diff --git "a/distillation/log/log-train-2022-05-27-13-56-55-3" "b/distillation/log/log-train-2022-05-27-13-56-55-3"
new file mode 100644--- /dev/null
+++ "b/distillation/log/log-train-2022-05-27-13-56-55-3"
@@ -0,0 +1,982 @@
+2022-05-27 13:56:55,368 INFO [train.py:887] (3/4) Training started
+2022-05-27 13:56:55,368 INFO [train.py:897] (3/4) Device: cuda:3
+2022-05-27 13:56:55,371 INFO [train.py:906] (3/4) {'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': 1600, 'feature_dim': 80, 'subsampling_factor': 4, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.13', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f4fefe4882bc0ae59af951da3f47335d5495ef71', 'k2-git-date': 'Thu Feb 10 15:16:02 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'stateless6', 'icefall-git-sha1': '50641cd-dirty', 'icefall-git-date': 'Fri May 27 13:49:39 2022', 'icefall-path': '/ceph-data2/ly/open_source/vq3_icefall', 'k2-path': '/ceph-jb/yaozengwei/workspace/rnnt/k2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-ly/open-source/hubert/lhotse/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-3-0307202051-57dc848959-8tmmp', 'IP address': '10.177.24.138'}, 'enable_distiallation': True, 'distillation_layer': 5, 'num_codebooks': 16, 'world_size': 4, 'master_port': 12359, 'tensorboard': True, 'num_epochs': 50, 'start_epoch': 1, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless6/exp'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'initial_lr': 0.003, 'lr_batches': 5000, 'lr_epochs': 6, 'context_size': 2, 'prune_range': 5, 'lm_scale': 0.25, 'am_scale': 0.0, 'simple_loss_scale': 0.5, 'codebook_loss_scale': 0.1, 'seed': 42, 'print_diagnostics': False, 'save_every_n': 8000, 'keep_last_k': 20, 'average_period': 100, 'use_fp16': False, 'full_libri': False, 'manifest_dir': PosixPath('data/vq_fbank'), 'max_duration': 300, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'drop_last': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': -1, 'enable_musan': True, 'input_strategy': 'PrecomputedFeatures', 'blank_id': 0, 'vocab_size': 500}
+2022-05-27 13:56:55,371 INFO [train.py:908] (3/4) About to create model
+2022-05-27 13:56:55,883 INFO [train.py:912] (3/4) Number of model parameters: 85075176
+2022-05-27 13:57:00,408 INFO [train.py:927] (3/4) Using DDP
+2022-05-27 13:57:00,574 INFO [asr_datamodule.py:408] (3/4) About to get train-clean-100 cuts
+2022-05-27 13:57:08,623 INFO [asr_datamodule.py:225] (3/4) Enable MUSAN
+2022-05-27 13:57:08,623 INFO [asr_datamodule.py:226] (3/4) About to get Musan cuts
+2022-05-27 13:57:12,096 INFO [asr_datamodule.py:254] (3/4) Enable SpecAugment
+2022-05-27 13:57:12,097 INFO [asr_datamodule.py:255] (3/4) Time warp factor: -1
+2022-05-27 13:57:12,097 INFO [asr_datamodule.py:267] (3/4) Num frame mask: 10
+2022-05-27 13:57:12,097 INFO [asr_datamodule.py:280] (3/4) About to create train dataset
+2022-05-27 13:57:12,097 INFO [asr_datamodule.py:309] (3/4) Using BucketingSampler.
+2022-05-27 13:57:12,410 INFO [asr_datamodule.py:325] (3/4) About to create train dataloader
+2022-05-27 13:57:12,410 INFO [asr_datamodule.py:429] (3/4) About to get dev-clean cuts
+2022-05-27 13:57:12,545 INFO [asr_datamodule.py:434] (3/4) About to get dev-other cuts
+2022-05-27 13:57:12,663 INFO [asr_datamodule.py:356] (3/4) About to create dev dataset
+2022-05-27 13:57:12,676 INFO [asr_datamodule.py:375] (3/4) About to create dev dataloader
+2022-05-27 13:57:12,676 INFO [train.py:1054] (3/4) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
+2022-05-27 13:57:15,193 INFO [distributed.py:874] (3/4) Reducer buckets have been rebuilt in this iteration.
+2022-05-27 13:57:27,692 INFO [train.py:823] (3/4) Epoch 1, batch 0, loss[loss=9.248, simple_loss=1.749, pruned_loss=6.679, codebook_loss=83.73, over 7286.00 frames.], tot_loss[loss=9.248, simple_loss=1.749, pruned_loss=6.679, codebook_loss=83.73, over 7286.00 frames.], batch size: 21, lr: 3.00e-03
+2022-05-27 13:58:08,136 INFO [train.py:823] (3/4) Epoch 1, batch 50, loss[loss=5.454, simple_loss=1.084, pruned_loss=6.922, codebook_loss=49.12, over 7161.00 frames.], tot_loss[loss=6.762, simple_loss=1.132, pruned_loss=6.804, codebook_loss=61.96, over 322028.89 frames.], batch size: 23, lr: 3.00e-03
+2022-05-27 13:58:49,203 INFO [train.py:823] (3/4) Epoch 1, batch 100, loss[loss=4.483, simple_loss=0.8789, pruned_loss=6.81, codebook_loss=40.44, over 7188.00 frames.], tot_loss[loss=5.719, simple_loss=1.019, pruned_loss=6.808, codebook_loss=52.09, over 564021.41 frames.], batch size: 20, lr: 3.00e-03
+2022-05-27 13:59:29,583 INFO [train.py:823] (3/4) Epoch 1, batch 150, loss[loss=4.25, simple_loss=0.9114, pruned_loss=6.843, codebook_loss=37.95, over 7338.00 frames.], tot_loss[loss=5.135, simple_loss=0.9474, pruned_loss=6.78, codebook_loss=46.62, over 754370.83 frames.], batch size: 23, lr: 3.00e-03
+2022-05-27 14:00:10,105 INFO [train.py:823] (3/4) Epoch 1, batch 200, loss[loss=3.931, simple_loss=0.7554, pruned_loss=6.607, codebook_loss=35.53, over 7300.00 frames.], tot_loss[loss=4.762, simple_loss=0.9064, pruned_loss=6.755, codebook_loss=43.08, over 903263.45 frames.], batch size: 19, lr: 3.00e-03
+2022-05-27 14:00:50,337 INFO [train.py:823] (3/4) Epoch 1, batch 250, loss[loss=3.783, simple_loss=0.6867, pruned_loss=6.513, codebook_loss=34.4, over 7287.00 frames.], tot_loss[loss=4.499, simple_loss=0.8696, pruned_loss=6.719, codebook_loss=40.64, over 1014421.72 frames.], batch size: 17, lr: 3.00e-03
+2022-05-27 14:01:30,773 INFO [train.py:823] (3/4) Epoch 1, batch 300, loss[loss=3.832, simple_loss=0.7882, pruned_loss=6.762, codebook_loss=34.38, over 7199.00 frames.], tot_loss[loss=4.287, simple_loss=0.8292, pruned_loss=6.69, codebook_loss=38.72, over 1106216.70 frames.], batch size: 24, lr: 3.00e-03
+2022-05-27 14:02:10,823 INFO [train.py:823] (3/4) Epoch 1, batch 350, loss[loss=3.634, simple_loss=0.6706, pruned_loss=6.514, codebook_loss=32.98, over 6592.00 frames.], tot_loss[loss=4.108, simple_loss=0.7832, pruned_loss=6.669, codebook_loss=37.16, over 1177131.05 frames.], batch size: 34, lr: 3.00e-03
+2022-05-27 14:02:51,180 INFO [train.py:823] (3/4) Epoch 1, batch 400, loss[loss=3.573, simple_loss=0.6125, pruned_loss=6.664, codebook_loss=32.67, over 5085.00 frames.], tot_loss[loss=3.965, simple_loss=0.7418, pruned_loss=6.658, codebook_loss=35.95, over 1228101.57 frames.], batch size: 46, lr: 3.00e-03
+2022-05-27 14:03:31,151 INFO [train.py:823] (3/4) Epoch 1, batch 450, loss[loss=3.467, simple_loss=0.5905, pruned_loss=6.581, codebook_loss=31.72, over 7193.00 frames.], tot_loss[loss=3.844, simple_loss=0.7025, pruned_loss=6.639, codebook_loss=34.92, over 1273912.37 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:04:11,752 INFO [train.py:823] (3/4) Epoch 1, batch 500, loss[loss=3.33, simple_loss=0.5326, pruned_loss=6.514, codebook_loss=30.64, over 7380.00 frames.], tot_loss[loss=3.732, simple_loss=0.667, pruned_loss=6.624, codebook_loss=33.98, over 1308352.84 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:04:51,652 INFO [train.py:823] (3/4) Epoch 1, batch 550, loss[loss=3.467, simple_loss=0.6026, pruned_loss=6.618, codebook_loss=31.66, over 7202.00 frames.], tot_loss[loss=3.645, simple_loss=0.6377, pruned_loss=6.615, codebook_loss=33.26, over 1329858.82 frames.], batch size: 25, lr: 2.99e-03
+2022-05-27 14:05:31,972 INFO [train.py:823] (3/4) Epoch 1, batch 600, loss[loss=3.139, simple_loss=0.4725, pruned_loss=6.613, codebook_loss=29.03, over 7295.00 frames.], tot_loss[loss=3.558, simple_loss=0.6072, pruned_loss=6.602, codebook_loss=32.54, over 1346431.42 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:06:11,929 INFO [train.py:823] (3/4) Epoch 1, batch 650, loss[loss=3.299, simple_loss=0.5271, pruned_loss=6.562, codebook_loss=30.35, over 7097.00 frames.], tot_loss[loss=3.484, simple_loss=0.5843, pruned_loss=6.6, codebook_loss=31.92, over 1361092.04 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:06:52,043 INFO [train.py:823] (3/4) Epoch 1, batch 700, loss[loss=3.149, simple_loss=0.4419, pruned_loss=6.441, codebook_loss=29.28, over 7158.00 frames.], tot_loss[loss=3.422, simple_loss=0.5619, pruned_loss=6.592, codebook_loss=31.41, over 1373735.52 frames.], batch size: 17, lr: 2.99e-03
+2022-05-27 14:07:31,813 INFO [train.py:823] (3/4) Epoch 1, batch 750, loss[loss=3.089, simple_loss=0.3943, pruned_loss=6.387, codebook_loss=28.91, over 7252.00 frames.], tot_loss[loss=3.359, simple_loss=0.5437, pruned_loss=6.595, codebook_loss=30.88, over 1387143.31 frames.], batch size: 16, lr: 2.98e-03
+2022-05-27 14:08:12,262 INFO [train.py:823] (3/4) Epoch 1, batch 800, loss[loss=3.138, simple_loss=0.4759, pruned_loss=6.629, codebook_loss=29, over 7154.00 frames.], tot_loss[loss=3.31, simple_loss=0.5266, pruned_loss=6.596, codebook_loss=30.46, over 1393311.31 frames.], batch size: 23, lr: 2.98e-03
+2022-05-27 14:08:52,266 INFO [train.py:823] (3/4) Epoch 1, batch 850, loss[loss=2.961, simple_loss=0.4045, pruned_loss=6.425, codebook_loss=27.59, over 7008.00 frames.], tot_loss[loss=3.267, simple_loss=0.5133, pruned_loss=6.594, codebook_loss=30.1, over 1400289.56 frames.], batch size: 16, lr: 2.98e-03
+2022-05-27 14:09:32,255 INFO [train.py:823] (3/4) Epoch 1, batch 900, loss[loss=3.025, simple_loss=0.4139, pruned_loss=6.455, codebook_loss=28.18, over 7288.00 frames.], tot_loss[loss=3.217, simple_loss=0.4983, pruned_loss=6.591, codebook_loss=29.68, over 1403742.06 frames.], batch size: 17, lr: 2.98e-03
+2022-05-27 14:10:24,075 INFO [train.py:823] (3/4) Epoch 2, batch 0, loss[loss=2.927, simple_loss=0.3935, pruned_loss=6.643, codebook_loss=27.3, over 7099.00 frames.], tot_loss[loss=2.927, simple_loss=0.3935, pruned_loss=6.643, codebook_loss=27.3, over 7099.00 frames.], batch size: 19, lr: 2.95e-03
+2022-05-27 14:11:04,143 INFO [train.py:823] (3/4) Epoch 2, batch 50, loss[loss=3.023, simple_loss=0.4494, pruned_loss=6.601, codebook_loss=27.98, over 7378.00 frames.], tot_loss[loss=3.009, simple_loss=0.4344, pruned_loss=6.579, codebook_loss=27.91, over 322848.62 frames.], batch size: 21, lr: 2.95e-03
+2022-05-27 14:11:44,113 INFO [train.py:823] (3/4) Epoch 2, batch 100, loss[loss=2.96, simple_loss=0.4397, pruned_loss=6.66, codebook_loss=27.4, over 6986.00 frames.], tot_loss[loss=2.977, simple_loss=0.4248, pruned_loss=6.576, codebook_loss=27.65, over 564403.17 frames.], batch size: 26, lr: 2.95e-03
+2022-05-27 14:12:24,090 INFO [train.py:823] (3/4) Epoch 2, batch 150, loss[loss=3.081, simple_loss=0.4018, pruned_loss=6.381, codebook_loss=28.8, over 7296.00 frames.], tot_loss[loss=2.961, simple_loss=0.4207, pruned_loss=6.573, codebook_loss=27.51, over 758504.82 frames.], batch size: 17, lr: 2.94e-03
+2022-05-27 14:13:04,792 INFO [train.py:823] (3/4) Epoch 2, batch 200, loss[loss=2.971, simple_loss=0.4335, pruned_loss=6.574, codebook_loss=27.54, over 7103.00 frames.], tot_loss[loss=2.945, simple_loss=0.417, pruned_loss=6.573, codebook_loss=27.37, over 906625.71 frames.], batch size: 18, lr: 2.94e-03
+2022-05-27 14:13:44,834 INFO [train.py:823] (3/4) Epoch 2, batch 250, loss[loss=3.082, simple_loss=0.3702, pruned_loss=6.477, codebook_loss=28.97, over 7157.00 frames.], tot_loss[loss=2.934, simple_loss=0.4132, pruned_loss=6.572, codebook_loss=27.27, over 1017913.31 frames.], batch size: 17, lr: 2.94e-03
+2022-05-27 14:14:25,461 INFO [train.py:823] (3/4) Epoch 2, batch 300, loss[loss=2.827, simple_loss=0.3407, pruned_loss=6.436, codebook_loss=26.57, over 7013.00 frames.], tot_loss[loss=2.929, simple_loss=0.4121, pruned_loss=6.575, codebook_loss=27.23, over 1108790.99 frames.], batch size: 16, lr: 2.93e-03
+2022-05-27 14:15:07,011 INFO [train.py:823] (3/4) Epoch 2, batch 350, loss[loss=2.822, simple_loss=0.4218, pruned_loss=6.642, codebook_loss=26.11, over 7137.00 frames.], tot_loss[loss=2.931, simple_loss=0.412, pruned_loss=6.581, codebook_loss=27.25, over 1176034.05 frames.], batch size: 23, lr: 2.93e-03
+2022-05-27 14:15:51,502 INFO [train.py:823] (3/4) Epoch 2, batch 400, loss[loss=2.914, simple_loss=0.4035, pruned_loss=6.516, codebook_loss=27.12, over 7100.00 frames.], tot_loss[loss=2.923, simple_loss=0.4106, pruned_loss=6.581, codebook_loss=27.18, over 1224745.08 frames.], batch size: 18, lr: 2.93e-03
+2022-05-27 14:16:31,412 INFO [train.py:823] (3/4) Epoch 2, batch 450, loss[loss=2.779, simple_loss=0.3832, pruned_loss=6.625, codebook_loss=25.88, over 7288.00 frames.], tot_loss[loss=2.902, simple_loss=0.4062, pruned_loss=6.58, codebook_loss=26.99, over 1265761.32 frames.], batch size: 21, lr: 2.92e-03
+2022-05-27 14:17:11,910 INFO [train.py:823] (3/4) Epoch 2, batch 500, loss[loss=2.859, simple_loss=0.4195, pruned_loss=6.714, codebook_loss=26.49, over 6907.00 frames.], tot_loss[loss=2.884, simple_loss=0.4028, pruned_loss=6.583, codebook_loss=26.83, over 1302081.72 frames.], batch size: 29, lr: 2.92e-03
+2022-05-27 14:17:51,825 INFO [train.py:823] (3/4) Epoch 2, batch 550, loss[loss=2.859, simple_loss=0.3959, pruned_loss=6.566, codebook_loss=26.61, over 5203.00 frames.], tot_loss[loss=2.874, simple_loss=0.4, pruned_loss=6.581, codebook_loss=26.74, over 1324000.87 frames.], batch size: 46, lr: 2.92e-03
+2022-05-27 14:18:32,335 INFO [train.py:823] (3/4) Epoch 2, batch 600, loss[loss=2.756, simple_loss=0.4108, pruned_loss=6.682, codebook_loss=25.51, over 7284.00 frames.], tot_loss[loss=2.863, simple_loss=0.3989, pruned_loss=6.583, codebook_loss=26.63, over 1341074.43 frames.], batch size: 21, lr: 2.91e-03
+2022-05-27 14:19:12,443 INFO [train.py:823] (3/4) Epoch 2, batch 650, loss[loss=2.721, simple_loss=0.4081, pruned_loss=6.659, codebook_loss=25.17, over 7290.00 frames.], tot_loss[loss=2.847, simple_loss=0.3967, pruned_loss=6.591, codebook_loss=26.48, over 1358983.62 frames.], batch size: 22, lr: 2.91e-03
+2022-05-27 14:19:53,601 INFO [train.py:823] (3/4) Epoch 2, batch 700, loss[loss=2.812, simple_loss=0.3638, pruned_loss=6.528, codebook_loss=26.3, over 7026.00 frames.], tot_loss[loss=2.834, simple_loss=0.3939, pruned_loss=6.597, codebook_loss=26.37, over 1374884.45 frames.], batch size: 17, lr: 2.90e-03
+2022-05-27 14:20:34,246 INFO [train.py:823] (3/4) Epoch 2, batch 750, loss[loss=2.857, simple_loss=0.4066, pruned_loss=6.706, codebook_loss=26.53, over 7459.00 frames.], tot_loss[loss=2.816, simple_loss=0.3896, pruned_loss=6.598, codebook_loss=26.21, over 1381415.13 frames.], batch size: 21, lr: 2.90e-03
+2022-05-27 14:21:14,869 INFO [train.py:823] (3/4) Epoch 2, batch 800, loss[loss=2.877, simple_loss=0.3846, pruned_loss=6.598, codebook_loss=26.85, over 4799.00 frames.], tot_loss[loss=2.818, simple_loss=0.3894, pruned_loss=6.604, codebook_loss=26.23, over 1386790.36 frames.], batch size: 47, lr: 2.89e-03
+2022-05-27 14:21:56,045 INFO [train.py:823] (3/4) Epoch 2, batch 850, loss[loss=2.822, simple_loss=0.3995, pruned_loss=6.572, codebook_loss=26.23, over 7188.00 frames.], tot_loss[loss=2.8, simple_loss=0.3867, pruned_loss=6.606, codebook_loss=26.07, over 1390606.15 frames.], batch size: 20, lr: 2.89e-03
+2022-05-27 14:22:36,181 INFO [train.py:823] (3/4) Epoch 2, batch 900, loss[loss=2.628, simple_loss=0.3118, pruned_loss=6.525, codebook_loss=24.72, over 7319.00 frames.], tot_loss[loss=2.783, simple_loss=0.3838, pruned_loss=6.61, codebook_loss=25.92, over 1395070.64 frames.], batch size: 18, lr: 2.89e-03
+2022-05-27 14:23:30,854 INFO [train.py:823] (3/4) Epoch 3, batch 0, loss[loss=2.653, simple_loss=0.3284, pruned_loss=6.521, codebook_loss=24.89, over 7307.00 frames.], tot_loss[loss=2.653, simple_loss=0.3284, pruned_loss=6.521, codebook_loss=24.89, over 7307.00 frames.], batch size: 17, lr: 2.83e-03
+2022-05-27 14:24:11,237 INFO [train.py:823] (3/4) Epoch 3, batch 50, loss[loss=2.845, simple_loss=0.3868, pruned_loss=6.544, codebook_loss=26.52, over 4808.00 frames.], tot_loss[loss=2.703, simple_loss=0.3642, pruned_loss=6.598, codebook_loss=25.21, over 319508.92 frames.], batch size: 46, lr: 2.82e-03
+2022-05-27 14:24:51,187 INFO [train.py:823] (3/4) Epoch 3, batch 100, loss[loss=2.671, simple_loss=0.3714, pruned_loss=6.658, codebook_loss=24.85, over 7003.00 frames.], tot_loss[loss=2.707, simple_loss=0.3665, pruned_loss=6.587, codebook_loss=25.24, over 565311.34 frames.], batch size: 26, lr: 2.82e-03
+2022-05-27 14:25:31,469 INFO [train.py:823] (3/4) Epoch 3, batch 150, loss[loss=2.623, simple_loss=0.351, pruned_loss=6.607, codebook_loss=24.47, over 7376.00 frames.], tot_loss[loss=2.695, simple_loss=0.3624, pruned_loss=6.589, codebook_loss=25.14, over 756448.47 frames.], batch size: 20, lr: 2.81e-03
+2022-05-27 14:26:11,610 INFO [train.py:823] (3/4) Epoch 3, batch 200, loss[loss=2.604, simple_loss=0.3548, pruned_loss=6.633, codebook_loss=24.26, over 7099.00 frames.], tot_loss[loss=2.684, simple_loss=0.3605, pruned_loss=6.597, codebook_loss=25.04, over 907484.79 frames.], batch size: 20, lr: 2.81e-03
+2022-05-27 14:26:51,964 INFO [train.py:823] (3/4) Epoch 3, batch 250, loss[loss=2.604, simple_loss=0.3334, pruned_loss=6.665, codebook_loss=24.38, over 7034.00 frames.], tot_loss[loss=2.677, simple_loss=0.359, pruned_loss=6.609, codebook_loss=24.97, over 1025930.32 frames.], batch size: 26, lr: 2.80e-03
+2022-05-27 14:27:31,817 INFO [train.py:823] (3/4) Epoch 3, batch 300, loss[loss=2.477, simple_loss=0.3006, pruned_loss=6.54, codebook_loss=23.27, over 7394.00 frames.], tot_loss[loss=2.678, simple_loss=0.3591, pruned_loss=6.619, codebook_loss=24.98, over 1115552.34 frames.], batch size: 19, lr: 2.80e-03
+2022-05-27 14:28:12,719 INFO [train.py:823] (3/4) Epoch 3, batch 350, loss[loss=2.743, simple_loss=0.3955, pruned_loss=6.646, codebook_loss=25.45, over 7346.00 frames.], tot_loss[loss=2.691, simple_loss=0.3597, pruned_loss=6.62, codebook_loss=25.11, over 1186029.68 frames.], batch size: 23, lr: 2.79e-03
+2022-05-27 14:28:52,479 INFO [train.py:823] (3/4) Epoch 3, batch 400, loss[loss=2.544, simple_loss=0.3039, pruned_loss=6.424, codebook_loss=23.92, over 7299.00 frames.], tot_loss[loss=2.69, simple_loss=0.3594, pruned_loss=6.614, codebook_loss=25.1, over 1238992.70 frames.], batch size: 18, lr: 2.79e-03
+2022-05-27 14:29:32,947 INFO [train.py:823] (3/4) Epoch 3, batch 450, loss[loss=2.617, simple_loss=0.3289, pruned_loss=6.519, codebook_loss=24.53, over 7184.00 frames.], tot_loss[loss=2.69, simple_loss=0.3596, pruned_loss=6.618, codebook_loss=25.1, over 1272241.84 frames.], batch size: 18, lr: 2.78e-03
+2022-05-27 14:30:12,773 INFO [train.py:823] (3/4) Epoch 3, batch 500, loss[loss=2.725, simple_loss=0.3054, pruned_loss=6.51, codebook_loss=25.72, over 7301.00 frames.], tot_loss[loss=2.693, simple_loss=0.3583, pruned_loss=6.617, codebook_loss=25.14, over 1304119.04 frames.], batch size: 18, lr: 2.77e-03
+2022-05-27 14:30:52,966 INFO [train.py:823] (3/4) Epoch 3, batch 550, loss[loss=2.632, simple_loss=0.383, pruned_loss=6.731, codebook_loss=24.4, over 7180.00 frames.], tot_loss[loss=2.68, simple_loss=0.3585, pruned_loss=6.627, codebook_loss=25.01, over 1332772.79 frames.], batch size: 21, lr: 2.77e-03
+2022-05-27 14:31:32,958 INFO [train.py:823] (3/4) Epoch 3, batch 600, loss[loss=2.606, simple_loss=0.347, pruned_loss=6.691, codebook_loss=24.32, over 7381.00 frames.], tot_loss[loss=2.674, simple_loss=0.3553, pruned_loss=6.625, codebook_loss=24.96, over 1345669.07 frames.], batch size: 20, lr: 2.76e-03
+2022-05-27 14:32:13,212 INFO [train.py:823] (3/4) Epoch 3, batch 650, loss[loss=2.744, simple_loss=0.387, pruned_loss=6.62, codebook_loss=25.5, over 5170.00 frames.], tot_loss[loss=2.665, simple_loss=0.3547, pruned_loss=6.631, codebook_loss=24.87, over 1362793.28 frames.], batch size: 48, lr: 2.76e-03
+2022-05-27 14:32:52,994 INFO [train.py:823] (3/4) Epoch 3, batch 700, loss[loss=2.597, simple_loss=0.3669, pruned_loss=6.667, codebook_loss=24.14, over 7291.00 frames.], tot_loss[loss=2.657, simple_loss=0.3524, pruned_loss=6.625, codebook_loss=24.81, over 1375342.83 frames.], batch size: 22, lr: 2.75e-03
+2022-05-27 14:33:33,467 INFO [train.py:823] (3/4) Epoch 3, batch 750, loss[loss=2.574, simple_loss=0.3497, pruned_loss=6.697, codebook_loss=23.99, over 7220.00 frames.], tot_loss[loss=2.647, simple_loss=0.3511, pruned_loss=6.625, codebook_loss=24.71, over 1383430.35 frames.], batch size: 19, lr: 2.75e-03
+2022-05-27 14:34:13,286 INFO [train.py:823] (3/4) Epoch 3, batch 800, loss[loss=2.811, simple_loss=0.4508, pruned_loss=6.778, codebook_loss=25.86, over 7419.00 frames.], tot_loss[loss=2.642, simple_loss=0.3516, pruned_loss=6.628, codebook_loss=24.66, over 1393435.05 frames.], batch size: 22, lr: 2.74e-03
+2022-05-27 14:34:53,235 INFO [train.py:823] (3/4) Epoch 3, batch 850, loss[loss=2.537, simple_loss=0.3379, pruned_loss=6.632, codebook_loss=23.68, over 7094.00 frames.], tot_loss[loss=2.644, simple_loss=0.3508, pruned_loss=6.626, codebook_loss=24.68, over 1395895.99 frames.], batch size: 19, lr: 2.74e-03
+2022-05-27 14:35:32,648 INFO [train.py:823] (3/4) Epoch 3, batch 900, loss[loss=2.637, simple_loss=0.356, pruned_loss=6.692, codebook_loss=24.59, over 5249.00 frames.], tot_loss[loss=2.64, simple_loss=0.3502, pruned_loss=6.633, codebook_loss=24.65, over 1393089.78 frames.], batch size: 47, lr: 2.73e-03
+2022-05-27 14:36:26,054 INFO [train.py:823] (3/4) Epoch 4, batch 0, loss[loss=2.464, simple_loss=0.2981, pruned_loss=6.595, codebook_loss=23.15, over 7100.00 frames.], tot_loss[loss=2.464, simple_loss=0.2981, pruned_loss=6.595, codebook_loss=23.15, over 7100.00 frames.], batch size: 19, lr: 2.64e-03
+2022-05-27 14:37:06,178 INFO [train.py:823] (3/4) Epoch 4, batch 50, loss[loss=2.494, simple_loss=0.2769, pruned_loss=6.401, codebook_loss=23.55, over 7019.00 frames.], tot_loss[loss=2.559, simple_loss=0.3242, pruned_loss=6.602, codebook_loss=23.97, over 319738.31 frames.], batch size: 17, lr: 2.64e-03
+2022-05-27 14:37:46,125 INFO [train.py:823] (3/4) Epoch 4, batch 100, loss[loss=2.542, simple_loss=0.3757, pruned_loss=6.767, codebook_loss=23.54, over 7378.00 frames.], tot_loss[loss=2.562, simple_loss=0.3289, pruned_loss=6.624, codebook_loss=23.97, over 565049.83 frames.], batch size: 21, lr: 2.63e-03
+2022-05-27 14:38:25,737 INFO [train.py:823] (3/4) Epoch 4, batch 150, loss[loss=2.638, simple_loss=0.3456, pruned_loss=6.561, codebook_loss=24.65, over 7163.00 frames.], tot_loss[loss=2.571, simple_loss=0.3313, pruned_loss=6.635, codebook_loss=24.05, over 751625.30 frames.], batch size: 17, lr: 2.63e-03
+2022-05-27 14:39:07,320 INFO [train.py:823] (3/4) Epoch 4, batch 200, loss[loss=2.557, simple_loss=0.2947, pruned_loss=0.9031, codebook_loss=23.2, over 7186.00 frames.], tot_loss[loss=2.662, simple_loss=0.3429, pruned_loss=4.806, codebook_loss=24.03, over 903849.80 frames.], batch size: 18, lr: 2.62e-03
+2022-05-27 14:39:46,951 INFO [train.py:823] (3/4) Epoch 4, batch 250, loss[loss=2.748, simple_loss=0.3657, pruned_loss=0.6972, codebook_loss=24.95, over 7376.00 frames.], tot_loss[loss=2.663, simple_loss=0.3412, pruned_loss=3.568, codebook_loss=24.06, over 1022500.21 frames.], batch size: 21, lr: 2.62e-03
+2022-05-27 14:40:29,642 INFO [train.py:823] (3/4) Epoch 4, batch 300, loss[loss=2.619, simple_loss=0.3552, pruned_loss=0.4303, codebook_loss=23.98, over 7197.00 frames.], tot_loss[loss=2.649, simple_loss=0.3403, pruned_loss=2.707, codebook_loss=24.03, over 1108406.27 frames.], batch size: 20, lr: 2.61e-03
+2022-05-27 14:41:09,189 INFO [train.py:823] (3/4) Epoch 4, batch 350, loss[loss=2.681, simple_loss=0.3712, pruned_loss=0.3337, codebook_loss=24.62, over 7146.00 frames.], tot_loss[loss=2.633, simple_loss=0.3392, pruned_loss=2.08, codebook_loss=23.98, over 1172561.77 frames.], batch size: 23, lr: 2.60e-03
+2022-05-27 14:41:49,190 INFO [train.py:823] (3/4) Epoch 4, batch 400, loss[loss=2.564, simple_loss=0.3538, pruned_loss=0.2375, codebook_loss=23.63, over 7213.00 frames.], tot_loss[loss=2.624, simple_loss=0.3381, pruned_loss=1.611, codebook_loss=24, over 1225880.67 frames.], batch size: 25, lr: 2.60e-03
+2022-05-27 14:42:28,856 INFO [train.py:823] (3/4) Epoch 4, batch 450, loss[loss=2.479, simple_loss=0.2961, pruned_loss=0.1557, codebook_loss=23.16, over 7151.00 frames.], tot_loss[loss=2.611, simple_loss=0.3369, pruned_loss=1.264, codebook_loss=23.96, over 1268208.90 frames.], batch size: 17, lr: 2.59e-03
+2022-05-27 14:43:08,814 INFO [train.py:823] (3/4) Epoch 4, batch 500, loss[loss=2.473, simple_loss=0.3308, pruned_loss=0.162, codebook_loss=22.91, over 7239.00 frames.], tot_loss[loss=2.597, simple_loss=0.3372, pruned_loss=1.003, codebook_loss=23.89, over 1304437.58 frames.], batch size: 25, lr: 2.59e-03
+2022-05-27 14:43:48,395 INFO [train.py:823] (3/4) Epoch 4, batch 550, loss[loss=2.597, simple_loss=0.3163, pruned_loss=0.1627, codebook_loss=24.23, over 7393.00 frames.], tot_loss[loss=2.587, simple_loss=0.3347, pruned_loss=0.8047, codebook_loss=23.85, over 1331958.26 frames.], batch size: 19, lr: 2.58e-03
+2022-05-27 14:44:28,571 INFO [train.py:823] (3/4) Epoch 4, batch 600, loss[loss=2.608, simple_loss=0.3556, pruned_loss=0.1802, codebook_loss=24.12, over 7181.00 frames.], tot_loss[loss=2.577, simple_loss=0.3341, pruned_loss=0.6541, codebook_loss=23.8, over 1354207.18 frames.], batch size: 21, lr: 2.57e-03
+2022-05-27 14:45:08,627 INFO [train.py:823] (3/4) Epoch 4, batch 650, loss[loss=2.465, simple_loss=0.3093, pruned_loss=0.1428, codebook_loss=22.96, over 7370.00 frames.], tot_loss[loss=2.564, simple_loss=0.3318, pruned_loss=0.5378, codebook_loss=23.71, over 1369919.11 frames.], batch size: 20, lr: 2.57e-03
+2022-05-27 14:45:48,454 INFO [train.py:823] (3/4) Epoch 4, batch 700, loss[loss=2.687, simple_loss=0.3551, pruned_loss=0.1869, codebook_loss=24.91, over 4621.00 frames.], tot_loss[loss=2.568, simple_loss=0.334, pruned_loss=0.4529, codebook_loss=23.76, over 1375803.70 frames.], batch size: 47, lr: 2.56e-03
+2022-05-27 14:46:28,093 INFO [train.py:823] (3/4) Epoch 4, batch 750, loss[loss=2.489, simple_loss=0.3199, pruned_loss=0.1404, codebook_loss=23.15, over 7104.00 frames.], tot_loss[loss=2.571, simple_loss=0.3333, pruned_loss=0.3845, codebook_loss=23.82, over 1384215.45 frames.], batch size: 19, lr: 2.56e-03
+2022-05-27 14:47:08,127 INFO [train.py:823] (3/4) Epoch 4, batch 800, loss[loss=2.453, simple_loss=0.2953, pruned_loss=0.1013, codebook_loss=22.95, over 7032.00 frames.], tot_loss[loss=2.565, simple_loss=0.3325, pruned_loss=0.331, codebook_loss=23.78, over 1385858.75 frames.], batch size: 17, lr: 2.55e-03
+2022-05-27 14:47:47,741 INFO [train.py:823] (3/4) Epoch 4, batch 850, loss[loss=2.504, simple_loss=0.3286, pruned_loss=0.1365, codebook_loss=23.27, over 7300.00 frames.], tot_loss[loss=2.564, simple_loss=0.3326, pruned_loss=0.2889, codebook_loss=23.79, over 1391874.54 frames.], batch size: 22, lr: 2.54e-03
+2022-05-27 14:48:27,891 INFO [train.py:823] (3/4) Epoch 4, batch 900, loss[loss=2.48, simple_loss=0.2876, pruned_loss=0.0909, codebook_loss=23.28, over 7188.00 frames.], tot_loss[loss=2.562, simple_loss=0.3312, pruned_loss=0.2559, codebook_loss=23.78, over 1388604.74 frames.], batch size: 18, lr: 2.54e-03
+2022-05-27 14:49:21,903 INFO [train.py:823] (3/4) Epoch 5, batch 0, loss[loss=2.363, simple_loss=0.332, pruned_loss=0.122, codebook_loss=21.85, over 7343.00 frames.], tot_loss[loss=2.363, simple_loss=0.332, pruned_loss=0.122, codebook_loss=21.85, over 7343.00 frames.], batch size: 23, lr: 2.44e-03
+2022-05-27 14:50:02,127 INFO [train.py:823] (3/4) Epoch 5, batch 50, loss[loss=2.393, simple_loss=0.295, pruned_loss=0.096, codebook_loss=22.36, over 6987.00 frames.], tot_loss[loss=2.509, simple_loss=0.3213, pruned_loss=0.1287, codebook_loss=23.35, over 326408.56 frames.], batch size: 26, lr: 2.44e-03
+2022-05-27 14:50:41,834 INFO [train.py:823] (3/4) Epoch 5, batch 100, loss[loss=2.519, simple_loss=0.3314, pruned_loss=0.1426, codebook_loss=23.39, over 7114.00 frames.], tot_loss[loss=2.495, simple_loss=0.319, pruned_loss=0.1235, codebook_loss=23.23, over 570754.53 frames.], batch size: 20, lr: 2.43e-03
+2022-05-27 14:51:21,918 INFO [train.py:823] (3/4) Epoch 5, batch 150, loss[loss=2.503, simple_loss=0.3216, pruned_loss=0.1218, codebook_loss=23.31, over 7372.00 frames.], tot_loss[loss=2.512, simple_loss=0.3179, pruned_loss=0.1232, codebook_loss=23.4, over 758784.07 frames.], batch size: 20, lr: 2.42e-03
+2022-05-27 14:52:01,342 INFO [train.py:823] (3/4) Epoch 5, batch 200, loss[loss=2.585, simple_loss=0.3779, pruned_loss=0.1584, codebook_loss=23.8, over 7190.00 frames.], tot_loss[loss=2.515, simple_loss=0.3204, pruned_loss=0.1248, codebook_loss=23.42, over 905035.96 frames.], batch size: 22, lr: 2.42e-03
+2022-05-27 14:52:41,367 INFO [train.py:823] (3/4) Epoch 5, batch 250, loss[loss=2.494, simple_loss=0.3367, pruned_loss=0.1441, codebook_loss=23.11, over 4485.00 frames.], tot_loss[loss=2.515, simple_loss=0.3209, pruned_loss=0.1256, codebook_loss=23.42, over 1012272.04 frames.], batch size: 47, lr: 2.41e-03
+2022-05-27 14:53:20,952 INFO [train.py:823] (3/4) Epoch 5, batch 300, loss[loss=2.565, simple_loss=0.3601, pruned_loss=0.1645, codebook_loss=23.68, over 7148.00 frames.], tot_loss[loss=2.51, simple_loss=0.3215, pruned_loss=0.1238, codebook_loss=23.37, over 1103412.50 frames.], batch size: 23, lr: 2.41e-03
+2022-05-27 14:54:00,912 INFO [train.py:823] (3/4) Epoch 5, batch 350, loss[loss=2.458, simple_loss=0.3536, pruned_loss=0.1249, codebook_loss=22.69, over 7237.00 frames.], tot_loss[loss=2.506, simple_loss=0.3203, pruned_loss=0.1216, codebook_loss=23.34, over 1173855.80 frames.], batch size: 24, lr: 2.40e-03
+2022-05-27 14:54:40,916 INFO [train.py:823] (3/4) Epoch 5, batch 400, loss[loss=2.628, simple_loss=0.2902, pruned_loss=0.1145, codebook_loss=24.72, over 7441.00 frames.], tot_loss[loss=2.5, simple_loss=0.3193, pruned_loss=0.1201, codebook_loss=23.28, over 1233372.86 frames.], batch size: 18, lr: 2.39e-03
+2022-05-27 14:55:20,867 INFO [train.py:823] (3/4) Epoch 5, batch 450, loss[loss=2.376, simple_loss=0.3126, pruned_loss=0.09603, codebook_loss=22.1, over 7041.00 frames.], tot_loss[loss=2.495, simple_loss=0.3197, pruned_loss=0.1193, codebook_loss=23.23, over 1268872.25 frames.], batch size: 26, lr: 2.39e-03
+2022-05-27 14:56:00,505 INFO [train.py:823] (3/4) Epoch 5, batch 500, loss[loss=2.415, simple_loss=0.2932, pruned_loss=0.09952, codebook_loss=22.59, over 7187.00 frames.], tot_loss[loss=2.491, simple_loss=0.3187, pruned_loss=0.118, codebook_loss=23.2, over 1303888.56 frames.], batch size: 19, lr: 2.38e-03
+2022-05-27 14:56:40,388 INFO [train.py:823] (3/4) Epoch 5, batch 550, loss[loss=2.556, simple_loss=0.3543, pruned_loss=0.1399, codebook_loss=23.65, over 6938.00 frames.], tot_loss[loss=2.486, simple_loss=0.3176, pruned_loss=0.1169, codebook_loss=23.16, over 1329293.81 frames.], batch size: 29, lr: 2.38e-03
+2022-05-27 14:57:20,185 INFO [train.py:823] (3/4) Epoch 5, batch 600, loss[loss=2.471, simple_loss=0.3314, pruned_loss=0.1103, codebook_loss=22.94, over 6534.00 frames.], tot_loss[loss=2.483, simple_loss=0.3171, pruned_loss=0.1155, codebook_loss=23.12, over 1348238.86 frames.], batch size: 34, lr: 2.37e-03
+2022-05-27 14:58:00,322 INFO [train.py:823] (3/4) Epoch 5, batch 650, loss[loss=2.454, simple_loss=0.3408, pruned_loss=0.1205, codebook_loss=22.72, over 7287.00 frames.], tot_loss[loss=2.484, simple_loss=0.3171, pruned_loss=0.1156, codebook_loss=23.14, over 1363649.51 frames.], batch size: 21, lr: 2.37e-03
+2022-05-27 14:58:39,919 INFO [train.py:823] (3/4) Epoch 5, batch 700, loss[loss=2.405, simple_loss=0.3178, pruned_loss=0.107, codebook_loss=22.36, over 7008.00 frames.], tot_loss[loss=2.483, simple_loss=0.3171, pruned_loss=0.1149, codebook_loss=23.13, over 1372859.12 frames.], batch size: 26, lr: 2.36e-03
+2022-05-27 14:59:19,733 INFO [train.py:823] (3/4) Epoch 5, batch 750, loss[loss=2.485, simple_loss=0.3384, pruned_loss=0.1268, codebook_loss=23.04, over 7144.00 frames.], tot_loss[loss=2.482, simple_loss=0.3181, pruned_loss=0.1147, codebook_loss=23.11, over 1381295.10 frames.], batch size: 23, lr: 2.35e-03
+2022-05-27 14:59:59,676 INFO [train.py:823] (3/4) Epoch 5, batch 800, loss[loss=2.398, simple_loss=0.3142, pruned_loss=0.1012, codebook_loss=22.31, over 4870.00 frames.], tot_loss[loss=2.476, simple_loss=0.3169, pruned_loss=0.1128, codebook_loss=23.06, over 1391093.48 frames.], batch size: 47, lr: 2.35e-03
+2022-05-27 15:00:39,941 INFO [train.py:823] (3/4) Epoch 5, batch 850, loss[loss=2.356, simple_loss=0.2866, pruned_loss=0.09259, codebook_loss=22.03, over 7144.00 frames.], tot_loss[loss=2.468, simple_loss=0.315, pruned_loss=0.1108, codebook_loss=23, over 1396734.11 frames.], batch size: 17, lr: 2.34e-03
+2022-05-27 15:01:19,749 INFO [train.py:823] (3/4) Epoch 5, batch 900, loss[loss=2.539, simple_loss=0.3347, pruned_loss=0.1146, codebook_loss=23.6, over 6950.00 frames.], tot_loss[loss=2.465, simple_loss=0.3143, pruned_loss=0.1097, codebook_loss=22.97, over 1399130.57 frames.], batch size: 29, lr: 2.34e-03
+2022-05-27 15:02:14,638 INFO [train.py:823] (3/4) Epoch 6, batch 0, loss[loss=2.507, simple_loss=0.3272, pruned_loss=0.1053, codebook_loss=23.32, over 7176.00 frames.], tot_loss[loss=2.507, simple_loss=0.3272, pruned_loss=0.1053, codebook_loss=23.32, over 7176.00 frames.], batch size: 22, lr: 2.24e-03
+2022-05-27 15:02:54,283 INFO [train.py:823] (3/4) Epoch 6, batch 50, loss[loss=2.469, simple_loss=0.3242, pruned_loss=0.09653, codebook_loss=22.97, over 7170.00 frames.], tot_loss[loss=2.437, simple_loss=0.3124, pruned_loss=0.1019, codebook_loss=22.7, over 318579.50 frames.], batch size: 21, lr: 2.23e-03
+2022-05-27 15:03:35,014 INFO [train.py:823] (3/4) Epoch 6, batch 100, loss[loss=2.367, simple_loss=0.3025, pruned_loss=0.09031, codebook_loss=22.07, over 7237.00 frames.], tot_loss[loss=2.427, simple_loss=0.3056, pruned_loss=0.09821, codebook_loss=22.64, over 565522.97 frames.], batch size: 24, lr: 2.23e-03
+2022-05-27 15:04:14,720 INFO [train.py:823] (3/4) Epoch 6, batch 150, loss[loss=2.331, simple_loss=0.3037, pruned_loss=0.09034, codebook_loss=21.7, over 7295.00 frames.], tot_loss[loss=2.428, simple_loss=0.3057, pruned_loss=0.09755, codebook_loss=22.65, over 754874.04 frames.], batch size: 19, lr: 2.22e-03
+2022-05-27 15:04:56,279 INFO [train.py:823] (3/4) Epoch 6, batch 200, loss[loss=2.429, simple_loss=0.3185, pruned_loss=0.1008, codebook_loss=22.59, over 7205.00 frames.], tot_loss[loss=2.431, simple_loss=0.3053, pruned_loss=0.0973, codebook_loss=22.69, over 900503.61 frames.], batch size: 25, lr: 2.22e-03
+2022-05-27 15:05:38,510 INFO [train.py:823] (3/4) Epoch 6, batch 250, loss[loss=2.563, simple_loss=0.3119, pruned_loss=0.1087, codebook_loss=23.96, over 6602.00 frames.], tot_loss[loss=2.435, simple_loss=0.3073, pruned_loss=0.09881, codebook_loss=22.72, over 1016955.04 frames.], batch size: 34, lr: 2.21e-03
+2022-05-27 15:06:18,629 INFO [train.py:823] (3/4) Epoch 6, batch 300, loss[loss=2.379, simple_loss=0.3143, pruned_loss=0.08585, codebook_loss=22.13, over 7201.00 frames.], tot_loss[loss=2.43, simple_loss=0.3075, pruned_loss=0.09834, codebook_loss=22.67, over 1107411.56 frames.], batch size: 20, lr: 2.21e-03
+2022-05-27 15:06:58,750 INFO [train.py:823] (3/4) Epoch 6, batch 350, loss[loss=2.34, simple_loss=0.2712, pruned_loss=0.07189, codebook_loss=21.97, over 7091.00 frames.], tot_loss[loss=2.429, simple_loss=0.307, pruned_loss=0.09794, codebook_loss=22.65, over 1178301.96 frames.], batch size: 18, lr: 2.20e-03
+2022-05-27 15:07:39,167 INFO [train.py:823] (3/4) Epoch 6, batch 400, loss[loss=2.417, simple_loss=0.3093, pruned_loss=0.09819, codebook_loss=22.52, over 7177.00 frames.], tot_loss[loss=2.421, simple_loss=0.3048, pruned_loss=0.09637, codebook_loss=22.59, over 1234911.80 frames.], batch size: 22, lr: 2.19e-03
+2022-05-27 15:08:18,972 INFO [train.py:823] (3/4) Epoch 6, batch 450, loss[loss=2.404, simple_loss=0.3155, pruned_loss=0.09351, codebook_loss=22.37, over 6728.00 frames.], tot_loss[loss=2.423, simple_loss=0.305, pruned_loss=0.09665, codebook_loss=22.61, over 1267775.23 frames.], batch size: 34, lr: 2.19e-03
+2022-05-27 15:08:59,165 INFO [train.py:823] (3/4) Epoch 6, batch 500, loss[loss=2.506, simple_loss=0.3419, pruned_loss=0.117, codebook_loss=23.23, over 7146.00 frames.], tot_loss[loss=2.434, simple_loss=0.3068, pruned_loss=0.0983, codebook_loss=22.71, over 1298292.52 frames.], batch size: 23, lr: 2.18e-03
+2022-05-27 15:09:39,081 INFO [train.py:823] (3/4) Epoch 6, batch 550, loss[loss=2.238, simple_loss=0.2722, pruned_loss=0.06534, codebook_loss=20.95, over 7094.00 frames.], tot_loss[loss=2.432, simple_loss=0.3074, pruned_loss=0.09808, codebook_loss=22.68, over 1325533.12 frames.], batch size: 18, lr: 2.18e-03
+2022-05-27 15:10:19,163 INFO [train.py:823] (3/4) Epoch 6, batch 600, loss[loss=2.388, simple_loss=0.3108, pruned_loss=0.08998, codebook_loss=22.24, over 7094.00 frames.], tot_loss[loss=2.431, simple_loss=0.307, pruned_loss=0.09807, codebook_loss=22.68, over 1343796.35 frames.], batch size: 18, lr: 2.17e-03
+2022-05-27 15:10:58,927 INFO [train.py:823] (3/4) Epoch 6, batch 650, loss[loss=2.395, simple_loss=0.3012, pruned_loss=0.0935, codebook_loss=22.35, over 7384.00 frames.], tot_loss[loss=2.431, simple_loss=0.3063, pruned_loss=0.09753, codebook_loss=22.68, over 1361719.80 frames.], batch size: 19, lr: 2.17e-03
+2022-05-27 15:11:39,185 INFO [train.py:823] (3/4) Epoch 6, batch 700, loss[loss=2.308, simple_loss=0.2886, pruned_loss=0.07625, codebook_loss=21.56, over 7192.00 frames.], tot_loss[loss=2.427, simple_loss=0.3064, pruned_loss=0.09719, codebook_loss=22.64, over 1376338.36 frames.], batch size: 19, lr: 2.16e-03
+2022-05-27 15:12:18,885 INFO [train.py:823] (3/4) Epoch 6, batch 750, loss[loss=2.285, simple_loss=0.268, pruned_loss=0.06649, codebook_loss=21.45, over 7096.00 frames.], tot_loss[loss=2.427, simple_loss=0.3063, pruned_loss=0.09639, codebook_loss=22.65, over 1384482.76 frames.], batch size: 19, lr: 2.16e-03
+2022-05-27 15:12:59,163 INFO [train.py:823] (3/4) Epoch 6, batch 800, loss[loss=2.457, simple_loss=0.2796, pruned_loss=0.09611, codebook_loss=23.07, over 7013.00 frames.], tot_loss[loss=2.422, simple_loss=0.305, pruned_loss=0.09559, codebook_loss=22.6, over 1390764.59 frames.], batch size: 16, lr: 2.15e-03
+2022-05-27 15:13:39,134 INFO [train.py:823] (3/4) Epoch 6, batch 850, loss[loss=2.45, simple_loss=0.3024, pruned_loss=0.1063, codebook_loss=22.88, over 7215.00 frames.], tot_loss[loss=2.43, simple_loss=0.3046, pruned_loss=0.09599, codebook_loss=22.68, over 1394444.71 frames.], batch size: 16, lr: 2.15e-03
+2022-05-27 15:14:19,248 INFO [train.py:823] (3/4) Epoch 6, batch 900, loss[loss=2.346, simple_loss=0.2808, pruned_loss=0.07607, codebook_loss=21.98, over 7298.00 frames.], tot_loss[loss=2.422, simple_loss=0.3031, pruned_loss=0.09399, codebook_loss=22.62, over 1397524.58 frames.], batch size: 17, lr: 2.14e-03
+2022-05-27 15:15:12,729 INFO [train.py:823] (3/4) Epoch 7, batch 0, loss[loss=2.273, simple_loss=0.2678, pruned_loss=0.06686, codebook_loss=21.33, over 7106.00 frames.], tot_loss[loss=2.273, simple_loss=0.2678, pruned_loss=0.06686, codebook_loss=21.33, over 7106.00 frames.], batch size: 19, lr: 2.05e-03
+2022-05-27 15:15:52,757 INFO [train.py:823] (3/4) Epoch 7, batch 50, loss[loss=2.328, simple_loss=0.2493, pruned_loss=0.06776, codebook_loss=21.96, over 7264.00 frames.], tot_loss[loss=2.402, simple_loss=0.2968, pruned_loss=0.08873, codebook_loss=22.44, over 322826.00 frames.], batch size: 16, lr: 2.04e-03
+2022-05-27 15:16:32,384 INFO [train.py:823] (3/4) Epoch 7, batch 100, loss[loss=2.302, simple_loss=0.2834, pruned_loss=0.07397, codebook_loss=21.53, over 7115.00 frames.], tot_loss[loss=2.378, simple_loss=0.2929, pruned_loss=0.08524, codebook_loss=22.23, over 562833.18 frames.], batch size: 20, lr: 2.04e-03
+2022-05-27 15:17:12,521 INFO [train.py:823] (3/4) Epoch 7, batch 150, loss[loss=2.454, simple_loss=0.2866, pruned_loss=0.08369, codebook_loss=23.03, over 7369.00 frames.], tot_loss[loss=2.391, simple_loss=0.2961, pruned_loss=0.08784, codebook_loss=22.34, over 753380.26 frames.], batch size: 21, lr: 2.03e-03
+2022-05-27 15:17:52,354 INFO [train.py:823] (3/4) Epoch 7, batch 200, loss[loss=2.542, simple_loss=0.2948, pruned_loss=0.08704, codebook_loss=23.85, over 7017.00 frames.], tot_loss[loss=2.384, simple_loss=0.2953, pruned_loss=0.08592, codebook_loss=22.28, over 904854.02 frames.], batch size: 26, lr: 2.03e-03
+2022-05-27 15:18:32,533 INFO [train.py:823] (3/4) Epoch 7, batch 250, loss[loss=2.475, simple_loss=0.2892, pruned_loss=0.06985, codebook_loss=23.24, over 7285.00 frames.], tot_loss[loss=2.385, simple_loss=0.2959, pruned_loss=0.08682, codebook_loss=22.29, over 1019747.30 frames.], batch size: 22, lr: 2.02e-03
+2022-05-27 15:19:12,244 INFO [train.py:823] (3/4) Epoch 7, batch 300, loss[loss=2.373, simple_loss=0.2698, pruned_loss=0.07664, codebook_loss=22.31, over 7153.00 frames.], tot_loss[loss=2.388, simple_loss=0.2971, pruned_loss=0.08748, codebook_loss=22.3, over 1108392.18 frames.], batch size: 17, lr: 2.02e-03
+2022-05-27 15:19:52,537 INFO [train.py:823] (3/4) Epoch 7, batch 350, loss[loss=2.53, simple_loss=0.3255, pruned_loss=0.1085, codebook_loss=22.58, over 7301.00 frames.], tot_loss[loss=2.422, simple_loss=0.2995, pruned_loss=0.09031, codebook_loss=22.4, over 1175452.57 frames.], batch size: 19, lr: 2.01e-03
+2022-05-27 15:20:32,264 INFO [train.py:823] (3/4) Epoch 7, batch 400, loss[loss=2.418, simple_loss=0.3368, pruned_loss=0.09969, codebook_loss=21.5, over 7342.00 frames.], tot_loss[loss=2.442, simple_loss=0.3014, pruned_loss=0.09159, codebook_loss=22.43, over 1229721.06 frames.], batch size: 23, lr: 2.01e-03
+2022-05-27 15:21:12,307 INFO [train.py:823] (3/4) Epoch 7, batch 450, loss[loss=2.41, simple_loss=0.32, pruned_loss=0.0843, codebook_loss=21.65, over 7176.00 frames.], tot_loss[loss=2.448, simple_loss=0.3022, pruned_loss=0.09143, codebook_loss=22.38, over 1268036.93 frames.], batch size: 22, lr: 2.00e-03
+2022-05-27 15:21:52,025 INFO [train.py:823] (3/4) Epoch 7, batch 500, loss[loss=2.849, simple_loss=0.3368, pruned_loss=0.1243, codebook_loss=25.56, over 6983.00 frames.], tot_loss[loss=2.454, simple_loss=0.3022, pruned_loss=0.09035, codebook_loss=22.37, over 1302377.92 frames.], batch size: 26, lr: 2.00e-03
+2022-05-27 15:22:32,333 INFO [train.py:823] (3/4) Epoch 7, batch 550, loss[loss=2.445, simple_loss=0.2947, pruned_loss=0.07025, codebook_loss=22.27, over 6624.00 frames.], tot_loss[loss=2.456, simple_loss=0.3011, pruned_loss=0.08901, codebook_loss=22.36, over 1326561.35 frames.], batch size: 35, lr: 1.99e-03
+2022-05-27 15:23:12,066 INFO [train.py:823] (3/4) Epoch 7, batch 600, loss[loss=2.384, simple_loss=0.3042, pruned_loss=0.07803, codebook_loss=21.54, over 7375.00 frames.], tot_loss[loss=2.47, simple_loss=0.3022, pruned_loss=0.08928, codebook_loss=22.44, over 1344356.52 frames.], batch size: 21, lr: 1.99e-03
+2022-05-27 15:23:52,224 INFO [train.py:823] (3/4) Epoch 7, batch 650, loss[loss=2.499, simple_loss=0.327, pruned_loss=0.09883, codebook_loss=22.37, over 7111.00 frames.], tot_loss[loss=2.468, simple_loss=0.3014, pruned_loss=0.08779, codebook_loss=22.41, over 1360638.16 frames.], batch size: 20, lr: 1.98e-03
+2022-05-27 15:24:32,096 INFO [train.py:823] (3/4) Epoch 7, batch 700, loss[loss=2.422, simple_loss=0.2886, pruned_loss=0.07558, codebook_loss=22.02, over 7102.00 frames.], tot_loss[loss=2.473, simple_loss=0.3029, pruned_loss=0.08837, codebook_loss=22.42, over 1369876.03 frames.], batch size: 18, lr: 1.98e-03
+2022-05-27 15:25:12,102 INFO [train.py:823] (3/4) Epoch 7, batch 750, loss[loss=2.512, simple_loss=0.3174, pruned_loss=0.1033, codebook_loss=22.5, over 6995.00 frames.], tot_loss[loss=2.474, simple_loss=0.3026, pruned_loss=0.08789, codebook_loss=22.41, over 1377658.05 frames.], batch size: 26, lr: 1.97e-03
+2022-05-27 15:25:51,518 INFO [train.py:823] (3/4) Epoch 7, batch 800, loss[loss=2.391, simple_loss=0.2796, pruned_loss=0.06276, codebook_loss=21.89, over 7190.00 frames.], tot_loss[loss=2.468, simple_loss=0.3028, pruned_loss=0.08704, codebook_loss=22.35, over 1386934.11 frames.], batch size: 19, lr: 1.97e-03
+2022-05-27 15:26:31,117 INFO [train.py:823] (3/4) Epoch 7, batch 850, loss[loss=2.5, simple_loss=0.3383, pruned_loss=0.09806, codebook_loss=22.33, over 7372.00 frames.], tot_loss[loss=2.472, simple_loss=0.3048, pruned_loss=0.08765, codebook_loss=22.35, over 1388010.37 frames.], batch size: 21, lr: 1.97e-03
+2022-05-27 15:27:11,912 INFO [train.py:823] (3/4) Epoch 7, batch 900, loss[loss=2.444, simple_loss=0.3272, pruned_loss=0.09306, codebook_loss=21.87, over 6913.00 frames.], tot_loss[loss=2.458, simple_loss=0.3031, pruned_loss=0.08585, codebook_loss=22.24, over 1390435.73 frames.], batch size: 29, lr: 1.96e-03
+2022-05-27 15:28:02,635 INFO [train.py:823] (3/4) Epoch 8, batch 0, loss[loss=2.311, simple_loss=0.2881, pruned_loss=0.0639, codebook_loss=21.03, over 7416.00 frames.], tot_loss[loss=2.311, simple_loss=0.2881, pruned_loss=0.0639, codebook_loss=21.03, over 7416.00 frames.], batch size: 22, lr: 1.88e-03
+2022-05-27 15:28:42,306 INFO [train.py:823] (3/4) Epoch 8, batch 50, loss[loss=2.44, simple_loss=0.3224, pruned_loss=0.086, codebook_loss=21.93, over 7238.00 frames.], tot_loss[loss=2.394, simple_loss=0.2963, pruned_loss=0.07482, codebook_loss=21.71, over 320843.21 frames.], batch size: 24, lr: 1.87e-03
+2022-05-27 15:29:23,685 INFO [train.py:823] (3/4) Epoch 8, batch 100, loss[loss=2.57, simple_loss=0.2974, pruned_loss=0.08991, codebook_loss=23.31, over 7030.00 frames.], tot_loss[loss=2.418, simple_loss=0.2986, pruned_loss=0.0776, codebook_loss=21.91, over 565330.38 frames.], batch size: 17, lr: 1.87e-03
+2022-05-27 15:30:05,851 INFO [train.py:823] (3/4) Epoch 8, batch 150, loss[loss=2.447, simple_loss=0.3123, pruned_loss=0.07911, codebook_loss=22.12, over 7277.00 frames.], tot_loss[loss=2.424, simple_loss=0.2985, pruned_loss=0.07779, codebook_loss=21.97, over 754033.82 frames.], batch size: 20, lr: 1.86e-03
+2022-05-27 15:30:45,998 INFO [train.py:823] (3/4) Epoch 8, batch 200, loss[loss=2.418, simple_loss=0.2881, pruned_loss=0.07433, codebook_loss=21.99, over 7009.00 frames.], tot_loss[loss=2.42, simple_loss=0.2977, pruned_loss=0.07709, codebook_loss=21.94, over 899741.48 frames.], batch size: 16, lr: 1.86e-03
+2022-05-27 15:31:25,750 INFO [train.py:823] (3/4) Epoch 8, batch 250, loss[loss=2.435, simple_loss=0.3225, pruned_loss=0.08148, codebook_loss=21.93, over 7153.00 frames.], tot_loss[loss=2.419, simple_loss=0.2958, pruned_loss=0.07653, codebook_loss=21.95, over 1013712.26 frames.], batch size: 23, lr: 1.85e-03
+2022-05-27 15:32:06,063 INFO [train.py:823] (3/4) Epoch 8, batch 300, loss[loss=2.493, simple_loss=0.2939, pruned_loss=0.08506, codebook_loss=22.61, over 7387.00 frames.], tot_loss[loss=2.414, simple_loss=0.2953, pruned_loss=0.07589, codebook_loss=21.91, over 1106028.30 frames.], batch size: 19, lr: 1.85e-03
+2022-05-27 15:32:45,541 INFO [train.py:823] (3/4) Epoch 8, batch 350, loss[loss=2.341, simple_loss=0.2644, pruned_loss=0.0621, codebook_loss=21.47, over 6997.00 frames.], tot_loss[loss=2.42, simple_loss=0.2951, pruned_loss=0.07613, codebook_loss=21.96, over 1166664.31 frames.], batch size: 16, lr: 1.85e-03
+2022-05-27 15:33:25,397 INFO [train.py:823] (3/4) Epoch 8, batch 400, loss[loss=2.348, simple_loss=0.3226, pruned_loss=0.08921, codebook_loss=20.98, over 7172.00 frames.], tot_loss[loss=2.427, simple_loss=0.2961, pruned_loss=0.07665, codebook_loss=22.02, over 1222656.52 frames.], batch size: 22, lr: 1.84e-03
+2022-05-27 15:34:05,060 INFO [train.py:823] (3/4) Epoch 8, batch 450, loss[loss=2.922, simple_loss=0.3223, pruned_loss=0.1014, codebook_loss=26.6, over 6566.00 frames.], tot_loss[loss=2.429, simple_loss=0.2968, pruned_loss=0.0771, codebook_loss=22.03, over 1266127.55 frames.], batch size: 34, lr: 1.84e-03
+2022-05-27 15:34:45,233 INFO [train.py:823] (3/4) Epoch 8, batch 500, loss[loss=2.434, simple_loss=0.2656, pruned_loss=0.07159, codebook_loss=22.3, over 7308.00 frames.], tot_loss[loss=2.43, simple_loss=0.2968, pruned_loss=0.07732, codebook_loss=22.04, over 1301651.53 frames.], batch size: 17, lr: 1.83e-03
+2022-05-27 15:35:24,774 INFO [train.py:823] (3/4) Epoch 8, batch 550, loss[loss=2.813, simple_loss=0.3347, pruned_loss=0.09942, codebook_loss=25.46, over 7181.00 frames.], tot_loss[loss=2.431, simple_loss=0.298, pruned_loss=0.07684, codebook_loss=22.05, over 1326271.33 frames.], batch size: 22, lr: 1.83e-03
+2022-05-27 15:36:04,728 INFO [train.py:823] (3/4) Epoch 8, batch 600, loss[loss=2.599, simple_loss=0.3071, pruned_loss=0.08337, codebook_loss=23.62, over 7003.00 frames.], tot_loss[loss=2.437, simple_loss=0.2979, pruned_loss=0.07686, codebook_loss=22.11, over 1343818.00 frames.], batch size: 17, lr: 1.82e-03
+2022-05-27 15:36:44,525 INFO [train.py:823] (3/4) Epoch 8, batch 650, loss[loss=2.376, simple_loss=0.3078, pruned_loss=0.08174, codebook_loss=21.41, over 7015.00 frames.], tot_loss[loss=2.426, simple_loss=0.297, pruned_loss=0.07591, codebook_loss=22.02, over 1361575.18 frames.], batch size: 26, lr: 1.82e-03
+2022-05-27 15:37:24,992 INFO [train.py:823] (3/4) Epoch 8, batch 700, loss[loss=2.721, simple_loss=0.3061, pruned_loss=0.1011, codebook_loss=24.67, over 7290.00 frames.], tot_loss[loss=2.417, simple_loss=0.2968, pruned_loss=0.07541, codebook_loss=21.94, over 1379338.92 frames.], batch size: 19, lr: 1.82e-03
+2022-05-27 15:38:04,512 INFO [train.py:823] (3/4) Epoch 8, batch 750, loss[loss=2.425, simple_loss=0.2816, pruned_loss=0.06938, codebook_loss=22.15, over 7101.00 frames.], tot_loss[loss=2.416, simple_loss=0.2959, pruned_loss=0.07474, codebook_loss=21.94, over 1387055.75 frames.], batch size: 18, lr: 1.81e-03
+2022-05-27 15:38:44,421 INFO [train.py:823] (3/4) Epoch 8, batch 800, loss[loss=2.492, simple_loss=0.311, pruned_loss=0.09597, codebook_loss=22.41, over 4746.00 frames.], tot_loss[loss=2.415, simple_loss=0.2955, pruned_loss=0.07434, codebook_loss=21.93, over 1387897.07 frames.], batch size: 46, lr: 1.81e-03
+2022-05-27 15:39:24,092 INFO [train.py:823] (3/4) Epoch 8, batch 850, loss[loss=2.383, simple_loss=0.2923, pruned_loss=0.07356, codebook_loss=21.64, over 7188.00 frames.], tot_loss[loss=2.419, simple_loss=0.2954, pruned_loss=0.07481, codebook_loss=21.97, over 1390259.63 frames.], batch size: 20, lr: 1.80e-03
+2022-05-27 15:40:04,007 INFO [train.py:823] (3/4) Epoch 8, batch 900, loss[loss=2.38, simple_loss=0.3043, pruned_loss=0.07117, codebook_loss=21.57, over 7089.00 frames.], tot_loss[loss=2.434, simple_loss=0.2974, pruned_loss=0.07649, codebook_loss=22.09, over 1394437.32 frames.], batch size: 18, lr: 1.80e-03
+2022-05-27 15:40:54,934 INFO [train.py:823] (3/4) Epoch 9, batch 0, loss[loss=2.301, simple_loss=0.2949, pruned_loss=0.06037, codebook_loss=20.93, over 7191.00 frames.], tot_loss[loss=2.301, simple_loss=0.2949, pruned_loss=0.06037, codebook_loss=20.93, over 7191.00 frames.], batch size: 21, lr: 1.72e-03
+2022-05-27 15:41:35,082 INFO [train.py:823] (3/4) Epoch 9, batch 50, loss[loss=2.339, simple_loss=0.2724, pruned_loss=0.06243, codebook_loss=21.4, over 7387.00 frames.], tot_loss[loss=2.398, simple_loss=0.2871, pruned_loss=0.0695, codebook_loss=21.85, over 319728.90 frames.], batch size: 19, lr: 1.72e-03
+2022-05-27 15:42:14,626 INFO [train.py:823] (3/4) Epoch 9, batch 100, loss[loss=2.376, simple_loss=0.2946, pruned_loss=0.0671, codebook_loss=21.62, over 7292.00 frames.], tot_loss[loss=2.375, simple_loss=0.2894, pruned_loss=0.06953, codebook_loss=21.61, over 563761.31 frames.], batch size: 19, lr: 1.71e-03
+2022-05-27 15:42:54,773 INFO [train.py:823] (3/4) Epoch 9, batch 150, loss[loss=2.486, simple_loss=0.287, pruned_loss=0.05892, codebook_loss=22.83, over 7097.00 frames.], tot_loss[loss=2.383, simple_loss=0.2917, pruned_loss=0.07098, codebook_loss=21.66, over 754201.28 frames.], batch size: 19, lr: 1.71e-03
+2022-05-27 15:43:34,131 INFO [train.py:823] (3/4) Epoch 9, batch 200, loss[loss=2.355, simple_loss=0.2893, pruned_loss=0.06051, codebook_loss=21.5, over 7286.00 frames.], tot_loss[loss=2.388, simple_loss=0.2926, pruned_loss=0.07126, codebook_loss=21.7, over 896585.99 frames.], batch size: 20, lr: 1.71e-03
+2022-05-27 15:44:14,348 INFO [train.py:823] (3/4) Epoch 9, batch 250, loss[loss=2.269, simple_loss=0.2726, pruned_loss=0.05117, codebook_loss=20.82, over 7181.00 frames.], tot_loss[loss=2.377, simple_loss=0.2914, pruned_loss=0.07035, codebook_loss=21.61, over 1012626.59 frames.], batch size: 20, lr: 1.70e-03
+2022-05-27 15:44:53,901 INFO [train.py:823] (3/4) Epoch 9, batch 300, loss[loss=2.419, simple_loss=0.3092, pruned_loss=0.09707, codebook_loss=21.67, over 7190.00 frames.], tot_loss[loss=2.381, simple_loss=0.2909, pruned_loss=0.07072, codebook_loss=21.65, over 1104358.04 frames.], batch size: 18, lr: 1.70e-03
+2022-05-27 15:45:34,260 INFO [train.py:823] (3/4) Epoch 9, batch 350, loss[loss=2.396, simple_loss=0.2541, pruned_loss=0.05536, codebook_loss=22.13, over 7287.00 frames.], tot_loss[loss=2.375, simple_loss=0.2903, pruned_loss=0.06983, codebook_loss=21.6, over 1173378.74 frames.], batch size: 17, lr: 1.70e-03
+2022-05-27 15:46:14,413 INFO [train.py:823] (3/4) Epoch 9, batch 400, loss[loss=2.307, simple_loss=0.3005, pruned_loss=0.06363, codebook_loss=20.93, over 7305.00 frames.], tot_loss[loss=2.372, simple_loss=0.2891, pruned_loss=0.06872, codebook_loss=21.59, over 1229830.52 frames.], batch size: 22, lr: 1.69e-03
+2022-05-27 15:46:57,537 INFO [train.py:823] (3/4) Epoch 9, batch 450, loss[loss=2.26, simple_loss=0.2654, pruned_loss=0.05148, codebook_loss=20.76, over 7192.00 frames.], tot_loss[loss=2.378, simple_loss=0.2911, pruned_loss=0.06954, codebook_loss=21.63, over 1271631.45 frames.], batch size: 19, lr: 1.69e-03
+2022-05-27 15:47:37,341 INFO [train.py:823] (3/4) Epoch 9, batch 500, loss[loss=2.387, simple_loss=0.3138, pruned_loss=0.08597, codebook_loss=21.44, over 7228.00 frames.], tot_loss[loss=2.382, simple_loss=0.2927, pruned_loss=0.07073, codebook_loss=21.65, over 1305188.81 frames.], batch size: 24, lr: 1.68e-03
+2022-05-27 15:48:17,623 INFO [train.py:823] (3/4) Epoch 9, batch 550, loss[loss=2.584, simple_loss=0.2947, pruned_loss=0.06883, codebook_loss=23.68, over 7204.00 frames.], tot_loss[loss=2.383, simple_loss=0.2923, pruned_loss=0.07023, codebook_loss=21.66, over 1333807.51 frames.], batch size: 19, lr: 1.68e-03
+2022-05-27 15:48:57,599 INFO [train.py:823] (3/4) Epoch 9, batch 600, loss[loss=2.967, simple_loss=0.2963, pruned_loss=0.09971, codebook_loss=27.19, over 7156.00 frames.], tot_loss[loss=2.388, simple_loss=0.2916, pruned_loss=0.07015, codebook_loss=21.72, over 1354101.53 frames.], batch size: 17, lr: 1.68e-03
+2022-05-27 15:49:37,637 INFO [train.py:823] (3/4) Epoch 9, batch 650, loss[loss=2.366, simple_loss=0.3008, pruned_loss=0.07087, codebook_loss=21.45, over 6961.00 frames.], tot_loss[loss=2.38, simple_loss=0.2902, pruned_loss=0.06851, codebook_loss=21.67, over 1367118.30 frames.], batch size: 29, lr: 1.67e-03
+2022-05-27 15:50:17,612 INFO [train.py:823] (3/4) Epoch 9, batch 700, loss[loss=2.364, simple_loss=0.2919, pruned_loss=0.06238, codebook_loss=21.56, over 7294.00 frames.], tot_loss[loss=2.381, simple_loss=0.2901, pruned_loss=0.06832, codebook_loss=21.67, over 1375125.87 frames.], batch size: 22, lr: 1.67e-03
+2022-05-27 15:50:59,096 INFO [train.py:823] (3/4) Epoch 9, batch 750, loss[loss=2.355, simple_loss=0.2529, pruned_loss=0.06095, codebook_loss=21.68, over 7183.00 frames.], tot_loss[loss=2.387, simple_loss=0.2917, pruned_loss=0.06976, codebook_loss=21.71, over 1385694.14 frames.], batch size: 18, lr: 1.67e-03
+2022-05-27 15:51:38,641 INFO [train.py:823] (3/4) Epoch 9, batch 800, loss[loss=2.295, simple_loss=0.2731, pruned_loss=0.05749, codebook_loss=21.01, over 7096.00 frames.], tot_loss[loss=2.384, simple_loss=0.2913, pruned_loss=0.06891, codebook_loss=21.69, over 1387983.55 frames.], batch size: 19, lr: 1.66e-03
+2022-05-27 15:52:18,625 INFO [train.py:823] (3/4) Epoch 9, batch 850, loss[loss=2.305, simple_loss=0.2359, pruned_loss=0.04333, codebook_loss=21.44, over 7286.00 frames.], tot_loss[loss=2.371, simple_loss=0.2901, pruned_loss=0.0675, codebook_loss=21.58, over 1397788.74 frames.], batch size: 16, lr: 1.66e-03
+2022-05-27 15:52:58,165 INFO [train.py:823] (3/4) Epoch 9, batch 900, loss[loss=2.492, simple_loss=0.2767, pruned_loss=0.07831, codebook_loss=22.75, over 7236.00 frames.], tot_loss[loss=2.377, simple_loss=0.2912, pruned_loss=0.06823, codebook_loss=21.64, over 1399798.41 frames.], batch size: 16, lr: 1.65e-03
+2022-05-27 15:53:54,914 INFO [train.py:823] (3/4) Epoch 10, batch 0, loss[loss=2.351, simple_loss=0.2876, pruned_loss=0.06473, codebook_loss=21.42, over 7106.00 frames.], tot_loss[loss=2.351, simple_loss=0.2876, pruned_loss=0.06473, codebook_loss=21.42, over 7106.00 frames.], batch size: 20, lr: 1.59e-03
+2022-05-27 15:54:34,616 INFO [train.py:823] (3/4) Epoch 10, batch 50, loss[loss=2.523, simple_loss=0.2493, pruned_loss=0.05521, codebook_loss=23.44, over 7028.00 frames.], tot_loss[loss=2.363, simple_loss=0.2866, pruned_loss=0.06429, codebook_loss=21.55, over 319356.87 frames.], batch size: 17, lr: 1.58e-03
+2022-05-27 15:55:15,570 INFO [train.py:823] (3/4) Epoch 10, batch 100, loss[loss=2.272, simple_loss=0.2649, pruned_loss=0.05512, codebook_loss=20.84, over 7373.00 frames.], tot_loss[loss=2.352, simple_loss=0.2858, pruned_loss=0.06432, codebook_loss=21.45, over 559712.63 frames.], batch size: 20, lr: 1.58e-03
+2022-05-27 15:55:54,972 INFO [train.py:823] (3/4) Epoch 10, batch 150, loss[loss=2.674, simple_loss=0.3267, pruned_loss=0.1158, codebook_loss=23.95, over 7282.00 frames.], tot_loss[loss=2.349, simple_loss=0.2885, pruned_loss=0.06472, codebook_loss=21.4, over 749634.14 frames.], batch size: 20, lr: 1.58e-03
+2022-05-27 15:56:35,127 INFO [train.py:823] (3/4) Epoch 10, batch 200, loss[loss=2.344, simple_loss=0.3069, pruned_loss=0.07416, codebook_loss=21.16, over 7298.00 frames.], tot_loss[loss=2.348, simple_loss=0.2866, pruned_loss=0.06442, codebook_loss=21.41, over 901205.95 frames.], batch size: 21, lr: 1.57e-03
+2022-05-27 15:57:14,778 INFO [train.py:823] (3/4) Epoch 10, batch 250, loss[loss=2.28, simple_loss=0.278, pruned_loss=0.06452, codebook_loss=20.76, over 7381.00 frames.], tot_loss[loss=2.345, simple_loss=0.2858, pruned_loss=0.06345, codebook_loss=21.39, over 1017309.78 frames.], batch size: 21, lr: 1.57e-03
+2022-05-27 15:57:54,573 INFO [train.py:823] (3/4) Epoch 10, batch 300, loss[loss=2.37, simple_loss=0.2908, pruned_loss=0.0702, codebook_loss=21.54, over 7014.00 frames.], tot_loss[loss=2.346, simple_loss=0.2858, pruned_loss=0.06347, codebook_loss=21.4, over 1108771.41 frames.], batch size: 26, lr: 1.57e-03
+2022-05-27 15:58:34,247 INFO [train.py:823] (3/4) Epoch 10, batch 350, loss[loss=2.345, simple_loss=0.2612, pruned_loss=0.05967, codebook_loss=21.55, over 6776.00 frames.], tot_loss[loss=2.339, simple_loss=0.2843, pruned_loss=0.06232, codebook_loss=21.35, over 1175441.32 frames.], batch size: 15, lr: 1.56e-03
+2022-05-27 15:59:14,379 INFO [train.py:823] (3/4) Epoch 10, batch 400, loss[loss=2.302, simple_loss=0.2842, pruned_loss=0.06685, codebook_loss=20.93, over 7089.00 frames.], tot_loss[loss=2.351, simple_loss=0.2863, pruned_loss=0.06371, codebook_loss=21.44, over 1224897.08 frames.], batch size: 19, lr: 1.56e-03
+2022-05-27 15:59:54,092 INFO [train.py:823] (3/4) Epoch 10, batch 450, loss[loss=2.407, simple_loss=0.2872, pruned_loss=0.06727, codebook_loss=21.96, over 7274.00 frames.], tot_loss[loss=2.352, simple_loss=0.2862, pruned_loss=0.0639, codebook_loss=21.45, over 1266077.79 frames.], batch size: 20, lr: 1.56e-03
+2022-05-27 16:00:34,194 INFO [train.py:823] (3/4) Epoch 10, batch 500, loss[loss=2.229, simple_loss=0.2633, pruned_loss=0.04676, codebook_loss=20.5, over 7280.00 frames.], tot_loss[loss=2.353, simple_loss=0.2866, pruned_loss=0.06446, codebook_loss=21.45, over 1298862.51 frames.], batch size: 20, lr: 1.55e-03
+2022-05-27 16:01:14,175 INFO [train.py:823] (3/4) Epoch 10, batch 550, loss[loss=2.277, simple_loss=0.2564, pruned_loss=0.04137, codebook_loss=21.07, over 7112.00 frames.], tot_loss[loss=2.348, simple_loss=0.2857, pruned_loss=0.06345, codebook_loss=21.42, over 1328526.92 frames.], batch size: 18, lr: 1.55e-03
+2022-05-27 16:01:54,264 INFO [train.py:823] (3/4) Epoch 10, batch 600, loss[loss=2.301, simple_loss=0.2705, pruned_loss=0.04929, codebook_loss=21.16, over 7301.00 frames.], tot_loss[loss=2.349, simple_loss=0.2857, pruned_loss=0.06308, codebook_loss=21.43, over 1352695.22 frames.], batch size: 19, lr: 1.55e-03
+2022-05-27 16:02:33,983 INFO [train.py:823] (3/4) Epoch 10, batch 650, loss[loss=2.239, simple_loss=0.278, pruned_loss=0.04695, codebook_loss=20.53, over 7184.00 frames.], tot_loss[loss=2.344, simple_loss=0.2842, pruned_loss=0.06222, codebook_loss=21.39, over 1370493.85 frames.], batch size: 21, lr: 1.54e-03
+2022-05-27 16:03:14,289 INFO [train.py:823] (3/4) Epoch 10, batch 700, loss[loss=2.88, simple_loss=0.3002, pruned_loss=0.1008, codebook_loss=26.29, over 7021.00 frames.], tot_loss[loss=2.345, simple_loss=0.2841, pruned_loss=0.06234, codebook_loss=21.4, over 1384990.70 frames.], batch size: 16, lr: 1.54e-03
+2022-05-27 16:03:53,952 INFO [train.py:823] (3/4) Epoch 10, batch 750, loss[loss=2.196, simple_loss=0.255, pruned_loss=0.04636, codebook_loss=20.22, over 7185.00 frames.], tot_loss[loss=2.351, simple_loss=0.2848, pruned_loss=0.0628, codebook_loss=21.45, over 1393061.40 frames.], batch size: 18, lr: 1.54e-03
+2022-05-27 16:04:34,061 INFO [train.py:823] (3/4) Epoch 10, batch 800, loss[loss=2.255, simple_loss=0.2742, pruned_loss=0.05055, codebook_loss=20.68, over 7220.00 frames.], tot_loss[loss=2.341, simple_loss=0.2845, pruned_loss=0.06172, codebook_loss=21.37, over 1399304.47 frames.], batch size: 25, lr: 1.53e-03
+2022-05-27 16:05:13,995 INFO [train.py:823] (3/4) Epoch 10, batch 850, loss[loss=2.291, simple_loss=0.2847, pruned_loss=0.05693, codebook_loss=20.92, over 7157.00 frames.], tot_loss[loss=2.344, simple_loss=0.2846, pruned_loss=0.06229, codebook_loss=21.39, over 1405275.05 frames.], batch size: 22, lr: 1.53e-03
+2022-05-27 16:05:54,086 INFO [train.py:823] (3/4) Epoch 10, batch 900, loss[loss=2.447, simple_loss=0.2558, pruned_loss=0.05091, codebook_loss=22.68, over 7268.00 frames.], tot_loss[loss=2.347, simple_loss=0.2843, pruned_loss=0.06234, codebook_loss=21.43, over 1405714.79 frames.], batch size: 16, lr: 1.53e-03
+2022-05-27 16:06:46,055 INFO [train.py:823] (3/4) Epoch 11, batch 0, loss[loss=2.486, simple_loss=0.2731, pruned_loss=0.04948, codebook_loss=23, over 7086.00 frames.], tot_loss[loss=2.486, simple_loss=0.2731, pruned_loss=0.04948, codebook_loss=23, over 7086.00 frames.], batch size: 19, lr: 1.47e-03
+2022-05-27 16:07:26,157 INFO [train.py:823] (3/4) Epoch 11, batch 50, loss[loss=2.315, simple_loss=0.2816, pruned_loss=0.06421, codebook_loss=21.1, over 6264.00 frames.], tot_loss[loss=2.329, simple_loss=0.284, pruned_loss=0.06061, codebook_loss=21.26, over 323072.97 frames.], batch size: 34, lr: 1.47e-03
+2022-05-27 16:08:06,017 INFO [train.py:823] (3/4) Epoch 11, batch 100, loss[loss=2.223, simple_loss=0.236, pruned_loss=0.04015, codebook_loss=20.65, over 7157.00 frames.], tot_loss[loss=2.315, simple_loss=0.2797, pruned_loss=0.05888, codebook_loss=21.16, over 569847.79 frames.], batch size: 17, lr: 1.46e-03
+2022-05-27 16:08:46,160 INFO [train.py:823] (3/4) Epoch 11, batch 150, loss[loss=2.246, simple_loss=0.2975, pruned_loss=0.0629, codebook_loss=20.34, over 7214.00 frames.], tot_loss[loss=2.318, simple_loss=0.2796, pruned_loss=0.05889, codebook_loss=21.19, over 761191.95 frames.], batch size: 24, lr: 1.46e-03
+2022-05-27 16:09:25,527 INFO [train.py:823] (3/4) Epoch 11, batch 200, loss[loss=2.212, simple_loss=0.2796, pruned_loss=0.05274, codebook_loss=20.2, over 7098.00 frames.], tot_loss[loss=2.324, simple_loss=0.2824, pruned_loss=0.06035, codebook_loss=21.22, over 900908.74 frames.], batch size: 19, lr: 1.46e-03
+2022-05-27 16:10:05,752 INFO [train.py:823] (3/4) Epoch 11, batch 250, loss[loss=2.252, simple_loss=0.2725, pruned_loss=0.05499, codebook_loss=20.6, over 7092.00 frames.], tot_loss[loss=2.319, simple_loss=0.2802, pruned_loss=0.0587, codebook_loss=21.2, over 1014003.68 frames.], batch size: 18, lr: 1.45e-03
+2022-05-27 16:10:45,562 INFO [train.py:823] (3/4) Epoch 11, batch 300, loss[loss=2.32, simple_loss=0.3054, pruned_loss=0.07005, codebook_loss=20.98, over 7196.00 frames.], tot_loss[loss=2.321, simple_loss=0.2803, pruned_loss=0.05912, codebook_loss=21.22, over 1105000.59 frames.], batch size: 25, lr: 1.45e-03
+2022-05-27 16:11:25,747 INFO [train.py:823] (3/4) Epoch 11, batch 350, loss[loss=2.244, simple_loss=0.2757, pruned_loss=0.05226, codebook_loss=20.54, over 7224.00 frames.], tot_loss[loss=2.319, simple_loss=0.2796, pruned_loss=0.05815, codebook_loss=21.21, over 1176646.16 frames.], batch size: 25, lr: 1.45e-03
+2022-05-27 16:12:05,520 INFO [train.py:823] (3/4) Epoch 11, batch 400, loss[loss=2.276, simple_loss=0.2921, pruned_loss=0.05759, codebook_loss=20.72, over 7090.00 frames.], tot_loss[loss=2.318, simple_loss=0.2802, pruned_loss=0.05841, codebook_loss=21.2, over 1231138.44 frames.], batch size: 19, lr: 1.44e-03
+2022-05-27 16:12:45,579 INFO [train.py:823] (3/4) Epoch 11, batch 450, loss[loss=2.266, simple_loss=0.2952, pruned_loss=0.05909, codebook_loss=20.59, over 7282.00 frames.], tot_loss[loss=2.313, simple_loss=0.28, pruned_loss=0.05829, codebook_loss=21.15, over 1269701.89 frames.], batch size: 22, lr: 1.44e-03
+2022-05-27 16:13:25,309 INFO [train.py:823] (3/4) Epoch 11, batch 500, loss[loss=2.249, simple_loss=0.2828, pruned_loss=0.05356, codebook_loss=20.54, over 6564.00 frames.], tot_loss[loss=2.315, simple_loss=0.2816, pruned_loss=0.05928, codebook_loss=21.15, over 1304396.67 frames.], batch size: 34, lr: 1.44e-03
+2022-05-27 16:14:05,255 INFO [train.py:823] (3/4) Epoch 11, batch 550, loss[loss=2.371, simple_loss=0.2691, pruned_loss=0.04373, codebook_loss=21.93, over 7432.00 frames.], tot_loss[loss=2.325, simple_loss=0.2825, pruned_loss=0.0603, codebook_loss=21.23, over 1332095.51 frames.], batch size: 22, lr: 1.44e-03
+2022-05-27 16:14:46,361 INFO [train.py:823] (3/4) Epoch 11, batch 600, loss[loss=2.245, simple_loss=0.2612, pruned_loss=0.04852, codebook_loss=20.66, over 7385.00 frames.], tot_loss[loss=2.325, simple_loss=0.2822, pruned_loss=0.06002, codebook_loss=21.24, over 1350770.78 frames.], batch size: 19, lr: 1.43e-03
+2022-05-27 16:15:26,712 INFO [train.py:823] (3/4) Epoch 11, batch 650, loss[loss=2.304, simple_loss=0.2637, pruned_loss=0.05861, codebook_loss=21.13, over 7310.00 frames.], tot_loss[loss=2.318, simple_loss=0.2811, pruned_loss=0.05932, codebook_loss=21.18, over 1368899.19 frames.], batch size: 18, lr: 1.43e-03
+2022-05-27 16:16:06,589 INFO [train.py:823] (3/4) Epoch 11, batch 700, loss[loss=2.433, simple_loss=0.2818, pruned_loss=0.08057, codebook_loss=22.11, over 7141.00 frames.], tot_loss[loss=2.315, simple_loss=0.2814, pruned_loss=0.05976, codebook_loss=21.15, over 1382193.97 frames.], batch size: 17, lr: 1.43e-03
+2022-05-27 16:16:46,853 INFO [train.py:823] (3/4) Epoch 11, batch 750, loss[loss=2.241, simple_loss=0.2414, pruned_loss=0.03721, codebook_loss=20.83, over 7309.00 frames.], tot_loss[loss=2.32, simple_loss=0.2802, pruned_loss=0.05973, codebook_loss=21.2, over 1390504.11 frames.], batch size: 17, lr: 1.42e-03
+2022-05-27 16:17:26,686 INFO [train.py:823] (3/4) Epoch 11, batch 800, loss[loss=2.402, simple_loss=0.2703, pruned_loss=0.04998, codebook_loss=22.17, over 7199.00 frames.], tot_loss[loss=2.319, simple_loss=0.2804, pruned_loss=0.05932, codebook_loss=21.2, over 1395592.17 frames.], batch size: 19, lr: 1.42e-03
+2022-05-27 16:18:08,321 INFO [train.py:823] (3/4) Epoch 11, batch 850, loss[loss=2.15, simple_loss=0.267, pruned_loss=0.04501, codebook_loss=19.72, over 7106.00 frames.], tot_loss[loss=2.319, simple_loss=0.2805, pruned_loss=0.05962, codebook_loss=21.19, over 1399219.98 frames.], batch size: 20, lr: 1.42e-03
+2022-05-27 16:18:49,133 INFO [train.py:823] (3/4) Epoch 11, batch 900, loss[loss=2.23, simple_loss=0.2441, pruned_loss=0.04612, codebook_loss=20.62, over 6789.00 frames.], tot_loss[loss=2.314, simple_loss=0.2817, pruned_loss=0.06002, codebook_loss=21.13, over 1398853.36 frames.], batch size: 15, lr: 1.42e-03
+2022-05-27 16:19:44,428 INFO [train.py:823] (3/4) Epoch 12, batch 0, loss[loss=2.245, simple_loss=0.2634, pruned_loss=0.06017, codebook_loss=20.53, over 7297.00 frames.], tot_loss[loss=2.245, simple_loss=0.2634, pruned_loss=0.06017, codebook_loss=20.53, over 7297.00 frames.], batch size: 17, lr: 1.36e-03
+2022-05-27 16:20:24,322 INFO [train.py:823] (3/4) Epoch 12, batch 50, loss[loss=2.27, simple_loss=0.2914, pruned_loss=0.06371, codebook_loss=20.6, over 7250.00 frames.], tot_loss[loss=2.33, simple_loss=0.2793, pruned_loss=0.05985, codebook_loss=21.3, over 317595.63 frames.], batch size: 24, lr: 1.36e-03
+2022-05-27 16:21:04,300 INFO [train.py:823] (3/4) Epoch 12, batch 100, loss[loss=2.608, simple_loss=0.293, pruned_loss=0.07406, codebook_loss=23.87, over 7151.00 frames.], tot_loss[loss=2.309, simple_loss=0.2799, pruned_loss=0.05843, codebook_loss=21.1, over 561629.40 frames.], batch size: 23, lr: 1.36e-03
+2022-05-27 16:21:44,024 INFO [train.py:823] (3/4) Epoch 12, batch 150, loss[loss=2.173, simple_loss=0.2633, pruned_loss=0.04567, codebook_loss=19.95, over 7281.00 frames.], tot_loss[loss=2.304, simple_loss=0.2789, pruned_loss=0.05755, codebook_loss=21.07, over 752145.04 frames.], batch size: 20, lr: 1.36e-03
+2022-05-27 16:22:24,274 INFO [train.py:823] (3/4) Epoch 12, batch 200, loss[loss=2.411, simple_loss=0.2851, pruned_loss=0.06918, codebook_loss=21.99, over 6788.00 frames.], tot_loss[loss=2.297, simple_loss=0.2782, pruned_loss=0.05625, codebook_loss=21.02, over 898324.38 frames.], batch size: 15, lr: 1.35e-03
+2022-05-27 16:23:03,814 INFO [train.py:823] (3/4) Epoch 12, batch 250, loss[loss=2.234, simple_loss=0.2846, pruned_loss=0.04382, codebook_loss=20.48, over 7006.00 frames.], tot_loss[loss=2.302, simple_loss=0.2789, pruned_loss=0.05691, codebook_loss=21.06, over 1015413.95 frames.], batch size: 26, lr: 1.35e-03
+2022-05-27 16:23:43,710 INFO [train.py:823] (3/4) Epoch 12, batch 300, loss[loss=2.299, simple_loss=0.2871, pruned_loss=0.05209, codebook_loss=21.03, over 7192.00 frames.], tot_loss[loss=2.302, simple_loss=0.2791, pruned_loss=0.05679, codebook_loss=21.06, over 1101930.22 frames.], batch size: 19, lr: 1.35e-03
+2022-05-27 16:24:23,587 INFO [train.py:823] (3/4) Epoch 12, batch 350, loss[loss=2.246, simple_loss=0.2954, pruned_loss=0.06054, codebook_loss=20.38, over 7327.00 frames.], tot_loss[loss=2.294, simple_loss=0.2784, pruned_loss=0.05573, codebook_loss=20.99, over 1176153.07 frames.], batch size: 23, lr: 1.35e-03
+2022-05-27 16:25:03,593 INFO [train.py:823] (3/4) Epoch 12, batch 400, loss[loss=2.254, simple_loss=0.2773, pruned_loss=0.04946, codebook_loss=20.65, over 7077.00 frames.], tot_loss[loss=2.29, simple_loss=0.2775, pruned_loss=0.05498, codebook_loss=20.97, over 1230958.68 frames.], batch size: 29, lr: 1.34e-03
+2022-05-27 16:25:43,360 INFO [train.py:823] (3/4) Epoch 12, batch 450, loss[loss=2.773, simple_loss=0.3039, pruned_loss=0.06403, codebook_loss=25.58, over 7375.00 frames.], tot_loss[loss=2.287, simple_loss=0.2779, pruned_loss=0.05487, codebook_loss=20.93, over 1272894.33 frames.], batch size: 20, lr: 1.34e-03
+2022-05-27 16:26:23,677 INFO [train.py:823] (3/4) Epoch 12, batch 500, loss[loss=2.226, simple_loss=0.2676, pruned_loss=0.05008, codebook_loss=20.42, over 7275.00 frames.], tot_loss[loss=2.285, simple_loss=0.2763, pruned_loss=0.0546, codebook_loss=20.92, over 1310495.71 frames.], batch size: 20, lr: 1.34e-03
+2022-05-27 16:27:03,418 INFO [train.py:823] (3/4) Epoch 12, batch 550, loss[loss=2.336, simple_loss=0.2517, pruned_loss=0.03706, codebook_loss=21.73, over 7039.00 frames.], tot_loss[loss=2.285, simple_loss=0.2775, pruned_loss=0.05558, codebook_loss=20.9, over 1338124.19 frames.], batch size: 17, lr: 1.34e-03
+2022-05-27 16:27:43,508 INFO [train.py:823] (3/4) Epoch 12, batch 600, loss[loss=2.221, simple_loss=0.2452, pruned_loss=0.04275, codebook_loss=20.55, over 7220.00 frames.], tot_loss[loss=2.286, simple_loss=0.2772, pruned_loss=0.05541, codebook_loss=20.92, over 1358490.85 frames.], batch size: 16, lr: 1.33e-03
+2022-05-27 16:28:23,496 INFO [train.py:823] (3/4) Epoch 12, batch 650, loss[loss=2.187, simple_loss=0.2816, pruned_loss=0.04527, codebook_loss=20.01, over 7289.00 frames.], tot_loss[loss=2.286, simple_loss=0.2773, pruned_loss=0.05527, codebook_loss=20.92, over 1371289.02 frames.], batch size: 21, lr: 1.33e-03
+2022-05-27 16:29:04,047 INFO [train.py:823] (3/4) Epoch 12, batch 700, loss[loss=2.319, simple_loss=0.2773, pruned_loss=0.04673, codebook_loss=21.33, over 7270.00 frames.], tot_loss[loss=2.292, simple_loss=0.278, pruned_loss=0.05565, codebook_loss=20.98, over 1381761.79 frames.], batch size: 20, lr: 1.33e-03
+2022-05-27 16:29:43,713 INFO [train.py:823] (3/4) Epoch 12, batch 750, loss[loss=2.332, simple_loss=0.3167, pruned_loss=0.08431, codebook_loss=20.89, over 7289.00 frames.], tot_loss[loss=2.29, simple_loss=0.278, pruned_loss=0.05587, codebook_loss=20.95, over 1387591.69 frames.], batch size: 22, lr: 1.33e-03
+2022-05-27 16:30:23,756 INFO [train.py:823] (3/4) Epoch 12, batch 800, loss[loss=2.361, simple_loss=0.3042, pruned_loss=0.07688, codebook_loss=21.32, over 7301.00 frames.], tot_loss[loss=2.288, simple_loss=0.2772, pruned_loss=0.05514, codebook_loss=20.94, over 1394398.06 frames.], batch size: 22, lr: 1.32e-03
+2022-05-27 16:31:03,441 INFO [train.py:823] (3/4) Epoch 12, batch 850, loss[loss=2.264, simple_loss=0.2748, pruned_loss=0.04885, codebook_loss=20.78, over 7194.00 frames.], tot_loss[loss=2.282, simple_loss=0.2772, pruned_loss=0.05447, codebook_loss=20.89, over 1399940.00 frames.], batch size: 18, lr: 1.32e-03
+2022-05-27 16:31:43,310 INFO [train.py:823] (3/4) Epoch 12, batch 900, loss[loss=2.22, simple_loss=0.2593, pruned_loss=0.04873, codebook_loss=20.41, over 7101.00 frames.], tot_loss[loss=2.29, simple_loss=0.277, pruned_loss=0.05546, codebook_loss=20.96, over 1395899.94 frames.], batch size: 19, lr: 1.32e-03
+2022-05-27 16:32:36,843 INFO [train.py:823] (3/4) Epoch 13, batch 0, loss[loss=2.253, simple_loss=0.2901, pruned_loss=0.05657, codebook_loss=20.52, over 7168.00 frames.], tot_loss[loss=2.253, simple_loss=0.2901, pruned_loss=0.05657, codebook_loss=20.52, over 7168.00 frames.], batch size: 22, lr: 1.27e-03
+2022-05-27 16:33:17,127 INFO [train.py:823] (3/4) Epoch 13, batch 50, loss[loss=2.152, simple_loss=0.2566, pruned_loss=0.04476, codebook_loss=19.79, over 7290.00 frames.], tot_loss[loss=2.266, simple_loss=0.2714, pruned_loss=0.05501, codebook_loss=20.75, over 318199.23 frames.], batch size: 19, lr: 1.27e-03
+2022-05-27 16:33:56,693 INFO [train.py:823] (3/4) Epoch 13, batch 100, loss[loss=2.18, simple_loss=0.2464, pruned_loss=0.03774, codebook_loss=20.19, over 7300.00 frames.], tot_loss[loss=2.267, simple_loss=0.273, pruned_loss=0.05369, codebook_loss=20.77, over 561439.47 frames.], batch size: 18, lr: 1.27e-03
+2022-05-27 16:34:36,923 INFO [train.py:823] (3/4) Epoch 13, batch 150, loss[loss=2.263, simple_loss=0.2454, pruned_loss=0.04331, codebook_loss=20.97, over 7397.00 frames.], tot_loss[loss=2.268, simple_loss=0.2735, pruned_loss=0.05332, codebook_loss=20.78, over 751425.58 frames.], batch size: 19, lr: 1.26e-03
+2022-05-27 16:35:16,782 INFO [train.py:823] (3/4) Epoch 13, batch 200, loss[loss=2.22, simple_loss=0.2477, pruned_loss=0.04969, codebook_loss=20.46, over 7423.00 frames.], tot_loss[loss=2.265, simple_loss=0.2731, pruned_loss=0.053, codebook_loss=20.75, over 903217.42 frames.], batch size: 18, lr: 1.26e-03
+2022-05-27 16:35:57,005 INFO [train.py:823] (3/4) Epoch 13, batch 250, loss[loss=2.491, simple_loss=0.3081, pruned_loss=0.08338, codebook_loss=22.53, over 7166.00 frames.], tot_loss[loss=2.263, simple_loss=0.2728, pruned_loss=0.0527, codebook_loss=20.74, over 1016684.36 frames.], batch size: 22, lr: 1.26e-03
+2022-05-27 16:36:37,068 INFO [train.py:823] (3/4) Epoch 13, batch 300, loss[loss=2.2, simple_loss=0.2463, pruned_loss=0.04605, codebook_loss=20.31, over 7284.00 frames.], tot_loss[loss=2.262, simple_loss=0.2715, pruned_loss=0.05197, codebook_loss=20.74, over 1110664.92 frames.], batch size: 17, lr: 1.26e-03
+2022-05-27 16:37:16,855 INFO [train.py:823] (3/4) Epoch 13, batch 350, loss[loss=2.278, simple_loss=0.2789, pruned_loss=0.04846, codebook_loss=20.9, over 6526.00 frames.], tot_loss[loss=2.255, simple_loss=0.2727, pruned_loss=0.05231, codebook_loss=20.66, over 1176929.54 frames.], batch size: 34, lr: 1.26e-03
+2022-05-27 16:37:56,769 INFO [train.py:823] (3/4) Epoch 13, batch 400, loss[loss=2.304, simple_loss=0.2798, pruned_loss=0.06099, codebook_loss=21.03, over 6968.00 frames.], tot_loss[loss=2.256, simple_loss=0.2728, pruned_loss=0.05284, codebook_loss=20.67, over 1230610.96 frames.], batch size: 26, lr: 1.25e-03
+2022-05-27 16:38:36,632 INFO [train.py:823] (3/4) Epoch 13, batch 450, loss[loss=2.269, simple_loss=0.2818, pruned_loss=0.05301, codebook_loss=20.75, over 6914.00 frames.], tot_loss[loss=2.261, simple_loss=0.2731, pruned_loss=0.05308, codebook_loss=20.71, over 1268243.26 frames.], batch size: 29, lr: 1.25e-03
+2022-05-27 16:39:17,526 INFO [train.py:823] (3/4) Epoch 13, batch 500, loss[loss=2.329, simple_loss=0.2733, pruned_loss=0.05553, codebook_loss=21.36, over 6868.00 frames.], tot_loss[loss=2.261, simple_loss=0.2727, pruned_loss=0.05291, codebook_loss=20.71, over 1301197.40 frames.], batch size: 29, lr: 1.25e-03
+2022-05-27 16:39:57,606 INFO [train.py:823] (3/4) Epoch 13, batch 550, loss[loss=2.15, simple_loss=0.263, pruned_loss=0.04298, codebook_loss=19.75, over 7285.00 frames.], tot_loss[loss=2.263, simple_loss=0.2725, pruned_loss=0.05297, codebook_loss=20.74, over 1322786.18 frames.], batch size: 19, lr: 1.25e-03
+2022-05-27 16:40:37,173 INFO [train.py:823] (3/4) Epoch 13, batch 600, loss[loss=2.293, simple_loss=0.2984, pruned_loss=0.07396, codebook_loss=20.7, over 7275.00 frames.], tot_loss[loss=2.267, simple_loss=0.2741, pruned_loss=0.05342, codebook_loss=20.76, over 1344920.50 frames.], batch size: 20, lr: 1.24e-03
+2022-05-27 16:41:17,351 INFO [train.py:823] (3/4) Epoch 13, batch 650, loss[loss=2.494, simple_loss=0.2769, pruned_loss=0.05746, codebook_loss=22.98, over 7202.00 frames.], tot_loss[loss=2.267, simple_loss=0.2735, pruned_loss=0.05294, codebook_loss=20.78, over 1361114.49 frames.], batch size: 19, lr: 1.24e-03
+2022-05-27 16:41:57,044 INFO [train.py:823] (3/4) Epoch 13, batch 700, loss[loss=2.172, simple_loss=0.2425, pruned_loss=0.04076, codebook_loss=20.1, over 7035.00 frames.], tot_loss[loss=2.271, simple_loss=0.274, pruned_loss=0.05315, codebook_loss=20.81, over 1370797.89 frames.], batch size: 17, lr: 1.24e-03
+2022-05-27 16:42:38,231 INFO [train.py:823] (3/4) Epoch 13, batch 750, loss[loss=2.289, simple_loss=0.2812, pruned_loss=0.05922, codebook_loss=20.89, over 6936.00 frames.], tot_loss[loss=2.259, simple_loss=0.2743, pruned_loss=0.05239, codebook_loss=20.7, over 1378372.50 frames.], batch size: 29, lr: 1.24e-03
+2022-05-27 16:43:19,055 INFO [train.py:823] (3/4) Epoch 13, batch 800, loss[loss=2.323, simple_loss=0.2994, pruned_loss=0.07509, codebook_loss=20.99, over 7165.00 frames.], tot_loss[loss=2.264, simple_loss=0.2751, pruned_loss=0.05361, codebook_loss=20.73, over 1385586.90 frames.], batch size: 23, lr: 1.24e-03
+2022-05-27 16:44:00,616 INFO [train.py:823] (3/4) Epoch 13, batch 850, loss[loss=2.272, simple_loss=0.2978, pruned_loss=0.07098, codebook_loss=20.52, over 7278.00 frames.], tot_loss[loss=2.264, simple_loss=0.2748, pruned_loss=0.05357, codebook_loss=20.73, over 1395866.36 frames.], batch size: 20, lr: 1.23e-03
+2022-05-27 16:44:39,955 INFO [train.py:823] (3/4) Epoch 13, batch 900, loss[loss=2.227, simple_loss=0.2709, pruned_loss=0.0477, codebook_loss=20.44, over 7298.00 frames.], tot_loss[loss=2.262, simple_loss=0.2753, pruned_loss=0.05352, codebook_loss=20.71, over 1395548.05 frames.], batch size: 19, lr: 1.23e-03
+2022-05-27 16:45:19,790 INFO [train.py:823] (3/4) Epoch 13, batch 950, loss[loss=2.214, simple_loss=0.2427, pruned_loss=0.03833, codebook_loss=20.54, over 7021.00 frames.], tot_loss[loss=2.26, simple_loss=0.2747, pruned_loss=0.05271, codebook_loss=20.7, over 1395243.64 frames.], batch size: 16, lr: 1.23e-03
+2022-05-27 16:45:35,289 INFO [train.py:823] (3/4) Epoch 14, batch 0, loss[loss=2.139, simple_loss=0.2785, pruned_loss=0.05072, codebook_loss=19.49, over 7294.00 frames.], tot_loss[loss=2.139, simple_loss=0.2785, pruned_loss=0.05072, codebook_loss=19.49, over 7294.00 frames.], batch size: 22, lr: 1.19e-03
+2022-05-27 16:46:15,198 INFO [train.py:823] (3/4) Epoch 14, batch 50, loss[loss=2.275, simple_loss=0.3089, pruned_loss=0.06923, codebook_loss=20.51, over 7216.00 frames.], tot_loss[loss=2.24, simple_loss=0.271, pruned_loss=0.05061, codebook_loss=20.54, over 324572.54 frames.], batch size: 25, lr: 1.19e-03
+2022-05-27 16:46:55,257 INFO [train.py:823] (3/4) Epoch 14, batch 100, loss[loss=2.189, simple_loss=0.2708, pruned_loss=0.04296, codebook_loss=20.11, over 7253.00 frames.], tot_loss[loss=2.253, simple_loss=0.2722, pruned_loss=0.0514, codebook_loss=20.65, over 570366.38 frames.], batch size: 24, lr: 1.19e-03
+2022-05-27 16:47:34,771 INFO [train.py:823] (3/4) Epoch 14, batch 150, loss[loss=2.191, simple_loss=0.2792, pruned_loss=0.05104, codebook_loss=20.01, over 7279.00 frames.], tot_loss[loss=2.26, simple_loss=0.2731, pruned_loss=0.05211, codebook_loss=20.72, over 754716.59 frames.], batch size: 21, lr: 1.18e-03
+2022-05-27 16:48:14,998 INFO [train.py:823] (3/4) Epoch 14, batch 200, loss[loss=2.254, simple_loss=0.3056, pruned_loss=0.06331, codebook_loss=20.38, over 7370.00 frames.], tot_loss[loss=2.251, simple_loss=0.2731, pruned_loss=0.05144, codebook_loss=20.63, over 901183.52 frames.], batch size: 21, lr: 1.18e-03
+2022-05-27 16:48:54,994 INFO [train.py:823] (3/4) Epoch 14, batch 250, loss[loss=2.163, simple_loss=0.241, pruned_loss=0.03696, codebook_loss=20.05, over 7298.00 frames.], tot_loss[loss=2.245, simple_loss=0.2701, pruned_loss=0.05016, codebook_loss=20.6, over 1019225.37 frames.], batch size: 19, lr: 1.18e-03
+2022-05-27 16:49:35,005 INFO [train.py:823] (3/4) Epoch 14, batch 300, loss[loss=2.189, simple_loss=0.2808, pruned_loss=0.04156, codebook_loss=20.07, over 6273.00 frames.], tot_loss[loss=2.243, simple_loss=0.2706, pruned_loss=0.05033, codebook_loss=20.57, over 1099203.83 frames.], batch size: 34, lr: 1.18e-03
+2022-05-27 16:50:14,796 INFO [train.py:823] (3/4) Epoch 14, batch 350, loss[loss=2.228, simple_loss=0.2451, pruned_loss=0.04462, codebook_loss=20.61, over 7290.00 frames.], tot_loss[loss=2.234, simple_loss=0.2714, pruned_loss=0.04957, codebook_loss=20.49, over 1176006.43 frames.], batch size: 19, lr: 1.18e-03
+2022-05-27 16:50:54,549 INFO [train.py:823] (3/4) Epoch 14, batch 400, loss[loss=2.159, simple_loss=0.2647, pruned_loss=0.03507, codebook_loss=19.91, over 7289.00 frames.], tot_loss[loss=2.237, simple_loss=0.2718, pruned_loss=0.05022, codebook_loss=20.51, over 1231445.86 frames.], batch size: 19, lr: 1.17e-03
+2022-05-27 16:51:34,201 INFO [train.py:823] (3/4) Epoch 14, batch 450, loss[loss=2.124, simple_loss=0.2412, pruned_loss=0.03364, codebook_loss=19.7, over 7090.00 frames.], tot_loss[loss=2.237, simple_loss=0.2718, pruned_loss=0.05019, codebook_loss=20.51, over 1269770.56 frames.], batch size: 18, lr: 1.17e-03
+2022-05-27 16:52:14,435 INFO [train.py:823] (3/4) Epoch 14, batch 500, loss[loss=2.214, simple_loss=0.2707, pruned_loss=0.05122, codebook_loss=20.28, over 7180.00 frames.], tot_loss[loss=2.235, simple_loss=0.2712, pruned_loss=0.05016, codebook_loss=20.49, over 1304416.29 frames.], batch size: 21, lr: 1.17e-03
+2022-05-27 16:52:54,037 INFO [train.py:823] (3/4) Epoch 14, batch 550, loss[loss=2.321, simple_loss=0.2798, pruned_loss=0.07246, codebook_loss=21.09, over 7227.00 frames.], tot_loss[loss=2.245, simple_loss=0.2715, pruned_loss=0.05113, codebook_loss=20.59, over 1334211.99 frames.], batch size: 25, lr: 1.17e-03
+2022-05-27 16:53:34,421 INFO [train.py:823] (3/4) Epoch 14, batch 600, loss[loss=2.275, simple_loss=0.2556, pruned_loss=0.04535, codebook_loss=21.02, over 7390.00 frames.], tot_loss[loss=2.243, simple_loss=0.2687, pruned_loss=0.05018, codebook_loss=20.58, over 1355015.55 frames.], batch size: 19, lr: 1.17e-03
+2022-05-27 16:54:14,392 INFO [train.py:823] (3/4) Epoch 14, batch 650, loss[loss=2.21, simple_loss=0.2312, pruned_loss=0.03819, codebook_loss=20.57, over 7285.00 frames.], tot_loss[loss=2.238, simple_loss=0.2686, pruned_loss=0.04977, codebook_loss=20.54, over 1369053.99 frames.], batch size: 17, lr: 1.16e-03
+2022-05-27 16:54:54,549 INFO [train.py:823] (3/4) Epoch 14, batch 700, loss[loss=2.21, simple_loss=0.2807, pruned_loss=0.0493, codebook_loss=20.2, over 7279.00 frames.], tot_loss[loss=2.239, simple_loss=0.269, pruned_loss=0.04991, codebook_loss=20.55, over 1377623.78 frames.], batch size: 21, lr: 1.16e-03
+2022-05-27 16:55:34,005 INFO [train.py:823] (3/4) Epoch 14, batch 750, loss[loss=2.221, simple_loss=0.2883, pruned_loss=0.05783, codebook_loss=20.19, over 7116.00 frames.], tot_loss[loss=2.241, simple_loss=0.2692, pruned_loss=0.04967, codebook_loss=20.57, over 1387470.45 frames.], batch size: 20, lr: 1.16e-03
+2022-05-27 16:56:14,263 INFO [train.py:823] (3/4) Epoch 14, batch 800, loss[loss=2.331, simple_loss=0.277, pruned_loss=0.05956, codebook_loss=21.33, over 7199.00 frames.], tot_loss[loss=2.243, simple_loss=0.2697, pruned_loss=0.04982, codebook_loss=20.58, over 1393438.20 frames.], batch size: 19, lr: 1.16e-03
+2022-05-27 16:56:54,066 INFO [train.py:823] (3/4) Epoch 14, batch 850, loss[loss=2.14, simple_loss=0.2681, pruned_loss=0.0397, codebook_loss=19.67, over 7292.00 frames.], tot_loss[loss=2.239, simple_loss=0.2697, pruned_loss=0.04964, codebook_loss=20.55, over 1396719.45 frames.], batch size: 20, lr: 1.16e-03
+2022-05-27 16:57:34,187 INFO [train.py:823] (3/4) Epoch 14, batch 900, loss[loss=2.185, simple_loss=0.2686, pruned_loss=0.05205, codebook_loss=19.98, over 7016.00 frames.], tot_loss[loss=2.243, simple_loss=0.2696, pruned_loss=0.04976, codebook_loss=20.59, over 1400429.79 frames.], batch size: 17, lr: 1.15e-03
+2022-05-27 16:58:27,977 INFO [train.py:823] (3/4) Epoch 15, batch 0, loss[loss=2.148, simple_loss=0.2342, pruned_loss=0.03703, codebook_loss=19.94, over 7202.00 frames.], tot_loss[loss=2.148, simple_loss=0.2342, pruned_loss=0.03703, codebook_loss=19.94, over 7202.00 frames.], batch size: 19, lr: 1.12e-03
+2022-05-27 16:59:07,739 INFO [train.py:823] (3/4) Epoch 15, batch 50, loss[loss=2.227, simple_loss=0.273, pruned_loss=0.05508, codebook_loss=20.35, over 7192.00 frames.], tot_loss[loss=2.224, simple_loss=0.27, pruned_loss=0.04815, codebook_loss=20.41, over 319303.33 frames.], batch size: 18, lr: 1.12e-03
+2022-05-27 16:59:47,353 INFO [train.py:823] (3/4) Epoch 15, batch 100, loss[loss=2.418, simple_loss=0.3012, pruned_loss=0.06293, codebook_loss=22.04, over 7419.00 frames.], tot_loss[loss=2.222, simple_loss=0.2673, pruned_loss=0.04825, codebook_loss=20.4, over 559572.48 frames.], batch size: 22, lr: 1.11e-03
+2022-05-27 17:00:27,646 INFO [train.py:823] (3/4) Epoch 15, batch 150, loss[loss=2.442, simple_loss=0.2458, pruned_loss=0.05519, codebook_loss=22.64, over 7309.00 frames.], tot_loss[loss=2.219, simple_loss=0.2648, pruned_loss=0.04763, codebook_loss=20.39, over 751715.78 frames.], batch size: 17, lr: 1.11e-03
+2022-05-27 17:01:07,297 INFO [train.py:823] (3/4) Epoch 15, batch 200, loss[loss=2.223, simple_loss=0.3003, pruned_loss=0.06113, codebook_loss=20.11, over 7155.00 frames.], tot_loss[loss=2.238, simple_loss=0.2674, pruned_loss=0.04942, codebook_loss=20.55, over 897931.09 frames.], batch size: 23, lr: 1.11e-03
+2022-05-27 17:01:47,504 INFO [train.py:823] (3/4) Epoch 15, batch 250, loss[loss=2.149, simple_loss=0.2839, pruned_loss=0.04496, codebook_loss=19.62, over 6734.00 frames.], tot_loss[loss=2.233, simple_loss=0.2671, pruned_loss=0.04875, codebook_loss=20.51, over 1014464.89 frames.], batch size: 34, lr: 1.11e-03
+2022-05-27 17:02:27,354 INFO [train.py:823] (3/4) Epoch 15, batch 300, loss[loss=2.288, simple_loss=0.2799, pruned_loss=0.05773, codebook_loss=20.9, over 7188.00 frames.], tot_loss[loss=2.229, simple_loss=0.2669, pruned_loss=0.0488, codebook_loss=20.46, over 1103522.72 frames.], batch size: 18, lr: 1.11e-03
+2022-05-27 17:03:08,869 INFO [train.py:823] (3/4) Epoch 15, batch 350, loss[loss=2.227, simple_loss=0.2653, pruned_loss=0.0438, codebook_loss=20.5, over 7370.00 frames.], tot_loss[loss=2.223, simple_loss=0.2672, pruned_loss=0.04793, codebook_loss=20.42, over 1175995.39 frames.], batch size: 20, lr: 1.10e-03
+2022-05-27 17:03:48,688 INFO [train.py:823] (3/4) Epoch 15, batch 400, loss[loss=2.047, simple_loss=0.2395, pruned_loss=0.03149, codebook_loss=18.96, over 7102.00 frames.], tot_loss[loss=2.228, simple_loss=0.2673, pruned_loss=0.04809, codebook_loss=20.46, over 1227640.51 frames.], batch size: 19, lr: 1.10e-03
+2022-05-27 17:04:28,832 INFO [train.py:823] (3/4) Epoch 15, batch 450, loss[loss=2.191, simple_loss=0.2698, pruned_loss=0.05204, codebook_loss=20.04, over 7229.00 frames.], tot_loss[loss=2.223, simple_loss=0.2665, pruned_loss=0.04798, codebook_loss=20.42, over 1275428.23 frames.], batch size: 24, lr: 1.10e-03
+2022-05-27 17:05:08,653 INFO [train.py:823] (3/4) Epoch 15, batch 500, loss[loss=2.147, simple_loss=0.2646, pruned_loss=0.03951, codebook_loss=19.75, over 7115.00 frames.], tot_loss[loss=2.219, simple_loss=0.267, pruned_loss=0.04776, codebook_loss=20.38, over 1311213.46 frames.], batch size: 20, lr: 1.10e-03
+2022-05-27 17:05:48,665 INFO [train.py:823] (3/4) Epoch 15, batch 550, loss[loss=2.206, simple_loss=0.2581, pruned_loss=0.03819, codebook_loss=20.39, over 7017.00 frames.], tot_loss[loss=2.22, simple_loss=0.2668, pruned_loss=0.04811, codebook_loss=20.38, over 1332042.52 frames.], batch size: 17, lr: 1.10e-03
+2022-05-27 17:06:28,760 INFO [train.py:823] (3/4) Epoch 15, batch 600, loss[loss=2.228, simple_loss=0.2436, pruned_loss=0.03947, codebook_loss=20.67, over 7291.00 frames.], tot_loss[loss=2.228, simple_loss=0.2677, pruned_loss=0.0485, codebook_loss=20.46, over 1355929.07 frames.], batch size: 19, lr: 1.10e-03
+2022-05-27 17:07:08,796 INFO [train.py:823] (3/4) Epoch 15, batch 650, loss[loss=2.218, simple_loss=0.3058, pruned_loss=0.06181, codebook_loss=20.03, over 7160.00 frames.], tot_loss[loss=2.225, simple_loss=0.2678, pruned_loss=0.04845, codebook_loss=20.43, over 1367567.01 frames.], batch size: 22, lr: 1.09e-03
+2022-05-27 17:07:51,621 INFO [train.py:823] (3/4) Epoch 15, batch 700, loss[loss=2.135, simple_loss=0.2761, pruned_loss=0.03911, codebook_loss=19.58, over 6809.00 frames.], tot_loss[loss=2.224, simple_loss=0.268, pruned_loss=0.04866, codebook_loss=20.42, over 1382183.92 frames.], batch size: 29, lr: 1.09e-03
+2022-05-27 17:08:32,967 INFO [train.py:823] (3/4) Epoch 15, batch 750, loss[loss=2.213, simple_loss=0.2819, pruned_loss=0.0574, codebook_loss=20.14, over 5383.00 frames.], tot_loss[loss=2.22, simple_loss=0.2676, pruned_loss=0.04866, codebook_loss=20.38, over 1386221.65 frames.], batch size: 48, lr: 1.09e-03
+2022-05-27 17:09:12,719 INFO [train.py:823] (3/4) Epoch 15, batch 800, loss[loss=2.179, simple_loss=0.2654, pruned_loss=0.048, codebook_loss=19.98, over 7196.00 frames.], tot_loss[loss=2.219, simple_loss=0.2678, pruned_loss=0.04801, codebook_loss=20.37, over 1389789.18 frames.], batch size: 19, lr: 1.09e-03
+2022-05-27 17:09:53,044 INFO [train.py:823] (3/4) Epoch 15, batch 850, loss[loss=2.343, simple_loss=0.2865, pruned_loss=0.06663, codebook_loss=21.33, over 7203.00 frames.], tot_loss[loss=2.216, simple_loss=0.2675, pruned_loss=0.04777, codebook_loss=20.34, over 1395412.47 frames.], batch size: 25, lr: 1.09e-03
+2022-05-27 17:10:33,291 INFO [train.py:823] (3/4) Epoch 15, batch 900, loss[loss=2.17, simple_loss=0.2713, pruned_loss=0.04451, codebook_loss=19.9, over 7111.00 frames.], tot_loss[loss=2.222, simple_loss=0.2688, pruned_loss=0.04857, codebook_loss=20.39, over 1400241.06 frames.], batch size: 19, lr: 1.09e-03
+2022-05-27 17:11:13,323 INFO [train.py:823] (3/4) Epoch 15, batch 950, loss[loss=2.156, simple_loss=0.2744, pruned_loss=0.0461, codebook_loss=19.73, over 4544.00 frames.], tot_loss[loss=2.223, simple_loss=0.2689, pruned_loss=0.04871, codebook_loss=20.4, over 1380435.86 frames.], batch size: 47, lr: 1.08e-03
+2022-05-27 17:11:28,491 INFO [train.py:823] (3/4) Epoch 16, batch 0, loss[loss=2.151, simple_loss=0.2592, pruned_loss=0.04922, codebook_loss=19.72, over 5250.00 frames.], tot_loss[loss=2.151, simple_loss=0.2592, pruned_loss=0.04922, codebook_loss=19.72, over 5250.00 frames.], batch size: 47, lr: 1.05e-03
+2022-05-27 17:12:08,304 INFO [train.py:823] (3/4) Epoch 16, batch 50, loss[loss=2.161, simple_loss=0.2526, pruned_loss=0.04385, codebook_loss=19.9, over 7023.00 frames.], tot_loss[loss=2.156, simple_loss=0.2617, pruned_loss=0.0431, codebook_loss=19.82, over 319222.04 frames.], batch size: 16, lr: 1.05e-03
+2022-05-27 17:12:48,665 INFO [train.py:823] (3/4) Epoch 16, batch 100, loss[loss=2.178, simple_loss=0.2627, pruned_loss=0.04567, codebook_loss=20.01, over 7201.00 frames.], tot_loss[loss=2.194, simple_loss=0.2623, pruned_loss=0.04531, codebook_loss=20.17, over 561236.57 frames.], batch size: 19, lr: 1.05e-03
+2022-05-27 17:13:28,976 INFO [train.py:823] (3/4) Epoch 16, batch 150, loss[loss=2.119, simple_loss=0.2579, pruned_loss=0.04543, codebook_loss=19.45, over 7392.00 frames.], tot_loss[loss=2.193, simple_loss=0.2625, pruned_loss=0.04522, codebook_loss=20.16, over 756688.37 frames.], batch size: 19, lr: 1.05e-03
+2022-05-27 17:14:09,508 INFO [train.py:823] (3/4) Epoch 16, batch 200, loss[loss=2.246, simple_loss=0.2987, pruned_loss=0.06851, codebook_loss=20.28, over 7159.00 frames.], tot_loss[loss=2.204, simple_loss=0.2641, pruned_loss=0.04687, codebook_loss=20.25, over 903530.97 frames.], batch size: 23, lr: 1.05e-03
+2022-05-27 17:14:49,495 INFO [train.py:823] (3/4) Epoch 16, batch 250, loss[loss=2.161, simple_loss=0.2795, pruned_loss=0.05047, codebook_loss=19.71, over 7224.00 frames.], tot_loss[loss=2.194, simple_loss=0.2642, pruned_loss=0.04603, codebook_loss=20.16, over 1012591.00 frames.], batch size: 25, lr: 1.04e-03
+2022-05-27 17:15:30,001 INFO [train.py:823] (3/4) Epoch 16, batch 300, loss[loss=2.319, simple_loss=0.2978, pruned_loss=0.05947, codebook_loss=21.1, over 7242.00 frames.], tot_loss[loss=2.199, simple_loss=0.2631, pruned_loss=0.04584, codebook_loss=20.22, over 1105483.88 frames.], batch size: 24, lr: 1.04e-03
+2022-05-27 17:16:09,522 INFO [train.py:823] (3/4) Epoch 16, batch 350, loss[loss=2.223, simple_loss=0.2912, pruned_loss=0.06067, codebook_loss=20.16, over 7324.00 frames.], tot_loss[loss=2.207, simple_loss=0.264, pruned_loss=0.04667, codebook_loss=20.28, over 1173271.99 frames.], batch size: 23, lr: 1.04e-03
+2022-05-27 17:16:49,906 INFO [train.py:823] (3/4) Epoch 16, batch 400, loss[loss=2.178, simple_loss=0.2541, pruned_loss=0.0411, codebook_loss=20.1, over 7293.00 frames.], tot_loss[loss=2.204, simple_loss=0.2647, pruned_loss=0.04672, codebook_loss=20.24, over 1228755.96 frames.], batch size: 19, lr: 1.04e-03
+2022-05-27 17:17:29,852 INFO [train.py:823] (3/4) Epoch 16, batch 450, loss[loss=2.395, simple_loss=0.2908, pruned_loss=0.04889, codebook_loss=22.01, over 7412.00 frames.], tot_loss[loss=2.207, simple_loss=0.2659, pruned_loss=0.04712, codebook_loss=20.27, over 1276700.76 frames.], batch size: 22, lr: 1.04e-03
+2022-05-27 17:18:10,059 INFO [train.py:823] (3/4) Epoch 16, batch 500, loss[loss=2.226, simple_loss=0.2931, pruned_loss=0.06397, codebook_loss=20.16, over 6987.00 frames.], tot_loss[loss=2.205, simple_loss=0.2645, pruned_loss=0.04611, codebook_loss=20.26, over 1312410.02 frames.], batch size: 29, lr: 1.04e-03
+2022-05-27 17:18:49,957 INFO [train.py:823] (3/4) Epoch 16, batch 550, loss[loss=2.285, simple_loss=0.2976, pruned_loss=0.05996, codebook_loss=20.76, over 7378.00 frames.], tot_loss[loss=2.204, simple_loss=0.2653, pruned_loss=0.0465, codebook_loss=20.25, over 1331042.67 frames.], batch size: 21, lr: 1.03e-03
+2022-05-27 17:19:30,256 INFO [train.py:823] (3/4) Epoch 16, batch 600, loss[loss=2.121, simple_loss=0.2427, pruned_loss=0.04054, codebook_loss=19.59, over 7100.00 frames.], tot_loss[loss=2.204, simple_loss=0.265, pruned_loss=0.04642, codebook_loss=20.25, over 1345393.36 frames.], batch size: 19, lr: 1.03e-03
+2022-05-27 17:20:09,980 INFO [train.py:823] (3/4) Epoch 16, batch 650, loss[loss=2.316, simple_loss=0.2658, pruned_loss=0.05595, codebook_loss=21.27, over 6792.00 frames.], tot_loss[loss=2.211, simple_loss=0.2665, pruned_loss=0.04719, codebook_loss=20.3, over 1361215.06 frames.], batch size: 15, lr: 1.03e-03
+2022-05-27 17:20:50,255 INFO [train.py:823] (3/4) Epoch 16, batch 700, loss[loss=2.133, simple_loss=0.2645, pruned_loss=0.03882, codebook_loss=19.62, over 7292.00 frames.], tot_loss[loss=2.21, simple_loss=0.2659, pruned_loss=0.04681, codebook_loss=20.3, over 1371363.35 frames.], batch size: 19, lr: 1.03e-03
+2022-05-27 17:21:29,865 INFO [train.py:823] (3/4) Epoch 16, batch 750, loss[loss=2.19, simple_loss=0.2542, pruned_loss=0.03977, codebook_loss=20.23, over 7175.00 frames.], tot_loss[loss=2.209, simple_loss=0.2656, pruned_loss=0.04673, codebook_loss=20.29, over 1384167.03 frames.], batch size: 18, lr: 1.03e-03
+2022-05-27 17:22:09,877 INFO [train.py:823] (3/4) Epoch 16, batch 800, loss[loss=2.463, simple_loss=0.2923, pruned_loss=0.07403, codebook_loss=22.43, over 7384.00 frames.], tot_loss[loss=2.211, simple_loss=0.2663, pruned_loss=0.04706, codebook_loss=20.31, over 1394493.79 frames.], batch size: 20, lr: 1.03e-03
+2022-05-27 17:22:49,735 INFO [train.py:823] (3/4) Epoch 16, batch 850, loss[loss=2.127, simple_loss=0.2565, pruned_loss=0.03422, codebook_loss=19.64, over 7187.00 frames.], tot_loss[loss=2.206, simple_loss=0.2663, pruned_loss=0.0469, codebook_loss=20.26, over 1401167.71 frames.], batch size: 21, lr: 1.03e-03
+2022-05-27 17:23:29,827 INFO [train.py:823] (3/4) Epoch 16, batch 900, loss[loss=2.235, simple_loss=0.2666, pruned_loss=0.05443, codebook_loss=20.48, over 7027.00 frames.], tot_loss[loss=2.202, simple_loss=0.2656, pruned_loss=0.04651, codebook_loss=20.23, over 1400611.40 frames.], batch size: 17, lr: 1.02e-03
+2022-05-27 17:24:23,380 INFO [train.py:823] (3/4) Epoch 17, batch 0, loss[loss=2.126, simple_loss=0.274, pruned_loss=0.03304, codebook_loss=19.56, over 7186.00 frames.], tot_loss[loss=2.126, simple_loss=0.274, pruned_loss=0.03304, codebook_loss=19.56, over 7186.00 frames.], batch size: 21, lr: 9.94e-04
+2022-05-27 17:25:03,584 INFO [train.py:823] (3/4) Epoch 17, batch 50, loss[loss=2.228, simple_loss=0.2893, pruned_loss=0.06369, codebook_loss=20.2, over 7020.00 frames.], tot_loss[loss=2.215, simple_loss=0.2688, pruned_loss=0.04755, codebook_loss=20.33, over 315332.28 frames.], batch size: 26, lr: 9.92e-04
+2022-05-27 17:25:43,305 INFO [train.py:823] (3/4) Epoch 17, batch 100, loss[loss=2.148, simple_loss=0.2819, pruned_loss=0.04595, codebook_loss=19.62, over 6963.00 frames.], tot_loss[loss=2.192, simple_loss=0.2657, pruned_loss=0.04422, codebook_loss=20.15, over 560659.06 frames.], batch size: 26, lr: 9.91e-04
+2022-05-27 17:26:24,348 INFO [train.py:823] (3/4) Epoch 17, batch 150, loss[loss=2.148, simple_loss=0.2454, pruned_loss=0.04356, codebook_loss=19.82, over 7194.00 frames.], tot_loss[loss=2.185, simple_loss=0.2658, pruned_loss=0.04463, codebook_loss=20.07, over 748192.67 frames.], batch size: 18, lr: 9.89e-04
+2022-05-27 17:27:04,187 INFO [train.py:823] (3/4) Epoch 17, batch 200, loss[loss=2.088, simple_loss=0.2638, pruned_loss=0.03373, codebook_loss=19.22, over 6816.00 frames.], tot_loss[loss=2.189, simple_loss=0.2663, pruned_loss=0.04463, codebook_loss=20.11, over 897810.46 frames.], batch size: 29, lr: 9.88e-04
+2022-05-27 17:27:44,504 INFO [train.py:823] (3/4) Epoch 17, batch 250, loss[loss=2.168, simple_loss=0.2692, pruned_loss=0.04786, codebook_loss=19.86, over 7339.00 frames.], tot_loss[loss=2.181, simple_loss=0.2655, pruned_loss=0.04419, codebook_loss=20.04, over 1018330.56 frames.], batch size: 23, lr: 9.86e-04
+2022-05-27 17:28:23,999 INFO [train.py:823] (3/4) Epoch 17, batch 300, loss[loss=2.145, simple_loss=0.2474, pruned_loss=0.04462, codebook_loss=19.77, over 7299.00 frames.], tot_loss[loss=2.181, simple_loss=0.2656, pruned_loss=0.04441, codebook_loss=20.04, over 1104169.23 frames.], batch size: 18, lr: 9.85e-04
+2022-05-27 17:29:04,164 INFO [train.py:823] (3/4) Epoch 17, batch 350, loss[loss=2.065, simple_loss=0.2503, pruned_loss=0.0342, codebook_loss=19.06, over 7389.00 frames.], tot_loss[loss=2.182, simple_loss=0.2643, pruned_loss=0.0443, codebook_loss=20.05, over 1170536.05 frames.], batch size: 19, lr: 9.84e-04
+2022-05-27 17:29:43,925 INFO [train.py:823] (3/4) Epoch 17, batch 400, loss[loss=2.253, simple_loss=0.2653, pruned_loss=0.05036, codebook_loss=20.7, over 7097.00 frames.], tot_loss[loss=2.192, simple_loss=0.2631, pruned_loss=0.0443, codebook_loss=20.16, over 1226844.42 frames.], batch size: 19, lr: 9.82e-04
+2022-05-27 17:30:24,089 INFO [train.py:823] (3/4) Epoch 17, batch 450, loss[loss=2.259, simple_loss=0.288, pruned_loss=0.06176, codebook_loss=20.53, over 4749.00 frames.], tot_loss[loss=2.193, simple_loss=0.2629, pruned_loss=0.04442, codebook_loss=20.17, over 1261436.47 frames.], batch size: 47, lr: 9.81e-04
+2022-05-27 17:31:03,726 INFO [train.py:823] (3/4) Epoch 17, batch 500, loss[loss=2.133, simple_loss=0.2282, pruned_loss=0.0286, codebook_loss=19.9, over 6982.00 frames.], tot_loss[loss=2.193, simple_loss=0.2633, pruned_loss=0.04481, codebook_loss=20.17, over 1297110.86 frames.], batch size: 16, lr: 9.79e-04
+2022-05-27 17:31:43,977 INFO [train.py:823] (3/4) Epoch 17, batch 550, loss[loss=2.189, simple_loss=0.2796, pruned_loss=0.04135, codebook_loss=20.08, over 7105.00 frames.], tot_loss[loss=2.193, simple_loss=0.2635, pruned_loss=0.04508, codebook_loss=20.16, over 1326830.05 frames.], batch size: 20, lr: 9.78e-04
+2022-05-27 17:32:26,191 INFO [train.py:823] (3/4) Epoch 17, batch 600, loss[loss=2.198, simple_loss=0.2748, pruned_loss=0.06006, codebook_loss=20, over 7310.00 frames.], tot_loss[loss=2.199, simple_loss=0.2633, pruned_loss=0.04491, codebook_loss=20.23, over 1349116.14 frames.], batch size: 22, lr: 9.76e-04
+2022-05-27 17:33:07,654 INFO [train.py:823] (3/4) Epoch 17, batch 650, loss[loss=2.294, simple_loss=0.2463, pruned_loss=0.04692, codebook_loss=21.24, over 7017.00 frames.], tot_loss[loss=2.199, simple_loss=0.2628, pruned_loss=0.04474, codebook_loss=20.23, over 1362199.18 frames.], batch size: 16, lr: 9.75e-04
+2022-05-27 17:33:47,422 INFO [train.py:823] (3/4) Epoch 17, batch 700, loss[loss=2.156, simple_loss=0.2323, pruned_loss=0.03134, codebook_loss=20.09, over 7201.00 frames.], tot_loss[loss=2.198, simple_loss=0.2629, pruned_loss=0.04479, codebook_loss=20.22, over 1373430.29 frames.], batch size: 16, lr: 9.74e-04
+2022-05-27 17:34:27,701 INFO [train.py:823] (3/4) Epoch 17, batch 750, loss[loss=2.209, simple_loss=0.2305, pruned_loss=0.03816, codebook_loss=20.56, over 7159.00 frames.], tot_loss[loss=2.192, simple_loss=0.2625, pruned_loss=0.04455, codebook_loss=20.16, over 1385429.69 frames.], batch size: 17, lr: 9.72e-04
+2022-05-27 17:35:07,558 INFO [train.py:823] (3/4) Epoch 17, batch 800, loss[loss=2.187, simple_loss=0.245, pruned_loss=0.04158, codebook_loss=20.23, over 7034.00 frames.], tot_loss[loss=2.191, simple_loss=0.2628, pruned_loss=0.04463, codebook_loss=20.15, over 1389268.34 frames.], batch size: 16, lr: 9.71e-04
+2022-05-27 17:35:50,792 INFO [train.py:823] (3/4) Epoch 17, batch 850, loss[loss=2.152, simple_loss=0.2772, pruned_loss=0.044, codebook_loss=19.7, over 7422.00 frames.], tot_loss[loss=2.186, simple_loss=0.262, pruned_loss=0.04404, codebook_loss=20.11, over 1395556.45 frames.], batch size: 22, lr: 9.69e-04
+2022-05-27 17:36:30,827 INFO [train.py:823] (3/4) Epoch 17, batch 900, loss[loss=2.206, simple_loss=0.25, pruned_loss=0.05438, codebook_loss=20.27, over 7290.00 frames.], tot_loss[loss=2.185, simple_loss=0.2621, pruned_loss=0.04435, codebook_loss=20.1, over 1401122.19 frames.], batch size: 17, lr: 9.68e-04
+2022-05-27 17:37:10,650 INFO [train.py:823] (3/4) Epoch 17, batch 950, loss[loss=2.201, simple_loss=0.2726, pruned_loss=0.06205, codebook_loss=20.03, over 4684.00 frames.], tot_loss[loss=2.186, simple_loss=0.2621, pruned_loss=0.04465, codebook_loss=20.1, over 1397027.55 frames.], batch size: 46, lr: 9.67e-04
+2022-05-27 17:37:26,010 INFO [train.py:823] (3/4) Epoch 18, batch 0, loss[loss=2.138, simple_loss=0.2651, pruned_loss=0.04414, codebook_loss=19.61, over 7375.00 frames.], tot_loss[loss=2.138, simple_loss=0.2651, pruned_loss=0.04414, codebook_loss=19.61, over 7375.00 frames.], batch size: 21, lr: 9.41e-04
+2022-05-27 17:38:06,270 INFO [train.py:823] (3/4) Epoch 18, batch 50, loss[loss=2.117, simple_loss=0.2601, pruned_loss=0.03634, codebook_loss=19.51, over 7323.00 frames.], tot_loss[loss=2.17, simple_loss=0.2594, pruned_loss=0.04176, codebook_loss=19.98, over 322125.82 frames.], batch size: 23, lr: 9.40e-04
+2022-05-27 17:38:46,070 INFO [train.py:823] (3/4) Epoch 18, batch 100, loss[loss=2.048, simple_loss=0.2565, pruned_loss=0.02926, codebook_loss=18.9, over 7285.00 frames.], tot_loss[loss=2.163, simple_loss=0.2597, pruned_loss=0.04097, codebook_loss=19.92, over 563710.17 frames.], batch size: 20, lr: 9.39e-04
+2022-05-27 17:39:26,380 INFO [train.py:823] (3/4) Epoch 18, batch 150, loss[loss=2.106, simple_loss=0.2494, pruned_loss=0.03857, codebook_loss=19.42, over 7202.00 frames.], tot_loss[loss=2.169, simple_loss=0.26, pruned_loss=0.04169, codebook_loss=19.97, over 756530.52 frames.], batch size: 20, lr: 9.37e-04
+2022-05-27 17:40:06,115 INFO [train.py:823] (3/4) Epoch 18, batch 200, loss[loss=2.096, simple_loss=0.2631, pruned_loss=0.03863, codebook_loss=19.26, over 7294.00 frames.], tot_loss[loss=2.164, simple_loss=0.2605, pruned_loss=0.04198, codebook_loss=19.92, over 907243.01 frames.], batch size: 21, lr: 9.36e-04
+2022-05-27 17:40:46,115 INFO [train.py:823] (3/4) Epoch 18, batch 250, loss[loss=2.085, simple_loss=0.2456, pruned_loss=0.02814, codebook_loss=19.34, over 7303.00 frames.], tot_loss[loss=2.173, simple_loss=0.2628, pruned_loss=0.04357, codebook_loss=19.98, over 1015489.32 frames.], batch size: 22, lr: 9.35e-04
+2022-05-27 17:41:26,328 INFO [train.py:823] (3/4) Epoch 18, batch 300, loss[loss=2.389, simple_loss=0.2407, pruned_loss=0.04837, codebook_loss=22.21, over 7425.00 frames.], tot_loss[loss=2.175, simple_loss=0.2614, pruned_loss=0.04355, codebook_loss=20.01, over 1106366.84 frames.], batch size: 18, lr: 9.33e-04
+2022-05-27 17:42:06,842 INFO [train.py:823] (3/4) Epoch 18, batch 350, loss[loss=2.142, simple_loss=0.2695, pruned_loss=0.04236, codebook_loss=19.65, over 7283.00 frames.], tot_loss[loss=2.169, simple_loss=0.2612, pruned_loss=0.04353, codebook_loss=19.95, over 1175489.25 frames.], batch size: 20, lr: 9.32e-04
+2022-05-27 17:42:46,676 INFO [train.py:823] (3/4) Epoch 18, batch 400, loss[loss=2.268, simple_loss=0.2641, pruned_loss=0.05189, codebook_loss=20.84, over 7383.00 frames.], tot_loss[loss=2.169, simple_loss=0.2621, pruned_loss=0.04408, codebook_loss=19.94, over 1227721.05 frames.], batch size: 19, lr: 9.31e-04
+2022-05-27 17:43:26,808 INFO [train.py:823] (3/4) Epoch 18, batch 450, loss[loss=2.164, simple_loss=0.2773, pruned_loss=0.04895, codebook_loss=19.76, over 7143.00 frames.], tot_loss[loss=2.173, simple_loss=0.2627, pruned_loss=0.04422, codebook_loss=19.98, over 1269727.28 frames.], batch size: 23, lr: 9.29e-04
+2022-05-27 17:44:06,718 INFO [train.py:823] (3/4) Epoch 18, batch 500, loss[loss=2.12, simple_loss=0.2777, pruned_loss=0.04688, codebook_loss=19.34, over 7417.00 frames.], tot_loss[loss=2.173, simple_loss=0.2615, pruned_loss=0.04367, codebook_loss=19.98, over 1307434.63 frames.], batch size: 22, lr: 9.28e-04
+2022-05-27 17:44:47,130 INFO [train.py:823] (3/4) Epoch 18, batch 550, loss[loss=2.064, simple_loss=0.2569, pruned_loss=0.02978, codebook_loss=19.05, over 7317.00 frames.], tot_loss[loss=2.168, simple_loss=0.2601, pruned_loss=0.04321, codebook_loss=19.95, over 1335838.73 frames.], batch size: 23, lr: 9.27e-04
+2022-05-27 17:45:26,660 INFO [train.py:823] (3/4) Epoch 18, batch 600, loss[loss=2.143, simple_loss=0.2556, pruned_loss=0.04269, codebook_loss=19.73, over 7287.00 frames.], tot_loss[loss=2.166, simple_loss=0.2599, pruned_loss=0.04289, codebook_loss=19.94, over 1357854.03 frames.], batch size: 19, lr: 9.26e-04
+2022-05-27 17:46:06,507 INFO [train.py:823] (3/4) Epoch 18, batch 650, loss[loss=2.103, simple_loss=0.2378, pruned_loss=0.02952, codebook_loss=19.55, over 7090.00 frames.], tot_loss[loss=2.162, simple_loss=0.2593, pruned_loss=0.04264, codebook_loss=19.89, over 1371368.07 frames.], batch size: 19, lr: 9.24e-04
+2022-05-27 17:46:46,416 INFO [train.py:823] (3/4) Epoch 18, batch 700, loss[loss=2.093, simple_loss=0.247, pruned_loss=0.03956, codebook_loss=19.3, over 7189.00 frames.], tot_loss[loss=2.161, simple_loss=0.2596, pruned_loss=0.04293, codebook_loss=19.89, over 1376760.33 frames.], batch size: 19, lr: 9.23e-04
+2022-05-27 17:47:26,765 INFO [train.py:823] (3/4) Epoch 18, batch 750, loss[loss=2.238, simple_loss=0.2643, pruned_loss=0.0549, codebook_loss=20.51, over 7091.00 frames.], tot_loss[loss=2.165, simple_loss=0.2605, pruned_loss=0.04307, codebook_loss=19.91, over 1388482.30 frames.], batch size: 18, lr: 9.22e-04
+2022-05-27 17:48:06,482 INFO [train.py:823] (3/4) Epoch 18, batch 800, loss[loss=2.2, simple_loss=0.2585, pruned_loss=0.03304, codebook_loss=20.37, over 7190.00 frames.], tot_loss[loss=2.163, simple_loss=0.2597, pruned_loss=0.04243, codebook_loss=19.9, over 1391853.96 frames.], batch size: 20, lr: 9.21e-04
+2022-05-27 17:48:46,491 INFO [train.py:823] (3/4) Epoch 18, batch 850, loss[loss=2.166, simple_loss=0.2661, pruned_loss=0.03862, codebook_loss=19.95, over 7175.00 frames.], tot_loss[loss=2.16, simple_loss=0.2593, pruned_loss=0.04231, codebook_loss=19.88, over 1394442.32 frames.], batch size: 21, lr: 9.19e-04
+2022-05-27 17:49:26,195 INFO [train.py:823] (3/4) Epoch 18, batch 900, loss[loss=2.137, simple_loss=0.2356, pruned_loss=0.04022, codebook_loss=19.79, over 7163.00 frames.], tot_loss[loss=2.169, simple_loss=0.2605, pruned_loss=0.04286, codebook_loss=19.96, over 1401359.45 frames.], batch size: 17, lr: 9.18e-04
+2022-05-27 17:50:07,352 INFO [train.py:823] (3/4) Epoch 18, batch 950, loss[loss=2.195, simple_loss=0.2646, pruned_loss=0.04748, codebook_loss=20.15, over 4883.00 frames.], tot_loss[loss=2.172, simple_loss=0.2612, pruned_loss=0.04321, codebook_loss=19.98, over 1373610.98 frames.], batch size: 47, lr: 9.17e-04
+2022-05-27 17:50:22,772 INFO [train.py:823] (3/4) Epoch 19, batch 0, loss[loss=2.089, simple_loss=0.259, pruned_loss=0.04395, codebook_loss=19.16, over 7005.00 frames.], tot_loss[loss=2.089, simple_loss=0.259, pruned_loss=0.04395, codebook_loss=19.16, over 7005.00 frames.], batch size: 26, lr: 8.94e-04
+2022-05-27 17:51:02,623 INFO [train.py:823] (3/4) Epoch 19, batch 50, loss[loss=2.099, simple_loss=0.2631, pruned_loss=0.0383, codebook_loss=19.29, over 7195.00 frames.], tot_loss[loss=2.157, simple_loss=0.2562, pruned_loss=0.04137, codebook_loss=19.88, over 325362.00 frames.], batch size: 19, lr: 8.92e-04
+2022-05-27 17:51:43,092 INFO [train.py:823] (3/4) Epoch 19, batch 100, loss[loss=2.092, simple_loss=0.2576, pruned_loss=0.03178, codebook_loss=19.32, over 6625.00 frames.], tot_loss[loss=2.154, simple_loss=0.257, pruned_loss=0.04126, codebook_loss=19.84, over 565889.03 frames.], batch size: 34, lr: 8.91e-04
+2022-05-27 17:52:23,023 INFO [train.py:823] (3/4) Epoch 19, batch 150, loss[loss=2.047, simple_loss=0.2536, pruned_loss=0.03703, codebook_loss=18.83, over 7098.00 frames.], tot_loss[loss=2.152, simple_loss=0.2569, pruned_loss=0.04159, codebook_loss=19.82, over 759137.70 frames.], batch size: 18, lr: 8.90e-04
+2022-05-27 17:53:03,222 INFO [train.py:823] (3/4) Epoch 19, batch 200, loss[loss=2.185, simple_loss=0.2742, pruned_loss=0.05308, codebook_loss=19.95, over 7159.00 frames.], tot_loss[loss=2.155, simple_loss=0.2571, pruned_loss=0.04173, codebook_loss=19.84, over 901824.53 frames.], batch size: 22, lr: 8.89e-04
+2022-05-27 17:53:42,988 INFO [train.py:823] (3/4) Epoch 19, batch 250, loss[loss=2.036, simple_loss=0.2272, pruned_loss=0.02341, codebook_loss=18.99, over 7101.00 frames.], tot_loss[loss=2.151, simple_loss=0.2583, pruned_loss=0.04162, codebook_loss=19.8, over 1018347.95 frames.], batch size: 19, lr: 8.88e-04
+2022-05-27 17:54:23,001 INFO [train.py:823] (3/4) Epoch 19, batch 300, loss[loss=2.065, simple_loss=0.2344, pruned_loss=0.02213, codebook_loss=19.26, over 7014.00 frames.], tot_loss[loss=2.16, simple_loss=0.2595, pruned_loss=0.04256, codebook_loss=19.88, over 1110478.46 frames.], batch size: 16, lr: 8.87e-04
+2022-05-27 17:55:02,850 INFO [train.py:823] (3/4) Epoch 19, batch 350, loss[loss=2.227, simple_loss=0.3225, pruned_loss=0.08212, codebook_loss=19.84, over 7304.00 frames.], tot_loss[loss=2.151, simple_loss=0.2601, pruned_loss=0.04256, codebook_loss=19.78, over 1178380.77 frames.], batch size: 18, lr: 8.85e-04
+2022-05-27 17:55:43,664 INFO [train.py:823] (3/4) Epoch 19, batch 400, loss[loss=2.172, simple_loss=0.2393, pruned_loss=0.03749, codebook_loss=20.15, over 7016.00 frames.], tot_loss[loss=2.15, simple_loss=0.2598, pruned_loss=0.04231, codebook_loss=19.78, over 1235591.99 frames.], batch size: 16, lr: 8.84e-04
+2022-05-27 17:56:23,361 INFO [train.py:823] (3/4) Epoch 19, batch 450, loss[loss=2.197, simple_loss=0.2693, pruned_loss=0.03608, codebook_loss=20.26, over 7159.00 frames.], tot_loss[loss=2.156, simple_loss=0.2615, pruned_loss=0.04285, codebook_loss=19.82, over 1277956.00 frames.], batch size: 23, lr: 8.83e-04
+2022-05-27 17:57:06,163 INFO [train.py:823] (3/4) Epoch 19, batch 500, loss[loss=2.219, simple_loss=0.2876, pruned_loss=0.05142, codebook_loss=20.23, over 6512.00 frames.], tot_loss[loss=2.154, simple_loss=0.2612, pruned_loss=0.04268, codebook_loss=19.8, over 1310285.63 frames.], batch size: 34, lr: 8.82e-04
+2022-05-27 17:57:47,351 INFO [train.py:823] (3/4) Epoch 19, batch 550, loss[loss=2.07, simple_loss=0.2527, pruned_loss=0.03162, codebook_loss=19.12, over 7009.00 frames.], tot_loss[loss=2.154, simple_loss=0.2613, pruned_loss=0.04271, codebook_loss=19.8, over 1331819.63 frames.], batch size: 17, lr: 8.81e-04
+2022-05-27 17:58:27,533 INFO [train.py:823] (3/4) Epoch 19, batch 600, loss[loss=2.442, simple_loss=0.2645, pruned_loss=0.05678, codebook_loss=22.53, over 7105.00 frames.], tot_loss[loss=2.154, simple_loss=0.2614, pruned_loss=0.04263, codebook_loss=19.81, over 1352052.08 frames.], batch size: 19, lr: 8.80e-04
+2022-05-27 17:59:07,240 INFO [train.py:823] (3/4) Epoch 19, batch 650, loss[loss=1.987, simple_loss=0.2166, pruned_loss=0.01886, codebook_loss=18.6, over 7023.00 frames.], tot_loss[loss=2.152, simple_loss=0.2596, pruned_loss=0.04177, codebook_loss=19.8, over 1365919.92 frames.], batch size: 17, lr: 8.78e-04
+2022-05-27 17:59:47,326 INFO [train.py:823] (3/4) Epoch 19, batch 700, loss[loss=2.066, simple_loss=0.2577, pruned_loss=0.03811, codebook_loss=18.99, over 7058.00 frames.], tot_loss[loss=2.148, simple_loss=0.2591, pruned_loss=0.04133, codebook_loss=19.77, over 1377195.61 frames.], batch size: 26, lr: 8.77e-04
+2022-05-27 18:00:27,358 INFO [train.py:823] (3/4) Epoch 19, batch 750, loss[loss=2.138, simple_loss=0.2746, pruned_loss=0.04539, codebook_loss=19.55, over 7370.00 frames.], tot_loss[loss=2.15, simple_loss=0.2587, pruned_loss=0.04131, codebook_loss=19.79, over 1387348.92 frames.], batch size: 21, lr: 8.76e-04
+2022-05-27 18:01:07,505 INFO [train.py:823] (3/4) Epoch 19, batch 800, loss[loss=2.152, simple_loss=0.2753, pruned_loss=0.0388, codebook_loss=19.75, over 7301.00 frames.], tot_loss[loss=2.155, simple_loss=0.2595, pruned_loss=0.04198, codebook_loss=19.83, over 1397011.11 frames.], batch size: 22, lr: 8.75e-04
+2022-05-27 18:01:47,287 INFO [train.py:823] (3/4) Epoch 19, batch 850, loss[loss=2.119, simple_loss=0.2647, pruned_loss=0.035, codebook_loss=19.52, over 7377.00 frames.], tot_loss[loss=2.162, simple_loss=0.2596, pruned_loss=0.04205, codebook_loss=19.91, over 1402778.46 frames.], batch size: 21, lr: 8.74e-04
+2022-05-27 18:02:27,152 INFO [train.py:823] (3/4) Epoch 19, batch 900, loss[loss=2.127, simple_loss=0.2842, pruned_loss=0.04914, codebook_loss=19.36, over 7065.00 frames.], tot_loss[loss=2.164, simple_loss=0.2604, pruned_loss=0.043, codebook_loss=19.91, over 1394939.82 frames.], batch size: 26, lr: 8.73e-04
+2022-05-27 18:03:20,039 INFO [train.py:823] (3/4) Epoch 20, batch 0, loss[loss=2.133, simple_loss=0.2712, pruned_loss=0.04975, codebook_loss=19.47, over 6600.00 frames.], tot_loss[loss=2.133, simple_loss=0.2712, pruned_loss=0.04975, codebook_loss=19.47, over 6600.00 frames.], batch size: 34, lr: 8.51e-04
+2022-05-27 18:04:00,436 INFO [train.py:823] (3/4) Epoch 20, batch 50, loss[loss=2.041, simple_loss=0.2278, pruned_loss=0.03349, codebook_loss=18.94, over 7311.00 frames.], tot_loss[loss=2.123, simple_loss=0.2539, pruned_loss=0.03829, codebook_loss=19.57, over 322564.14 frames.], batch size: 18, lr: 8.49e-04
+2022-05-27 18:04:40,155 INFO [train.py:823] (3/4) Epoch 20, batch 100, loss[loss=2.067, simple_loss=0.2601, pruned_loss=0.0442, codebook_loss=18.93, over 5271.00 frames.], tot_loss[loss=2.134, simple_loss=0.2557, pruned_loss=0.04016, codebook_loss=19.66, over 563269.67 frames.], batch size: 47, lr: 8.48e-04
+2022-05-27 18:05:20,186 INFO [train.py:823] (3/4) Epoch 20, batch 150, loss[loss=2.076, simple_loss=0.2212, pruned_loss=0.01883, codebook_loss=19.47, over 7291.00 frames.], tot_loss[loss=2.143, simple_loss=0.2567, pruned_loss=0.04044, codebook_loss=19.74, over 752754.92 frames.], batch size: 17, lr: 8.47e-04
+2022-05-27 18:05:59,936 INFO [train.py:823] (3/4) Epoch 20, batch 200, loss[loss=2.085, simple_loss=0.2441, pruned_loss=0.03486, codebook_loss=19.28, over 7004.00 frames.], tot_loss[loss=2.134, simple_loss=0.2575, pruned_loss=0.04049, codebook_loss=19.65, over 903503.65 frames.], batch size: 16, lr: 8.46e-04
+2022-05-27 18:06:40,101 INFO [train.py:823] (3/4) Epoch 20, batch 250, loss[loss=2.432, simple_loss=0.2678, pruned_loss=0.04659, codebook_loss=22.52, over 7315.00 frames.], tot_loss[loss=2.161, simple_loss=0.2586, pruned_loss=0.04205, codebook_loss=19.9, over 1017599.35 frames.], batch size: 18, lr: 8.45e-04
+2022-05-27 18:07:19,811 INFO [train.py:823] (3/4) Epoch 20, batch 300, loss[loss=2.074, simple_loss=0.2775, pruned_loss=0.04448, codebook_loss=18.91, over 7308.00 frames.], tot_loss[loss=2.155, simple_loss=0.2591, pruned_loss=0.04162, codebook_loss=19.83, over 1107894.14 frames.], batch size: 22, lr: 8.44e-04
+2022-05-27 18:08:00,085 INFO [train.py:823] (3/4) Epoch 20, batch 350, loss[loss=2.088, simple_loss=0.2644, pruned_loss=0.04616, codebook_loss=19.1, over 7192.00 frames.], tot_loss[loss=2.154, simple_loss=0.2592, pruned_loss=0.04135, codebook_loss=19.83, over 1177034.75 frames.], batch size: 20, lr: 8.43e-04
+2022-05-27 18:08:40,165 INFO [train.py:823] (3/4) Epoch 20, batch 400, loss[loss=2.17, simple_loss=0.2836, pruned_loss=0.05774, codebook_loss=19.7, over 7165.00 frames.], tot_loss[loss=2.157, simple_loss=0.2593, pruned_loss=0.04168, codebook_loss=19.85, over 1231968.92 frames.], batch size: 23, lr: 8.42e-04
+2022-05-27 18:09:20,009 INFO [train.py:823] (3/4) Epoch 20, batch 450, loss[loss=2.085, simple_loss=0.2238, pruned_loss=0.04136, codebook_loss=19.31, over 7164.00 frames.], tot_loss[loss=2.153, simple_loss=0.2593, pruned_loss=0.04154, codebook_loss=19.82, over 1269717.21 frames.], batch size: 17, lr: 8.41e-04
+2022-05-27 18:09:59,743 INFO [train.py:823] (3/4) Epoch 20, batch 500, loss[loss=2.263, simple_loss=0.2752, pruned_loss=0.06298, codebook_loss=20.63, over 7025.00 frames.], tot_loss[loss=2.155, simple_loss=0.2595, pruned_loss=0.04154, codebook_loss=19.84, over 1305551.25 frames.], batch size: 17, lr: 8.40e-04
+2022-05-27 18:10:40,037 INFO [train.py:823] (3/4) Epoch 20, batch 550, loss[loss=2, simple_loss=0.2506, pruned_loss=0.02706, codebook_loss=18.48, over 7142.00 frames.], tot_loss[loss=2.151, simple_loss=0.2579, pruned_loss=0.04107, codebook_loss=19.81, over 1333648.98 frames.], batch size: 23, lr: 8.39e-04
+2022-05-27 18:11:19,658 INFO [train.py:823] (3/4) Epoch 20, batch 600, loss[loss=2.7, simple_loss=0.278, pruned_loss=0.06899, codebook_loss=24.92, over 7092.00 frames.], tot_loss[loss=2.159, simple_loss=0.2584, pruned_loss=0.04154, codebook_loss=19.88, over 1349815.66 frames.], batch size: 18, lr: 8.38e-04
+2022-05-27 18:11:59,841 INFO [train.py:823] (3/4) Epoch 20, batch 650, loss[loss=2.123, simple_loss=0.2575, pruned_loss=0.04312, codebook_loss=19.51, over 6928.00 frames.], tot_loss[loss=2.153, simple_loss=0.2578, pruned_loss=0.04121, codebook_loss=19.83, over 1365287.06 frames.], batch size: 29, lr: 8.37e-04
+2022-05-27 18:12:39,833 INFO [train.py:823] (3/4) Epoch 20, batch 700, loss[loss=2.201, simple_loss=0.283, pruned_loss=0.05888, codebook_loss=20.01, over 7097.00 frames.], tot_loss[loss=2.153, simple_loss=0.2574, pruned_loss=0.04104, codebook_loss=19.83, over 1379889.45 frames.], batch size: 18, lr: 8.36e-04
+2022-05-27 18:13:20,105 INFO [train.py:823] (3/4) Epoch 20, batch 750, loss[loss=2.078, simple_loss=0.2661, pruned_loss=0.03705, codebook_loss=19.08, over 7285.00 frames.], tot_loss[loss=2.149, simple_loss=0.2564, pruned_loss=0.0409, codebook_loss=19.8, over 1389447.25 frames.], batch size: 21, lr: 8.35e-04
+2022-05-27 18:13:59,607 INFO [train.py:823] (3/4) Epoch 20, batch 800, loss[loss=2.057, simple_loss=0.2404, pruned_loss=0.02906, codebook_loss=19.08, over 7014.00 frames.], tot_loss[loss=2.146, simple_loss=0.2573, pruned_loss=0.04076, codebook_loss=19.77, over 1397710.93 frames.], batch size: 17, lr: 8.34e-04
+2022-05-27 18:14:41,111 INFO [train.py:823] (3/4) Epoch 20, batch 850, loss[loss=2.172, simple_loss=0.2972, pruned_loss=0.06029, codebook_loss=19.63, over 7018.00 frames.], tot_loss[loss=2.149, simple_loss=0.2571, pruned_loss=0.04092, codebook_loss=19.8, over 1400763.91 frames.], batch size: 26, lr: 8.33e-04
+2022-05-27 18:15:20,824 INFO [train.py:823] (3/4) Epoch 20, batch 900, loss[loss=2.135, simple_loss=0.2265, pruned_loss=0.03908, codebook_loss=19.82, over 6796.00 frames.], tot_loss[loss=2.149, simple_loss=0.2575, pruned_loss=0.04096, codebook_loss=19.79, over 1397727.15 frames.], batch size: 15, lr: 8.31e-04
+2022-05-27 18:16:14,133 INFO [train.py:823] (3/4) Epoch 21, batch 0, loss[loss=2.061, simple_loss=0.242, pruned_loss=0.03527, codebook_loss=19.04, over 7196.00 frames.], tot_loss[loss=2.061, simple_loss=0.242, pruned_loss=0.03527, codebook_loss=19.04, over 7196.00 frames.], batch size: 18, lr: 8.11e-04
+2022-05-27 18:16:54,242 INFO [train.py:823] (3/4) Epoch 21, batch 50, loss[loss=2.12, simple_loss=0.2761, pruned_loss=0.04191, codebook_loss=19.4, over 7176.00 frames.], tot_loss[loss=2.134, simple_loss=0.2563, pruned_loss=0.04019, codebook_loss=19.66, over 318777.74 frames.], batch size: 25, lr: 8.10e-04
+2022-05-27 18:17:33,850 INFO [train.py:823] (3/4) Epoch 21, batch 100, loss[loss=2.116, simple_loss=0.2767, pruned_loss=0.03875, codebook_loss=19.39, over 6488.00 frames.], tot_loss[loss=2.113, simple_loss=0.2532, pruned_loss=0.03793, codebook_loss=19.48, over 562583.16 frames.], batch size: 34, lr: 8.09e-04
+2022-05-27 18:18:14,079 INFO [train.py:823] (3/4) Epoch 21, batch 150, loss[loss=2.151, simple_loss=0.2424, pruned_loss=0.03242, codebook_loss=19.97, over 7281.00 frames.], tot_loss[loss=2.12, simple_loss=0.254, pruned_loss=0.03864, codebook_loss=19.54, over 755674.57 frames.], batch size: 20, lr: 8.08e-04
+2022-05-27 18:18:54,160 INFO [train.py:823] (3/4) Epoch 21, batch 200, loss[loss=2.021, simple_loss=0.225, pruned_loss=0.02615, codebook_loss=18.82, over 7291.00 frames.], tot_loss[loss=2.125, simple_loss=0.2553, pruned_loss=0.03942, codebook_loss=19.58, over 903116.72 frames.], batch size: 18, lr: 8.07e-04
+2022-05-27 18:19:34,331 INFO [train.py:823] (3/4) Epoch 21, batch 250, loss[loss=2.04, simple_loss=0.2356, pruned_loss=0.03166, codebook_loss=18.9, over 7283.00 frames.], tot_loss[loss=2.122, simple_loss=0.255, pruned_loss=0.03945, codebook_loss=19.55, over 1011286.32 frames.], batch size: 20, lr: 8.06e-04
+2022-05-27 18:20:13,835 INFO [train.py:823] (3/4) Epoch 21, batch 300, loss[loss=2.122, simple_loss=0.2578, pruned_loss=0.04256, codebook_loss=19.5, over 6622.00 frames.], tot_loss[loss=2.126, simple_loss=0.2555, pruned_loss=0.03879, codebook_loss=19.6, over 1099538.36 frames.], batch size: 34, lr: 8.05e-04
+2022-05-27 18:20:53,793 INFO [train.py:823] (3/4) Epoch 21, batch 350, loss[loss=2.119, simple_loss=0.2873, pruned_loss=0.04749, codebook_loss=19.28, over 7416.00 frames.], tot_loss[loss=2.125, simple_loss=0.2555, pruned_loss=0.03879, codebook_loss=19.59, over 1170407.74 frames.], batch size: 22, lr: 8.04e-04
+2022-05-27 18:21:36,256 INFO [train.py:823] (3/4) Epoch 21, batch 400, loss[loss=2.102, simple_loss=0.2346, pruned_loss=0.03568, codebook_loss=19.49, over 7297.00 frames.], tot_loss[loss=2.131, simple_loss=0.2568, pruned_loss=0.03957, codebook_loss=19.63, over 1225729.28 frames.], batch size: 17, lr: 8.03e-04
+2022-05-27 18:22:17,603 INFO [train.py:823] (3/4) Epoch 21, batch 450, loss[loss=2.101, simple_loss=0.2615, pruned_loss=0.03764, codebook_loss=19.32, over 7189.00 frames.], tot_loss[loss=2.136, simple_loss=0.2569, pruned_loss=0.04025, codebook_loss=19.68, over 1270355.17 frames.], batch size: 21, lr: 8.02e-04
+2022-05-27 18:22:57,217 INFO [train.py:823] (3/4) Epoch 21, batch 500, loss[loss=1.998, simple_loss=0.2159, pruned_loss=0.0247, codebook_loss=18.66, over 7181.00 frames.], tot_loss[loss=2.135, simple_loss=0.257, pruned_loss=0.03989, codebook_loss=19.67, over 1303730.54 frames.], batch size: 18, lr: 8.01e-04
+2022-05-27 18:23:37,556 INFO [train.py:823] (3/4) Epoch 21, batch 550, loss[loss=2.063, simple_loss=0.2651, pruned_loss=0.0411, codebook_loss=18.89, over 7372.00 frames.], tot_loss[loss=2.129, simple_loss=0.2558, pruned_loss=0.03938, codebook_loss=19.62, over 1335434.53 frames.], batch size: 21, lr: 8.00e-04
+2022-05-27 18:24:17,352 INFO [train.py:823] (3/4) Epoch 21, batch 600, loss[loss=2.197, simple_loss=0.2684, pruned_loss=0.04783, codebook_loss=20.15, over 6640.00 frames.], tot_loss[loss=2.131, simple_loss=0.2561, pruned_loss=0.03973, codebook_loss=19.63, over 1352936.60 frames.], batch size: 34, lr: 8.00e-04
+2022-05-27 18:24:57,554 INFO [train.py:823] (3/4) Epoch 21, batch 650, loss[loss=2.163, simple_loss=0.2846, pruned_loss=0.05266, codebook_loss=19.68, over 7302.00 frames.], tot_loss[loss=2.137, simple_loss=0.2568, pruned_loss=0.0401, codebook_loss=19.69, over 1368950.96 frames.], batch size: 22, lr: 7.99e-04
+2022-05-27 18:25:36,986 INFO [train.py:823] (3/4) Epoch 21, batch 700, loss[loss=2.157, simple_loss=0.2642, pruned_loss=0.04201, codebook_loss=19.83, over 7188.00 frames.], tot_loss[loss=2.14, simple_loss=0.2582, pruned_loss=0.0408, codebook_loss=19.7, over 1379664.86 frames.], batch size: 20, lr: 7.98e-04
+2022-05-27 18:26:16,782 INFO [train.py:823] (3/4) Epoch 21, batch 750, loss[loss=2.154, simple_loss=0.2457, pruned_loss=0.02581, codebook_loss=20.06, over 7227.00 frames.], tot_loss[loss=2.137, simple_loss=0.2567, pruned_loss=0.04054, codebook_loss=19.68, over 1378049.41 frames.], batch size: 25, lr: 7.97e-04
+2022-05-27 18:26:56,253 INFO [train.py:823] (3/4) Epoch 21, batch 800, loss[loss=2.115, simple_loss=0.2605, pruned_loss=0.03478, codebook_loss=19.5, over 7338.00 frames.], tot_loss[loss=2.131, simple_loss=0.2563, pruned_loss=0.03986, codebook_loss=19.63, over 1384414.58 frames.], batch size: 23, lr: 7.96e-04
+2022-05-27 18:27:36,613 INFO [train.py:823] (3/4) Epoch 21, batch 850, loss[loss=2.272, simple_loss=0.253, pruned_loss=0.03596, codebook_loss=21.09, over 7206.00 frames.], tot_loss[loss=2.129, simple_loss=0.2554, pruned_loss=0.03933, codebook_loss=19.62, over 1389769.94 frames.], batch size: 20, lr: 7.95e-04
+2022-05-27 18:28:15,984 INFO [train.py:823] (3/4) Epoch 21, batch 900, loss[loss=2.047, simple_loss=0.2457, pruned_loss=0.02831, codebook_loss=18.95, over 7367.00 frames.], tot_loss[loss=2.13, simple_loss=0.2556, pruned_loss=0.03962, codebook_loss=19.63, over 1388052.14 frames.], batch size: 20, lr: 7.94e-04
+2022-05-27 18:29:10,616 INFO [train.py:823] (3/4) Epoch 22, batch 0, loss[loss=2.004, simple_loss=0.2485, pruned_loss=0.02459, codebook_loss=18.55, over 7367.00 frames.], tot_loss[loss=2.004, simple_loss=0.2485, pruned_loss=0.02459, codebook_loss=18.55, over 7367.00 frames.], batch size: 21, lr: 7.75e-04
+2022-05-27 18:29:50,464 INFO [train.py:823] (3/4) Epoch 22, batch 50, loss[loss=2.166, simple_loss=0.2535, pruned_loss=0.03764, codebook_loss=20.01, over 7158.00 frames.], tot_loss[loss=2.083, simple_loss=0.2486, pruned_loss=0.03551, codebook_loss=19.23, over 322231.64 frames.], batch size: 22, lr: 7.74e-04
+2022-05-27 18:30:30,764 INFO [train.py:823] (3/4) Epoch 22, batch 100, loss[loss=2.171, simple_loss=0.2685, pruned_loss=0.03911, codebook_loss=19.98, over 7108.00 frames.], tot_loss[loss=2.097, simple_loss=0.2519, pruned_loss=0.03686, codebook_loss=19.34, over 567522.49 frames.], batch size: 20, lr: 7.73e-04
+2022-05-27 18:31:10,245 INFO [train.py:823] (3/4) Epoch 22, batch 150, loss[loss=2.22, simple_loss=0.2778, pruned_loss=0.05545, codebook_loss=20.25, over 4709.00 frames.], tot_loss[loss=2.117, simple_loss=0.254, pruned_loss=0.0382, codebook_loss=19.51, over 754747.52 frames.], batch size: 46, lr: 7.73e-04
+2022-05-27 18:31:50,140 INFO [train.py:823] (3/4) Epoch 22, batch 200, loss[loss=2.118, simple_loss=0.2697, pruned_loss=0.03894, codebook_loss=19.44, over 7110.00 frames.], tot_loss[loss=2.117, simple_loss=0.2545, pruned_loss=0.03854, codebook_loss=19.52, over 898540.36 frames.], batch size: 20, lr: 7.72e-04
+2022-05-27 18:32:29,936 INFO [train.py:823] (3/4) Epoch 22, batch 250, loss[loss=2.271, simple_loss=0.2365, pruned_loss=0.03132, codebook_loss=21.21, over 7111.00 frames.], tot_loss[loss=2.118, simple_loss=0.2546, pruned_loss=0.03844, codebook_loss=19.52, over 1016344.23 frames.], batch size: 18, lr: 7.71e-04
+2022-05-27 18:33:10,003 INFO [train.py:823] (3/4) Epoch 22, batch 300, loss[loss=2.129, simple_loss=0.2373, pruned_loss=0.03333, codebook_loss=19.77, over 7185.00 frames.], tot_loss[loss=2.12, simple_loss=0.2552, pruned_loss=0.03902, codebook_loss=19.53, over 1102390.70 frames.], batch size: 18, lr: 7.70e-04
+2022-05-27 18:33:49,729 INFO [train.py:823] (3/4) Epoch 22, batch 350, loss[loss=2.106, simple_loss=0.2408, pruned_loss=0.03036, codebook_loss=19.55, over 6959.00 frames.], tot_loss[loss=2.122, simple_loss=0.2554, pruned_loss=0.03969, codebook_loss=19.54, over 1173769.66 frames.], batch size: 29, lr: 7.69e-04
+2022-05-27 18:34:29,889 INFO [train.py:823] (3/4) Epoch 22, batch 400, loss[loss=2.171, simple_loss=0.2798, pruned_loss=0.04767, codebook_loss=19.84, over 7191.00 frames.], tot_loss[loss=2.122, simple_loss=0.2543, pruned_loss=0.03942, codebook_loss=19.55, over 1231004.99 frames.], batch size: 21, lr: 7.68e-04
+2022-05-27 18:35:09,673 INFO [train.py:823] (3/4) Epoch 22, batch 450, loss[loss=2.212, simple_loss=0.2396, pruned_loss=0.04371, codebook_loss=20.48, over 6867.00 frames.], tot_loss[loss=2.123, simple_loss=0.2542, pruned_loss=0.03953, codebook_loss=19.56, over 1277487.58 frames.], batch size: 15, lr: 7.67e-04
+2022-05-27 18:35:49,494 INFO [train.py:823] (3/4) Epoch 22, batch 500, loss[loss=2.169, simple_loss=0.2706, pruned_loss=0.0432, codebook_loss=19.91, over 6536.00 frames.], tot_loss[loss=2.122, simple_loss=0.2539, pruned_loss=0.03941, codebook_loss=19.55, over 1304063.79 frames.], batch size: 34, lr: 7.66e-04
+2022-05-27 18:36:29,456 INFO [train.py:823] (3/4) Epoch 22, batch 550, loss[loss=2.033, simple_loss=0.2673, pruned_loss=0.02917, codebook_loss=18.7, over 6875.00 frames.], tot_loss[loss=2.119, simple_loss=0.2535, pruned_loss=0.03907, codebook_loss=19.53, over 1330853.32 frames.], batch size: 29, lr: 7.65e-04
+2022-05-27 18:37:09,854 INFO [train.py:823] (3/4) Epoch 22, batch 600, loss[loss=2.094, simple_loss=0.2154, pruned_loss=0.03833, codebook_loss=19.48, over 7023.00 frames.], tot_loss[loss=2.12, simple_loss=0.2528, pruned_loss=0.03858, codebook_loss=19.55, over 1350076.86 frames.], batch size: 17, lr: 7.65e-04
+2022-05-27 18:37:49,497 INFO [train.py:823] (3/4) Epoch 22, batch 650, loss[loss=2.244, simple_loss=0.285, pruned_loss=0.05305, codebook_loss=20.49, over 7112.00 frames.], tot_loss[loss=2.121, simple_loss=0.2531, pruned_loss=0.03882, codebook_loss=19.56, over 1359773.81 frames.], batch size: 20, lr: 7.64e-04
+2022-05-27 18:38:29,554 INFO [train.py:823] (3/4) Epoch 22, batch 700, loss[loss=2.078, simple_loss=0.2582, pruned_loss=0.04092, codebook_loss=19.08, over 7093.00 frames.], tot_loss[loss=2.118, simple_loss=0.2527, pruned_loss=0.03807, codebook_loss=19.53, over 1372683.96 frames.], batch size: 19, lr: 7.63e-04
+2022-05-27 18:39:10,335 INFO [train.py:823] (3/4) Epoch 22, batch 750, loss[loss=2.046, simple_loss=0.2387, pruned_loss=0.02504, codebook_loss=19.02, over 7006.00 frames.], tot_loss[loss=2.115, simple_loss=0.2527, pruned_loss=0.03801, codebook_loss=19.5, over 1381709.99 frames.], batch size: 16, lr: 7.62e-04
+2022-05-27 18:39:50,582 INFO [train.py:823] (3/4) Epoch 22, batch 800, loss[loss=2.084, simple_loss=0.2452, pruned_loss=0.03843, codebook_loss=19.23, over 7381.00 frames.], tot_loss[loss=2.118, simple_loss=0.2526, pruned_loss=0.03797, codebook_loss=19.53, over 1391358.33 frames.], batch size: 20, lr: 7.61e-04
+2022-05-27 18:40:30,227 INFO [train.py:823] (3/4) Epoch 22, batch 850, loss[loss=2.067, simple_loss=0.2557, pruned_loss=0.0283, codebook_loss=19.1, over 6433.00 frames.], tot_loss[loss=2.114, simple_loss=0.2532, pruned_loss=0.03812, codebook_loss=19.5, over 1400670.62 frames.], batch size: 34, lr: 7.60e-04
+2022-05-27 18:41:10,120 INFO [train.py:823] (3/4) Epoch 22, batch 900, loss[loss=2.04, simple_loss=0.266, pruned_loss=0.03842, codebook_loss=18.69, over 7154.00 frames.], tot_loss[loss=2.117, simple_loss=0.2541, pruned_loss=0.03886, codebook_loss=19.51, over 1405432.18 frames.], batch size: 23, lr: 7.59e-04
+2022-05-27 18:42:03,935 INFO [train.py:823] (3/4) Epoch 23, batch 0, loss[loss=1.97, simple_loss=0.2215, pruned_loss=0.02644, codebook_loss=18.32, over 7233.00 frames.], tot_loss[loss=1.97, simple_loss=0.2215, pruned_loss=0.02644, codebook_loss=18.32, over 7233.00 frames.], batch size: 16, lr: 7.42e-04
+2022-05-27 18:42:44,097 INFO [train.py:823] (3/4) Epoch 23, batch 50, loss[loss=2.191, simple_loss=0.2542, pruned_loss=0.03668, codebook_loss=20.27, over 7387.00 frames.], tot_loss[loss=2.152, simple_loss=0.255, pruned_loss=0.04026, codebook_loss=19.85, over 321206.00 frames.], batch size: 21, lr: 7.41e-04
+2022-05-27 18:43:23,808 INFO [train.py:823] (3/4) Epoch 23, batch 100, loss[loss=2.235, simple_loss=0.2468, pruned_loss=0.03332, codebook_loss=20.78, over 7368.00 frames.], tot_loss[loss=2.111, simple_loss=0.2529, pruned_loss=0.03784, codebook_loss=19.47, over 562013.06 frames.], batch size: 20, lr: 7.41e-04
+2022-05-27 18:44:03,969 INFO [train.py:823] (3/4) Epoch 23, batch 150, loss[loss=2.002, simple_loss=0.2259, pruned_loss=0.02491, codebook_loss=18.64, over 7324.00 frames.], tot_loss[loss=2.112, simple_loss=0.2544, pruned_loss=0.0383, codebook_loss=19.47, over 751975.59 frames.], batch size: 18, lr: 7.40e-04
+2022-05-27 18:44:43,913 INFO [train.py:823] (3/4) Epoch 23, batch 200, loss[loss=2.114, simple_loss=0.2554, pruned_loss=0.04762, codebook_loss=19.38, over 4991.00 frames.], tot_loss[loss=2.113, simple_loss=0.2541, pruned_loss=0.03824, codebook_loss=19.47, over 897660.47 frames.], batch size: 47, lr: 7.39e-04
+2022-05-27 18:45:24,177 INFO [train.py:823] (3/4) Epoch 23, batch 250, loss[loss=2.255, simple_loss=0.2436, pruned_loss=0.04319, codebook_loss=20.9, over 7102.00 frames.], tot_loss[loss=2.118, simple_loss=0.2544, pruned_loss=0.03854, codebook_loss=19.52, over 1017295.13 frames.], batch size: 18, lr: 7.38e-04
+2022-05-27 18:46:03,755 INFO [train.py:823] (3/4) Epoch 23, batch 300, loss[loss=2.034, simple_loss=0.2532, pruned_loss=0.03495, codebook_loss=18.72, over 7287.00 frames.], tot_loss[loss=2.112, simple_loss=0.2548, pruned_loss=0.03826, codebook_loss=19.46, over 1110589.70 frames.], batch size: 22, lr: 7.37e-04
+2022-05-27 18:46:48,083 INFO [train.py:823] (3/4) Epoch 23, batch 350, loss[loss=2.128, simple_loss=0.2585, pruned_loss=0.04613, codebook_loss=19.52, over 7276.00 frames.], tot_loss[loss=2.107, simple_loss=0.2537, pruned_loss=0.03802, codebook_loss=19.43, over 1181517.72 frames.], batch size: 20, lr: 7.36e-04
+2022-05-27 18:47:28,151 INFO [train.py:823] (3/4) Epoch 23, batch 400, loss[loss=2.285, simple_loss=0.2241, pruned_loss=0.03551, codebook_loss=21.38, over 7303.00 frames.], tot_loss[loss=2.108, simple_loss=0.2517, pruned_loss=0.03741, codebook_loss=19.45, over 1233521.08 frames.], batch size: 17, lr: 7.36e-04
+2022-05-27 18:48:08,281 INFO [train.py:823] (3/4) Epoch 23, batch 450, loss[loss=2.237, simple_loss=0.2589, pruned_loss=0.04324, codebook_loss=20.65, over 5333.00 frames.], tot_loss[loss=2.113, simple_loss=0.2519, pruned_loss=0.03778, codebook_loss=19.5, over 1272817.08 frames.], batch size: 46, lr: 7.35e-04
+2022-05-27 18:48:47,876 INFO [train.py:823] (3/4) Epoch 23, batch 500, loss[loss=2.27, simple_loss=0.2771, pruned_loss=0.03709, codebook_loss=20.94, over 6413.00 frames.], tot_loss[loss=2.119, simple_loss=0.2535, pruned_loss=0.03844, codebook_loss=19.53, over 1302570.90 frames.], batch size: 34, lr: 7.34e-04
+2022-05-27 18:49:28,078 INFO [train.py:823] (3/4) Epoch 23, batch 550, loss[loss=2.073, simple_loss=0.285, pruned_loss=0.04857, codebook_loss=18.82, over 7206.00 frames.], tot_loss[loss=2.124, simple_loss=0.255, pruned_loss=0.03885, codebook_loss=19.57, over 1332882.41 frames.], batch size: 24, lr: 7.33e-04
+2022-05-27 18:50:07,717 INFO [train.py:823] (3/4) Epoch 23, batch 600, loss[loss=2.064, simple_loss=0.2523, pruned_loss=0.03331, codebook_loss=19.05, over 4475.00 frames.], tot_loss[loss=2.131, simple_loss=0.2545, pruned_loss=0.03873, codebook_loss=19.65, over 1348447.77 frames.], batch size: 47, lr: 7.32e-04
+2022-05-27 18:50:47,672 INFO [train.py:823] (3/4) Epoch 23, batch 650, loss[loss=2.132, simple_loss=0.2599, pruned_loss=0.04762, codebook_loss=19.55, over 7106.00 frames.], tot_loss[loss=2.119, simple_loss=0.2533, pruned_loss=0.03783, codebook_loss=19.55, over 1362977.09 frames.], batch size: 19, lr: 7.32e-04
+2022-05-27 18:51:27,248 INFO [train.py:823] (3/4) Epoch 23, batch 700, loss[loss=2.104, simple_loss=0.2316, pruned_loss=0.03999, codebook_loss=19.48, over 6989.00 frames.], tot_loss[loss=2.123, simple_loss=0.253, pruned_loss=0.03843, codebook_loss=19.58, over 1369696.88 frames.], batch size: 16, lr: 7.31e-04
+2022-05-27 18:52:07,634 INFO [train.py:823] (3/4) Epoch 23, batch 750, loss[loss=2.164, simple_loss=0.267, pruned_loss=0.05801, codebook_loss=19.73, over 4894.00 frames.], tot_loss[loss=2.123, simple_loss=0.2535, pruned_loss=0.03834, codebook_loss=19.58, over 1376159.89 frames.], batch size: 46, lr: 7.30e-04
+2022-05-27 18:52:47,394 INFO [train.py:823] (3/4) Epoch 23, batch 800, loss[loss=2.1, simple_loss=0.2328, pruned_loss=0.03592, codebook_loss=19.48, over 7198.00 frames.], tot_loss[loss=2.115, simple_loss=0.2521, pruned_loss=0.03747, codebook_loss=19.51, over 1388884.77 frames.], batch size: 18, lr: 7.29e-04
+2022-05-27 18:53:27,292 INFO [train.py:823] (3/4) Epoch 23, batch 850, loss[loss=2.128, simple_loss=0.2854, pruned_loss=0.04826, codebook_loss=19.37, over 7153.00 frames.], tot_loss[loss=2.113, simple_loss=0.2521, pruned_loss=0.03739, codebook_loss=19.5, over 1396064.42 frames.], batch size: 23, lr: 7.28e-04
+2022-05-27 18:54:07,052 INFO [train.py:823] (3/4) Epoch 23, batch 900, loss[loss=2.315, simple_loss=0.2334, pruned_loss=0.04048, codebook_loss=21.58, over 7005.00 frames.], tot_loss[loss=2.115, simple_loss=0.2514, pruned_loss=0.03754, codebook_loss=19.52, over 1400473.15 frames.], batch size: 17, lr: 7.28e-04
+2022-05-27 18:55:01,303 INFO [train.py:823] (3/4) Epoch 24, batch 0, loss[loss=1.937, simple_loss=0.2234, pruned_loss=0.02087, codebook_loss=18.04, over 7301.00 frames.], tot_loss[loss=1.937, simple_loss=0.2234, pruned_loss=0.02087, codebook_loss=18.04, over 7301.00 frames.], batch size: 18, lr: 7.12e-04
+2022-05-27 18:55:40,720 INFO [train.py:823] (3/4) Epoch 24, batch 50, loss[loss=1.991, simple_loss=0.2254, pruned_loss=0.03561, codebook_loss=18.42, over 7162.00 frames.], tot_loss[loss=2.081, simple_loss=0.2495, pruned_loss=0.03534, codebook_loss=19.21, over 318684.03 frames.], batch size: 17, lr: 7.11e-04
+2022-05-27 18:56:20,770 INFO [train.py:823] (3/4) Epoch 24, batch 100, loss[loss=2.087, simple_loss=0.2577, pruned_loss=0.03585, codebook_loss=19.23, over 6502.00 frames.], tot_loss[loss=2.089, simple_loss=0.2517, pruned_loss=0.03637, codebook_loss=19.26, over 559266.72 frames.], batch size: 34, lr: 7.10e-04
+2022-05-27 18:57:00,444 INFO [train.py:823] (3/4) Epoch 24, batch 150, loss[loss=2.194, simple_loss=0.2591, pruned_loss=0.04084, codebook_loss=20.24, over 6947.00 frames.], tot_loss[loss=2.088, simple_loss=0.253, pruned_loss=0.03685, codebook_loss=19.25, over 749961.44 frames.], batch size: 29, lr: 7.10e-04
+2022-05-27 18:57:40,629 INFO [train.py:823] (3/4) Epoch 24, batch 200, loss[loss=2.145, simple_loss=0.2682, pruned_loss=0.03516, codebook_loss=19.75, over 7284.00 frames.], tot_loss[loss=2.083, simple_loss=0.2515, pruned_loss=0.03626, codebook_loss=19.21, over 899671.12 frames.], batch size: 21, lr: 7.09e-04
+2022-05-27 18:58:20,122 INFO [train.py:823] (3/4) Epoch 24, batch 250, loss[loss=2.206, simple_loss=0.208, pruned_loss=0.02458, codebook_loss=20.77, over 7283.00 frames.], tot_loss[loss=2.087, simple_loss=0.2504, pruned_loss=0.03574, codebook_loss=19.26, over 1015311.09 frames.], batch size: 17, lr: 7.08e-04
+2022-05-27 18:59:00,250 INFO [train.py:823] (3/4) Epoch 24, batch 300, loss[loss=2.043, simple_loss=0.2605, pruned_loss=0.03862, codebook_loss=18.74, over 7326.00 frames.], tot_loss[loss=2.098, simple_loss=0.2511, pruned_loss=0.03672, codebook_loss=19.36, over 1100125.32 frames.], batch size: 23, lr: 7.07e-04
+2022-05-27 18:59:40,287 INFO [train.py:823] (3/4) Epoch 24, batch 350, loss[loss=2.056, simple_loss=0.2019, pruned_loss=0.03175, codebook_loss=19.23, over 7303.00 frames.], tot_loss[loss=2.097, simple_loss=0.2505, pruned_loss=0.03649, codebook_loss=19.36, over 1175170.99 frames.], batch size: 17, lr: 7.07e-04
+2022-05-27 19:00:20,413 INFO [train.py:823] (3/4) Epoch 24, batch 400, loss[loss=2.031, simple_loss=0.245, pruned_loss=0.0349, codebook_loss=18.74, over 7335.00 frames.], tot_loss[loss=2.097, simple_loss=0.2501, pruned_loss=0.03654, codebook_loss=19.35, over 1227707.11 frames.], batch size: 23, lr: 7.06e-04
+2022-05-27 19:01:00,218 INFO [train.py:823] (3/4) Epoch 24, batch 450, loss[loss=2.11, simple_loss=0.2154, pruned_loss=0.02209, codebook_loss=19.8, over 7187.00 frames.], tot_loss[loss=2.094, simple_loss=0.2494, pruned_loss=0.03603, codebook_loss=19.33, over 1269240.81 frames.], batch size: 18, lr: 7.05e-04
+2022-05-27 19:01:40,603 INFO [train.py:823] (3/4) Epoch 24, batch 500, loss[loss=2.014, simple_loss=0.2559, pruned_loss=0.03092, codebook_loss=18.55, over 7294.00 frames.], tot_loss[loss=2.094, simple_loss=0.2497, pruned_loss=0.03619, codebook_loss=19.33, over 1304751.91 frames.], batch size: 21, lr: 7.04e-04
+2022-05-27 19:02:20,510 INFO [train.py:823] (3/4) Epoch 24, batch 550, loss[loss=2.051, simple_loss=0.2653, pruned_loss=0.02647, codebook_loss=18.92, over 6468.00 frames.], tot_loss[loss=2.094, simple_loss=0.2507, pruned_loss=0.03629, codebook_loss=19.32, over 1328594.44 frames.], batch size: 34, lr: 7.04e-04
+2022-05-27 19:03:01,848 INFO [train.py:823] (3/4) Epoch 24, batch 600, loss[loss=2.073, simple_loss=0.2729, pruned_loss=0.05073, codebook_loss=18.85, over 7148.00 frames.], tot_loss[loss=2.094, simple_loss=0.2511, pruned_loss=0.03643, codebook_loss=19.32, over 1346230.34 frames.], batch size: 23, lr: 7.03e-04
+2022-05-27 19:03:41,793 INFO [train.py:823] (3/4) Epoch 24, batch 650, loss[loss=2.16, simple_loss=0.2339, pruned_loss=0.03287, codebook_loss=20.11, over 7097.00 frames.], tot_loss[loss=2.096, simple_loss=0.2515, pruned_loss=0.03663, codebook_loss=19.33, over 1359447.53 frames.], batch size: 19, lr: 7.02e-04
+2022-05-27 19:04:21,936 INFO [train.py:823] (3/4) Epoch 24, batch 700, loss[loss=2.091, simple_loss=0.277, pruned_loss=0.04296, codebook_loss=19.09, over 7164.00 frames.], tot_loss[loss=2.098, simple_loss=0.2528, pruned_loss=0.03716, codebook_loss=19.35, over 1372411.12 frames.], batch size: 22, lr: 7.01e-04
+2022-05-27 19:05:01,669 INFO [train.py:823] (3/4) Epoch 24, batch 750, loss[loss=2.07, simple_loss=0.2446, pruned_loss=0.03687, codebook_loss=19.11, over 7110.00 frames.], tot_loss[loss=2.096, simple_loss=0.2524, pruned_loss=0.03692, codebook_loss=19.33, over 1385176.64 frames.], batch size: 20, lr: 7.01e-04
+2022-05-27 19:05:41,788 INFO [train.py:823] (3/4) Epoch 24, batch 800, loss[loss=2.229, simple_loss=0.2353, pruned_loss=0.03952, codebook_loss=20.71, over 7256.00 frames.], tot_loss[loss=2.098, simple_loss=0.252, pruned_loss=0.03672, codebook_loss=19.35, over 1393410.46 frames.], batch size: 16, lr: 7.00e-04
+2022-05-27 19:06:21,572 INFO [train.py:823] (3/4) Epoch 24, batch 850, loss[loss=1.992, simple_loss=0.2576, pruned_loss=0.03143, codebook_loss=18.32, over 7093.00 frames.], tot_loss[loss=2.097, simple_loss=0.2515, pruned_loss=0.03657, codebook_loss=19.35, over 1396853.47 frames.], batch size: 20, lr: 6.99e-04
+2022-05-27 19:07:01,707 INFO [train.py:823] (3/4) Epoch 24, batch 900, loss[loss=2.171, simple_loss=0.2427, pruned_loss=0.0325, codebook_loss=20.17, over 6495.00 frames.], tot_loss[loss=2.102, simple_loss=0.2521, pruned_loss=0.03717, codebook_loss=19.38, over 1400176.05 frames.], batch size: 34, lr: 6.98e-04
+2022-05-27 19:07:42,334 INFO [train.py:823] (3/4) Epoch 24, batch 950, loss[loss=2.117, simple_loss=0.2521, pruned_loss=0.04499, codebook_loss=19.46, over 7091.00 frames.], tot_loss[loss=2.106, simple_loss=0.2529, pruned_loss=0.03732, codebook_loss=19.42, over 1395377.36 frames.], batch size: 18, lr: 6.98e-04
+2022-05-27 19:07:57,248 INFO [train.py:823] (3/4) Epoch 25, batch 0, loss[loss=1.968, simple_loss=0.2595, pruned_loss=0.02173, codebook_loss=18.16, over 7290.00 frames.], tot_loss[loss=1.968, simple_loss=0.2595, pruned_loss=0.02173, codebook_loss=18.16, over 7290.00 frames.], batch size: 21, lr: 6.84e-04
+2022-05-27 19:08:37,534 INFO [train.py:823] (3/4) Epoch 25, batch 50, loss[loss=2.097, simple_loss=0.2309, pruned_loss=0.03892, codebook_loss=19.42, over 7311.00 frames.], tot_loss[loss=2.088, simple_loss=0.2465, pruned_loss=0.03448, codebook_loss=19.3, over 323952.04 frames.], batch size: 17, lr: 6.83e-04
+2022-05-27 19:09:17,673 INFO [train.py:823] (3/4) Epoch 25, batch 100, loss[loss=2.235, simple_loss=0.2666, pruned_loss=0.05484, codebook_loss=20.47, over 6863.00 frames.], tot_loss[loss=2.093, simple_loss=0.2486, pruned_loss=0.03594, codebook_loss=19.33, over 563756.79 frames.], batch size: 15, lr: 6.82e-04
+2022-05-27 19:09:58,096 INFO [train.py:823] (3/4) Epoch 25, batch 150, loss[loss=2.162, simple_loss=0.2852, pruned_loss=0.03726, codebook_loss=19.82, over 7315.00 frames.], tot_loss[loss=2.099, simple_loss=0.2481, pruned_loss=0.03539, codebook_loss=19.39, over 758516.71 frames.], batch size: 22, lr: 6.82e-04
+2022-05-27 19:10:38,131 INFO [train.py:823] (3/4) Epoch 25, batch 200, loss[loss=2.157, simple_loss=0.2719, pruned_loss=0.04887, codebook_loss=19.72, over 7288.00 frames.], tot_loss[loss=2.089, simple_loss=0.2489, pruned_loss=0.03562, codebook_loss=19.29, over 910708.14 frames.], batch size: 21, lr: 6.81e-04
+2022-05-27 19:11:21,037 INFO [train.py:823] (3/4) Epoch 25, batch 250, loss[loss=2.071, simple_loss=0.2223, pruned_loss=0.02891, codebook_loss=19.31, over 7287.00 frames.], tot_loss[loss=2.084, simple_loss=0.249, pruned_loss=0.03588, codebook_loss=19.24, over 1023237.71 frames.], batch size: 17, lr: 6.80e-04
+2022-05-27 19:12:03,745 INFO [train.py:823] (3/4) Epoch 25, batch 300, loss[loss=2.059, simple_loss=0.2591, pruned_loss=0.03018, codebook_loss=18.99, over 7287.00 frames.], tot_loss[loss=2.079, simple_loss=0.249, pruned_loss=0.03523, codebook_loss=19.2, over 1116635.04 frames.], batch size: 21, lr: 6.80e-04
+2022-05-27 19:12:48,205 INFO [train.py:823] (3/4) Epoch 25, batch 350, loss[loss=2.36, simple_loss=0.2706, pruned_loss=0.05228, codebook_loss=21.73, over 7145.00 frames.], tot_loss[loss=2.081, simple_loss=0.2492, pruned_loss=0.03539, codebook_loss=19.21, over 1182724.80 frames.], batch size: 23, lr: 6.79e-04
+2022-05-27 19:13:30,505 INFO [train.py:823] (3/4) Epoch 25, batch 400, loss[loss=2.002, simple_loss=0.2429, pruned_loss=0.02854, codebook_loss=18.52, over 7239.00 frames.], tot_loss[loss=2.079, simple_loss=0.2504, pruned_loss=0.03535, codebook_loss=19.18, over 1239017.38 frames.], batch size: 25, lr: 6.78e-04
+2022-05-27 19:14:15,077 INFO [train.py:823] (3/4) Epoch 25, batch 450, loss[loss=2.011, simple_loss=0.2201, pruned_loss=0.01906, codebook_loss=18.82, over 6815.00 frames.], tot_loss[loss=2.085, simple_loss=0.2509, pruned_loss=0.03585, codebook_loss=19.23, over 1269972.45 frames.], batch size: 15, lr: 6.77e-04
+2022-05-27 19:14:56,680 INFO [train.py:823] (3/4) Epoch 25, batch 500, loss[loss=2.018, simple_loss=0.2149, pruned_loss=0.02176, codebook_loss=18.89, over 7003.00 frames.], tot_loss[loss=2.084, simple_loss=0.2512, pruned_loss=0.03605, codebook_loss=19.22, over 1303703.64 frames.], batch size: 16, lr: 6.77e-04
+2022-05-27 19:15:42,058 INFO [train.py:823] (3/4) Epoch 25, batch 550, loss[loss=2.387, simple_loss=0.2605, pruned_loss=0.04708, codebook_loss=22.1, over 7185.00 frames.], tot_loss[loss=2.094, simple_loss=0.2507, pruned_loss=0.03642, codebook_loss=19.32, over 1330660.59 frames.], batch size: 21, lr: 6.76e-04
+2022-05-27 19:16:24,005 INFO [train.py:823] (3/4) Epoch 25, batch 600, loss[loss=2.035, simple_loss=0.2689, pruned_loss=0.02774, codebook_loss=18.72, over 7281.00 frames.], tot_loss[loss=2.093, simple_loss=0.2492, pruned_loss=0.03588, codebook_loss=19.32, over 1343635.36 frames.], batch size: 21, lr: 6.75e-04
+2022-05-27 19:17:05,140 INFO [train.py:823] (3/4) Epoch 25, batch 650, loss[loss=2.249, simple_loss=0.2582, pruned_loss=0.03835, codebook_loss=20.81, over 7282.00 frames.], tot_loss[loss=2.093, simple_loss=0.2493, pruned_loss=0.03567, codebook_loss=19.33, over 1358812.33 frames.], batch size: 20, lr: 6.75e-04
+2022-05-27 19:17:47,810 INFO [train.py:823] (3/4) Epoch 25, batch 700, loss[loss=2.001, simple_loss=0.2141, pruned_loss=0.02791, codebook_loss=18.66, over 7157.00 frames.], tot_loss[loss=2.09, simple_loss=0.2492, pruned_loss=0.0354, codebook_loss=19.3, over 1370112.66 frames.], batch size: 17, lr: 6.74e-04
+2022-05-27 19:18:28,141 INFO [train.py:823] (3/4) Epoch 25, batch 750, loss[loss=2.156, simple_loss=0.2645, pruned_loss=0.03932, codebook_loss=19.84, over 7376.00 frames.], tot_loss[loss=2.093, simple_loss=0.2493, pruned_loss=0.03615, codebook_loss=19.32, over 1378485.75 frames.], batch size: 20, lr: 6.73e-04
+2022-05-27 19:19:08,116 INFO [train.py:823] (3/4) Epoch 25, batch 800, loss[loss=2.036, simple_loss=0.247, pruned_loss=0.03726, codebook_loss=18.75, over 7186.00 frames.], tot_loss[loss=2.09, simple_loss=0.2482, pruned_loss=0.03558, codebook_loss=19.3, over 1390966.57 frames.], batch size: 21, lr: 6.73e-04
+2022-05-27 19:19:48,349 INFO [train.py:823] (3/4) Epoch 25, batch 850, loss[loss=2.162, simple_loss=0.2249, pruned_loss=0.02604, codebook_loss=20.23, over 7199.00 frames.], tot_loss[loss=2.089, simple_loss=0.2491, pruned_loss=0.03555, codebook_loss=19.29, over 1396346.30 frames.], batch size: 18, lr: 6.72e-04
+2022-05-27 19:20:27,868 INFO [train.py:823] (3/4) Epoch 25, batch 900, loss[loss=2.072, simple_loss=0.2666, pruned_loss=0.03426, codebook_loss=19.05, over 6520.00 frames.], tot_loss[loss=2.085, simple_loss=0.2488, pruned_loss=0.03478, codebook_loss=19.25, over 1394619.07 frames.], batch size: 34, lr: 6.71e-04
+2022-05-27 19:21:22,333 INFO [train.py:823] (3/4) Epoch 26, batch 0, loss[loss=2.258, simple_loss=0.2146, pruned_loss=0.02933, codebook_loss=21.21, over 7322.00 frames.], tot_loss[loss=2.258, simple_loss=0.2146, pruned_loss=0.02933, codebook_loss=21.21, over 7322.00 frames.], batch size: 18, lr: 6.58e-04
+2022-05-27 19:22:03,632 INFO [train.py:823] (3/4) Epoch 26, batch 50, loss[loss=2.008, simple_loss=0.2468, pruned_loss=0.03463, codebook_loss=18.5, over 7369.00 frames.], tot_loss[loss=2.068, simple_loss=0.2467, pruned_loss=0.03387, codebook_loss=19.1, over 324754.65 frames.], batch size: 20, lr: 6.57e-04
+2022-05-27 19:22:43,981 INFO [train.py:823] (3/4) Epoch 26, batch 100, loss[loss=2.04, simple_loss=0.2489, pruned_loss=0.04278, codebook_loss=18.73, over 7212.00 frames.], tot_loss[loss=2.071, simple_loss=0.2479, pruned_loss=0.03426, codebook_loss=19.13, over 568123.11 frames.], batch size: 25, lr: 6.56e-04
+2022-05-27 19:23:23,786 INFO [train.py:823] (3/4) Epoch 26, batch 150, loss[loss=2.048, simple_loss=0.2682, pruned_loss=0.03695, codebook_loss=18.77, over 7164.00 frames.], tot_loss[loss=2.077, simple_loss=0.2468, pruned_loss=0.03448, codebook_loss=19.19, over 754137.70 frames.], batch size: 25, lr: 6.56e-04
+2022-05-27 19:24:03,986 INFO [train.py:823] (3/4) Epoch 26, batch 200, loss[loss=2.233, simple_loss=0.2438, pruned_loss=0.03641, codebook_loss=20.75, over 7101.00 frames.], tot_loss[loss=2.082, simple_loss=0.248, pruned_loss=0.03533, codebook_loss=19.23, over 900298.44 frames.], batch size: 18, lr: 6.55e-04
+2022-05-27 19:24:43,853 INFO [train.py:823] (3/4) Epoch 26, batch 250, loss[loss=1.983, simple_loss=0.2481, pruned_loss=0.03008, codebook_loss=18.29, over 7404.00 frames.], tot_loss[loss=2.085, simple_loss=0.2486, pruned_loss=0.03606, codebook_loss=19.25, over 1015815.07 frames.], batch size: 22, lr: 6.55e-04
+2022-05-27 19:25:27,425 INFO [train.py:823] (3/4) Epoch 26, batch 300, loss[loss=2.146, simple_loss=0.2542, pruned_loss=0.03882, codebook_loss=19.8, over 7103.00 frames.], tot_loss[loss=2.087, simple_loss=0.249, pruned_loss=0.03601, codebook_loss=19.27, over 1106369.97 frames.], batch size: 20, lr: 6.54e-04
+2022-05-27 19:26:07,490 INFO [train.py:823] (3/4) Epoch 26, batch 350, loss[loss=2.48, simple_loss=0.2554, pruned_loss=0.04496, codebook_loss=23.07, over 6630.00 frames.], tot_loss[loss=2.087, simple_loss=0.2492, pruned_loss=0.03608, codebook_loss=19.26, over 1177762.13 frames.], batch size: 34, lr: 6.53e-04
+2022-05-27 19:26:47,611 INFO [train.py:823] (3/4) Epoch 26, batch 400, loss[loss=2.015, simple_loss=0.2525, pruned_loss=0.04059, codebook_loss=18.49, over 7133.00 frames.], tot_loss[loss=2.083, simple_loss=0.2495, pruned_loss=0.03567, codebook_loss=19.22, over 1234719.89 frames.], batch size: 23, lr: 6.53e-04
+2022-05-27 19:27:28,676 INFO [train.py:823] (3/4) Epoch 26, batch 450, loss[loss=1.971, simple_loss=0.2365, pruned_loss=0.01984, codebook_loss=18.33, over 7188.00 frames.], tot_loss[loss=2.084, simple_loss=0.2494, pruned_loss=0.0356, codebook_loss=19.24, over 1274797.37 frames.], batch size: 21, lr: 6.52e-04
+2022-05-27 19:28:08,952 INFO [train.py:823] (3/4) Epoch 26, batch 500, loss[loss=2.086, simple_loss=0.2683, pruned_loss=0.04917, codebook_loss=19.03, over 7026.00 frames.], tot_loss[loss=2.083, simple_loss=0.2491, pruned_loss=0.03538, codebook_loss=19.23, over 1305367.79 frames.], batch size: 26, lr: 6.51e-04
+2022-05-27 19:28:49,089 INFO [train.py:823] (3/4) Epoch 26, batch 550, loss[loss=1.978, simple_loss=0.2329, pruned_loss=0.03426, codebook_loss=18.27, over 6995.00 frames.], tot_loss[loss=2.079, simple_loss=0.2487, pruned_loss=0.03491, codebook_loss=19.2, over 1328943.85 frames.], batch size: 16, lr: 6.51e-04
+2022-05-27 19:29:29,457 INFO [train.py:823] (3/4) Epoch 26, batch 600, loss[loss=2.002, simple_loss=0.258, pruned_loss=0.03139, codebook_loss=18.42, over 7306.00 frames.], tot_loss[loss=2.078, simple_loss=0.2488, pruned_loss=0.03517, codebook_loss=19.18, over 1348789.29 frames.], batch size: 22, lr: 6.50e-04
+2022-05-27 19:30:09,304 INFO [train.py:823] (3/4) Epoch 26, batch 650, loss[loss=2.218, simple_loss=0.2557, pruned_loss=0.0363, codebook_loss=20.54, over 7347.00 frames.], tot_loss[loss=2.076, simple_loss=0.2478, pruned_loss=0.03468, codebook_loss=19.17, over 1358037.22 frames.], batch size: 23, lr: 6.49e-04
+2022-05-27 19:30:49,388 INFO [train.py:823] (3/4) Epoch 26, batch 700, loss[loss=2.175, simple_loss=0.2662, pruned_loss=0.03427, codebook_loss=20.08, over 6982.00 frames.], tot_loss[loss=2.085, simple_loss=0.2489, pruned_loss=0.0353, codebook_loss=19.25, over 1371249.80 frames.], batch size: 26, lr: 6.49e-04
+2022-05-27 19:31:29,088 INFO [train.py:823] (3/4) Epoch 26, batch 750, loss[loss=1.985, simple_loss=0.2415, pruned_loss=0.02346, codebook_loss=18.41, over 7296.00 frames.], tot_loss[loss=2.088, simple_loss=0.2495, pruned_loss=0.03553, codebook_loss=19.27, over 1374157.96 frames.], batch size: 19, lr: 6.48e-04
+2022-05-27 19:32:09,219 INFO [train.py:823] (3/4) Epoch 26, batch 800, loss[loss=2.048, simple_loss=0.2289, pruned_loss=0.03003, codebook_loss=19.03, over 7243.00 frames.], tot_loss[loss=2.091, simple_loss=0.2498, pruned_loss=0.03585, codebook_loss=19.3, over 1383275.76 frames.], batch size: 16, lr: 6.47e-04
+2022-05-27 19:32:49,162 INFO [train.py:823] (3/4) Epoch 26, batch 850, loss[loss=1.946, simple_loss=0.2132, pruned_loss=0.01921, codebook_loss=18.21, over 7231.00 frames.], tot_loss[loss=2.082, simple_loss=0.2494, pruned_loss=0.0352, codebook_loss=19.22, over 1395030.47 frames.], batch size: 16, lr: 6.47e-04
+2022-05-27 19:33:29,196 INFO [train.py:823] (3/4) Epoch 26, batch 900, loss[loss=2.093, simple_loss=0.2418, pruned_loss=0.0369, codebook_loss=19.36, over 7018.00 frames.], tot_loss[loss=2.085, simple_loss=0.25, pruned_loss=0.03555, codebook_loss=19.24, over 1396925.88 frames.], batch size: 17, lr: 6.46e-04
+2022-05-27 19:34:22,985 INFO [train.py:823] (3/4) Epoch 27, batch 0, loss[loss=2.046, simple_loss=0.2356, pruned_loss=0.02836, codebook_loss=19, over 7191.00 frames.], tot_loss[loss=2.046, simple_loss=0.2356, pruned_loss=0.02836, codebook_loss=19, over 7191.00 frames.], batch size: 18, lr: 6.34e-04
+2022-05-27 19:35:03,203 INFO [train.py:823] (3/4) Epoch 27, batch 50, loss[loss=2.122, simple_loss=0.2536, pruned_loss=0.0437, codebook_loss=19.51, over 7184.00 frames.], tot_loss[loss=2.065, simple_loss=0.2461, pruned_loss=0.03559, codebook_loss=19.07, over 321545.62 frames.], batch size: 18, lr: 6.33e-04
+2022-05-27 19:35:42,732 INFO [train.py:823] (3/4) Epoch 27, batch 100, loss[loss=1.991, simple_loss=0.2582, pruned_loss=0.03913, codebook_loss=18.23, over 7237.00 frames.], tot_loss[loss=2.053, simple_loss=0.2478, pruned_loss=0.03439, codebook_loss=18.94, over 563217.21 frames.], batch size: 25, lr: 6.32e-04
+2022-05-27 19:36:26,851 INFO [train.py:823] (3/4) Epoch 27, batch 150, loss[loss=2.086, simple_loss=0.2263, pruned_loss=0.0265, codebook_loss=19.46, over 7310.00 frames.], tot_loss[loss=2.054, simple_loss=0.2479, pruned_loss=0.03447, codebook_loss=18.95, over 752102.35 frames.], batch size: 18, lr: 6.32e-04
+2022-05-27 19:37:06,339 INFO [train.py:823] (3/4) Epoch 27, batch 200, loss[loss=2.04, simple_loss=0.2407, pruned_loss=0.026, codebook_loss=18.94, over 7423.00 frames.], tot_loss[loss=2.067, simple_loss=0.2486, pruned_loss=0.03552, codebook_loss=19.07, over 898785.67 frames.], batch size: 22, lr: 6.31e-04
+2022-05-27 19:37:46,514 INFO [train.py:823] (3/4) Epoch 27, batch 250, loss[loss=1.984, simple_loss=0.221, pruned_loss=0.02149, codebook_loss=18.52, over 7037.00 frames.], tot_loss[loss=2.065, simple_loss=0.2488, pruned_loss=0.03501, codebook_loss=19.06, over 1011571.49 frames.], batch size: 17, lr: 6.31e-04
+2022-05-27 19:38:26,682 INFO [train.py:823] (3/4) Epoch 27, batch 300, loss[loss=1.985, simple_loss=0.2413, pruned_loss=0.01787, codebook_loss=18.46, over 7359.00 frames.], tot_loss[loss=2.072, simple_loss=0.2484, pruned_loss=0.03486, codebook_loss=19.13, over 1105085.86 frames.], batch size: 21, lr: 6.30e-04
+2022-05-27 19:39:06,900 INFO [train.py:823] (3/4) Epoch 27, batch 350, loss[loss=1.989, simple_loss=0.2272, pruned_loss=0.02984, codebook_loss=18.45, over 7292.00 frames.], tot_loss[loss=2.079, simple_loss=0.2475, pruned_loss=0.03458, codebook_loss=19.2, over 1177122.55 frames.], batch size: 19, lr: 6.29e-04
+2022-05-27 19:39:46,752 INFO [train.py:823] (3/4) Epoch 27, batch 400, loss[loss=2.03, simple_loss=0.2507, pruned_loss=0.02679, codebook_loss=18.78, over 7279.00 frames.], tot_loss[loss=2.086, simple_loss=0.2482, pruned_loss=0.03517, codebook_loss=19.27, over 1231913.97 frames.], batch size: 20, lr: 6.29e-04
+2022-05-27 19:40:27,029 INFO [train.py:823] (3/4) Epoch 27, batch 450, loss[loss=2.122, simple_loss=0.268, pruned_loss=0.05779, codebook_loss=19.31, over 5257.00 frames.], tot_loss[loss=2.08, simple_loss=0.2472, pruned_loss=0.03478, codebook_loss=19.22, over 1276058.50 frames.], batch size: 46, lr: 6.28e-04
+2022-05-27 19:41:06,535 INFO [train.py:823] (3/4) Epoch 27, batch 500, loss[loss=2.669, simple_loss=0.3019, pruned_loss=0.08831, codebook_loss=24.3, over 7169.00 frames.], tot_loss[loss=2.084, simple_loss=0.2475, pruned_loss=0.03492, codebook_loss=19.25, over 1300624.61 frames.], batch size: 23, lr: 6.28e-04
+2022-05-27 19:41:46,721 INFO [train.py:823] (3/4) Epoch 27, batch 550, loss[loss=2.023, simple_loss=0.2467, pruned_loss=0.03155, codebook_loss=18.68, over 7278.00 frames.], tot_loss[loss=2.084, simple_loss=0.2486, pruned_loss=0.03539, codebook_loss=19.24, over 1328831.65 frames.], batch size: 20, lr: 6.27e-04
+2022-05-27 19:42:26,683 INFO [train.py:823] (3/4) Epoch 27, batch 600, loss[loss=2.081, simple_loss=0.2227, pruned_loss=0.03504, codebook_loss=19.35, over 7307.00 frames.], tot_loss[loss=2.082, simple_loss=0.2481, pruned_loss=0.03487, codebook_loss=19.23, over 1354864.03 frames.], batch size: 18, lr: 6.26e-04
+2022-05-27 19:43:06,797 INFO [train.py:823] (3/4) Epoch 27, batch 650, loss[loss=2.115, simple_loss=0.2353, pruned_loss=0.02349, codebook_loss=19.74, over 7200.00 frames.], tot_loss[loss=2.076, simple_loss=0.248, pruned_loss=0.03476, codebook_loss=19.17, over 1373641.25 frames.], batch size: 19, lr: 6.26e-04
+2022-05-27 19:43:46,842 INFO [train.py:823] (3/4) Epoch 27, batch 700, loss[loss=2.171, simple_loss=0.266, pruned_loss=0.03516, codebook_loss=20.03, over 7368.00 frames.], tot_loss[loss=2.08, simple_loss=0.248, pruned_loss=0.03449, codebook_loss=19.21, over 1384652.36 frames.], batch size: 21, lr: 6.25e-04
+2022-05-27 19:44:26,961 INFO [train.py:823] (3/4) Epoch 27, batch 750, loss[loss=2.2, simple_loss=0.234, pruned_loss=0.02848, codebook_loss=20.55, over 7194.00 frames.], tot_loss[loss=2.079, simple_loss=0.2482, pruned_loss=0.03456, codebook_loss=19.21, over 1391853.05 frames.], batch size: 19, lr: 6.25e-04
+2022-05-27 19:45:06,636 INFO [train.py:823] (3/4) Epoch 27, batch 800, loss[loss=2.063, simple_loss=0.2611, pruned_loss=0.04366, codebook_loss=18.89, over 7151.00 frames.], tot_loss[loss=2.08, simple_loss=0.2488, pruned_loss=0.03501, codebook_loss=19.21, over 1392743.17 frames.], batch size: 23, lr: 6.24e-04
+2022-05-27 19:45:46,842 INFO [train.py:823] (3/4) Epoch 27, batch 850, loss[loss=2.182, simple_loss=0.27, pruned_loss=0.04482, codebook_loss=20.02, over 7110.00 frames.], tot_loss[loss=2.077, simple_loss=0.2478, pruned_loss=0.03483, codebook_loss=19.18, over 1395979.18 frames.], batch size: 20, lr: 6.23e-04
+2022-05-27 19:46:26,344 INFO [train.py:823] (3/4) Epoch 27, batch 900, loss[loss=2.058, simple_loss=0.2201, pruned_loss=0.02934, codebook_loss=19.18, over 7273.00 frames.], tot_loss[loss=2.076, simple_loss=0.2478, pruned_loss=0.03466, codebook_loss=19.17, over 1398341.42 frames.], batch size: 17, lr: 6.23e-04
+2022-05-27 19:47:20,702 INFO [train.py:823] (3/4) Epoch 28, batch 0, loss[loss=1.932, simple_loss=0.2351, pruned_loss=0.03026, codebook_loss=17.84, over 7193.00 frames.], tot_loss[loss=1.932, simple_loss=0.2351, pruned_loss=0.03026, codebook_loss=17.84, over 7193.00 frames.], batch size: 20, lr: 6.11e-04
+2022-05-27 19:48:00,135 INFO [train.py:823] (3/4) Epoch 28, batch 50, loss[loss=2.222, simple_loss=0.2619, pruned_loss=0.03514, codebook_loss=20.56, over 7114.00 frames.], tot_loss[loss=2.033, simple_loss=0.2434, pruned_loss=0.03177, codebook_loss=18.8, over 316771.55 frames.], batch size: 20, lr: 6.11e-04
+2022-05-27 19:48:40,413 INFO [train.py:823] (3/4) Epoch 28, batch 100, loss[loss=2.106, simple_loss=0.2732, pruned_loss=0.05422, codebook_loss=19.16, over 7041.00 frames.], tot_loss[loss=2.042, simple_loss=0.2448, pruned_loss=0.03269, codebook_loss=18.87, over 562605.90 frames.], batch size: 26, lr: 6.10e-04
+2022-05-27 19:49:20,190 INFO [train.py:823] (3/4) Epoch 28, batch 150, loss[loss=2.062, simple_loss=0.2435, pruned_loss=0.04609, codebook_loss=18.95, over 4480.00 frames.], tot_loss[loss=2.048, simple_loss=0.2442, pruned_loss=0.03264, codebook_loss=18.94, over 750747.88 frames.], batch size: 46, lr: 6.09e-04
+2022-05-27 19:50:00,322 INFO [train.py:823] (3/4) Epoch 28, batch 200, loss[loss=2.238, simple_loss=0.2626, pruned_loss=0.03812, codebook_loss=20.69, over 7197.00 frames.], tot_loss[loss=2.045, simple_loss=0.2443, pruned_loss=0.03271, codebook_loss=18.9, over 900950.91 frames.], batch size: 20, lr: 6.09e-04
+2022-05-27 19:50:40,294 INFO [train.py:823] (3/4) Epoch 28, batch 250, loss[loss=1.999, simple_loss=0.2309, pruned_loss=0.02326, codebook_loss=18.6, over 7332.00 frames.], tot_loss[loss=2.04, simple_loss=0.2443, pruned_loss=0.03245, codebook_loss=18.86, over 1016695.28 frames.], batch size: 23, lr: 6.08e-04
+2022-05-27 19:51:22,053 INFO [train.py:823] (3/4) Epoch 28, batch 300, loss[loss=2.086, simple_loss=0.2667, pruned_loss=0.03719, codebook_loss=19.15, over 6983.00 frames.], tot_loss[loss=2.05, simple_loss=0.2449, pruned_loss=0.03293, codebook_loss=18.94, over 1104761.99 frames.], batch size: 29, lr: 6.08e-04
+2022-05-27 19:52:01,919 INFO [train.py:823] (3/4) Epoch 28, batch 350, loss[loss=2.144, simple_loss=0.2759, pruned_loss=0.0403, codebook_loss=19.66, over 7355.00 frames.], tot_loss[loss=2.056, simple_loss=0.2457, pruned_loss=0.03318, codebook_loss=19, over 1174949.22 frames.], batch size: 23, lr: 6.07e-04
+2022-05-27 19:52:42,297 INFO [train.py:823] (3/4) Epoch 28, batch 400, loss[loss=1.941, simple_loss=0.2632, pruned_loss=0.0259, codebook_loss=17.84, over 7288.00 frames.], tot_loss[loss=2.061, simple_loss=0.2455, pruned_loss=0.03298, codebook_loss=19.05, over 1229194.22 frames.], batch size: 21, lr: 6.07e-04
+2022-05-27 19:53:21,976 INFO [train.py:823] (3/4) Epoch 28, batch 450, loss[loss=1.966, simple_loss=0.2415, pruned_loss=0.02393, codebook_loss=18.22, over 6882.00 frames.], tot_loss[loss=2.059, simple_loss=0.2455, pruned_loss=0.033, codebook_loss=19.03, over 1269471.76 frames.], batch size: 29, lr: 6.06e-04
+2022-05-27 19:54:02,150 INFO [train.py:823] (3/4) Epoch 28, batch 500, loss[loss=2.071, simple_loss=0.2669, pruned_loss=0.03747, codebook_loss=19, over 6925.00 frames.], tot_loss[loss=2.056, simple_loss=0.2452, pruned_loss=0.03319, codebook_loss=19.01, over 1306225.49 frames.], batch size: 29, lr: 6.06e-04
+2022-05-27 19:54:41,599 INFO [train.py:823] (3/4) Epoch 28, batch 550, loss[loss=2, simple_loss=0.2465, pruned_loss=0.03227, codebook_loss=18.45, over 7104.00 frames.], tot_loss[loss=2.059, simple_loss=0.2458, pruned_loss=0.03337, codebook_loss=19.02, over 1329720.45 frames.], batch size: 20, lr: 6.05e-04
+2022-05-27 19:55:21,347 INFO [train.py:823] (3/4) Epoch 28, batch 600, loss[loss=2.075, simple_loss=0.24, pruned_loss=0.03336, codebook_loss=19.22, over 7195.00 frames.], tot_loss[loss=2.057, simple_loss=0.2462, pruned_loss=0.0334, codebook_loss=19.01, over 1348303.75 frames.], batch size: 19, lr: 6.04e-04
+2022-05-27 19:56:01,411 INFO [train.py:823] (3/4) Epoch 28, batch 650, loss[loss=2.023, simple_loss=0.2392, pruned_loss=0.03365, codebook_loss=18.7, over 7281.00 frames.], tot_loss[loss=2.058, simple_loss=0.2461, pruned_loss=0.03319, codebook_loss=19.02, over 1366866.40 frames.], batch size: 19, lr: 6.04e-04
+2022-05-27 19:56:41,254 INFO [train.py:823] (3/4) Epoch 28, batch 700, loss[loss=2.022, simple_loss=0.2365, pruned_loss=0.03616, codebook_loss=18.67, over 7306.00 frames.], tot_loss[loss=2.062, simple_loss=0.2468, pruned_loss=0.03338, codebook_loss=19.06, over 1376787.43 frames.], batch size: 18, lr: 6.03e-04
+2022-05-27 19:57:20,985 INFO [train.py:823] (3/4) Epoch 28, batch 750, loss[loss=2.04, simple_loss=0.2548, pruned_loss=0.03968, codebook_loss=18.73, over 5113.00 frames.], tot_loss[loss=2.065, simple_loss=0.2472, pruned_loss=0.03385, codebook_loss=19.07, over 1383278.07 frames.], batch size: 47, lr: 6.03e-04
+2022-05-27 19:58:00,964 INFO [train.py:823] (3/4) Epoch 28, batch 800, loss[loss=1.927, simple_loss=0.2239, pruned_loss=0.01482, codebook_loss=18, over 7010.00 frames.], tot_loss[loss=2.065, simple_loss=0.2474, pruned_loss=0.03386, codebook_loss=19.07, over 1395206.81 frames.], batch size: 16, lr: 6.02e-04
+2022-05-27 19:58:40,825 INFO [train.py:823] (3/4) Epoch 28, batch 850, loss[loss=2.058, simple_loss=0.255, pruned_loss=0.03181, codebook_loss=18.99, over 7370.00 frames.], tot_loss[loss=2.065, simple_loss=0.2477, pruned_loss=0.03374, codebook_loss=19.08, over 1398631.55 frames.], batch size: 21, lr: 6.02e-04
+2022-05-27 19:59:20,854 INFO [train.py:823] (3/4) Epoch 28, batch 900, loss[loss=2.096, simple_loss=0.2626, pruned_loss=0.03674, codebook_loss=19.28, over 7376.00 frames.], tot_loss[loss=2.062, simple_loss=0.2479, pruned_loss=0.03393, codebook_loss=19.05, over 1401842.58 frames.], batch size: 21, lr: 6.01e-04
+2022-05-27 20:00:14,132 INFO [train.py:823] (3/4) Epoch 29, batch 0, loss[loss=1.938, simple_loss=0.2498, pruned_loss=0.03163, codebook_loss=17.81, over 6984.00 frames.], tot_loss[loss=1.938, simple_loss=0.2498, pruned_loss=0.03163, codebook_loss=17.81, over 6984.00 frames.], batch size: 26, lr: 5.90e-04
+2022-05-27 20:00:55,902 INFO [train.py:823] (3/4) Epoch 29, batch 50, loss[loss=2.015, simple_loss=0.2433, pruned_loss=0.02429, codebook_loss=18.69, over 7283.00 frames.], tot_loss[loss=2.049, simple_loss=0.2461, pruned_loss=0.03361, codebook_loss=18.92, over 321218.79 frames.], batch size: 21, lr: 5.90e-04
+2022-05-27 20:01:38,104 INFO [train.py:823] (3/4) Epoch 29, batch 100, loss[loss=2.009, simple_loss=0.2352, pruned_loss=0.03044, codebook_loss=18.61, over 7216.00 frames.], tot_loss[loss=2.049, simple_loss=0.2466, pruned_loss=0.03419, codebook_loss=18.92, over 569850.86 frames.], batch size: 24, lr: 5.89e-04
+2022-05-27 20:02:18,483 INFO [train.py:823] (3/4) Epoch 29, batch 150, loss[loss=2.33, simple_loss=0.2683, pruned_loss=0.05765, codebook_loss=21.38, over 7293.00 frames.], tot_loss[loss=2.058, simple_loss=0.2454, pruned_loss=0.03487, codebook_loss=19.01, over 759500.72 frames.], batch size: 19, lr: 5.89e-04
+2022-05-27 20:02:58,103 INFO [train.py:823] (3/4) Epoch 29, batch 200, loss[loss=1.93, simple_loss=0.255, pruned_loss=0.03345, codebook_loss=17.7, over 7340.00 frames.], tot_loss[loss=2.057, simple_loss=0.2464, pruned_loss=0.03468, codebook_loss=18.99, over 897931.45 frames.], batch size: 23, lr: 5.88e-04
+2022-05-27 20:03:38,444 INFO [train.py:823] (3/4) Epoch 29, batch 250, loss[loss=2.035, simple_loss=0.2447, pruned_loss=0.03109, codebook_loss=18.82, over 7391.00 frames.], tot_loss[loss=2.051, simple_loss=0.2449, pruned_loss=0.03375, codebook_loss=18.95, over 1015100.09 frames.], batch size: 19, lr: 5.88e-04
+2022-05-27 20:04:18,168 INFO [train.py:823] (3/4) Epoch 29, batch 300, loss[loss=2.038, simple_loss=0.2387, pruned_loss=0.03346, codebook_loss=18.85, over 7282.00 frames.], tot_loss[loss=2.055, simple_loss=0.245, pruned_loss=0.03385, codebook_loss=18.99, over 1104604.26 frames.], batch size: 20, lr: 5.87e-04
+2022-05-27 20:04:58,344 INFO [train.py:823] (3/4) Epoch 29, batch 350, loss[loss=1.993, simple_loss=0.2199, pruned_loss=0.03102, codebook_loss=18.52, over 6764.00 frames.], tot_loss[loss=2.056, simple_loss=0.2449, pruned_loss=0.03362, codebook_loss=19, over 1173600.32 frames.], batch size: 15, lr: 5.87e-04
+2022-05-27 20:05:37,844 INFO [train.py:823] (3/4) Epoch 29, batch 400, loss[loss=2.094, simple_loss=0.2258, pruned_loss=0.03815, codebook_loss=19.43, over 7291.00 frames.], tot_loss[loss=2.056, simple_loss=0.2461, pruned_loss=0.03371, codebook_loss=18.99, over 1229901.91 frames.], batch size: 17, lr: 5.86e-04
+2022-05-27 20:06:18,210 INFO [train.py:823] (3/4) Epoch 29, batch 450, loss[loss=2.068, simple_loss=0.2311, pruned_loss=0.02901, codebook_loss=19.23, over 7094.00 frames.], tot_loss[loss=2.053, simple_loss=0.2456, pruned_loss=0.03344, codebook_loss=18.96, over 1270357.89 frames.], batch size: 18, lr: 5.85e-04
+2022-05-27 20:06:57,636 INFO [train.py:823] (3/4) Epoch 29, batch 500, loss[loss=2.059, simple_loss=0.2423, pruned_loss=0.02723, codebook_loss=19.11, over 7118.00 frames.], tot_loss[loss=2.051, simple_loss=0.2457, pruned_loss=0.0333, codebook_loss=18.95, over 1298908.98 frames.], batch size: 20, lr: 5.85e-04
+2022-05-27 20:07:37,737 INFO [train.py:823] (3/4) Epoch 29, batch 550, loss[loss=2.01, simple_loss=0.2419, pruned_loss=0.02225, codebook_loss=18.67, over 6465.00 frames.], tot_loss[loss=2.051, simple_loss=0.2453, pruned_loss=0.03305, codebook_loss=18.95, over 1327901.29 frames.], batch size: 34, lr: 5.84e-04
+2022-05-27 20:08:17,446 INFO [train.py:823] (3/4) Epoch 29, batch 600, loss[loss=1.995, simple_loss=0.2396, pruned_loss=0.02643, codebook_loss=18.48, over 6615.00 frames.], tot_loss[loss=2.06, simple_loss=0.2467, pruned_loss=0.03376, codebook_loss=19.03, over 1348248.92 frames.], batch size: 34, lr: 5.84e-04
+2022-05-27 20:08:57,756 INFO [train.py:823] (3/4) Epoch 29, batch 650, loss[loss=2.045, simple_loss=0.2431, pruned_loss=0.03312, codebook_loss=18.9, over 7375.00 frames.], tot_loss[loss=2.06, simple_loss=0.2473, pruned_loss=0.03408, codebook_loss=19.02, over 1365598.95 frames.], batch size: 20, lr: 5.83e-04
+2022-05-27 20:09:37,319 INFO [train.py:823] (3/4) Epoch 29, batch 700, loss[loss=1.952, simple_loss=0.2283, pruned_loss=0.02578, codebook_loss=18.12, over 7204.00 frames.], tot_loss[loss=2.059, simple_loss=0.2467, pruned_loss=0.03392, codebook_loss=19.02, over 1372923.90 frames.], batch size: 19, lr: 5.83e-04
+2022-05-27 20:10:17,496 INFO [train.py:823] (3/4) Epoch 29, batch 750, loss[loss=2.022, simple_loss=0.2587, pruned_loss=0.0417, codebook_loss=18.51, over 4813.00 frames.], tot_loss[loss=2.062, simple_loss=0.2474, pruned_loss=0.03397, codebook_loss=19.04, over 1380966.66 frames.], batch size: 47, lr: 5.82e-04
+2022-05-27 20:10:57,086 INFO [train.py:823] (3/4) Epoch 29, batch 800, loss[loss=2.049, simple_loss=0.2406, pruned_loss=0.03756, codebook_loss=18.91, over 7191.00 frames.], tot_loss[loss=2.06, simple_loss=0.2467, pruned_loss=0.03362, codebook_loss=19.03, over 1388449.87 frames.], batch size: 18, lr: 5.82e-04
+2022-05-27 20:11:37,252 INFO [train.py:823] (3/4) Epoch 29, batch 850, loss[loss=2.04, simple_loss=0.2723, pruned_loss=0.04162, codebook_loss=18.62, over 7257.00 frames.], tot_loss[loss=2.057, simple_loss=0.247, pruned_loss=0.03335, codebook_loss=19, over 1397819.45 frames.], batch size: 24, lr: 5.81e-04
+2022-05-27 20:12:16,639 INFO [train.py:823] (3/4) Epoch 29, batch 900, loss[loss=2.085, simple_loss=0.2723, pruned_loss=0.04013, codebook_loss=19.09, over 7158.00 frames.], tot_loss[loss=2.061, simple_loss=0.247, pruned_loss=0.03371, codebook_loss=19.04, over 1396382.18 frames.], batch size: 22, lr: 5.81e-04
+2022-05-27 20:12:56,397 INFO [train.py:823] (3/4) Epoch 29, batch 950, loss[loss=2.901, simple_loss=0.3141, pruned_loss=0.08468, codebook_loss=26.59, over 5100.00 frames.], tot_loss[loss=2.067, simple_loss=0.2462, pruned_loss=0.03375, codebook_loss=19.1, over 1391855.04 frames.], batch size: 47, lr: 5.80e-04
+2022-05-27 20:13:08,685 INFO [train.py:823] (3/4) Epoch 30, batch 0, loss[loss=2.11, simple_loss=0.2515, pruned_loss=0.03082, codebook_loss=19.53, over 7380.00 frames.], tot_loss[loss=2.11, simple_loss=0.2515, pruned_loss=0.03082, codebook_loss=19.53, over 7380.00 frames.], batch size: 20, lr: 5.71e-04
+2022-05-27 20:13:48,318 INFO [train.py:823] (3/4) Epoch 30, batch 50, loss[loss=1.971, simple_loss=0.2279, pruned_loss=0.02879, codebook_loss=18.29, over 7099.00 frames.], tot_loss[loss=2.049, simple_loss=0.2433, pruned_loss=0.03264, codebook_loss=18.94, over 314527.25 frames.], batch size: 19, lr: 5.70e-04
+2022-05-27 20:14:28,414 INFO [train.py:823] (3/4) Epoch 30, batch 100, loss[loss=1.97, simple_loss=0.2179, pruned_loss=0.03409, codebook_loss=18.27, over 7301.00 frames.], tot_loss[loss=2.041, simple_loss=0.2431, pruned_loss=0.03212, codebook_loss=18.88, over 561111.50 frames.], batch size: 17, lr: 5.70e-04
+2022-05-27 20:15:09,340 INFO [train.py:823] (3/4) Epoch 30, batch 150, loss[loss=2.08, simple_loss=0.2504, pruned_loss=0.04387, codebook_loss=19.11, over 7149.00 frames.], tot_loss[loss=2.054, simple_loss=0.2456, pruned_loss=0.03356, codebook_loss=18.98, over 752911.65 frames.], batch size: 23, lr: 5.69e-04
+2022-05-27 20:15:49,642 INFO [train.py:823] (3/4) Epoch 30, batch 200, loss[loss=1.974, simple_loss=0.2785, pruned_loss=0.03768, codebook_loss=17.97, over 7157.00 frames.], tot_loss[loss=2.057, simple_loss=0.2467, pruned_loss=0.03407, codebook_loss=18.99, over 900172.73 frames.], batch size: 23, lr: 5.69e-04
+2022-05-27 20:16:29,384 INFO [train.py:823] (3/4) Epoch 30, batch 250, loss[loss=1.959, simple_loss=0.2346, pruned_loss=0.02713, codebook_loss=18.14, over 7098.00 frames.], tot_loss[loss=2.054, simple_loss=0.2469, pruned_loss=0.03392, codebook_loss=18.97, over 1012332.01 frames.], batch size: 19, lr: 5.68e-04
+2022-05-27 20:17:09,786 INFO [train.py:823] (3/4) Epoch 30, batch 300, loss[loss=1.981, simple_loss=0.2207, pruned_loss=0.0317, codebook_loss=18.39, over 7149.00 frames.], tot_loss[loss=2.051, simple_loss=0.2478, pruned_loss=0.03395, codebook_loss=18.94, over 1105660.57 frames.], batch size: 17, lr: 5.68e-04
+2022-05-27 20:17:49,599 INFO [train.py:823] (3/4) Epoch 30, batch 350, loss[loss=2.312, simple_loss=0.2536, pruned_loss=0.0351, codebook_loss=21.5, over 7235.00 frames.], tot_loss[loss=2.058, simple_loss=0.2466, pruned_loss=0.03359, codebook_loss=19.01, over 1175753.51 frames.], batch size: 24, lr: 5.67e-04
+2022-05-27 20:18:29,834 INFO [train.py:823] (3/4) Epoch 30, batch 400, loss[loss=2.014, simple_loss=0.2738, pruned_loss=0.03679, codebook_loss=18.4, over 7037.00 frames.], tot_loss[loss=2.054, simple_loss=0.2456, pruned_loss=0.03331, codebook_loss=18.98, over 1230347.90 frames.], batch size: 26, lr: 5.67e-04
+2022-05-27 20:19:09,335 INFO [train.py:823] (3/4) Epoch 30, batch 450, loss[loss=2.085, simple_loss=0.2581, pruned_loss=0.04076, codebook_loss=19.15, over 6923.00 frames.], tot_loss[loss=2.052, simple_loss=0.2452, pruned_loss=0.03315, codebook_loss=18.97, over 1269023.08 frames.], batch size: 29, lr: 5.66e-04
+2022-05-27 20:19:49,224 INFO [train.py:823] (3/4) Epoch 30, batch 500, loss[loss=2.194, simple_loss=0.2229, pruned_loss=0.02272, codebook_loss=20.6, over 7087.00 frames.], tot_loss[loss=2.054, simple_loss=0.2453, pruned_loss=0.03291, codebook_loss=18.99, over 1301861.66 frames.], batch size: 19, lr: 5.66e-04
+2022-05-27 20:20:29,048 INFO [train.py:823] (3/4) Epoch 30, batch 550, loss[loss=2.292, simple_loss=0.2563, pruned_loss=0.03477, codebook_loss=21.29, over 7408.00 frames.], tot_loss[loss=2.058, simple_loss=0.2459, pruned_loss=0.03322, codebook_loss=19.01, over 1326328.95 frames.], batch size: 22, lr: 5.65e-04
+2022-05-27 20:21:09,007 INFO [train.py:823] (3/4) Epoch 30, batch 600, loss[loss=1.979, simple_loss=0.2265, pruned_loss=0.02439, codebook_loss=18.41, over 7205.00 frames.], tot_loss[loss=2.056, simple_loss=0.2452, pruned_loss=0.03301, codebook_loss=19, over 1344019.78 frames.], batch size: 19, lr: 5.65e-04
+2022-05-27 20:21:48,897 INFO [train.py:823] (3/4) Epoch 30, batch 650, loss[loss=1.952, simple_loss=0.2278, pruned_loss=0.02098, codebook_loss=18.17, over 7426.00 frames.], tot_loss[loss=2.05, simple_loss=0.2446, pruned_loss=0.03283, codebook_loss=18.95, over 1357221.16 frames.], batch size: 22, lr: 5.64e-04
+2022-05-27 20:22:29,363 INFO [train.py:823] (3/4) Epoch 30, batch 700, loss[loss=1.975, simple_loss=0.2256, pruned_loss=0.03042, codebook_loss=18.32, over 7298.00 frames.], tot_loss[loss=2.052, simple_loss=0.2435, pruned_loss=0.03278, codebook_loss=18.97, over 1376137.44 frames.], batch size: 19, lr: 5.64e-04
+2022-05-27 20:23:09,110 INFO [train.py:823] (3/4) Epoch 30, batch 750, loss[loss=1.953, simple_loss=0.2198, pruned_loss=0.02257, codebook_loss=18.21, over 7097.00 frames.], tot_loss[loss=2.052, simple_loss=0.2436, pruned_loss=0.03277, codebook_loss=18.98, over 1383165.88 frames.], batch size: 18, lr: 5.63e-04
+2022-05-27 20:23:48,809 INFO [train.py:823] (3/4) Epoch 30, batch 800, loss[loss=1.942, simple_loss=0.2464, pruned_loss=0.02439, codebook_loss=17.95, over 6986.00 frames.], tot_loss[loss=2.049, simple_loss=0.2437, pruned_loss=0.03226, codebook_loss=18.95, over 1393043.93 frames.], batch size: 26, lr: 5.63e-04
+2022-05-27 20:24:28,424 INFO [train.py:823] (3/4) Epoch 30, batch 850, loss[loss=2.062, simple_loss=0.2213, pruned_loss=0.03168, codebook_loss=19.2, over 7197.00 frames.], tot_loss[loss=2.053, simple_loss=0.2439, pruned_loss=0.03233, codebook_loss=18.99, over 1392240.16 frames.], batch size: 18, lr: 5.62e-04
+2022-05-27 20:25:08,265 INFO [train.py:823] (3/4) Epoch 30, batch 900, loss[loss=2.128, simple_loss=0.2523, pruned_loss=0.03076, codebook_loss=19.71, over 7288.00 frames.], tot_loss[loss=2.051, simple_loss=0.2444, pruned_loss=0.03244, codebook_loss=18.96, over 1396429.90 frames.], batch size: 19, lr: 5.62e-04
+2022-05-27 20:26:05,264 INFO [train.py:823] (3/4) Epoch 31, batch 0, loss[loss=2.262, simple_loss=0.2463, pruned_loss=0.02827, codebook_loss=21.1, over 7373.00 frames.], tot_loss[loss=2.262, simple_loss=0.2463, pruned_loss=0.02827, codebook_loss=21.1, over 7373.00 frames.], batch size: 20, lr: 5.52e-04
+2022-05-27 20:26:45,558 INFO [train.py:823] (3/4) Epoch 31, batch 50, loss[loss=1.942, simple_loss=0.2092, pruned_loss=0.02456, codebook_loss=18.13, over 7191.00 frames.], tot_loss[loss=2.036, simple_loss=0.2401, pruned_loss=0.03147, codebook_loss=18.85, over 324793.46 frames.], batch size: 18, lr: 5.52e-04
+2022-05-27 20:27:25,004 INFO [train.py:823] (3/4) Epoch 31, batch 100, loss[loss=2.43, simple_loss=0.2247, pruned_loss=0.02602, codebook_loss=22.92, over 7270.00 frames.], tot_loss[loss=2.043, simple_loss=0.2425, pruned_loss=0.03144, codebook_loss=18.9, over 565427.25 frames.], batch size: 16, lr: 5.51e-04
+2022-05-27 20:28:05,136 INFO [train.py:823] (3/4) Epoch 31, batch 150, loss[loss=1.971, simple_loss=0.247, pruned_loss=0.02368, codebook_loss=18.24, over 7171.00 frames.], tot_loss[loss=2.045, simple_loss=0.2439, pruned_loss=0.03221, codebook_loss=18.91, over 754198.16 frames.], batch size: 25, lr: 5.51e-04
+2022-05-27 20:28:44,828 INFO [train.py:823] (3/4) Epoch 31, batch 200, loss[loss=2.013, simple_loss=0.2533, pruned_loss=0.02765, codebook_loss=18.59, over 7098.00 frames.], tot_loss[loss=2.045, simple_loss=0.2443, pruned_loss=0.03211, codebook_loss=18.91, over 898730.86 frames.], batch size: 18, lr: 5.50e-04
+2022-05-27 20:29:24,822 INFO [train.py:823] (3/4) Epoch 31, batch 250, loss[loss=1.98, simple_loss=0.2084, pruned_loss=0.01847, codebook_loss=18.58, over 7145.00 frames.], tot_loss[loss=2.05, simple_loss=0.2438, pruned_loss=0.03266, codebook_loss=18.95, over 1006096.90 frames.], batch size: 17, lr: 5.50e-04
+2022-05-27 20:30:04,886 INFO [train.py:823] (3/4) Epoch 31, batch 300, loss[loss=2.047, simple_loss=0.263, pruned_loss=0.03537, codebook_loss=18.8, over 7311.00 frames.], tot_loss[loss=2.042, simple_loss=0.2437, pruned_loss=0.0321, codebook_loss=18.88, over 1097927.34 frames.], batch size: 22, lr: 5.49e-04
+2022-05-27 20:30:44,878 INFO [train.py:823] (3/4) Epoch 31, batch 350, loss[loss=2.198, simple_loss=0.2362, pruned_loss=0.04467, codebook_loss=20.35, over 7165.00 frames.], tot_loss[loss=2.042, simple_loss=0.2434, pruned_loss=0.03199, codebook_loss=18.88, over 1164543.82 frames.], batch size: 17, lr: 5.49e-04
+2022-05-27 20:31:24,690 INFO [train.py:823] (3/4) Epoch 31, batch 400, loss[loss=1.978, simple_loss=0.2274, pruned_loss=0.02587, codebook_loss=18.39, over 7376.00 frames.], tot_loss[loss=2.04, simple_loss=0.2432, pruned_loss=0.03163, codebook_loss=18.87, over 1225947.05 frames.], batch size: 19, lr: 5.49e-04
+2022-05-27 20:32:04,790 INFO [train.py:823] (3/4) Epoch 31, batch 450, loss[loss=1.996, simple_loss=0.2212, pruned_loss=0.02587, codebook_loss=18.6, over 7302.00 frames.], tot_loss[loss=2.04, simple_loss=0.2437, pruned_loss=0.03197, codebook_loss=18.86, over 1269691.24 frames.], batch size: 18, lr: 5.48e-04
+2022-05-27 20:32:44,647 INFO [train.py:823] (3/4) Epoch 31, batch 500, loss[loss=2.024, simple_loss=0.244, pruned_loss=0.03184, codebook_loss=18.7, over 7099.00 frames.], tot_loss[loss=2.048, simple_loss=0.2439, pruned_loss=0.03249, codebook_loss=18.93, over 1302350.20 frames.], batch size: 18, lr: 5.48e-04
+2022-05-27 20:33:24,729 INFO [train.py:823] (3/4) Epoch 31, batch 550, loss[loss=2.149, simple_loss=0.2354, pruned_loss=0.02565, codebook_loss=20.05, over 7393.00 frames.], tot_loss[loss=2.048, simple_loss=0.2434, pruned_loss=0.03212, codebook_loss=18.94, over 1326122.70 frames.], batch size: 19, lr: 5.47e-04
+2022-05-27 20:34:04,425 INFO [train.py:823] (3/4) Epoch 31, batch 600, loss[loss=2.008, simple_loss=0.2167, pruned_loss=0.02968, codebook_loss=18.7, over 7284.00 frames.], tot_loss[loss=2.045, simple_loss=0.2439, pruned_loss=0.03201, codebook_loss=18.91, over 1347173.68 frames.], batch size: 16, lr: 5.47e-04
+2022-05-27 20:34:44,373 INFO [train.py:823] (3/4) Epoch 31, batch 650, loss[loss=2.061, simple_loss=0.2706, pruned_loss=0.04625, codebook_loss=18.8, over 7143.00 frames.], tot_loss[loss=2.043, simple_loss=0.2438, pruned_loss=0.03212, codebook_loss=18.89, over 1362392.90 frames.], batch size: 22, lr: 5.46e-04
+2022-05-27 20:35:24,060 INFO [train.py:823] (3/4) Epoch 31, batch 700, loss[loss=2.048, simple_loss=0.2338, pruned_loss=0.03634, codebook_loss=18.94, over 7301.00 frames.], tot_loss[loss=2.051, simple_loss=0.2447, pruned_loss=0.03286, codebook_loss=18.95, over 1370214.07 frames.], batch size: 17, lr: 5.46e-04
+2022-05-27 20:36:04,269 INFO [train.py:823] (3/4) Epoch 31, batch 750, loss[loss=1.965, simple_loss=0.2147, pruned_loss=0.0201, codebook_loss=18.38, over 7305.00 frames.], tot_loss[loss=2.051, simple_loss=0.2446, pruned_loss=0.03282, codebook_loss=18.96, over 1381850.78 frames.], batch size: 18, lr: 5.45e-04
+2022-05-27 20:36:44,234 INFO [train.py:823] (3/4) Epoch 31, batch 800, loss[loss=2.045, simple_loss=0.2373, pruned_loss=0.03386, codebook_loss=18.92, over 6780.00 frames.], tot_loss[loss=2.054, simple_loss=0.2444, pruned_loss=0.03325, codebook_loss=18.99, over 1391565.64 frames.], batch size: 15, lr: 5.45e-04
+2022-05-27 20:37:23,993 INFO [train.py:823] (3/4) Epoch 31, batch 850, loss[loss=2.019, simple_loss=0.2541, pruned_loss=0.03384, codebook_loss=18.58, over 7032.00 frames.], tot_loss[loss=2.054, simple_loss=0.245, pruned_loss=0.03341, codebook_loss=18.98, over 1390958.06 frames.], batch size: 26, lr: 5.44e-04
+2022-05-27 20:38:03,436 INFO [train.py:823] (3/4) Epoch 31, batch 900, loss[loss=2.044, simple_loss=0.2352, pruned_loss=0.03517, codebook_loss=18.91, over 7102.00 frames.], tot_loss[loss=2.05, simple_loss=0.2453, pruned_loss=0.03336, codebook_loss=18.94, over 1396763.30 frames.], batch size: 19, lr: 5.44e-04
+2022-05-27 20:38:58,908 INFO [train.py:823] (3/4) Epoch 32, batch 0, loss[loss=1.987, simple_loss=0.239, pruned_loss=0.03267, codebook_loss=18.35, over 5096.00 frames.], tot_loss[loss=1.987, simple_loss=0.239, pruned_loss=0.03267, codebook_loss=18.35, over 5096.00 frames.], batch size: 47, lr: 5.35e-04
+2022-05-27 20:39:38,636 INFO [train.py:823] (3/4) Epoch 32, batch 50, loss[loss=2.013, simple_loss=0.227, pruned_loss=0.02855, codebook_loss=18.71, over 7291.00 frames.], tot_loss[loss=2.026, simple_loss=0.2441, pruned_loss=0.03242, codebook_loss=18.71, over 320168.68 frames.], batch size: 17, lr: 5.35e-04
+2022-05-27 20:40:18,789 INFO [train.py:823] (3/4) Epoch 32, batch 100, loss[loss=2.216, simple_loss=0.2914, pruned_loss=0.06334, codebook_loss=20.07, over 7165.00 frames.], tot_loss[loss=2.036, simple_loss=0.2459, pruned_loss=0.03333, codebook_loss=18.8, over 565839.58 frames.], batch size: 22, lr: 5.34e-04
+2022-05-27 20:40:58,682 INFO [train.py:823] (3/4) Epoch 32, batch 150, loss[loss=2.027, simple_loss=0.2281, pruned_loss=0.02768, codebook_loss=18.86, over 7193.00 frames.], tot_loss[loss=2.046, simple_loss=0.245, pruned_loss=0.03328, codebook_loss=18.9, over 758707.17 frames.], batch size: 19, lr: 5.34e-04
+2022-05-27 20:41:38,651 INFO [train.py:823] (3/4) Epoch 32, batch 200, loss[loss=1.998, simple_loss=0.243, pruned_loss=0.03363, codebook_loss=18.43, over 7186.00 frames.], tot_loss[loss=2.037, simple_loss=0.2449, pruned_loss=0.03299, codebook_loss=18.82, over 904842.65 frames.], batch size: 19, lr: 5.33e-04
+2022-05-27 20:42:18,575 INFO [train.py:823] (3/4) Epoch 32, batch 250, loss[loss=2.043, simple_loss=0.2599, pruned_loss=0.03376, codebook_loss=18.79, over 7193.00 frames.], tot_loss[loss=2.033, simple_loss=0.2441, pruned_loss=0.03261, codebook_loss=18.78, over 1021132.98 frames.], batch size: 19, lr: 5.33e-04
+2022-05-27 20:42:58,413 INFO [train.py:823] (3/4) Epoch 32, batch 300, loss[loss=2.019, simple_loss=0.2516, pruned_loss=0.03042, codebook_loss=18.63, over 7288.00 frames.], tot_loss[loss=2.034, simple_loss=0.2436, pruned_loss=0.03259, codebook_loss=18.79, over 1106561.52 frames.], batch size: 19, lr: 5.32e-04
+2022-05-27 20:43:38,309 INFO [train.py:823] (3/4) Epoch 32, batch 350, loss[loss=2.076, simple_loss=0.2398, pruned_loss=0.04353, codebook_loss=19.12, over 7422.00 frames.], tot_loss[loss=2.036, simple_loss=0.2443, pruned_loss=0.03278, codebook_loss=18.81, over 1177208.82 frames.], batch size: 17, lr: 5.32e-04
+2022-05-27 20:44:18,242 INFO [train.py:823] (3/4) Epoch 32, batch 400, loss[loss=2.021, simple_loss=0.2444, pruned_loss=0.0308, codebook_loss=18.68, over 6662.00 frames.], tot_loss[loss=2.039, simple_loss=0.2453, pruned_loss=0.03295, codebook_loss=18.84, over 1227078.57 frames.], batch size: 34, lr: 5.32e-04
+2022-05-27 20:44:58,190 INFO [train.py:823] (3/4) Epoch 32, batch 450, loss[loss=1.993, simple_loss=0.2532, pruned_loss=0.03596, codebook_loss=18.31, over 7155.00 frames.], tot_loss[loss=2.037, simple_loss=0.2442, pruned_loss=0.03204, codebook_loss=18.83, over 1267454.59 frames.], batch size: 23, lr: 5.31e-04
+2022-05-27 20:45:38,568 INFO [train.py:823] (3/4) Epoch 32, batch 500, loss[loss=1.951, simple_loss=0.2463, pruned_loss=0.02378, codebook_loss=18.04, over 7197.00 frames.], tot_loss[loss=2.034, simple_loss=0.2429, pruned_loss=0.03144, codebook_loss=18.81, over 1301559.26 frames.], batch size: 20, lr: 5.31e-04
+2022-05-27 20:46:18,548 INFO [train.py:823] (3/4) Epoch 32, batch 550, loss[loss=2.035, simple_loss=0.2601, pruned_loss=0.04714, codebook_loss=18.58, over 7221.00 frames.], tot_loss[loss=2.028, simple_loss=0.2433, pruned_loss=0.03141, codebook_loss=18.75, over 1329602.26 frames.], batch size: 25, lr: 5.30e-04
+2022-05-27 20:46:58,696 INFO [train.py:823] (3/4) Epoch 32, batch 600, loss[loss=1.976, simple_loss=0.2243, pruned_loss=0.02281, codebook_loss=18.42, over 7277.00 frames.], tot_loss[loss=2.031, simple_loss=0.2436, pruned_loss=0.03156, codebook_loss=18.78, over 1350392.23 frames.], batch size: 17, lr: 5.30e-04
+2022-05-27 20:47:38,449 INFO [train.py:823] (3/4) Epoch 32, batch 650, loss[loss=1.949, simple_loss=0.2422, pruned_loss=0.02835, codebook_loss=17.99, over 7033.00 frames.], tot_loss[loss=2.036, simple_loss=0.2435, pruned_loss=0.03179, codebook_loss=18.82, over 1362886.25 frames.], batch size: 26, lr: 5.29e-04
+2022-05-27 20:48:18,783 INFO [train.py:823] (3/4) Epoch 32, batch 700, loss[loss=1.986, simple_loss=0.2474, pruned_loss=0.02268, codebook_loss=18.4, over 7106.00 frames.], tot_loss[loss=2.034, simple_loss=0.2429, pruned_loss=0.03165, codebook_loss=18.8, over 1379065.77 frames.], batch size: 20, lr: 5.29e-04
+2022-05-27 20:48:58,636 INFO [train.py:823] (3/4) Epoch 32, batch 750, loss[loss=1.992, simple_loss=0.2373, pruned_loss=0.03327, codebook_loss=18.4, over 7396.00 frames.], tot_loss[loss=2.034, simple_loss=0.2428, pruned_loss=0.03155, codebook_loss=18.81, over 1389247.21 frames.], batch size: 19, lr: 5.29e-04
+2022-05-27 20:49:38,923 INFO [train.py:823] (3/4) Epoch 32, batch 800, loss[loss=1.974, simple_loss=0.2046, pruned_loss=0.0216, codebook_loss=18.5, over 7147.00 frames.], tot_loss[loss=2.035, simple_loss=0.2431, pruned_loss=0.03186, codebook_loss=18.81, over 1397411.59 frames.], batch size: 17, lr: 5.28e-04
+2022-05-27 20:50:20,037 INFO [train.py:823] (3/4) Epoch 32, batch 850, loss[loss=2.004, simple_loss=0.2255, pruned_loss=0.02399, codebook_loss=18.68, over 7020.00 frames.], tot_loss[loss=2.038, simple_loss=0.243, pruned_loss=0.032, codebook_loss=18.85, over 1400615.84 frames.], batch size: 17, lr: 5.28e-04
+2022-05-27 20:51:02,542 INFO [train.py:823] (3/4) Epoch 32, batch 900, loss[loss=1.967, simple_loss=0.222, pruned_loss=0.0261, codebook_loss=18.3, over 7030.00 frames.], tot_loss[loss=2.043, simple_loss=0.244, pruned_loss=0.03245, codebook_loss=18.89, over 1406418.16 frames.], batch size: 17, lr: 5.27e-04
+2022-05-27 20:51:56,412 INFO [train.py:823] (3/4) Epoch 33, batch 0, loss[loss=1.944, simple_loss=0.2343, pruned_loss=0.02724, codebook_loss=18, over 6842.00 frames.], tot_loss[loss=1.944, simple_loss=0.2343, pruned_loss=0.02724, codebook_loss=18, over 6842.00 frames.], batch size: 29, lr: 5.19e-04
+2022-05-27 20:52:36,649 INFO [train.py:823] (3/4) Epoch 33, batch 50, loss[loss=1.988, simple_loss=0.2127, pruned_loss=0.02451, codebook_loss=18.58, over 7158.00 frames.], tot_loss[loss=2.031, simple_loss=0.2431, pruned_loss=0.03226, codebook_loss=18.78, over 317003.75 frames.], batch size: 17, lr: 5.18e-04
+2022-05-27 20:53:16,496 INFO [train.py:823] (3/4) Epoch 33, batch 100, loss[loss=1.926, simple_loss=0.2124, pruned_loss=0.02492, codebook_loss=17.95, over 6814.00 frames.], tot_loss[loss=2.048, simple_loss=0.2431, pruned_loss=0.0323, codebook_loss=18.94, over 560891.57 frames.], batch size: 15, lr: 5.18e-04
+2022-05-27 20:53:56,618 INFO [train.py:823] (3/4) Epoch 33, batch 150, loss[loss=1.95, simple_loss=0.2433, pruned_loss=0.02728, codebook_loss=18.01, over 7184.00 frames.], tot_loss[loss=2.045, simple_loss=0.2456, pruned_loss=0.03292, codebook_loss=18.9, over 750112.44 frames.], batch size: 21, lr: 5.18e-04
+2022-05-27 20:54:36,237 INFO [train.py:823] (3/4) Epoch 33, batch 200, loss[loss=1.955, simple_loss=0.2607, pruned_loss=0.03312, codebook_loss=17.91, over 7112.00 frames.], tot_loss[loss=2.042, simple_loss=0.2442, pruned_loss=0.03228, codebook_loss=18.87, over 894321.08 frames.], batch size: 20, lr: 5.17e-04
+2022-05-27 20:55:16,535 INFO [train.py:823] (3/4) Epoch 33, batch 250, loss[loss=2.099, simple_loss=0.2795, pruned_loss=0.05138, codebook_loss=19.08, over 7156.00 frames.], tot_loss[loss=2.039, simple_loss=0.2428, pruned_loss=0.0318, codebook_loss=18.86, over 1014440.73 frames.], batch size: 23, lr: 5.17e-04
+2022-05-27 20:55:56,432 INFO [train.py:823] (3/4) Epoch 33, batch 300, loss[loss=2.346, simple_loss=0.2207, pruned_loss=0.03799, codebook_loss=21.98, over 7158.00 frames.], tot_loss[loss=2.034, simple_loss=0.2424, pruned_loss=0.03115, codebook_loss=18.82, over 1107539.13 frames.], batch size: 17, lr: 5.16e-04
+2022-05-27 20:56:36,522 INFO [train.py:823] (3/4) Epoch 33, batch 350, loss[loss=1.987, simple_loss=0.2477, pruned_loss=0.03088, codebook_loss=18.32, over 7328.00 frames.], tot_loss[loss=2.035, simple_loss=0.243, pruned_loss=0.03159, codebook_loss=18.81, over 1176919.42 frames.], batch size: 23, lr: 5.16e-04
+2022-05-27 20:57:16,238 INFO [train.py:823] (3/4) Epoch 33, batch 400, loss[loss=2.104, simple_loss=0.2686, pruned_loss=0.04891, codebook_loss=19.21, over 7410.00 frames.], tot_loss[loss=2.039, simple_loss=0.2434, pruned_loss=0.0318, codebook_loss=18.85, over 1230839.78 frames.], batch size: 22, lr: 5.16e-04
+2022-05-27 20:57:56,223 INFO [train.py:823] (3/4) Epoch 33, batch 450, loss[loss=1.969, simple_loss=0.2232, pruned_loss=0.01765, codebook_loss=18.4, over 7294.00 frames.], tot_loss[loss=2.042, simple_loss=0.244, pruned_loss=0.03176, codebook_loss=18.88, over 1272007.03 frames.], batch size: 19, lr: 5.15e-04
+2022-05-27 20:58:35,800 INFO [train.py:823] (3/4) Epoch 33, batch 500, loss[loss=2.032, simple_loss=0.238, pruned_loss=0.03546, codebook_loss=18.78, over 6842.00 frames.], tot_loss[loss=2.046, simple_loss=0.2441, pruned_loss=0.0319, codebook_loss=18.92, over 1306168.48 frames.], batch size: 29, lr: 5.15e-04
+2022-05-27 20:59:15,999 INFO [train.py:823] (3/4) Epoch 33, batch 550, loss[loss=2.079, simple_loss=0.2412, pruned_loss=0.03673, codebook_loss=19.21, over 7400.00 frames.], tot_loss[loss=2.045, simple_loss=0.2439, pruned_loss=0.03217, codebook_loss=18.91, over 1334400.97 frames.], batch size: 19, lr: 5.14e-04
+2022-05-27 20:59:56,122 INFO [train.py:823] (3/4) Epoch 33, batch 600, loss[loss=1.935, simple_loss=0.2401, pruned_loss=0.02781, codebook_loss=17.87, over 7427.00 frames.], tot_loss[loss=2.041, simple_loss=0.2425, pruned_loss=0.03186, codebook_loss=18.88, over 1354023.43 frames.], batch size: 22, lr: 5.14e-04
+2022-05-27 21:00:36,436 INFO [train.py:823] (3/4) Epoch 33, batch 650, loss[loss=2.142, simple_loss=0.2286, pruned_loss=0.0334, codebook_loss=19.94, over 7147.00 frames.], tot_loss[loss=2.046, simple_loss=0.242, pruned_loss=0.03174, codebook_loss=18.94, over 1372731.08 frames.], batch size: 17, lr: 5.14e-04
+2022-05-27 21:01:16,084 INFO [train.py:823] (3/4) Epoch 33, batch 700, loss[loss=2.034, simple_loss=0.2459, pruned_loss=0.0269, codebook_loss=18.84, over 6438.00 frames.], tot_loss[loss=2.047, simple_loss=0.2428, pruned_loss=0.03181, codebook_loss=18.94, over 1384069.37 frames.], batch size: 34, lr: 5.13e-04
+2022-05-27 21:01:56,096 INFO [train.py:823] (3/4) Epoch 33, batch 750, loss[loss=2.098, simple_loss=0.2706, pruned_loss=0.0464, codebook_loss=19.16, over 7188.00 frames.], tot_loss[loss=2.047, simple_loss=0.2436, pruned_loss=0.03208, codebook_loss=18.93, over 1391274.34 frames.], batch size: 25, lr: 5.13e-04
+2022-05-27 21:02:35,450 INFO [train.py:823] (3/4) Epoch 33, batch 800, loss[loss=1.942, simple_loss=0.2551, pruned_loss=0.04062, codebook_loss=17.74, over 7179.00 frames.], tot_loss[loss=2.042, simple_loss=0.2444, pruned_loss=0.0318, codebook_loss=18.88, over 1391842.47 frames.], batch size: 22, lr: 5.12e-04
+2022-05-27 21:03:16,867 INFO [train.py:823] (3/4) Epoch 33, batch 850, loss[loss=1.942, simple_loss=0.2389, pruned_loss=0.02556, codebook_loss=17.97, over 7094.00 frames.], tot_loss[loss=2.038, simple_loss=0.2434, pruned_loss=0.03183, codebook_loss=18.85, over 1400399.25 frames.], batch size: 18, lr: 5.12e-04
+2022-05-27 21:03:56,329 INFO [train.py:823] (3/4) Epoch 33, batch 900, loss[loss=2.099, simple_loss=0.2213, pruned_loss=0.0346, codebook_loss=19.53, over 7021.00 frames.], tot_loss[loss=2.041, simple_loss=0.243, pruned_loss=0.03201, codebook_loss=18.87, over 1402069.81 frames.], batch size: 16, lr: 5.12e-04
+2022-05-27 21:04:47,352 INFO [train.py:823] (3/4) Epoch 34, batch 0, loss[loss=2.017, simple_loss=0.2501, pruned_loss=0.03046, codebook_loss=18.61, over 7206.00 frames.], tot_loss[loss=2.017, simple_loss=0.2501, pruned_loss=0.03046, codebook_loss=18.61, over 7206.00 frames.], batch size: 24, lr: 5.04e-04
+2022-05-27 21:05:27,119 INFO [train.py:823] (3/4) Epoch 34, batch 50, loss[loss=2.017, simple_loss=0.2335, pruned_loss=0.03439, codebook_loss=18.66, over 6788.00 frames.], tot_loss[loss=2.024, simple_loss=0.2391, pruned_loss=0.02916, codebook_loss=18.76, over 320062.37 frames.], batch size: 15, lr: 5.03e-04
+2022-05-27 21:06:07,173 INFO [train.py:823] (3/4) Epoch 34, batch 100, loss[loss=1.991, simple_loss=0.2463, pruned_loss=0.02098, codebook_loss=18.47, over 7285.00 frames.], tot_loss[loss=2.034, simple_loss=0.2422, pruned_loss=0.03126, codebook_loss=18.82, over 561009.64 frames.], batch size: 21, lr: 5.03e-04
+2022-05-27 21:06:47,134 INFO [train.py:823] (3/4) Epoch 34, batch 150, loss[loss=1.93, simple_loss=0.2494, pruned_loss=0.02176, codebook_loss=17.84, over 7308.00 frames.], tot_loss[loss=2.03, simple_loss=0.2428, pruned_loss=0.03072, codebook_loss=18.78, over 754516.39 frames.], batch size: 22, lr: 5.02e-04
+2022-05-27 21:07:27,067 INFO [train.py:823] (3/4) Epoch 34, batch 200, loss[loss=1.905, simple_loss=0.2336, pruned_loss=0.01907, codebook_loss=17.69, over 7005.00 frames.], tot_loss[loss=2.031, simple_loss=0.2427, pruned_loss=0.03116, codebook_loss=18.79, over 902434.22 frames.], batch size: 26, lr: 5.02e-04
+2022-05-27 21:08:06,809 INFO [train.py:823] (3/4) Epoch 34, batch 250, loss[loss=2.284, simple_loss=0.2623, pruned_loss=0.04374, codebook_loss=21.09, over 7032.00 frames.], tot_loss[loss=2.027, simple_loss=0.242, pruned_loss=0.03086, codebook_loss=18.75, over 1013202.21 frames.], batch size: 26, lr: 5.02e-04
+2022-05-27 21:08:46,831 INFO [train.py:823] (3/4) Epoch 34, batch 300, loss[loss=2.083, simple_loss=0.2411, pruned_loss=0.02511, codebook_loss=19.37, over 7375.00 frames.], tot_loss[loss=2.028, simple_loss=0.2413, pruned_loss=0.03034, codebook_loss=18.77, over 1103721.11 frames.], batch size: 21, lr: 5.01e-04
+2022-05-27 21:09:26,875 INFO [train.py:823] (3/4) Epoch 34, batch 350, loss[loss=1.982, simple_loss=0.2405, pruned_loss=0.02679, codebook_loss=18.35, over 7100.00 frames.], tot_loss[loss=2.026, simple_loss=0.2418, pruned_loss=0.03057, codebook_loss=18.75, over 1169976.21 frames.], batch size: 19, lr: 5.01e-04
+2022-05-27 21:10:07,255 INFO [train.py:823] (3/4) Epoch 34, batch 400, loss[loss=1.971, simple_loss=0.2358, pruned_loss=0.02543, codebook_loss=18.28, over 7275.00 frames.], tot_loss[loss=2.026, simple_loss=0.2419, pruned_loss=0.0309, codebook_loss=18.74, over 1224368.22 frames.], batch size: 21, lr: 5.00e-04
+2022-05-27 21:10:46,993 INFO [train.py:823] (3/4) Epoch 34, batch 450, loss[loss=1.982, simple_loss=0.2589, pruned_loss=0.0263, codebook_loss=18.26, over 7275.00 frames.], tot_loss[loss=2.027, simple_loss=0.2422, pruned_loss=0.03096, codebook_loss=18.75, over 1270064.96 frames.], batch size: 20, lr: 5.00e-04
+2022-05-27 21:11:27,174 INFO [train.py:823] (3/4) Epoch 34, batch 500, loss[loss=1.952, simple_loss=0.241, pruned_loss=0.03001, codebook_loss=18.01, over 7163.00 frames.], tot_loss[loss=2.033, simple_loss=0.2416, pruned_loss=0.03093, codebook_loss=18.81, over 1303480.65 frames.], batch size: 23, lr: 5.00e-04
+2022-05-27 21:12:07,374 INFO [train.py:823] (3/4) Epoch 34, batch 550, loss[loss=1.981, simple_loss=0.242, pruned_loss=0.0347, codebook_loss=18.26, over 7184.00 frames.], tot_loss[loss=2.024, simple_loss=0.2414, pruned_loss=0.03056, codebook_loss=18.73, over 1335243.82 frames.], batch size: 25, lr: 4.99e-04
+2022-05-27 21:12:47,516 INFO [train.py:823] (3/4) Epoch 34, batch 600, loss[loss=1.923, simple_loss=0.2133, pruned_loss=0.0225, codebook_loss=17.94, over 7301.00 frames.], tot_loss[loss=2.024, simple_loss=0.2415, pruned_loss=0.03059, codebook_loss=18.72, over 1352678.36 frames.], batch size: 17, lr: 4.99e-04
+2022-05-27 21:13:27,630 INFO [train.py:823] (3/4) Epoch 34, batch 650, loss[loss=2.121, simple_loss=0.2585, pruned_loss=0.04253, codebook_loss=19.49, over 6939.00 frames.], tot_loss[loss=2.029, simple_loss=0.2406, pruned_loss=0.03051, codebook_loss=18.78, over 1367397.89 frames.], batch size: 29, lr: 4.99e-04
+2022-05-27 21:14:11,307 INFO [train.py:823] (3/4) Epoch 34, batch 700, loss[loss=1.979, simple_loss=0.2318, pruned_loss=0.02483, codebook_loss=18.38, over 7374.00 frames.], tot_loss[loss=2.032, simple_loss=0.2411, pruned_loss=0.03064, codebook_loss=18.8, over 1377208.98 frames.], batch size: 20, lr: 4.98e-04
+2022-05-27 21:14:51,481 INFO [train.py:823] (3/4) Epoch 34, batch 750, loss[loss=2.044, simple_loss=0.2232, pruned_loss=0.02377, codebook_loss=19.09, over 6995.00 frames.], tot_loss[loss=2.035, simple_loss=0.2417, pruned_loss=0.03097, codebook_loss=18.83, over 1388855.59 frames.], batch size: 16, lr: 4.98e-04
+2022-05-27 21:15:35,819 INFO [train.py:823] (3/4) Epoch 34, batch 800, loss[loss=2.034, simple_loss=0.2426, pruned_loss=0.03058, codebook_loss=18.82, over 7199.00 frames.], tot_loss[loss=2.036, simple_loss=0.2416, pruned_loss=0.03071, codebook_loss=18.85, over 1396554.10 frames.], batch size: 19, lr: 4.97e-04
+2022-05-27 21:16:15,604 INFO [train.py:823] (3/4) Epoch 34, batch 850, loss[loss=1.972, simple_loss=0.2478, pruned_loss=0.02204, codebook_loss=18.26, over 7374.00 frames.], tot_loss[loss=2.029, simple_loss=0.242, pruned_loss=0.03029, codebook_loss=18.77, over 1396406.19 frames.], batch size: 21, lr: 4.97e-04
+2022-05-27 21:16:55,845 INFO [train.py:823] (3/4) Epoch 34, batch 900, loss[loss=1.985, simple_loss=0.212, pruned_loss=0.02517, codebook_loss=18.53, over 7091.00 frames.], tot_loss[loss=2.032, simple_loss=0.2418, pruned_loss=0.03054, codebook_loss=18.8, over 1400626.42 frames.], batch size: 18, lr: 4.97e-04
+2022-05-27 21:17:49,282 INFO [train.py:823] (3/4) Epoch 35, batch 0, loss[loss=2.068, simple_loss=0.2468, pruned_loss=0.01824, codebook_loss=19.26, over 7180.00 frames.], tot_loss[loss=2.068, simple_loss=0.2468, pruned_loss=0.01824, codebook_loss=19.26, over 7180.00 frames.], batch size: 21, lr: 4.89e-04
+2022-05-27 21:18:30,078 INFO [train.py:823] (3/4) Epoch 35, batch 50, loss[loss=2.134, simple_loss=0.2196, pruned_loss=0.02577, codebook_loss=19.99, over 7182.00 frames.], tot_loss[loss=2.027, simple_loss=0.2434, pruned_loss=0.03012, codebook_loss=18.75, over 323302.94 frames.], batch size: 18, lr: 4.89e-04
+2022-05-27 21:19:10,012 INFO [train.py:823] (3/4) Epoch 35, batch 100, loss[loss=1.957, simple_loss=0.2316, pruned_loss=0.0262, codebook_loss=18.15, over 6328.00 frames.], tot_loss[loss=2.024, simple_loss=0.2418, pruned_loss=0.02961, codebook_loss=18.74, over 567933.91 frames.], batch size: 34, lr: 4.88e-04
+2022-05-27 21:19:50,178 INFO [train.py:823] (3/4) Epoch 35, batch 150, loss[loss=2.032, simple_loss=0.2447, pruned_loss=0.02507, codebook_loss=18.85, over 7198.00 frames.], tot_loss[loss=2.02, simple_loss=0.2412, pruned_loss=0.02949, codebook_loss=18.7, over 753093.92 frames.], batch size: 25, lr: 4.88e-04
+2022-05-27 21:20:30,531 INFO [train.py:823] (3/4) Epoch 35, batch 200, loss[loss=1.977, simple_loss=0.2527, pruned_loss=0.03199, codebook_loss=18.19, over 6956.00 frames.], tot_loss[loss=2.023, simple_loss=0.2411, pruned_loss=0.02995, codebook_loss=18.73, over 902759.65 frames.], batch size: 29, lr: 4.88e-04
+2022-05-27 21:21:10,401 INFO [train.py:823] (3/4) Epoch 35, batch 250, loss[loss=1.983, simple_loss=0.256, pruned_loss=0.03273, codebook_loss=18.22, over 7254.00 frames.], tot_loss[loss=2.018, simple_loss=0.2412, pruned_loss=0.03004, codebook_loss=18.68, over 1013149.23 frames.], batch size: 24, lr: 4.87e-04
+2022-05-27 21:21:50,270 INFO [train.py:823] (3/4) Epoch 35, batch 300, loss[loss=1.951, simple_loss=0.2376, pruned_loss=0.02675, codebook_loss=18.06, over 7284.00 frames.], tot_loss[loss=2.023, simple_loss=0.2423, pruned_loss=0.03069, codebook_loss=18.71, over 1105209.82 frames.], batch size: 21, lr: 4.87e-04
+2022-05-27 21:22:30,351 INFO [train.py:823] (3/4) Epoch 35, batch 350, loss[loss=2.016, simple_loss=0.2401, pruned_loss=0.03061, codebook_loss=18.66, over 7087.00 frames.], tot_loss[loss=2.02, simple_loss=0.2425, pruned_loss=0.03039, codebook_loss=18.68, over 1170410.36 frames.], batch size: 18, lr: 4.87e-04
+2022-05-27 21:23:10,164 INFO [train.py:823] (3/4) Epoch 35, batch 400, loss[loss=2.019, simple_loss=0.2493, pruned_loss=0.03416, codebook_loss=18.6, over 7169.00 frames.], tot_loss[loss=2.022, simple_loss=0.2423, pruned_loss=0.0306, codebook_loss=18.71, over 1222130.86 frames.], batch size: 22, lr: 4.86e-04
+2022-05-27 21:23:50,300 INFO [train.py:823] (3/4) Epoch 35, batch 450, loss[loss=2.057, simple_loss=0.2209, pruned_loss=0.03464, codebook_loss=19.12, over 7294.00 frames.], tot_loss[loss=2.021, simple_loss=0.2417, pruned_loss=0.03037, codebook_loss=18.7, over 1269727.05 frames.], batch size: 17, lr: 4.86e-04
+2022-05-27 21:24:30,262 INFO [train.py:823] (3/4) Epoch 35, batch 500, loss[loss=2, simple_loss=0.2296, pruned_loss=0.029, codebook_loss=18.56, over 7432.00 frames.], tot_loss[loss=2.018, simple_loss=0.2418, pruned_loss=0.03044, codebook_loss=18.67, over 1304706.81 frames.], batch size: 18, lr: 4.86e-04
+2022-05-27 21:25:10,223 INFO [train.py:823] (3/4) Epoch 35, batch 550, loss[loss=2.004, simple_loss=0.217, pruned_loss=0.02343, codebook_loss=18.72, over 7026.00 frames.], tot_loss[loss=2.02, simple_loss=0.2411, pruned_loss=0.03041, codebook_loss=18.69, over 1328127.99 frames.], batch size: 17, lr: 4.85e-04
+2022-05-27 21:25:50,301 INFO [train.py:823] (3/4) Epoch 35, batch 600, loss[loss=2.104, simple_loss=0.2566, pruned_loss=0.0346, codebook_loss=19.41, over 7278.00 frames.], tot_loss[loss=2.024, simple_loss=0.2411, pruned_loss=0.03047, codebook_loss=18.73, over 1349375.55 frames.], batch size: 20, lr: 4.85e-04
+2022-05-27 21:26:30,436 INFO [train.py:823] (3/4) Epoch 35, batch 650, loss[loss=2.05, simple_loss=0.2657, pruned_loss=0.03983, codebook_loss=18.77, over 7066.00 frames.], tot_loss[loss=2.025, simple_loss=0.241, pruned_loss=0.0307, codebook_loss=18.74, over 1367975.95 frames.], batch size: 26, lr: 4.84e-04
+2022-05-27 21:27:11,673 INFO [train.py:823] (3/4) Epoch 35, batch 700, loss[loss=2.012, simple_loss=0.2556, pruned_loss=0.02679, codebook_loss=18.58, over 7274.00 frames.], tot_loss[loss=2.027, simple_loss=0.2406, pruned_loss=0.03056, codebook_loss=18.76, over 1377360.00 frames.], batch size: 20, lr: 4.84e-04
+2022-05-27 21:27:51,851 INFO [train.py:823] (3/4) Epoch 35, batch 750, loss[loss=1.996, simple_loss=0.2283, pruned_loss=0.02508, codebook_loss=18.57, over 7087.00 frames.], tot_loss[loss=2.027, simple_loss=0.2415, pruned_loss=0.03083, codebook_loss=18.75, over 1390322.26 frames.], batch size: 19, lr: 4.84e-04
+2022-05-27 21:28:31,669 INFO [train.py:823] (3/4) Epoch 35, batch 800, loss[loss=1.961, simple_loss=0.2236, pruned_loss=0.02162, codebook_loss=18.28, over 7310.00 frames.], tot_loss[loss=2.026, simple_loss=0.2409, pruned_loss=0.03062, codebook_loss=18.74, over 1394648.90 frames.], batch size: 18, lr: 4.83e-04
+2022-05-27 21:29:11,835 INFO [train.py:823] (3/4) Epoch 35, batch 850, loss[loss=2.032, simple_loss=0.257, pruned_loss=0.03273, codebook_loss=18.71, over 7420.00 frames.], tot_loss[loss=2.028, simple_loss=0.2409, pruned_loss=0.03068, codebook_loss=18.77, over 1402925.95 frames.], batch size: 22, lr: 4.83e-04
+2022-05-27 21:29:51,289 INFO [train.py:823] (3/4) Epoch 35, batch 900, loss[loss=2.027, simple_loss=0.2435, pruned_loss=0.02241, codebook_loss=18.83, over 6641.00 frames.], tot_loss[loss=2.027, simple_loss=0.2403, pruned_loss=0.03052, codebook_loss=18.76, over 1400744.95 frames.], batch size: 34, lr: 4.83e-04
+2022-05-27 21:30:31,015 INFO [train.py:823] (3/4) Epoch 35, batch 950, loss[loss=1.958, simple_loss=0.2442, pruned_loss=0.03496, codebook_loss=18.01, over 5082.00 frames.], tot_loss[loss=2.025, simple_loss=0.2413, pruned_loss=0.03074, codebook_loss=18.74, over 1379662.49 frames.], batch size: 47, lr: 4.82e-04
+2022-05-27 21:30:46,167 INFO [train.py:823] (3/4) Epoch 36, batch 0, loss[loss=1.937, simple_loss=0.2417, pruned_loss=0.02338, codebook_loss=17.93, over 7409.00 frames.], tot_loss[loss=1.937, simple_loss=0.2417, pruned_loss=0.02338, codebook_loss=17.93, over 7409.00 frames.], batch size: 22, lr: 4.76e-04
+2022-05-27 21:31:25,793 INFO [train.py:823] (3/4) Epoch 36, batch 50, loss[loss=1.976, simple_loss=0.2199, pruned_loss=0.02277, codebook_loss=18.43, over 7145.00 frames.], tot_loss[loss=2.019, simple_loss=0.2393, pruned_loss=0.03037, codebook_loss=18.69, over 318861.83 frames.], batch size: 17, lr: 4.75e-04
+2022-05-27 21:32:05,764 INFO [train.py:823] (3/4) Epoch 36, batch 100, loss[loss=2.049, simple_loss=0.2533, pruned_loss=0.03854, codebook_loss=18.83, over 6634.00 frames.], tot_loss[loss=2.012, simple_loss=0.2388, pruned_loss=0.02948, codebook_loss=18.64, over 564560.45 frames.], batch size: 34, lr: 4.75e-04
+2022-05-27 21:32:45,260 INFO [train.py:823] (3/4) Epoch 36, batch 150, loss[loss=1.991, simple_loss=0.2493, pruned_loss=0.04103, codebook_loss=18.26, over 7215.00 frames.], tot_loss[loss=2.017, simple_loss=0.24, pruned_loss=0.02998, codebook_loss=18.67, over 751771.14 frames.], batch size: 25, lr: 4.74e-04
+2022-05-27 21:33:25,502 INFO [train.py:823] (3/4) Epoch 36, batch 200, loss[loss=1.941, simple_loss=0.2088, pruned_loss=0.02534, codebook_loss=18.11, over 7293.00 frames.], tot_loss[loss=2.012, simple_loss=0.2386, pruned_loss=0.02935, codebook_loss=18.63, over 900198.36 frames.], batch size: 17, lr: 4.74e-04
+2022-05-27 21:34:05,051 INFO [train.py:823] (3/4) Epoch 36, batch 250, loss[loss=1.938, simple_loss=0.2322, pruned_loss=0.02523, codebook_loss=17.97, over 7395.00 frames.], tot_loss[loss=2.021, simple_loss=0.2389, pruned_loss=0.02969, codebook_loss=18.72, over 1013143.97 frames.], batch size: 19, lr: 4.74e-04
+2022-05-27 21:34:45,302 INFO [train.py:823] (3/4) Epoch 36, batch 300, loss[loss=1.911, simple_loss=0.2488, pruned_loss=0.02527, codebook_loss=17.61, over 7328.00 frames.], tot_loss[loss=2.019, simple_loss=0.2394, pruned_loss=0.02957, codebook_loss=18.7, over 1101459.63 frames.], batch size: 23, lr: 4.73e-04
+2022-05-27 21:35:25,042 INFO [train.py:823] (3/4) Epoch 36, batch 350, loss[loss=2.054, simple_loss=0.2517, pruned_loss=0.03421, codebook_loss=18.94, over 7386.00 frames.], tot_loss[loss=2.017, simple_loss=0.2405, pruned_loss=0.02983, codebook_loss=18.67, over 1171443.18 frames.], batch size: 20, lr: 4.73e-04
+2022-05-27 21:36:05,134 INFO [train.py:823] (3/4) Epoch 36, batch 400, loss[loss=2.07, simple_loss=0.2473, pruned_loss=0.03671, codebook_loss=19.1, over 7090.00 frames.], tot_loss[loss=2.014, simple_loss=0.2409, pruned_loss=0.03019, codebook_loss=18.64, over 1226565.18 frames.], batch size: 18, lr: 4.73e-04
+2022-05-27 21:36:44,922 INFO [train.py:823] (3/4) Epoch 36, batch 450, loss[loss=2.001, simple_loss=0.2402, pruned_loss=0.0339, codebook_loss=18.47, over 7038.00 frames.], tot_loss[loss=2.013, simple_loss=0.2404, pruned_loss=0.03011, codebook_loss=18.63, over 1269067.13 frames.], batch size: 26, lr: 4.72e-04
+2022-05-27 21:37:25,000 INFO [train.py:823] (3/4) Epoch 36, batch 500, loss[loss=2.1, simple_loss=0.2543, pruned_loss=0.03782, codebook_loss=19.35, over 7234.00 frames.], tot_loss[loss=2.011, simple_loss=0.2404, pruned_loss=0.03025, codebook_loss=18.61, over 1299460.19 frames.], batch size: 24, lr: 4.72e-04
+2022-05-27 21:38:04,893 INFO [train.py:823] (3/4) Epoch 36, batch 550, loss[loss=1.993, simple_loss=0.2177, pruned_loss=0.03128, codebook_loss=18.53, over 7286.00 frames.], tot_loss[loss=2.011, simple_loss=0.2401, pruned_loss=0.02999, codebook_loss=18.61, over 1326779.79 frames.], batch size: 17, lr: 4.72e-04
+2022-05-27 21:38:45,257 INFO [train.py:823] (3/4) Epoch 36, batch 600, loss[loss=2.1, simple_loss=0.2154, pruned_loss=0.02244, codebook_loss=19.69, over 7304.00 frames.], tot_loss[loss=2.016, simple_loss=0.2401, pruned_loss=0.02997, codebook_loss=18.66, over 1345371.07 frames.], batch size: 17, lr: 4.71e-04
+2022-05-27 21:39:26,310 INFO [train.py:823] (3/4) Epoch 36, batch 650, loss[loss=2.092, simple_loss=0.2263, pruned_loss=0.01844, codebook_loss=19.61, over 7367.00 frames.], tot_loss[loss=2.023, simple_loss=0.2414, pruned_loss=0.03033, codebook_loss=18.72, over 1361303.73 frames.], batch size: 21, lr: 4.71e-04
+2022-05-27 21:40:09,239 INFO [train.py:823] (3/4) Epoch 36, batch 700, loss[loss=2.009, simple_loss=0.2247, pruned_loss=0.03352, codebook_loss=18.64, over 7294.00 frames.], tot_loss[loss=2.026, simple_loss=0.2415, pruned_loss=0.03055, codebook_loss=18.74, over 1377180.21 frames.], batch size: 17, lr: 4.71e-04
+2022-05-27 21:40:49,259 INFO [train.py:823] (3/4) Epoch 36, batch 750, loss[loss=2.094, simple_loss=0.2631, pruned_loss=0.0359, codebook_loss=19.26, over 7269.00 frames.], tot_loss[loss=2.028, simple_loss=0.2409, pruned_loss=0.03039, codebook_loss=18.77, over 1387429.34 frames.], batch size: 21, lr: 4.70e-04
+2022-05-27 21:41:29,167 INFO [train.py:823] (3/4) Epoch 36, batch 800, loss[loss=2.02, simple_loss=0.2541, pruned_loss=0.03389, codebook_loss=18.59, over 7378.00 frames.], tot_loss[loss=2.024, simple_loss=0.2409, pruned_loss=0.03011, codebook_loss=18.73, over 1387645.79 frames.], batch size: 21, lr: 4.70e-04
+2022-05-27 21:42:08,718 INFO [train.py:823] (3/4) Epoch 36, batch 850, loss[loss=1.934, simple_loss=0.2464, pruned_loss=0.03536, codebook_loss=17.75, over 7347.00 frames.], tot_loss[loss=2.024, simple_loss=0.24, pruned_loss=0.02997, codebook_loss=18.74, over 1388923.25 frames.], batch size: 23, lr: 4.70e-04
+2022-05-27 21:42:48,763 INFO [train.py:823] (3/4) Epoch 36, batch 900, loss[loss=1.932, simple_loss=0.2459, pruned_loss=0.02438, codebook_loss=17.85, over 7406.00 frames.], tot_loss[loss=2.02, simple_loss=0.2406, pruned_loss=0.02966, codebook_loss=18.7, over 1396891.69 frames.], batch size: 22, lr: 4.69e-04
+2022-05-27 21:43:42,177 INFO [train.py:823] (3/4) Epoch 37, batch 0, loss[loss=1.953, simple_loss=0.251, pruned_loss=0.0285, codebook_loss=17.99, over 6434.00 frames.], tot_loss[loss=1.953, simple_loss=0.251, pruned_loss=0.0285, codebook_loss=17.99, over 6434.00 frames.], batch size: 34, lr: 4.63e-04
+2022-05-27 21:44:22,074 INFO [train.py:823] (3/4) Epoch 37, batch 50, loss[loss=2.163, simple_loss=0.2526, pruned_loss=0.03167, codebook_loss=20.05, over 7291.00 frames.], tot_loss[loss=2.017, simple_loss=0.2445, pruned_loss=0.03173, codebook_loss=18.63, over 318466.80 frames.], batch size: 22, lr: 4.62e-04
+2022-05-27 21:45:01,725 INFO [train.py:823] (3/4) Epoch 37, batch 100, loss[loss=2.004, simple_loss=0.2473, pruned_loss=0.03157, codebook_loss=18.49, over 7220.00 frames.], tot_loss[loss=2.009, simple_loss=0.2418, pruned_loss=0.03093, codebook_loss=18.57, over 561835.44 frames.], batch size: 24, lr: 4.62e-04
+2022-05-27 21:45:41,732 INFO [train.py:823] (3/4) Epoch 37, batch 150, loss[loss=2.041, simple_loss=0.2501, pruned_loss=0.02537, codebook_loss=18.91, over 7176.00 frames.], tot_loss[loss=2.014, simple_loss=0.2411, pruned_loss=0.03051, codebook_loss=18.63, over 750047.09 frames.], batch size: 21, lr: 4.62e-04
+2022-05-27 21:46:21,865 INFO [train.py:823] (3/4) Epoch 37, batch 200, loss[loss=1.94, simple_loss=0.2508, pruned_loss=0.03011, codebook_loss=17.85, over 7248.00 frames.], tot_loss[loss=2.015, simple_loss=0.2397, pruned_loss=0.03021, codebook_loss=18.65, over 902529.57 frames.], batch size: 24, lr: 4.61e-04
+2022-05-27 21:47:01,954 INFO [train.py:823] (3/4) Epoch 37, batch 250, loss[loss=2.061, simple_loss=0.2634, pruned_loss=0.04138, codebook_loss=18.87, over 7001.00 frames.], tot_loss[loss=2.011, simple_loss=0.2404, pruned_loss=0.03042, codebook_loss=18.6, over 1019179.88 frames.], batch size: 26, lr: 4.61e-04
+2022-05-27 21:47:41,868 INFO [train.py:823] (3/4) Epoch 37, batch 300, loss[loss=1.923, simple_loss=0.2072, pruned_loss=0.02384, codebook_loss=17.95, over 6987.00 frames.], tot_loss[loss=2.014, simple_loss=0.2399, pruned_loss=0.03025, codebook_loss=18.64, over 1104283.98 frames.], batch size: 16, lr: 4.61e-04
+2022-05-27 21:48:21,742 INFO [train.py:823] (3/4) Epoch 37, batch 350, loss[loss=2.071, simple_loss=0.2591, pruned_loss=0.0295, codebook_loss=19.12, over 7192.00 frames.], tot_loss[loss=2.007, simple_loss=0.2399, pruned_loss=0.02988, codebook_loss=18.57, over 1172535.64 frames.], batch size: 25, lr: 4.60e-04
+2022-05-27 21:49:01,284 INFO [train.py:823] (3/4) Epoch 37, batch 400, loss[loss=1.972, simple_loss=0.2074, pruned_loss=0.02252, codebook_loss=18.46, over 7286.00 frames.], tot_loss[loss=2.007, simple_loss=0.2399, pruned_loss=0.02958, codebook_loss=18.58, over 1229058.43 frames.], batch size: 17, lr: 4.60e-04
+2022-05-27 21:49:41,269 INFO [train.py:823] (3/4) Epoch 37, batch 450, loss[loss=2.175, simple_loss=0.2313, pruned_loss=0.03021, codebook_loss=20.29, over 7202.00 frames.], tot_loss[loss=2.014, simple_loss=0.241, pruned_loss=0.03032, codebook_loss=18.63, over 1268455.24 frames.], batch size: 19, lr: 4.60e-04
+2022-05-27 21:50:22,183 INFO [train.py:823] (3/4) Epoch 37, batch 500, loss[loss=1.982, simple_loss=0.2297, pruned_loss=0.03029, codebook_loss=18.36, over 7017.00 frames.], tot_loss[loss=2.018, simple_loss=0.2415, pruned_loss=0.03056, codebook_loss=18.67, over 1303959.84 frames.], batch size: 16, lr: 4.59e-04
+2022-05-27 21:51:02,115 INFO [train.py:823] (3/4) Epoch 37, batch 550, loss[loss=1.992, simple_loss=0.2074, pruned_loss=0.02491, codebook_loss=18.63, over 7012.00 frames.], tot_loss[loss=2.02, simple_loss=0.241, pruned_loss=0.03052, codebook_loss=18.69, over 1329430.64 frames.], batch size: 16, lr: 4.59e-04
+2022-05-27 21:51:41,640 INFO [train.py:823] (3/4) Epoch 37, batch 600, loss[loss=1.954, simple_loss=0.2483, pruned_loss=0.02294, codebook_loss=18.07, over 7349.00 frames.], tot_loss[loss=2.019, simple_loss=0.2419, pruned_loss=0.03063, codebook_loss=18.68, over 1348783.18 frames.], batch size: 23, lr: 4.59e-04
+2022-05-27 21:52:22,245 INFO [train.py:823] (3/4) Epoch 37, batch 650, loss[loss=2.008, simple_loss=0.224, pruned_loss=0.03158, codebook_loss=18.65, over 7169.00 frames.], tot_loss[loss=2.015, simple_loss=0.2412, pruned_loss=0.03037, codebook_loss=18.65, over 1364043.32 frames.], batch size: 17, lr: 4.58e-04
+2022-05-27 21:53:01,927 INFO [train.py:823] (3/4) Epoch 37, batch 700, loss[loss=1.963, simple_loss=0.2479, pruned_loss=0.02396, codebook_loss=18.15, over 7409.00 frames.], tot_loss[loss=2.015, simple_loss=0.2417, pruned_loss=0.03016, codebook_loss=18.64, over 1371898.30 frames.], batch size: 22, lr: 4.58e-04
+2022-05-27 21:53:41,856 INFO [train.py:823] (3/4) Epoch 37, batch 750, loss[loss=1.938, simple_loss=0.2412, pruned_loss=0.02837, codebook_loss=17.89, over 4866.00 frames.], tot_loss[loss=2.014, simple_loss=0.241, pruned_loss=0.02985, codebook_loss=18.64, over 1379864.06 frames.], batch size: 46, lr: 4.58e-04
+2022-05-27 21:54:21,480 INFO [train.py:823] (3/4) Epoch 37, batch 800, loss[loss=1.993, simple_loss=0.2591, pruned_loss=0.0323, codebook_loss=18.31, over 7286.00 frames.], tot_loss[loss=2.012, simple_loss=0.241, pruned_loss=0.02979, codebook_loss=18.62, over 1385468.60 frames.], batch size: 21, lr: 4.57e-04
+2022-05-27 21:55:01,506 INFO [train.py:823] (3/4) Epoch 37, batch 850, loss[loss=2.139, simple_loss=0.2307, pruned_loss=0.03867, codebook_loss=19.85, over 7224.00 frames.], tot_loss[loss=2.017, simple_loss=0.2405, pruned_loss=0.02978, codebook_loss=18.67, over 1387311.87 frames.], batch size: 16, lr: 4.57e-04
+2022-05-27 21:55:41,468 INFO [train.py:823] (3/4) Epoch 37, batch 900, loss[loss=2.128, simple_loss=0.3145, pruned_loss=0.06705, codebook_loss=19.04, over 7153.00 frames.], tot_loss[loss=2.021, simple_loss=0.2406, pruned_loss=0.03007, codebook_loss=18.7, over 1394107.53 frames.], batch size: 23, lr: 4.57e-04
+2022-05-27 21:56:35,761 INFO [train.py:823] (3/4) Epoch 38, batch 0, loss[loss=1.889, simple_loss=0.2332, pruned_loss=0.02309, codebook_loss=17.49, over 7392.00 frames.], tot_loss[loss=1.889, simple_loss=0.2332, pruned_loss=0.02309, codebook_loss=17.49, over 7392.00 frames.], batch size: 19, lr: 4.50e-04
+2022-05-27 21:57:15,592 INFO [train.py:823] (3/4) Epoch 38, batch 50, loss[loss=1.95, simple_loss=0.2418, pruned_loss=0.02371, codebook_loss=18.06, over 7109.00 frames.], tot_loss[loss=1.998, simple_loss=0.2407, pruned_loss=0.02934, codebook_loss=18.48, over 322555.24 frames.], batch size: 19, lr: 4.50e-04
+2022-05-27 21:57:55,716 INFO [train.py:823] (3/4) Epoch 38, batch 100, loss[loss=1.936, simple_loss=0.244, pruned_loss=0.03053, codebook_loss=17.83, over 7352.00 frames.], tot_loss[loss=2.004, simple_loss=0.2391, pruned_loss=0.02901, codebook_loss=18.55, over 565394.95 frames.], batch size: 23, lr: 4.50e-04
+2022-05-27 21:58:35,476 INFO [train.py:823] (3/4) Epoch 38, batch 150, loss[loss=1.997, simple_loss=0.265, pruned_loss=0.03163, codebook_loss=18.33, over 6972.00 frames.], tot_loss[loss=1.998, simple_loss=0.2377, pruned_loss=0.02863, codebook_loss=18.51, over 754111.14 frames.], batch size: 26, lr: 4.50e-04
+2022-05-27 21:59:15,485 INFO [train.py:823] (3/4) Epoch 38, batch 200, loss[loss=2.037, simple_loss=0.2652, pruned_loss=0.03868, codebook_loss=18.66, over 6488.00 frames.], tot_loss[loss=1.999, simple_loss=0.2378, pruned_loss=0.02831, codebook_loss=18.51, over 901627.93 frames.], batch size: 34, lr: 4.49e-04
+2022-05-27 21:59:55,448 INFO [train.py:823] (3/4) Epoch 38, batch 250, loss[loss=1.951, simple_loss=0.2414, pruned_loss=0.02877, codebook_loss=18.01, over 7107.00 frames.], tot_loss[loss=1.996, simple_loss=0.2382, pruned_loss=0.02876, codebook_loss=18.48, over 1020877.45 frames.], batch size: 20, lr: 4.49e-04
+2022-05-27 22:00:35,331 INFO [train.py:823] (3/4) Epoch 38, batch 300, loss[loss=1.9, simple_loss=0.2431, pruned_loss=0.02562, codebook_loss=17.53, over 7281.00 frames.], tot_loss[loss=1.996, simple_loss=0.2393, pruned_loss=0.02946, codebook_loss=18.47, over 1107496.05 frames.], batch size: 21, lr: 4.49e-04
+2022-05-27 22:01:15,225 INFO [train.py:823] (3/4) Epoch 38, batch 350, loss[loss=1.849, simple_loss=0.2272, pruned_loss=0.02258, codebook_loss=17.13, over 6843.00 frames.], tot_loss[loss=1.995, simple_loss=0.2399, pruned_loss=0.02956, codebook_loss=18.45, over 1182161.63 frames.], batch size: 15, lr: 4.48e-04
+2022-05-27 22:01:55,558 INFO [train.py:823] (3/4) Epoch 38, batch 400, loss[loss=1.957, simple_loss=0.2414, pruned_loss=0.02898, codebook_loss=18.07, over 4793.00 frames.], tot_loss[loss=1.996, simple_loss=0.2409, pruned_loss=0.02967, codebook_loss=18.45, over 1235641.38 frames.], batch size: 46, lr: 4.48e-04
+2022-05-27 22:02:35,637 INFO [train.py:823] (3/4) Epoch 38, batch 450, loss[loss=1.979, simple_loss=0.258, pruned_loss=0.02704, codebook_loss=18.23, over 7199.00 frames.], tot_loss[loss=2.004, simple_loss=0.24, pruned_loss=0.0296, codebook_loss=18.55, over 1281253.90 frames.], batch size: 20, lr: 4.48e-04
+2022-05-27 22:03:16,104 INFO [train.py:823] (3/4) Epoch 38, batch 500, loss[loss=1.993, simple_loss=0.2692, pruned_loss=0.03397, codebook_loss=18.24, over 7275.00 frames.], tot_loss[loss=2.004, simple_loss=0.2388, pruned_loss=0.02949, codebook_loss=18.55, over 1315818.23 frames.], batch size: 21, lr: 4.47e-04
+2022-05-27 22:03:55,603 INFO [train.py:823] (3/4) Epoch 38, batch 550, loss[loss=2.057, simple_loss=0.2674, pruned_loss=0.03857, codebook_loss=18.85, over 7201.00 frames.], tot_loss[loss=2.01, simple_loss=0.2395, pruned_loss=0.03024, codebook_loss=18.6, over 1334205.90 frames.], batch size: 20, lr: 4.47e-04
+2022-05-27 22:04:38,505 INFO [train.py:823] (3/4) Epoch 38, batch 600, loss[loss=2.019, simple_loss=0.2565, pruned_loss=0.03152, codebook_loss=18.6, over 6480.00 frames.], tot_loss[loss=2.014, simple_loss=0.2394, pruned_loss=0.03027, codebook_loss=18.64, over 1351933.20 frames.], batch size: 34, lr: 4.47e-04
+2022-05-27 22:05:19,549 INFO [train.py:823] (3/4) Epoch 38, batch 650, loss[loss=1.965, simple_loss=0.2491, pruned_loss=0.03219, codebook_loss=18.08, over 7281.00 frames.], tot_loss[loss=2.011, simple_loss=0.241, pruned_loss=0.03078, codebook_loss=18.6, over 1367393.24 frames.], batch size: 20, lr: 4.46e-04
+2022-05-27 22:05:59,576 INFO [train.py:823] (3/4) Epoch 38, batch 700, loss[loss=2.071, simple_loss=0.2545, pruned_loss=0.04337, codebook_loss=19, over 7172.00 frames.], tot_loss[loss=2.01, simple_loss=0.2411, pruned_loss=0.03063, codebook_loss=18.59, over 1377756.08 frames.], batch size: 22, lr: 4.46e-04
+2022-05-27 22:06:39,262 INFO [train.py:823] (3/4) Epoch 38, batch 750, loss[loss=1.991, simple_loss=0.2549, pruned_loss=0.03698, codebook_loss=18.27, over 7250.00 frames.], tot_loss[loss=2.008, simple_loss=0.2408, pruned_loss=0.03021, codebook_loss=18.57, over 1381937.42 frames.], batch size: 24, lr: 4.46e-04
+2022-05-27 22:07:19,345 INFO [train.py:823] (3/4) Epoch 38, batch 800, loss[loss=2.01, simple_loss=0.2434, pruned_loss=0.02628, codebook_loss=18.62, over 7370.00 frames.], tot_loss[loss=2.01, simple_loss=0.2419, pruned_loss=0.03071, codebook_loss=18.59, over 1384647.98 frames.], batch size: 21, lr: 4.45e-04
+2022-05-27 22:07:59,082 INFO [train.py:823] (3/4) Epoch 38, batch 850, loss[loss=2.144, simple_loss=0.2959, pruned_loss=0.04637, codebook_loss=19.5, over 6953.00 frames.], tot_loss[loss=2.013, simple_loss=0.2423, pruned_loss=0.03053, codebook_loss=18.62, over 1394793.35 frames.], batch size: 29, lr: 4.45e-04
+2022-05-27 22:08:39,083 INFO [train.py:823] (3/4) Epoch 38, batch 900, loss[loss=1.991, simple_loss=0.2463, pruned_loss=0.02789, codebook_loss=18.4, over 6997.00 frames.], tot_loss[loss=2.015, simple_loss=0.2415, pruned_loss=0.03013, codebook_loss=18.64, over 1399008.30 frames.], batch size: 16, lr: 4.45e-04
+2022-05-27 22:09:18,349 INFO [train.py:823] (3/4) Epoch 38, batch 950, loss[loss=2.073, simple_loss=0.2713, pruned_loss=0.05439, codebook_loss=18.83, over 5200.00 frames.], tot_loss[loss=2.014, simple_loss=0.241, pruned_loss=0.03019, codebook_loss=18.63, over 1375364.17 frames.], batch size: 47, lr: 4.45e-04
+2022-05-27 22:09:30,204 INFO [train.py:823] (3/4) Epoch 39, batch 0, loss[loss=1.937, simple_loss=0.2366, pruned_loss=0.03007, codebook_loss=17.88, over 7276.00 frames.], tot_loss[loss=1.937, simple_loss=0.2366, pruned_loss=0.03007, codebook_loss=17.88, over 7276.00 frames.], batch size: 19, lr: 4.39e-04
+2022-05-27 22:10:10,200 INFO [train.py:823] (3/4) Epoch 39, batch 50, loss[loss=1.985, simple_loss=0.2389, pruned_loss=0.03119, codebook_loss=18.34, over 7417.00 frames.], tot_loss[loss=1.99, simple_loss=0.2385, pruned_loss=0.0292, codebook_loss=18.41, over 321312.30 frames.], batch size: 22, lr: 4.39e-04
+2022-05-27 22:10:50,154 INFO [train.py:823] (3/4) Epoch 39, batch 100, loss[loss=1.988, simple_loss=0.2193, pruned_loss=0.02765, codebook_loss=18.51, over 7309.00 frames.], tot_loss[loss=1.998, simple_loss=0.2366, pruned_loss=0.02887, codebook_loss=18.5, over 566048.29 frames.], batch size: 18, lr: 4.38e-04
+2022-05-27 22:11:30,528 INFO [train.py:823] (3/4) Epoch 39, batch 150, loss[loss=1.956, simple_loss=0.2467, pruned_loss=0.0277, codebook_loss=18.05, over 7212.00 frames.], tot_loss[loss=1.994, simple_loss=0.2354, pruned_loss=0.02807, codebook_loss=18.49, over 754149.49 frames.], batch size: 25, lr: 4.38e-04
+2022-05-27 22:12:10,658 INFO [train.py:823] (3/4) Epoch 39, batch 200, loss[loss=2.001, simple_loss=0.2345, pruned_loss=0.03543, codebook_loss=18.48, over 7385.00 frames.], tot_loss[loss=2.002, simple_loss=0.2359, pruned_loss=0.02828, codebook_loss=18.56, over 905912.36 frames.], batch size: 19, lr: 4.38e-04
+2022-05-27 22:12:50,931 INFO [train.py:823] (3/4) Epoch 39, batch 250, loss[loss=2.196, simple_loss=0.2437, pruned_loss=0.03161, codebook_loss=20.43, over 7296.00 frames.], tot_loss[loss=2.004, simple_loss=0.2363, pruned_loss=0.02805, codebook_loss=18.58, over 1019954.24 frames.], batch size: 19, lr: 4.37e-04
+2022-05-27 22:13:31,057 INFO [train.py:823] (3/4) Epoch 39, batch 300, loss[loss=2.018, simple_loss=0.2474, pruned_loss=0.04129, codebook_loss=18.53, over 7283.00 frames.], tot_loss[loss=2.006, simple_loss=0.2364, pruned_loss=0.02833, codebook_loss=18.59, over 1112219.51 frames.], batch size: 19, lr: 4.37e-04
+2022-05-27 22:14:11,203 INFO [train.py:823] (3/4) Epoch 39, batch 350, loss[loss=2.042, simple_loss=0.2423, pruned_loss=0.03862, codebook_loss=18.83, over 7366.00 frames.], tot_loss[loss=2.005, simple_loss=0.2369, pruned_loss=0.02853, codebook_loss=18.58, over 1183682.09 frames.], batch size: 20, lr: 4.37e-04
+2022-05-27 22:14:52,343 INFO [train.py:823] (3/4) Epoch 39, batch 400, loss[loss=2.236, simple_loss=0.2397, pruned_loss=0.03588, codebook_loss=20.8, over 7020.00 frames.], tot_loss[loss=2.006, simple_loss=0.2377, pruned_loss=0.02871, codebook_loss=18.59, over 1241105.88 frames.], batch size: 17, lr: 4.36e-04
+2022-05-27 22:15:32,465 INFO [train.py:823] (3/4) Epoch 39, batch 450, loss[loss=2.037, simple_loss=0.2458, pruned_loss=0.0379, codebook_loss=18.77, over 7047.00 frames.], tot_loss[loss=2.006, simple_loss=0.2387, pruned_loss=0.02875, codebook_loss=18.58, over 1280504.53 frames.], batch size: 26, lr: 4.36e-04
+2022-05-27 22:16:12,056 INFO [train.py:823] (3/4) Epoch 39, batch 500, loss[loss=2.213, simple_loss=0.2524, pruned_loss=0.04233, codebook_loss=20.45, over 5204.00 frames.], tot_loss[loss=2.004, simple_loss=0.2379, pruned_loss=0.02873, codebook_loss=18.57, over 1309979.14 frames.], batch size: 48, lr: 4.36e-04
+2022-05-27 22:16:52,123 INFO [train.py:823] (3/4) Epoch 39, batch 550, loss[loss=2.008, simple_loss=0.2504, pruned_loss=0.04304, codebook_loss=18.4, over 7190.00 frames.], tot_loss[loss=2.007, simple_loss=0.2383, pruned_loss=0.02931, codebook_loss=18.59, over 1330776.35 frames.], batch size: 25, lr: 4.36e-04
+2022-05-27 22:17:32,016 INFO [train.py:823] (3/4) Epoch 39, batch 600, loss[loss=1.966, simple_loss=0.2203, pruned_loss=0.02854, codebook_loss=18.27, over 7032.00 frames.], tot_loss[loss=2.005, simple_loss=0.2384, pruned_loss=0.02901, codebook_loss=18.57, over 1354505.25 frames.], batch size: 17, lr: 4.35e-04
+2022-05-27 22:18:12,413 INFO [train.py:823] (3/4) Epoch 39, batch 650, loss[loss=2.144, simple_loss=0.247, pruned_loss=0.02983, codebook_loss=19.91, over 7394.00 frames.], tot_loss[loss=2.005, simple_loss=0.2383, pruned_loss=0.02882, codebook_loss=18.57, over 1373343.69 frames.], batch size: 19, lr: 4.35e-04
+2022-05-27 22:18:52,191 INFO [train.py:823] (3/4) Epoch 39, batch 700, loss[loss=1.94, simple_loss=0.2529, pruned_loss=0.03327, codebook_loss=17.8, over 7242.00 frames.], tot_loss[loss=2.007, simple_loss=0.2387, pruned_loss=0.02886, codebook_loss=18.59, over 1382791.75 frames.], batch size: 24, lr: 4.35e-04
+2022-05-27 22:19:32,459 INFO [train.py:823] (3/4) Epoch 39, batch 750, loss[loss=1.94, simple_loss=0.2517, pruned_loss=0.02621, codebook_loss=17.88, over 7375.00 frames.], tot_loss[loss=2.012, simple_loss=0.2384, pruned_loss=0.02882, codebook_loss=18.64, over 1390573.56 frames.], batch size: 20, lr: 4.34e-04
+2022-05-27 22:20:12,032 INFO [train.py:823] (3/4) Epoch 39, batch 800, loss[loss=1.962, simple_loss=0.2195, pruned_loss=0.02361, codebook_loss=18.29, over 7180.00 frames.], tot_loss[loss=2.013, simple_loss=0.2387, pruned_loss=0.02868, codebook_loss=18.65, over 1399391.10 frames.], batch size: 18, lr: 4.34e-04
+2022-05-27 22:20:52,209 INFO [train.py:823] (3/4) Epoch 39, batch 850, loss[loss=1.945, simple_loss=0.2512, pruned_loss=0.03106, codebook_loss=17.88, over 7323.00 frames.], tot_loss[loss=2.013, simple_loss=0.2392, pruned_loss=0.02886, codebook_loss=18.64, over 1398473.52 frames.], batch size: 23, lr: 4.34e-04
+2022-05-27 22:21:31,571 INFO [train.py:823] (3/4) Epoch 39, batch 900, loss[loss=2.073, simple_loss=0.2516, pruned_loss=0.03796, codebook_loss=19.09, over 6994.00 frames.], tot_loss[loss=2.018, simple_loss=0.241, pruned_loss=0.02956, codebook_loss=18.68, over 1391259.45 frames.], batch size: 29, lr: 4.34e-04
+2022-05-27 22:22:10,923 INFO [train.py:823] (3/4) Epoch 39, batch 950, loss[loss=2.021, simple_loss=0.2484, pruned_loss=0.0372, codebook_loss=18.59, over 4848.00 frames.], tot_loss[loss=2.016, simple_loss=0.2411, pruned_loss=0.02986, codebook_loss=18.66, over 1364093.55 frames.], batch size: 47, lr: 4.33e-04
+2022-05-27 22:22:23,046 INFO [train.py:823] (3/4) Epoch 40, batch 0, loss[loss=2.055, simple_loss=0.2556, pruned_loss=0.03067, codebook_loss=18.97, over 7179.00 frames.], tot_loss[loss=2.055, simple_loss=0.2556, pruned_loss=0.03067, codebook_loss=18.97, over 7179.00 frames.], batch size: 23, lr: 4.28e-04
+2022-05-27 22:23:02,830 INFO [train.py:823] (3/4) Epoch 40, batch 50, loss[loss=1.956, simple_loss=0.2528, pruned_loss=0.03243, codebook_loss=17.97, over 7116.00 frames.], tot_loss[loss=2.007, simple_loss=0.2377, pruned_loss=0.03005, codebook_loss=18.58, over 318446.80 frames.], batch size: 20, lr: 4.28e-04
+2022-05-27 22:23:42,932 INFO [train.py:823] (3/4) Epoch 40, batch 100, loss[loss=1.984, simple_loss=0.2001, pruned_loss=0.0287, codebook_loss=18.55, over 6784.00 frames.], tot_loss[loss=2.007, simple_loss=0.2384, pruned_loss=0.02994, codebook_loss=18.57, over 560220.80 frames.], batch size: 15, lr: 4.27e-04
+2022-05-27 22:24:22,703 INFO [train.py:823] (3/4) Epoch 40, batch 150, loss[loss=2.042, simple_loss=0.2529, pruned_loss=0.03148, codebook_loss=18.84, over 6947.00 frames.], tot_loss[loss=2.013, simple_loss=0.2389, pruned_loss=0.02985, codebook_loss=18.64, over 746819.18 frames.], batch size: 29, lr: 4.27e-04
+2022-05-27 22:25:02,893 INFO [train.py:823] (3/4) Epoch 40, batch 200, loss[loss=1.935, simple_loss=0.2429, pruned_loss=0.02321, codebook_loss=17.9, over 7186.00 frames.], tot_loss[loss=2.009, simple_loss=0.239, pruned_loss=0.02966, codebook_loss=18.6, over 897898.52 frames.], batch size: 21, lr: 4.27e-04
+2022-05-27 22:25:42,826 INFO [train.py:823] (3/4) Epoch 40, batch 250, loss[loss=2.038, simple_loss=0.2351, pruned_loss=0.02659, codebook_loss=18.94, over 6800.00 frames.], tot_loss[loss=2.001, simple_loss=0.2386, pruned_loss=0.02896, codebook_loss=18.53, over 1015092.18 frames.], batch size: 15, lr: 4.26e-04
+2022-05-27 22:26:23,214 INFO [train.py:823] (3/4) Epoch 40, batch 300, loss[loss=1.976, simple_loss=0.2434, pruned_loss=0.02963, codebook_loss=18.25, over 7380.00 frames.], tot_loss[loss=2.004, simple_loss=0.2379, pruned_loss=0.02871, codebook_loss=18.57, over 1105914.62 frames.], batch size: 20, lr: 4.26e-04
+2022-05-27 22:27:03,141 INFO [train.py:823] (3/4) Epoch 40, batch 350, loss[loss=1.897, simple_loss=0.2505, pruned_loss=0.01723, codebook_loss=17.54, over 6486.00 frames.], tot_loss[loss=2.006, simple_loss=0.2382, pruned_loss=0.02867, codebook_loss=18.58, over 1178806.88 frames.], batch size: 34, lr: 4.26e-04
+2022-05-27 22:27:43,318 INFO [train.py:823] (3/4) Epoch 40, batch 400, loss[loss=2.005, simple_loss=0.202, pruned_loss=0.0243, codebook_loss=18.8, over 6997.00 frames.], tot_loss[loss=2.002, simple_loss=0.2378, pruned_loss=0.02843, codebook_loss=18.54, over 1237480.94 frames.], batch size: 16, lr: 4.26e-04
+2022-05-27 22:28:23,144 INFO [train.py:823] (3/4) Epoch 40, batch 450, loss[loss=1.919, simple_loss=0.1946, pruned_loss=0.01614, codebook_loss=18.06, over 7218.00 frames.], tot_loss[loss=2.001, simple_loss=0.238, pruned_loss=0.02833, codebook_loss=18.54, over 1277224.19 frames.], batch size: 16, lr: 4.25e-04
+2022-05-27 22:29:05,772 INFO [train.py:823] (3/4) Epoch 40, batch 500, loss[loss=1.947, simple_loss=0.2282, pruned_loss=0.02357, codebook_loss=18.09, over 7372.00 frames.], tot_loss[loss=2.003, simple_loss=0.2383, pruned_loss=0.0285, codebook_loss=18.56, over 1309750.51 frames.], batch size: 20, lr: 4.25e-04
+2022-05-27 22:29:47,095 INFO [train.py:823] (3/4) Epoch 40, batch 550, loss[loss=1.874, simple_loss=0.2499, pruned_loss=0.01936, codebook_loss=17.3, over 7310.00 frames.], tot_loss[loss=2.002, simple_loss=0.2381, pruned_loss=0.02846, codebook_loss=18.54, over 1336904.92 frames.], batch size: 22, lr: 4.25e-04
+2022-05-27 22:30:27,068 INFO [train.py:823] (3/4) Epoch 40, batch 600, loss[loss=1.929, simple_loss=0.2462, pruned_loss=0.01789, codebook_loss=17.88, over 7308.00 frames.], tot_loss[loss=2, simple_loss=0.2381, pruned_loss=0.02843, codebook_loss=18.52, over 1356484.09 frames.], batch size: 22, lr: 4.24e-04
+2022-05-27 22:31:06,976 INFO [train.py:823] (3/4) Epoch 40, batch 650, loss[loss=1.898, simple_loss=0.2343, pruned_loss=0.01616, codebook_loss=17.64, over 7186.00 frames.], tot_loss[loss=2.002, simple_loss=0.2386, pruned_loss=0.02885, codebook_loss=18.53, over 1366494.37 frames.], batch size: 19, lr: 4.24e-04
+2022-05-27 22:31:46,874 INFO [train.py:823] (3/4) Epoch 40, batch 700, loss[loss=2.077, simple_loss=0.2393, pruned_loss=0.02051, codebook_loss=19.37, over 7188.00 frames.], tot_loss[loss=2.005, simple_loss=0.2401, pruned_loss=0.02923, codebook_loss=18.55, over 1378506.89 frames.], batch size: 20, lr: 4.24e-04
+2022-05-27 22:32:26,841 INFO [train.py:823] (3/4) Epoch 40, batch 750, loss[loss=2.017, simple_loss=0.2646, pruned_loss=0.03731, codebook_loss=18.48, over 4903.00 frames.], tot_loss[loss=2.01, simple_loss=0.2409, pruned_loss=0.02977, codebook_loss=18.59, over 1389018.47 frames.], batch size: 47, lr: 4.24e-04
+2022-05-27 22:33:07,186 INFO [train.py:823] (3/4) Epoch 40, batch 800, loss[loss=1.978, simple_loss=0.2371, pruned_loss=0.02418, codebook_loss=18.35, over 7176.00 frames.], tot_loss[loss=2.013, simple_loss=0.2406, pruned_loss=0.02987, codebook_loss=18.63, over 1391256.20 frames.], batch size: 21, lr: 4.23e-04
+2022-05-27 22:33:46,913 INFO [train.py:823] (3/4) Epoch 40, batch 850, loss[loss=1.922, simple_loss=0.2272, pruned_loss=0.02237, codebook_loss=17.86, over 7164.00 frames.], tot_loss[loss=2.018, simple_loss=0.2411, pruned_loss=0.03043, codebook_loss=18.67, over 1399735.73 frames.], batch size: 22, lr: 4.23e-04
+2022-05-27 22:34:26,960 INFO [train.py:823] (3/4) Epoch 40, batch 900, loss[loss=2.244, simple_loss=0.2551, pruned_loss=0.03977, codebook_loss=20.77, over 7364.00 frames.], tot_loss[loss=2.011, simple_loss=0.2402, pruned_loss=0.02997, codebook_loss=18.61, over 1391327.71 frames.], batch size: 20, lr: 4.23e-04
+2022-05-27 22:35:20,789 INFO [train.py:823] (3/4) Epoch 41, batch 0, loss[loss=1.895, simple_loss=0.2259, pruned_loss=0.02208, codebook_loss=17.6, over 7083.00 frames.], tot_loss[loss=1.895, simple_loss=0.2259, pruned_loss=0.02208, codebook_loss=17.6, over 7083.00 frames.], batch size: 19, lr: 4.17e-04
+2022-05-27 22:36:00,869 INFO [train.py:823] (3/4) Epoch 41, batch 50, loss[loss=1.979, simple_loss=0.2377, pruned_loss=0.03798, codebook_loss=18.22, over 7362.00 frames.], tot_loss[loss=2.007, simple_loss=0.2399, pruned_loss=0.02918, codebook_loss=18.58, over 321250.31 frames.], batch size: 20, lr: 4.17e-04
+2022-05-27 22:36:40,297 INFO [train.py:823] (3/4) Epoch 41, batch 100, loss[loss=2.032, simple_loss=0.24, pruned_loss=0.02947, codebook_loss=18.83, over 7104.00 frames.], tot_loss[loss=2.011, simple_loss=0.2412, pruned_loss=0.02969, codebook_loss=18.61, over 561138.76 frames.], batch size: 18, lr: 4.17e-04
+2022-05-27 22:37:20,561 INFO [train.py:823] (3/4) Epoch 41, batch 150, loss[loss=1.932, simple_loss=0.2373, pruned_loss=0.03195, codebook_loss=17.82, over 7001.00 frames.], tot_loss[loss=2.001, simple_loss=0.2401, pruned_loss=0.02922, codebook_loss=18.52, over 753281.83 frames.], batch size: 26, lr: 4.17e-04
+2022-05-27 22:38:00,367 INFO [train.py:823] (3/4) Epoch 41, batch 200, loss[loss=2.027, simple_loss=0.2321, pruned_loss=0.02617, codebook_loss=18.84, over 7389.00 frames.], tot_loss[loss=2.003, simple_loss=0.2404, pruned_loss=0.02923, codebook_loss=18.54, over 905834.14 frames.], batch size: 19, lr: 4.16e-04
+2022-05-27 22:38:41,533 INFO [train.py:823] (3/4) Epoch 41, batch 250, loss[loss=2.058, simple_loss=0.2444, pruned_loss=0.03617, codebook_loss=19, over 7106.00 frames.], tot_loss[loss=2, simple_loss=0.2393, pruned_loss=0.02917, codebook_loss=18.51, over 1016369.67 frames.], batch size: 19, lr: 4.16e-04
+2022-05-27 22:39:21,240 INFO [train.py:823] (3/4) Epoch 41, batch 300, loss[loss=1.936, simple_loss=0.2246, pruned_loss=0.02355, codebook_loss=18, over 7371.00 frames.], tot_loss[loss=1.999, simple_loss=0.2381, pruned_loss=0.02886, codebook_loss=18.51, over 1107206.19 frames.], batch size: 20, lr: 4.16e-04
+2022-05-27 22:40:01,388 INFO [train.py:823] (3/4) Epoch 41, batch 350, loss[loss=2.09, simple_loss=0.2601, pruned_loss=0.0439, codebook_loss=19.16, over 7176.00 frames.], tot_loss[loss=1.995, simple_loss=0.2387, pruned_loss=0.02884, codebook_loss=18.47, over 1174707.08 frames.], batch size: 22, lr: 4.15e-04
+2022-05-27 22:40:41,065 INFO [train.py:823] (3/4) Epoch 41, batch 400, loss[loss=1.932, simple_loss=0.2326, pruned_loss=0.02493, codebook_loss=17.91, over 7156.00 frames.], tot_loss[loss=1.999, simple_loss=0.2386, pruned_loss=0.02907, codebook_loss=18.5, over 1221207.89 frames.], batch size: 23, lr: 4.15e-04
+2022-05-27 22:41:21,049 INFO [train.py:823] (3/4) Epoch 41, batch 450, loss[loss=2.028, simple_loss=0.2266, pruned_loss=0.03006, codebook_loss=18.85, over 7100.00 frames.], tot_loss[loss=2.004, simple_loss=0.239, pruned_loss=0.02911, codebook_loss=18.55, over 1264031.01 frames.], batch size: 18, lr: 4.15e-04
+2022-05-27 22:42:00,714 INFO [train.py:823] (3/4) Epoch 41, batch 500, loss[loss=1.956, simple_loss=0.2449, pruned_loss=0.02712, codebook_loss=18.06, over 7301.00 frames.], tot_loss[loss=2.002, simple_loss=0.2396, pruned_loss=0.02916, codebook_loss=18.53, over 1299343.12 frames.], batch size: 22, lr: 4.15e-04
+2022-05-27 22:42:40,902 INFO [train.py:823] (3/4) Epoch 41, batch 550, loss[loss=1.908, simple_loss=0.2191, pruned_loss=0.01928, codebook_loss=17.79, over 7193.00 frames.], tot_loss[loss=2, simple_loss=0.2389, pruned_loss=0.02874, codebook_loss=18.52, over 1323334.50 frames.], batch size: 19, lr: 4.14e-04
+2022-05-27 22:43:20,791 INFO [train.py:823] (3/4) Epoch 41, batch 600, loss[loss=1.944, simple_loss=0.2578, pruned_loss=0.02963, codebook_loss=17.86, over 7182.00 frames.], tot_loss[loss=1.999, simple_loss=0.2387, pruned_loss=0.02852, codebook_loss=18.51, over 1339716.07 frames.], batch size: 21, lr: 4.14e-04
+2022-05-27 22:44:00,851 INFO [train.py:823] (3/4) Epoch 41, batch 650, loss[loss=1.979, simple_loss=0.2536, pruned_loss=0.0272, codebook_loss=18.25, over 7188.00 frames.], tot_loss[loss=1.997, simple_loss=0.2388, pruned_loss=0.02844, codebook_loss=18.49, over 1358738.15 frames.], batch size: 21, lr: 4.14e-04
+2022-05-27 22:44:40,539 INFO [train.py:823] (3/4) Epoch 41, batch 700, loss[loss=1.949, simple_loss=0.202, pruned_loss=0.02047, codebook_loss=18.27, over 6889.00 frames.], tot_loss[loss=1.992, simple_loss=0.2382, pruned_loss=0.02844, codebook_loss=18.45, over 1371608.91 frames.], batch size: 15, lr: 4.14e-04
+2022-05-27 22:45:20,395 INFO [train.py:823] (3/4) Epoch 41, batch 750, loss[loss=1.925, simple_loss=0.2127, pruned_loss=0.023, codebook_loss=17.96, over 7183.00 frames.], tot_loss[loss=1.994, simple_loss=0.2381, pruned_loss=0.02837, codebook_loss=18.47, over 1379542.30 frames.], batch size: 18, lr: 4.13e-04
+2022-05-27 22:45:59,898 INFO [train.py:823] (3/4) Epoch 41, batch 800, loss[loss=1.938, simple_loss=0.2196, pruned_loss=0.02335, codebook_loss=18.05, over 7300.00 frames.], tot_loss[loss=1.995, simple_loss=0.238, pruned_loss=0.02867, codebook_loss=18.48, over 1381575.43 frames.], batch size: 17, lr: 4.13e-04
+2022-05-27 22:46:40,271 INFO [train.py:823] (3/4) Epoch 41, batch 850, loss[loss=1.922, simple_loss=0.2142, pruned_loss=0.02518, codebook_loss=17.9, over 7286.00 frames.], tot_loss[loss=1.994, simple_loss=0.2388, pruned_loss=0.02864, codebook_loss=18.46, over 1394358.58 frames.], batch size: 19, lr: 4.13e-04
+2022-05-27 22:47:20,137 INFO [train.py:823] (3/4) Epoch 41, batch 900, loss[loss=2.013, simple_loss=0.2035, pruned_loss=0.02417, codebook_loss=18.87, over 7279.00 frames.], tot_loss[loss=1.997, simple_loss=0.238, pruned_loss=0.02862, codebook_loss=18.5, over 1400002.36 frames.], batch size: 17, lr: 4.13e-04
+2022-05-27 22:48:13,564 INFO [train.py:823] (3/4) Epoch 42, batch 0, loss[loss=1.977, simple_loss=0.242, pruned_loss=0.02006, codebook_loss=18.36, over 7295.00 frames.], tot_loss[loss=1.977, simple_loss=0.242, pruned_loss=0.02006, codebook_loss=18.36, over 7295.00 frames.], batch size: 21, lr: 4.07e-04
+2022-05-27 22:48:53,524 INFO [train.py:823] (3/4) Epoch 42, batch 50, loss[loss=2.092, simple_loss=0.2212, pruned_loss=0.02934, codebook_loss=19.52, over 7390.00 frames.], tot_loss[loss=1.987, simple_loss=0.2345, pruned_loss=0.02724, codebook_loss=18.42, over 323954.37 frames.], batch size: 19, lr: 4.07e-04
+2022-05-27 22:49:33,736 INFO [train.py:823] (3/4) Epoch 42, batch 100, loss[loss=1.909, simple_loss=0.2104, pruned_loss=0.02376, codebook_loss=17.8, over 6810.00 frames.], tot_loss[loss=1.973, simple_loss=0.2353, pruned_loss=0.02683, codebook_loss=18.28, over 565962.79 frames.], batch size: 15, lr: 4.07e-04
+2022-05-27 22:50:13,513 INFO [train.py:823] (3/4) Epoch 42, batch 150, loss[loss=2.102, simple_loss=0.2523, pruned_loss=0.02976, codebook_loss=19.47, over 7178.00 frames.], tot_loss[loss=1.97, simple_loss=0.2343, pruned_loss=0.02675, codebook_loss=18.26, over 755756.40 frames.], batch size: 22, lr: 4.07e-04
+2022-05-27 22:50:53,444 INFO [train.py:823] (3/4) Epoch 42, batch 200, loss[loss=1.937, simple_loss=0.2447, pruned_loss=0.03456, codebook_loss=17.8, over 7219.00 frames.], tot_loss[loss=1.977, simple_loss=0.2355, pruned_loss=0.02692, codebook_loss=18.32, over 901419.87 frames.], batch size: 24, lr: 4.06e-04
+2022-05-27 22:51:33,126 INFO [train.py:823] (3/4) Epoch 42, batch 250, loss[loss=2.151, simple_loss=0.2217, pruned_loss=0.0276, codebook_loss=20.12, over 7146.00 frames.], tot_loss[loss=1.991, simple_loss=0.2365, pruned_loss=0.0276, codebook_loss=18.45, over 1016806.59 frames.], batch size: 17, lr: 4.06e-04
+2022-05-27 22:52:13,181 INFO [train.py:823] (3/4) Epoch 42, batch 300, loss[loss=1.915, simple_loss=0.2336, pruned_loss=0.0232, codebook_loss=17.75, over 7187.00 frames.], tot_loss[loss=1.996, simple_loss=0.2367, pruned_loss=0.02779, codebook_loss=18.5, over 1101213.78 frames.], batch size: 21, lr: 4.06e-04
+2022-05-27 22:52:52,888 INFO [train.py:823] (3/4) Epoch 42, batch 350, loss[loss=1.898, simple_loss=0.2165, pruned_loss=0.02738, codebook_loss=17.62, over 7140.00 frames.], tot_loss[loss=1.993, simple_loss=0.2363, pruned_loss=0.02756, codebook_loss=18.47, over 1167545.47 frames.], batch size: 17, lr: 4.06e-04
+2022-05-27 22:53:35,684 INFO [train.py:823] (3/4) Epoch 42, batch 400, loss[loss=1.953, simple_loss=0.2029, pruned_loss=0.02533, codebook_loss=18.26, over 7289.00 frames.], tot_loss[loss=2.003, simple_loss=0.2366, pruned_loss=0.02824, codebook_loss=18.56, over 1217631.74 frames.], batch size: 17, lr: 4.05e-04
+2022-05-27 22:54:16,815 INFO [train.py:823] (3/4) Epoch 42, batch 450, loss[loss=1.995, simple_loss=0.2393, pruned_loss=0.03019, codebook_loss=18.45, over 7196.00 frames.], tot_loss[loss=1.997, simple_loss=0.2373, pruned_loss=0.02779, codebook_loss=18.5, over 1267478.96 frames.], batch size: 25, lr: 4.05e-04
+2022-05-27 22:54:57,135 INFO [train.py:823] (3/4) Epoch 42, batch 500, loss[loss=1.998, simple_loss=0.2062, pruned_loss=0.01987, codebook_loss=18.75, over 7156.00 frames.], tot_loss[loss=1.998, simple_loss=0.2369, pruned_loss=0.02787, codebook_loss=18.52, over 1302255.36 frames.], batch size: 17, lr: 4.05e-04
+2022-05-27 22:55:36,612 INFO [train.py:823] (3/4) Epoch 42, batch 550, loss[loss=2.064, simple_loss=0.2348, pruned_loss=0.02976, codebook_loss=19.17, over 7184.00 frames.], tot_loss[loss=1.998, simple_loss=0.2374, pruned_loss=0.02795, codebook_loss=18.51, over 1322168.69 frames.], batch size: 18, lr: 4.05e-04
+2022-05-27 22:56:16,726 INFO [train.py:823] (3/4) Epoch 42, batch 600, loss[loss=1.966, simple_loss=0.2529, pruned_loss=0.03166, codebook_loss=18.08, over 7194.00 frames.], tot_loss[loss=2, simple_loss=0.2385, pruned_loss=0.02809, codebook_loss=18.53, over 1343673.71 frames.], batch size: 20, lr: 4.04e-04
+2022-05-27 22:56:56,705 INFO [train.py:823] (3/4) Epoch 42, batch 650, loss[loss=2.045, simple_loss=0.2773, pruned_loss=0.05482, codebook_loss=18.51, over 7151.00 frames.], tot_loss[loss=1.999, simple_loss=0.239, pruned_loss=0.02852, codebook_loss=18.51, over 1363988.35 frames.], batch size: 23, lr: 4.04e-04
+2022-05-27 22:57:36,497 INFO [train.py:823] (3/4) Epoch 42, batch 700, loss[loss=1.972, simple_loss=0.2695, pruned_loss=0.02705, codebook_loss=18.1, over 7003.00 frames.], tot_loss[loss=1.999, simple_loss=0.2396, pruned_loss=0.02898, codebook_loss=18.5, over 1369693.81 frames.], batch size: 29, lr: 4.04e-04
+2022-05-27 22:58:16,379 INFO [train.py:823] (3/4) Epoch 42, batch 750, loss[loss=2.102, simple_loss=0.2748, pruned_loss=0.03688, codebook_loss=19.28, over 7374.00 frames.], tot_loss[loss=1.998, simple_loss=0.2389, pruned_loss=0.02862, codebook_loss=18.5, over 1383156.32 frames.], batch size: 21, lr: 4.04e-04
+2022-05-27 22:58:56,361 INFO [train.py:823] (3/4) Epoch 42, batch 800, loss[loss=2.21, simple_loss=0.2523, pruned_loss=0.02945, codebook_loss=20.54, over 6287.00 frames.], tot_loss[loss=1.999, simple_loss=0.2384, pruned_loss=0.02821, codebook_loss=18.51, over 1391058.57 frames.], batch size: 34, lr: 4.03e-04
+2022-05-27 22:59:36,091 INFO [train.py:823] (3/4) Epoch 42, batch 850, loss[loss=1.916, simple_loss=0.2229, pruned_loss=0.02399, codebook_loss=17.81, over 7023.00 frames.], tot_loss[loss=1.992, simple_loss=0.2379, pruned_loss=0.02817, codebook_loss=18.44, over 1396161.99 frames.], batch size: 17, lr: 4.03e-04
+2022-05-27 23:00:15,922 INFO [train.py:823] (3/4) Epoch 42, batch 900, loss[loss=1.955, simple_loss=0.2393, pruned_loss=0.02671, codebook_loss=18.09, over 5094.00 frames.], tot_loss[loss=1.99, simple_loss=0.2372, pruned_loss=0.02809, codebook_loss=18.43, over 1395149.03 frames.], batch size: 46, lr: 4.03e-04
+2022-05-27 23:01:10,031 INFO [train.py:823] (3/4) Epoch 43, batch 0, loss[loss=1.867, simple_loss=0.226, pruned_loss=0.01925, codebook_loss=17.35, over 7287.00 frames.], tot_loss[loss=1.867, simple_loss=0.226, pruned_loss=0.01925, codebook_loss=17.35, over 7287.00 frames.], batch size: 19, lr: 3.98e-04
+2022-05-27 23:01:50,281 INFO [train.py:823] (3/4) Epoch 43, batch 50, loss[loss=1.948, simple_loss=0.2381, pruned_loss=0.02859, codebook_loss=18.01, over 7374.00 frames.], tot_loss[loss=1.964, simple_loss=0.2359, pruned_loss=0.02743, codebook_loss=18.19, over 321893.73 frames.], batch size: 20, lr: 3.98e-04
+2022-05-27 23:02:31,479 INFO [train.py:823] (3/4) Epoch 43, batch 100, loss[loss=2.15, simple_loss=0.2605, pruned_loss=0.04602, codebook_loss=19.73, over 7164.00 frames.], tot_loss[loss=1.981, simple_loss=0.2367, pruned_loss=0.02852, codebook_loss=18.34, over 564852.71 frames.], batch size: 23, lr: 3.97e-04
+2022-05-27 23:03:15,193 INFO [train.py:823] (3/4) Epoch 43, batch 150, loss[loss=1.997, simple_loss=0.2459, pruned_loss=0.03348, codebook_loss=18.4, over 6710.00 frames.], tot_loss[loss=2.003, simple_loss=0.2372, pruned_loss=0.02946, codebook_loss=18.55, over 754286.81 frames.], batch size: 34, lr: 3.97e-04
+2022-05-27 23:03:55,328 INFO [train.py:823] (3/4) Epoch 43, batch 200, loss[loss=2.276, simple_loss=0.2584, pruned_loss=0.04971, codebook_loss=20.97, over 7341.00 frames.], tot_loss[loss=1.993, simple_loss=0.2372, pruned_loss=0.02881, codebook_loss=18.46, over 905531.89 frames.], batch size: 23, lr: 3.97e-04
+2022-05-27 23:04:35,714 INFO [train.py:823] (3/4) Epoch 43, batch 250, loss[loss=2.054, simple_loss=0.2105, pruned_loss=0.01856, codebook_loss=19.3, over 7307.00 frames.], tot_loss[loss=1.991, simple_loss=0.2369, pruned_loss=0.02868, codebook_loss=18.44, over 1022066.92 frames.], batch size: 18, lr: 3.97e-04
+2022-05-27 23:05:15,238 INFO [train.py:823] (3/4) Epoch 43, batch 300, loss[loss=1.917, simple_loss=0.2421, pruned_loss=0.02913, codebook_loss=17.67, over 7093.00 frames.], tot_loss[loss=1.987, simple_loss=0.2375, pruned_loss=0.0287, codebook_loss=18.4, over 1102826.09 frames.], batch size: 18, lr: 3.96e-04
+2022-05-27 23:05:55,388 INFO [train.py:823] (3/4) Epoch 43, batch 350, loss[loss=2.337, simple_loss=0.2747, pruned_loss=0.05876, codebook_loss=21.41, over 7343.00 frames.], tot_loss[loss=1.996, simple_loss=0.2376, pruned_loss=0.02897, codebook_loss=18.48, over 1174627.44 frames.], batch size: 23, lr: 3.96e-04
+2022-05-27 23:06:35,434 INFO [train.py:823] (3/4) Epoch 43, batch 400, loss[loss=1.916, simple_loss=0.2284, pruned_loss=0.02088, codebook_loss=17.81, over 7183.00 frames.], tot_loss[loss=1.997, simple_loss=0.237, pruned_loss=0.02872, codebook_loss=18.5, over 1229076.84 frames.], batch size: 20, lr: 3.96e-04
+2022-05-27 23:07:15,836 INFO [train.py:823] (3/4) Epoch 43, batch 450, loss[loss=1.874, simple_loss=0.2255, pruned_loss=0.0169, codebook_loss=17.44, over 7172.00 frames.], tot_loss[loss=1.996, simple_loss=0.2368, pruned_loss=0.02815, codebook_loss=18.49, over 1275581.23 frames.], batch size: 21, lr: 3.96e-04
+2022-05-27 23:07:55,851 INFO [train.py:823] (3/4) Epoch 43, batch 500, loss[loss=2.012, simple_loss=0.2031, pruned_loss=0.02109, codebook_loss=18.89, over 7026.00 frames.], tot_loss[loss=2, simple_loss=0.237, pruned_loss=0.02882, codebook_loss=18.53, over 1307689.14 frames.], batch size: 17, lr: 3.95e-04
+2022-05-27 23:08:36,127 INFO [train.py:823] (3/4) Epoch 43, batch 550, loss[loss=1.888, simple_loss=0.2368, pruned_loss=0.01991, codebook_loss=17.5, over 7285.00 frames.], tot_loss[loss=1.999, simple_loss=0.2382, pruned_loss=0.02886, codebook_loss=18.51, over 1337582.44 frames.], batch size: 21, lr: 3.95e-04
+2022-05-27 23:09:15,804 INFO [train.py:823] (3/4) Epoch 43, batch 600, loss[loss=2.229, simple_loss=0.264, pruned_loss=0.03559, codebook_loss=20.62, over 7174.00 frames.], tot_loss[loss=1.999, simple_loss=0.2385, pruned_loss=0.02862, codebook_loss=18.51, over 1357093.34 frames.], batch size: 22, lr: 3.95e-04
+2022-05-27 23:09:55,887 INFO [train.py:823] (3/4) Epoch 43, batch 650, loss[loss=2.174, simple_loss=0.2701, pruned_loss=0.05014, codebook_loss=19.89, over 7187.00 frames.], tot_loss[loss=1.997, simple_loss=0.2381, pruned_loss=0.02843, codebook_loss=18.5, over 1373768.80 frames.], batch size: 20, lr: 3.95e-04
+2022-05-27 23:10:35,787 INFO [train.py:823] (3/4) Epoch 43, batch 700, loss[loss=1.884, simple_loss=0.2162, pruned_loss=0.01781, codebook_loss=17.58, over 7039.00 frames.], tot_loss[loss=2.001, simple_loss=0.2383, pruned_loss=0.02847, codebook_loss=18.53, over 1384013.02 frames.], batch size: 17, lr: 3.94e-04
+2022-05-27 23:11:16,035 INFO [train.py:823] (3/4) Epoch 43, batch 750, loss[loss=2.052, simple_loss=0.2371, pruned_loss=0.01826, codebook_loss=19.15, over 7174.00 frames.], tot_loss[loss=2.001, simple_loss=0.2375, pruned_loss=0.02811, codebook_loss=18.54, over 1392704.60 frames.], batch size: 21, lr: 3.94e-04
+2022-05-27 23:11:55,933 INFO [train.py:823] (3/4) Epoch 43, batch 800, loss[loss=1.864, simple_loss=0.2285, pruned_loss=0.01692, codebook_loss=17.33, over 7307.00 frames.], tot_loss[loss=1.996, simple_loss=0.237, pruned_loss=0.02788, codebook_loss=18.5, over 1402273.55 frames.], batch size: 22, lr: 3.94e-04
+2022-05-27 23:12:36,063 INFO [train.py:823] (3/4) Epoch 43, batch 850, loss[loss=1.948, simple_loss=0.2477, pruned_loss=0.0337, codebook_loss=17.9, over 7162.00 frames.], tot_loss[loss=1.992, simple_loss=0.2361, pruned_loss=0.02752, codebook_loss=18.46, over 1404009.61 frames.], batch size: 22, lr: 3.94e-04
+2022-05-27 23:13:16,035 INFO [train.py:823] (3/4) Epoch 43, batch 900, loss[loss=1.868, simple_loss=0.2083, pruned_loss=0.01736, codebook_loss=17.46, over 6799.00 frames.], tot_loss[loss=1.993, simple_loss=0.2354, pruned_loss=0.02753, codebook_loss=18.48, over 1402061.08 frames.], batch size: 15, lr: 3.93e-04
+2022-05-27 23:14:05,788 INFO [train.py:823] (3/4) Epoch 44, batch 0, loss[loss=1.94, simple_loss=0.2334, pruned_loss=0.01894, codebook_loss=18.04, over 7294.00 frames.], tot_loss[loss=1.94, simple_loss=0.2334, pruned_loss=0.01894, codebook_loss=18.04, over 7294.00 frames.], batch size: 22, lr: 3.89e-04
+2022-05-27 23:14:46,507 INFO [train.py:823] (3/4) Epoch 44, batch 50, loss[loss=1.97, simple_loss=0.2262, pruned_loss=0.0277, codebook_loss=18.29, over 7432.00 frames.], tot_loss[loss=1.979, simple_loss=0.2334, pruned_loss=0.02669, codebook_loss=18.35, over 322609.10 frames.], batch size: 18, lr: 3.89e-04
+2022-05-27 23:15:26,592 INFO [train.py:823] (3/4) Epoch 44, batch 100, loss[loss=2.066, simple_loss=0.2324, pruned_loss=0.02987, codebook_loss=19.2, over 7277.00 frames.], tot_loss[loss=1.973, simple_loss=0.2358, pruned_loss=0.02774, codebook_loss=18.27, over 566829.67 frames.], batch size: 20, lr: 3.88e-04
+2022-05-27 23:16:06,725 INFO [train.py:823] (3/4) Epoch 44, batch 150, loss[loss=1.944, simple_loss=0.2359, pruned_loss=0.02804, codebook_loss=17.98, over 7277.00 frames.], tot_loss[loss=1.971, simple_loss=0.2352, pruned_loss=0.02724, codebook_loss=18.26, over 757808.74 frames.], batch size: 20, lr: 3.88e-04
+2022-05-27 23:16:46,975 INFO [train.py:823] (3/4) Epoch 44, batch 200, loss[loss=1.967, simple_loss=0.2654, pruned_loss=0.03191, codebook_loss=18.03, over 7225.00 frames.], tot_loss[loss=1.972, simple_loss=0.2364, pruned_loss=0.02764, codebook_loss=18.26, over 903622.73 frames.], batch size: 24, lr: 3.88e-04
+2022-05-27 23:17:26,785 INFO [train.py:823] (3/4) Epoch 44, batch 250, loss[loss=1.95, simple_loss=0.2436, pruned_loss=0.02334, codebook_loss=18.05, over 7155.00 frames.], tot_loss[loss=1.977, simple_loss=0.2369, pruned_loss=0.02766, codebook_loss=18.31, over 1019418.96 frames.], batch size: 23, lr: 3.88e-04
+2022-05-27 23:18:08,119 INFO [train.py:823] (3/4) Epoch 44, batch 300, loss[loss=1.913, simple_loss=0.2475, pruned_loss=0.0224, codebook_loss=17.67, over 7276.00 frames.], tot_loss[loss=1.978, simple_loss=0.2373, pruned_loss=0.02769, codebook_loss=18.32, over 1106740.48 frames.], batch size: 21, lr: 3.87e-04
+2022-05-27 23:18:50,352 INFO [train.py:823] (3/4) Epoch 44, batch 350, loss[loss=2.075, simple_loss=0.2049, pruned_loss=0.02158, codebook_loss=19.51, over 7013.00 frames.], tot_loss[loss=1.983, simple_loss=0.237, pruned_loss=0.02804, codebook_loss=18.36, over 1169330.22 frames.], batch size: 16, lr: 3.87e-04
+2022-05-27 23:19:30,584 INFO [train.py:823] (3/4) Epoch 44, batch 400, loss[loss=1.955, simple_loss=0.2604, pruned_loss=0.03277, codebook_loss=17.92, over 4786.00 frames.], tot_loss[loss=1.983, simple_loss=0.2363, pruned_loss=0.02758, codebook_loss=18.38, over 1221222.37 frames.], batch size: 46, lr: 3.87e-04
+2022-05-27 23:20:10,461 INFO [train.py:823] (3/4) Epoch 44, batch 450, loss[loss=1.986, simple_loss=0.2498, pruned_loss=0.03241, codebook_loss=18.28, over 7239.00 frames.], tot_loss[loss=1.981, simple_loss=0.2371, pruned_loss=0.02765, codebook_loss=18.35, over 1264738.87 frames.], batch size: 25, lr: 3.87e-04
+2022-05-27 23:20:50,576 INFO [train.py:823] (3/4) Epoch 44, batch 500, loss[loss=1.878, simple_loss=0.2316, pruned_loss=0.02409, codebook_loss=17.38, over 7154.00 frames.], tot_loss[loss=1.983, simple_loss=0.2364, pruned_loss=0.02766, codebook_loss=18.37, over 1302144.06 frames.], batch size: 17, lr: 3.86e-04
+2022-05-27 23:21:30,261 INFO [train.py:823] (3/4) Epoch 44, batch 550, loss[loss=2.161, simple_loss=0.2643, pruned_loss=0.0405, codebook_loss=19.89, over 7226.00 frames.], tot_loss[loss=1.981, simple_loss=0.2365, pruned_loss=0.02722, codebook_loss=18.35, over 1329951.49 frames.], batch size: 24, lr: 3.86e-04
+2022-05-27 23:22:10,617 INFO [train.py:823] (3/4) Epoch 44, batch 600, loss[loss=1.91, simple_loss=0.2311, pruned_loss=0.02352, codebook_loss=17.7, over 7395.00 frames.], tot_loss[loss=1.982, simple_loss=0.2365, pruned_loss=0.02696, codebook_loss=18.36, over 1352432.68 frames.], batch size: 19, lr: 3.86e-04
+2022-05-27 23:22:50,454 INFO [train.py:823] (3/4) Epoch 44, batch 650, loss[loss=1.831, simple_loss=0.2414, pruned_loss=0.01651, codebook_loss=16.94, over 7433.00 frames.], tot_loss[loss=1.988, simple_loss=0.2363, pruned_loss=0.02715, codebook_loss=18.43, over 1367352.28 frames.], batch size: 22, lr: 3.86e-04
+2022-05-27 23:23:30,770 INFO [train.py:823] (3/4) Epoch 44, batch 700, loss[loss=1.99, simple_loss=0.2434, pruned_loss=0.02984, codebook_loss=18.38, over 7152.00 frames.], tot_loss[loss=1.986, simple_loss=0.2354, pruned_loss=0.02701, codebook_loss=18.42, over 1378616.39 frames.], batch size: 23, lr: 3.85e-04
+2022-05-27 23:24:10,477 INFO [train.py:823] (3/4) Epoch 44, batch 750, loss[loss=2.28, simple_loss=0.2417, pruned_loss=0.04463, codebook_loss=21.15, over 7168.00 frames.], tot_loss[loss=1.987, simple_loss=0.2363, pruned_loss=0.02717, codebook_loss=18.41, over 1390333.60 frames.], batch size: 17, lr: 3.85e-04
+2022-05-27 23:24:50,892 INFO [train.py:823] (3/4) Epoch 44, batch 800, loss[loss=2.191, simple_loss=0.2703, pruned_loss=0.04069, codebook_loss=20.15, over 7204.00 frames.], tot_loss[loss=1.987, simple_loss=0.237, pruned_loss=0.02728, codebook_loss=18.41, over 1396542.93 frames.], batch size: 25, lr: 3.85e-04
+2022-05-27 23:25:30,978 INFO [train.py:823] (3/4) Epoch 44, batch 850, loss[loss=1.927, simple_loss=0.2015, pruned_loss=0.02469, codebook_loss=18.02, over 6804.00 frames.], tot_loss[loss=1.987, simple_loss=0.2367, pruned_loss=0.02719, codebook_loss=18.41, over 1401785.91 frames.], batch size: 15, lr: 3.85e-04
+2022-05-27 23:26:12,395 INFO [train.py:823] (3/4) Epoch 44, batch 900, loss[loss=2.07, simple_loss=0.2166, pruned_loss=0.02696, codebook_loss=19.35, over 7287.00 frames.], tot_loss[loss=1.993, simple_loss=0.2371, pruned_loss=0.02772, codebook_loss=18.47, over 1400096.62 frames.], batch size: 17, lr: 3.85e-04
+2022-05-27 23:26:52,094 INFO [train.py:823] (3/4) Epoch 44, batch 950, loss[loss=1.952, simple_loss=0.234, pruned_loss=0.03253, codebook_loss=18.03, over 4986.00 frames.], tot_loss[loss=1.99, simple_loss=0.2366, pruned_loss=0.02764, codebook_loss=18.44, over 1376987.95 frames.], batch size: 46, lr: 3.84e-04
+2022-05-27 23:27:07,449 INFO [train.py:823] (3/4) Epoch 45, batch 0, loss[loss=1.874, simple_loss=0.2317, pruned_loss=0.01778, codebook_loss=17.4, over 7286.00 frames.], tot_loss[loss=1.874, simple_loss=0.2317, pruned_loss=0.01778, codebook_loss=17.4, over 7286.00 frames.], batch size: 20, lr: 3.80e-04
+2022-05-27 23:27:47,718 INFO [train.py:823] (3/4) Epoch 45, batch 50, loss[loss=1.905, simple_loss=0.2439, pruned_loss=0.02361, codebook_loss=17.6, over 7286.00 frames.], tot_loss[loss=1.997, simple_loss=0.2351, pruned_loss=0.02684, codebook_loss=18.53, over 324187.50 frames.], batch size: 21, lr: 3.80e-04
+2022-05-27 23:28:27,624 INFO [train.py:823] (3/4) Epoch 45, batch 100, loss[loss=1.985, simple_loss=0.2738, pruned_loss=0.03962, codebook_loss=18.09, over 7374.00 frames.], tot_loss[loss=1.978, simple_loss=0.2368, pruned_loss=0.02723, codebook_loss=18.32, over 566408.00 frames.], batch size: 21, lr: 3.80e-04
+2022-05-27 23:29:07,803 INFO [train.py:823] (3/4) Epoch 45, batch 150, loss[loss=1.915, simple_loss=0.2101, pruned_loss=0.03027, codebook_loss=17.8, over 7228.00 frames.], tot_loss[loss=1.976, simple_loss=0.2356, pruned_loss=0.02699, codebook_loss=18.31, over 752089.90 frames.], batch size: 16, lr: 3.79e-04
+2022-05-27 23:29:47,567 INFO [train.py:823] (3/4) Epoch 45, batch 200, loss[loss=1.983, simple_loss=0.2204, pruned_loss=0.02366, codebook_loss=18.49, over 5396.00 frames.], tot_loss[loss=1.99, simple_loss=0.2361, pruned_loss=0.0278, codebook_loss=18.44, over 897543.60 frames.], batch size: 48, lr: 3.79e-04
+2022-05-27 23:30:27,703 INFO [train.py:823] (3/4) Epoch 45, batch 250, loss[loss=1.915, simple_loss=0.23, pruned_loss=0.02718, codebook_loss=17.73, over 6416.00 frames.], tot_loss[loss=1.987, simple_loss=0.2359, pruned_loss=0.02794, codebook_loss=18.41, over 1010571.35 frames.], batch size: 34, lr: 3.79e-04
+2022-05-27 23:31:07,618 INFO [train.py:823] (3/4) Epoch 45, batch 300, loss[loss=1.89, simple_loss=0.2537, pruned_loss=0.02879, codebook_loss=17.35, over 7161.00 frames.], tot_loss[loss=1.982, simple_loss=0.2351, pruned_loss=0.02715, codebook_loss=18.38, over 1099452.75 frames.], batch size: 23, lr: 3.79e-04
+2022-05-27 23:31:47,910 INFO [train.py:823] (3/4) Epoch 45, batch 350, loss[loss=1.938, simple_loss=0.2436, pruned_loss=0.02796, codebook_loss=17.88, over 7422.00 frames.], tot_loss[loss=1.98, simple_loss=0.2356, pruned_loss=0.0271, codebook_loss=18.35, over 1171846.80 frames.], batch size: 22, lr: 3.78e-04
+2022-05-27 23:32:27,587 INFO [train.py:823] (3/4) Epoch 45, batch 400, loss[loss=1.987, simple_loss=0.2547, pruned_loss=0.04118, codebook_loss=18.18, over 7372.00 frames.], tot_loss[loss=1.979, simple_loss=0.2349, pruned_loss=0.02699, codebook_loss=18.35, over 1228904.45 frames.], batch size: 20, lr: 3.78e-04
+2022-05-27 23:33:07,576 INFO [train.py:823] (3/4) Epoch 45, batch 450, loss[loss=1.949, simple_loss=0.233, pruned_loss=0.02924, codebook_loss=18.03, over 7194.00 frames.], tot_loss[loss=1.979, simple_loss=0.2349, pruned_loss=0.02733, codebook_loss=18.34, over 1269036.94 frames.], batch size: 18, lr: 3.78e-04
+2022-05-27 23:33:47,518 INFO [train.py:823] (3/4) Epoch 45, batch 500, loss[loss=1.928, simple_loss=0.2459, pruned_loss=0.03274, codebook_loss=17.73, over 7225.00 frames.], tot_loss[loss=1.986, simple_loss=0.2361, pruned_loss=0.02813, codebook_loss=18.4, over 1308178.37 frames.], batch size: 24, lr: 3.78e-04
+2022-05-27 23:34:27,798 INFO [train.py:823] (3/4) Epoch 45, batch 550, loss[loss=1.955, simple_loss=0.2297, pruned_loss=0.02536, codebook_loss=18.15, over 7184.00 frames.], tot_loss[loss=1.985, simple_loss=0.2349, pruned_loss=0.02797, codebook_loss=18.4, over 1334512.72 frames.], batch size: 18, lr: 3.78e-04
+2022-05-27 23:35:07,236 INFO [train.py:823] (3/4) Epoch 45, batch 600, loss[loss=2.012, simple_loss=0.2433, pruned_loss=0.03101, codebook_loss=18.6, over 6516.00 frames.], tot_loss[loss=1.979, simple_loss=0.2352, pruned_loss=0.02764, codebook_loss=18.34, over 1347955.52 frames.], batch size: 34, lr: 3.77e-04
+2022-05-27 23:35:47,198 INFO [train.py:823] (3/4) Epoch 45, batch 650, loss[loss=1.979, simple_loss=0.2468, pruned_loss=0.03435, codebook_loss=18.21, over 7146.00 frames.], tot_loss[loss=1.979, simple_loss=0.2346, pruned_loss=0.02729, codebook_loss=18.35, over 1363179.06 frames.], batch size: 23, lr: 3.77e-04
+2022-05-27 23:36:26,953 INFO [train.py:823] (3/4) Epoch 45, batch 700, loss[loss=1.997, simple_loss=0.2441, pruned_loss=0.02163, codebook_loss=18.53, over 7318.00 frames.], tot_loss[loss=1.984, simple_loss=0.2357, pruned_loss=0.02759, codebook_loss=18.38, over 1377499.09 frames.], batch size: 22, lr: 3.77e-04
+2022-05-27 23:37:06,797 INFO [train.py:823] (3/4) Epoch 45, batch 750, loss[loss=1.944, simple_loss=0.2616, pruned_loss=0.03741, codebook_loss=17.76, over 6992.00 frames.], tot_loss[loss=1.986, simple_loss=0.2362, pruned_loss=0.02785, codebook_loss=18.41, over 1386216.86 frames.], batch size: 29, lr: 3.77e-04
+2022-05-27 23:37:46,679 INFO [train.py:823] (3/4) Epoch 45, batch 800, loss[loss=2.426, simple_loss=0.274, pruned_loss=0.04954, codebook_loss=22.39, over 7329.00 frames.], tot_loss[loss=1.983, simple_loss=0.2359, pruned_loss=0.02741, codebook_loss=18.38, over 1396078.10 frames.], batch size: 23, lr: 3.77e-04
+2022-05-27 23:38:26,825 INFO [train.py:823] (3/4) Epoch 45, batch 850, loss[loss=1.939, simple_loss=0.2416, pruned_loss=0.02001, codebook_loss=17.98, over 7185.00 frames.], tot_loss[loss=1.987, simple_loss=0.2371, pruned_loss=0.02749, codebook_loss=18.41, over 1398619.35 frames.], batch size: 21, lr: 3.76e-04
+2022-05-27 23:39:06,646 INFO [train.py:823] (3/4) Epoch 45, batch 900, loss[loss=2.103, simple_loss=0.211, pruned_loss=0.02686, codebook_loss=19.71, over 7420.00 frames.], tot_loss[loss=1.988, simple_loss=0.2373, pruned_loss=0.02761, codebook_loss=18.42, over 1401421.03 frames.], batch size: 18, lr: 3.76e-04
+2022-05-27 23:40:00,614 INFO [train.py:823] (3/4) Epoch 46, batch 0, loss[loss=1.984, simple_loss=0.2586, pruned_loss=0.04283, codebook_loss=18.12, over 7161.00 frames.], tot_loss[loss=1.984, simple_loss=0.2586, pruned_loss=0.04283, codebook_loss=18.12, over 7161.00 frames.], batch size: 22, lr: 3.72e-04
+2022-05-27 23:40:40,265 INFO [train.py:823] (3/4) Epoch 46, batch 50, loss[loss=1.937, simple_loss=0.2314, pruned_loss=0.02444, codebook_loss=17.97, over 7274.00 frames.], tot_loss[loss=1.966, simple_loss=0.2349, pruned_loss=0.02579, codebook_loss=18.22, over 315484.88 frames.], batch size: 20, lr: 3.72e-04
+2022-05-27 23:41:20,236 INFO [train.py:823] (3/4) Epoch 46, batch 100, loss[loss=1.933, simple_loss=0.1983, pruned_loss=0.02244, codebook_loss=18.12, over 7002.00 frames.], tot_loss[loss=1.962, simple_loss=0.2329, pruned_loss=0.02574, codebook_loss=18.2, over 561918.69 frames.], batch size: 16, lr: 3.71e-04
+2022-05-27 23:42:00,099 INFO [train.py:823] (3/4) Epoch 46, batch 150, loss[loss=1.919, simple_loss=0.2452, pruned_loss=0.02823, codebook_loss=17.68, over 7115.00 frames.], tot_loss[loss=1.969, simple_loss=0.2345, pruned_loss=0.02712, codebook_loss=18.24, over 754697.52 frames.], batch size: 20, lr: 3.71e-04
+2022-05-27 23:42:40,050 INFO [train.py:823] (3/4) Epoch 46, batch 200, loss[loss=1.911, simple_loss=0.2445, pruned_loss=0.02903, codebook_loss=17.6, over 7343.00 frames.], tot_loss[loss=1.974, simple_loss=0.2337, pruned_loss=0.0268, codebook_loss=18.31, over 906996.07 frames.], batch size: 23, lr: 3.71e-04
+2022-05-27 23:43:22,186 INFO [train.py:823] (3/4) Epoch 46, batch 250, loss[loss=1.977, simple_loss=0.2325, pruned_loss=0.0284, codebook_loss=18.32, over 7131.00 frames.], tot_loss[loss=1.977, simple_loss=0.2343, pruned_loss=0.02737, codebook_loss=18.33, over 1021908.17 frames.], batch size: 23, lr: 3.71e-04
+2022-05-27 23:44:03,550 INFO [train.py:823] (3/4) Epoch 46, batch 300, loss[loss=1.947, simple_loss=0.2409, pruned_loss=0.02028, codebook_loss=18.06, over 7017.00 frames.], tot_loss[loss=1.975, simple_loss=0.2357, pruned_loss=0.02745, codebook_loss=18.3, over 1108234.52 frames.], batch size: 29, lr: 3.70e-04
+2022-05-27 23:44:43,222 INFO [train.py:823] (3/4) Epoch 46, batch 350, loss[loss=2.096, simple_loss=0.266, pruned_loss=0.02444, codebook_loss=19.38, over 6380.00 frames.], tot_loss[loss=1.98, simple_loss=0.2367, pruned_loss=0.02762, codebook_loss=18.35, over 1180274.17 frames.], batch size: 34, lr: 3.70e-04
+2022-05-27 23:45:23,233 INFO [train.py:823] (3/4) Epoch 46, batch 400, loss[loss=1.919, simple_loss=0.2538, pruned_loss=0.03512, codebook_loss=17.57, over 7141.00 frames.], tot_loss[loss=1.98, simple_loss=0.2376, pruned_loss=0.02759, codebook_loss=18.33, over 1236717.43 frames.], batch size: 23, lr: 3.70e-04
+2022-05-27 23:46:03,199 INFO [train.py:823] (3/4) Epoch 46, batch 450, loss[loss=1.931, simple_loss=0.222, pruned_loss=0.01759, codebook_loss=18.02, over 7280.00 frames.], tot_loss[loss=1.981, simple_loss=0.2362, pruned_loss=0.02724, codebook_loss=18.36, over 1279403.60 frames.], batch size: 20, lr: 3.70e-04
+2022-05-27 23:46:42,933 INFO [train.py:823] (3/4) Epoch 46, batch 500, loss[loss=1.941, simple_loss=0.2184, pruned_loss=0.02464, codebook_loss=18.07, over 6781.00 frames.], tot_loss[loss=1.978, simple_loss=0.2363, pruned_loss=0.02691, codebook_loss=18.33, over 1304275.09 frames.], batch size: 15, lr: 3.70e-04
+2022-05-27 23:47:22,897 INFO [train.py:823] (3/4) Epoch 46, batch 550, loss[loss=1.952, simple_loss=0.248, pruned_loss=0.0248, codebook_loss=18.03, over 7308.00 frames.], tot_loss[loss=1.982, simple_loss=0.2365, pruned_loss=0.02715, codebook_loss=18.37, over 1333790.05 frames.], batch size: 22, lr: 3.69e-04
+2022-05-27 23:48:03,036 INFO [train.py:823] (3/4) Epoch 46, batch 600, loss[loss=1.919, simple_loss=0.2042, pruned_loss=0.01895, codebook_loss=17.98, over 7027.00 frames.], tot_loss[loss=1.978, simple_loss=0.2357, pruned_loss=0.0267, codebook_loss=18.34, over 1351841.42 frames.], batch size: 17, lr: 3.69e-04
+2022-05-27 23:48:42,907 INFO [train.py:823] (3/4) Epoch 46, batch 650, loss[loss=1.884, simple_loss=0.2434, pruned_loss=0.02339, codebook_loss=17.39, over 7155.00 frames.], tot_loss[loss=1.974, simple_loss=0.2351, pruned_loss=0.0264, codebook_loss=18.3, over 1366309.10 frames.], batch size: 23, lr: 3.69e-04
+2022-05-27 23:49:24,244 INFO [train.py:823] (3/4) Epoch 46, batch 700, loss[loss=1.937, simple_loss=0.2161, pruned_loss=0.02465, codebook_loss=18.04, over 7166.00 frames.], tot_loss[loss=1.978, simple_loss=0.2344, pruned_loss=0.02662, codebook_loss=18.34, over 1375147.95 frames.], batch size: 17, lr: 3.69e-04
+2022-05-27 23:50:04,156 INFO [train.py:823] (3/4) Epoch 46, batch 750, loss[loss=2.078, simple_loss=0.2445, pruned_loss=0.02852, codebook_loss=19.28, over 6566.00 frames.], tot_loss[loss=1.974, simple_loss=0.2343, pruned_loss=0.02641, codebook_loss=18.3, over 1383761.04 frames.], batch size: 34, lr: 3.69e-04
+2022-05-27 23:50:44,396 INFO [train.py:823] (3/4) Epoch 46, batch 800, loss[loss=2.069, simple_loss=0.2391, pruned_loss=0.03596, codebook_loss=19.14, over 7194.00 frames.], tot_loss[loss=1.98, simple_loss=0.2349, pruned_loss=0.02648, codebook_loss=18.36, over 1387459.05 frames.], batch size: 20, lr: 3.68e-04
+2022-05-27 23:51:24,080 INFO [train.py:823] (3/4) Epoch 46, batch 850, loss[loss=2.006, simple_loss=0.2634, pruned_loss=0.03839, codebook_loss=18.36, over 7363.00 frames.], tot_loss[loss=1.983, simple_loss=0.2354, pruned_loss=0.02686, codebook_loss=18.38, over 1390097.31 frames.], batch size: 23, lr: 3.68e-04
+2022-05-27 23:52:04,346 INFO [train.py:823] (3/4) Epoch 46, batch 900, loss[loss=1.873, simple_loss=0.2173, pruned_loss=0.01271, codebook_loss=17.51, over 7089.00 frames.], tot_loss[loss=1.985, simple_loss=0.236, pruned_loss=0.02701, codebook_loss=18.4, over 1397112.78 frames.], batch size: 18, lr: 3.68e-04
+2022-05-27 23:52:54,937 INFO [train.py:823] (3/4) Epoch 47, batch 0, loss[loss=1.899, simple_loss=0.2057, pruned_loss=0.02017, codebook_loss=17.76, over 7004.00 frames.], tot_loss[loss=1.899, simple_loss=0.2057, pruned_loss=0.02017, codebook_loss=17.76, over 7004.00 frames.], batch size: 16, lr: 3.64e-04
+2022-05-27 23:53:35,053 INFO [train.py:823] (3/4) Epoch 47, batch 50, loss[loss=2.07, simple_loss=0.2297, pruned_loss=0.02362, codebook_loss=19.31, over 7292.00 frames.], tot_loss[loss=1.947, simple_loss=0.2303, pruned_loss=0.02446, codebook_loss=18.08, over 322164.17 frames.], batch size: 17, lr: 3.64e-04
+2022-05-27 23:54:15,084 INFO [train.py:823] (3/4) Epoch 47, batch 100, loss[loss=1.805, simple_loss=0.2007, pruned_loss=0.01453, codebook_loss=16.9, over 7307.00 frames.], tot_loss[loss=1.966, simple_loss=0.2302, pruned_loss=0.02515, codebook_loss=18.26, over 565706.97 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:54:55,172 INFO [train.py:823] (3/4) Epoch 47, batch 150, loss[loss=2.111, simple_loss=0.2548, pruned_loss=0.03381, codebook_loss=19.5, over 7298.00 frames.], tot_loss[loss=1.967, simple_loss=0.2323, pruned_loss=0.02637, codebook_loss=18.25, over 757100.12 frames.], batch size: 22, lr: 3.63e-04
+2022-05-27 23:55:34,803 INFO [train.py:823] (3/4) Epoch 47, batch 200, loss[loss=2.133, simple_loss=0.2439, pruned_loss=0.0378, codebook_loss=19.73, over 7089.00 frames.], tot_loss[loss=1.973, simple_loss=0.234, pruned_loss=0.02698, codebook_loss=18.29, over 901192.27 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:56:14,831 INFO [train.py:823] (3/4) Epoch 47, batch 250, loss[loss=1.87, simple_loss=0.2252, pruned_loss=0.0181, codebook_loss=17.39, over 7389.00 frames.], tot_loss[loss=1.968, simple_loss=0.2338, pruned_loss=0.0265, codebook_loss=18.25, over 1022368.63 frames.], batch size: 19, lr: 3.63e-04
+2022-05-27 23:56:54,301 INFO [train.py:823] (3/4) Epoch 47, batch 300, loss[loss=1.963, simple_loss=0.2103, pruned_loss=0.0216, codebook_loss=18.36, over 7190.00 frames.], tot_loss[loss=1.965, simple_loss=0.234, pruned_loss=0.02607, codebook_loss=18.22, over 1111519.07 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:57:34,850 INFO [train.py:823] (3/4) Epoch 47, batch 350, loss[loss=1.944, simple_loss=0.237, pruned_loss=0.02389, codebook_loss=18.02, over 7284.00 frames.], tot_loss[loss=1.965, simple_loss=0.234, pruned_loss=0.02625, codebook_loss=18.22, over 1179159.41 frames.], batch size: 20, lr: 3.62e-04
+2022-05-27 23:58:14,539 INFO [train.py:823] (3/4) Epoch 47, batch 400, loss[loss=1.914, simple_loss=0.2402, pruned_loss=0.02495, codebook_loss=17.69, over 7278.00 frames.], tot_loss[loss=1.965, simple_loss=0.2356, pruned_loss=0.0267, codebook_loss=18.21, over 1233340.59 frames.], batch size: 20, lr: 3.62e-04
+2022-05-27 23:58:54,558 INFO [train.py:823] (3/4) Epoch 47, batch 450, loss[loss=1.934, simple_loss=0.2197, pruned_loss=0.02137, codebook_loss=18.03, over 7153.00 frames.], tot_loss[loss=1.968, simple_loss=0.2356, pruned_loss=0.02657, codebook_loss=18.23, over 1273917.14 frames.], batch size: 17, lr: 3.62e-04
+2022-05-27 23:59:34,088 INFO [train.py:823] (3/4) Epoch 47, batch 500, loss[loss=1.913, simple_loss=0.2312, pruned_loss=0.02674, codebook_loss=17.71, over 7089.00 frames.], tot_loss[loss=1.972, simple_loss=0.2361, pruned_loss=0.02679, codebook_loss=18.27, over 1302754.52 frames.], batch size: 19, lr: 3.62e-04
+2022-05-28 00:00:14,252 INFO [train.py:823] (3/4) Epoch 47, batch 550, loss[loss=1.842, simple_loss=0.2148, pruned_loss=0.02343, codebook_loss=17.11, over 7389.00 frames.], tot_loss[loss=1.969, simple_loss=0.2352, pruned_loss=0.02648, codebook_loss=18.25, over 1327552.71 frames.], batch size: 19, lr: 3.62e-04
+2022-05-28 00:00:54,095 INFO [train.py:823] (3/4) Epoch 47, batch 600, loss[loss=1.973, simple_loss=0.255, pruned_loss=0.03322, codebook_loss=18.12, over 7025.00 frames.], tot_loss[loss=1.966, simple_loss=0.2349, pruned_loss=0.02633, codebook_loss=18.22, over 1347041.82 frames.], batch size: 26, lr: 3.61e-04
+2022-05-28 00:01:34,140 INFO [train.py:823] (3/4) Epoch 47, batch 650, loss[loss=1.895, simple_loss=0.2019, pruned_loss=0.02335, codebook_loss=17.71, over 7302.00 frames.], tot_loss[loss=1.962, simple_loss=0.2358, pruned_loss=0.02626, codebook_loss=18.18, over 1364952.86 frames.], batch size: 17, lr: 3.61e-04
+2022-05-28 00:02:14,068 INFO [train.py:823] (3/4) Epoch 47, batch 700, loss[loss=1.923, simple_loss=0.2896, pruned_loss=0.03569, codebook_loss=17.43, over 7325.00 frames.], tot_loss[loss=1.966, simple_loss=0.2354, pruned_loss=0.02636, codebook_loss=18.22, over 1372123.80 frames.], batch size: 23, lr: 3.61e-04
+2022-05-28 00:02:54,284 INFO [train.py:823] (3/4) Epoch 47, batch 750, loss[loss=1.904, simple_loss=0.2185, pruned_loss=0.02764, codebook_loss=17.67, over 7295.00 frames.], tot_loss[loss=1.968, simple_loss=0.2354, pruned_loss=0.02657, codebook_loss=18.24, over 1384285.90 frames.], batch size: 19, lr: 3.61e-04
+2022-05-28 00:03:34,017 INFO [train.py:823] (3/4) Epoch 47, batch 800, loss[loss=1.993, simple_loss=0.243, pruned_loss=0.02719, codebook_loss=18.44, over 6986.00 frames.], tot_loss[loss=1.971, simple_loss=0.2349, pruned_loss=0.02636, codebook_loss=18.27, over 1391345.36 frames.], batch size: 26, lr: 3.61e-04
+2022-05-28 00:04:13,981 INFO [train.py:823] (3/4) Epoch 47, batch 850, loss[loss=1.928, simple_loss=0.2309, pruned_loss=0.02531, codebook_loss=17.87, over 7199.00 frames.], tot_loss[loss=1.974, simple_loss=0.2354, pruned_loss=0.02691, codebook_loss=18.29, over 1393361.89 frames.], batch size: 18, lr: 3.60e-04
+2022-05-28 00:04:53,643 INFO [train.py:823] (3/4) Epoch 47, batch 900, loss[loss=1.869, simple_loss=0.2287, pruned_loss=0.01798, codebook_loss=17.37, over 7305.00 frames.], tot_loss[loss=1.971, simple_loss=0.2355, pruned_loss=0.02677, codebook_loss=18.27, over 1398045.59 frames.], batch size: 22, lr: 3.60e-04
+2022-05-28 00:05:47,407 INFO [train.py:823] (3/4) Epoch 48, batch 0, loss[loss=1.844, simple_loss=0.2278, pruned_loss=0.01728, codebook_loss=17.13, over 7181.00 frames.], tot_loss[loss=1.844, simple_loss=0.2278, pruned_loss=0.01728, codebook_loss=17.13, over 7181.00 frames.], batch size: 21, lr: 3.56e-04
+2022-05-28 00:06:27,212 INFO [train.py:823] (3/4) Epoch 48, batch 50, loss[loss=2.12, simple_loss=0.2234, pruned_loss=0.02877, codebook_loss=19.8, over 7167.00 frames.], tot_loss[loss=1.982, simple_loss=0.2335, pruned_loss=0.02578, codebook_loss=18.39, over 320604.17 frames.], batch size: 17, lr: 3.56e-04
+2022-05-28 00:07:07,665 INFO [train.py:823] (3/4) Epoch 48, batch 100, loss[loss=1.898, simple_loss=0.2337, pruned_loss=0.01736, codebook_loss=17.64, over 7183.00 frames.], tot_loss[loss=1.972, simple_loss=0.234, pruned_loss=0.02689, codebook_loss=18.28, over 565228.52 frames.], batch size: 25, lr: 3.56e-04
+2022-05-28 00:07:49,902 INFO [train.py:823] (3/4) Epoch 48, batch 150, loss[loss=1.923, simple_loss=0.2067, pruned_loss=0.02472, codebook_loss=17.95, over 7305.00 frames.], tot_loss[loss=1.968, simple_loss=0.235, pruned_loss=0.02674, codebook_loss=18.23, over 759984.17 frames.], batch size: 17, lr: 3.56e-04
+2022-05-28 00:08:31,454 INFO [train.py:823] (3/4) Epoch 48, batch 200, loss[loss=1.925, simple_loss=0.2485, pruned_loss=0.02599, codebook_loss=17.75, over 7303.00 frames.], tot_loss[loss=1.97, simple_loss=0.2339, pruned_loss=0.02637, codebook_loss=18.27, over 908407.65 frames.], batch size: 22, lr: 3.55e-04
+2022-05-28 00:09:11,317 INFO [train.py:823] (3/4) Epoch 48, batch 250, loss[loss=1.926, simple_loss=0.2408, pruned_loss=0.02582, codebook_loss=17.8, over 7192.00 frames.], tot_loss[loss=1.971, simple_loss=0.2339, pruned_loss=0.02678, codebook_loss=18.27, over 1024406.57 frames.], batch size: 19, lr: 3.55e-04
+2022-05-28 00:09:51,421 INFO [train.py:823] (3/4) Epoch 48, batch 300, loss[loss=2.006, simple_loss=0.2621, pruned_loss=0.04062, codebook_loss=18.34, over 6976.00 frames.], tot_loss[loss=1.966, simple_loss=0.2333, pruned_loss=0.02669, codebook_loss=18.23, over 1116213.24 frames.], batch size: 26, lr: 3.55e-04
+2022-05-28 00:10:30,857 INFO [train.py:823] (3/4) Epoch 48, batch 350, loss[loss=1.979, simple_loss=0.2458, pruned_loss=0.02677, codebook_loss=18.3, over 4909.00 frames.], tot_loss[loss=1.972, simple_loss=0.2339, pruned_loss=0.02654, codebook_loss=18.29, over 1182418.43 frames.], batch size: 47, lr: 3.55e-04
+2022-05-28 00:11:11,335 INFO [train.py:823] (3/4) Epoch 48, batch 400, loss[loss=1.946, simple_loss=0.2477, pruned_loss=0.025, codebook_loss=17.97, over 6473.00 frames.], tot_loss[loss=1.972, simple_loss=0.2333, pruned_loss=0.02644, codebook_loss=18.29, over 1237673.15 frames.], batch size: 34, lr: 3.55e-04
+2022-05-28 00:11:50,925 INFO [train.py:823] (3/4) Epoch 48, batch 450, loss[loss=1.969, simple_loss=0.2302, pruned_loss=0.02844, codebook_loss=18.25, over 7297.00 frames.], tot_loss[loss=1.972, simple_loss=0.2345, pruned_loss=0.02654, codebook_loss=18.28, over 1279941.44 frames.], batch size: 17, lr: 3.54e-04
+2022-05-28 00:12:31,155 INFO [train.py:823] (3/4) Epoch 48, batch 500, loss[loss=1.956, simple_loss=0.254, pruned_loss=0.02758, codebook_loss=18.02, over 7201.00 frames.], tot_loss[loss=1.974, simple_loss=0.2355, pruned_loss=0.02671, codebook_loss=18.29, over 1310454.55 frames.], batch size: 20, lr: 3.54e-04
+2022-05-28 00:13:11,075 INFO [train.py:823] (3/4) Epoch 48, batch 550, loss[loss=1.905, simple_loss=0.2405, pruned_loss=0.01596, codebook_loss=17.69, over 7421.00 frames.], tot_loss[loss=1.971, simple_loss=0.2353, pruned_loss=0.02662, codebook_loss=18.27, over 1330320.80 frames.], batch size: 22, lr: 3.54e-04
+2022-05-28 00:13:52,288 INFO [train.py:823] (3/4) Epoch 48, batch 600, loss[loss=1.94, simple_loss=0.2372, pruned_loss=0.02018, codebook_loss=18.01, over 7281.00 frames.], tot_loss[loss=1.972, simple_loss=0.2361, pruned_loss=0.02666, codebook_loss=18.28, over 1350349.87 frames.], batch size: 20, lr: 3.54e-04
+2022-05-28 00:14:32,038 INFO [train.py:823] (3/4) Epoch 48, batch 650, loss[loss=1.909, simple_loss=0.2403, pruned_loss=0.02304, codebook_loss=17.66, over 7379.00 frames.], tot_loss[loss=1.966, simple_loss=0.2357, pruned_loss=0.02608, codebook_loss=18.23, over 1364111.63 frames.], batch size: 21, lr: 3.54e-04
+2022-05-28 00:15:11,923 INFO [train.py:823] (3/4) Epoch 48, batch 700, loss[loss=1.942, simple_loss=0.2488, pruned_loss=0.02957, codebook_loss=17.88, over 7170.00 frames.], tot_loss[loss=1.966, simple_loss=0.2364, pruned_loss=0.02634, codebook_loss=18.21, over 1371771.46 frames.], batch size: 22, lr: 3.53e-04
+2022-05-28 00:15:51,679 INFO [train.py:823] (3/4) Epoch 48, batch 750, loss[loss=1.917, simple_loss=0.2346, pruned_loss=0.02319, codebook_loss=17.77, over 7104.00 frames.], tot_loss[loss=1.966, simple_loss=0.236, pruned_loss=0.02622, codebook_loss=18.22, over 1384600.24 frames.], batch size: 19, lr: 3.53e-04
+2022-05-28 00:16:31,785 INFO [train.py:823] (3/4) Epoch 48, batch 800, loss[loss=1.929, simple_loss=0.2461, pruned_loss=0.03252, codebook_loss=17.74, over 7341.00 frames.], tot_loss[loss=1.966, simple_loss=0.2352, pruned_loss=0.02591, codebook_loss=18.22, over 1391852.25 frames.], batch size: 23, lr: 3.53e-04
+2022-05-28 00:17:11,217 INFO [train.py:823] (3/4) Epoch 48, batch 850, loss[loss=2.026, simple_loss=0.2438, pruned_loss=0.03494, codebook_loss=18.69, over 7299.00 frames.], tot_loss[loss=1.975, simple_loss=0.2351, pruned_loss=0.0261, codebook_loss=18.31, over 1392627.79 frames.], batch size: 17, lr: 3.53e-04
+2022-05-28 00:17:51,125 INFO [train.py:823] (3/4) Epoch 48, batch 900, loss[loss=1.968, simple_loss=0.2221, pruned_loss=0.02557, codebook_loss=18.31, over 7294.00 frames.], tot_loss[loss=1.975, simple_loss=0.235, pruned_loss=0.02614, codebook_loss=18.32, over 1395086.31 frames.], batch size: 19, lr: 3.53e-04
+2022-05-28 00:18:41,955 INFO [train.py:823] (3/4) Epoch 49, batch 0, loss[loss=1.9, simple_loss=0.2409, pruned_loss=0.02348, codebook_loss=17.56, over 7376.00 frames.], tot_loss[loss=1.9, simple_loss=0.2409, pruned_loss=0.02348, codebook_loss=17.56, over 7376.00 frames.], batch size: 20, lr: 3.49e-04
+2022-05-28 00:19:21,915 INFO [train.py:823] (3/4) Epoch 49, batch 50, loss[loss=1.952, simple_loss=0.2446, pruned_loss=0.02246, codebook_loss=18.07, over 7277.00 frames.], tot_loss[loss=1.934, simple_loss=0.2343, pruned_loss=0.02455, codebook_loss=17.92, over 318493.05 frames.], batch size: 21, lr: 3.49e-04
+2022-05-28 00:20:01,480 INFO [train.py:823] (3/4) Epoch 49, batch 100, loss[loss=1.862, simple_loss=0.2259, pruned_loss=0.01898, codebook_loss=17.3, over 7190.00 frames.], tot_loss[loss=1.935, simple_loss=0.2344, pruned_loss=0.02481, codebook_loss=17.93, over 560555.37 frames.], batch size: 18, lr: 3.48e-04
+2022-05-28 00:20:41,940 INFO [train.py:823] (3/4) Epoch 49, batch 150, loss[loss=2.092, simple_loss=0.2513, pruned_loss=0.03838, codebook_loss=19.28, over 4737.00 frames.], tot_loss[loss=1.949, simple_loss=0.234, pruned_loss=0.02554, codebook_loss=18.06, over 750857.87 frames.], batch size: 46, lr: 3.48e-04
+2022-05-28 00:21:21,722 INFO [train.py:823] (3/4) Epoch 49, batch 200, loss[loss=1.889, simple_loss=0.2416, pruned_loss=0.02484, codebook_loss=17.44, over 7144.00 frames.], tot_loss[loss=1.953, simple_loss=0.2327, pruned_loss=0.02544, codebook_loss=18.11, over 901890.46 frames.], batch size: 23, lr: 3.48e-04
+2022-05-28 00:22:01,875 INFO [train.py:823] (3/4) Epoch 49, batch 250, loss[loss=1.929, simple_loss=0.2352, pruned_loss=0.023, codebook_loss=17.88, over 7192.00 frames.], tot_loss[loss=1.962, simple_loss=0.2339, pruned_loss=0.0258, codebook_loss=18.19, over 1022260.87 frames.], batch size: 20, lr: 3.48e-04
+2022-05-28 00:22:41,595 INFO [train.py:823] (3/4) Epoch 49, batch 300, loss[loss=1.842, simple_loss=0.2113, pruned_loss=0.01644, codebook_loss=17.2, over 7296.00 frames.], tot_loss[loss=1.963, simple_loss=0.2331, pruned_loss=0.02587, codebook_loss=18.21, over 1113947.56 frames.], batch size: 18, lr: 3.48e-04
+2022-05-28 00:23:21,771 INFO [train.py:823] (3/4) Epoch 49, batch 350, loss[loss=2.176, simple_loss=0.2613, pruned_loss=0.03723, codebook_loss=20.08, over 7221.00 frames.], tot_loss[loss=1.963, simple_loss=0.2327, pruned_loss=0.02526, codebook_loss=18.21, over 1177552.32 frames.], batch size: 25, lr: 3.48e-04
+2022-05-28 00:24:01,388 INFO [train.py:823] (3/4) Epoch 49, batch 400, loss[loss=2.036, simple_loss=0.2184, pruned_loss=0.03493, codebook_loss=18.92, over 7003.00 frames.], tot_loss[loss=1.969, simple_loss=0.2333, pruned_loss=0.02576, codebook_loss=18.27, over 1227909.30 frames.], batch size: 16, lr: 3.47e-04
+2022-05-28 00:24:41,470 INFO [train.py:823] (3/4) Epoch 49, batch 450, loss[loss=1.921, simple_loss=0.2556, pruned_loss=0.0323, codebook_loss=17.6, over 7254.00 frames.], tot_loss[loss=1.969, simple_loss=0.2331, pruned_loss=0.02592, codebook_loss=18.27, over 1272409.68 frames.], batch size: 24, lr: 3.47e-04
+2022-05-28 00:25:21,295 INFO [train.py:823] (3/4) Epoch 49, batch 500, loss[loss=1.967, simple_loss=0.2511, pruned_loss=0.02755, codebook_loss=18.14, over 6452.00 frames.], tot_loss[loss=1.965, simple_loss=0.2338, pruned_loss=0.02604, codebook_loss=18.22, over 1303818.04 frames.], batch size: 34, lr: 3.47e-04
+2022-05-28 00:26:01,621 INFO [train.py:823] (3/4) Epoch 49, batch 550, loss[loss=1.9, simple_loss=0.212, pruned_loss=0.02103, codebook_loss=17.73, over 7296.00 frames.], tot_loss[loss=1.967, simple_loss=0.233, pruned_loss=0.02573, codebook_loss=18.25, over 1330746.28 frames.], batch size: 17, lr: 3.47e-04
+2022-05-28 00:26:41,357 INFO [train.py:823] (3/4) Epoch 49, batch 600, loss[loss=1.918, simple_loss=0.2309, pruned_loss=0.0246, codebook_loss=17.78, over 7211.00 frames.], tot_loss[loss=1.97, simple_loss=0.2336, pruned_loss=0.02598, codebook_loss=18.27, over 1350247.35 frames.], batch size: 24, lr: 3.47e-04
+2022-05-28 00:27:21,543 INFO [train.py:823] (3/4) Epoch 49, batch 650, loss[loss=1.82, simple_loss=0.2091, pruned_loss=0.01159, codebook_loss=17.04, over 7154.00 frames.], tot_loss[loss=1.969, simple_loss=0.2339, pruned_loss=0.02622, codebook_loss=18.25, over 1366297.97 frames.], batch size: 17, lr: 3.46e-04
+2022-05-28 00:28:00,826 INFO [train.py:823] (3/4) Epoch 49, batch 700, loss[loss=2.048, simple_loss=0.255, pruned_loss=0.02471, codebook_loss=18.96, over 7419.00 frames.], tot_loss[loss=1.977, simple_loss=0.2353, pruned_loss=0.02691, codebook_loss=18.33, over 1370408.54 frames.], batch size: 22, lr: 3.46e-04
+2022-05-28 00:28:40,797 INFO [train.py:823] (3/4) Epoch 49, batch 750, loss[loss=1.965, simple_loss=0.2311, pruned_loss=0.02558, codebook_loss=18.24, over 7298.00 frames.], tot_loss[loss=1.974, simple_loss=0.2354, pruned_loss=0.02672, codebook_loss=18.29, over 1381062.66 frames.], batch size: 19, lr: 3.46e-04
+2022-05-28 00:29:20,494 INFO [train.py:823] (3/4) Epoch 49, batch 800, loss[loss=1.909, simple_loss=0.1962, pruned_loss=0.0138, codebook_loss=17.97, over 7168.00 frames.], tot_loss[loss=1.97, simple_loss=0.2352, pruned_loss=0.02677, codebook_loss=18.26, over 1384913.20 frames.], batch size: 17, lr: 3.46e-04
+2022-05-28 00:30:00,451 INFO [train.py:823] (3/4) Epoch 49, batch 850, loss[loss=1.929, simple_loss=0.2239, pruned_loss=0.02469, codebook_loss=17.92, over 7099.00 frames.], tot_loss[loss=1.968, simple_loss=0.2353, pruned_loss=0.02654, codebook_loss=18.24, over 1391293.57 frames.], batch size: 18, lr: 3.46e-04
+2022-05-28 00:30:40,057 INFO [train.py:823] (3/4) Epoch 49, batch 900, loss[loss=1.949, simple_loss=0.2277, pruned_loss=0.01915, codebook_loss=18.16, over 6488.00 frames.], tot_loss[loss=1.973, simple_loss=0.2356, pruned_loss=0.02661, codebook_loss=18.29, over 1394025.69 frames.], batch size: 34, lr: 3.45e-04
+2022-05-28 00:31:35,692 INFO [train.py:823] (3/4) Epoch 50, batch 0, loss[loss=1.948, simple_loss=0.2326, pruned_loss=0.02569, codebook_loss=18.06, over 6936.00 frames.], tot_loss[loss=1.948, simple_loss=0.2326, pruned_loss=0.02569, codebook_loss=18.06, over 6936.00 frames.], batch size: 29, lr: 3.42e-04
+2022-05-28 00:32:17,065 INFO [train.py:823] (3/4) Epoch 50, batch 50, loss[loss=2.013, simple_loss=0.2369, pruned_loss=0.02515, codebook_loss=18.69, over 7276.00 frames.], tot_loss[loss=1.968, simple_loss=0.2294, pruned_loss=0.02564, codebook_loss=18.27, over 322107.71 frames.], batch size: 20, lr: 3.42e-04
+2022-05-28 00:32:59,759 INFO [train.py:823] (3/4) Epoch 50, batch 100, loss[loss=1.917, simple_loss=0.2361, pruned_loss=0.03379, codebook_loss=17.65, over 7174.00 frames.], tot_loss[loss=1.947, simple_loss=0.2305, pruned_loss=0.02475, codebook_loss=18.07, over 564213.30 frames.], batch size: 23, lr: 3.41e-04
+2022-05-28 00:33:39,328 INFO [train.py:823] (3/4) Epoch 50, batch 150, loss[loss=2.048, simple_loss=0.2403, pruned_loss=0.03725, codebook_loss=18.91, over 7376.00 frames.], tot_loss[loss=1.965, simple_loss=0.2342, pruned_loss=0.0264, codebook_loss=18.21, over 753055.60 frames.], batch size: 21, lr: 3.41e-04
+2022-05-28 00:34:19,388 INFO [train.py:823] (3/4) Epoch 50, batch 200, loss[loss=2.021, simple_loss=0.2339, pruned_loss=0.02672, codebook_loss=18.77, over 7096.00 frames.], tot_loss[loss=1.969, simple_loss=0.235, pruned_loss=0.02643, codebook_loss=18.25, over 902498.41 frames.], batch size: 18, lr: 3.41e-04
+2022-05-28 00:34:59,341 INFO [train.py:823] (3/4) Epoch 50, batch 250, loss[loss=2.01, simple_loss=0.2521, pruned_loss=0.03282, codebook_loss=18.51, over 7186.00 frames.], tot_loss[loss=1.962, simple_loss=0.2339, pruned_loss=0.02584, codebook_loss=18.19, over 1020201.78 frames.], batch size: 22, lr: 3.41e-04
+2022-05-28 00:35:39,393 INFO [train.py:823] (3/4) Epoch 50, batch 300, loss[loss=1.991, simple_loss=0.2564, pruned_loss=0.04335, codebook_loss=18.19, over 7200.00 frames.], tot_loss[loss=1.966, simple_loss=0.2344, pruned_loss=0.02588, codebook_loss=18.23, over 1110516.11 frames.], batch size: 20, lr: 3.41e-04
+2022-05-28 00:36:19,040 INFO [train.py:823] (3/4) Epoch 50, batch 350, loss[loss=2.437, simple_loss=0.2234, pruned_loss=0.02476, codebook_loss=23, over 7428.00 frames.], tot_loss[loss=1.962, simple_loss=0.2335, pruned_loss=0.02542, codebook_loss=18.2, over 1178555.04 frames.], batch size: 22, lr: 3.41e-04
+2022-05-28 00:36:59,300 INFO [train.py:823] (3/4) Epoch 50, batch 400, loss[loss=1.946, simple_loss=0.2356, pruned_loss=0.0284, codebook_loss=18, over 7039.00 frames.], tot_loss[loss=1.964, simple_loss=0.2325, pruned_loss=0.02547, codebook_loss=18.22, over 1232927.42 frames.], batch size: 26, lr: 3.40e-04
+2022-05-28 00:37:40,220 INFO [train.py:823] (3/4) Epoch 50, batch 450, loss[loss=1.925, simple_loss=0.238, pruned_loss=0.02578, codebook_loss=17.8, over 6612.00 frames.], tot_loss[loss=1.963, simple_loss=0.2338, pruned_loss=0.02579, codebook_loss=18.2, over 1274024.13 frames.], batch size: 34, lr: 3.40e-04
+2022-05-28 00:38:20,353 INFO [train.py:823] (3/4) Epoch 50, batch 500, loss[loss=1.915, simple_loss=0.2313, pruned_loss=0.02688, codebook_loss=17.73, over 7306.00 frames.], tot_loss[loss=1.965, simple_loss=0.2341, pruned_loss=0.02597, codebook_loss=18.22, over 1306809.58 frames.], batch size: 19, lr: 3.40e-04
+2022-05-28 00:39:00,418 INFO [train.py:823] (3/4) Epoch 50, batch 550, loss[loss=1.913, simple_loss=0.2299, pruned_loss=0.02345, codebook_loss=17.75, over 7202.00 frames.], tot_loss[loss=1.969, simple_loss=0.2346, pruned_loss=0.02621, codebook_loss=18.25, over 1334806.25 frames.], batch size: 24, lr: 3.40e-04
+2022-05-28 00:39:40,461 INFO [train.py:823] (3/4) Epoch 50, batch 600, loss[loss=1.961, simple_loss=0.2112, pruned_loss=0.01372, codebook_loss=18.41, over 7010.00 frames.], tot_loss[loss=1.969, simple_loss=0.2347, pruned_loss=0.02627, codebook_loss=18.25, over 1353035.86 frames.], batch size: 16, lr: 3.40e-04
+2022-05-28 00:40:20,088 INFO [train.py:823] (3/4) Epoch 50, batch 650, loss[loss=1.861, simple_loss=0.1939, pruned_loss=0.01167, codebook_loss=17.53, over 7008.00 frames.], tot_loss[loss=1.967, simple_loss=0.2354, pruned_loss=0.02652, codebook_loss=18.23, over 1363871.23 frames.], batch size: 16, lr: 3.39e-04
+2022-05-28 00:41:00,233 INFO [train.py:823] (3/4) Epoch 50, batch 700, loss[loss=1.93, simple_loss=0.2242, pruned_loss=0.01871, codebook_loss=17.99, over 7001.00 frames.], tot_loss[loss=1.969, simple_loss=0.2351, pruned_loss=0.02669, codebook_loss=18.24, over 1376281.23 frames.], batch size: 16, lr: 3.39e-04
+2022-05-28 00:41:39,953 INFO [train.py:823] (3/4) Epoch 50, batch 750, loss[loss=1.954, simple_loss=0.2521, pruned_loss=0.02899, codebook_loss=17.99, over 7299.00 frames.], tot_loss[loss=1.967, simple_loss=0.2353, pruned_loss=0.02657, codebook_loss=18.23, over 1382934.02 frames.], batch size: 22, lr: 3.39e-04
+2022-05-28 00:42:20,188 INFO [train.py:823] (3/4) Epoch 50, batch 800, loss[loss=1.999, simple_loss=0.2376, pruned_loss=0.02614, codebook_loss=18.54, over 7093.00 frames.], tot_loss[loss=1.968, simple_loss=0.2351, pruned_loss=0.02667, codebook_loss=18.23, over 1390690.65 frames.], batch size: 19, lr: 3.39e-04
+2022-05-28 00:43:00,014 INFO [train.py:823] (3/4) Epoch 50, batch 850, loss[loss=1.961, simple_loss=0.2499, pruned_loss=0.03637, codebook_loss=18, over 4888.00 frames.], tot_loss[loss=1.976, simple_loss=0.2354, pruned_loss=0.02699, codebook_loss=18.32, over 1395477.55 frames.], batch size: 47, lr: 3.39e-04
+2022-05-28 00:43:39,831 INFO [train.py:823] (3/4) Epoch 50, batch 900, loss[loss=1.917, simple_loss=0.2358, pruned_loss=0.01656, codebook_loss=17.83, over 6423.00 frames.], tot_loss[loss=1.97, simple_loss=0.2354, pruned_loss=0.02647, codebook_loss=18.26, over 1397783.08 frames.], batch size: 34, lr: 3.39e-04
+2022-05-28 00:44:19,520 INFO [train.py:1038] (3/4) Done!