diff --git "a/distillation/log/log-train-2022-05-27-13-56-55-1" "b/distillation/log/log-train-2022-05-27-13-56-55-1"
new file mode 100644--- /dev/null
+++ "b/distillation/log/log-train-2022-05-27-13-56-55-1"
@@ -0,0 +1,982 @@
+2022-05-27 13:56:55,368 INFO [train.py:887] (1/4) Training started
+2022-05-27 13:56:55,368 INFO [train.py:897] (1/4) Device: cuda:1
+2022-05-27 13:56:55,370 INFO [train.py:906] (1/4) {'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] (1/4) About to create model
+2022-05-27 13:56:55,874 INFO [train.py:912] (1/4) Number of model parameters: 85075176
+2022-05-27 13:57:00,396 INFO [train.py:927] (1/4) Using DDP
+2022-05-27 13:57:00,574 INFO [asr_datamodule.py:408] (1/4) About to get train-clean-100 cuts
+2022-05-27 13:57:08,723 INFO [asr_datamodule.py:225] (1/4) Enable MUSAN
+2022-05-27 13:57:08,723 INFO [asr_datamodule.py:226] (1/4) About to get Musan cuts
+2022-05-27 13:57:12,326 INFO [asr_datamodule.py:254] (1/4) Enable SpecAugment
+2022-05-27 13:57:12,326 INFO [asr_datamodule.py:255] (1/4) Time warp factor: -1
+2022-05-27 13:57:12,326 INFO [asr_datamodule.py:267] (1/4) Num frame mask: 10
+2022-05-27 13:57:12,326 INFO [asr_datamodule.py:280] (1/4) About to create train dataset
+2022-05-27 13:57:12,326 INFO [asr_datamodule.py:309] (1/4) Using BucketingSampler.
+2022-05-27 13:57:12,641 INFO [asr_datamodule.py:325] (1/4) About to create train dataloader
+2022-05-27 13:57:12,641 INFO [asr_datamodule.py:429] (1/4) About to get dev-clean cuts
+2022-05-27 13:57:12,793 INFO [asr_datamodule.py:434] (1/4) About to get dev-other cuts
+2022-05-27 13:57:12,942 INFO [asr_datamodule.py:356] (1/4) About to create dev dataset
+2022-05-27 13:57:12,952 INFO [asr_datamodule.py:375] (1/4) About to create dev dataloader
+2022-05-27 13:57:12,952 INFO [train.py:1054] (1/4) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
+2022-05-27 13:57:15,194 INFO [distributed.py:874] (1/4) Reducer buckets have been rebuilt in this iteration.
+2022-05-27 13:57:27,687 INFO [train.py:823] (1/4) Epoch 1, batch 0, loss[loss=9.119, simple_loss=1.607, pruned_loss=6.558, codebook_loss=83.16, over 7285.00 frames.], tot_loss[loss=9.119, simple_loss=1.607, pruned_loss=6.558, codebook_loss=83.16, over 7285.00 frames.], batch size: 21, lr: 3.00e-03
+2022-05-27 13:58:08,137 INFO [train.py:823] (1/4) Epoch 1, batch 50, loss[loss=5.476, simple_loss=1.095, pruned_loss=7.026, codebook_loss=49.29, over 7171.00 frames.], tot_loss[loss=6.746, simple_loss=1.125, pruned_loss=6.806, codebook_loss=61.84, over 322696.48 frames.], batch size: 23, lr: 3.00e-03
+2022-05-27 13:58:49,219 INFO [train.py:823] (1/4) Epoch 1, batch 100, loss[loss=4.581, simple_loss=0.8852, pruned_loss=6.806, codebook_loss=41.38, over 7186.00 frames.], tot_loss[loss=5.709, simple_loss=1.014, pruned_loss=6.809, codebook_loss=52.02, over 564199.28 frames.], batch size: 20, lr: 3.00e-03
+2022-05-27 13:59:29,590 INFO [train.py:823] (1/4) Epoch 1, batch 150, loss[loss=4.255, simple_loss=0.856, pruned_loss=6.713, codebook_loss=38.27, over 7334.00 frames.], tot_loss[loss=5.13, simple_loss=0.9466, pruned_loss=6.782, codebook_loss=46.56, over 754187.93 frames.], batch size: 23, lr: 3.00e-03
+2022-05-27 14:00:10,088 INFO [train.py:823] (1/4) Epoch 1, batch 200, loss[loss=3.997, simple_loss=0.8303, pruned_loss=6.721, codebook_loss=35.82, over 7280.00 frames.], tot_loss[loss=4.757, simple_loss=0.9046, pruned_loss=6.753, codebook_loss=43.05, over 903302.93 frames.], batch size: 19, lr: 3.00e-03
+2022-05-27 14:00:50,332 INFO [train.py:823] (1/4) Epoch 1, batch 250, loss[loss=3.831, simple_loss=0.7065, pruned_loss=6.523, codebook_loss=34.78, over 7286.00 frames.], tot_loss[loss=4.5, simple_loss=0.8672, pruned_loss=6.721, codebook_loss=40.66, over 1014857.97 frames.], batch size: 17, lr: 3.00e-03
+2022-05-27 14:01:30,777 INFO [train.py:823] (1/4) Epoch 1, batch 300, loss[loss=3.723, simple_loss=0.744, pruned_loss=6.691, codebook_loss=33.51, over 7236.00 frames.], tot_loss[loss=4.284, simple_loss=0.8247, pruned_loss=6.688, codebook_loss=38.72, over 1106254.47 frames.], batch size: 24, lr: 3.00e-03
+2022-05-27 14:02:10,848 INFO [train.py:823] (1/4) Epoch 1, batch 350, loss[loss=3.687, simple_loss=0.713, pruned_loss=6.716, codebook_loss=33.3, over 6570.00 frames.], tot_loss[loss=4.102, simple_loss=0.7792, pruned_loss=6.668, codebook_loss=37.12, over 1177194.33 frames.], batch size: 34, lr: 3.00e-03
+2022-05-27 14:02:51,183 INFO [train.py:823] (1/4) Epoch 1, batch 400, loss[loss=3.555, simple_loss=0.676, pruned_loss=6.728, codebook_loss=32.17, over 4958.00 frames.], tot_loss[loss=3.958, simple_loss=0.7377, pruned_loss=6.656, codebook_loss=35.9, over 1228214.42 frames.], batch size: 46, lr: 3.00e-03
+2022-05-27 14:03:31,155 INFO [train.py:823] (1/4) Epoch 1, batch 450, loss[loss=3.372, simple_loss=0.5538, pruned_loss=6.564, codebook_loss=30.95, over 7192.00 frames.], tot_loss[loss=3.831, simple_loss=0.6974, pruned_loss=6.638, codebook_loss=34.82, over 1274243.69 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:04:11,750 INFO [train.py:823] (1/4) Epoch 1, batch 500, loss[loss=3.347, simple_loss=0.546, pruned_loss=6.491, codebook_loss=30.74, over 7390.00 frames.], tot_loss[loss=3.725, simple_loss=0.6643, pruned_loss=6.626, codebook_loss=33.93, over 1308662.69 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:04:51,670 INFO [train.py:823] (1/4) Epoch 1, batch 550, loss[loss=3.447, simple_loss=0.578, pruned_loss=6.516, codebook_loss=31.58, over 7194.00 frames.], tot_loss[loss=3.639, simple_loss=0.6356, pruned_loss=6.617, codebook_loss=33.22, over 1330211.74 frames.], batch size: 25, lr: 2.99e-03
+2022-05-27 14:05:31,972 INFO [train.py:823] (1/4) Epoch 1, batch 600, loss[loss=3.092, simple_loss=0.4852, pruned_loss=6.69, codebook_loss=28.5, over 7289.00 frames.], tot_loss[loss=3.558, simple_loss=0.6076, pruned_loss=6.604, codebook_loss=32.54, over 1346921.03 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:06:11,925 INFO [train.py:823] (1/4) Epoch 1, batch 650, loss[loss=3.182, simple_loss=0.4583, pruned_loss=6.549, codebook_loss=29.53, over 7102.00 frames.], tot_loss[loss=3.485, simple_loss=0.5846, pruned_loss=6.602, codebook_loss=31.93, over 1360973.52 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:06:52,065 INFO [train.py:823] (1/4) Epoch 1, batch 700, loss[loss=3.086, simple_loss=0.4123, pruned_loss=6.37, codebook_loss=28.79, over 7168.00 frames.], tot_loss[loss=3.417, simple_loss=0.5601, pruned_loss=6.594, codebook_loss=31.37, over 1372814.37 frames.], batch size: 17, lr: 2.99e-03
+2022-05-27 14:07:31,808 INFO [train.py:823] (1/4) Epoch 1, batch 750, loss[loss=3.191, simple_loss=0.4518, pruned_loss=6.471, codebook_loss=29.66, over 6852.00 frames.], tot_loss[loss=3.359, simple_loss=0.5428, pruned_loss=6.593, codebook_loss=30.88, over 1385970.93 frames.], batch size: 15, lr: 2.98e-03
+2022-05-27 14:08:12,262 INFO [train.py:823] (1/4) Epoch 1, batch 800, loss[loss=3.281, simple_loss=0.5137, pruned_loss=6.659, codebook_loss=30.24, over 7152.00 frames.], tot_loss[loss=3.306, simple_loss=0.5239, pruned_loss=6.594, codebook_loss=30.44, over 1391606.50 frames.], batch size: 23, lr: 2.98e-03
+2022-05-27 14:08:52,261 INFO [train.py:823] (1/4) Epoch 1, batch 850, loss[loss=3.022, simple_loss=0.4139, pruned_loss=6.378, codebook_loss=28.15, over 6996.00 frames.], tot_loss[loss=3.26, simple_loss=0.5105, pruned_loss=6.593, codebook_loss=30.05, over 1399711.89 frames.], batch size: 16, lr: 2.98e-03
+2022-05-27 14:09:32,236 INFO [train.py:823] (1/4) Epoch 1, batch 900, loss[loss=3.028, simple_loss=0.4134, pruned_loss=6.524, codebook_loss=28.22, over 7296.00 frames.], tot_loss[loss=3.213, simple_loss=0.4972, pruned_loss=6.595, codebook_loss=29.64, over 1402674.48 frames.], batch size: 17, lr: 2.98e-03
+2022-05-27 14:10:24,076 INFO [train.py:823] (1/4) Epoch 2, batch 0, loss[loss=2.994, simple_loss=0.418, pruned_loss=6.641, codebook_loss=27.85, over 7099.00 frames.], tot_loss[loss=2.994, simple_loss=0.418, pruned_loss=6.641, codebook_loss=27.85, over 7099.00 frames.], batch size: 19, lr: 2.95e-03
+2022-05-27 14:11:04,131 INFO [train.py:823] (1/4) Epoch 2, batch 50, loss[loss=3.065, simple_loss=0.4548, pruned_loss=6.579, codebook_loss=28.37, over 7378.00 frames.], tot_loss[loss=3.014, simple_loss=0.4344, pruned_loss=6.572, codebook_loss=27.97, over 323389.42 frames.], batch size: 21, lr: 2.95e-03
+2022-05-27 14:11:44,090 INFO [train.py:823] (1/4) Epoch 2, batch 100, loss[loss=2.947, simple_loss=0.4632, pruned_loss=6.681, codebook_loss=27.16, over 7017.00 frames.], tot_loss[loss=2.989, simple_loss=0.4271, pruned_loss=6.573, codebook_loss=27.76, over 565808.13 frames.], batch size: 26, lr: 2.95e-03
+2022-05-27 14:12:24,111 INFO [train.py:823] (1/4) Epoch 2, batch 150, loss[loss=3.071, simple_loss=0.4127, pruned_loss=6.391, codebook_loss=28.65, over 7302.00 frames.], tot_loss[loss=2.978, simple_loss=0.4258, pruned_loss=6.579, codebook_loss=27.65, over 758274.69 frames.], batch size: 17, lr: 2.94e-03
+2022-05-27 14:13:04,788 INFO [train.py:823] (1/4) Epoch 2, batch 200, loss[loss=2.951, simple_loss=0.3886, pruned_loss=6.542, codebook_loss=27.56, over 7101.00 frames.], tot_loss[loss=2.959, simple_loss=0.4212, pruned_loss=6.576, codebook_loss=27.49, over 906003.51 frames.], batch size: 18, lr: 2.94e-03
+2022-05-27 14:13:44,835 INFO [train.py:823] (1/4) Epoch 2, batch 250, loss[loss=2.994, simple_loss=0.3739, pruned_loss=6.52, codebook_loss=28.07, over 7157.00 frames.], tot_loss[loss=2.945, simple_loss=0.4172, pruned_loss=6.576, codebook_loss=27.36, over 1016735.29 frames.], batch size: 17, lr: 2.94e-03
+2022-05-27 14:14:25,466 INFO [train.py:823] (1/4) Epoch 2, batch 300, loss[loss=2.893, simple_loss=0.3728, pruned_loss=6.454, codebook_loss=27.06, over 7014.00 frames.], tot_loss[loss=2.933, simple_loss=0.4144, pruned_loss=6.582, codebook_loss=27.26, over 1107352.31 frames.], batch size: 16, lr: 2.93e-03
+2022-05-27 14:15:07,009 INFO [train.py:823] (1/4) Epoch 2, batch 350, loss[loss=2.814, simple_loss=0.4043, pruned_loss=6.581, codebook_loss=26.12, over 7158.00 frames.], tot_loss[loss=2.931, simple_loss=0.4142, pruned_loss=6.589, codebook_loss=27.24, over 1174985.96 frames.], batch size: 23, lr: 2.93e-03
+2022-05-27 14:15:51,504 INFO [train.py:823] (1/4) Epoch 2, batch 400, loss[loss=2.816, simple_loss=0.3841, pruned_loss=6.551, codebook_loss=26.24, over 7099.00 frames.], tot_loss[loss=2.922, simple_loss=0.4118, pruned_loss=6.583, codebook_loss=27.16, over 1225844.95 frames.], batch size: 18, lr: 2.93e-03
+2022-05-27 14:16:31,406 INFO [train.py:823] (1/4) Epoch 2, batch 450, loss[loss=2.764, simple_loss=0.3754, pruned_loss=6.594, codebook_loss=25.77, over 7294.00 frames.], tot_loss[loss=2.9, simple_loss=0.407, pruned_loss=6.584, codebook_loss=26.96, over 1265480.19 frames.], batch size: 21, lr: 2.92e-03
+2022-05-27 14:17:11,904 INFO [train.py:823] (1/4) Epoch 2, batch 500, loss[loss=2.806, simple_loss=0.3901, pruned_loss=6.56, codebook_loss=26.11, over 6986.00 frames.], tot_loss[loss=2.882, simple_loss=0.4042, pruned_loss=6.588, codebook_loss=26.8, over 1301602.75 frames.], batch size: 29, lr: 2.92e-03
+2022-05-27 14:17:51,826 INFO [train.py:823] (1/4) Epoch 2, batch 550, loss[loss=2.975, simple_loss=0.4427, pruned_loss=6.599, codebook_loss=27.54, over 4913.00 frames.], tot_loss[loss=2.875, simple_loss=0.4012, pruned_loss=6.585, codebook_loss=26.74, over 1323931.28 frames.], batch size: 46, lr: 2.92e-03
+2022-05-27 14:18:32,330 INFO [train.py:823] (1/4) Epoch 2, batch 600, loss[loss=2.836, simple_loss=0.4361, pruned_loss=6.692, codebook_loss=26.18, over 7279.00 frames.], tot_loss[loss=2.86, simple_loss=0.3979, pruned_loss=6.582, codebook_loss=26.62, over 1340833.71 frames.], batch size: 21, lr: 2.91e-03
+2022-05-27 14:19:12,446 INFO [train.py:823] (1/4) Epoch 2, batch 650, loss[loss=2.75, simple_loss=0.4196, pruned_loss=6.665, codebook_loss=25.41, over 7297.00 frames.], tot_loss[loss=2.85, simple_loss=0.3976, pruned_loss=6.591, codebook_loss=26.51, over 1358665.66 frames.], batch size: 22, lr: 2.91e-03
+2022-05-27 14:19:53,601 INFO [train.py:823] (1/4) Epoch 2, batch 700, loss[loss=2.81, simple_loss=0.362, pruned_loss=6.549, codebook_loss=26.29, over 7016.00 frames.], tot_loss[loss=2.835, simple_loss=0.3943, pruned_loss=6.597, codebook_loss=26.37, over 1373865.15 frames.], batch size: 17, lr: 2.90e-03
+2022-05-27 14:20:34,237 INFO [train.py:823] (1/4) Epoch 2, batch 750, loss[loss=2.88, simple_loss=0.4127, pruned_loss=6.711, codebook_loss=26.74, over 7112.00 frames.], tot_loss[loss=2.812, simple_loss=0.3901, pruned_loss=6.598, codebook_loss=26.17, over 1381256.23 frames.], batch size: 20, lr: 2.90e-03
+2022-05-27 14:21:14,871 INFO [train.py:823] (1/4) Epoch 2, batch 800, loss[loss=2.916, simple_loss=0.3908, pruned_loss=6.636, codebook_loss=27.2, over 5356.00 frames.], tot_loss[loss=2.816, simple_loss=0.3891, pruned_loss=6.6, codebook_loss=26.21, over 1387930.39 frames.], batch size: 48, lr: 2.89e-03
+2022-05-27 14:21:56,041 INFO [train.py:823] (1/4) Epoch 2, batch 850, loss[loss=2.776, simple_loss=0.3755, pruned_loss=6.563, codebook_loss=25.89, over 7194.00 frames.], tot_loss[loss=2.803, simple_loss=0.3863, pruned_loss=6.599, codebook_loss=26.1, over 1391896.02 frames.], batch size: 20, lr: 2.89e-03
+2022-05-27 14:22:36,205 INFO [train.py:823] (1/4) Epoch 2, batch 900, loss[loss=2.726, simple_loss=0.318, pruned_loss=6.49, codebook_loss=25.67, over 7298.00 frames.], tot_loss[loss=2.785, simple_loss=0.3834, pruned_loss=6.603, codebook_loss=25.94, over 1395660.60 frames.], batch size: 18, lr: 2.89e-03
+2022-05-27 14:23:30,853 INFO [train.py:823] (1/4) Epoch 3, batch 0, loss[loss=2.666, simple_loss=0.3435, pruned_loss=6.509, codebook_loss=24.95, over 7300.00 frames.], tot_loss[loss=2.666, simple_loss=0.3435, pruned_loss=6.509, codebook_loss=24.95, over 7300.00 frames.], batch size: 17, lr: 2.83e-03
+2022-05-27 14:24:11,242 INFO [train.py:823] (1/4) Epoch 3, batch 50, loss[loss=2.809, simple_loss=0.365, pruned_loss=6.494, codebook_loss=26.27, over 4837.00 frames.], tot_loss[loss=2.703, simple_loss=0.3623, pruned_loss=6.593, codebook_loss=25.22, over 319422.96 frames.], batch size: 46, lr: 2.82e-03
+2022-05-27 14:24:51,182 INFO [train.py:823] (1/4) Epoch 3, batch 100, loss[loss=2.694, simple_loss=0.3998, pruned_loss=6.657, codebook_loss=24.94, over 6907.00 frames.], tot_loss[loss=2.704, simple_loss=0.3613, pruned_loss=6.584, codebook_loss=25.23, over 565648.31 frames.], batch size: 26, lr: 2.82e-03
+2022-05-27 14:25:31,469 INFO [train.py:823] (1/4) Epoch 3, batch 150, loss[loss=2.692, simple_loss=0.4081, pruned_loss=6.625, codebook_loss=24.88, over 7375.00 frames.], tot_loss[loss=2.697, simple_loss=0.3613, pruned_loss=6.59, codebook_loss=25.17, over 756699.81 frames.], batch size: 20, lr: 2.81e-03
+2022-05-27 14:26:11,605 INFO [train.py:823] (1/4) Epoch 3, batch 200, loss[loss=2.725, simple_loss=0.3772, pruned_loss=6.525, codebook_loss=25.36, over 7103.00 frames.], tot_loss[loss=2.691, simple_loss=0.36, pruned_loss=6.594, codebook_loss=25.11, over 908234.17 frames.], batch size: 20, lr: 2.81e-03
+2022-05-27 14:26:51,969 INFO [train.py:823] (1/4) Epoch 3, batch 250, loss[loss=2.624, simple_loss=0.3694, pruned_loss=6.796, codebook_loss=24.4, over 6992.00 frames.], tot_loss[loss=2.682, simple_loss=0.3597, pruned_loss=6.607, codebook_loss=25.02, over 1026110.13 frames.], batch size: 26, lr: 2.80e-03
+2022-05-27 14:27:31,802 INFO [train.py:823] (1/4) Epoch 3, batch 300, loss[loss=2.536, simple_loss=0.3292, pruned_loss=6.587, codebook_loss=23.72, over 7387.00 frames.], tot_loss[loss=2.683, simple_loss=0.3611, pruned_loss=6.621, codebook_loss=25.02, over 1115753.93 frames.], batch size: 19, lr: 2.80e-03
+2022-05-27 14:28:12,715 INFO [train.py:823] (1/4) Epoch 3, batch 350, loss[loss=2.677, simple_loss=0.3692, pruned_loss=6.595, codebook_loss=24.92, over 7340.00 frames.], tot_loss[loss=2.688, simple_loss=0.3586, pruned_loss=6.618, codebook_loss=25.09, over 1186118.55 frames.], batch size: 23, lr: 2.79e-03
+2022-05-27 14:28:52,454 INFO [train.py:823] (1/4) Epoch 3, batch 400, loss[loss=2.606, simple_loss=0.3234, pruned_loss=6.452, codebook_loss=24.45, over 7296.00 frames.], tot_loss[loss=2.69, simple_loss=0.3602, pruned_loss=6.614, codebook_loss=25.1, over 1240273.39 frames.], batch size: 18, lr: 2.79e-03
+2022-05-27 14:29:32,963 INFO [train.py:823] (1/4) Epoch 3, batch 450, loss[loss=2.594, simple_loss=0.3522, pruned_loss=6.634, codebook_loss=24.18, over 7171.00 frames.], tot_loss[loss=2.69, simple_loss=0.3598, pruned_loss=6.616, codebook_loss=25.1, over 1274525.16 frames.], batch size: 18, lr: 2.78e-03
+2022-05-27 14:30:12,769 INFO [train.py:823] (1/4) Epoch 3, batch 500, loss[loss=2.739, simple_loss=0.3107, pruned_loss=6.555, codebook_loss=25.84, over 7306.00 frames.], tot_loss[loss=2.694, simple_loss=0.3592, pruned_loss=6.618, codebook_loss=25.15, over 1306195.70 frames.], batch size: 18, lr: 2.77e-03
+2022-05-27 14:30:52,967 INFO [train.py:823] (1/4) Epoch 3, batch 550, loss[loss=2.68, simple_loss=0.3737, pruned_loss=6.591, codebook_loss=24.94, over 7184.00 frames.], tot_loss[loss=2.684, simple_loss=0.359, pruned_loss=6.623, codebook_loss=25.05, over 1334718.00 frames.], batch size: 21, lr: 2.77e-03
+2022-05-27 14:31:32,956 INFO [train.py:823] (1/4) Epoch 3, batch 600, loss[loss=2.62, simple_loss=0.3343, pruned_loss=6.587, codebook_loss=24.52, over 7372.00 frames.], tot_loss[loss=2.68, simple_loss=0.3566, pruned_loss=6.625, codebook_loss=25.02, over 1346881.30 frames.], batch size: 20, lr: 2.76e-03
+2022-05-27 14:32:13,207 INFO [train.py:823] (1/4) Epoch 3, batch 650, loss[loss=2.65, simple_loss=0.3551, pruned_loss=6.624, codebook_loss=24.72, over 4644.00 frames.], tot_loss[loss=2.667, simple_loss=0.3546, pruned_loss=6.629, codebook_loss=24.9, over 1363237.93 frames.], batch size: 46, lr: 2.76e-03
+2022-05-27 14:32:52,989 INFO [train.py:823] (1/4) Epoch 3, batch 700, loss[loss=2.548, simple_loss=0.345, pruned_loss=6.649, codebook_loss=23.75, over 7300.00 frames.], tot_loss[loss=2.657, simple_loss=0.352, pruned_loss=6.621, codebook_loss=24.81, over 1375769.14 frames.], batch size: 22, lr: 2.75e-03
+2022-05-27 14:33:33,463 INFO [train.py:823] (1/4) Epoch 3, batch 750, loss[loss=2.572, simple_loss=0.3279, pruned_loss=6.521, codebook_loss=24.08, over 7183.00 frames.], tot_loss[loss=2.647, simple_loss=0.3506, pruned_loss=6.622, codebook_loss=24.72, over 1384075.79 frames.], batch size: 19, lr: 2.75e-03
+2022-05-27 14:34:13,284 INFO [train.py:823] (1/4) Epoch 3, batch 800, loss[loss=2.679, simple_loss=0.3799, pruned_loss=6.704, codebook_loss=24.89, over 7411.00 frames.], tot_loss[loss=2.644, simple_loss=0.3518, pruned_loss=6.628, codebook_loss=24.68, over 1393907.42 frames.], batch size: 22, lr: 2.74e-03
+2022-05-27 14:34:53,235 INFO [train.py:823] (1/4) Epoch 3, batch 850, loss[loss=2.519, simple_loss=0.3268, pruned_loss=6.637, codebook_loss=23.55, over 7090.00 frames.], tot_loss[loss=2.647, simple_loss=0.3519, pruned_loss=6.631, codebook_loss=24.71, over 1396140.92 frames.], batch size: 19, lr: 2.74e-03
+2022-05-27 14:35:32,632 INFO [train.py:823] (1/4) Epoch 3, batch 900, loss[loss=2.708, simple_loss=0.3856, pruned_loss=6.731, codebook_loss=25.15, over 5196.00 frames.], tot_loss[loss=2.647, simple_loss=0.3522, pruned_loss=6.635, codebook_loss=24.71, over 1392933.01 frames.], batch size: 47, lr: 2.73e-03
+2022-05-27 14:36:26,056 INFO [train.py:823] (1/4) Epoch 4, batch 0, loss[loss=2.575, simple_loss=0.3444, pruned_loss=6.57, codebook_loss=24.03, over 7092.00 frames.], tot_loss[loss=2.575, simple_loss=0.3444, pruned_loss=6.57, codebook_loss=24.03, over 7092.00 frames.], batch size: 19, lr: 2.64e-03
+2022-05-27 14:37:06,183 INFO [train.py:823] (1/4) Epoch 4, batch 50, loss[loss=2.563, simple_loss=0.3261, pruned_loss=6.486, codebook_loss=23.99, over 7027.00 frames.], tot_loss[loss=2.559, simple_loss=0.3286, pruned_loss=6.613, codebook_loss=23.95, over 319529.39 frames.], batch size: 17, lr: 2.64e-03
+2022-05-27 14:37:46,124 INFO [train.py:823] (1/4) Epoch 4, batch 100, loss[loss=2.582, simple_loss=0.3487, pruned_loss=6.723, codebook_loss=24.07, over 7372.00 frames.], tot_loss[loss=2.565, simple_loss=0.3324, pruned_loss=6.636, codebook_loss=23.99, over 564665.90 frames.], batch size: 21, lr: 2.63e-03
+2022-05-27 14:38:25,732 INFO [train.py:823] (1/4) Epoch 4, batch 150, loss[loss=2.524, simple_loss=0.3105, pruned_loss=6.451, codebook_loss=23.69, over 7153.00 frames.], tot_loss[loss=2.58, simple_loss=0.3346, pruned_loss=6.639, codebook_loss=24.12, over 750479.63 frames.], batch size: 17, lr: 2.63e-03
+2022-05-27 14:39:07,321 INFO [train.py:823] (1/4) Epoch 4, batch 200, loss[loss=2.615, simple_loss=0.3279, pruned_loss=0.9885, codebook_loss=23.52, over 7184.00 frames.], tot_loss[loss=2.664, simple_loss=0.3456, pruned_loss=4.812, codebook_loss=24.03, over 902771.36 frames.], batch size: 18, lr: 2.62e-03
+2022-05-27 14:39:46,948 INFO [train.py:823] (1/4) Epoch 4, batch 250, loss[loss=2.829, simple_loss=0.3622, pruned_loss=0.6943, codebook_loss=25.79, over 7387.00 frames.], tot_loss[loss=2.666, simple_loss=0.3427, pruned_loss=3.571, codebook_loss=24.08, over 1021436.50 frames.], batch size: 21, lr: 2.62e-03
+2022-05-27 14:40:29,644 INFO [train.py:823] (1/4) Epoch 4, batch 300, loss[loss=2.653, simple_loss=0.3655, pruned_loss=0.4583, codebook_loss=24.24, over 7203.00 frames.], tot_loss[loss=2.653, simple_loss=0.3422, pruned_loss=2.711, codebook_loss=24.05, over 1106555.74 frames.], batch size: 20, lr: 2.61e-03
+2022-05-27 14:41:09,207 INFO [train.py:823] (1/4) Epoch 4, batch 350, loss[loss=2.656, simple_loss=0.3803, pruned_loss=0.3442, codebook_loss=24.32, over 7142.00 frames.], tot_loss[loss=2.636, simple_loss=0.3414, pruned_loss=2.081, codebook_loss=23.99, over 1172353.05 frames.], batch size: 23, lr: 2.60e-03
+2022-05-27 14:41:49,186 INFO [train.py:823] (1/4) Epoch 4, batch 400, loss[loss=2.521, simple_loss=0.3224, pruned_loss=0.2062, codebook_loss=23.39, over 7243.00 frames.], tot_loss[loss=2.622, simple_loss=0.3385, pruned_loss=1.61, codebook_loss=23.97, over 1226221.68 frames.], batch size: 25, lr: 2.60e-03
+2022-05-27 14:42:28,861 INFO [train.py:823] (1/4) Epoch 4, batch 450, loss[loss=2.509, simple_loss=0.2935, pruned_loss=0.1607, codebook_loss=23.47, over 7162.00 frames.], tot_loss[loss=2.609, simple_loss=0.338, pruned_loss=1.264, codebook_loss=23.94, over 1268363.43 frames.], batch size: 17, lr: 2.59e-03
+2022-05-27 14:43:08,818 INFO [train.py:823] (1/4) Epoch 4, batch 500, loss[loss=2.582, simple_loss=0.3642, pruned_loss=0.2037, codebook_loss=23.8, over 7215.00 frames.], tot_loss[loss=2.599, simple_loss=0.3389, pruned_loss=1.004, codebook_loss=23.9, over 1305192.78 frames.], batch size: 25, lr: 2.59e-03
+2022-05-27 14:43:48,400 INFO [train.py:823] (1/4) Epoch 4, batch 550, loss[loss=2.6, simple_loss=0.3356, pruned_loss=0.1645, codebook_loss=24.16, over 7391.00 frames.], tot_loss[loss=2.589, simple_loss=0.337, pruned_loss=0.8061, codebook_loss=23.86, over 1332012.35 frames.], batch size: 19, lr: 2.58e-03
+2022-05-27 14:44:28,576 INFO [train.py:823] (1/4) Epoch 4, batch 600, loss[loss=2.541, simple_loss=0.3612, pruned_loss=0.1839, codebook_loss=23.42, over 7199.00 frames.], tot_loss[loss=2.573, simple_loss=0.3351, pruned_loss=0.6537, codebook_loss=23.75, over 1353997.24 frames.], batch size: 21, lr: 2.57e-03
+2022-05-27 14:45:08,637 INFO [train.py:823] (1/4) Epoch 4, batch 650, loss[loss=2.407, simple_loss=0.3002, pruned_loss=0.1121, codebook_loss=22.46, over 7369.00 frames.], tot_loss[loss=2.562, simple_loss=0.3337, pruned_loss=0.5384, codebook_loss=23.68, over 1370274.31 frames.], batch size: 20, lr: 2.57e-03
+2022-05-27 14:45:48,453 INFO [train.py:823] (1/4) Epoch 4, batch 700, loss[loss=2.652, simple_loss=0.341, pruned_loss=0.1605, codebook_loss=24.65, over 5010.00 frames.], tot_loss[loss=2.568, simple_loss=0.3355, pruned_loss=0.4532, codebook_loss=23.76, over 1376822.69 frames.], batch size: 47, lr: 2.56e-03
+2022-05-27 14:46:28,115 INFO [train.py:823] (1/4) Epoch 4, batch 750, loss[loss=2.399, simple_loss=0.3203, pruned_loss=0.1112, codebook_loss=22.28, over 7099.00 frames.], tot_loss[loss=2.575, simple_loss=0.3353, pruned_loss=0.3855, codebook_loss=23.85, over 1384770.05 frames.], batch size: 19, lr: 2.56e-03
+2022-05-27 14:47:08,130 INFO [train.py:823] (1/4) Epoch 4, batch 800, loss[loss=2.435, simple_loss=0.2763, pruned_loss=0.09351, codebook_loss=22.87, over 7016.00 frames.], tot_loss[loss=2.572, simple_loss=0.3355, pruned_loss=0.3335, codebook_loss=23.83, over 1387450.17 frames.], batch size: 17, lr: 2.55e-03
+2022-05-27 14:47:47,725 INFO [train.py:823] (1/4) Epoch 4, batch 850, loss[loss=2.546, simple_loss=0.3344, pruned_loss=0.1382, codebook_loss=23.65, over 7313.00 frames.], tot_loss[loss=2.571, simple_loss=0.3347, pruned_loss=0.2908, codebook_loss=23.84, over 1392701.21 frames.], batch size: 22, lr: 2.54e-03
+2022-05-27 14:48:27,887 INFO [train.py:823] (1/4) Epoch 4, batch 900, loss[loss=2.51, simple_loss=0.3008, pruned_loss=0.1141, codebook_loss=23.48, over 7185.00 frames.], tot_loss[loss=2.566, simple_loss=0.3324, pruned_loss=0.2569, codebook_loss=23.82, over 1389384.97 frames.], batch size: 18, lr: 2.54e-03
+2022-05-27 14:49:21,905 INFO [train.py:823] (1/4) Epoch 5, batch 0, loss[loss=2.426, simple_loss=0.3294, pruned_loss=0.1211, codebook_loss=22.49, over 7335.00 frames.], tot_loss[loss=2.426, simple_loss=0.3294, pruned_loss=0.1211, codebook_loss=22.49, over 7335.00 frames.], batch size: 23, lr: 2.44e-03
+2022-05-27 14:50:02,122 INFO [train.py:823] (1/4) Epoch 5, batch 50, loss[loss=2.415, simple_loss=0.328, pruned_loss=0.1189, codebook_loss=22.39, over 6961.00 frames.], tot_loss[loss=2.507, simple_loss=0.3199, pruned_loss=0.1264, codebook_loss=23.35, over 325626.83 frames.], batch size: 26, lr: 2.44e-03
+2022-05-27 14:50:41,829 INFO [train.py:823] (1/4) Epoch 5, batch 100, loss[loss=2.414, simple_loss=0.3047, pruned_loss=0.1067, codebook_loss=22.51, over 7111.00 frames.], tot_loss[loss=2.502, simple_loss=0.3188, pruned_loss=0.1226, codebook_loss=23.3, over 569619.04 frames.], batch size: 20, lr: 2.43e-03
+2022-05-27 14:51:21,914 INFO [train.py:823] (1/4) Epoch 5, batch 150, loss[loss=2.364, simple_loss=0.3008, pruned_loss=0.08957, codebook_loss=22.05, over 7382.00 frames.], tot_loss[loss=2.518, simple_loss=0.3186, pruned_loss=0.1234, codebook_loss=23.47, over 757758.11 frames.], batch size: 20, lr: 2.42e-03
+2022-05-27 14:52:01,338 INFO [train.py:823] (1/4) Epoch 5, batch 200, loss[loss=2.41, simple_loss=0.3303, pruned_loss=0.1012, codebook_loss=22.35, over 7160.00 frames.], tot_loss[loss=2.521, simple_loss=0.3209, pruned_loss=0.125, codebook_loss=23.48, over 904625.75 frames.], batch size: 22, lr: 2.42e-03
+2022-05-27 14:52:41,376 INFO [train.py:823] (1/4) Epoch 5, batch 250, loss[loss=2.48, simple_loss=0.342, pruned_loss=0.1358, codebook_loss=22.95, over 4967.00 frames.], tot_loss[loss=2.52, simple_loss=0.3214, pruned_loss=0.1255, codebook_loss=23.46, over 1015069.83 frames.], batch size: 48, lr: 2.41e-03
+2022-05-27 14:53:20,953 INFO [train.py:823] (1/4) Epoch 5, batch 300, loss[loss=2.575, simple_loss=0.3586, pruned_loss=0.1569, codebook_loss=23.8, over 7161.00 frames.], tot_loss[loss=2.509, simple_loss=0.3217, pruned_loss=0.1238, codebook_loss=23.36, over 1105470.83 frames.], batch size: 23, lr: 2.41e-03
+2022-05-27 14:54:00,919 INFO [train.py:823] (1/4) Epoch 5, batch 350, loss[loss=2.511, simple_loss=0.3474, pruned_loss=0.1284, codebook_loss=23.24, over 7221.00 frames.], tot_loss[loss=2.508, simple_loss=0.3221, pruned_loss=0.1234, codebook_loss=23.34, over 1176011.27 frames.], batch size: 24, lr: 2.40e-03
+2022-05-27 14:54:40,904 INFO [train.py:823] (1/4) Epoch 5, batch 400, loss[loss=2.611, simple_loss=0.3285, pruned_loss=0.1349, codebook_loss=24.33, over 7021.00 frames.], tot_loss[loss=2.502, simple_loss=0.3211, pruned_loss=0.1211, codebook_loss=23.29, over 1235303.93 frames.], batch size: 17, lr: 2.39e-03
+2022-05-27 14:55:20,833 INFO [train.py:823] (1/4) Epoch 5, batch 450, loss[loss=2.418, simple_loss=0.3137, pruned_loss=0.1081, codebook_loss=22.51, over 7046.00 frames.], tot_loss[loss=2.495, simple_loss=0.3207, pruned_loss=0.1196, codebook_loss=23.23, over 1270798.89 frames.], batch size: 26, lr: 2.39e-03
+2022-05-27 14:56:00,549 INFO [train.py:823] (1/4) Epoch 5, batch 500, loss[loss=2.514, simple_loss=0.3109, pruned_loss=0.12, codebook_loss=23.47, over 7187.00 frames.], tot_loss[loss=2.492, simple_loss=0.3195, pruned_loss=0.1181, codebook_loss=23.2, over 1305775.70 frames.], batch size: 19, lr: 2.38e-03
+2022-05-27 14:56:40,383 INFO [train.py:823] (1/4) Epoch 5, batch 550, loss[loss=2.538, simple_loss=0.3227, pruned_loss=0.1271, codebook_loss=23.64, over 6936.00 frames.], tot_loss[loss=2.488, simple_loss=0.3193, pruned_loss=0.1176, codebook_loss=23.17, over 1331825.69 frames.], batch size: 29, lr: 2.38e-03
+2022-05-27 14:57:20,189 INFO [train.py:823] (1/4) Epoch 5, batch 600, loss[loss=2.481, simple_loss=0.3213, pruned_loss=0.1153, codebook_loss=23.08, over 6555.00 frames.], tot_loss[loss=2.484, simple_loss=0.318, pruned_loss=0.1157, codebook_loss=23.14, over 1350295.07 frames.], batch size: 34, lr: 2.37e-03
+2022-05-27 14:58:00,316 INFO [train.py:823] (1/4) Epoch 5, batch 650, loss[loss=2.411, simple_loss=0.3358, pruned_loss=0.09884, codebook_loss=22.33, over 7285.00 frames.], tot_loss[loss=2.482, simple_loss=0.3171, pruned_loss=0.1141, codebook_loss=23.12, over 1365083.46 frames.], batch size: 21, lr: 2.37e-03
+2022-05-27 14:58:39,920 INFO [train.py:823] (1/4) Epoch 5, batch 700, loss[loss=2.482, simple_loss=0.3537, pruned_loss=0.143, codebook_loss=22.91, over 7065.00 frames.], tot_loss[loss=2.478, simple_loss=0.317, pruned_loss=0.1134, codebook_loss=23.08, over 1374133.98 frames.], batch size: 26, lr: 2.36e-03
+2022-05-27 14:59:19,728 INFO [train.py:823] (1/4) Epoch 5, batch 750, loss[loss=2.545, simple_loss=0.3641, pruned_loss=0.1473, codebook_loss=23.49, over 7157.00 frames.], tot_loss[loss=2.478, simple_loss=0.3175, pruned_loss=0.1134, codebook_loss=23.08, over 1382399.55 frames.], batch size: 23, lr: 2.35e-03
+2022-05-27 14:59:59,643 INFO [train.py:823] (1/4) Epoch 5, batch 800, loss[loss=2.525, simple_loss=0.338, pruned_loss=0.1381, codebook_loss=23.42, over 5086.00 frames.], tot_loss[loss=2.475, simple_loss=0.3173, pruned_loss=0.1127, codebook_loss=23.06, over 1392287.98 frames.], batch size: 47, lr: 2.35e-03
+2022-05-27 15:00:39,937 INFO [train.py:823] (1/4) Epoch 5, batch 850, loss[loss=2.408, simple_loss=0.2955, pruned_loss=0.1057, codebook_loss=22.5, over 7155.00 frames.], tot_loss[loss=2.469, simple_loss=0.3159, pruned_loss=0.1111, codebook_loss=23, over 1398749.11 frames.], batch size: 17, lr: 2.34e-03
+2022-05-27 15:01:19,753 INFO [train.py:823] (1/4) Epoch 5, batch 900, loss[loss=2.541, simple_loss=0.3454, pruned_loss=0.1243, codebook_loss=23.56, over 6903.00 frames.], tot_loss[loss=2.466, simple_loss=0.3163, pruned_loss=0.1106, codebook_loss=22.96, over 1400731.75 frames.], batch size: 29, lr: 2.34e-03
+2022-05-27 15:02:14,644 INFO [train.py:823] (1/4) Epoch 6, batch 0, loss[loss=2.501, simple_loss=0.3241, pruned_loss=0.09977, codebook_loss=23.29, over 7165.00 frames.], tot_loss[loss=2.501, simple_loss=0.3241, pruned_loss=0.09977, codebook_loss=23.29, over 7165.00 frames.], batch size: 22, lr: 2.24e-03
+2022-05-27 15:02:54,285 INFO [train.py:823] (1/4) Epoch 6, batch 50, loss[loss=2.405, simple_loss=0.3003, pruned_loss=0.08718, codebook_loss=22.46, over 7185.00 frames.], tot_loss[loss=2.427, simple_loss=0.3103, pruned_loss=0.0983, codebook_loss=22.62, over 318919.82 frames.], batch size: 21, lr: 2.23e-03
+2022-05-27 15:03:34,992 INFO [train.py:823] (1/4) Epoch 6, batch 100, loss[loss=2.417, simple_loss=0.3153, pruned_loss=0.112, codebook_loss=22.48, over 7222.00 frames.], tot_loss[loss=2.425, simple_loss=0.3044, pruned_loss=0.09745, codebook_loss=22.63, over 565330.45 frames.], batch size: 24, lr: 2.23e-03
+2022-05-27 15:04:14,715 INFO [train.py:823] (1/4) Epoch 6, batch 150, loss[loss=2.35, simple_loss=0.3143, pruned_loss=0.08681, codebook_loss=21.84, over 7304.00 frames.], tot_loss[loss=2.423, simple_loss=0.305, pruned_loss=0.0965, codebook_loss=22.61, over 754702.04 frames.], batch size: 19, lr: 2.22e-03
+2022-05-27 15:04:56,278 INFO [train.py:823] (1/4) Epoch 6, batch 200, loss[loss=2.432, simple_loss=0.3239, pruned_loss=0.08875, codebook_loss=22.61, over 7218.00 frames.], tot_loss[loss=2.422, simple_loss=0.3045, pruned_loss=0.09588, codebook_loss=22.61, over 901014.07 frames.], batch size: 25, lr: 2.22e-03
+2022-05-27 15:05:38,505 INFO [train.py:823] (1/4) Epoch 6, batch 250, loss[loss=2.585, simple_loss=0.3348, pruned_loss=0.1053, codebook_loss=24.07, over 6537.00 frames.], tot_loss[loss=2.429, simple_loss=0.3067, pruned_loss=0.0977, codebook_loss=22.65, over 1017789.25 frames.], batch size: 34, lr: 2.21e-03
+2022-05-27 15:06:18,613 INFO [train.py:823] (1/4) Epoch 6, batch 300, loss[loss=2.323, simple_loss=0.3157, pruned_loss=0.08923, codebook_loss=21.56, over 7200.00 frames.], tot_loss[loss=2.429, simple_loss=0.3077, pruned_loss=0.09817, codebook_loss=22.65, over 1108051.09 frames.], batch size: 20, lr: 2.21e-03
+2022-05-27 15:06:58,771 INFO [train.py:823] (1/4) Epoch 6, batch 350, loss[loss=2.371, simple_loss=0.2926, pruned_loss=0.08265, codebook_loss=22.16, over 7098.00 frames.], tot_loss[loss=2.427, simple_loss=0.3071, pruned_loss=0.09751, codebook_loss=22.64, over 1178763.25 frames.], batch size: 18, lr: 2.20e-03
+2022-05-27 15:07:39,162 INFO [train.py:823] (1/4) Epoch 6, batch 400, loss[loss=2.398, simple_loss=0.3143, pruned_loss=0.1017, codebook_loss=22.3, over 7162.00 frames.], tot_loss[loss=2.421, simple_loss=0.3059, pruned_loss=0.09696, codebook_loss=22.59, over 1234845.68 frames.], batch size: 22, lr: 2.19e-03
+2022-05-27 15:08:18,990 INFO [train.py:823] (1/4) Epoch 6, batch 450, loss[loss=2.432, simple_loss=0.307, pruned_loss=0.1055, codebook_loss=22.68, over 6635.00 frames.], tot_loss[loss=2.426, simple_loss=0.3071, pruned_loss=0.09821, codebook_loss=22.63, over 1267394.92 frames.], batch size: 34, lr: 2.19e-03
+2022-05-27 15:08:59,154 INFO [train.py:823] (1/4) Epoch 6, batch 500, loss[loss=2.407, simple_loss=0.3084, pruned_loss=0.0889, codebook_loss=22.44, over 7141.00 frames.], tot_loss[loss=2.436, simple_loss=0.309, pruned_loss=0.1, codebook_loss=22.72, over 1298316.14 frames.], batch size: 23, lr: 2.18e-03
+2022-05-27 15:09:39,062 INFO [train.py:823] (1/4) Epoch 6, batch 550, loss[loss=2.365, simple_loss=0.2935, pruned_loss=0.08168, codebook_loss=22.1, over 7094.00 frames.], tot_loss[loss=2.433, simple_loss=0.3079, pruned_loss=0.0988, codebook_loss=22.69, over 1325257.90 frames.], batch size: 18, lr: 2.18e-03
+2022-05-27 15:10:19,158 INFO [train.py:823] (1/4) Epoch 6, batch 600, loss[loss=2.366, simple_loss=0.2797, pruned_loss=0.0767, codebook_loss=22.18, over 7089.00 frames.], tot_loss[loss=2.435, simple_loss=0.3079, pruned_loss=0.09877, codebook_loss=22.71, over 1342109.40 frames.], batch size: 18, lr: 2.17e-03
+2022-05-27 15:10:58,947 INFO [train.py:823] (1/4) Epoch 6, batch 650, loss[loss=2.45, simple_loss=0.2885, pruned_loss=0.1019, codebook_loss=22.95, over 7390.00 frames.], tot_loss[loss=2.432, simple_loss=0.3059, pruned_loss=0.09698, codebook_loss=22.7, over 1359505.02 frames.], batch size: 19, lr: 2.17e-03
+2022-05-27 15:11:39,183 INFO [train.py:823] (1/4) Epoch 6, batch 700, loss[loss=2.344, simple_loss=0.2927, pruned_loss=0.08686, codebook_loss=21.89, over 7200.00 frames.], tot_loss[loss=2.427, simple_loss=0.3058, pruned_loss=0.0964, codebook_loss=22.64, over 1375017.51 frames.], batch size: 19, lr: 2.16e-03
+2022-05-27 15:12:18,880 INFO [train.py:823] (1/4) Epoch 6, batch 750, loss[loss=2.37, simple_loss=0.3074, pruned_loss=0.09433, codebook_loss=22.07, over 7104.00 frames.], tot_loss[loss=2.431, simple_loss=0.3066, pruned_loss=0.09674, codebook_loss=22.68, over 1383298.74 frames.], batch size: 19, lr: 2.16e-03
+2022-05-27 15:12:59,165 INFO [train.py:823] (1/4) Epoch 6, batch 800, loss[loss=2.407, simple_loss=0.2652, pruned_loss=0.07185, codebook_loss=22.67, over 7005.00 frames.], tot_loss[loss=2.426, simple_loss=0.3054, pruned_loss=0.09594, codebook_loss=22.63, over 1389827.27 frames.], batch size: 16, lr: 2.15e-03
+2022-05-27 15:13:39,112 INFO [train.py:823] (1/4) Epoch 6, batch 850, loss[loss=2.451, simple_loss=0.2904, pruned_loss=0.09819, codebook_loss=22.96, over 6843.00 frames.], tot_loss[loss=2.436, simple_loss=0.3063, pruned_loss=0.09708, codebook_loss=22.73, over 1394314.10 frames.], batch size: 15, lr: 2.15e-03
+2022-05-27 15:14:19,233 INFO [train.py:823] (1/4) Epoch 6, batch 900, loss[loss=2.324, simple_loss=0.2675, pruned_loss=0.0777, codebook_loss=21.83, over 7273.00 frames.], tot_loss[loss=2.428, simple_loss=0.3038, pruned_loss=0.09482, codebook_loss=22.67, over 1397659.99 frames.], batch size: 17, lr: 2.14e-03
+2022-05-27 15:15:12,728 INFO [train.py:823] (1/4) Epoch 7, batch 0, loss[loss=2.338, simple_loss=0.295, pruned_loss=0.06814, codebook_loss=21.83, over 7100.00 frames.], tot_loss[loss=2.338, simple_loss=0.295, pruned_loss=0.06814, codebook_loss=21.83, over 7100.00 frames.], batch size: 19, lr: 2.05e-03
+2022-05-27 15:15:52,754 INFO [train.py:823] (1/4) Epoch 7, batch 50, loss[loss=2.341, simple_loss=0.2566, pruned_loss=0.07386, codebook_loss=22.05, over 6807.00 frames.], tot_loss[loss=2.39, simple_loss=0.2953, pruned_loss=0.08476, codebook_loss=22.34, over 322424.66 frames.], batch size: 15, lr: 2.04e-03
+2022-05-27 15:16:32,359 INFO [train.py:823] (1/4) Epoch 7, batch 100, loss[loss=2.385, simple_loss=0.3043, pruned_loss=0.08026, codebook_loss=22.24, over 7105.00 frames.], tot_loss[loss=2.378, simple_loss=0.2939, pruned_loss=0.08407, codebook_loss=22.22, over 561746.28 frames.], batch size: 20, lr: 2.04e-03
+2022-05-27 15:17:12,515 INFO [train.py:823] (1/4) Epoch 7, batch 150, loss[loss=2.425, simple_loss=0.3187, pruned_loss=0.09151, codebook_loss=22.57, over 7382.00 frames.], tot_loss[loss=2.387, simple_loss=0.2969, pruned_loss=0.0872, codebook_loss=22.29, over 752360.69 frames.], batch size: 21, lr: 2.03e-03
+2022-05-27 15:17:52,337 INFO [train.py:823] (1/4) Epoch 7, batch 200, loss[loss=2.52, simple_loss=0.3149, pruned_loss=0.08748, codebook_loss=23.54, over 7017.00 frames.], tot_loss[loss=2.39, simple_loss=0.2977, pruned_loss=0.08801, codebook_loss=22.32, over 903308.78 frames.], batch size: 26, lr: 2.03e-03
+2022-05-27 15:18:32,533 INFO [train.py:823] (1/4) Epoch 7, batch 250, loss[loss=2.559, simple_loss=0.3168, pruned_loss=0.1005, codebook_loss=23.9, over 7312.00 frames.], tot_loss[loss=2.382, simple_loss=0.2969, pruned_loss=0.08682, codebook_loss=22.25, over 1018543.96 frames.], batch size: 22, lr: 2.02e-03
+2022-05-27 15:19:12,262 INFO [train.py:823] (1/4) Epoch 7, batch 300, loss[loss=2.323, simple_loss=0.2576, pruned_loss=0.07265, codebook_loss=21.87, over 7166.00 frames.], tot_loss[loss=2.381, simple_loss=0.2964, pruned_loss=0.08652, codebook_loss=22.24, over 1108530.68 frames.], batch size: 17, lr: 2.02e-03
+2022-05-27 15:19:52,560 INFO [train.py:823] (1/4) Epoch 7, batch 350, loss[loss=2.467, simple_loss=0.2961, pruned_loss=0.09087, codebook_loss=22.28, over 7290.00 frames.], tot_loss[loss=2.418, simple_loss=0.2986, pruned_loss=0.09013, codebook_loss=22.36, over 1175711.06 frames.], batch size: 19, lr: 2.01e-03
+2022-05-27 15:20:32,257 INFO [train.py:823] (1/4) Epoch 7, batch 400, loss[loss=2.442, simple_loss=0.3314, pruned_loss=0.1061, codebook_loss=21.7, over 7325.00 frames.], tot_loss[loss=2.443, simple_loss=0.3016, pruned_loss=0.09275, codebook_loss=22.42, over 1230234.90 frames.], batch size: 23, lr: 2.01e-03
+2022-05-27 15:21:12,300 INFO [train.py:823] (1/4) Epoch 7, batch 450, loss[loss=2.501, simple_loss=0.3253, pruned_loss=0.1106, codebook_loss=22.27, over 7166.00 frames.], tot_loss[loss=2.45, simple_loss=0.3038, pruned_loss=0.09283, codebook_loss=22.38, over 1267365.47 frames.], batch size: 22, lr: 2.00e-03
+2022-05-27 15:21:52,027 INFO [train.py:823] (1/4) Epoch 7, batch 500, loss[loss=2.83, simple_loss=0.3456, pruned_loss=0.1158, codebook_loss=25.42, over 7015.00 frames.], tot_loss[loss=2.461, simple_loss=0.3048, pruned_loss=0.09223, codebook_loss=22.41, over 1301271.62 frames.], batch size: 26, lr: 2.00e-03
+2022-05-27 15:22:32,326 INFO [train.py:823] (1/4) Epoch 7, batch 550, loss[loss=2.364, simple_loss=0.2914, pruned_loss=0.07677, codebook_loss=21.42, over 6636.00 frames.], tot_loss[loss=2.466, simple_loss=0.3044, pruned_loss=0.09151, codebook_loss=22.41, over 1325389.80 frames.], batch size: 34, lr: 1.99e-03
+2022-05-27 15:23:12,062 INFO [train.py:823] (1/4) Epoch 7, batch 600, loss[loss=2.523, simple_loss=0.3321, pruned_loss=0.1058, codebook_loss=22.52, over 7380.00 frames.], tot_loss[loss=2.477, simple_loss=0.3047, pruned_loss=0.09104, codebook_loss=22.47, over 1343608.29 frames.], batch size: 21, lr: 1.99e-03
+2022-05-27 15:23:52,222 INFO [train.py:823] (1/4) Epoch 7, batch 650, loss[loss=2.444, simple_loss=0.2978, pruned_loss=0.07427, codebook_loss=22.21, over 7116.00 frames.], tot_loss[loss=2.475, simple_loss=0.3035, pruned_loss=0.08939, codebook_loss=22.44, over 1360885.87 frames.], batch size: 20, lr: 1.98e-03
+2022-05-27 15:24:32,097 INFO [train.py:823] (1/4) Epoch 7, batch 700, loss[loss=2.451, simple_loss=0.2762, pruned_loss=0.07406, codebook_loss=22.39, over 7089.00 frames.], tot_loss[loss=2.475, simple_loss=0.3041, pruned_loss=0.08923, codebook_loss=22.42, over 1368891.81 frames.], batch size: 18, lr: 1.98e-03
+2022-05-27 15:25:12,128 INFO [train.py:823] (1/4) Epoch 7, batch 750, loss[loss=2.478, simple_loss=0.3259, pruned_loss=0.09855, codebook_loss=22.16, over 6995.00 frames.], tot_loss[loss=2.475, simple_loss=0.3029, pruned_loss=0.08851, codebook_loss=22.42, over 1377925.63 frames.], batch size: 26, lr: 1.97e-03
+2022-05-27 15:25:51,517 INFO [train.py:823] (1/4) Epoch 7, batch 800, loss[loss=2.451, simple_loss=0.3087, pruned_loss=0.09098, codebook_loss=22.06, over 7193.00 frames.], tot_loss[loss=2.471, simple_loss=0.3033, pruned_loss=0.08751, codebook_loss=22.37, over 1387839.17 frames.], batch size: 19, lr: 1.97e-03
+2022-05-27 15:26:31,115 INFO [train.py:823] (1/4) Epoch 7, batch 850, loss[loss=2.378, simple_loss=0.2981, pruned_loss=0.08019, codebook_loss=21.49, over 7382.00 frames.], tot_loss[loss=2.474, simple_loss=0.3045, pruned_loss=0.08787, codebook_loss=22.38, over 1388669.07 frames.], batch size: 21, lr: 1.97e-03
+2022-05-27 15:27:11,916 INFO [train.py:823] (1/4) Epoch 7, batch 900, loss[loss=2.543, simple_loss=0.3315, pruned_loss=0.1153, codebook_loss=22.62, over 6999.00 frames.], tot_loss[loss=2.465, simple_loss=0.3039, pruned_loss=0.08671, codebook_loss=22.29, over 1390467.36 frames.], batch size: 29, lr: 1.96e-03
+2022-05-27 15:28:02,622 INFO [train.py:823] (1/4) Epoch 8, batch 0, loss[loss=2.415, simple_loss=0.3069, pruned_loss=0.07234, codebook_loss=21.89, over 7426.00 frames.], tot_loss[loss=2.415, simple_loss=0.3069, pruned_loss=0.07234, codebook_loss=21.89, over 7426.00 frames.], batch size: 22, lr: 1.88e-03
+2022-05-27 15:28:42,271 INFO [train.py:823] (1/4) Epoch 8, batch 50, loss[loss=2.326, simple_loss=0.2806, pruned_loss=0.05681, codebook_loss=21.29, over 7266.00 frames.], tot_loss[loss=2.401, simple_loss=0.298, pruned_loss=0.07599, codebook_loss=21.76, over 320515.75 frames.], batch size: 24, lr: 1.87e-03
+2022-05-27 15:29:23,685 INFO [train.py:823] (1/4) Epoch 8, batch 100, loss[loss=2.607, simple_loss=0.2907, pruned_loss=0.09106, codebook_loss=23.71, over 7022.00 frames.], tot_loss[loss=2.429, simple_loss=0.303, pruned_loss=0.08025, codebook_loss=21.97, over 563865.70 frames.], batch size: 17, lr: 1.87e-03
+2022-05-27 15:30:05,853 INFO [train.py:823] (1/4) Epoch 8, batch 150, loss[loss=2.367, simple_loss=0.2776, pruned_loss=0.06619, codebook_loss=21.62, over 7293.00 frames.], tot_loss[loss=2.425, simple_loss=0.2986, pruned_loss=0.07808, codebook_loss=21.97, over 752973.36 frames.], batch size: 20, lr: 1.86e-03
+2022-05-27 15:30:45,995 INFO [train.py:823] (1/4) Epoch 8, batch 200, loss[loss=2.446, simple_loss=0.2499, pruned_loss=0.06079, codebook_loss=22.61, over 6990.00 frames.], tot_loss[loss=2.426, simple_loss=0.2986, pruned_loss=0.07849, codebook_loss=21.98, over 899345.75 frames.], batch size: 16, lr: 1.86e-03
+2022-05-27 15:31:25,745 INFO [train.py:823] (1/4) Epoch 8, batch 250, loss[loss=2.446, simple_loss=0.3239, pruned_loss=0.08375, codebook_loss=22, over 7143.00 frames.], tot_loss[loss=2.429, simple_loss=0.2981, pruned_loss=0.0785, codebook_loss=22.02, over 1013356.15 frames.], batch size: 23, lr: 1.85e-03
+2022-05-27 15:32:06,063 INFO [train.py:823] (1/4) Epoch 8, batch 300, loss[loss=2.507, simple_loss=0.3214, pruned_loss=0.1042, codebook_loss=22.43, over 7390.00 frames.], tot_loss[loss=2.424, simple_loss=0.2983, pruned_loss=0.07844, codebook_loss=21.97, over 1106223.46 frames.], batch size: 19, lr: 1.85e-03
+2022-05-27 15:32:45,539 INFO [train.py:823] (1/4) Epoch 8, batch 350, loss[loss=2.303, simple_loss=0.2596, pruned_loss=0.05727, codebook_loss=21.16, over 7016.00 frames.], tot_loss[loss=2.423, simple_loss=0.2963, pruned_loss=0.07745, codebook_loss=21.97, over 1167186.44 frames.], batch size: 16, lr: 1.85e-03
+2022-05-27 15:33:25,405 INFO [train.py:823] (1/4) Epoch 8, batch 400, loss[loss=2.386, simple_loss=0.3128, pruned_loss=0.08198, codebook_loss=21.47, over 7178.00 frames.], tot_loss[loss=2.429, simple_loss=0.2981, pruned_loss=0.07819, codebook_loss=22.02, over 1222828.89 frames.], batch size: 22, lr: 1.84e-03
+2022-05-27 15:34:05,057 INFO [train.py:823] (1/4) Epoch 8, batch 450, loss[loss=2.96, simple_loss=0.3308, pruned_loss=0.1061, codebook_loss=26.88, over 6354.00 frames.], tot_loss[loss=2.437, simple_loss=0.2993, pruned_loss=0.07901, codebook_loss=22.08, over 1265014.34 frames.], batch size: 34, lr: 1.84e-03
+2022-05-27 15:34:45,226 INFO [train.py:823] (1/4) Epoch 8, batch 500, loss[loss=2.437, simple_loss=0.2683, pruned_loss=0.07484, codebook_loss=22.29, over 7267.00 frames.], tot_loss[loss=2.436, simple_loss=0.2985, pruned_loss=0.07821, codebook_loss=22.08, over 1300418.88 frames.], batch size: 17, lr: 1.83e-03
+2022-05-27 15:35:24,770 INFO [train.py:823] (1/4) Epoch 8, batch 550, loss[loss=2.749, simple_loss=0.296, pruned_loss=0.08518, codebook_loss=25.16, over 7166.00 frames.], tot_loss[loss=2.438, simple_loss=0.2993, pruned_loss=0.07825, codebook_loss=22.1, over 1324421.74 frames.], batch size: 22, lr: 1.83e-03
+2022-05-27 15:36:04,695 INFO [train.py:823] (1/4) Epoch 8, batch 600, loss[loss=2.578, simple_loss=0.2956, pruned_loss=0.08055, codebook_loss=23.5, over 7027.00 frames.], tot_loss[loss=2.445, simple_loss=0.2994, pruned_loss=0.07825, codebook_loss=22.17, over 1343594.38 frames.], batch size: 17, lr: 1.82e-03
+2022-05-27 15:36:44,528 INFO [train.py:823] (1/4) Epoch 8, batch 650, loss[loss=2.325, simple_loss=0.292, pruned_loss=0.06899, codebook_loss=21.1, over 7004.00 frames.], tot_loss[loss=2.434, simple_loss=0.2985, pruned_loss=0.07755, codebook_loss=22.07, over 1361345.01 frames.], batch size: 26, lr: 1.82e-03
+2022-05-27 15:37:24,993 INFO [train.py:823] (1/4) Epoch 8, batch 700, loss[loss=2.54, simple_loss=0.2725, pruned_loss=0.06762, codebook_loss=23.36, over 7300.00 frames.], tot_loss[loss=2.425, simple_loss=0.2981, pruned_loss=0.0767, codebook_loss=21.99, over 1380432.26 frames.], batch size: 19, lr: 1.82e-03
+2022-05-27 15:38:04,507 INFO [train.py:823] (1/4) Epoch 8, batch 750, loss[loss=2.336, simple_loss=0.2666, pruned_loss=0.05172, codebook_loss=21.51, over 7088.00 frames.], tot_loss[loss=2.422, simple_loss=0.2974, pruned_loss=0.07618, codebook_loss=21.97, over 1387474.95 frames.], batch size: 18, lr: 1.81e-03
+2022-05-27 15:38:44,416 INFO [train.py:823] (1/4) Epoch 8, batch 800, loss[loss=2.566, simple_loss=0.3138, pruned_loss=0.1019, codebook_loss=23.07, over 5512.00 frames.], tot_loss[loss=2.418, simple_loss=0.2965, pruned_loss=0.07526, codebook_loss=21.95, over 1389457.74 frames.], batch size: 47, lr: 1.81e-03
+2022-05-27 15:39:24,087 INFO [train.py:823] (1/4) Epoch 8, batch 850, loss[loss=2.436, simple_loss=0.3209, pruned_loss=0.0779, codebook_loss=21.98, over 7187.00 frames.], tot_loss[loss=2.418, simple_loss=0.2954, pruned_loss=0.07492, codebook_loss=21.96, over 1391391.02 frames.], batch size: 20, lr: 1.80e-03
+2022-05-27 15:40:04,010 INFO [train.py:823] (1/4) Epoch 8, batch 900, loss[loss=2.377, simple_loss=0.2897, pruned_loss=0.06932, codebook_loss=21.62, over 7086.00 frames.], tot_loss[loss=2.431, simple_loss=0.2964, pruned_loss=0.07609, codebook_loss=22.07, over 1395088.65 frames.], batch size: 18, lr: 1.80e-03
+2022-05-27 15:40:54,933 INFO [train.py:823] (1/4) Epoch 9, batch 0, loss[loss=2.279, simple_loss=0.3018, pruned_loss=0.06151, codebook_loss=20.67, over 7189.00 frames.], tot_loss[loss=2.279, simple_loss=0.3018, pruned_loss=0.06151, codebook_loss=20.67, over 7189.00 frames.], batch size: 21, lr: 1.72e-03
+2022-05-27 15:41:35,078 INFO [train.py:823] (1/4) Epoch 9, batch 50, loss[loss=2.32, simple_loss=0.2636, pruned_loss=0.0468, codebook_loss=21.42, over 7389.00 frames.], tot_loss[loss=2.407, simple_loss=0.292, pruned_loss=0.07224, codebook_loss=21.89, over 319310.05 frames.], batch size: 19, lr: 1.72e-03
+2022-05-27 15:42:14,610 INFO [train.py:823] (1/4) Epoch 9, batch 100, loss[loss=2.269, simple_loss=0.2634, pruned_loss=0.05307, codebook_loss=20.84, over 7298.00 frames.], tot_loss[loss=2.366, simple_loss=0.2898, pruned_loss=0.06789, codebook_loss=21.53, over 563251.78 frames.], batch size: 19, lr: 1.71e-03
+2022-05-27 15:42:54,768 INFO [train.py:823] (1/4) Epoch 9, batch 150, loss[loss=2.477, simple_loss=0.2728, pruned_loss=0.04699, codebook_loss=22.94, over 7098.00 frames.], tot_loss[loss=2.375, simple_loss=0.2902, pruned_loss=0.06879, codebook_loss=21.61, over 753204.55 frames.], batch size: 19, lr: 1.71e-03
+2022-05-27 15:43:34,135 INFO [train.py:823] (1/4) Epoch 9, batch 200, loss[loss=2.33, simple_loss=0.2975, pruned_loss=0.06211, codebook_loss=21.19, over 7278.00 frames.], tot_loss[loss=2.373, simple_loss=0.2899, pruned_loss=0.06826, codebook_loss=21.6, over 895378.76 frames.], batch size: 20, lr: 1.71e-03
+2022-05-27 15:44:14,346 INFO [train.py:823] (1/4) Epoch 9, batch 250, loss[loss=2.371, simple_loss=0.2931, pruned_loss=0.07163, codebook_loss=21.53, over 7194.00 frames.], tot_loss[loss=2.366, simple_loss=0.2895, pruned_loss=0.06778, codebook_loss=21.53, over 1011775.04 frames.], batch size: 20, lr: 1.70e-03
+2022-05-27 15:44:53,899 INFO [train.py:823] (1/4) Epoch 9, batch 300, loss[loss=2.375, simple_loss=0.2872, pruned_loss=0.0708, codebook_loss=21.6, over 7194.00 frames.], tot_loss[loss=2.372, simple_loss=0.2902, pruned_loss=0.0684, codebook_loss=21.58, over 1103202.08 frames.], batch size: 18, lr: 1.70e-03
+2022-05-27 15:45:34,256 INFO [train.py:823] (1/4) Epoch 9, batch 350, loss[loss=2.367, simple_loss=0.2637, pruned_loss=0.05626, codebook_loss=21.79, over 7289.00 frames.], tot_loss[loss=2.363, simple_loss=0.288, pruned_loss=0.06729, codebook_loss=21.52, over 1173135.09 frames.], batch size: 17, lr: 1.70e-03
+2022-05-27 15:46:14,409 INFO [train.py:823] (1/4) Epoch 9, batch 400, loss[loss=2.325, simple_loss=0.3007, pruned_loss=0.06448, codebook_loss=21.1, over 7301.00 frames.], tot_loss[loss=2.369, simple_loss=0.2884, pruned_loss=0.06778, codebook_loss=21.57, over 1230534.09 frames.], batch size: 22, lr: 1.69e-03
+2022-05-27 15:46:57,540 INFO [train.py:823] (1/4) Epoch 9, batch 450, loss[loss=2.323, simple_loss=0.28, pruned_loss=0.05537, codebook_loss=21.28, over 7195.00 frames.], tot_loss[loss=2.379, simple_loss=0.2906, pruned_loss=0.06906, codebook_loss=21.64, over 1271631.12 frames.], batch size: 19, lr: 1.69e-03
+2022-05-27 15:47:37,357 INFO [train.py:823] (1/4) Epoch 9, batch 500, loss[loss=2.283, simple_loss=0.2889, pruned_loss=0.05941, codebook_loss=20.8, over 7248.00 frames.], tot_loss[loss=2.381, simple_loss=0.292, pruned_loss=0.06984, codebook_loss=21.65, over 1305081.57 frames.], batch size: 24, lr: 1.68e-03
+2022-05-27 15:48:17,621 INFO [train.py:823] (1/4) Epoch 9, batch 550, loss[loss=2.743, simple_loss=0.3062, pruned_loss=0.1075, codebook_loss=24.82, over 7206.00 frames.], tot_loss[loss=2.381, simple_loss=0.2917, pruned_loss=0.0694, codebook_loss=21.66, over 1334414.37 frames.], batch size: 19, lr: 1.68e-03
+2022-05-27 15:48:57,601 INFO [train.py:823] (1/4) Epoch 9, batch 600, loss[loss=2.778, simple_loss=0.2772, pruned_loss=0.07792, codebook_loss=25.61, over 7148.00 frames.], tot_loss[loss=2.383, simple_loss=0.2899, pruned_loss=0.06882, codebook_loss=21.7, over 1353461.04 frames.], batch size: 17, lr: 1.68e-03
+2022-05-27 15:49:37,631 INFO [train.py:823] (1/4) Epoch 9, batch 650, loss[loss=2.307, simple_loss=0.2973, pruned_loss=0.07005, codebook_loss=20.89, over 7031.00 frames.], tot_loss[loss=2.379, simple_loss=0.289, pruned_loss=0.06816, codebook_loss=21.67, over 1366525.95 frames.], batch size: 29, lr: 1.67e-03
+2022-05-27 15:50:17,591 INFO [train.py:823] (1/4) Epoch 9, batch 700, loss[loss=2.465, simple_loss=0.299, pruned_loss=0.07217, codebook_loss=22.44, over 7298.00 frames.], tot_loss[loss=2.383, simple_loss=0.2898, pruned_loss=0.06808, codebook_loss=21.7, over 1375208.78 frames.], batch size: 22, lr: 1.67e-03
+2022-05-27 15:50:59,097 INFO [train.py:823] (1/4) Epoch 9, batch 750, loss[loss=2.265, simple_loss=0.2575, pruned_loss=0.0483, codebook_loss=20.88, over 7188.00 frames.], tot_loss[loss=2.388, simple_loss=0.2916, pruned_loss=0.06945, codebook_loss=21.72, over 1386027.30 frames.], batch size: 18, lr: 1.67e-03
+2022-05-27 15:51:38,645 INFO [train.py:823] (1/4) Epoch 9, batch 800, loss[loss=2.306, simple_loss=0.2741, pruned_loss=0.05817, codebook_loss=21.1, over 7098.00 frames.], tot_loss[loss=2.384, simple_loss=0.291, pruned_loss=0.0685, codebook_loss=21.7, over 1387040.86 frames.], batch size: 19, lr: 1.66e-03
+2022-05-27 15:52:18,620 INFO [train.py:823] (1/4) Epoch 9, batch 850, loss[loss=2.412, simple_loss=0.2655, pruned_loss=0.06025, codebook_loss=22.19, over 6830.00 frames.], tot_loss[loss=2.376, simple_loss=0.2907, pruned_loss=0.06784, codebook_loss=21.63, over 1396740.91 frames.], batch size: 15, lr: 1.66e-03
+2022-05-27 15:52:58,166 INFO [train.py:823] (1/4) Epoch 9, batch 900, loss[loss=2.606, simple_loss=0.321, pruned_loss=0.1121, codebook_loss=23.33, over 7246.00 frames.], tot_loss[loss=2.391, simple_loss=0.2929, pruned_loss=0.07054, codebook_loss=21.74, over 1399729.59 frames.], batch size: 16, lr: 1.65e-03
+2022-05-27 15:53:54,913 INFO [train.py:823] (1/4) Epoch 10, batch 0, loss[loss=2.358, simple_loss=0.2826, pruned_loss=0.05827, codebook_loss=21.59, over 7111.00 frames.], tot_loss[loss=2.358, simple_loss=0.2826, pruned_loss=0.05827, codebook_loss=21.59, over 7111.00 frames.], batch size: 20, lr: 1.59e-03
+2022-05-27 15:54:34,637 INFO [train.py:823] (1/4) Epoch 10, batch 50, loss[loss=2.472, simple_loss=0.2701, pruned_loss=0.05536, codebook_loss=22.81, over 7036.00 frames.], tot_loss[loss=2.366, simple_loss=0.2865, pruned_loss=0.06659, codebook_loss=21.56, over 319226.37 frames.], batch size: 17, lr: 1.58e-03
+2022-05-27 15:55:15,568 INFO [train.py:823] (1/4) Epoch 10, batch 100, loss[loss=2.266, simple_loss=0.2719, pruned_loss=0.05786, codebook_loss=20.72, over 7372.00 frames.], tot_loss[loss=2.343, simple_loss=0.2835, pruned_loss=0.06373, codebook_loss=21.37, over 560865.30 frames.], batch size: 20, lr: 1.58e-03
+2022-05-27 15:55:54,975 INFO [train.py:823] (1/4) Epoch 10, batch 150, loss[loss=2.512, simple_loss=0.3003, pruned_loss=0.08772, codebook_loss=22.74, over 7276.00 frames.], tot_loss[loss=2.34, simple_loss=0.2855, pruned_loss=0.06382, codebook_loss=21.33, over 750745.90 frames.], batch size: 20, lr: 1.58e-03
+2022-05-27 15:56:35,123 INFO [train.py:823] (1/4) Epoch 10, batch 200, loss[loss=2.387, simple_loss=0.2868, pruned_loss=0.07085, codebook_loss=21.73, over 7281.00 frames.], tot_loss[loss=2.343, simple_loss=0.2845, pruned_loss=0.0639, codebook_loss=21.37, over 901995.75 frames.], batch size: 21, lr: 1.57e-03
+2022-05-27 15:57:14,780 INFO [train.py:823] (1/4) Epoch 10, batch 250, loss[loss=2.232, simple_loss=0.2706, pruned_loss=0.04913, codebook_loss=20.48, over 7378.00 frames.], tot_loss[loss=2.345, simple_loss=0.2846, pruned_loss=0.06351, codebook_loss=21.39, over 1017827.86 frames.], batch size: 21, lr: 1.57e-03
+2022-05-27 15:57:54,570 INFO [train.py:823] (1/4) Epoch 10, batch 300, loss[loss=2.328, simple_loss=0.2961, pruned_loss=0.07474, codebook_loss=21.05, over 6984.00 frames.], tot_loss[loss=2.347, simple_loss=0.2856, pruned_loss=0.06407, codebook_loss=21.4, over 1109226.72 frames.], batch size: 26, lr: 1.57e-03
+2022-05-27 15:58:34,252 INFO [train.py:823] (1/4) Epoch 10, batch 350, loss[loss=2.236, simple_loss=0.2442, pruned_loss=0.03848, codebook_loss=20.76, over 7280.00 frames.], tot_loss[loss=2.339, simple_loss=0.2853, pruned_loss=0.06321, codebook_loss=21.34, over 1175939.41 frames.], batch size: 16, lr: 1.56e-03
+2022-05-27 15:59:14,383 INFO [train.py:823] (1/4) Epoch 10, batch 400, loss[loss=2.338, simple_loss=0.2915, pruned_loss=0.0616, codebook_loss=21.31, over 7092.00 frames.], tot_loss[loss=2.348, simple_loss=0.2863, pruned_loss=0.06374, codebook_loss=21.41, over 1225930.46 frames.], batch size: 19, lr: 1.56e-03
+2022-05-27 15:59:54,074 INFO [train.py:823] (1/4) Epoch 10, batch 450, loss[loss=2.492, simple_loss=0.306, pruned_loss=0.096, codebook_loss=22.43, over 7276.00 frames.], tot_loss[loss=2.349, simple_loss=0.2863, pruned_loss=0.06391, codebook_loss=21.42, over 1266947.05 frames.], batch size: 20, lr: 1.56e-03
+2022-05-27 16:00:34,198 INFO [train.py:823] (1/4) Epoch 10, batch 500, loss[loss=2.34, simple_loss=0.2852, pruned_loss=0.061, codebook_loss=21.36, over 7273.00 frames.], tot_loss[loss=2.349, simple_loss=0.286, pruned_loss=0.06407, codebook_loss=21.42, over 1299286.75 frames.], batch size: 20, lr: 1.55e-03
+2022-05-27 16:01:14,176 INFO [train.py:823] (1/4) Epoch 10, batch 550, loss[loss=2.229, simple_loss=0.2593, pruned_loss=0.04585, codebook_loss=20.53, over 7099.00 frames.], tot_loss[loss=2.348, simple_loss=0.2851, pruned_loss=0.06371, codebook_loss=21.42, over 1329015.45 frames.], batch size: 18, lr: 1.55e-03
+2022-05-27 16:01:54,265 INFO [train.py:823] (1/4) Epoch 10, batch 600, loss[loss=2.249, simple_loss=0.2401, pruned_loss=0.04283, codebook_loss=20.86, over 7278.00 frames.], tot_loss[loss=2.353, simple_loss=0.2858, pruned_loss=0.06385, codebook_loss=21.46, over 1353827.34 frames.], batch size: 19, lr: 1.55e-03
+2022-05-27 16:02:33,984 INFO [train.py:823] (1/4) Epoch 10, batch 650, loss[loss=2.341, simple_loss=0.3047, pruned_loss=0.07058, codebook_loss=21.18, over 7199.00 frames.], tot_loss[loss=2.347, simple_loss=0.2842, pruned_loss=0.06309, codebook_loss=21.42, over 1371789.76 frames.], batch size: 21, lr: 1.54e-03
+2022-05-27 16:03:14,286 INFO [train.py:823] (1/4) Epoch 10, batch 700, loss[loss=2.818, simple_loss=0.2682, pruned_loss=0.07486, codebook_loss=26.09, over 7024.00 frames.], tot_loss[loss=2.348, simple_loss=0.2852, pruned_loss=0.0633, codebook_loss=21.43, over 1385287.26 frames.], batch size: 16, lr: 1.54e-03
+2022-05-27 16:03:53,950 INFO [train.py:823] (1/4) Epoch 10, batch 750, loss[loss=2.303, simple_loss=0.277, pruned_loss=0.06465, codebook_loss=21, over 7186.00 frames.], tot_loss[loss=2.35, simple_loss=0.2848, pruned_loss=0.06325, codebook_loss=21.45, over 1392438.96 frames.], batch size: 18, lr: 1.54e-03
+2022-05-27 16:04:34,042 INFO [train.py:823] (1/4) Epoch 10, batch 800, loss[loss=2.321, simple_loss=0.3007, pruned_loss=0.06618, codebook_loss=21.04, over 7193.00 frames.], tot_loss[loss=2.346, simple_loss=0.2851, pruned_loss=0.06322, codebook_loss=21.4, over 1399590.84 frames.], batch size: 25, lr: 1.53e-03
+2022-05-27 16:05:14,011 INFO [train.py:823] (1/4) Epoch 10, batch 850, loss[loss=2.324, simple_loss=0.292, pruned_loss=0.07768, codebook_loss=21.01, over 7152.00 frames.], tot_loss[loss=2.346, simple_loss=0.2846, pruned_loss=0.06309, codebook_loss=21.4, over 1406063.01 frames.], batch size: 22, lr: 1.53e-03
+2022-05-27 16:05:54,090 INFO [train.py:823] (1/4) Epoch 10, batch 900, loss[loss=2.55, simple_loss=0.2812, pruned_loss=0.06765, codebook_loss=23.42, over 7233.00 frames.], tot_loss[loss=2.349, simple_loss=0.2839, pruned_loss=0.06277, codebook_loss=21.44, over 1406186.60 frames.], batch size: 16, lr: 1.53e-03
+2022-05-27 16:06:46,057 INFO [train.py:823] (1/4) Epoch 11, batch 0, loss[loss=2.516, simple_loss=0.275, pruned_loss=0.05228, codebook_loss=23.26, over 7096.00 frames.], tot_loss[loss=2.516, simple_loss=0.275, pruned_loss=0.05228, codebook_loss=23.26, over 7096.00 frames.], batch size: 19, lr: 1.47e-03
+2022-05-27 16:07:26,145 INFO [train.py:823] (1/4) Epoch 11, batch 50, loss[loss=2.422, simple_loss=0.3097, pruned_loss=0.08217, codebook_loss=21.85, over 6492.00 frames.], tot_loss[loss=2.332, simple_loss=0.2827, pruned_loss=0.06057, codebook_loss=21.3, over 323174.39 frames.], batch size: 34, lr: 1.47e-03
+2022-05-27 16:08:06,020 INFO [train.py:823] (1/4) Epoch 11, batch 100, loss[loss=2.295, simple_loss=0.2519, pruned_loss=0.05529, codebook_loss=21.14, over 7142.00 frames.], tot_loss[loss=2.322, simple_loss=0.2801, pruned_loss=0.05881, codebook_loss=21.23, over 569152.74 frames.], batch size: 17, lr: 1.46e-03
+2022-05-27 16:08:46,158 INFO [train.py:823] (1/4) Epoch 11, batch 150, loss[loss=2.255, simple_loss=0.2878, pruned_loss=0.05501, codebook_loss=20.56, over 7223.00 frames.], tot_loss[loss=2.33, simple_loss=0.2801, pruned_loss=0.05948, codebook_loss=21.3, over 760596.92 frames.], batch size: 24, lr: 1.46e-03
+2022-05-27 16:09:25,522 INFO [train.py:823] (1/4) Epoch 11, batch 200, loss[loss=2.29, simple_loss=0.2769, pruned_loss=0.05706, codebook_loss=20.95, over 7106.00 frames.], tot_loss[loss=2.327, simple_loss=0.2814, pruned_loss=0.05944, codebook_loss=21.27, over 901436.39 frames.], batch size: 19, lr: 1.46e-03
+2022-05-27 16:10:05,762 INFO [train.py:823] (1/4) Epoch 11, batch 250, loss[loss=2.313, simple_loss=0.2921, pruned_loss=0.07164, codebook_loss=20.95, over 7093.00 frames.], tot_loss[loss=2.329, simple_loss=0.2821, pruned_loss=0.05939, codebook_loss=21.28, over 1014801.96 frames.], batch size: 18, lr: 1.45e-03
+2022-05-27 16:10:45,560 INFO [train.py:823] (1/4) Epoch 11, batch 300, loss[loss=2.277, simple_loss=0.2724, pruned_loss=0.05228, codebook_loss=20.88, over 7213.00 frames.], tot_loss[loss=2.326, simple_loss=0.2808, pruned_loss=0.05899, codebook_loss=21.27, over 1105633.22 frames.], batch size: 25, lr: 1.45e-03
+2022-05-27 16:11:25,751 INFO [train.py:823] (1/4) Epoch 11, batch 350, loss[loss=2.213, simple_loss=0.2854, pruned_loss=0.04757, codebook_loss=20.23, over 7197.00 frames.], tot_loss[loss=2.323, simple_loss=0.2801, pruned_loss=0.05867, codebook_loss=21.24, over 1176997.60 frames.], batch size: 25, lr: 1.45e-03
+2022-05-27 16:12:05,500 INFO [train.py:823] (1/4) Epoch 11, batch 400, loss[loss=2.313, simple_loss=0.3003, pruned_loss=0.07226, codebook_loss=20.9, over 7094.00 frames.], tot_loss[loss=2.318, simple_loss=0.2796, pruned_loss=0.05814, codebook_loss=21.2, over 1231342.69 frames.], batch size: 19, lr: 1.44e-03
+2022-05-27 16:12:45,570 INFO [train.py:823] (1/4) Epoch 11, batch 450, loss[loss=2.21, simple_loss=0.2813, pruned_loss=0.05729, codebook_loss=20.12, over 7297.00 frames.], tot_loss[loss=2.314, simple_loss=0.2798, pruned_loss=0.05836, codebook_loss=21.16, over 1270050.26 frames.], batch size: 22, lr: 1.44e-03
+2022-05-27 16:13:25,304 INFO [train.py:823] (1/4) Epoch 11, batch 500, loss[loss=2.261, simple_loss=0.2697, pruned_loss=0.04633, codebook_loss=20.8, over 6395.00 frames.], tot_loss[loss=2.314, simple_loss=0.2803, pruned_loss=0.05863, codebook_loss=21.15, over 1303304.16 frames.], batch size: 34, lr: 1.44e-03
+2022-05-27 16:14:05,251 INFO [train.py:823] (1/4) Epoch 11, batch 550, loss[loss=2.417, simple_loss=0.2669, pruned_loss=0.04714, codebook_loss=22.36, over 7409.00 frames.], tot_loss[loss=2.32, simple_loss=0.2809, pruned_loss=0.05922, codebook_loss=21.2, over 1331940.68 frames.], batch size: 22, lr: 1.44e-03
+2022-05-27 16:14:46,339 INFO [train.py:823] (1/4) Epoch 11, batch 600, loss[loss=2.251, simple_loss=0.2658, pruned_loss=0.05047, codebook_loss=20.67, over 7381.00 frames.], tot_loss[loss=2.323, simple_loss=0.2811, pruned_loss=0.05989, codebook_loss=21.23, over 1350839.67 frames.], batch size: 19, lr: 1.43e-03
+2022-05-27 16:15:26,714 INFO [train.py:823] (1/4) Epoch 11, batch 650, loss[loss=2.352, simple_loss=0.2762, pruned_loss=0.06867, codebook_loss=21.46, over 7308.00 frames.], tot_loss[loss=2.316, simple_loss=0.2804, pruned_loss=0.05897, codebook_loss=21.17, over 1367855.61 frames.], batch size: 18, lr: 1.43e-03
+2022-05-27 16:16:06,584 INFO [train.py:823] (1/4) Epoch 11, batch 700, loss[loss=2.587, simple_loss=0.3204, pruned_loss=0.1004, codebook_loss=23.27, over 7164.00 frames.], tot_loss[loss=2.311, simple_loss=0.2805, pruned_loss=0.05889, codebook_loss=21.12, over 1382336.10 frames.], batch size: 17, lr: 1.43e-03
+2022-05-27 16:16:46,849 INFO [train.py:823] (1/4) Epoch 11, batch 750, loss[loss=2.188, simple_loss=0.2327, pruned_loss=0.04012, codebook_loss=20.31, over 7290.00 frames.], tot_loss[loss=2.314, simple_loss=0.2801, pruned_loss=0.0591, codebook_loss=21.14, over 1389992.95 frames.], batch size: 17, lr: 1.42e-03
+2022-05-27 16:17:26,669 INFO [train.py:823] (1/4) Epoch 11, batch 800, loss[loss=2.44, simple_loss=0.2706, pruned_loss=0.0488, codebook_loss=22.56, over 7194.00 frames.], tot_loss[loss=2.316, simple_loss=0.2804, pruned_loss=0.05871, codebook_loss=21.17, over 1395338.88 frames.], batch size: 19, lr: 1.42e-03
+2022-05-27 16:18:08,295 INFO [train.py:823] (1/4) Epoch 11, batch 850, loss[loss=2.345, simple_loss=0.3251, pruned_loss=0.06869, codebook_loss=21.14, over 7109.00 frames.], tot_loss[loss=2.318, simple_loss=0.2807, pruned_loss=0.05902, codebook_loss=21.18, over 1397754.24 frames.], batch size: 20, lr: 1.42e-03
+2022-05-27 16:18:49,106 INFO [train.py:823] (1/4) Epoch 11, batch 900, loss[loss=2.269, simple_loss=0.2454, pruned_loss=0.03934, codebook_loss=21.07, over 6802.00 frames.], tot_loss[loss=2.311, simple_loss=0.2814, pruned_loss=0.0587, codebook_loss=21.11, over 1397530.65 frames.], batch size: 15, lr: 1.42e-03
+2022-05-27 16:19:44,428 INFO [train.py:823] (1/4) Epoch 12, batch 0, loss[loss=2.324, simple_loss=0.2706, pruned_loss=0.06813, codebook_loss=21.21, over 7304.00 frames.], tot_loss[loss=2.324, simple_loss=0.2706, pruned_loss=0.06813, codebook_loss=21.21, over 7304.00 frames.], batch size: 17, lr: 1.36e-03
+2022-05-27 16:20:24,313 INFO [train.py:823] (1/4) Epoch 12, batch 50, loss[loss=2.305, simple_loss=0.3016, pruned_loss=0.06775, codebook_loss=20.87, over 7243.00 frames.], tot_loss[loss=2.333, simple_loss=0.2768, pruned_loss=0.05904, codebook_loss=21.36, over 316972.22 frames.], batch size: 24, lr: 1.36e-03
+2022-05-27 16:21:04,297 INFO [train.py:823] (1/4) Epoch 12, batch 100, loss[loss=2.599, simple_loss=0.3106, pruned_loss=0.06304, codebook_loss=23.8, over 7147.00 frames.], tot_loss[loss=2.311, simple_loss=0.277, pruned_loss=0.05704, codebook_loss=21.16, over 561006.18 frames.], batch size: 23, lr: 1.36e-03
+2022-05-27 16:21:44,020 INFO [train.py:823] (1/4) Epoch 12, batch 150, loss[loss=2.252, simple_loss=0.2632, pruned_loss=0.04782, codebook_loss=20.72, over 7288.00 frames.], tot_loss[loss=2.307, simple_loss=0.2773, pruned_loss=0.05677, codebook_loss=21.11, over 752301.74 frames.], batch size: 20, lr: 1.36e-03
+2022-05-27 16:22:24,279 INFO [train.py:823] (1/4) Epoch 12, batch 200, loss[loss=2.396, simple_loss=0.2464, pruned_loss=0.05188, codebook_loss=22.21, over 6827.00 frames.], tot_loss[loss=2.304, simple_loss=0.2783, pruned_loss=0.05725, codebook_loss=21.08, over 899136.27 frames.], batch size: 15, lr: 1.35e-03
+2022-05-27 16:23:03,805 INFO [train.py:823] (1/4) Epoch 12, batch 250, loss[loss=2.219, simple_loss=0.2801, pruned_loss=0.05392, codebook_loss=20.25, over 7029.00 frames.], tot_loss[loss=2.305, simple_loss=0.2783, pruned_loss=0.05714, codebook_loss=21.08, over 1016485.73 frames.], batch size: 26, lr: 1.35e-03
+2022-05-27 16:23:43,706 INFO [train.py:823] (1/4) Epoch 12, batch 300, loss[loss=2.307, simple_loss=0.2637, pruned_loss=0.04478, codebook_loss=21.3, over 7202.00 frames.], tot_loss[loss=2.298, simple_loss=0.2776, pruned_loss=0.05612, codebook_loss=21.03, over 1102976.48 frames.], batch size: 19, lr: 1.35e-03
+2022-05-27 16:24:23,582 INFO [train.py:823] (1/4) Epoch 12, batch 350, loss[loss=2.223, simple_loss=0.2787, pruned_loss=0.05226, codebook_loss=20.31, over 7342.00 frames.], tot_loss[loss=2.293, simple_loss=0.2768, pruned_loss=0.05559, codebook_loss=20.99, over 1176756.92 frames.], batch size: 23, lr: 1.35e-03
+2022-05-27 16:25:03,604 INFO [train.py:823] (1/4) Epoch 12, batch 400, loss[loss=2.33, simple_loss=0.2874, pruned_loss=0.0628, codebook_loss=21.23, over 6966.00 frames.], tot_loss[loss=2.29, simple_loss=0.2767, pruned_loss=0.05495, codebook_loss=20.96, over 1231223.11 frames.], batch size: 29, lr: 1.34e-03
+2022-05-27 16:25:43,358 INFO [train.py:823] (1/4) Epoch 12, batch 450, loss[loss=2.739, simple_loss=0.2901, pruned_loss=0.06814, codebook_loss=25.26, over 7378.00 frames.], tot_loss[loss=2.283, simple_loss=0.2766, pruned_loss=0.05455, codebook_loss=20.91, over 1273895.98 frames.], batch size: 20, lr: 1.34e-03
+2022-05-27 16:26:23,676 INFO [train.py:823] (1/4) Epoch 12, batch 500, loss[loss=2.264, simple_loss=0.2907, pruned_loss=0.06186, codebook_loss=20.57, over 7280.00 frames.], tot_loss[loss=2.283, simple_loss=0.2758, pruned_loss=0.05436, codebook_loss=20.9, over 1311806.29 frames.], batch size: 20, lr: 1.34e-03
+2022-05-27 16:27:03,422 INFO [train.py:823] (1/4) Epoch 12, batch 550, loss[loss=2.413, simple_loss=0.2607, pruned_loss=0.05668, codebook_loss=22.26, over 7428.00 frames.], tot_loss[loss=2.284, simple_loss=0.2774, pruned_loss=0.05506, codebook_loss=20.91, over 1339766.31 frames.], batch size: 18, lr: 1.34e-03
+2022-05-27 16:27:43,508 INFO [train.py:823] (1/4) Epoch 12, batch 600, loss[loss=2.299, simple_loss=0.2493, pruned_loss=0.05362, codebook_loss=21.21, over 7211.00 frames.], tot_loss[loss=2.281, simple_loss=0.2761, pruned_loss=0.05438, codebook_loss=20.88, over 1360176.91 frames.], batch size: 16, lr: 1.33e-03
+2022-05-27 16:28:23,515 INFO [train.py:823] (1/4) Epoch 12, batch 650, loss[loss=2.261, simple_loss=0.2759, pruned_loss=0.04953, codebook_loss=20.73, over 7279.00 frames.], tot_loss[loss=2.286, simple_loss=0.2763, pruned_loss=0.05479, codebook_loss=20.93, over 1371038.42 frames.], batch size: 21, lr: 1.33e-03
+2022-05-27 16:29:04,025 INFO [train.py:823] (1/4) Epoch 12, batch 700, loss[loss=2.263, simple_loss=0.274, pruned_loss=0.05365, codebook_loss=20.73, over 7283.00 frames.], tot_loss[loss=2.295, simple_loss=0.2773, pruned_loss=0.05539, codebook_loss=21.01, over 1382557.38 frames.], batch size: 20, lr: 1.33e-03
+2022-05-27 16:29:43,713 INFO [train.py:823] (1/4) Epoch 12, batch 750, loss[loss=2.362, simple_loss=0.3159, pruned_loss=0.08061, codebook_loss=21.24, over 7304.00 frames.], tot_loss[loss=2.29, simple_loss=0.2777, pruned_loss=0.05537, codebook_loss=20.96, over 1388743.98 frames.], batch size: 22, lr: 1.33e-03
+2022-05-27 16:30:23,751 INFO [train.py:823] (1/4) Epoch 12, batch 800, loss[loss=2.24, simple_loss=0.2672, pruned_loss=0.04814, codebook_loss=20.58, over 7296.00 frames.], tot_loss[loss=2.289, simple_loss=0.2773, pruned_loss=0.05507, codebook_loss=20.95, over 1395593.63 frames.], batch size: 22, lr: 1.32e-03
+2022-05-27 16:31:03,439 INFO [train.py:823] (1/4) Epoch 12, batch 850, loss[loss=2.249, simple_loss=0.2699, pruned_loss=0.04982, codebook_loss=20.64, over 7187.00 frames.], tot_loss[loss=2.286, simple_loss=0.2771, pruned_loss=0.05517, codebook_loss=20.93, over 1401162.62 frames.], batch size: 18, lr: 1.32e-03
+2022-05-27 16:31:43,308 INFO [train.py:823] (1/4) Epoch 12, batch 900, loss[loss=2.264, simple_loss=0.2802, pruned_loss=0.05333, codebook_loss=20.7, over 7098.00 frames.], tot_loss[loss=2.294, simple_loss=0.2776, pruned_loss=0.05613, codebook_loss=20.99, over 1396543.75 frames.], batch size: 19, lr: 1.32e-03
+2022-05-27 16:32:36,845 INFO [train.py:823] (1/4) Epoch 13, batch 0, loss[loss=2.238, simple_loss=0.2828, pruned_loss=0.05316, codebook_loss=20.43, over 7170.00 frames.], tot_loss[loss=2.238, simple_loss=0.2828, pruned_loss=0.05316, codebook_loss=20.43, over 7170.00 frames.], batch size: 22, lr: 1.27e-03
+2022-05-27 16:33:17,128 INFO [train.py:823] (1/4) Epoch 13, batch 50, loss[loss=2.195, simple_loss=0.2538, pruned_loss=0.03907, codebook_loss=20.29, over 7296.00 frames.], tot_loss[loss=2.242, simple_loss=0.2692, pruned_loss=0.04946, codebook_loss=20.58, over 317868.64 frames.], batch size: 19, lr: 1.27e-03
+2022-05-27 16:33:56,702 INFO [train.py:823] (1/4) Epoch 13, batch 100, loss[loss=2.156, simple_loss=0.2496, pruned_loss=0.03498, codebook_loss=19.97, over 7329.00 frames.], tot_loss[loss=2.265, simple_loss=0.2732, pruned_loss=0.05325, codebook_loss=20.75, over 562640.07 frames.], batch size: 18, lr: 1.27e-03
+2022-05-27 16:34:36,922 INFO [train.py:823] (1/4) Epoch 13, batch 150, loss[loss=2.291, simple_loss=0.2586, pruned_loss=0.04973, codebook_loss=21.12, over 7386.00 frames.], tot_loss[loss=2.27, simple_loss=0.2732, pruned_loss=0.05325, codebook_loss=20.8, over 752724.13 frames.], batch size: 19, lr: 1.26e-03
+2022-05-27 16:35:16,778 INFO [train.py:823] (1/4) Epoch 13, batch 200, loss[loss=2.242, simple_loss=0.25, pruned_loss=0.05165, codebook_loss=20.65, over 7015.00 frames.], tot_loss[loss=2.271, simple_loss=0.2735, pruned_loss=0.05391, codebook_loss=20.81, over 903040.21 frames.], batch size: 17, lr: 1.26e-03
+2022-05-27 16:35:56,988 INFO [train.py:823] (1/4) Epoch 13, batch 250, loss[loss=2.459, simple_loss=0.2891, pruned_loss=0.06023, codebook_loss=22.55, over 7149.00 frames.], tot_loss[loss=2.266, simple_loss=0.2732, pruned_loss=0.05314, codebook_loss=20.77, over 1016555.54 frames.], batch size: 22, lr: 1.26e-03
+2022-05-27 16:36:37,052 INFO [train.py:823] (1/4) Epoch 13, batch 300, loss[loss=2.265, simple_loss=0.2461, pruned_loss=0.05305, codebook_loss=20.89, over 7292.00 frames.], tot_loss[loss=2.261, simple_loss=0.2723, pruned_loss=0.05242, codebook_loss=20.73, over 1109464.86 frames.], batch size: 17, lr: 1.26e-03
+2022-05-27 16:37:16,859 INFO [train.py:823] (1/4) Epoch 13, batch 350, loss[loss=2.295, simple_loss=0.2692, pruned_loss=0.05313, codebook_loss=21.08, over 6537.00 frames.], tot_loss[loss=2.256, simple_loss=0.273, pruned_loss=0.05292, codebook_loss=20.67, over 1176687.28 frames.], batch size: 34, lr: 1.26e-03
+2022-05-27 16:37:56,788 INFO [train.py:823] (1/4) Epoch 13, batch 400, loss[loss=2.306, simple_loss=0.2918, pruned_loss=0.05838, codebook_loss=21.01, over 7055.00 frames.], tot_loss[loss=2.259, simple_loss=0.2733, pruned_loss=0.05287, codebook_loss=20.7, over 1230350.63 frames.], batch size: 26, lr: 1.25e-03
+2022-05-27 16:38:36,651 INFO [train.py:823] (1/4) Epoch 13, batch 450, loss[loss=2.286, simple_loss=0.2891, pruned_loss=0.05242, codebook_loss=20.89, over 6981.00 frames.], tot_loss[loss=2.259, simple_loss=0.2729, pruned_loss=0.05241, codebook_loss=20.7, over 1267342.17 frames.], batch size: 29, lr: 1.25e-03
+2022-05-27 16:39:17,552 INFO [train.py:823] (1/4) Epoch 13, batch 500, loss[loss=2.483, simple_loss=0.316, pruned_loss=0.0802, codebook_loss=22.45, over 6881.00 frames.], tot_loss[loss=2.258, simple_loss=0.2715, pruned_loss=0.0521, codebook_loss=20.71, over 1300354.43 frames.], batch size: 29, lr: 1.25e-03
+2022-05-27 16:39:57,601 INFO [train.py:823] (1/4) Epoch 13, batch 550, loss[loss=2.242, simple_loss=0.2733, pruned_loss=0.05711, codebook_loss=20.48, over 7288.00 frames.], tot_loss[loss=2.262, simple_loss=0.2714, pruned_loss=0.05241, codebook_loss=20.74, over 1321505.13 frames.], batch size: 19, lr: 1.25e-03
+2022-05-27 16:40:37,172 INFO [train.py:823] (1/4) Epoch 13, batch 600, loss[loss=2.379, simple_loss=0.2811, pruned_loss=0.08148, codebook_loss=21.57, over 7272.00 frames.], tot_loss[loss=2.266, simple_loss=0.2733, pruned_loss=0.05341, codebook_loss=20.76, over 1343695.48 frames.], batch size: 20, lr: 1.24e-03
+2022-05-27 16:41:17,352 INFO [train.py:823] (1/4) Epoch 13, batch 650, loss[loss=2.385, simple_loss=0.2783, pruned_loss=0.03822, codebook_loss=22.08, over 7195.00 frames.], tot_loss[loss=2.264, simple_loss=0.2734, pruned_loss=0.0526, codebook_loss=20.75, over 1359935.65 frames.], batch size: 19, lr: 1.24e-03
+2022-05-27 16:41:57,049 INFO [train.py:823] (1/4) Epoch 13, batch 700, loss[loss=2.243, simple_loss=0.2475, pruned_loss=0.0442, codebook_loss=20.75, over 7036.00 frames.], tot_loss[loss=2.265, simple_loss=0.2736, pruned_loss=0.05247, codebook_loss=20.76, over 1371171.67 frames.], batch size: 17, lr: 1.24e-03
+2022-05-27 16:42:38,232 INFO [train.py:823] (1/4) Epoch 13, batch 750, loss[loss=2.233, simple_loss=0.2788, pruned_loss=0.04577, codebook_loss=20.47, over 6928.00 frames.], tot_loss[loss=2.258, simple_loss=0.2742, pruned_loss=0.05238, codebook_loss=20.68, over 1379078.48 frames.], batch size: 29, lr: 1.24e-03
+2022-05-27 16:43:19,050 INFO [train.py:823] (1/4) Epoch 13, batch 800, loss[loss=2.265, simple_loss=0.2942, pruned_loss=0.05907, codebook_loss=20.59, over 7155.00 frames.], tot_loss[loss=2.258, simple_loss=0.2745, pruned_loss=0.05283, codebook_loss=20.68, over 1385656.16 frames.], batch size: 23, lr: 1.24e-03
+2022-05-27 16:44:00,618 INFO [train.py:823] (1/4) Epoch 13, batch 850, loss[loss=2.264, simple_loss=0.2738, pruned_loss=0.05558, codebook_loss=20.72, over 7283.00 frames.], tot_loss[loss=2.256, simple_loss=0.2739, pruned_loss=0.05246, codebook_loss=20.67, over 1396223.96 frames.], batch size: 20, lr: 1.23e-03
+2022-05-27 16:44:39,949 INFO [train.py:823] (1/4) Epoch 13, batch 900, loss[loss=2.171, simple_loss=0.2484, pruned_loss=0.03768, codebook_loss=20.09, over 7275.00 frames.], tot_loss[loss=2.254, simple_loss=0.2736, pruned_loss=0.05199, codebook_loss=20.65, over 1395856.24 frames.], batch size: 19, lr: 1.23e-03
+2022-05-27 16:45:19,808 INFO [train.py:823] (1/4) Epoch 13, batch 950, loss[loss=2.236, simple_loss=0.2505, pruned_loss=0.05033, codebook_loss=20.61, over 7022.00 frames.], tot_loss[loss=2.256, simple_loss=0.2731, pruned_loss=0.05185, codebook_loss=20.67, over 1394385.02 frames.], batch size: 16, lr: 1.23e-03
+2022-05-27 16:45:35,290 INFO [train.py:823] (1/4) Epoch 14, batch 0, loss[loss=2.162, simple_loss=0.2822, pruned_loss=0.04487, codebook_loss=19.76, over 7292.00 frames.], tot_loss[loss=2.162, simple_loss=0.2822, pruned_loss=0.04487, codebook_loss=19.76, over 7292.00 frames.], batch size: 22, lr: 1.19e-03
+2022-05-27 16:46:15,203 INFO [train.py:823] (1/4) Epoch 14, batch 50, loss[loss=2.197, simple_loss=0.2931, pruned_loss=0.05335, codebook_loss=19.98, over 7208.00 frames.], tot_loss[loss=2.227, simple_loss=0.2663, pruned_loss=0.04851, codebook_loss=20.46, over 325006.14 frames.], batch size: 25, lr: 1.19e-03
+2022-05-27 16:46:55,256 INFO [train.py:823] (1/4) Epoch 14, batch 100, loss[loss=2.222, simple_loss=0.283, pruned_loss=0.0579, codebook_loss=20.23, over 7208.00 frames.], tot_loss[loss=2.257, simple_loss=0.2711, pruned_loss=0.05144, codebook_loss=20.7, over 570824.44 frames.], batch size: 24, lr: 1.19e-03
+2022-05-27 16:47:34,766 INFO [train.py:823] (1/4) Epoch 14, batch 150, loss[loss=2.146, simple_loss=0.2597, pruned_loss=0.03838, codebook_loss=19.78, over 7283.00 frames.], tot_loss[loss=2.257, simple_loss=0.2708, pruned_loss=0.05089, codebook_loss=20.7, over 756840.20 frames.], batch size: 21, lr: 1.18e-03
+2022-05-27 16:48:14,993 INFO [train.py:823] (1/4) Epoch 14, batch 200, loss[loss=2.095, simple_loss=0.2492, pruned_loss=0.02963, codebook_loss=19.41, over 7383.00 frames.], tot_loss[loss=2.25, simple_loss=0.2714, pruned_loss=0.05081, codebook_loss=20.63, over 902175.57 frames.], batch size: 21, lr: 1.18e-03
+2022-05-27 16:48:54,989 INFO [train.py:823] (1/4) Epoch 14, batch 250, loss[loss=2.161, simple_loss=0.2346, pruned_loss=0.04004, codebook_loss=20.04, over 7297.00 frames.], tot_loss[loss=2.241, simple_loss=0.2684, pruned_loss=0.04927, codebook_loss=20.57, over 1020148.03 frames.], batch size: 19, lr: 1.18e-03
+2022-05-27 16:49:34,990 INFO [train.py:823] (1/4) Epoch 14, batch 300, loss[loss=2.203, simple_loss=0.2726, pruned_loss=0.03904, codebook_loss=20.27, over 6461.00 frames.], tot_loss[loss=2.239, simple_loss=0.2694, pruned_loss=0.04969, codebook_loss=20.55, over 1100235.52 frames.], batch size: 34, lr: 1.18e-03
+2022-05-27 16:50:14,791 INFO [train.py:823] (1/4) Epoch 14, batch 350, loss[loss=2.327, simple_loss=0.2683, pruned_loss=0.05913, codebook_loss=21.33, over 7293.00 frames.], tot_loss[loss=2.23, simple_loss=0.2699, pruned_loss=0.049, codebook_loss=20.46, over 1176304.91 frames.], batch size: 19, lr: 1.18e-03
+2022-05-27 16:50:54,547 INFO [train.py:823] (1/4) Epoch 14, batch 400, loss[loss=2.139, simple_loss=0.256, pruned_loss=0.04083, codebook_loss=19.7, over 7290.00 frames.], tot_loss[loss=2.233, simple_loss=0.27, pruned_loss=0.04984, codebook_loss=20.48, over 1230654.99 frames.], batch size: 19, lr: 1.17e-03
+2022-05-27 16:51:34,203 INFO [train.py:823] (1/4) Epoch 14, batch 450, loss[loss=2.124, simple_loss=0.2399, pruned_loss=0.03271, codebook_loss=19.71, over 7082.00 frames.], tot_loss[loss=2.232, simple_loss=0.2706, pruned_loss=0.04974, codebook_loss=20.47, over 1268695.31 frames.], batch size: 18, lr: 1.17e-03
+2022-05-27 16:52:14,457 INFO [train.py:823] (1/4) Epoch 14, batch 500, loss[loss=2.29, simple_loss=0.295, pruned_loss=0.06288, codebook_loss=20.8, over 7189.00 frames.], tot_loss[loss=2.23, simple_loss=0.2701, pruned_loss=0.04951, codebook_loss=20.45, over 1302907.22 frames.], batch size: 21, lr: 1.17e-03
+2022-05-27 16:52:54,034 INFO [train.py:823] (1/4) Epoch 14, batch 550, loss[loss=2.261, simple_loss=0.2776, pruned_loss=0.05929, codebook_loss=20.63, over 7237.00 frames.], tot_loss[loss=2.237, simple_loss=0.2695, pruned_loss=0.04953, codebook_loss=20.53, over 1333123.45 frames.], batch size: 25, lr: 1.17e-03
+2022-05-27 16:53:34,423 INFO [train.py:823] (1/4) Epoch 14, batch 600, loss[loss=2.308, simple_loss=0.2509, pruned_loss=0.0417, codebook_loss=21.41, over 7382.00 frames.], tot_loss[loss=2.235, simple_loss=0.2673, pruned_loss=0.04874, codebook_loss=20.52, over 1353975.76 frames.], batch size: 19, lr: 1.17e-03
+2022-05-27 16:54:14,397 INFO [train.py:823] (1/4) Epoch 14, batch 650, loss[loss=2.172, simple_loss=0.2337, pruned_loss=0.03408, codebook_loss=20.21, over 7296.00 frames.], tot_loss[loss=2.232, simple_loss=0.2677, pruned_loss=0.04863, codebook_loss=20.49, over 1367459.22 frames.], batch size: 17, lr: 1.16e-03
+2022-05-27 16:54:54,550 INFO [train.py:823] (1/4) Epoch 14, batch 700, loss[loss=2.297, simple_loss=0.2886, pruned_loss=0.05717, codebook_loss=20.95, over 7281.00 frames.], tot_loss[loss=2.233, simple_loss=0.2679, pruned_loss=0.04888, codebook_loss=20.5, over 1375870.03 frames.], batch size: 21, lr: 1.16e-03
+2022-05-27 16:55:33,993 INFO [train.py:823] (1/4) Epoch 14, batch 750, loss[loss=2.241, simple_loss=0.2916, pruned_loss=0.06556, codebook_loss=20.3, over 7114.00 frames.], tot_loss[loss=2.239, simple_loss=0.2693, pruned_loss=0.04973, codebook_loss=20.54, over 1386581.89 frames.], batch size: 20, lr: 1.16e-03
+2022-05-27 16:56:14,275 INFO [train.py:823] (1/4) Epoch 14, batch 800, loss[loss=2.202, simple_loss=0.2529, pruned_loss=0.03952, codebook_loss=20.36, over 7193.00 frames.], tot_loss[loss=2.241, simple_loss=0.2693, pruned_loss=0.04992, codebook_loss=20.56, over 1393048.44 frames.], batch size: 19, lr: 1.16e-03
+2022-05-27 16:56:54,063 INFO [train.py:823] (1/4) Epoch 14, batch 850, loss[loss=2.18, simple_loss=0.2781, pruned_loss=0.0404, codebook_loss=20.01, over 7273.00 frames.], tot_loss[loss=2.239, simple_loss=0.2689, pruned_loss=0.04992, codebook_loss=20.55, over 1396555.31 frames.], batch size: 20, lr: 1.16e-03
+2022-05-27 16:57:34,187 INFO [train.py:823] (1/4) Epoch 14, batch 900, loss[loss=2.188, simple_loss=0.2704, pruned_loss=0.04273, codebook_loss=20.1, over 7018.00 frames.], tot_loss[loss=2.242, simple_loss=0.2689, pruned_loss=0.04971, codebook_loss=20.58, over 1400832.79 frames.], batch size: 17, lr: 1.15e-03
+2022-05-27 16:58:27,976 INFO [train.py:823] (1/4) Epoch 15, batch 0, loss[loss=2.155, simple_loss=0.2469, pruned_loss=0.03807, codebook_loss=19.93, over 7201.00 frames.], tot_loss[loss=2.155, simple_loss=0.2469, pruned_loss=0.03807, codebook_loss=19.93, over 7201.00 frames.], batch size: 19, lr: 1.12e-03
+2022-05-27 16:59:07,736 INFO [train.py:823] (1/4) Epoch 15, batch 50, loss[loss=2.213, simple_loss=0.2433, pruned_loss=0.04667, codebook_loss=20.45, over 7189.00 frames.], tot_loss[loss=2.229, simple_loss=0.271, pruned_loss=0.04981, codebook_loss=20.44, over 319378.95 frames.], batch size: 18, lr: 1.12e-03
+2022-05-27 16:59:47,349 INFO [train.py:823] (1/4) Epoch 15, batch 100, loss[loss=2.383, simple_loss=0.2803, pruned_loss=0.0519, codebook_loss=21.91, over 7407.00 frames.], tot_loss[loss=2.22, simple_loss=0.2671, pruned_loss=0.04832, codebook_loss=20.38, over 558828.35 frames.], batch size: 22, lr: 1.11e-03
+2022-05-27 17:00:27,642 INFO [train.py:823] (1/4) Epoch 15, batch 150, loss[loss=2.348, simple_loss=0.2403, pruned_loss=0.04753, codebook_loss=21.8, over 7295.00 frames.], tot_loss[loss=2.217, simple_loss=0.2654, pruned_loss=0.04772, codebook_loss=20.36, over 752263.05 frames.], batch size: 17, lr: 1.11e-03
+2022-05-27 17:01:07,280 INFO [train.py:823] (1/4) Epoch 15, batch 200, loss[loss=2.268, simple_loss=0.2743, pruned_loss=0.05148, codebook_loss=20.79, over 7161.00 frames.], tot_loss[loss=2.229, simple_loss=0.2666, pruned_loss=0.04824, codebook_loss=20.48, over 898715.05 frames.], batch size: 23, lr: 1.11e-03
+2022-05-27 17:01:47,509 INFO [train.py:823] (1/4) Epoch 15, batch 250, loss[loss=2.087, simple_loss=0.2414, pruned_loss=0.02691, codebook_loss=19.39, over 6514.00 frames.], tot_loss[loss=2.228, simple_loss=0.2672, pruned_loss=0.04814, codebook_loss=20.46, over 1015364.96 frames.], batch size: 34, lr: 1.11e-03
+2022-05-27 17:02:27,349 INFO [train.py:823] (1/4) Epoch 15, batch 300, loss[loss=2.294, simple_loss=0.2796, pruned_loss=0.05614, codebook_loss=20.98, over 7193.00 frames.], tot_loss[loss=2.223, simple_loss=0.2662, pruned_loss=0.04797, codebook_loss=20.42, over 1105028.20 frames.], batch size: 18, lr: 1.11e-03
+2022-05-27 17:03:08,873 INFO [train.py:823] (1/4) Epoch 15, batch 350, loss[loss=2.171, simple_loss=0.2672, pruned_loss=0.04455, codebook_loss=19.93, over 7377.00 frames.], tot_loss[loss=2.222, simple_loss=0.2674, pruned_loss=0.04786, codebook_loss=20.4, over 1177331.64 frames.], batch size: 20, lr: 1.10e-03
+2022-05-27 17:03:48,661 INFO [train.py:823] (1/4) Epoch 15, batch 400, loss[loss=2.148, simple_loss=0.2683, pruned_loss=0.03872, codebook_loss=19.75, over 7098.00 frames.], tot_loss[loss=2.226, simple_loss=0.2671, pruned_loss=0.04764, codebook_loss=20.44, over 1228584.89 frames.], batch size: 19, lr: 1.10e-03
+2022-05-27 17:04:28,839 INFO [train.py:823] (1/4) Epoch 15, batch 450, loss[loss=2.198, simple_loss=0.2821, pruned_loss=0.05541, codebook_loss=20.01, over 7236.00 frames.], tot_loss[loss=2.223, simple_loss=0.2664, pruned_loss=0.04736, codebook_loss=20.42, over 1276489.29 frames.], batch size: 24, lr: 1.10e-03
+2022-05-27 17:05:08,682 INFO [train.py:823] (1/4) Epoch 15, batch 500, loss[loss=2.166, simple_loss=0.2932, pruned_loss=0.05406, codebook_loss=19.66, over 7125.00 frames.], tot_loss[loss=2.219, simple_loss=0.267, pruned_loss=0.04739, codebook_loss=20.38, over 1311811.94 frames.], batch size: 20, lr: 1.10e-03
+2022-05-27 17:05:48,661 INFO [train.py:823] (1/4) Epoch 15, batch 550, loss[loss=2.147, simple_loss=0.2398, pruned_loss=0.03609, codebook_loss=19.91, over 7028.00 frames.], tot_loss[loss=2.219, simple_loss=0.2673, pruned_loss=0.04773, codebook_loss=20.38, over 1331534.18 frames.], batch size: 17, lr: 1.10e-03
+2022-05-27 17:06:28,766 INFO [train.py:823] (1/4) Epoch 15, batch 600, loss[loss=2.279, simple_loss=0.267, pruned_loss=0.05302, codebook_loss=20.93, over 7290.00 frames.], tot_loss[loss=2.225, simple_loss=0.2673, pruned_loss=0.04761, codebook_loss=20.44, over 1355716.88 frames.], batch size: 19, lr: 1.10e-03
+2022-05-27 17:07:08,784 INFO [train.py:823] (1/4) Epoch 15, batch 650, loss[loss=2.232, simple_loss=0.2778, pruned_loss=0.04733, codebook_loss=20.46, over 7171.00 frames.], tot_loss[loss=2.224, simple_loss=0.2677, pruned_loss=0.04782, codebook_loss=20.42, over 1367640.01 frames.], batch size: 22, lr: 1.09e-03
+2022-05-27 17:07:51,622 INFO [train.py:823] (1/4) Epoch 15, batch 700, loss[loss=2.243, simple_loss=0.2728, pruned_loss=0.04965, codebook_loss=20.57, over 6903.00 frames.], tot_loss[loss=2.223, simple_loss=0.2673, pruned_loss=0.04778, codebook_loss=20.42, over 1382522.50 frames.], batch size: 29, lr: 1.09e-03
+2022-05-27 17:08:32,971 INFO [train.py:823] (1/4) Epoch 15, batch 750, loss[loss=2.223, simple_loss=0.2744, pruned_loss=0.05101, codebook_loss=20.35, over 4775.00 frames.], tot_loss[loss=2.221, simple_loss=0.2673, pruned_loss=0.04784, codebook_loss=20.39, over 1385617.91 frames.], batch size: 47, lr: 1.09e-03
+2022-05-27 17:09:12,735 INFO [train.py:823] (1/4) Epoch 15, batch 800, loss[loss=2.1, simple_loss=0.237, pruned_loss=0.03329, codebook_loss=19.48, over 7197.00 frames.], tot_loss[loss=2.218, simple_loss=0.2674, pruned_loss=0.04727, codebook_loss=20.37, over 1390074.48 frames.], batch size: 19, lr: 1.09e-03
+2022-05-27 17:09:53,056 INFO [train.py:823] (1/4) Epoch 15, batch 850, loss[loss=2.428, simple_loss=0.2936, pruned_loss=0.07348, codebook_loss=22.08, over 7208.00 frames.], tot_loss[loss=2.218, simple_loss=0.2665, pruned_loss=0.04726, codebook_loss=20.38, over 1394921.89 frames.], batch size: 25, lr: 1.09e-03
+2022-05-27 17:10:33,290 INFO [train.py:823] (1/4) Epoch 15, batch 900, loss[loss=2.175, simple_loss=0.2662, pruned_loss=0.04811, codebook_loss=19.93, over 7090.00 frames.], tot_loss[loss=2.222, simple_loss=0.2675, pruned_loss=0.04776, codebook_loss=20.41, over 1399779.89 frames.], batch size: 19, lr: 1.09e-03
+2022-05-27 17:11:13,321 INFO [train.py:823] (1/4) Epoch 15, batch 950, loss[loss=2.206, simple_loss=0.2672, pruned_loss=0.0567, codebook_loss=20.16, over 4746.00 frames.], tot_loss[loss=2.223, simple_loss=0.2676, pruned_loss=0.0478, codebook_loss=20.41, over 1381080.09 frames.], batch size: 46, lr: 1.08e-03
+2022-05-27 17:11:28,488 INFO [train.py:823] (1/4) Epoch 16, batch 0, loss[loss=2.088, simple_loss=0.2589, pruned_loss=0.03651, codebook_loss=19.22, over 5155.00 frames.], tot_loss[loss=2.088, simple_loss=0.2589, pruned_loss=0.03651, codebook_loss=19.22, over 5155.00 frames.], batch size: 47, lr: 1.05e-03
+2022-05-27 17:12:08,305 INFO [train.py:823] (1/4) Epoch 16, batch 50, loss[loss=2.138, simple_loss=0.2272, pruned_loss=0.0391, codebook_loss=19.86, over 7018.00 frames.], tot_loss[loss=2.151, simple_loss=0.2589, pruned_loss=0.04156, codebook_loss=19.8, over 318884.96 frames.], batch size: 16, lr: 1.05e-03
+2022-05-27 17:12:48,662 INFO [train.py:823] (1/4) Epoch 16, batch 100, loss[loss=2.12, simple_loss=0.2678, pruned_loss=0.03641, codebook_loss=19.49, over 7203.00 frames.], tot_loss[loss=2.184, simple_loss=0.2598, pruned_loss=0.04349, codebook_loss=20.11, over 560756.47 frames.], batch size: 19, lr: 1.05e-03
+2022-05-27 17:13:28,990 INFO [train.py:823] (1/4) Epoch 16, batch 150, loss[loss=2.159, simple_loss=0.2612, pruned_loss=0.05381, codebook_loss=19.74, over 7402.00 frames.], tot_loss[loss=2.185, simple_loss=0.2607, pruned_loss=0.04412, codebook_loss=20.1, over 756175.59 frames.], batch size: 19, lr: 1.05e-03
+2022-05-27 17:14:09,506 INFO [train.py:823] (1/4) Epoch 16, batch 200, loss[loss=2.248, simple_loss=0.2857, pruned_loss=0.05426, codebook_loss=20.51, over 7170.00 frames.], tot_loss[loss=2.199, simple_loss=0.2633, pruned_loss=0.04551, codebook_loss=20.22, over 904234.88 frames.], batch size: 23, lr: 1.05e-03
+2022-05-27 17:14:49,493 INFO [train.py:823] (1/4) Epoch 16, batch 250, loss[loss=2.242, simple_loss=0.289, pruned_loss=0.06425, codebook_loss=20.34, over 7220.00 frames.], tot_loss[loss=2.197, simple_loss=0.2642, pruned_loss=0.04593, codebook_loss=20.19, over 1013068.72 frames.], batch size: 25, lr: 1.04e-03
+2022-05-27 17:15:29,983 INFO [train.py:823] (1/4) Epoch 16, batch 300, loss[loss=2.406, simple_loss=0.305, pruned_loss=0.0808, codebook_loss=21.73, over 7260.00 frames.], tot_loss[loss=2.199, simple_loss=0.2637, pruned_loss=0.0455, codebook_loss=20.21, over 1106088.19 frames.], batch size: 24, lr: 1.04e-03
+2022-05-27 17:16:09,525 INFO [train.py:823] (1/4) Epoch 16, batch 350, loss[loss=2.162, simple_loss=0.2693, pruned_loss=0.04668, codebook_loss=19.8, over 7336.00 frames.], tot_loss[loss=2.209, simple_loss=0.2651, pruned_loss=0.04699, codebook_loss=20.3, over 1173328.42 frames.], batch size: 23, lr: 1.04e-03
+2022-05-27 17:16:49,904 INFO [train.py:823] (1/4) Epoch 16, batch 400, loss[loss=2.165, simple_loss=0.2456, pruned_loss=0.04508, codebook_loss=19.97, over 7292.00 frames.], tot_loss[loss=2.199, simple_loss=0.2644, pruned_loss=0.04604, codebook_loss=20.21, over 1228523.17 frames.], batch size: 19, lr: 1.04e-03
+2022-05-27 17:17:29,838 INFO [train.py:823] (1/4) Epoch 16, batch 450, loss[loss=2.378, simple_loss=0.2919, pruned_loss=0.05703, codebook_loss=21.75, over 7405.00 frames.], tot_loss[loss=2.203, simple_loss=0.2651, pruned_loss=0.04623, codebook_loss=20.24, over 1275783.12 frames.], batch size: 22, lr: 1.04e-03
+2022-05-27 17:18:10,095 INFO [train.py:823] (1/4) Epoch 16, batch 500, loss[loss=2.222, simple_loss=0.2784, pruned_loss=0.04853, codebook_loss=20.34, over 6927.00 frames.], tot_loss[loss=2.204, simple_loss=0.2651, pruned_loss=0.04629, codebook_loss=20.25, over 1311362.79 frames.], batch size: 29, lr: 1.04e-03
+2022-05-27 17:18:49,958 INFO [train.py:823] (1/4) Epoch 16, batch 550, loss[loss=2.277, simple_loss=0.3, pruned_loss=0.05298, codebook_loss=20.74, over 7380.00 frames.], tot_loss[loss=2.201, simple_loss=0.2658, pruned_loss=0.04639, codebook_loss=20.21, over 1329592.72 frames.], batch size: 21, lr: 1.03e-03
+2022-05-27 17:19:30,268 INFO [train.py:823] (1/4) Epoch 16, batch 600, loss[loss=2.202, simple_loss=0.259, pruned_loss=0.03602, codebook_loss=20.36, over 7117.00 frames.], tot_loss[loss=2.2, simple_loss=0.2657, pruned_loss=0.04616, codebook_loss=20.21, over 1345281.72 frames.], batch size: 19, lr: 1.03e-03
+2022-05-27 17:20:09,985 INFO [train.py:823] (1/4) Epoch 16, batch 650, loss[loss=2.252, simple_loss=0.2534, pruned_loss=0.03711, codebook_loss=20.88, over 7203.00 frames.], tot_loss[loss=2.206, simple_loss=0.2665, pruned_loss=0.04644, codebook_loss=20.27, over 1361359.17 frames.], batch size: 16, lr: 1.03e-03
+2022-05-27 17:20:50,259 INFO [train.py:823] (1/4) Epoch 16, batch 700, loss[loss=2.05, simple_loss=0.2255, pruned_loss=0.02673, codebook_loss=19.1, over 7299.00 frames.], tot_loss[loss=2.207, simple_loss=0.2654, pruned_loss=0.04602, codebook_loss=20.28, over 1370199.47 frames.], batch size: 19, lr: 1.03e-03
+2022-05-27 17:21:29,860 INFO [train.py:823] (1/4) Epoch 16, batch 750, loss[loss=2.207, simple_loss=0.2499, pruned_loss=0.05391, codebook_loss=20.28, over 7195.00 frames.], tot_loss[loss=2.209, simple_loss=0.2664, pruned_loss=0.04676, codebook_loss=20.29, over 1382580.48 frames.], batch size: 18, lr: 1.03e-03
+2022-05-27 17:22:09,879 INFO [train.py:823] (1/4) Epoch 16, batch 800, loss[loss=2.409, simple_loss=0.2852, pruned_loss=0.05818, codebook_loss=22.09, over 7384.00 frames.], tot_loss[loss=2.21, simple_loss=0.2669, pruned_loss=0.04686, codebook_loss=20.3, over 1393197.42 frames.], batch size: 20, lr: 1.03e-03
+2022-05-27 17:22:49,730 INFO [train.py:823] (1/4) Epoch 16, batch 850, loss[loss=2.17, simple_loss=0.2805, pruned_loss=0.04265, codebook_loss=19.87, over 7190.00 frames.], tot_loss[loss=2.206, simple_loss=0.2665, pruned_loss=0.04665, codebook_loss=20.26, over 1400301.49 frames.], batch size: 21, lr: 1.03e-03
+2022-05-27 17:23:29,826 INFO [train.py:823] (1/4) Epoch 16, batch 900, loss[loss=2.226, simple_loss=0.2693, pruned_loss=0.05162, codebook_loss=20.4, over 7026.00 frames.], tot_loss[loss=2.201, simple_loss=0.2657, pruned_loss=0.0462, codebook_loss=20.22, over 1400833.37 frames.], batch size: 17, lr: 1.02e-03
+2022-05-27 17:24:23,412 INFO [train.py:823] (1/4) Epoch 17, batch 0, loss[loss=2.093, simple_loss=0.2514, pruned_loss=0.03119, codebook_loss=19.36, over 7192.00 frames.], tot_loss[loss=2.093, simple_loss=0.2514, pruned_loss=0.03119, codebook_loss=19.36, over 7192.00 frames.], batch size: 21, lr: 9.94e-04
+2022-05-27 17:25:03,612 INFO [train.py:823] (1/4) Epoch 17, batch 50, loss[loss=2.109, simple_loss=0.2622, pruned_loss=0.02946, codebook_loss=19.48, over 6998.00 frames.], tot_loss[loss=2.208, simple_loss=0.2666, pruned_loss=0.04664, codebook_loss=20.28, over 315225.62 frames.], batch size: 26, lr: 9.92e-04
+2022-05-27 17:25:43,293 INFO [train.py:823] (1/4) Epoch 17, batch 100, loss[loss=2.119, simple_loss=0.2641, pruned_loss=0.03393, codebook_loss=19.53, over 7019.00 frames.], tot_loss[loss=2.192, simple_loss=0.2659, pruned_loss=0.04504, codebook_loss=20.14, over 560731.90 frames.], batch size: 26, lr: 9.91e-04
+2022-05-27 17:26:24,353 INFO [train.py:823] (1/4) Epoch 17, batch 150, loss[loss=2.061, simple_loss=0.2362, pruned_loss=0.02753, codebook_loss=19.15, over 7195.00 frames.], tot_loss[loss=2.183, simple_loss=0.2648, pruned_loss=0.04527, codebook_loss=20.06, over 748940.06 frames.], batch size: 18, lr: 9.89e-04
+2022-05-27 17:27:04,183 INFO [train.py:823] (1/4) Epoch 17, batch 200, loss[loss=2.214, simple_loss=0.2946, pruned_loss=0.06272, codebook_loss=20.04, over 6951.00 frames.], tot_loss[loss=2.187, simple_loss=0.2657, pruned_loss=0.04538, codebook_loss=20.09, over 897614.68 frames.], batch size: 29, lr: 9.88e-04
+2022-05-27 17:27:44,507 INFO [train.py:823] (1/4) Epoch 17, batch 250, loss[loss=2.185, simple_loss=0.2735, pruned_loss=0.05753, codebook_loss=19.91, over 7332.00 frames.], tot_loss[loss=2.181, simple_loss=0.2649, pruned_loss=0.04522, codebook_loss=20.03, over 1018412.98 frames.], batch size: 23, lr: 9.86e-04
+2022-05-27 17:28:23,995 INFO [train.py:823] (1/4) Epoch 17, batch 300, loss[loss=2.168, simple_loss=0.2573, pruned_loss=0.05319, codebook_loss=19.86, over 7298.00 frames.], tot_loss[loss=2.177, simple_loss=0.2646, pruned_loss=0.0448, codebook_loss=20, over 1104100.57 frames.], batch size: 18, lr: 9.85e-04
+2022-05-27 17:29:04,140 INFO [train.py:823] (1/4) Epoch 17, batch 350, loss[loss=2.115, simple_loss=0.255, pruned_loss=0.03837, codebook_loss=19.49, over 7397.00 frames.], tot_loss[loss=2.178, simple_loss=0.2635, pruned_loss=0.04436, codebook_loss=20.02, over 1170736.07 frames.], batch size: 19, lr: 9.84e-04
+2022-05-27 17:29:43,927 INFO [train.py:823] (1/4) Epoch 17, batch 400, loss[loss=2.113, simple_loss=0.2595, pruned_loss=0.04135, codebook_loss=19.42, over 7097.00 frames.], tot_loss[loss=2.189, simple_loss=0.2625, pruned_loss=0.04445, codebook_loss=20.13, over 1226781.03 frames.], batch size: 19, lr: 9.82e-04
+2022-05-27 17:30:24,094 INFO [train.py:823] (1/4) Epoch 17, batch 450, loss[loss=2.217, simple_loss=0.2892, pruned_loss=0.06449, codebook_loss=20.08, over 4918.00 frames.], tot_loss[loss=2.189, simple_loss=0.2618, pruned_loss=0.04392, codebook_loss=20.14, over 1261609.97 frames.], batch size: 48, lr: 9.81e-04
+2022-05-27 17:31:03,720 INFO [train.py:823] (1/4) Epoch 17, batch 500, loss[loss=2.189, simple_loss=0.2282, pruned_loss=0.03702, codebook_loss=20.38, over 7000.00 frames.], tot_loss[loss=2.187, simple_loss=0.2619, pruned_loss=0.04383, codebook_loss=20.13, over 1297508.51 frames.], batch size: 16, lr: 9.79e-04
+2022-05-27 17:31:43,972 INFO [train.py:823] (1/4) Epoch 17, batch 550, loss[loss=2.144, simple_loss=0.2708, pruned_loss=0.03667, codebook_loss=19.72, over 7120.00 frames.], tot_loss[loss=2.188, simple_loss=0.2623, pruned_loss=0.04417, codebook_loss=20.13, over 1327112.02 frames.], batch size: 20, lr: 9.78e-04
+2022-05-27 17:32:26,191 INFO [train.py:823] (1/4) Epoch 17, batch 600, loss[loss=2.106, simple_loss=0.2613, pruned_loss=0.03734, codebook_loss=19.38, over 7306.00 frames.], tot_loss[loss=2.197, simple_loss=0.2625, pruned_loss=0.04427, codebook_loss=20.22, over 1349623.01 frames.], batch size: 22, lr: 9.76e-04
+2022-05-27 17:33:07,632 INFO [train.py:823] (1/4) Epoch 17, batch 650, loss[loss=2.161, simple_loss=0.2295, pruned_loss=0.03308, codebook_loss=20.14, over 7022.00 frames.], tot_loss[loss=2.197, simple_loss=0.2623, pruned_loss=0.04451, codebook_loss=20.22, over 1363176.76 frames.], batch size: 16, lr: 9.75e-04
+2022-05-27 17:33:47,422 INFO [train.py:823] (1/4) Epoch 17, batch 700, loss[loss=2.083, simple_loss=0.2284, pruned_loss=0.03545, codebook_loss=19.33, over 6806.00 frames.], tot_loss[loss=2.193, simple_loss=0.2618, pruned_loss=0.04402, codebook_loss=20.18, over 1374754.66 frames.], batch size: 15, lr: 9.74e-04
+2022-05-27 17:34:27,710 INFO [train.py:823] (1/4) Epoch 17, batch 750, loss[loss=2.082, simple_loss=0.2291, pruned_loss=0.02772, codebook_loss=19.4, over 7160.00 frames.], tot_loss[loss=2.192, simple_loss=0.2626, pruned_loss=0.04453, codebook_loss=20.16, over 1386370.70 frames.], batch size: 17, lr: 9.72e-04
+2022-05-27 17:35:07,559 INFO [train.py:823] (1/4) Epoch 17, batch 800, loss[loss=2.082, simple_loss=0.2304, pruned_loss=0.03189, codebook_loss=19.35, over 6997.00 frames.], tot_loss[loss=2.191, simple_loss=0.2628, pruned_loss=0.0447, codebook_loss=20.15, over 1389098.65 frames.], batch size: 16, lr: 9.71e-04
+2022-05-27 17:35:50,776 INFO [train.py:823] (1/4) Epoch 17, batch 850, loss[loss=2.273, simple_loss=0.2967, pruned_loss=0.06153, codebook_loss=20.64, over 7409.00 frames.], tot_loss[loss=2.184, simple_loss=0.2619, pruned_loss=0.04405, codebook_loss=20.09, over 1395576.86 frames.], batch size: 22, lr: 9.69e-04
+2022-05-27 17:36:30,810 INFO [train.py:823] (1/4) Epoch 17, batch 900, loss[loss=2.088, simple_loss=0.2316, pruned_loss=0.03672, codebook_loss=19.36, over 7299.00 frames.], tot_loss[loss=2.181, simple_loss=0.2611, pruned_loss=0.04395, codebook_loss=20.06, over 1402048.40 frames.], batch size: 17, lr: 9.68e-04
+2022-05-27 17:37:10,656 INFO [train.py:823] (1/4) Epoch 17, batch 950, loss[loss=2.21, simple_loss=0.2714, pruned_loss=0.04971, codebook_loss=20.24, over 4799.00 frames.], tot_loss[loss=2.182, simple_loss=0.262, pruned_loss=0.04465, codebook_loss=20.06, over 1397463.20 frames.], batch size: 47, lr: 9.67e-04
+2022-05-27 17:37:26,035 INFO [train.py:823] (1/4) Epoch 18, batch 0, loss[loss=2.125, simple_loss=0.2718, pruned_loss=0.04374, codebook_loss=19.45, over 7376.00 frames.], tot_loss[loss=2.125, simple_loss=0.2718, pruned_loss=0.04374, codebook_loss=19.45, over 7376.00 frames.], batch size: 21, lr: 9.41e-04
+2022-05-27 17:38:06,268 INFO [train.py:823] (1/4) Epoch 18, batch 50, loss[loss=2.135, simple_loss=0.2765, pruned_loss=0.04865, codebook_loss=19.48, over 7348.00 frames.], tot_loss[loss=2.182, simple_loss=0.2599, pruned_loss=0.04327, codebook_loss=20.09, over 321769.34 frames.], batch size: 23, lr: 9.40e-04
+2022-05-27 17:38:46,066 INFO [train.py:823] (1/4) Epoch 18, batch 100, loss[loss=2.139, simple_loss=0.271, pruned_loss=0.0515, codebook_loss=19.52, over 7279.00 frames.], tot_loss[loss=2.172, simple_loss=0.2619, pruned_loss=0.04342, codebook_loss=19.97, over 563165.73 frames.], batch size: 20, lr: 9.39e-04
+2022-05-27 17:39:26,378 INFO [train.py:823] (1/4) Epoch 18, batch 150, loss[loss=2.098, simple_loss=0.2574, pruned_loss=0.04537, codebook_loss=19.23, over 7196.00 frames.], tot_loss[loss=2.174, simple_loss=0.2608, pruned_loss=0.0429, codebook_loss=20.01, over 756738.39 frames.], batch size: 20, lr: 9.37e-04
+2022-05-27 17:40:06,124 INFO [train.py:823] (1/4) Epoch 18, batch 200, loss[loss=2.141, simple_loss=0.2829, pruned_loss=0.05056, codebook_loss=19.49, over 7279.00 frames.], tot_loss[loss=2.165, simple_loss=0.2604, pruned_loss=0.04246, codebook_loss=19.92, over 906928.02 frames.], batch size: 21, lr: 9.36e-04
+2022-05-27 17:40:46,121 INFO [train.py:823] (1/4) Epoch 18, batch 250, loss[loss=2.109, simple_loss=0.2687, pruned_loss=0.04359, codebook_loss=19.31, over 7301.00 frames.], tot_loss[loss=2.169, simple_loss=0.2617, pruned_loss=0.04351, codebook_loss=19.95, over 1016110.06 frames.], batch size: 22, lr: 9.35e-04
+2022-05-27 17:41:26,324 INFO [train.py:823] (1/4) Epoch 18, batch 300, loss[loss=2.456, simple_loss=0.246, pruned_loss=0.0453, codebook_loss=22.87, over 7433.00 frames.], tot_loss[loss=2.176, simple_loss=0.2622, pruned_loss=0.04439, codebook_loss=20, over 1106428.59 frames.], batch size: 18, lr: 9.33e-04
+2022-05-27 17:42:06,844 INFO [train.py:823] (1/4) Epoch 18, batch 350, loss[loss=2.203, simple_loss=0.2761, pruned_loss=0.05913, codebook_loss=20.06, over 7282.00 frames.], tot_loss[loss=2.169, simple_loss=0.2618, pruned_loss=0.04413, codebook_loss=19.94, over 1175733.34 frames.], batch size: 20, lr: 9.32e-04
+2022-05-27 17:42:46,672 INFO [train.py:823] (1/4) Epoch 18, batch 400, loss[loss=2.123, simple_loss=0.2404, pruned_loss=0.03744, codebook_loss=19.65, over 7381.00 frames.], tot_loss[loss=2.168, simple_loss=0.2624, pruned_loss=0.0442, codebook_loss=19.92, over 1227244.17 frames.], batch size: 19, lr: 9.31e-04
+2022-05-27 17:43:26,812 INFO [train.py:823] (1/4) Epoch 18, batch 450, loss[loss=2.102, simple_loss=0.2686, pruned_loss=0.03974, codebook_loss=19.28, over 7163.00 frames.], tot_loss[loss=2.169, simple_loss=0.263, pruned_loss=0.04398, codebook_loss=19.93, over 1270391.35 frames.], batch size: 23, lr: 9.29e-04
+2022-05-27 17:44:06,719 INFO [train.py:823] (1/4) Epoch 18, batch 500, loss[loss=2.11, simple_loss=0.2845, pruned_loss=0.0375, codebook_loss=19.3, over 7413.00 frames.], tot_loss[loss=2.168, simple_loss=0.2625, pruned_loss=0.04364, codebook_loss=19.93, over 1308144.12 frames.], batch size: 22, lr: 9.28e-04
+2022-05-27 17:44:47,102 INFO [train.py:823] (1/4) Epoch 18, batch 550, loss[loss=2.07, simple_loss=0.2628, pruned_loss=0.03769, codebook_loss=19.01, over 7329.00 frames.], tot_loss[loss=2.168, simple_loss=0.2617, pruned_loss=0.04335, codebook_loss=19.93, over 1335900.70 frames.], batch size: 23, lr: 9.27e-04
+2022-05-27 17:45:26,660 INFO [train.py:823] (1/4) Epoch 18, batch 600, loss[loss=2.164, simple_loss=0.2481, pruned_loss=0.03603, codebook_loss=20.04, over 7282.00 frames.], tot_loss[loss=2.167, simple_loss=0.2609, pruned_loss=0.04293, codebook_loss=19.94, over 1357721.73 frames.], batch size: 19, lr: 9.26e-04
+2022-05-27 17:46:06,507 INFO [train.py:823] (1/4) Epoch 18, batch 650, loss[loss=2.059, simple_loss=0.2487, pruned_loss=0.03747, codebook_loss=18.97, over 7101.00 frames.], tot_loss[loss=2.165, simple_loss=0.261, pruned_loss=0.04284, codebook_loss=19.91, over 1371954.76 frames.], batch size: 19, lr: 9.24e-04
+2022-05-27 17:46:46,418 INFO [train.py:823] (1/4) Epoch 18, batch 700, loss[loss=2.029, simple_loss=0.2459, pruned_loss=0.03002, codebook_loss=18.76, over 7197.00 frames.], tot_loss[loss=2.164, simple_loss=0.261, pruned_loss=0.04315, codebook_loss=19.9, over 1376247.89 frames.], batch size: 19, lr: 9.23e-04
+2022-05-27 17:47:26,792 INFO [train.py:823] (1/4) Epoch 18, batch 750, loss[loss=2.046, simple_loss=0.2276, pruned_loss=0.02424, codebook_loss=19.08, over 7098.00 frames.], tot_loss[loss=2.164, simple_loss=0.2609, pruned_loss=0.04291, codebook_loss=19.91, over 1387924.43 frames.], batch size: 18, lr: 9.22e-04
+2022-05-27 17:48:06,490 INFO [train.py:823] (1/4) Epoch 18, batch 800, loss[loss=2.221, simple_loss=0.2561, pruned_loss=0.04026, codebook_loss=20.52, over 7194.00 frames.], tot_loss[loss=2.165, simple_loss=0.2604, pruned_loss=0.04272, codebook_loss=19.92, over 1392026.48 frames.], batch size: 20, lr: 9.21e-04
+2022-05-27 17:48:46,496 INFO [train.py:823] (1/4) Epoch 18, batch 850, loss[loss=2.107, simple_loss=0.2791, pruned_loss=0.04598, codebook_loss=19.22, over 7180.00 frames.], tot_loss[loss=2.16, simple_loss=0.2597, pruned_loss=0.04228, codebook_loss=19.88, over 1395095.75 frames.], batch size: 21, lr: 9.19e-04
+2022-05-27 17:49:26,190 INFO [train.py:823] (1/4) Epoch 18, batch 900, loss[loss=2.072, simple_loss=0.2247, pruned_loss=0.03077, codebook_loss=19.28, over 7159.00 frames.], tot_loss[loss=2.168, simple_loss=0.2601, pruned_loss=0.04274, codebook_loss=19.95, over 1401934.25 frames.], batch size: 17, lr: 9.18e-04
+2022-05-27 17:50:07,354 INFO [train.py:823] (1/4) Epoch 18, batch 950, loss[loss=2.266, simple_loss=0.2716, pruned_loss=0.05291, codebook_loss=20.77, over 5164.00 frames.], tot_loss[loss=2.168, simple_loss=0.2602, pruned_loss=0.0427, codebook_loss=19.96, over 1375890.26 frames.], batch size: 46, lr: 9.17e-04
+2022-05-27 17:50:22,767 INFO [train.py:823] (1/4) Epoch 19, batch 0, loss[loss=2.088, simple_loss=0.2735, pruned_loss=0.04526, codebook_loss=19.06, over 7012.00 frames.], tot_loss[loss=2.088, simple_loss=0.2735, pruned_loss=0.04526, codebook_loss=19.06, over 7012.00 frames.], batch size: 26, lr: 8.94e-04
+2022-05-27 17:51:02,611 INFO [train.py:823] (1/4) Epoch 19, batch 50, loss[loss=2.047, simple_loss=0.2407, pruned_loss=0.02847, codebook_loss=18.98, over 7187.00 frames.], tot_loss[loss=2.14, simple_loss=0.253, pruned_loss=0.03895, codebook_loss=19.75, over 325638.68 frames.], batch size: 19, lr: 8.92e-04
+2022-05-27 17:51:43,090 INFO [train.py:823] (1/4) Epoch 19, batch 100, loss[loss=2.115, simple_loss=0.2633, pruned_loss=0.03131, codebook_loss=19.52, over 6554.00 frames.], tot_loss[loss=2.143, simple_loss=0.2546, pruned_loss=0.03984, codebook_loss=19.76, over 566245.83 frames.], batch size: 34, lr: 8.91e-04
+2022-05-27 17:52:23,019 INFO [train.py:823] (1/4) Epoch 19, batch 150, loss[loss=1.996, simple_loss=0.2284, pruned_loss=0.02657, codebook_loss=18.55, over 7094.00 frames.], tot_loss[loss=2.152, simple_loss=0.2555, pruned_loss=0.04117, codebook_loss=19.83, over 758714.30 frames.], batch size: 18, lr: 8.90e-04
+2022-05-27 17:53:03,234 INFO [train.py:823] (1/4) Epoch 19, batch 200, loss[loss=2.147, simple_loss=0.2654, pruned_loss=0.05146, codebook_loss=19.63, over 7175.00 frames.], tot_loss[loss=2.155, simple_loss=0.2569, pruned_loss=0.04191, codebook_loss=19.85, over 901566.92 frames.], batch size: 22, lr: 8.89e-04
+2022-05-27 17:53:42,983 INFO [train.py:823] (1/4) Epoch 19, batch 250, loss[loss=2.088, simple_loss=0.2573, pruned_loss=0.03918, codebook_loss=19.21, over 7118.00 frames.], tot_loss[loss=2.15, simple_loss=0.2578, pruned_loss=0.0417, codebook_loss=19.79, over 1017976.77 frames.], batch size: 19, lr: 8.88e-04
+2022-05-27 17:54:23,016 INFO [train.py:823] (1/4) Epoch 19, batch 300, loss[loss=2.1, simple_loss=0.2383, pruned_loss=0.03507, codebook_loss=19.46, over 7009.00 frames.], tot_loss[loss=2.159, simple_loss=0.2587, pruned_loss=0.04246, codebook_loss=19.87, over 1110083.84 frames.], batch size: 16, lr: 8.87e-04
+2022-05-27 17:55:02,852 INFO [train.py:823] (1/4) Epoch 19, batch 350, loss[loss=2.162, simple_loss=0.3099, pruned_loss=0.06879, codebook_loss=19.38, over 7314.00 frames.], tot_loss[loss=2.153, simple_loss=0.2597, pruned_loss=0.04254, codebook_loss=19.8, over 1177471.48 frames.], batch size: 18, lr: 8.85e-04
+2022-05-27 17:55:43,655 INFO [train.py:823] (1/4) Epoch 19, batch 400, loss[loss=2.283, simple_loss=0.2382, pruned_loss=0.03359, codebook_loss=21.3, over 7017.00 frames.], tot_loss[loss=2.153, simple_loss=0.2602, pruned_loss=0.04263, codebook_loss=19.8, over 1235055.68 frames.], batch size: 16, lr: 8.84e-04
+2022-05-27 17:56:23,370 INFO [train.py:823] (1/4) Epoch 19, batch 450, loss[loss=2.219, simple_loss=0.282, pruned_loss=0.052, codebook_loss=20.26, over 7141.00 frames.], tot_loss[loss=2.157, simple_loss=0.2606, pruned_loss=0.04277, codebook_loss=19.84, over 1277048.05 frames.], batch size: 23, lr: 8.83e-04
+2022-05-27 17:57:06,159 INFO [train.py:823] (1/4) Epoch 19, batch 500, loss[loss=2.209, simple_loss=0.2729, pruned_loss=0.0447, codebook_loss=20.28, over 6519.00 frames.], tot_loss[loss=2.155, simple_loss=0.2599, pruned_loss=0.04235, codebook_loss=19.83, over 1310057.46 frames.], batch size: 34, lr: 8.82e-04
+2022-05-27 17:57:47,349 INFO [train.py:823] (1/4) Epoch 19, batch 550, loss[loss=2.065, simple_loss=0.2267, pruned_loss=0.03443, codebook_loss=19.17, over 7022.00 frames.], tot_loss[loss=2.154, simple_loss=0.2594, pruned_loss=0.04197, codebook_loss=19.82, over 1332813.60 frames.], batch size: 17, lr: 8.81e-04
+2022-05-27 17:58:27,513 INFO [train.py:823] (1/4) Epoch 19, batch 600, loss[loss=2.514, simple_loss=0.2839, pruned_loss=0.07003, codebook_loss=23.02, over 7101.00 frames.], tot_loss[loss=2.154, simple_loss=0.2596, pruned_loss=0.04201, codebook_loss=19.82, over 1352661.02 frames.], batch size: 19, lr: 8.80e-04
+2022-05-27 17:59:07,245 INFO [train.py:823] (1/4) Epoch 19, batch 650, loss[loss=2.002, simple_loss=0.2264, pruned_loss=0.02291, codebook_loss=18.66, over 7431.00 frames.], tot_loss[loss=2.156, simple_loss=0.2593, pruned_loss=0.04212, codebook_loss=19.85, over 1367283.40 frames.], batch size: 18, lr: 8.78e-04
+2022-05-27 17:59:47,324 INFO [train.py:823] (1/4) Epoch 19, batch 700, loss[loss=2.064, simple_loss=0.2624, pruned_loss=0.0372, codebook_loss=18.95, over 6977.00 frames.], tot_loss[loss=2.152, simple_loss=0.2587, pruned_loss=0.04169, codebook_loss=19.81, over 1378039.12 frames.], batch size: 26, lr: 8.77e-04
+2022-05-27 18:00:27,375 INFO [train.py:823] (1/4) Epoch 19, batch 750, loss[loss=2.082, simple_loss=0.2559, pruned_loss=0.03726, codebook_loss=19.17, over 7375.00 frames.], tot_loss[loss=2.151, simple_loss=0.2581, pruned_loss=0.04143, codebook_loss=19.81, over 1389729.38 frames.], batch size: 21, lr: 8.76e-04
+2022-05-27 18:01:07,500 INFO [train.py:823] (1/4) Epoch 19, batch 800, loss[loss=2.184, simple_loss=0.2714, pruned_loss=0.0449, codebook_loss=20.03, over 7312.00 frames.], tot_loss[loss=2.155, simple_loss=0.2586, pruned_loss=0.04173, codebook_loss=19.84, over 1398716.66 frames.], batch size: 22, lr: 8.75e-04
+2022-05-27 18:01:47,273 INFO [train.py:823] (1/4) Epoch 19, batch 850, loss[loss=2.149, simple_loss=0.2579, pruned_loss=0.03611, codebook_loss=19.84, over 7386.00 frames.], tot_loss[loss=2.161, simple_loss=0.259, pruned_loss=0.04189, codebook_loss=19.89, over 1403499.84 frames.], batch size: 21, lr: 8.74e-04
+2022-05-27 18:02:27,147 INFO [train.py:823] (1/4) Epoch 19, batch 900, loss[loss=2.093, simple_loss=0.2618, pruned_loss=0.03707, codebook_loss=19.25, over 7029.00 frames.], tot_loss[loss=2.165, simple_loss=0.26, pruned_loss=0.04277, codebook_loss=19.92, over 1393411.70 frames.], batch size: 26, lr: 8.73e-04
+2022-05-27 18:03:20,011 INFO [train.py:823] (1/4) Epoch 20, batch 0, loss[loss=2.099, simple_loss=0.257, pruned_loss=0.03967, codebook_loss=19.31, over 6502.00 frames.], tot_loss[loss=2.099, simple_loss=0.257, pruned_loss=0.03967, codebook_loss=19.31, over 6502.00 frames.], batch size: 34, lr: 8.51e-04
+2022-05-27 18:04:00,441 INFO [train.py:823] (1/4) Epoch 20, batch 50, loss[loss=2.132, simple_loss=0.2568, pruned_loss=0.04302, codebook_loss=19.61, over 7296.00 frames.], tot_loss[loss=2.133, simple_loss=0.2603, pruned_loss=0.03921, codebook_loss=19.64, over 322458.19 frames.], batch size: 18, lr: 8.49e-04
+2022-05-27 18:04:40,160 INFO [train.py:823] (1/4) Epoch 20, batch 100, loss[loss=2.151, simple_loss=0.2693, pruned_loss=0.04993, codebook_loss=19.67, over 4719.00 frames.], tot_loss[loss=2.144, simple_loss=0.2596, pruned_loss=0.04039, codebook_loss=19.73, over 561857.89 frames.], batch size: 46, lr: 8.48e-04
+2022-05-27 18:05:20,190 INFO [train.py:823] (1/4) Epoch 20, batch 150, loss[loss=2.176, simple_loss=0.2372, pruned_loss=0.04064, codebook_loss=20.17, over 7293.00 frames.], tot_loss[loss=2.149, simple_loss=0.2581, pruned_loss=0.04078, codebook_loss=19.79, over 751450.44 frames.], batch size: 17, lr: 8.47e-04
+2022-05-27 18:05:59,937 INFO [train.py:823] (1/4) Epoch 20, batch 200, loss[loss=2.066, simple_loss=0.2206, pruned_loss=0.03261, codebook_loss=19.23, over 7004.00 frames.], tot_loss[loss=2.14, simple_loss=0.257, pruned_loss=0.04068, codebook_loss=19.71, over 902554.66 frames.], batch size: 16, lr: 8.46e-04
+2022-05-27 18:06:40,070 INFO [train.py:823] (1/4) Epoch 20, batch 250, loss[loss=2.311, simple_loss=0.2421, pruned_loss=0.03716, codebook_loss=21.52, over 7305.00 frames.], tot_loss[loss=2.164, simple_loss=0.2576, pruned_loss=0.04163, codebook_loss=19.93, over 1017441.11 frames.], batch size: 18, lr: 8.45e-04
+2022-05-27 18:07:19,809 INFO [train.py:823] (1/4) Epoch 20, batch 300, loss[loss=2.214, simple_loss=0.2942, pruned_loss=0.06165, codebook_loss=20.05, over 7292.00 frames.], tot_loss[loss=2.16, simple_loss=0.2587, pruned_loss=0.04198, codebook_loss=19.89, over 1107388.31 frames.], batch size: 22, lr: 8.44e-04
+2022-05-27 18:08:00,063 INFO [train.py:823] (1/4) Epoch 20, batch 350, loss[loss=2.097, simple_loss=0.266, pruned_loss=0.04428, codebook_loss=19.2, over 7207.00 frames.], tot_loss[loss=2.156, simple_loss=0.2587, pruned_loss=0.04154, codebook_loss=19.85, over 1176473.67 frames.], batch size: 20, lr: 8.43e-04
+2022-05-27 18:08:40,166 INFO [train.py:823] (1/4) Epoch 20, batch 400, loss[loss=2.118, simple_loss=0.2647, pruned_loss=0.04599, codebook_loss=19.39, over 7152.00 frames.], tot_loss[loss=2.156, simple_loss=0.2579, pruned_loss=0.0411, codebook_loss=19.86, over 1231891.63 frames.], batch size: 23, lr: 8.42e-04
+2022-05-27 18:09:20,011 INFO [train.py:823] (1/4) Epoch 20, batch 450, loss[loss=2.048, simple_loss=0.2171, pruned_loss=0.02949, codebook_loss=19.1, over 7153.00 frames.], tot_loss[loss=2.151, simple_loss=0.2578, pruned_loss=0.04079, codebook_loss=19.81, over 1270286.53 frames.], batch size: 17, lr: 8.41e-04
+2022-05-27 18:09:59,752 INFO [train.py:823] (1/4) Epoch 20, batch 500, loss[loss=2.21, simple_loss=0.2553, pruned_loss=0.04727, codebook_loss=20.35, over 7016.00 frames.], tot_loss[loss=2.153, simple_loss=0.2577, pruned_loss=0.04067, codebook_loss=19.84, over 1306230.86 frames.], batch size: 17, lr: 8.40e-04
+2022-05-27 18:10:40,039 INFO [train.py:823] (1/4) Epoch 20, batch 550, loss[loss=2.089, simple_loss=0.256, pruned_loss=0.04113, codebook_loss=19.2, over 7156.00 frames.], tot_loss[loss=2.152, simple_loss=0.2569, pruned_loss=0.04061, codebook_loss=19.83, over 1334613.22 frames.], batch size: 23, lr: 8.39e-04
+2022-05-27 18:11:19,658 INFO [train.py:823] (1/4) Epoch 20, batch 600, loss[loss=2.628, simple_loss=0.275, pruned_loss=0.0581, codebook_loss=24.32, over 7101.00 frames.], tot_loss[loss=2.16, simple_loss=0.2576, pruned_loss=0.04128, codebook_loss=19.9, over 1349823.43 frames.], batch size: 18, lr: 8.38e-04
+2022-05-27 18:11:59,850 INFO [train.py:823] (1/4) Epoch 20, batch 650, loss[loss=2.147, simple_loss=0.2784, pruned_loss=0.04502, codebook_loss=19.63, over 7041.00 frames.], tot_loss[loss=2.151, simple_loss=0.2569, pruned_loss=0.0407, codebook_loss=19.82, over 1365387.50 frames.], batch size: 29, lr: 8.37e-04
+2022-05-27 18:12:39,853 INFO [train.py:823] (1/4) Epoch 20, batch 700, loss[loss=2.079, simple_loss=0.239, pruned_loss=0.03543, codebook_loss=19.24, over 7096.00 frames.], tot_loss[loss=2.148, simple_loss=0.256, pruned_loss=0.04026, codebook_loss=19.8, over 1380646.90 frames.], batch size: 18, lr: 8.36e-04
+2022-05-27 18:13:20,087 INFO [train.py:823] (1/4) Epoch 20, batch 750, loss[loss=2.052, simple_loss=0.2578, pruned_loss=0.03324, codebook_loss=18.9, over 7279.00 frames.], tot_loss[loss=2.147, simple_loss=0.2556, pruned_loss=0.04031, codebook_loss=19.79, over 1391193.79 frames.], batch size: 21, lr: 8.35e-04
+2022-05-27 18:13:59,603 INFO [train.py:823] (1/4) Epoch 20, batch 800, loss[loss=2.089, simple_loss=0.2447, pruned_loss=0.02788, codebook_loss=19.38, over 7017.00 frames.], tot_loss[loss=2.145, simple_loss=0.2568, pruned_loss=0.04029, codebook_loss=19.76, over 1398845.08 frames.], batch size: 17, lr: 8.34e-04
+2022-05-27 18:14:41,112 INFO [train.py:823] (1/4) Epoch 20, batch 850, loss[loss=2.014, simple_loss=0.2529, pruned_loss=0.02479, codebook_loss=18.63, over 7040.00 frames.], tot_loss[loss=2.145, simple_loss=0.2554, pruned_loss=0.03968, codebook_loss=19.77, over 1402154.41 frames.], batch size: 26, lr: 8.33e-04
+2022-05-27 18:15:20,824 INFO [train.py:823] (1/4) Epoch 20, batch 900, loss[loss=2.107, simple_loss=0.2431, pruned_loss=0.04413, codebook_loss=19.41, over 6774.00 frames.], tot_loss[loss=2.148, simple_loss=0.2567, pruned_loss=0.04044, codebook_loss=19.79, over 1399367.44 frames.], batch size: 15, lr: 8.31e-04
+2022-05-27 18:16:14,136 INFO [train.py:823] (1/4) Epoch 21, batch 0, loss[loss=2.021, simple_loss=0.2357, pruned_loss=0.03204, codebook_loss=18.71, over 7197.00 frames.], tot_loss[loss=2.021, simple_loss=0.2357, pruned_loss=0.03204, codebook_loss=18.71, over 7197.00 frames.], batch size: 18, lr: 8.11e-04
+2022-05-27 18:16:54,245 INFO [train.py:823] (1/4) Epoch 21, batch 50, loss[loss=2.047, simple_loss=0.257, pruned_loss=0.0352, codebook_loss=18.83, over 7238.00 frames.], tot_loss[loss=2.133, simple_loss=0.2552, pruned_loss=0.03882, codebook_loss=19.66, over 318338.56 frames.], batch size: 25, lr: 8.10e-04
+2022-05-27 18:17:33,854 INFO [train.py:823] (1/4) Epoch 21, batch 100, loss[loss=2.031, simple_loss=0.2444, pruned_loss=0.02827, codebook_loss=18.8, over 6414.00 frames.], tot_loss[loss=2.115, simple_loss=0.2522, pruned_loss=0.03756, codebook_loss=19.52, over 561747.28 frames.], batch size: 34, lr: 8.09e-04
+2022-05-27 18:18:14,066 INFO [train.py:823] (1/4) Epoch 21, batch 150, loss[loss=2.169, simple_loss=0.2792, pruned_loss=0.04535, codebook_loss=19.84, over 7276.00 frames.], tot_loss[loss=2.127, simple_loss=0.2541, pruned_loss=0.03976, codebook_loss=19.6, over 755308.07 frames.], batch size: 20, lr: 8.08e-04
+2022-05-27 18:18:54,155 INFO [train.py:823] (1/4) Epoch 21, batch 200, loss[loss=2.07, simple_loss=0.2228, pruned_loss=0.03094, codebook_loss=19.27, over 7306.00 frames.], tot_loss[loss=2.128, simple_loss=0.2542, pruned_loss=0.0395, codebook_loss=19.61, over 903517.31 frames.], batch size: 18, lr: 8.07e-04
+2022-05-27 18:19:34,330 INFO [train.py:823] (1/4) Epoch 21, batch 250, loss[loss=2.032, simple_loss=0.2365, pruned_loss=0.03053, codebook_loss=18.83, over 7273.00 frames.], tot_loss[loss=2.124, simple_loss=0.2542, pruned_loss=0.0396, codebook_loss=19.57, over 1012188.89 frames.], batch size: 20, lr: 8.06e-04
+2022-05-27 18:20:13,830 INFO [train.py:823] (1/4) Epoch 21, batch 300, loss[loss=2.069, simple_loss=0.262, pruned_loss=0.03788, codebook_loss=19, over 6588.00 frames.], tot_loss[loss=2.129, simple_loss=0.2545, pruned_loss=0.03962, codebook_loss=19.62, over 1100400.63 frames.], batch size: 34, lr: 8.05e-04
+2022-05-27 18:20:53,789 INFO [train.py:823] (1/4) Epoch 21, batch 350, loss[loss=2.067, simple_loss=0.2673, pruned_loss=0.03517, codebook_loss=18.98, over 7411.00 frames.], tot_loss[loss=2.125, simple_loss=0.2545, pruned_loss=0.0388, codebook_loss=19.59, over 1171395.74 frames.], batch size: 22, lr: 8.04e-04
+2022-05-27 18:21:36,252 INFO [train.py:823] (1/4) Epoch 21, batch 400, loss[loss=2.138, simple_loss=0.2337, pruned_loss=0.03383, codebook_loss=19.87, over 7297.00 frames.], tot_loss[loss=2.132, simple_loss=0.256, pruned_loss=0.03977, codebook_loss=19.65, over 1226491.01 frames.], batch size: 17, lr: 8.03e-04
+2022-05-27 18:22:17,603 INFO [train.py:823] (1/4) Epoch 21, batch 450, loss[loss=2.082, simple_loss=0.2588, pruned_loss=0.03631, codebook_loss=19.16, over 7186.00 frames.], tot_loss[loss=2.135, simple_loss=0.2562, pruned_loss=0.0395, codebook_loss=19.67, over 1270883.82 frames.], batch size: 21, lr: 8.02e-04
+2022-05-27 18:22:57,212 INFO [train.py:823] (1/4) Epoch 21, batch 500, loss[loss=2.123, simple_loss=0.2368, pruned_loss=0.03416, codebook_loss=19.7, over 7183.00 frames.], tot_loss[loss=2.132, simple_loss=0.2562, pruned_loss=0.03929, codebook_loss=19.65, over 1303981.90 frames.], batch size: 18, lr: 8.01e-04
+2022-05-27 18:23:37,551 INFO [train.py:823] (1/4) Epoch 21, batch 550, loss[loss=2.057, simple_loss=0.2652, pruned_loss=0.03465, codebook_loss=18.9, over 7377.00 frames.], tot_loss[loss=2.129, simple_loss=0.2557, pruned_loss=0.03933, codebook_loss=19.62, over 1335405.63 frames.], batch size: 21, lr: 8.00e-04
+2022-05-27 18:24:17,351 INFO [train.py:823] (1/4) Epoch 21, batch 600, loss[loss=2.213, simple_loss=0.2749, pruned_loss=0.04091, codebook_loss=20.35, over 6408.00 frames.], tot_loss[loss=2.136, simple_loss=0.2565, pruned_loss=0.04039, codebook_loss=19.68, over 1352921.66 frames.], batch size: 34, lr: 8.00e-04
+2022-05-27 18:24:57,532 INFO [train.py:823] (1/4) Epoch 21, batch 650, loss[loss=2.158, simple_loss=0.2555, pruned_loss=0.03837, codebook_loss=19.92, over 7309.00 frames.], tot_loss[loss=2.142, simple_loss=0.2576, pruned_loss=0.04091, codebook_loss=19.72, over 1368854.36 frames.], batch size: 22, lr: 7.99e-04
+2022-05-27 18:25:36,983 INFO [train.py:823] (1/4) Epoch 21, batch 700, loss[loss=2.119, simple_loss=0.2567, pruned_loss=0.03916, codebook_loss=19.51, over 7184.00 frames.], tot_loss[loss=2.146, simple_loss=0.2586, pruned_loss=0.04157, codebook_loss=19.75, over 1379970.90 frames.], batch size: 20, lr: 7.98e-04
+2022-05-27 18:26:16,779 INFO [train.py:823] (1/4) Epoch 21, batch 750, loss[loss=2.186, simple_loss=0.277, pruned_loss=0.05123, codebook_loss=19.96, over 7207.00 frames.], tot_loss[loss=2.139, simple_loss=0.2567, pruned_loss=0.04083, codebook_loss=19.69, over 1378402.86 frames.], batch size: 25, lr: 7.97e-04
+2022-05-27 18:26:56,284 INFO [train.py:823] (1/4) Epoch 21, batch 800, loss[loss=2.058, simple_loss=0.2455, pruned_loss=0.02947, codebook_loss=19.05, over 7351.00 frames.], tot_loss[loss=2.133, simple_loss=0.2562, pruned_loss=0.04007, codebook_loss=19.65, over 1384002.19 frames.], batch size: 23, lr: 7.96e-04
+2022-05-27 18:27:36,614 INFO [train.py:823] (1/4) Epoch 21, batch 850, loss[loss=2.229, simple_loss=0.2611, pruned_loss=0.03619, codebook_loss=20.62, over 7190.00 frames.], tot_loss[loss=2.129, simple_loss=0.2552, pruned_loss=0.03969, codebook_loss=19.62, over 1388565.93 frames.], batch size: 20, lr: 7.95e-04
+2022-05-27 18:28:15,982 INFO [train.py:823] (1/4) Epoch 21, batch 900, loss[loss=2.053, simple_loss=0.2604, pruned_loss=0.0335, codebook_loss=18.9, over 7361.00 frames.], tot_loss[loss=2.127, simple_loss=0.255, pruned_loss=0.03963, codebook_loss=19.6, over 1386291.04 frames.], batch size: 20, lr: 7.94e-04
+2022-05-27 18:29:10,588 INFO [train.py:823] (1/4) Epoch 22, batch 0, loss[loss=1.972, simple_loss=0.2425, pruned_loss=0.0233, codebook_loss=18.27, over 7380.00 frames.], tot_loss[loss=1.972, simple_loss=0.2425, pruned_loss=0.0233, codebook_loss=18.27, over 7380.00 frames.], batch size: 21, lr: 7.75e-04
+2022-05-27 18:29:50,465 INFO [train.py:823] (1/4) Epoch 22, batch 50, loss[loss=2.239, simple_loss=0.2741, pruned_loss=0.05194, codebook_loss=20.5, over 7175.00 frames.], tot_loss[loss=2.092, simple_loss=0.2484, pruned_loss=0.03601, codebook_loss=19.32, over 321284.61 frames.], batch size: 22, lr: 7.74e-04
+2022-05-27 18:30:30,766 INFO [train.py:823] (1/4) Epoch 22, batch 100, loss[loss=2.25, simple_loss=0.2771, pruned_loss=0.0561, codebook_loss=20.55, over 7110.00 frames.], tot_loss[loss=2.1, simple_loss=0.251, pruned_loss=0.03714, codebook_loss=19.37, over 567964.59 frames.], batch size: 20, lr: 7.73e-04
+2022-05-27 18:31:10,249 INFO [train.py:823] (1/4) Epoch 22, batch 150, loss[loss=2.197, simple_loss=0.2855, pruned_loss=0.06474, codebook_loss=19.89, over 4889.00 frames.], tot_loss[loss=2.119, simple_loss=0.2547, pruned_loss=0.03911, codebook_loss=19.53, over 754699.48 frames.], batch size: 47, lr: 7.73e-04
+2022-05-27 18:31:50,144 INFO [train.py:823] (1/4) Epoch 22, batch 200, loss[loss=2.207, simple_loss=0.2822, pruned_loss=0.05206, codebook_loss=20.13, over 7113.00 frames.], tot_loss[loss=2.119, simple_loss=0.2561, pruned_loss=0.03905, codebook_loss=19.52, over 899062.12 frames.], batch size: 20, lr: 7.72e-04
+2022-05-27 18:32:29,931 INFO [train.py:823] (1/4) Epoch 22, batch 250, loss[loss=2.235, simple_loss=0.2336, pruned_loss=0.0297, codebook_loss=20.89, over 7085.00 frames.], tot_loss[loss=2.116, simple_loss=0.2551, pruned_loss=0.03843, codebook_loss=19.5, over 1016762.95 frames.], batch size: 18, lr: 7.71e-04
+2022-05-27 18:33:09,999 INFO [train.py:823] (1/4) Epoch 22, batch 300, loss[loss=2.064, simple_loss=0.2401, pruned_loss=0.03515, codebook_loss=19.09, over 7193.00 frames.], tot_loss[loss=2.114, simple_loss=0.2544, pruned_loss=0.03809, codebook_loss=19.49, over 1104233.73 frames.], batch size: 18, lr: 7.70e-04
+2022-05-27 18:33:49,727 INFO [train.py:823] (1/4) Epoch 22, batch 350, loss[loss=2.056, simple_loss=0.2581, pruned_loss=0.02264, codebook_loss=19.04, over 7054.00 frames.], tot_loss[loss=2.117, simple_loss=0.2555, pruned_loss=0.03885, codebook_loss=19.5, over 1175928.68 frames.], batch size: 29, lr: 7.69e-04
+2022-05-27 18:34:29,890 INFO [train.py:823] (1/4) Epoch 22, batch 400, loss[loss=2.127, simple_loss=0.2608, pruned_loss=0.03915, codebook_loss=19.57, over 7177.00 frames.], tot_loss[loss=2.117, simple_loss=0.2548, pruned_loss=0.03872, codebook_loss=19.51, over 1231457.93 frames.], batch size: 21, lr: 7.68e-04
+2022-05-27 18:35:09,680 INFO [train.py:823] (1/4) Epoch 22, batch 450, loss[loss=2.446, simple_loss=0.258, pruned_loss=0.07411, codebook_loss=22.43, over 7238.00 frames.], tot_loss[loss=2.117, simple_loss=0.2547, pruned_loss=0.03863, codebook_loss=19.51, over 1277992.98 frames.], batch size: 16, lr: 7.67e-04
+2022-05-27 18:35:49,489 INFO [train.py:823] (1/4) Epoch 22, batch 500, loss[loss=2.167, simple_loss=0.2617, pruned_loss=0.03488, codebook_loss=20.02, over 6447.00 frames.], tot_loss[loss=2.116, simple_loss=0.254, pruned_loss=0.03836, codebook_loss=19.51, over 1304178.88 frames.], batch size: 34, lr: 7.66e-04
+2022-05-27 18:36:29,479 INFO [train.py:823] (1/4) Epoch 22, batch 550, loss[loss=2.096, simple_loss=0.2585, pruned_loss=0.0316, codebook_loss=19.35, over 6914.00 frames.], tot_loss[loss=2.114, simple_loss=0.2536, pruned_loss=0.03811, codebook_loss=19.49, over 1329866.61 frames.], batch size: 29, lr: 7.65e-04
+2022-05-27 18:37:09,849 INFO [train.py:823] (1/4) Epoch 22, batch 600, loss[loss=2.152, simple_loss=0.2435, pruned_loss=0.04262, codebook_loss=19.87, over 7013.00 frames.], tot_loss[loss=2.115, simple_loss=0.2532, pruned_loss=0.03797, codebook_loss=19.5, over 1348994.39 frames.], batch size: 17, lr: 7.65e-04
+2022-05-27 18:37:49,502 INFO [train.py:823] (1/4) Epoch 22, batch 650, loss[loss=2.081, simple_loss=0.2739, pruned_loss=0.03425, codebook_loss=19.1, over 7112.00 frames.], tot_loss[loss=2.119, simple_loss=0.2539, pruned_loss=0.03867, codebook_loss=19.54, over 1359212.04 frames.], batch size: 20, lr: 7.64e-04
+2022-05-27 18:38:29,553 INFO [train.py:823] (1/4) Epoch 22, batch 700, loss[loss=2.089, simple_loss=0.2604, pruned_loss=0.04014, codebook_loss=19.19, over 7103.00 frames.], tot_loss[loss=2.121, simple_loss=0.2539, pruned_loss=0.0386, codebook_loss=19.56, over 1371888.00 frames.], batch size: 19, lr: 7.63e-04
+2022-05-27 18:39:10,342 INFO [train.py:823] (1/4) Epoch 22, batch 750, loss[loss=2.139, simple_loss=0.235, pruned_loss=0.03596, codebook_loss=19.85, over 7000.00 frames.], tot_loss[loss=2.119, simple_loss=0.2537, pruned_loss=0.03822, codebook_loss=19.53, over 1381705.02 frames.], batch size: 16, lr: 7.62e-04
+2022-05-27 18:39:50,603 INFO [train.py:823] (1/4) Epoch 22, batch 800, loss[loss=2.177, simple_loss=0.2339, pruned_loss=0.03726, codebook_loss=20.22, over 7372.00 frames.], tot_loss[loss=2.12, simple_loss=0.2531, pruned_loss=0.03779, codebook_loss=19.56, over 1391744.44 frames.], batch size: 20, lr: 7.61e-04
+2022-05-27 18:40:30,204 INFO [train.py:823] (1/4) Epoch 22, batch 850, loss[loss=2.167, simple_loss=0.2791, pruned_loss=0.0467, codebook_loss=19.81, over 6620.00 frames.], tot_loss[loss=2.114, simple_loss=0.2535, pruned_loss=0.03771, codebook_loss=19.5, over 1400003.72 frames.], batch size: 34, lr: 7.60e-04
+2022-05-27 18:41:10,116 INFO [train.py:823] (1/4) Epoch 22, batch 900, loss[loss=2.056, simple_loss=0.2672, pruned_loss=0.04489, codebook_loss=18.78, over 7159.00 frames.], tot_loss[loss=2.112, simple_loss=0.2542, pruned_loss=0.03779, codebook_loss=19.48, over 1404926.76 frames.], batch size: 23, lr: 7.59e-04
+2022-05-27 18:42:03,935 INFO [train.py:823] (1/4) Epoch 23, batch 0, loss[loss=2.02, simple_loss=0.2164, pruned_loss=0.02746, codebook_loss=18.84, over 6820.00 frames.], tot_loss[loss=2.02, simple_loss=0.2164, pruned_loss=0.02746, codebook_loss=18.84, over 6820.00 frames.], batch size: 15, lr: 7.42e-04
+2022-05-27 18:42:44,102 INFO [train.py:823] (1/4) Epoch 23, batch 50, loss[loss=2.34, simple_loss=0.2676, pruned_loss=0.04729, codebook_loss=21.59, over 7367.00 frames.], tot_loss[loss=2.15, simple_loss=0.2534, pruned_loss=0.03786, codebook_loss=19.86, over 321251.93 frames.], batch size: 21, lr: 7.41e-04
+2022-05-27 18:43:23,809 INFO [train.py:823] (1/4) Epoch 23, batch 100, loss[loss=2.356, simple_loss=0.2595, pruned_loss=0.04109, codebook_loss=21.85, over 7381.00 frames.], tot_loss[loss=2.118, simple_loss=0.2536, pruned_loss=0.03756, codebook_loss=19.54, over 563105.37 frames.], batch size: 20, lr: 7.41e-04
+2022-05-27 18:44:03,967 INFO [train.py:823] (1/4) Epoch 23, batch 150, loss[loss=2.016, simple_loss=0.2212, pruned_loss=0.02728, codebook_loss=18.78, over 7311.00 frames.], tot_loss[loss=2.115, simple_loss=0.2543, pruned_loss=0.03797, codebook_loss=19.5, over 752642.94 frames.], batch size: 18, lr: 7.40e-04
+2022-05-27 18:44:43,909 INFO [train.py:823] (1/4) Epoch 23, batch 200, loss[loss=2.056, simple_loss=0.2506, pruned_loss=0.0354, codebook_loss=18.95, over 4856.00 frames.], tot_loss[loss=2.111, simple_loss=0.2532, pruned_loss=0.03776, codebook_loss=19.46, over 899515.87 frames.], batch size: 48, lr: 7.39e-04
+2022-05-27 18:45:24,179 INFO [train.py:823] (1/4) Epoch 23, batch 250, loss[loss=2.244, simple_loss=0.2479, pruned_loss=0.03007, codebook_loss=20.9, over 7108.00 frames.], tot_loss[loss=2.114, simple_loss=0.2531, pruned_loss=0.03775, codebook_loss=19.5, over 1018947.25 frames.], batch size: 18, lr: 7.38e-04
+2022-05-27 18:46:03,753 INFO [train.py:823] (1/4) Epoch 23, batch 300, loss[loss=2.098, simple_loss=0.2644, pruned_loss=0.04029, codebook_loss=19.26, over 7296.00 frames.], tot_loss[loss=2.109, simple_loss=0.2538, pruned_loss=0.03756, codebook_loss=19.44, over 1111510.74 frames.], batch size: 22, lr: 7.37e-04
+2022-05-27 18:46:48,079 INFO [train.py:823] (1/4) Epoch 23, batch 350, loss[loss=2.187, simple_loss=0.27, pruned_loss=0.04586, codebook_loss=20.06, over 7287.00 frames.], tot_loss[loss=2.101, simple_loss=0.2526, pruned_loss=0.03727, codebook_loss=19.38, over 1182285.27 frames.], batch size: 20, lr: 7.36e-04
+2022-05-27 18:47:28,146 INFO [train.py:823] (1/4) Epoch 23, batch 400, loss[loss=2.246, simple_loss=0.2163, pruned_loss=0.03495, codebook_loss=21.03, over 7302.00 frames.], tot_loss[loss=2.105, simple_loss=0.2508, pruned_loss=0.03698, codebook_loss=19.43, over 1234437.81 frames.], batch size: 17, lr: 7.36e-04
+2022-05-27 18:48:08,281 INFO [train.py:823] (1/4) Epoch 23, batch 450, loss[loss=2.231, simple_loss=0.2684, pruned_loss=0.04337, codebook_loss=20.53, over 5052.00 frames.], tot_loss[loss=2.112, simple_loss=0.2519, pruned_loss=0.03757, codebook_loss=19.48, over 1273747.77 frames.], batch size: 47, lr: 7.35e-04
+2022-05-27 18:48:47,871 INFO [train.py:823] (1/4) Epoch 23, batch 500, loss[loss=2.278, simple_loss=0.2739, pruned_loss=0.0375, codebook_loss=21.04, over 6487.00 frames.], tot_loss[loss=2.111, simple_loss=0.2527, pruned_loss=0.03757, codebook_loss=19.47, over 1303175.96 frames.], batch size: 34, lr: 7.34e-04
+2022-05-27 18:49:28,073 INFO [train.py:823] (1/4) Epoch 23, batch 550, loss[loss=2.065, simple_loss=0.2554, pruned_loss=0.03587, codebook_loss=19.02, over 7255.00 frames.], tot_loss[loss=2.116, simple_loss=0.2535, pruned_loss=0.03757, codebook_loss=19.51, over 1333751.16 frames.], batch size: 24, lr: 7.33e-04
+2022-05-27 18:50:07,729 INFO [train.py:823] (1/4) Epoch 23, batch 600, loss[loss=2.163, simple_loss=0.2675, pruned_loss=0.05756, codebook_loss=19.72, over 4728.00 frames.], tot_loss[loss=2.125, simple_loss=0.2537, pruned_loss=0.0382, codebook_loss=19.6, over 1349055.50 frames.], batch size: 47, lr: 7.32e-04
+2022-05-27 18:50:47,678 INFO [train.py:823] (1/4) Epoch 23, batch 650, loss[loss=2.055, simple_loss=0.2433, pruned_loss=0.02806, codebook_loss=19.05, over 7098.00 frames.], tot_loss[loss=2.113, simple_loss=0.2525, pruned_loss=0.03744, codebook_loss=19.49, over 1364012.05 frames.], batch size: 19, lr: 7.32e-04
+2022-05-27 18:51:27,253 INFO [train.py:823] (1/4) Epoch 23, batch 700, loss[loss=2.125, simple_loss=0.2473, pruned_loss=0.03407, codebook_loss=19.68, over 7021.00 frames.], tot_loss[loss=2.117, simple_loss=0.2534, pruned_loss=0.03805, codebook_loss=19.52, over 1370518.97 frames.], batch size: 16, lr: 7.31e-04
+2022-05-27 18:52:07,633 INFO [train.py:823] (1/4) Epoch 23, batch 750, loss[loss=2.18, simple_loss=0.2767, pruned_loss=0.05677, codebook_loss=19.85, over 5035.00 frames.], tot_loss[loss=2.117, simple_loss=0.2533, pruned_loss=0.03813, codebook_loss=19.52, over 1376687.41 frames.], batch size: 46, lr: 7.30e-04
+2022-05-27 18:52:47,392 INFO [train.py:823] (1/4) Epoch 23, batch 800, loss[loss=2.136, simple_loss=0.2454, pruned_loss=0.04204, codebook_loss=19.72, over 7191.00 frames.], tot_loss[loss=2.116, simple_loss=0.2528, pruned_loss=0.03823, codebook_loss=19.51, over 1388941.33 frames.], batch size: 18, lr: 7.29e-04
+2022-05-27 18:53:27,292 INFO [train.py:823] (1/4) Epoch 23, batch 850, loss[loss=2.161, simple_loss=0.2828, pruned_loss=0.05457, codebook_loss=19.65, over 7155.00 frames.], tot_loss[loss=2.112, simple_loss=0.2522, pruned_loss=0.0375, codebook_loss=19.48, over 1396382.53 frames.], batch size: 23, lr: 7.28e-04
+2022-05-27 18:54:07,047 INFO [train.py:823] (1/4) Epoch 23, batch 900, loss[loss=2.384, simple_loss=0.251, pruned_loss=0.04729, codebook_loss=22.11, over 7039.00 frames.], tot_loss[loss=2.113, simple_loss=0.2512, pruned_loss=0.03756, codebook_loss=19.5, over 1401594.56 frames.], batch size: 17, lr: 7.28e-04
+2022-05-27 18:55:01,281 INFO [train.py:823] (1/4) Epoch 24, batch 0, loss[loss=1.971, simple_loss=0.2232, pruned_loss=0.02196, codebook_loss=18.38, over 7307.00 frames.], tot_loss[loss=1.971, simple_loss=0.2232, pruned_loss=0.02196, codebook_loss=18.38, over 7307.00 frames.], batch size: 18, lr: 7.12e-04
+2022-05-27 18:55:40,718 INFO [train.py:823] (1/4) Epoch 24, batch 50, loss[loss=2.03, simple_loss=0.223, pruned_loss=0.0269, codebook_loss=18.91, over 7153.00 frames.], tot_loss[loss=2.086, simple_loss=0.2506, pruned_loss=0.03607, codebook_loss=19.25, over 319039.56 frames.], batch size: 17, lr: 7.11e-04
+2022-05-27 18:56:20,789 INFO [train.py:823] (1/4) Epoch 24, batch 100, loss[loss=2.121, simple_loss=0.2601, pruned_loss=0.03384, codebook_loss=19.57, over 6626.00 frames.], tot_loss[loss=2.097, simple_loss=0.252, pruned_loss=0.03744, codebook_loss=19.33, over 560111.59 frames.], batch size: 34, lr: 7.10e-04
+2022-05-27 18:57:00,439 INFO [train.py:823] (1/4) Epoch 24, batch 150, loss[loss=2.237, simple_loss=0.2731, pruned_loss=0.03868, codebook_loss=20.62, over 6901.00 frames.], tot_loss[loss=2.087, simple_loss=0.2529, pruned_loss=0.03691, codebook_loss=19.24, over 750081.10 frames.], batch size: 29, lr: 7.10e-04
+2022-05-27 18:57:40,627 INFO [train.py:823] (1/4) Epoch 24, batch 200, loss[loss=2.077, simple_loss=0.2589, pruned_loss=0.03033, codebook_loss=19.17, over 7283.00 frames.], tot_loss[loss=2.083, simple_loss=0.252, pruned_loss=0.0367, codebook_loss=19.21, over 899507.83 frames.], batch size: 21, lr: 7.09e-04
+2022-05-27 18:58:20,140 INFO [train.py:823] (1/4) Epoch 24, batch 250, loss[loss=2.275, simple_loss=0.2366, pruned_loss=0.03661, codebook_loss=21.2, over 7292.00 frames.], tot_loss[loss=2.087, simple_loss=0.251, pruned_loss=0.03611, codebook_loss=19.25, over 1014810.16 frames.], batch size: 17, lr: 7.08e-04
+2022-05-27 18:59:00,241 INFO [train.py:823] (1/4) Epoch 24, batch 300, loss[loss=2.08, simple_loss=0.2664, pruned_loss=0.04266, codebook_loss=19.05, over 7338.00 frames.], tot_loss[loss=2.101, simple_loss=0.2518, pruned_loss=0.03732, codebook_loss=19.38, over 1100247.00 frames.], batch size: 23, lr: 7.07e-04
+2022-05-27 18:59:40,305 INFO [train.py:823] (1/4) Epoch 24, batch 350, loss[loss=2.079, simple_loss=0.2319, pruned_loss=0.0323, codebook_loss=19.31, over 7289.00 frames.], tot_loss[loss=2.104, simple_loss=0.2512, pruned_loss=0.03719, codebook_loss=19.41, over 1174826.60 frames.], batch size: 17, lr: 7.07e-04
+2022-05-27 19:00:20,420 INFO [train.py:823] (1/4) Epoch 24, batch 400, loss[loss=2.004, simple_loss=0.2436, pruned_loss=0.0329, codebook_loss=18.49, over 7337.00 frames.], tot_loss[loss=2.099, simple_loss=0.2505, pruned_loss=0.03695, codebook_loss=19.37, over 1226272.46 frames.], batch size: 23, lr: 7.06e-04
+2022-05-27 19:01:00,213 INFO [train.py:823] (1/4) Epoch 24, batch 450, loss[loss=2.196, simple_loss=0.2436, pruned_loss=0.03761, codebook_loss=20.37, over 7180.00 frames.], tot_loss[loss=2.099, simple_loss=0.2512, pruned_loss=0.03716, codebook_loss=19.36, over 1267565.35 frames.], batch size: 18, lr: 7.05e-04
+2022-05-27 19:01:40,618 INFO [train.py:823] (1/4) Epoch 24, batch 500, loss[loss=2.108, simple_loss=0.2659, pruned_loss=0.03928, codebook_loss=19.36, over 7285.00 frames.], tot_loss[loss=2.1, simple_loss=0.2519, pruned_loss=0.03722, codebook_loss=19.37, over 1303718.01 frames.], batch size: 21, lr: 7.04e-04
+2022-05-27 19:02:20,506 INFO [train.py:823] (1/4) Epoch 24, batch 550, loss[loss=2.052, simple_loss=0.2589, pruned_loss=0.02481, codebook_loss=18.98, over 6503.00 frames.], tot_loss[loss=2.098, simple_loss=0.2518, pruned_loss=0.03675, codebook_loss=19.36, over 1327625.26 frames.], batch size: 34, lr: 7.04e-04
+2022-05-27 19:03:01,849 INFO [train.py:823] (1/4) Epoch 24, batch 600, loss[loss=2.035, simple_loss=0.2581, pruned_loss=0.03432, codebook_loss=18.72, over 7149.00 frames.], tot_loss[loss=2.099, simple_loss=0.2526, pruned_loss=0.03694, codebook_loss=19.36, over 1346385.93 frames.], batch size: 23, lr: 7.03e-04
+2022-05-27 19:03:41,791 INFO [train.py:823] (1/4) Epoch 24, batch 650, loss[loss=2.158, simple_loss=0.2609, pruned_loss=0.04659, codebook_loss=19.81, over 7102.00 frames.], tot_loss[loss=2.098, simple_loss=0.2524, pruned_loss=0.03671, codebook_loss=19.35, over 1359369.10 frames.], batch size: 19, lr: 7.02e-04
+2022-05-27 19:04:21,959 INFO [train.py:823] (1/4) Epoch 24, batch 700, loss[loss=2.06, simple_loss=0.2662, pruned_loss=0.0434, codebook_loss=18.84, over 7171.00 frames.], tot_loss[loss=2.099, simple_loss=0.2525, pruned_loss=0.0366, codebook_loss=19.36, over 1373552.19 frames.], batch size: 22, lr: 7.01e-04
+2022-05-27 19:05:01,649 INFO [train.py:823] (1/4) Epoch 24, batch 750, loss[loss=2.03, simple_loss=0.2534, pruned_loss=0.03883, codebook_loss=18.64, over 7113.00 frames.], tot_loss[loss=2.092, simple_loss=0.2519, pruned_loss=0.03626, codebook_loss=19.3, over 1385772.65 frames.], batch size: 20, lr: 7.01e-04
+2022-05-27 19:05:41,778 INFO [train.py:823] (1/4) Epoch 24, batch 800, loss[loss=2.158, simple_loss=0.2248, pruned_loss=0.03555, codebook_loss=20.1, over 6815.00 frames.], tot_loss[loss=2.098, simple_loss=0.2513, pruned_loss=0.03636, codebook_loss=19.36, over 1392968.09 frames.], batch size: 15, lr: 7.00e-04
+2022-05-27 19:06:21,579 INFO [train.py:823] (1/4) Epoch 24, batch 850, loss[loss=2.03, simple_loss=0.2447, pruned_loss=0.02639, codebook_loss=18.81, over 7111.00 frames.], tot_loss[loss=2.096, simple_loss=0.2509, pruned_loss=0.03619, codebook_loss=19.35, over 1396416.94 frames.], batch size: 20, lr: 6.99e-04
+2022-05-27 19:07:01,702 INFO [train.py:823] (1/4) Epoch 24, batch 900, loss[loss=2.257, simple_loss=0.2708, pruned_loss=0.04663, codebook_loss=20.75, over 6525.00 frames.], tot_loss[loss=2.1, simple_loss=0.2509, pruned_loss=0.03637, codebook_loss=19.38, over 1398715.02 frames.], batch size: 34, lr: 6.98e-04
+2022-05-27 19:07:42,332 INFO [train.py:823] (1/4) Epoch 24, batch 950, loss[loss=2.014, simple_loss=0.2344, pruned_loss=0.02799, codebook_loss=18.69, over 7098.00 frames.], tot_loss[loss=2.104, simple_loss=0.2513, pruned_loss=0.0365, codebook_loss=19.42, over 1394978.30 frames.], batch size: 18, lr: 6.98e-04
+2022-05-27 19:07:57,244 INFO [train.py:823] (1/4) Epoch 25, batch 0, loss[loss=1.925, simple_loss=0.2423, pruned_loss=0.01777, codebook_loss=17.86, over 7284.00 frames.], tot_loss[loss=1.925, simple_loss=0.2423, pruned_loss=0.01777, codebook_loss=17.86, over 7284.00 frames.], batch size: 21, lr: 6.84e-04
+2022-05-27 19:08:37,518 INFO [train.py:823] (1/4) Epoch 25, batch 50, loss[loss=2.06, simple_loss=0.2294, pruned_loss=0.03283, codebook_loss=19.12, over 7307.00 frames.], tot_loss[loss=2.095, simple_loss=0.2504, pruned_loss=0.03574, codebook_loss=19.34, over 324429.92 frames.], batch size: 17, lr: 6.83e-04
+2022-05-27 19:09:17,677 INFO [train.py:823] (1/4) Epoch 25, batch 100, loss[loss=2.095, simple_loss=0.2301, pruned_loss=0.03678, codebook_loss=19.44, over 7256.00 frames.], tot_loss[loss=2.098, simple_loss=0.2503, pruned_loss=0.03643, codebook_loss=19.36, over 564418.63 frames.], batch size: 16, lr: 6.82e-04
+2022-05-27 19:09:58,091 INFO [train.py:823] (1/4) Epoch 25, batch 150, loss[loss=2.11, simple_loss=0.2506, pruned_loss=0.02984, codebook_loss=19.55, over 7309.00 frames.], tot_loss[loss=2.098, simple_loss=0.2475, pruned_loss=0.03521, codebook_loss=19.39, over 759483.52 frames.], batch size: 22, lr: 6.82e-04
+2022-05-27 19:10:38,128 INFO [train.py:823] (1/4) Epoch 25, batch 200, loss[loss=2.015, simple_loss=0.2409, pruned_loss=0.02891, codebook_loss=18.65, over 7286.00 frames.], tot_loss[loss=2.088, simple_loss=0.2484, pruned_loss=0.03552, codebook_loss=19.28, over 911205.79 frames.], batch size: 21, lr: 6.81e-04
+2022-05-27 19:11:21,039 INFO [train.py:823] (1/4) Epoch 25, batch 250, loss[loss=2.027, simple_loss=0.2189, pruned_loss=0.02455, codebook_loss=18.93, over 7297.00 frames.], tot_loss[loss=2.083, simple_loss=0.2487, pruned_loss=0.03564, codebook_loss=19.23, over 1022539.54 frames.], batch size: 17, lr: 6.80e-04
+2022-05-27 19:12:03,741 INFO [train.py:823] (1/4) Epoch 25, batch 300, loss[loss=1.952, simple_loss=0.254, pruned_loss=0.02313, codebook_loss=18.01, over 7292.00 frames.], tot_loss[loss=2.082, simple_loss=0.2494, pruned_loss=0.03548, codebook_loss=19.22, over 1116498.44 frames.], batch size: 21, lr: 6.80e-04
+2022-05-27 19:12:48,185 INFO [train.py:823] (1/4) Epoch 25, batch 350, loss[loss=2.304, simple_loss=0.2807, pruned_loss=0.04509, codebook_loss=21.19, over 7137.00 frames.], tot_loss[loss=2.082, simple_loss=0.2492, pruned_loss=0.03549, codebook_loss=19.22, over 1182458.43 frames.], batch size: 23, lr: 6.79e-04
+2022-05-27 19:13:30,514 INFO [train.py:823] (1/4) Epoch 25, batch 400, loss[loss=2.06, simple_loss=0.2567, pruned_loss=0.04511, codebook_loss=18.87, over 7197.00 frames.], tot_loss[loss=2.081, simple_loss=0.251, pruned_loss=0.03586, codebook_loss=19.2, over 1239269.42 frames.], batch size: 25, lr: 6.78e-04
+2022-05-27 19:14:15,047 INFO [train.py:823] (1/4) Epoch 25, batch 450, loss[loss=2.121, simple_loss=0.2432, pruned_loss=0.04939, codebook_loss=19.5, over 6807.00 frames.], tot_loss[loss=2.089, simple_loss=0.252, pruned_loss=0.03654, codebook_loss=19.27, over 1269806.50 frames.], batch size: 15, lr: 6.77e-04
+2022-05-27 19:14:56,681 INFO [train.py:823] (1/4) Epoch 25, batch 500, loss[loss=2.024, simple_loss=0.2094, pruned_loss=0.03093, codebook_loss=18.89, over 7012.00 frames.], tot_loss[loss=2.085, simple_loss=0.2515, pruned_loss=0.03639, codebook_loss=19.23, over 1303213.10 frames.], batch size: 16, lr: 6.77e-04
+2022-05-27 19:15:42,061 INFO [train.py:823] (1/4) Epoch 25, batch 550, loss[loss=2.56, simple_loss=0.2913, pruned_loss=0.07014, codebook_loss=23.44, over 7181.00 frames.], tot_loss[loss=2.094, simple_loss=0.2514, pruned_loss=0.0369, codebook_loss=19.31, over 1331015.13 frames.], batch size: 21, lr: 6.76e-04
+2022-05-27 19:16:23,985 INFO [train.py:823] (1/4) Epoch 25, batch 600, loss[loss=1.955, simple_loss=0.2592, pruned_loss=0.01981, codebook_loss=18.06, over 7284.00 frames.], tot_loss[loss=2.092, simple_loss=0.2501, pruned_loss=0.03621, codebook_loss=19.31, over 1344751.41 frames.], batch size: 21, lr: 6.75e-04
+2022-05-27 19:17:05,141 INFO [train.py:823] (1/4) Epoch 25, batch 650, loss[loss=2.237, simple_loss=0.2509, pruned_loss=0.03199, codebook_loss=20.79, over 7274.00 frames.], tot_loss[loss=2.092, simple_loss=0.2501, pruned_loss=0.03589, codebook_loss=19.31, over 1359229.26 frames.], batch size: 20, lr: 6.75e-04
+2022-05-27 19:17:47,809 INFO [train.py:823] (1/4) Epoch 25, batch 700, loss[loss=1.913, simple_loss=0.2197, pruned_loss=0.0173, codebook_loss=17.86, over 7139.00 frames.], tot_loss[loss=2.09, simple_loss=0.2503, pruned_loss=0.03594, codebook_loss=19.29, over 1370763.22 frames.], batch size: 17, lr: 6.74e-04
+2022-05-27 19:18:28,142 INFO [train.py:823] (1/4) Epoch 25, batch 750, loss[loss=2.059, simple_loss=0.2407, pruned_loss=0.03113, codebook_loss=19.08, over 7386.00 frames.], tot_loss[loss=2.086, simple_loss=0.2488, pruned_loss=0.03539, codebook_loss=19.26, over 1378302.14 frames.], batch size: 20, lr: 6.73e-04
+2022-05-27 19:19:08,121 INFO [train.py:823] (1/4) Epoch 25, batch 800, loss[loss=2.046, simple_loss=0.2561, pruned_loss=0.03329, codebook_loss=18.85, over 7190.00 frames.], tot_loss[loss=2.088, simple_loss=0.2486, pruned_loss=0.03542, codebook_loss=19.29, over 1389613.23 frames.], batch size: 21, lr: 6.73e-04
+2022-05-27 19:19:48,341 INFO [train.py:823] (1/4) Epoch 25, batch 850, loss[loss=2.165, simple_loss=0.2299, pruned_loss=0.02402, codebook_loss=20.26, over 7188.00 frames.], tot_loss[loss=2.089, simple_loss=0.2497, pruned_loss=0.03552, codebook_loss=19.29, over 1395483.38 frames.], batch size: 18, lr: 6.72e-04
+2022-05-27 19:20:27,866 INFO [train.py:823] (1/4) Epoch 25, batch 900, loss[loss=2.101, simple_loss=0.267, pruned_loss=0.03419, codebook_loss=19.33, over 6413.00 frames.], tot_loss[loss=2.087, simple_loss=0.2499, pruned_loss=0.03541, codebook_loss=19.27, over 1394531.05 frames.], batch size: 34, lr: 6.71e-04
+2022-05-27 19:21:22,331 INFO [train.py:823] (1/4) Epoch 26, batch 0, loss[loss=2.268, simple_loss=0.224, pruned_loss=0.02864, codebook_loss=21.28, over 7294.00 frames.], tot_loss[loss=2.268, simple_loss=0.224, pruned_loss=0.02864, codebook_loss=21.28, over 7294.00 frames.], batch size: 18, lr: 6.58e-04
+2022-05-27 19:22:03,632 INFO [train.py:823] (1/4) Epoch 26, batch 50, loss[loss=2.034, simple_loss=0.2489, pruned_loss=0.03122, codebook_loss=18.79, over 7372.00 frames.], tot_loss[loss=2.063, simple_loss=0.2459, pruned_loss=0.03273, codebook_loss=19.08, over 323615.13 frames.], batch size: 20, lr: 6.57e-04
+2022-05-27 19:22:43,982 INFO [train.py:823] (1/4) Epoch 26, batch 100, loss[loss=2.003, simple_loss=0.2692, pruned_loss=0.03457, codebook_loss=18.34, over 7223.00 frames.], tot_loss[loss=2.063, simple_loss=0.2478, pruned_loss=0.03335, codebook_loss=19.05, over 568708.99 frames.], batch size: 25, lr: 6.56e-04
+2022-05-27 19:23:23,781 INFO [train.py:823] (1/4) Epoch 26, batch 150, loss[loss=2.024, simple_loss=0.2485, pruned_loss=0.03354, codebook_loss=18.66, over 7173.00 frames.], tot_loss[loss=2.075, simple_loss=0.2479, pruned_loss=0.03448, codebook_loss=19.16, over 755171.50 frames.], batch size: 25, lr: 6.56e-04
+2022-05-27 19:24:03,990 INFO [train.py:823] (1/4) Epoch 26, batch 200, loss[loss=2.24, simple_loss=0.2435, pruned_loss=0.03046, codebook_loss=20.88, over 7097.00 frames.], tot_loss[loss=2.08, simple_loss=0.2491, pruned_loss=0.03491, codebook_loss=19.21, over 901378.70 frames.], batch size: 18, lr: 6.55e-04
+2022-05-27 19:24:43,855 INFO [train.py:823] (1/4) Epoch 26, batch 250, loss[loss=2.066, simple_loss=0.2623, pruned_loss=0.03332, codebook_loss=19.01, over 7419.00 frames.], tot_loss[loss=2.081, simple_loss=0.2488, pruned_loss=0.03512, codebook_loss=19.22, over 1016961.31 frames.], batch size: 22, lr: 6.55e-04
+2022-05-27 19:25:27,420 INFO [train.py:823] (1/4) Epoch 26, batch 300, loss[loss=2.125, simple_loss=0.2571, pruned_loss=0.0305, codebook_loss=19.66, over 7117.00 frames.], tot_loss[loss=2.083, simple_loss=0.2487, pruned_loss=0.03518, codebook_loss=19.24, over 1107512.99 frames.], batch size: 20, lr: 6.54e-04
+2022-05-27 19:26:07,492 INFO [train.py:823] (1/4) Epoch 26, batch 350, loss[loss=2.517, simple_loss=0.2688, pruned_loss=0.04411, codebook_loss=23.39, over 6481.00 frames.], tot_loss[loss=2.083, simple_loss=0.2486, pruned_loss=0.03517, codebook_loss=19.24, over 1178699.74 frames.], batch size: 34, lr: 6.53e-04
+2022-05-27 19:26:47,590 INFO [train.py:823] (1/4) Epoch 26, batch 400, loss[loss=2.032, simple_loss=0.2626, pruned_loss=0.03768, codebook_loss=18.63, over 7156.00 frames.], tot_loss[loss=2.079, simple_loss=0.2483, pruned_loss=0.0351, codebook_loss=19.2, over 1234466.99 frames.], batch size: 23, lr: 6.53e-04
+2022-05-27 19:27:28,673 INFO [train.py:823] (1/4) Epoch 26, batch 450, loss[loss=2.102, simple_loss=0.2551, pruned_loss=0.04123, codebook_loss=19.33, over 7192.00 frames.], tot_loss[loss=2.082, simple_loss=0.2487, pruned_loss=0.0349, codebook_loss=19.23, over 1274079.77 frames.], batch size: 21, lr: 6.52e-04
+2022-05-27 19:28:08,964 INFO [train.py:823] (1/4) Epoch 26, batch 500, loss[loss=2.106, simple_loss=0.2751, pruned_loss=0.04773, codebook_loss=19.21, over 7042.00 frames.], tot_loss[loss=2.084, simple_loss=0.2501, pruned_loss=0.03538, codebook_loss=19.24, over 1304984.66 frames.], batch size: 26, lr: 6.51e-04
+2022-05-27 19:28:49,105 INFO [train.py:823] (1/4) Epoch 26, batch 550, loss[loss=1.996, simple_loss=0.2083, pruned_loss=0.02205, codebook_loss=18.7, over 7008.00 frames.], tot_loss[loss=2.081, simple_loss=0.2493, pruned_loss=0.03498, codebook_loss=19.22, over 1328407.74 frames.], batch size: 16, lr: 6.51e-04
+2022-05-27 19:29:29,452 INFO [train.py:823] (1/4) Epoch 26, batch 600, loss[loss=2.061, simple_loss=0.248, pruned_loss=0.02337, codebook_loss=19.14, over 7310.00 frames.], tot_loss[loss=2.077, simple_loss=0.2483, pruned_loss=0.03442, codebook_loss=19.19, over 1347898.44 frames.], batch size: 22, lr: 6.50e-04
+2022-05-27 19:30:09,300 INFO [train.py:823] (1/4) Epoch 26, batch 650, loss[loss=2.309, simple_loss=0.2731, pruned_loss=0.04825, codebook_loss=21.24, over 7335.00 frames.], tot_loss[loss=2.077, simple_loss=0.2474, pruned_loss=0.03439, codebook_loss=19.19, over 1359083.17 frames.], batch size: 23, lr: 6.49e-04
+2022-05-27 19:30:49,393 INFO [train.py:823] (1/4) Epoch 26, batch 700, loss[loss=2.199, simple_loss=0.2669, pruned_loss=0.04513, codebook_loss=20.2, over 7032.00 frames.], tot_loss[loss=2.085, simple_loss=0.2486, pruned_loss=0.03496, codebook_loss=19.26, over 1372551.33 frames.], batch size: 26, lr: 6.49e-04
+2022-05-27 19:31:29,083 INFO [train.py:823] (1/4) Epoch 26, batch 750, loss[loss=1.919, simple_loss=0.2339, pruned_loss=0.02204, codebook_loss=17.8, over 7295.00 frames.], tot_loss[loss=2.09, simple_loss=0.2493, pruned_loss=0.03549, codebook_loss=19.3, over 1375478.07 frames.], batch size: 19, lr: 6.48e-04
+2022-05-27 19:32:09,215 INFO [train.py:823] (1/4) Epoch 26, batch 800, loss[loss=2.118, simple_loss=0.2229, pruned_loss=0.04065, codebook_loss=19.66, over 6838.00 frames.], tot_loss[loss=2.091, simple_loss=0.2489, pruned_loss=0.03567, codebook_loss=19.31, over 1382551.86 frames.], batch size: 15, lr: 6.47e-04
+2022-05-27 19:32:49,157 INFO [train.py:823] (1/4) Epoch 26, batch 850, loss[loss=2.07, simple_loss=0.2268, pruned_loss=0.03238, codebook_loss=19.24, over 6834.00 frames.], tot_loss[loss=2.082, simple_loss=0.2483, pruned_loss=0.03503, codebook_loss=19.23, over 1393870.39 frames.], batch size: 15, lr: 6.47e-04
+2022-05-27 19:33:29,201 INFO [train.py:823] (1/4) Epoch 26, batch 900, loss[loss=2.074, simple_loss=0.2103, pruned_loss=0.02809, codebook_loss=19.4, over 7027.00 frames.], tot_loss[loss=2.085, simple_loss=0.2493, pruned_loss=0.03525, codebook_loss=19.25, over 1395412.92 frames.], batch size: 17, lr: 6.46e-04
+2022-05-27 19:34:22,987 INFO [train.py:823] (1/4) Epoch 27, batch 0, loss[loss=2.016, simple_loss=0.2281, pruned_loss=0.03167, codebook_loss=18.7, over 7200.00 frames.], tot_loss[loss=2.016, simple_loss=0.2281, pruned_loss=0.03167, codebook_loss=18.7, over 7200.00 frames.], batch size: 18, lr: 6.34e-04
+2022-05-27 19:35:03,205 INFO [train.py:823] (1/4) Epoch 27, batch 50, loss[loss=2.07, simple_loss=0.2269, pruned_loss=0.02957, codebook_loss=19.27, over 7197.00 frames.], tot_loss[loss=2.055, simple_loss=0.2472, pruned_loss=0.03361, codebook_loss=18.98, over 322164.09 frames.], batch size: 18, lr: 6.33e-04
+2022-05-27 19:35:42,727 INFO [train.py:823] (1/4) Epoch 27, batch 100, loss[loss=2.031, simple_loss=0.2754, pruned_loss=0.03998, codebook_loss=18.53, over 7199.00 frames.], tot_loss[loss=2.048, simple_loss=0.2483, pruned_loss=0.03406, codebook_loss=18.9, over 563833.12 frames.], batch size: 25, lr: 6.32e-04
+2022-05-27 19:36:26,849 INFO [train.py:823] (1/4) Epoch 27, batch 150, loss[loss=2.028, simple_loss=0.2194, pruned_loss=0.02439, codebook_loss=18.94, over 7310.00 frames.], tot_loss[loss=2.054, simple_loss=0.2485, pruned_loss=0.03529, codebook_loss=18.94, over 753343.49 frames.], batch size: 18, lr: 6.32e-04
+2022-05-27 19:37:06,343 INFO [train.py:823] (1/4) Epoch 27, batch 200, loss[loss=2.099, simple_loss=0.2529, pruned_loss=0.03081, codebook_loss=19.41, over 7427.00 frames.], tot_loss[loss=2.067, simple_loss=0.249, pruned_loss=0.03587, codebook_loss=19.06, over 900366.66 frames.], batch size: 22, lr: 6.31e-04
+2022-05-27 19:37:46,521 INFO [train.py:823] (1/4) Epoch 27, batch 250, loss[loss=1.995, simple_loss=0.2292, pruned_loss=0.02858, codebook_loss=18.52, over 7026.00 frames.], tot_loss[loss=2.067, simple_loss=0.2498, pruned_loss=0.03556, codebook_loss=19.06, over 1012676.86 frames.], batch size: 17, lr: 6.31e-04
+2022-05-27 19:38:26,678 INFO [train.py:823] (1/4) Epoch 27, batch 300, loss[loss=1.961, simple_loss=0.2264, pruned_loss=0.01626, codebook_loss=18.32, over 7385.00 frames.], tot_loss[loss=2.069, simple_loss=0.2476, pruned_loss=0.03466, codebook_loss=19.1, over 1106914.27 frames.], batch size: 21, lr: 6.30e-04
+2022-05-27 19:39:06,902 INFO [train.py:823] (1/4) Epoch 27, batch 350, loss[loss=1.983, simple_loss=0.2423, pruned_loss=0.03207, codebook_loss=18.3, over 7294.00 frames.], tot_loss[loss=2.076, simple_loss=0.2476, pruned_loss=0.03467, codebook_loss=19.17, over 1178611.34 frames.], batch size: 19, lr: 6.29e-04
+2022-05-27 19:39:46,734 INFO [train.py:823] (1/4) Epoch 27, batch 400, loss[loss=2.087, simple_loss=0.2511, pruned_loss=0.03534, codebook_loss=19.26, over 7278.00 frames.], tot_loss[loss=2.084, simple_loss=0.2484, pruned_loss=0.03502, codebook_loss=19.25, over 1233213.84 frames.], batch size: 20, lr: 6.29e-04
+2022-05-27 19:40:27,039 INFO [train.py:823] (1/4) Epoch 27, batch 450, loss[loss=2.099, simple_loss=0.2544, pruned_loss=0.05114, codebook_loss=19.2, over 4919.00 frames.], tot_loss[loss=2.078, simple_loss=0.248, pruned_loss=0.03491, codebook_loss=19.19, over 1276488.96 frames.], batch size: 46, lr: 6.28e-04
+2022-05-27 19:41:06,537 INFO [train.py:823] (1/4) Epoch 27, batch 500, loss[loss=2.677, simple_loss=0.301, pruned_loss=0.09452, codebook_loss=24.32, over 7153.00 frames.], tot_loss[loss=2.082, simple_loss=0.2482, pruned_loss=0.03547, codebook_loss=19.23, over 1300939.57 frames.], batch size: 23, lr: 6.28e-04
+2022-05-27 19:41:46,717 INFO [train.py:823] (1/4) Epoch 27, batch 550, loss[loss=2.029, simple_loss=0.2502, pruned_loss=0.03435, codebook_loss=18.7, over 7279.00 frames.], tot_loss[loss=2.079, simple_loss=0.2487, pruned_loss=0.03527, codebook_loss=19.19, over 1329357.97 frames.], batch size: 20, lr: 6.27e-04
+2022-05-27 19:42:26,687 INFO [train.py:823] (1/4) Epoch 27, batch 600, loss[loss=2.018, simple_loss=0.2227, pruned_loss=0.0304, codebook_loss=18.77, over 7308.00 frames.], tot_loss[loss=2.079, simple_loss=0.2486, pruned_loss=0.03504, codebook_loss=19.2, over 1355642.22 frames.], batch size: 18, lr: 6.26e-04
+2022-05-27 19:43:06,783 INFO [train.py:823] (1/4) Epoch 27, batch 650, loss[loss=2.149, simple_loss=0.2377, pruned_loss=0.03147, codebook_loss=19.99, over 7192.00 frames.], tot_loss[loss=2.074, simple_loss=0.249, pruned_loss=0.03485, codebook_loss=19.14, over 1374110.36 frames.], batch size: 19, lr: 6.26e-04
+2022-05-27 19:43:46,840 INFO [train.py:823] (1/4) Epoch 27, batch 700, loss[loss=2.156, simple_loss=0.2706, pruned_loss=0.03178, codebook_loss=19.89, over 7371.00 frames.], tot_loss[loss=2.079, simple_loss=0.2487, pruned_loss=0.03478, codebook_loss=19.19, over 1383805.53 frames.], batch size: 21, lr: 6.25e-04
+2022-05-27 19:44:26,939 INFO [train.py:823] (1/4) Epoch 27, batch 750, loss[loss=2.193, simple_loss=0.2353, pruned_loss=0.03366, codebook_loss=20.41, over 7197.00 frames.], tot_loss[loss=2.079, simple_loss=0.2482, pruned_loss=0.03447, codebook_loss=19.2, over 1392459.90 frames.], batch size: 19, lr: 6.25e-04
+2022-05-27 19:45:06,639 INFO [train.py:823] (1/4) Epoch 27, batch 800, loss[loss=2.139, simple_loss=0.278, pruned_loss=0.05372, codebook_loss=19.46, over 7164.00 frames.], tot_loss[loss=2.081, simple_loss=0.2489, pruned_loss=0.03499, codebook_loss=19.21, over 1393285.32 frames.], batch size: 23, lr: 6.24e-04
+2022-05-27 19:45:46,844 INFO [train.py:823] (1/4) Epoch 27, batch 850, loss[loss=2.115, simple_loss=0.278, pruned_loss=0.04804, codebook_loss=19.28, over 7105.00 frames.], tot_loss[loss=2.077, simple_loss=0.2476, pruned_loss=0.03483, codebook_loss=19.18, over 1395927.18 frames.], batch size: 20, lr: 6.23e-04
+2022-05-27 19:46:26,352 INFO [train.py:823] (1/4) Epoch 27, batch 900, loss[loss=2.1, simple_loss=0.2214, pruned_loss=0.03079, codebook_loss=19.59, over 7290.00 frames.], tot_loss[loss=2.075, simple_loss=0.2472, pruned_loss=0.03449, codebook_loss=19.17, over 1398403.82 frames.], batch size: 17, lr: 6.23e-04
+2022-05-27 19:47:20,731 INFO [train.py:823] (1/4) Epoch 28, batch 0, loss[loss=1.98, simple_loss=0.2599, pruned_loss=0.02861, codebook_loss=18.22, over 7195.00 frames.], tot_loss[loss=1.98, simple_loss=0.2599, pruned_loss=0.02861, codebook_loss=18.22, over 7195.00 frames.], batch size: 20, lr: 6.11e-04
+2022-05-27 19:48:00,117 INFO [train.py:823] (1/4) Epoch 28, batch 50, loss[loss=2.223, simple_loss=0.2543, pruned_loss=0.03267, codebook_loss=20.63, over 7105.00 frames.], tot_loss[loss=2.033, simple_loss=0.2419, pruned_loss=0.03212, codebook_loss=18.8, over 316042.98 frames.], batch size: 20, lr: 6.11e-04
+2022-05-27 19:48:40,411 INFO [train.py:823] (1/4) Epoch 28, batch 100, loss[loss=2.042, simple_loss=0.2501, pruned_loss=0.03451, codebook_loss=18.83, over 7015.00 frames.], tot_loss[loss=2.04, simple_loss=0.2441, pruned_loss=0.03266, codebook_loss=18.86, over 560482.98 frames.], batch size: 26, lr: 6.10e-04
+2022-05-27 19:49:20,226 INFO [train.py:823] (1/4) Epoch 28, batch 150, loss[loss=2.067, simple_loss=0.2682, pruned_loss=0.04141, codebook_loss=18.92, over 4952.00 frames.], tot_loss[loss=2.048, simple_loss=0.2448, pruned_loss=0.03288, codebook_loss=18.93, over 748868.88 frames.], batch size: 46, lr: 6.09e-04
+2022-05-27 19:50:00,334 INFO [train.py:823] (1/4) Epoch 28, batch 200, loss[loss=2.321, simple_loss=0.2639, pruned_loss=0.04298, codebook_loss=21.46, over 7193.00 frames.], tot_loss[loss=2.045, simple_loss=0.2442, pruned_loss=0.03258, codebook_loss=18.91, over 898760.56 frames.], batch size: 20, lr: 6.09e-04
+2022-05-27 19:50:40,300 INFO [train.py:823] (1/4) Epoch 28, batch 250, loss[loss=2.192, simple_loss=0.2889, pruned_loss=0.05167, codebook_loss=19.96, over 7340.00 frames.], tot_loss[loss=2.044, simple_loss=0.2453, pruned_loss=0.03319, codebook_loss=18.88, over 1015232.31 frames.], batch size: 23, lr: 6.08e-04
+2022-05-27 19:51:22,051 INFO [train.py:823] (1/4) Epoch 28, batch 300, loss[loss=2.064, simple_loss=0.2765, pruned_loss=0.04592, codebook_loss=18.8, over 6981.00 frames.], tot_loss[loss=2.049, simple_loss=0.2462, pruned_loss=0.03347, codebook_loss=18.92, over 1103615.78 frames.], batch size: 29, lr: 6.08e-04
+2022-05-27 19:52:01,909 INFO [train.py:823] (1/4) Epoch 28, batch 350, loss[loss=2.139, simple_loss=0.2727, pruned_loss=0.04098, codebook_loss=19.61, over 7343.00 frames.], tot_loss[loss=2.052, simple_loss=0.2455, pruned_loss=0.03351, codebook_loss=18.96, over 1174853.01 frames.], batch size: 23, lr: 6.07e-04
+2022-05-27 19:52:42,274 INFO [train.py:823] (1/4) Epoch 28, batch 400, loss[loss=1.93, simple_loss=0.253, pruned_loss=0.02562, codebook_loss=17.78, over 7285.00 frames.], tot_loss[loss=2.057, simple_loss=0.2456, pruned_loss=0.03368, codebook_loss=19.01, over 1230168.73 frames.], batch size: 21, lr: 6.07e-04
+2022-05-27 19:53:21,980 INFO [train.py:823] (1/4) Epoch 28, batch 450, loss[loss=2.005, simple_loss=0.2414, pruned_loss=0.03555, codebook_loss=18.49, over 6919.00 frames.], tot_loss[loss=2.054, simple_loss=0.2453, pruned_loss=0.03327, codebook_loss=18.98, over 1270022.25 frames.], batch size: 29, lr: 6.06e-04
+2022-05-27 19:54:02,155 INFO [train.py:823] (1/4) Epoch 28, batch 500, loss[loss=2.093, simple_loss=0.2596, pruned_loss=0.04981, codebook_loss=19.13, over 6888.00 frames.], tot_loss[loss=2.053, simple_loss=0.2456, pruned_loss=0.03346, codebook_loss=18.97, over 1307104.60 frames.], batch size: 29, lr: 6.06e-04
+2022-05-27 19:54:41,595 INFO [train.py:823] (1/4) Epoch 28, batch 550, loss[loss=2.006, simple_loss=0.2535, pruned_loss=0.03072, codebook_loss=18.49, over 7110.00 frames.], tot_loss[loss=2.055, simple_loss=0.2462, pruned_loss=0.0335, codebook_loss=18.98, over 1330486.92 frames.], batch size: 20, lr: 6.05e-04
+2022-05-27 19:55:21,351 INFO [train.py:823] (1/4) Epoch 28, batch 600, loss[loss=2.099, simple_loss=0.2433, pruned_loss=0.02914, codebook_loss=19.48, over 7199.00 frames.], tot_loss[loss=2.055, simple_loss=0.2469, pruned_loss=0.03346, codebook_loss=18.98, over 1348742.42 frames.], batch size: 19, lr: 6.04e-04
+2022-05-27 19:56:01,412 INFO [train.py:823] (1/4) Epoch 28, batch 650, loss[loss=2.045, simple_loss=0.2324, pruned_loss=0.02364, codebook_loss=19.05, over 7291.00 frames.], tot_loss[loss=2.059, simple_loss=0.2461, pruned_loss=0.03323, codebook_loss=19.02, over 1367977.07 frames.], batch size: 19, lr: 6.04e-04
+2022-05-27 19:56:41,256 INFO [train.py:823] (1/4) Epoch 28, batch 700, loss[loss=1.938, simple_loss=0.2081, pruned_loss=0.01936, codebook_loss=18.15, over 7319.00 frames.], tot_loss[loss=2.062, simple_loss=0.2465, pruned_loss=0.03349, codebook_loss=19.05, over 1377176.08 frames.], batch size: 18, lr: 6.03e-04
+2022-05-27 19:57:20,987 INFO [train.py:823] (1/4) Epoch 28, batch 750, loss[loss=2.017, simple_loss=0.2576, pruned_loss=0.03967, codebook_loss=18.49, over 4781.00 frames.], tot_loss[loss=2.065, simple_loss=0.2471, pruned_loss=0.03373, codebook_loss=19.08, over 1383920.30 frames.], batch size: 47, lr: 6.03e-04
+2022-05-27 19:58:00,965 INFO [train.py:823] (1/4) Epoch 28, batch 800, loss[loss=2.004, simple_loss=0.2188, pruned_loss=0.02017, codebook_loss=18.74, over 7011.00 frames.], tot_loss[loss=2.064, simple_loss=0.2469, pruned_loss=0.03352, codebook_loss=19.07, over 1395314.84 frames.], batch size: 16, lr: 6.02e-04
+2022-05-27 19:58:40,827 INFO [train.py:823] (1/4) Epoch 28, batch 850, loss[loss=2.007, simple_loss=0.2557, pruned_loss=0.03179, codebook_loss=18.47, over 7371.00 frames.], tot_loss[loss=2.065, simple_loss=0.2474, pruned_loss=0.03362, codebook_loss=19.07, over 1399590.19 frames.], batch size: 21, lr: 6.02e-04
+2022-05-27 19:59:20,852 INFO [train.py:823] (1/4) Epoch 28, batch 900, loss[loss=2.129, simple_loss=0.238, pruned_loss=0.03651, codebook_loss=19.73, over 7361.00 frames.], tot_loss[loss=2.063, simple_loss=0.2474, pruned_loss=0.03392, codebook_loss=19.06, over 1401536.03 frames.], batch size: 21, lr: 6.01e-04
+2022-05-27 20:00:14,131 INFO [train.py:823] (1/4) Epoch 29, batch 0, loss[loss=2.008, simple_loss=0.2545, pruned_loss=0.04253, codebook_loss=18.38, over 6991.00 frames.], tot_loss[loss=2.008, simple_loss=0.2545, pruned_loss=0.04253, codebook_loss=18.38, over 6991.00 frames.], batch size: 26, lr: 5.90e-04
+2022-05-27 20:00:55,904 INFO [train.py:823] (1/4) Epoch 29, batch 50, loss[loss=1.978, simple_loss=0.2372, pruned_loss=0.02284, codebook_loss=18.36, over 7290.00 frames.], tot_loss[loss=2.045, simple_loss=0.2428, pruned_loss=0.03227, codebook_loss=18.91, over 321614.85 frames.], batch size: 21, lr: 5.90e-04
+2022-05-27 20:01:38,103 INFO [train.py:823] (1/4) Epoch 29, batch 100, loss[loss=2.019, simple_loss=0.2562, pruned_loss=0.03641, codebook_loss=18.55, over 7218.00 frames.], tot_loss[loss=2.038, simple_loss=0.2445, pruned_loss=0.03192, codebook_loss=18.84, over 570173.58 frames.], batch size: 24, lr: 5.89e-04
+2022-05-27 20:02:18,478 INFO [train.py:823] (1/4) Epoch 29, batch 150, loss[loss=2.163, simple_loss=0.2284, pruned_loss=0.02992, codebook_loss=20.18, over 7296.00 frames.], tot_loss[loss=2.047, simple_loss=0.2454, pruned_loss=0.03284, codebook_loss=18.92, over 760350.01 frames.], batch size: 19, lr: 5.89e-04
+2022-05-27 20:02:58,082 INFO [train.py:823] (1/4) Epoch 29, batch 200, loss[loss=2.006, simple_loss=0.2646, pruned_loss=0.03772, codebook_loss=18.36, over 7333.00 frames.], tot_loss[loss=2.048, simple_loss=0.2468, pruned_loss=0.03315, codebook_loss=18.91, over 900377.09 frames.], batch size: 23, lr: 5.88e-04
+2022-05-27 20:03:38,423 INFO [train.py:823] (1/4) Epoch 29, batch 250, loss[loss=1.995, simple_loss=0.244, pruned_loss=0.0323, codebook_loss=18.41, over 7385.00 frames.], tot_loss[loss=2.042, simple_loss=0.2451, pruned_loss=0.03271, codebook_loss=18.87, over 1016050.78 frames.], batch size: 19, lr: 5.88e-04
+2022-05-27 20:04:18,164 INFO [train.py:823] (1/4) Epoch 29, batch 300, loss[loss=2.015, simple_loss=0.2369, pruned_loss=0.02619, codebook_loss=18.71, over 7264.00 frames.], tot_loss[loss=2.051, simple_loss=0.2453, pruned_loss=0.03305, codebook_loss=18.95, over 1105419.52 frames.], batch size: 20, lr: 5.87e-04
+2022-05-27 20:04:58,344 INFO [train.py:823] (1/4) Epoch 29, batch 350, loss[loss=2.019, simple_loss=0.2275, pruned_loss=0.03371, codebook_loss=18.72, over 6836.00 frames.], tot_loss[loss=2.054, simple_loss=0.246, pruned_loss=0.03356, codebook_loss=18.98, over 1173334.95 frames.], batch size: 15, lr: 5.87e-04
+2022-05-27 20:05:37,841 INFO [train.py:823] (1/4) Epoch 29, batch 400, loss[loss=1.994, simple_loss=0.2131, pruned_loss=0.02583, codebook_loss=18.62, over 7298.00 frames.], tot_loss[loss=2.053, simple_loss=0.2466, pruned_loss=0.03344, codebook_loss=18.96, over 1229024.77 frames.], batch size: 17, lr: 5.86e-04
+2022-05-27 20:06:18,210 INFO [train.py:823] (1/4) Epoch 29, batch 450, loss[loss=2.113, simple_loss=0.2342, pruned_loss=0.03711, codebook_loss=19.58, over 7098.00 frames.], tot_loss[loss=2.052, simple_loss=0.2455, pruned_loss=0.03318, codebook_loss=18.96, over 1269611.28 frames.], batch size: 18, lr: 5.85e-04
+2022-05-27 20:06:57,650 INFO [train.py:823] (1/4) Epoch 29, batch 500, loss[loss=2.103, simple_loss=0.2646, pruned_loss=0.04235, codebook_loss=19.28, over 7112.00 frames.], tot_loss[loss=2.05, simple_loss=0.2452, pruned_loss=0.0328, codebook_loss=18.94, over 1297325.97 frames.], batch size: 20, lr: 5.85e-04
+2022-05-27 20:07:37,742 INFO [train.py:823] (1/4) Epoch 29, batch 550, loss[loss=1.978, simple_loss=0.256, pruned_loss=0.02844, codebook_loss=18.22, over 6513.00 frames.], tot_loss[loss=2.048, simple_loss=0.2444, pruned_loss=0.03219, codebook_loss=18.94, over 1326624.61 frames.], batch size: 34, lr: 5.84e-04
+2022-05-27 20:08:17,448 INFO [train.py:823] (1/4) Epoch 29, batch 600, loss[loss=1.985, simple_loss=0.2366, pruned_loss=0.02598, codebook_loss=18.4, over 6280.00 frames.], tot_loss[loss=2.053, simple_loss=0.2448, pruned_loss=0.03228, codebook_loss=18.99, over 1346807.57 frames.], batch size: 34, lr: 5.84e-04
+2022-05-27 20:08:57,758 INFO [train.py:823] (1/4) Epoch 29, batch 650, loss[loss=2.014, simple_loss=0.2703, pruned_loss=0.03665, codebook_loss=18.42, over 7363.00 frames.], tot_loss[loss=2.053, simple_loss=0.2456, pruned_loss=0.03271, codebook_loss=18.98, over 1363736.47 frames.], batch size: 20, lr: 5.83e-04
+2022-05-27 20:09:37,319 INFO [train.py:823] (1/4) Epoch 29, batch 700, loss[loss=2.014, simple_loss=0.2331, pruned_loss=0.03097, codebook_loss=18.66, over 7187.00 frames.], tot_loss[loss=2.055, simple_loss=0.2454, pruned_loss=0.03301, codebook_loss=18.99, over 1371546.54 frames.], batch size: 19, lr: 5.83e-04
+2022-05-27 20:10:17,501 INFO [train.py:823] (1/4) Epoch 29, batch 750, loss[loss=2.063, simple_loss=0.2519, pruned_loss=0.04052, codebook_loss=18.96, over 5194.00 frames.], tot_loss[loss=2.06, simple_loss=0.2458, pruned_loss=0.03324, codebook_loss=19.04, over 1379889.50 frames.], batch size: 46, lr: 5.82e-04
+2022-05-27 20:10:57,097 INFO [train.py:823] (1/4) Epoch 29, batch 800, loss[loss=2.077, simple_loss=0.2308, pruned_loss=0.04324, codebook_loss=19.18, over 7194.00 frames.], tot_loss[loss=2.061, simple_loss=0.2453, pruned_loss=0.0331, codebook_loss=19.05, over 1387165.44 frames.], batch size: 18, lr: 5.82e-04
+2022-05-27 20:11:37,260 INFO [train.py:823] (1/4) Epoch 29, batch 850, loss[loss=2.094, simple_loss=0.2631, pruned_loss=0.04522, codebook_loss=19.18, over 7213.00 frames.], tot_loss[loss=2.059, simple_loss=0.2458, pruned_loss=0.03295, codebook_loss=19.03, over 1397147.17 frames.], batch size: 24, lr: 5.81e-04
+2022-05-27 20:12:16,640 INFO [train.py:823] (1/4) Epoch 29, batch 900, loss[loss=2.105, simple_loss=0.2824, pruned_loss=0.04303, codebook_loss=19.21, over 7174.00 frames.], tot_loss[loss=2.062, simple_loss=0.2466, pruned_loss=0.03354, codebook_loss=19.05, over 1395905.77 frames.], batch size: 22, lr: 5.81e-04
+2022-05-27 20:12:56,392 INFO [train.py:823] (1/4) Epoch 29, batch 950, loss[loss=3.001, simple_loss=0.3287, pruned_loss=0.1084, codebook_loss=27.28, over 4601.00 frames.], tot_loss[loss=2.07, simple_loss=0.2469, pruned_loss=0.03402, codebook_loss=19.12, over 1389768.49 frames.], batch size: 46, lr: 5.80e-04
+2022-05-27 20:13:08,704 INFO [train.py:823] (1/4) Epoch 30, batch 0, loss[loss=2.105, simple_loss=0.2374, pruned_loss=0.03276, codebook_loss=19.54, over 7371.00 frames.], tot_loss[loss=2.105, simple_loss=0.2374, pruned_loss=0.03276, codebook_loss=19.54, over 7371.00 frames.], batch size: 20, lr: 5.71e-04
+2022-05-27 20:13:48,292 INFO [train.py:823] (1/4) Epoch 30, batch 50, loss[loss=2.077, simple_loss=0.25, pruned_loss=0.0367, codebook_loss=19.16, over 7091.00 frames.], tot_loss[loss=2.044, simple_loss=0.2428, pruned_loss=0.03205, codebook_loss=18.91, over 315254.47 frames.], batch size: 19, lr: 5.70e-04
+2022-05-27 20:14:28,408 INFO [train.py:823] (1/4) Epoch 30, batch 100, loss[loss=1.986, simple_loss=0.2178, pruned_loss=0.03096, codebook_loss=18.46, over 7298.00 frames.], tot_loss[loss=2.037, simple_loss=0.2425, pruned_loss=0.03148, codebook_loss=18.85, over 561893.02 frames.], batch size: 17, lr: 5.70e-04
+2022-05-27 20:15:09,328 INFO [train.py:823] (1/4) Epoch 30, batch 150, loss[loss=2.044, simple_loss=0.2551, pruned_loss=0.02915, codebook_loss=18.88, over 7172.00 frames.], tot_loss[loss=2.049, simple_loss=0.2454, pruned_loss=0.03283, codebook_loss=18.94, over 753969.28 frames.], batch size: 23, lr: 5.69e-04
+2022-05-27 20:15:49,638 INFO [train.py:823] (1/4) Epoch 30, batch 200, loss[loss=1.988, simple_loss=0.2477, pruned_loss=0.03603, codebook_loss=18.28, over 7151.00 frames.], tot_loss[loss=2.05, simple_loss=0.2453, pruned_loss=0.03284, codebook_loss=18.95, over 901728.81 frames.], batch size: 23, lr: 5.69e-04
+2022-05-27 20:16:29,378 INFO [train.py:823] (1/4) Epoch 30, batch 250, loss[loss=1.964, simple_loss=0.242, pruned_loss=0.02927, codebook_loss=18.14, over 7107.00 frames.], tot_loss[loss=2.05, simple_loss=0.2456, pruned_loss=0.03285, codebook_loss=18.95, over 1013849.69 frames.], batch size: 19, lr: 5.68e-04
+2022-05-27 20:17:09,781 INFO [train.py:823] (1/4) Epoch 30, batch 300, loss[loss=1.983, simple_loss=0.2211, pruned_loss=0.0284, codebook_loss=18.44, over 7152.00 frames.], tot_loss[loss=2.043, simple_loss=0.2458, pruned_loss=0.03256, codebook_loss=18.87, over 1107294.18 frames.], batch size: 17, lr: 5.68e-04
+2022-05-27 20:17:49,600 INFO [train.py:823] (1/4) Epoch 30, batch 350, loss[loss=2.348, simple_loss=0.2561, pruned_loss=0.04207, codebook_loss=21.78, over 7222.00 frames.], tot_loss[loss=2.051, simple_loss=0.2448, pruned_loss=0.03277, codebook_loss=18.96, over 1177324.74 frames.], batch size: 24, lr: 5.67e-04
+2022-05-27 20:18:29,836 INFO [train.py:823] (1/4) Epoch 30, batch 400, loss[loss=1.979, simple_loss=0.2682, pruned_loss=0.03861, codebook_loss=18.06, over 7011.00 frames.], tot_loss[loss=2.047, simple_loss=0.2448, pruned_loss=0.03255, codebook_loss=18.92, over 1231396.43 frames.], batch size: 26, lr: 5.67e-04
+2022-05-27 20:19:09,336 INFO [train.py:823] (1/4) Epoch 30, batch 450, loss[loss=2.088, simple_loss=0.2577, pruned_loss=0.03736, codebook_loss=19.22, over 6950.00 frames.], tot_loss[loss=2.049, simple_loss=0.2449, pruned_loss=0.03282, codebook_loss=18.94, over 1270014.48 frames.], batch size: 29, lr: 5.66e-04
+2022-05-27 20:19:49,244 INFO [train.py:823] (1/4) Epoch 30, batch 500, loss[loss=2.31, simple_loss=0.2576, pruned_loss=0.05306, codebook_loss=21.28, over 7101.00 frames.], tot_loss[loss=2.052, simple_loss=0.2444, pruned_loss=0.03269, codebook_loss=18.97, over 1303479.35 frames.], batch size: 19, lr: 5.66e-04
+2022-05-27 20:20:29,049 INFO [train.py:823] (1/4) Epoch 30, batch 550, loss[loss=2.356, simple_loss=0.2631, pruned_loss=0.04124, codebook_loss=21.83, over 7416.00 frames.], tot_loss[loss=2.054, simple_loss=0.2445, pruned_loss=0.03281, codebook_loss=18.99, over 1327013.04 frames.], batch size: 22, lr: 5.65e-04
+2022-05-27 20:21:09,008 INFO [train.py:823] (1/4) Epoch 30, batch 600, loss[loss=1.969, simple_loss=0.2318, pruned_loss=0.02594, codebook_loss=18.27, over 7199.00 frames.], tot_loss[loss=2.052, simple_loss=0.2444, pruned_loss=0.0326, codebook_loss=18.98, over 1345070.47 frames.], batch size: 19, lr: 5.65e-04
+2022-05-27 20:21:48,895 INFO [train.py:823] (1/4) Epoch 30, batch 650, loss[loss=1.977, simple_loss=0.2467, pruned_loss=0.02731, codebook_loss=18.26, over 7418.00 frames.], tot_loss[loss=2.048, simple_loss=0.2439, pruned_loss=0.03249, codebook_loss=18.93, over 1358743.48 frames.], batch size: 22, lr: 5.64e-04
+2022-05-27 20:22:29,362 INFO [train.py:823] (1/4) Epoch 30, batch 700, loss[loss=2.007, simple_loss=0.2413, pruned_loss=0.03584, codebook_loss=18.51, over 7289.00 frames.], tot_loss[loss=2.048, simple_loss=0.2431, pruned_loss=0.03252, codebook_loss=18.94, over 1376611.80 frames.], batch size: 19, lr: 5.64e-04
+2022-05-27 20:23:09,104 INFO [train.py:823] (1/4) Epoch 30, batch 750, loss[loss=1.974, simple_loss=0.2155, pruned_loss=0.03095, codebook_loss=18.35, over 7091.00 frames.], tot_loss[loss=2.052, simple_loss=0.2437, pruned_loss=0.03302, codebook_loss=18.97, over 1382854.50 frames.], batch size: 18, lr: 5.63e-04
+2022-05-27 20:23:48,806 INFO [train.py:823] (1/4) Epoch 30, batch 800, loss[loss=2.013, simple_loss=0.2465, pruned_loss=0.04065, codebook_loss=18.49, over 6999.00 frames.], tot_loss[loss=2.049, simple_loss=0.2438, pruned_loss=0.03255, codebook_loss=18.95, over 1392164.62 frames.], batch size: 26, lr: 5.63e-04
+2022-05-27 20:24:28,390 INFO [train.py:823] (1/4) Epoch 30, batch 850, loss[loss=2.08, simple_loss=0.2362, pruned_loss=0.03261, codebook_loss=19.3, over 7178.00 frames.], tot_loss[loss=2.053, simple_loss=0.2442, pruned_loss=0.03266, codebook_loss=18.99, over 1390274.64 frames.], batch size: 18, lr: 5.62e-04
+2022-05-27 20:25:08,260 INFO [train.py:823] (1/4) Epoch 30, batch 900, loss[loss=2.182, simple_loss=0.2365, pruned_loss=0.03446, codebook_loss=20.29, over 7296.00 frames.], tot_loss[loss=2.053, simple_loss=0.2447, pruned_loss=0.03282, codebook_loss=18.98, over 1394558.73 frames.], batch size: 19, lr: 5.62e-04
+2022-05-27 20:26:05,253 INFO [train.py:823] (1/4) Epoch 31, batch 0, loss[loss=2.232, simple_loss=0.234, pruned_loss=0.03361, codebook_loss=20.82, over 7364.00 frames.], tot_loss[loss=2.232, simple_loss=0.234, pruned_loss=0.03361, codebook_loss=20.82, over 7364.00 frames.], batch size: 20, lr: 5.52e-04
+2022-05-27 20:26:45,571 INFO [train.py:823] (1/4) Epoch 31, batch 50, loss[loss=1.94, simple_loss=0.2219, pruned_loss=0.02215, codebook_loss=18.07, over 7188.00 frames.], tot_loss[loss=2.05, simple_loss=0.2433, pruned_loss=0.0331, codebook_loss=18.95, over 324532.96 frames.], batch size: 18, lr: 5.52e-04
+2022-05-27 20:27:24,999 INFO [train.py:823] (1/4) Epoch 31, batch 100, loss[loss=2.427, simple_loss=0.2209, pruned_loss=0.02537, codebook_loss=22.91, over 6774.00 frames.], tot_loss[loss=2.049, simple_loss=0.2442, pruned_loss=0.03292, codebook_loss=18.94, over 564395.66 frames.], batch size: 15, lr: 5.51e-04
+2022-05-27 20:28:05,123 INFO [train.py:823] (1/4) Epoch 31, batch 150, loss[loss=2.025, simple_loss=0.2568, pruned_loss=0.03497, codebook_loss=18.61, over 7200.00 frames.], tot_loss[loss=2.046, simple_loss=0.2448, pruned_loss=0.03311, codebook_loss=18.9, over 753399.94 frames.], batch size: 25, lr: 5.51e-04
+2022-05-27 20:28:44,794 INFO [train.py:823] (1/4) Epoch 31, batch 200, loss[loss=1.997, simple_loss=0.2407, pruned_loss=0.03699, codebook_loss=18.39, over 7103.00 frames.], tot_loss[loss=2.044, simple_loss=0.2442, pruned_loss=0.03227, codebook_loss=18.9, over 897763.93 frames.], batch size: 18, lr: 5.50e-04
+2022-05-27 20:29:24,817 INFO [train.py:823] (1/4) Epoch 31, batch 250, loss[loss=1.986, simple_loss=0.2276, pruned_loss=0.03326, codebook_loss=18.39, over 7162.00 frames.], tot_loss[loss=2.049, simple_loss=0.2439, pruned_loss=0.0328, codebook_loss=18.94, over 1004158.72 frames.], batch size: 17, lr: 5.50e-04
+2022-05-27 20:30:04,898 INFO [train.py:823] (1/4) Epoch 31, batch 300, loss[loss=1.95, simple_loss=0.2639, pruned_loss=0.03224, codebook_loss=17.86, over 7298.00 frames.], tot_loss[loss=2.042, simple_loss=0.2431, pruned_loss=0.03209, codebook_loss=18.89, over 1096473.70 frames.], batch size: 22, lr: 5.49e-04
+2022-05-27 20:30:44,876 INFO [train.py:823] (1/4) Epoch 31, batch 350, loss[loss=2.047, simple_loss=0.2264, pruned_loss=0.03228, codebook_loss=19.02, over 7144.00 frames.], tot_loss[loss=2.041, simple_loss=0.2435, pruned_loss=0.03217, codebook_loss=18.87, over 1163535.32 frames.], batch size: 17, lr: 5.49e-04
+2022-05-27 20:31:24,694 INFO [train.py:823] (1/4) Epoch 31, batch 400, loss[loss=1.996, simple_loss=0.2244, pruned_loss=0.02137, codebook_loss=18.62, over 7395.00 frames.], tot_loss[loss=2.038, simple_loss=0.2434, pruned_loss=0.03189, codebook_loss=18.85, over 1224975.80 frames.], batch size: 19, lr: 5.49e-04
+2022-05-27 20:32:04,790 INFO [train.py:823] (1/4) Epoch 31, batch 450, loss[loss=2.05, simple_loss=0.2166, pruned_loss=0.02203, codebook_loss=19.2, over 7317.00 frames.], tot_loss[loss=2.037, simple_loss=0.2438, pruned_loss=0.03205, codebook_loss=18.83, over 1269708.62 frames.], batch size: 18, lr: 5.48e-04
+2022-05-27 20:32:44,652 INFO [train.py:823] (1/4) Epoch 31, batch 500, loss[loss=1.985, simple_loss=0.233, pruned_loss=0.0275, codebook_loss=18.41, over 7089.00 frames.], tot_loss[loss=2.042, simple_loss=0.2431, pruned_loss=0.03204, codebook_loss=18.88, over 1302170.06 frames.], batch size: 18, lr: 5.48e-04
+2022-05-27 20:33:24,727 INFO [train.py:823] (1/4) Epoch 31, batch 550, loss[loss=2.177, simple_loss=0.2281, pruned_loss=0.02805, codebook_loss=20.35, over 7391.00 frames.], tot_loss[loss=2.047, simple_loss=0.2422, pruned_loss=0.03199, codebook_loss=18.94, over 1326765.29 frames.], batch size: 19, lr: 5.47e-04
+2022-05-27 20:34:04,428 INFO [train.py:823] (1/4) Epoch 31, batch 600, loss[loss=2.067, simple_loss=0.2485, pruned_loss=0.0341, codebook_loss=19.08, over 7251.00 frames.], tot_loss[loss=2.043, simple_loss=0.2428, pruned_loss=0.03215, codebook_loss=18.9, over 1347424.59 frames.], batch size: 16, lr: 5.47e-04
+2022-05-27 20:34:44,371 INFO [train.py:823] (1/4) Epoch 31, batch 650, loss[loss=1.989, simple_loss=0.2604, pruned_loss=0.03474, codebook_loss=18.24, over 7156.00 frames.], tot_loss[loss=2.041, simple_loss=0.2427, pruned_loss=0.03198, codebook_loss=18.87, over 1362802.05 frames.], batch size: 22, lr: 5.46e-04
+2022-05-27 20:35:24,058 INFO [train.py:823] (1/4) Epoch 31, batch 700, loss[loss=1.964, simple_loss=0.2121, pruned_loss=0.02554, codebook_loss=18.32, over 7314.00 frames.], tot_loss[loss=2.046, simple_loss=0.244, pruned_loss=0.03266, codebook_loss=18.91, over 1370974.74 frames.], batch size: 17, lr: 5.46e-04
+2022-05-27 20:36:04,249 INFO [train.py:823] (1/4) Epoch 31, batch 750, loss[loss=1.934, simple_loss=0.2035, pruned_loss=0.02151, codebook_loss=18.11, over 7302.00 frames.], tot_loss[loss=2.046, simple_loss=0.2441, pruned_loss=0.03242, codebook_loss=18.91, over 1382599.02 frames.], batch size: 18, lr: 5.45e-04
+2022-05-27 20:36:44,239 INFO [train.py:823] (1/4) Epoch 31, batch 800, loss[loss=2.059, simple_loss=0.2337, pruned_loss=0.03823, codebook_loss=19.04, over 7212.00 frames.], tot_loss[loss=2.047, simple_loss=0.244, pruned_loss=0.03238, codebook_loss=18.92, over 1392944.02 frames.], batch size: 16, lr: 5.45e-04
+2022-05-27 20:37:23,980 INFO [train.py:823] (1/4) Epoch 31, batch 850, loss[loss=2.077, simple_loss=0.2645, pruned_loss=0.04063, codebook_loss=19.04, over 6978.00 frames.], tot_loss[loss=2.048, simple_loss=0.2445, pruned_loss=0.03295, codebook_loss=18.93, over 1392245.08 frames.], batch size: 26, lr: 5.44e-04
+2022-05-27 20:38:03,456 INFO [train.py:823] (1/4) Epoch 31, batch 900, loss[loss=1.947, simple_loss=0.231, pruned_loss=0.01771, codebook_loss=18.14, over 7096.00 frames.], tot_loss[loss=2.048, simple_loss=0.2457, pruned_loss=0.03321, codebook_loss=18.92, over 1396579.60 frames.], batch size: 19, lr: 5.44e-04
+2022-05-27 20:38:58,912 INFO [train.py:823] (1/4) Epoch 32, batch 0, loss[loss=2.011, simple_loss=0.2473, pruned_loss=0.03494, codebook_loss=18.52, over 5130.00 frames.], tot_loss[loss=2.011, simple_loss=0.2473, pruned_loss=0.03494, codebook_loss=18.52, over 5130.00 frames.], batch size: 46, lr: 5.35e-04
+2022-05-27 20:39:38,612 INFO [train.py:823] (1/4) Epoch 32, batch 50, loss[loss=2.01, simple_loss=0.2084, pruned_loss=0.02662, codebook_loss=18.79, over 7293.00 frames.], tot_loss[loss=2.022, simple_loss=0.2408, pruned_loss=0.0299, codebook_loss=18.72, over 319734.13 frames.], batch size: 17, lr: 5.35e-04
+2022-05-27 20:40:18,784 INFO [train.py:823] (1/4) Epoch 32, batch 100, loss[loss=2.022, simple_loss=0.2458, pruned_loss=0.03527, codebook_loss=18.63, over 7163.00 frames.], tot_loss[loss=2.035, simple_loss=0.2441, pruned_loss=0.03222, codebook_loss=18.81, over 566110.36 frames.], batch size: 22, lr: 5.34e-04
+2022-05-27 20:40:58,681 INFO [train.py:823] (1/4) Epoch 32, batch 150, loss[loss=2.071, simple_loss=0.2371, pruned_loss=0.03273, codebook_loss=19.19, over 7198.00 frames.], tot_loss[loss=2.05, simple_loss=0.2444, pruned_loss=0.03233, codebook_loss=18.96, over 759161.26 frames.], batch size: 19, lr: 5.34e-04
+2022-05-27 20:41:38,652 INFO [train.py:823] (1/4) Epoch 32, batch 200, loss[loss=2.019, simple_loss=0.2499, pruned_loss=0.03227, codebook_loss=18.62, over 7204.00 frames.], tot_loss[loss=2.04, simple_loss=0.2452, pruned_loss=0.03202, codebook_loss=18.85, over 905295.43 frames.], batch size: 19, lr: 5.33e-04
+2022-05-27 20:42:18,579 INFO [train.py:823] (1/4) Epoch 32, batch 250, loss[loss=2.093, simple_loss=0.2446, pruned_loss=0.02915, codebook_loss=19.41, over 7195.00 frames.], tot_loss[loss=2.031, simple_loss=0.2433, pruned_loss=0.03148, codebook_loss=18.78, over 1022807.81 frames.], batch size: 19, lr: 5.33e-04
+2022-05-27 20:42:58,403 INFO [train.py:823] (1/4) Epoch 32, batch 300, loss[loss=1.971, simple_loss=0.2408, pruned_loss=0.02925, codebook_loss=18.21, over 7293.00 frames.], tot_loss[loss=2.032, simple_loss=0.2428, pruned_loss=0.03154, codebook_loss=18.79, over 1107898.40 frames.], batch size: 19, lr: 5.32e-04
+2022-05-27 20:43:38,304 INFO [train.py:823] (1/4) Epoch 32, batch 350, loss[loss=2.127, simple_loss=0.2551, pruned_loss=0.0489, codebook_loss=19.51, over 7005.00 frames.], tot_loss[loss=2.033, simple_loss=0.2431, pruned_loss=0.03171, codebook_loss=18.8, over 1176770.47 frames.], batch size: 16, lr: 5.32e-04
+2022-05-27 20:44:18,233 INFO [train.py:823] (1/4) Epoch 32, batch 400, loss[loss=1.991, simple_loss=0.2446, pruned_loss=0.02694, codebook_loss=18.41, over 6546.00 frames.], tot_loss[loss=2.036, simple_loss=0.244, pruned_loss=0.03195, codebook_loss=18.82, over 1226708.22 frames.], batch size: 34, lr: 5.32e-04
+2022-05-27 20:44:58,185 INFO [train.py:823] (1/4) Epoch 32, batch 450, loss[loss=1.989, simple_loss=0.2579, pruned_loss=0.0393, codebook_loss=18.2, over 7139.00 frames.], tot_loss[loss=2.039, simple_loss=0.2434, pruned_loss=0.03193, codebook_loss=18.86, over 1267333.02 frames.], batch size: 23, lr: 5.31e-04
+2022-05-27 20:45:38,584 INFO [train.py:823] (1/4) Epoch 32, batch 500, loss[loss=1.988, simple_loss=0.2406, pruned_loss=0.03074, codebook_loss=18.37, over 7196.00 frames.], tot_loss[loss=2.04, simple_loss=0.2429, pruned_loss=0.03194, codebook_loss=18.86, over 1300778.41 frames.], batch size: 20, lr: 5.31e-04
+2022-05-27 20:46:18,545 INFO [train.py:823] (1/4) Epoch 32, batch 550, loss[loss=2.019, simple_loss=0.2658, pruned_loss=0.04372, codebook_loss=18.42, over 7167.00 frames.], tot_loss[loss=2.034, simple_loss=0.2435, pruned_loss=0.0317, codebook_loss=18.8, over 1328992.95 frames.], batch size: 25, lr: 5.30e-04
+2022-05-27 20:46:58,691 INFO [train.py:823] (1/4) Epoch 32, batch 600, loss[loss=1.976, simple_loss=0.2089, pruned_loss=0.02548, codebook_loss=18.46, over 7298.00 frames.], tot_loss[loss=2.036, simple_loss=0.2445, pruned_loss=0.032, codebook_loss=18.82, over 1349653.36 frames.], batch size: 17, lr: 5.30e-04
+2022-05-27 20:47:38,435 INFO [train.py:823] (1/4) Epoch 32, batch 650, loss[loss=1.998, simple_loss=0.262, pruned_loss=0.03518, codebook_loss=18.32, over 7032.00 frames.], tot_loss[loss=2.041, simple_loss=0.2448, pruned_loss=0.03223, codebook_loss=18.86, over 1362378.25 frames.], batch size: 26, lr: 5.29e-04
+2022-05-27 20:48:18,752 INFO [train.py:823] (1/4) Epoch 32, batch 700, loss[loss=1.977, simple_loss=0.2378, pruned_loss=0.02812, codebook_loss=18.3, over 7102.00 frames.], tot_loss[loss=2.037, simple_loss=0.2438, pruned_loss=0.03194, codebook_loss=18.83, over 1378298.47 frames.], batch size: 20, lr: 5.29e-04
+2022-05-27 20:48:58,640 INFO [train.py:823] (1/4) Epoch 32, batch 750, loss[loss=1.977, simple_loss=0.2152, pruned_loss=0.02627, codebook_loss=18.43, over 7392.00 frames.], tot_loss[loss=2.037, simple_loss=0.2432, pruned_loss=0.03164, codebook_loss=18.84, over 1388944.26 frames.], batch size: 19, lr: 5.29e-04
+2022-05-27 20:49:38,940 INFO [train.py:823] (1/4) Epoch 32, batch 800, loss[loss=2.073, simple_loss=0.2049, pruned_loss=0.01971, codebook_loss=19.51, over 7165.00 frames.], tot_loss[loss=2.034, simple_loss=0.2427, pruned_loss=0.03148, codebook_loss=18.81, over 1397253.45 frames.], batch size: 17, lr: 5.28e-04
+2022-05-27 20:50:20,033 INFO [train.py:823] (1/4) Epoch 32, batch 850, loss[loss=1.974, simple_loss=0.2078, pruned_loss=0.02433, codebook_loss=18.46, over 7418.00 frames.], tot_loss[loss=2.038, simple_loss=0.2428, pruned_loss=0.03177, codebook_loss=18.84, over 1400927.30 frames.], batch size: 18, lr: 5.28e-04
+2022-05-27 20:51:02,554 INFO [train.py:823] (1/4) Epoch 32, batch 900, loss[loss=2.017, simple_loss=0.2245, pruned_loss=0.0313, codebook_loss=18.73, over 7027.00 frames.], tot_loss[loss=2.041, simple_loss=0.2436, pruned_loss=0.03197, codebook_loss=18.88, over 1405370.82 frames.], batch size: 17, lr: 5.27e-04
+2022-05-27 20:51:56,392 INFO [train.py:823] (1/4) Epoch 33, batch 0, loss[loss=1.936, simple_loss=0.2348, pruned_loss=0.02395, codebook_loss=17.95, over 7040.00 frames.], tot_loss[loss=1.936, simple_loss=0.2348, pruned_loss=0.02395, codebook_loss=17.95, over 7040.00 frames.], batch size: 29, lr: 5.19e-04
+2022-05-27 20:52:36,663 INFO [train.py:823] (1/4) Epoch 33, batch 50, loss[loss=2.096, simple_loss=0.2278, pruned_loss=0.03303, codebook_loss=19.49, over 7153.00 frames.], tot_loss[loss=2.032, simple_loss=0.2432, pruned_loss=0.03165, codebook_loss=18.79, over 317680.44 frames.], batch size: 17, lr: 5.18e-04
+2022-05-27 20:53:16,499 INFO [train.py:823] (1/4) Epoch 33, batch 100, loss[loss=1.954, simple_loss=0.2101, pruned_loss=0.02477, codebook_loss=18.24, over 6820.00 frames.], tot_loss[loss=2.046, simple_loss=0.2415, pruned_loss=0.03166, codebook_loss=18.94, over 562243.72 frames.], batch size: 15, lr: 5.18e-04
+2022-05-27 20:53:56,618 INFO [train.py:823] (1/4) Epoch 33, batch 150, loss[loss=1.932, simple_loss=0.2399, pruned_loss=0.02369, codebook_loss=17.89, over 7193.00 frames.], tot_loss[loss=2.039, simple_loss=0.2436, pruned_loss=0.03187, codebook_loss=18.86, over 751473.00 frames.], batch size: 21, lr: 5.18e-04
+2022-05-27 20:54:36,232 INFO [train.py:823] (1/4) Epoch 33, batch 200, loss[loss=1.995, simple_loss=0.2716, pruned_loss=0.03658, codebook_loss=18.23, over 7116.00 frames.], tot_loss[loss=2.036, simple_loss=0.2431, pruned_loss=0.03137, codebook_loss=18.83, over 893384.96 frames.], batch size: 20, lr: 5.17e-04
+2022-05-27 20:55:16,530 INFO [train.py:823] (1/4) Epoch 33, batch 250, loss[loss=2.04, simple_loss=0.2635, pruned_loss=0.03719, codebook_loss=18.71, over 7147.00 frames.], tot_loss[loss=2.04, simple_loss=0.2435, pruned_loss=0.03191, codebook_loss=18.87, over 1014057.98 frames.], batch size: 23, lr: 5.17e-04
+2022-05-27 20:55:56,435 INFO [train.py:823] (1/4) Epoch 33, batch 300, loss[loss=2.408, simple_loss=0.2449, pruned_loss=0.04864, codebook_loss=22.37, over 7165.00 frames.], tot_loss[loss=2.034, simple_loss=0.2423, pruned_loss=0.03107, codebook_loss=18.81, over 1107514.58 frames.], batch size: 17, lr: 5.16e-04
+2022-05-27 20:56:36,517 INFO [train.py:823] (1/4) Epoch 33, batch 350, loss[loss=2.011, simple_loss=0.257, pruned_loss=0.04298, codebook_loss=18.4, over 7323.00 frames.], tot_loss[loss=2.035, simple_loss=0.2431, pruned_loss=0.03154, codebook_loss=18.82, over 1177112.87 frames.], batch size: 23, lr: 5.16e-04
+2022-05-27 20:57:16,234 INFO [train.py:823] (1/4) Epoch 33, batch 400, loss[loss=2.009, simple_loss=0.2612, pruned_loss=0.03633, codebook_loss=18.42, over 7420.00 frames.], tot_loss[loss=2.038, simple_loss=0.2432, pruned_loss=0.03137, codebook_loss=18.85, over 1231630.49 frames.], batch size: 22, lr: 5.16e-04
+2022-05-27 20:57:56,238 INFO [train.py:823] (1/4) Epoch 33, batch 450, loss[loss=1.982, simple_loss=0.2357, pruned_loss=0.02591, codebook_loss=18.38, over 7296.00 frames.], tot_loss[loss=2.039, simple_loss=0.2434, pruned_loss=0.03116, codebook_loss=18.86, over 1272769.39 frames.], batch size: 19, lr: 5.15e-04
+2022-05-27 20:58:35,798 INFO [train.py:823] (1/4) Epoch 33, batch 500, loss[loss=2.003, simple_loss=0.2368, pruned_loss=0.02537, codebook_loss=18.59, over 6956.00 frames.], tot_loss[loss=2.044, simple_loss=0.2438, pruned_loss=0.03149, codebook_loss=18.9, over 1307132.83 frames.], batch size: 29, lr: 5.15e-04
+2022-05-27 20:59:16,000 INFO [train.py:823] (1/4) Epoch 33, batch 550, loss[loss=2.106, simple_loss=0.2559, pruned_loss=0.04607, codebook_loss=19.32, over 7395.00 frames.], tot_loss[loss=2.044, simple_loss=0.2439, pruned_loss=0.03177, codebook_loss=18.91, over 1335630.37 frames.], batch size: 19, lr: 5.14e-04
+2022-05-27 20:59:56,145 INFO [train.py:823] (1/4) Epoch 33, batch 600, loss[loss=1.996, simple_loss=0.2628, pruned_loss=0.03453, codebook_loss=18.3, over 7430.00 frames.], tot_loss[loss=2.042, simple_loss=0.2427, pruned_loss=0.03166, codebook_loss=18.89, over 1353874.26 frames.], batch size: 22, lr: 5.14e-04
+2022-05-27 21:00:36,455 INFO [train.py:823] (1/4) Epoch 33, batch 650, loss[loss=2.068, simple_loss=0.2016, pruned_loss=0.0152, codebook_loss=19.52, over 7157.00 frames.], tot_loss[loss=2.045, simple_loss=0.2422, pruned_loss=0.03152, codebook_loss=18.92, over 1373281.00 frames.], batch size: 17, lr: 5.14e-04
+2022-05-27 21:01:16,095 INFO [train.py:823] (1/4) Epoch 33, batch 700, loss[loss=2.063, simple_loss=0.2403, pruned_loss=0.03002, codebook_loss=19.13, over 6434.00 frames.], tot_loss[loss=2.044, simple_loss=0.2423, pruned_loss=0.0314, codebook_loss=18.91, over 1384039.91 frames.], batch size: 34, lr: 5.13e-04
+2022-05-27 21:01:56,091 INFO [train.py:823] (1/4) Epoch 33, batch 750, loss[loss=2.098, simple_loss=0.2709, pruned_loss=0.03886, codebook_loss=19.24, over 7194.00 frames.], tot_loss[loss=2.044, simple_loss=0.2433, pruned_loss=0.0314, codebook_loss=18.91, over 1389997.00 frames.], batch size: 25, lr: 5.13e-04
+2022-05-27 21:02:35,424 INFO [train.py:823] (1/4) Epoch 33, batch 800, loss[loss=2.005, simple_loss=0.2669, pruned_loss=0.04255, codebook_loss=18.29, over 7179.00 frames.], tot_loss[loss=2.038, simple_loss=0.2441, pruned_loss=0.0315, codebook_loss=18.84, over 1389906.96 frames.], batch size: 22, lr: 5.12e-04
+2022-05-27 21:03:16,846 INFO [train.py:823] (1/4) Epoch 33, batch 850, loss[loss=1.998, simple_loss=0.2212, pruned_loss=0.02569, codebook_loss=18.62, over 7077.00 frames.], tot_loss[loss=2.034, simple_loss=0.2432, pruned_loss=0.03132, codebook_loss=18.81, over 1399318.53 frames.], batch size: 18, lr: 5.12e-04
+2022-05-27 21:03:56,328 INFO [train.py:823] (1/4) Epoch 33, batch 900, loss[loss=2.021, simple_loss=0.2163, pruned_loss=0.02649, codebook_loss=18.87, over 7001.00 frames.], tot_loss[loss=2.037, simple_loss=0.2433, pruned_loss=0.03118, codebook_loss=18.84, over 1400847.70 frames.], batch size: 16, lr: 5.12e-04
+2022-05-27 21:04:47,353 INFO [train.py:823] (1/4) Epoch 34, batch 0, loss[loss=2.03, simple_loss=0.2549, pruned_loss=0.02256, codebook_loss=18.8, over 7192.00 frames.], tot_loss[loss=2.03, simple_loss=0.2549, pruned_loss=0.02256, codebook_loss=18.8, over 7192.00 frames.], batch size: 24, lr: 5.04e-04
+2022-05-27 21:05:27,123 INFO [train.py:823] (1/4) Epoch 34, batch 50, loss[loss=2.045, simple_loss=0.2259, pruned_loss=0.03428, codebook_loss=18.98, over 7208.00 frames.], tot_loss[loss=2.028, simple_loss=0.2383, pruned_loss=0.02951, codebook_loss=18.8, over 319673.07 frames.], batch size: 16, lr: 5.03e-04
+2022-05-27 21:06:07,168 INFO [train.py:823] (1/4) Epoch 34, batch 100, loss[loss=1.948, simple_loss=0.2454, pruned_loss=0.01909, codebook_loss=18.06, over 7277.00 frames.], tot_loss[loss=2.029, simple_loss=0.2412, pruned_loss=0.03007, codebook_loss=18.79, over 560528.65 frames.], batch size: 21, lr: 5.03e-04
+2022-05-27 21:06:47,136 INFO [train.py:823] (1/4) Epoch 34, batch 150, loss[loss=1.978, simple_loss=0.2549, pruned_loss=0.03641, codebook_loss=18.14, over 7299.00 frames.], tot_loss[loss=2.031, simple_loss=0.2421, pruned_loss=0.03022, codebook_loss=18.79, over 753979.70 frames.], batch size: 22, lr: 5.02e-04
+2022-05-27 21:07:27,094 INFO [train.py:823] (1/4) Epoch 34, batch 200, loss[loss=1.959, simple_loss=0.262, pruned_loss=0.02888, codebook_loss=17.99, over 7024.00 frames.], tot_loss[loss=2.032, simple_loss=0.2421, pruned_loss=0.03063, codebook_loss=18.81, over 901824.34 frames.], batch size: 26, lr: 5.02e-04
+2022-05-27 21:08:06,789 INFO [train.py:823] (1/4) Epoch 34, batch 250, loss[loss=2.211, simple_loss=0.2542, pruned_loss=0.03488, codebook_loss=20.49, over 6928.00 frames.], tot_loss[loss=2.032, simple_loss=0.2426, pruned_loss=0.03106, codebook_loss=18.8, over 1012062.84 frames.], batch size: 26, lr: 5.02e-04
+2022-05-27 21:08:46,835 INFO [train.py:823] (1/4) Epoch 34, batch 300, loss[loss=2.005, simple_loss=0.2329, pruned_loss=0.02177, codebook_loss=18.67, over 7374.00 frames.], tot_loss[loss=2.032, simple_loss=0.2426, pruned_loss=0.03133, codebook_loss=18.8, over 1101804.28 frames.], batch size: 21, lr: 5.01e-04
+2022-05-27 21:09:26,854 INFO [train.py:823] (1/4) Epoch 34, batch 350, loss[loss=1.971, simple_loss=0.2335, pruned_loss=0.02373, codebook_loss=18.3, over 7111.00 frames.], tot_loss[loss=2.029, simple_loss=0.2431, pruned_loss=0.03139, codebook_loss=18.76, over 1169304.57 frames.], batch size: 19, lr: 5.01e-04
+2022-05-27 21:10:07,250 INFO [train.py:823] (1/4) Epoch 34, batch 400, loss[loss=2.01, simple_loss=0.2621, pruned_loss=0.03817, codebook_loss=18.41, over 7294.00 frames.], tot_loss[loss=2.028, simple_loss=0.2429, pruned_loss=0.0315, codebook_loss=18.75, over 1224252.14 frames.], batch size: 21, lr: 5.00e-04
+2022-05-27 21:10:46,990 INFO [train.py:823] (1/4) Epoch 34, batch 450, loss[loss=2.112, simple_loss=0.2736, pruned_loss=0.05385, codebook_loss=19.21, over 7289.00 frames.], tot_loss[loss=2.03, simple_loss=0.2431, pruned_loss=0.03161, codebook_loss=18.77, over 1270096.95 frames.], batch size: 20, lr: 5.00e-04
+2022-05-27 21:11:27,177 INFO [train.py:823] (1/4) Epoch 34, batch 500, loss[loss=2.087, simple_loss=0.263, pruned_loss=0.04272, codebook_loss=19.13, over 7166.00 frames.], tot_loss[loss=2.035, simple_loss=0.2428, pruned_loss=0.03142, codebook_loss=18.82, over 1303102.39 frames.], batch size: 23, lr: 5.00e-04
+2022-05-27 21:12:07,372 INFO [train.py:823] (1/4) Epoch 34, batch 550, loss[loss=2.013, simple_loss=0.249, pruned_loss=0.03641, codebook_loss=18.52, over 7200.00 frames.], tot_loss[loss=2.027, simple_loss=0.2425, pruned_loss=0.03096, codebook_loss=18.75, over 1335260.47 frames.], batch size: 25, lr: 4.99e-04
+2022-05-27 21:12:47,528 INFO [train.py:823] (1/4) Epoch 34, batch 600, loss[loss=1.945, simple_loss=0.2038, pruned_loss=0.02174, codebook_loss=18.22, over 7300.00 frames.], tot_loss[loss=2.027, simple_loss=0.2427, pruned_loss=0.03086, codebook_loss=18.74, over 1353061.58 frames.], batch size: 17, lr: 4.99e-04
+2022-05-27 21:13:27,633 INFO [train.py:823] (1/4) Epoch 34, batch 650, loss[loss=2.12, simple_loss=0.2596, pruned_loss=0.04021, codebook_loss=19.5, over 6971.00 frames.], tot_loss[loss=2.033, simple_loss=0.2416, pruned_loss=0.03092, codebook_loss=18.81, over 1367133.36 frames.], batch size: 29, lr: 4.99e-04
+2022-05-27 21:14:11,304 INFO [train.py:823] (1/4) Epoch 34, batch 700, loss[loss=1.999, simple_loss=0.2357, pruned_loss=0.03501, codebook_loss=18.46, over 7372.00 frames.], tot_loss[loss=2.034, simple_loss=0.2415, pruned_loss=0.03107, codebook_loss=18.82, over 1375537.17 frames.], batch size: 20, lr: 4.98e-04
+2022-05-27 21:14:51,476 INFO [train.py:823] (1/4) Epoch 34, batch 750, loss[loss=1.961, simple_loss=0.2151, pruned_loss=0.01919, codebook_loss=18.35, over 7008.00 frames.], tot_loss[loss=2.041, simple_loss=0.2423, pruned_loss=0.03162, codebook_loss=18.88, over 1387446.09 frames.], batch size: 16, lr: 4.98e-04
+2022-05-27 21:15:35,813 INFO [train.py:823] (1/4) Epoch 34, batch 800, loss[loss=1.944, simple_loss=0.212, pruned_loss=0.01771, codebook_loss=18.2, over 7212.00 frames.], tot_loss[loss=2.044, simple_loss=0.2426, pruned_loss=0.03194, codebook_loss=18.9, over 1395525.39 frames.], batch size: 19, lr: 4.97e-04
+2022-05-27 21:16:15,609 INFO [train.py:823] (1/4) Epoch 34, batch 850, loss[loss=1.956, simple_loss=0.2434, pruned_loss=0.02527, codebook_loss=18.09, over 7374.00 frames.], tot_loss[loss=2.033, simple_loss=0.2422, pruned_loss=0.03127, codebook_loss=18.81, over 1395941.53 frames.], batch size: 21, lr: 4.97e-04
+2022-05-27 21:16:55,866 INFO [train.py:823] (1/4) Epoch 34, batch 900, loss[loss=2.011, simple_loss=0.2403, pruned_loss=0.03168, codebook_loss=18.6, over 7102.00 frames.], tot_loss[loss=2.036, simple_loss=0.2421, pruned_loss=0.03134, codebook_loss=18.83, over 1400053.35 frames.], batch size: 18, lr: 4.97e-04
+2022-05-27 21:17:49,294 INFO [train.py:823] (1/4) Epoch 35, batch 0, loss[loss=2.126, simple_loss=0.2432, pruned_loss=0.02119, codebook_loss=19.83, over 7186.00 frames.], tot_loss[loss=2.126, simple_loss=0.2432, pruned_loss=0.02119, codebook_loss=19.83, over 7186.00 frames.], batch size: 21, lr: 4.89e-04
+2022-05-27 21:18:30,080 INFO [train.py:823] (1/4) Epoch 35, batch 50, loss[loss=2.194, simple_loss=0.2364, pruned_loss=0.03684, codebook_loss=20.39, over 7191.00 frames.], tot_loss[loss=2.031, simple_loss=0.2439, pruned_loss=0.03005, codebook_loss=18.79, over 323702.48 frames.], batch size: 18, lr: 4.89e-04
+2022-05-27 21:19:10,039 INFO [train.py:823] (1/4) Epoch 35, batch 100, loss[loss=1.997, simple_loss=0.2424, pruned_loss=0.02128, codebook_loss=18.55, over 6563.00 frames.], tot_loss[loss=2.029, simple_loss=0.243, pruned_loss=0.03008, codebook_loss=18.77, over 568737.04 frames.], batch size: 34, lr: 4.88e-04
+2022-05-27 21:19:50,176 INFO [train.py:823] (1/4) Epoch 35, batch 150, loss[loss=2.117, simple_loss=0.2349, pruned_loss=0.0308, codebook_loss=19.69, over 7216.00 frames.], tot_loss[loss=2.023, simple_loss=0.2406, pruned_loss=0.02998, codebook_loss=18.73, over 755001.50 frames.], batch size: 25, lr: 4.88e-04
+2022-05-27 21:20:30,560 INFO [train.py:823] (1/4) Epoch 35, batch 200, loss[loss=1.89, simple_loss=0.2239, pruned_loss=0.01735, codebook_loss=17.61, over 6868.00 frames.], tot_loss[loss=2.028, simple_loss=0.2407, pruned_loss=0.03022, codebook_loss=18.78, over 904674.09 frames.], batch size: 29, lr: 4.88e-04
+2022-05-27 21:21:10,402 INFO [train.py:823] (1/4) Epoch 35, batch 250, loss[loss=1.929, simple_loss=0.2438, pruned_loss=0.02841, codebook_loss=17.78, over 7221.00 frames.], tot_loss[loss=2.02, simple_loss=0.2405, pruned_loss=0.03011, codebook_loss=18.69, over 1013474.34 frames.], batch size: 24, lr: 4.87e-04
+2022-05-27 21:21:50,288 INFO [train.py:823] (1/4) Epoch 35, batch 300, loss[loss=1.978, simple_loss=0.2505, pruned_loss=0.03772, codebook_loss=18.15, over 7285.00 frames.], tot_loss[loss=2.022, simple_loss=0.2409, pruned_loss=0.03086, codebook_loss=18.7, over 1106714.22 frames.], batch size: 21, lr: 4.87e-04
+2022-05-27 21:22:30,346 INFO [train.py:823] (1/4) Epoch 35, batch 350, loss[loss=1.936, simple_loss=0.2043, pruned_loss=0.02432, codebook_loss=18.1, over 7088.00 frames.], tot_loss[loss=2.019, simple_loss=0.2405, pruned_loss=0.03064, codebook_loss=18.68, over 1172875.77 frames.], batch size: 18, lr: 4.87e-04
+2022-05-27 21:23:10,166 INFO [train.py:823] (1/4) Epoch 35, batch 400, loss[loss=2.131, simple_loss=0.2602, pruned_loss=0.04052, codebook_loss=19.61, over 7155.00 frames.], tot_loss[loss=2.022, simple_loss=0.2409, pruned_loss=0.03098, codebook_loss=18.7, over 1223339.61 frames.], batch size: 22, lr: 4.86e-04
+2022-05-27 21:23:50,296 INFO [train.py:823] (1/4) Epoch 35, batch 450, loss[loss=1.997, simple_loss=0.2156, pruned_loss=0.02627, codebook_loss=18.63, over 7298.00 frames.], tot_loss[loss=2.023, simple_loss=0.2413, pruned_loss=0.03087, codebook_loss=18.71, over 1270565.69 frames.], batch size: 17, lr: 4.86e-04
+2022-05-27 21:24:30,258 INFO [train.py:823] (1/4) Epoch 35, batch 500, loss[loss=1.993, simple_loss=0.2223, pruned_loss=0.02716, codebook_loss=18.55, over 7017.00 frames.], tot_loss[loss=2.02, simple_loss=0.2415, pruned_loss=0.03057, codebook_loss=18.68, over 1305729.87 frames.], batch size: 17, lr: 4.86e-04
+2022-05-27 21:25:10,227 INFO [train.py:823] (1/4) Epoch 35, batch 550, loss[loss=1.978, simple_loss=0.2189, pruned_loss=0.0269, codebook_loss=18.42, over 7022.00 frames.], tot_loss[loss=2.021, simple_loss=0.2417, pruned_loss=0.03075, codebook_loss=18.7, over 1329081.57 frames.], batch size: 17, lr: 4.85e-04
+2022-05-27 21:25:50,311 INFO [train.py:823] (1/4) Epoch 35, batch 600, loss[loss=2.07, simple_loss=0.2573, pruned_loss=0.03536, codebook_loss=19.06, over 7276.00 frames.], tot_loss[loss=2.025, simple_loss=0.2416, pruned_loss=0.03081, codebook_loss=18.74, over 1349045.60 frames.], batch size: 20, lr: 4.85e-04
+2022-05-27 21:26:30,417 INFO [train.py:823] (1/4) Epoch 35, batch 650, loss[loss=2.043, simple_loss=0.2505, pruned_loss=0.02836, codebook_loss=18.9, over 6971.00 frames.], tot_loss[loss=2.029, simple_loss=0.2412, pruned_loss=0.03084, codebook_loss=18.77, over 1368173.90 frames.], batch size: 26, lr: 4.84e-04
+2022-05-27 21:27:11,695 INFO [train.py:823] (1/4) Epoch 35, batch 700, loss[loss=1.989, simple_loss=0.2344, pruned_loss=0.02338, codebook_loss=18.49, over 7274.00 frames.], tot_loss[loss=2.032, simple_loss=0.241, pruned_loss=0.03107, codebook_loss=18.8, over 1378294.64 frames.], batch size: 20, lr: 4.84e-04
+2022-05-27 21:27:51,846 INFO [train.py:823] (1/4) Epoch 35, batch 750, loss[loss=1.944, simple_loss=0.2247, pruned_loss=0.01964, codebook_loss=18.12, over 7111.00 frames.], tot_loss[loss=2.032, simple_loss=0.2425, pruned_loss=0.03133, codebook_loss=18.79, over 1391286.95 frames.], batch size: 19, lr: 4.84e-04
+2022-05-27 21:28:31,666 INFO [train.py:823] (1/4) Epoch 35, batch 800, loss[loss=1.958, simple_loss=0.2269, pruned_loss=0.02725, codebook_loss=18.17, over 7311.00 frames.], tot_loss[loss=2.031, simple_loss=0.2428, pruned_loss=0.0315, codebook_loss=18.78, over 1395224.78 frames.], batch size: 18, lr: 4.83e-04
+2022-05-27 21:29:11,830 INFO [train.py:823] (1/4) Epoch 35, batch 850, loss[loss=2.072, simple_loss=0.2625, pruned_loss=0.0275, codebook_loss=19.13, over 7413.00 frames.], tot_loss[loss=2.033, simple_loss=0.2431, pruned_loss=0.0314, codebook_loss=18.8, over 1404157.32 frames.], batch size: 22, lr: 4.83e-04
+2022-05-27 21:29:51,291 INFO [train.py:823] (1/4) Epoch 35, batch 900, loss[loss=2.072, simple_loss=0.2509, pruned_loss=0.03184, codebook_loss=19.15, over 6475.00 frames.], tot_loss[loss=2.033, simple_loss=0.2431, pruned_loss=0.03143, codebook_loss=18.8, over 1401431.40 frames.], batch size: 34, lr: 4.83e-04
+2022-05-27 21:30:31,018 INFO [train.py:823] (1/4) Epoch 35, batch 950, loss[loss=1.954, simple_loss=0.2448, pruned_loss=0.0365, codebook_loss=17.96, over 4890.00 frames.], tot_loss[loss=2.034, simple_loss=0.2437, pruned_loss=0.032, codebook_loss=18.8, over 1379222.59 frames.], batch size: 48, lr: 4.82e-04
+2022-05-27 21:30:46,169 INFO [train.py:823] (1/4) Epoch 36, batch 0, loss[loss=1.951, simple_loss=0.2633, pruned_loss=0.02528, codebook_loss=17.94, over 7418.00 frames.], tot_loss[loss=1.951, simple_loss=0.2633, pruned_loss=0.02528, codebook_loss=17.94, over 7418.00 frames.], batch size: 22, lr: 4.76e-04
+2022-05-27 21:31:25,792 INFO [train.py:823] (1/4) Epoch 36, batch 50, loss[loss=1.931, simple_loss=0.2098, pruned_loss=0.01963, codebook_loss=18.06, over 7171.00 frames.], tot_loss[loss=2.01, simple_loss=0.2373, pruned_loss=0.02852, codebook_loss=18.63, over 318573.21 frames.], batch size: 17, lr: 4.75e-04
+2022-05-27 21:32:05,764 INFO [train.py:823] (1/4) Epoch 36, batch 100, loss[loss=2.014, simple_loss=0.2586, pruned_loss=0.0368, codebook_loss=18.48, over 6508.00 frames.], tot_loss[loss=2.01, simple_loss=0.2399, pruned_loss=0.02901, codebook_loss=18.61, over 564379.59 frames.], batch size: 34, lr: 4.75e-04
+2022-05-27 21:32:45,257 INFO [train.py:823] (1/4) Epoch 36, batch 150, loss[loss=1.979, simple_loss=0.2494, pruned_loss=0.03671, codebook_loss=18.18, over 7221.00 frames.], tot_loss[loss=2.02, simple_loss=0.2415, pruned_loss=0.03039, codebook_loss=18.69, over 751580.86 frames.], batch size: 25, lr: 4.74e-04
+2022-05-27 21:33:25,468 INFO [train.py:823] (1/4) Epoch 36, batch 200, loss[loss=1.964, simple_loss=0.2159, pruned_loss=0.02896, codebook_loss=18.27, over 7308.00 frames.], tot_loss[loss=2.02, simple_loss=0.2415, pruned_loss=0.03049, codebook_loss=18.68, over 899331.08 frames.], batch size: 17, lr: 4.74e-04
+2022-05-27 21:34:05,048 INFO [train.py:823] (1/4) Epoch 36, batch 250, loss[loss=1.937, simple_loss=0.2293, pruned_loss=0.02266, codebook_loss=17.99, over 7385.00 frames.], tot_loss[loss=2.029, simple_loss=0.2411, pruned_loss=0.03071, codebook_loss=18.78, over 1013033.39 frames.], batch size: 19, lr: 4.74e-04
+2022-05-27 21:34:45,306 INFO [train.py:823] (1/4) Epoch 36, batch 300, loss[loss=2.066, simple_loss=0.2593, pruned_loss=0.04174, codebook_loss=18.95, over 7347.00 frames.], tot_loss[loss=2.024, simple_loss=0.2397, pruned_loss=0.03007, codebook_loss=18.74, over 1102157.87 frames.], batch size: 23, lr: 4.73e-04
+2022-05-27 21:35:25,043 INFO [train.py:823] (1/4) Epoch 36, batch 350, loss[loss=1.997, simple_loss=0.2347, pruned_loss=0.02737, codebook_loss=18.52, over 7374.00 frames.], tot_loss[loss=2.018, simple_loss=0.2394, pruned_loss=0.02981, codebook_loss=18.69, over 1172512.04 frames.], batch size: 20, lr: 4.73e-04
+2022-05-27 21:36:05,136 INFO [train.py:823] (1/4) Epoch 36, batch 400, loss[loss=2.103, simple_loss=0.2275, pruned_loss=0.03259, codebook_loss=19.57, over 7104.00 frames.], tot_loss[loss=2.016, simple_loss=0.2409, pruned_loss=0.03028, codebook_loss=18.66, over 1227868.36 frames.], batch size: 18, lr: 4.73e-04
+2022-05-27 21:36:44,921 INFO [train.py:823] (1/4) Epoch 36, batch 450, loss[loss=1.99, simple_loss=0.2629, pruned_loss=0.03783, codebook_loss=18.21, over 7012.00 frames.], tot_loss[loss=2.021, simple_loss=0.2414, pruned_loss=0.03093, codebook_loss=18.7, over 1270255.07 frames.], batch size: 26, lr: 4.72e-04
+2022-05-27 21:37:25,014 INFO [train.py:823] (1/4) Epoch 36, batch 500, loss[loss=2.138, simple_loss=0.2626, pruned_loss=0.03991, codebook_loss=19.67, over 7200.00 frames.], tot_loss[loss=2.018, simple_loss=0.2414, pruned_loss=0.03072, codebook_loss=18.67, over 1301052.62 frames.], batch size: 24, lr: 4.72e-04
+2022-05-27 21:38:04,894 INFO [train.py:823] (1/4) Epoch 36, batch 550, loss[loss=1.978, simple_loss=0.222, pruned_loss=0.02391, codebook_loss=18.43, over 7297.00 frames.], tot_loss[loss=2.016, simple_loss=0.2408, pruned_loss=0.03028, codebook_loss=18.65, over 1327820.38 frames.], batch size: 17, lr: 4.72e-04
+2022-05-27 21:38:45,256 INFO [train.py:823] (1/4) Epoch 36, batch 600, loss[loss=2.168, simple_loss=0.2315, pruned_loss=0.03355, codebook_loss=20.19, over 7283.00 frames.], tot_loss[loss=2.023, simple_loss=0.2415, pruned_loss=0.03089, codebook_loss=18.71, over 1346225.55 frames.], batch size: 17, lr: 4.71e-04
+2022-05-27 21:39:26,315 INFO [train.py:823] (1/4) Epoch 36, batch 650, loss[loss=2.246, simple_loss=0.2771, pruned_loss=0.04289, codebook_loss=20.64, over 7374.00 frames.], tot_loss[loss=2.029, simple_loss=0.2428, pruned_loss=0.03144, codebook_loss=18.76, over 1361482.67 frames.], batch size: 21, lr: 4.71e-04
+2022-05-27 21:40:09,243 INFO [train.py:823] (1/4) Epoch 36, batch 700, loss[loss=2.047, simple_loss=0.2249, pruned_loss=0.04054, codebook_loss=18.94, over 7293.00 frames.], tot_loss[loss=2.031, simple_loss=0.2429, pruned_loss=0.03145, codebook_loss=18.78, over 1377560.38 frames.], batch size: 17, lr: 4.71e-04
+2022-05-27 21:40:49,257 INFO [train.py:823] (1/4) Epoch 36, batch 750, loss[loss=2.031, simple_loss=0.2503, pruned_loss=0.03379, codebook_loss=18.72, over 7285.00 frames.], tot_loss[loss=2.03, simple_loss=0.2418, pruned_loss=0.03119, codebook_loss=18.78, over 1386588.53 frames.], batch size: 21, lr: 4.70e-04
+2022-05-27 21:41:29,162 INFO [train.py:823] (1/4) Epoch 36, batch 800, loss[loss=1.942, simple_loss=0.2453, pruned_loss=0.02485, codebook_loss=17.94, over 7373.00 frames.], tot_loss[loss=2.026, simple_loss=0.2418, pruned_loss=0.03085, codebook_loss=18.74, over 1387730.61 frames.], batch size: 21, lr: 4.70e-04
+2022-05-27 21:42:08,716 INFO [train.py:823] (1/4) Epoch 36, batch 850, loss[loss=1.917, simple_loss=0.2457, pruned_loss=0.02876, codebook_loss=17.66, over 7351.00 frames.], tot_loss[loss=2.029, simple_loss=0.2416, pruned_loss=0.03098, codebook_loss=18.77, over 1388268.37 frames.], batch size: 23, lr: 4.70e-04
+2022-05-27 21:42:48,768 INFO [train.py:823] (1/4) Epoch 36, batch 900, loss[loss=1.904, simple_loss=0.244, pruned_loss=0.01831, codebook_loss=17.64, over 7425.00 frames.], tot_loss[loss=2.027, simple_loss=0.2425, pruned_loss=0.0309, codebook_loss=18.75, over 1396152.75 frames.], batch size: 22, lr: 4.69e-04
+2022-05-27 21:43:42,190 INFO [train.py:823] (1/4) Epoch 37, batch 0, loss[loss=1.924, simple_loss=0.2434, pruned_loss=0.02562, codebook_loss=17.76, over 6508.00 frames.], tot_loss[loss=1.924, simple_loss=0.2434, pruned_loss=0.02562, codebook_loss=17.76, over 6508.00 frames.], batch size: 34, lr: 4.63e-04
+2022-05-27 21:44:22,064 INFO [train.py:823] (1/4) Epoch 37, batch 50, loss[loss=2.107, simple_loss=0.2486, pruned_loss=0.02912, codebook_loss=19.54, over 7309.00 frames.], tot_loss[loss=2.012, simple_loss=0.2433, pruned_loss=0.0298, codebook_loss=18.6, over 319984.74 frames.], batch size: 22, lr: 4.62e-04
+2022-05-27 21:45:01,721 INFO [train.py:823] (1/4) Epoch 37, batch 100, loss[loss=1.971, simple_loss=0.2492, pruned_loss=0.02995, codebook_loss=18.17, over 7205.00 frames.], tot_loss[loss=2.005, simple_loss=0.2427, pruned_loss=0.02977, codebook_loss=18.54, over 562122.93 frames.], batch size: 24, lr: 4.62e-04
+2022-05-27 21:45:41,728 INFO [train.py:823] (1/4) Epoch 37, batch 150, loss[loss=2.032, simple_loss=0.2311, pruned_loss=0.01904, codebook_loss=18.97, over 7188.00 frames.], tot_loss[loss=2.012, simple_loss=0.2424, pruned_loss=0.03008, codebook_loss=18.6, over 751018.24 frames.], batch size: 21, lr: 4.62e-04
+2022-05-27 21:46:21,879 INFO [train.py:823] (1/4) Epoch 37, batch 200, loss[loss=1.965, simple_loss=0.2553, pruned_loss=0.03574, codebook_loss=18.02, over 7219.00 frames.], tot_loss[loss=2.012, simple_loss=0.2399, pruned_loss=0.03016, codebook_loss=18.62, over 903887.61 frames.], batch size: 24, lr: 4.61e-04
+2022-05-27 21:47:01,949 INFO [train.py:823] (1/4) Epoch 37, batch 250, loss[loss=2.026, simple_loss=0.2355, pruned_loss=0.02933, codebook_loss=18.79, over 6992.00 frames.], tot_loss[loss=2.01, simple_loss=0.2406, pruned_loss=0.03025, codebook_loss=18.59, over 1020635.86 frames.], batch size: 26, lr: 4.61e-04
+2022-05-27 21:47:41,872 INFO [train.py:823] (1/4) Epoch 37, batch 300, loss[loss=1.955, simple_loss=0.2263, pruned_loss=0.02627, codebook_loss=18.16, over 7015.00 frames.], tot_loss[loss=2.013, simple_loss=0.2395, pruned_loss=0.02989, codebook_loss=18.63, over 1106265.49 frames.], batch size: 16, lr: 4.61e-04
+2022-05-27 21:48:21,741 INFO [train.py:823] (1/4) Epoch 37, batch 350, loss[loss=2.19, simple_loss=0.2642, pruned_loss=0.04516, codebook_loss=20.13, over 7207.00 frames.], tot_loss[loss=2.007, simple_loss=0.2394, pruned_loss=0.02967, codebook_loss=18.58, over 1172941.57 frames.], batch size: 25, lr: 4.60e-04
+2022-05-27 21:49:01,283 INFO [train.py:823] (1/4) Epoch 37, batch 400, loss[loss=1.998, simple_loss=0.2281, pruned_loss=0.03244, codebook_loss=18.51, over 7305.00 frames.], tot_loss[loss=2.009, simple_loss=0.2403, pruned_loss=0.02987, codebook_loss=18.59, over 1229323.32 frames.], batch size: 17, lr: 4.60e-04
+2022-05-27 21:49:41,286 INFO [train.py:823] (1/4) Epoch 37, batch 450, loss[loss=2.163, simple_loss=0.2156, pruned_loss=0.01921, codebook_loss=20.36, over 7191.00 frames.], tot_loss[loss=2.014, simple_loss=0.2408, pruned_loss=0.02997, codebook_loss=18.63, over 1268692.07 frames.], batch size: 19, lr: 4.60e-04
+2022-05-27 21:50:22,182 INFO [train.py:823] (1/4) Epoch 37, batch 500, loss[loss=2.021, simple_loss=0.2285, pruned_loss=0.02915, codebook_loss=18.77, over 7019.00 frames.], tot_loss[loss=2.017, simple_loss=0.2411, pruned_loss=0.03027, codebook_loss=18.66, over 1303751.09 frames.], batch size: 16, lr: 4.59e-04
+2022-05-27 21:51:02,117 INFO [train.py:823] (1/4) Epoch 37, batch 550, loss[loss=2.023, simple_loss=0.2202, pruned_loss=0.02954, codebook_loss=18.83, over 7002.00 frames.], tot_loss[loss=2.021, simple_loss=0.2415, pruned_loss=0.03058, codebook_loss=18.7, over 1330586.87 frames.], batch size: 16, lr: 4.59e-04
+2022-05-27 21:51:41,638 INFO [train.py:823] (1/4) Epoch 37, batch 600, loss[loss=1.922, simple_loss=0.2361, pruned_loss=0.02381, codebook_loss=17.8, over 7341.00 frames.], tot_loss[loss=2.016, simple_loss=0.2418, pruned_loss=0.03022, codebook_loss=18.65, over 1350554.66 frames.], batch size: 23, lr: 4.59e-04
+2022-05-27 21:52:22,245 INFO [train.py:823] (1/4) Epoch 37, batch 650, loss[loss=1.925, simple_loss=0.1951, pruned_loss=0.02182, codebook_loss=18.06, over 7137.00 frames.], tot_loss[loss=2.011, simple_loss=0.241, pruned_loss=0.02966, codebook_loss=18.61, over 1366073.85 frames.], batch size: 17, lr: 4.58e-04
+2022-05-27 21:53:01,933 INFO [train.py:823] (1/4) Epoch 37, batch 700, loss[loss=1.959, simple_loss=0.253, pruned_loss=0.02114, codebook_loss=18.12, over 7418.00 frames.], tot_loss[loss=2.012, simple_loss=0.241, pruned_loss=0.0294, codebook_loss=18.62, over 1372897.19 frames.], batch size: 22, lr: 4.58e-04
+2022-05-27 21:53:41,851 INFO [train.py:823] (1/4) Epoch 37, batch 750, loss[loss=1.989, simple_loss=0.2455, pruned_loss=0.03536, codebook_loss=18.31, over 5131.00 frames.], tot_loss[loss=2.014, simple_loss=0.2412, pruned_loss=0.02948, codebook_loss=18.64, over 1379841.16 frames.], batch size: 47, lr: 4.58e-04
+2022-05-27 21:54:21,484 INFO [train.py:823] (1/4) Epoch 37, batch 800, loss[loss=1.937, simple_loss=0.2636, pruned_loss=0.02635, codebook_loss=17.79, over 7284.00 frames.], tot_loss[loss=2.011, simple_loss=0.2413, pruned_loss=0.02951, codebook_loss=18.61, over 1384503.47 frames.], batch size: 21, lr: 4.57e-04
+2022-05-27 21:55:01,504 INFO [train.py:823] (1/4) Epoch 37, batch 850, loss[loss=2.054, simple_loss=0.2058, pruned_loss=0.01863, codebook_loss=19.33, over 6800.00 frames.], tot_loss[loss=2.014, simple_loss=0.24, pruned_loss=0.02947, codebook_loss=18.65, over 1386175.43 frames.], batch size: 15, lr: 4.57e-04
+2022-05-27 21:55:41,438 INFO [train.py:823] (1/4) Epoch 37, batch 900, loss[loss=2.037, simple_loss=0.3126, pruned_loss=0.05517, codebook_loss=18.26, over 7148.00 frames.], tot_loss[loss=2.016, simple_loss=0.2393, pruned_loss=0.02959, codebook_loss=18.67, over 1392659.44 frames.], batch size: 23, lr: 4.57e-04
+2022-05-27 21:56:35,793 INFO [train.py:823] (1/4) Epoch 38, batch 0, loss[loss=1.897, simple_loss=0.2259, pruned_loss=0.02373, codebook_loss=17.6, over 7392.00 frames.], tot_loss[loss=1.897, simple_loss=0.2259, pruned_loss=0.02373, codebook_loss=17.6, over 7392.00 frames.], batch size: 19, lr: 4.50e-04
+2022-05-27 21:57:15,587 INFO [train.py:823] (1/4) Epoch 38, batch 50, loss[loss=1.961, simple_loss=0.2424, pruned_loss=0.02842, codebook_loss=18.11, over 7112.00 frames.], tot_loss[loss=1.99, simple_loss=0.2367, pruned_loss=0.02838, codebook_loss=18.44, over 321742.22 frames.], batch size: 19, lr: 4.50e-04
+2022-05-27 21:57:55,720 INFO [train.py:823] (1/4) Epoch 38, batch 100, loss[loss=2.025, simple_loss=0.2639, pruned_loss=0.03725, codebook_loss=18.56, over 7345.00 frames.], tot_loss[loss=2.01, simple_loss=0.2403, pruned_loss=0.02992, codebook_loss=18.59, over 565342.28 frames.], batch size: 23, lr: 4.50e-04
+2022-05-27 21:58:35,473 INFO [train.py:823] (1/4) Epoch 38, batch 150, loss[loss=1.97, simple_loss=0.25, pruned_loss=0.03187, codebook_loss=18.13, over 6998.00 frames.], tot_loss[loss=2.006, simple_loss=0.24, pruned_loss=0.02975, codebook_loss=18.57, over 754084.96 frames.], batch size: 26, lr: 4.50e-04
+2022-05-27 21:59:15,482 INFO [train.py:823] (1/4) Epoch 38, batch 200, loss[loss=2.03, simple_loss=0.2608, pruned_loss=0.03224, codebook_loss=18.67, over 6404.00 frames.], tot_loss[loss=2.007, simple_loss=0.2404, pruned_loss=0.0298, codebook_loss=18.57, over 902332.05 frames.], batch size: 34, lr: 4.49e-04
+2022-05-27 21:59:55,442 INFO [train.py:823] (1/4) Epoch 38, batch 250, loss[loss=1.95, simple_loss=0.2392, pruned_loss=0.02786, codebook_loss=18.03, over 7117.00 frames.], tot_loss[loss=1.997, simple_loss=0.239, pruned_loss=0.02911, codebook_loss=18.49, over 1021306.89 frames.], batch size: 20, lr: 4.49e-04
+2022-05-27 22:00:35,326 INFO [train.py:823] (1/4) Epoch 38, batch 300, loss[loss=1.918, simple_loss=0.2367, pruned_loss=0.02073, codebook_loss=17.79, over 7289.00 frames.], tot_loss[loss=1.997, simple_loss=0.2397, pruned_loss=0.0296, codebook_loss=18.47, over 1107854.88 frames.], batch size: 21, lr: 4.49e-04
+2022-05-27 22:01:15,220 INFO [train.py:823] (1/4) Epoch 38, batch 350, loss[loss=1.965, simple_loss=0.2025, pruned_loss=0.02168, codebook_loss=18.42, over 6794.00 frames.], tot_loss[loss=1.997, simple_loss=0.2395, pruned_loss=0.02931, codebook_loss=18.48, over 1181858.94 frames.], batch size: 15, lr: 4.48e-04
+2022-05-27 22:01:55,562 INFO [train.py:823] (1/4) Epoch 38, batch 400, loss[loss=1.997, simple_loss=0.2386, pruned_loss=0.03441, codebook_loss=18.43, over 4535.00 frames.], tot_loss[loss=1.998, simple_loss=0.2402, pruned_loss=0.02954, codebook_loss=18.48, over 1235800.33 frames.], batch size: 46, lr: 4.48e-04
+2022-05-27 22:02:35,642 INFO [train.py:823] (1/4) Epoch 38, batch 450, loss[loss=2.004, simple_loss=0.2447, pruned_loss=0.03246, codebook_loss=18.49, over 7190.00 frames.], tot_loss[loss=2.007, simple_loss=0.2398, pruned_loss=0.02958, codebook_loss=18.58, over 1280837.89 frames.], batch size: 20, lr: 4.48e-04
+2022-05-27 22:03:16,103 INFO [train.py:823] (1/4) Epoch 38, batch 500, loss[loss=1.905, simple_loss=0.2316, pruned_loss=0.02199, codebook_loss=17.67, over 7280.00 frames.], tot_loss[loss=2.007, simple_loss=0.2389, pruned_loss=0.02954, codebook_loss=18.58, over 1314427.43 frames.], batch size: 21, lr: 4.47e-04
+2022-05-27 22:03:55,602 INFO [train.py:823] (1/4) Epoch 38, batch 550, loss[loss=1.989, simple_loss=0.245, pruned_loss=0.0386, codebook_loss=18.28, over 7194.00 frames.], tot_loss[loss=2.01, simple_loss=0.2392, pruned_loss=0.02956, codebook_loss=18.61, over 1331882.89 frames.], batch size: 20, lr: 4.47e-04
+2022-05-27 22:04:38,500 INFO [train.py:823] (1/4) Epoch 38, batch 600, loss[loss=1.994, simple_loss=0.2691, pruned_loss=0.02784, codebook_loss=18.32, over 6392.00 frames.], tot_loss[loss=2.014, simple_loss=0.2394, pruned_loss=0.02972, codebook_loss=18.65, over 1350493.74 frames.], batch size: 34, lr: 4.47e-04
+2022-05-27 22:05:19,551 INFO [train.py:823] (1/4) Epoch 38, batch 650, loss[loss=1.983, simple_loss=0.2317, pruned_loss=0.03078, codebook_loss=18.36, over 7289.00 frames.], tot_loss[loss=2.006, simple_loss=0.2392, pruned_loss=0.02935, codebook_loss=18.57, over 1367365.43 frames.], batch size: 20, lr: 4.46e-04
+2022-05-27 22:05:59,575 INFO [train.py:823] (1/4) Epoch 38, batch 700, loss[loss=2.032, simple_loss=0.2621, pruned_loss=0.03911, codebook_loss=18.62, over 7170.00 frames.], tot_loss[loss=2.007, simple_loss=0.2399, pruned_loss=0.02954, codebook_loss=18.57, over 1376991.68 frames.], batch size: 22, lr: 4.46e-04
+2022-05-27 22:06:39,248 INFO [train.py:823] (1/4) Epoch 38, batch 750, loss[loss=1.963, simple_loss=0.2655, pruned_loss=0.03052, codebook_loss=18, over 7237.00 frames.], tot_loss[loss=2.006, simple_loss=0.2394, pruned_loss=0.02937, codebook_loss=18.57, over 1383520.65 frames.], batch size: 24, lr: 4.46e-04
+2022-05-27 22:07:19,374 INFO [train.py:823] (1/4) Epoch 38, batch 800, loss[loss=2.043, simple_loss=0.2396, pruned_loss=0.02522, codebook_loss=18.98, over 7376.00 frames.], tot_loss[loss=2.006, simple_loss=0.2393, pruned_loss=0.0293, codebook_loss=18.57, over 1385802.74 frames.], batch size: 21, lr: 4.45e-04
+2022-05-27 22:07:59,082 INFO [train.py:823] (1/4) Epoch 38, batch 850, loss[loss=2.065, simple_loss=0.2645, pruned_loss=0.03294, codebook_loss=19, over 6961.00 frames.], tot_loss[loss=2.004, simple_loss=0.2387, pruned_loss=0.02897, codebook_loss=18.56, over 1395563.56 frames.], batch size: 29, lr: 4.45e-04
+2022-05-27 22:08:39,092 INFO [train.py:823] (1/4) Epoch 38, batch 900, loss[loss=1.969, simple_loss=0.2183, pruned_loss=0.02879, codebook_loss=18.31, over 7012.00 frames.], tot_loss[loss=2.008, simple_loss=0.2387, pruned_loss=0.02896, codebook_loss=18.6, over 1399219.74 frames.], batch size: 16, lr: 4.45e-04
+2022-05-27 22:09:18,324 INFO [train.py:823] (1/4) Epoch 38, batch 950, loss[loss=2.109, simple_loss=0.2633, pruned_loss=0.05135, codebook_loss=19.26, over 4819.00 frames.], tot_loss[loss=2.009, simple_loss=0.2382, pruned_loss=0.02907, codebook_loss=18.61, over 1374990.41 frames.], batch size: 46, lr: 4.45e-04
+2022-05-27 22:09:30,205 INFO [train.py:823] (1/4) Epoch 39, batch 0, loss[loss=1.92, simple_loss=0.2352, pruned_loss=0.02382, codebook_loss=17.79, over 7295.00 frames.], tot_loss[loss=1.92, simple_loss=0.2352, pruned_loss=0.02382, codebook_loss=17.79, over 7295.00 frames.], batch size: 19, lr: 4.39e-04
+2022-05-27 22:10:10,202 INFO [train.py:823] (1/4) Epoch 39, batch 50, loss[loss=2.037, simple_loss=0.2587, pruned_loss=0.03468, codebook_loss=18.73, over 7413.00 frames.], tot_loss[loss=1.995, simple_loss=0.2413, pruned_loss=0.02965, codebook_loss=18.45, over 321654.92 frames.], batch size: 22, lr: 4.39e-04
+2022-05-27 22:10:50,169 INFO [train.py:823] (1/4) Epoch 39, batch 100, loss[loss=1.883, simple_loss=0.2126, pruned_loss=0.0198, codebook_loss=17.57, over 7313.00 frames.], tot_loss[loss=2.003, simple_loss=0.239, pruned_loss=0.02928, codebook_loss=18.55, over 566131.82 frames.], batch size: 18, lr: 4.38e-04
+2022-05-27 22:11:30,533 INFO [train.py:823] (1/4) Epoch 39, batch 150, loss[loss=1.93, simple_loss=0.2507, pruned_loss=0.03227, codebook_loss=17.72, over 7229.00 frames.], tot_loss[loss=1.994, simple_loss=0.237, pruned_loss=0.02833, codebook_loss=18.47, over 754441.14 frames.], batch size: 25, lr: 4.38e-04
+2022-05-27 22:12:10,661 INFO [train.py:823] (1/4) Epoch 39, batch 200, loss[loss=1.966, simple_loss=0.2295, pruned_loss=0.03012, codebook_loss=18.21, over 7379.00 frames.], tot_loss[loss=2.002, simple_loss=0.2366, pruned_loss=0.02861, codebook_loss=18.55, over 906605.73 frames.], batch size: 19, lr: 4.38e-04
+2022-05-27 22:12:50,929 INFO [train.py:823] (1/4) Epoch 39, batch 250, loss[loss=2.14, simple_loss=0.2354, pruned_loss=0.04104, codebook_loss=19.81, over 7292.00 frames.], tot_loss[loss=2.006, simple_loss=0.2372, pruned_loss=0.02871, codebook_loss=18.59, over 1021152.28 frames.], batch size: 19, lr: 4.37e-04
+2022-05-27 22:13:31,059 INFO [train.py:823] (1/4) Epoch 39, batch 300, loss[loss=1.956, simple_loss=0.2286, pruned_loss=0.02984, codebook_loss=18.12, over 7295.00 frames.], tot_loss[loss=2.009, simple_loss=0.2374, pruned_loss=0.02895, codebook_loss=18.62, over 1113537.98 frames.], batch size: 19, lr: 4.37e-04
+2022-05-27 22:14:11,205 INFO [train.py:823] (1/4) Epoch 39, batch 350, loss[loss=1.966, simple_loss=0.234, pruned_loss=0.02297, codebook_loss=18.26, over 7372.00 frames.], tot_loss[loss=2.005, simple_loss=0.2371, pruned_loss=0.02863, codebook_loss=18.58, over 1184671.43 frames.], batch size: 20, lr: 4.37e-04
+2022-05-27 22:14:52,368 INFO [train.py:823] (1/4) Epoch 39, batch 400, loss[loss=2.128, simple_loss=0.214, pruned_loss=0.01954, codebook_loss=20.01, over 7026.00 frames.], tot_loss[loss=2.006, simple_loss=0.2378, pruned_loss=0.02866, codebook_loss=18.58, over 1241404.57 frames.], batch size: 17, lr: 4.36e-04
+2022-05-27 22:15:32,467 INFO [train.py:823] (1/4) Epoch 39, batch 450, loss[loss=2, simple_loss=0.2623, pruned_loss=0.03647, codebook_loss=18.32, over 6977.00 frames.], tot_loss[loss=2.004, simple_loss=0.2379, pruned_loss=0.02832, codebook_loss=18.56, over 1281067.28 frames.], batch size: 26, lr: 4.36e-04
+2022-05-27 22:16:12,043 INFO [train.py:823] (1/4) Epoch 39, batch 500, loss[loss=2.248, simple_loss=0.267, pruned_loss=0.04961, codebook_loss=20.64, over 4449.00 frames.], tot_loss[loss=2.003, simple_loss=0.2378, pruned_loss=0.02853, codebook_loss=18.56, over 1310981.59 frames.], batch size: 47, lr: 4.36e-04
+2022-05-27 22:16:52,093 INFO [train.py:823] (1/4) Epoch 39, batch 550, loss[loss=1.892, simple_loss=0.2387, pruned_loss=0.02397, codebook_loss=17.49, over 7230.00 frames.], tot_loss[loss=2.001, simple_loss=0.2382, pruned_loss=0.02856, codebook_loss=18.54, over 1332236.66 frames.], batch size: 25, lr: 4.36e-04
+2022-05-27 22:17:32,015 INFO [train.py:823] (1/4) Epoch 39, batch 600, loss[loss=1.937, simple_loss=0.2235, pruned_loss=0.02753, codebook_loss=17.97, over 7428.00 frames.], tot_loss[loss=2.001, simple_loss=0.2381, pruned_loss=0.02882, codebook_loss=18.53, over 1355368.38 frames.], batch size: 18, lr: 4.35e-04
+2022-05-27 22:18:12,378 INFO [train.py:823] (1/4) Epoch 39, batch 650, loss[loss=2, simple_loss=0.2327, pruned_loss=0.02481, codebook_loss=18.58, over 7403.00 frames.], tot_loss[loss=2.003, simple_loss=0.2382, pruned_loss=0.0289, codebook_loss=18.55, over 1373969.17 frames.], batch size: 19, lr: 4.35e-04
+2022-05-27 22:18:52,186 INFO [train.py:823] (1/4) Epoch 39, batch 700, loss[loss=2.019, simple_loss=0.2478, pruned_loss=0.03417, codebook_loss=18.61, over 7238.00 frames.], tot_loss[loss=2.007, simple_loss=0.2382, pruned_loss=0.02876, codebook_loss=18.59, over 1384162.71 frames.], batch size: 24, lr: 4.35e-04
+2022-05-27 22:19:32,457 INFO [train.py:823] (1/4) Epoch 39, batch 750, loss[loss=2.04, simple_loss=0.2596, pruned_loss=0.04014, codebook_loss=18.7, over 7384.00 frames.], tot_loss[loss=2.013, simple_loss=0.238, pruned_loss=0.02888, codebook_loss=18.65, over 1390589.14 frames.], batch size: 20, lr: 4.34e-04
+2022-05-27 22:20:12,064 INFO [train.py:823] (1/4) Epoch 39, batch 800, loss[loss=2.031, simple_loss=0.2345, pruned_loss=0.03601, codebook_loss=18.78, over 7197.00 frames.], tot_loss[loss=2.018, simple_loss=0.2389, pruned_loss=0.02894, codebook_loss=18.7, over 1399331.25 frames.], batch size: 18, lr: 4.34e-04
+2022-05-27 22:20:52,207 INFO [train.py:823] (1/4) Epoch 39, batch 850, loss[loss=1.974, simple_loss=0.2645, pruned_loss=0.02782, codebook_loss=18.14, over 7347.00 frames.], tot_loss[loss=2.02, simple_loss=0.239, pruned_loss=0.02908, codebook_loss=18.71, over 1398598.51 frames.], batch size: 23, lr: 4.34e-04
+2022-05-27 22:21:31,559 INFO [train.py:823] (1/4) Epoch 39, batch 900, loss[loss=1.994, simple_loss=0.2457, pruned_loss=0.03009, codebook_loss=18.41, over 6877.00 frames.], tot_loss[loss=2.02, simple_loss=0.24, pruned_loss=0.02977, codebook_loss=18.71, over 1390426.73 frames.], batch size: 29, lr: 4.34e-04
+2022-05-27 22:22:10,947 INFO [train.py:823] (1/4) Epoch 39, batch 950, loss[loss=2.032, simple_loss=0.2575, pruned_loss=0.03987, codebook_loss=18.64, over 4669.00 frames.], tot_loss[loss=2.017, simple_loss=0.2401, pruned_loss=0.02998, codebook_loss=18.67, over 1364677.42 frames.], batch size: 46, lr: 4.33e-04
+2022-05-27 22:22:23,046 INFO [train.py:823] (1/4) Epoch 40, batch 0, loss[loss=2.027, simple_loss=0.2494, pruned_loss=0.02783, codebook_loss=18.75, over 7162.00 frames.], tot_loss[loss=2.027, simple_loss=0.2494, pruned_loss=0.02783, codebook_loss=18.75, over 7162.00 frames.], batch size: 23, lr: 4.28e-04
+2022-05-27 22:23:02,823 INFO [train.py:823] (1/4) Epoch 40, batch 50, loss[loss=1.946, simple_loss=0.2491, pruned_loss=0.02787, codebook_loss=17.93, over 7113.00 frames.], tot_loss[loss=2.021, simple_loss=0.2412, pruned_loss=0.0315, codebook_loss=18.69, over 318055.80 frames.], batch size: 20, lr: 4.28e-04
+2022-05-27 22:23:42,937 INFO [train.py:823] (1/4) Epoch 40, batch 100, loss[loss=2.01, simple_loss=0.2208, pruned_loss=0.02805, codebook_loss=18.72, over 7209.00 frames.], tot_loss[loss=2.008, simple_loss=0.2398, pruned_loss=0.03023, codebook_loss=18.58, over 558982.98 frames.], batch size: 16, lr: 4.27e-04
+2022-05-27 22:24:22,704 INFO [train.py:823] (1/4) Epoch 40, batch 150, loss[loss=2.006, simple_loss=0.2427, pruned_loss=0.03235, codebook_loss=18.52, over 7036.00 frames.], tot_loss[loss=2.011, simple_loss=0.2393, pruned_loss=0.0297, codebook_loss=18.61, over 746554.84 frames.], batch size: 29, lr: 4.27e-04
+2022-05-27 22:25:02,894 INFO [train.py:823] (1/4) Epoch 40, batch 200, loss[loss=1.976, simple_loss=0.2452, pruned_loss=0.02605, codebook_loss=18.27, over 7175.00 frames.], tot_loss[loss=2.01, simple_loss=0.239, pruned_loss=0.02951, codebook_loss=18.61, over 897462.28 frames.], batch size: 21, lr: 4.27e-04
+2022-05-27 22:25:42,825 INFO [train.py:823] (1/4) Epoch 40, batch 250, loss[loss=2.03, simple_loss=0.2121, pruned_loss=0.02598, codebook_loss=18.98, over 6813.00 frames.], tot_loss[loss=1.998, simple_loss=0.2384, pruned_loss=0.02884, codebook_loss=18.5, over 1014289.79 frames.], batch size: 15, lr: 4.26e-04
+2022-05-27 22:26:23,212 INFO [train.py:823] (1/4) Epoch 40, batch 300, loss[loss=1.995, simple_loss=0.229, pruned_loss=0.02429, codebook_loss=18.56, over 7373.00 frames.], tot_loss[loss=1.999, simple_loss=0.2379, pruned_loss=0.02829, codebook_loss=18.52, over 1106052.67 frames.], batch size: 20, lr: 4.26e-04
+2022-05-27 22:27:03,139 INFO [train.py:823] (1/4) Epoch 40, batch 350, loss[loss=1.935, simple_loss=0.2422, pruned_loss=0.02642, codebook_loss=17.88, over 6570.00 frames.], tot_loss[loss=2.004, simple_loss=0.2388, pruned_loss=0.02876, codebook_loss=18.56, over 1178629.17 frames.], batch size: 34, lr: 4.26e-04
+2022-05-27 22:27:43,320 INFO [train.py:823] (1/4) Epoch 40, batch 400, loss[loss=2.225, simple_loss=0.2386, pruned_loss=0.03313, codebook_loss=20.72, over 7017.00 frames.], tot_loss[loss=2.004, simple_loss=0.2389, pruned_loss=0.0288, codebook_loss=18.55, over 1237031.25 frames.], batch size: 16, lr: 4.26e-04
+2022-05-27 22:28:23,128 INFO [train.py:823] (1/4) Epoch 40, batch 450, loss[loss=2.049, simple_loss=0.2256, pruned_loss=0.02502, codebook_loss=19.11, over 6830.00 frames.], tot_loss[loss=2.005, simple_loss=0.2392, pruned_loss=0.02894, codebook_loss=18.56, over 1276407.07 frames.], batch size: 15, lr: 4.25e-04
+2022-05-27 22:29:05,776 INFO [train.py:823] (1/4) Epoch 40, batch 500, loss[loss=1.947, simple_loss=0.2287, pruned_loss=0.01994, codebook_loss=18.13, over 7369.00 frames.], tot_loss[loss=2.007, simple_loss=0.2403, pruned_loss=0.02952, codebook_loss=18.58, over 1308795.41 frames.], batch size: 20, lr: 4.25e-04
+2022-05-27 22:29:47,090 INFO [train.py:823] (1/4) Epoch 40, batch 550, loss[loss=1.898, simple_loss=0.2631, pruned_loss=0.02433, codebook_loss=17.42, over 7299.00 frames.], tot_loss[loss=2.005, simple_loss=0.2393, pruned_loss=0.02928, codebook_loss=18.56, over 1335526.06 frames.], batch size: 22, lr: 4.25e-04
+2022-05-27 22:30:27,070 INFO [train.py:823] (1/4) Epoch 40, batch 600, loss[loss=1.932, simple_loss=0.2423, pruned_loss=0.02488, codebook_loss=17.86, over 7295.00 frames.], tot_loss[loss=2, simple_loss=0.2395, pruned_loss=0.02919, codebook_loss=18.51, over 1355005.50 frames.], batch size: 22, lr: 4.24e-04
+2022-05-27 22:31:06,972 INFO [train.py:823] (1/4) Epoch 40, batch 650, loss[loss=1.932, simple_loss=0.2375, pruned_loss=0.02074, codebook_loss=17.92, over 7202.00 frames.], tot_loss[loss=2.002, simple_loss=0.2398, pruned_loss=0.02923, codebook_loss=18.53, over 1364554.94 frames.], batch size: 19, lr: 4.24e-04
+2022-05-27 22:31:46,869 INFO [train.py:823] (1/4) Epoch 40, batch 700, loss[loss=2.124, simple_loss=0.2387, pruned_loss=0.02222, codebook_loss=19.83, over 7194.00 frames.], tot_loss[loss=2.004, simple_loss=0.241, pruned_loss=0.02929, codebook_loss=18.54, over 1377225.99 frames.], batch size: 20, lr: 4.24e-04
+2022-05-27 22:32:26,846 INFO [train.py:823] (1/4) Epoch 40, batch 750, loss[loss=1.951, simple_loss=0.2329, pruned_loss=0.03039, codebook_loss=18.04, over 4875.00 frames.], tot_loss[loss=2.007, simple_loss=0.2404, pruned_loss=0.02932, codebook_loss=18.58, over 1388358.01 frames.], batch size: 46, lr: 4.24e-04
+2022-05-27 22:33:07,185 INFO [train.py:823] (1/4) Epoch 40, batch 800, loss[loss=1.897, simple_loss=0.2435, pruned_loss=0.02544, codebook_loss=17.5, over 7182.00 frames.], tot_loss[loss=2.01, simple_loss=0.24, pruned_loss=0.0291, codebook_loss=18.6, over 1388057.20 frames.], batch size: 21, lr: 4.23e-04
+2022-05-27 22:33:46,911 INFO [train.py:823] (1/4) Epoch 40, batch 850, loss[loss=1.915, simple_loss=0.242, pruned_loss=0.01662, codebook_loss=17.77, over 7165.00 frames.], tot_loss[loss=2.009, simple_loss=0.2398, pruned_loss=0.02898, codebook_loss=18.6, over 1397074.35 frames.], batch size: 22, lr: 4.23e-04
+2022-05-27 22:34:26,959 INFO [train.py:823] (1/4) Epoch 40, batch 900, loss[loss=2.055, simple_loss=0.2225, pruned_loss=0.02092, codebook_loss=19.23, over 7377.00 frames.], tot_loss[loss=2.006, simple_loss=0.2397, pruned_loss=0.02924, codebook_loss=18.57, over 1390651.78 frames.], batch size: 20, lr: 4.23e-04
+2022-05-27 22:35:20,791 INFO [train.py:823] (1/4) Epoch 41, batch 0, loss[loss=1.862, simple_loss=0.208, pruned_loss=0.01861, codebook_loss=17.4, over 7097.00 frames.], tot_loss[loss=1.862, simple_loss=0.208, pruned_loss=0.01861, codebook_loss=17.4, over 7097.00 frames.], batch size: 19, lr: 4.17e-04
+2022-05-27 22:36:00,864 INFO [train.py:823] (1/4) Epoch 41, batch 50, loss[loss=1.932, simple_loss=0.24, pruned_loss=0.02923, codebook_loss=17.83, over 7376.00 frames.], tot_loss[loss=2.002, simple_loss=0.2371, pruned_loss=0.02743, codebook_loss=18.56, over 322095.46 frames.], batch size: 20, lr: 4.17e-04
+2022-05-27 22:36:40,299 INFO [train.py:823] (1/4) Epoch 41, batch 100, loss[loss=1.883, simple_loss=0.232, pruned_loss=0.02572, codebook_loss=17.41, over 7098.00 frames.], tot_loss[loss=2.002, simple_loss=0.2383, pruned_loss=0.02797, codebook_loss=18.55, over 562108.59 frames.], batch size: 18, lr: 4.17e-04
+2022-05-27 22:37:20,567 INFO [train.py:823] (1/4) Epoch 41, batch 150, loss[loss=1.886, simple_loss=0.2328, pruned_loss=0.01711, codebook_loss=17.52, over 7000.00 frames.], tot_loss[loss=1.991, simple_loss=0.2371, pruned_loss=0.0278, codebook_loss=18.44, over 753817.47 frames.], batch size: 26, lr: 4.17e-04
+2022-05-27 22:38:00,339 INFO [train.py:823] (1/4) Epoch 41, batch 200, loss[loss=2.064, simple_loss=0.2354, pruned_loss=0.02257, codebook_loss=19.23, over 7387.00 frames.], tot_loss[loss=1.994, simple_loss=0.2382, pruned_loss=0.02809, codebook_loss=18.47, over 905283.15 frames.], batch size: 19, lr: 4.16e-04
+2022-05-27 22:38:41,553 INFO [train.py:823] (1/4) Epoch 41, batch 250, loss[loss=2.037, simple_loss=0.2372, pruned_loss=0.02813, codebook_loss=18.9, over 7095.00 frames.], tot_loss[loss=1.995, simple_loss=0.2376, pruned_loss=0.02848, codebook_loss=18.48, over 1015987.10 frames.], batch size: 19, lr: 4.16e-04
+2022-05-27 22:39:21,244 INFO [train.py:823] (1/4) Epoch 41, batch 300, loss[loss=1.891, simple_loss=0.2301, pruned_loss=0.0171, codebook_loss=17.58, over 7370.00 frames.], tot_loss[loss=1.993, simple_loss=0.237, pruned_loss=0.02785, codebook_loss=18.46, over 1106857.09 frames.], batch size: 20, lr: 4.16e-04
+2022-05-27 22:40:01,365 INFO [train.py:823] (1/4) Epoch 41, batch 350, loss[loss=2.053, simple_loss=0.264, pruned_loss=0.03579, codebook_loss=18.85, over 7170.00 frames.], tot_loss[loss=1.993, simple_loss=0.238, pruned_loss=0.02817, codebook_loss=18.46, over 1174558.20 frames.], batch size: 22, lr: 4.15e-04
+2022-05-27 22:40:41,048 INFO [train.py:823] (1/4) Epoch 41, batch 400, loss[loss=1.922, simple_loss=0.2412, pruned_loss=0.02494, codebook_loss=17.77, over 7137.00 frames.], tot_loss[loss=1.999, simple_loss=0.2386, pruned_loss=0.02871, codebook_loss=18.51, over 1221431.42 frames.], batch size: 23, lr: 4.15e-04
+2022-05-27 22:41:21,066 INFO [train.py:823] (1/4) Epoch 41, batch 450, loss[loss=2.079, simple_loss=0.2294, pruned_loss=0.03957, codebook_loss=19.24, over 7092.00 frames.], tot_loss[loss=2.005, simple_loss=0.2383, pruned_loss=0.02871, codebook_loss=18.57, over 1263073.01 frames.], batch size: 18, lr: 4.15e-04
+2022-05-27 22:42:00,719 INFO [train.py:823] (1/4) Epoch 41, batch 500, loss[loss=2.006, simple_loss=0.2497, pruned_loss=0.03755, codebook_loss=18.43, over 7299.00 frames.], tot_loss[loss=2.006, simple_loss=0.2392, pruned_loss=0.02909, codebook_loss=18.57, over 1298689.82 frames.], batch size: 22, lr: 4.15e-04
+2022-05-27 22:42:40,903 INFO [train.py:823] (1/4) Epoch 41, batch 550, loss[loss=1.904, simple_loss=0.2529, pruned_loss=0.02768, codebook_loss=17.5, over 7200.00 frames.], tot_loss[loss=2.001, simple_loss=0.2382, pruned_loss=0.02862, codebook_loss=18.54, over 1322079.19 frames.], batch size: 19, lr: 4.14e-04
+2022-05-27 22:43:20,795 INFO [train.py:823] (1/4) Epoch 41, batch 600, loss[loss=1.976, simple_loss=0.2672, pruned_loss=0.0367, codebook_loss=18.05, over 7177.00 frames.], tot_loss[loss=1.999, simple_loss=0.238, pruned_loss=0.02851, codebook_loss=18.52, over 1338804.37 frames.], batch size: 21, lr: 4.14e-04
+2022-05-27 22:44:00,846 INFO [train.py:823] (1/4) Epoch 41, batch 650, loss[loss=2.011, simple_loss=0.2479, pruned_loss=0.02654, codebook_loss=18.61, over 7179.00 frames.], tot_loss[loss=1.997, simple_loss=0.2375, pruned_loss=0.02801, codebook_loss=18.5, over 1357906.20 frames.], batch size: 21, lr: 4.14e-04
+2022-05-27 22:44:40,512 INFO [train.py:823] (1/4) Epoch 41, batch 700, loss[loss=1.974, simple_loss=0.2187, pruned_loss=0.02286, codebook_loss=18.41, over 7244.00 frames.], tot_loss[loss=1.993, simple_loss=0.2373, pruned_loss=0.02813, codebook_loss=18.47, over 1371326.07 frames.], batch size: 16, lr: 4.14e-04
+2022-05-27 22:45:20,395 INFO [train.py:823] (1/4) Epoch 41, batch 750, loss[loss=1.922, simple_loss=0.2217, pruned_loss=0.02433, codebook_loss=17.87, over 7187.00 frames.], tot_loss[loss=1.993, simple_loss=0.2374, pruned_loss=0.02811, codebook_loss=18.46, over 1380159.51 frames.], batch size: 18, lr: 4.13e-04
+2022-05-27 22:45:59,898 INFO [train.py:823] (1/4) Epoch 41, batch 800, loss[loss=1.943, simple_loss=0.2051, pruned_loss=0.02269, codebook_loss=18.18, over 7299.00 frames.], tot_loss[loss=1.995, simple_loss=0.2378, pruned_loss=0.02854, codebook_loss=18.47, over 1383144.82 frames.], batch size: 17, lr: 4.13e-04
+2022-05-27 22:46:40,265 INFO [train.py:823] (1/4) Epoch 41, batch 850, loss[loss=1.966, simple_loss=0.225, pruned_loss=0.02549, codebook_loss=18.28, over 7305.00 frames.], tot_loss[loss=1.994, simple_loss=0.2385, pruned_loss=0.02859, codebook_loss=18.46, over 1395528.34 frames.], batch size: 19, lr: 4.13e-04
+2022-05-27 22:47:20,138 INFO [train.py:823] (1/4) Epoch 41, batch 900, loss[loss=1.934, simple_loss=0.2089, pruned_loss=0.02059, codebook_loss=18.09, over 7306.00 frames.], tot_loss[loss=1.998, simple_loss=0.2382, pruned_loss=0.02873, codebook_loss=18.5, over 1400822.57 frames.], batch size: 17, lr: 4.13e-04
+2022-05-27 22:48:13,583 INFO [train.py:823] (1/4) Epoch 42, batch 0, loss[loss=1.997, simple_loss=0.2481, pruned_loss=0.02074, codebook_loss=18.52, over 7288.00 frames.], tot_loss[loss=1.997, simple_loss=0.2481, pruned_loss=0.02074, codebook_loss=18.52, over 7288.00 frames.], batch size: 21, lr: 4.07e-04
+2022-05-27 22:48:53,518 INFO [train.py:823] (1/4) Epoch 42, batch 50, loss[loss=2.12, simple_loss=0.2285, pruned_loss=0.02988, codebook_loss=19.76, over 7388.00 frames.], tot_loss[loss=1.986, simple_loss=0.2334, pruned_loss=0.02755, codebook_loss=18.42, over 323520.26 frames.], batch size: 19, lr: 4.07e-04
+2022-05-27 22:49:33,742 INFO [train.py:823] (1/4) Epoch 42, batch 100, loss[loss=1.982, simple_loss=0.2117, pruned_loss=0.02847, codebook_loss=18.47, over 7233.00 frames.], tot_loss[loss=1.978, simple_loss=0.2348, pruned_loss=0.02762, codebook_loss=18.33, over 566332.69 frames.], batch size: 16, lr: 4.07e-04
+2022-05-27 22:50:13,506 INFO [train.py:823] (1/4) Epoch 42, batch 150, loss[loss=2.067, simple_loss=0.2367, pruned_loss=0.02297, codebook_loss=19.26, over 7178.00 frames.], tot_loss[loss=1.976, simple_loss=0.2351, pruned_loss=0.02761, codebook_loss=18.31, over 755653.59 frames.], batch size: 22, lr: 4.07e-04
+2022-05-27 22:50:53,443 INFO [train.py:823] (1/4) Epoch 42, batch 200, loss[loss=1.944, simple_loss=0.2427, pruned_loss=0.0267, codebook_loss=17.96, over 7240.00 frames.], tot_loss[loss=1.987, simple_loss=0.2368, pruned_loss=0.02828, codebook_loss=18.4, over 901443.67 frames.], batch size: 24, lr: 4.06e-04
+2022-05-27 22:51:33,128 INFO [train.py:823] (1/4) Epoch 42, batch 250, loss[loss=2.136, simple_loss=0.2174, pruned_loss=0.02512, codebook_loss=20.02, over 7147.00 frames.], tot_loss[loss=1.999, simple_loss=0.2378, pruned_loss=0.02883, codebook_loss=18.51, over 1016831.45 frames.], batch size: 17, lr: 4.06e-04
+2022-05-27 22:52:13,180 INFO [train.py:823] (1/4) Epoch 42, batch 300, loss[loss=1.962, simple_loss=0.2372, pruned_loss=0.03263, codebook_loss=18.1, over 7187.00 frames.], tot_loss[loss=2.003, simple_loss=0.2376, pruned_loss=0.02878, codebook_loss=18.56, over 1101675.03 frames.], batch size: 21, lr: 4.06e-04
+2022-05-27 22:52:52,888 INFO [train.py:823] (1/4) Epoch 42, batch 350, loss[loss=2.088, simple_loss=0.2306, pruned_loss=0.03924, codebook_loss=19.34, over 7155.00 frames.], tot_loss[loss=1.999, simple_loss=0.2371, pruned_loss=0.02849, codebook_loss=18.52, over 1168395.34 frames.], batch size: 17, lr: 4.06e-04
+2022-05-27 22:53:35,689 INFO [train.py:823] (1/4) Epoch 42, batch 400, loss[loss=1.956, simple_loss=0.2133, pruned_loss=0.02124, codebook_loss=18.28, over 7300.00 frames.], tot_loss[loss=2.005, simple_loss=0.2374, pruned_loss=0.02842, codebook_loss=18.58, over 1219245.03 frames.], batch size: 17, lr: 4.05e-04
+2022-05-27 22:54:16,813 INFO [train.py:823] (1/4) Epoch 42, batch 450, loss[loss=2.044, simple_loss=0.2666, pruned_loss=0.03382, codebook_loss=18.77, over 7217.00 frames.], tot_loss[loss=2, simple_loss=0.2386, pruned_loss=0.0285, codebook_loss=18.53, over 1268708.68 frames.], batch size: 25, lr: 4.05e-04
+2022-05-27 22:54:57,133 INFO [train.py:823] (1/4) Epoch 42, batch 500, loss[loss=2.057, simple_loss=0.2135, pruned_loss=0.025, codebook_loss=19.25, over 7139.00 frames.], tot_loss[loss=1.997, simple_loss=0.2372, pruned_loss=0.02819, codebook_loss=18.5, over 1303120.88 frames.], batch size: 17, lr: 4.05e-04
+2022-05-27 22:55:36,606 INFO [train.py:823] (1/4) Epoch 42, batch 550, loss[loss=2.014, simple_loss=0.2181, pruned_loss=0.01927, codebook_loss=18.86, over 7183.00 frames.], tot_loss[loss=1.997, simple_loss=0.2373, pruned_loss=0.02822, codebook_loss=18.5, over 1322749.41 frames.], batch size: 18, lr: 4.05e-04
+2022-05-27 22:56:16,721 INFO [train.py:823] (1/4) Epoch 42, batch 600, loss[loss=1.915, simple_loss=0.2284, pruned_loss=0.023, codebook_loss=17.78, over 7193.00 frames.], tot_loss[loss=1.999, simple_loss=0.238, pruned_loss=0.02817, codebook_loss=18.52, over 1344233.91 frames.], batch size: 20, lr: 4.04e-04
+2022-05-27 22:56:56,700 INFO [train.py:823] (1/4) Epoch 42, batch 650, loss[loss=2.064, simple_loss=0.2509, pruned_loss=0.04115, codebook_loss=18.98, over 7137.00 frames.], tot_loss[loss=1.996, simple_loss=0.2386, pruned_loss=0.02841, codebook_loss=18.49, over 1364836.35 frames.], batch size: 23, lr: 4.04e-04
+2022-05-27 22:57:36,490 INFO [train.py:823] (1/4) Epoch 42, batch 700, loss[loss=1.922, simple_loss=0.2548, pruned_loss=0.02499, codebook_loss=17.69, over 6887.00 frames.], tot_loss[loss=1.997, simple_loss=0.2395, pruned_loss=0.02897, codebook_loss=18.48, over 1371644.82 frames.], batch size: 29, lr: 4.04e-04
+2022-05-27 22:58:16,374 INFO [train.py:823] (1/4) Epoch 42, batch 750, loss[loss=2.081, simple_loss=0.2583, pruned_loss=0.0306, codebook_loss=19.21, over 7382.00 frames.], tot_loss[loss=1.998, simple_loss=0.2389, pruned_loss=0.02874, codebook_loss=18.5, over 1385723.78 frames.], batch size: 21, lr: 4.04e-04
+2022-05-27 22:58:56,344 INFO [train.py:823] (1/4) Epoch 42, batch 800, loss[loss=2.204, simple_loss=0.2587, pruned_loss=0.03139, codebook_loss=20.43, over 6569.00 frames.], tot_loss[loss=1.999, simple_loss=0.2386, pruned_loss=0.02857, codebook_loss=18.51, over 1393700.88 frames.], batch size: 34, lr: 4.03e-04
+2022-05-27 22:59:36,088 INFO [train.py:823] (1/4) Epoch 42, batch 850, loss[loss=2.007, simple_loss=0.2211, pruned_loss=0.02902, codebook_loss=18.67, over 7013.00 frames.], tot_loss[loss=1.994, simple_loss=0.2377, pruned_loss=0.02823, codebook_loss=18.47, over 1400046.59 frames.], batch size: 17, lr: 4.03e-04
+2022-05-27 23:00:15,920 INFO [train.py:823] (1/4) Epoch 42, batch 900, loss[loss=2.062, simple_loss=0.2619, pruned_loss=0.04347, codebook_loss=18.88, over 5349.00 frames.], tot_loss[loss=1.991, simple_loss=0.2372, pruned_loss=0.02819, codebook_loss=18.44, over 1398975.44 frames.], batch size: 46, lr: 4.03e-04
+2022-05-27 23:01:10,027 INFO [train.py:823] (1/4) Epoch 43, batch 0, loss[loss=1.932, simple_loss=0.2244, pruned_loss=0.0214, codebook_loss=17.98, over 7289.00 frames.], tot_loss[loss=1.932, simple_loss=0.2244, pruned_loss=0.0214, codebook_loss=17.98, over 7289.00 frames.], batch size: 19, lr: 3.98e-04
+2022-05-27 23:01:50,276 INFO [train.py:823] (1/4) Epoch 43, batch 50, loss[loss=1.927, simple_loss=0.2288, pruned_loss=0.02445, codebook_loss=17.89, over 7372.00 frames.], tot_loss[loss=1.979, simple_loss=0.239, pruned_loss=0.02923, codebook_loss=18.31, over 322642.04 frames.], batch size: 20, lr: 3.98e-04
+2022-05-27 23:02:31,475 INFO [train.py:823] (1/4) Epoch 43, batch 100, loss[loss=2.138, simple_loss=0.24, pruned_loss=0.03286, codebook_loss=19.85, over 7150.00 frames.], tot_loss[loss=1.982, simple_loss=0.236, pruned_loss=0.0279, codebook_loss=18.36, over 566809.77 frames.], batch size: 23, lr: 3.97e-04
+2022-05-27 23:03:15,179 INFO [train.py:823] (1/4) Epoch 43, batch 150, loss[loss=2.049, simple_loss=0.2233, pruned_loss=0.02778, codebook_loss=19.09, over 6547.00 frames.], tot_loss[loss=2.006, simple_loss=0.2385, pruned_loss=0.02941, codebook_loss=18.57, over 755954.79 frames.], batch size: 35, lr: 3.97e-04
+2022-05-27 23:03:55,330 INFO [train.py:823] (1/4) Epoch 43, batch 200, loss[loss=2.269, simple_loss=0.2777, pruned_loss=0.04857, codebook_loss=20.81, over 7340.00 frames.], tot_loss[loss=1.995, simple_loss=0.2386, pruned_loss=0.02907, codebook_loss=18.47, over 907141.05 frames.], batch size: 23, lr: 3.97e-04
+2022-05-27 23:04:35,699 INFO [train.py:823] (1/4) Epoch 43, batch 250, loss[loss=2.135, simple_loss=0.2442, pruned_loss=0.03293, codebook_loss=19.8, over 7308.00 frames.], tot_loss[loss=1.992, simple_loss=0.2385, pruned_loss=0.02865, codebook_loss=18.44, over 1022927.14 frames.], batch size: 18, lr: 3.97e-04
+2022-05-27 23:05:15,235 INFO [train.py:823] (1/4) Epoch 43, batch 300, loss[loss=1.92, simple_loss=0.2427, pruned_loss=0.03022, codebook_loss=17.69, over 7104.00 frames.], tot_loss[loss=1.985, simple_loss=0.2372, pruned_loss=0.02802, codebook_loss=18.38, over 1102784.68 frames.], batch size: 18, lr: 3.96e-04
+2022-05-27 23:05:55,398 INFO [train.py:823] (1/4) Epoch 43, batch 350, loss[loss=2.361, simple_loss=0.2711, pruned_loss=0.06298, codebook_loss=21.63, over 7346.00 frames.], tot_loss[loss=1.994, simple_loss=0.2385, pruned_loss=0.02881, codebook_loss=18.46, over 1174949.81 frames.], batch size: 23, lr: 3.96e-04
+2022-05-27 23:06:35,430 INFO [train.py:823] (1/4) Epoch 43, batch 400, loss[loss=1.971, simple_loss=0.2446, pruned_loss=0.03254, codebook_loss=18.16, over 7193.00 frames.], tot_loss[loss=1.992, simple_loss=0.2374, pruned_loss=0.02831, codebook_loss=18.45, over 1229584.23 frames.], batch size: 20, lr: 3.96e-04
+2022-05-27 23:07:15,799 INFO [train.py:823] (1/4) Epoch 43, batch 450, loss[loss=1.901, simple_loss=0.2357, pruned_loss=0.01626, codebook_loss=17.67, over 7184.00 frames.], tot_loss[loss=1.995, simple_loss=0.238, pruned_loss=0.02836, codebook_loss=18.48, over 1276097.72 frames.], batch size: 21, lr: 3.96e-04
+2022-05-27 23:07:55,851 INFO [train.py:823] (1/4) Epoch 43, batch 500, loss[loss=2.028, simple_loss=0.2006, pruned_loss=0.01698, codebook_loss=19.11, over 7419.00 frames.], tot_loss[loss=2.001, simple_loss=0.2386, pruned_loss=0.029, codebook_loss=18.52, over 1307449.12 frames.], batch size: 18, lr: 3.95e-04
+2022-05-27 23:08:36,106 INFO [train.py:823] (1/4) Epoch 43, batch 550, loss[loss=1.897, simple_loss=0.2563, pruned_loss=0.02794, codebook_loss=17.41, over 7275.00 frames.], tot_loss[loss=1.996, simple_loss=0.2391, pruned_loss=0.02895, codebook_loss=18.48, over 1337319.64 frames.], batch size: 21, lr: 3.95e-04
+2022-05-27 23:09:15,808 INFO [train.py:823] (1/4) Epoch 43, batch 600, loss[loss=2.171, simple_loss=0.2575, pruned_loss=0.0387, codebook_loss=20.04, over 7165.00 frames.], tot_loss[loss=1.995, simple_loss=0.2385, pruned_loss=0.02834, codebook_loss=18.47, over 1356896.61 frames.], batch size: 22, lr: 3.95e-04
+2022-05-27 23:09:55,882 INFO [train.py:823] (1/4) Epoch 43, batch 650, loss[loss=1.94, simple_loss=0.2435, pruned_loss=0.03033, codebook_loss=17.88, over 7196.00 frames.], tot_loss[loss=1.993, simple_loss=0.2376, pruned_loss=0.028, codebook_loss=18.46, over 1374131.81 frames.], batch size: 20, lr: 3.95e-04
+2022-05-27 23:10:35,793 INFO [train.py:823] (1/4) Epoch 43, batch 700, loss[loss=1.988, simple_loss=0.2157, pruned_loss=0.02436, codebook_loss=18.56, over 7445.00 frames.], tot_loss[loss=1.997, simple_loss=0.2376, pruned_loss=0.02794, codebook_loss=18.5, over 1384505.59 frames.], batch size: 18, lr: 3.94e-04
+2022-05-27 23:11:16,030 INFO [train.py:823] (1/4) Epoch 43, batch 750, loss[loss=2.08, simple_loss=0.2401, pruned_loss=0.02529, codebook_loss=19.35, over 7184.00 frames.], tot_loss[loss=1.997, simple_loss=0.2372, pruned_loss=0.02799, codebook_loss=18.51, over 1394756.17 frames.], batch size: 21, lr: 3.94e-04
+2022-05-27 23:11:55,937 INFO [train.py:823] (1/4) Epoch 43, batch 800, loss[loss=1.857, simple_loss=0.2341, pruned_loss=0.01934, codebook_loss=17.21, over 7310.00 frames.], tot_loss[loss=1.996, simple_loss=0.2368, pruned_loss=0.02785, codebook_loss=18.5, over 1403720.47 frames.], batch size: 22, lr: 3.94e-04
+2022-05-27 23:12:36,064 INFO [train.py:823] (1/4) Epoch 43, batch 850, loss[loss=1.913, simple_loss=0.2397, pruned_loss=0.02245, codebook_loss=17.7, over 7169.00 frames.], tot_loss[loss=1.993, simple_loss=0.2364, pruned_loss=0.02737, codebook_loss=18.47, over 1405758.55 frames.], batch size: 22, lr: 3.94e-04
+2022-05-27 23:13:16,026 INFO [train.py:823] (1/4) Epoch 43, batch 900, loss[loss=1.931, simple_loss=0.2233, pruned_loss=0.02963, codebook_loss=17.9, over 7239.00 frames.], tot_loss[loss=1.992, simple_loss=0.2361, pruned_loss=0.02765, codebook_loss=18.47, over 1403241.52 frames.], batch size: 16, lr: 3.93e-04
+2022-05-27 23:14:05,789 INFO [train.py:823] (1/4) Epoch 44, batch 0, loss[loss=1.926, simple_loss=0.257, pruned_loss=0.02631, codebook_loss=17.72, over 7312.00 frames.], tot_loss[loss=1.926, simple_loss=0.257, pruned_loss=0.02631, codebook_loss=17.72, over 7312.00 frames.], batch size: 22, lr: 3.89e-04
+2022-05-27 23:14:46,502 INFO [train.py:823] (1/4) Epoch 44, batch 50, loss[loss=1.956, simple_loss=0.2295, pruned_loss=0.02732, codebook_loss=18.13, over 7017.00 frames.], tot_loss[loss=1.976, simple_loss=0.232, pruned_loss=0.02626, codebook_loss=18.34, over 321668.43 frames.], batch size: 17, lr: 3.89e-04
+2022-05-27 23:15:26,625 INFO [train.py:823] (1/4) Epoch 44, batch 100, loss[loss=2.107, simple_loss=0.2414, pruned_loss=0.03745, codebook_loss=19.48, over 7278.00 frames.], tot_loss[loss=1.969, simple_loss=0.2339, pruned_loss=0.02681, codebook_loss=18.25, over 566331.57 frames.], batch size: 20, lr: 3.88e-04
+2022-05-27 23:16:06,703 INFO [train.py:823] (1/4) Epoch 44, batch 150, loss[loss=1.987, simple_loss=0.2357, pruned_loss=0.02796, codebook_loss=18.42, over 7283.00 frames.], tot_loss[loss=1.974, simple_loss=0.2364, pruned_loss=0.02788, codebook_loss=18.28, over 757642.89 frames.], batch size: 20, lr: 3.88e-04
+2022-05-27 23:16:46,974 INFO [train.py:823] (1/4) Epoch 44, batch 200, loss[loss=1.981, simple_loss=0.2543, pruned_loss=0.03518, codebook_loss=18.18, over 7235.00 frames.], tot_loss[loss=1.969, simple_loss=0.2359, pruned_loss=0.0277, codebook_loss=18.23, over 903171.91 frames.], batch size: 24, lr: 3.88e-04
+2022-05-27 23:17:26,787 INFO [train.py:823] (1/4) Epoch 44, batch 250, loss[loss=1.946, simple_loss=0.2242, pruned_loss=0.02423, codebook_loss=18.1, over 7164.00 frames.], tot_loss[loss=1.974, simple_loss=0.2359, pruned_loss=0.02744, codebook_loss=18.28, over 1019795.76 frames.], batch size: 23, lr: 3.88e-04
+2022-05-27 23:18:08,123 INFO [train.py:823] (1/4) Epoch 44, batch 300, loss[loss=1.954, simple_loss=0.2502, pruned_loss=0.02812, codebook_loss=18.01, over 7275.00 frames.], tot_loss[loss=1.978, simple_loss=0.2362, pruned_loss=0.02757, codebook_loss=18.32, over 1107182.02 frames.], batch size: 21, lr: 3.87e-04
+2022-05-27 23:18:50,347 INFO [train.py:823] (1/4) Epoch 44, batch 350, loss[loss=2.115, simple_loss=0.2074, pruned_loss=0.02446, codebook_loss=19.87, over 7010.00 frames.], tot_loss[loss=1.983, simple_loss=0.2369, pruned_loss=0.02768, codebook_loss=18.37, over 1171211.46 frames.], batch size: 16, lr: 3.87e-04
+2022-05-27 23:19:30,578 INFO [train.py:823] (1/4) Epoch 44, batch 400, loss[loss=1.95, simple_loss=0.2225, pruned_loss=0.02316, codebook_loss=18.16, over 5042.00 frames.], tot_loss[loss=1.985, simple_loss=0.2365, pruned_loss=0.02777, codebook_loss=18.39, over 1222496.53 frames.], batch size: 47, lr: 3.87e-04
+2022-05-27 23:20:10,456 INFO [train.py:823] (1/4) Epoch 44, batch 450, loss[loss=1.957, simple_loss=0.2406, pruned_loss=0.02936, codebook_loss=18.08, over 7241.00 frames.], tot_loss[loss=1.984, simple_loss=0.2365, pruned_loss=0.02775, codebook_loss=18.38, over 1265652.20 frames.], batch size: 25, lr: 3.87e-04
+2022-05-27 23:20:50,569 INFO [train.py:823] (1/4) Epoch 44, batch 500, loss[loss=1.934, simple_loss=0.2468, pruned_loss=0.03095, codebook_loss=17.8, over 7147.00 frames.], tot_loss[loss=1.985, simple_loss=0.2363, pruned_loss=0.02788, codebook_loss=18.39, over 1302801.85 frames.], batch size: 17, lr: 3.86e-04
+2022-05-27 23:21:30,264 INFO [train.py:823] (1/4) Epoch 44, batch 550, loss[loss=2.156, simple_loss=0.2401, pruned_loss=0.03373, codebook_loss=20.02, over 7232.00 frames.], tot_loss[loss=1.983, simple_loss=0.2364, pruned_loss=0.02752, codebook_loss=18.37, over 1331330.62 frames.], batch size: 24, lr: 3.86e-04
+2022-05-27 23:22:10,616 INFO [train.py:823] (1/4) Epoch 44, batch 600, loss[loss=1.909, simple_loss=0.2238, pruned_loss=0.02556, codebook_loss=17.71, over 7399.00 frames.], tot_loss[loss=1.982, simple_loss=0.2364, pruned_loss=0.02731, codebook_loss=18.36, over 1353982.98 frames.], batch size: 19, lr: 3.86e-04
+2022-05-27 23:22:50,473 INFO [train.py:823] (1/4) Epoch 44, batch 650, loss[loss=1.86, simple_loss=0.2278, pruned_loss=0.01578, codebook_loss=17.3, over 7428.00 frames.], tot_loss[loss=1.988, simple_loss=0.237, pruned_loss=0.02735, codebook_loss=18.42, over 1367465.91 frames.], batch size: 22, lr: 3.86e-04
+2022-05-27 23:23:30,765 INFO [train.py:823] (1/4) Epoch 44, batch 700, loss[loss=1.959, simple_loss=0.2539, pruned_loss=0.02855, codebook_loss=18.04, over 7126.00 frames.], tot_loss[loss=1.988, simple_loss=0.2367, pruned_loss=0.02742, codebook_loss=18.43, over 1379333.11 frames.], batch size: 23, lr: 3.85e-04
+2022-05-27 23:24:10,490 INFO [train.py:823] (1/4) Epoch 44, batch 750, loss[loss=2.225, simple_loss=0.2429, pruned_loss=0.03919, codebook_loss=20.64, over 7164.00 frames.], tot_loss[loss=1.991, simple_loss=0.2374, pruned_loss=0.02794, codebook_loss=18.45, over 1390848.61 frames.], batch size: 17, lr: 3.85e-04
+2022-05-27 23:24:50,894 INFO [train.py:823] (1/4) Epoch 44, batch 800, loss[loss=2.192, simple_loss=0.2594, pruned_loss=0.02529, codebook_loss=20.37, over 7212.00 frames.], tot_loss[loss=1.994, simple_loss=0.2387, pruned_loss=0.02849, codebook_loss=18.46, over 1397368.48 frames.], batch size: 25, lr: 3.85e-04
+2022-05-27 23:25:30,967 INFO [train.py:823] (1/4) Epoch 44, batch 850, loss[loss=2.018, simple_loss=0.2179, pruned_loss=0.0357, codebook_loss=18.73, over 7233.00 frames.], tot_loss[loss=1.993, simple_loss=0.2382, pruned_loss=0.02851, codebook_loss=18.46, over 1403682.08 frames.], batch size: 16, lr: 3.85e-04
+2022-05-27 23:26:12,391 INFO [train.py:823] (1/4) Epoch 44, batch 900, loss[loss=2.047, simple_loss=0.2066, pruned_loss=0.01937, codebook_loss=19.24, over 7279.00 frames.], tot_loss[loss=1.997, simple_loss=0.2386, pruned_loss=0.02865, codebook_loss=18.49, over 1401357.96 frames.], batch size: 17, lr: 3.85e-04
+2022-05-27 23:26:52,105 INFO [train.py:823] (1/4) Epoch 44, batch 950, loss[loss=1.998, simple_loss=0.2507, pruned_loss=0.04234, codebook_loss=18.3, over 4885.00 frames.], tot_loss[loss=1.998, simple_loss=0.2381, pruned_loss=0.02886, codebook_loss=18.5, over 1378094.23 frames.], batch size: 47, lr: 3.84e-04
+2022-05-27 23:27:07,451 INFO [train.py:823] (1/4) Epoch 45, batch 0, loss[loss=1.875, simple_loss=0.2274, pruned_loss=0.02272, codebook_loss=17.39, over 7285.00 frames.], tot_loss[loss=1.875, simple_loss=0.2274, pruned_loss=0.02272, codebook_loss=17.39, over 7285.00 frames.], batch size: 20, lr: 3.80e-04
+2022-05-27 23:27:47,728 INFO [train.py:823] (1/4) Epoch 45, batch 50, loss[loss=1.903, simple_loss=0.2434, pruned_loss=0.02266, codebook_loss=17.59, over 7286.00 frames.], tot_loss[loss=1.997, simple_loss=0.234, pruned_loss=0.02753, codebook_loss=18.52, over 323982.53 frames.], batch size: 21, lr: 3.80e-04
+2022-05-27 23:28:27,600 INFO [train.py:823] (1/4) Epoch 45, batch 100, loss[loss=1.913, simple_loss=0.2656, pruned_loss=0.0292, codebook_loss=17.51, over 7377.00 frames.], tot_loss[loss=1.973, simple_loss=0.2348, pruned_loss=0.02717, codebook_loss=18.29, over 567486.50 frames.], batch size: 21, lr: 3.80e-04
+2022-05-27 23:29:07,786 INFO [train.py:823] (1/4) Epoch 45, batch 150, loss[loss=2.033, simple_loss=0.223, pruned_loss=0.03518, codebook_loss=18.86, over 7235.00 frames.], tot_loss[loss=1.975, simple_loss=0.2361, pruned_loss=0.02783, codebook_loss=18.29, over 752825.57 frames.], batch size: 16, lr: 3.79e-04
+2022-05-27 23:29:47,591 INFO [train.py:823] (1/4) Epoch 45, batch 200, loss[loss=2.098, simple_loss=0.2507, pruned_loss=0.04063, codebook_loss=19.32, over 4973.00 frames.], tot_loss[loss=1.985, simple_loss=0.2362, pruned_loss=0.02772, codebook_loss=18.4, over 896746.72 frames.], batch size: 46, lr: 3.79e-04
+2022-05-27 23:30:27,676 INFO [train.py:823] (1/4) Epoch 45, batch 250, loss[loss=1.931, simple_loss=0.238, pruned_loss=0.02191, codebook_loss=17.9, over 6625.00 frames.], tot_loss[loss=1.985, simple_loss=0.2365, pruned_loss=0.02759, codebook_loss=18.39, over 1010643.81 frames.], batch size: 34, lr: 3.79e-04
+2022-05-27 23:31:07,619 INFO [train.py:823] (1/4) Epoch 45, batch 300, loss[loss=1.976, simple_loss=0.262, pruned_loss=0.02735, codebook_loss=18.18, over 7161.00 frames.], tot_loss[loss=1.979, simple_loss=0.2351, pruned_loss=0.02688, codebook_loss=18.34, over 1100293.54 frames.], batch size: 23, lr: 3.79e-04
+2022-05-27 23:31:47,898 INFO [train.py:823] (1/4) Epoch 45, batch 350, loss[loss=2.06, simple_loss=0.2522, pruned_loss=0.03701, codebook_loss=18.97, over 7418.00 frames.], tot_loss[loss=1.979, simple_loss=0.2357, pruned_loss=0.0272, codebook_loss=18.34, over 1173146.05 frames.], batch size: 22, lr: 3.78e-04
+2022-05-27 23:32:27,584 INFO [train.py:823] (1/4) Epoch 45, batch 400, loss[loss=1.996, simple_loss=0.2415, pruned_loss=0.03573, codebook_loss=18.4, over 7380.00 frames.], tot_loss[loss=1.982, simple_loss=0.2358, pruned_loss=0.02755, codebook_loss=18.37, over 1229890.76 frames.], batch size: 20, lr: 3.78e-04
+2022-05-27 23:33:07,581 INFO [train.py:823] (1/4) Epoch 45, batch 450, loss[loss=1.961, simple_loss=0.2235, pruned_loss=0.03569, codebook_loss=18.14, over 7186.00 frames.], tot_loss[loss=1.98, simple_loss=0.2365, pruned_loss=0.02785, codebook_loss=18.34, over 1270116.04 frames.], batch size: 18, lr: 3.78e-04
+2022-05-27 23:33:47,507 INFO [train.py:823] (1/4) Epoch 45, batch 500, loss[loss=1.995, simple_loss=0.2714, pruned_loss=0.046, codebook_loss=18.13, over 7199.00 frames.], tot_loss[loss=1.986, simple_loss=0.237, pruned_loss=0.02837, codebook_loss=18.39, over 1309238.86 frames.], batch size: 24, lr: 3.78e-04
+2022-05-27 23:34:27,803 INFO [train.py:823] (1/4) Epoch 45, batch 550, loss[loss=1.889, simple_loss=0.2156, pruned_loss=0.02299, codebook_loss=17.58, over 7200.00 frames.], tot_loss[loss=1.985, simple_loss=0.2358, pruned_loss=0.02771, codebook_loss=18.39, over 1335073.26 frames.], batch size: 18, lr: 3.78e-04
+2022-05-27 23:35:07,239 INFO [train.py:823] (1/4) Epoch 45, batch 600, loss[loss=1.939, simple_loss=0.2349, pruned_loss=0.02134, codebook_loss=18.01, over 6600.00 frames.], tot_loss[loss=1.977, simple_loss=0.2354, pruned_loss=0.02707, codebook_loss=18.32, over 1349151.85 frames.], batch size: 34, lr: 3.77e-04
+2022-05-27 23:35:47,192 INFO [train.py:823] (1/4) Epoch 45, batch 650, loss[loss=1.985, simple_loss=0.2546, pruned_loss=0.02901, codebook_loss=18.29, over 7160.00 frames.], tot_loss[loss=1.979, simple_loss=0.2353, pruned_loss=0.02695, codebook_loss=18.34, over 1364195.07 frames.], batch size: 23, lr: 3.77e-04
+2022-05-27 23:36:26,970 INFO [train.py:823] (1/4) Epoch 45, batch 700, loss[loss=2.089, simple_loss=0.2567, pruned_loss=0.03662, codebook_loss=19.24, over 7301.00 frames.], tot_loss[loss=1.981, simple_loss=0.2361, pruned_loss=0.02726, codebook_loss=18.35, over 1378450.59 frames.], batch size: 22, lr: 3.77e-04
+2022-05-27 23:37:06,802 INFO [train.py:823] (1/4) Epoch 45, batch 750, loss[loss=1.923, simple_loss=0.2391, pruned_loss=0.0256, codebook_loss=17.78, over 6948.00 frames.], tot_loss[loss=1.984, simple_loss=0.2366, pruned_loss=0.02738, codebook_loss=18.38, over 1387524.66 frames.], batch size: 29, lr: 3.77e-04
+2022-05-27 23:37:46,668 INFO [train.py:823] (1/4) Epoch 45, batch 800, loss[loss=2.354, simple_loss=0.2423, pruned_loss=0.0395, codebook_loss=21.94, over 7311.00 frames.], tot_loss[loss=1.982, simple_loss=0.2365, pruned_loss=0.02718, codebook_loss=18.37, over 1396725.74 frames.], batch size: 23, lr: 3.77e-04
+2022-05-27 23:38:26,827 INFO [train.py:823] (1/4) Epoch 45, batch 850, loss[loss=2.029, simple_loss=0.2538, pruned_loss=0.03689, codebook_loss=18.65, over 7193.00 frames.], tot_loss[loss=1.986, simple_loss=0.2378, pruned_loss=0.02761, codebook_loss=18.4, over 1398895.74 frames.], batch size: 21, lr: 3.76e-04
+2022-05-27 23:39:06,641 INFO [train.py:823] (1/4) Epoch 45, batch 900, loss[loss=2.213, simple_loss=0.2365, pruned_loss=0.03605, codebook_loss=20.58, over 7025.00 frames.], tot_loss[loss=1.991, simple_loss=0.2385, pruned_loss=0.02812, codebook_loss=18.43, over 1401138.58 frames.], batch size: 17, lr: 3.76e-04
+2022-05-27 23:40:00,601 INFO [train.py:823] (1/4) Epoch 46, batch 0, loss[loss=1.98, simple_loss=0.2503, pruned_loss=0.03761, codebook_loss=18.17, over 7185.00 frames.], tot_loss[loss=1.98, simple_loss=0.2503, pruned_loss=0.03761, codebook_loss=18.17, over 7185.00 frames.], batch size: 22, lr: 3.72e-04
+2022-05-27 23:40:40,261 INFO [train.py:823] (1/4) Epoch 46, batch 50, loss[loss=2.007, simple_loss=0.2508, pruned_loss=0.02598, codebook_loss=18.56, over 7288.00 frames.], tot_loss[loss=1.971, simple_loss=0.235, pruned_loss=0.0273, codebook_loss=18.27, over 314716.28 frames.], batch size: 20, lr: 3.72e-04
+2022-05-27 23:41:20,232 INFO [train.py:823] (1/4) Epoch 46, batch 100, loss[loss=1.893, simple_loss=0.2043, pruned_loss=0.02209, codebook_loss=17.69, over 7030.00 frames.], tot_loss[loss=1.966, simple_loss=0.2331, pruned_loss=0.02668, codebook_loss=18.23, over 560957.85 frames.], batch size: 16, lr: 3.71e-04
+2022-05-27 23:42:00,068 INFO [train.py:823] (1/4) Epoch 46, batch 150, loss[loss=1.911, simple_loss=0.226, pruned_loss=0.01819, codebook_loss=17.79, over 7118.00 frames.], tot_loss[loss=1.967, simple_loss=0.2341, pruned_loss=0.02688, codebook_loss=18.23, over 753275.21 frames.], batch size: 20, lr: 3.71e-04
+2022-05-27 23:42:40,056 INFO [train.py:823] (1/4) Epoch 46, batch 200, loss[loss=1.99, simple_loss=0.2461, pruned_loss=0.03209, codebook_loss=18.35, over 7336.00 frames.], tot_loss[loss=1.97, simple_loss=0.2332, pruned_loss=0.02685, codebook_loss=18.27, over 906327.93 frames.], batch size: 23, lr: 3.71e-04
+2022-05-27 23:43:22,190 INFO [train.py:823] (1/4) Epoch 46, batch 250, loss[loss=1.933, simple_loss=0.2502, pruned_loss=0.03552, codebook_loss=17.72, over 7143.00 frames.], tot_loss[loss=1.969, simple_loss=0.2338, pruned_loss=0.0267, codebook_loss=18.25, over 1020815.40 frames.], batch size: 23, lr: 3.71e-04
+2022-05-27 23:44:03,546 INFO [train.py:823] (1/4) Epoch 46, batch 300, loss[loss=1.927, simple_loss=0.2495, pruned_loss=0.02083, codebook_loss=17.82, over 6961.00 frames.], tot_loss[loss=1.969, simple_loss=0.2348, pruned_loss=0.02704, codebook_loss=18.24, over 1108086.23 frames.], batch size: 29, lr: 3.70e-04
+2022-05-27 23:44:43,204 INFO [train.py:823] (1/4) Epoch 46, batch 350, loss[loss=2.074, simple_loss=0.2675, pruned_loss=0.02848, codebook_loss=19.11, over 6582.00 frames.], tot_loss[loss=1.974, simple_loss=0.2364, pruned_loss=0.02721, codebook_loss=18.28, over 1179688.11 frames.], batch size: 34, lr: 3.70e-04
+2022-05-27 23:45:23,228 INFO [train.py:823] (1/4) Epoch 46, batch 400, loss[loss=1.895, simple_loss=0.2378, pruned_loss=0.02552, codebook_loss=17.51, over 7151.00 frames.], tot_loss[loss=1.972, simple_loss=0.2366, pruned_loss=0.02685, codebook_loss=18.27, over 1236093.76 frames.], batch size: 23, lr: 3.70e-04
+2022-05-27 23:46:03,183 INFO [train.py:823] (1/4) Epoch 46, batch 450, loss[loss=1.947, simple_loss=0.2499, pruned_loss=0.02847, codebook_loss=17.94, over 7280.00 frames.], tot_loss[loss=1.978, simple_loss=0.2363, pruned_loss=0.02683, codebook_loss=18.33, over 1279186.35 frames.], batch size: 20, lr: 3.70e-04
+2022-05-27 23:46:42,929 INFO [train.py:823] (1/4) Epoch 46, batch 500, loss[loss=1.907, simple_loss=0.2048, pruned_loss=0.02356, codebook_loss=17.81, over 6777.00 frames.], tot_loss[loss=1.982, simple_loss=0.2367, pruned_loss=0.02737, codebook_loss=18.36, over 1303467.77 frames.], batch size: 15, lr: 3.70e-04
+2022-05-27 23:47:22,900 INFO [train.py:823] (1/4) Epoch 46, batch 550, loss[loss=1.958, simple_loss=0.2334, pruned_loss=0.02338, codebook_loss=18.18, over 7306.00 frames.], tot_loss[loss=1.986, simple_loss=0.2366, pruned_loss=0.0275, codebook_loss=18.4, over 1333433.13 frames.], batch size: 22, lr: 3.69e-04
+2022-05-27 23:48:03,036 INFO [train.py:823] (1/4) Epoch 46, batch 600, loss[loss=1.999, simple_loss=0.2214, pruned_loss=0.02473, codebook_loss=18.64, over 7019.00 frames.], tot_loss[loss=1.982, simple_loss=0.2361, pruned_loss=0.027, codebook_loss=18.37, over 1352147.72 frames.], batch size: 17, lr: 3.69e-04
+2022-05-27 23:48:42,894 INFO [train.py:823] (1/4) Epoch 46, batch 650, loss[loss=1.978, simple_loss=0.2503, pruned_loss=0.03451, codebook_loss=18.19, over 7154.00 frames.], tot_loss[loss=1.978, simple_loss=0.2358, pruned_loss=0.02703, codebook_loss=18.33, over 1366911.66 frames.], batch size: 23, lr: 3.69e-04
+2022-05-27 23:49:24,211 INFO [train.py:823] (1/4) Epoch 46, batch 700, loss[loss=1.871, simple_loss=0.2112, pruned_loss=0.01532, codebook_loss=17.51, over 7151.00 frames.], tot_loss[loss=1.981, simple_loss=0.2349, pruned_loss=0.02693, codebook_loss=18.37, over 1374845.29 frames.], batch size: 17, lr: 3.69e-04
+2022-05-27 23:50:04,153 INFO [train.py:823] (1/4) Epoch 46, batch 750, loss[loss=2.119, simple_loss=0.2594, pruned_loss=0.03013, codebook_loss=19.59, over 6525.00 frames.], tot_loss[loss=1.98, simple_loss=0.2352, pruned_loss=0.02697, codebook_loss=18.35, over 1383027.24 frames.], batch size: 34, lr: 3.69e-04
+2022-05-27 23:50:44,397 INFO [train.py:823] (1/4) Epoch 46, batch 800, loss[loss=1.976, simple_loss=0.2286, pruned_loss=0.0226, codebook_loss=18.39, over 7204.00 frames.], tot_loss[loss=1.985, simple_loss=0.235, pruned_loss=0.02682, codebook_loss=18.41, over 1387163.99 frames.], batch size: 20, lr: 3.68e-04
+2022-05-27 23:51:24,083 INFO [train.py:823] (1/4) Epoch 46, batch 850, loss[loss=1.997, simple_loss=0.2582, pruned_loss=0.03798, codebook_loss=18.3, over 7320.00 frames.], tot_loss[loss=1.985, simple_loss=0.2347, pruned_loss=0.02671, codebook_loss=18.41, over 1389384.65 frames.], batch size: 23, lr: 3.68e-04
+2022-05-27 23:52:04,330 INFO [train.py:823] (1/4) Epoch 46, batch 900, loss[loss=1.916, simple_loss=0.2272, pruned_loss=0.02351, codebook_loss=17.79, over 7102.00 frames.], tot_loss[loss=1.987, simple_loss=0.2354, pruned_loss=0.02693, codebook_loss=18.42, over 1396865.00 frames.], batch size: 18, lr: 3.68e-04
+2022-05-27 23:52:54,926 INFO [train.py:823] (1/4) Epoch 47, batch 0, loss[loss=1.886, simple_loss=0.1991, pruned_loss=0.01789, codebook_loss=17.69, over 7017.00 frames.], tot_loss[loss=1.886, simple_loss=0.1991, pruned_loss=0.01789, codebook_loss=17.69, over 7017.00 frames.], batch size: 16, lr: 3.64e-04
+2022-05-27 23:53:35,049 INFO [train.py:823] (1/4) Epoch 47, batch 50, loss[loss=2.076, simple_loss=0.2258, pruned_loss=0.03664, codebook_loss=19.26, over 7313.00 frames.], tot_loss[loss=1.946, simple_loss=0.2301, pruned_loss=0.02399, codebook_loss=18.07, over 321812.20 frames.], batch size: 17, lr: 3.64e-04
+2022-05-27 23:54:15,107 INFO [train.py:823] (1/4) Epoch 47, batch 100, loss[loss=1.815, simple_loss=0.2058, pruned_loss=0.01088, codebook_loss=17.01, over 7314.00 frames.], tot_loss[loss=1.964, simple_loss=0.2295, pruned_loss=0.02426, codebook_loss=18.25, over 565189.48 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:54:55,173 INFO [train.py:823] (1/4) Epoch 47, batch 150, loss[loss=2.083, simple_loss=0.2504, pruned_loss=0.02357, codebook_loss=19.34, over 7294.00 frames.], tot_loss[loss=1.967, simple_loss=0.2316, pruned_loss=0.02505, codebook_loss=18.26, over 757365.55 frames.], batch size: 22, lr: 3.63e-04
+2022-05-27 23:55:34,801 INFO [train.py:823] (1/4) Epoch 47, batch 200, loss[loss=2, simple_loss=0.2245, pruned_loss=0.02029, codebook_loss=18.67, over 7080.00 frames.], tot_loss[loss=1.966, simple_loss=0.2326, pruned_loss=0.02579, codebook_loss=18.24, over 901232.00 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:56:14,829 INFO [train.py:823] (1/4) Epoch 47, batch 250, loss[loss=1.948, simple_loss=0.2434, pruned_loss=0.02857, codebook_loss=17.98, over 7395.00 frames.], tot_loss[loss=1.968, simple_loss=0.234, pruned_loss=0.02641, codebook_loss=18.25, over 1022264.01 frames.], batch size: 19, lr: 3.63e-04
+2022-05-27 23:56:54,299 INFO [train.py:823] (1/4) Epoch 47, batch 300, loss[loss=1.919, simple_loss=0.2249, pruned_loss=0.01936, codebook_loss=17.87, over 7187.00 frames.], tot_loss[loss=1.966, simple_loss=0.2344, pruned_loss=0.026, codebook_loss=18.23, over 1111707.96 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:57:34,825 INFO [train.py:823] (1/4) Epoch 47, batch 350, loss[loss=1.966, simple_loss=0.2289, pruned_loss=0.02196, codebook_loss=18.29, over 7287.00 frames.], tot_loss[loss=1.965, simple_loss=0.2341, pruned_loss=0.02593, codebook_loss=18.22, over 1179185.09 frames.], batch size: 20, lr: 3.62e-04
+2022-05-27 23:58:14,547 INFO [train.py:823] (1/4) Epoch 47, batch 400, loss[loss=1.898, simple_loss=0.2279, pruned_loss=0.01942, codebook_loss=17.64, over 7278.00 frames.], tot_loss[loss=1.967, simple_loss=0.236, pruned_loss=0.02672, codebook_loss=18.22, over 1233472.43 frames.], batch size: 20, lr: 3.62e-04
+2022-05-27 23:58:54,525 INFO [train.py:823] (1/4) Epoch 47, batch 450, loss[loss=1.91, simple_loss=0.2086, pruned_loss=0.02148, codebook_loss=17.84, over 7162.00 frames.], tot_loss[loss=1.965, simple_loss=0.2349, pruned_loss=0.02626, codebook_loss=18.22, over 1274457.72 frames.], batch size: 17, lr: 3.62e-04
+2022-05-27 23:59:34,088 INFO [train.py:823] (1/4) Epoch 47, batch 500, loss[loss=1.877, simple_loss=0.218, pruned_loss=0.01791, codebook_loss=17.5, over 7095.00 frames.], tot_loss[loss=1.969, simple_loss=0.2348, pruned_loss=0.0263, codebook_loss=18.25, over 1302667.20 frames.], batch size: 19, lr: 3.62e-04
+2022-05-28 00:00:14,248 INFO [train.py:823] (1/4) Epoch 47, batch 550, loss[loss=1.941, simple_loss=0.2348, pruned_loss=0.03482, codebook_loss=17.89, over 7386.00 frames.], tot_loss[loss=1.97, simple_loss=0.2342, pruned_loss=0.02635, codebook_loss=18.26, over 1328874.85 frames.], batch size: 19, lr: 3.62e-04
+2022-05-28 00:00:54,087 INFO [train.py:823] (1/4) Epoch 47, batch 600, loss[loss=1.904, simple_loss=0.2574, pruned_loss=0.02385, codebook_loss=17.51, over 6981.00 frames.], tot_loss[loss=1.967, simple_loss=0.2346, pruned_loss=0.02642, codebook_loss=18.24, over 1347395.69 frames.], batch size: 26, lr: 3.61e-04
+2022-05-28 00:01:34,140 INFO [train.py:823] (1/4) Epoch 47, batch 650, loss[loss=2.021, simple_loss=0.2144, pruned_loss=0.02571, codebook_loss=18.88, over 7286.00 frames.], tot_loss[loss=1.968, simple_loss=0.2352, pruned_loss=0.02671, codebook_loss=18.23, over 1364860.68 frames.], batch size: 17, lr: 3.61e-04
+2022-05-28 00:02:14,068 INFO [train.py:823] (1/4) Epoch 47, batch 700, loss[loss=1.937, simple_loss=0.2715, pruned_loss=0.02778, codebook_loss=17.74, over 7350.00 frames.], tot_loss[loss=1.97, simple_loss=0.2354, pruned_loss=0.02698, codebook_loss=18.26, over 1372291.43 frames.], batch size: 23, lr: 3.61e-04
+2022-05-28 00:02:54,283 INFO [train.py:823] (1/4) Epoch 47, batch 750, loss[loss=1.955, simple_loss=0.2031, pruned_loss=0.02704, codebook_loss=18.26, over 7300.00 frames.], tot_loss[loss=1.971, simple_loss=0.235, pruned_loss=0.02694, codebook_loss=18.26, over 1384196.74 frames.], batch size: 19, lr: 3.61e-04
+2022-05-28 00:03:34,012 INFO [train.py:823] (1/4) Epoch 47, batch 800, loss[loss=1.982, simple_loss=0.2415, pruned_loss=0.02351, codebook_loss=18.38, over 6965.00 frames.], tot_loss[loss=1.974, simple_loss=0.2349, pruned_loss=0.02692, codebook_loss=18.29, over 1391061.70 frames.], batch size: 26, lr: 3.61e-04
+2022-05-28 00:04:13,986 INFO [train.py:823] (1/4) Epoch 47, batch 850, loss[loss=1.931, simple_loss=0.2094, pruned_loss=0.01728, codebook_loss=18.09, over 7195.00 frames.], tot_loss[loss=1.973, simple_loss=0.2349, pruned_loss=0.02682, codebook_loss=18.29, over 1392009.81 frames.], batch size: 18, lr: 3.60e-04
+2022-05-28 00:04:53,639 INFO [train.py:823] (1/4) Epoch 47, batch 900, loss[loss=1.837, simple_loss=0.2387, pruned_loss=0.01941, codebook_loss=16.98, over 7307.00 frames.], tot_loss[loss=1.97, simple_loss=0.2348, pruned_loss=0.02663, codebook_loss=18.26, over 1397453.59 frames.], batch size: 22, lr: 3.60e-04
+2022-05-28 00:05:47,401 INFO [train.py:823] (1/4) Epoch 48, batch 0, loss[loss=1.847, simple_loss=0.226, pruned_loss=0.01662, codebook_loss=17.18, over 7190.00 frames.], tot_loss[loss=1.847, simple_loss=0.226, pruned_loss=0.01662, codebook_loss=17.18, over 7190.00 frames.], batch size: 21, lr: 3.56e-04
+2022-05-28 00:06:27,209 INFO [train.py:823] (1/4) Epoch 48, batch 50, loss[loss=2.046, simple_loss=0.2039, pruned_loss=0.02217, codebook_loss=19.22, over 7143.00 frames.], tot_loss[loss=1.969, simple_loss=0.2338, pruned_loss=0.02598, codebook_loss=18.26, over 320071.33 frames.], batch size: 17, lr: 3.56e-04
+2022-05-28 00:07:07,671 INFO [train.py:823] (1/4) Epoch 48, batch 100, loss[loss=1.889, simple_loss=0.2586, pruned_loss=0.02357, codebook_loss=17.36, over 7223.00 frames.], tot_loss[loss=1.963, simple_loss=0.2346, pruned_loss=0.02611, codebook_loss=18.19, over 565858.60 frames.], batch size: 25, lr: 3.56e-04
+2022-05-28 00:07:49,898 INFO [train.py:823] (1/4) Epoch 48, batch 150, loss[loss=1.93, simple_loss=0.21, pruned_loss=0.02041, codebook_loss=18.04, over 7294.00 frames.], tot_loss[loss=1.965, simple_loss=0.2358, pruned_loss=0.0265, codebook_loss=18.21, over 760494.79 frames.], batch size: 17, lr: 3.56e-04
+2022-05-28 00:08:31,450 INFO [train.py:823] (1/4) Epoch 48, batch 200, loss[loss=1.882, simple_loss=0.2572, pruned_loss=0.02489, codebook_loss=17.28, over 7308.00 frames.], tot_loss[loss=1.968, simple_loss=0.2346, pruned_loss=0.02629, codebook_loss=18.25, over 906640.64 frames.], batch size: 22, lr: 3.55e-04
+2022-05-28 00:09:11,317 INFO [train.py:823] (1/4) Epoch 48, batch 250, loss[loss=1.981, simple_loss=0.2402, pruned_loss=0.03427, codebook_loss=18.26, over 7207.00 frames.], tot_loss[loss=1.967, simple_loss=0.234, pruned_loss=0.02623, codebook_loss=18.24, over 1023203.23 frames.], batch size: 19, lr: 3.55e-04
+2022-05-28 00:09:51,419 INFO [train.py:823] (1/4) Epoch 48, batch 300, loss[loss=1.906, simple_loss=0.2425, pruned_loss=0.02495, codebook_loss=17.6, over 6970.00 frames.], tot_loss[loss=1.96, simple_loss=0.233, pruned_loss=0.02592, codebook_loss=18.18, over 1115887.08 frames.], batch size: 26, lr: 3.55e-04
+2022-05-28 00:10:30,853 INFO [train.py:823] (1/4) Epoch 48, batch 350, loss[loss=1.952, simple_loss=0.2427, pruned_loss=0.02632, codebook_loss=18.04, over 4832.00 frames.], tot_loss[loss=1.97, simple_loss=0.2335, pruned_loss=0.02637, codebook_loss=18.27, over 1182417.81 frames.], batch size: 47, lr: 3.55e-04
+2022-05-28 00:11:11,347 INFO [train.py:823] (1/4) Epoch 48, batch 400, loss[loss=1.919, simple_loss=0.2365, pruned_loss=0.02362, codebook_loss=17.77, over 6479.00 frames.], tot_loss[loss=1.968, simple_loss=0.2332, pruned_loss=0.02625, codebook_loss=18.25, over 1238762.48 frames.], batch size: 34, lr: 3.55e-04
+2022-05-28 00:11:50,920 INFO [train.py:823] (1/4) Epoch 48, batch 450, loss[loss=1.99, simple_loss=0.2283, pruned_loss=0.02834, codebook_loss=18.47, over 7295.00 frames.], tot_loss[loss=1.971, simple_loss=0.2343, pruned_loss=0.02665, codebook_loss=18.27, over 1280787.90 frames.], batch size: 17, lr: 3.54e-04
+2022-05-28 00:12:31,151 INFO [train.py:823] (1/4) Epoch 48, batch 500, loss[loss=2.032, simple_loss=0.2635, pruned_loss=0.03671, codebook_loss=18.64, over 7197.00 frames.], tot_loss[loss=1.975, simple_loss=0.2356, pruned_loss=0.02728, codebook_loss=18.3, over 1311108.41 frames.], batch size: 20, lr: 3.54e-04
+2022-05-28 00:13:11,073 INFO [train.py:823] (1/4) Epoch 48, batch 550, loss[loss=1.923, simple_loss=0.2485, pruned_loss=0.02631, codebook_loss=17.72, over 7427.00 frames.], tot_loss[loss=1.972, simple_loss=0.2355, pruned_loss=0.02703, codebook_loss=18.27, over 1331642.82 frames.], batch size: 22, lr: 3.54e-04
+2022-05-28 00:13:52,285 INFO [train.py:823] (1/4) Epoch 48, batch 600, loss[loss=1.963, simple_loss=0.2332, pruned_loss=0.02791, codebook_loss=18.18, over 7282.00 frames.], tot_loss[loss=1.974, simple_loss=0.2363, pruned_loss=0.02711, codebook_loss=18.29, over 1350619.39 frames.], batch size: 20, lr: 3.54e-04
+2022-05-28 00:14:32,034 INFO [train.py:823] (1/4) Epoch 48, batch 650, loss[loss=1.869, simple_loss=0.2249, pruned_loss=0.01776, codebook_loss=17.39, over 7381.00 frames.], tot_loss[loss=1.97, simple_loss=0.2357, pruned_loss=0.0267, codebook_loss=18.25, over 1364839.86 frames.], batch size: 21, lr: 3.54e-04
+2022-05-28 00:15:11,904 INFO [train.py:823] (1/4) Epoch 48, batch 700, loss[loss=1.965, simple_loss=0.2447, pruned_loss=0.03053, codebook_loss=18.12, over 7180.00 frames.], tot_loss[loss=1.966, simple_loss=0.236, pruned_loss=0.02665, codebook_loss=18.21, over 1372019.24 frames.], batch size: 22, lr: 3.53e-04
+2022-05-28 00:15:51,674 INFO [train.py:823] (1/4) Epoch 48, batch 750, loss[loss=1.917, simple_loss=0.2298, pruned_loss=0.02576, codebook_loss=17.77, over 7107.00 frames.], tot_loss[loss=1.966, simple_loss=0.2354, pruned_loss=0.02658, codebook_loss=18.21, over 1383798.57 frames.], batch size: 19, lr: 3.53e-04
+2022-05-28 00:16:31,783 INFO [train.py:823] (1/4) Epoch 48, batch 800, loss[loss=1.967, simple_loss=0.2619, pruned_loss=0.0404, codebook_loss=17.96, over 7349.00 frames.], tot_loss[loss=1.967, simple_loss=0.235, pruned_loss=0.02637, codebook_loss=18.23, over 1391335.08 frames.], batch size: 23, lr: 3.53e-04
+2022-05-28 00:17:11,213 INFO [train.py:823] (1/4) Epoch 48, batch 850, loss[loss=1.904, simple_loss=0.2291, pruned_loss=0.02784, codebook_loss=17.61, over 7293.00 frames.], tot_loss[loss=1.972, simple_loss=0.2346, pruned_loss=0.02647, codebook_loss=18.28, over 1391709.23 frames.], batch size: 17, lr: 3.53e-04
+2022-05-28 00:17:51,123 INFO [train.py:823] (1/4) Epoch 48, batch 900, loss[loss=1.956, simple_loss=0.2304, pruned_loss=0.0232, codebook_loss=18.18, over 7290.00 frames.], tot_loss[loss=1.971, simple_loss=0.2347, pruned_loss=0.02627, codebook_loss=18.28, over 1395355.89 frames.], batch size: 19, lr: 3.53e-04
+2022-05-28 00:18:41,956 INFO [train.py:823] (1/4) Epoch 49, batch 0, loss[loss=1.89, simple_loss=0.2371, pruned_loss=0.02128, codebook_loss=17.5, over 7378.00 frames.], tot_loss[loss=1.89, simple_loss=0.2371, pruned_loss=0.02128, codebook_loss=17.5, over 7378.00 frames.], batch size: 20, lr: 3.49e-04
+2022-05-28 00:19:21,916 INFO [train.py:823] (1/4) Epoch 49, batch 50, loss[loss=1.939, simple_loss=0.2332, pruned_loss=0.01997, codebook_loss=18.03, over 7276.00 frames.], tot_loss[loss=1.938, simple_loss=0.2346, pruned_loss=0.02537, codebook_loss=17.96, over 318735.81 frames.], batch size: 21, lr: 3.49e-04
+2022-05-28 00:20:01,475 INFO [train.py:823] (1/4) Epoch 49, batch 100, loss[loss=1.909, simple_loss=0.217, pruned_loss=0.01975, codebook_loss=17.81, over 7181.00 frames.], tot_loss[loss=1.937, simple_loss=0.233, pruned_loss=0.02454, codebook_loss=17.96, over 560671.69 frames.], batch size: 18, lr: 3.48e-04
+2022-05-28 00:20:41,943 INFO [train.py:823] (1/4) Epoch 49, batch 150, loss[loss=2.053, simple_loss=0.2289, pruned_loss=0.03685, codebook_loss=19.02, over 4704.00 frames.], tot_loss[loss=1.948, simple_loss=0.2324, pruned_loss=0.02507, codebook_loss=18.07, over 751079.39 frames.], batch size: 47, lr: 3.48e-04
+2022-05-28 00:21:21,725 INFO [train.py:823] (1/4) Epoch 49, batch 200, loss[loss=1.951, simple_loss=0.2448, pruned_loss=0.03469, codebook_loss=17.94, over 7125.00 frames.], tot_loss[loss=1.953, simple_loss=0.2316, pruned_loss=0.02497, codebook_loss=18.12, over 901388.92 frames.], batch size: 23, lr: 3.48e-04
+2022-05-28 00:22:01,860 INFO [train.py:823] (1/4) Epoch 49, batch 250, loss[loss=1.951, simple_loss=0.2338, pruned_loss=0.0288, codebook_loss=18.06, over 7200.00 frames.], tot_loss[loss=1.963, simple_loss=0.2336, pruned_loss=0.0259, codebook_loss=18.21, over 1021745.64 frames.], batch size: 20, lr: 3.48e-04
+2022-05-28 00:22:41,591 INFO [train.py:823] (1/4) Epoch 49, batch 300, loss[loss=1.819, simple_loss=0.2161, pruned_loss=0.01495, codebook_loss=16.96, over 7304.00 frames.], tot_loss[loss=1.963, simple_loss=0.2334, pruned_loss=0.02569, codebook_loss=18.21, over 1113795.49 frames.], batch size: 18, lr: 3.48e-04
+2022-05-28 00:23:21,765 INFO [train.py:823] (1/4) Epoch 49, batch 350, loss[loss=2.097, simple_loss=0.2509, pruned_loss=0.02422, codebook_loss=19.47, over 7202.00 frames.], tot_loss[loss=1.962, simple_loss=0.2334, pruned_loss=0.02553, codebook_loss=18.2, over 1176804.46 frames.], batch size: 25, lr: 3.48e-04
+2022-05-28 00:24:01,388 INFO [train.py:823] (1/4) Epoch 49, batch 400, loss[loss=2.009, simple_loss=0.2032, pruned_loss=0.02832, codebook_loss=18.79, over 7008.00 frames.], tot_loss[loss=1.97, simple_loss=0.2337, pruned_loss=0.02613, codebook_loss=18.27, over 1228102.94 frames.], batch size: 16, lr: 3.47e-04
+2022-05-28 00:24:41,435 INFO [train.py:823] (1/4) Epoch 49, batch 450, loss[loss=1.944, simple_loss=0.2621, pruned_loss=0.03251, codebook_loss=17.81, over 7242.00 frames.], tot_loss[loss=1.967, simple_loss=0.2336, pruned_loss=0.02616, codebook_loss=18.24, over 1273703.01 frames.], batch size: 24, lr: 3.47e-04
+2022-05-28 00:25:21,290 INFO [train.py:823] (1/4) Epoch 49, batch 500, loss[loss=1.908, simple_loss=0.2304, pruned_loss=0.02521, codebook_loss=17.68, over 6654.00 frames.], tot_loss[loss=1.963, simple_loss=0.2334, pruned_loss=0.02616, codebook_loss=18.2, over 1305687.91 frames.], batch size: 34, lr: 3.47e-04
+2022-05-28 00:26:01,621 INFO [train.py:823] (1/4) Epoch 49, batch 550, loss[loss=1.936, simple_loss=0.2237, pruned_loss=0.02517, codebook_loss=17.99, over 7291.00 frames.], tot_loss[loss=1.966, simple_loss=0.2327, pruned_loss=0.02617, codebook_loss=18.24, over 1332660.35 frames.], batch size: 17, lr: 3.47e-04
+2022-05-28 00:26:41,362 INFO [train.py:823] (1/4) Epoch 49, batch 600, loss[loss=1.93, simple_loss=0.2265, pruned_loss=0.02966, codebook_loss=17.87, over 7227.00 frames.], tot_loss[loss=1.968, simple_loss=0.2331, pruned_loss=0.02627, codebook_loss=18.26, over 1351102.12 frames.], batch size: 24, lr: 3.47e-04
+2022-05-28 00:27:21,540 INFO [train.py:823] (1/4) Epoch 49, batch 650, loss[loss=1.93, simple_loss=0.217, pruned_loss=0.0249, codebook_loss=17.97, over 7150.00 frames.], tot_loss[loss=1.967, simple_loss=0.233, pruned_loss=0.02607, codebook_loss=18.24, over 1367542.19 frames.], batch size: 17, lr: 3.46e-04
+2022-05-28 00:28:00,823 INFO [train.py:823] (1/4) Epoch 49, batch 700, loss[loss=1.956, simple_loss=0.2367, pruned_loss=0.02234, codebook_loss=18.15, over 7414.00 frames.], tot_loss[loss=1.977, simple_loss=0.2343, pruned_loss=0.02672, codebook_loss=18.33, over 1370981.96 frames.], batch size: 22, lr: 3.46e-04
+2022-05-28 00:28:40,814 INFO [train.py:823] (1/4) Epoch 49, batch 750, loss[loss=1.938, simple_loss=0.2126, pruned_loss=0.02376, codebook_loss=18.08, over 7290.00 frames.], tot_loss[loss=1.974, simple_loss=0.2349, pruned_loss=0.02685, codebook_loss=18.29, over 1381036.69 frames.], batch size: 19, lr: 3.46e-04
+2022-05-28 00:29:20,490 INFO [train.py:823] (1/4) Epoch 49, batch 800, loss[loss=1.985, simple_loss=0.212, pruned_loss=0.03529, codebook_loss=18.44, over 7143.00 frames.], tot_loss[loss=1.973, simple_loss=0.2351, pruned_loss=0.02687, codebook_loss=18.29, over 1385316.65 frames.], batch size: 17, lr: 3.46e-04
+2022-05-28 00:30:00,425 INFO [train.py:823] (1/4) Epoch 49, batch 850, loss[loss=1.887, simple_loss=0.2163, pruned_loss=0.02286, codebook_loss=17.56, over 7099.00 frames.], tot_loss[loss=1.968, simple_loss=0.2341, pruned_loss=0.02635, codebook_loss=18.25, over 1391380.87 frames.], batch size: 18, lr: 3.46e-04
+2022-05-28 00:30:40,052 INFO [train.py:823] (1/4) Epoch 49, batch 900, loss[loss=1.987, simple_loss=0.2354, pruned_loss=0.02777, codebook_loss=18.41, over 6437.00 frames.], tot_loss[loss=1.972, simple_loss=0.2346, pruned_loss=0.02667, codebook_loss=18.28, over 1393757.99 frames.], batch size: 34, lr: 3.45e-04
+2022-05-28 00:31:35,684 INFO [train.py:823] (1/4) Epoch 50, batch 0, loss[loss=1.949, simple_loss=0.2513, pruned_loss=0.02385, codebook_loss=17.99, over 7102.00 frames.], tot_loss[loss=1.949, simple_loss=0.2513, pruned_loss=0.02385, codebook_loss=17.99, over 7102.00 frames.], batch size: 29, lr: 3.42e-04
+2022-05-28 00:32:17,067 INFO [train.py:823] (1/4) Epoch 50, batch 50, loss[loss=2.015, simple_loss=0.2542, pruned_loss=0.03099, codebook_loss=18.57, over 7278.00 frames.], tot_loss[loss=1.972, simple_loss=0.2314, pruned_loss=0.02547, codebook_loss=18.31, over 322576.71 frames.], batch size: 20, lr: 3.42e-04
+2022-05-28 00:32:59,753 INFO [train.py:823] (1/4) Epoch 50, batch 100, loss[loss=1.982, simple_loss=0.2518, pruned_loss=0.04153, codebook_loss=18.15, over 7165.00 frames.], tot_loss[loss=1.951, simple_loss=0.2324, pruned_loss=0.02569, codebook_loss=18.1, over 563946.34 frames.], batch size: 23, lr: 3.41e-04
+2022-05-28 00:33:39,335 INFO [train.py:823] (1/4) Epoch 50, batch 150, loss[loss=1.966, simple_loss=0.2359, pruned_loss=0.02962, codebook_loss=18.19, over 7381.00 frames.], tot_loss[loss=1.965, simple_loss=0.235, pruned_loss=0.02643, codebook_loss=18.21, over 752567.33 frames.], batch size: 21, lr: 3.41e-04
+2022-05-28 00:34:19,392 INFO [train.py:823] (1/4) Epoch 50, batch 200, loss[loss=2.106, simple_loss=0.2461, pruned_loss=0.03829, codebook_loss=19.45, over 7096.00 frames.], tot_loss[loss=1.965, simple_loss=0.234, pruned_loss=0.02649, codebook_loss=18.22, over 901796.41 frames.], batch size: 18, lr: 3.41e-04
+2022-05-28 00:34:59,309 INFO [train.py:823] (1/4) Epoch 50, batch 250, loss[loss=2.026, simple_loss=0.2495, pruned_loss=0.04439, codebook_loss=18.57, over 7167.00 frames.], tot_loss[loss=1.96, simple_loss=0.2325, pruned_loss=0.02605, codebook_loss=18.18, over 1020177.41 frames.], batch size: 22, lr: 3.41e-04
+2022-05-28 00:35:39,376 INFO [train.py:823] (1/4) Epoch 50, batch 300, loss[loss=2.011, simple_loss=0.2494, pruned_loss=0.03434, codebook_loss=18.52, over 7195.00 frames.], tot_loss[loss=1.966, simple_loss=0.2342, pruned_loss=0.0264, codebook_loss=18.23, over 1110377.88 frames.], batch size: 20, lr: 3.41e-04
+2022-05-28 00:36:19,045 INFO [train.py:823] (1/4) Epoch 50, batch 350, loss[loss=2.399, simple_loss=0.2402, pruned_loss=0.03108, codebook_loss=22.48, over 7417.00 frames.], tot_loss[loss=1.962, simple_loss=0.2339, pruned_loss=0.0263, codebook_loss=18.18, over 1178994.45 frames.], batch size: 22, lr: 3.41e-04
+2022-05-28 00:36:59,295 INFO [train.py:823] (1/4) Epoch 50, batch 400, loss[loss=1.963, simple_loss=0.2509, pruned_loss=0.03533, codebook_loss=18.02, over 7029.00 frames.], tot_loss[loss=1.964, simple_loss=0.2338, pruned_loss=0.02619, codebook_loss=18.21, over 1233042.73 frames.], batch size: 26, lr: 3.40e-04
+2022-05-28 00:37:40,219 INFO [train.py:823] (1/4) Epoch 50, batch 450, loss[loss=1.943, simple_loss=0.2216, pruned_loss=0.02011, codebook_loss=18.12, over 6378.00 frames.], tot_loss[loss=1.962, simple_loss=0.2343, pruned_loss=0.0262, codebook_loss=18.19, over 1273840.30 frames.], batch size: 34, lr: 3.40e-04
+2022-05-28 00:38:20,398 INFO [train.py:823] (1/4) Epoch 50, batch 500, loss[loss=1.904, simple_loss=0.2228, pruned_loss=0.02247, codebook_loss=17.7, over 7286.00 frames.], tot_loss[loss=1.965, simple_loss=0.2348, pruned_loss=0.02631, codebook_loss=18.21, over 1307166.63 frames.], batch size: 19, lr: 3.40e-04
+2022-05-28 00:39:00,413 INFO [train.py:823] (1/4) Epoch 50, batch 550, loss[loss=2.048, simple_loss=0.2524, pruned_loss=0.04279, codebook_loss=18.79, over 7232.00 frames.], tot_loss[loss=1.966, simple_loss=0.2343, pruned_loss=0.02638, codebook_loss=18.23, over 1334747.11 frames.], batch size: 24, lr: 3.40e-04
+2022-05-28 00:39:40,466 INFO [train.py:823] (1/4) Epoch 50, batch 600, loss[loss=1.932, simple_loss=0.216, pruned_loss=0.02024, codebook_loss=18.03, over 7027.00 frames.], tot_loss[loss=1.964, simple_loss=0.2341, pruned_loss=0.0262, codebook_loss=18.21, over 1352591.42 frames.], batch size: 16, lr: 3.40e-04
+2022-05-28 00:40:20,088 INFO [train.py:823] (1/4) Epoch 50, batch 650, loss[loss=1.92, simple_loss=0.2163, pruned_loss=0.02143, codebook_loss=17.9, over 7009.00 frames.], tot_loss[loss=1.964, simple_loss=0.2351, pruned_loss=0.02673, codebook_loss=18.2, over 1363437.61 frames.], batch size: 16, lr: 3.39e-04
+2022-05-28 00:41:00,236 INFO [train.py:823] (1/4) Epoch 50, batch 700, loss[loss=1.917, simple_loss=0.2047, pruned_loss=0.01694, codebook_loss=17.97, over 7018.00 frames.], tot_loss[loss=1.965, simple_loss=0.2342, pruned_loss=0.0267, codebook_loss=18.21, over 1375529.33 frames.], batch size: 16, lr: 3.39e-04
+2022-05-28 00:41:39,956 INFO [train.py:823] (1/4) Epoch 50, batch 750, loss[loss=2.06, simple_loss=0.241, pruned_loss=0.02946, codebook_loss=19.1, over 7309.00 frames.], tot_loss[loss=1.966, simple_loss=0.2345, pruned_loss=0.0268, codebook_loss=18.22, over 1383246.21 frames.], batch size: 22, lr: 3.39e-04
+2022-05-28 00:42:20,187 INFO [train.py:823] (1/4) Epoch 50, batch 800, loss[loss=1.925, simple_loss=0.2117, pruned_loss=0.0214, codebook_loss=17.98, over 7092.00 frames.], tot_loss[loss=1.966, simple_loss=0.2342, pruned_loss=0.02689, codebook_loss=18.22, over 1391478.30 frames.], batch size: 19, lr: 3.39e-04
+2022-05-28 00:43:00,012 INFO [train.py:823] (1/4) Epoch 50, batch 850, loss[loss=2.002, simple_loss=0.2538, pruned_loss=0.04221, codebook_loss=18.33, over 4434.00 frames.], tot_loss[loss=1.973, simple_loss=0.2344, pruned_loss=0.02687, codebook_loss=18.29, over 1396447.64 frames.], batch size: 46, lr: 3.39e-04
+2022-05-28 00:43:39,821 INFO [train.py:823] (1/4) Epoch 50, batch 900, loss[loss=1.961, simple_loss=0.2309, pruned_loss=0.02307, codebook_loss=18.23, over 6405.00 frames.], tot_loss[loss=1.968, simple_loss=0.2345, pruned_loss=0.02666, codebook_loss=18.24, over 1399129.83 frames.], batch size: 34, lr: 3.39e-04
+2022-05-28 00:44:19,555 INFO [train.py:1038] (1/4) Done!