222 INFO [train.py:761] (5/8) Epoch 32, batch 4000, loss[loss=0.2203, simple_loss=0.3142, pruned_loss=0.06326, over 4793.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3079, pruned_loss=0.07191, over 967086.13 frames.], batch size: 12, lr: 4.79e-04
2022-05-29 15:31:47,866 INFO [train.py:761] (5/8) Epoch 32, batch 4050, loss[loss=0.2311, simple_loss=0.3175, pruned_loss=0.07231, over 4965.00 frames.], tot_loss[loss=0.226, simple_loss=0.3077, pruned_loss=0.07217, over 966304.24 frames.], batch size: 14, lr: 4.79e-04
2022-05-29 15:32:26,014 INFO [train.py:761] (5/8) Epoch 32, batch 4100, loss[loss=0.2063, simple_loss=0.2951, pruned_loss=0.05873, over 4922.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3091, pruned_loss=0.0728, over 967344.27 frames.], batch size: 13, lr: 4.79e-04
2022-05-29 15:33:03,573 INFO [train.py:761] (5/8) Epoch 32, batch 4150, loss[loss=0.2428, simple_loss=0.3343, pruned_loss=0.07566, over 4869.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3087, pruned_loss=0.07282, over 966724.39 frames.], batch size: 26, lr: 4.78e-04
2022-05-29 15:33:41,559 INFO [train.py:761] (5/8) Epoch 32, batch 4200, loss[loss=0.2596, simple_loss=0.322, pruned_loss=0.09858, over 4888.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3097, pruned_loss=0.0733, over 966811.96 frames.], batch size: 17, lr: 4.78e-04
2022-05-29 15:34:19,998 INFO [train.py:761] (5/8) Epoch 32, batch 4250, loss[loss=0.2517, simple_loss=0.3264, pruned_loss=0.08851, over 4803.00 frames.], tot_loss[loss=0.2288, simple_loss=0.31, pruned_loss=0.07374, over 966490.48 frames.], batch size: 16, lr: 4.78e-04
2022-05-29 15:34:58,519 INFO [train.py:761] (5/8) Epoch 32, batch 4300, loss[loss=0.2673, simple_loss=0.3383, pruned_loss=0.09819, over 4795.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3104, pruned_loss=0.07397, over 966620.56 frames.], batch size: 16, lr: 4.78e-04
2022-05-29 15:35:36,368 INFO [train.py:761] (5/8) Epoch 32, batch 4350, loss[loss=0.1931, simple_loss=0.2815, pruned_loss=0.05232, over 4976.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3091, pruned_loss=0.07362, over 966953.29 frames.], batch size: 12, lr: 4.78e-04
2022-05-29 15:36:14,094 INFO [train.py:761] (5/8) Epoch 32, batch 4400, loss[loss=0.1678, simple_loss=0.2641, pruned_loss=0.03572, over 4860.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3082, pruned_loss=0.07316, over 966638.68 frames.], batch size: 13, lr: 4.78e-04
2022-05-29 15:36:52,429 INFO [train.py:761] (5/8) Epoch 32, batch 4450, loss[loss=0.2253, simple_loss=0.3016, pruned_loss=0.07449, over 4979.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3066, pruned_loss=0.07251, over 966708.32 frames.], batch size: 12, lr: 4.78e-04
2022-05-29 15:37:31,177 INFO [train.py:761] (5/8) Epoch 32, batch 4500, loss[loss=0.2352, simple_loss=0.3135, pruned_loss=0.07846, over 4918.00 frames.], tot_loss[loss=0.2249, simple_loss=0.306, pruned_loss=0.0719, over 966840.22 frames.], batch size: 13, lr: 4.78e-04
2022-05-29 15:38:09,023 INFO [train.py:761] (5/8) Epoch 32, batch 4550, loss[loss=0.2099, simple_loss=0.2746, pruned_loss=0.0726, over 4740.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3057, pruned_loss=0.07142, over 966741.14 frames.], batch size: 11, lr: 4.78e-04
2022-05-29 15:38:47,254 INFO [train.py:761] (5/8) Epoch 32, batch 4600, loss[loss=0.2174, simple_loss=0.3086, pruned_loss=0.0631, over 4715.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3057, pruned_loss=0.07132, over 966614.02 frames.], batch size: 14, lr: 4.78e-04
2022-05-29 15:39:25,077 INFO [train.py:761] (5/8) Epoch 32, batch 4650, loss[loss=0.2241, simple_loss=0.3076, pruned_loss=0.07033, over 4849.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3057, pruned_loss=0.0709, over 966635.02 frames.], batch size: 13, lr: 4.78e-04
2022-05-29 15:40:04,193 INFO [train.py:761] (5/8) Epoch 32, batch 4700, loss[loss=0.3254, simple_loss=0.3896, pruned_loss=0.1306, over 4895.00 frames.], tot_loss[loss=0.225, simple_loss=0.3068, pruned_loss=0.0716, over 966433.38 frames.], batch size: 50, lr: 4.78e-04
2022-05-29 15:40:42,222 INFO [train.py:761] (5/8) Epoch 32, batch 4750, loss[loss=0.2714, simple_loss=0.3399, pruned_loss=0.1015, over 4915.00 frames.], tot_loss[loss=0.225, simple_loss=0.3065, pruned_loss=0.07174, over 966969.37 frames.], batch size: 13, lr: 4.78e-04
2022-05-29 15:41:20,536 INFO [train.py:761] (5/8) Epoch 32, batch 4800, loss[loss=0.2682, simple_loss=0.3537, pruned_loss=0.09129, over 4790.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3052, pruned_loss=0.07085, over 966192.11 frames.], batch size: 14, lr: 4.78e-04
2022-05-29 15:41:58,694 INFO [train.py:761] (5/8) Epoch 32, batch 4850, loss[loss=0.2543, simple_loss=0.3189, pruned_loss=0.09484, over 4886.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3044, pruned_loss=0.07096, over 965278.03 frames.], batch size: 12, lr: 4.78e-04
2022-05-29 15:42:36,736 INFO [train.py:761] (5/8) Epoch 32, batch 4900, loss[loss=0.2428, simple_loss=0.3319, pruned_loss=0.07689, over 4884.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3058, pruned_loss=0.0714, over 966456.73 frames.], batch size: 15, lr: 4.78e-04
2022-05-29 15:43:14,876 INFO [train.py:761] (5/8) Epoch 32, batch 4950, loss[loss=0.2649, simple_loss=0.3488, pruned_loss=0.09055, over 4678.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3052, pruned_loss=0.0709, over 965604.35 frames.], batch size: 13, lr: 4.78e-04
2022-05-29 15:43:53,371 INFO [train.py:761] (5/8) Epoch 32, batch 5000, loss[loss=0.2112, simple_loss=0.3059, pruned_loss=0.05826, over 4839.00 frames.], tot_loss[loss=0.2232, simple_loss=0.305, pruned_loss=0.07069, over 966189.30 frames.], batch size: 17, lr: 4.78e-04
2022-05-29 15:44:32,099 INFO [train.py:761] (5/8) Epoch 32, batch 5050, loss[loss=0.1972, simple_loss=0.2654, pruned_loss=0.06449, over 4734.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3051, pruned_loss=0.07081, over 965457.79 frames.], batch size: 11, lr: 4.77e-04
2022-05-29 15:45:11,027 INFO [train.py:761] (5/8) Epoch 32, batch 5100, loss[loss=0.2398, simple_loss=0.335, pruned_loss=0.07228, over 4767.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3062, pruned_loss=0.07145, over 967113.43 frames.], batch size: 15, lr: 4.77e-04
2022-05-29 15:45:48,823 INFO [train.py:761] (5/8) Epoch 32, batch 5150, loss[loss=0.2194, simple_loss=0.2915, pruned_loss=0.07369, over 4986.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3061, pruned_loss=0.07148, over 967500.18 frames.], batch size: 13, lr: 4.77e-04
2022-05-29 15:46:27,479 INFO [train.py:761] (5/8) Epoch 32, batch 5200, loss[loss=0.2259, simple_loss=0.3113, pruned_loss=0.07026, over 4971.00 frames.], tot_loss[loss=0.223, simple_loss=0.305, pruned_loss=0.07043, over 967400.22 frames.], batch size: 15, lr: 4.77e-04
2022-05-29 15:47:06,319 INFO [train.py:761] (5/8) Epoch 32, batch 5250, loss[loss=0.2788, simple_loss=0.3537, pruned_loss=0.102, over 4911.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3052, pruned_loss=0.07066, over 967032.66 frames.], batch size: 14, lr: 4.77e-04
2022-05-29 15:47:44,851 INFO [train.py:761] (5/8) Epoch 32, batch 5300, loss[loss=0.1867, simple_loss=0.2735, pruned_loss=0.04993, over 4896.00 frames.], tot_loss[loss=0.224, simple_loss=0.3059, pruned_loss=0.07102, over 967020.56 frames.], batch size: 12, lr: 4.77e-04
2022-05-29 15:48:22,588 INFO [train.py:761] (5/8) Epoch 32, batch 5350, loss[loss=0.2428, simple_loss=0.3204, pruned_loss=0.08264, over 4768.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3055, pruned_loss=0.07051, over 966890.37 frames.], batch size: 15, lr: 4.77e-04
2022-05-29 15:49:00,926 INFO [train.py:761] (5/8) Epoch 32, batch 5400, loss[loss=0.2189, simple_loss=0.3094, pruned_loss=0.06416, over 4973.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3065, pruned_loss=0.07068, over 965864.82 frames.], batch size: 14, lr: 4.77e-04
2022-05-29 15:49:39,021 INFO [train.py:761] (5/8) Epoch 32, batch 5450, loss[loss=0.2035, simple_loss=0.2971, pruned_loss=0.05493, over 4814.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3072, pruned_loss=0.07106, over 965806.47 frames.], batch size: 20, lr: 4.77e-04
2022-05-29 15:50:17,161 INFO [train.py:761] (5/8) Epoch 32, batch 5500, loss[loss=0.2494, simple_loss=0.3205, pruned_loss=0.08919, over 4836.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3076, pruned_loss=0.07039, over 965421.60 frames.], batch size: 18, lr: 4.77e-04
2022-05-29 15:50:55,338 INFO [train.py:761] (5/8) Epoch 32, batch 5550, loss[loss=0.2559, simple_loss=0.3334, pruned_loss=0.08915, over 4916.00 frames.], tot_loss[loss=0.224, simple_loss=0.3074, pruned_loss=0.07028, over 965673.65 frames.], batch size: 26, lr: 4.77e-04
2022-05-29 15:51:33,739 INFO [train.py:761] (5/8) Epoch 32, batch 5600, loss[loss=0.215, simple_loss=0.2958, pruned_loss=0.06707, over 4927.00 frames.], tot_loss[loss=0.2239, simple_loss=0.307, pruned_loss=0.07035, over 966814.65 frames.], batch size: 13, lr: 4.77e-04
2022-05-29 15:52:11,273 INFO [train.py:761] (5/8) Epoch 32, batch 5650, loss[loss=0.1768, simple_loss=0.2639, pruned_loss=0.04485, over 4668.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3073, pruned_loss=0.07057, over 967098.12 frames.], batch size: 12, lr: 4.77e-04
2022-05-29 15:52:50,473 INFO [train.py:761] (5/8) Epoch 32, batch 5700, loss[loss=0.2291, simple_loss=0.2825, pruned_loss=0.08782, over 4835.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3063, pruned_loss=0.07013, over 967174.43 frames.], batch size: 11, lr: 4.77e-04
2022-05-29 15:53:28,450 INFO [train.py:761] (5/8) Epoch 32, batch 5750, loss[loss=0.2565, simple_loss=0.3377, pruned_loss=0.08761, over 4860.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3071, pruned_loss=0.07109, over 967100.59 frames.], batch size: 26, lr: 4.77e-04
2022-05-29 15:54:06,878 INFO [train.py:761] (5/8) Epoch 32, batch 5800, loss[loss=0.2794, simple_loss=0.3542, pruned_loss=0.1023, over 4960.00 frames.], tot_loss[loss=0.2269, simple_loss=0.309, pruned_loss=0.07242, over 966322.45 frames.], batch size: 47, lr: 4.77e-04
2022-05-29 15:54:45,500 INFO [train.py:761] (5/8) Epoch 32, batch 5850, loss[loss=0.2342, simple_loss=0.3123, pruned_loss=0.07802, over 4902.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3081, pruned_loss=0.07225, over 967200.19 frames.], batch size: 26, lr: 4.77e-04
2022-05-29 15:55:23,582 INFO [train.py:761] (5/8) Epoch 32, batch 5900, loss[loss=0.2669, simple_loss=0.3446, pruned_loss=0.09458, over 4937.00 frames.], tot_loss[loss=0.226, simple_loss=0.3084, pruned_loss=0.07184, over 966774.22 frames.], batch size: 47, lr: 4.77e-04
2022-05-29 15:56:01,654 INFO [train.py:761] (5/8) Epoch 32, batch 5950, loss[loss=0.2643, simple_loss=0.3431, pruned_loss=0.09273, over 4885.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3092, pruned_loss=0.07313, over 966350.77 frames.], batch size: 45, lr: 4.76e-04
2022-05-29 15:56:40,194 INFO [train.py:761] (5/8) Epoch 32, batch 6000, loss[loss=0.2255, simple_loss=0.2944, pruned_loss=0.07829, over 4974.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3084, pruned_loss=0.07269, over 966620.89 frames.], batch size: 15, lr: 4.76e-04
2022-05-29 15:56:40,194 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 15:56:49,998 INFO [train.py:790] (5/8) Epoch 32, validation: loss=0.1977, simple_loss=0.3006, pruned_loss=0.04738, over 944034.00 frames.
2022-05-29 15:57:28,533 INFO [train.py:761] (5/8) Epoch 32, batch 6050, loss[loss=0.1572, simple_loss=0.2491, pruned_loss=0.03262, over 4734.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3072, pruned_loss=0.07161, over 966239.44 frames.], batch size: 12, lr: 4.76e-04
2022-05-29 15:58:06,511 INFO [train.py:761] (5/8) Epoch 32, batch 6100, loss[loss=0.2589, simple_loss=0.3371, pruned_loss=0.09042, over 4854.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3067, pruned_loss=0.0717, over 966260.46 frames.], batch size: 18, lr: 4.76e-04
2022-05-29 15:58:44,800 INFO [train.py:761] (5/8) Epoch 32, batch 6150, loss[loss=0.254, simple_loss=0.3346, pruned_loss=0.08667, over 4969.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3068, pruned_loss=0.07181, over 966486.04 frames.], batch size: 47, lr: 4.76e-04
2022-05-29 15:59:23,363 INFO [train.py:761] (5/8) Epoch 32, batch 6200, loss[loss=0.2318, simple_loss=0.3232, pruned_loss=0.07021, over 4922.00 frames.], tot_loss[loss=0.2251, simple_loss=0.307, pruned_loss=0.07164, over 966613.52 frames.], batch size: 14, lr: 4.76e-04
2022-05-29 16:00:01,896 INFO [train.py:761] (5/8) Epoch 32, batch 6250, loss[loss=0.2367, simple_loss=0.3187, pruned_loss=0.07737, over 4796.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3057, pruned_loss=0.07125, over 965693.76 frames.], batch size: 16, lr: 4.76e-04
2022-05-29 16:00:40,435 INFO [train.py:761] (5/8) Epoch 32, batch 6300, loss[loss=0.1806, simple_loss=0.2796, pruned_loss=0.04076, over 4721.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3055, pruned_loss=0.07102, over 965732.30 frames.], batch size: 13, lr: 4.76e-04
2022-05-29 16:01:18,463 INFO [train.py:761] (5/8) Epoch 32, batch 6350, loss[loss=0.2045, simple_loss=0.297, pruned_loss=0.05597, over 4973.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3047, pruned_loss=0.07004, over 965491.04 frames.], batch size: 14, lr: 4.76e-04
2022-05-29 16:01:56,488 INFO [train.py:761] (5/8) Epoch 32, batch 6400, loss[loss=0.2281, simple_loss=0.2959, pruned_loss=0.08015, over 4650.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3054, pruned_loss=0.07015, over 965714.86 frames.], batch size: 11, lr: 4.76e-04
2022-05-29 16:02:34,636 INFO [train.py:761] (5/8) Epoch 32, batch 6450, loss[loss=0.227, simple_loss=0.3123, pruned_loss=0.07082, over 4664.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3046, pruned_loss=0.06983, over 965399.35 frames.], batch size: 13, lr: 4.76e-04
2022-05-29 16:03:12,916 INFO [train.py:761] (5/8) Epoch 32, batch 6500, loss[loss=0.2351, simple_loss=0.3096, pruned_loss=0.08033, over 4908.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3028, pruned_loss=0.06902, over 965497.53 frames.], batch size: 26, lr: 4.76e-04
2022-05-29 16:03:51,084 INFO [train.py:761] (5/8) Epoch 32, batch 6550, loss[loss=0.2741, simple_loss=0.3422, pruned_loss=0.103, over 4885.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3028, pruned_loss=0.06888, over 965284.46 frames.], batch size: 46, lr: 4.76e-04
2022-05-29 16:04:29,671 INFO [train.py:761] (5/8) Epoch 32, batch 6600, loss[loss=0.1856, simple_loss=0.2806, pruned_loss=0.04524, over 4969.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3036, pruned_loss=0.06988, over 966047.67 frames.], batch size: 12, lr: 4.76e-04
2022-05-29 16:05:08,437 INFO [train.py:761] (5/8) Epoch 32, batch 6650, loss[loss=0.2047, simple_loss=0.3048, pruned_loss=0.0523, over 4909.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3033, pruned_loss=0.06988, over 965589.91 frames.], batch size: 14, lr: 4.76e-04
2022-05-29 16:05:47,177 INFO [train.py:761] (5/8) Epoch 32, batch 6700, loss[loss=0.2261, simple_loss=0.3286, pruned_loss=0.06177, over 4674.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3041, pruned_loss=0.06943, over 966152.52 frames.], batch size: 13, lr: 4.76e-04
2022-05-29 16:06:40,876 INFO [train.py:761] (5/8) Epoch 33, batch 0, loss[loss=0.193, simple_loss=0.2839, pruned_loss=0.05108, over 4725.00 frames.], tot_loss[loss=0.193, simple_loss=0.2839, pruned_loss=0.05108, over 4725.00 frames.], batch size: 12, lr: 4.76e-04
2022-05-29 16:07:19,756 INFO [train.py:761] (5/8) Epoch 33, batch 50, loss[loss=0.2152, simple_loss=0.2967, pruned_loss=0.0668, over 4858.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3055, pruned_loss=0.06114, over 218892.61 frames.], batch size: 13, lr: 4.76e-04
2022-05-29 16:07:57,627 INFO [train.py:761] (5/8) Epoch 33, batch 100, loss[loss=0.1863, simple_loss=0.2709, pruned_loss=0.05082, over 4845.00 frames.], tot_loss[loss=0.2127, simple_loss=0.3035, pruned_loss=0.06096, over 385286.56 frames.], batch size: 11, lr: 4.75e-04
2022-05-29 16:08:38,513 INFO [train.py:761] (5/8) Epoch 33, batch 150, loss[loss=0.187, simple_loss=0.2726, pruned_loss=0.05068, over 4654.00 frames.], tot_loss[loss=0.21, simple_loss=0.3006, pruned_loss=0.05964, over 513800.52 frames.], batch size: 11, lr: 4.75e-04
2022-05-29 16:09:16,756 INFO [train.py:761] (5/8) Epoch 33, batch 200, loss[loss=0.1603, simple_loss=0.2414, pruned_loss=0.03956, over 4535.00 frames.], tot_loss[loss=0.2084, simple_loss=0.299, pruned_loss=0.05894, over 614591.76 frames.], batch size: 10, lr: 4.75e-04
2022-05-29 16:09:54,685 INFO [train.py:761] (5/8) Epoch 33, batch 250, loss[loss=0.2005, simple_loss=0.2947, pruned_loss=0.05309, over 4907.00 frames.], tot_loss[loss=0.2066, simple_loss=0.298, pruned_loss=0.05756, over 693578.78 frames.], batch size: 13, lr: 4.75e-04
2022-05-29 16:10:32,618 INFO [train.py:761] (5/8) Epoch 33, batch 300, loss[loss=0.2295, simple_loss=0.3229, pruned_loss=0.06803, over 4954.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2983, pruned_loss=0.05802, over 753033.73 frames.], batch size: 16, lr: 4.75e-04
2022-05-29 16:11:11,037 INFO [train.py:761] (5/8) Epoch 33, batch 350, loss[loss=0.1904, simple_loss=0.2759, pruned_loss=0.05239, over 4658.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2975, pruned_loss=0.05674, over 800635.46 frames.], batch size: 12, lr: 4.75e-04
2022-05-29 16:11:49,188 INFO [train.py:761] (5/8) Epoch 33, batch 400, loss[loss=0.2697, simple_loss=0.3431, pruned_loss=0.09817, over 4943.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2966, pruned_loss=0.05687, over 836250.35 frames.], batch size: 50, lr: 4.75e-04
2022-05-29 16:12:27,322 INFO [train.py:761] (5/8) Epoch 33, batch 450, loss[loss=0.198, simple_loss=0.2954, pruned_loss=0.05025, over 4782.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2969, pruned_loss=0.05663, over 866199.39 frames.], batch size: 14, lr: 4.75e-04
2022-05-29 16:13:04,677 INFO [train.py:761] (5/8) Epoch 33, batch 500, loss[loss=0.1912, simple_loss=0.2959, pruned_loss=0.04326, over 4778.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2965, pruned_loss=0.05633, over 889641.38 frames.], batch size: 14, lr: 4.75e-04
2022-05-29 16:13:43,031 INFO [train.py:761] (5/8) Epoch 33, batch 550, loss[loss=0.2235, simple_loss=0.3235, pruned_loss=0.06173, over 4911.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2955, pruned_loss=0.05545, over 906400.28 frames.], batch size: 14, lr: 4.75e-04
2022-05-29 16:14:21,249 INFO [train.py:761] (5/8) Epoch 33, batch 600, loss[loss=0.1711, simple_loss=0.2684, pruned_loss=0.03691, over 4916.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2961, pruned_loss=0.0561, over 918970.31 frames.], batch size: 13, lr: 4.75e-04
2022-05-29 16:14:59,868 INFO [train.py:761] (5/8) Epoch 33, batch 650, loss[loss=0.1691, simple_loss=0.272, pruned_loss=0.03307, over 4989.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2975, pruned_loss=0.05641, over 930180.27 frames.], batch size: 13, lr: 4.75e-04
2022-05-29 16:15:37,866 INFO [train.py:761] (5/8) Epoch 33, batch 700, loss[loss=0.204, simple_loss=0.2853, pruned_loss=0.06133, over 4925.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2966, pruned_loss=0.05624, over 937079.23 frames.], batch size: 13, lr: 4.75e-04
2022-05-29 16:16:15,816 INFO [train.py:761] (5/8) Epoch 33, batch 750, loss[loss=0.2098, simple_loss=0.2946, pruned_loss=0.06252, over 4855.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2963, pruned_loss=0.05623, over 944000.82 frames.], batch size: 13, lr: 4.75e-04
2022-05-29 16:16:53,823 INFO [train.py:761] (5/8) Epoch 33, batch 800, loss[loss=0.252, simple_loss=0.335, pruned_loss=0.0845, over 4771.00 frames.], tot_loss[loss=0.2052, simple_loss=0.297, pruned_loss=0.05674, over 949564.81 frames.], batch size: 15, lr: 4.75e-04
2022-05-29 16:17:31,854 INFO [train.py:761] (5/8) Epoch 33, batch 850, loss[loss=0.1887, simple_loss=0.2686, pruned_loss=0.05444, over 4646.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2979, pruned_loss=0.05822, over 953229.97 frames.], batch size: 11, lr: 4.75e-04
2022-05-29 16:18:09,511 INFO [train.py:761] (5/8) Epoch 33, batch 900, loss[loss=0.2273, simple_loss=0.2962, pruned_loss=0.07916, over 4565.00 frames.], tot_loss[loss=0.208, simple_loss=0.2984, pruned_loss=0.05882, over 955734.65 frames.], batch size: 10, lr: 4.75e-04
2022-05-29 16:18:47,736 INFO [train.py:761] (5/8) Epoch 33, batch 950, loss[loss=0.2189, simple_loss=0.3174, pruned_loss=0.06019, over 4852.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2995, pruned_loss=0.05867, over 957360.15 frames.], batch size: 18, lr: 4.75e-04
2022-05-29 16:19:25,431 INFO [train.py:761] (5/8) Epoch 33, batch 1000, loss[loss=0.1755, simple_loss=0.2597, pruned_loss=0.0457, over 4742.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2991, pruned_loss=0.05829, over 959946.60 frames.], batch size: 11, lr: 4.75e-04
2022-05-29 16:20:03,411 INFO [train.py:761] (5/8) Epoch 33, batch 1050, loss[loss=0.2458, simple_loss=0.3089, pruned_loss=0.09132, over 4808.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2999, pruned_loss=0.0584, over 961211.93 frames.], batch size: 12, lr: 4.74e-04
2022-05-29 16:20:41,387 INFO [train.py:761] (5/8) Epoch 33, batch 1100, loss[loss=0.2025, simple_loss=0.2909, pruned_loss=0.05706, over 4787.00 frames.], tot_loss[loss=0.2084, simple_loss=0.3001, pruned_loss=0.0584, over 961967.72 frames.], batch size: 14, lr: 4.74e-04
2022-05-29 16:21:19,950 INFO [train.py:761] (5/8) Epoch 33, batch 1150, loss[loss=0.204, simple_loss=0.307, pruned_loss=0.05047, over 4759.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2997, pruned_loss=0.05826, over 961677.83 frames.], batch size: 16, lr: 4.74e-04
2022-05-29 16:21:57,820 INFO [train.py:761] (5/8) Epoch 33, batch 1200, loss[loss=0.2192, simple_loss=0.3194, pruned_loss=0.05948, over 4708.00 frames.], tot_loss[loss=0.2088, simple_loss=0.3006, pruned_loss=0.05848, over 962207.22 frames.], batch size: 14, lr: 4.74e-04
2022-05-29 16:22:35,668 INFO [train.py:761] (5/8) Epoch 33, batch 1250, loss[loss=0.2064, simple_loss=0.2843, pruned_loss=0.06421, over 4973.00 frames.], tot_loss[loss=0.2079, simple_loss=0.3003, pruned_loss=0.05774, over 963160.92 frames.], batch size: 12, lr: 4.74e-04
2022-05-29 16:23:13,672 INFO [train.py:761] (5/8) Epoch 33, batch 1300, loss[loss=0.1993, simple_loss=0.2807, pruned_loss=0.05894, over 4734.00 frames.], tot_loss[loss=0.2078, simple_loss=0.3, pruned_loss=0.05784, over 963824.70 frames.], batch size: 12, lr: 4.74e-04
2022-05-29 16:23:51,840 INFO [train.py:761] (5/8) Epoch 33, batch 1350, loss[loss=0.2062, simple_loss=0.2949, pruned_loss=0.05881, over 4979.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2994, pruned_loss=0.05798, over 964200.54 frames.], batch size: 14, lr: 4.74e-04
2022-05-29 16:24:29,402 INFO [train.py:761] (5/8) Epoch 33, batch 1400, loss[loss=0.2128, simple_loss=0.3074, pruned_loss=0.05903, over 4972.00 frames.], tot_loss[loss=0.2096, simple_loss=0.3016, pruned_loss=0.05881, over 965982.50 frames.], batch size: 14, lr: 4.74e-04
2022-05-29 16:25:07,632 INFO [train.py:761] (5/8) Epoch 33, batch 1450, loss[loss=0.2336, simple_loss=0.3347, pruned_loss=0.06627, over 4958.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2998, pruned_loss=0.05793, over 965503.14 frames.], batch size: 16, lr: 4.74e-04
2022-05-29 16:25:45,801 INFO [train.py:761] (5/8) Epoch 33, batch 1500, loss[loss=0.1765, simple_loss=0.28, pruned_loss=0.03648, over 4979.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2997, pruned_loss=0.05803, over 965542.32 frames.], batch size: 14, lr: 4.74e-04
2022-05-29 16:26:23,460 INFO [train.py:761] (5/8) Epoch 33, batch 1550, loss[loss=0.1844, simple_loss=0.2878, pruned_loss=0.04051, over 4850.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2989, pruned_loss=0.05728, over 965848.30 frames.], batch size: 14, lr: 4.74e-04
2022-05-29 16:27:00,988 INFO [train.py:761] (5/8) Epoch 33, batch 1600, loss[loss=0.2228, simple_loss=0.325, pruned_loss=0.06026, over 4853.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2981, pruned_loss=0.05721, over 965480.74 frames.], batch size: 14, lr: 4.74e-04
2022-05-29 16:27:39,290 INFO [train.py:761] (5/8) Epoch 33, batch 1650, loss[loss=0.2324, simple_loss=0.3235, pruned_loss=0.07058, over 4974.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2979, pruned_loss=0.05684, over 965292.64 frames.], batch size: 14, lr: 4.74e-04
2022-05-29 16:28:16,794 INFO [train.py:761] (5/8) Epoch 33, batch 1700, loss[loss=0.2489, simple_loss=0.3448, pruned_loss=0.07648, over 4983.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2968, pruned_loss=0.05677, over 965680.91 frames.], batch size: 27, lr: 4.74e-04
2022-05-29 16:28:55,257 INFO [train.py:761] (5/8) Epoch 33, batch 1750, loss[loss=0.2452, simple_loss=0.3267, pruned_loss=0.08178, over 4785.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2989, pruned_loss=0.05787, over 966342.04 frames.], batch size: 14, lr: 4.74e-04
2022-05-29 16:29:33,609 INFO [train.py:761] (5/8) Epoch 33, batch 1800, loss[loss=0.253, simple_loss=0.3485, pruned_loss=0.07869, over 4890.00 frames.], tot_loss[loss=0.2095, simple_loss=0.3013, pruned_loss=0.05886, over 966477.01 frames.], batch size: 15, lr: 4.74e-04
2022-05-29 16:30:11,475 INFO [train.py:761] (5/8) Epoch 33, batch 1850, loss[loss=0.237, simple_loss=0.329, pruned_loss=0.07247, over 4739.00 frames.], tot_loss[loss=0.2099, simple_loss=0.3015, pruned_loss=0.05913, over 966807.94 frames.], batch size: 20, lr: 4.74e-04
2022-05-29 16:30:49,399 INFO [train.py:761] (5/8) Epoch 33, batch 1900, loss[loss=0.2151, simple_loss=0.3115, pruned_loss=0.05932, over 4952.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2996, pruned_loss=0.05755, over 966072.42 frames.], batch size: 21, lr: 4.74e-04
2022-05-29 16:31:27,489 INFO [train.py:761] (5/8) Epoch 33, batch 1950, loss[loss=0.2036, simple_loss=0.292, pruned_loss=0.05762, over 4729.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2994, pruned_loss=0.05742, over 966108.58 frames.], batch size: 12, lr: 4.73e-04
2022-05-29 16:32:05,414 INFO [train.py:761] (5/8) Epoch 33, batch 2000, loss[loss=0.1744, simple_loss=0.2686, pruned_loss=0.04013, over 4857.00 frames.], tot_loss[loss=0.207, simple_loss=0.2992, pruned_loss=0.05744, over 966577.47 frames.], batch size: 13, lr: 4.73e-04
2022-05-29 16:32:43,779 INFO [train.py:761] (5/8) Epoch 33, batch 2050, loss[loss=0.1848, simple_loss=0.2826, pruned_loss=0.04346, over 4961.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2997, pruned_loss=0.05805, over 967178.57 frames.], batch size: 16, lr: 4.73e-04
2022-05-29 16:33:21,633 INFO [train.py:761] (5/8) Epoch 33, batch 2100, loss[loss=0.1793, simple_loss=0.2876, pruned_loss=0.03553, over 4664.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2998, pruned_loss=0.0577, over 967027.40 frames.], batch size: 12, lr: 4.73e-04
2022-05-29 16:33:59,435 INFO [train.py:761] (5/8) Epoch 33, batch 2150, loss[loss=0.2323, simple_loss=0.3258, pruned_loss=0.06942, over 4981.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2998, pruned_loss=0.05734, over 967381.51 frames.], batch size: 15, lr: 4.73e-04
2022-05-29 16:34:37,520 INFO [train.py:761] (5/8) Epoch 33, batch 2200, loss[loss=0.1718, simple_loss=0.2571, pruned_loss=0.0433, over 4642.00 frames.], tot_loss[loss=0.2074, simple_loss=0.3002, pruned_loss=0.05723, over 967764.82 frames.], batch size: 11, lr: 4.73e-04
2022-05-29 16:35:15,536 INFO [train.py:761] (5/8) Epoch 33, batch 2250, loss[loss=0.1627, simple_loss=0.2569, pruned_loss=0.03422, over 4739.00 frames.], tot_loss[loss=0.2083, simple_loss=0.3011, pruned_loss=0.05779, over 967374.05 frames.], batch size: 11, lr: 4.73e-04
2022-05-29 16:35:53,238 INFO [train.py:761] (5/8) Epoch 33, batch 2300, loss[loss=0.2228, simple_loss=0.3274, pruned_loss=0.0591, over 4728.00 frames.], tot_loss[loss=0.208, simple_loss=0.3006, pruned_loss=0.05771, over 967461.59 frames.], batch size: 13, lr: 4.73e-04
2022-05-29 16:36:39,355 INFO [train.py:761] (5/8) Epoch 33, batch 2350, loss[loss=0.2093, simple_loss=0.2999, pruned_loss=0.05934, over 4974.00 frames.], tot_loss[loss=0.2077, simple_loss=0.3002, pruned_loss=0.05758, over 967460.48 frames.], batch size: 15, lr: 4.73e-04
2022-05-29 16:37:17,556 INFO [train.py:761] (5/8) Epoch 33, batch 2400, loss[loss=0.2135, simple_loss=0.3102, pruned_loss=0.05843, over 4836.00 frames.], tot_loss[loss=0.2072, simple_loss=0.3001, pruned_loss=0.05712, over 967587.99 frames.], batch size: 16, lr: 4.73e-04
2022-05-29 16:37:55,617 INFO [train.py:761] (5/8) Epoch 33, batch 2450, loss[loss=0.209, simple_loss=0.3124, pruned_loss=0.05277, over 4788.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2996, pruned_loss=0.05686, over 966347.73 frames.], batch size: 15, lr: 4.73e-04
2022-05-29 16:38:33,343 INFO [train.py:761] (5/8) Epoch 33, batch 2500, loss[loss=0.2108, simple_loss=0.279, pruned_loss=0.07136, over 4958.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2986, pruned_loss=0.05726, over 966718.91 frames.], batch size: 12, lr: 4.73e-04
2022-05-29 16:39:11,064 INFO [train.py:761] (5/8) Epoch 33, batch 2550, loss[loss=0.1838, simple_loss=0.2858, pruned_loss=0.04086, over 4723.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2997, pruned_loss=0.05749, over 966777.16 frames.], batch size: 14, lr: 4.73e-04
2022-05-29 16:39:48,917 INFO [train.py:761] (5/8) Epoch 33, batch 2600, loss[loss=0.1857, simple_loss=0.2781, pruned_loss=0.04666, over 4793.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2986, pruned_loss=0.05743, over 966512.12 frames.], batch size: 12, lr: 4.73e-04
2022-05-29 16:40:26,941 INFO [train.py:761] (5/8) Epoch 33, batch 2650, loss[loss=0.2125, simple_loss=0.3002, pruned_loss=0.06241, over 4731.00 frames.], tot_loss[loss=0.2072, simple_loss=0.299, pruned_loss=0.05769, over 965918.38 frames.], batch size: 12, lr: 4.73e-04
2022-05-29 16:41:04,970 INFO [train.py:761] (5/8) Epoch 33, batch 2700, loss[loss=0.1652, simple_loss=0.2662, pruned_loss=0.03205, over 4805.00 frames.], tot_loss[loss=0.2083, simple_loss=0.3002, pruned_loss=0.0582, over 966277.95 frames.], batch size: 12, lr: 4.73e-04
2022-05-29 16:41:43,137 INFO [train.py:761] (5/8) Epoch 33, batch 2750, loss[loss=0.2401, simple_loss=0.3459, pruned_loss=0.06716, over 4791.00 frames.], tot_loss[loss=0.2077, simple_loss=0.3, pruned_loss=0.05767, over 966250.89 frames.], batch size: 26, lr: 4.73e-04
2022-05-29 16:42:20,724 INFO [train.py:761] (5/8) Epoch 33, batch 2800, loss[loss=0.2108, simple_loss=0.3039, pruned_loss=0.05885, over 4813.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2995, pruned_loss=0.05682, over 966994.57 frames.], batch size: 16, lr: 4.73e-04
2022-05-29 16:42:58,619 INFO [train.py:761] (5/8) Epoch 33, batch 2850, loss[loss=0.1911, simple_loss=0.2888, pruned_loss=0.04673, over 4792.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2996, pruned_loss=0.05733, over 967217.93 frames.], batch size: 20, lr: 4.73e-04
2022-05-29 16:43:36,806 INFO [train.py:761] (5/8) Epoch 33, batch 2900, loss[loss=0.184, simple_loss=0.2647, pruned_loss=0.05163, over 4823.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2997, pruned_loss=0.05767, over 967041.63 frames.], batch size: 11, lr: 4.72e-04
2022-05-29 16:44:14,885 INFO [train.py:761] (5/8) Epoch 33, batch 2950, loss[loss=0.1997, simple_loss=0.2912, pruned_loss=0.05407, over 4855.00 frames.], tot_loss[loss=0.207, simple_loss=0.2994, pruned_loss=0.05731, over 966326.86 frames.], batch size: 17, lr: 4.72e-04
2022-05-29 16:44:53,057 INFO [train.py:761] (5/8) Epoch 33, batch 3000, loss[loss=0.2247, simple_loss=0.3246, pruned_loss=0.0624, over 4785.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2992, pruned_loss=0.05683, over 965523.06 frames.], batch size: 16, lr: 4.72e-04
2022-05-29 16:44:53,057 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 16:45:03,229 INFO [train.py:790] (5/8) Epoch 33, validation: loss=0.2018, simple_loss=0.3018, pruned_loss=0.05091, over 944034.00 frames.
2022-05-29 16:45:41,469 INFO [train.py:761] (5/8) Epoch 33, batch 3050, loss[loss=0.2121, simple_loss=0.3019, pruned_loss=0.06115, over 4787.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2997, pruned_loss=0.05767, over 965638.17 frames.], batch size: 14, lr: 4.72e-04
2022-05-29 16:46:19,838 INFO [train.py:761] (5/8) Epoch 33, batch 3100, loss[loss=0.206, simple_loss=0.2944, pruned_loss=0.05883, over 4852.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2996, pruned_loss=0.0585, over 965944.71 frames.], batch size: 13, lr: 4.72e-04
2022-05-29 16:46:57,429 INFO [train.py:761] (5/8) Epoch 33, batch 3150, loss[loss=0.1941, simple_loss=0.2817, pruned_loss=0.05323, over 4730.00 frames.], tot_loss[loss=0.2107, simple_loss=0.3008, pruned_loss=0.0603, over 966895.94 frames.], batch size: 12, lr: 4.72e-04
2022-05-29 16:47:35,310 INFO [train.py:761] (5/8) Epoch 33, batch 3200, loss[loss=0.1895, simple_loss=0.2715, pruned_loss=0.05379, over 4811.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3028, pruned_loss=0.06209, over 967433.94 frames.], batch size: 12, lr: 4.72e-04
2022-05-29 16:48:13,592 INFO [train.py:761] (5/8) Epoch 33, batch 3250, loss[loss=0.2443, simple_loss=0.3208, pruned_loss=0.08389, over 4848.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3038, pruned_loss=0.06394, over 967595.56 frames.], batch size: 18, lr: 4.72e-04
2022-05-29 16:48:51,802 INFO [train.py:761] (5/8) Epoch 33, batch 3300, loss[loss=0.1824, simple_loss=0.2722, pruned_loss=0.04627, over 4677.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3054, pruned_loss=0.06619, over 967760.12 frames.], batch size: 13, lr: 4.72e-04
2022-05-29 16:49:30,036 INFO [train.py:761] (5/8) Epoch 33, batch 3350, loss[loss=0.2211, simple_loss=0.2897, pruned_loss=0.07626, over 4978.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3071, pruned_loss=0.06805, over 968102.12 frames.], batch size: 11, lr: 4.72e-04
2022-05-29 16:50:08,200 INFO [train.py:761] (5/8) Epoch 33, batch 3400, loss[loss=0.1679, simple_loss=0.2602, pruned_loss=0.03779, over 4737.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3093, pruned_loss=0.0699, over 967410.16 frames.], batch size: 12, lr: 4.72e-04
2022-05-29 16:50:47,101 INFO [train.py:761] (5/8) Epoch 33, batch 3450, loss[loss=0.2313, simple_loss=0.3165, pruned_loss=0.07308, over 4852.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3091, pruned_loss=0.06966, over 967845.57 frames.], batch size: 18, lr: 4.72e-04
2022-05-29 16:51:24,973 INFO [train.py:761] (5/8) Epoch 33, batch 3500, loss[loss=0.1822, simple_loss=0.255, pruned_loss=0.05471, over 4641.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3064, pruned_loss=0.06943, over 966664.53 frames.], batch size: 11, lr: 4.72e-04
2022-05-29 16:52:02,912 INFO [train.py:761] (5/8) Epoch 33, batch 3550, loss[loss=0.257, simple_loss=0.3382, pruned_loss=0.08792, over 4859.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3074, pruned_loss=0.0699, over 966428.14 frames.], batch size: 26, lr: 4.72e-04
2022-05-29 16:52:41,011 INFO [train.py:761] (5/8) Epoch 33, batch 3600, loss[loss=0.1753, simple_loss=0.2581, pruned_loss=0.04623, over 4748.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3082, pruned_loss=0.07113, over 966675.30 frames.], batch size: 11, lr: 4.72e-04
2022-05-29 16:53:19,946 INFO [train.py:761] (5/8) Epoch 33, batch 3650, loss[loss=0.1689, simple_loss=0.2502, pruned_loss=0.04383, over 4970.00 frames.], tot_loss[loss=0.225, simple_loss=0.3077, pruned_loss=0.07108, over 966860.61 frames.], batch size: 12, lr: 4.72e-04
2022-05-29 16:53:58,547 INFO [train.py:761] (5/8) Epoch 33, batch 3700, loss[loss=0.2385, simple_loss=0.3309, pruned_loss=0.0731, over 4874.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3092, pruned_loss=0.07229, over 967859.23 frames.], batch size: 15, lr: 4.72e-04
2022-05-29 16:54:36,777 INFO [train.py:761] (5/8) Epoch 33, batch 3750, loss[loss=0.2378, simple_loss=0.3168, pruned_loss=0.07941, over 4761.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3075, pruned_loss=0.07214, over 967955.92 frames.], batch size: 15, lr: 4.72e-04
2022-05-29 16:55:15,034 INFO [train.py:761] (5/8) Epoch 33, batch 3800, loss[loss=0.2222, simple_loss=0.304, pruned_loss=0.07019, over 4663.00 frames.], tot_loss[loss=0.2256, simple_loss=0.307, pruned_loss=0.07211, over 967671.86 frames.], batch size: 13, lr: 4.71e-04
2022-05-29 16:55:52,801 INFO [train.py:761] (5/8) Epoch 33, batch 3850, loss[loss=0.2423, simple_loss=0.3349, pruned_loss=0.07488, over 4850.00 frames.], tot_loss[loss=0.2262, simple_loss=0.3075, pruned_loss=0.07249, over 966597.66 frames.], batch size: 14, lr: 4.71e-04
2022-05-29 16:56:30,987 INFO [train.py:761] (5/8) Epoch 33, batch 3900, loss[loss=0.2522, simple_loss=0.3317, pruned_loss=0.08641, over 4924.00 frames.], tot_loss[loss=0.2256, simple_loss=0.307, pruned_loss=0.07211, over 966800.69 frames.], batch size: 26, lr: 4.71e-04
2022-05-29 16:57:09,141 INFO [train.py:761] (5/8) Epoch 33, batch 3950, loss[loss=0.2076, simple_loss=0.2938, pruned_loss=0.06076, over 4788.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3076, pruned_loss=0.07225, over 966713.11 frames.], batch size: 13, lr: 4.71e-04
2022-05-29 16:57:47,932 INFO [train.py:761] (5/8) Epoch 33, batch 4000, loss[loss=0.2526, simple_loss=0.3248, pruned_loss=0.09023, over 4881.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3066, pruned_loss=0.07186, over 967133.41 frames.], batch size: 15, lr: 4.71e-04
2022-05-29 16:58:25,826 INFO [train.py:761] (5/8) Epoch 33, batch 4050, loss[loss=0.2251, simple_loss=0.3199, pruned_loss=0.06516, over 4967.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3059, pruned_loss=0.07148, over 966566.22 frames.], batch size: 14, lr: 4.71e-04
2022-05-29 16:59:03,239 INFO [train.py:761] (5/8) Epoch 33, batch 4100, loss[loss=0.238, simple_loss=0.3219, pruned_loss=0.07711, over 4710.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3068, pruned_loss=0.07143, over 966085.31 frames.], batch size: 14, lr: 4.71e-04
2022-05-29 16:59:41,544 INFO [train.py:761] (5/8) Epoch 33, batch 4150, loss[loss=0.2237, simple_loss=0.3209, pruned_loss=0.06321, over 4882.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3072, pruned_loss=0.07163, over 966269.86 frames.], batch size: 15, lr: 4.71e-04
2022-05-29 17:00:19,774 INFO [train.py:761] (5/8) Epoch 33, batch 4200, loss[loss=0.2533, simple_loss=0.328, pruned_loss=0.08935, over 4975.00 frames.], tot_loss[loss=0.225, simple_loss=0.3068, pruned_loss=0.07159, over 966179.68 frames.], batch size: 14, lr: 4.71e-04
2022-05-29 17:00:58,300 INFO [train.py:761] (5/8) Epoch 33, batch 4250, loss[loss=0.156, simple_loss=0.2402, pruned_loss=0.03596, over 4662.00 frames.], tot_loss[loss=0.225, simple_loss=0.3072, pruned_loss=0.07146, over 965861.35 frames.], batch size: 12, lr: 4.71e-04
2022-05-29 17:01:36,399 INFO [train.py:761] (5/8) Epoch 33, batch 4300, loss[loss=0.2186, simple_loss=0.3008, pruned_loss=0.06819, over 4862.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3079, pruned_loss=0.07186, over 966779.27 frames.], batch size: 13, lr: 4.71e-04
2022-05-29 17:02:14,926 INFO [train.py:761] (5/8) Epoch 33, batch 4350, loss[loss=0.2484, simple_loss=0.3353, pruned_loss=0.08079, over 4908.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3081, pruned_loss=0.07178, over 966712.10 frames.], batch size: 14, lr: 4.71e-04
2022-05-29 17:02:53,060 INFO [train.py:761] (5/8) Epoch 33, batch 4400, loss[loss=0.1765, simple_loss=0.2763, pruned_loss=0.03833, over 4894.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3078, pruned_loss=0.07166, over 965180.23 frames.], batch size: 17, lr: 4.71e-04
2022-05-29 17:03:31,128 INFO [train.py:761] (5/8) Epoch 33, batch 4450, loss[loss=0.2664, simple_loss=0.3671, pruned_loss=0.0828, over 4882.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3088, pruned_loss=0.07249, over 965033.63 frames.], batch size: 15, lr: 4.71e-04
2022-05-29 17:04:09,458 INFO [train.py:761] (5/8) Epoch 33, batch 4500, loss[loss=0.2742, simple_loss=0.3505, pruned_loss=0.099, over 4904.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3079, pruned_loss=0.0717, over 965767.45 frames.], batch size: 17, lr: 4.71e-04
2022-05-29 17:04:48,158 INFO [train.py:761] (5/8) Epoch 33, batch 4550, loss[loss=0.2268, simple_loss=0.3252, pruned_loss=0.06423, over 4852.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3079, pruned_loss=0.07168, over 965930.40 frames.], batch size: 13, lr: 4.71e-04
2022-05-29 17:05:25,937 INFO [train.py:761] (5/8) Epoch 33, batch 4600, loss[loss=0.2242, simple_loss=0.3135, pruned_loss=0.06744, over 4878.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3059, pruned_loss=0.07081, over 964700.32 frames.], batch size: 15, lr: 4.71e-04
2022-05-29 17:06:04,602 INFO [train.py:761] (5/8) Epoch 33, batch 4650, loss[loss=0.2104, simple_loss=0.2842, pruned_loss=0.06829, over 4742.00 frames.], tot_loss[loss=0.2263, simple_loss=0.308, pruned_loss=0.07236, over 966519.28 frames.], batch size: 12, lr: 4.71e-04
2022-05-29 17:06:42,308 INFO [train.py:761] (5/8) Epoch 33, batch 4700, loss[loss=0.1959, simple_loss=0.2781, pruned_loss=0.05689, over 4997.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3062, pruned_loss=0.07138, over 966693.12 frames.], batch size: 13, lr: 4.71e-04
2022-05-29 17:07:20,553 INFO [train.py:761] (5/8) Epoch 33, batch 4750, loss[loss=0.2408, simple_loss=0.3247, pruned_loss=0.07844, over 4965.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3058, pruned_loss=0.07149, over 965865.30 frames.], batch size: 16, lr: 4.70e-04
2022-05-29 17:07:58,507 INFO [train.py:761] (5/8) Epoch 33, batch 4800, loss[loss=0.2414, simple_loss=0.316, pruned_loss=0.08345, over 4773.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3059, pruned_loss=0.07033, over 964872.63 frames.], batch size: 15, lr: 4.70e-04
2022-05-29 17:08:36,385 INFO [train.py:761] (5/8) Epoch 33, batch 4850, loss[loss=0.2238, simple_loss=0.304, pruned_loss=0.07179, over 4916.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3073, pruned_loss=0.07101, over 965984.58 frames.], batch size: 25, lr: 4.70e-04
2022-05-29 17:09:14,181 INFO [train.py:761] (5/8) Epoch 33, batch 4900, loss[loss=0.195, simple_loss=0.2931, pruned_loss=0.04848, over 4790.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3064, pruned_loss=0.07063, over 965559.32 frames.], batch size: 14, lr: 4.70e-04
2022-05-29 17:09:52,551 INFO [train.py:761] (5/8) Epoch 33, batch 4950, loss[loss=0.2793, simple_loss=0.3488, pruned_loss=0.1049, over 4904.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3063, pruned_loss=0.07054, over 965533.61 frames.], batch size: 48, lr: 4.70e-04
2022-05-29 17:10:30,403 INFO [train.py:761] (5/8) Epoch 33, batch 5000, loss[loss=0.1863, simple_loss=0.2633, pruned_loss=0.05468, over 4739.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3068, pruned_loss=0.07093, over 966720.82 frames.], batch size: 11, lr: 4.70e-04
2022-05-29 17:11:08,653 INFO [train.py:761] (5/8) Epoch 33, batch 5050, loss[loss=0.2036, simple_loss=0.2717, pruned_loss=0.06776, over 4733.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3045, pruned_loss=0.07004, over 966302.83 frames.], batch size: 11, lr: 4.70e-04
2022-05-29 17:11:47,020 INFO [train.py:761] (5/8) Epoch 33, batch 5100, loss[loss=0.2434, simple_loss=0.3269, pruned_loss=0.07993, over 4866.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3057, pruned_loss=0.07049, over 967077.77 frames.], batch size: 17, lr: 4.70e-04
2022-05-29 17:12:25,946 INFO [train.py:761] (5/8) Epoch 33, batch 5150, loss[loss=0.2248, simple_loss=0.2869, pruned_loss=0.08142, over 4980.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3053, pruned_loss=0.07065, over 967152.88 frames.], batch size: 12, lr: 4.70e-04
2022-05-29 17:13:04,100 INFO [train.py:761] (5/8) Epoch 33, batch 5200, loss[loss=0.1665, simple_loss=0.2578, pruned_loss=0.03761, over 4871.00 frames.], tot_loss[loss=0.223, simple_loss=0.3049, pruned_loss=0.07054, over 967729.20 frames.], batch size: 12, lr: 4.70e-04
2022-05-29 17:13:42,329 INFO [train.py:761] (5/8) Epoch 33, batch 5250, loss[loss=0.211, simple_loss=0.2889, pruned_loss=0.06654, over 4735.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3041, pruned_loss=0.07041, over 967917.25 frames.], batch size: 11, lr: 4.70e-04
2022-05-29 17:14:20,190 INFO [train.py:761] (5/8) Epoch 33, batch 5300, loss[loss=0.2339, simple_loss=0.3225, pruned_loss=0.07265, over 4987.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3037, pruned_loss=0.06997, over 966720.71 frames.], batch size: 14, lr: 4.70e-04
2022-05-29 17:14:59,117 INFO [train.py:761] (5/8) Epoch 33, batch 5350, loss[loss=0.2077, simple_loss=0.2971, pruned_loss=0.05914, over 4987.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3061, pruned_loss=0.07106, over 967410.81 frames.], batch size: 13, lr: 4.70e-04
2022-05-29 17:15:37,568 INFO [train.py:761] (5/8) Epoch 33, batch 5400, loss[loss=0.2548, simple_loss=0.342, pruned_loss=0.08377, over 4773.00 frames.], tot_loss[loss=0.225, simple_loss=0.3067, pruned_loss=0.07169, over 967116.62 frames.], batch size: 20, lr: 4.70e-04
2022-05-29 17:16:15,919 INFO [train.py:761] (5/8) Epoch 33, batch 5450, loss[loss=0.202, simple_loss=0.2955, pruned_loss=0.05425, over 4834.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3066, pruned_loss=0.07139, over 967882.35 frames.], batch size: 18, lr: 4.70e-04
2022-05-29 17:16:54,302 INFO [train.py:761] (5/8) Epoch 33, batch 5500, loss[loss=0.2076, simple_loss=0.2949, pruned_loss=0.06015, over 4813.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3057, pruned_loss=0.07094, over 968435.17 frames.], batch size: 20, lr: 4.70e-04
2022-05-29 17:17:32,650 INFO [train.py:761] (5/8) Epoch 33, batch 5550, loss[loss=0.2368, simple_loss=0.3164, pruned_loss=0.07859, over 4913.00 frames.], tot_loss[loss=0.2232, simple_loss=0.305, pruned_loss=0.0707, over 968379.01 frames.], batch size: 14, lr: 4.70e-04
2022-05-29 17:18:10,974 INFO [train.py:761] (5/8) Epoch 33, batch 5600, loss[loss=0.2926, simple_loss=0.3566, pruned_loss=0.1143, over 4885.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3053, pruned_loss=0.07054, over 967695.00 frames.], batch size: 17, lr: 4.70e-04
2022-05-29 17:18:49,335 INFO [train.py:761] (5/8) Epoch 33, batch 5650, loss[loss=0.2168, simple_loss=0.2861, pruned_loss=0.07373, over 4840.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3035, pruned_loss=0.0698, over 966906.87 frames.], batch size: 11, lr: 4.70e-04
2022-05-29 17:19:27,728 INFO [train.py:761] (5/8) Epoch 33, batch 5700, loss[loss=0.2457, simple_loss=0.3181, pruned_loss=0.08668, over 4726.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3044, pruned_loss=0.06964, over 967205.08 frames.], batch size: 12, lr: 4.69e-04
2022-05-29 17:20:05,476 INFO [train.py:761] (5/8) Epoch 33, batch 5750, loss[loss=0.2154, simple_loss=0.3171, pruned_loss=0.05681, over 4718.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3034, pruned_loss=0.06872, over 966795.37 frames.], batch size: 14, lr: 4.69e-04
2022-05-29 17:20:43,381 INFO [train.py:761] (5/8) Epoch 33, batch 5800, loss[loss=0.2603, simple_loss=0.3349, pruned_loss=0.09288, over 4879.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3035, pruned_loss=0.06968, over 965999.72 frames.], batch size: 17, lr: 4.69e-04
2022-05-29 17:21:21,995 INFO [train.py:761] (5/8) Epoch 33, batch 5850, loss[loss=0.2383, simple_loss=0.3079, pruned_loss=0.08438, over 4881.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3054, pruned_loss=0.07044, over 966106.42 frames.], batch size: 15, lr: 4.69e-04
2022-05-29 17:22:00,917 INFO [train.py:761] (5/8) Epoch 33, batch 5900, loss[loss=0.1773, simple_loss=0.2592, pruned_loss=0.04775, over 4823.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3052, pruned_loss=0.07076, over 965986.94 frames.], batch size: 11, lr: 4.69e-04
2022-05-29 17:22:39,269 INFO [train.py:761] (5/8) Epoch 33, batch 5950, loss[loss=0.1967, simple_loss=0.2758, pruned_loss=0.0588, over 4799.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3061, pruned_loss=0.07129, over 965737.02 frames.], batch size: 12, lr: 4.69e-04
2022-05-29 17:23:17,645 INFO [train.py:761] (5/8) Epoch 33, batch 6000, loss[loss=0.2304, simple_loss=0.3088, pruned_loss=0.07603, over 4918.00 frames.], tot_loss[loss=0.2233, simple_loss=0.305, pruned_loss=0.07081, over 965180.21 frames.], batch size: 13, lr: 4.69e-04
2022-05-29 17:23:17,645 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 17:23:27,532 INFO [train.py:790] (5/8) Epoch 33, validation: loss=0.1992, simple_loss=0.3008, pruned_loss=0.04875, over 944034.00 frames.
2022-05-29 17:24:06,245 INFO [train.py:761] (5/8) Epoch 33, batch 6050, loss[loss=0.2121, simple_loss=0.3025, pruned_loss=0.06092, over 4672.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3048, pruned_loss=0.0708, over 964947.94 frames.], batch size: 13, lr: 4.69e-04
2022-05-29 17:24:44,528 INFO [train.py:761] (5/8) Epoch 33, batch 6100, loss[loss=0.2471, simple_loss=0.3248, pruned_loss=0.08468, over 4824.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3043, pruned_loss=0.07043, over 965194.87 frames.], batch size: 18, lr: 4.69e-04
2022-05-29 17:25:22,550 INFO [train.py:761] (5/8) Epoch 33, batch 6150, loss[loss=0.2278, simple_loss=0.3092, pruned_loss=0.07325, over 4669.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3039, pruned_loss=0.07072, over 964629.89 frames.], batch size: 12, lr: 4.69e-04
2022-05-29 17:26:01,070 INFO [train.py:761] (5/8) Epoch 33, batch 6200, loss[loss=0.2228, simple_loss=0.2935, pruned_loss=0.07609, over 4885.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3033, pruned_loss=0.0706, over 965441.29 frames.], batch size: 12, lr: 4.69e-04
2022-05-29 17:26:39,687 INFO [train.py:761] (5/8) Epoch 33, batch 6250, loss[loss=0.2546, simple_loss=0.3392, pruned_loss=0.085, over 4955.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3041, pruned_loss=0.07005, over 966693.76 frames.], batch size: 16, lr: 4.69e-04
2022-05-29 17:27:17,538 INFO [train.py:761] (5/8) Epoch 33, batch 6300, loss[loss=0.2156, simple_loss=0.2982, pruned_loss=0.06644, over 4864.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3049, pruned_loss=0.07063, over 966009.36 frames.], batch size: 13, lr: 4.69e-04
2022-05-29 17:27:55,485 INFO [train.py:761] (5/8) Epoch 33, batch 6350, loss[loss=0.222, simple_loss=0.2981, pruned_loss=0.07297, over 4869.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3043, pruned_loss=0.07032, over 966798.69 frames.], batch size: 17, lr: 4.69e-04
2022-05-29 17:28:33,388 INFO [train.py:761] (5/8) Epoch 33, batch 6400, loss[loss=0.205, simple_loss=0.2855, pruned_loss=0.06231, over 4804.00 frames.], tot_loss[loss=0.223, simple_loss=0.3051, pruned_loss=0.07047, over 967884.38 frames.], batch size: 12, lr: 4.69e-04
2022-05-29 17:29:12,255 INFO [train.py:761] (5/8) Epoch 33, batch 6450, loss[loss=0.251, simple_loss=0.3409, pruned_loss=0.08059, over 4910.00 frames.], tot_loss[loss=0.2217, simple_loss=0.304, pruned_loss=0.06971, over 967377.69 frames.], batch size: 14, lr: 4.69e-04
2022-05-29 17:29:50,126 INFO [train.py:761] (5/8) Epoch 33, batch 6500, loss[loss=0.2097, simple_loss=0.3108, pruned_loss=0.05425, over 4843.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3042, pruned_loss=0.0703, over 968257.42 frames.], batch size: 14, lr: 4.69e-04
2022-05-29 17:30:28,474 INFO [train.py:761] (5/8) Epoch 33, batch 6550, loss[loss=0.2027, simple_loss=0.2895, pruned_loss=0.05795, over 4908.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3027, pruned_loss=0.06891, over 967713.19 frames.], batch size: 14, lr: 4.69e-04
2022-05-29 17:31:06,544 INFO [train.py:761] (5/8) Epoch 33, batch 6600, loss[loss=0.2516, simple_loss=0.3401, pruned_loss=0.0816, over 4860.00 frames.], tot_loss[loss=0.2206, simple_loss=0.3027, pruned_loss=0.06931, over 967034.26 frames.], batch size: 26, lr: 4.69e-04
2022-05-29 17:31:45,006 INFO [train.py:761] (5/8) Epoch 33, batch 6650, loss[loss=0.1843, simple_loss=0.2718, pruned_loss=0.04841, over 4976.00 frames.], tot_loss[loss=0.2201, simple_loss=0.3025, pruned_loss=0.06888, over 965890.62 frames.], batch size: 14, lr: 4.68e-04
2022-05-29 17:32:23,335 INFO [train.py:761] (5/8) Epoch 33, batch 6700, loss[loss=0.2328, simple_loss=0.3208, pruned_loss=0.07241, over 4974.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3025, pruned_loss=0.06868, over 966422.88 frames.], batch size: 14, lr: 4.68e-04
2022-05-29 17:33:15,470 INFO [train.py:761] (5/8) Epoch 34, batch 0, loss[loss=0.1858, simple_loss=0.2806, pruned_loss=0.04556, over 4644.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2806, pruned_loss=0.04556, over 4644.00 frames.], batch size: 11, lr: 4.68e-04
2022-05-29 17:33:53,945 INFO [train.py:761] (5/8) Epoch 34, batch 50, loss[loss=0.2283, simple_loss=0.3096, pruned_loss=0.07352, over 4791.00 frames.], tot_loss[loss=0.21, simple_loss=0.2989, pruned_loss=0.06053, over 217590.22 frames.], batch size: 14, lr: 4.68e-04
2022-05-29 17:34:32,160 INFO [train.py:761] (5/8) Epoch 34, batch 100, loss[loss=0.1508, simple_loss=0.2373, pruned_loss=0.03216, over 4975.00 frames.], tot_loss[loss=0.2051, simple_loss=0.296, pruned_loss=0.05711, over 383821.59 frames.], batch size: 12, lr: 4.68e-04
2022-05-29 17:35:10,494 INFO [train.py:761] (5/8) Epoch 34, batch 150, loss[loss=0.2076, simple_loss=0.3047, pruned_loss=0.05528, over 4971.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2922, pruned_loss=0.05459, over 512857.57 frames.], batch size: 15, lr: 4.68e-04
2022-05-29 17:35:48,694 INFO [train.py:761] (5/8) Epoch 34, batch 200, loss[loss=0.222, simple_loss=0.3187, pruned_loss=0.06269, over 4975.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2922, pruned_loss=0.05474, over 612875.56 frames.], batch size: 15, lr: 4.68e-04
2022-05-29 17:36:26,960 INFO [train.py:761] (5/8) Epoch 34, batch 250, loss[loss=0.172, simple_loss=0.2623, pruned_loss=0.0409, over 4650.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2933, pruned_loss=0.05452, over 690945.50 frames.], batch size: 12, lr: 4.68e-04
2022-05-29 17:37:05,202 INFO [train.py:761] (5/8) Epoch 34, batch 300, loss[loss=0.2023, simple_loss=0.3018, pruned_loss=0.05144, over 4974.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2936, pruned_loss=0.0546, over 752167.25 frames.], batch size: 15, lr: 4.68e-04
2022-05-29 17:37:43,627 INFO [train.py:761] (5/8) Epoch 34, batch 350, loss[loss=0.1981, simple_loss=0.2855, pruned_loss=0.05539, over 4790.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2938, pruned_loss=0.05421, over 799912.62 frames.], batch size: 13, lr: 4.68e-04
2022-05-29 17:38:21,325 INFO [train.py:761] (5/8) Epoch 34, batch 400, loss[loss=0.2249, simple_loss=0.3002, pruned_loss=0.07474, over 4738.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2942, pruned_loss=0.05419, over 835682.97 frames.], batch size: 12, lr: 4.68e-04
2022-05-29 17:38:59,628 INFO [train.py:761] (5/8) Epoch 34, batch 450, loss[loss=0.2573, simple_loss=0.3445, pruned_loss=0.08512, over 4936.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2928, pruned_loss=0.05388, over 863248.43 frames.], batch size: 46, lr: 4.68e-04
2022-05-29 17:39:37,725 INFO [train.py:761] (5/8) Epoch 34, batch 500, loss[loss=0.2061, simple_loss=0.3075, pruned_loss=0.05228, over 4849.00 frames.], tot_loss[loss=0.199, simple_loss=0.2914, pruned_loss=0.05328, over 886473.76 frames.], batch size: 14, lr: 4.68e-04
2022-05-29 17:40:15,877 INFO [train.py:761] (5/8) Epoch 34, batch 550, loss[loss=0.2023, simple_loss=0.2929, pruned_loss=0.05583, over 4727.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2938, pruned_loss=0.0538, over 903681.27 frames.], batch size: 12, lr: 4.68e-04
2022-05-29 17:40:54,076 INFO [train.py:761] (5/8) Epoch 34, batch 600, loss[loss=0.2104, simple_loss=0.3092, pruned_loss=0.05582, over 4846.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2941, pruned_loss=0.05437, over 917952.23 frames.], batch size: 14, lr: 4.68e-04
2022-05-29 17:41:31,858 INFO [train.py:761] (5/8) Epoch 34, batch 650, loss[loss=0.1759, simple_loss=0.2551, pruned_loss=0.04835, over 4810.00 frames.], tot_loss[loss=0.202, simple_loss=0.2947, pruned_loss=0.05468, over 929207.98 frames.], batch size: 12, lr: 4.68e-04
2022-05-29 17:42:09,997 INFO [train.py:761] (5/8) Epoch 34, batch 700, loss[loss=0.2081, simple_loss=0.2918, pruned_loss=0.06219, over 4980.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2953, pruned_loss=0.05508, over 939189.38 frames.], batch size: 11, lr: 4.68e-04
2022-05-29 17:42:48,093 INFO [train.py:761] (5/8) Epoch 34, batch 750, loss[loss=0.2014, simple_loss=0.2885, pruned_loss=0.05714, over 4998.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2948, pruned_loss=0.05493, over 945718.07 frames.], batch size: 11, lr: 4.68e-04
2022-05-29 17:43:25,771 INFO [train.py:761] (5/8) Epoch 34, batch 800, loss[loss=0.1992, simple_loss=0.2951, pruned_loss=0.05166, over 4979.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2961, pruned_loss=0.05546, over 950167.32 frames.], batch size: 14, lr: 4.68e-04
2022-05-29 17:44:03,871 INFO [train.py:761] (5/8) Epoch 34, batch 850, loss[loss=0.1819, simple_loss=0.2747, pruned_loss=0.04458, over 4784.00 frames.], tot_loss[loss=0.205, simple_loss=0.2973, pruned_loss=0.05636, over 953505.70 frames.], batch size: 13, lr: 4.67e-04
2022-05-29 17:44:41,383 INFO [train.py:761] (5/8) Epoch 34, batch 900, loss[loss=0.2103, simple_loss=0.3151, pruned_loss=0.05274, over 4879.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2983, pruned_loss=0.05667, over 955675.17 frames.], batch size: 15, lr: 4.67e-04
2022-05-29 17:45:19,032 INFO [train.py:761] (5/8) Epoch 34, batch 950, loss[loss=0.2191, simple_loss=0.3098, pruned_loss=0.06425, over 4673.00 frames.], tot_loss[loss=0.206, simple_loss=0.2986, pruned_loss=0.05669, over 958402.08 frames.], batch size: 13, lr: 4.67e-04
2022-05-29 17:45:57,191 INFO [train.py:761] (5/8) Epoch 34, batch 1000, loss[loss=0.1924, simple_loss=0.2726, pruned_loss=0.05606, over 4793.00 frames.], tot_loss[loss=0.2066, simple_loss=0.299, pruned_loss=0.05704, over 959176.65 frames.], batch size: 13, lr: 4.67e-04
2022-05-29 17:46:35,303 INFO [train.py:761] (5/8) Epoch 34, batch 1050, loss[loss=0.2175, simple_loss=0.3236, pruned_loss=0.05568, over 4984.00 frames.], tot_loss[loss=0.2056, simple_loss=0.298, pruned_loss=0.05658, over 959330.46 frames.], batch size: 15, lr: 4.67e-04
2022-05-29 17:47:13,102 INFO [train.py:761] (5/8) Epoch 34, batch 1100, loss[loss=0.22, simple_loss=0.3064, pruned_loss=0.06682, over 4800.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2991, pruned_loss=0.05699, over 960875.86 frames.], batch size: 12, lr: 4.67e-04
2022-05-29 17:47:51,017 INFO [train.py:761] (5/8) Epoch 34, batch 1150, loss[loss=0.2135, simple_loss=0.3145, pruned_loss=0.05625, over 4842.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2988, pruned_loss=0.057, over 961980.40 frames.], batch size: 26, lr: 4.67e-04
2022-05-29 17:48:29,019 INFO [train.py:761] (5/8) Epoch 34, batch 1200, loss[loss=0.2299, simple_loss=0.3323, pruned_loss=0.06372, over 4768.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2984, pruned_loss=0.05663, over 962913.38 frames.], batch size: 20, lr: 4.67e-04
2022-05-29 17:49:14,976 INFO [train.py:761] (5/8) Epoch 34, batch 1250, loss[loss=0.1818, simple_loss=0.2626, pruned_loss=0.05053, over 4556.00 frames.], tot_loss[loss=0.2065, simple_loss=0.299, pruned_loss=0.05699, over 963690.25 frames.], batch size: 10, lr: 4.67e-04
2022-05-29 17:49:52,833 INFO [train.py:761] (5/8) Epoch 34, batch 1300, loss[loss=0.1619, simple_loss=0.2473, pruned_loss=0.03828, over 4739.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2993, pruned_loss=0.05728, over 964494.83 frames.], batch size: 11, lr: 4.67e-04
2022-05-29 17:50:31,343 INFO [train.py:761] (5/8) Epoch 34, batch 1350, loss[loss=0.2263, simple_loss=0.3204, pruned_loss=0.06608, over 4934.00 frames.], tot_loss[loss=0.207, simple_loss=0.2993, pruned_loss=0.05735, over 964003.44 frames.], batch size: 44, lr: 4.67e-04
2022-05-29 17:51:08,996 INFO [train.py:761] (5/8) Epoch 34, batch 1400, loss[loss=0.2382, simple_loss=0.3297, pruned_loss=0.07336, over 4822.00 frames.], tot_loss[loss=0.2077, simple_loss=0.3001, pruned_loss=0.0576, over 963861.23 frames.], batch size: 18, lr: 4.67e-04
2022-05-29 17:51:51,043 INFO [train.py:761] (5/8) Epoch 34, batch 1450, loss[loss=0.1537, simple_loss=0.2497, pruned_loss=0.02886, over 4654.00 frames.], tot_loss[loss=0.2065, simple_loss=0.299, pruned_loss=0.05697, over 964576.48 frames.], batch size: 11, lr: 4.67e-04
2022-05-29 17:52:29,257 INFO [train.py:761] (5/8) Epoch 34, batch 1500, loss[loss=0.2572, simple_loss=0.3455, pruned_loss=0.08444, over 4906.00 frames.], tot_loss[loss=0.2076, simple_loss=0.3004, pruned_loss=0.05736, over 965326.77 frames.], batch size: 46, lr: 4.67e-04
2022-05-29 17:53:07,637 INFO [train.py:761] (5/8) Epoch 34, batch 1550, loss[loss=0.2027, simple_loss=0.2956, pruned_loss=0.05493, over 4660.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2997, pruned_loss=0.05729, over 965137.55 frames.], batch size: 12, lr: 4.67e-04
2022-05-29 17:53:45,246 INFO [train.py:761] (5/8) Epoch 34, batch 1600, loss[loss=0.1859, simple_loss=0.273, pruned_loss=0.04939, over 4815.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2986, pruned_loss=0.05709, over 965771.44 frames.], batch size: 12, lr: 4.67e-04
2022-05-29 17:54:23,522 INFO [train.py:761] (5/8) Epoch 34, batch 1650, loss[loss=0.2111, simple_loss=0.3128, pruned_loss=0.05466, over 4777.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2979, pruned_loss=0.05669, over 964842.49 frames.], batch size: 14, lr: 4.67e-04
2022-05-29 17:55:01,301 INFO [train.py:761] (5/8) Epoch 34, batch 1700, loss[loss=0.2583, simple_loss=0.3543, pruned_loss=0.0811, over 4806.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2988, pruned_loss=0.05737, over 964823.11 frames.], batch size: 16, lr: 4.67e-04
2022-05-29 17:55:46,402 INFO [train.py:761] (5/8) Epoch 34, batch 1750, loss[loss=0.222, simple_loss=0.3174, pruned_loss=0.0633, over 4855.00 frames.], tot_loss[loss=0.208, simple_loss=0.2997, pruned_loss=0.0581, over 965966.51 frames.], batch size: 13, lr: 4.67e-04
2022-05-29 17:56:24,077 INFO [train.py:761] (5/8) Epoch 34, batch 1800, loss[loss=0.2685, simple_loss=0.3746, pruned_loss=0.08116, over 4960.00 frames.], tot_loss[loss=0.2091, simple_loss=0.3012, pruned_loss=0.05844, over 966904.08 frames.], batch size: 27, lr: 4.66e-04
2022-05-29 17:57:02,153 INFO [train.py:761] (5/8) Epoch 34, batch 1850, loss[loss=0.1942, simple_loss=0.3044, pruned_loss=0.04197, over 4713.00 frames.], tot_loss[loss=0.2084, simple_loss=0.3011, pruned_loss=0.05784, over 967538.57 frames.], batch size: 14, lr: 4.66e-04
2022-05-29 17:57:39,896 INFO [train.py:761] (5/8) Epoch 34, batch 1900, loss[loss=0.1761, simple_loss=0.2806, pruned_loss=0.03582, over 4672.00 frames.], tot_loss[loss=0.207, simple_loss=0.3001, pruned_loss=0.057, over 967877.56 frames.], batch size: 13, lr: 4.66e-04
2022-05-29 17:58:17,996 INFO [train.py:761] (5/8) Epoch 34, batch 1950, loss[loss=0.2149, simple_loss=0.3089, pruned_loss=0.06049, over 4765.00 frames.], tot_loss[loss=0.2069, simple_loss=0.3, pruned_loss=0.05687, over 967049.45 frames.], batch size: 16, lr: 4.66e-04
2022-05-29 17:58:55,949 INFO [train.py:761] (5/8) Epoch 34, batch 2000, loss[loss=0.223, simple_loss=0.3161, pruned_loss=0.06493, over 4782.00 frames.], tot_loss[loss=0.207, simple_loss=0.2999, pruned_loss=0.057, over 965729.71 frames.], batch size: 15, lr: 4.66e-04
2022-05-29 17:59:33,946 INFO [train.py:761] (5/8) Epoch 34, batch 2050, loss[loss=0.2073, simple_loss=0.3043, pruned_loss=0.05514, over 4713.00 frames.], tot_loss[loss=0.206, simple_loss=0.2992, pruned_loss=0.05645, over 965845.82 frames.], batch size: 14, lr: 4.66e-04
2022-05-29 18:00:12,101 INFO [train.py:761] (5/8) Epoch 34, batch 2100, loss[loss=0.2066, simple_loss=0.3283, pruned_loss=0.04248, over 4786.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2996, pruned_loss=0.05659, over 966226.00 frames.], batch size: 15, lr: 4.66e-04
2022-05-29 18:00:49,851 INFO [train.py:761] (5/8) Epoch 34, batch 2150, loss[loss=0.1879, simple_loss=0.2833, pruned_loss=0.0463, over 4968.00 frames.], tot_loss[loss=0.2073, simple_loss=0.3005, pruned_loss=0.05702, over 967792.11 frames.], batch size: 14, lr: 4.66e-04
2022-05-29 18:01:35,006 INFO [train.py:761] (5/8) Epoch 34, batch 2200, loss[loss=0.2395, simple_loss=0.323, pruned_loss=0.07803, over 4768.00 frames.], tot_loss[loss=0.2064, simple_loss=0.3, pruned_loss=0.05638, over 967365.60 frames.], batch size: 20, lr: 4.66e-04
2022-05-29 18:02:13,465 INFO [train.py:761] (5/8) Epoch 34, batch 2250, loss[loss=0.2329, simple_loss=0.3174, pruned_loss=0.07423, over 4794.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2994, pruned_loss=0.0565, over 966590.35 frames.], batch size: 25, lr: 4.66e-04
2022-05-29 18:02:51,186 INFO [train.py:761] (5/8) Epoch 34, batch 2300, loss[loss=0.2199, simple_loss=0.3241, pruned_loss=0.05783, over 4900.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2995, pruned_loss=0.05654, over 966453.68 frames.], batch size: 17, lr: 4.66e-04
2022-05-29 18:03:29,345 INFO [train.py:761] (5/8) Epoch 34, batch 2350, loss[loss=0.1874, simple_loss=0.2698, pruned_loss=0.05246, over 4792.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2999, pruned_loss=0.05644, over 966392.31 frames.], batch size: 13, lr: 4.66e-04
2022-05-29 18:04:06,838 INFO [train.py:761] (5/8) Epoch 34, batch 2400, loss[loss=0.2009, simple_loss=0.2944, pruned_loss=0.0537, over 4837.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2988, pruned_loss=0.0561, over 965662.42 frames.], batch size: 20, lr: 4.66e-04
2022-05-29 18:04:45,029 INFO [train.py:761] (5/8) Epoch 34, batch 2450, loss[loss=0.2051, simple_loss=0.3059, pruned_loss=0.05211, over 4910.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2989, pruned_loss=0.05587, over 966577.88 frames.], batch size: 13, lr: 4.66e-04
2022-05-29 18:05:23,008 INFO [train.py:761] (5/8) Epoch 34, batch 2500, loss[loss=0.2069, simple_loss=0.3118, pruned_loss=0.05097, over 4720.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2991, pruned_loss=0.05606, over 965912.34 frames.], batch size: 13, lr: 4.66e-04
2022-05-29 18:06:00,909 INFO [train.py:761] (5/8) Epoch 34, batch 2550, loss[loss=0.1586, simple_loss=0.2515, pruned_loss=0.03283, over 4890.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2993, pruned_loss=0.05613, over 965337.02 frames.], batch size: 12, lr: 4.66e-04
2022-05-29 18:06:38,591 INFO [train.py:761] (5/8) Epoch 34, batch 2600, loss[loss=0.1782, simple_loss=0.2811, pruned_loss=0.03765, over 4789.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2986, pruned_loss=0.05578, over 966372.79 frames.], batch size: 14, lr: 4.66e-04
2022-05-29 18:07:23,842 INFO [train.py:761] (5/8) Epoch 34, batch 2650, loss[loss=0.2058, simple_loss=0.2886, pruned_loss=0.06147, over 4670.00 frames.], tot_loss[loss=0.2068, simple_loss=0.3001, pruned_loss=0.05679, over 966939.86 frames.], batch size: 12, lr: 4.66e-04
2022-05-29 18:08:01,026 INFO [train.py:761] (5/8) Epoch 34, batch 2700, loss[loss=0.196, simple_loss=0.2961, pruned_loss=0.04798, over 4969.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2995, pruned_loss=0.0566, over 966928.06 frames.], batch size: 15, lr: 4.66e-04
2022-05-29 18:08:39,229 INFO [train.py:761] (5/8) Epoch 34, batch 2750, loss[loss=0.1932, simple_loss=0.2693, pruned_loss=0.05852, over 4968.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2993, pruned_loss=0.05644, over 967658.31 frames.], batch size: 12, lr: 4.65e-04
2022-05-29 18:09:17,397 INFO [train.py:761] (5/8) Epoch 34, batch 2800, loss[loss=0.2159, simple_loss=0.3214, pruned_loss=0.05517, over 4900.00 frames.], tot_loss[loss=0.2051, simple_loss=0.298, pruned_loss=0.05609, over 967454.19 frames.], batch size: 45, lr: 4.65e-04
2022-05-29 18:09:55,521 INFO [train.py:761] (5/8) Epoch 34, batch 2850, loss[loss=0.1784, simple_loss=0.272, pruned_loss=0.04238, over 4727.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2969, pruned_loss=0.05567, over 967488.41 frames.], batch size: 11, lr: 4.65e-04
2022-05-29 18:10:33,500 INFO [train.py:761] (5/8) Epoch 34, batch 2900, loss[loss=0.2354, simple_loss=0.3314, pruned_loss=0.0697, over 4721.00 frames.], tot_loss[loss=0.204, simple_loss=0.297, pruned_loss=0.05554, over 966259.19 frames.], batch size: 14, lr: 4.65e-04
2022-05-29 18:11:11,599 INFO [train.py:761] (5/8) Epoch 34, batch 2950, loss[loss=0.2538, simple_loss=0.3294, pruned_loss=0.08912, over 4879.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2982, pruned_loss=0.05649, over 965398.17 frames.], batch size: 46, lr: 4.65e-04
2022-05-29 18:11:49,438 INFO [train.py:761] (5/8) Epoch 34, batch 3000, loss[loss=0.2435, simple_loss=0.3217, pruned_loss=0.08265, over 4948.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2979, pruned_loss=0.05615, over 965791.95 frames.], batch size: 16, lr: 4.65e-04
2022-05-29 18:11:49,438 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 18:11:59,433 INFO [train.py:790] (5/8) Epoch 34, validation: loss=0.2051, simple_loss=0.3033, pruned_loss=0.05347, over 944034.00 frames.
2022-05-29 18:12:37,355 INFO [train.py:761] (5/8) Epoch 34, batch 3050, loss[loss=0.1992, simple_loss=0.271, pruned_loss=0.06373, over 4639.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2986, pruned_loss=0.05649, over 966660.06 frames.], batch size: 11, lr: 4.65e-04
2022-05-29 18:13:15,224 INFO [train.py:761] (5/8) Epoch 34, batch 3100, loss[loss=0.1764, simple_loss=0.2729, pruned_loss=0.03996, over 4916.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2984, pruned_loss=0.05694, over 965280.32 frames.], batch size: 13, lr: 4.65e-04
2022-05-29 18:14:08,340 INFO [train.py:761] (5/8) Epoch 34, batch 3150, loss[loss=0.1959, simple_loss=0.2961, pruned_loss=0.04786, over 4926.00 frames.], tot_loss[loss=0.2088, simple_loss=0.3001, pruned_loss=0.05875, over 965999.96 frames.], batch size: 26, lr: 4.65e-04
2022-05-29 18:14:46,305 INFO [train.py:761] (5/8) Epoch 34, batch 3200, loss[loss=0.2344, simple_loss=0.3379, pruned_loss=0.06547, over 4833.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3007, pruned_loss=0.05973, over 966354.80 frames.], batch size: 20, lr: 4.65e-04
2022-05-29 18:15:24,851 INFO [train.py:761] (5/8) Epoch 34, batch 3250, loss[loss=0.223, simple_loss=0.309, pruned_loss=0.06852, over 4884.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3017, pruned_loss=0.06076, over 966529.18 frames.], batch size: 12, lr: 4.65e-04
2022-05-29 18:16:03,273 INFO [train.py:761] (5/8) Epoch 34, batch 3300, loss[loss=0.2748, simple_loss=0.3583, pruned_loss=0.09566, over 4726.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3027, pruned_loss=0.06233, over 966404.56 frames.], batch size: 14, lr: 4.65e-04
2022-05-29 18:16:41,053 INFO [train.py:761] (5/8) Epoch 34, batch 3350, loss[loss=0.2026, simple_loss=0.3, pruned_loss=0.05263, over 4670.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3025, pruned_loss=0.06347, over 965811.10 frames.], batch size: 13, lr: 4.65e-04
2022-05-29 18:17:18,991 INFO [train.py:761] (5/8) Epoch 34, batch 3400, loss[loss=0.2513, simple_loss=0.337, pruned_loss=0.08284, over 4871.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3033, pruned_loss=0.0644, over 966074.49 frames.], batch size: 17, lr: 4.65e-04
2022-05-29 18:17:57,158 INFO [train.py:761] (5/8) Epoch 34, batch 3450, loss[loss=0.2602, simple_loss=0.3232, pruned_loss=0.09858, over 4789.00 frames.], tot_loss[loss=0.217, simple_loss=0.3034, pruned_loss=0.06529, over 965369.37 frames.], batch size: 13, lr: 4.65e-04
2022-05-29 18:18:35,016 INFO [train.py:761] (5/8) Epoch 34, batch 3500, loss[loss=0.1755, simple_loss=0.2673, pruned_loss=0.04184, over 4726.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3021, pruned_loss=0.06524, over 965571.06 frames.], batch size: 12, lr: 4.65e-04
2022-05-29 18:19:13,007 INFO [train.py:761] (5/8) Epoch 34, batch 3550, loss[loss=0.2009, simple_loss=0.2825, pruned_loss=0.05958, over 4983.00 frames.], tot_loss[loss=0.2175, simple_loss=0.302, pruned_loss=0.0665, over 964715.21 frames.], batch size: 12, lr: 4.65e-04
2022-05-29 18:19:50,346 INFO [train.py:761] (5/8) Epoch 34, batch 3600, loss[loss=0.2407, simple_loss=0.3239, pruned_loss=0.07871, over 4815.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3036, pruned_loss=0.0681, over 963688.38 frames.], batch size: 16, lr: 4.65e-04
2022-05-29 18:20:28,816 INFO [train.py:761] (5/8) Epoch 34, batch 3650, loss[loss=0.2205, simple_loss=0.3093, pruned_loss=0.06586, over 4845.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3024, pruned_loss=0.06764, over 964978.31 frames.], batch size: 13, lr: 4.65e-04
2022-05-29 18:21:14,030 INFO [train.py:761] (5/8) Epoch 34, batch 3700, loss[loss=0.211, simple_loss=0.2802, pruned_loss=0.07096, over 4791.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3018, pruned_loss=0.06735, over 965161.18 frames.], batch size: 14, lr: 4.65e-04
2022-05-29 18:21:52,719 INFO [train.py:761] (5/8) Epoch 34, batch 3750, loss[loss=0.1857, simple_loss=0.2768, pruned_loss=0.04731, over 4992.00 frames.], tot_loss[loss=0.218, simple_loss=0.3016, pruned_loss=0.06727, over 966057.91 frames.], batch size: 13, lr: 4.64e-04
2022-05-29 18:22:30,615 INFO [train.py:761] (5/8) Epoch 34, batch 3800, loss[loss=0.221, simple_loss=0.2931, pruned_loss=0.07442, over 4971.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3018, pruned_loss=0.06802, over 964709.43 frames.], batch size: 11, lr: 4.64e-04
2022-05-29 18:23:08,735 INFO [train.py:761] (5/8) Epoch 34, batch 3850, loss[loss=0.2583, simple_loss=0.3426, pruned_loss=0.08701, over 4779.00 frames.], tot_loss[loss=0.2205, simple_loss=0.303, pruned_loss=0.06902, over 964160.16 frames.], batch size: 20, lr: 4.64e-04
2022-05-29 18:23:47,020 INFO [train.py:761] (5/8) Epoch 34, batch 3900, loss[loss=0.2568, simple_loss=0.348, pruned_loss=0.08282, over 4914.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3043, pruned_loss=0.06976, over 964531.06 frames.], batch size: 46, lr: 4.64e-04
2022-05-29 18:24:24,978 INFO [train.py:761] (5/8) Epoch 34, batch 3950, loss[loss=0.231, simple_loss=0.3211, pruned_loss=0.07045, over 4785.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3064, pruned_loss=0.07143, over 964109.34 frames.], batch size: 15, lr: 4.64e-04
2022-05-29 18:25:02,968 INFO [train.py:761] (5/8) Epoch 34, batch 4000, loss[loss=0.2052, simple_loss=0.283, pruned_loss=0.06368, over 4663.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3062, pruned_loss=0.07118, over 963824.20 frames.], batch size: 12, lr: 4.64e-04
2022-05-29 18:25:41,246 INFO [train.py:761] (5/8) Epoch 34, batch 4050, loss[loss=0.2373, simple_loss=0.3158, pruned_loss=0.07937, over 4972.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3051, pruned_loss=0.07103, over 964785.98 frames.], batch size: 14, lr: 4.64e-04
2022-05-29 18:26:19,630 INFO [train.py:761] (5/8) Epoch 34, batch 4100, loss[loss=0.1939, simple_loss=0.277, pruned_loss=0.05539, over 4809.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3046, pruned_loss=0.06993, over 964816.18 frames.], batch size: 12, lr: 4.64e-04
2022-05-29 18:26:58,107 INFO [train.py:761] (5/8) Epoch 34, batch 4150, loss[loss=0.2544, simple_loss=0.3254, pruned_loss=0.09167, over 4790.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3055, pruned_loss=0.07045, over 965248.42 frames.], batch size: 25, lr: 4.64e-04
2022-05-29 18:27:35,833 INFO [train.py:761] (5/8) Epoch 34, batch 4200, loss[loss=0.2221, simple_loss=0.2822, pruned_loss=0.08104, over 4836.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3045, pruned_loss=0.07013, over 964534.15 frames.], batch size: 11, lr: 4.64e-04
2022-05-29 18:28:14,113 INFO [train.py:761] (5/8) Epoch 34, batch 4250, loss[loss=0.2384, simple_loss=0.3321, pruned_loss=0.07231, over 4945.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3052, pruned_loss=0.07051, over 965360.99 frames.], batch size: 26, lr: 4.64e-04
2022-05-29 18:28:52,135 INFO [train.py:761] (5/8) Epoch 34, batch 4300, loss[loss=0.1922, simple_loss=0.2745, pruned_loss=0.05492, over 4978.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3048, pruned_loss=0.07015, over 965561.50 frames.], batch size: 14, lr: 4.64e-04
2022-05-29 18:29:30,603 INFO [train.py:761] (5/8) Epoch 34, batch 4350, loss[loss=0.2219, simple_loss=0.3073, pruned_loss=0.06828, over 4851.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3037, pruned_loss=0.06922, over 964832.62 frames.], batch size: 14, lr: 4.64e-04
2022-05-29 18:30:08,582 INFO [train.py:761] (5/8) Epoch 34, batch 4400, loss[loss=0.2806, simple_loss=0.3623, pruned_loss=0.09943, over 4779.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3038, pruned_loss=0.06975, over 964415.80 frames.], batch size: 15, lr: 4.64e-04
2022-05-29 18:30:46,755 INFO [train.py:761] (5/8) Epoch 34, batch 4450, loss[loss=0.1883, simple_loss=0.2816, pruned_loss=0.04749, over 4810.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3024, pruned_loss=0.0692, over 964579.74 frames.], batch size: 12, lr: 4.64e-04
2022-05-29 18:31:24,884 INFO [train.py:761] (5/8) Epoch 34, batch 4500, loss[loss=0.2192, simple_loss=0.3105, pruned_loss=0.06391, over 4712.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3037, pruned_loss=0.06999, over 964534.54 frames.], batch size: 14, lr: 4.64e-04
2022-05-29 18:32:03,156 INFO [train.py:761] (5/8) Epoch 34, batch 4550, loss[loss=0.2309, simple_loss=0.3164, pruned_loss=0.07267, over 4837.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3035, pruned_loss=0.06991, over 965797.37 frames.], batch size: 18, lr: 4.64e-04
2022-05-29 18:32:41,451 INFO [train.py:761] (5/8) Epoch 34, batch 4600, loss[loss=0.1872, simple_loss=0.287, pruned_loss=0.04367, over 4771.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3035, pruned_loss=0.0699, over 966344.50 frames.], batch size: 13, lr: 4.64e-04
2022-05-29 18:33:19,827 INFO [train.py:761] (5/8) Epoch 34, batch 4650, loss[loss=0.2078, simple_loss=0.2939, pruned_loss=0.06087, over 4793.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3055, pruned_loss=0.07095, over 967250.80 frames.], batch size: 16, lr: 4.64e-04
2022-05-29 18:33:57,869 INFO [train.py:761] (5/8) Epoch 34, batch 4700, loss[loss=0.259, simple_loss=0.3378, pruned_loss=0.09011, over 4975.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3048, pruned_loss=0.07084, over 966852.44 frames.], batch size: 15, lr: 4.63e-04
2022-05-29 18:34:35,969 INFO [train.py:761] (5/8) Epoch 34, batch 4750, loss[loss=0.2028, simple_loss=0.2807, pruned_loss=0.06243, over 4723.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3042, pruned_loss=0.07053, over 966868.28 frames.], batch size: 11, lr: 4.63e-04
2022-05-29 18:35:13,981 INFO [train.py:761] (5/8) Epoch 34, batch 4800, loss[loss=0.2287, simple_loss=0.3181, pruned_loss=0.06962, over 4669.00 frames.], tot_loss[loss=0.2231, simple_loss=0.305, pruned_loss=0.07057, over 967059.82 frames.], batch size: 13, lr: 4.63e-04
2022-05-29 18:35:52,335 INFO [train.py:761] (5/8) Epoch 34, batch 4850, loss[loss=0.2117, simple_loss=0.2842, pruned_loss=0.06965, over 4851.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3046, pruned_loss=0.07054, over 966161.86 frames.], batch size: 13, lr: 4.63e-04
2022-05-29 18:36:30,399 INFO [train.py:761] (5/8) Epoch 34, batch 4900, loss[loss=0.1949, simple_loss=0.272, pruned_loss=0.0589, over 4748.00 frames.], tot_loss[loss=0.2225, simple_loss=0.304, pruned_loss=0.07046, over 966738.26 frames.], batch size: 11, lr: 4.63e-04
2022-05-29 18:37:08,366 INFO [train.py:761] (5/8) Epoch 34, batch 4950, loss[loss=0.2451, simple_loss=0.3054, pruned_loss=0.09242, over 4727.00 frames.], tot_loss[loss=0.224, simple_loss=0.3057, pruned_loss=0.07114, over 967936.23 frames.], batch size: 11, lr: 4.63e-04
2022-05-29 18:37:46,924 INFO [train.py:761] (5/8) Epoch 34, batch 5000, loss[loss=0.2654, simple_loss=0.3536, pruned_loss=0.08856, over 4911.00 frames.], tot_loss[loss=0.223, simple_loss=0.3045, pruned_loss=0.07073, over 966380.18 frames.], batch size: 47, lr: 4.63e-04
2022-05-29 18:38:25,557 INFO [train.py:761] (5/8) Epoch 34, batch 5050, loss[loss=0.2262, simple_loss=0.3067, pruned_loss=0.07285, over 4973.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3042, pruned_loss=0.07107, over 966089.59 frames.], batch size: 14, lr: 4.63e-04
2022-05-29 18:39:03,716 INFO [train.py:761] (5/8) Epoch 34, batch 5100, loss[loss=0.2288, simple_loss=0.318, pruned_loss=0.06983, over 4722.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3043, pruned_loss=0.07067, over 965365.88 frames.], batch size: 14, lr: 4.63e-04
2022-05-29 18:39:41,720 INFO [train.py:761] (5/8) Epoch 34, batch 5150, loss[loss=0.2135, simple_loss=0.2952, pruned_loss=0.06592, over 4814.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3038, pruned_loss=0.07067, over 965014.84 frames.], batch size: 12, lr: 4.63e-04
2022-05-29 18:40:19,887 INFO [train.py:761] (5/8) Epoch 34, batch 5200, loss[loss=0.2228, simple_loss=0.3023, pruned_loss=0.07161, over 4973.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3042, pruned_loss=0.07068, over 964405.71 frames.], batch size: 14, lr: 4.63e-04
2022-05-29 18:40:58,208 INFO [train.py:761] (5/8) Epoch 34, batch 5250, loss[loss=0.2217, simple_loss=0.3011, pruned_loss=0.07117, over 4742.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3028, pruned_loss=0.06998, over 964538.53 frames.], batch size: 12, lr: 4.63e-04
2022-05-29 18:41:36,570 INFO [train.py:761] (5/8) Epoch 34, batch 5300, loss[loss=0.2158, simple_loss=0.3005, pruned_loss=0.06557, over 4813.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3033, pruned_loss=0.06968, over 964371.80 frames.], batch size: 20, lr: 4.63e-04
2022-05-29 18:42:15,176 INFO [train.py:761] (5/8) Epoch 34, batch 5350, loss[loss=0.2601, simple_loss=0.3323, pruned_loss=0.09394, over 4955.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3045, pruned_loss=0.07102, over 964135.52 frames.], batch size: 21, lr: 4.63e-04
2022-05-29 18:42:52,910 INFO [train.py:761] (5/8) Epoch 34, batch 5400, loss[loss=0.2365, simple_loss=0.314, pruned_loss=0.07951, over 4973.00 frames.], tot_loss[loss=0.223, simple_loss=0.3041, pruned_loss=0.07093, over 964574.40 frames.], batch size: 15, lr: 4.63e-04
2022-05-29 18:43:30,652 INFO [train.py:761] (5/8) Epoch 34, batch 5450, loss[loss=0.2322, simple_loss=0.3137, pruned_loss=0.07539, over 4785.00 frames.], tot_loss[loss=0.222, simple_loss=0.3035, pruned_loss=0.07029, over 963505.91 frames.], batch size: 14, lr: 4.63e-04
2022-05-29 18:44:08,980 INFO [train.py:761] (5/8) Epoch 34, batch 5500, loss[loss=0.2414, simple_loss=0.3243, pruned_loss=0.07924, over 4785.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3021, pruned_loss=0.06951, over 963517.63 frames.], batch size: 14, lr: 4.63e-04
2022-05-29 18:44:47,395 INFO [train.py:761] (5/8) Epoch 34, batch 5550, loss[loss=0.243, simple_loss=0.3136, pruned_loss=0.0862, over 4719.00 frames.], tot_loss[loss=0.2206, simple_loss=0.3021, pruned_loss=0.06958, over 963503.16 frames.], batch size: 14, lr: 4.63e-04
2022-05-29 18:45:25,571 INFO [train.py:761] (5/8) Epoch 34, batch 5600, loss[loss=0.2259, simple_loss=0.3036, pruned_loss=0.07408, over 4781.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3026, pruned_loss=0.06985, over 962726.02 frames.], batch size: 13, lr: 4.63e-04
2022-05-29 18:46:03,731 INFO [train.py:761] (5/8) Epoch 34, batch 5650, loss[loss=0.2027, simple_loss=0.2809, pruned_loss=0.06223, over 4566.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3022, pruned_loss=0.0693, over 962449.41 frames.], batch size: 10, lr: 4.63e-04
2022-05-29 18:46:42,706 INFO [train.py:761] (5/8) Epoch 34, batch 5700, loss[loss=0.2118, simple_loss=0.2927, pruned_loss=0.0654, over 4918.00 frames.], tot_loss[loss=0.2219, simple_loss=0.304, pruned_loss=0.06994, over 965140.85 frames.], batch size: 13, lr: 4.62e-04
2022-05-29 18:47:20,813 INFO [train.py:761] (5/8) Epoch 34, batch 5750, loss[loss=0.2288, simple_loss=0.296, pruned_loss=0.08075, over 4851.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3024, pruned_loss=0.06935, over 966010.29 frames.], batch size: 11, lr: 4.62e-04
2022-05-29 18:47:58,942 INFO [train.py:761] (5/8) Epoch 34, batch 5800, loss[loss=0.206, simple_loss=0.2981, pruned_loss=0.05696, over 4888.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3018, pruned_loss=0.06866, over 966724.70 frames.], batch size: 15, lr: 4.62e-04
2022-05-29 18:48:37,505 INFO [train.py:761] (5/8) Epoch 34, batch 5850, loss[loss=0.1963, simple_loss=0.2816, pruned_loss=0.05551, over 4806.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3022, pruned_loss=0.06843, over 966048.89 frames.], batch size: 12, lr: 4.62e-04
2022-05-29 18:49:15,778 INFO [train.py:761] (5/8) Epoch 34, batch 5900, loss[loss=0.2263, simple_loss=0.2903, pruned_loss=0.08115, over 4828.00 frames.], tot_loss[loss=0.2208, simple_loss=0.3032, pruned_loss=0.06921, over 965423.00 frames.], batch size: 11, lr: 4.62e-04
2022-05-29 18:49:53,870 INFO [train.py:761] (5/8) Epoch 34, batch 5950, loss[loss=0.2364, simple_loss=0.3213, pruned_loss=0.07575, over 4891.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3035, pruned_loss=0.06934, over 966013.56 frames.], batch size: 17, lr: 4.62e-04
2022-05-29 18:50:31,686 INFO [train.py:761] (5/8) Epoch 34, batch 6000, loss[loss=0.233, simple_loss=0.3063, pruned_loss=0.07986, over 4962.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3037, pruned_loss=0.06963, over 967006.97 frames.], batch size: 16, lr: 4.62e-04
2022-05-29 18:50:31,687 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 18:50:41,590 INFO [train.py:790] (5/8) Epoch 34, validation: loss=0.1962, simple_loss=0.2992, pruned_loss=0.04656, over 944034.00 frames.
2022-05-29 18:51:20,667 INFO [train.py:761] (5/8) Epoch 34, batch 6050, loss[loss=0.2391, simple_loss=0.325, pruned_loss=0.07658, over 4850.00 frames.], tot_loss[loss=0.2229, simple_loss=0.305, pruned_loss=0.07043, over 966687.06 frames.], batch size: 17, lr: 4.62e-04
2022-05-29 18:51:59,327 INFO [train.py:761] (5/8) Epoch 34, batch 6100, loss[loss=0.2012, simple_loss=0.2741, pruned_loss=0.06411, over 4854.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3045, pruned_loss=0.0699, over 966375.17 frames.], batch size: 13, lr: 4.62e-04
2022-05-29 18:52:38,090 INFO [train.py:761] (5/8) Epoch 34, batch 6150, loss[loss=0.2612, simple_loss=0.3329, pruned_loss=0.09479, over 4798.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3047, pruned_loss=0.06994, over 966468.31 frames.], batch size: 12, lr: 4.62e-04
2022-05-29 18:53:16,336 INFO [train.py:761] (5/8) Epoch 34, batch 6200, loss[loss=0.1894, simple_loss=0.2924, pruned_loss=0.04323, over 4926.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3029, pruned_loss=0.06902, over 965811.39 frames.], batch size: 21, lr: 4.62e-04
2022-05-29 18:53:54,549 INFO [train.py:761] (5/8) Epoch 34, batch 6250, loss[loss=0.3021, simple_loss=0.3838, pruned_loss=0.1102, over 4962.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3036, pruned_loss=0.0695, over 965884.01 frames.], batch size: 51, lr: 4.62e-04
2022-05-29 18:54:32,505 INFO [train.py:761] (5/8) Epoch 34, batch 6300, loss[loss=0.2878, simple_loss=0.3603, pruned_loss=0.1076, over 4965.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3046, pruned_loss=0.06977, over 966501.95 frames.], batch size: 42, lr: 4.62e-04
2022-05-29 18:55:10,544 INFO [train.py:761] (5/8) Epoch 34, batch 6350, loss[loss=0.2421, simple_loss=0.3182, pruned_loss=0.08307, over 4827.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3046, pruned_loss=0.06957, over 966424.97 frames.], batch size: 11, lr: 4.62e-04
2022-05-29 18:55:48,682 INFO [train.py:761] (5/8) Epoch 34, batch 6400, loss[loss=0.1892, simple_loss=0.2941, pruned_loss=0.04211, over 4987.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3051, pruned_loss=0.06923, over 967230.32 frames.], batch size: 13, lr: 4.62e-04
2022-05-29 18:56:27,702 INFO [train.py:761] (5/8) Epoch 34, batch 6450, loss[loss=0.2616, simple_loss=0.341, pruned_loss=0.09112, over 4791.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3041, pruned_loss=0.06902, over 968014.57 frames.], batch size: 14, lr: 4.62e-04
2022-05-29 18:57:05,939 INFO [train.py:761] (5/8) Epoch 34, batch 6500, loss[loss=0.2218, simple_loss=0.2978, pruned_loss=0.07288, over 4642.00 frames.], tot_loss[loss=0.2227, simple_loss=0.305, pruned_loss=0.07021, over 967302.44 frames.], batch size: 11, lr: 4.62e-04
2022-05-29 18:57:44,268 INFO [train.py:761] (5/8) Epoch 34, batch 6550, loss[loss=0.216, simple_loss=0.3012, pruned_loss=0.06535, over 4975.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3053, pruned_loss=0.07026, over 967900.52 frames.], batch size: 14, lr: 4.62e-04
2022-05-29 18:58:23,291 INFO [train.py:761] (5/8) Epoch 34, batch 6600, loss[loss=0.1978, simple_loss=0.2784, pruned_loss=0.05856, over 4660.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3033, pruned_loss=0.06964, over 967801.42 frames.], batch size: 12, lr: 4.62e-04
2022-05-29 18:59:01,857 INFO [train.py:761] (5/8) Epoch 34, batch 6650, loss[loss=0.2253, simple_loss=0.3258, pruned_loss=0.0624, over 4984.00 frames.], tot_loss[loss=0.2201, simple_loss=0.3024, pruned_loss=0.06888, over 967345.51 frames.], batch size: 21, lr: 4.62e-04
2022-05-29 18:59:39,841 INFO [train.py:761] (5/8) Epoch 34, batch 6700, loss[loss=0.2629, simple_loss=0.3336, pruned_loss=0.09608, over 4819.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3038, pruned_loss=0.06974, over 967257.35 frames.], batch size: 25, lr: 4.61e-04
2022-05-29 19:00:36,617 INFO [train.py:761] (5/8) Epoch 35, batch 0, loss[loss=0.2119, simple_loss=0.3076, pruned_loss=0.05815, over 4793.00 frames.], tot_loss[loss=0.2119, simple_loss=0.3076, pruned_loss=0.05815, over 4793.00 frames.], batch size: 15, lr: 4.61e-04
2022-05-29 19:01:14,398 INFO [train.py:761] (5/8) Epoch 35, batch 50, loss[loss=0.2423, simple_loss=0.3349, pruned_loss=0.07487, over 4898.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2979, pruned_loss=0.05987, over 217641.69 frames.], batch size: 15, lr: 4.61e-04
2022-05-29 19:01:52,494 INFO [train.py:761] (5/8) Epoch 35, batch 100, loss[loss=0.2027, simple_loss=0.2932, pruned_loss=0.05605, over 4664.00 frames.], tot_loss[loss=0.2046, simple_loss=0.294, pruned_loss=0.05764, over 383941.05 frames.], batch size: 12, lr: 4.61e-04
2022-05-29 19:02:30,732 INFO [train.py:761] (5/8) Epoch 35, batch 150, loss[loss=0.2219, simple_loss=0.3149, pruned_loss=0.0645, over 4975.00 frames.], tot_loss[loss=0.205, simple_loss=0.2961, pruned_loss=0.05696, over 512515.64 frames.], batch size: 15, lr: 4.61e-04
2022-05-29 19:03:08,850 INFO [train.py:761] (5/8) Epoch 35, batch 200, loss[loss=0.2167, simple_loss=0.2956, pruned_loss=0.06894, over 4781.00 frames.], tot_loss[loss=0.206, simple_loss=0.2968, pruned_loss=0.05762, over 612830.19 frames.], batch size: 13, lr: 4.61e-04
2022-05-29 19:03:46,795 INFO [train.py:761] (5/8) Epoch 35, batch 250, loss[loss=0.1791, simple_loss=0.2818, pruned_loss=0.03822, over 4954.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2951, pruned_loss=0.05615, over 691010.29 frames.], batch size: 16, lr: 4.61e-04
2022-05-29 19:04:24,349 INFO [train.py:761] (5/8) Epoch 35, batch 300, loss[loss=0.1942, simple_loss=0.2956, pruned_loss=0.04645, over 4718.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2945, pruned_loss=0.05579, over 752353.11 frames.], batch size: 14, lr: 4.61e-04
2022-05-29 19:05:02,426 INFO [train.py:761] (5/8) Epoch 35, batch 350, loss[loss=0.1807, simple_loss=0.277, pruned_loss=0.04222, over 4663.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2947, pruned_loss=0.05569, over 800607.98 frames.], batch size: 12, lr: 4.61e-04
2022-05-29 19:05:40,490 INFO [train.py:761] (5/8) Epoch 35, batch 400, loss[loss=0.1888, simple_loss=0.2767, pruned_loss=0.05046, over 4665.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2948, pruned_loss=0.05545, over 836687.68 frames.], batch size: 12, lr: 4.61e-04
2022-05-29 19:06:17,989 INFO [train.py:761] (5/8) Epoch 35, batch 450, loss[loss=0.2149, simple_loss=0.3123, pruned_loss=0.05873, over 4916.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2937, pruned_loss=0.0549, over 864812.11 frames.], batch size: 14, lr: 4.61e-04
2022-05-29 19:06:56,107 INFO [train.py:761] (5/8) Epoch 35, batch 500, loss[loss=0.1895, simple_loss=0.2811, pruned_loss=0.04898, over 4669.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2945, pruned_loss=0.05489, over 887729.02 frames.], batch size: 13, lr: 4.61e-04
2022-05-29 19:07:33,675 INFO [train.py:761] (5/8) Epoch 35, batch 550, loss[loss=0.2154, simple_loss=0.3168, pruned_loss=0.05705, over 4886.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2943, pruned_loss=0.05469, over 905107.81 frames.], batch size: 43, lr: 4.61e-04
2022-05-29 19:08:11,853 INFO [train.py:761] (5/8) Epoch 35, batch 600, loss[loss=0.2069, simple_loss=0.3054, pruned_loss=0.05417, over 4783.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2949, pruned_loss=0.05516, over 919455.41 frames.], batch size: 20, lr: 4.61e-04
2022-05-29 19:08:49,436 INFO [train.py:761] (5/8) Epoch 35, batch 650, loss[loss=0.2294, simple_loss=0.3291, pruned_loss=0.06484, over 4784.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2966, pruned_loss=0.05558, over 929667.71 frames.], batch size: 18, lr: 4.61e-04
2022-05-29 19:09:27,426 INFO [train.py:761] (5/8) Epoch 35, batch 700, loss[loss=0.1981, simple_loss=0.2982, pruned_loss=0.04903, over 4718.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2971, pruned_loss=0.05598, over 937937.36 frames.], batch size: 14, lr: 4.61e-04
2022-05-29 19:10:04,999 INFO [train.py:761] (5/8) Epoch 35, batch 750, loss[loss=0.2075, simple_loss=0.277, pruned_loss=0.06903, over 4971.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2975, pruned_loss=0.05633, over 943849.70 frames.], batch size: 12, lr: 4.61e-04
2022-05-29 19:10:43,189 INFO [train.py:761] (5/8) Epoch 35, batch 800, loss[loss=0.1987, simple_loss=0.2942, pruned_loss=0.05162, over 4759.00 frames.], tot_loss[loss=0.206, simple_loss=0.2987, pruned_loss=0.05666, over 948141.35 frames.], batch size: 15, lr: 4.61e-04
2022-05-29 19:11:21,757 INFO [train.py:761] (5/8) Epoch 35, batch 850, loss[loss=0.2917, simple_loss=0.3672, pruned_loss=0.1081, over 4882.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2985, pruned_loss=0.05682, over 952558.13 frames.], batch size: 47, lr: 4.61e-04
2022-05-29 19:11:59,922 INFO [train.py:761] (5/8) Epoch 35, batch 900, loss[loss=0.2122, simple_loss=0.3004, pruned_loss=0.06206, over 4847.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2979, pruned_loss=0.05668, over 956541.80 frames.], batch size: 14, lr: 4.61e-04
2022-05-29 19:12:37,684 INFO [train.py:761] (5/8) Epoch 35, batch 950, loss[loss=0.229, simple_loss=0.3012, pruned_loss=0.07843, over 4667.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2985, pruned_loss=0.05729, over 958270.50 frames.], batch size: 12, lr: 4.60e-04
2022-05-29 19:13:15,421 INFO [train.py:761] (5/8) Epoch 35, batch 1000, loss[loss=0.2083, simple_loss=0.3078, pruned_loss=0.05443, over 4792.00 frames.], tot_loss[loss=0.207, simple_loss=0.2989, pruned_loss=0.05756, over 959956.22 frames.], batch size: 14, lr: 4.60e-04
2022-05-29 19:13:53,566 INFO [train.py:761] (5/8) Epoch 35, batch 1050, loss[loss=0.1913, simple_loss=0.2835, pruned_loss=0.04953, over 4804.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2992, pruned_loss=0.05797, over 962487.41 frames.], batch size: 12, lr: 4.60e-04
2022-05-29 19:14:31,704 INFO [train.py:761] (5/8) Epoch 35, batch 1100, loss[loss=0.1794, simple_loss=0.2707, pruned_loss=0.04407, over 4803.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2977, pruned_loss=0.0577, over 963133.81 frames.], batch size: 12, lr: 4.60e-04
2022-05-29 19:15:09,661 INFO [train.py:761] (5/8) Epoch 35, batch 1150, loss[loss=0.1549, simple_loss=0.2454, pruned_loss=0.03221, over 4728.00 frames.], tot_loss[loss=0.2048, simple_loss=0.296, pruned_loss=0.05679, over 962277.69 frames.], batch size: 12, lr: 4.60e-04
2022-05-29 19:15:47,782 INFO [train.py:761] (5/8) Epoch 35, batch 1200, loss[loss=0.2248, simple_loss=0.3184, pruned_loss=0.0656, over 4813.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2971, pruned_loss=0.05695, over 963184.22 frames.], batch size: 16, lr: 4.60e-04
2022-05-29 19:16:25,779 INFO [train.py:761] (5/8) Epoch 35, batch 1250, loss[loss=0.2162, simple_loss=0.3067, pruned_loss=0.06282, over 4844.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2991, pruned_loss=0.05774, over 964004.44 frames.], batch size: 26, lr: 4.60e-04
2022-05-29 19:17:03,971 INFO [train.py:761] (5/8) Epoch 35, batch 1300, loss[loss=0.1768, simple_loss=0.2601, pruned_loss=0.04669, over 4964.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2992, pruned_loss=0.05821, over 964519.85 frames.], batch size: 11, lr: 4.60e-04
2022-05-29 19:17:41,568 INFO [train.py:761] (5/8) Epoch 35, batch 1350, loss[loss=0.1732, simple_loss=0.2814, pruned_loss=0.0325, over 4722.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2984, pruned_loss=0.05789, over 965219.83 frames.], batch size: 14, lr: 4.60e-04
2022-05-29 19:18:19,779 INFO [train.py:761] (5/8) Epoch 35, batch 1400, loss[loss=0.1869, simple_loss=0.2777, pruned_loss=0.04807, over 4914.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2985, pruned_loss=0.05809, over 965265.18 frames.], batch size: 13, lr: 4.60e-04
2022-05-29 19:18:58,017 INFO [train.py:761] (5/8) Epoch 35, batch 1450, loss[loss=0.1911, simple_loss=0.2828, pruned_loss=0.04969, over 4859.00 frames.], tot_loss[loss=0.2075, simple_loss=0.299, pruned_loss=0.05799, over 965649.17 frames.], batch size: 13, lr: 4.60e-04
2022-05-29 19:19:36,160 INFO [train.py:761] (5/8) Epoch 35, batch 1500, loss[loss=0.223, simple_loss=0.3185, pruned_loss=0.06376, over 4714.00 frames.], tot_loss[loss=0.2086, simple_loss=0.3002, pruned_loss=0.05849, over 965494.53 frames.], batch size: 14, lr: 4.60e-04
2022-05-29 19:20:14,080 INFO [train.py:761] (5/8) Epoch 35, batch 1550, loss[loss=0.253, simple_loss=0.3371, pruned_loss=0.08448, over 4786.00 frames.], tot_loss[loss=0.2072, simple_loss=0.299, pruned_loss=0.05772, over 964780.67 frames.], batch size: 16, lr: 4.60e-04
2022-05-29 19:20:52,337 INFO [train.py:761] (5/8) Epoch 35, batch 1600, loss[loss=0.2359, simple_loss=0.3177, pruned_loss=0.0771, over 4767.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2996, pruned_loss=0.05808, over 965402.76 frames.], batch size: 15, lr: 4.60e-04
2022-05-29 19:21:29,929 INFO [train.py:761] (5/8) Epoch 35, batch 1650, loss[loss=0.2174, simple_loss=0.2965, pruned_loss=0.06919, over 4970.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2988, pruned_loss=0.05816, over 965674.94 frames.], batch size: 12, lr: 4.60e-04
2022-05-29 19:22:07,522 INFO [train.py:761] (5/8) Epoch 35, batch 1700, loss[loss=0.2242, simple_loss=0.3103, pruned_loss=0.06904, over 4730.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2976, pruned_loss=0.0579, over 965796.09 frames.], batch size: 13, lr: 4.60e-04
2022-05-29 19:22:44,891 INFO [train.py:761] (5/8) Epoch 35, batch 1750, loss[loss=0.2362, simple_loss=0.3316, pruned_loss=0.07038, over 4913.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2991, pruned_loss=0.05838, over 966272.57 frames.], batch size: 14, lr: 4.60e-04
2022-05-29 19:23:23,771 INFO [train.py:761] (5/8) Epoch 35, batch 1800, loss[loss=0.2032, simple_loss=0.3122, pruned_loss=0.0471, over 4973.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2981, pruned_loss=0.05749, over 967034.18 frames.], batch size: 15, lr: 4.60e-04
2022-05-29 19:24:01,409 INFO [train.py:761] (5/8) Epoch 35, batch 1850, loss[loss=0.1777, simple_loss=0.2666, pruned_loss=0.04435, over 4969.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2974, pruned_loss=0.05692, over 966504.54 frames.], batch size: 12, lr: 4.60e-04
2022-05-29 19:24:39,432 INFO [train.py:761] (5/8) Epoch 35, batch 1900, loss[loss=0.2187, simple_loss=0.3108, pruned_loss=0.06329, over 4919.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2987, pruned_loss=0.05678, over 966299.54 frames.], batch size: 21, lr: 4.60e-04
2022-05-29 19:25:17,516 INFO [train.py:761] (5/8) Epoch 35, batch 1950, loss[loss=0.1991, simple_loss=0.3009, pruned_loss=0.04865, over 4916.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2981, pruned_loss=0.05638, over 967349.55 frames.], batch size: 14, lr: 4.59e-04
2022-05-29 19:25:55,609 INFO [train.py:761] (5/8) Epoch 35, batch 2000, loss[loss=0.2334, simple_loss=0.3172, pruned_loss=0.07477, over 4726.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2983, pruned_loss=0.05656, over 966352.87 frames.], batch size: 13, lr: 4.59e-04
2022-05-29 19:26:34,167 INFO [train.py:761] (5/8) Epoch 35, batch 2050, loss[loss=0.2114, simple_loss=0.3075, pruned_loss=0.0576, over 4885.00 frames.], tot_loss[loss=0.2056, simple_loss=0.298, pruned_loss=0.05662, over 965112.66 frames.], batch size: 17, lr: 4.59e-04
2022-05-29 19:27:12,023 INFO [train.py:761] (5/8) Epoch 35, batch 2100, loss[loss=0.1956, simple_loss=0.2865, pruned_loss=0.05241, over 4800.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2992, pruned_loss=0.05709, over 966568.82 frames.], batch size: 12, lr: 4.59e-04
2022-05-29 19:27:49,588 INFO [train.py:761] (5/8) Epoch 35, batch 2150, loss[loss=0.199, simple_loss=0.2662, pruned_loss=0.06587, over 4857.00 frames.], tot_loss[loss=0.206, simple_loss=0.2985, pruned_loss=0.0568, over 966953.70 frames.], batch size: 13, lr: 4.59e-04
2022-05-29 19:28:28,064 INFO [train.py:761] (5/8) Epoch 35, batch 2200, loss[loss=0.2054, simple_loss=0.2973, pruned_loss=0.05675, over 4852.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2985, pruned_loss=0.05734, over 966791.86 frames.], batch size: 13, lr: 4.59e-04
2022-05-29 19:29:06,326 INFO [train.py:761] (5/8) Epoch 35, batch 2250, loss[loss=0.1967, simple_loss=0.2861, pruned_loss=0.05359, over 4981.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2999, pruned_loss=0.05783, over 966747.32 frames.], batch size: 12, lr: 4.59e-04
2022-05-29 19:29:44,215 INFO [train.py:761] (5/8) Epoch 35, batch 2300, loss[loss=0.2298, simple_loss=0.3256, pruned_loss=0.06697, over 4773.00 frames.], tot_loss[loss=0.2099, simple_loss=0.3021, pruned_loss=0.05882, over 967072.83 frames.], batch size: 15, lr: 4.59e-04
2022-05-29 19:30:21,981 INFO [train.py:761] (5/8) Epoch 35, batch 2350, loss[loss=0.2153, simple_loss=0.2961, pruned_loss=0.06726, over 4896.00 frames.], tot_loss[loss=0.2098, simple_loss=0.3017, pruned_loss=0.05899, over 967600.29 frames.], batch size: 15, lr: 4.59e-04
2022-05-29 19:31:00,299 INFO [train.py:761] (5/8) Epoch 35, batch 2400, loss[loss=0.2306, simple_loss=0.3362, pruned_loss=0.06256, over 4915.00 frames.], tot_loss[loss=0.2096, simple_loss=0.3011, pruned_loss=0.05903, over 968033.27 frames.], batch size: 14, lr: 4.59e-04
2022-05-29 19:31:37,658 INFO [train.py:761] (5/8) Epoch 35, batch 2450, loss[loss=0.1778, simple_loss=0.2665, pruned_loss=0.04462, over 4866.00 frames.], tot_loss[loss=0.2081, simple_loss=0.3, pruned_loss=0.05806, over 966841.09 frames.], batch size: 13, lr: 4.59e-04
2022-05-29 19:32:15,838 INFO [train.py:761] (5/8) Epoch 35, batch 2500, loss[loss=0.1972, simple_loss=0.2827, pruned_loss=0.05586, over 4986.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2981, pruned_loss=0.05676, over 966233.92 frames.], batch size: 13, lr: 4.59e-04
2022-05-29 19:32:53,902 INFO [train.py:761] (5/8) Epoch 35, batch 2550, loss[loss=0.2408, simple_loss=0.328, pruned_loss=0.07685, over 4953.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2989, pruned_loss=0.05694, over 966983.28 frames.], batch size: 21, lr: 4.59e-04
2022-05-29 19:33:32,028 INFO [train.py:761] (5/8) Epoch 35, batch 2600, loss[loss=0.1533, simple_loss=0.235, pruned_loss=0.03576, over 4541.00 frames.], tot_loss[loss=0.2062, simple_loss=0.298, pruned_loss=0.05723, over 966727.62 frames.], batch size: 10, lr: 4.59e-04
2022-05-29 19:34:09,863 INFO [train.py:761] (5/8) Epoch 35, batch 2650, loss[loss=0.1896, simple_loss=0.2896, pruned_loss=0.04473, over 4715.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2967, pruned_loss=0.05635, over 966452.62 frames.], batch size: 12, lr: 4.59e-04
2022-05-29 19:34:51,116 INFO [train.py:761] (5/8) Epoch 35, batch 2700, loss[loss=0.1876, simple_loss=0.285, pruned_loss=0.04503, over 4735.00 frames.], tot_loss[loss=0.2045, simple_loss=0.297, pruned_loss=0.05596, over 966944.91 frames.], batch size: 12, lr: 4.59e-04
2022-05-29 19:35:29,069 INFO [train.py:761] (5/8) Epoch 35, batch 2750, loss[loss=0.2131, simple_loss=0.3145, pruned_loss=0.05586, over 4708.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2978, pruned_loss=0.05625, over 965667.97 frames.], batch size: 14, lr: 4.59e-04
2022-05-29 19:36:06,825 INFO [train.py:761] (5/8) Epoch 35, batch 2800, loss[loss=0.225, simple_loss=0.3264, pruned_loss=0.06178, over 4811.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2983, pruned_loss=0.05565, over 966691.55 frames.], batch size: 18, lr: 4.59e-04
2022-05-29 19:36:44,892 INFO [train.py:761] (5/8) Epoch 35, batch 2850, loss[loss=0.1798, simple_loss=0.2604, pruned_loss=0.04964, over 4879.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2968, pruned_loss=0.0552, over 966101.52 frames.], batch size: 12, lr: 4.59e-04
2022-05-29 19:37:23,283 INFO [train.py:761] (5/8) Epoch 35, batch 2900, loss[loss=0.1994, simple_loss=0.2895, pruned_loss=0.05463, over 4804.00 frames.], tot_loss[loss=0.204, simple_loss=0.2971, pruned_loss=0.05544, over 966826.09 frames.], batch size: 12, lr: 4.59e-04
2022-05-29 19:38:01,527 INFO [train.py:761] (5/8) Epoch 35, batch 2950, loss[loss=0.2244, simple_loss=0.3257, pruned_loss=0.0615, over 4762.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2983, pruned_loss=0.05613, over 966453.87 frames.], batch size: 15, lr: 4.58e-04
2022-05-29 19:38:39,312 INFO [train.py:761] (5/8) Epoch 35, batch 3000, loss[loss=0.203, simple_loss=0.3006, pruned_loss=0.05274, over 4803.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2996, pruned_loss=0.05666, over 966383.20 frames.], batch size: 20, lr: 4.58e-04
2022-05-29 19:38:39,312 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 19:38:49,161 INFO [train.py:790] (5/8) Epoch 35, validation: loss=0.2037, simple_loss=0.3025, pruned_loss=0.05247, over 944034.00 frames.
2022-05-29 19:39:27,096 INFO [train.py:761] (5/8) Epoch 35, batch 3050, loss[loss=0.221, simple_loss=0.3028, pruned_loss=0.06957, over 4670.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2994, pruned_loss=0.05719, over 966234.86 frames.], batch size: 12, lr: 4.58e-04
2022-05-29 19:40:05,030 INFO [train.py:761] (5/8) Epoch 35, batch 3100, loss[loss=0.2444, simple_loss=0.3333, pruned_loss=0.07777, over 4916.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2991, pruned_loss=0.05691, over 965953.86 frames.], batch size: 45, lr: 4.58e-04
2022-05-29 19:40:42,938 INFO [train.py:761] (5/8) Epoch 35, batch 3150, loss[loss=0.2075, simple_loss=0.2907, pruned_loss=0.06211, over 4922.00 frames.], tot_loss[loss=0.209, simple_loss=0.3005, pruned_loss=0.05874, over 966523.50 frames.], batch size: 13, lr: 4.58e-04
2022-05-29 19:41:21,099 INFO [train.py:761] (5/8) Epoch 35, batch 3200, loss[loss=0.2269, simple_loss=0.317, pruned_loss=0.0684, over 4726.00 frames.], tot_loss[loss=0.21, simple_loss=0.3005, pruned_loss=0.0598, over 965622.35 frames.], batch size: 13, lr: 4.58e-04
2022-05-29 19:41:58,946 INFO [train.py:761] (5/8) Epoch 35, batch 3250, loss[loss=0.2963, simple_loss=0.373, pruned_loss=0.1098, over 4974.00 frames.], tot_loss[loss=0.2108, simple_loss=0.3006, pruned_loss=0.06054, over 965578.52 frames.], batch size: 15, lr: 4.58e-04
2022-05-29 19:42:37,013 INFO [train.py:761] (5/8) Epoch 35, batch 3300, loss[loss=0.2738, simple_loss=0.3377, pruned_loss=0.105, over 4883.00 frames.], tot_loss[loss=0.2127, simple_loss=0.3012, pruned_loss=0.06207, over 965579.55 frames.], batch size: 15, lr: 4.58e-04
2022-05-29 19:43:15,293 INFO [train.py:761] (5/8) Epoch 35, batch 3350, loss[loss=0.2081, simple_loss=0.3054, pruned_loss=0.05534, over 4787.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3031, pruned_loss=0.06332, over 966863.53 frames.], batch size: 13, lr: 4.58e-04
2022-05-29 19:43:53,663 INFO [train.py:761] (5/8) Epoch 35, batch 3400, loss[loss=0.2012, simple_loss=0.2963, pruned_loss=0.0531, over 4875.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3029, pruned_loss=0.06439, over 968146.22 frames.], batch size: 12, lr: 4.58e-04
2022-05-29 19:44:31,751 INFO [train.py:761] (5/8) Epoch 35, batch 3450, loss[loss=0.2178, simple_loss=0.3155, pruned_loss=0.06003, over 4863.00 frames.], tot_loss[loss=0.2165, simple_loss=0.303, pruned_loss=0.06502, over 968904.25 frames.], batch size: 18, lr: 4.58e-04
2022-05-29 19:45:09,923 INFO [train.py:761] (5/8) Epoch 35, batch 3500, loss[loss=0.1844, simple_loss=0.2701, pruned_loss=0.04932, over 4801.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3047, pruned_loss=0.06636, over 968528.56 frames.], batch size: 12, lr: 4.58e-04
2022-05-29 19:45:47,927 INFO [train.py:761] (5/8) Epoch 35, batch 3550, loss[loss=0.2315, simple_loss=0.3162, pruned_loss=0.07336, over 4973.00 frames.], tot_loss[loss=0.219, simple_loss=0.3041, pruned_loss=0.067, over 967764.45 frames.], batch size: 27, lr: 4.58e-04
2022-05-29 19:46:25,959 INFO [train.py:761] (5/8) Epoch 35, batch 3600, loss[loss=0.2192, simple_loss=0.3141, pruned_loss=0.06216, over 4674.00 frames.], tot_loss[loss=0.2183, simple_loss=0.303, pruned_loss=0.06677, over 966768.03 frames.], batch size: 13, lr: 4.58e-04
2022-05-29 19:47:03,697 INFO [train.py:761] (5/8) Epoch 35, batch 3650, loss[loss=0.2346, simple_loss=0.3135, pruned_loss=0.07779, over 4861.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3007, pruned_loss=0.06638, over 966390.91 frames.], batch size: 13, lr: 4.58e-04
2022-05-29 19:47:41,957 INFO [train.py:761] (5/8) Epoch 35, batch 3700, loss[loss=0.2462, simple_loss=0.3297, pruned_loss=0.08138, over 4778.00 frames.], tot_loss[loss=0.2193, simple_loss=0.303, pruned_loss=0.06783, over 966788.85 frames.], batch size: 14, lr: 4.58e-04
2022-05-29 19:48:19,694 INFO [train.py:761] (5/8) Epoch 35, batch 3750, loss[loss=0.2191, simple_loss=0.3055, pruned_loss=0.06633, over 4838.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3027, pruned_loss=0.06799, over 966928.45 frames.], batch size: 18, lr: 4.58e-04
2022-05-29 19:48:58,230 INFO [train.py:761] (5/8) Epoch 35, batch 3800, loss[loss=0.1925, simple_loss=0.2649, pruned_loss=0.06009, over 4817.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3019, pruned_loss=0.06857, over 966637.41 frames.], batch size: 11, lr: 4.58e-04
2022-05-29 19:49:36,023 INFO [train.py:761] (5/8) Epoch 35, batch 3850, loss[loss=0.2424, simple_loss=0.3167, pruned_loss=0.08403, over 4802.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3036, pruned_loss=0.07041, over 966601.31 frames.], batch size: 12, lr: 4.58e-04
2022-05-29 19:50:14,515 INFO [train.py:761] (5/8) Epoch 35, batch 3900, loss[loss=0.2462, simple_loss=0.3262, pruned_loss=0.08307, over 4847.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3041, pruned_loss=0.0702, over 967567.04 frames.], batch size: 18, lr: 4.58e-04
2022-05-29 19:50:53,268 INFO [train.py:761] (5/8) Epoch 35, batch 3950, loss[loss=0.1867, simple_loss=0.2657, pruned_loss=0.05386, over 4639.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3044, pruned_loss=0.07037, over 967369.79 frames.], batch size: 11, lr: 4.57e-04
2022-05-29 19:51:31,848 INFO [train.py:761] (5/8) Epoch 35, batch 4000, loss[loss=0.2101, simple_loss=0.3064, pruned_loss=0.05693, over 4983.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3045, pruned_loss=0.07034, over 967617.93 frames.], batch size: 15, lr: 4.57e-04
2022-05-29 19:52:10,132 INFO [train.py:761] (5/8) Epoch 35, batch 4050, loss[loss=0.1935, simple_loss=0.2779, pruned_loss=0.05461, over 4789.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3042, pruned_loss=0.07043, over 967738.38 frames.], batch size: 13, lr: 4.57e-04
2022-05-29 19:52:48,253 INFO [train.py:761] (5/8) Epoch 35, batch 4100, loss[loss=0.2254, simple_loss=0.3192, pruned_loss=0.06585, over 4803.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3045, pruned_loss=0.07053, over 966012.93 frames.], batch size: 16, lr: 4.57e-04
2022-05-29 19:53:26,416 INFO [train.py:761] (5/8) Epoch 35, batch 4150, loss[loss=0.2243, simple_loss=0.3082, pruned_loss=0.07021, over 4994.00 frames.], tot_loss[loss=0.2234, simple_loss=0.305, pruned_loss=0.07094, over 966218.93 frames.], batch size: 13, lr: 4.57e-04
2022-05-29 19:54:05,059 INFO [train.py:761] (5/8) Epoch 35, batch 4200, loss[loss=0.2215, simple_loss=0.3037, pruned_loss=0.06964, over 4780.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3044, pruned_loss=0.07013, over 967066.63 frames.], batch size: 20, lr: 4.57e-04
2022-05-29 19:54:42,946 INFO [train.py:761] (5/8) Epoch 35, batch 4250, loss[loss=0.1838, simple_loss=0.2722, pruned_loss=0.04769, over 4614.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3035, pruned_loss=0.06985, over 966805.22 frames.], batch size: 12, lr: 4.57e-04
2022-05-29 19:55:21,609 INFO [train.py:761] (5/8) Epoch 35, batch 4300, loss[loss=0.2191, simple_loss=0.2927, pruned_loss=0.07272, over 4733.00 frames.], tot_loss[loss=0.2204, simple_loss=0.303, pruned_loss=0.06889, over 967537.65 frames.], batch size: 12, lr: 4.57e-04
2022-05-29 19:55:59,555 INFO [train.py:761] (5/8) Epoch 35, batch 4350, loss[loss=0.183, simple_loss=0.2624, pruned_loss=0.05175, over 4729.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3039, pruned_loss=0.06941, over 966771.38 frames.], batch size: 12, lr: 4.57e-04
2022-05-29 19:56:37,871 INFO [train.py:761] (5/8) Epoch 35, batch 4400, loss[loss=0.1963, simple_loss=0.2698, pruned_loss=0.06138, over 4729.00 frames.], tot_loss[loss=0.2208, simple_loss=0.3031, pruned_loss=0.0692, over 967816.38 frames.], batch size: 12, lr: 4.57e-04
2022-05-29 19:57:16,155 INFO [train.py:761] (5/8) Epoch 35, batch 4450, loss[loss=0.199, simple_loss=0.284, pruned_loss=0.05697, over 4782.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3026, pruned_loss=0.06921, over 967923.15 frames.], batch size: 13, lr: 4.57e-04
2022-05-29 19:57:54,310 INFO [train.py:761] (5/8) Epoch 35, batch 4500, loss[loss=0.2009, simple_loss=0.3034, pruned_loss=0.04918, over 4843.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3016, pruned_loss=0.0688, over 966636.35 frames.], batch size: 18, lr: 4.57e-04
2022-05-29 19:58:32,771 INFO [train.py:761] (5/8) Epoch 35, batch 4550, loss[loss=0.2278, simple_loss=0.3178, pruned_loss=0.06887, over 4950.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3021, pruned_loss=0.06881, over 966349.69 frames.], batch size: 46, lr: 4.57e-04
2022-05-29 19:59:11,262 INFO [train.py:761] (5/8) Epoch 35, batch 4600, loss[loss=0.2649, simple_loss=0.3493, pruned_loss=0.09022, over 4927.00 frames.], tot_loss[loss=0.22, simple_loss=0.3027, pruned_loss=0.06865, over 966761.41 frames.], batch size: 45, lr: 4.57e-04
2022-05-29 19:59:49,083 INFO [train.py:761] (5/8) Epoch 35, batch 4650, loss[loss=0.1899, simple_loss=0.2688, pruned_loss=0.05553, over 4979.00 frames.], tot_loss[loss=0.22, simple_loss=0.3027, pruned_loss=0.06865, over 966289.36 frames.], batch size: 15, lr: 4.57e-04
2022-05-29 20:00:27,391 INFO [train.py:761] (5/8) Epoch 35, batch 4700, loss[loss=0.2467, simple_loss=0.3205, pruned_loss=0.0864, over 4845.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3026, pruned_loss=0.06909, over 966336.42 frames.], batch size: 17, lr: 4.57e-04
2022-05-29 20:01:05,175 INFO [train.py:761] (5/8) Epoch 35, batch 4750, loss[loss=0.1554, simple_loss=0.2344, pruned_loss=0.03817, over 4838.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3014, pruned_loss=0.06867, over 966893.60 frames.], batch size: 11, lr: 4.57e-04
2022-05-29 20:01:43,586 INFO [train.py:761] (5/8) Epoch 35, batch 4800, loss[loss=0.2027, simple_loss=0.2752, pruned_loss=0.06508, over 4734.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3014, pruned_loss=0.06872, over 967865.56 frames.], batch size: 11, lr: 4.57e-04
2022-05-29 20:02:21,423 INFO [train.py:761] (5/8) Epoch 35, batch 4850, loss[loss=0.258, simple_loss=0.3502, pruned_loss=0.08287, over 4898.00 frames.], tot_loss[loss=0.218, simple_loss=0.3005, pruned_loss=0.06772, over 967693.57 frames.], batch size: 25, lr: 4.57e-04
2022-05-29 20:02:59,743 INFO [train.py:761] (5/8) Epoch 35, batch 4900, loss[loss=0.2036, simple_loss=0.2818, pruned_loss=0.06274, over 4878.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3011, pruned_loss=0.06774, over 967389.18 frames.], batch size: 12, lr: 4.57e-04
2022-05-29 20:03:37,687 INFO [train.py:761] (5/8) Epoch 35, batch 4950, loss[loss=0.1836, simple_loss=0.2605, pruned_loss=0.0533, over 4984.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3004, pruned_loss=0.06747, over 967118.01 frames.], batch size: 11, lr: 4.57e-04
2022-05-29 20:04:16,339 INFO [train.py:761] (5/8) Epoch 35, batch 5000, loss[loss=0.2401, simple_loss=0.3215, pruned_loss=0.07938, over 4826.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3019, pruned_loss=0.06837, over 966454.12 frames.], batch size: 18, lr: 4.56e-04
2022-05-29 20:04:54,821 INFO [train.py:761] (5/8) Epoch 35, batch 5050, loss[loss=0.232, simple_loss=0.3229, pruned_loss=0.07059, over 4845.00 frames.], tot_loss[loss=0.2208, simple_loss=0.3032, pruned_loss=0.0692, over 966602.08 frames.], batch size: 14, lr: 4.56e-04
2022-05-29 20:05:33,557 INFO [train.py:761] (5/8) Epoch 35, batch 5100, loss[loss=0.2059, simple_loss=0.3001, pruned_loss=0.05589, over 4677.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3058, pruned_loss=0.07081, over 966371.03 frames.], batch size: 13, lr: 4.56e-04
2022-05-29 20:06:11,336 INFO [train.py:761] (5/8) Epoch 35, batch 5150, loss[loss=0.2309, simple_loss=0.3094, pruned_loss=0.07621, over 4876.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3049, pruned_loss=0.07022, over 967710.29 frames.], batch size: 26, lr: 4.56e-04
2022-05-29 20:06:50,011 INFO [train.py:761] (5/8) Epoch 35, batch 5200, loss[loss=0.2273, simple_loss=0.3162, pruned_loss=0.06924, over 4802.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3059, pruned_loss=0.07077, over 968174.69 frames.], batch size: 20, lr: 4.56e-04
2022-05-29 20:07:28,396 INFO [train.py:761] (5/8) Epoch 35, batch 5250, loss[loss=0.2018, simple_loss=0.2732, pruned_loss=0.06514, over 4804.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3055, pruned_loss=0.07035, over 967674.63 frames.], batch size: 12, lr: 4.56e-04
2022-05-29 20:08:06,826 INFO [train.py:761] (5/8) Epoch 35, batch 5300, loss[loss=0.2278, simple_loss=0.3114, pruned_loss=0.07206, over 4672.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3048, pruned_loss=0.06955, over 966691.76 frames.], batch size: 13, lr: 4.56e-04
2022-05-29 20:08:45,256 INFO [train.py:761] (5/8) Epoch 35, batch 5350, loss[loss=0.1924, simple_loss=0.2859, pruned_loss=0.04946, over 4727.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3055, pruned_loss=0.07001, over 967455.91 frames.], batch size: 13, lr: 4.56e-04
2022-05-29 20:09:23,290 INFO [train.py:761] (5/8) Epoch 35, batch 5400, loss[loss=0.2487, simple_loss=0.3225, pruned_loss=0.08749, over 4950.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3054, pruned_loss=0.06989, over 967081.83 frames.], batch size: 26, lr: 4.56e-04
2022-05-29 20:10:01,492 INFO [train.py:761] (5/8) Epoch 35, batch 5450, loss[loss=0.2963, simple_loss=0.3539, pruned_loss=0.1194, over 4929.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3051, pruned_loss=0.07014, over 966901.85 frames.], batch size: 47, lr: 4.56e-04
2022-05-29 20:10:40,079 INFO [train.py:761] (5/8) Epoch 35, batch 5500, loss[loss=0.2011, simple_loss=0.2631, pruned_loss=0.06959, over 4988.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3044, pruned_loss=0.0702, over 967560.89 frames.], batch size: 12, lr: 4.56e-04
2022-05-29 20:11:18,537 INFO [train.py:761] (5/8) Epoch 35, batch 5550, loss[loss=0.2618, simple_loss=0.3457, pruned_loss=0.0889, over 4792.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3039, pruned_loss=0.06964, over 967552.34 frames.], batch size: 13, lr: 4.56e-04
2022-05-29 20:11:56,613 INFO [train.py:761] (5/8) Epoch 35, batch 5600, loss[loss=0.2425, simple_loss=0.3294, pruned_loss=0.07778, over 4856.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3044, pruned_loss=0.06963, over 967305.11 frames.], batch size: 17, lr: 4.56e-04
2022-05-29 20:12:34,456 INFO [train.py:761] (5/8) Epoch 35, batch 5650, loss[loss=0.1974, simple_loss=0.2891, pruned_loss=0.0529, over 4846.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3037, pruned_loss=0.06969, over 966636.70 frames.], batch size: 17, lr: 4.56e-04
2022-05-29 20:13:13,078 INFO [train.py:761] (5/8) Epoch 35, batch 5700, loss[loss=0.2173, simple_loss=0.3084, pruned_loss=0.06308, over 4793.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3051, pruned_loss=0.07023, over 968229.57 frames.], batch size: 14, lr: 4.56e-04
2022-05-29 20:13:51,413 INFO [train.py:761] (5/8) Epoch 35, batch 5750, loss[loss=0.2275, simple_loss=0.3139, pruned_loss=0.07055, over 4947.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3041, pruned_loss=0.06981, over 966302.35 frames.], batch size: 16, lr: 4.56e-04
2022-05-29 20:14:30,330 INFO [train.py:761] (5/8) Epoch 35, batch 5800, loss[loss=0.2121, simple_loss=0.2873, pruned_loss=0.06843, over 4956.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3034, pruned_loss=0.06915, over 966002.50 frames.], batch size: 16, lr: 4.56e-04
2022-05-29 20:15:08,827 INFO [train.py:761] (5/8) Epoch 35, batch 5850, loss[loss=0.2074, simple_loss=0.2928, pruned_loss=0.061, over 4912.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3042, pruned_loss=0.06918, over 966445.43 frames.], batch size: 14, lr: 4.56e-04
2022-05-29 20:15:46,713 INFO [train.py:761] (5/8) Epoch 35, batch 5900, loss[loss=0.2126, simple_loss=0.2824, pruned_loss=0.0714, over 4650.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3043, pruned_loss=0.06919, over 966042.37 frames.], batch size: 11, lr: 4.56e-04
2022-05-29 20:16:24,619 INFO [train.py:761] (5/8) Epoch 35, batch 5950, loss[loss=0.2779, simple_loss=0.3604, pruned_loss=0.09767, over 4859.00 frames.], tot_loss[loss=0.2207, simple_loss=0.304, pruned_loss=0.0687, over 965556.96 frames.], batch size: 14, lr: 4.56e-04
2022-05-29 20:17:03,084 INFO [train.py:761] (5/8) Epoch 35, batch 6000, loss[loss=0.212, simple_loss=0.3, pruned_loss=0.06196, over 4925.00 frames.], tot_loss[loss=0.2198, simple_loss=0.303, pruned_loss=0.06826, over 965504.11 frames.], batch size: 26, lr: 4.55e-04
2022-05-29 20:17:03,085 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 20:17:13,048 INFO [train.py:790] (5/8) Epoch 35, validation: loss=0.1981, simple_loss=0.2995, pruned_loss=0.0484, over 944034.00 frames.
2022-05-29 20:17:50,906 INFO [train.py:761] (5/8) Epoch 35, batch 6050, loss[loss=0.1855, simple_loss=0.2666, pruned_loss=0.05224, over 4735.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3039, pruned_loss=0.06893, over 965006.20 frames.], batch size: 12, lr: 4.55e-04
2022-05-29 20:18:29,070 INFO [train.py:761] (5/8) Epoch 35, batch 6100, loss[loss=0.1956, simple_loss=0.2897, pruned_loss=0.05074, over 4891.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3052, pruned_loss=0.06978, over 965552.26 frames.], batch size: 25, lr: 4.55e-04
2022-05-29 20:19:06,762 INFO [train.py:761] (5/8) Epoch 35, batch 6150, loss[loss=0.2235, simple_loss=0.2812, pruned_loss=0.0829, over 4977.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3054, pruned_loss=0.07037, over 965097.78 frames.], batch size: 12, lr: 4.55e-04
2022-05-29 20:19:45,396 INFO [train.py:761] (5/8) Epoch 35, batch 6200, loss[loss=0.2168, simple_loss=0.3085, pruned_loss=0.06255, over 4918.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3041, pruned_loss=0.06987, over 964665.64 frames.], batch size: 13, lr: 4.55e-04
2022-05-29 20:20:23,565 INFO [train.py:761] (5/8) Epoch 35, batch 6250, loss[loss=0.2335, simple_loss=0.3146, pruned_loss=0.07617, over 4915.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3041, pruned_loss=0.06947, over 965410.35 frames.], batch size: 14, lr: 4.55e-04
2022-05-29 20:21:02,179 INFO [train.py:761] (5/8) Epoch 35, batch 6300, loss[loss=0.2006, simple_loss=0.2954, pruned_loss=0.05292, over 4672.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3033, pruned_loss=0.06924, over 964539.08 frames.], batch size: 13, lr: 4.55e-04
2022-05-29 20:21:40,369 INFO [train.py:761] (5/8) Epoch 35, batch 6350, loss[loss=0.1639, simple_loss=0.2488, pruned_loss=0.03951, over 4982.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3026, pruned_loss=0.06916, over 965169.22 frames.], batch size: 12, lr: 4.55e-04
2022-05-29 20:22:18,751 INFO [train.py:761] (5/8) Epoch 35, batch 6400, loss[loss=0.2151, simple_loss=0.319, pruned_loss=0.05561, over 4763.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3023, pruned_loss=0.069, over 965044.13 frames.], batch size: 20, lr: 4.55e-04
2022-05-29 20:22:57,221 INFO [train.py:761] (5/8) Epoch 35, batch 6450, loss[loss=0.2506, simple_loss=0.3412, pruned_loss=0.08005, over 4968.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3025, pruned_loss=0.06912, over 965888.31 frames.], batch size: 15, lr: 4.55e-04
2022-05-29 20:23:35,494 INFO [train.py:761] (5/8) Epoch 35, batch 6500, loss[loss=0.2155, simple_loss=0.3018, pruned_loss=0.06456, over 4975.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3028, pruned_loss=0.06876, over 966207.65 frames.], batch size: 14, lr: 4.55e-04
2022-05-29 20:24:13,325 INFO [train.py:761] (5/8) Epoch 35, batch 6550, loss[loss=0.1745, simple_loss=0.2576, pruned_loss=0.04569, over 4787.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3014, pruned_loss=0.06776, over 966949.10 frames.], batch size: 13, lr: 4.55e-04
2022-05-29 20:24:51,943 INFO [train.py:761] (5/8) Epoch 35, batch 6600, loss[loss=0.2075, simple_loss=0.2922, pruned_loss=0.06136, over 4850.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3, pruned_loss=0.06718, over 966233.84 frames.], batch size: 13, lr: 4.55e-04
2022-05-29 20:25:30,280 INFO [train.py:761] (5/8) Epoch 35, batch 6650, loss[loss=0.2493, simple_loss=0.3228, pruned_loss=0.08788, over 4916.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3004, pruned_loss=0.06792, over 965255.49 frames.], batch size: 14, lr: 4.55e-04
2022-05-29 20:26:08,746 INFO [train.py:761] (5/8) Epoch 35, batch 6700, loss[loss=0.2058, simple_loss=0.3078, pruned_loss=0.05191, over 4852.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3013, pruned_loss=0.0688, over 965800.60 frames.], batch size: 18, lr: 4.55e-04
2022-05-29 20:27:01,212 INFO [train.py:761] (5/8) Epoch 36, batch 0, loss[loss=0.1824, simple_loss=0.2925, pruned_loss=0.03616, over 4711.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2925, pruned_loss=0.03616, over 4711.00 frames.], batch size: 14, lr: 4.55e-04
2022-05-29 20:27:39,320 INFO [train.py:761] (5/8) Epoch 36, batch 50, loss[loss=0.1784, simple_loss=0.2842, pruned_loss=0.03627, over 4971.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2995, pruned_loss=0.0566, over 217413.48 frames.], batch size: 12, lr: 4.55e-04
2022-05-29 20:28:17,260 INFO [train.py:761] (5/8) Epoch 36, batch 100, loss[loss=0.1864, simple_loss=0.27, pruned_loss=0.05142, over 4669.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2976, pruned_loss=0.05612, over 383523.42 frames.], batch size: 12, lr: 4.55e-04
2022-05-29 20:28:55,833 INFO [train.py:761] (5/8) Epoch 36, batch 150, loss[loss=0.2079, simple_loss=0.3074, pruned_loss=0.0542, over 4714.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2968, pruned_loss=0.05567, over 511831.36 frames.], batch size: 14, lr: 4.55e-04
2022-05-29 20:29:33,638 INFO [train.py:761] (5/8) Epoch 36, batch 200, loss[loss=0.2498, simple_loss=0.3299, pruned_loss=0.08485, over 4910.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2968, pruned_loss=0.05648, over 612347.63 frames.], batch size: 14, lr: 4.55e-04
2022-05-29 20:30:11,771 INFO [train.py:761] (5/8) Epoch 36, batch 250, loss[loss=0.1998, simple_loss=0.2916, pruned_loss=0.05404, over 4664.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2968, pruned_loss=0.05644, over 689726.04 frames.], batch size: 12, lr: 4.55e-04
2022-05-29 20:30:49,431 INFO [train.py:761] (5/8) Epoch 36, batch 300, loss[loss=0.2244, simple_loss=0.3198, pruned_loss=0.06446, over 4798.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2976, pruned_loss=0.05699, over 751144.06 frames.], batch size: 16, lr: 4.54e-04
2022-05-29 20:31:27,474 INFO [train.py:761] (5/8) Epoch 36, batch 350, loss[loss=0.1836, simple_loss=0.2664, pruned_loss=0.05036, over 4732.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2963, pruned_loss=0.05616, over 798679.31 frames.], batch size: 11, lr: 4.54e-04
2022-05-29 20:32:05,417 INFO [train.py:761] (5/8) Epoch 36, batch 400, loss[loss=0.1786, simple_loss=0.2659, pruned_loss=0.04564, over 4808.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2951, pruned_loss=0.05565, over 835639.59 frames.], batch size: 12, lr: 4.54e-04
2022-05-29 20:32:43,561 INFO [train.py:761] (5/8) Epoch 36, batch 450, loss[loss=0.2016, simple_loss=0.2982, pruned_loss=0.05249, over 4854.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2955, pruned_loss=0.0554, over 864401.70 frames.], batch size: 14, lr: 4.54e-04
2022-05-29 20:33:21,407 INFO [train.py:761] (5/8) Epoch 36, batch 500, loss[loss=0.151, simple_loss=0.2426, pruned_loss=0.02976, over 4892.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2947, pruned_loss=0.05509, over 886636.34 frames.], batch size: 12, lr: 4.54e-04
2022-05-29 20:33:59,923 INFO [train.py:761] (5/8) Epoch 36, batch 550, loss[loss=0.2135, simple_loss=0.3058, pruned_loss=0.06058, over 4967.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2948, pruned_loss=0.05472, over 903752.97 frames.], batch size: 15, lr: 4.54e-04
2022-05-29 20:34:38,117 INFO [train.py:761] (5/8) Epoch 36, batch 600, loss[loss=0.2023, simple_loss=0.291, pruned_loss=0.05682, over 4943.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2948, pruned_loss=0.0547, over 917175.41 frames.], batch size: 16, lr: 4.54e-04
2022-05-29 20:35:16,112 INFO [train.py:761] (5/8) Epoch 36, batch 650, loss[loss=0.2076, simple_loss=0.3038, pruned_loss=0.05568, over 4899.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2947, pruned_loss=0.05456, over 927853.18 frames.], batch size: 15, lr: 4.54e-04
2022-05-29 20:35:53,726 INFO [train.py:761] (5/8) Epoch 36, batch 700, loss[loss=0.23, simple_loss=0.3237, pruned_loss=0.0681, over 4979.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2957, pruned_loss=0.05502, over 936913.80 frames.], batch size: 14, lr: 4.54e-04
2022-05-29 20:36:32,371 INFO [train.py:761] (5/8) Epoch 36, batch 750, loss[loss=0.1611, simple_loss=0.2538, pruned_loss=0.03417, over 4725.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2953, pruned_loss=0.05559, over 943291.09 frames.], batch size: 11, lr: 4.54e-04
2022-05-29 20:37:09,982 INFO [train.py:761] (5/8) Epoch 36, batch 800, loss[loss=0.2376, simple_loss=0.333, pruned_loss=0.07115, over 4982.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2959, pruned_loss=0.05613, over 948353.10 frames.], batch size: 21, lr: 4.54e-04
2022-05-29 20:37:47,918 INFO [train.py:761] (5/8) Epoch 36, batch 850, loss[loss=0.2132, simple_loss=0.3034, pruned_loss=0.06154, over 4755.00 frames.], tot_loss[loss=0.204, simple_loss=0.2962, pruned_loss=0.05589, over 951782.07 frames.], batch size: 15, lr: 4.54e-04
2022-05-29 20:38:25,777 INFO [train.py:761] (5/8) Epoch 36, batch 900, loss[loss=0.2357, simple_loss=0.3286, pruned_loss=0.07143, over 4954.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2959, pruned_loss=0.05586, over 955254.55 frames.], batch size: 16, lr: 4.54e-04
2022-05-29 20:39:04,169 INFO [train.py:761] (5/8) Epoch 36, batch 950, loss[loss=0.1799, simple_loss=0.2745, pruned_loss=0.04264, over 4730.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2961, pruned_loss=0.05629, over 956955.34 frames.], batch size: 12, lr: 4.54e-04
2022-05-29 20:39:41,944 INFO [train.py:761] (5/8) Epoch 36, batch 1000, loss[loss=0.1865, simple_loss=0.279, pruned_loss=0.04701, over 4731.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2968, pruned_loss=0.05654, over 958045.62 frames.], batch size: 12, lr: 4.54e-04
2022-05-29 20:40:20,143 INFO [train.py:761] (5/8) Epoch 36, batch 1050, loss[loss=0.1902, simple_loss=0.2725, pruned_loss=0.05395, over 4854.00 frames.], tot_loss[loss=0.2039, simple_loss=0.296, pruned_loss=0.05592, over 959467.00 frames.], batch size: 13, lr: 4.54e-04
2022-05-29 20:40:57,910 INFO [train.py:761] (5/8) Epoch 36, batch 1100, loss[loss=0.1992, simple_loss=0.2848, pruned_loss=0.05681, over 4732.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2975, pruned_loss=0.05696, over 960527.80 frames.], batch size: 12, lr: 4.54e-04
2022-05-29 20:41:36,063 INFO [train.py:761] (5/8) Epoch 36, batch 1150, loss[loss=0.1912, simple_loss=0.2764, pruned_loss=0.05298, over 4804.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2988, pruned_loss=0.05764, over 961172.21 frames.], batch size: 12, lr: 4.54e-04
2022-05-29 20:42:13,938 INFO [train.py:761] (5/8) Epoch 36, batch 1200, loss[loss=0.2134, simple_loss=0.3026, pruned_loss=0.06205, over 4663.00 frames.], tot_loss[loss=0.2063, simple_loss=0.298, pruned_loss=0.05735, over 961803.96 frames.], batch size: 12, lr: 4.54e-04
2022-05-29 20:42:51,891 INFO [train.py:761] (5/8) Epoch 36, batch 1250, loss[loss=0.1974, simple_loss=0.2854, pruned_loss=0.05468, over 4920.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2981, pruned_loss=0.05741, over 964105.06 frames.], batch size: 13, lr: 4.54e-04
2022-05-29 20:43:29,418 INFO [train.py:761] (5/8) Epoch 36, batch 1300, loss[loss=0.1687, simple_loss=0.2691, pruned_loss=0.03417, over 4666.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2971, pruned_loss=0.05665, over 964313.95 frames.], batch size: 13, lr: 4.54e-04
2022-05-29 20:44:06,994 INFO [train.py:761] (5/8) Epoch 36, batch 1350, loss[loss=0.1977, simple_loss=0.3133, pruned_loss=0.04103, over 4896.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2976, pruned_loss=0.05655, over 965253.57 frames.], batch size: 26, lr: 4.53e-04
2022-05-29 20:44:45,334 INFO [train.py:761] (5/8) Epoch 36, batch 1400, loss[loss=0.2155, simple_loss=0.3046, pruned_loss=0.06318, over 4731.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2964, pruned_loss=0.05597, over 965004.61 frames.], batch size: 12, lr: 4.53e-04
2022-05-29 20:45:23,333 INFO [train.py:761] (5/8) Epoch 36, batch 1450, loss[loss=0.1864, simple_loss=0.266, pruned_loss=0.0534, over 4986.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2971, pruned_loss=0.05664, over 965487.78 frames.], batch size: 11, lr: 4.53e-04
2022-05-29 20:46:00,887 INFO [train.py:761] (5/8) Epoch 36, batch 1500, loss[loss=0.2561, simple_loss=0.3521, pruned_loss=0.08004, over 4812.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2977, pruned_loss=0.05649, over 967087.56 frames.], batch size: 18, lr: 4.53e-04
2022-05-29 20:46:39,056 INFO [train.py:761] (5/8) Epoch 36, batch 1550, loss[loss=0.1869, simple_loss=0.2925, pruned_loss=0.04065, over 4857.00 frames.], tot_loss[loss=0.205, simple_loss=0.2972, pruned_loss=0.05646, over 966867.41 frames.], batch size: 13, lr: 4.53e-04
2022-05-29 20:47:16,947 INFO [train.py:761] (5/8) Epoch 36, batch 1600, loss[loss=0.2205, simple_loss=0.3166, pruned_loss=0.06222, over 4987.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2977, pruned_loss=0.05669, over 967360.45 frames.], batch size: 13, lr: 4.53e-04
2022-05-29 20:47:54,675 INFO [train.py:761] (5/8) Epoch 36, batch 1650, loss[loss=0.1857, simple_loss=0.2958, pruned_loss=0.03779, over 4854.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2969, pruned_loss=0.05602, over 966569.07 frames.], batch size: 13, lr: 4.53e-04
2022-05-29 20:48:32,790 INFO [train.py:761] (5/8) Epoch 36, batch 1700, loss[loss=0.1815, simple_loss=0.2811, pruned_loss=0.04095, over 4805.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2981, pruned_loss=0.05645, over 965657.19 frames.], batch size: 12, lr: 4.53e-04
2022-05-29 20:49:11,000 INFO [train.py:761] (5/8) Epoch 36, batch 1750, loss[loss=0.1966, simple_loss=0.2908, pruned_loss=0.05121, over 4878.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2986, pruned_loss=0.05637, over 965949.65 frames.], batch size: 15, lr: 4.53e-04
2022-05-29 20:49:48,525 INFO [train.py:761] (5/8) Epoch 36, batch 1800, loss[loss=0.1772, simple_loss=0.2601, pruned_loss=0.04715, over 4723.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2977, pruned_loss=0.05596, over 964976.13 frames.], batch size: 11, lr: 4.53e-04
2022-05-29 20:50:26,363 INFO [train.py:761] (5/8) Epoch 36, batch 1850, loss[loss=0.1656, simple_loss=0.2532, pruned_loss=0.03901, over 4932.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2976, pruned_loss=0.05589, over 964936.51 frames.], batch size: 13, lr: 4.53e-04
2022-05-29 20:51:04,569 INFO [train.py:761] (5/8) Epoch 36, batch 1900, loss[loss=0.2277, simple_loss=0.3108, pruned_loss=0.07231, over 4966.00 frames.], tot_loss[loss=0.206, simple_loss=0.2987, pruned_loss=0.05665, over 966687.51 frames.], batch size: 14, lr: 4.53e-04
2022-05-29 20:51:42,688 INFO [train.py:761] (5/8) Epoch 36, batch 1950, loss[loss=0.1852, simple_loss=0.2888, pruned_loss=0.04085, over 4664.00 frames.], tot_loss[loss=0.205, simple_loss=0.2978, pruned_loss=0.05607, over 965424.88 frames.], batch size: 12, lr: 4.53e-04
2022-05-29 20:52:20,289 INFO [train.py:761] (5/8) Epoch 36, batch 2000, loss[loss=0.1794, simple_loss=0.2737, pruned_loss=0.04255, over 4978.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2974, pruned_loss=0.0558, over 965720.17 frames.], batch size: 13, lr: 4.53e-04
2022-05-29 20:52:58,929 INFO [train.py:761] (5/8) Epoch 36, batch 2050, loss[loss=0.243, simple_loss=0.3376, pruned_loss=0.07415, over 4942.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2986, pruned_loss=0.0564, over 966039.40 frames.], batch size: 16, lr: 4.53e-04
2022-05-29 20:53:36,944 INFO [train.py:761] (5/8) Epoch 36, batch 2100, loss[loss=0.2444, simple_loss=0.3293, pruned_loss=0.07981, over 4789.00 frames.], tot_loss[loss=0.2068, simple_loss=0.3001, pruned_loss=0.0567, over 966666.55 frames.], batch size: 15, lr: 4.53e-04
2022-05-29 20:54:15,196 INFO [train.py:761] (5/8) Epoch 36, batch 2150, loss[loss=0.2135, simple_loss=0.3048, pruned_loss=0.06112, over 4924.00 frames.], tot_loss[loss=0.206, simple_loss=0.299, pruned_loss=0.05645, over 966087.32 frames.], batch size: 13, lr: 4.53e-04
2022-05-29 20:54:52,948 INFO [train.py:761] (5/8) Epoch 36, batch 2200, loss[loss=0.2186, simple_loss=0.3222, pruned_loss=0.0575, over 4789.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2997, pruned_loss=0.05635, over 965938.98 frames.], batch size: 14, lr: 4.53e-04
2022-05-29 20:55:31,460 INFO [train.py:761] (5/8) Epoch 36, batch 2250, loss[loss=0.2199, simple_loss=0.3071, pruned_loss=0.06634, over 4893.00 frames.], tot_loss[loss=0.2055, simple_loss=0.299, pruned_loss=0.05604, over 964999.74 frames.], batch size: 15, lr: 4.53e-04
2022-05-29 20:56:09,466 INFO [train.py:761] (5/8) Epoch 36, batch 2300, loss[loss=0.1905, simple_loss=0.2816, pruned_loss=0.04971, over 4855.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2986, pruned_loss=0.05595, over 964721.06 frames.], batch size: 13, lr: 4.53e-04
2022-05-29 20:56:47,899 INFO [train.py:761] (5/8) Epoch 36, batch 2350, loss[loss=0.1826, simple_loss=0.3011, pruned_loss=0.032, over 4877.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2978, pruned_loss=0.05598, over 964728.52 frames.], batch size: 15, lr: 4.53e-04
2022-05-29 20:57:25,718 INFO [train.py:761] (5/8) Epoch 36, batch 2400, loss[loss=0.2131, simple_loss=0.3072, pruned_loss=0.05948, over 4945.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2965, pruned_loss=0.05548, over 964726.31 frames.], batch size: 16, lr: 4.52e-04
2022-05-29 20:58:03,715 INFO [train.py:761] (5/8) Epoch 36, batch 2450, loss[loss=0.2028, simple_loss=0.3108, pruned_loss=0.04735, over 4812.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2978, pruned_loss=0.05566, over 966133.12 frames.], batch size: 16, lr: 4.52e-04
2022-05-29 20:58:41,736 INFO [train.py:761] (5/8) Epoch 36, batch 2500, loss[loss=0.1853, simple_loss=0.2685, pruned_loss=0.05106, over 4888.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2968, pruned_loss=0.05587, over 966475.97 frames.], batch size: 12, lr: 4.52e-04
2022-05-29 20:59:19,953 INFO [train.py:761] (5/8) Epoch 36, batch 2550, loss[loss=0.1757, simple_loss=0.267, pruned_loss=0.04218, over 4969.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2979, pruned_loss=0.05648, over 966481.73 frames.], batch size: 12, lr: 4.52e-04
2022-05-29 20:59:57,295 INFO [train.py:761] (5/8) Epoch 36, batch 2600, loss[loss=0.1849, simple_loss=0.2864, pruned_loss=0.04166, over 4925.00 frames.], tot_loss[loss=0.2052, simple_loss=0.298, pruned_loss=0.05622, over 967176.42 frames.], batch size: 13, lr: 4.52e-04
2022-05-29 21:00:35,450 INFO [train.py:761] (5/8) Epoch 36, batch 2650, loss[loss=0.2045, simple_loss=0.2977, pruned_loss=0.05564, over 4970.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2982, pruned_loss=0.05657, over 967243.71 frames.], batch size: 14, lr: 4.52e-04
2022-05-29 21:01:12,998 INFO [train.py:761] (5/8) Epoch 36, batch 2700, loss[loss=0.1652, simple_loss=0.2533, pruned_loss=0.03852, over 4825.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2977, pruned_loss=0.05652, over 966666.27 frames.], batch size: 11, lr: 4.52e-04
2022-05-29 21:01:50,934 INFO [train.py:761] (5/8) Epoch 36, batch 2750, loss[loss=0.2092, simple_loss=0.3002, pruned_loss=0.0591, over 4890.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2971, pruned_loss=0.05637, over 966166.11 frames.], batch size: 12, lr: 4.52e-04
2022-05-29 21:02:28,812 INFO [train.py:761] (5/8) Epoch 36, batch 2800, loss[loss=0.2033, simple_loss=0.2952, pruned_loss=0.05565, over 4663.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2975, pruned_loss=0.0569, over 965702.64 frames.], batch size: 12, lr: 4.52e-04
2022-05-29 21:03:06,091 INFO [train.py:761] (5/8) Epoch 36, batch 2850, loss[loss=0.1876, simple_loss=0.2872, pruned_loss=0.04398, over 4879.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2962, pruned_loss=0.05644, over 965746.23 frames.], batch size: 15, lr: 4.52e-04
2022-05-29 21:03:43,483 INFO [train.py:761] (5/8) Epoch 36, batch 2900, loss[loss=0.2138, simple_loss=0.3067, pruned_loss=0.06044, over 4905.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2975, pruned_loss=0.05673, over 965354.60 frames.], batch size: 26, lr: 4.52e-04
2022-05-29 21:04:21,642 INFO [train.py:761] (5/8) Epoch 36, batch 2950, loss[loss=0.1594, simple_loss=0.2474, pruned_loss=0.03575, over 4724.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2963, pruned_loss=0.05637, over 964008.79 frames.], batch size: 11, lr: 4.52e-04
2022-05-29 21:04:59,438 INFO [train.py:761] (5/8) Epoch 36, batch 3000, loss[loss=0.2206, simple_loss=0.3162, pruned_loss=0.06257, over 4812.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2961, pruned_loss=0.05572, over 963769.93 frames.], batch size: 20, lr: 4.52e-04
2022-05-29 21:04:59,438 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 21:05:09,422 INFO [train.py:790] (5/8) Epoch 36, validation: loss=0.2037, simple_loss=0.3021, pruned_loss=0.05262, over 944034.00 frames.
2022-05-29 21:05:48,064 INFO [train.py:761] (5/8) Epoch 36, batch 3050, loss[loss=0.2068, simple_loss=0.3042, pruned_loss=0.05469, over 4870.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2967, pruned_loss=0.05591, over 964255.97 frames.], batch size: 17, lr: 4.52e-04
2022-05-29 21:06:25,979 INFO [train.py:761] (5/8) Epoch 36, batch 3100, loss[loss=0.1672, simple_loss=0.252, pruned_loss=0.04116, over 4730.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2973, pruned_loss=0.05652, over 964704.22 frames.], batch size: 11, lr: 4.52e-04
2022-05-29 21:07:04,297 INFO [train.py:761] (5/8) Epoch 36, batch 3150, loss[loss=0.2632, simple_loss=0.3526, pruned_loss=0.08688, over 4875.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2983, pruned_loss=0.05824, over 964038.63 frames.], batch size: 15, lr: 4.52e-04
2022-05-29 21:07:42,114 INFO [train.py:761] (5/8) Epoch 36, batch 3200, loss[loss=0.1848, simple_loss=0.2793, pruned_loss=0.04515, over 4856.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3, pruned_loss=0.06005, over 964974.54 frames.], batch size: 13, lr: 4.52e-04
2022-05-29 21:08:20,354 INFO [train.py:761] (5/8) Epoch 36, batch 3250, loss[loss=0.2175, simple_loss=0.2862, pruned_loss=0.0744, over 4923.00 frames.], tot_loss[loss=0.2114, simple_loss=0.3001, pruned_loss=0.0614, over 964654.88 frames.], batch size: 13, lr: 4.52e-04
2022-05-29 21:08:57,965 INFO [train.py:761] (5/8) Epoch 36, batch 3300, loss[loss=0.2164, simple_loss=0.2979, pruned_loss=0.06746, over 4673.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3004, pruned_loss=0.0621, over 964939.31 frames.], batch size: 13, lr: 4.52e-04
2022-05-29 21:09:35,657 INFO [train.py:761] (5/8) Epoch 36, batch 3350, loss[loss=0.1927, simple_loss=0.2952, pruned_loss=0.0451, over 4913.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3008, pruned_loss=0.06276, over 965744.61 frames.], batch size: 14, lr: 4.52e-04
2022-05-29 21:10:13,602 INFO [train.py:761] (5/8) Epoch 36, batch 3400, loss[loss=0.3146, simple_loss=0.3673, pruned_loss=0.131, over 4887.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3013, pruned_loss=0.06395, over 965858.59 frames.], batch size: 26, lr: 4.52e-04
2022-05-29 21:10:51,594 INFO [train.py:761] (5/8) Epoch 36, batch 3450, loss[loss=0.2129, simple_loss=0.3045, pruned_loss=0.06066, over 4933.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3016, pruned_loss=0.06516, over 966704.19 frames.], batch size: 16, lr: 4.51e-04
2022-05-29 21:11:29,741 INFO [train.py:761] (5/8) Epoch 36, batch 3500, loss[loss=0.2213, simple_loss=0.3017, pruned_loss=0.07047, over 4889.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2999, pruned_loss=0.06558, over 966298.55 frames.], batch size: 17, lr: 4.51e-04
2022-05-29 21:12:07,810 INFO [train.py:761] (5/8) Epoch 36, batch 3550, loss[loss=0.2758, simple_loss=0.3387, pruned_loss=0.1064, over 4960.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2993, pruned_loss=0.06595, over 966245.75 frames.], batch size: 16, lr: 4.51e-04
2022-05-29 21:12:46,072 INFO [train.py:761] (5/8) Epoch 36, batch 3600, loss[loss=0.2467, simple_loss=0.3169, pruned_loss=0.08828, over 4736.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3009, pruned_loss=0.06734, over 966215.21 frames.], batch size: 12, lr: 4.51e-04
2022-05-29 21:13:24,427 INFO [train.py:761] (5/8) Epoch 36, batch 3650, loss[loss=0.203, simple_loss=0.2896, pruned_loss=0.05819, over 4811.00 frames.], tot_loss[loss=0.2179, simple_loss=0.301, pruned_loss=0.06744, over 964978.78 frames.], batch size: 12, lr: 4.51e-04
2022-05-29 21:14:02,307 INFO [train.py:761] (5/8) Epoch 36, batch 3700, loss[loss=0.1888, simple_loss=0.2706, pruned_loss=0.05351, over 4980.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3014, pruned_loss=0.06848, over 966239.25 frames.], batch size: 12, lr: 4.51e-04
2022-05-29 21:14:40,690 INFO [train.py:761] (5/8) Epoch 36, batch 3750, loss[loss=0.2741, simple_loss=0.3502, pruned_loss=0.09903, over 4932.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3026, pruned_loss=0.06903, over 966480.22 frames.], batch size: 46, lr: 4.51e-04
2022-05-29 21:15:18,702 INFO [train.py:761] (5/8) Epoch 36, batch 3800, loss[loss=0.1589, simple_loss=0.2491, pruned_loss=0.0343, over 4878.00 frames.], tot_loss[loss=0.2206, simple_loss=0.303, pruned_loss=0.06906, over 967366.23 frames.], batch size: 12, lr: 4.51e-04
2022-05-29 21:15:57,668 INFO [train.py:761] (5/8) Epoch 36, batch 3850, loss[loss=0.2256, simple_loss=0.2985, pruned_loss=0.07633, over 4876.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3031, pruned_loss=0.06968, over 967843.75 frames.], batch size: 15, lr: 4.51e-04
2022-05-29 21:16:35,340 INFO [train.py:761] (5/8) Epoch 36, batch 3900, loss[loss=0.2198, simple_loss=0.3094, pruned_loss=0.06514, over 4977.00 frames.], tot_loss[loss=0.22, simple_loss=0.3021, pruned_loss=0.06891, over 967373.71 frames.], batch size: 14, lr: 4.51e-04
2022-05-29 21:17:16,644 INFO [train.py:761] (5/8) Epoch 36, batch 3950, loss[loss=0.1927, simple_loss=0.2701, pruned_loss=0.05764, over 4794.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3023, pruned_loss=0.06906, over 967052.52 frames.], batch size: 12, lr: 4.51e-04
2022-05-29 21:17:55,062 INFO [train.py:761] (5/8) Epoch 36, batch 4000, loss[loss=0.2075, simple_loss=0.2797, pruned_loss=0.06767, over 4974.00 frames.], tot_loss[loss=0.2209, simple_loss=0.303, pruned_loss=0.06936, over 967642.12 frames.], batch size: 12, lr: 4.51e-04
2022-05-29 21:18:33,484 INFO [train.py:761] (5/8) Epoch 36, batch 4050, loss[loss=0.1779, simple_loss=0.2666, pruned_loss=0.04462, over 4804.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3025, pruned_loss=0.06892, over 966879.35 frames.], batch size: 12, lr: 4.51e-04
2022-05-29 21:19:11,439 INFO [train.py:761] (5/8) Epoch 36, batch 4100, loss[loss=0.2097, simple_loss=0.2921, pruned_loss=0.06365, over 4847.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3044, pruned_loss=0.07001, over 967547.55 frames.], batch size: 13, lr: 4.51e-04
2022-05-29 21:19:49,506 INFO [train.py:761] (5/8) Epoch 36, batch 4150, loss[loss=0.217, simple_loss=0.2979, pruned_loss=0.06803, over 4774.00 frames.], tot_loss[loss=0.222, simple_loss=0.3044, pruned_loss=0.06976, over 968294.09 frames.], batch size: 15, lr: 4.51e-04
2022-05-29 21:20:27,487 INFO [train.py:761] (5/8) Epoch 36, batch 4200, loss[loss=0.2572, simple_loss=0.3423, pruned_loss=0.08608, over 4796.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3044, pruned_loss=0.06963, over 967170.02 frames.], batch size: 16, lr: 4.51e-04
2022-05-29 21:21:06,277 INFO [train.py:761] (5/8) Epoch 36, batch 4250, loss[loss=0.2237, simple_loss=0.308, pruned_loss=0.06969, over 4678.00 frames.], tot_loss[loss=0.2208, simple_loss=0.3037, pruned_loss=0.06896, over 966503.38 frames.], batch size: 13, lr: 4.51e-04
2022-05-29 21:21:44,768 INFO [train.py:761] (5/8) Epoch 36, batch 4300, loss[loss=0.2236, simple_loss=0.291, pruned_loss=0.07811, over 4829.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3038, pruned_loss=0.06947, over 966666.76 frames.], batch size: 11, lr: 4.51e-04
2022-05-29 21:22:23,056 INFO [train.py:761] (5/8) Epoch 36, batch 4350, loss[loss=0.212, simple_loss=0.2963, pruned_loss=0.06382, over 4809.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3031, pruned_loss=0.06951, over 965744.12 frames.], batch size: 12, lr: 4.51e-04
2022-05-29 21:23:01,128 INFO [train.py:761] (5/8) Epoch 36, batch 4400, loss[loss=0.1682, simple_loss=0.2636, pruned_loss=0.03645, over 4966.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3037, pruned_loss=0.0695, over 966579.17 frames.], batch size: 11, lr: 4.51e-04
2022-05-29 21:23:39,497 INFO [train.py:761] (5/8) Epoch 36, batch 4450, loss[loss=0.2149, simple_loss=0.2969, pruned_loss=0.06643, over 4852.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3032, pruned_loss=0.06909, over 966796.88 frames.], batch size: 13, lr: 4.51e-04
2022-05-29 21:24:17,238 INFO [train.py:761] (5/8) Epoch 36, batch 4500, loss[loss=0.2341, simple_loss=0.3259, pruned_loss=0.07117, over 4775.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3022, pruned_loss=0.06862, over 967047.63 frames.], batch size: 15, lr: 4.50e-04
2022-05-29 21:24:55,763 INFO [train.py:761] (5/8) Epoch 36, batch 4550, loss[loss=0.2375, simple_loss=0.3214, pruned_loss=0.07677, over 4780.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3021, pruned_loss=0.06867, over 967228.66 frames.], batch size: 13, lr: 4.50e-04
2022-05-29 21:25:34,166 INFO [train.py:761] (5/8) Epoch 36, batch 4600, loss[loss=0.1889, simple_loss=0.266, pruned_loss=0.0559, over 4896.00 frames.], tot_loss[loss=0.2201, simple_loss=0.3022, pruned_loss=0.06898, over 966621.12 frames.], batch size: 12, lr: 4.50e-04
2022-05-29 21:26:12,678 INFO [train.py:761] (5/8) Epoch 36, batch 4650, loss[loss=0.1924, simple_loss=0.2785, pruned_loss=0.05316, over 4847.00 frames.], tot_loss[loss=0.2198, simple_loss=0.3017, pruned_loss=0.06894, over 966767.88 frames.], batch size: 13, lr: 4.50e-04
2022-05-29 21:26:50,721 INFO [train.py:761] (5/8) Epoch 36, batch 4700, loss[loss=0.2434, simple_loss=0.3295, pruned_loss=0.07868, over 4956.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3016, pruned_loss=0.06874, over 965973.77 frames.], batch size: 16, lr: 4.50e-04
2022-05-29 21:27:28,891 INFO [train.py:761] (5/8) Epoch 36, batch 4750, loss[loss=0.182, simple_loss=0.2674, pruned_loss=0.04828, over 4639.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3028, pruned_loss=0.06912, over 966917.28 frames.], batch size: 11, lr: 4.50e-04
2022-05-29 21:28:07,266 INFO [train.py:761] (5/8) Epoch 36, batch 4800, loss[loss=0.2294, simple_loss=0.3249, pruned_loss=0.06691, over 4795.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3028, pruned_loss=0.06907, over 966122.13 frames.], batch size: 14, lr: 4.50e-04
2022-05-29 21:28:45,875 INFO [train.py:761] (5/8) Epoch 36, batch 4850, loss[loss=0.1748, simple_loss=0.2454, pruned_loss=0.05206, over 4978.00 frames.], tot_loss[loss=0.2191, simple_loss=0.302, pruned_loss=0.06813, over 966130.94 frames.], batch size: 12, lr: 4.50e-04
2022-05-29 21:29:23,953 INFO [train.py:761] (5/8) Epoch 36, batch 4900, loss[loss=0.1843, simple_loss=0.2749, pruned_loss=0.04683, over 4980.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3009, pruned_loss=0.06784, over 964561.38 frames.], batch size: 12, lr: 4.50e-04
2022-05-29 21:30:02,347 INFO [train.py:761] (5/8) Epoch 36, batch 4950, loss[loss=0.1754, simple_loss=0.2596, pruned_loss=0.04564, over 4732.00 frames.], tot_loss[loss=0.2187, simple_loss=0.301, pruned_loss=0.06818, over 965653.44 frames.], batch size: 11, lr: 4.50e-04
2022-05-29 21:30:39,782 INFO [train.py:761] (5/8) Epoch 36, batch 5000, loss[loss=0.1758, simple_loss=0.2609, pruned_loss=0.04536, over 4726.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3005, pruned_loss=0.06783, over 965781.36 frames.], batch size: 11, lr: 4.50e-04
2022-05-29 21:31:18,547 INFO [train.py:761] (5/8) Epoch 36, batch 5050, loss[loss=0.2521, simple_loss=0.3026, pruned_loss=0.1007, over 4744.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3, pruned_loss=0.06775, over 963717.61 frames.], batch size: 11, lr: 4.50e-04
2022-05-29 21:31:56,950 INFO [train.py:761] (5/8) Epoch 36, batch 5100, loss[loss=0.1789, simple_loss=0.2473, pruned_loss=0.05522, over 4736.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3011, pruned_loss=0.06882, over 964156.36 frames.], batch size: 11, lr: 4.50e-04
2022-05-29 21:32:35,338 INFO [train.py:761] (5/8) Epoch 36, batch 5150, loss[loss=0.26, simple_loss=0.3471, pruned_loss=0.08643, over 4847.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3031, pruned_loss=0.0697, over 966129.27 frames.], batch size: 17, lr: 4.50e-04
2022-05-29 21:33:12,880 INFO [train.py:761] (5/8) Epoch 36, batch 5200, loss[loss=0.2079, simple_loss=0.2954, pruned_loss=0.06015, over 4782.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3038, pruned_loss=0.06988, over 966579.05 frames.], batch size: 14, lr: 4.50e-04
2022-05-29 21:33:51,272 INFO [train.py:761] (5/8) Epoch 36, batch 5250, loss[loss=0.2019, simple_loss=0.2833, pruned_loss=0.06023, over 4648.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3039, pruned_loss=0.06945, over 966685.31 frames.], batch size: 11, lr: 4.50e-04
2022-05-29 21:34:29,631 INFO [train.py:761] (5/8) Epoch 36, batch 5300, loss[loss=0.2391, simple_loss=0.3273, pruned_loss=0.07542, over 4764.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3045, pruned_loss=0.06963, over 967135.21 frames.], batch size: 15, lr: 4.50e-04
2022-05-29 21:35:08,308 INFO [train.py:761] (5/8) Epoch 36, batch 5350, loss[loss=0.2208, simple_loss=0.3193, pruned_loss=0.06109, over 4988.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3056, pruned_loss=0.06987, over 967512.98 frames.], batch size: 26, lr: 4.50e-04
2022-05-29 21:35:46,320 INFO [train.py:761] (5/8) Epoch 36, batch 5400, loss[loss=0.2372, simple_loss=0.3297, pruned_loss=0.07232, over 4969.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3052, pruned_loss=0.0691, over 968538.32 frames.], batch size: 46, lr: 4.50e-04
2022-05-29 21:36:24,831 INFO [train.py:761] (5/8) Epoch 36, batch 5450, loss[loss=0.2235, simple_loss=0.3009, pruned_loss=0.07309, over 4675.00 frames.], tot_loss[loss=0.2188, simple_loss=0.303, pruned_loss=0.06734, over 968598.23 frames.], batch size: 13, lr: 4.50e-04
2022-05-29 21:37:03,823 INFO [train.py:761] (5/8) Epoch 36, batch 5500, loss[loss=0.1934, simple_loss=0.2672, pruned_loss=0.05976, over 4733.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3027, pruned_loss=0.06722, over 969464.03 frames.], batch size: 11, lr: 4.50e-04
2022-05-29 21:37:42,608 INFO [train.py:761] (5/8) Epoch 36, batch 5550, loss[loss=0.253, simple_loss=0.3327, pruned_loss=0.08659, over 4886.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3019, pruned_loss=0.06757, over 968470.46 frames.], batch size: 15, lr: 4.50e-04
2022-05-29 21:38:20,645 INFO [train.py:761] (5/8) Epoch 36, batch 5600, loss[loss=0.2133, simple_loss=0.314, pruned_loss=0.05631, over 4870.00 frames.], tot_loss[loss=0.22, simple_loss=0.3033, pruned_loss=0.06837, over 967751.83 frames.], batch size: 18, lr: 4.49e-04
2022-05-29 21:38:58,149 INFO [train.py:761] (5/8) Epoch 36, batch 5650, loss[loss=0.2202, simple_loss=0.3067, pruned_loss=0.06687, over 4800.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3038, pruned_loss=0.06973, over 967064.63 frames.], batch size: 20, lr: 4.49e-04
2022-05-29 21:39:36,271 INFO [train.py:761] (5/8) Epoch 36, batch 5700, loss[loss=0.1924, simple_loss=0.2829, pruned_loss=0.0509, over 4953.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3039, pruned_loss=0.06947, over 966658.98 frames.], batch size: 16, lr: 4.49e-04
2022-05-29 21:40:14,429 INFO [train.py:761] (5/8) Epoch 36, batch 5750, loss[loss=0.2272, simple_loss=0.2937, pruned_loss=0.08035, over 4975.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3032, pruned_loss=0.06946, over 965778.39 frames.], batch size: 12, lr: 4.49e-04
2022-05-29 21:40:52,573 INFO [train.py:761] (5/8) Epoch 36, batch 5800, loss[loss=0.2567, simple_loss=0.3357, pruned_loss=0.0888, over 4897.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3035, pruned_loss=0.06913, over 966564.33 frames.], batch size: 17, lr: 4.49e-04
2022-05-29 21:41:30,993 INFO [train.py:761] (5/8) Epoch 36, batch 5850, loss[loss=0.2319, simple_loss=0.3242, pruned_loss=0.06975, over 4834.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3042, pruned_loss=0.06923, over 967631.08 frames.], batch size: 25, lr: 4.49e-04
2022-05-29 21:42:09,219 INFO [train.py:761] (5/8) Epoch 36, batch 5900, loss[loss=0.2433, simple_loss=0.3233, pruned_loss=0.08163, over 4962.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3051, pruned_loss=0.06957, over 967109.90 frames.], batch size: 16, lr: 4.49e-04
2022-05-29 21:42:47,555 INFO [train.py:761] (5/8) Epoch 36, batch 5950, loss[loss=0.2504, simple_loss=0.3232, pruned_loss=0.08883, over 4981.00 frames.], tot_loss[loss=0.222, simple_loss=0.3049, pruned_loss=0.06958, over 967054.11 frames.], batch size: 15, lr: 4.49e-04
2022-05-29 21:43:25,709 INFO [train.py:761] (5/8) Epoch 36, batch 6000, loss[loss=0.2038, simple_loss=0.2893, pruned_loss=0.0591, over 4558.00 frames.], tot_loss[loss=0.2215, simple_loss=0.304, pruned_loss=0.06948, over 966878.64 frames.], batch size: 10, lr: 4.49e-04
2022-05-29 21:43:25,710 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 21:43:35,731 INFO [train.py:790] (5/8) Epoch 36, validation: loss=0.1973, simple_loss=0.2991, pruned_loss=0.04773, over 944034.00 frames.
2022-05-29 21:44:13,743 INFO [train.py:761] (5/8) Epoch 36, batch 6050, loss[loss=0.1663, simple_loss=0.2566, pruned_loss=0.03799, over 4971.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3032, pruned_loss=0.06856, over 967564.57 frames.], batch size: 12, lr: 4.49e-04
2022-05-29 21:44:52,006 INFO [train.py:761] (5/8) Epoch 36, batch 6100, loss[loss=0.2012, simple_loss=0.2867, pruned_loss=0.05787, over 4973.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3007, pruned_loss=0.06755, over 966803.92 frames.], batch size: 14, lr: 4.49e-04
2022-05-29 21:45:30,230 INFO [train.py:761] (5/8) Epoch 36, batch 6150, loss[loss=0.2463, simple_loss=0.3207, pruned_loss=0.08592, over 4918.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3015, pruned_loss=0.06807, over 965990.92 frames.], batch size: 14, lr: 4.49e-04
2022-05-29 21:46:08,084 INFO [train.py:761] (5/8) Epoch 36, batch 6200, loss[loss=0.2102, simple_loss=0.2808, pruned_loss=0.06979, over 4903.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3019, pruned_loss=0.06823, over 966875.89 frames.], batch size: 12, lr: 4.49e-04
2022-05-29 21:46:46,753 INFO [train.py:761] (5/8) Epoch 36, batch 6250, loss[loss=0.235, simple_loss=0.313, pruned_loss=0.07855, over 4672.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3021, pruned_loss=0.06851, over 966700.61 frames.], batch size: 13, lr: 4.49e-04
2022-05-29 21:47:24,853 INFO [train.py:761] (5/8) Epoch 36, batch 6300, loss[loss=0.221, simple_loss=0.3054, pruned_loss=0.06829, over 4715.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3022, pruned_loss=0.0683, over 966147.48 frames.], batch size: 14, lr: 4.49e-04
2022-05-29 21:48:03,417 INFO [train.py:761] (5/8) Epoch 36, batch 6350, loss[loss=0.2006, simple_loss=0.2894, pruned_loss=0.05591, over 4721.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3024, pruned_loss=0.0682, over 967170.09 frames.], batch size: 12, lr: 4.49e-04
2022-05-29 21:48:41,501 INFO [train.py:761] (5/8) Epoch 36, batch 6400, loss[loss=0.201, simple_loss=0.2844, pruned_loss=0.05877, over 4850.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3008, pruned_loss=0.06753, over 967187.85 frames.], batch size: 14, lr: 4.49e-04
2022-05-29 21:49:19,929 INFO [train.py:761] (5/8) Epoch 36, batch 6450, loss[loss=0.2062, simple_loss=0.2964, pruned_loss=0.05797, over 4759.00 frames.], tot_loss[loss=0.2206, simple_loss=0.3028, pruned_loss=0.06918, over 968293.25 frames.], batch size: 15, lr: 4.49e-04
2022-05-29 21:49:58,200 INFO [train.py:761] (5/8) Epoch 36, batch 6500, loss[loss=0.1882, simple_loss=0.2676, pruned_loss=0.05442, over 4734.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3037, pruned_loss=0.06929, over 967448.33 frames.], batch size: 11, lr: 4.49e-04
2022-05-29 21:50:37,036 INFO [train.py:761] (5/8) Epoch 36, batch 6550, loss[loss=0.2029, simple_loss=0.2739, pruned_loss=0.06593, over 4725.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3052, pruned_loss=0.06953, over 967746.51 frames.], batch size: 11, lr: 4.49e-04
2022-05-29 21:51:15,413 INFO [train.py:761] (5/8) Epoch 36, batch 6600, loss[loss=0.23, simple_loss=0.3299, pruned_loss=0.06506, over 4711.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3063, pruned_loss=0.06998, over 967484.10 frames.], batch size: 14, lr: 4.49e-04
2022-05-29 21:51:53,750 INFO [train.py:761] (5/8) Epoch 36, batch 6650, loss[loss=0.2473, simple_loss=0.3196, pruned_loss=0.08746, over 4854.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3057, pruned_loss=0.07042, over 966582.33 frames.], batch size: 13, lr: 4.48e-04
2022-05-29 21:52:31,531 INFO [train.py:761] (5/8) Epoch 36, batch 6700, loss[loss=0.2322, simple_loss=0.3295, pruned_loss=0.06748, over 4916.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3052, pruned_loss=0.07015, over 966978.72 frames.], batch size: 14, lr: 4.48e-04
2022-05-29 21:53:23,270 INFO [train.py:761] (5/8) Epoch 37, batch 0, loss[loss=0.1895, simple_loss=0.2685, pruned_loss=0.0552, over 4553.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2685, pruned_loss=0.0552, over 4553.00 frames.], batch size: 10, lr: 4.48e-04
2022-05-29 21:54:01,180 INFO [train.py:761] (5/8) Epoch 37, batch 50, loss[loss=0.237, simple_loss=0.3208, pruned_loss=0.07657, over 4827.00 frames.], tot_loss[loss=0.203, simple_loss=0.2953, pruned_loss=0.05535, over 217645.22 frames.], batch size: 18, lr: 4.48e-04
2022-05-29 21:54:39,080 INFO [train.py:761] (5/8) Epoch 37, batch 100, loss[loss=0.225, simple_loss=0.3211, pruned_loss=0.06448, over 4668.00 frames.], tot_loss[loss=0.2043, simple_loss=0.297, pruned_loss=0.05583, over 384455.21 frames.], batch size: 13, lr: 4.48e-04
2022-05-29 21:55:17,336 INFO [train.py:761] (5/8) Epoch 37, batch 150, loss[loss=0.2415, simple_loss=0.3436, pruned_loss=0.06963, over 4978.00 frames.], tot_loss[loss=0.205, simple_loss=0.2978, pruned_loss=0.05614, over 513331.72 frames.], batch size: 15, lr: 4.48e-04
2022-05-29 21:55:55,875 INFO [train.py:761] (5/8) Epoch 37, batch 200, loss[loss=0.173, simple_loss=0.277, pruned_loss=0.03448, over 4785.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2972, pruned_loss=0.05599, over 612464.08 frames.], batch size: 14, lr: 4.48e-04
2022-05-29 21:56:33,670 INFO [train.py:761] (5/8) Epoch 37, batch 250, loss[loss=0.1665, simple_loss=0.2624, pruned_loss=0.0353, over 4727.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2962, pruned_loss=0.05535, over 691292.79 frames.], batch size: 12, lr: 4.48e-04
2022-05-29 21:57:11,840 INFO [train.py:761] (5/8) Epoch 37, batch 300, loss[loss=0.1936, simple_loss=0.2919, pruned_loss=0.04763, over 4914.00 frames.], tot_loss[loss=0.2019, simple_loss=0.295, pruned_loss=0.05434, over 751813.26 frames.], batch size: 14, lr: 4.48e-04
2022-05-29 21:57:49,137 INFO [train.py:761] (5/8) Epoch 37, batch 350, loss[loss=0.1973, simple_loss=0.3074, pruned_loss=0.04361, over 4979.00 frames.], tot_loss[loss=0.2012, simple_loss=0.294, pruned_loss=0.0542, over 798609.32 frames.], batch size: 15, lr: 4.48e-04
2022-05-29 21:58:27,690 INFO [train.py:761] (5/8) Epoch 37, batch 400, loss[loss=0.2129, simple_loss=0.2947, pruned_loss=0.06558, over 4916.00 frames.], tot_loss[loss=0.201, simple_loss=0.2936, pruned_loss=0.05421, over 836153.49 frames.], batch size: 13, lr: 4.48e-04
2022-05-29 21:59:05,809 INFO [train.py:761] (5/8) Epoch 37, batch 450, loss[loss=0.2174, simple_loss=0.3223, pruned_loss=0.05625, over 4785.00 frames.], tot_loss[loss=0.2024, simple_loss=0.295, pruned_loss=0.0549, over 865001.67 frames.], batch size: 13, lr: 4.48e-04
2022-05-29 21:59:43,761 INFO [train.py:761] (5/8) Epoch 37, batch 500, loss[loss=0.1747, simple_loss=0.2786, pruned_loss=0.03537, over 4657.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2952, pruned_loss=0.05465, over 888391.82 frames.], batch size: 12, lr: 4.48e-04
2022-05-29 22:00:21,460 INFO [train.py:761] (5/8) Epoch 37, batch 550, loss[loss=0.2329, simple_loss=0.3212, pruned_loss=0.07236, over 4713.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2953, pruned_loss=0.05466, over 906336.37 frames.], batch size: 13, lr: 4.48e-04
2022-05-29 22:00:59,453 INFO [train.py:761] (5/8) Epoch 37, batch 600, loss[loss=0.1895, simple_loss=0.2881, pruned_loss=0.04551, over 4915.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2944, pruned_loss=0.054, over 919914.61 frames.], batch size: 14, lr: 4.48e-04
2022-05-29 22:01:37,596 INFO [train.py:761] (5/8) Epoch 37, batch 650, loss[loss=0.1827, simple_loss=0.3028, pruned_loss=0.03133, over 4787.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2948, pruned_loss=0.05426, over 929280.20 frames.], batch size: 14, lr: 4.48e-04
2022-05-29 22:02:15,963 INFO [train.py:761] (5/8) Epoch 37, batch 700, loss[loss=0.1806, simple_loss=0.2644, pruned_loss=0.0484, over 4742.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2938, pruned_loss=0.05425, over 936640.57 frames.], batch size: 11, lr: 4.48e-04
2022-05-29 22:02:53,907 INFO [train.py:761] (5/8) Epoch 37, batch 750, loss[loss=0.1612, simple_loss=0.247, pruned_loss=0.0377, over 4722.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2934, pruned_loss=0.05437, over 943598.34 frames.], batch size: 11, lr: 4.48e-04
2022-05-29 22:03:31,835 INFO [train.py:761] (5/8) Epoch 37, batch 800, loss[loss=0.1589, simple_loss=0.2441, pruned_loss=0.03685, over 4739.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2941, pruned_loss=0.05502, over 949172.21 frames.], batch size: 11, lr: 4.48e-04
2022-05-29 22:04:10,013 INFO [train.py:761] (5/8) Epoch 37, batch 850, loss[loss=0.2184, simple_loss=0.3092, pruned_loss=0.06382, over 4913.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2942, pruned_loss=0.05481, over 952076.30 frames.], batch size: 13, lr: 4.48e-04
2022-05-29 22:04:48,387 INFO [train.py:761] (5/8) Epoch 37, batch 900, loss[loss=0.2267, simple_loss=0.3155, pruned_loss=0.06892, over 4800.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2966, pruned_loss=0.05589, over 954190.10 frames.], batch size: 16, lr: 4.48e-04
2022-05-29 22:05:26,270 INFO [train.py:761] (5/8) Epoch 37, batch 950, loss[loss=0.2523, simple_loss=0.3467, pruned_loss=0.07895, over 4670.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2953, pruned_loss=0.05542, over 956500.13 frames.], batch size: 13, lr: 4.48e-04
2022-05-29 22:06:04,444 INFO [train.py:761] (5/8) Epoch 37, batch 1000, loss[loss=0.1783, simple_loss=0.277, pruned_loss=0.0398, over 4926.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2979, pruned_loss=0.05599, over 959056.06 frames.], batch size: 13, lr: 4.47e-04
2022-05-29 22:06:42,127 INFO [train.py:761] (5/8) Epoch 37, batch 1050, loss[loss=0.1922, simple_loss=0.2885, pruned_loss=0.04797, over 4976.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2971, pruned_loss=0.05584, over 961767.86 frames.], batch size: 15, lr: 4.47e-04
2022-05-29 22:07:20,071 INFO [train.py:761] (5/8) Epoch 37, batch 1100, loss[loss=0.2368, simple_loss=0.3328, pruned_loss=0.07041, over 4733.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2978, pruned_loss=0.05631, over 962069.25 frames.], batch size: 13, lr: 4.47e-04
2022-05-29 22:07:57,889 INFO [train.py:761] (5/8) Epoch 37, batch 1150, loss[loss=0.1592, simple_loss=0.2688, pruned_loss=0.02478, over 4789.00 frames.], tot_loss[loss=0.205, simple_loss=0.2979, pruned_loss=0.05608, over 962704.06 frames.], batch size: 14, lr: 4.47e-04
2022-05-29 22:08:36,134 INFO [train.py:761] (5/8) Epoch 37, batch 1200, loss[loss=0.2265, simple_loss=0.3264, pruned_loss=0.06326, over 4813.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2975, pruned_loss=0.05583, over 963306.33 frames.], batch size: 16, lr: 4.47e-04
2022-05-29 22:09:13,725 INFO [train.py:761] (5/8) Epoch 37, batch 1250, loss[loss=0.1794, simple_loss=0.2675, pruned_loss=0.04565, over 4994.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2968, pruned_loss=0.05585, over 964412.52 frames.], batch size: 12, lr: 4.47e-04
2022-05-29 22:09:52,124 INFO [train.py:761] (5/8) Epoch 37, batch 1300, loss[loss=0.2013, simple_loss=0.2878, pruned_loss=0.05744, over 4970.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2973, pruned_loss=0.05605, over 964494.57 frames.], batch size: 16, lr: 4.47e-04
2022-05-29 22:10:30,127 INFO [train.py:761] (5/8) Epoch 37, batch 1350, loss[loss=0.2041, simple_loss=0.3133, pruned_loss=0.04748, over 4975.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2973, pruned_loss=0.05628, over 966745.17 frames.], batch size: 26, lr: 4.47e-04
2022-05-29 22:11:07,823 INFO [train.py:761] (5/8) Epoch 37, batch 1400, loss[loss=0.2036, simple_loss=0.2805, pruned_loss=0.06334, over 4974.00 frames.], tot_loss[loss=0.2042, simple_loss=0.296, pruned_loss=0.05614, over 966664.32 frames.], batch size: 14, lr: 4.47e-04
2022-05-29 22:11:45,951 INFO [train.py:761] (5/8) Epoch 37, batch 1450, loss[loss=0.1782, simple_loss=0.2625, pruned_loss=0.04697, over 4658.00 frames.], tot_loss[loss=0.205, simple_loss=0.2965, pruned_loss=0.05678, over 966694.19 frames.], batch size: 12, lr: 4.47e-04
2022-05-29 22:12:24,171 INFO [train.py:761] (5/8) Epoch 37, batch 1500, loss[loss=0.2334, simple_loss=0.3256, pruned_loss=0.07065, over 4989.00 frames.], tot_loss[loss=0.2054, simple_loss=0.297, pruned_loss=0.05693, over 967198.46 frames.], batch size: 21, lr: 4.47e-04
2022-05-29 22:13:02,306 INFO [train.py:761] (5/8) Epoch 37, batch 1550, loss[loss=0.2003, simple_loss=0.2921, pruned_loss=0.05421, over 4790.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2968, pruned_loss=0.05637, over 966858.16 frames.], batch size: 14, lr: 4.47e-04
2022-05-29 22:13:40,046 INFO [train.py:761] (5/8) Epoch 37, batch 1600, loss[loss=0.2175, simple_loss=0.3142, pruned_loss=0.06039, over 4890.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2969, pruned_loss=0.05608, over 966876.93 frames.], batch size: 15, lr: 4.47e-04
2022-05-29 22:14:17,407 INFO [train.py:761] (5/8) Epoch 37, batch 1650, loss[loss=0.213, simple_loss=0.3124, pruned_loss=0.05681, over 4874.00 frames.], tot_loss[loss=0.205, simple_loss=0.2979, pruned_loss=0.05606, over 965226.91 frames.], batch size: 17, lr: 4.47e-04
2022-05-29 22:14:55,185 INFO [train.py:761] (5/8) Epoch 37, batch 1700, loss[loss=0.1829, simple_loss=0.2895, pruned_loss=0.03814, over 4676.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2984, pruned_loss=0.05667, over 964767.81 frames.], batch size: 12, lr: 4.47e-04
2022-05-29 22:15:32,953 INFO [train.py:761] (5/8) Epoch 37, batch 1750, loss[loss=0.1623, simple_loss=0.2504, pruned_loss=0.03712, over 4966.00 frames.], tot_loss[loss=0.2053, simple_loss=0.298, pruned_loss=0.05629, over 965426.11 frames.], batch size: 11, lr: 4.47e-04
2022-05-29 22:16:10,746 INFO [train.py:761] (5/8) Epoch 37, batch 1800, loss[loss=0.1716, simple_loss=0.254, pruned_loss=0.04461, over 4890.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2977, pruned_loss=0.05608, over 965675.72 frames.], batch size: 12, lr: 4.47e-04
2022-05-29 22:16:48,706 INFO [train.py:761] (5/8) Epoch 37, batch 1850, loss[loss=0.2065, simple_loss=0.3125, pruned_loss=0.05021, over 4831.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2976, pruned_loss=0.05647, over 964990.65 frames.], batch size: 20, lr: 4.47e-04
2022-05-29 22:17:26,720 INFO [train.py:761] (5/8) Epoch 37, batch 1900, loss[loss=0.215, simple_loss=0.2947, pruned_loss=0.06766, over 4729.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2978, pruned_loss=0.05665, over 965197.87 frames.], batch size: 12, lr: 4.47e-04
2022-05-29 22:18:04,527 INFO [train.py:761] (5/8) Epoch 37, batch 1950, loss[loss=0.1801, simple_loss=0.272, pruned_loss=0.04411, over 4808.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2979, pruned_loss=0.05663, over 964289.56 frames.], batch size: 12, lr: 4.47e-04
2022-05-29 22:18:43,018 INFO [train.py:761] (5/8) Epoch 37, batch 2000, loss[loss=0.2318, simple_loss=0.3268, pruned_loss=0.06834, over 4865.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2974, pruned_loss=0.05661, over 964680.44 frames.], batch size: 15, lr: 4.47e-04
2022-05-29 22:19:20,607 INFO [train.py:761] (5/8) Epoch 37, batch 2050, loss[loss=0.2147, simple_loss=0.3182, pruned_loss=0.05565, over 4799.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2974, pruned_loss=0.05646, over 966345.69 frames.], batch size: 16, lr: 4.47e-04
2022-05-29 22:19:58,231 INFO [train.py:761] (5/8) Epoch 37, batch 2100, loss[loss=0.1691, simple_loss=0.2612, pruned_loss=0.03857, over 4667.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2971, pruned_loss=0.05619, over 966698.59 frames.], batch size: 12, lr: 4.46e-04
2022-05-29 22:20:36,443 INFO [train.py:761] (5/8) Epoch 37, batch 2150, loss[loss=0.235, simple_loss=0.3278, pruned_loss=0.07103, over 4935.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2974, pruned_loss=0.0564, over 966147.35 frames.], batch size: 48, lr: 4.46e-04
2022-05-29 22:21:14,583 INFO [train.py:761] (5/8) Epoch 37, batch 2200, loss[loss=0.2091, simple_loss=0.3075, pruned_loss=0.05531, over 4674.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2981, pruned_loss=0.05691, over 966457.58 frames.], batch size: 13, lr: 4.46e-04
2022-05-29 22:21:52,547 INFO [train.py:761] (5/8) Epoch 37, batch 2250, loss[loss=0.2132, simple_loss=0.2972, pruned_loss=0.0646, over 4787.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2982, pruned_loss=0.05716, over 966591.99 frames.], batch size: 14, lr: 4.46e-04
2022-05-29 22:22:30,889 INFO [train.py:761] (5/8) Epoch 37, batch 2300, loss[loss=0.2562, simple_loss=0.3315, pruned_loss=0.0905, over 4959.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2983, pruned_loss=0.05723, over 966391.04 frames.], batch size: 49, lr: 4.46e-04
2022-05-29 22:23:08,851 INFO [train.py:761] (5/8) Epoch 37, batch 2350, loss[loss=0.1612, simple_loss=0.2452, pruned_loss=0.03864, over 4968.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2973, pruned_loss=0.05644, over 965995.07 frames.], batch size: 12, lr: 4.46e-04
2022-05-29 22:23:47,205 INFO [train.py:761] (5/8) Epoch 37, batch 2400, loss[loss=0.2323, simple_loss=0.3164, pruned_loss=0.07409, over 4970.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2982, pruned_loss=0.05723, over 965978.65 frames.], batch size: 16, lr: 4.46e-04
2022-05-29 22:24:25,812 INFO [train.py:761] (5/8) Epoch 37, batch 2450, loss[loss=0.2121, simple_loss=0.3087, pruned_loss=0.05778, over 4793.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2966, pruned_loss=0.05682, over 967222.89 frames.], batch size: 13, lr: 4.46e-04
2022-05-29 22:25:03,429 INFO [train.py:761] (5/8) Epoch 37, batch 2500, loss[loss=0.2102, simple_loss=0.3041, pruned_loss=0.05818, over 4715.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2967, pruned_loss=0.05657, over 965980.46 frames.], batch size: 14, lr: 4.46e-04
2022-05-29 22:25:40,956 INFO [train.py:761] (5/8) Epoch 37, batch 2550, loss[loss=0.2116, simple_loss=0.2993, pruned_loss=0.06194, over 4809.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2974, pruned_loss=0.05696, over 965303.22 frames.], batch size: 12, lr: 4.46e-04
2022-05-29 22:26:19,158 INFO [train.py:761] (5/8) Epoch 37, batch 2600, loss[loss=0.2149, simple_loss=0.3087, pruned_loss=0.0605, over 4833.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2969, pruned_loss=0.05591, over 966463.97 frames.], batch size: 18, lr: 4.46e-04
2022-05-29 22:26:57,244 INFO [train.py:761] (5/8) Epoch 37, batch 2650, loss[loss=0.2384, simple_loss=0.3328, pruned_loss=0.07204, over 4825.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2956, pruned_loss=0.05556, over 965579.00 frames.], batch size: 25, lr: 4.46e-04
2022-05-29 22:27:34,891 INFO [train.py:761] (5/8) Epoch 37, batch 2700, loss[loss=0.1804, simple_loss=0.2793, pruned_loss=0.04072, over 4916.00 frames.], tot_loss[loss=0.2028, simple_loss=0.295, pruned_loss=0.05528, over 966253.57 frames.], batch size: 13, lr: 4.46e-04
2022-05-29 22:28:12,981 INFO [train.py:761] (5/8) Epoch 37, batch 2750, loss[loss=0.1984, simple_loss=0.2704, pruned_loss=0.06322, over 4984.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2955, pruned_loss=0.05557, over 966713.09 frames.], batch size: 11, lr: 4.46e-04
2022-05-29 22:28:50,828 INFO [train.py:761] (5/8) Epoch 37, batch 2800, loss[loss=0.2185, simple_loss=0.2826, pruned_loss=0.07719, over 4804.00 frames.], tot_loss[loss=0.203, simple_loss=0.2956, pruned_loss=0.05517, over 967238.34 frames.], batch size: 12, lr: 4.46e-04
2022-05-29 22:29:28,381 INFO [train.py:761] (5/8) Epoch 37, batch 2850, loss[loss=0.2301, simple_loss=0.3239, pruned_loss=0.0682, over 4779.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2952, pruned_loss=0.05504, over 966378.37 frames.], batch size: 15, lr: 4.46e-04
2022-05-29 22:30:06,579 INFO [train.py:761] (5/8) Epoch 37, batch 2900, loss[loss=0.2282, simple_loss=0.3108, pruned_loss=0.07284, over 4876.00 frames.], tot_loss[loss=0.2024, simple_loss=0.295, pruned_loss=0.05493, over 966850.10 frames.], batch size: 17, lr: 4.46e-04
2022-05-29 22:30:44,691 INFO [train.py:761] (5/8) Epoch 37, batch 2950, loss[loss=0.1587, simple_loss=0.2432, pruned_loss=0.03716, over 4878.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2961, pruned_loss=0.05576, over 966932.75 frames.], batch size: 12, lr: 4.46e-04
2022-05-29 22:31:22,489 INFO [train.py:761] (5/8) Epoch 37, batch 3000, loss[loss=0.1557, simple_loss=0.2467, pruned_loss=0.0323, over 4889.00 frames.], tot_loss[loss=0.205, simple_loss=0.2972, pruned_loss=0.05645, over 966368.80 frames.], batch size: 12, lr: 4.46e-04
2022-05-29 22:31:22,489 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 22:31:32,401 INFO [train.py:790] (5/8) Epoch 37, validation: loss=0.2032, simple_loss=0.3017, pruned_loss=0.05229, over 944034.00 frames.
2022-05-29 22:32:17,767 INFO [train.py:761] (5/8) Epoch 37, batch 3050, loss[loss=0.184, simple_loss=0.2711, pruned_loss=0.04848, over 4986.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2978, pruned_loss=0.05673, over 965998.95 frames.], batch size: 13, lr: 4.46e-04
2022-05-29 22:32:55,851 INFO [train.py:761] (5/8) Epoch 37, batch 3100, loss[loss=0.1884, simple_loss=0.2805, pruned_loss=0.04814, over 4952.00 frames.], tot_loss[loss=0.2064, simple_loss=0.298, pruned_loss=0.05742, over 966529.96 frames.], batch size: 16, lr: 4.46e-04
2022-05-29 22:33:34,235 INFO [train.py:761] (5/8) Epoch 37, batch 3150, loss[loss=0.2014, simple_loss=0.3032, pruned_loss=0.04977, over 4921.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2995, pruned_loss=0.05816, over 966404.41 frames.], batch size: 14, lr: 4.46e-04
2022-05-29 22:34:12,383 INFO [train.py:761] (5/8) Epoch 37, batch 3200, loss[loss=0.2357, simple_loss=0.3064, pruned_loss=0.08249, over 4971.00 frames.], tot_loss[loss=0.2109, simple_loss=0.3015, pruned_loss=0.0601, over 966719.12 frames.], batch size: 11, lr: 4.45e-04
2022-05-29 22:34:50,574 INFO [train.py:761] (5/8) Epoch 37, batch 3250, loss[loss=0.202, simple_loss=0.2977, pruned_loss=0.05315, over 4658.00 frames.], tot_loss[loss=0.2113, simple_loss=0.3013, pruned_loss=0.06061, over 966763.19 frames.], batch size: 12, lr: 4.45e-04
2022-05-29 22:35:28,667 INFO [train.py:761] (5/8) Epoch 37, batch 3300, loss[loss=0.2284, simple_loss=0.3224, pruned_loss=0.06722, over 4770.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3008, pruned_loss=0.06191, over 967131.13 frames.], batch size: 20, lr: 4.45e-04
2022-05-29 22:36:06,201 INFO [train.py:761] (5/8) Epoch 37, batch 3350, loss[loss=0.2525, simple_loss=0.3309, pruned_loss=0.08707, over 4971.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3006, pruned_loss=0.06338, over 966192.27 frames.], batch size: 14, lr: 4.45e-04
2022-05-29 22:36:44,528 INFO [train.py:761] (5/8) Epoch 37, batch 3400, loss[loss=0.2002, simple_loss=0.2844, pruned_loss=0.05799, over 4977.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3016, pruned_loss=0.06463, over 966560.96 frames.], batch size: 15, lr: 4.45e-04
2022-05-29 22:37:22,639 INFO [train.py:761] (5/8) Epoch 37, batch 3450, loss[loss=0.2193, simple_loss=0.2942, pruned_loss=0.07221, over 4833.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3018, pruned_loss=0.06594, over 965279.04 frames.], batch size: 18, lr: 4.45e-04
2022-05-29 22:38:01,065 INFO [train.py:761] (5/8) Epoch 37, batch 3500, loss[loss=0.215, simple_loss=0.2996, pruned_loss=0.0652, over 4931.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3019, pruned_loss=0.06624, over 965341.49 frames.], batch size: 27, lr: 4.45e-04
2022-05-29 22:38:38,994 INFO [train.py:761] (5/8) Epoch 37, batch 3550, loss[loss=0.1968, simple_loss=0.2859, pruned_loss=0.05386, over 4719.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3029, pruned_loss=0.06726, over 965511.12 frames.], batch size: 13, lr: 4.45e-04
2022-05-29 22:39:17,226 INFO [train.py:761] (5/8) Epoch 37, batch 3600, loss[loss=0.1851, simple_loss=0.2611, pruned_loss=0.05457, over 4641.00 frames.], tot_loss[loss=0.219, simple_loss=0.3022, pruned_loss=0.06795, over 965144.86 frames.], batch size: 11, lr: 4.45e-04
2022-05-29 22:39:55,552 INFO [train.py:761] (5/8) Epoch 37, batch 3650, loss[loss=0.232, simple_loss=0.3261, pruned_loss=0.06897, over 4972.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3027, pruned_loss=0.06822, over 964857.10 frames.], batch size: 14, lr: 4.45e-04
2022-05-29 22:40:33,999 INFO [train.py:761] (5/8) Epoch 37, batch 3700, loss[loss=0.1989, simple_loss=0.2756, pruned_loss=0.06114, over 4740.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3043, pruned_loss=0.06923, over 965390.28 frames.], batch size: 12, lr: 4.45e-04
2022-05-29 22:41:11,636 INFO [train.py:761] (5/8) Epoch 37, batch 3750, loss[loss=0.3133, simple_loss=0.3795, pruned_loss=0.1236, over 4932.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3043, pruned_loss=0.06941, over 964811.23 frames.], batch size: 49, lr: 4.45e-04
2022-05-29 22:41:50,424 INFO [train.py:761] (5/8) Epoch 37, batch 3800, loss[loss=0.1989, simple_loss=0.2731, pruned_loss=0.06241, over 4728.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3038, pruned_loss=0.06932, over 965004.26 frames.], batch size: 11, lr: 4.45e-04
2022-05-29 22:42:28,076 INFO [train.py:761] (5/8) Epoch 37, batch 3850, loss[loss=0.2298, simple_loss=0.3182, pruned_loss=0.07066, over 4870.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3042, pruned_loss=0.06945, over 966147.97 frames.], batch size: 15, lr: 4.45e-04
2022-05-29 22:43:06,852 INFO [train.py:761] (5/8) Epoch 37, batch 3900, loss[loss=0.1691, simple_loss=0.2565, pruned_loss=0.04082, over 4982.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3034, pruned_loss=0.06916, over 966983.89 frames.], batch size: 13, lr: 4.45e-04
2022-05-29 22:43:45,490 INFO [train.py:761] (5/8) Epoch 37, batch 3950, loss[loss=0.2361, simple_loss=0.295, pruned_loss=0.08855, over 4893.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3041, pruned_loss=0.07038, over 966300.08 frames.], batch size: 12, lr: 4.45e-04
2022-05-29 22:44:23,960 INFO [train.py:761] (5/8) Epoch 37, batch 4000, loss[loss=0.176, simple_loss=0.2578, pruned_loss=0.04709, over 4972.00 frames.], tot_loss[loss=0.223, simple_loss=0.3042, pruned_loss=0.07088, over 966905.39 frames.], batch size: 12, lr: 4.45e-04
2022-05-29 22:45:02,098 INFO [train.py:761] (5/8) Epoch 37, batch 4050, loss[loss=0.2225, simple_loss=0.3001, pruned_loss=0.07244, over 4788.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3048, pruned_loss=0.07082, over 966178.50 frames.], batch size: 20, lr: 4.45e-04
2022-05-29 22:45:39,816 INFO [train.py:761] (5/8) Epoch 37, batch 4100, loss[loss=0.2429, simple_loss=0.3374, pruned_loss=0.07417, over 4848.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3048, pruned_loss=0.07028, over 966533.40 frames.], batch size: 20, lr: 4.45e-04
2022-05-29 22:46:18,389 INFO [train.py:761] (5/8) Epoch 37, batch 4150, loss[loss=0.238, simple_loss=0.3128, pruned_loss=0.0816, over 4826.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3032, pruned_loss=0.0699, over 966352.75 frames.], batch size: 18, lr: 4.45e-04
2022-05-29 22:46:56,147 INFO [train.py:761] (5/8) Epoch 37, batch 4200, loss[loss=0.2215, simple_loss=0.3077, pruned_loss=0.06766, over 4724.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3047, pruned_loss=0.07043, over 966433.43 frames.], batch size: 13, lr: 4.45e-04
2022-05-29 22:47:34,277 INFO [train.py:761] (5/8) Epoch 37, batch 4250, loss[loss=0.2111, simple_loss=0.2885, pruned_loss=0.06686, over 4731.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3037, pruned_loss=0.06971, over 966588.37 frames.], batch size: 12, lr: 4.45e-04
2022-05-29 22:48:12,578 INFO [train.py:761] (5/8) Epoch 37, batch 4300, loss[loss=0.169, simple_loss=0.2533, pruned_loss=0.04241, over 4811.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3035, pruned_loss=0.06948, over 966239.38 frames.], batch size: 12, lr: 4.44e-04
2022-05-29 22:48:50,313 INFO [train.py:761] (5/8) Epoch 37, batch 4350, loss[loss=0.2098, simple_loss=0.2911, pruned_loss=0.06421, over 4674.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3029, pruned_loss=0.06892, over 965278.42 frames.], batch size: 13, lr: 4.44e-04
2022-05-29 22:49:28,927 INFO [train.py:761] (5/8) Epoch 37, batch 4400, loss[loss=0.2297, simple_loss=0.3057, pruned_loss=0.07683, over 4905.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3015, pruned_loss=0.06866, over 964480.77 frames.], batch size: 17, lr: 4.44e-04
2022-05-29 22:50:07,211 INFO [train.py:761] (5/8) Epoch 37, batch 4450, loss[loss=0.283, simple_loss=0.345, pruned_loss=0.1105, over 4786.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3041, pruned_loss=0.06966, over 965180.81 frames.], batch size: 14, lr: 4.44e-04
2022-05-29 22:50:45,425 INFO [train.py:761] (5/8) Epoch 37, batch 4500, loss[loss=0.1881, simple_loss=0.2714, pruned_loss=0.05244, over 4640.00 frames.], tot_loss[loss=0.223, simple_loss=0.3048, pruned_loss=0.07058, over 964024.92 frames.], batch size: 11, lr: 4.44e-04
2022-05-29 22:51:23,092 INFO [train.py:761] (5/8) Epoch 37, batch 4550, loss[loss=0.1667, simple_loss=0.2434, pruned_loss=0.04505, over 4988.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3023, pruned_loss=0.0692, over 963788.45 frames.], batch size: 11, lr: 4.44e-04
2022-05-29 22:52:01,364 INFO [train.py:761] (5/8) Epoch 37, batch 4600, loss[loss=0.1894, simple_loss=0.2818, pruned_loss=0.04848, over 4964.00 frames.], tot_loss[loss=0.22, simple_loss=0.3025, pruned_loss=0.06877, over 964601.77 frames.], batch size: 15, lr: 4.44e-04
2022-05-29 22:52:39,184 INFO [train.py:761] (5/8) Epoch 37, batch 4650, loss[loss=0.225, simple_loss=0.322, pruned_loss=0.06406, over 4676.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3027, pruned_loss=0.0685, over 964330.93 frames.], batch size: 13, lr: 4.44e-04
2022-05-29 22:53:17,402 INFO [train.py:761] (5/8) Epoch 37, batch 4700, loss[loss=0.1969, simple_loss=0.3023, pruned_loss=0.04571, over 4787.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3058, pruned_loss=0.07034, over 964233.81 frames.], batch size: 18, lr: 4.44e-04
2022-05-29 22:53:55,729 INFO [train.py:761] (5/8) Epoch 37, batch 4750, loss[loss=0.1726, simple_loss=0.2626, pruned_loss=0.04133, over 4851.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3031, pruned_loss=0.06878, over 963680.05 frames.], batch size: 13, lr: 4.44e-04
2022-05-29 22:54:33,914 INFO [train.py:761] (5/8) Epoch 37, batch 4800, loss[loss=0.2548, simple_loss=0.3239, pruned_loss=0.09283, over 4960.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3027, pruned_loss=0.06901, over 964023.56 frames.], batch size: 16, lr: 4.44e-04
2022-05-29 22:55:11,640 INFO [train.py:761] (5/8) Epoch 37, batch 4850, loss[loss=0.2177, simple_loss=0.309, pruned_loss=0.06318, over 4983.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3026, pruned_loss=0.0689, over 964699.52 frames.], batch size: 26, lr: 4.44e-04
2022-05-29 22:55:49,973 INFO [train.py:761] (5/8) Epoch 37, batch 4900, loss[loss=0.1982, simple_loss=0.2829, pruned_loss=0.0567, over 4882.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3023, pruned_loss=0.06877, over 964293.03 frames.], batch size: 15, lr: 4.44e-04
2022-05-29 22:56:28,541 INFO [train.py:761] (5/8) Epoch 37, batch 4950, loss[loss=0.2004, simple_loss=0.2856, pruned_loss=0.05764, over 4990.00 frames.], tot_loss[loss=0.2208, simple_loss=0.3032, pruned_loss=0.0692, over 964910.69 frames.], batch size: 13, lr: 4.44e-04
2022-05-29 22:57:07,063 INFO [train.py:761] (5/8) Epoch 37, batch 5000, loss[loss=0.2326, simple_loss=0.3012, pruned_loss=0.08197, over 4848.00 frames.], tot_loss[loss=0.2198, simple_loss=0.3026, pruned_loss=0.06846, over 965642.00 frames.], batch size: 11, lr: 4.44e-04
2022-05-29 22:57:45,338 INFO [train.py:761] (5/8) Epoch 37, batch 5050, loss[loss=0.2329, simple_loss=0.3335, pruned_loss=0.06612, over 4904.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3037, pruned_loss=0.06923, over 965702.55 frames.], batch size: 21, lr: 4.44e-04
2022-05-29 22:58:24,215 INFO [train.py:761] (5/8) Epoch 37, batch 5100, loss[loss=0.2147, simple_loss=0.2873, pruned_loss=0.07102, over 4640.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3059, pruned_loss=0.07088, over 966219.54 frames.], batch size: 11, lr: 4.44e-04
2022-05-29 22:59:02,757 INFO [train.py:761] (5/8) Epoch 37, batch 5150, loss[loss=0.2276, simple_loss=0.3337, pruned_loss=0.06073, over 4985.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3049, pruned_loss=0.06986, over 965632.31 frames.], batch size: 15, lr: 4.44e-04
2022-05-29 22:59:44,003 INFO [train.py:761] (5/8) Epoch 37, batch 5200, loss[loss=0.2287, simple_loss=0.3141, pruned_loss=0.07164, over 4663.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3044, pruned_loss=0.06971, over 964345.51 frames.], batch size: 13, lr: 4.44e-04
2022-05-29 23:00:21,853 INFO [train.py:761] (5/8) Epoch 37, batch 5250, loss[loss=0.1904, simple_loss=0.2738, pruned_loss=0.05351, over 4797.00 frames.], tot_loss[loss=0.2206, simple_loss=0.3033, pruned_loss=0.06897, over 964166.53 frames.], batch size: 14, lr: 4.44e-04
2022-05-29 23:01:00,444 INFO [train.py:761] (5/8) Epoch 37, batch 5300, loss[loss=0.2408, simple_loss=0.3107, pruned_loss=0.08546, over 4737.00 frames.], tot_loss[loss=0.22, simple_loss=0.302, pruned_loss=0.06899, over 964570.91 frames.], batch size: 12, lr: 4.44e-04
2022-05-29 23:01:38,319 INFO [train.py:761] (5/8) Epoch 37, batch 5350, loss[loss=0.1917, simple_loss=0.2839, pruned_loss=0.04973, over 4862.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3002, pruned_loss=0.06783, over 964910.01 frames.], batch size: 13, lr: 4.44e-04
2022-05-29 23:02:16,772 INFO [train.py:761] (5/8) Epoch 37, batch 5400, loss[loss=0.2816, simple_loss=0.3371, pruned_loss=0.113, over 4936.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3005, pruned_loss=0.06803, over 966054.37 frames.], batch size: 16, lr: 4.44e-04
2022-05-29 23:02:54,507 INFO [train.py:761] (5/8) Epoch 37, batch 5450, loss[loss=0.2355, simple_loss=0.3075, pruned_loss=0.08175, over 4723.00 frames.], tot_loss[loss=0.219, simple_loss=0.3015, pruned_loss=0.06824, over 966389.55 frames.], batch size: 13, lr: 4.43e-04
2022-05-29 23:03:32,124 INFO [train.py:761] (5/8) Epoch 37, batch 5500, loss[loss=0.1801, simple_loss=0.2646, pruned_loss=0.0478, over 4730.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3006, pruned_loss=0.06711, over 965493.22 frames.], batch size: 12, lr: 4.43e-04
2022-05-29 23:04:10,026 INFO [train.py:761] (5/8) Epoch 37, batch 5550, loss[loss=0.2933, simple_loss=0.3564, pruned_loss=0.1151, over 4969.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3017, pruned_loss=0.06761, over 965922.69 frames.], batch size: 47, lr: 4.43e-04
2022-05-29 23:04:48,324 INFO [train.py:761] (5/8) Epoch 37, batch 5600, loss[loss=0.1978, simple_loss=0.2821, pruned_loss=0.05673, over 4734.00 frames.], tot_loss[loss=0.219, simple_loss=0.3022, pruned_loss=0.06786, over 966163.10 frames.], batch size: 12, lr: 4.43e-04
2022-05-29 23:05:26,733 INFO [train.py:761] (5/8) Epoch 37, batch 5650, loss[loss=0.2168, simple_loss=0.321, pruned_loss=0.05636, over 4887.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3015, pruned_loss=0.06742, over 967154.05 frames.], batch size: 17, lr: 4.43e-04
2022-05-29 23:06:05,261 INFO [train.py:761] (5/8) Epoch 37, batch 5700, loss[loss=0.1964, simple_loss=0.2734, pruned_loss=0.05975, over 4739.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3008, pruned_loss=0.06688, over 967108.35 frames.], batch size: 12, lr: 4.43e-04
2022-05-29 23:06:43,483 INFO [train.py:761] (5/8) Epoch 37, batch 5750, loss[loss=0.2238, simple_loss=0.3109, pruned_loss=0.06836, over 4866.00 frames.], tot_loss[loss=0.2179, simple_loss=0.301, pruned_loss=0.06735, over 967017.30 frames.], batch size: 17, lr: 4.43e-04
2022-05-29 23:07:21,445 INFO [train.py:761] (5/8) Epoch 37, batch 5800, loss[loss=0.2094, simple_loss=0.2867, pruned_loss=0.06601, over 4930.00 frames.], tot_loss[loss=0.218, simple_loss=0.3011, pruned_loss=0.06746, over 967322.54 frames.], batch size: 13, lr: 4.43e-04
2022-05-29 23:08:00,111 INFO [train.py:761] (5/8) Epoch 37, batch 5850, loss[loss=0.2349, simple_loss=0.3254, pruned_loss=0.0722, over 4771.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3002, pruned_loss=0.06698, over 966474.68 frames.], batch size: 15, lr: 4.43e-04
2022-05-29 23:08:38,500 INFO [train.py:761] (5/8) Epoch 37, batch 5900, loss[loss=0.2652, simple_loss=0.3424, pruned_loss=0.09404, over 4802.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3013, pruned_loss=0.06695, over 966792.15 frames.], batch size: 16, lr: 4.43e-04
2022-05-29 23:09:16,729 INFO [train.py:761] (5/8) Epoch 37, batch 5950, loss[loss=0.2276, simple_loss=0.3072, pruned_loss=0.07402, over 4853.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3021, pruned_loss=0.06767, over 966157.23 frames.], batch size: 18, lr: 4.43e-04
2022-05-29 23:09:54,784 INFO [train.py:761] (5/8) Epoch 37, batch 6000, loss[loss=0.2226, simple_loss=0.3061, pruned_loss=0.06957, over 4812.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3026, pruned_loss=0.06809, over 966106.90 frames.], batch size: 16, lr: 4.43e-04
2022-05-29 23:09:54,785 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 23:10:04,467 INFO [train.py:790] (5/8) Epoch 37, validation: loss=0.197, simple_loss=0.299, pruned_loss=0.04745, over 944034.00 frames.
2022-05-29 23:10:42,810 INFO [train.py:761] (5/8) Epoch 37, batch 6050, loss[loss=0.2086, simple_loss=0.2877, pruned_loss=0.06474, over 4814.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3014, pruned_loss=0.06794, over 966328.75 frames.], batch size: 16, lr: 4.43e-04
2022-05-29 23:11:21,547 INFO [train.py:761] (5/8) Epoch 37, batch 6100, loss[loss=0.1875, simple_loss=0.2818, pruned_loss=0.04663, over 4985.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3009, pruned_loss=0.06822, over 965787.03 frames.], batch size: 15, lr: 4.43e-04
2022-05-29 23:11:59,335 INFO [train.py:761] (5/8) Epoch 37, batch 6150, loss[loss=0.1802, simple_loss=0.2751, pruned_loss=0.04266, over 4906.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3016, pruned_loss=0.06847, over 965531.67 frames.], batch size: 14, lr: 4.43e-04
2022-05-29 23:12:37,235 INFO [train.py:761] (5/8) Epoch 37, batch 6200, loss[loss=0.2306, simple_loss=0.3097, pruned_loss=0.0758, over 4781.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3022, pruned_loss=0.06908, over 965722.95 frames.], batch size: 13, lr: 4.43e-04
2022-05-29 23:13:15,868 INFO [train.py:761] (5/8) Epoch 37, batch 6250, loss[loss=0.2084, simple_loss=0.2888, pruned_loss=0.06406, over 4860.00 frames.], tot_loss[loss=0.2201, simple_loss=0.3024, pruned_loss=0.0689, over 965588.39 frames.], batch size: 13, lr: 4.43e-04
2022-05-29 23:13:54,661 INFO [train.py:761] (5/8) Epoch 37, batch 6300, loss[loss=0.1975, simple_loss=0.2864, pruned_loss=0.05428, over 4796.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3003, pruned_loss=0.06773, over 966982.10 frames.], batch size: 12, lr: 4.43e-04
2022-05-29 23:14:33,133 INFO [train.py:761] (5/8) Epoch 37, batch 6350, loss[loss=0.2219, simple_loss=0.3087, pruned_loss=0.06751, over 4880.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3003, pruned_loss=0.06772, over 966668.33 frames.], batch size: 15, lr: 4.43e-04
2022-05-29 23:15:10,943 INFO [train.py:761] (5/8) Epoch 37, batch 6400, loss[loss=0.2225, simple_loss=0.3184, pruned_loss=0.06327, over 4715.00 frames.], tot_loss[loss=0.2176, simple_loss=0.2999, pruned_loss=0.06768, over 966290.10 frames.], batch size: 13, lr: 4.43e-04
2022-05-29 23:15:49,423 INFO [train.py:761] (5/8) Epoch 37, batch 6450, loss[loss=0.1944, simple_loss=0.2849, pruned_loss=0.05189, over 4725.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3004, pruned_loss=0.06755, over 966821.96 frames.], batch size: 13, lr: 4.43e-04
2022-05-29 23:16:27,612 INFO [train.py:761] (5/8) Epoch 37, batch 6500, loss[loss=0.2172, simple_loss=0.3139, pruned_loss=0.06026, over 4753.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3006, pruned_loss=0.06736, over 966276.59 frames.], batch size: 15, lr: 4.43e-04
2022-05-29 23:17:05,354 INFO [train.py:761] (5/8) Epoch 37, batch 6550, loss[loss=0.1868, simple_loss=0.2811, pruned_loss=0.04621, over 4915.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3012, pruned_loss=0.06667, over 966866.63 frames.], batch size: 20, lr: 4.42e-04
2022-05-29 23:17:43,756 INFO [train.py:761] (5/8) Epoch 37, batch 6600, loss[loss=0.2009, simple_loss=0.2775, pruned_loss=0.06209, over 4732.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3016, pruned_loss=0.06693, over 968384.78 frames.], batch size: 12, lr: 4.42e-04
2022-05-29 23:18:22,484 INFO [train.py:761] (5/8) Epoch 37, batch 6650, loss[loss=0.1696, simple_loss=0.2575, pruned_loss=0.04091, over 4882.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3011, pruned_loss=0.06756, over 968244.84 frames.], batch size: 12, lr: 4.42e-04
2022-05-29 23:19:01,543 INFO [train.py:761] (5/8) Epoch 37, batch 6700, loss[loss=0.2229, simple_loss=0.3275, pruned_loss=0.0592, over 4792.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3014, pruned_loss=0.06768, over 968037.65 frames.], batch size: 14, lr: 4.42e-04
2022-05-29 23:19:53,018 INFO [train.py:761] (5/8) Epoch 38, batch 0, loss[loss=0.1777, simple_loss=0.2766, pruned_loss=0.0394, over 4668.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2766, pruned_loss=0.0394, over 4668.00 frames.], batch size: 12, lr: 4.42e-04
2022-05-29 23:20:31,182 INFO [train.py:761] (5/8) Epoch 38, batch 50, loss[loss=0.2357, simple_loss=0.3322, pruned_loss=0.06964, over 4850.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2984, pruned_loss=0.05695, over 219324.25 frames.], batch size: 17, lr: 4.42e-04
2022-05-29 23:21:08,183 INFO [train.py:761] (5/8) Epoch 38, batch 100, loss[loss=0.1908, simple_loss=0.2795, pruned_loss=0.05106, over 4884.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2953, pruned_loss=0.05422, over 384935.16 frames.], batch size: 12, lr: 4.42e-04
2022-05-29 23:21:46,261 INFO [train.py:761] (5/8) Epoch 38, batch 150, loss[loss=0.1721, simple_loss=0.267, pruned_loss=0.03863, over 4866.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2969, pruned_loss=0.05505, over 513947.35 frames.], batch size: 18, lr: 4.42e-04
2022-05-29 23:22:24,255 INFO [train.py:761] (5/8) Epoch 38, batch 200, loss[loss=0.1868, simple_loss=0.2771, pruned_loss=0.04824, over 4831.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2952, pruned_loss=0.0539, over 614319.31 frames.], batch size: 11, lr: 4.42e-04
2022-05-29 23:23:02,279 INFO [train.py:761] (5/8) Epoch 38, batch 250, loss[loss=0.1855, simple_loss=0.2703, pruned_loss=0.05038, over 4989.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2946, pruned_loss=0.05381, over 693873.16 frames.], batch size: 13, lr: 4.42e-04
2022-05-29 23:23:40,030 INFO [train.py:761] (5/8) Epoch 38, batch 300, loss[loss=0.1716, simple_loss=0.2628, pruned_loss=0.04018, over 4737.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2947, pruned_loss=0.05428, over 753792.25 frames.], batch size: 12, lr: 4.42e-04
2022-05-29 23:24:18,025 INFO [train.py:761] (5/8) Epoch 38, batch 350, loss[loss=0.2064, simple_loss=0.2888, pruned_loss=0.06204, over 4925.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2939, pruned_loss=0.05393, over 801248.49 frames.], batch size: 13, lr: 4.42e-04
2022-05-29 23:24:55,809 INFO [train.py:761] (5/8) Epoch 38, batch 400, loss[loss=0.2017, simple_loss=0.2872, pruned_loss=0.05811, over 4732.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2931, pruned_loss=0.05352, over 837214.52 frames.], batch size: 11, lr: 4.42e-04
2022-05-29 23:25:33,613 INFO [train.py:761] (5/8) Epoch 38, batch 450, loss[loss=0.1871, simple_loss=0.2765, pruned_loss=0.04889, over 4740.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2935, pruned_loss=0.05354, over 866196.53 frames.], batch size: 11, lr: 4.42e-04
2022-05-29 23:26:11,785 INFO [train.py:761] (5/8) Epoch 38, batch 500, loss[loss=0.2082, simple_loss=0.312, pruned_loss=0.05223, over 4972.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2914, pruned_loss=0.05245, over 888395.39 frames.], batch size: 15, lr: 4.42e-04
2022-05-29 23:26:50,308 INFO [train.py:761] (5/8) Epoch 38, batch 550, loss[loss=0.2056, simple_loss=0.2879, pruned_loss=0.06169, over 4730.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2912, pruned_loss=0.05256, over 904649.53 frames.], batch size: 11, lr: 4.42e-04
2022-05-29 23:27:27,968 INFO [train.py:761] (5/8) Epoch 38, batch 600, loss[loss=0.2257, simple_loss=0.3201, pruned_loss=0.06558, over 4850.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2923, pruned_loss=0.05352, over 917926.03 frames.], batch size: 14, lr: 4.42e-04
2022-05-29 23:28:06,738 INFO [train.py:761] (5/8) Epoch 38, batch 650, loss[loss=0.2075, simple_loss=0.3023, pruned_loss=0.0564, over 4924.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2928, pruned_loss=0.05345, over 928005.61 frames.], batch size: 14, lr: 4.42e-04
2022-05-29 23:28:44,951 INFO [train.py:761] (5/8) Epoch 38, batch 700, loss[loss=0.2303, simple_loss=0.3204, pruned_loss=0.07008, over 4821.00 frames.], tot_loss[loss=0.2012, simple_loss=0.294, pruned_loss=0.05424, over 937562.65 frames.], batch size: 18, lr: 4.42e-04
2022-05-29 23:29:23,281 INFO [train.py:761] (5/8) Epoch 38, batch 750, loss[loss=0.2595, simple_loss=0.3449, pruned_loss=0.08708, over 4947.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2959, pruned_loss=0.0559, over 944060.87 frames.], batch size: 16, lr: 4.42e-04
2022-05-29 23:30:01,232 INFO [train.py:761] (5/8) Epoch 38, batch 800, loss[loss=0.2162, simple_loss=0.3161, pruned_loss=0.05816, over 4785.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2963, pruned_loss=0.05643, over 948964.94 frames.], batch size: 14, lr: 4.42e-04
2022-05-29 23:30:39,397 INFO [train.py:761] (5/8) Epoch 38, batch 850, loss[loss=0.163, simple_loss=0.2514, pruned_loss=0.03734, over 4976.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2958, pruned_loss=0.05642, over 952888.64 frames.], batch size: 12, lr: 4.42e-04
2022-05-29 23:31:16,862 INFO [train.py:761] (5/8) Epoch 38, batch 900, loss[loss=0.2076, simple_loss=0.2923, pruned_loss=0.06146, over 4927.00 frames.], tot_loss[loss=0.2055, simple_loss=0.297, pruned_loss=0.057, over 955843.69 frames.], batch size: 13, lr: 4.42e-04
2022-05-29 23:31:54,804 INFO [train.py:761] (5/8) Epoch 38, batch 950, loss[loss=0.1657, simple_loss=0.2475, pruned_loss=0.04197, over 4727.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2966, pruned_loss=0.0569, over 957869.90 frames.], batch size: 11, lr: 4.41e-04
2022-05-29 23:32:32,787 INFO [train.py:761] (5/8) Epoch 38, batch 1000, loss[loss=0.2341, simple_loss=0.3179, pruned_loss=0.07518, over 4915.00 frames.], tot_loss[loss=0.2053, simple_loss=0.297, pruned_loss=0.05681, over 959811.33 frames.], batch size: 14, lr: 4.41e-04
2022-05-29 23:33:10,744 INFO [train.py:761] (5/8) Epoch 38, batch 1050, loss[loss=0.2127, simple_loss=0.3092, pruned_loss=0.05808, over 4676.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2982, pruned_loss=0.05769, over 961739.00 frames.], batch size: 13, lr: 4.41e-04
2022-05-29 23:33:48,786 INFO [train.py:761] (5/8) Epoch 38, batch 1100, loss[loss=0.1776, simple_loss=0.2819, pruned_loss=0.03671, over 4851.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2984, pruned_loss=0.05717, over 962806.49 frames.], batch size: 13, lr: 4.41e-04
2022-05-29 23:34:26,593 INFO [train.py:761] (5/8) Epoch 38, batch 1150, loss[loss=0.2214, simple_loss=0.3188, pruned_loss=0.06194, over 4889.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2977, pruned_loss=0.05602, over 964355.25 frames.], batch size: 17, lr: 4.41e-04
2022-05-29 23:35:04,161 INFO [train.py:761] (5/8) Epoch 38, batch 1200, loss[loss=0.1783, simple_loss=0.2776, pruned_loss=0.03954, over 4984.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2969, pruned_loss=0.0562, over 964995.89 frames.], batch size: 13, lr: 4.41e-04
2022-05-29 23:35:41,926 INFO [train.py:761] (5/8) Epoch 38, batch 1250, loss[loss=0.1884, simple_loss=0.2874, pruned_loss=0.04473, over 4975.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2985, pruned_loss=0.05646, over 965533.99 frames.], batch size: 14, lr: 4.41e-04
2022-05-29 23:36:19,423 INFO [train.py:761] (5/8) Epoch 38, batch 1300, loss[loss=0.2221, simple_loss=0.3168, pruned_loss=0.06373, over 4866.00 frames.], tot_loss[loss=0.2052, simple_loss=0.298, pruned_loss=0.05624, over 965582.48 frames.], batch size: 17, lr: 4.41e-04
2022-05-29 23:36:57,365 INFO [train.py:761] (5/8) Epoch 38, batch 1350, loss[loss=0.1727, simple_loss=0.2621, pruned_loss=0.04165, over 4796.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2981, pruned_loss=0.05658, over 965582.42 frames.], batch size: 12, lr: 4.41e-04
2022-05-29 23:37:35,676 INFO [train.py:761] (5/8) Epoch 38, batch 1400, loss[loss=0.2347, simple_loss=0.3125, pruned_loss=0.07845, over 4803.00 frames.], tot_loss[loss=0.206, simple_loss=0.2986, pruned_loss=0.05674, over 965977.09 frames.], batch size: 16, lr: 4.41e-04
2022-05-29 23:38:13,305 INFO [train.py:761] (5/8) Epoch 38, batch 1450, loss[loss=0.1864, simple_loss=0.2729, pruned_loss=0.04993, over 4840.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2991, pruned_loss=0.05689, over 966323.00 frames.], batch size: 11, lr: 4.41e-04
2022-05-29 23:38:50,952 INFO [train.py:761] (5/8) Epoch 38, batch 1500, loss[loss=0.1694, simple_loss=0.2762, pruned_loss=0.03128, over 4984.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2974, pruned_loss=0.05592, over 966512.56 frames.], batch size: 13, lr: 4.41e-04
2022-05-29 23:39:28,753 INFO [train.py:761] (5/8) Epoch 38, batch 1550, loss[loss=0.2449, simple_loss=0.3301, pruned_loss=0.07989, over 4844.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2971, pruned_loss=0.05586, over 965686.26 frames.], batch size: 14, lr: 4.41e-04
2022-05-29 23:40:06,998 INFO [train.py:761] (5/8) Epoch 38, batch 1600, loss[loss=0.242, simple_loss=0.3312, pruned_loss=0.07637, over 4850.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2968, pruned_loss=0.05594, over 964692.92 frames.], batch size: 14, lr: 4.41e-04
2022-05-29 23:40:44,947 INFO [train.py:761] (5/8) Epoch 38, batch 1650, loss[loss=0.2087, simple_loss=0.3085, pruned_loss=0.05449, over 4854.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2971, pruned_loss=0.05614, over 965196.86 frames.], batch size: 13, lr: 4.41e-04
2022-05-29 23:41:22,744 INFO [train.py:761] (5/8) Epoch 38, batch 1700, loss[loss=0.1767, simple_loss=0.2792, pruned_loss=0.03711, over 4675.00 frames.], tot_loss[loss=0.204, simple_loss=0.2965, pruned_loss=0.05578, over 964853.79 frames.], batch size: 13, lr: 4.41e-04
2022-05-29 23:42:00,760 INFO [train.py:761] (5/8) Epoch 38, batch 1750, loss[loss=0.2468, simple_loss=0.3512, pruned_loss=0.07124, over 4961.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2972, pruned_loss=0.0559, over 964113.21 frames.], batch size: 16, lr: 4.41e-04
2022-05-29 23:42:38,374 INFO [train.py:761] (5/8) Epoch 38, batch 1800, loss[loss=0.1595, simple_loss=0.2458, pruned_loss=0.03658, over 4735.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2973, pruned_loss=0.05603, over 964459.97 frames.], batch size: 11, lr: 4.41e-04
2022-05-29 23:43:16,089 INFO [train.py:761] (5/8) Epoch 38, batch 1850, loss[loss=0.2043, simple_loss=0.3018, pruned_loss=0.05338, over 4665.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2967, pruned_loss=0.05632, over 965606.22 frames.], batch size: 12, lr: 4.41e-04
2022-05-29 23:43:53,824 INFO [train.py:761] (5/8) Epoch 38, batch 1900, loss[loss=0.2008, simple_loss=0.2996, pruned_loss=0.05105, over 4965.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2973, pruned_loss=0.05668, over 965614.27 frames.], batch size: 12, lr: 4.41e-04
2022-05-29 23:44:31,820 INFO [train.py:761] (5/8) Epoch 38, batch 1950, loss[loss=0.1695, simple_loss=0.2576, pruned_loss=0.04072, over 4970.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2964, pruned_loss=0.0562, over 964810.54 frames.], batch size: 11, lr: 4.41e-04
2022-05-29 23:45:09,299 INFO [train.py:761] (5/8) Epoch 38, batch 2000, loss[loss=0.2002, simple_loss=0.2849, pruned_loss=0.05778, over 4664.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2944, pruned_loss=0.05511, over 966203.63 frames.], batch size: 12, lr: 4.41e-04
2022-05-29 23:45:47,886 INFO [train.py:761] (5/8) Epoch 38, batch 2050, loss[loss=0.1673, simple_loss=0.2613, pruned_loss=0.03669, over 4822.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2964, pruned_loss=0.05574, over 965754.47 frames.], batch size: 11, lr: 4.41e-04
2022-05-29 23:46:25,774 INFO [train.py:761] (5/8) Epoch 38, batch 2100, loss[loss=0.2275, simple_loss=0.3251, pruned_loss=0.06497, over 4782.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2965, pruned_loss=0.05544, over 966117.54 frames.], batch size: 16, lr: 4.40e-04
2022-05-29 23:47:03,891 INFO [train.py:761] (5/8) Epoch 38, batch 2150, loss[loss=0.1942, simple_loss=0.2912, pruned_loss=0.04863, over 4720.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2987, pruned_loss=0.05623, over 967603.80 frames.], batch size: 14, lr: 4.40e-04
2022-05-29 23:47:41,833 INFO [train.py:761] (5/8) Epoch 38, batch 2200, loss[loss=0.2036, simple_loss=0.2919, pruned_loss=0.05769, over 4974.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2992, pruned_loss=0.05658, over 968367.87 frames.], batch size: 14, lr: 4.40e-04
2022-05-29 23:48:19,834 INFO [train.py:761] (5/8) Epoch 38, batch 2250, loss[loss=0.2345, simple_loss=0.3184, pruned_loss=0.07531, over 4760.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2999, pruned_loss=0.05739, over 968196.67 frames.], batch size: 15, lr: 4.40e-04
2022-05-29 23:48:57,499 INFO [train.py:761] (5/8) Epoch 38, batch 2300, loss[loss=0.2034, simple_loss=0.3127, pruned_loss=0.04705, over 4728.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2987, pruned_loss=0.05644, over 967515.83 frames.], batch size: 13, lr: 4.40e-04
2022-05-29 23:49:35,578 INFO [train.py:761] (5/8) Epoch 38, batch 2350, loss[loss=0.2258, simple_loss=0.325, pruned_loss=0.06324, over 4974.00 frames.], tot_loss[loss=0.2044, simple_loss=0.297, pruned_loss=0.05593, over 967005.76 frames.], batch size: 14, lr: 4.40e-04
2022-05-29 23:50:13,213 INFO [train.py:761] (5/8) Epoch 38, batch 2400, loss[loss=0.2185, simple_loss=0.3024, pruned_loss=0.0673, over 4840.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2983, pruned_loss=0.05631, over 967728.63 frames.], batch size: 20, lr: 4.40e-04
2022-05-29 23:50:51,120 INFO [train.py:761] (5/8) Epoch 38, batch 2450, loss[loss=0.2331, simple_loss=0.3355, pruned_loss=0.06536, over 4811.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2985, pruned_loss=0.05646, over 968072.69 frames.], batch size: 16, lr: 4.40e-04
2022-05-29 23:51:29,362 INFO [train.py:761] (5/8) Epoch 38, batch 2500, loss[loss=0.2017, simple_loss=0.2917, pruned_loss=0.05579, over 4664.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2987, pruned_loss=0.05647, over 967035.24 frames.], batch size: 12, lr: 4.40e-04
2022-05-29 23:52:07,366 INFO [train.py:761] (5/8) Epoch 38, batch 2550, loss[loss=0.1804, simple_loss=0.2835, pruned_loss=0.03863, over 4920.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2988, pruned_loss=0.05648, over 966050.09 frames.], batch size: 14, lr: 4.40e-04
2022-05-29 23:52:46,033 INFO [train.py:761] (5/8) Epoch 38, batch 2600, loss[loss=0.1732, simple_loss=0.2598, pruned_loss=0.04325, over 4829.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2981, pruned_loss=0.05608, over 966400.54 frames.], batch size: 11, lr: 4.40e-04
2022-05-29 23:53:23,628 INFO [train.py:761] (5/8) Epoch 38, batch 2650, loss[loss=0.1689, simple_loss=0.2636, pruned_loss=0.03712, over 4632.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2966, pruned_loss=0.0551, over 966189.90 frames.], batch size: 11, lr: 4.40e-04
2022-05-29 23:54:01,157 INFO [train.py:761] (5/8) Epoch 38, batch 2700, loss[loss=0.1989, simple_loss=0.2947, pruned_loss=0.0516, over 4790.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2961, pruned_loss=0.05504, over 965916.06 frames.], batch size: 13, lr: 4.40e-04
2022-05-29 23:54:39,486 INFO [train.py:761] (5/8) Epoch 38, batch 2750, loss[loss=0.192, simple_loss=0.2814, pruned_loss=0.05133, over 4854.00 frames.], tot_loss[loss=0.203, simple_loss=0.2959, pruned_loss=0.05502, over 964865.03 frames.], batch size: 14, lr: 4.40e-04
2022-05-29 23:55:24,962 INFO [train.py:761] (5/8) Epoch 38, batch 2800, loss[loss=0.2152, simple_loss=0.3214, pruned_loss=0.05454, over 4913.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2947, pruned_loss=0.05453, over 964628.04 frames.], batch size: 21, lr: 4.40e-04
2022-05-29 23:56:03,213 INFO [train.py:761] (5/8) Epoch 38, batch 2850, loss[loss=0.178, simple_loss=0.2707, pruned_loss=0.04265, over 4669.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2955, pruned_loss=0.05476, over 965583.19 frames.], batch size: 12, lr: 4.40e-04
2022-05-29 23:56:40,924 INFO [train.py:761] (5/8) Epoch 38, batch 2900, loss[loss=0.206, simple_loss=0.2999, pruned_loss=0.0561, over 4765.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2945, pruned_loss=0.0541, over 965924.48 frames.], batch size: 15, lr: 4.40e-04
2022-05-29 23:57:19,018 INFO [train.py:761] (5/8) Epoch 38, batch 2950, loss[loss=0.1829, simple_loss=0.2829, pruned_loss=0.04144, over 4841.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2964, pruned_loss=0.05472, over 966169.95 frames.], batch size: 13, lr: 4.40e-04
2022-05-29 23:57:56,983 INFO [train.py:761] (5/8) Epoch 38, batch 3000, loss[loss=0.1879, simple_loss=0.3034, pruned_loss=0.03627, over 4759.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2969, pruned_loss=0.05539, over 965871.16 frames.], batch size: 15, lr: 4.40e-04
2022-05-29 23:57:56,983 INFO [train.py:781] (5/8) Computing validation loss
2022-05-29 23:58:06,850 INFO [train.py:790] (5/8) Epoch 38, validation: loss=0.2035, simple_loss=0.3017, pruned_loss=0.05269, over 944034.00 frames.
2022-05-29 23:58:44,844 INFO [train.py:761] (5/8) Epoch 38, batch 3050, loss[loss=0.2174, simple_loss=0.3111, pruned_loss=0.06183, over 4775.00 frames.], tot_loss[loss=0.204, simple_loss=0.2972, pruned_loss=0.05544, over 965577.88 frames.], batch size: 15, lr: 4.40e-04
2022-05-29 23:59:22,772 INFO [train.py:761] (5/8) Epoch 38, batch 3100, loss[loss=0.1561, simple_loss=0.2394, pruned_loss=0.0364, over 4730.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2964, pruned_loss=0.05542, over 966129.22 frames.], batch size: 12, lr: 4.40e-04
2022-05-30 00:00:00,920 INFO [train.py:761] (5/8) Epoch 38, batch 3150, loss[loss=0.2405, simple_loss=0.3347, pruned_loss=0.07315, over 4858.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2968, pruned_loss=0.05654, over 967359.00 frames.], batch size: 18, lr: 4.40e-04
2022-05-30 00:00:46,337 INFO [train.py:761] (5/8) Epoch 38, batch 3200, loss[loss=0.2017, simple_loss=0.2891, pruned_loss=0.05713, over 4720.00 frames.], tot_loss[loss=0.208, simple_loss=0.2987, pruned_loss=0.05863, over 967592.87 frames.], batch size: 13, lr: 4.39e-04
2022-05-30 00:01:24,600 INFO [train.py:761] (5/8) Epoch 38, batch 3250, loss[loss=0.2894, simple_loss=0.3504, pruned_loss=0.1142, over 4793.00 frames.], tot_loss[loss=0.21, simple_loss=0.2994, pruned_loss=0.06034, over 966910.67 frames.], batch size: 14, lr: 4.39e-04
2022-05-30 00:02:02,634 INFO [train.py:761] (5/8) Epoch 38, batch 3300, loss[loss=0.1816, simple_loss=0.2583, pruned_loss=0.05242, over 4728.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2999, pruned_loss=0.06141, over 966081.42 frames.], batch size: 12, lr: 4.39e-04
2022-05-30 00:02:40,707 INFO [train.py:761] (5/8) Epoch 38, batch 3350, loss[loss=0.1988, simple_loss=0.3041, pruned_loss=0.04679, over 4886.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2984, pruned_loss=0.06124, over 965755.20 frames.], batch size: 15, lr: 4.39e-04
2022-05-30 00:03:18,882 INFO [train.py:761] (5/8) Epoch 38, batch 3400, loss[loss=0.1899, simple_loss=0.2877, pruned_loss=0.04603, over 4790.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2983, pruned_loss=0.06164, over 965532.46 frames.], batch size: 14, lr: 4.39e-04
2022-05-30 00:03:56,671 INFO [train.py:761] (5/8) Epoch 38, batch 3450, loss[loss=0.2258, simple_loss=0.2979, pruned_loss=0.07688, over 4857.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2989, pruned_loss=0.06327, over 965865.70 frames.], batch size: 13, lr: 4.39e-04
2022-05-30 00:04:34,515 INFO [train.py:761] (5/8) Epoch 38, batch 3500, loss[loss=0.1986, simple_loss=0.2765, pruned_loss=0.06036, over 4712.00 frames.], tot_loss[loss=0.2123, simple_loss=0.298, pruned_loss=0.06328, over 965254.05 frames.], batch size: 11, lr: 4.39e-04
2022-05-30 00:05:12,237 INFO [train.py:761] (5/8) Epoch 38, batch 3550, loss[loss=0.2143, simple_loss=0.2959, pruned_loss=0.06632, over 4672.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2996, pruned_loss=0.06482, over 965482.89 frames.], batch size: 13, lr: 4.39e-04
2022-05-30 00:05:50,234 INFO [train.py:761] (5/8) Epoch 38, batch 3600, loss[loss=0.2609, simple_loss=0.3321, pruned_loss=0.09481, over 4815.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3002, pruned_loss=0.06635, over 965221.73 frames.], batch size: 18, lr: 4.39e-04
2022-05-30 00:06:28,526 INFO [train.py:761] (5/8) Epoch 38, batch 3650, loss[loss=0.1677, simple_loss=0.2428, pruned_loss=0.04626, over 4974.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3002, pruned_loss=0.06664, over 965127.53 frames.], batch size: 12, lr: 4.39e-04
2022-05-30 00:07:06,550 INFO [train.py:761] (5/8) Epoch 38, batch 3700, loss[loss=0.2397, simple_loss=0.3233, pruned_loss=0.07799, over 4946.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3021, pruned_loss=0.06777, over 965484.09 frames.], batch size: 16, lr: 4.39e-04
2022-05-30 00:07:44,417 INFO [train.py:761] (5/8) Epoch 38, batch 3750, loss[loss=0.2557, simple_loss=0.3356, pruned_loss=0.08795, over 4782.00 frames.], tot_loss[loss=0.22, simple_loss=0.3024, pruned_loss=0.06875, over 964909.43 frames.], batch size: 20, lr: 4.39e-04
2022-05-30 00:08:21,887 INFO [train.py:761] (5/8) Epoch 38, batch 3800, loss[loss=0.2093, simple_loss=0.2973, pruned_loss=0.06064, over 4723.00 frames.], tot_loss[loss=0.2201, simple_loss=0.3026, pruned_loss=0.06877, over 965714.72 frames.], batch size: 13, lr: 4.39e-04
2022-05-30 00:09:07,101 INFO [train.py:761] (5/8) Epoch 38, batch 3850, loss[loss=0.1978, simple_loss=0.273, pruned_loss=0.06132, over 4976.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3012, pruned_loss=0.06836, over 964892.71 frames.], batch size: 12, lr: 4.39e-04
2022-05-30 00:09:45,520 INFO [train.py:761] (5/8) Epoch 38, batch 3900, loss[loss=0.2273, simple_loss=0.3059, pruned_loss=0.07436, over 4671.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3026, pruned_loss=0.06886, over 964923.92 frames.], batch size: 12, lr: 4.39e-04
2022-05-30 00:10:24,671 INFO [train.py:761] (5/8) Epoch 38, batch 3950, loss[loss=0.2334, simple_loss=0.3186, pruned_loss=0.07412, over 4931.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3033, pruned_loss=0.06992, over 966764.48 frames.], batch size: 25, lr: 4.39e-04
2022-05-30 00:11:02,729 INFO [train.py:761] (5/8) Epoch 38, batch 4000, loss[loss=0.248, simple_loss=0.3249, pruned_loss=0.08558, over 4614.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3042, pruned_loss=0.07034, over 966105.29 frames.], batch size: 12, lr: 4.39e-04
2022-05-30 00:11:41,242 INFO [train.py:761] (5/8) Epoch 38, batch 4050, loss[loss=0.2282, simple_loss=0.3045, pruned_loss=0.07595, over 4989.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3031, pruned_loss=0.06979, over 966519.98 frames.], batch size: 13, lr: 4.39e-04
2022-05-30 00:12:19,263 INFO [train.py:761] (5/8) Epoch 38, batch 4100, loss[loss=0.23, simple_loss=0.2835, pruned_loss=0.08827, over 4824.00 frames.], tot_loss[loss=0.2206, simple_loss=0.3027, pruned_loss=0.0692, over 967355.40 frames.], batch size: 11, lr: 4.39e-04
2022-05-30 00:12:57,297 INFO [train.py:761] (5/8) Epoch 38, batch 4150, loss[loss=0.2134, simple_loss=0.2955, pruned_loss=0.0656, over 4910.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3036, pruned_loss=0.06907, over 967273.92 frames.], batch size: 14, lr: 4.39e-04
2022-05-30 00:13:35,245 INFO [train.py:761] (5/8) Epoch 38, batch 4200, loss[loss=0.2384, simple_loss=0.33, pruned_loss=0.07335, over 4765.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3024, pruned_loss=0.06875, over 966310.76 frames.], batch size: 15, lr: 4.39e-04
2022-05-30 00:14:13,843 INFO [train.py:761] (5/8) Epoch 38, batch 4250, loss[loss=0.2148, simple_loss=0.3227, pruned_loss=0.05342, over 4815.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3031, pruned_loss=0.06894, over 966479.53 frames.], batch size: 16, lr: 4.39e-04
2022-05-30 00:14:51,610 INFO [train.py:761] (5/8) Epoch 38, batch 4300, loss[loss=0.2, simple_loss=0.3014, pruned_loss=0.04929, over 4671.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3024, pruned_loss=0.06873, over 966314.75 frames.], batch size: 13, lr: 4.39e-04
2022-05-30 00:15:30,445 INFO [train.py:761] (5/8) Epoch 38, batch 4350, loss[loss=0.1941, simple_loss=0.2927, pruned_loss=0.04773, over 4784.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3024, pruned_loss=0.06822, over 966594.47 frames.], batch size: 14, lr: 4.39e-04
2022-05-30 00:16:08,384 INFO [train.py:761] (5/8) Epoch 38, batch 4400, loss[loss=0.1725, simple_loss=0.2607, pruned_loss=0.04212, over 4719.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3021, pruned_loss=0.06857, over 965991.46 frames.], batch size: 14, lr: 4.38e-04
2022-05-30 00:16:47,117 INFO [train.py:761] (5/8) Epoch 38, batch 4450, loss[loss=0.2076, simple_loss=0.3035, pruned_loss=0.05581, over 4819.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3018, pruned_loss=0.06881, over 965545.27 frames.], batch size: 18, lr: 4.38e-04
2022-05-30 00:17:25,237 INFO [train.py:761] (5/8) Epoch 38, batch 4500, loss[loss=0.2199, simple_loss=0.2944, pruned_loss=0.07271, over 4857.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3003, pruned_loss=0.06844, over 964786.08 frames.], batch size: 13, lr: 4.38e-04
2022-05-30 00:18:03,952 INFO [train.py:761] (5/8) Epoch 38, batch 4550, loss[loss=0.2408, simple_loss=0.3269, pruned_loss=0.0773, over 4891.00 frames.], tot_loss[loss=0.219, simple_loss=0.3009, pruned_loss=0.06853, over 964967.17 frames.], batch size: 17, lr: 4.38e-04
2022-05-30 00:18:49,409 INFO [train.py:761] (5/8) Epoch 38, batch 4600, loss[loss=0.2328, simple_loss=0.3157, pruned_loss=0.0749, over 4724.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3, pruned_loss=0.06787, over 964895.27 frames.], batch size: 13, lr: 4.38e-04
2022-05-30 00:19:27,854 INFO [train.py:761] (5/8) Epoch 38, batch 4650, loss[loss=0.1936, simple_loss=0.2904, pruned_loss=0.0484, over 4849.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3012, pruned_loss=0.06808, over 964839.65 frames.], batch size: 14, lr: 4.38e-04
2022-05-30 00:20:05,625 INFO [train.py:761] (5/8) Epoch 38, batch 4700, loss[loss=0.223, simple_loss=0.3258, pruned_loss=0.06005, over 4792.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3011, pruned_loss=0.06796, over 965021.61 frames.], batch size: 14, lr: 4.38e-04
2022-05-30 00:20:44,076 INFO [train.py:761] (5/8) Epoch 38, batch 4750, loss[loss=0.2191, simple_loss=0.3105, pruned_loss=0.0638, over 4922.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3013, pruned_loss=0.06815, over 964865.71 frames.], batch size: 13, lr: 4.38e-04
2022-05-30 00:21:22,199 INFO [train.py:761] (5/8) Epoch 38, batch 4800, loss[loss=0.2152, simple_loss=0.313, pruned_loss=0.05876, over 4769.00 frames.], tot_loss[loss=0.22, simple_loss=0.3023, pruned_loss=0.06887, over 964716.36 frames.], batch size: 15, lr: 4.38e-04
2022-05-30 00:22:00,679 INFO [train.py:761] (5/8) Epoch 38, batch 4850, loss[loss=0.2285, simple_loss=0.3191, pruned_loss=0.0689, over 4919.00 frames.], tot_loss[loss=0.2198, simple_loss=0.3023, pruned_loss=0.06864, over 965475.04 frames.], batch size: 13, lr: 4.38e-04
2022-05-30 00:22:38,710 INFO [train.py:761] (5/8) Epoch 38, batch 4900, loss[loss=0.1616, simple_loss=0.2559, pruned_loss=0.03368, over 4729.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3015, pruned_loss=0.06778, over 966111.42 frames.], batch size: 12, lr: 4.38e-04
2022-05-30 00:23:17,201 INFO [train.py:761] (5/8) Epoch 38, batch 4950, loss[loss=0.2169, simple_loss=0.3031, pruned_loss=0.06538, over 4798.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3013, pruned_loss=0.06768, over 966275.30 frames.], batch size: 16, lr: 4.38e-04
2022-05-30 00:23:55,763 INFO [train.py:761] (5/8) Epoch 38, batch 5000, loss[loss=0.1954, simple_loss=0.2681, pruned_loss=0.0614, over 4834.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3011, pruned_loss=0.06787, over 965626.65 frames.], batch size: 11, lr: 4.38e-04
2022-05-30 00:24:33,598 INFO [train.py:761] (5/8) Epoch 38, batch 5050, loss[loss=0.2253, simple_loss=0.3145, pruned_loss=0.06799, over 4715.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2994, pruned_loss=0.06675, over 965596.17 frames.], batch size: 14, lr: 4.38e-04
2022-05-30 00:25:11,559 INFO [train.py:761] (5/8) Epoch 38, batch 5100, loss[loss=0.2106, simple_loss=0.2909, pruned_loss=0.06516, over 4985.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2995, pruned_loss=0.06715, over 965448.52 frames.], batch size: 13, lr: 4.38e-04
2022-05-30 00:25:49,702 INFO [train.py:761] (5/8) Epoch 38, batch 5150, loss[loss=0.2267, simple_loss=0.3078, pruned_loss=0.07283, over 4728.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2993, pruned_loss=0.06684, over 966624.34 frames.], batch size: 13, lr: 4.38e-04
2022-05-30 00:26:34,825 INFO [train.py:761] (5/8) Epoch 38, batch 5200, loss[loss=0.2021, simple_loss=0.2772, pruned_loss=0.06352, over 4886.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2996, pruned_loss=0.06673, over 966577.04 frames.], batch size: 12, lr: 4.38e-04
2022-05-30 00:27:13,327 INFO [train.py:761] (5/8) Epoch 38, batch 5250, loss[loss=0.2089, simple_loss=0.2899, pruned_loss=0.06395, over 4658.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2998, pruned_loss=0.06699, over 965861.28 frames.], batch size: 12, lr: 4.38e-04
2022-05-30 00:27:50,745 INFO [train.py:761] (5/8) Epoch 38, batch 5300, loss[loss=0.1798, simple_loss=0.2647, pruned_loss=0.04748, over 4747.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3001, pruned_loss=0.0671, over 965551.64 frames.], batch size: 11, lr: 4.38e-04
2022-05-30 00:28:29,320 INFO [train.py:761] (5/8) Epoch 38, batch 5350, loss[loss=0.2152, simple_loss=0.3028, pruned_loss=0.06375, over 4793.00 frames.], tot_loss[loss=0.2175, simple_loss=0.3, pruned_loss=0.06753, over 965062.34 frames.], batch size: 16, lr: 4.38e-04
2022-05-30 00:29:07,352 INFO [train.py:761] (5/8) Epoch 38, batch 5400, loss[loss=0.259, simple_loss=0.3392, pruned_loss=0.08935, over 4952.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2999, pruned_loss=0.06686, over 965410.56 frames.], batch size: 16, lr: 4.38e-04
2022-05-30 00:29:46,338 INFO [train.py:761] (5/8) Epoch 38, batch 5450, loss[loss=0.1679, simple_loss=0.2407, pruned_loss=0.04752, over 4532.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2991, pruned_loss=0.06633, over 965150.48 frames.], batch size: 10, lr: 4.38e-04
2022-05-30 00:30:25,108 INFO [train.py:761] (5/8) Epoch 38, batch 5500, loss[loss=0.2499, simple_loss=0.3353, pruned_loss=0.08222, over 4784.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3001, pruned_loss=0.06733, over 964703.43 frames.], batch size: 13, lr: 4.38e-04
2022-05-30 00:31:11,151 INFO [train.py:761] (5/8) Epoch 38, batch 5550, loss[loss=0.2404, simple_loss=0.3191, pruned_loss=0.08084, over 4967.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3001, pruned_loss=0.06735, over 964847.00 frames.], batch size: 14, lr: 4.37e-04
2022-05-30 00:31:49,940 INFO [train.py:761] (5/8) Epoch 38, batch 5600, loss[loss=0.1715, simple_loss=0.2506, pruned_loss=0.04622, over 4579.00 frames.], tot_loss[loss=0.2176, simple_loss=0.301, pruned_loss=0.06712, over 964478.69 frames.], batch size: 11, lr: 4.37e-04
2022-05-30 00:32:28,070 INFO [train.py:761] (5/8) Epoch 38, batch 5650, loss[loss=0.192, simple_loss=0.2698, pruned_loss=0.05714, over 4849.00 frames.], tot_loss[loss=0.218, simple_loss=0.3016, pruned_loss=0.0672, over 965891.23 frames.], batch size: 13, lr: 4.37e-04
2022-05-30 00:33:06,018 INFO [train.py:761] (5/8) Epoch 38, batch 5700, loss[loss=0.2062, simple_loss=0.2978, pruned_loss=0.05724, over 4794.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3001, pruned_loss=0.06639, over 965792.56 frames.], batch size: 13, lr: 4.37e-04
2022-05-30 00:33:44,919 INFO [train.py:761] (5/8) Epoch 38, batch 5750, loss[loss=0.202, simple_loss=0.2813, pruned_loss=0.06134, over 4804.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3015, pruned_loss=0.06682, over 965506.83 frames.], batch size: 12, lr: 4.37e-04
2022-05-30 00:34:30,603 INFO [train.py:761] (5/8) Epoch 38, batch 5800, loss[loss=0.2153, simple_loss=0.3205, pruned_loss=0.05502, over 4883.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3006, pruned_loss=0.06643, over 965521.80 frames.], batch size: 17, lr: 4.37e-04
2022-05-30 00:35:09,223 INFO [train.py:761] (5/8) Epoch 38, batch 5850, loss[loss=0.2104, simple_loss=0.2974, pruned_loss=0.06166, over 4674.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3015, pruned_loss=0.06743, over 964782.57 frames.], batch size: 12, lr: 4.37e-04
2022-05-30 00:35:47,238 INFO [train.py:761] (5/8) Epoch 38, batch 5900, loss[loss=0.2122, simple_loss=0.2998, pruned_loss=0.06229, over 4796.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2999, pruned_loss=0.06656, over 964071.68 frames.], batch size: 12, lr: 4.37e-04
2022-05-30 00:36:25,835 INFO [train.py:761] (5/8) Epoch 38, batch 5950, loss[loss=0.2065, simple_loss=0.3029, pruned_loss=0.05504, over 4721.00 frames.], tot_loss[loss=0.218, simple_loss=0.3012, pruned_loss=0.06739, over 964238.63 frames.], batch size: 13, lr: 4.37e-04
2022-05-30 00:37:04,201 INFO [train.py:761] (5/8) Epoch 38, batch 6000, loss[loss=0.2043, simple_loss=0.2919, pruned_loss=0.05839, over 4670.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3001, pruned_loss=0.06663, over 964774.35 frames.], batch size: 13, lr: 4.37e-04
2022-05-30 00:37:04,201 INFO [train.py:781] (5/8) Computing validation loss
2022-05-30 00:37:14,077 INFO [train.py:790] (5/8) Epoch 38, validation: loss=0.1977, simple_loss=0.2989, pruned_loss=0.04819, over 944034.00 frames.
2022-05-30 00:37:51,852 INFO [train.py:761] (5/8) Epoch 38, batch 6050, loss[loss=0.2281, simple_loss=0.3115, pruned_loss=0.07236, over 4846.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3005, pruned_loss=0.067, over 964971.98 frames.], batch size: 14, lr: 4.37e-04
2022-05-30 00:38:30,719 INFO [train.py:761] (5/8) Epoch 38, batch 6100, loss[loss=0.1646, simple_loss=0.2511, pruned_loss=0.03904, over 4836.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3006, pruned_loss=0.067, over 966192.50 frames.], batch size: 11, lr: 4.37e-04
2022-05-30 00:39:09,237 INFO [train.py:761] (5/8) Epoch 38, batch 6150, loss[loss=0.2142, simple_loss=0.3089, pruned_loss=0.05973, over 4775.00 frames.], tot_loss[loss=0.2175, simple_loss=0.3007, pruned_loss=0.06713, over 966742.65 frames.], batch size: 13, lr: 4.37e-04
2022-05-30 00:39:47,771 INFO [train.py:761] (5/8) Epoch 38, batch 6200, loss[loss=0.2075, simple_loss=0.2979, pruned_loss=0.0585, over 4932.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3024, pruned_loss=0.06764, over 965854.52 frames.], batch size: 13, lr: 4.37e-04
2022-05-30 00:40:25,950 INFO [train.py:761] (5/8) Epoch 38, batch 6250, loss[loss=0.2253, simple_loss=0.2906, pruned_loss=0.07999, over 4878.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3016, pruned_loss=0.06695, over 965581.88 frames.], batch size: 15, lr: 4.37e-04
2022-05-30 00:41:04,361 INFO [train.py:761] (5/8) Epoch 38, batch 6300, loss[loss=0.2243, simple_loss=0.307, pruned_loss=0.07081, over 4785.00 frames.], tot_loss[loss=0.2187, simple_loss=0.302, pruned_loss=0.06769, over 966333.79 frames.], batch size: 14, lr: 4.37e-04
2022-05-30 00:41:42,650 INFO [train.py:761] (5/8) Epoch 38, batch 6350, loss[loss=0.2178, simple_loss=0.3106, pruned_loss=0.06248, over 4674.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3032, pruned_loss=0.06829, over 967270.05 frames.], batch size: 13, lr: 4.37e-04
2022-05-30 00:42:21,251 INFO [train.py:761] (5/8) Epoch 38, batch 6400, loss[loss=0.2423, simple_loss=0.3367, pruned_loss=0.07392, over 4977.00 frames.], tot_loss[loss=0.22, simple_loss=0.3028, pruned_loss=0.06862, over 965864.72 frames.], batch size: 15, lr: 4.37e-04
2022-05-30 00:43:02,964 INFO [train.py:761] (5/8) Epoch 38, batch 6450, loss[loss=0.2007, simple_loss=0.2994, pruned_loss=0.05101, over 4929.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3021, pruned_loss=0.06817, over 966159.46 frames.], batch size: 13, lr: 4.37e-04
2022-05-30 00:43:41,060 INFO [train.py:761] (5/8) Epoch 38, batch 6500, loss[loss=0.1885, simple_loss=0.268, pruned_loss=0.05453, over 4964.00 frames.], tot_loss[loss=0.2202, simple_loss=0.303, pruned_loss=0.06876, over 964787.27 frames.], batch size: 12, lr: 4.37e-04
2022-05-30 00:44:19,663 INFO [train.py:761] (5/8) Epoch 38, batch 6550, loss[loss=0.2553, simple_loss=0.3248, pruned_loss=0.09287, over 4886.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3034, pruned_loss=0.06924, over 965728.17 frames.], batch size: 17, lr: 4.37e-04
2022-05-30 00:44:58,316 INFO [train.py:761] (5/8) Epoch 38, batch 6600, loss[loss=0.2307, simple_loss=0.3212, pruned_loss=0.07011, over 4791.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3036, pruned_loss=0.06915, over 966388.18 frames.], batch size: 14, lr: 4.37e-04
2022-05-30 00:45:36,239 INFO [train.py:761] (5/8) Epoch 38, batch 6650, loss[loss=0.1882, simple_loss=0.2636, pruned_loss=0.05635, over 4644.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3025, pruned_loss=0.06826, over 966573.28 frames.], batch size: 11, lr: 4.37e-04
2022-05-30 00:46:14,423 INFO [train.py:761] (5/8) Epoch 38, batch 6700, loss[loss=0.2323, simple_loss=0.326, pruned_loss=0.06932, over 4974.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3031, pruned_loss=0.06917, over 966973.65 frames.], batch size: 15, lr: 4.36e-04
2022-05-30 00:47:08,611 INFO [train.py:761] (5/8) Epoch 39, batch 0, loss[loss=0.2344, simple_loss=0.336, pruned_loss=0.06637, over 4805.00 frames.], tot_loss[loss=0.2344, simple_loss=0.336, pruned_loss=0.06637, over 4805.00 frames.], batch size: 18, lr: 4.36e-04
2022-05-30 00:47:46,764 INFO [train.py:761] (5/8) Epoch 39, batch 50, loss[loss=0.1902, simple_loss=0.2818, pruned_loss=0.04935, over 4876.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2931, pruned_loss=0.05418, over 217871.26 frames.], batch size: 12, lr: 4.36e-04
2022-05-30 00:48:25,190 INFO [train.py:761] (5/8) Epoch 39, batch 100, loss[loss=0.1941, simple_loss=0.2939, pruned_loss=0.04713, over 4675.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2951, pruned_loss=0.05435, over 383460.93 frames.], batch size: 13, lr: 4.36e-04
2022-05-30 00:49:03,174 INFO [train.py:761] (5/8) Epoch 39, batch 150, loss[loss=0.2087, simple_loss=0.3056, pruned_loss=0.05594, over 4974.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2926, pruned_loss=0.05379, over 512911.14 frames.], batch size: 14, lr: 4.36e-04
2022-05-30 00:49:41,261 INFO [train.py:761] (5/8) Epoch 39, batch 200, loss[loss=0.1808, simple_loss=0.2841, pruned_loss=0.03876, over 4853.00 frames.], tot_loss[loss=0.199, simple_loss=0.2913, pruned_loss=0.0533, over 613435.40 frames.], batch size: 13, lr: 4.36e-04
2022-05-30 00:50:19,229 INFO [train.py:761] (5/8) Epoch 39, batch 250, loss[loss=0.2345, simple_loss=0.3377, pruned_loss=0.06565, over 4789.00 frames.], tot_loss[loss=0.201, simple_loss=0.2935, pruned_loss=0.05421, over 692480.68 frames.], batch size: 14, lr: 4.36e-04
2022-05-30 00:50:57,357 INFO [train.py:761] (5/8) Epoch 39, batch 300, loss[loss=0.2681, simple_loss=0.3566, pruned_loss=0.08985, over 4988.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2956, pruned_loss=0.05535, over 753938.08 frames.], batch size: 27, lr: 4.36e-04
2022-05-30 00:51:35,326 INFO [train.py:761] (5/8) Epoch 39, batch 350, loss[loss=0.1466, simple_loss=0.2341, pruned_loss=0.02957, over 4884.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2946, pruned_loss=0.05475, over 801669.90 frames.], batch size: 12, lr: 4.36e-04
2022-05-30 00:52:12,891 INFO [train.py:761] (5/8) Epoch 39, batch 400, loss[loss=0.2095, simple_loss=0.2996, pruned_loss=0.05965, over 4879.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2944, pruned_loss=0.05468, over 837343.25 frames.], batch size: 15, lr: 4.36e-04
2022-05-30 00:52:51,227 INFO [train.py:761] (5/8) Epoch 39, batch 450, loss[loss=0.2053, simple_loss=0.2819, pruned_loss=0.06429, over 4755.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2933, pruned_loss=0.05392, over 866435.03 frames.], batch size: 15, lr: 4.36e-04
2022-05-30 00:53:29,343 INFO [train.py:761] (5/8) Epoch 39, batch 500, loss[loss=0.2474, simple_loss=0.3349, pruned_loss=0.07992, over 4878.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2924, pruned_loss=0.05346, over 887083.86 frames.], batch size: 17, lr: 4.36e-04
2022-05-30 00:54:07,179 INFO [train.py:761] (5/8) Epoch 39, batch 550, loss[loss=0.1732, simple_loss=0.2615, pruned_loss=0.04248, over 4726.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2924, pruned_loss=0.05323, over 903665.15 frames.], batch size: 12, lr: 4.36e-04
2022-05-30 00:54:45,433 INFO [train.py:761] (5/8) Epoch 39, batch 600, loss[loss=0.215, simple_loss=0.3177, pruned_loss=0.05614, over 4813.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2936, pruned_loss=0.05377, over 917799.24 frames.], batch size: 18, lr: 4.36e-04
2022-05-30 00:55:22,847 INFO [train.py:761] (5/8) Epoch 39, batch 650, loss[loss=0.2026, simple_loss=0.3154, pruned_loss=0.04491, over 4909.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2939, pruned_loss=0.05397, over 927262.84 frames.], batch size: 14, lr: 4.36e-04
2022-05-30 00:56:01,197 INFO [train.py:761] (5/8) Epoch 39, batch 700, loss[loss=0.1925, simple_loss=0.2973, pruned_loss=0.04387, over 4799.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2944, pruned_loss=0.05385, over 936902.71 frames.], batch size: 20, lr: 4.36e-04
2022-05-30 00:56:39,249 INFO [train.py:761] (5/8) Epoch 39, batch 750, loss[loss=0.1698, simple_loss=0.2532, pruned_loss=0.0432, over 4888.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2935, pruned_loss=0.05397, over 943483.68 frames.], batch size: 12, lr: 4.36e-04
2022-05-30 00:57:17,262 INFO [train.py:761] (5/8) Epoch 39, batch 800, loss[loss=0.1704, simple_loss=0.2773, pruned_loss=0.03173, over 4847.00 frames.], tot_loss[loss=0.2005, simple_loss=0.293, pruned_loss=0.05403, over 948030.34 frames.], batch size: 14, lr: 4.36e-04
2022-05-30 00:57:55,308 INFO [train.py:761] (5/8) Epoch 39, batch 850, loss[loss=0.1892, simple_loss=0.2844, pruned_loss=0.04702, over 4857.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2933, pruned_loss=0.05441, over 950811.05 frames.], batch size: 14, lr: 4.36e-04
2022-05-30 00:58:33,314 INFO [train.py:761] (5/8) Epoch 39, batch 900, loss[loss=0.2218, simple_loss=0.32, pruned_loss=0.06181, over 4880.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2936, pruned_loss=0.0543, over 952914.37 frames.], batch size: 17, lr: 4.36e-04
2022-05-30 00:59:11,322 INFO [train.py:761] (5/8) Epoch 39, batch 950, loss[loss=0.2802, simple_loss=0.3601, pruned_loss=0.1001, over 4956.00 frames.], tot_loss[loss=0.2017, simple_loss=0.294, pruned_loss=0.05465, over 955736.18 frames.], batch size: 16, lr: 4.36e-04
2022-05-30 00:59:49,344 INFO [train.py:761] (5/8) Epoch 39, batch 1000, loss[loss=0.1921, simple_loss=0.2816, pruned_loss=0.05132, over 4922.00 frames.], tot_loss[loss=0.203, simple_loss=0.295, pruned_loss=0.05545, over 958094.82 frames.], batch size: 13, lr: 4.36e-04
2022-05-30 01:00:27,021 INFO [train.py:761] (5/8) Epoch 39, batch 1050, loss[loss=0.1999, simple_loss=0.291, pruned_loss=0.05445, over 4815.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2947, pruned_loss=0.05491, over 959884.39 frames.], batch size: 11, lr: 4.36e-04
2022-05-30 01:01:05,134 INFO [train.py:761] (5/8) Epoch 39, batch 1100, loss[loss=0.1934, simple_loss=0.2733, pruned_loss=0.05677, over 4973.00 frames.], tot_loss[loss=0.203, simple_loss=0.2956, pruned_loss=0.05517, over 961751.59 frames.], batch size: 11, lr: 4.36e-04
2022-05-30 01:01:43,038 INFO [train.py:761] (5/8) Epoch 39, batch 1150, loss[loss=0.1886, simple_loss=0.2863, pruned_loss=0.04543, over 4643.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2959, pruned_loss=0.05483, over 961865.31 frames.], batch size: 11, lr: 4.35e-04
2022-05-30 01:02:21,189 INFO [train.py:761] (5/8) Epoch 39, batch 1200, loss[loss=0.2454, simple_loss=0.3394, pruned_loss=0.07573, over 4936.00 frames.], tot_loss[loss=0.2018, simple_loss=0.295, pruned_loss=0.05437, over 962443.80 frames.], batch size: 48, lr: 4.35e-04
2022-05-30 01:02:59,358 INFO [train.py:761] (5/8) Epoch 39, batch 1250, loss[loss=0.1941, simple_loss=0.2929, pruned_loss=0.04767, over 4720.00 frames.], tot_loss[loss=0.203, simple_loss=0.2959, pruned_loss=0.05507, over 964744.44 frames.], batch size: 14, lr: 4.35e-04
2022-05-30 01:03:37,403 INFO [train.py:761] (5/8) Epoch 39, batch 1300, loss[loss=0.1961, simple_loss=0.2901, pruned_loss=0.05102, over 4907.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2955, pruned_loss=0.05538, over 964275.12 frames.], batch size: 14, lr: 4.35e-04
2022-05-30 01:04:14,694 INFO [train.py:761] (5/8) Epoch 39, batch 1350, loss[loss=0.1911, simple_loss=0.2793, pruned_loss=0.0515, over 4671.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2946, pruned_loss=0.05461, over 964377.54 frames.], batch size: 12, lr: 4.35e-04
2022-05-30 01:04:52,681 INFO [train.py:761] (5/8) Epoch 39, batch 1400, loss[loss=0.192, simple_loss=0.274, pruned_loss=0.05496, over 4656.00 frames.], tot_loss[loss=0.2013, simple_loss=0.294, pruned_loss=0.05424, over 964043.45 frames.], batch size: 11, lr: 4.35e-04
2022-05-30 01:05:30,549 INFO [train.py:761] (5/8) Epoch 39, batch 1450, loss[loss=0.1773, simple_loss=0.2787, pruned_loss=0.03799, over 4916.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2952, pruned_loss=0.05468, over 963916.64 frames.], batch size: 14, lr: 4.35e-04
2022-05-30 01:06:08,586 INFO [train.py:761] (5/8) Epoch 39, batch 1500, loss[loss=0.1813, simple_loss=0.2747, pruned_loss=0.04397, over 4988.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2951, pruned_loss=0.05465, over 963808.80 frames.], batch size: 13, lr: 4.35e-04
2022-05-30 01:06:46,615 INFO [train.py:761] (5/8) Epoch 39, batch 1550, loss[loss=0.1511, simple_loss=0.2526, pruned_loss=0.02479, over 4802.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2932, pruned_loss=0.05366, over 963459.36 frames.], batch size: 12, lr: 4.35e-04
2022-05-30 01:07:24,556 INFO [train.py:761] (5/8) Epoch 39, batch 1600, loss[loss=0.2278, simple_loss=0.3098, pruned_loss=0.07289, over 4923.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2933, pruned_loss=0.05365, over 964671.28 frames.], batch size: 13, lr: 4.35e-04
2022-05-30 01:08:02,795 INFO [train.py:761] (5/8) Epoch 39, batch 1650, loss[loss=0.1562, simple_loss=0.2608, pruned_loss=0.02586, over 4651.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2955, pruned_loss=0.05398, over 965368.01 frames.], batch size: 11, lr: 4.35e-04
2022-05-30 01:08:40,855 INFO [train.py:761] (5/8) Epoch 39, batch 1700, loss[loss=0.2179, simple_loss=0.3173, pruned_loss=0.05922, over 4863.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2966, pruned_loss=0.05502, over 965377.71 frames.], batch size: 41, lr: 4.35e-04
2022-05-30 01:09:18,240 INFO [train.py:761] (5/8) Epoch 39, batch 1750, loss[loss=0.1928, simple_loss=0.2887, pruned_loss=0.04844, over 4791.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2961, pruned_loss=0.05484, over 964799.41 frames.], batch size: 13, lr: 4.35e-04
2022-05-30 01:09:56,128 INFO [train.py:761] (5/8) Epoch 39, batch 1800, loss[loss=0.1696, simple_loss=0.2568, pruned_loss=0.04126, over 4980.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2955, pruned_loss=0.05421, over 964252.22 frames.], batch size: 12, lr: 4.35e-04
2022-05-30 01:10:34,024 INFO [train.py:761] (5/8) Epoch 39, batch 1850, loss[loss=0.2367, simple_loss=0.3268, pruned_loss=0.07326, over 4846.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2949, pruned_loss=0.05376, over 964721.17 frames.], batch size: 20, lr: 4.35e-04
2022-05-30 01:11:12,188 INFO [train.py:761] (5/8) Epoch 39, batch 1900, loss[loss=0.2063, simple_loss=0.3065, pruned_loss=0.05309, over 4858.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2939, pruned_loss=0.05348, over 964690.66 frames.], batch size: 14, lr: 4.35e-04
2022-05-30 01:11:49,695 INFO [train.py:761] (5/8) Epoch 39, batch 1950, loss[loss=0.1988, simple_loss=0.3007, pruned_loss=0.04844, over 4941.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2947, pruned_loss=0.05386, over 965165.82 frames.], batch size: 16, lr: 4.35e-04
2022-05-30 01:12:27,762 INFO [train.py:761] (5/8) Epoch 39, batch 2000, loss[loss=0.2856, simple_loss=0.3727, pruned_loss=0.09927, over 4893.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2968, pruned_loss=0.05531, over 966626.77 frames.], batch size: 26, lr: 4.35e-04
2022-05-30 01:13:05,583 INFO [train.py:761] (5/8) Epoch 39, batch 2050, loss[loss=0.1452, simple_loss=0.2368, pruned_loss=0.02681, over 4582.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2963, pruned_loss=0.05455, over 966280.76 frames.], batch size: 10, lr: 4.35e-04
2022-05-30 01:13:43,983 INFO [train.py:761] (5/8) Epoch 39, batch 2100, loss[loss=0.2329, simple_loss=0.3265, pruned_loss=0.06965, over 4886.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2971, pruned_loss=0.05485, over 967077.56 frames.], batch size: 17, lr: 4.35e-04
2022-05-30 01:14:22,183 INFO [train.py:761] (5/8) Epoch 39, batch 2150, loss[loss=0.1782, simple_loss=0.268, pruned_loss=0.04424, over 4563.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2968, pruned_loss=0.05521, over 967861.44 frames.], batch size: 10, lr: 4.35e-04
2022-05-30 01:15:00,153 INFO [train.py:761] (5/8) Epoch 39, batch 2200, loss[loss=0.2286, simple_loss=0.332, pruned_loss=0.06261, over 4962.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2972, pruned_loss=0.05565, over 966788.60 frames.], batch size: 45, lr: 4.35e-04
2022-05-30 01:15:38,039 INFO [train.py:761] (5/8) Epoch 39, batch 2250, loss[loss=0.1636, simple_loss=0.2528, pruned_loss=0.03715, over 4721.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2961, pruned_loss=0.05472, over 966680.19 frames.], batch size: 12, lr: 4.35e-04
2022-05-30 01:16:15,998 INFO [train.py:761] (5/8) Epoch 39, batch 2300, loss[loss=0.1823, simple_loss=0.2597, pruned_loss=0.05249, over 4642.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2957, pruned_loss=0.05466, over 966891.22 frames.], batch size: 11, lr: 4.35e-04
2022-05-30 01:16:53,740 INFO [train.py:761] (5/8) Epoch 39, batch 2350, loss[loss=0.2436, simple_loss=0.3203, pruned_loss=0.0835, over 4871.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2952, pruned_loss=0.05411, over 966210.17 frames.], batch size: 26, lr: 4.34e-04
2022-05-30 01:17:31,946 INFO [train.py:761] (5/8) Epoch 39, batch 2400, loss[loss=0.1966, simple_loss=0.278, pruned_loss=0.05757, over 4822.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2955, pruned_loss=0.05472, over 965567.61 frames.], batch size: 11, lr: 4.34e-04
2022-05-30 01:18:09,190 INFO [train.py:761] (5/8) Epoch 39, batch 2450, loss[loss=0.186, simple_loss=0.2936, pruned_loss=0.03922, over 4668.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2956, pruned_loss=0.05429, over 965010.71 frames.], batch size: 12, lr: 4.34e-04
2022-05-30 01:18:47,395 INFO [train.py:761] (5/8) Epoch 39, batch 2500, loss[loss=0.2094, simple_loss=0.2909, pruned_loss=0.06396, over 4923.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2949, pruned_loss=0.05403, over 965928.85 frames.], batch size: 13, lr: 4.34e-04
2022-05-30 01:19:25,430 INFO [train.py:761] (5/8) Epoch 39, batch 2550, loss[loss=0.1825, simple_loss=0.2733, pruned_loss=0.04589, over 4972.00 frames.], tot_loss[loss=0.2012, simple_loss=0.295, pruned_loss=0.05368, over 965778.19 frames.], batch size: 11, lr: 4.34e-04
2022-05-30 01:20:03,330 INFO [train.py:761] (5/8) Epoch 39, batch 2600, loss[loss=0.2269, simple_loss=0.3159, pruned_loss=0.06901, over 4863.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2957, pruned_loss=0.05386, over 965928.35 frames.], batch size: 25, lr: 4.34e-04
2022-05-30 01:20:41,387 INFO [train.py:761] (5/8) Epoch 39, batch 2650, loss[loss=0.2337, simple_loss=0.3162, pruned_loss=0.07554, over 4780.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2955, pruned_loss=0.05394, over 965858.06 frames.], batch size: 16, lr: 4.34e-04
2022-05-30 01:21:19,397 INFO [train.py:761] (5/8) Epoch 39, batch 2700, loss[loss=0.2084, simple_loss=0.3242, pruned_loss=0.0463, over 4805.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2955, pruned_loss=0.0541, over 965869.02 frames.], batch size: 16, lr: 4.34e-04
2022-05-30 01:21:57,319 INFO [train.py:761] (5/8) Epoch 39, batch 2750, loss[loss=0.1748, simple_loss=0.2642, pruned_loss=0.04266, over 4930.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2955, pruned_loss=0.05466, over 966874.82 frames.], batch size: 13, lr: 4.34e-04
2022-05-30 01:22:35,638 INFO [train.py:761] (5/8) Epoch 39, batch 2800, loss[loss=0.2155, simple_loss=0.3094, pruned_loss=0.06079, over 4809.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2957, pruned_loss=0.05458, over 967969.81 frames.], batch size: 16, lr: 4.34e-04
2022-05-30 01:23:13,062 INFO [train.py:761] (5/8) Epoch 39, batch 2850, loss[loss=0.1422, simple_loss=0.2395, pruned_loss=0.02247, over 4600.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2958, pruned_loss=0.05425, over 967296.99 frames.], batch size: 10, lr: 4.34e-04
2022-05-30 01:23:51,027 INFO [train.py:761] (5/8) Epoch 39, batch 2900, loss[loss=0.1879, simple_loss=0.2826, pruned_loss=0.04663, over 4917.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2952, pruned_loss=0.05402, over 967118.94 frames.], batch size: 14, lr: 4.34e-04
2022-05-30 01:24:29,068 INFO [train.py:761] (5/8) Epoch 39, batch 2950, loss[loss=0.2237, simple_loss=0.3169, pruned_loss=0.06525, over 4851.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2957, pruned_loss=0.05471, over 966623.44 frames.], batch size: 14, lr: 4.34e-04
2022-05-30 01:25:06,825 INFO [train.py:761] (5/8) Epoch 39, batch 3000, loss[loss=0.2015, simple_loss=0.293, pruned_loss=0.05498, over 4787.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2947, pruned_loss=0.05432, over 966687.71 frames.], batch size: 14, lr: 4.34e-04
2022-05-30 01:25:06,825 INFO [train.py:781] (5/8) Computing validation loss
2022-05-30 01:25:16,859 INFO [train.py:790] (5/8) Epoch 39, validation: loss=0.203, simple_loss=0.3011, pruned_loss=0.05249, over 944034.00 frames.
2022-05-30 01:25:54,989 INFO [train.py:761] (5/8) Epoch 39, batch 3050, loss[loss=0.1568, simple_loss=0.2421, pruned_loss=0.03573, over 4743.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2939, pruned_loss=0.05413, over 965737.57 frames.], batch size: 11, lr: 4.34e-04
2022-05-30 01:26:32,944 INFO [train.py:761] (5/8) Epoch 39, batch 3100, loss[loss=0.1775, simple_loss=0.2637, pruned_loss=0.04569, over 4977.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2942, pruned_loss=0.05462, over 966347.61 frames.], batch size: 12, lr: 4.34e-04
2022-05-30 01:27:10,608 INFO [train.py:761] (5/8) Epoch 39, batch 3150, loss[loss=0.2312, simple_loss=0.3198, pruned_loss=0.07127, over 4867.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2956, pruned_loss=0.05604, over 965712.83 frames.], batch size: 25, lr: 4.34e-04
2022-05-30 01:27:48,658 INFO [train.py:761] (5/8) Epoch 39, batch 3200, loss[loss=0.1706, simple_loss=0.2545, pruned_loss=0.04337, over 4837.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2963, pruned_loss=0.05753, over 965602.67 frames.], batch size: 11, lr: 4.34e-04
2022-05-30 01:28:26,428 INFO [train.py:761] (5/8) Epoch 39, batch 3250, loss[loss=0.2676, simple_loss=0.3581, pruned_loss=0.08853, over 4885.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2984, pruned_loss=0.05916, over 964974.31 frames.], batch size: 15, lr: 4.34e-04
2022-05-30 01:29:04,349 INFO [train.py:761] (5/8) Epoch 39, batch 3300, loss[loss=0.1873, simple_loss=0.2828, pruned_loss=0.04594, over 4912.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2985, pruned_loss=0.05981, over 965987.16 frames.], batch size: 14, lr: 4.34e-04
2022-05-30 01:29:42,642 INFO [train.py:761] (5/8) Epoch 39, batch 3350, loss[loss=0.1927, simple_loss=0.2817, pruned_loss=0.05182, over 4847.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2995, pruned_loss=0.06107, over 966953.31 frames.], batch size: 14, lr: 4.34e-04
2022-05-30 01:30:20,222 INFO [train.py:761] (5/8) Epoch 39, batch 3400, loss[loss=0.2051, simple_loss=0.2885, pruned_loss=0.06087, over 4786.00 frames.], tot_loss[loss=0.2118, simple_loss=0.2991, pruned_loss=0.06228, over 966606.83 frames.], batch size: 14, lr: 4.34e-04
2022-05-30 01:30:58,280 INFO [train.py:761] (5/8) Epoch 39, batch 3450, loss[loss=0.2186, simple_loss=0.294, pruned_loss=0.07159, over 4968.00 frames.], tot_loss[loss=0.2134, simple_loss=0.2998, pruned_loss=0.06349, over 967493.01 frames.], batch size: 12, lr: 4.34e-04
2022-05-30 01:31:35,653 INFO [train.py:761] (5/8) Epoch 39, batch 3500, loss[loss=0.1807, simple_loss=0.2565, pruned_loss=0.05247, over 4960.00 frames.], tot_loss[loss=0.2152, simple_loss=0.301, pruned_loss=0.06472, over 966726.75 frames.], batch size: 11, lr: 4.33e-04
2022-05-30 01:32:13,348 INFO [train.py:761] (5/8) Epoch 39, batch 3550, loss[loss=0.2605, simple_loss=0.3319, pruned_loss=0.0946, over 4767.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3016, pruned_loss=0.066, over 967045.31 frames.], batch size: 15, lr: 4.33e-04
2022-05-30 01:32:51,747 INFO [train.py:761] (5/8) Epoch 39, batch 3600, loss[loss=0.2142, simple_loss=0.2955, pruned_loss=0.06645, over 4992.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3026, pruned_loss=0.06684, over 967669.74 frames.], batch size: 13, lr: 4.33e-04
2022-05-30 01:33:30,044 INFO [train.py:761] (5/8) Epoch 39, batch 3650, loss[loss=0.2331, simple_loss=0.3227, pruned_loss=0.07181, over 4735.00 frames.], tot_loss[loss=0.2177, simple_loss=0.302, pruned_loss=0.06672, over 966717.57 frames.], batch size: 13, lr: 4.33e-04
2022-05-30 01:34:08,606 INFO [train.py:761] (5/8) Epoch 39, batch 3700, loss[loss=0.2169, simple_loss=0.295, pruned_loss=0.06945, over 4906.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3015, pruned_loss=0.06736, over 965741.52 frames.], batch size: 17, lr: 4.33e-04
2022-05-30 01:34:46,307 INFO [train.py:761] (5/8) Epoch 39, batch 3750, loss[loss=0.2619, simple_loss=0.3521, pruned_loss=0.08583, over 4933.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3008, pruned_loss=0.06735, over 966541.36 frames.], batch size: 26, lr: 4.33e-04
2022-05-30 01:35:24,372 INFO [train.py:761] (5/8) Epoch 39, batch 3800, loss[loss=0.1836, simple_loss=0.2625, pruned_loss=0.05236, over 4639.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3016, pruned_loss=0.06807, over 966855.35 frames.], batch size: 11, lr: 4.33e-04
2022-05-30 01:36:02,410 INFO [train.py:761] (5/8) Epoch 39, batch 3850, loss[loss=0.1879, simple_loss=0.2888, pruned_loss=0.04354, over 4719.00 frames.], tot_loss[loss=0.218, simple_loss=0.3005, pruned_loss=0.06774, over 965170.42 frames.], batch size: 14, lr: 4.33e-04
2022-05-30 01:36:40,239 INFO [train.py:761] (5/8) Epoch 39, batch 3900, loss[loss=0.274, simple_loss=0.3392, pruned_loss=0.1044, over 4814.00 frames.], tot_loss[loss=0.2187, simple_loss=0.301, pruned_loss=0.06822, over 966081.04 frames.], batch size: 16, lr: 4.33e-04
2022-05-30 01:37:17,852 INFO [train.py:761] (5/8) Epoch 39, batch 3950, loss[loss=0.2609, simple_loss=0.3177, pruned_loss=0.1021, over 4839.00 frames.], tot_loss[loss=0.2198, simple_loss=0.3024, pruned_loss=0.06857, over 965798.59 frames.], batch size: 17, lr: 4.33e-04
2022-05-30 01:37:55,991 INFO [train.py:761] (5/8) Epoch 39, batch 4000, loss[loss=0.2283, simple_loss=0.2949, pruned_loss=0.08083, over 4805.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3031, pruned_loss=0.06863, over 967048.98 frames.], batch size: 12, lr: 4.33e-04
2022-05-30 01:38:34,695 INFO [train.py:761] (5/8) Epoch 39, batch 4050, loss[loss=0.2684, simple_loss=0.3364, pruned_loss=0.1002, over 4713.00 frames.], tot_loss[loss=0.221, simple_loss=0.3035, pruned_loss=0.06921, over 967460.71 frames.], batch size: 14, lr: 4.33e-04
2022-05-30 01:39:13,972 INFO [train.py:761] (5/8) Epoch 39, batch 4100, loss[loss=0.1808, simple_loss=0.2703, pruned_loss=0.04565, over 4667.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3032, pruned_loss=0.06905, over 968237.20 frames.], batch size: 12, lr: 4.33e-04
2022-05-30 01:39:52,060 INFO [train.py:761] (5/8) Epoch 39, batch 4150, loss[loss=0.1734, simple_loss=0.2724, pruned_loss=0.03719, over 4775.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3012, pruned_loss=0.0675, over 967687.91 frames.], batch size: 13, lr: 4.33e-04
2022-05-30 01:40:30,772 INFO [train.py:761] (5/8) Epoch 39, batch 4200, loss[loss=0.1983, simple_loss=0.2785, pruned_loss=0.059, over 4966.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3026, pruned_loss=0.06838, over 966564.64 frames.], batch size: 16, lr: 4.33e-04
2022-05-30 01:41:08,669 INFO [train.py:761] (5/8) Epoch 39, batch 4250, loss[loss=0.2088, simple_loss=0.2727, pruned_loss=0.07242, over 4739.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3023, pruned_loss=0.06826, over 966020.98 frames.], batch size: 11, lr: 4.33e-04
2022-05-30 01:41:46,934 INFO [train.py:761] (5/8) Epoch 39, batch 4300, loss[loss=0.2316, simple_loss=0.3225, pruned_loss=0.07035, over 4863.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3026, pruned_loss=0.06836, over 966863.35 frames.], batch size: 26, lr: 4.33e-04
2022-05-30 01:42:24,806 INFO [train.py:761] (5/8) Epoch 39, batch 4350, loss[loss=0.1792, simple_loss=0.2746, pruned_loss=0.04191, over 4835.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3021, pruned_loss=0.0676, over 967301.47 frames.], batch size: 11, lr: 4.33e-04
2022-05-30 01:43:02,987 INFO [train.py:761] (5/8) Epoch 39, batch 4400, loss[loss=0.1914, simple_loss=0.2916, pruned_loss=0.04563, over 4977.00 frames.], tot_loss[loss=0.218, simple_loss=0.3017, pruned_loss=0.06713, over 967618.74 frames.], batch size: 14, lr: 4.33e-04
2022-05-30 01:43:40,959 INFO [train.py:761] (5/8) Epoch 39, batch 4450, loss[loss=0.2056, simple_loss=0.3071, pruned_loss=0.05208, over 4782.00 frames.], tot_loss[loss=0.2188, simple_loss=0.302, pruned_loss=0.06783, over 967426.15 frames.], batch size: 20, lr: 4.33e-04
2022-05-30 01:44:19,632 INFO [train.py:761] (5/8) Epoch 39, batch 4500, loss[loss=0.2456, simple_loss=0.3313, pruned_loss=0.07997, over 4966.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3015, pruned_loss=0.06793, over 966909.64 frames.], batch size: 16, lr: 4.33e-04
2022-05-30 01:44:58,169 INFO [train.py:761] (5/8) Epoch 39, batch 4550, loss[loss=0.2113, simple_loss=0.3031, pruned_loss=0.05975, over 4815.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3019, pruned_loss=0.06826, over 966012.34 frames.], batch size: 16, lr: 4.33e-04
2022-05-30 01:45:36,131 INFO [train.py:761] (5/8) Epoch 39, batch 4600, loss[loss=0.1806, simple_loss=0.2675, pruned_loss=0.04689, over 4660.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3002, pruned_loss=0.06765, over 965529.77 frames.], batch size: 12, lr: 4.33e-04
2022-05-30 01:46:14,486 INFO [train.py:761] (5/8) Epoch 39, batch 4650, loss[loss=0.1971, simple_loss=0.2947, pruned_loss=0.04969, over 4976.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2993, pruned_loss=0.06692, over 965602.20 frames.], batch size: 21, lr: 4.33e-04
2022-05-30 01:46:52,468 INFO [train.py:761] (5/8) Epoch 39, batch 4700, loss[loss=0.2135, simple_loss=0.2983, pruned_loss=0.06431, over 4880.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2998, pruned_loss=0.06741, over 964591.98 frames.], batch size: 12, lr: 4.33e-04
2022-05-30 01:47:30,982 INFO [train.py:761] (5/8) Epoch 39, batch 4750, loss[loss=0.1868, simple_loss=0.2582, pruned_loss=0.05767, over 4828.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2986, pruned_loss=0.06679, over 964697.47 frames.], batch size: 11, lr: 4.32e-04
2022-05-30 01:48:09,628 INFO [train.py:761] (5/8) Epoch 39, batch 4800, loss[loss=0.2233, simple_loss=0.2931, pruned_loss=0.07675, over 4974.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2991, pruned_loss=0.06708, over 965546.65 frames.], batch size: 12, lr: 4.32e-04
2022-05-30 01:48:47,887 INFO [train.py:761] (5/8) Epoch 39, batch 4850, loss[loss=0.2498, simple_loss=0.329, pruned_loss=0.08535, over 4942.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2992, pruned_loss=0.06646, over 965473.26 frames.], batch size: 16, lr: 4.32e-04
2022-05-30 01:49:26,148 INFO [train.py:761] (5/8) Epoch 39, batch 4900, loss[loss=0.1966, simple_loss=0.2813, pruned_loss=0.05596, over 4669.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2994, pruned_loss=0.06659, over 965492.50 frames.], batch size: 12, lr: 4.32e-04
2022-05-30 01:50:04,368 INFO [train.py:761] (5/8) Epoch 39, batch 4950, loss[loss=0.2191, simple_loss=0.3087, pruned_loss=0.06471, over 4832.00 frames.], tot_loss[loss=0.216, simple_loss=0.2994, pruned_loss=0.06632, over 965803.18 frames.], batch size: 18, lr: 4.32e-04
2022-05-30 01:50:42,521 INFO [train.py:761] (5/8) Epoch 39, batch 5000, loss[loss=0.2385, simple_loss=0.3235, pruned_loss=0.07679, over 4805.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2993, pruned_loss=0.06647, over 964782.18 frames.], batch size: 16, lr: 4.32e-04
2022-05-30 01:51:20,934 INFO [train.py:761] (5/8) Epoch 39, batch 5050, loss[loss=0.2338, simple_loss=0.3185, pruned_loss=0.07458, over 4856.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2987, pruned_loss=0.06604, over 964874.12 frames.], batch size: 14, lr: 4.32e-04
2022-05-30 01:51:59,059 INFO [train.py:761] (5/8) Epoch 39, batch 5100, loss[loss=0.1995, simple_loss=0.2875, pruned_loss=0.0558, over 4775.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2993, pruned_loss=0.06647, over 965263.11 frames.], batch size: 15, lr: 4.32e-04
2022-05-30 01:52:37,020 INFO [train.py:761] (5/8) Epoch 39, batch 5150, loss[loss=0.2552, simple_loss=0.3383, pruned_loss=0.08601, over 4834.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3003, pruned_loss=0.06697, over 965029.04 frames.], batch size: 45, lr: 4.32e-04
2022-05-30 01:53:15,266 INFO [train.py:761] (5/8) Epoch 39, batch 5200, loss[loss=0.2516, simple_loss=0.3331, pruned_loss=0.08506, over 4766.00 frames.], tot_loss[loss=0.2174, simple_loss=0.301, pruned_loss=0.06688, over 965141.50 frames.], batch size: 15, lr: 4.32e-04
2022-05-30 01:53:53,445 INFO [train.py:761] (5/8) Epoch 39, batch 5250, loss[loss=0.1957, simple_loss=0.2859, pruned_loss=0.05272, over 4854.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3002, pruned_loss=0.06681, over 965887.03 frames.], batch size: 18, lr: 4.32e-04
2022-05-30 01:54:31,446 INFO [train.py:761] (5/8) Epoch 39, batch 5300, loss[loss=0.2291, simple_loss=0.3152, pruned_loss=0.07146, over 4925.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3, pruned_loss=0.06677, over 966100.21 frames.], batch size: 14, lr: 4.32e-04
2022-05-30 01:55:09,505 INFO [train.py:761] (5/8) Epoch 39, batch 5350, loss[loss=0.1938, simple_loss=0.2807, pruned_loss=0.0535, over 4801.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3002, pruned_loss=0.06668, over 966584.52 frames.], batch size: 12, lr: 4.32e-04
2022-05-30 01:55:47,892 INFO [train.py:761] (5/8) Epoch 39, batch 5400, loss[loss=0.2301, simple_loss=0.3183, pruned_loss=0.07095, over 4782.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3012, pruned_loss=0.06722, over 967968.17 frames.], batch size: 20, lr: 4.32e-04
2022-05-30 01:56:25,688 INFO [train.py:761] (5/8) Epoch 39, batch 5450, loss[loss=0.2313, simple_loss=0.3024, pruned_loss=0.08006, over 4984.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3008, pruned_loss=0.06701, over 967321.34 frames.], batch size: 15, lr: 4.32e-04
2022-05-30 01:57:04,118 INFO [train.py:761] (5/8) Epoch 39, batch 5500, loss[loss=0.2119, simple_loss=0.2855, pruned_loss=0.06911, over 4806.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2996, pruned_loss=0.06603, over 968029.62 frames.], batch size: 12, lr: 4.32e-04
2022-05-30 01:57:42,263 INFO [train.py:761] (5/8) Epoch 39, batch 5550, loss[loss=0.2655, simple_loss=0.3501, pruned_loss=0.09039, over 4972.00 frames.], tot_loss[loss=0.216, simple_loss=0.2996, pruned_loss=0.06621, over 968543.54 frames.], batch size: 47, lr: 4.32e-04
2022-05-30 01:58:20,656 INFO [train.py:761] (5/8) Epoch 39, batch 5600, loss[loss=0.2326, simple_loss=0.3078, pruned_loss=0.07872, over 4958.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2991, pruned_loss=0.066, over 968108.19 frames.], batch size: 16, lr: 4.32e-04
2022-05-30 01:58:58,509 INFO [train.py:761] (5/8) Epoch 39, batch 5650, loss[loss=0.1975, simple_loss=0.272, pruned_loss=0.06152, over 4788.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3, pruned_loss=0.06626, over 967266.87 frames.], batch size: 13, lr: 4.32e-04
2022-05-30 01:59:36,458 INFO [train.py:761] (5/8) Epoch 39, batch 5700, loss[loss=0.2478, simple_loss=0.3243, pruned_loss=0.08568, over 4909.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3007, pruned_loss=0.06671, over 967720.91 frames.], batch size: 49, lr: 4.32e-04
2022-05-30 02:00:14,136 INFO [train.py:761] (5/8) Epoch 39, batch 5750, loss[loss=0.1961, simple_loss=0.2795, pruned_loss=0.0564, over 4854.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3003, pruned_loss=0.06665, over 968034.21 frames.], batch size: 11, lr: 4.32e-04
2022-05-30 02:00:52,544 INFO [train.py:761] (5/8) Epoch 39, batch 5800, loss[loss=0.2412, simple_loss=0.3162, pruned_loss=0.08312, over 4664.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3002, pruned_loss=0.0666, over 967525.65 frames.], batch size: 12, lr: 4.32e-04
2022-05-30 02:01:30,590 INFO [train.py:761] (5/8) Epoch 39, batch 5850, loss[loss=0.2407, simple_loss=0.3179, pruned_loss=0.08173, over 4912.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2992, pruned_loss=0.06591, over 967230.95 frames.], batch size: 26, lr: 4.32e-04
2022-05-30 02:02:09,843 INFO [train.py:761] (5/8) Epoch 39, batch 5900, loss[loss=0.1963, simple_loss=0.2738, pruned_loss=0.05944, over 4648.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2999, pruned_loss=0.06632, over 966944.67 frames.], batch size: 11, lr: 4.32e-04
2022-05-30 02:02:47,901 INFO [train.py:761] (5/8) Epoch 39, batch 5950, loss[loss=0.1925, simple_loss=0.2851, pruned_loss=0.04996, over 4787.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2996, pruned_loss=0.06593, over 966370.85 frames.], batch size: 14, lr: 4.31e-04
2022-05-30 02:03:26,390 INFO [train.py:761] (5/8) Epoch 39, batch 6000, loss[loss=0.2098, simple_loss=0.2841, pruned_loss=0.06774, over 4989.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3005, pruned_loss=0.06663, over 966660.23 frames.], batch size: 13, lr: 4.31e-04
2022-05-30 02:03:26,390 INFO [train.py:781] (5/8) Computing validation loss
2022-05-30 02:03:36,490 INFO [train.py:790] (5/8) Epoch 39, validation: loss=0.1966, simple_loss=0.2987, pruned_loss=0.0473, over 944034.00 frames.
2022-05-30 02:04:14,634 INFO [train.py:761] (5/8) Epoch 39, batch 6050, loss[loss=0.266, simple_loss=0.333, pruned_loss=0.09953, over 4933.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2988, pruned_loss=0.06598, over 966865.02 frames.], batch size: 51, lr: 4.31e-04
2022-05-30 02:04:53,381 INFO [train.py:761] (5/8) Epoch 39, batch 6100, loss[loss=0.1949, simple_loss=0.2926, pruned_loss=0.04864, over 4844.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2996, pruned_loss=0.06632, over 966767.04 frames.], batch size: 20, lr: 4.31e-04
2022-05-30 02:05:31,933 INFO [train.py:761] (5/8) Epoch 39, batch 6150, loss[loss=0.1828, simple_loss=0.2736, pruned_loss=0.04602, over 4879.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3005, pruned_loss=0.06733, over 966463.60 frames.], batch size: 12, lr: 4.31e-04
2022-05-30 02:06:10,445 INFO [train.py:761] (5/8) Epoch 39, batch 6200, loss[loss=0.1928, simple_loss=0.2807, pruned_loss=0.05249, over 4653.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3, pruned_loss=0.06693, over 965491.48 frames.], batch size: 11, lr: 4.31e-04
2022-05-30 02:06:48,606 INFO [train.py:761] (5/8) Epoch 39, batch 6250, loss[loss=0.1864, simple_loss=0.2693, pruned_loss=0.05171, over 4811.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3011, pruned_loss=0.06819, over 965253.57 frames.], batch size: 12, lr: 4.31e-04
2022-05-30 02:07:26,915 INFO [train.py:761] (5/8) Epoch 39, batch 6300, loss[loss=0.2087, simple_loss=0.2935, pruned_loss=0.06192, over 4718.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3007, pruned_loss=0.06809, over 965385.14 frames.], batch size: 14, lr: 4.31e-04
2022-05-30 02:08:05,275 INFO [train.py:761] (5/8) Epoch 39, batch 6350, loss[loss=0.2219, simple_loss=0.2912, pruned_loss=0.07627, over 4813.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2986, pruned_loss=0.06661, over 964781.34 frames.], batch size: 16, lr: 4.31e-04
2022-05-30 02:08:43,871 INFO [train.py:761] (5/8) Epoch 39, batch 6400, loss[loss=0.2767, simple_loss=0.3446, pruned_loss=0.1044, over 4783.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2983, pruned_loss=0.06634, over 964882.22 frames.], batch size: 15, lr: 4.31e-04
2022-05-30 02:09:21,915 INFO [train.py:761] (5/8) Epoch 39, batch 6450, loss[loss=0.2018, simple_loss=0.3021, pruned_loss=0.05074, over 4911.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2992, pruned_loss=0.06648, over 965759.40 frames.], batch size: 14, lr: 4.31e-04
2022-05-30 02:10:01,099 INFO [train.py:761] (5/8) Epoch 39, batch 6500, loss[loss=0.1665, simple_loss=0.258, pruned_loss=0.03751, over 4980.00 frames.], tot_loss[loss=0.2167, simple_loss=0.2997, pruned_loss=0.06685, over 966249.13 frames.], batch size: 13, lr: 4.31e-04
2022-05-30 02:10:39,358 INFO [train.py:761] (5/8) Epoch 39, batch 6550, loss[loss=0.2009, simple_loss=0.3105, pruned_loss=0.04566, over 4846.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3001, pruned_loss=0.06701, over 966246.11 frames.], batch size: 18, lr: 4.31e-04
2022-05-30 02:11:18,067 INFO [train.py:761] (5/8) Epoch 39, batch 6600, loss[loss=0.2372, simple_loss=0.3315, pruned_loss=0.07138, over 4843.00 frames.], tot_loss[loss=0.2158, simple_loss=0.299, pruned_loss=0.06631, over 966108.86 frames.], batch size: 14, lr: 4.31e-04
2022-05-30 02:11:55,945 INFO [train.py:761] (5/8) Epoch 39, batch 6650, loss[loss=0.2486, simple_loss=0.3316, pruned_loss=0.08278, over 4718.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3, pruned_loss=0.06656, over 965686.16 frames.], batch size: 13, lr: 4.31e-04
2022-05-30 02:12:33,839 INFO [train.py:761] (5/8) Epoch 39, batch 6700, loss[loss=0.2149, simple_loss=0.2968, pruned_loss=0.06649, over 4788.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3002, pruned_loss=0.06647, over 966991.19 frames.], batch size: 13, lr: 4.31e-04
2022-05-30 02:13:24,762 INFO [train.py:761] (5/8) Epoch 40, batch 0, loss[loss=0.1932, simple_loss=0.2886, pruned_loss=0.04888, over 4782.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2886, pruned_loss=0.04888, over 4782.00 frames.], batch size: 15, lr: 4.31e-04
2022-05-30 02:14:03,332 INFO [train.py:761] (5/8) Epoch 40, batch 50, loss[loss=0.2495, simple_loss=0.3408, pruned_loss=0.0791, over 4863.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2926, pruned_loss=0.05335, over 218140.34 frames.], batch size: 49, lr: 4.31e-04
2022-05-30 02:14:41,238 INFO [train.py:761] (5/8) Epoch 40, batch 100, loss[loss=0.1785, simple_loss=0.266, pruned_loss=0.04548, over 4589.00 frames.], tot_loss[loss=0.1971, simple_loss=0.289, pruned_loss=0.05264, over 384323.50 frames.], batch size: 10, lr: 4.31e-04
2022-05-30 02:15:19,516 INFO [train.py:761] (5/8) Epoch 40, batch 150, loss[loss=0.1498, simple_loss=0.2455, pruned_loss=0.02704, over 4714.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2916, pruned_loss=0.05329, over 514493.19 frames.], batch size: 13, lr: 4.31e-04
2022-05-30 02:15:57,295 INFO [train.py:761] (5/8) Epoch 40, batch 200, loss[loss=0.1904, simple_loss=0.2874, pruned_loss=0.0467, over 4854.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2922, pruned_loss=0.05368, over 615306.00 frames.], batch size: 13, lr: 4.31e-04
2022-05-30 02:16:35,388 INFO [train.py:761] (5/8) Epoch 40, batch 250, loss[loss=0.2386, simple_loss=0.3327, pruned_loss=0.07223, over 4817.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2936, pruned_loss=0.05371, over 692719.64 frames.], batch size: 20, lr: 4.31e-04
2022-05-30 02:17:13,864 INFO [train.py:761] (5/8) Epoch 40, batch 300, loss[loss=0.2172, simple_loss=0.3016, pruned_loss=0.06637, over 4870.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2935, pruned_loss=0.05412, over 753458.94 frames.], batch size: 20, lr: 4.31e-04
2022-05-30 02:17:52,456 INFO [train.py:761] (5/8) Epoch 40, batch 350, loss[loss=0.2141, simple_loss=0.3068, pruned_loss=0.06065, over 4967.00 frames.], tot_loss[loss=0.201, simple_loss=0.2937, pruned_loss=0.05414, over 801130.57 frames.], batch size: 14, lr: 4.31e-04
2022-05-30 02:18:30,476 INFO [train.py:761] (5/8) Epoch 40, batch 400, loss[loss=0.178, simple_loss=0.2635, pruned_loss=0.04625, over 4563.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2936, pruned_loss=0.05405, over 837991.19 frames.], batch size: 10, lr: 4.30e-04
2022-05-30 02:19:08,804 INFO [train.py:761] (5/8) Epoch 40, batch 450, loss[loss=0.2348, simple_loss=0.3105, pruned_loss=0.07957, over 4723.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2942, pruned_loss=0.05433, over 866679.53 frames.], batch size: 13, lr: 4.30e-04
2022-05-30 02:19:46,777 INFO [train.py:761] (5/8) Epoch 40, batch 500, loss[loss=0.2299, simple_loss=0.3306, pruned_loss=0.06462, over 4848.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2934, pruned_loss=0.05342, over 889485.90 frames.], batch size: 17, lr: 4.30e-04
2022-05-30 02:20:24,918 INFO [train.py:761] (5/8) Epoch 40, batch 550, loss[loss=0.1828, simple_loss=0.2695, pruned_loss=0.04802, over 4858.00 frames.], tot_loss[loss=0.2, simple_loss=0.2925, pruned_loss=0.05376, over 905897.24 frames.], batch size: 13, lr: 4.30e-04
2022-05-30 02:21:02,901 INFO [train.py:761] (5/8) Epoch 40, batch 600, loss[loss=0.2183, simple_loss=0.3113, pruned_loss=0.06263, over 4673.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2917, pruned_loss=0.05334, over 918185.68 frames.], batch size: 13, lr: 4.30e-04
2022-05-30 02:21:41,135 INFO [train.py:761] (5/8) Epoch 40, batch 650, loss[loss=0.1938, simple_loss=0.2925, pruned_loss=0.04757, over 4670.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2919, pruned_loss=0.05373, over 928724.93 frames.], batch size: 13, lr: 4.30e-04
2022-05-30 02:22:19,207 INFO [train.py:761] (5/8) Epoch 40, batch 700, loss[loss=0.214, simple_loss=0.3055, pruned_loss=0.06122, over 4774.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2916, pruned_loss=0.0536, over 937002.78 frames.], batch size: 15, lr: 4.30e-04
2022-05-30 02:22:57,637 INFO [train.py:761] (5/8) Epoch 40, batch 750, loss[loss=0.2015, simple_loss=0.296, pruned_loss=0.05346, over 4853.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2915, pruned_loss=0.05358, over 943800.80 frames.], batch size: 18, lr: 4.30e-04
2022-05-30 02:23:35,282 INFO [train.py:761] (5/8) Epoch 40, batch 800, loss[loss=0.1944, simple_loss=0.3001, pruned_loss=0.04431, over 4840.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2932, pruned_loss=0.05385, over 948040.46 frames.], batch size: 13, lr: 4.30e-04
2022-05-30 02:24:13,439 INFO [train.py:761] (5/8) Epoch 40, batch 850, loss[loss=0.2424, simple_loss=0.3286, pruned_loss=0.07811, over 4911.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2938, pruned_loss=0.05421, over 952948.78 frames.], batch size: 47, lr: 4.30e-04
2022-05-30 02:24:51,535 INFO [train.py:761] (5/8) Epoch 40, batch 900, loss[loss=0.1637, simple_loss=0.2579, pruned_loss=0.03474, over 4585.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2926, pruned_loss=0.05386, over 954183.63 frames.], batch size: 10, lr: 4.30e-04
2022-05-30 02:25:32,852 INFO [train.py:761] (5/8) Epoch 40, batch 950, loss[loss=0.1737, simple_loss=0.2696, pruned_loss=0.03893, over 4853.00 frames.], tot_loss[loss=0.201, simple_loss=0.2931, pruned_loss=0.05445, over 957279.61 frames.], batch size: 14, lr: 4.30e-04
2022-05-30 02:26:10,416 INFO [train.py:761] (5/8) Epoch 40, batch 1000, loss[loss=0.2105, simple_loss=0.3052, pruned_loss=0.05789, over 4970.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2933, pruned_loss=0.05418, over 959405.25 frames.], batch size: 16, lr: 4.30e-04
2022-05-30 02:26:48,512 INFO [train.py:761] (5/8) Epoch 40, batch 1050, loss[loss=0.1945, simple_loss=0.2926, pruned_loss=0.04816, over 4846.00 frames.], tot_loss[loss=0.201, simple_loss=0.2938, pruned_loss=0.05407, over 959293.33 frames.], batch size: 13, lr: 4.30e-04
2022-05-30 02:27:26,282 INFO [train.py:761] (5/8) Epoch 40, batch 1100, loss[loss=0.2143, simple_loss=0.3195, pruned_loss=0.05456, over 4915.00 frames.], tot_loss[loss=0.2022, simple_loss=0.295, pruned_loss=0.05475, over 960955.40 frames.], batch size: 14, lr: 4.30e-04
2022-05-30 02:28:04,403 INFO [train.py:761] (5/8) Epoch 40, batch 1150, loss[loss=0.1774, simple_loss=0.2599, pruned_loss=0.04747, over 4665.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2948, pruned_loss=0.05442, over 961597.37 frames.], batch size: 12, lr: 4.30e-04
2022-05-30 02:28:42,007 INFO [train.py:761] (5/8) Epoch 40, batch 1200, loss[loss=0.2033, simple_loss=0.2879, pruned_loss=0.05934, over 4662.00 frames.], tot_loss[loss=0.2024, simple_loss=0.295, pruned_loss=0.05493, over 962628.96 frames.], batch size: 12, lr: 4.30e-04
2022-05-30 02:29:20,161 INFO [train.py:761] (5/8) Epoch 40, batch 1250, loss[loss=0.1606, simple_loss=0.2505, pruned_loss=0.0353, over 4909.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2947, pruned_loss=0.05509, over 963304.21 frames.], batch size: 14, lr: 4.30e-04
2022-05-30 02:29:58,354 INFO [train.py:761] (5/8) Epoch 40, batch 1300, loss[loss=0.2053, simple_loss=0.3032, pruned_loss=0.05373, over 4981.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2964, pruned_loss=0.05614, over 965123.68 frames.], batch size: 14, lr: 4.30e-04
2022-05-30 02:30:36,446 INFO [train.py:761] (5/8) Epoch 40, batch 1350, loss[loss=0.2103, simple_loss=0.2907, pruned_loss=0.06499, over 4814.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2979, pruned_loss=0.05672, over 965528.32 frames.], batch size: 12, lr: 4.30e-04
2022-05-30 02:31:14,308 INFO [train.py:761] (5/8) Epoch 40, batch 1400, loss[loss=0.169, simple_loss=0.2751, pruned_loss=0.03149, over 4736.00 frames.], tot_loss[loss=0.2057, simple_loss=0.298, pruned_loss=0.05675, over 965138.24 frames.], batch size: 11, lr: 4.30e-04
2022-05-30 02:31:52,626 INFO [train.py:761] (5/8) Epoch 40, batch 1450, loss[loss=0.1859, simple_loss=0.2895, pruned_loss=0.04113, over 4820.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2971, pruned_loss=0.05598, over 965862.50 frames.], batch size: 16, lr: 4.30e-04
2022-05-30 02:32:30,623 INFO [train.py:761] (5/8) Epoch 40, batch 1500, loss[loss=0.1717, simple_loss=0.2582, pruned_loss=0.04266, over 4884.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2965, pruned_loss=0.05563, over 965934.15 frames.], batch size: 12, lr: 4.30e-04
2022-05-30 02:33:08,523 INFO [train.py:761] (5/8) Epoch 40, batch 1550, loss[loss=0.2221, simple_loss=0.3006, pruned_loss=0.07183, over 4726.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2976, pruned_loss=0.0563, over 965796.21 frames.], batch size: 12, lr: 4.30e-04
2022-05-30 02:33:46,183 INFO [train.py:761] (5/8) Epoch 40, batch 1600, loss[loss=0.2282, simple_loss=0.3231, pruned_loss=0.06664, over 4900.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2975, pruned_loss=0.05644, over 966570.42 frames.], batch size: 17, lr: 4.30e-04
2022-05-30 02:34:24,728 INFO [train.py:761] (5/8) Epoch 40, batch 1650, loss[loss=0.2389, simple_loss=0.3349, pruned_loss=0.07145, over 4775.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2971, pruned_loss=0.05633, over 966318.05 frames.], batch size: 13, lr: 4.29e-04
2022-05-30 02:35:03,349 INFO [train.py:761] (5/8) Epoch 40, batch 1700, loss[loss=0.1979, simple_loss=0.3114, pruned_loss=0.04218, over 4794.00 frames.], tot_loss[loss=0.205, simple_loss=0.2972, pruned_loss=0.05634, over 966440.04 frames.], batch size: 25, lr: 4.29e-04
2022-05-30 02:35:41,217 INFO [train.py:761] (5/8) Epoch 40, batch 1750, loss[loss=0.189, simple_loss=0.2882, pruned_loss=0.04488, over 4880.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2969, pruned_loss=0.05582, over 966244.84 frames.], batch size: 15, lr: 4.29e-04
2022-05-30 02:36:18,977 INFO [train.py:761] (5/8) Epoch 40, batch 1800, loss[loss=0.204, simple_loss=0.3064, pruned_loss=0.05081, over 4981.00 frames.], tot_loss[loss=0.204, simple_loss=0.2969, pruned_loss=0.05553, over 967223.43 frames.], batch size: 15, lr: 4.29e-04
2022-05-30 02:36:57,278 INFO [train.py:761] (5/8) Epoch 40, batch 1850, loss[loss=0.1671, simple_loss=0.2662, pruned_loss=0.03396, over 4779.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2971, pruned_loss=0.05555, over 966846.15 frames.], batch size: 14, lr: 4.29e-04
2022-05-30 02:37:35,201 INFO [train.py:761] (5/8) Epoch 40, batch 1900, loss[loss=0.2392, simple_loss=0.3248, pruned_loss=0.07682, over 4911.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2971, pruned_loss=0.05574, over 965879.86 frames.], batch size: 44, lr: 4.29e-04
2022-05-30 02:38:12,936 INFO [train.py:761] (5/8) Epoch 40, batch 1950, loss[loss=0.2413, simple_loss=0.327, pruned_loss=0.07783, over 4804.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2974, pruned_loss=0.05615, over 965612.83 frames.], batch size: 20, lr: 4.29e-04
2022-05-30 02:38:50,864 INFO [train.py:761] (5/8) Epoch 40, batch 2000, loss[loss=0.203, simple_loss=0.2954, pruned_loss=0.05528, over 4827.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2968, pruned_loss=0.05584, over 964421.45 frames.], batch size: 18, lr: 4.29e-04
2022-05-30 02:39:28,855 INFO [train.py:761] (5/8) Epoch 40, batch 2050, loss[loss=0.1794, simple_loss=0.2678, pruned_loss=0.04556, over 4921.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2959, pruned_loss=0.05499, over 967200.71 frames.], batch size: 13, lr: 4.29e-04
2022-05-30 02:40:06,662 INFO [train.py:761] (5/8) Epoch 40, batch 2100, loss[loss=0.1804, simple_loss=0.2782, pruned_loss=0.0413, over 4612.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2959, pruned_loss=0.05474, over 966091.84 frames.], batch size: 12, lr: 4.29e-04
2022-05-30 02:40:44,599 INFO [train.py:761] (5/8) Epoch 40, batch 2150, loss[loss=0.2062, simple_loss=0.3068, pruned_loss=0.05276, over 4926.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2963, pruned_loss=0.05522, over 965242.15 frames.], batch size: 14, lr: 4.29e-04
2022-05-30 02:41:22,599 INFO [train.py:761] (5/8) Epoch 40, batch 2200, loss[loss=0.2466, simple_loss=0.3361, pruned_loss=0.07852, over 4880.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2964, pruned_loss=0.05516, over 965827.63 frames.], batch size: 17, lr: 4.29e-04
2022-05-30 02:42:00,248 INFO [train.py:761] (5/8) Epoch 40, batch 2250, loss[loss=0.1725, simple_loss=0.2564, pruned_loss=0.0443, over 4736.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2965, pruned_loss=0.05571, over 966146.58 frames.], batch size: 11, lr: 4.29e-04
2022-05-30 02:42:37,511 INFO [train.py:761] (5/8) Epoch 40, batch 2300, loss[loss=0.226, simple_loss=0.3246, pruned_loss=0.06367, over 4932.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2963, pruned_loss=0.05516, over 965493.57 frames.], batch size: 26, lr: 4.29e-04
2022-05-30 02:43:15,390 INFO [train.py:761] (5/8) Epoch 40, batch 2350, loss[loss=0.2335, simple_loss=0.318, pruned_loss=0.07449, over 4888.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2978, pruned_loss=0.05586, over 966099.61 frames.], batch size: 15, lr: 4.29e-04
2022-05-30 02:43:53,149 INFO [train.py:761] (5/8) Epoch 40, batch 2400, loss[loss=0.2433, simple_loss=0.3351, pruned_loss=0.07575, over 4876.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2969, pruned_loss=0.05548, over 967753.21 frames.], batch size: 17, lr: 4.29e-04
2022-05-30 02:44:31,478 INFO [train.py:761] (5/8) Epoch 40, batch 2450, loss[loss=0.2326, simple_loss=0.326, pruned_loss=0.06959, over 4818.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2981, pruned_loss=0.05586, over 967208.96 frames.], batch size: 20, lr: 4.29e-04
2022-05-30 02:45:09,939 INFO [train.py:761] (5/8) Epoch 40, batch 2500, loss[loss=0.2208, simple_loss=0.3163, pruned_loss=0.06266, over 4808.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2993, pruned_loss=0.05642, over 967683.35 frames.], batch size: 20, lr: 4.29e-04
2022-05-30 02:45:48,278 INFO [train.py:761] (5/8) Epoch 40, batch 2550, loss[loss=0.2136, simple_loss=0.3081, pruned_loss=0.05953, over 4976.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2988, pruned_loss=0.05574, over 966922.45 frames.], batch size: 15, lr: 4.29e-04
2022-05-30 02:46:26,363 INFO [train.py:761] (5/8) Epoch 40, batch 2600, loss[loss=0.1801, simple_loss=0.2615, pruned_loss=0.0493, over 4733.00 frames.], tot_loss[loss=0.2044, simple_loss=0.298, pruned_loss=0.0554, over 967225.14 frames.], batch size: 12, lr: 4.29e-04
2022-05-30 02:47:04,638 INFO [train.py:761] (5/8) Epoch 40, batch 2650, loss[loss=0.1882, simple_loss=0.2771, pruned_loss=0.04967, over 4916.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2972, pruned_loss=0.05502, over 966688.41 frames.], batch size: 13, lr: 4.29e-04
2022-05-30 02:47:42,574 INFO [train.py:761] (5/8) Epoch 40, batch 2700, loss[loss=0.1951, simple_loss=0.2825, pruned_loss=0.05385, over 4740.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2966, pruned_loss=0.05449, over 966667.55 frames.], batch size: 12, lr: 4.29e-04
2022-05-30 02:48:20,353 INFO [train.py:761] (5/8) Epoch 40, batch 2750, loss[loss=0.2632, simple_loss=0.3537, pruned_loss=0.0863, over 4874.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2973, pruned_loss=0.05487, over 967153.02 frames.], batch size: 50, lr: 4.29e-04
2022-05-30 02:48:58,210 INFO [train.py:761] (5/8) Epoch 40, batch 2800, loss[loss=0.2056, simple_loss=0.3057, pruned_loss=0.05274, over 4755.00 frames.], tot_loss[loss=0.203, simple_loss=0.2966, pruned_loss=0.0547, over 966633.58 frames.], batch size: 15, lr: 4.29e-04
2022-05-30 02:49:36,057 INFO [train.py:761] (5/8) Epoch 40, batch 2850, loss[loss=0.2142, simple_loss=0.3051, pruned_loss=0.06164, over 4952.00 frames.], tot_loss[loss=0.2025, simple_loss=0.296, pruned_loss=0.05452, over 967602.42 frames.], batch size: 16, lr: 4.29e-04
2022-05-30 02:50:13,981 INFO [train.py:761] (5/8) Epoch 40, batch 2900, loss[loss=0.1952, simple_loss=0.2703, pruned_loss=0.06006, over 4989.00 frames.], tot_loss[loss=0.2021, simple_loss=0.296, pruned_loss=0.05413, over 967521.68 frames.], batch size: 12, lr: 4.28e-04
2022-05-30 02:50:52,136 INFO [train.py:761] (5/8) Epoch 40, batch 2950, loss[loss=0.176, simple_loss=0.2718, pruned_loss=0.04008, over 4761.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2979, pruned_loss=0.05492, over 967844.07 frames.], batch size: 15, lr: 4.28e-04
2022-05-30 02:51:29,635 INFO [train.py:761] (5/8) Epoch 40, batch 3000, loss[loss=0.1513, simple_loss=0.2426, pruned_loss=0.03005, over 4830.00 frames.], tot_loss[loss=0.203, simple_loss=0.2971, pruned_loss=0.05444, over 967995.84 frames.], batch size: 11, lr: 4.28e-04
2022-05-30 02:51:29,636 INFO [train.py:781] (5/8) Computing validation loss
2022-05-30 02:51:39,791 INFO [train.py:790] (5/8) Epoch 40, validation: loss=0.2014, simple_loss=0.3005, pruned_loss=0.05119, over 944034.00 frames.
2022-05-30 02:52:18,048 INFO [train.py:761] (5/8) Epoch 40, batch 3050, loss[loss=0.1837, simple_loss=0.2913, pruned_loss=0.03806, over 4923.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2968, pruned_loss=0.05493, over 967760.01 frames.], batch size: 13, lr: 4.28e-04
2022-05-30 02:52:56,353 INFO [train.py:761] (5/8) Epoch 40, batch 3100, loss[loss=0.1663, simple_loss=0.2512, pruned_loss=0.04076, over 4632.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2968, pruned_loss=0.05587, over 968037.83 frames.], batch size: 11, lr: 4.28e-04
2022-05-30 02:53:34,512 INFO [train.py:761] (5/8) Epoch 40, batch 3150, loss[loss=0.2196, simple_loss=0.2971, pruned_loss=0.07104, over 4860.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2972, pruned_loss=0.05676, over 967045.85 frames.], batch size: 13, lr: 4.28e-04
2022-05-30 02:54:11,997 INFO [train.py:761] (5/8) Epoch 40, batch 3200, loss[loss=0.2368, simple_loss=0.3325, pruned_loss=0.07056, over 4966.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2979, pruned_loss=0.05765, over 967503.73 frames.], batch size: 15, lr: 4.28e-04
2022-05-30 02:54:49,905 INFO [train.py:761] (5/8) Epoch 40, batch 3250, loss[loss=0.217, simple_loss=0.3052, pruned_loss=0.06439, over 4730.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2977, pruned_loss=0.05874, over 966602.79 frames.], batch size: 12, lr: 4.28e-04
2022-05-30 02:55:28,583 INFO [train.py:761] (5/8) Epoch 40, batch 3300, loss[loss=0.2129, simple_loss=0.3158, pruned_loss=0.05504, over 4971.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2971, pruned_loss=0.0599, over 967470.17 frames.], batch size: 14, lr: 4.28e-04
2022-05-30 02:56:07,097 INFO [train.py:761] (5/8) Epoch 40, batch 3350, loss[loss=0.2208, simple_loss=0.2948, pruned_loss=0.07334, over 4561.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2964, pruned_loss=0.06046, over 966721.24 frames.], batch size: 10, lr: 4.28e-04
2022-05-30 02:56:44,543 INFO [train.py:761] (5/8) Epoch 40, batch 3400, loss[loss=0.1847, simple_loss=0.2662, pruned_loss=0.05166, over 4640.00 frames.], tot_loss[loss=0.2099, simple_loss=0.297, pruned_loss=0.06144, over 967231.54 frames.], batch size: 11, lr: 4.28e-04
2022-05-30 02:57:22,344 INFO [train.py:761] (5/8) Epoch 40, batch 3450, loss[loss=0.1774, simple_loss=0.2533, pruned_loss=0.05071, over 4839.00 frames.], tot_loss[loss=0.2115, simple_loss=0.2974, pruned_loss=0.06278, over 965914.22 frames.], batch size: 11, lr: 4.28e-04
2022-05-30 02:58:00,597 INFO [train.py:761] (5/8) Epoch 40, batch 3500, loss[loss=0.2063, simple_loss=0.2947, pruned_loss=0.0589, over 4810.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2983, pruned_loss=0.06332, over 965474.06 frames.], batch size: 16, lr: 4.28e-04
2022-05-30 02:58:38,501 INFO [train.py:761] (5/8) Epoch 40, batch 3550, loss[loss=0.2395, simple_loss=0.3069, pruned_loss=0.08606, over 4533.00 frames.], tot_loss[loss=0.215, simple_loss=0.3, pruned_loss=0.06502, over 965674.33 frames.], batch size: 10, lr: 4.28e-04
2022-05-30 02:59:16,094 INFO [train.py:761] (5/8) Epoch 40, batch 3600, loss[loss=0.2101, simple_loss=0.2853, pruned_loss=0.06742, over 4979.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2996, pruned_loss=0.06484, over 966691.40 frames.], batch size: 12, lr: 4.28e-04
2022-05-30 02:59:53,635 INFO [train.py:761] (5/8) Epoch 40, batch 3650, loss[loss=0.2986, simple_loss=0.3567, pruned_loss=0.1202, over 4894.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2995, pruned_loss=0.06536, over 966683.07 frames.], batch size: 48, lr: 4.28e-04
2022-05-30 03:00:31,718 INFO [train.py:761] (5/8) Epoch 40, batch 3700, loss[loss=0.2111, simple_loss=0.2979, pruned_loss=0.06214, over 4859.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3014, pruned_loss=0.06658, over 966398.45 frames.], batch size: 13, lr: 4.28e-04
2022-05-30 03:01:09,470 INFO [train.py:761] (5/8) Epoch 40, batch 3750, loss[loss=0.2585, simple_loss=0.3297, pruned_loss=0.09366, over 4924.00 frames.], tot_loss[loss=0.217, simple_loss=0.3005, pruned_loss=0.0668, over 966094.69 frames.], batch size: 47, lr: 4.28e-04
2022-05-30 03:01:47,034 INFO [train.py:761] (5/8) Epoch 40, batch 3800, loss[loss=0.2417, simple_loss=0.3209, pruned_loss=0.08124, over 4669.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3017, pruned_loss=0.06802, over 965742.57 frames.], batch size: 13, lr: 4.28e-04
2022-05-30 03:02:25,279 INFO [train.py:761] (5/8) Epoch 40, batch 3850, loss[loss=0.308, simple_loss=0.375, pruned_loss=0.1205, over 4762.00 frames.], tot_loss[loss=0.219, simple_loss=0.3016, pruned_loss=0.06818, over 964796.14 frames.], batch size: 15, lr: 4.28e-04
2022-05-30 03:03:03,982 INFO [train.py:761] (5/8) Epoch 40, batch 3900, loss[loss=0.224, simple_loss=0.3103, pruned_loss=0.06887, over 4986.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3, pruned_loss=0.06724, over 964779.81 frames.], batch size: 13, lr: 4.28e-04
2022-05-30 03:03:42,459 INFO [train.py:761] (5/8) Epoch 40, batch 3950, loss[loss=0.2268, simple_loss=0.3132, pruned_loss=0.07017, over 4723.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2993, pruned_loss=0.06683, over 964388.53 frames.], batch size: 13, lr: 4.28e-04
2022-05-30 03:04:20,956 INFO [train.py:761] (5/8) Epoch 40, batch 4000, loss[loss=0.3093, simple_loss=0.378, pruned_loss=0.1203, over 4958.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3012, pruned_loss=0.06815, over 965243.99 frames.], batch size: 48, lr: 4.28e-04
2022-05-30 03:04:59,243 INFO [train.py:761] (5/8) Epoch 40, batch 4050, loss[loss=0.2779, simple_loss=0.3484, pruned_loss=0.1037, over 4855.00 frames.], tot_loss[loss=0.2195, simple_loss=0.302, pruned_loss=0.06848, over 965284.47 frames.], batch size: 14, lr: 4.28e-04
2022-05-30 03:05:37,156 INFO [train.py:761] (5/8) Epoch 40, batch 4100, loss[loss=0.1994, simple_loss=0.2905, pruned_loss=0.0542, over 4875.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3026, pruned_loss=0.06895, over 964876.25 frames.], batch size: 15, lr: 4.27e-04
2022-05-30 03:06:15,768 INFO [train.py:761] (5/8) Epoch 40, batch 4150, loss[loss=0.2178, simple_loss=0.3054, pruned_loss=0.06511, over 4910.00 frames.], tot_loss[loss=0.219, simple_loss=0.3021, pruned_loss=0.068, over 964896.01 frames.], batch size: 14, lr: 4.27e-04
2022-05-30 03:06:54,228 INFO [train.py:761] (5/8) Epoch 40, batch 4200, loss[loss=0.2095, simple_loss=0.2915, pruned_loss=0.06378, over 4884.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3013, pruned_loss=0.06827, over 965031.85 frames.], batch size: 15, lr: 4.27e-04
2022-05-30 03:07:32,683 INFO [train.py:761] (5/8) Epoch 40, batch 4250, loss[loss=0.2402, simple_loss=0.3138, pruned_loss=0.08334, over 4676.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3004, pruned_loss=0.06748, over 965969.60 frames.], batch size: 13, lr: 4.27e-04
2022-05-30 03:08:10,562 INFO [train.py:761] (5/8) Epoch 40, batch 4300, loss[loss=0.211, simple_loss=0.2981, pruned_loss=0.06192, over 4859.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2999, pruned_loss=0.06694, over 965796.16 frames.], batch size: 13, lr: 4.27e-04
2022-05-30 03:08:48,560 INFO [train.py:761] (5/8) Epoch 40, batch 4350, loss[loss=0.2306, simple_loss=0.3162, pruned_loss=0.07253, over 4670.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3009, pruned_loss=0.06787, over 965527.25 frames.], batch size: 13, lr: 4.27e-04
2022-05-30 03:09:27,038 INFO [train.py:761] (5/8) Epoch 40, batch 4400, loss[loss=0.2155, simple_loss=0.297, pruned_loss=0.067, over 4917.00 frames.], tot_loss[loss=0.219, simple_loss=0.3011, pruned_loss=0.06848, over 967056.18 frames.], batch size: 14, lr: 4.27e-04
2022-05-30 03:10:06,321 INFO [train.py:761] (5/8) Epoch 40, batch 4450, loss[loss=0.1843, simple_loss=0.2766, pruned_loss=0.04598, over 4974.00 frames.], tot_loss[loss=0.2194, simple_loss=0.3015, pruned_loss=0.06858, over 966194.61 frames.], batch size: 14, lr: 4.27e-04
2022-05-30 03:10:44,245 INFO [train.py:761] (5/8) Epoch 40, batch 4500, loss[loss=0.1882, simple_loss=0.2774, pruned_loss=0.04947, over 4849.00 frames.], tot_loss[loss=0.2201, simple_loss=0.3023, pruned_loss=0.06901, over 965245.21 frames.], batch size: 18, lr: 4.27e-04
2022-05-30 03:11:22,573 INFO [train.py:761] (5/8) Epoch 40, batch 4550, loss[loss=0.2248, simple_loss=0.2977, pruned_loss=0.07598, over 4730.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3009, pruned_loss=0.06847, over 966065.53 frames.], batch size: 13, lr: 4.27e-04
2022-05-30 03:12:00,512 INFO [train.py:761] (5/8) Epoch 40, batch 4600, loss[loss=0.2334, simple_loss=0.32, pruned_loss=0.0734, over 4848.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3012, pruned_loss=0.06819, over 966036.41 frames.], batch size: 17, lr: 4.27e-04
2022-05-30 03:12:39,011 INFO [train.py:761] (5/8) Epoch 40, batch 4650, loss[loss=0.2258, simple_loss=0.3113, pruned_loss=0.07017, over 4805.00 frames.], tot_loss[loss=0.2206, simple_loss=0.3031, pruned_loss=0.06907, over 966148.32 frames.], batch size: 16, lr: 4.27e-04
2022-05-30 03:13:17,230 INFO [train.py:761] (5/8) Epoch 40, batch 4700, loss[loss=0.2305, simple_loss=0.3157, pruned_loss=0.07258, over 4889.00 frames.], tot_loss[loss=0.218, simple_loss=0.3007, pruned_loss=0.0676, over 966441.72 frames.], batch size: 15, lr: 4.27e-04
2022-05-30 03:13:55,634 INFO [train.py:761] (5/8) Epoch 40, batch 4750, loss[loss=0.175, simple_loss=0.2632, pruned_loss=0.04342, over 4804.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3008, pruned_loss=0.06752, over 965932.10 frames.], batch size: 12, lr: 4.27e-04
2022-05-30 03:14:34,141 INFO [train.py:761] (5/8) Epoch 40, batch 4800, loss[loss=0.2314, simple_loss=0.3128, pruned_loss=0.07502, over 4925.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3013, pruned_loss=0.06796, over 966388.11 frames.], batch size: 14, lr: 4.27e-04
2022-05-30 03:15:12,355 INFO [train.py:761] (5/8) Epoch 40, batch 4850, loss[loss=0.1781, simple_loss=0.2538, pruned_loss=0.05115, over 4730.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3017, pruned_loss=0.06807, over 966557.88 frames.], batch size: 12, lr: 4.27e-04
2022-05-30 03:15:50,607 INFO [train.py:761] (5/8) Epoch 40, batch 4900, loss[loss=0.2515, simple_loss=0.3304, pruned_loss=0.08634, over 4947.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3011, pruned_loss=0.0674, over 966773.34 frames.], batch size: 48, lr: 4.27e-04
2022-05-30 03:16:28,819 INFO [train.py:761] (5/8) Epoch 40, batch 4950, loss[loss=0.2805, simple_loss=0.3528, pruned_loss=0.1041, over 4795.00 frames.], tot_loss[loss=0.218, simple_loss=0.3009, pruned_loss=0.06755, over 967193.99 frames.], batch size: 16, lr: 4.27e-04
2022-05-30 03:17:06,721 INFO [train.py:761] (5/8) Epoch 40, batch 5000, loss[loss=0.2606, simple_loss=0.3233, pruned_loss=0.09893, over 4922.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3004, pruned_loss=0.06737, over 966738.19 frames.], batch size: 14, lr: 4.27e-04
2022-05-30 03:17:45,241 INFO [train.py:761] (5/8) Epoch 40, batch 5050, loss[loss=0.2384, simple_loss=0.3224, pruned_loss=0.07718, over 4929.00 frames.], tot_loss[loss=0.2176, simple_loss=0.3001, pruned_loss=0.06761, over 967057.68 frames.], batch size: 47, lr: 4.27e-04
2022-05-30 03:18:23,563 INFO [train.py:761] (5/8) Epoch 40, batch 5100, loss[loss=0.1694, simple_loss=0.2519, pruned_loss=0.04351, over 4634.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3001, pruned_loss=0.06759, over 967270.20 frames.], batch size: 11, lr: 4.27e-04
2022-05-30 03:19:01,869 INFO [train.py:761] (5/8) Epoch 40, batch 5150, loss[loss=0.2255, simple_loss=0.3158, pruned_loss=0.06761, over 4797.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2999, pruned_loss=0.06718, over 966855.50 frames.], batch size: 14, lr: 4.27e-04
2022-05-30 03:19:40,239 INFO [train.py:761] (5/8) Epoch 40, batch 5200, loss[loss=0.1747, simple_loss=0.2629, pruned_loss=0.04324, over 4734.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3004, pruned_loss=0.06699, over 965736.94 frames.], batch size: 12, lr: 4.27e-04
2022-05-30 03:20:19,406 INFO [train.py:761] (5/8) Epoch 40, batch 5250, loss[loss=0.185, simple_loss=0.2534, pruned_loss=0.05828, over 4745.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2986, pruned_loss=0.06607, over 965012.49 frames.], batch size: 11, lr: 4.27e-04
2022-05-30 03:20:58,015 INFO [train.py:761] (5/8) Epoch 40, batch 5300, loss[loss=0.1966, simple_loss=0.2832, pruned_loss=0.05502, over 4964.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2993, pruned_loss=0.06611, over 964960.38 frames.], batch size: 21, lr: 4.27e-04
2022-05-30 03:21:36,174 INFO [train.py:761] (5/8) Epoch 40, batch 5350, loss[loss=0.2242, simple_loss=0.3192, pruned_loss=0.06459, over 4873.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2999, pruned_loss=0.06654, over 965338.91 frames.], batch size: 15, lr: 4.27e-04
2022-05-30 03:22:14,610 INFO [train.py:761] (5/8) Epoch 40, batch 5400, loss[loss=0.2636, simple_loss=0.3377, pruned_loss=0.09478, over 4924.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2993, pruned_loss=0.0658, over 966195.33 frames.], batch size: 46, lr: 4.26e-04
2022-05-30 03:22:53,451 INFO [train.py:761] (5/8) Epoch 40, batch 5450, loss[loss=0.2377, simple_loss=0.3107, pruned_loss=0.08237, over 4921.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3003, pruned_loss=0.06633, over 967190.16 frames.], batch size: 13, lr: 4.26e-04
2022-05-30 03:23:31,755 INFO [train.py:761] (5/8) Epoch 40, batch 5500, loss[loss=0.2203, simple_loss=0.3118, pruned_loss=0.06443, over 4759.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3001, pruned_loss=0.06649, over 967486.28 frames.], batch size: 20, lr: 4.26e-04
2022-05-30 03:24:09,260 INFO [train.py:761] (5/8) Epoch 40, batch 5550, loss[loss=0.2219, simple_loss=0.3036, pruned_loss=0.07008, over 4994.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2998, pruned_loss=0.06641, over 966646.15 frames.], batch size: 13, lr: 4.26e-04
2022-05-30 03:24:47,582 INFO [train.py:761] (5/8) Epoch 40, batch 5600, loss[loss=0.2503, simple_loss=0.3333, pruned_loss=0.08361, over 4874.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3001, pruned_loss=0.06633, over 966668.40 frames.], batch size: 15, lr: 4.26e-04
2022-05-30 03:25:26,011 INFO [train.py:761] (5/8) Epoch 40, batch 5650, loss[loss=0.2377, simple_loss=0.3223, pruned_loss=0.0765, over 4885.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2997, pruned_loss=0.06593, over 966481.11 frames.], batch size: 15, lr: 4.26e-04
2022-05-30 03:26:04,721 INFO [train.py:761] (5/8) Epoch 40, batch 5700, loss[loss=0.2265, simple_loss=0.3084, pruned_loss=0.07234, over 4667.00 frames.], tot_loss[loss=0.216, simple_loss=0.3002, pruned_loss=0.06597, over 965993.64 frames.], batch size: 13, lr: 4.26e-04
2022-05-30 03:26:42,754 INFO [train.py:761] (5/8) Epoch 40, batch 5750, loss[loss=0.202, simple_loss=0.2987, pruned_loss=0.05268, over 4734.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2999, pruned_loss=0.06618, over 965483.53 frames.], batch size: 12, lr: 4.26e-04
2022-05-30 03:27:20,546 INFO [train.py:761] (5/8) Epoch 40, batch 5800, loss[loss=0.2418, simple_loss=0.3303, pruned_loss=0.07667, over 4782.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3, pruned_loss=0.06656, over 964419.10 frames.], batch size: 14, lr: 4.26e-04
2022-05-30 03:27:58,982 INFO [train.py:761] (5/8) Epoch 40, batch 5850, loss[loss=0.2098, simple_loss=0.3031, pruned_loss=0.0583, over 4845.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3015, pruned_loss=0.06746, over 965442.69 frames.], batch size: 18, lr: 4.26e-04
2022-05-30 03:28:37,489 INFO [train.py:761] (5/8) Epoch 40, batch 5900, loss[loss=0.2088, simple_loss=0.2801, pruned_loss=0.0688, over 4801.00 frames.], tot_loss[loss=0.219, simple_loss=0.3023, pruned_loss=0.06779, over 966208.05 frames.], batch size: 12, lr: 4.26e-04
2022-05-30 03:29:16,321 INFO [train.py:761] (5/8) Epoch 40, batch 5950, loss[loss=0.2246, simple_loss=0.3125, pruned_loss=0.06828, over 4833.00 frames.], tot_loss[loss=0.221, simple_loss=0.3043, pruned_loss=0.06889, over 965015.48 frames.], batch size: 25, lr: 4.26e-04
2022-05-30 03:29:54,805 INFO [train.py:761] (5/8) Epoch 40, batch 6000, loss[loss=0.2023, simple_loss=0.3005, pruned_loss=0.05208, over 4850.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3047, pruned_loss=0.06905, over 964767.35 frames.], batch size: 14, lr: 4.26e-04
2022-05-30 03:29:54,805 INFO [train.py:781] (5/8) Computing validation loss
2022-05-30 03:30:04,583 INFO [train.py:790] (5/8) Epoch 40, validation: loss=0.1969, simple_loss=0.2979, pruned_loss=0.04791, over 944034.00 frames.
2022-05-30 03:30:43,122 INFO [train.py:761] (5/8) Epoch 40, batch 6050, loss[loss=0.2433, simple_loss=0.323, pruned_loss=0.08175, over 4713.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3037, pruned_loss=0.0686, over 964909.14 frames.], batch size: 14, lr: 4.26e-04
2022-05-30 03:31:21,322 INFO [train.py:761] (5/8) Epoch 40, batch 6100, loss[loss=0.2092, simple_loss=0.2935, pruned_loss=0.0625, over 4876.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3029, pruned_loss=0.06831, over 964984.18 frames.], batch size: 12, lr: 4.26e-04
2022-05-30 03:31:59,855 INFO [train.py:761] (5/8) Epoch 40, batch 6150, loss[loss=0.1805, simple_loss=0.2623, pruned_loss=0.04936, over 4655.00 frames.], tot_loss[loss=0.2198, simple_loss=0.3025, pruned_loss=0.0685, over 966041.53 frames.], batch size: 12, lr: 4.26e-04
2022-05-30 03:32:38,164 INFO [train.py:761] (5/8) Epoch 40, batch 6200, loss[loss=0.2205, simple_loss=0.306, pruned_loss=0.0675, over 4666.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3016, pruned_loss=0.06793, over 965520.57 frames.], batch size: 12, lr: 4.26e-04
2022-05-30 03:33:16,615 INFO [train.py:761] (5/8) Epoch 40, batch 6250, loss[loss=0.2757, simple_loss=0.3396, pruned_loss=0.106, over 4913.00 frames.], tot_loss[loss=0.2191, simple_loss=0.302, pruned_loss=0.06808, over 966122.24 frames.], batch size: 48, lr: 4.26e-04
2022-05-30 03:33:54,929 INFO [train.py:761] (5/8) Epoch 40, batch 6300, loss[loss=0.1931, simple_loss=0.2648, pruned_loss=0.06066, over 4560.00 frames.], tot_loss[loss=0.219, simple_loss=0.3026, pruned_loss=0.06766, over 966245.15 frames.], batch size: 10, lr: 4.26e-04
2022-05-30 03:34:32,838 INFO [train.py:761] (5/8) Epoch 40, batch 6350, loss[loss=0.2643, simple_loss=0.3092, pruned_loss=0.1097, over 4857.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3014, pruned_loss=0.06723, over 965060.50 frames.], batch size: 13, lr: 4.26e-04
2022-05-30 03:35:11,237 INFO [train.py:761] (5/8) Epoch 40, batch 6400, loss[loss=0.2248, simple_loss=0.2919, pruned_loss=0.07889, over 4667.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3011, pruned_loss=0.06687, over 964663.88 frames.], batch size: 12, lr: 4.26e-04
2022-05-30 03:35:49,580 INFO [train.py:761] (5/8) Epoch 40, batch 6450, loss[loss=0.2126, simple_loss=0.3092, pruned_loss=0.05796, over 4992.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3021, pruned_loss=0.06776, over 964502.23 frames.], batch size: 13, lr: 4.26e-04
2022-05-30 03:36:27,559 INFO [train.py:761] (5/8) Epoch 40, batch 6500, loss[loss=0.2152, simple_loss=0.2913, pruned_loss=0.06957, over 4989.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3015, pruned_loss=0.06739, over 964356.52 frames.], batch size: 13, lr: 4.26e-04
2022-05-30 03:37:06,347 INFO [train.py:761] (5/8) Epoch 40, batch 6550, loss[loss=0.2104, simple_loss=0.2959, pruned_loss=0.06247, over 4731.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3014, pruned_loss=0.06722, over 964892.37 frames.], batch size: 13, lr: 4.26e-04
2022-05-30 03:37:44,588 INFO [train.py:761] (5/8) Epoch 40, batch 6600, loss[loss=0.1924, simple_loss=0.2652, pruned_loss=0.05979, over 4660.00 frames.], tot_loss[loss=0.2182, simple_loss=0.302, pruned_loss=0.06718, over 965302.50 frames.], batch size: 12, lr: 4.26e-04
2022-05-30 03:38:22,670 INFO [train.py:761] (5/8) Epoch 40, batch 6650, loss[loss=0.1992, simple_loss=0.2625, pruned_loss=0.06796, over 4733.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3015, pruned_loss=0.06747, over 965291.93 frames.], batch size: 11, lr: 4.25e-04
2022-05-30 03:39:00,690 INFO [train.py:761] (5/8) Epoch 40, batch 6700, loss[loss=0.2215, simple_loss=0.311, pruned_loss=0.066, over 4780.00 frames.], tot_loss[loss=0.217, simple_loss=0.3, pruned_loss=0.06697, over 965535.18 frames.], batch size: 13, lr: 4.25e-04
2022-05-30 03:39:39,187 INFO [train.py:970] (5/8) Done!