diff --git "a/distillation/log/log-train-2022-05-27-13-56-55-2" "b/distillation/log/log-train-2022-05-27-13-56-55-2"
new file mode 100644--- /dev/null
+++ "b/distillation/log/log-train-2022-05-27-13-56-55-2"
@@ -0,0 +1,982 @@
+2022-05-27 13:56:55,366 INFO [train.py:887] (2/4) Training started
+2022-05-27 13:56:55,367 INFO [train.py:897] (2/4) Device: cuda:2
+2022-05-27 13:56:55,368 INFO [train.py:906] (2/4) {'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 13:56:55,369 INFO [train.py:908] (2/4) About to create model
+2022-05-27 13:56:55,838 INFO [train.py:912] (2/4) Number of model parameters: 85075176
+2022-05-27 13:57:00,374 INFO [train.py:927] (2/4) Using DDP
+2022-05-27 13:57:00,574 INFO [asr_datamodule.py:408] (2/4) About to get train-clean-100 cuts
+2022-05-27 13:57:08,835 INFO [asr_datamodule.py:225] (2/4) Enable MUSAN
+2022-05-27 13:57:08,836 INFO [asr_datamodule.py:226] (2/4) About to get Musan cuts
+2022-05-27 13:57:12,432 INFO [asr_datamodule.py:254] (2/4) Enable SpecAugment
+2022-05-27 13:57:12,432 INFO [asr_datamodule.py:255] (2/4) Time warp factor: -1
+2022-05-27 13:57:12,433 INFO [asr_datamodule.py:267] (2/4) Num frame mask: 10
+2022-05-27 13:57:12,433 INFO [asr_datamodule.py:280] (2/4) About to create train dataset
+2022-05-27 13:57:12,433 INFO [asr_datamodule.py:309] (2/4) Using BucketingSampler.
+2022-05-27 13:57:12,748 INFO [asr_datamodule.py:325] (2/4) About to create train dataloader
+2022-05-27 13:57:12,749 INFO [asr_datamodule.py:429] (2/4) About to get dev-clean cuts
+2022-05-27 13:57:12,888 INFO [asr_datamodule.py:434] (2/4) About to get dev-other cuts
+2022-05-27 13:57:13,002 INFO [asr_datamodule.py:356] (2/4) About to create dev dataset
+2022-05-27 13:57:13,011 INFO [asr_datamodule.py:375] (2/4) About to create dev dataloader
+2022-05-27 13:57:13,012 INFO [train.py:1054] (2/4) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
+2022-05-27 13:57:15,193 INFO [distributed.py:874] (2/4) Reducer buckets have been rebuilt in this iteration.
+2022-05-27 13:57:27,688 INFO [train.py:823] (2/4) Epoch 1, batch 0, loss[loss=9.188, simple_loss=1.728, pruned_loss=6.67, codebook_loss=83.24, over 7281.00 frames.], tot_loss[loss=9.188, simple_loss=1.728, pruned_loss=6.67, codebook_loss=83.24, over 7281.00 frames.], batch size: 21, lr: 3.00e-03
+2022-05-27 13:58:08,133 INFO [train.py:823] (2/4) Epoch 1, batch 50, loss[loss=5.364, simple_loss=1.009, pruned_loss=6.815, codebook_loss=48.59, over 7148.00 frames.], tot_loss[loss=6.753, simple_loss=1.123, pruned_loss=6.798, codebook_loss=61.92, over 322117.15 frames.], batch size: 23, lr: 3.00e-03
+2022-05-27 13:58:49,199 INFO [train.py:823] (2/4) Epoch 1, batch 100, loss[loss=4.475, simple_loss=0.8796, pruned_loss=6.749, codebook_loss=40.35, over 7198.00 frames.], tot_loss[loss=5.707, simple_loss=1.014, pruned_loss=6.809, codebook_loss=52.01, over 564350.66 frames.], batch size: 20, lr: 3.00e-03
+2022-05-27 13:59:29,583 INFO [train.py:823] (2/4) Epoch 1, batch 150, loss[loss=4.386, simple_loss=0.8834, pruned_loss=6.816, codebook_loss=39.44, over 7335.00 frames.], tot_loss[loss=5.132, simple_loss=0.9481, pruned_loss=6.788, codebook_loss=46.58, over 754765.62 frames.], batch size: 23, lr: 3.00e-03
+2022-05-27 14:00:10,084 INFO [train.py:823] (2/4) Epoch 1, batch 200, loss[loss=3.965, simple_loss=0.7859, pruned_loss=6.602, codebook_loss=35.72, over 7289.00 frames.], tot_loss[loss=4.758, simple_loss=0.9062, pruned_loss=6.758, codebook_loss=43.04, over 904582.73 frames.], batch size: 19, lr: 3.00e-03
+2022-05-27 14:00:50,308 INFO [train.py:823] (2/4) Epoch 1, batch 250, loss[loss=3.726, simple_loss=0.6804, pruned_loss=6.482, codebook_loss=33.86, over 7283.00 frames.], tot_loss[loss=4.498, simple_loss=0.8689, pruned_loss=6.727, codebook_loss=40.64, over 1014628.52 frames.], batch size: 17, lr: 3.00e-03
+2022-05-27 14:01:30,772 INFO [train.py:823] (2/4) Epoch 1, batch 300, loss[loss=3.692, simple_loss=0.7223, pruned_loss=6.679, codebook_loss=33.3, over 7216.00 frames.], tot_loss[loss=4.282, simple_loss=0.8261, pruned_loss=6.695, codebook_loss=38.69, over 1106272.13 frames.], batch size: 24, lr: 3.00e-03
+2022-05-27 14:02:10,824 INFO [train.py:823] (2/4) Epoch 1, batch 350, loss[loss=3.598, simple_loss=0.6583, pruned_loss=6.533, codebook_loss=32.69, over 6459.00 frames.], tot_loss[loss=4.099, simple_loss=0.7799, pruned_loss=6.67, codebook_loss=37.09, over 1177244.22 frames.], batch size: 34, lr: 3.00e-03
+2022-05-27 14:02:51,179 INFO [train.py:823] (2/4) Epoch 1, batch 400, loss[loss=3.495, simple_loss=0.6213, pruned_loss=6.612, codebook_loss=31.85, over 4812.00 frames.], tot_loss[loss=3.957, simple_loss=0.7388, pruned_loss=6.661, codebook_loss=35.88, over 1228059.48 frames.], batch size: 46, lr: 3.00e-03
+2022-05-27 14:03:31,156 INFO [train.py:823] (2/4) Epoch 1, batch 450, loss[loss=3.409, simple_loss=0.5839, pruned_loss=6.639, codebook_loss=31.17, over 7205.00 frames.], tot_loss[loss=3.838, simple_loss=0.7008, pruned_loss=6.643, codebook_loss=34.87, over 1274115.10 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:04:11,766 INFO [train.py:823] (2/4) Epoch 1, batch 500, loss[loss=3.236, simple_loss=0.4894, pruned_loss=6.439, codebook_loss=29.91, over 7389.00 frames.], tot_loss[loss=3.731, simple_loss=0.6684, pruned_loss=6.634, codebook_loss=33.97, over 1308811.12 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:04:51,665 INFO [train.py:823] (2/4) Epoch 1, batch 550, loss[loss=3.429, simple_loss=0.551, pruned_loss=6.506, codebook_loss=31.53, over 7221.00 frames.], tot_loss[loss=3.642, simple_loss=0.6376, pruned_loss=6.62, codebook_loss=33.23, over 1329725.40 frames.], batch size: 25, lr: 2.99e-03
+2022-05-27 14:05:31,968 INFO [train.py:823] (2/4) Epoch 1, batch 600, loss[loss=3.161, simple_loss=0.4554, pruned_loss=6.505, codebook_loss=29.33, over 7280.00 frames.], tot_loss[loss=3.56, simple_loss=0.6092, pruned_loss=6.608, codebook_loss=32.56, over 1346577.44 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:06:11,925 INFO [train.py:823] (2/4) Epoch 1, batch 650, loss[loss=3.238, simple_loss=0.4841, pruned_loss=6.618, codebook_loss=29.96, over 7099.00 frames.], tot_loss[loss=3.487, simple_loss=0.5865, pruned_loss=6.608, codebook_loss=31.94, over 1361440.64 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:06:52,040 INFO [train.py:823] (2/4) Epoch 1, batch 700, loss[loss=3.12, simple_loss=0.4575, pruned_loss=6.441, codebook_loss=28.91, over 7167.00 frames.], tot_loss[loss=3.422, simple_loss=0.5634, pruned_loss=6.6, codebook_loss=31.41, over 1373624.75 frames.], batch size: 17, lr: 2.99e-03
+2022-05-27 14:07:31,809 INFO [train.py:823] (2/4) Epoch 1, batch 750, loss[loss=3.057, simple_loss=0.3928, pruned_loss=6.416, codebook_loss=28.61, over 7224.00 frames.], tot_loss[loss=3.359, simple_loss=0.5429, pruned_loss=6.595, codebook_loss=30.88, over 1386861.15 frames.], batch size: 16, lr: 2.98e-03
+2022-05-27 14:08:12,266 INFO [train.py:823] (2/4) Epoch 1, batch 800, loss[loss=3.131, simple_loss=0.4667, pruned_loss=6.641, codebook_loss=28.97, over 7142.00 frames.], tot_loss[loss=3.309, simple_loss=0.5264, pruned_loss=6.597, codebook_loss=30.46, over 1392645.66 frames.], batch size: 23, lr: 2.98e-03
+2022-05-27 14:08:52,262 INFO [train.py:823] (2/4) Epoch 1, batch 850, loss[loss=2.923, simple_loss=0.3837, pruned_loss=6.43, codebook_loss=27.31, over 7028.00 frames.], tot_loss[loss=3.264, simple_loss=0.5138, pruned_loss=6.598, codebook_loss=30.07, over 1400094.73 frames.], batch size: 16, lr: 2.98e-03
+2022-05-27 14:09:32,235 INFO [train.py:823] (2/4) Epoch 1, batch 900, loss[loss=2.995, simple_loss=0.3936, pruned_loss=6.517, codebook_loss=27.98, over 7298.00 frames.], tot_loss[loss=3.218, simple_loss=0.4995, pruned_loss=6.596, codebook_loss=29.68, over 1403223.21 frames.], batch size: 17, lr: 2.98e-03
+2022-05-27 14:10:24,072 INFO [train.py:823] (2/4) Epoch 2, batch 0, loss[loss=2.964, simple_loss=0.4553, pruned_loss=6.744, codebook_loss=27.36, over 7096.00 frames.], tot_loss[loss=2.964, simple_loss=0.4553, pruned_loss=6.744, codebook_loss=27.36, over 7096.00 frames.], batch size: 19, lr: 2.95e-03
+2022-05-27 14:11:04,138 INFO [train.py:823] (2/4) Epoch 2, batch 50, loss[loss=3.082, simple_loss=0.4851, pruned_loss=6.704, codebook_loss=28.4, over 7375.00 frames.], tot_loss[loss=3, simple_loss=0.4298, pruned_loss=6.577, codebook_loss=27.85, over 322100.00 frames.], batch size: 21, lr: 2.95e-03
+2022-05-27 14:11:44,113 INFO [train.py:823] (2/4) Epoch 2, batch 100, loss[loss=2.923, simple_loss=0.4314, pruned_loss=6.59, codebook_loss=27.07, over 7014.00 frames.], tot_loss[loss=2.985, simple_loss=0.4276, pruned_loss=6.581, codebook_loss=27.71, over 564870.97 frames.], batch size: 26, lr: 2.95e-03
+2022-05-27 14:12:24,103 INFO [train.py:823] (2/4) Epoch 2, batch 150, loss[loss=2.875, simple_loss=0.3537, pruned_loss=6.481, codebook_loss=26.98, over 7297.00 frames.], tot_loss[loss=2.971, simple_loss=0.4247, pruned_loss=6.581, codebook_loss=27.59, over 758264.95 frames.], batch size: 17, lr: 2.94e-03
+2022-05-27 14:13:04,788 INFO [train.py:823] (2/4) Epoch 2, batch 200, loss[loss=2.983, simple_loss=0.4032, pruned_loss=6.415, codebook_loss=27.81, over 7092.00 frames.], tot_loss[loss=2.955, simple_loss=0.4212, pruned_loss=6.581, codebook_loss=27.45, over 906121.55 frames.], batch size: 18, lr: 2.94e-03
+2022-05-27 14:13:44,831 INFO [train.py:823] (2/4) Epoch 2, batch 250, loss[loss=3.029, simple_loss=0.4103, pruned_loss=6.495, codebook_loss=28.24, over 7168.00 frames.], tot_loss[loss=2.942, simple_loss=0.4173, pruned_loss=6.58, codebook_loss=27.33, over 1016975.65 frames.], batch size: 17, lr: 2.94e-03
+2022-05-27 14:14:25,462 INFO [train.py:823] (2/4) Epoch 2, batch 300, loss[loss=2.885, simple_loss=0.3541, pruned_loss=6.45, codebook_loss=27.08, over 7030.00 frames.], tot_loss[loss=2.929, simple_loss=0.4137, pruned_loss=6.582, codebook_loss=27.22, over 1108385.62 frames.], batch size: 16, lr: 2.93e-03
+2022-05-27 14:15:07,006 INFO [train.py:823] (2/4) Epoch 2, batch 350, loss[loss=2.822, simple_loss=0.3812, pruned_loss=6.587, codebook_loss=26.32, over 7137.00 frames.], tot_loss[loss=2.928, simple_loss=0.4122, pruned_loss=6.583, codebook_loss=27.22, over 1175723.80 frames.], batch size: 23, lr: 2.93e-03
+2022-05-27 14:15:51,499 INFO [train.py:823] (2/4) Epoch 2, batch 400, loss[loss=2.859, simple_loss=0.4065, pruned_loss=6.586, codebook_loss=26.56, over 7098.00 frames.], tot_loss[loss=2.918, simple_loss=0.4105, pruned_loss=6.582, codebook_loss=27.13, over 1226632.41 frames.], batch size: 18, lr: 2.93e-03
+2022-05-27 14:16:31,407 INFO [train.py:823] (2/4) Epoch 2, batch 450, loss[loss=2.808, simple_loss=0.4036, pruned_loss=6.655, codebook_loss=26.06, over 7290.00 frames.], tot_loss[loss=2.898, simple_loss=0.4065, pruned_loss=6.583, codebook_loss=26.94, over 1267549.91 frames.], batch size: 21, lr: 2.92e-03
+2022-05-27 14:17:11,907 INFO [train.py:823] (2/4) Epoch 2, batch 500, loss[loss=2.889, simple_loss=0.4396, pruned_loss=6.71, codebook_loss=26.69, over 6883.00 frames.], tot_loss[loss=2.883, simple_loss=0.4043, pruned_loss=6.588, codebook_loss=26.81, over 1303748.04 frames.], batch size: 29, lr: 2.92e-03
+2022-05-27 14:17:51,836 INFO [train.py:823] (2/4) Epoch 2, batch 550, loss[loss=2.849, simple_loss=0.3975, pruned_loss=6.577, codebook_loss=26.5, over 5104.00 frames.], tot_loss[loss=2.876, simple_loss=0.4024, pruned_loss=6.587, codebook_loss=26.75, over 1325316.18 frames.], batch size: 47, lr: 2.92e-03
+2022-05-27 14:18:32,330 INFO [train.py:823] (2/4) Epoch 2, batch 600, loss[loss=2.833, simple_loss=0.452, pruned_loss=6.73, codebook_loss=26.07, over 7273.00 frames.], tot_loss[loss=2.864, simple_loss=0.3997, pruned_loss=6.584, codebook_loss=26.64, over 1341943.69 frames.], batch size: 21, lr: 2.91e-03
+2022-05-27 14:19:12,452 INFO [train.py:823] (2/4) Epoch 2, batch 650, loss[loss=2.72, simple_loss=0.3825, pruned_loss=6.558, codebook_loss=25.29, over 7293.00 frames.], tot_loss[loss=2.846, simple_loss=0.3973, pruned_loss=6.589, codebook_loss=26.48, over 1359775.74 frames.], batch size: 22, lr: 2.91e-03
+2022-05-27 14:19:53,607 INFO [train.py:823] (2/4) Epoch 2, batch 700, loss[loss=2.694, simple_loss=0.333, pruned_loss=6.536, codebook_loss=25.28, over 7426.00 frames.], tot_loss[loss=2.83, simple_loss=0.3931, pruned_loss=6.595, codebook_loss=26.33, over 1375548.09 frames.], batch size: 18, lr: 2.90e-03
+2022-05-27 14:20:34,238 INFO [train.py:823] (2/4) Epoch 2, batch 750, loss[loss=2.842, simple_loss=0.3943, pruned_loss=6.74, codebook_loss=26.45, over 7108.00 frames.], tot_loss[loss=2.81, simple_loss=0.3886, pruned_loss=6.593, codebook_loss=26.15, over 1382393.39 frames.], batch size: 20, lr: 2.90e-03
+2022-05-27 14:21:14,866 INFO [train.py:823] (2/4) Epoch 2, batch 800, loss[loss=3.076, simple_loss=0.4541, pruned_loss=6.647, codebook_loss=28.49, over 5144.00 frames.], tot_loss[loss=2.811, simple_loss=0.3876, pruned_loss=6.597, codebook_loss=26.17, over 1387867.65 frames.], batch size: 48, lr: 2.89e-03
+2022-05-27 14:21:56,041 INFO [train.py:823] (2/4) Epoch 2, batch 850, loss[loss=2.795, simple_loss=0.3904, pruned_loss=6.553, codebook_loss=26, over 7186.00 frames.], tot_loss[loss=2.8, simple_loss=0.3862, pruned_loss=6.602, codebook_loss=26.07, over 1392033.16 frames.], batch size: 20, lr: 2.89e-03
+2022-05-27 14:22:36,176 INFO [train.py:823] (2/4) Epoch 2, batch 900, loss[loss=2.662, simple_loss=0.3415, pruned_loss=6.514, codebook_loss=24.91, over 7305.00 frames.], tot_loss[loss=2.783, simple_loss=0.3839, pruned_loss=6.607, codebook_loss=25.91, over 1396184.10 frames.], batch size: 18, lr: 2.89e-03
+2022-05-27 14:23:30,866 INFO [train.py:823] (2/4) Epoch 3, batch 0, loss[loss=2.636, simple_loss=0.3274, pruned_loss=6.535, codebook_loss=24.72, over 7289.00 frames.], tot_loss[loss=2.636, simple_loss=0.3274, pruned_loss=6.535, codebook_loss=24.72, over 7289.00 frames.], batch size: 17, lr: 2.83e-03
+2022-05-27 14:24:11,237 INFO [train.py:823] (2/4) Epoch 3, batch 50, loss[loss=2.82, simple_loss=0.4092, pruned_loss=6.526, codebook_loss=26.15, over 5017.00 frames.], tot_loss[loss=2.691, simple_loss=0.3625, pruned_loss=6.594, codebook_loss=25.1, over 319459.35 frames.], batch size: 48, lr: 2.82e-03
+2022-05-27 14:24:51,183 INFO [train.py:823] (2/4) Epoch 3, batch 100, loss[loss=2.667, simple_loss=0.4083, pruned_loss=6.814, codebook_loss=24.63, over 6955.00 frames.], tot_loss[loss=2.705, simple_loss=0.3649, pruned_loss=6.586, codebook_loss=25.23, over 565448.70 frames.], batch size: 26, lr: 2.82e-03
+2022-05-27 14:25:31,469 INFO [train.py:823] (2/4) Epoch 3, batch 150, loss[loss=2.705, simple_loss=0.3709, pruned_loss=6.595, codebook_loss=25.2, over 7381.00 frames.], tot_loss[loss=2.698, simple_loss=0.3635, pruned_loss=6.591, codebook_loss=25.17, over 756278.28 frames.], batch size: 20, lr: 2.81e-03
+2022-05-27 14:26:11,605 INFO [train.py:823] (2/4) Epoch 3, batch 200, loss[loss=2.569, simple_loss=0.3301, pruned_loss=6.579, codebook_loss=24.04, over 7114.00 frames.], tot_loss[loss=2.695, simple_loss=0.3623, pruned_loss=6.597, codebook_loss=25.14, over 907447.52 frames.], batch size: 20, lr: 2.81e-03
+2022-05-27 14:26:51,965 INFO [train.py:823] (2/4) Epoch 3, batch 250, loss[loss=2.65, simple_loss=0.3754, pruned_loss=6.678, codebook_loss=24.63, over 6990.00 frames.], tot_loss[loss=2.684, simple_loss=0.361, pruned_loss=6.61, codebook_loss=25.03, over 1025013.50 frames.], batch size: 26, lr: 2.80e-03
+2022-05-27 14:27:31,797 INFO [train.py:823] (2/4) Epoch 3, batch 300, loss[loss=2.558, simple_loss=0.3125, pruned_loss=6.497, codebook_loss=24.02, over 7381.00 frames.], tot_loss[loss=2.681, simple_loss=0.3592, pruned_loss=6.615, codebook_loss=25.02, over 1115420.00 frames.], batch size: 19, lr: 2.80e-03
+2022-05-27 14:28:12,714 INFO [train.py:823] (2/4) Epoch 3, batch 350, loss[loss=2.625, simple_loss=0.3615, pruned_loss=6.673, codebook_loss=24.44, over 7327.00 frames.], tot_loss[loss=2.687, simple_loss=0.3573, pruned_loss=6.614, codebook_loss=25.09, over 1187385.33 frames.], batch size: 23, lr: 2.79e-03
+2022-05-27 14:28:52,454 INFO [train.py:823] (2/4) Epoch 3, batch 400, loss[loss=2.619, simple_loss=0.3369, pruned_loss=6.46, codebook_loss=24.5, over 7295.00 frames.], tot_loss[loss=2.689, simple_loss=0.3595, pruned_loss=6.614, codebook_loss=25.09, over 1240171.60 frames.], batch size: 18, lr: 2.79e-03
+2022-05-27 14:29:32,967 INFO [train.py:823] (2/4) Epoch 3, batch 450, loss[loss=2.62, simple_loss=0.3221, pruned_loss=6.504, codebook_loss=24.59, over 7197.00 frames.], tot_loss[loss=2.69, simple_loss=0.3599, pruned_loss=6.616, codebook_loss=25.1, over 1273494.93 frames.], batch size: 18, lr: 2.78e-03
+2022-05-27 14:30:12,783 INFO [train.py:823] (2/4) Epoch 3, batch 500, loss[loss=2.729, simple_loss=0.3342, pruned_loss=6.56, codebook_loss=25.62, over 7295.00 frames.], tot_loss[loss=2.692, simple_loss=0.3582, pruned_loss=6.616, codebook_loss=25.13, over 1305942.26 frames.], batch size: 18, lr: 2.77e-03
+2022-05-27 14:30:52,963 INFO [train.py:823] (2/4) Epoch 3, batch 550, loss[loss=2.632, simple_loss=0.3914, pruned_loss=6.752, codebook_loss=24.36, over 7184.00 frames.], tot_loss[loss=2.681, simple_loss=0.3576, pruned_loss=6.627, codebook_loss=25.02, over 1334307.28 frames.], batch size: 21, lr: 2.77e-03
+2022-05-27 14:31:32,953 INFO [train.py:823] (2/4) Epoch 3, batch 600, loss[loss=2.643, simple_loss=0.3605, pruned_loss=6.631, codebook_loss=24.63, over 7378.00 frames.], tot_loss[loss=2.674, simple_loss=0.3545, pruned_loss=6.624, codebook_loss=24.97, over 1346996.98 frames.], batch size: 20, lr: 2.76e-03
+2022-05-27 14:32:13,207 INFO [train.py:823] (2/4) Epoch 3, batch 650, loss[loss=2.678, simple_loss=0.3723, pruned_loss=6.636, codebook_loss=24.92, over 4898.00 frames.], tot_loss[loss=2.664, simple_loss=0.354, pruned_loss=6.624, codebook_loss=24.86, over 1364152.75 frames.], batch size: 46, lr: 2.76e-03
+2022-05-27 14:32:52,990 INFO [train.py:823] (2/4) Epoch 3, batch 700, loss[loss=2.603, simple_loss=0.3529, pruned_loss=6.675, codebook_loss=24.27, over 7312.00 frames.], tot_loss[loss=2.661, simple_loss=0.3537, pruned_loss=6.622, codebook_loss=24.84, over 1376208.78 frames.], batch size: 22, lr: 2.75e-03
+2022-05-27 14:33:33,464 INFO [train.py:823] (2/4) Epoch 3, batch 750, loss[loss=2.574, simple_loss=0.3284, pruned_loss=6.633, codebook_loss=24.09, over 7215.00 frames.], tot_loss[loss=2.65, simple_loss=0.3517, pruned_loss=6.621, codebook_loss=24.74, over 1384169.80 frames.], batch size: 19, lr: 2.75e-03
+2022-05-27 14:34:13,283 INFO [train.py:823] (2/4) Epoch 3, batch 800, loss[loss=2.691, simple_loss=0.3862, pruned_loss=6.722, codebook_loss=24.98, over 7415.00 frames.], tot_loss[loss=2.646, simple_loss=0.3522, pruned_loss=6.626, codebook_loss=24.7, over 1394547.08 frames.], batch size: 22, lr: 2.74e-03
+2022-05-27 14:34:53,239 INFO [train.py:823] (2/4) Epoch 3, batch 850, loss[loss=2.485, simple_loss=0.3074, pruned_loss=6.6, codebook_loss=23.31, over 7448.00 frames.], tot_loss[loss=2.648, simple_loss=0.3523, pruned_loss=6.627, codebook_loss=24.72, over 1397461.82 frames.], batch size: 20, lr: 2.74e-03
+2022-05-27 14:35:32,634 INFO [train.py:823] (2/4) Epoch 3, batch 900, loss[loss=2.61, simple_loss=0.3565, pruned_loss=6.702, codebook_loss=24.32, over 4918.00 frames.], tot_loss[loss=2.645, simple_loss=0.3517, pruned_loss=6.635, codebook_loss=24.7, over 1393180.00 frames.], batch size: 47, lr: 2.73e-03
+2022-05-27 14:36:26,063 INFO [train.py:823] (2/4) Epoch 4, batch 0, loss[loss=2.556, simple_loss=0.3347, pruned_loss=6.599, codebook_loss=23.88, over 7112.00 frames.], tot_loss[loss=2.556, simple_loss=0.3347, pruned_loss=6.599, codebook_loss=23.88, over 7112.00 frames.], batch size: 19, lr: 2.64e-03
+2022-05-27 14:37:06,179 INFO [train.py:823] (2/4) Epoch 4, batch 50, loss[loss=2.509, simple_loss=0.2964, pruned_loss=6.548, codebook_loss=23.61, over 7016.00 frames.], tot_loss[loss=2.558, simple_loss=0.327, pruned_loss=6.605, codebook_loss=23.94, over 319918.16 frames.], batch size: 17, lr: 2.64e-03
+2022-05-27 14:37:46,119 INFO [train.py:823] (2/4) Epoch 4, batch 100, loss[loss=2.621, simple_loss=0.3518, pruned_loss=6.721, codebook_loss=24.45, over 7372.00 frames.], tot_loss[loss=2.566, simple_loss=0.3319, pruned_loss=6.63, codebook_loss=24, over 564640.56 frames.], batch size: 21, lr: 2.63e-03
+2022-05-27 14:38:25,744 INFO [train.py:823] (2/4) Epoch 4, batch 150, loss[loss=2.563, simple_loss=0.2943, pruned_loss=6.482, codebook_loss=24.16, over 7171.00 frames.], tot_loss[loss=2.579, simple_loss=0.3336, pruned_loss=6.635, codebook_loss=24.12, over 750406.18 frames.], batch size: 17, lr: 2.63e-03
+2022-05-27 14:39:07,310 INFO [train.py:823] (2/4) Epoch 4, batch 200, loss[loss=2.743, simple_loss=0.3421, pruned_loss=0.9965, codebook_loss=24.72, over 7201.00 frames.], tot_loss[loss=2.674, simple_loss=0.3476, pruned_loss=4.814, codebook_loss=24.11, over 902324.68 frames.], batch size: 18, lr: 2.62e-03
+2022-05-27 14:39:46,947 INFO [train.py:823] (2/4) Epoch 4, batch 250, loss[loss=2.693, simple_loss=0.3381, pruned_loss=0.6326, codebook_loss=24.61, over 7367.00 frames.], tot_loss[loss=2.669, simple_loss=0.3432, pruned_loss=3.569, codebook_loss=24.11, over 1020953.51 frames.], batch size: 21, lr: 2.62e-03
+2022-05-27 14:40:29,617 INFO [train.py:823] (2/4) Epoch 4, batch 300, loss[loss=2.561, simple_loss=0.3269, pruned_loss=0.3821, codebook_loss=23.6, over 7193.00 frames.], tot_loss[loss=2.655, simple_loss=0.3424, pruned_loss=2.709, codebook_loss=24.07, over 1106613.13 frames.], batch size: 20, lr: 2.61e-03
+2022-05-27 14:41:09,206 INFO [train.py:823] (2/4) Epoch 4, batch 350, loss[loss=2.661, simple_loss=0.3976, pruned_loss=0.3423, codebook_loss=24.28, over 7174.00 frames.], tot_loss[loss=2.638, simple_loss=0.3411, pruned_loss=2.08, codebook_loss=24.02, over 1172185.32 frames.], batch size: 23, lr: 2.60e-03
+2022-05-27 14:41:49,199 INFO [train.py:823] (2/4) Epoch 4, batch 400, loss[loss=2.604, simple_loss=0.364, pruned_loss=0.2504, codebook_loss=23.97, over 7171.00 frames.], tot_loss[loss=2.624, simple_loss=0.3384, pruned_loss=1.61, codebook_loss=24, over 1225044.78 frames.], batch size: 25, lr: 2.60e-03
+2022-05-27 14:42:28,859 INFO [train.py:823] (2/4) Epoch 4, batch 450, loss[loss=2.598, simple_loss=0.309, pruned_loss=0.1774, codebook_loss=24.26, over 7156.00 frames.], tot_loss[loss=2.614, simple_loss=0.3378, pruned_loss=1.263, codebook_loss=23.98, over 1267929.38 frames.], batch size: 17, lr: 2.59e-03
+2022-05-27 14:43:08,813 INFO [train.py:823] (2/4) Epoch 4, batch 500, loss[loss=2.594, simple_loss=0.3725, pruned_loss=0.202, codebook_loss=23.87, over 7192.00 frames.], tot_loss[loss=2.606, simple_loss=0.3396, pruned_loss=1.004, codebook_loss=23.96, over 1304391.37 frames.], batch size: 25, lr: 2.59e-03
+2022-05-27 14:43:48,395 INFO [train.py:823] (2/4) Epoch 4, batch 550, loss[loss=2.622, simple_loss=0.3371, pruned_loss=0.1671, codebook_loss=24.36, over 7393.00 frames.], tot_loss[loss=2.594, simple_loss=0.337, pruned_loss=0.8055, codebook_loss=23.91, over 1331861.48 frames.], batch size: 19, lr: 2.58e-03
+2022-05-27 14:44:28,574 INFO [train.py:823] (2/4) Epoch 4, batch 600, loss[loss=2.522, simple_loss=0.3398, pruned_loss=0.1596, codebook_loss=23.36, over 7188.00 frames.], tot_loss[loss=2.581, simple_loss=0.3355, pruned_loss=0.6542, codebook_loss=23.83, over 1354370.38 frames.], batch size: 21, lr: 2.57e-03
+2022-05-27 14:45:08,622 INFO [train.py:823] (2/4) Epoch 4, batch 650, loss[loss=2.589, simple_loss=0.3637, pruned_loss=0.1868, codebook_loss=23.89, over 7366.00 frames.], tot_loss[loss=2.569, simple_loss=0.3341, pruned_loss=0.5385, codebook_loss=23.75, over 1370701.32 frames.], batch size: 20, lr: 2.57e-03
+2022-05-27 14:45:48,465 INFO [train.py:823] (2/4) Epoch 4, batch 700, loss[loss=2.712, simple_loss=0.3694, pruned_loss=0.1964, codebook_loss=25.07, over 4679.00 frames.], tot_loss[loss=2.573, simple_loss=0.336, pruned_loss=0.454, codebook_loss=23.81, over 1376345.87 frames.], batch size: 47, lr: 2.56e-03
+2022-05-27 14:46:28,087 INFO [train.py:823] (2/4) Epoch 4, batch 750, loss[loss=2.534, simple_loss=0.3204, pruned_loss=0.1336, codebook_loss=23.6, over 7100.00 frames.], tot_loss[loss=2.577, simple_loss=0.335, pruned_loss=0.3855, codebook_loss=23.87, over 1384779.64 frames.], batch size: 19, lr: 2.56e-03
+2022-05-27 14:47:08,126 INFO [train.py:823] (2/4) Epoch 4, batch 800, loss[loss=2.489, simple_loss=0.2888, pruned_loss=0.1011, codebook_loss=23.34, over 7026.00 frames.], tot_loss[loss=2.572, simple_loss=0.3333, pruned_loss=0.3319, codebook_loss=23.85, over 1386654.31 frames.], batch size: 17, lr: 2.55e-03
+2022-05-27 14:47:47,720 INFO [train.py:823] (2/4) Epoch 4, batch 850, loss[loss=2.555, simple_loss=0.3281, pruned_loss=0.1307, codebook_loss=23.78, over 7308.00 frames.], tot_loss[loss=2.569, simple_loss=0.3318, pruned_loss=0.2882, codebook_loss=23.84, over 1392688.76 frames.], batch size: 22, lr: 2.54e-03
+2022-05-27 14:48:27,905 INFO [train.py:823] (2/4) Epoch 4, batch 900, loss[loss=2.568, simple_loss=0.3114, pruned_loss=0.1233, codebook_loss=24, over 7196.00 frames.], tot_loss[loss=2.571, simple_loss=0.3318, pruned_loss=0.2567, codebook_loss=23.87, over 1389173.62 frames.], batch size: 18, lr: 2.54e-03
+2022-05-27 14:49:21,904 INFO [train.py:823] (2/4) Epoch 5, batch 0, loss[loss=2.387, simple_loss=0.3079, pruned_loss=0.1153, codebook_loss=22.22, over 7347.00 frames.], tot_loss[loss=2.387, simple_loss=0.3079, pruned_loss=0.1153, codebook_loss=22.22, over 7347.00 frames.], batch size: 23, lr: 2.44e-03
+2022-05-27 14:50:02,122 INFO [train.py:823] (2/4) Epoch 5, batch 50, loss[loss=2.438, simple_loss=0.3311, pruned_loss=0.1138, codebook_loss=22.61, over 6981.00 frames.], tot_loss[loss=2.505, simple_loss=0.323, pruned_loss=0.129, codebook_loss=23.31, over 325777.98 frames.], batch size: 26, lr: 2.44e-03
+2022-05-27 14:50:41,829 INFO [train.py:823] (2/4) Epoch 5, batch 100, loss[loss=2.517, simple_loss=0.3335, pruned_loss=0.1293, codebook_loss=23.37, over 7107.00 frames.], tot_loss[loss=2.496, simple_loss=0.3209, pruned_loss=0.125, codebook_loss=23.23, over 570770.75 frames.], batch size: 20, lr: 2.43e-03
+2022-05-27 14:51:21,914 INFO [train.py:823] (2/4) Epoch 5, batch 150, loss[loss=2.456, simple_loss=0.3096, pruned_loss=0.1205, codebook_loss=22.89, over 7377.00 frames.], tot_loss[loss=2.516, simple_loss=0.3198, pruned_loss=0.1251, codebook_loss=23.43, over 758418.80 frames.], batch size: 20, lr: 2.42e-03
+2022-05-27 14:52:01,338 INFO [train.py:823] (2/4) Epoch 5, batch 200, loss[loss=2.555, simple_loss=0.3641, pruned_loss=0.1544, codebook_loss=23.58, over 7182.00 frames.], tot_loss[loss=2.519, simple_loss=0.3211, pruned_loss=0.1259, codebook_loss=23.46, over 904979.58 frames.], batch size: 22, lr: 2.42e-03
+2022-05-27 14:52:41,364 INFO [train.py:823] (2/4) Epoch 5, batch 250, loss[loss=2.607, simple_loss=0.3508, pruned_loss=0.1597, codebook_loss=24.16, over 5195.00 frames.], tot_loss[loss=2.515, simple_loss=0.3204, pruned_loss=0.1249, codebook_loss=23.42, over 1013869.42 frames.], batch size: 46, lr: 2.41e-03
+2022-05-27 14:53:20,948 INFO [train.py:823] (2/4) Epoch 5, batch 300, loss[loss=2.542, simple_loss=0.36, pruned_loss=0.1664, codebook_loss=23.45, over 7159.00 frames.], tot_loss[loss=2.501, simple_loss=0.3188, pruned_loss=0.122, codebook_loss=23.3, over 1105046.93 frames.], batch size: 23, lr: 2.41e-03
+2022-05-27 14:54:00,919 INFO [train.py:823] (2/4) Epoch 5, batch 350, loss[loss=2.388, simple_loss=0.3175, pruned_loss=0.09861, codebook_loss=22.2, over 7230.00 frames.], tot_loss[loss=2.502, simple_loss=0.3193, pruned_loss=0.1216, codebook_loss=23.31, over 1174667.34 frames.], batch size: 24, lr: 2.40e-03
+2022-05-27 14:54:40,905 INFO [train.py:823] (2/4) Epoch 5, batch 400, loss[loss=2.518, simple_loss=0.277, pruned_loss=0.08754, codebook_loss=23.71, over 7440.00 frames.], tot_loss[loss=2.5, simple_loss=0.3187, pruned_loss=0.1202, codebook_loss=23.28, over 1234218.16 frames.], batch size: 18, lr: 2.39e-03
+2022-05-27 14:55:20,832 INFO [train.py:823] (2/4) Epoch 5, batch 450, loss[loss=2.495, simple_loss=0.348, pruned_loss=0.133, codebook_loss=23.08, over 7049.00 frames.], tot_loss[loss=2.494, simple_loss=0.3184, pruned_loss=0.1192, codebook_loss=23.23, over 1269117.39 frames.], batch size: 26, lr: 2.39e-03
+2022-05-27 14:56:00,505 INFO [train.py:823] (2/4) Epoch 5, batch 500, loss[loss=2.441, simple_loss=0.304, pruned_loss=0.09025, codebook_loss=22.8, over 7198.00 frames.], tot_loss[loss=2.492, simple_loss=0.3188, pruned_loss=0.118, codebook_loss=23.2, over 1304777.07 frames.], batch size: 19, lr: 2.38e-03
+2022-05-27 14:56:40,384 INFO [train.py:823] (2/4) Epoch 5, batch 550, loss[loss=2.583, simple_loss=0.3579, pruned_loss=0.1483, codebook_loss=23.89, over 6920.00 frames.], tot_loss[loss=2.49, simple_loss=0.3196, pruned_loss=0.1184, codebook_loss=23.18, over 1330533.32 frames.], batch size: 29, lr: 2.38e-03
+2022-05-27 14:57:20,185 INFO [train.py:823] (2/4) Epoch 5, batch 600, loss[loss=2.44, simple_loss=0.3153, pruned_loss=0.105, codebook_loss=22.72, over 6707.00 frames.], tot_loss[loss=2.488, simple_loss=0.3187, pruned_loss=0.1174, codebook_loss=23.17, over 1348757.80 frames.], batch size: 34, lr: 2.37e-03
+2022-05-27 14:58:00,333 INFO [train.py:823] (2/4) Epoch 5, batch 650, loss[loss=2.403, simple_loss=0.3167, pruned_loss=0.1042, codebook_loss=22.34, over 7283.00 frames.], tot_loss[loss=2.486, simple_loss=0.3178, pruned_loss=0.1158, codebook_loss=23.16, over 1364094.35 frames.], batch size: 21, lr: 2.37e-03
+2022-05-27 14:58:39,929 INFO [train.py:823] (2/4) Epoch 5, batch 700, loss[loss=2.499, simple_loss=0.3324, pruned_loss=0.1349, codebook_loss=23.19, over 6978.00 frames.], tot_loss[loss=2.482, simple_loss=0.3171, pruned_loss=0.1146, codebook_loss=23.12, over 1373657.59 frames.], batch size: 26, lr: 2.36e-03
+2022-05-27 14:59:19,728 INFO [train.py:823] (2/4) Epoch 5, batch 750, loss[loss=2.484, simple_loss=0.3419, pruned_loss=0.1199, codebook_loss=23.01, over 7162.00 frames.], tot_loss[loss=2.48, simple_loss=0.3177, pruned_loss=0.1141, codebook_loss=23.1, over 1381397.83 frames.], batch size: 23, lr: 2.35e-03
+2022-05-27 14:59:59,657 INFO [train.py:823] (2/4) Epoch 5, batch 800, loss[loss=2.499, simple_loss=0.3458, pruned_loss=0.1198, codebook_loss=23.14, over 4933.00 frames.], tot_loss[loss=2.474, simple_loss=0.3168, pruned_loss=0.1127, codebook_loss=23.05, over 1391605.94 frames.], batch size: 47, lr: 2.35e-03
+2022-05-27 15:00:39,937 INFO [train.py:823] (2/4) Epoch 5, batch 850, loss[loss=2.38, simple_loss=0.291, pruned_loss=0.09708, codebook_loss=22.25, over 7150.00 frames.], tot_loss[loss=2.466, simple_loss=0.3155, pruned_loss=0.1108, codebook_loss=22.97, over 1398602.69 frames.], batch size: 17, lr: 2.34e-03
+2022-05-27 15:01:19,750 INFO [train.py:823] (2/4) Epoch 5, batch 900, loss[loss=2.59, simple_loss=0.3539, pruned_loss=0.1392, codebook_loss=23.99, over 6875.00 frames.], tot_loss[loss=2.464, simple_loss=0.3159, pruned_loss=0.1105, codebook_loss=22.95, over 1399814.47 frames.], batch size: 29, lr: 2.34e-03
+2022-05-27 15:02:14,637 INFO [train.py:823] (2/4) Epoch 6, batch 0, loss[loss=2.53, simple_loss=0.3359, pruned_loss=0.111, codebook_loss=23.51, over 7169.00 frames.], tot_loss[loss=2.53, simple_loss=0.3359, pruned_loss=0.111, codebook_loss=23.51, over 7169.00 frames.], batch size: 22, lr: 2.24e-03
+2022-05-27 15:02:54,281 INFO [train.py:823] (2/4) Epoch 6, batch 50, loss[loss=2.424, simple_loss=0.3042, pruned_loss=0.07873, codebook_loss=22.64, over 7182.00 frames.], tot_loss[loss=2.426, simple_loss=0.308, pruned_loss=0.09942, codebook_loss=22.62, over 319668.76 frames.], batch size: 21, lr: 2.23e-03
+2022-05-27 15:03:34,993 INFO [train.py:823] (2/4) Epoch 6, batch 100, loss[loss=2.332, simple_loss=0.3057, pruned_loss=0.09539, codebook_loss=21.69, over 7242.00 frames.], tot_loss[loss=2.42, simple_loss=0.3023, pruned_loss=0.09678, codebook_loss=22.6, over 566815.89 frames.], batch size: 24, lr: 2.23e-03
+2022-05-27 15:04:14,716 INFO [train.py:823] (2/4) Epoch 6, batch 150, loss[loss=2.361, simple_loss=0.3183, pruned_loss=0.0983, codebook_loss=21.92, over 7291.00 frames.], tot_loss[loss=2.427, simple_loss=0.3057, pruned_loss=0.09796, codebook_loss=22.65, over 756522.81 frames.], batch size: 19, lr: 2.22e-03
+2022-05-27 15:04:56,263 INFO [train.py:823] (2/4) Epoch 6, batch 200, loss[loss=2.391, simple_loss=0.2991, pruned_loss=0.07624, codebook_loss=22.34, over 7216.00 frames.], tot_loss[loss=2.429, simple_loss=0.3058, pruned_loss=0.09814, codebook_loss=22.67, over 902146.81 frames.], batch size: 25, lr: 2.22e-03
+2022-05-27 15:05:38,518 INFO [train.py:823] (2/4) Epoch 6, batch 250, loss[loss=2.522, simple_loss=0.3021, pruned_loss=0.08247, codebook_loss=23.63, over 6592.00 frames.], tot_loss[loss=2.433, simple_loss=0.3071, pruned_loss=0.0986, codebook_loss=22.69, over 1018227.17 frames.], batch size: 34, lr: 2.21e-03
+2022-05-27 15:06:18,608 INFO [train.py:823] (2/4) Epoch 6, batch 300, loss[loss=2.413, simple_loss=0.2952, pruned_loss=0.08357, codebook_loss=22.57, over 7192.00 frames.], tot_loss[loss=2.432, simple_loss=0.3078, pruned_loss=0.09853, codebook_loss=22.69, over 1108157.38 frames.], batch size: 20, lr: 2.21e-03
+2022-05-27 15:06:58,744 INFO [train.py:823] (2/4) Epoch 6, batch 350, loss[loss=2.371, simple_loss=0.2848, pruned_loss=0.09192, codebook_loss=22.19, over 7090.00 frames.], tot_loss[loss=2.431, simple_loss=0.3074, pruned_loss=0.09857, codebook_loss=22.67, over 1179998.29 frames.], batch size: 18, lr: 2.20e-03
+2022-05-27 15:07:39,162 INFO [train.py:823] (2/4) Epoch 6, batch 400, loss[loss=2.315, simple_loss=0.2965, pruned_loss=0.0794, codebook_loss=21.59, over 7183.00 frames.], tot_loss[loss=2.421, simple_loss=0.3057, pruned_loss=0.09707, codebook_loss=22.59, over 1235396.85 frames.], batch size: 22, lr: 2.19e-03
+2022-05-27 15:08:18,969 INFO [train.py:823] (2/4) Epoch 6, batch 450, loss[loss=2.364, simple_loss=0.2945, pruned_loss=0.0842, codebook_loss=22.08, over 6354.00 frames.], tot_loss[loss=2.426, simple_loss=0.3071, pruned_loss=0.09821, codebook_loss=22.62, over 1268187.94 frames.], batch size: 34, lr: 2.19e-03
+2022-05-27 15:08:59,144 INFO [train.py:823] (2/4) Epoch 6, batch 500, loss[loss=2.386, simple_loss=0.3082, pruned_loss=0.1036, codebook_loss=22.22, over 7149.00 frames.], tot_loss[loss=2.435, simple_loss=0.3096, pruned_loss=0.1002, codebook_loss=22.7, over 1298598.74 frames.], batch size: 23, lr: 2.18e-03
+2022-05-27 15:09:39,080 INFO [train.py:823] (2/4) Epoch 6, batch 550, loss[loss=2.258, simple_loss=0.2762, pruned_loss=0.0732, codebook_loss=21.12, over 7096.00 frames.], tot_loss[loss=2.431, simple_loss=0.3084, pruned_loss=0.09874, codebook_loss=22.67, over 1325623.31 frames.], batch size: 18, lr: 2.18e-03
+2022-05-27 15:10:19,158 INFO [train.py:823] (2/4) Epoch 6, batch 600, loss[loss=2.328, simple_loss=0.2712, pruned_loss=0.06941, codebook_loss=21.85, over 7102.00 frames.], tot_loss[loss=2.431, simple_loss=0.307, pruned_loss=0.09803, codebook_loss=22.68, over 1343726.79 frames.], batch size: 18, lr: 2.17e-03
+2022-05-27 15:10:58,939 INFO [train.py:823] (2/4) Epoch 6, batch 650, loss[loss=2.509, simple_loss=0.2987, pruned_loss=0.09894, codebook_loss=23.5, over 7390.00 frames.], tot_loss[loss=2.427, simple_loss=0.305, pruned_loss=0.09624, codebook_loss=22.65, over 1360163.13 frames.], batch size: 19, lr: 2.17e-03
+2022-05-27 15:11:39,181 INFO [train.py:823] (2/4) Epoch 6, batch 700, loss[loss=2.386, simple_loss=0.2931, pruned_loss=0.08781, codebook_loss=22.31, over 7201.00 frames.], tot_loss[loss=2.421, simple_loss=0.3047, pruned_loss=0.0951, codebook_loss=22.6, over 1375225.59 frames.], batch size: 19, lr: 2.16e-03
+2022-05-27 15:12:18,880 INFO [train.py:823] (2/4) Epoch 6, batch 750, loss[loss=2.36, simple_loss=0.2826, pruned_loss=0.08936, codebook_loss=22.1, over 7091.00 frames.], tot_loss[loss=2.423, simple_loss=0.3051, pruned_loss=0.09546, codebook_loss=22.61, over 1382504.40 frames.], batch size: 19, lr: 2.16e-03
+2022-05-27 15:12:59,161 INFO [train.py:823] (2/4) Epoch 6, batch 800, loss[loss=2.377, simple_loss=0.2677, pruned_loss=0.07877, codebook_loss=22.35, over 7023.00 frames.], tot_loss[loss=2.42, simple_loss=0.3044, pruned_loss=0.09495, codebook_loss=22.59, over 1388145.10 frames.], batch size: 16, lr: 2.15e-03
+2022-05-27 15:13:39,111 INFO [train.py:823] (2/4) Epoch 6, batch 850, loss[loss=2.412, simple_loss=0.2834, pruned_loss=0.0891, codebook_loss=22.61, over 6782.00 frames.], tot_loss[loss=2.43, simple_loss=0.3052, pruned_loss=0.09622, codebook_loss=22.67, over 1391565.28 frames.], batch size: 15, lr: 2.15e-03
+2022-05-27 15:14:19,235 INFO [train.py:823] (2/4) Epoch 6, batch 900, loss[loss=2.277, simple_loss=0.2498, pruned_loss=0.05593, codebook_loss=21.47, over 7291.00 frames.], tot_loss[loss=2.424, simple_loss=0.3039, pruned_loss=0.09478, codebook_loss=22.62, over 1395855.95 frames.], batch size: 17, lr: 2.14e-03
+2022-05-27 15:15:12,729 INFO [train.py:823] (2/4) Epoch 7, batch 0, loss[loss=2.289, simple_loss=0.2734, pruned_loss=0.06217, codebook_loss=21.46, over 7105.00 frames.], tot_loss[loss=2.289, simple_loss=0.2734, pruned_loss=0.06217, codebook_loss=21.46, over 7105.00 frames.], batch size: 19, lr: 2.05e-03
+2022-05-27 15:15:52,757 INFO [train.py:823] (2/4) Epoch 7, batch 50, loss[loss=2.362, simple_loss=0.2806, pruned_loss=0.07907, codebook_loss=22.14, over 7257.00 frames.], tot_loss[loss=2.398, simple_loss=0.2937, pruned_loss=0.08634, codebook_loss=22.42, over 323121.85 frames.], batch size: 16, lr: 2.04e-03
+2022-05-27 15:16:32,358 INFO [train.py:823] (2/4) Epoch 7, batch 100, loss[loss=2.333, simple_loss=0.2889, pruned_loss=0.07633, codebook_loss=21.8, over 7114.00 frames.], tot_loss[loss=2.377, simple_loss=0.2922, pruned_loss=0.08415, codebook_loss=22.22, over 562513.12 frames.], batch size: 20, lr: 2.04e-03
+2022-05-27 15:17:12,541 INFO [train.py:823] (2/4) Epoch 7, batch 150, loss[loss=2.406, simple_loss=0.3031, pruned_loss=0.0932, codebook_loss=22.45, over 7370.00 frames.], tot_loss[loss=2.389, simple_loss=0.2964, pruned_loss=0.08645, codebook_loss=22.32, over 753308.38 frames.], batch size: 21, lr: 2.03e-03
+2022-05-27 15:17:52,335 INFO [train.py:823] (2/4) Epoch 7, batch 200, loss[loss=2.571, simple_loss=0.3048, pruned_loss=0.09756, codebook_loss=24.09, over 7021.00 frames.], tot_loss[loss=2.387, simple_loss=0.2961, pruned_loss=0.08616, codebook_loss=22.31, over 904138.85 frames.], batch size: 26, lr: 2.03e-03
+2022-05-27 15:18:32,529 INFO [train.py:823] (2/4) Epoch 7, batch 250, loss[loss=2.507, simple_loss=0.3004, pruned_loss=0.08851, codebook_loss=23.48, over 7304.00 frames.], tot_loss[loss=2.38, simple_loss=0.2953, pruned_loss=0.08552, codebook_loss=22.24, over 1019578.68 frames.], batch size: 22, lr: 2.02e-03
+2022-05-27 15:19:12,256 INFO [train.py:823] (2/4) Epoch 7, batch 300, loss[loss=2.352, simple_loss=0.2591, pruned_loss=0.07477, codebook_loss=22.15, over 7155.00 frames.], tot_loss[loss=2.378, simple_loss=0.2964, pruned_loss=0.08551, codebook_loss=22.21, over 1108496.36 frames.], batch size: 17, lr: 2.02e-03
+2022-05-27 15:19:52,537 INFO [train.py:823] (2/4) Epoch 7, batch 350, loss[loss=2.388, simple_loss=0.2965, pruned_loss=0.07903, codebook_loss=21.61, over 7298.00 frames.], tot_loss[loss=2.417, simple_loss=0.2991, pruned_loss=0.08923, codebook_loss=22.34, over 1176644.06 frames.], batch size: 19, lr: 2.01e-03
+2022-05-27 15:20:32,257 INFO [train.py:823] (2/4) Epoch 7, batch 400, loss[loss=2.562, simple_loss=0.342, pruned_loss=0.1266, codebook_loss=22.64, over 7338.00 frames.], tot_loss[loss=2.44, simple_loss=0.3014, pruned_loss=0.09119, codebook_loss=22.4, over 1231171.24 frames.], batch size: 23, lr: 2.01e-03
+2022-05-27 15:21:12,317 INFO [train.py:823] (2/4) Epoch 7, batch 450, loss[loss=2.384, simple_loss=0.2915, pruned_loss=0.07046, codebook_loss=21.68, over 7159.00 frames.], tot_loss[loss=2.446, simple_loss=0.3022, pruned_loss=0.09105, codebook_loss=22.35, over 1268736.64 frames.], batch size: 22, lr: 2.00e-03
+2022-05-27 15:21:52,023 INFO [train.py:823] (2/4) Epoch 7, batch 500, loss[loss=2.73, simple_loss=0.316, pruned_loss=0.08818, codebook_loss=24.84, over 7000.00 frames.], tot_loss[loss=2.452, simple_loss=0.3022, pruned_loss=0.0901, codebook_loss=22.35, over 1302670.44 frames.], batch size: 26, lr: 2.00e-03
+2022-05-27 15:22:32,340 INFO [train.py:823] (2/4) Epoch 7, batch 550, loss[loss=2.409, simple_loss=0.306, pruned_loss=0.08944, codebook_loss=21.67, over 6615.00 frames.], tot_loss[loss=2.453, simple_loss=0.3009, pruned_loss=0.08864, codebook_loss=22.33, over 1326578.84 frames.], batch size: 34, lr: 1.99e-03
+2022-05-27 15:23:12,061 INFO [train.py:823] (2/4) Epoch 7, batch 600, loss[loss=2.409, simple_loss=0.3127, pruned_loss=0.07969, codebook_loss=21.73, over 7370.00 frames.], tot_loss[loss=2.462, simple_loss=0.3008, pruned_loss=0.08779, codebook_loss=22.38, over 1344739.70 frames.], batch size: 21, lr: 1.99e-03
+2022-05-27 15:23:52,232 INFO [train.py:823] (2/4) Epoch 7, batch 650, loss[loss=2.513, simple_loss=0.3319, pruned_loss=0.1059, codebook_loss=22.41, over 7114.00 frames.], tot_loss[loss=2.466, simple_loss=0.3009, pruned_loss=0.08775, codebook_loss=22.38, over 1361989.13 frames.], batch size: 20, lr: 1.98e-03
+2022-05-27 15:24:32,093 INFO [train.py:823] (2/4) Epoch 7, batch 700, loss[loss=2.408, simple_loss=0.3008, pruned_loss=0.07754, codebook_loss=21.8, over 7090.00 frames.], tot_loss[loss=2.467, simple_loss=0.3012, pruned_loss=0.08742, codebook_loss=22.37, over 1371569.08 frames.], batch size: 18, lr: 1.98e-03
+2022-05-27 15:25:12,123 INFO [train.py:823] (2/4) Epoch 7, batch 750, loss[loss=2.393, simple_loss=0.3005, pruned_loss=0.0838, codebook_loss=21.59, over 6974.00 frames.], tot_loss[loss=2.466, simple_loss=0.3001, pruned_loss=0.08641, codebook_loss=22.36, over 1378844.82 frames.], batch size: 26, lr: 1.97e-03
+2022-05-27 15:25:51,513 INFO [train.py:823] (2/4) Epoch 7, batch 800, loss[loss=2.402, simple_loss=0.3014, pruned_loss=0.07541, codebook_loss=21.76, over 7195.00 frames.], tot_loss[loss=2.467, simple_loss=0.3014, pruned_loss=0.08655, codebook_loss=22.35, over 1388951.86 frames.], batch size: 19, lr: 1.97e-03
+2022-05-27 15:26:31,113 INFO [train.py:823] (2/4) Epoch 7, batch 850, loss[loss=2.493, simple_loss=0.3273, pruned_loss=0.09636, codebook_loss=22.33, over 7379.00 frames.], tot_loss[loss=2.465, simple_loss=0.3023, pruned_loss=0.08594, codebook_loss=22.32, over 1389762.04 frames.], batch size: 21, lr: 1.97e-03
+2022-05-27 15:27:11,912 INFO [train.py:823] (2/4) Epoch 7, batch 900, loss[loss=2.469, simple_loss=0.3298, pruned_loss=0.104, codebook_loss=22, over 7031.00 frames.], tot_loss[loss=2.459, simple_loss=0.3023, pruned_loss=0.08548, codebook_loss=22.25, over 1391207.29 frames.], batch size: 29, lr: 1.96e-03
+2022-05-27 15:28:02,620 INFO [train.py:823] (2/4) Epoch 8, batch 0, loss[loss=2.358, simple_loss=0.2848, pruned_loss=0.06273, codebook_loss=21.53, over 7424.00 frames.], tot_loss[loss=2.358, simple_loss=0.2848, pruned_loss=0.06273, codebook_loss=21.53, over 7424.00 frames.], batch size: 22, lr: 1.88e-03
+2022-05-27 15:28:42,271 INFO [train.py:823] (2/4) Epoch 8, batch 50, loss[loss=2.389, simple_loss=0.2973, pruned_loss=0.07067, codebook_loss=21.7, over 7234.00 frames.], tot_loss[loss=2.388, simple_loss=0.2942, pruned_loss=0.07446, codebook_loss=21.67, over 320948.90 frames.], batch size: 24, lr: 1.87e-03
+2022-05-27 15:29:23,690 INFO [train.py:823] (2/4) Epoch 8, batch 100, loss[loss=2.641, simple_loss=0.271, pruned_loss=0.08763, codebook_loss=24.18, over 7430.00 frames.], tot_loss[loss=2.425, simple_loss=0.3003, pruned_loss=0.07998, codebook_loss=21.95, over 565085.77 frames.], batch size: 18, lr: 1.87e-03
+2022-05-27 15:30:05,849 INFO [train.py:823] (2/4) Epoch 8, batch 150, loss[loss=2.454, simple_loss=0.296, pruned_loss=0.06919, codebook_loss=22.37, over 7272.00 frames.], tot_loss[loss=2.422, simple_loss=0.2961, pruned_loss=0.07759, codebook_loss=21.97, over 753769.36 frames.], batch size: 20, lr: 1.86e-03
+2022-05-27 15:30:45,994 INFO [train.py:823] (2/4) Epoch 8, batch 200, loss[loss=2.344, simple_loss=0.2433, pruned_loss=0.0533, codebook_loss=21.69, over 6997.00 frames.], tot_loss[loss=2.42, simple_loss=0.2957, pruned_loss=0.07737, codebook_loss=21.95, over 898683.11 frames.], batch size: 16, lr: 1.86e-03
+2022-05-27 15:31:25,746 INFO [train.py:823] (2/4) Epoch 8, batch 250, loss[loss=2.393, simple_loss=0.289, pruned_loss=0.07101, codebook_loss=21.77, over 7144.00 frames.], tot_loss[loss=2.423, simple_loss=0.295, pruned_loss=0.07738, codebook_loss=21.99, over 1012843.27 frames.], batch size: 23, lr: 1.85e-03
+2022-05-27 15:32:06,058 INFO [train.py:823] (2/4) Epoch 8, batch 300, loss[loss=2.255, simple_loss=0.2666, pruned_loss=0.05774, codebook_loss=20.64, over 7394.00 frames.], tot_loss[loss=2.417, simple_loss=0.2946, pruned_loss=0.07678, codebook_loss=21.92, over 1106064.18 frames.], batch size: 19, lr: 1.85e-03
+2022-05-27 15:32:45,536 INFO [train.py:823] (2/4) Epoch 8, batch 350, loss[loss=2.336, simple_loss=0.2675, pruned_loss=0.06155, codebook_loss=21.41, over 7037.00 frames.], tot_loss[loss=2.418, simple_loss=0.2939, pruned_loss=0.07594, codebook_loss=21.95, over 1165882.75 frames.], batch size: 16, lr: 1.85e-03
+2022-05-27 15:33:25,397 INFO [train.py:823] (2/4) Epoch 8, batch 400, loss[loss=2.426, simple_loss=0.3114, pruned_loss=0.08331, codebook_loss=21.87, over 7134.00 frames.], tot_loss[loss=2.427, simple_loss=0.2958, pruned_loss=0.07665, codebook_loss=22.02, over 1220963.65 frames.], batch size: 22, lr: 1.84e-03
+2022-05-27 15:34:05,055 INFO [train.py:823] (2/4) Epoch 8, batch 450, loss[loss=2.853, simple_loss=0.3169, pruned_loss=0.09061, codebook_loss=26.04, over 6564.00 frames.], tot_loss[loss=2.431, simple_loss=0.2971, pruned_loss=0.07705, codebook_loss=22.05, over 1264634.54 frames.], batch size: 34, lr: 1.84e-03
+2022-05-27 15:34:45,227 INFO [train.py:823] (2/4) Epoch 8, batch 500, loss[loss=2.413, simple_loss=0.2804, pruned_loss=0.084, codebook_loss=21.89, over 7297.00 frames.], tot_loss[loss=2.432, simple_loss=0.2969, pruned_loss=0.07736, codebook_loss=22.06, over 1301526.42 frames.], batch size: 17, lr: 1.83e-03
+2022-05-27 15:35:24,769 INFO [train.py:823] (2/4) Epoch 8, batch 550, loss[loss=2.793, simple_loss=0.3138, pruned_loss=0.09527, codebook_loss=25.41, over 7165.00 frames.], tot_loss[loss=2.432, simple_loss=0.2976, pruned_loss=0.07703, codebook_loss=22.06, over 1325931.04 frames.], batch size: 22, lr: 1.83e-03
+2022-05-27 15:36:04,724 INFO [train.py:823] (2/4) Epoch 8, batch 600, loss[loss=2.49, simple_loss=0.2729, pruned_loss=0.06246, codebook_loss=22.91, over 7030.00 frames.], tot_loss[loss=2.439, simple_loss=0.2978, pruned_loss=0.07721, codebook_loss=22.13, over 1344354.35 frames.], batch size: 17, lr: 1.82e-03
+2022-05-27 15:36:44,524 INFO [train.py:823] (2/4) Epoch 8, batch 650, loss[loss=2.433, simple_loss=0.3243, pruned_loss=0.09059, codebook_loss=21.81, over 6960.00 frames.], tot_loss[loss=2.431, simple_loss=0.2978, pruned_loss=0.07671, codebook_loss=22.05, over 1362258.09 frames.], batch size: 26, lr: 1.82e-03
+2022-05-27 15:37:24,989 INFO [train.py:823] (2/4) Epoch 8, batch 700, loss[loss=2.7, simple_loss=0.3024, pruned_loss=0.09946, codebook_loss=24.5, over 7291.00 frames.], tot_loss[loss=2.418, simple_loss=0.2967, pruned_loss=0.07541, codebook_loss=21.95, over 1379898.94 frames.], batch size: 19, lr: 1.82e-03
+2022-05-27 15:38:04,507 INFO [train.py:823] (2/4) Epoch 8, batch 750, loss[loss=2.448, simple_loss=0.2789, pruned_loss=0.06688, codebook_loss=22.42, over 7097.00 frames.], tot_loss[loss=2.417, simple_loss=0.2964, pruned_loss=0.07513, codebook_loss=21.93, over 1387250.88 frames.], batch size: 18, lr: 1.81e-03
+2022-05-27 15:38:44,416 INFO [train.py:823] (2/4) Epoch 8, batch 800, loss[loss=2.507, simple_loss=0.3145, pruned_loss=0.0927, codebook_loss=22.57, over 5368.00 frames.], tot_loss[loss=2.414, simple_loss=0.2957, pruned_loss=0.07465, codebook_loss=21.91, over 1388112.29 frames.], batch size: 46, lr: 1.81e-03
+2022-05-27 15:39:24,088 INFO [train.py:823] (2/4) Epoch 8, batch 850, loss[loss=2.502, simple_loss=0.3219, pruned_loss=0.08744, codebook_loss=22.54, over 7194.00 frames.], tot_loss[loss=2.419, simple_loss=0.2953, pruned_loss=0.07511, codebook_loss=21.96, over 1390668.10 frames.], batch size: 20, lr: 1.80e-03
+2022-05-27 15:40:04,004 INFO [train.py:823] (2/4) Epoch 8, batch 900, loss[loss=2.32, simple_loss=0.2807, pruned_loss=0.06303, codebook_loss=21.16, over 7099.00 frames.], tot_loss[loss=2.432, simple_loss=0.2965, pruned_loss=0.07629, codebook_loss=22.08, over 1394773.75 frames.], batch size: 18, lr: 1.80e-03
+2022-05-27 15:40:54,929 INFO [train.py:823] (2/4) Epoch 9, batch 0, loss[loss=2.318, simple_loss=0.3189, pruned_loss=0.06999, codebook_loss=20.88, over 7187.00 frames.], tot_loss[loss=2.318, simple_loss=0.3189, pruned_loss=0.06999, codebook_loss=20.88, over 7187.00 frames.], batch size: 21, lr: 1.72e-03
+2022-05-27 15:41:35,079 INFO [train.py:823] (2/4) Epoch 9, batch 50, loss[loss=2.242, simple_loss=0.2613, pruned_loss=0.05132, codebook_loss=20.6, over 7392.00 frames.], tot_loss[loss=2.42, simple_loss=0.2949, pruned_loss=0.07506, codebook_loss=21.98, over 319610.06 frames.], batch size: 19, lr: 1.72e-03
+2022-05-27 15:42:14,606 INFO [train.py:823] (2/4) Epoch 9, batch 100, loss[loss=2.229, simple_loss=0.2535, pruned_loss=0.04753, codebook_loss=20.55, over 7293.00 frames.], tot_loss[loss=2.375, simple_loss=0.2911, pruned_loss=0.06946, codebook_loss=21.6, over 562899.83 frames.], batch size: 19, lr: 1.71e-03
+2022-05-27 15:42:54,769 INFO [train.py:823] (2/4) Epoch 9, batch 150, loss[loss=2.511, simple_loss=0.2939, pruned_loss=0.06128, codebook_loss=23.03, over 7100.00 frames.], tot_loss[loss=2.382, simple_loss=0.2919, pruned_loss=0.06995, codebook_loss=21.66, over 752579.04 frames.], batch size: 19, lr: 1.71e-03
+2022-05-27 15:43:34,131 INFO [train.py:823] (2/4) Epoch 9, batch 200, loss[loss=2.432, simple_loss=0.3132, pruned_loss=0.08322, codebook_loss=21.92, over 7282.00 frames.], tot_loss[loss=2.385, simple_loss=0.2924, pruned_loss=0.06975, codebook_loss=21.69, over 896160.55 frames.], batch size: 20, lr: 1.71e-03
+2022-05-27 15:44:14,343 INFO [train.py:823] (2/4) Epoch 9, batch 250, loss[loss=2.317, simple_loss=0.2944, pruned_loss=0.06345, codebook_loss=21.06, over 7193.00 frames.], tot_loss[loss=2.374, simple_loss=0.2911, pruned_loss=0.06898, codebook_loss=21.59, over 1011967.83 frames.], batch size: 20, lr: 1.70e-03
+2022-05-27 15:44:53,897 INFO [train.py:823] (2/4) Epoch 9, batch 300, loss[loss=2.3, simple_loss=0.2821, pruned_loss=0.0717, codebook_loss=20.88, over 7189.00 frames.], tot_loss[loss=2.375, simple_loss=0.2905, pruned_loss=0.06887, codebook_loss=21.61, over 1103271.84 frames.], batch size: 18, lr: 1.70e-03
+2022-05-27 15:45:34,255 INFO [train.py:823] (2/4) Epoch 9, batch 350, loss[loss=2.381, simple_loss=0.2422, pruned_loss=0.05152, codebook_loss=22.08, over 7288.00 frames.], tot_loss[loss=2.373, simple_loss=0.2897, pruned_loss=0.06859, codebook_loss=21.6, over 1173047.07 frames.], batch size: 17, lr: 1.70e-03
+2022-05-27 15:46:14,408 INFO [train.py:823] (2/4) Epoch 9, batch 400, loss[loss=2.302, simple_loss=0.2957, pruned_loss=0.06306, codebook_loss=20.91, over 7307.00 frames.], tot_loss[loss=2.372, simple_loss=0.2885, pruned_loss=0.06818, codebook_loss=21.6, over 1228981.97 frames.], batch size: 22, lr: 1.69e-03
+2022-05-27 15:46:57,536 INFO [train.py:823] (2/4) Epoch 9, batch 450, loss[loss=2.44, simple_loss=0.3035, pruned_loss=0.08479, codebook_loss=22.03, over 7187.00 frames.], tot_loss[loss=2.38, simple_loss=0.2908, pruned_loss=0.06895, codebook_loss=21.66, over 1270122.84 frames.], batch size: 19, lr: 1.69e-03
+2022-05-27 15:47:37,355 INFO [train.py:823] (2/4) Epoch 9, batch 500, loss[loss=2.367, simple_loss=0.2944, pruned_loss=0.0766, codebook_loss=21.43, over 7241.00 frames.], tot_loss[loss=2.378, simple_loss=0.2913, pruned_loss=0.06895, codebook_loss=21.63, over 1304026.77 frames.], batch size: 24, lr: 1.68e-03
+2022-05-27 15:48:17,618 INFO [train.py:823] (2/4) Epoch 9, batch 550, loss[loss=2.638, simple_loss=0.3051, pruned_loss=0.08076, codebook_loss=24.05, over 7187.00 frames.], tot_loss[loss=2.381, simple_loss=0.2917, pruned_loss=0.06953, codebook_loss=21.66, over 1333424.16 frames.], batch size: 19, lr: 1.68e-03
+2022-05-27 15:48:57,600 INFO [train.py:823] (2/4) Epoch 9, batch 600, loss[loss=2.783, simple_loss=0.2875, pruned_loss=0.08053, codebook_loss=25.58, over 7151.00 frames.], tot_loss[loss=2.388, simple_loss=0.2918, pruned_loss=0.06994, codebook_loss=21.72, over 1354622.41 frames.], batch size: 17, lr: 1.68e-03
+2022-05-27 15:49:37,633 INFO [train.py:823] (2/4) Epoch 9, batch 650, loss[loss=2.28, simple_loss=0.2951, pruned_loss=0.05707, codebook_loss=20.76, over 6942.00 frames.], tot_loss[loss=2.384, simple_loss=0.2909, pruned_loss=0.06964, codebook_loss=21.69, over 1368316.57 frames.], batch size: 29, lr: 1.67e-03
+2022-05-27 15:50:17,589 INFO [train.py:823] (2/4) Epoch 9, batch 700, loss[loss=2.397, simple_loss=0.2911, pruned_loss=0.06305, codebook_loss=21.89, over 7292.00 frames.], tot_loss[loss=2.383, simple_loss=0.2904, pruned_loss=0.06882, codebook_loss=21.69, over 1376692.58 frames.], batch size: 22, lr: 1.67e-03
+2022-05-27 15:50:59,093 INFO [train.py:823] (2/4) Epoch 9, batch 750, loss[loss=2.295, simple_loss=0.2653, pruned_loss=0.05028, codebook_loss=21.12, over 7197.00 frames.], tot_loss[loss=2.386, simple_loss=0.2918, pruned_loss=0.06974, codebook_loss=21.7, over 1387275.32 frames.], batch size: 18, lr: 1.67e-03
+2022-05-27 15:51:38,641 INFO [train.py:823] (2/4) Epoch 9, batch 800, loss[loss=2.315, simple_loss=0.2905, pruned_loss=0.06791, codebook_loss=21.02, over 7097.00 frames.], tot_loss[loss=2.386, simple_loss=0.2926, pruned_loss=0.06966, codebook_loss=21.7, over 1388666.32 frames.], batch size: 19, lr: 1.66e-03
+2022-05-27 15:52:18,621 INFO [train.py:823] (2/4) Epoch 9, batch 850, loss[loss=2.364, simple_loss=0.2752, pruned_loss=0.06839, codebook_loss=21.58, over 6816.00 frames.], tot_loss[loss=2.374, simple_loss=0.2914, pruned_loss=0.0684, codebook_loss=21.6, over 1397585.60 frames.], batch size: 15, lr: 1.66e-03
+2022-05-27 15:52:58,161 INFO [train.py:823] (2/4) Epoch 9, batch 900, loss[loss=2.577, simple_loss=0.2922, pruned_loss=0.1032, codebook_loss=23.27, over 6791.00 frames.], tot_loss[loss=2.381, simple_loss=0.2914, pruned_loss=0.06912, codebook_loss=21.66, over 1399049.05 frames.], batch size: 15, lr: 1.65e-03
+2022-05-27 15:53:54,914 INFO [train.py:823] (2/4) Epoch 10, batch 0, loss[loss=2.244, simple_loss=0.2613, pruned_loss=0.04079, codebook_loss=20.73, over 7108.00 frames.], tot_loss[loss=2.244, simple_loss=0.2613, pruned_loss=0.04079, codebook_loss=20.73, over 7108.00 frames.], batch size: 20, lr: 1.59e-03
+2022-05-27 15:54:34,631 INFO [train.py:823] (2/4) Epoch 10, batch 50, loss[loss=2.512, simple_loss=0.2637, pruned_loss=0.06123, codebook_loss=23.19, over 7030.00 frames.], tot_loss[loss=2.361, simple_loss=0.2875, pruned_loss=0.06448, codebook_loss=21.52, over 318926.07 frames.], batch size: 17, lr: 1.58e-03
+2022-05-27 15:55:15,569 INFO [train.py:823] (2/4) Epoch 10, batch 100, loss[loss=2.239, simple_loss=0.2662, pruned_loss=0.05494, codebook_loss=20.51, over 7391.00 frames.], tot_loss[loss=2.347, simple_loss=0.2852, pruned_loss=0.06322, codebook_loss=21.41, over 559343.44 frames.], batch size: 20, lr: 1.58e-03
+2022-05-27 15:55:54,951 INFO [train.py:823] (2/4) Epoch 10, batch 150, loss[loss=2.566, simple_loss=0.3205, pruned_loss=0.09558, codebook_loss=23.1, over 7288.00 frames.], tot_loss[loss=2.338, simple_loss=0.2867, pruned_loss=0.06298, codebook_loss=21.32, over 749687.64 frames.], batch size: 20, lr: 1.58e-03
+2022-05-27 15:56:35,132 INFO [train.py:823] (2/4) Epoch 10, batch 200, loss[loss=2.357, simple_loss=0.285, pruned_loss=0.06877, codebook_loss=21.45, over 7281.00 frames.], tot_loss[loss=2.337, simple_loss=0.2839, pruned_loss=0.06224, codebook_loss=21.33, over 901912.47 frames.], batch size: 21, lr: 1.57e-03
+2022-05-27 15:57:14,776 INFO [train.py:823] (2/4) Epoch 10, batch 250, loss[loss=2.218, simple_loss=0.2851, pruned_loss=0.04595, codebook_loss=20.3, over 7371.00 frames.], tot_loss[loss=2.341, simple_loss=0.2849, pruned_loss=0.06251, codebook_loss=21.36, over 1017878.55 frames.], batch size: 21, lr: 1.57e-03
+2022-05-27 15:57:54,568 INFO [train.py:823] (2/4) Epoch 10, batch 300, loss[loss=2.326, simple_loss=0.2996, pruned_loss=0.07481, codebook_loss=21.01, over 7012.00 frames.], tot_loss[loss=2.347, simple_loss=0.2859, pruned_loss=0.06391, codebook_loss=21.4, over 1108642.46 frames.], batch size: 26, lr: 1.57e-03
+2022-05-27 15:58:34,249 INFO [train.py:823] (2/4) Epoch 10, batch 350, loss[loss=2.472, simple_loss=0.2845, pruned_loss=0.08298, codebook_loss=22.47, over 7211.00 frames.], tot_loss[loss=2.343, simple_loss=0.2866, pruned_loss=0.06364, codebook_loss=21.36, over 1175171.86 frames.], batch size: 16, lr: 1.56e-03
+2022-05-27 15:59:14,374 INFO [train.py:823] (2/4) Epoch 10, batch 400, loss[loss=2.31, simple_loss=0.2838, pruned_loss=0.06699, codebook_loss=21.01, over 7104.00 frames.], tot_loss[loss=2.355, simple_loss=0.2884, pruned_loss=0.06529, codebook_loss=21.46, over 1224898.10 frames.], batch size: 19, lr: 1.56e-03
+2022-05-27 15:59:54,088 INFO [train.py:823] (2/4) Epoch 10, batch 450, loss[loss=2.364, simple_loss=0.2996, pruned_loss=0.07047, codebook_loss=21.43, over 7280.00 frames.], tot_loss[loss=2.357, simple_loss=0.2881, pruned_loss=0.06537, codebook_loss=21.48, over 1265972.38 frames.], batch size: 20, lr: 1.56e-03
+2022-05-27 16:00:34,194 INFO [train.py:823] (2/4) Epoch 10, batch 500, loss[loss=2.336, simple_loss=0.2866, pruned_loss=0.0598, codebook_loss=21.33, over 7279.00 frames.], tot_loss[loss=2.355, simple_loss=0.2872, pruned_loss=0.06486, codebook_loss=21.47, over 1298733.51 frames.], batch size: 20, lr: 1.55e-03
+2022-05-27 16:01:14,171 INFO [train.py:823] (2/4) Epoch 10, batch 550, loss[loss=2.243, simple_loss=0.2505, pruned_loss=0.04668, codebook_loss=20.71, over 7092.00 frames.], tot_loss[loss=2.351, simple_loss=0.2857, pruned_loss=0.06362, codebook_loss=21.45, over 1328885.31 frames.], batch size: 18, lr: 1.55e-03
+2022-05-27 16:01:54,261 INFO [train.py:823] (2/4) Epoch 10, batch 600, loss[loss=2.288, simple_loss=0.2708, pruned_loss=0.05857, codebook_loss=20.94, over 7306.00 frames.], tot_loss[loss=2.351, simple_loss=0.2858, pruned_loss=0.06347, codebook_loss=21.45, over 1353717.65 frames.], batch size: 19, lr: 1.55e-03
+2022-05-27 16:02:33,980 INFO [train.py:823] (2/4) Epoch 10, batch 650, loss[loss=2.315, simple_loss=0.3114, pruned_loss=0.06699, codebook_loss=20.93, over 7182.00 frames.], tot_loss[loss=2.345, simple_loss=0.284, pruned_loss=0.0629, codebook_loss=21.4, over 1371380.27 frames.], batch size: 21, lr: 1.54e-03
+2022-05-27 16:03:14,285 INFO [train.py:823] (2/4) Epoch 10, batch 700, loss[loss=2.764, simple_loss=0.2883, pruned_loss=0.07809, codebook_loss=25.42, over 7017.00 frames.], tot_loss[loss=2.346, simple_loss=0.2841, pruned_loss=0.06275, codebook_loss=21.41, over 1384932.27 frames.], batch size: 16, lr: 1.54e-03
+2022-05-27 16:03:53,948 INFO [train.py:823] (2/4) Epoch 10, batch 750, loss[loss=2.25, simple_loss=0.2658, pruned_loss=0.06088, codebook_loss=20.56, over 7190.00 frames.], tot_loss[loss=2.352, simple_loss=0.2853, pruned_loss=0.06387, codebook_loss=21.45, over 1392979.94 frames.], batch size: 18, lr: 1.54e-03
+2022-05-27 16:04:34,058 INFO [train.py:823] (2/4) Epoch 10, batch 800, loss[loss=2.271, simple_loss=0.3005, pruned_loss=0.05383, codebook_loss=20.67, over 7205.00 frames.], tot_loss[loss=2.347, simple_loss=0.2865, pruned_loss=0.06363, codebook_loss=21.41, over 1398465.85 frames.], batch size: 25, lr: 1.53e-03
+2022-05-27 16:05:13,991 INFO [train.py:823] (2/4) Epoch 10, batch 850, loss[loss=2.278, simple_loss=0.2879, pruned_loss=0.05849, codebook_loss=20.75, over 7182.00 frames.], tot_loss[loss=2.346, simple_loss=0.2863, pruned_loss=0.06322, codebook_loss=21.39, over 1405256.04 frames.], batch size: 22, lr: 1.53e-03
+2022-05-27 16:05:54,085 INFO [train.py:823] (2/4) Epoch 10, batch 900, loss[loss=2.563, simple_loss=0.2787, pruned_loss=0.06817, codebook_loss=23.56, over 7252.00 frames.], tot_loss[loss=2.351, simple_loss=0.2857, pruned_loss=0.06349, codebook_loss=21.44, over 1405334.13 frames.], batch size: 16, lr: 1.53e-03
+2022-05-27 16:06:46,053 INFO [train.py:823] (2/4) Epoch 11, batch 0, loss[loss=2.58, simple_loss=0.3291, pruned_loss=0.07241, codebook_loss=23.43, over 7108.00 frames.], tot_loss[loss=2.58, simple_loss=0.3291, pruned_loss=0.07241, codebook_loss=23.43, over 7108.00 frames.], batch size: 19, lr: 1.47e-03
+2022-05-27 16:07:26,141 INFO [train.py:823] (2/4) Epoch 11, batch 50, loss[loss=2.301, simple_loss=0.2712, pruned_loss=0.05711, codebook_loss=21.09, over 6523.00 frames.], tot_loss[loss=2.324, simple_loss=0.284, pruned_loss=0.0591, codebook_loss=21.23, over 323773.50 frames.], batch size: 34, lr: 1.47e-03
+2022-05-27 16:08:06,016 INFO [train.py:823] (2/4) Epoch 11, batch 100, loss[loss=2.332, simple_loss=0.2594, pruned_loss=0.05356, codebook_loss=21.49, over 7160.00 frames.], tot_loss[loss=2.315, simple_loss=0.2793, pruned_loss=0.05758, codebook_loss=21.17, over 569845.91 frames.], batch size: 17, lr: 1.46e-03
+2022-05-27 16:08:46,155 INFO [train.py:823] (2/4) Epoch 11, batch 150, loss[loss=2.269, simple_loss=0.2957, pruned_loss=0.06729, codebook_loss=20.54, over 7240.00 frames.], tot_loss[loss=2.325, simple_loss=0.2809, pruned_loss=0.05868, codebook_loss=21.26, over 760079.39 frames.], batch size: 24, lr: 1.46e-03
+2022-05-27 16:09:25,522 INFO [train.py:823] (2/4) Epoch 11, batch 200, loss[loss=2.273, simple_loss=0.28, pruned_loss=0.05511, codebook_loss=20.78, over 7100.00 frames.], tot_loss[loss=2.327, simple_loss=0.2828, pruned_loss=0.05992, codebook_loss=21.26, over 900402.06 frames.], batch size: 19, lr: 1.46e-03
+2022-05-27 16:10:05,748 INFO [train.py:823] (2/4) Epoch 11, batch 250, loss[loss=2.383, simple_loss=0.2942, pruned_loss=0.06933, codebook_loss=21.66, over 7082.00 frames.], tot_loss[loss=2.325, simple_loss=0.2812, pruned_loss=0.05886, codebook_loss=21.25, over 1013642.05 frames.], batch size: 18, lr: 1.45e-03
+2022-05-27 16:10:45,568 INFO [train.py:823] (2/4) Epoch 11, batch 300, loss[loss=2.361, simple_loss=0.2914, pruned_loss=0.06662, codebook_loss=21.49, over 7182.00 frames.], tot_loss[loss=2.323, simple_loss=0.2801, pruned_loss=0.05831, codebook_loss=21.25, over 1104703.88 frames.], batch size: 25, lr: 1.45e-03
+2022-05-27 16:11:25,760 INFO [train.py:823] (2/4) Epoch 11, batch 350, loss[loss=2.25, simple_loss=0.2882, pruned_loss=0.06005, codebook_loss=20.46, over 7194.00 frames.], tot_loss[loss=2.321, simple_loss=0.2797, pruned_loss=0.0583, codebook_loss=21.23, over 1176270.16 frames.], batch size: 25, lr: 1.45e-03
+2022-05-27 16:12:05,519 INFO [train.py:823] (2/4) Epoch 11, batch 400, loss[loss=2.239, simple_loss=0.3087, pruned_loss=0.05515, codebook_loss=20.3, over 7112.00 frames.], tot_loss[loss=2.319, simple_loss=0.2798, pruned_loss=0.05813, codebook_loss=21.21, over 1231092.30 frames.], batch size: 19, lr: 1.44e-03
+2022-05-27 16:12:45,575 INFO [train.py:823] (2/4) Epoch 11, batch 450, loss[loss=2.299, simple_loss=0.2895, pruned_loss=0.05882, codebook_loss=20.95, over 7303.00 frames.], tot_loss[loss=2.312, simple_loss=0.2798, pruned_loss=0.05796, codebook_loss=21.14, over 1269946.50 frames.], batch size: 22, lr: 1.44e-03
+2022-05-27 16:13:25,304 INFO [train.py:823] (2/4) Epoch 11, batch 500, loss[loss=2.203, simple_loss=0.2747, pruned_loss=0.04988, codebook_loss=20.16, over 6580.00 frames.], tot_loss[loss=2.312, simple_loss=0.2806, pruned_loss=0.05852, codebook_loss=21.14, over 1303685.48 frames.], batch size: 34, lr: 1.44e-03
+2022-05-27 16:14:05,257 INFO [train.py:823] (2/4) Epoch 11, batch 550, loss[loss=2.54, simple_loss=0.291, pruned_loss=0.06962, codebook_loss=23.25, over 7427.00 frames.], tot_loss[loss=2.321, simple_loss=0.2825, pruned_loss=0.05959, codebook_loss=21.2, over 1332329.18 frames.], batch size: 22, lr: 1.44e-03
+2022-05-27 16:14:46,356 INFO [train.py:823] (2/4) Epoch 11, batch 600, loss[loss=2.214, simple_loss=0.2545, pruned_loss=0.04091, codebook_loss=20.45, over 7382.00 frames.], tot_loss[loss=2.322, simple_loss=0.2817, pruned_loss=0.05948, codebook_loss=21.22, over 1350982.97 frames.], batch size: 19, lr: 1.43e-03
+2022-05-27 16:15:26,709 INFO [train.py:823] (2/4) Epoch 11, batch 650, loss[loss=2.337, simple_loss=0.271, pruned_loss=0.06768, codebook_loss=21.34, over 7291.00 frames.], tot_loss[loss=2.316, simple_loss=0.2808, pruned_loss=0.0588, codebook_loss=21.17, over 1368264.86 frames.], batch size: 18, lr: 1.43e-03
+2022-05-27 16:16:06,585 INFO [train.py:823] (2/4) Epoch 11, batch 700, loss[loss=2.436, simple_loss=0.2896, pruned_loss=0.08223, codebook_loss=22.09, over 7172.00 frames.], tot_loss[loss=2.313, simple_loss=0.2811, pruned_loss=0.05888, codebook_loss=21.13, over 1382501.83 frames.], batch size: 17, lr: 1.43e-03
+2022-05-27 16:16:46,848 INFO [train.py:823] (2/4) Epoch 11, batch 750, loss[loss=2.226, simple_loss=0.234, pruned_loss=0.04473, codebook_loss=20.65, over 7298.00 frames.], tot_loss[loss=2.316, simple_loss=0.28, pruned_loss=0.0591, codebook_loss=21.17, over 1392246.24 frames.], batch size: 17, lr: 1.42e-03
+2022-05-27 16:17:26,664 INFO [train.py:823] (2/4) Epoch 11, batch 800, loss[loss=2.403, simple_loss=0.2636, pruned_loss=0.04238, codebook_loss=22.29, over 7198.00 frames.], tot_loss[loss=2.319, simple_loss=0.2808, pruned_loss=0.05927, codebook_loss=21.2, over 1397163.59 frames.], batch size: 19, lr: 1.42e-03
+2022-05-27 16:18:08,296 INFO [train.py:823] (2/4) Epoch 11, batch 850, loss[loss=2.332, simple_loss=0.3106, pruned_loss=0.07145, codebook_loss=21.05, over 7111.00 frames.], tot_loss[loss=2.319, simple_loss=0.2809, pruned_loss=0.05918, codebook_loss=21.19, over 1399342.56 frames.], batch size: 20, lr: 1.42e-03
+2022-05-27 16:18:49,110 INFO [train.py:823] (2/4) Epoch 11, batch 900, loss[loss=2.226, simple_loss=0.2386, pruned_loss=0.04161, codebook_loss=20.65, over 7224.00 frames.], tot_loss[loss=2.312, simple_loss=0.2815, pruned_loss=0.05908, codebook_loss=21.12, over 1399206.09 frames.], batch size: 16, lr: 1.42e-03
+2022-05-27 16:19:44,424 INFO [train.py:823] (2/4) Epoch 12, batch 0, loss[loss=2.262, simple_loss=0.2647, pruned_loss=0.05256, codebook_loss=20.77, over 7281.00 frames.], tot_loss[loss=2.262, simple_loss=0.2647, pruned_loss=0.05256, codebook_loss=20.77, over 7281.00 frames.], batch size: 17, lr: 1.36e-03
+2022-05-27 16:20:24,313 INFO [train.py:823] (2/4) Epoch 12, batch 50, loss[loss=2.252, simple_loss=0.2935, pruned_loss=0.05765, codebook_loss=20.48, over 7252.00 frames.], tot_loss[loss=2.319, simple_loss=0.2778, pruned_loss=0.05749, codebook_loss=21.22, over 318075.90 frames.], batch size: 24, lr: 1.36e-03
+2022-05-27 16:21:04,296 INFO [train.py:823] (2/4) Epoch 12, batch 100, loss[loss=2.503, simple_loss=0.2675, pruned_loss=0.05388, codebook_loss=23.15, over 7164.00 frames.], tot_loss[loss=2.301, simple_loss=0.2788, pruned_loss=0.05706, codebook_loss=21.05, over 561951.77 frames.], batch size: 23, lr: 1.36e-03
+2022-05-27 16:21:44,036 INFO [train.py:823] (2/4) Epoch 12, batch 150, loss[loss=2.219, simple_loss=0.2606, pruned_loss=0.04333, codebook_loss=20.46, over 7274.00 frames.], tot_loss[loss=2.301, simple_loss=0.2782, pruned_loss=0.05631, codebook_loss=21.06, over 753048.03 frames.], batch size: 20, lr: 1.36e-03
+2022-05-27 16:22:24,283 INFO [train.py:823] (2/4) Epoch 12, batch 200, loss[loss=2.389, simple_loss=0.2595, pruned_loss=0.05121, codebook_loss=22.08, over 6761.00 frames.], tot_loss[loss=2.299, simple_loss=0.2782, pruned_loss=0.0564, codebook_loss=21.04, over 899374.89 frames.], batch size: 15, lr: 1.35e-03
+2022-05-27 16:23:03,805 INFO [train.py:823] (2/4) Epoch 12, batch 250, loss[loss=2.198, simple_loss=0.2811, pruned_loss=0.0435, codebook_loss=20.14, over 6973.00 frames.], tot_loss[loss=2.301, simple_loss=0.2776, pruned_loss=0.05637, codebook_loss=21.06, over 1016531.95 frames.], batch size: 26, lr: 1.35e-03
+2022-05-27 16:23:43,705 INFO [train.py:823] (2/4) Epoch 12, batch 300, loss[loss=2.199, simple_loss=0.2474, pruned_loss=0.03398, codebook_loss=20.41, over 7192.00 frames.], tot_loss[loss=2.299, simple_loss=0.2784, pruned_loss=0.05634, codebook_loss=21.03, over 1103425.29 frames.], batch size: 19, lr: 1.35e-03
+2022-05-27 16:24:23,582 INFO [train.py:823] (2/4) Epoch 12, batch 350, loss[loss=2.269, simple_loss=0.287, pruned_loss=0.05839, codebook_loss=20.67, over 7341.00 frames.], tot_loss[loss=2.293, simple_loss=0.2776, pruned_loss=0.0552, codebook_loss=20.99, over 1176717.09 frames.], batch size: 23, lr: 1.35e-03
+2022-05-27 16:25:03,604 INFO [train.py:823] (2/4) Epoch 12, batch 400, loss[loss=2.286, simple_loss=0.2812, pruned_loss=0.05157, codebook_loss=20.94, over 6937.00 frames.], tot_loss[loss=2.289, simple_loss=0.2771, pruned_loss=0.05469, codebook_loss=20.96, over 1231014.68 frames.], batch size: 29, lr: 1.34e-03
+2022-05-27 16:25:43,356 INFO [train.py:823] (2/4) Epoch 12, batch 450, loss[loss=2.815, simple_loss=0.2912, pruned_loss=0.07272, codebook_loss=25.97, over 7383.00 frames.], tot_loss[loss=2.286, simple_loss=0.2768, pruned_loss=0.05437, codebook_loss=20.93, over 1273502.70 frames.], batch size: 20, lr: 1.34e-03
+2022-05-27 16:26:23,672 INFO [train.py:823] (2/4) Epoch 12, batch 500, loss[loss=2.308, simple_loss=0.2809, pruned_loss=0.06861, codebook_loss=20.99, over 7298.00 frames.], tot_loss[loss=2.29, simple_loss=0.2771, pruned_loss=0.05536, codebook_loss=20.96, over 1310997.93 frames.], batch size: 20, lr: 1.34e-03
+2022-05-27 16:27:03,418 INFO [train.py:823] (2/4) Epoch 12, batch 550, loss[loss=2.401, simple_loss=0.255, pruned_loss=0.05957, codebook_loss=22.14, over 7032.00 frames.], tot_loss[loss=2.291, simple_loss=0.2775, pruned_loss=0.05603, codebook_loss=20.96, over 1338971.45 frames.], batch size: 17, lr: 1.34e-03
+2022-05-27 16:27:43,504 INFO [train.py:823] (2/4) Epoch 12, batch 600, loss[loss=2.227, simple_loss=0.2648, pruned_loss=0.05326, codebook_loss=20.41, over 6827.00 frames.], tot_loss[loss=2.287, simple_loss=0.2758, pruned_loss=0.055, codebook_loss=20.94, over 1359037.68 frames.], batch size: 15, lr: 1.33e-03
+2022-05-27 16:28:23,521 INFO [train.py:823] (2/4) Epoch 12, batch 650, loss[loss=2.175, simple_loss=0.2626, pruned_loss=0.03725, codebook_loss=20.06, over 7281.00 frames.], tot_loss[loss=2.288, simple_loss=0.2762, pruned_loss=0.05502, codebook_loss=20.95, over 1371423.39 frames.], batch size: 21, lr: 1.33e-03
+2022-05-27 16:29:04,024 INFO [train.py:823] (2/4) Epoch 12, batch 700, loss[loss=2.201, simple_loss=0.2765, pruned_loss=0.04039, codebook_loss=20.22, over 7273.00 frames.], tot_loss[loss=2.296, simple_loss=0.2771, pruned_loss=0.05591, codebook_loss=21.01, over 1383033.48 frames.], batch size: 20, lr: 1.33e-03
+2022-05-27 16:29:43,707 INFO [train.py:823] (2/4) Epoch 12, batch 750, loss[loss=2.209, simple_loss=0.313, pruned_loss=0.06098, codebook_loss=19.92, over 7304.00 frames.], tot_loss[loss=2.29, simple_loss=0.2771, pruned_loss=0.05533, codebook_loss=20.96, over 1389390.94 frames.], batch size: 22, lr: 1.33e-03
+2022-05-27 16:30:23,751 INFO [train.py:823] (2/4) Epoch 12, batch 800, loss[loss=2.255, simple_loss=0.2837, pruned_loss=0.05329, codebook_loss=20.6, over 7310.00 frames.], tot_loss[loss=2.291, simple_loss=0.2768, pruned_loss=0.05516, codebook_loss=20.97, over 1396278.02 frames.], batch size: 22, lr: 1.32e-03
+2022-05-27 16:31:03,405 INFO [train.py:823] (2/4) Epoch 12, batch 850, loss[loss=2.189, simple_loss=0.2541, pruned_loss=0.04342, codebook_loss=20.18, over 7199.00 frames.], tot_loss[loss=2.286, simple_loss=0.277, pruned_loss=0.05518, codebook_loss=20.93, over 1401322.12 frames.], batch size: 18, lr: 1.32e-03
+2022-05-27 16:31:43,306 INFO [train.py:823] (2/4) Epoch 12, batch 900, loss[loss=2.233, simple_loss=0.2797, pruned_loss=0.05769, codebook_loss=20.36, over 7084.00 frames.], tot_loss[loss=2.295, simple_loss=0.2773, pruned_loss=0.05631, codebook_loss=21, over 1397574.44 frames.], batch size: 19, lr: 1.32e-03
+2022-05-27 16:32:36,861 INFO [train.py:823] (2/4) Epoch 13, batch 0, loss[loss=2.275, simple_loss=0.3075, pruned_loss=0.06809, codebook_loss=20.53, over 7176.00 frames.], tot_loss[loss=2.275, simple_loss=0.3075, pruned_loss=0.06809, codebook_loss=20.53, over 7176.00 frames.], batch size: 22, lr: 1.27e-03
+2022-05-27 16:33:17,127 INFO [train.py:823] (2/4) Epoch 13, batch 50, loss[loss=2.18, simple_loss=0.2472, pruned_loss=0.03928, codebook_loss=20.17, over 7284.00 frames.], tot_loss[loss=2.261, simple_loss=0.2714, pruned_loss=0.05126, codebook_loss=20.74, over 317807.92 frames.], batch size: 19, lr: 1.27e-03
+2022-05-27 16:33:56,716 INFO [train.py:823] (2/4) Epoch 13, batch 100, loss[loss=2.208, simple_loss=0.257, pruned_loss=0.04363, codebook_loss=20.35, over 7298.00 frames.], tot_loss[loss=2.266, simple_loss=0.274, pruned_loss=0.05239, codebook_loss=20.77, over 561830.71 frames.], batch size: 18, lr: 1.27e-03
+2022-05-27 16:34:36,940 INFO [train.py:823] (2/4) Epoch 13, batch 150, loss[loss=2.323, simple_loss=0.279, pruned_loss=0.06098, codebook_loss=21.22, over 7391.00 frames.], tot_loss[loss=2.268, simple_loss=0.2728, pruned_loss=0.05168, codebook_loss=20.79, over 751829.12 frames.], batch size: 19, lr: 1.26e-03
+2022-05-27 16:35:16,793 INFO [train.py:823] (2/4) Epoch 13, batch 200, loss[loss=2.293, simple_loss=0.2682, pruned_loss=0.06272, codebook_loss=20.96, over 7025.00 frames.], tot_loss[loss=2.268, simple_loss=0.2736, pruned_loss=0.05234, codebook_loss=20.79, over 903218.45 frames.], batch size: 17, lr: 1.26e-03
+2022-05-27 16:35:56,991 INFO [train.py:823] (2/4) Epoch 13, batch 250, loss[loss=2.363, simple_loss=0.2832, pruned_loss=0.04889, codebook_loss=21.73, over 7165.00 frames.], tot_loss[loss=2.261, simple_loss=0.273, pruned_loss=0.05189, codebook_loss=20.73, over 1016486.04 frames.], batch size: 22, lr: 1.26e-03
+2022-05-27 16:36:37,048 INFO [train.py:823] (2/4) Epoch 13, batch 300, loss[loss=2.178, simple_loss=0.2222, pruned_loss=0.03589, codebook_loss=20.31, over 7301.00 frames.], tot_loss[loss=2.257, simple_loss=0.2722, pruned_loss=0.051, codebook_loss=20.7, over 1109945.28 frames.], batch size: 17, lr: 1.26e-03
+2022-05-27 16:37:16,854 INFO [train.py:823] (2/4) Epoch 13, batch 350, loss[loss=2.252, simple_loss=0.2682, pruned_loss=0.04186, codebook_loss=20.76, over 6348.00 frames.], tot_loss[loss=2.248, simple_loss=0.2723, pruned_loss=0.05058, codebook_loss=20.61, over 1175724.70 frames.], batch size: 34, lr: 1.26e-03
+2022-05-27 16:37:56,789 INFO [train.py:823] (2/4) Epoch 13, batch 400, loss[loss=2.256, simple_loss=0.2752, pruned_loss=0.04928, codebook_loss=20.69, over 6981.00 frames.], tot_loss[loss=2.252, simple_loss=0.273, pruned_loss=0.05116, codebook_loss=20.64, over 1229121.95 frames.], batch size: 26, lr: 1.25e-03
+2022-05-27 16:38:36,634 INFO [train.py:823] (2/4) Epoch 13, batch 450, loss[loss=2.296, simple_loss=0.2687, pruned_loss=0.04472, codebook_loss=21.17, over 7037.00 frames.], tot_loss[loss=2.254, simple_loss=0.273, pruned_loss=0.05146, codebook_loss=20.66, over 1267551.15 frames.], batch size: 29, lr: 1.25e-03
+2022-05-27 16:39:17,550 INFO [train.py:823] (2/4) Epoch 13, batch 500, loss[loss=2.466, simple_loss=0.3006, pruned_loss=0.06728, codebook_loss=22.48, over 6822.00 frames.], tot_loss[loss=2.262, simple_loss=0.2731, pruned_loss=0.05246, codebook_loss=20.73, over 1300796.12 frames.], batch size: 29, lr: 1.25e-03
+2022-05-27 16:39:57,567 INFO [train.py:823] (2/4) Epoch 13, batch 550, loss[loss=2.161, simple_loss=0.2622, pruned_loss=0.05036, codebook_loss=19.79, over 7299.00 frames.], tot_loss[loss=2.263, simple_loss=0.2734, pruned_loss=0.0528, codebook_loss=20.74, over 1321980.80 frames.], batch size: 19, lr: 1.25e-03
+2022-05-27 16:40:37,185 INFO [train.py:823] (2/4) Epoch 13, batch 600, loss[loss=2.33, simple_loss=0.2934, pruned_loss=0.06817, codebook_loss=21.15, over 7282.00 frames.], tot_loss[loss=2.264, simple_loss=0.2742, pruned_loss=0.05297, codebook_loss=20.74, over 1344454.51 frames.], batch size: 20, lr: 1.24e-03
+2022-05-27 16:41:17,331 INFO [train.py:823] (2/4) Epoch 13, batch 650, loss[loss=2.404, simple_loss=0.269, pruned_loss=0.04657, codebook_loss=22.23, over 7200.00 frames.], tot_loss[loss=2.265, simple_loss=0.2734, pruned_loss=0.05236, codebook_loss=20.76, over 1360614.48 frames.], batch size: 19, lr: 1.24e-03
+2022-05-27 16:41:57,044 INFO [train.py:823] (2/4) Epoch 13, batch 700, loss[loss=2.273, simple_loss=0.2416, pruned_loss=0.05096, codebook_loss=21.01, over 7013.00 frames.], tot_loss[loss=2.267, simple_loss=0.2736, pruned_loss=0.05253, codebook_loss=20.77, over 1371623.23 frames.], batch size: 17, lr: 1.24e-03
+2022-05-27 16:42:38,230 INFO [train.py:823] (2/4) Epoch 13, batch 750, loss[loss=2.193, simple_loss=0.2671, pruned_loss=0.04564, codebook_loss=20.14, over 6952.00 frames.], tot_loss[loss=2.259, simple_loss=0.274, pruned_loss=0.05233, codebook_loss=20.7, over 1379224.31 frames.], batch size: 29, lr: 1.24e-03
+2022-05-27 16:43:19,050 INFO [train.py:823] (2/4) Epoch 13, batch 800, loss[loss=2.263, simple_loss=0.3019, pruned_loss=0.05469, codebook_loss=20.57, over 7151.00 frames.], tot_loss[loss=2.259, simple_loss=0.2741, pruned_loss=0.05275, codebook_loss=20.69, over 1386650.88 frames.], batch size: 23, lr: 1.24e-03
+2022-05-27 16:44:00,618 INFO [train.py:823] (2/4) Epoch 13, batch 850, loss[loss=2.27, simple_loss=0.2918, pruned_loss=0.07605, codebook_loss=20.48, over 7275.00 frames.], tot_loss[loss=2.258, simple_loss=0.2732, pruned_loss=0.05231, codebook_loss=20.69, over 1396365.82 frames.], batch size: 20, lr: 1.23e-03
+2022-05-27 16:44:39,950 INFO [train.py:823] (2/4) Epoch 13, batch 900, loss[loss=2.201, simple_loss=0.2436, pruned_loss=0.03908, codebook_loss=20.4, over 7304.00 frames.], tot_loss[loss=2.258, simple_loss=0.2741, pruned_loss=0.05269, codebook_loss=20.68, over 1396532.58 frames.], batch size: 19, lr: 1.23e-03
+2022-05-27 16:45:19,787 INFO [train.py:823] (2/4) Epoch 13, batch 950, loss[loss=2.164, simple_loss=0.2327, pruned_loss=0.04089, codebook_loss=20.07, over 7002.00 frames.], tot_loss[loss=2.257, simple_loss=0.2733, pruned_loss=0.0521, codebook_loss=20.68, over 1395705.23 frames.], batch size: 16, lr: 1.23e-03
+2022-05-27 16:45:35,290 INFO [train.py:823] (2/4) Epoch 14, batch 0, loss[loss=2.119, simple_loss=0.241, pruned_loss=0.03258, codebook_loss=19.66, over 7316.00 frames.], tot_loss[loss=2.119, simple_loss=0.241, pruned_loss=0.03258, codebook_loss=19.66, over 7316.00 frames.], batch size: 22, lr: 1.19e-03
+2022-05-27 16:46:15,198 INFO [train.py:823] (2/4) Epoch 14, batch 50, loss[loss=2.192, simple_loss=0.2823, pruned_loss=0.04493, codebook_loss=20.06, over 7213.00 frames.], tot_loss[loss=2.237, simple_loss=0.2707, pruned_loss=0.04911, codebook_loss=20.53, over 325071.65 frames.], batch size: 25, lr: 1.19e-03
+2022-05-27 16:46:55,252 INFO [train.py:823] (2/4) Epoch 14, batch 100, loss[loss=2.222, simple_loss=0.2808, pruned_loss=0.0538, codebook_loss=20.28, over 7220.00 frames.], tot_loss[loss=2.249, simple_loss=0.2723, pruned_loss=0.05033, codebook_loss=20.63, over 570966.24 frames.], batch size: 24, lr: 1.19e-03
+2022-05-27 16:47:34,766 INFO [train.py:823] (2/4) Epoch 14, batch 150, loss[loss=2.226, simple_loss=0.2839, pruned_loss=0.05325, codebook_loss=20.31, over 7283.00 frames.], tot_loss[loss=2.259, simple_loss=0.2738, pruned_loss=0.0515, codebook_loss=20.71, over 755132.50 frames.], batch size: 21, lr: 1.18e-03
+2022-05-27 16:48:14,994 INFO [train.py:823] (2/4) Epoch 14, batch 200, loss[loss=2.139, simple_loss=0.2598, pruned_loss=0.03348, codebook_loss=19.76, over 7376.00 frames.], tot_loss[loss=2.248, simple_loss=0.2727, pruned_loss=0.05035, codebook_loss=20.61, over 900443.55 frames.], batch size: 21, lr: 1.18e-03
+2022-05-27 16:48:54,989 INFO [train.py:823] (2/4) Epoch 14, batch 250, loss[loss=2.222, simple_loss=0.2582, pruned_loss=0.04142, codebook_loss=20.51, over 7295.00 frames.], tot_loss[loss=2.241, simple_loss=0.2703, pruned_loss=0.04942, codebook_loss=20.57, over 1018626.96 frames.], batch size: 19, lr: 1.18e-03
+2022-05-27 16:49:34,983 INFO [train.py:823] (2/4) Epoch 14, batch 300, loss[loss=2.173, simple_loss=0.2673, pruned_loss=0.03639, codebook_loss=20.03, over 6374.00 frames.], tot_loss[loss=2.232, simple_loss=0.269, pruned_loss=0.04883, codebook_loss=20.49, over 1096978.46 frames.], batch size: 34, lr: 1.18e-03
+2022-05-27 16:50:14,792 INFO [train.py:823] (2/4) Epoch 14, batch 350, loss[loss=2.254, simple_loss=0.2534, pruned_loss=0.04778, codebook_loss=20.8, over 7303.00 frames.], tot_loss[loss=2.228, simple_loss=0.2697, pruned_loss=0.04893, codebook_loss=20.44, over 1174022.43 frames.], batch size: 19, lr: 1.18e-03
+2022-05-27 16:50:54,545 INFO [train.py:823] (2/4) Epoch 14, batch 400, loss[loss=2.169, simple_loss=0.2719, pruned_loss=0.04521, codebook_loss=19.88, over 7303.00 frames.], tot_loss[loss=2.232, simple_loss=0.2699, pruned_loss=0.0492, codebook_loss=20.48, over 1228702.29 frames.], batch size: 19, lr: 1.17e-03
+2022-05-27 16:51:34,199 INFO [train.py:823] (2/4) Epoch 14, batch 450, loss[loss=2.18, simple_loss=0.2519, pruned_loss=0.03705, codebook_loss=20.17, over 7097.00 frames.], tot_loss[loss=2.237, simple_loss=0.2714, pruned_loss=0.05011, codebook_loss=20.51, over 1267520.13 frames.], batch size: 18, lr: 1.17e-03
+2022-05-27 16:52:14,436 INFO [train.py:823] (2/4) Epoch 14, batch 500, loss[loss=2.178, simple_loss=0.2813, pruned_loss=0.05046, codebook_loss=19.87, over 7181.00 frames.], tot_loss[loss=2.234, simple_loss=0.2707, pruned_loss=0.04991, codebook_loss=20.49, over 1302716.11 frames.], batch size: 21, lr: 1.17e-03
+2022-05-27 16:52:54,032 INFO [train.py:823] (2/4) Epoch 14, batch 550, loss[loss=2.29, simple_loss=0.2856, pruned_loss=0.06409, codebook_loss=20.83, over 7244.00 frames.], tot_loss[loss=2.241, simple_loss=0.2708, pruned_loss=0.05034, codebook_loss=20.56, over 1333362.82 frames.], batch size: 25, lr: 1.17e-03
+2022-05-27 16:53:34,434 INFO [train.py:823] (2/4) Epoch 14, batch 600, loss[loss=2.345, simple_loss=0.2587, pruned_loss=0.05034, codebook_loss=21.65, over 7389.00 frames.], tot_loss[loss=2.24, simple_loss=0.2689, pruned_loss=0.04979, codebook_loss=20.56, over 1354459.78 frames.], batch size: 19, lr: 1.17e-03
+2022-05-27 16:54:14,392 INFO [train.py:823] (2/4) Epoch 14, batch 650, loss[loss=2.153, simple_loss=0.2352, pruned_loss=0.03225, codebook_loss=20.03, over 7289.00 frames.], tot_loss[loss=2.236, simple_loss=0.2693, pruned_loss=0.04967, codebook_loss=20.52, over 1367613.08 frames.], batch size: 17, lr: 1.16e-03
+2022-05-27 16:54:54,551 INFO [train.py:823] (2/4) Epoch 14, batch 700, loss[loss=2.195, simple_loss=0.2665, pruned_loss=0.04406, codebook_loss=20.17, over 7292.00 frames.], tot_loss[loss=2.237, simple_loss=0.2695, pruned_loss=0.04956, codebook_loss=20.53, over 1376803.55 frames.], batch size: 21, lr: 1.16e-03
+2022-05-27 16:55:34,020 INFO [train.py:823] (2/4) Epoch 14, batch 750, loss[loss=2.255, simple_loss=0.2783, pruned_loss=0.05772, codebook_loss=20.58, over 7112.00 frames.], tot_loss[loss=2.239, simple_loss=0.2692, pruned_loss=0.04932, codebook_loss=20.55, over 1387204.33 frames.], batch size: 20, lr: 1.16e-03
+2022-05-27 16:56:14,259 INFO [train.py:823] (2/4) Epoch 14, batch 800, loss[loss=2.297, simple_loss=0.2791, pruned_loss=0.06068, codebook_loss=20.97, over 7196.00 frames.], tot_loss[loss=2.24, simple_loss=0.2692, pruned_loss=0.04959, codebook_loss=20.55, over 1393288.40 frames.], batch size: 19, lr: 1.16e-03
+2022-05-27 16:56:54,027 INFO [train.py:823] (2/4) Epoch 14, batch 850, loss[loss=2.228, simple_loss=0.2667, pruned_loss=0.04034, codebook_loss=20.55, over 7275.00 frames.], tot_loss[loss=2.238, simple_loss=0.2698, pruned_loss=0.04975, codebook_loss=20.53, over 1396320.35 frames.], batch size: 20, lr: 1.16e-03
+2022-05-27 16:57:34,192 INFO [train.py:823] (2/4) Epoch 14, batch 900, loss[loss=2.195, simple_loss=0.2377, pruned_loss=0.04631, codebook_loss=20.3, over 7415.00 frames.], tot_loss[loss=2.241, simple_loss=0.2689, pruned_loss=0.04939, codebook_loss=20.57, over 1401445.65 frames.], batch size: 18, lr: 1.15e-03
+2022-05-27 16:58:27,942 INFO [train.py:823] (2/4) Epoch 15, batch 0, loss[loss=2.206, simple_loss=0.2533, pruned_loss=0.04202, codebook_loss=20.37, over 7203.00 frames.], tot_loss[loss=2.206, simple_loss=0.2533, pruned_loss=0.04202, codebook_loss=20.37, over 7203.00 frames.], batch size: 19, lr: 1.12e-03
+2022-05-27 16:59:07,735 INFO [train.py:823] (2/4) Epoch 15, batch 50, loss[loss=2.252, simple_loss=0.2778, pruned_loss=0.05325, codebook_loss=20.59, over 7190.00 frames.], tot_loss[loss=2.23, simple_loss=0.2721, pruned_loss=0.04958, codebook_loss=20.44, over 319879.13 frames.], batch size: 18, lr: 1.12e-03
+2022-05-27 16:59:47,349 INFO [train.py:823] (2/4) Epoch 15, batch 100, loss[loss=2.327, simple_loss=0.269, pruned_loss=0.04532, codebook_loss=21.47, over 7428.00 frames.], tot_loss[loss=2.227, simple_loss=0.2701, pruned_loss=0.04951, codebook_loss=20.42, over 560521.36 frames.], batch size: 22, lr: 1.11e-03
+2022-05-27 17:00:27,658 INFO [train.py:823] (2/4) Epoch 15, batch 150, loss[loss=2.371, simple_loss=0.2387, pruned_loss=0.04974, codebook_loss=22.02, over 7284.00 frames.], tot_loss[loss=2.223, simple_loss=0.2678, pruned_loss=0.04861, codebook_loss=20.41, over 752302.27 frames.], batch size: 17, lr: 1.11e-03
+2022-05-27 17:01:07,278 INFO [train.py:823] (2/4) Epoch 15, batch 200, loss[loss=2.29, simple_loss=0.2845, pruned_loss=0.05812, codebook_loss=20.9, over 7152.00 frames.], tot_loss[loss=2.235, simple_loss=0.269, pruned_loss=0.04961, codebook_loss=20.51, over 899224.04 frames.], batch size: 23, lr: 1.11e-03
+2022-05-27 17:01:47,504 INFO [train.py:823] (2/4) Epoch 15, batch 250, loss[loss=2.168, simple_loss=0.2741, pruned_loss=0.04938, codebook_loss=19.81, over 6589.00 frames.], tot_loss[loss=2.233, simple_loss=0.2683, pruned_loss=0.04906, codebook_loss=20.5, over 1015840.81 frames.], batch size: 34, lr: 1.11e-03
+2022-05-27 17:02:27,349 INFO [train.py:823] (2/4) Epoch 15, batch 300, loss[loss=2.297, simple_loss=0.2743, pruned_loss=0.06217, codebook_loss=20.97, over 7189.00 frames.], tot_loss[loss=2.227, simple_loss=0.2673, pruned_loss=0.04885, codebook_loss=20.45, over 1105518.82 frames.], batch size: 18, lr: 1.11e-03
+2022-05-27 17:03:08,870 INFO [train.py:823] (2/4) Epoch 15, batch 350, loss[loss=2.229, simple_loss=0.2711, pruned_loss=0.05285, codebook_loss=20.4, over 7381.00 frames.], tot_loss[loss=2.224, simple_loss=0.2682, pruned_loss=0.04835, codebook_loss=20.42, over 1177676.67 frames.], batch size: 20, lr: 1.10e-03
+2022-05-27 17:03:48,684 INFO [train.py:823] (2/4) Epoch 15, batch 400, loss[loss=2.196, simple_loss=0.2684, pruned_loss=0.05423, codebook_loss=20.08, over 7104.00 frames.], tot_loss[loss=2.23, simple_loss=0.268, pruned_loss=0.04867, codebook_loss=20.47, over 1229275.39 frames.], batch size: 19, lr: 1.10e-03
+2022-05-27 17:04:28,849 INFO [train.py:823] (2/4) Epoch 15, batch 450, loss[loss=2.219, simple_loss=0.2917, pruned_loss=0.0609, codebook_loss=20.13, over 7227.00 frames.], tot_loss[loss=2.223, simple_loss=0.2678, pruned_loss=0.04823, codebook_loss=20.41, over 1276664.89 frames.], batch size: 24, lr: 1.10e-03
+2022-05-27 17:05:08,677 INFO [train.py:823] (2/4) Epoch 15, batch 500, loss[loss=2.172, simple_loss=0.2655, pruned_loss=0.0372, codebook_loss=20.02, over 7107.00 frames.], tot_loss[loss=2.22, simple_loss=0.2679, pruned_loss=0.04797, codebook_loss=20.38, over 1312534.49 frames.], batch size: 20, lr: 1.10e-03
+2022-05-27 17:05:48,693 INFO [train.py:823] (2/4) Epoch 15, batch 550, loss[loss=2.193, simple_loss=0.2486, pruned_loss=0.04278, codebook_loss=20.26, over 7039.00 frames.], tot_loss[loss=2.218, simple_loss=0.2675, pruned_loss=0.04777, codebook_loss=20.36, over 1332999.89 frames.], batch size: 17, lr: 1.10e-03
+2022-05-27 17:06:28,751 INFO [train.py:823] (2/4) Epoch 15, batch 600, loss[loss=2.286, simple_loss=0.2803, pruned_loss=0.05563, codebook_loss=20.91, over 7301.00 frames.], tot_loss[loss=2.226, simple_loss=0.2676, pruned_loss=0.04781, codebook_loss=20.45, over 1356027.30 frames.], batch size: 19, lr: 1.10e-03
+2022-05-27 17:07:08,780 INFO [train.py:823] (2/4) Epoch 15, batch 650, loss[loss=2.168, simple_loss=0.2693, pruned_loss=0.04773, codebook_loss=19.86, over 7175.00 frames.], tot_loss[loss=2.224, simple_loss=0.2683, pruned_loss=0.04806, codebook_loss=20.42, over 1367606.64 frames.], batch size: 22, lr: 1.09e-03
+2022-05-27 17:07:51,633 INFO [train.py:823] (2/4) Epoch 15, batch 700, loss[loss=2.134, simple_loss=0.2641, pruned_loss=0.04272, codebook_loss=19.6, over 6938.00 frames.], tot_loss[loss=2.221, simple_loss=0.2673, pruned_loss=0.04767, codebook_loss=20.4, over 1382114.20 frames.], batch size: 29, lr: 1.09e-03
+2022-05-27 17:08:32,982 INFO [train.py:823] (2/4) Epoch 15, batch 750, loss[loss=2.274, simple_loss=0.284, pruned_loss=0.06384, codebook_loss=20.68, over 5056.00 frames.], tot_loss[loss=2.219, simple_loss=0.2675, pruned_loss=0.04773, codebook_loss=20.38, over 1384690.17 frames.], batch size: 47, lr: 1.09e-03
+2022-05-27 17:09:12,714 INFO [train.py:823] (2/4) Epoch 15, batch 800, loss[loss=2.098, simple_loss=0.2436, pruned_loss=0.03336, codebook_loss=19.43, over 7195.00 frames.], tot_loss[loss=2.217, simple_loss=0.2675, pruned_loss=0.0475, codebook_loss=20.35, over 1389388.42 frames.], batch size: 19, lr: 1.09e-03
+2022-05-27 17:09:53,053 INFO [train.py:823] (2/4) Epoch 15, batch 850, loss[loss=2.365, simple_loss=0.3041, pruned_loss=0.07053, codebook_loss=21.43, over 7213.00 frames.], tot_loss[loss=2.217, simple_loss=0.2674, pruned_loss=0.04742, codebook_loss=20.36, over 1394494.96 frames.], batch size: 25, lr: 1.09e-03
+2022-05-27 17:10:33,293 INFO [train.py:823] (2/4) Epoch 15, batch 900, loss[loss=2.104, simple_loss=0.2431, pruned_loss=0.03858, codebook_loss=19.43, over 7097.00 frames.], tot_loss[loss=2.217, simple_loss=0.268, pruned_loss=0.04749, codebook_loss=20.36, over 1399247.45 frames.], batch size: 19, lr: 1.09e-03
+2022-05-27 17:11:13,318 INFO [train.py:823] (2/4) Epoch 15, batch 950, loss[loss=2.244, simple_loss=0.2756, pruned_loss=0.05361, codebook_loss=20.53, over 5109.00 frames.], tot_loss[loss=2.22, simple_loss=0.2678, pruned_loss=0.04786, codebook_loss=20.38, over 1380211.53 frames.], batch size: 46, lr: 1.08e-03
+2022-05-27 17:11:28,470 INFO [train.py:823] (2/4) Epoch 16, batch 0, loss[loss=2.116, simple_loss=0.2529, pruned_loss=0.04037, codebook_loss=19.49, over 5204.00 frames.], tot_loss[loss=2.116, simple_loss=0.2529, pruned_loss=0.04037, codebook_loss=19.49, over 5204.00 frames.], batch size: 46, lr: 1.05e-03
+2022-05-27 17:12:08,301 INFO [train.py:823] (2/4) Epoch 16, batch 50, loss[loss=2.228, simple_loss=0.2372, pruned_loss=0.05003, codebook_loss=20.59, over 7018.00 frames.], tot_loss[loss=2.162, simple_loss=0.2619, pruned_loss=0.04282, codebook_loss=19.88, over 318030.81 frames.], batch size: 16, lr: 1.05e-03
+2022-05-27 17:12:48,661 INFO [train.py:823] (2/4) Epoch 16, batch 100, loss[loss=2.178, simple_loss=0.287, pruned_loss=0.0452, codebook_loss=19.89, over 7204.00 frames.], tot_loss[loss=2.194, simple_loss=0.2638, pruned_loss=0.04492, codebook_loss=20.17, over 560527.34 frames.], batch size: 19, lr: 1.05e-03
+2022-05-27 17:13:28,971 INFO [train.py:823] (2/4) Epoch 16, batch 150, loss[loss=2.199, simple_loss=0.2672, pruned_loss=0.05174, codebook_loss=20.14, over 7384.00 frames.], tot_loss[loss=2.19, simple_loss=0.2626, pruned_loss=0.04474, codebook_loss=20.14, over 756478.61 frames.], batch size: 19, lr: 1.05e-03
+2022-05-27 17:14:09,504 INFO [train.py:823] (2/4) Epoch 16, batch 200, loss[loss=2.141, simple_loss=0.265, pruned_loss=0.03671, codebook_loss=19.72, over 7179.00 frames.], tot_loss[loss=2.201, simple_loss=0.264, pruned_loss=0.04617, codebook_loss=20.23, over 903993.07 frames.], batch size: 23, lr: 1.05e-03
+2022-05-27 17:14:49,491 INFO [train.py:823] (2/4) Epoch 16, batch 250, loss[loss=2.152, simple_loss=0.2694, pruned_loss=0.04708, codebook_loss=19.7, over 7181.00 frames.], tot_loss[loss=2.195, simple_loss=0.2644, pruned_loss=0.04601, codebook_loss=20.17, over 1012725.22 frames.], batch size: 25, lr: 1.04e-03
+2022-05-27 17:15:29,984 INFO [train.py:823] (2/4) Epoch 16, batch 300, loss[loss=2.28, simple_loss=0.2799, pruned_loss=0.04648, codebook_loss=20.94, over 7222.00 frames.], tot_loss[loss=2.198, simple_loss=0.263, pruned_loss=0.04539, codebook_loss=20.21, over 1105772.08 frames.], batch size: 24, lr: 1.04e-03
+2022-05-27 17:16:09,520 INFO [train.py:823] (2/4) Epoch 16, batch 350, loss[loss=2.123, simple_loss=0.265, pruned_loss=0.03656, codebook_loss=19.54, over 7342.00 frames.], tot_loss[loss=2.207, simple_loss=0.2646, pruned_loss=0.04625, codebook_loss=20.28, over 1173220.43 frames.], batch size: 23, lr: 1.04e-03
+2022-05-27 17:16:49,901 INFO [train.py:823] (2/4) Epoch 16, batch 400, loss[loss=2.367, simple_loss=0.2897, pruned_loss=0.06982, codebook_loss=21.52, over 7284.00 frames.], tot_loss[loss=2.201, simple_loss=0.2646, pruned_loss=0.04571, codebook_loss=20.23, over 1228584.76 frames.], batch size: 19, lr: 1.04e-03
+2022-05-27 17:17:29,835 INFO [train.py:823] (2/4) Epoch 16, batch 450, loss[loss=2.362, simple_loss=0.2801, pruned_loss=0.05686, codebook_loss=21.65, over 7408.00 frames.], tot_loss[loss=2.204, simple_loss=0.265, pruned_loss=0.0457, codebook_loss=20.25, over 1275413.58 frames.], batch size: 22, lr: 1.04e-03
+2022-05-27 17:18:10,082 INFO [train.py:823] (2/4) Epoch 16, batch 500, loss[loss=2.268, simple_loss=0.3014, pruned_loss=0.06253, codebook_loss=20.55, over 6985.00 frames.], tot_loss[loss=2.204, simple_loss=0.2645, pruned_loss=0.04558, codebook_loss=20.26, over 1311464.19 frames.], batch size: 29, lr: 1.04e-03
+2022-05-27 17:18:49,973 INFO [train.py:823] (2/4) Epoch 16, batch 550, loss[loss=2.267, simple_loss=0.3005, pruned_loss=0.06174, codebook_loss=20.55, over 7369.00 frames.], tot_loss[loss=2.202, simple_loss=0.2655, pruned_loss=0.04583, codebook_loss=20.23, over 1329160.84 frames.], batch size: 21, lr: 1.03e-03
+2022-05-27 17:19:30,252 INFO [train.py:823] (2/4) Epoch 16, batch 600, loss[loss=2.187, simple_loss=0.2646, pruned_loss=0.05324, codebook_loss=20.01, over 7099.00 frames.], tot_loss[loss=2.207, simple_loss=0.2659, pruned_loss=0.04642, codebook_loss=20.28, over 1343973.78 frames.], batch size: 19, lr: 1.03e-03
+2022-05-27 17:20:09,981 INFO [train.py:823] (2/4) Epoch 16, batch 650, loss[loss=2.247, simple_loss=0.2634, pruned_loss=0.04918, codebook_loss=20.66, over 7191.00 frames.], tot_loss[loss=2.213, simple_loss=0.2678, pruned_loss=0.04721, codebook_loss=20.32, over 1360172.87 frames.], batch size: 16, lr: 1.03e-03
+2022-05-27 17:20:50,255 INFO [train.py:823] (2/4) Epoch 16, batch 700, loss[loss=2.139, simple_loss=0.2558, pruned_loss=0.04198, codebook_loss=19.7, over 7294.00 frames.], tot_loss[loss=2.215, simple_loss=0.2672, pruned_loss=0.04746, codebook_loss=20.34, over 1370662.70 frames.], batch size: 19, lr: 1.03e-03
+2022-05-27 17:21:29,882 INFO [train.py:823] (2/4) Epoch 16, batch 750, loss[loss=2.289, simple_loss=0.2597, pruned_loss=0.05484, codebook_loss=21.04, over 7181.00 frames.], tot_loss[loss=2.215, simple_loss=0.2676, pruned_loss=0.04774, codebook_loss=20.34, over 1382673.20 frames.], batch size: 18, lr: 1.03e-03
+2022-05-27 17:22:09,874 INFO [train.py:823] (2/4) Epoch 16, batch 800, loss[loss=2.319, simple_loss=0.2697, pruned_loss=0.0546, codebook_loss=21.29, over 7378.00 frames.], tot_loss[loss=2.21, simple_loss=0.2663, pruned_loss=0.04683, codebook_loss=20.3, over 1393118.91 frames.], batch size: 20, lr: 1.03e-03
+2022-05-27 17:22:49,730 INFO [train.py:823] (2/4) Epoch 16, batch 850, loss[loss=2.156, simple_loss=0.2714, pruned_loss=0.0445, codebook_loss=19.76, over 7191.00 frames.], tot_loss[loss=2.203, simple_loss=0.2661, pruned_loss=0.04641, codebook_loss=20.24, over 1400205.50 frames.], batch size: 21, lr: 1.03e-03
+2022-05-27 17:23:29,827 INFO [train.py:823] (2/4) Epoch 16, batch 900, loss[loss=2.126, simple_loss=0.2443, pruned_loss=0.03385, codebook_loss=19.7, over 7048.00 frames.], tot_loss[loss=2.199, simple_loss=0.2653, pruned_loss=0.0459, codebook_loss=20.2, over 1401352.48 frames.], batch size: 17, lr: 1.02e-03
+2022-05-27 17:24:23,377 INFO [train.py:823] (2/4) Epoch 17, batch 0, loss[loss=2.111, simple_loss=0.2739, pruned_loss=0.04077, codebook_loss=19.34, over 7194.00 frames.], tot_loss[loss=2.111, simple_loss=0.2739, pruned_loss=0.04077, codebook_loss=19.34, over 7194.00 frames.], batch size: 21, lr: 9.94e-04
+2022-05-27 17:25:03,608 INFO [train.py:823] (2/4) Epoch 17, batch 50, loss[loss=2.144, simple_loss=0.2632, pruned_loss=0.04006, codebook_loss=19.72, over 6961.00 frames.], tot_loss[loss=2.197, simple_loss=0.2657, pruned_loss=0.04504, codebook_loss=20.2, over 315280.01 frames.], batch size: 26, lr: 9.92e-04
+2022-05-27 17:25:43,294 INFO [train.py:823] (2/4) Epoch 17, batch 100, loss[loss=2.176, simple_loss=0.2904, pruned_loss=0.05111, codebook_loss=19.8, over 6981.00 frames.], tot_loss[loss=2.192, simple_loss=0.2645, pruned_loss=0.04465, codebook_loss=20.15, over 561397.29 frames.], batch size: 26, lr: 9.91e-04
+2022-05-27 17:26:24,349 INFO [train.py:823] (2/4) Epoch 17, batch 150, loss[loss=2.158, simple_loss=0.2399, pruned_loss=0.04005, codebook_loss=19.98, over 7189.00 frames.], tot_loss[loss=2.182, simple_loss=0.2643, pruned_loss=0.04509, codebook_loss=20.05, over 748632.73 frames.], batch size: 18, lr: 9.89e-04
+2022-05-27 17:27:04,186 INFO [train.py:823] (2/4) Epoch 17, batch 200, loss[loss=2.155, simple_loss=0.2988, pruned_loss=0.05096, codebook_loss=19.55, over 6908.00 frames.], tot_loss[loss=2.19, simple_loss=0.2656, pruned_loss=0.04571, codebook_loss=20.11, over 896806.88 frames.], batch size: 29, lr: 9.88e-04
+2022-05-27 17:27:44,508 INFO [train.py:823] (2/4) Epoch 17, batch 250, loss[loss=2.23, simple_loss=0.275, pruned_loss=0.0573, codebook_loss=20.35, over 7352.00 frames.], tot_loss[loss=2.186, simple_loss=0.2664, pruned_loss=0.04613, codebook_loss=20.07, over 1017719.87 frames.], batch size: 23, lr: 9.86e-04
+2022-05-27 17:28:23,995 INFO [train.py:823] (2/4) Epoch 17, batch 300, loss[loss=2.063, simple_loss=0.2468, pruned_loss=0.03713, codebook_loss=19.02, over 7307.00 frames.], tot_loss[loss=2.183, simple_loss=0.2663, pruned_loss=0.04596, codebook_loss=20.04, over 1104229.44 frames.], batch size: 18, lr: 9.85e-04
+2022-05-27 17:29:04,160 INFO [train.py:823] (2/4) Epoch 17, batch 350, loss[loss=2.089, simple_loss=0.2526, pruned_loss=0.03927, codebook_loss=19.23, over 7396.00 frames.], tot_loss[loss=2.184, simple_loss=0.2656, pruned_loss=0.04547, codebook_loss=20.05, over 1170506.60 frames.], batch size: 19, lr: 9.84e-04
+2022-05-27 17:29:43,934 INFO [train.py:823] (2/4) Epoch 17, batch 400, loss[loss=2.111, simple_loss=0.2584, pruned_loss=0.03994, codebook_loss=19.42, over 7102.00 frames.], tot_loss[loss=2.192, simple_loss=0.2631, pruned_loss=0.04487, codebook_loss=20.15, over 1225896.03 frames.], batch size: 19, lr: 9.82e-04
+2022-05-27 17:30:24,074 INFO [train.py:823] (2/4) Epoch 17, batch 450, loss[loss=2.221, simple_loss=0.2865, pruned_loss=0.06488, codebook_loss=20.13, over 5140.00 frames.], tot_loss[loss=2.194, simple_loss=0.2636, pruned_loss=0.04499, codebook_loss=20.17, over 1261914.67 frames.], batch size: 47, lr: 9.81e-04
+2022-05-27 17:31:03,721 INFO [train.py:823] (2/4) Epoch 17, batch 500, loss[loss=2.191, simple_loss=0.2436, pruned_loss=0.04019, codebook_loss=20.29, over 7002.00 frames.], tot_loss[loss=2.188, simple_loss=0.2632, pruned_loss=0.04429, codebook_loss=20.12, over 1296998.57 frames.], batch size: 16, lr: 9.79e-04
+2022-05-27 17:31:43,972 INFO [train.py:823] (2/4) Epoch 17, batch 550, loss[loss=2.081, simple_loss=0.2687, pruned_loss=0.03208, codebook_loss=19.15, over 7112.00 frames.], tot_loss[loss=2.19, simple_loss=0.2634, pruned_loss=0.04453, codebook_loss=20.14, over 1326845.70 frames.], batch size: 20, lr: 9.78e-04
+2022-05-27 17:32:26,188 INFO [train.py:823] (2/4) Epoch 17, batch 600, loss[loss=2.069, simple_loss=0.2652, pruned_loss=0.04221, codebook_loss=18.94, over 7311.00 frames.], tot_loss[loss=2.197, simple_loss=0.2638, pruned_loss=0.04486, codebook_loss=20.2, over 1349321.06 frames.], batch size: 22, lr: 9.76e-04
+2022-05-27 17:33:07,633 INFO [train.py:823] (2/4) Epoch 17, batch 650, loss[loss=2.267, simple_loss=0.251, pruned_loss=0.04737, codebook_loss=20.94, over 7000.00 frames.], tot_loss[loss=2.196, simple_loss=0.2627, pruned_loss=0.04446, codebook_loss=20.2, over 1362110.23 frames.], batch size: 16, lr: 9.75e-04
+2022-05-27 17:33:47,432 INFO [train.py:823] (2/4) Epoch 17, batch 700, loss[loss=2.137, simple_loss=0.2307, pruned_loss=0.0406, codebook_loss=19.81, over 6803.00 frames.], tot_loss[loss=2.189, simple_loss=0.2623, pruned_loss=0.04379, codebook_loss=20.15, over 1373084.45 frames.], batch size: 15, lr: 9.74e-04
+2022-05-27 17:34:27,710 INFO [train.py:823] (2/4) Epoch 17, batch 750, loss[loss=2.171, simple_loss=0.258, pruned_loss=0.04622, codebook_loss=19.96, over 7150.00 frames.], tot_loss[loss=2.185, simple_loss=0.2611, pruned_loss=0.04374, codebook_loss=20.1, over 1385801.54 frames.], batch size: 17, lr: 9.72e-04
+2022-05-27 17:35:07,556 INFO [train.py:823] (2/4) Epoch 17, batch 800, loss[loss=2.115, simple_loss=0.2267, pruned_loss=0.0325, codebook_loss=19.69, over 7014.00 frames.], tot_loss[loss=2.184, simple_loss=0.2617, pruned_loss=0.04373, codebook_loss=20.09, over 1389300.31 frames.], batch size: 16, lr: 9.71e-04
+2022-05-27 17:35:50,773 INFO [train.py:823] (2/4) Epoch 17, batch 850, loss[loss=2.139, simple_loss=0.2848, pruned_loss=0.04152, codebook_loss=19.55, over 7409.00 frames.], tot_loss[loss=2.18, simple_loss=0.2614, pruned_loss=0.04378, codebook_loss=20.06, over 1395806.71 frames.], batch size: 22, lr: 9.69e-04
+2022-05-27 17:36:30,812 INFO [train.py:823] (2/4) Epoch 17, batch 900, loss[loss=2.16, simple_loss=0.2421, pruned_loss=0.04448, codebook_loss=19.95, over 7297.00 frames.], tot_loss[loss=2.179, simple_loss=0.2615, pruned_loss=0.04407, codebook_loss=20.04, over 1401993.16 frames.], batch size: 17, lr: 9.68e-04
+2022-05-27 17:37:10,657 INFO [train.py:823] (2/4) Epoch 17, batch 950, loss[loss=2.155, simple_loss=0.2724, pruned_loss=0.04594, codebook_loss=19.73, over 4749.00 frames.], tot_loss[loss=2.182, simple_loss=0.2625, pruned_loss=0.04466, codebook_loss=20.07, over 1396464.97 frames.], batch size: 46, lr: 9.67e-04
+2022-05-27 17:37:25,999 INFO [train.py:823] (2/4) Epoch 18, batch 0, loss[loss=2.103, simple_loss=0.2681, pruned_loss=0.03607, codebook_loss=19.33, over 7366.00 frames.], tot_loss[loss=2.103, simple_loss=0.2681, pruned_loss=0.03607, codebook_loss=19.33, over 7366.00 frames.], batch size: 21, lr: 9.41e-04
+2022-05-27 17:38:06,265 INFO [train.py:823] (2/4) Epoch 18, batch 50, loss[loss=2.157, simple_loss=0.2608, pruned_loss=0.03802, codebook_loss=19.88, over 7319.00 frames.], tot_loss[loss=2.178, simple_loss=0.2619, pruned_loss=0.04339, codebook_loss=20.03, over 322224.29 frames.], batch size: 23, lr: 9.40e-04
+2022-05-27 17:38:46,066 INFO [train.py:823] (2/4) Epoch 18, batch 100, loss[loss=2.12, simple_loss=0.2459, pruned_loss=0.03786, codebook_loss=19.59, over 7280.00 frames.], tot_loss[loss=2.168, simple_loss=0.2614, pruned_loss=0.04291, codebook_loss=19.95, over 564217.13 frames.], batch size: 20, lr: 9.39e-04
+2022-05-27 17:39:26,376 INFO [train.py:823] (2/4) Epoch 18, batch 150, loss[loss=2.09, simple_loss=0.2705, pruned_loss=0.04272, codebook_loss=19.12, over 7200.00 frames.], tot_loss[loss=2.167, simple_loss=0.2593, pruned_loss=0.04229, codebook_loss=19.95, over 756982.47 frames.], batch size: 20, lr: 9.37e-04
+2022-05-27 17:40:06,111 INFO [train.py:823] (2/4) Epoch 18, batch 200, loss[loss=2.105, simple_loss=0.2649, pruned_loss=0.03576, codebook_loss=19.36, over 7279.00 frames.], tot_loss[loss=2.162, simple_loss=0.2596, pruned_loss=0.04235, codebook_loss=19.89, over 907630.87 frames.], batch size: 21, lr: 9.36e-04
+2022-05-27 17:40:46,116 INFO [train.py:823] (2/4) Epoch 18, batch 250, loss[loss=2.061, simple_loss=0.2606, pruned_loss=0.03012, codebook_loss=19.01, over 7302.00 frames.], tot_loss[loss=2.172, simple_loss=0.2624, pruned_loss=0.04406, codebook_loss=19.96, over 1015857.20 frames.], batch size: 22, lr: 9.35e-04
+2022-05-27 17:41:26,323 INFO [train.py:823] (2/4) Epoch 18, batch 300, loss[loss=2.44, simple_loss=0.2385, pruned_loss=0.03992, codebook_loss=22.81, over 7035.00 frames.], tot_loss[loss=2.175, simple_loss=0.2614, pruned_loss=0.0439, codebook_loss=20.01, over 1105644.21 frames.], batch size: 17, lr: 9.33e-04
+2022-05-27 17:42:06,868 INFO [train.py:823] (2/4) Epoch 18, batch 350, loss[loss=2.038, simple_loss=0.2633, pruned_loss=0.03562, codebook_loss=18.7, over 7281.00 frames.], tot_loss[loss=2.166, simple_loss=0.2618, pruned_loss=0.04373, codebook_loss=19.91, over 1176032.62 frames.], batch size: 20, lr: 9.32e-04
+2022-05-27 17:42:46,648 INFO [train.py:823] (2/4) Epoch 18, batch 400, loss[loss=2.049, simple_loss=0.2364, pruned_loss=0.02803, codebook_loss=19.03, over 7379.00 frames.], tot_loss[loss=2.169, simple_loss=0.2629, pruned_loss=0.04435, codebook_loss=19.93, over 1227446.55 frames.], batch size: 19, lr: 9.31e-04
+2022-05-27 17:43:26,811 INFO [train.py:823] (2/4) Epoch 18, batch 450, loss[loss=2.207, simple_loss=0.2796, pruned_loss=0.05465, codebook_loss=20.13, over 7164.00 frames.], tot_loss[loss=2.17, simple_loss=0.263, pruned_loss=0.04402, codebook_loss=19.94, over 1269236.22 frames.], batch size: 23, lr: 9.29e-04
+2022-05-27 17:44:06,715 INFO [train.py:823] (2/4) Epoch 18, batch 500, loss[loss=2.217, simple_loss=0.2874, pruned_loss=0.05828, codebook_loss=20.15, over 7411.00 frames.], tot_loss[loss=2.17, simple_loss=0.2623, pruned_loss=0.04371, codebook_loss=19.95, over 1307195.20 frames.], batch size: 22, lr: 9.28e-04
+2022-05-27 17:44:47,127 INFO [train.py:823] (2/4) Epoch 18, batch 550, loss[loss=2.036, simple_loss=0.2454, pruned_loss=0.02748, codebook_loss=18.86, over 7339.00 frames.], tot_loss[loss=2.167, simple_loss=0.261, pruned_loss=0.04299, codebook_loss=19.93, over 1335424.34 frames.], batch size: 23, lr: 9.27e-04
+2022-05-27 17:45:26,632 INFO [train.py:823] (2/4) Epoch 18, batch 600, loss[loss=2.134, simple_loss=0.2289, pruned_loss=0.03181, codebook_loss=19.88, over 7303.00 frames.], tot_loss[loss=2.165, simple_loss=0.2601, pruned_loss=0.04234, codebook_loss=19.93, over 1357547.13 frames.], batch size: 19, lr: 9.26e-04
+2022-05-27 17:46:06,503 INFO [train.py:823] (2/4) Epoch 18, batch 650, loss[loss=2.144, simple_loss=0.2439, pruned_loss=0.04442, codebook_loss=19.77, over 7098.00 frames.], tot_loss[loss=2.16, simple_loss=0.2597, pruned_loss=0.04203, codebook_loss=19.88, over 1371122.21 frames.], batch size: 19, lr: 9.24e-04
+2022-05-27 17:46:46,442 INFO [train.py:823] (2/4) Epoch 18, batch 700, loss[loss=2.21, simple_loss=0.2612, pruned_loss=0.04765, codebook_loss=20.32, over 7199.00 frames.], tot_loss[loss=2.161, simple_loss=0.2596, pruned_loss=0.04224, codebook_loss=19.88, over 1377187.61 frames.], batch size: 19, lr: 9.23e-04
+2022-05-27 17:47:26,797 INFO [train.py:823] (2/4) Epoch 18, batch 750, loss[loss=2.212, simple_loss=0.2511, pruned_loss=0.049, codebook_loss=20.38, over 7108.00 frames.], tot_loss[loss=2.16, simple_loss=0.2591, pruned_loss=0.04223, codebook_loss=19.88, over 1388955.22 frames.], batch size: 18, lr: 9.22e-04
+2022-05-27 17:48:06,498 INFO [train.py:823] (2/4) Epoch 18, batch 800, loss[loss=2.205, simple_loss=0.2693, pruned_loss=0.03732, codebook_loss=20.33, over 7186.00 frames.], tot_loss[loss=2.163, simple_loss=0.2593, pruned_loss=0.0425, codebook_loss=19.91, over 1392005.60 frames.], batch size: 20, lr: 9.21e-04
+2022-05-27 17:48:46,505 INFO [train.py:823] (2/4) Epoch 18, batch 850, loss[loss=2.139, simple_loss=0.2692, pruned_loss=0.04108, codebook_loss=19.63, over 7184.00 frames.], tot_loss[loss=2.159, simple_loss=0.2589, pruned_loss=0.04218, codebook_loss=19.87, over 1395431.90 frames.], batch size: 21, lr: 9.19e-04
+2022-05-27 17:49:26,191 INFO [train.py:823] (2/4) Epoch 18, batch 900, loss[loss=2.038, simple_loss=0.2189, pruned_loss=0.02372, codebook_loss=19.05, over 7140.00 frames.], tot_loss[loss=2.164, simple_loss=0.2594, pruned_loss=0.04245, codebook_loss=19.92, over 1402148.87 frames.], batch size: 17, lr: 9.18e-04
+2022-05-27 17:50:07,350 INFO [train.py:823] (2/4) Epoch 18, batch 950, loss[loss=2.214, simple_loss=0.2782, pruned_loss=0.05495, codebook_loss=20.2, over 4725.00 frames.], tot_loss[loss=2.166, simple_loss=0.2599, pruned_loss=0.04265, codebook_loss=19.94, over 1373957.03 frames.], batch size: 46, lr: 9.17e-04
+2022-05-27 17:50:22,767 INFO [train.py:823] (2/4) Epoch 19, batch 0, loss[loss=2.105, simple_loss=0.2722, pruned_loss=0.03826, codebook_loss=19.3, over 7032.00 frames.], tot_loss[loss=2.105, simple_loss=0.2722, pruned_loss=0.03826, codebook_loss=19.3, over 7032.00 frames.], batch size: 26, lr: 8.94e-04
+2022-05-27 17:51:02,636 INFO [train.py:823] (2/4) Epoch 19, batch 50, loss[loss=2.028, simple_loss=0.2354, pruned_loss=0.03258, codebook_loss=18.77, over 7184.00 frames.], tot_loss[loss=2.145, simple_loss=0.2534, pruned_loss=0.0387, codebook_loss=19.8, over 325498.76 frames.], batch size: 19, lr: 8.92e-04
+2022-05-27 17:51:43,088 INFO [train.py:823] (2/4) Epoch 19, batch 100, loss[loss=2.132, simple_loss=0.2758, pruned_loss=0.03685, codebook_loss=19.57, over 6371.00 frames.], tot_loss[loss=2.144, simple_loss=0.2543, pruned_loss=0.03979, codebook_loss=19.78, over 566085.67 frames.], batch size: 34, lr: 8.91e-04
+2022-05-27 17:52:23,022 INFO [train.py:823] (2/4) Epoch 19, batch 150, loss[loss=2.051, simple_loss=0.2489, pruned_loss=0.04045, codebook_loss=18.86, over 7086.00 frames.], tot_loss[loss=2.146, simple_loss=0.2548, pruned_loss=0.04056, codebook_loss=19.78, over 759139.51 frames.], batch size: 18, lr: 8.90e-04
+2022-05-27 17:53:03,226 INFO [train.py:823] (2/4) Epoch 19, batch 200, loss[loss=2.209, simple_loss=0.2914, pruned_loss=0.05739, codebook_loss=20.06, over 7157.00 frames.], tot_loss[loss=2.152, simple_loss=0.2564, pruned_loss=0.04126, codebook_loss=19.83, over 902295.69 frames.], batch size: 22, lr: 8.89e-04
+2022-05-27 17:53:42,983 INFO [train.py:823] (2/4) Epoch 19, batch 250, loss[loss=2.063, simple_loss=0.2288, pruned_loss=0.03122, codebook_loss=19.17, over 7094.00 frames.], tot_loss[loss=2.147, simple_loss=0.2577, pruned_loss=0.04102, codebook_loss=19.77, over 1019054.56 frames.], batch size: 19, lr: 8.88e-04
+2022-05-27 17:54:22,997 INFO [train.py:823] (2/4) Epoch 19, batch 300, loss[loss=2.123, simple_loss=0.2198, pruned_loss=0.02909, codebook_loss=19.84, over 7011.00 frames.], tot_loss[loss=2.155, simple_loss=0.2583, pruned_loss=0.04164, codebook_loss=19.85, over 1111105.51 frames.], batch size: 16, lr: 8.87e-04
+2022-05-27 17:55:02,848 INFO [train.py:823] (2/4) Epoch 19, batch 350, loss[loss=2.221, simple_loss=0.3091, pruned_loss=0.07307, codebook_loss=19.94, over 7320.00 frames.], tot_loss[loss=2.147, simple_loss=0.2591, pruned_loss=0.04169, codebook_loss=19.75, over 1178466.06 frames.], batch size: 18, lr: 8.85e-04
+2022-05-27 17:55:43,640 INFO [train.py:823] (2/4) Epoch 19, batch 400, loss[loss=2.105, simple_loss=0.2198, pruned_loss=0.02603, codebook_loss=19.69, over 7001.00 frames.], tot_loss[loss=2.147, simple_loss=0.2593, pruned_loss=0.04191, codebook_loss=19.76, over 1236206.86 frames.], batch size: 16, lr: 8.84e-04
+2022-05-27 17:56:23,356 INFO [train.py:823] (2/4) Epoch 19, batch 450, loss[loss=2.275, simple_loss=0.2801, pruned_loss=0.05436, codebook_loss=20.81, over 7150.00 frames.], tot_loss[loss=2.152, simple_loss=0.2599, pruned_loss=0.04237, codebook_loss=19.8, over 1278898.29 frames.], batch size: 23, lr: 8.83e-04
+2022-05-27 17:57:06,158 INFO [train.py:823] (2/4) Epoch 19, batch 500, loss[loss=2.141, simple_loss=0.2742, pruned_loss=0.04471, codebook_loss=19.59, over 6465.00 frames.], tot_loss[loss=2.151, simple_loss=0.2595, pruned_loss=0.04244, codebook_loss=19.78, over 1312390.03 frames.], batch size: 34, lr: 8.82e-04
+2022-05-27 17:57:47,326 INFO [train.py:823] (2/4) Epoch 19, batch 550, loss[loss=2.112, simple_loss=0.2513, pruned_loss=0.04386, codebook_loss=19.42, over 7422.00 frames.], tot_loss[loss=2.151, simple_loss=0.2595, pruned_loss=0.04232, codebook_loss=19.79, over 1335245.73 frames.], batch size: 18, lr: 8.81e-04
+2022-05-27 17:58:27,532 INFO [train.py:823] (2/4) Epoch 19, batch 600, loss[loss=2.551, simple_loss=0.2752, pruned_loss=0.06967, codebook_loss=23.44, over 7097.00 frames.], tot_loss[loss=2.153, simple_loss=0.26, pruned_loss=0.04234, codebook_loss=19.81, over 1354306.13 frames.], batch size: 19, lr: 8.80e-04
+2022-05-27 17:59:07,242 INFO [train.py:823] (2/4) Epoch 19, batch 650, loss[loss=2.071, simple_loss=0.2341, pruned_loss=0.03256, codebook_loss=19.21, over 7424.00 frames.], tot_loss[loss=2.155, simple_loss=0.2598, pruned_loss=0.04231, codebook_loss=19.83, over 1367830.08 frames.], batch size: 18, lr: 8.78e-04
+2022-05-27 17:59:47,321 INFO [train.py:823] (2/4) Epoch 19, batch 700, loss[loss=2.05, simple_loss=0.2609, pruned_loss=0.03225, codebook_loss=18.87, over 7064.00 frames.], tot_loss[loss=2.154, simple_loss=0.2592, pruned_loss=0.04198, codebook_loss=19.82, over 1378997.05 frames.], batch size: 26, lr: 8.77e-04
+2022-05-27 18:00:27,377 INFO [train.py:823] (2/4) Epoch 19, batch 750, loss[loss=2.101, simple_loss=0.2532, pruned_loss=0.03128, codebook_loss=19.43, over 7381.00 frames.], tot_loss[loss=2.152, simple_loss=0.2585, pruned_loss=0.04143, codebook_loss=19.82, over 1389289.23 frames.], batch size: 21, lr: 8.76e-04
+2022-05-27 18:01:07,500 INFO [train.py:823] (2/4) Epoch 19, batch 800, loss[loss=2.181, simple_loss=0.2701, pruned_loss=0.04385, codebook_loss=20.02, over 7319.00 frames.], tot_loss[loss=2.155, simple_loss=0.2591, pruned_loss=0.04163, codebook_loss=19.84, over 1398456.13 frames.], batch size: 22, lr: 8.75e-04
+2022-05-27 18:01:47,287 INFO [train.py:823] (2/4) Epoch 19, batch 850, loss[loss=2.216, simple_loss=0.2677, pruned_loss=0.04052, codebook_loss=20.41, over 7375.00 frames.], tot_loss[loss=2.163, simple_loss=0.2596, pruned_loss=0.04189, codebook_loss=19.91, over 1403197.16 frames.], batch size: 21, lr: 8.74e-04
+2022-05-27 18:02:27,153 INFO [train.py:823] (2/4) Epoch 19, batch 900, loss[loss=2.142, simple_loss=0.2647, pruned_loss=0.04253, codebook_loss=19.67, over 6967.00 frames.], tot_loss[loss=2.165, simple_loss=0.2607, pruned_loss=0.04253, codebook_loss=19.92, over 1395032.89 frames.], batch size: 26, lr: 8.73e-04
+2022-05-27 18:03:20,008 INFO [train.py:823] (2/4) Epoch 20, batch 0, loss[loss=2.141, simple_loss=0.2802, pruned_loss=0.04751, codebook_loss=19.53, over 6521.00 frames.], tot_loss[loss=2.141, simple_loss=0.2802, pruned_loss=0.04751, codebook_loss=19.53, over 6521.00 frames.], batch size: 34, lr: 8.51e-04
+2022-05-27 18:04:00,437 INFO [train.py:823] (2/4) Epoch 20, batch 50, loss[loss=2.034, simple_loss=0.2235, pruned_loss=0.03445, codebook_loss=18.88, over 7305.00 frames.], tot_loss[loss=2.13, simple_loss=0.2555, pruned_loss=0.03831, codebook_loss=19.64, over 321703.22 frames.], batch size: 18, lr: 8.49e-04
+2022-05-27 18:04:40,156 INFO [train.py:823] (2/4) Epoch 20, batch 100, loss[loss=2.135, simple_loss=0.2757, pruned_loss=0.05243, codebook_loss=19.45, over 4915.00 frames.], tot_loss[loss=2.138, simple_loss=0.2567, pruned_loss=0.0402, codebook_loss=19.7, over 561817.25 frames.], batch size: 48, lr: 8.48e-04
+2022-05-27 18:05:20,186 INFO [train.py:823] (2/4) Epoch 20, batch 150, loss[loss=2.121, simple_loss=0.2298, pruned_loss=0.03789, codebook_loss=19.68, over 7293.00 frames.], tot_loss[loss=2.149, simple_loss=0.2574, pruned_loss=0.04083, codebook_loss=19.79, over 750736.87 frames.], batch size: 17, lr: 8.47e-04
+2022-05-27 18:05:59,933 INFO [train.py:823] (2/4) Epoch 20, batch 200, loss[loss=2.001, simple_loss=0.2188, pruned_loss=0.01627, codebook_loss=18.75, over 7019.00 frames.], tot_loss[loss=2.136, simple_loss=0.2566, pruned_loss=0.03995, codebook_loss=19.68, over 902253.19 frames.], batch size: 16, lr: 8.46e-04
+2022-05-27 18:06:40,075 INFO [train.py:823] (2/4) Epoch 20, batch 250, loss[loss=2.351, simple_loss=0.2529, pruned_loss=0.04681, codebook_loss=21.78, over 7308.00 frames.], tot_loss[loss=2.156, simple_loss=0.2561, pruned_loss=0.04041, codebook_loss=19.88, over 1016895.13 frames.], batch size: 18, lr: 8.45e-04
+2022-05-27 18:07:19,806 INFO [train.py:823] (2/4) Epoch 20, batch 300, loss[loss=2.03, simple_loss=0.2521, pruned_loss=0.0352, codebook_loss=18.68, over 7311.00 frames.], tot_loss[loss=2.154, simple_loss=0.2567, pruned_loss=0.04024, codebook_loss=19.85, over 1106603.27 frames.], batch size: 22, lr: 8.44e-04
+2022-05-27 18:08:00,085 INFO [train.py:823] (2/4) Epoch 20, batch 350, loss[loss=2.082, simple_loss=0.2623, pruned_loss=0.04136, codebook_loss=19.09, over 7195.00 frames.], tot_loss[loss=2.152, simple_loss=0.2575, pruned_loss=0.04056, codebook_loss=19.83, over 1176208.37 frames.], batch size: 20, lr: 8.43e-04
+2022-05-27 18:08:40,162 INFO [train.py:823] (2/4) Epoch 20, batch 400, loss[loss=2.089, simple_loss=0.2562, pruned_loss=0.03264, codebook_loss=19.29, over 7150.00 frames.], tot_loss[loss=2.155, simple_loss=0.2578, pruned_loss=0.04067, codebook_loss=19.86, over 1230923.61 frames.], batch size: 23, lr: 8.42e-04
+2022-05-27 18:09:20,012 INFO [train.py:823] (2/4) Epoch 20, batch 450, loss[loss=2.043, simple_loss=0.2203, pruned_loss=0.02603, codebook_loss=19.07, over 7164.00 frames.], tot_loss[loss=2.15, simple_loss=0.2579, pruned_loss=0.04033, codebook_loss=19.81, over 1268809.60 frames.], batch size: 17, lr: 8.41e-04
+2022-05-27 18:09:59,752 INFO [train.py:823] (2/4) Epoch 20, batch 500, loss[loss=2.179, simple_loss=0.257, pruned_loss=0.0419, codebook_loss=20.09, over 7016.00 frames.], tot_loss[loss=2.152, simple_loss=0.2585, pruned_loss=0.04041, codebook_loss=19.82, over 1304286.68 frames.], batch size: 17, lr: 8.40e-04
+2022-05-27 18:10:40,034 INFO [train.py:823] (2/4) Epoch 20, batch 550, loss[loss=2.125, simple_loss=0.2763, pruned_loss=0.04416, codebook_loss=19.42, over 7139.00 frames.], tot_loss[loss=2.149, simple_loss=0.2574, pruned_loss=0.04029, codebook_loss=19.8, over 1332727.88 frames.], batch size: 23, lr: 8.39e-04
+2022-05-27 18:11:19,647 INFO [train.py:823] (2/4) Epoch 20, batch 600, loss[loss=2.701, simple_loss=0.2867, pruned_loss=0.06676, codebook_loss=24.91, over 7110.00 frames.], tot_loss[loss=2.155, simple_loss=0.2578, pruned_loss=0.04049, codebook_loss=19.86, over 1347978.24 frames.], batch size: 18, lr: 8.38e-04
+2022-05-27 18:11:59,837 INFO [train.py:823] (2/4) Epoch 20, batch 650, loss[loss=2.138, simple_loss=0.2847, pruned_loss=0.04219, codebook_loss=19.53, over 7003.00 frames.], tot_loss[loss=2.147, simple_loss=0.2567, pruned_loss=0.03984, codebook_loss=19.79, over 1365280.94 frames.], batch size: 29, lr: 8.37e-04
+2022-05-27 18:12:39,831 INFO [train.py:823] (2/4) Epoch 20, batch 700, loss[loss=2.055, simple_loss=0.2544, pruned_loss=0.03297, codebook_loss=18.95, over 7098.00 frames.], tot_loss[loss=2.146, simple_loss=0.2565, pruned_loss=0.03977, codebook_loss=19.78, over 1379694.80 frames.], batch size: 18, lr: 8.36e-04
+2022-05-27 18:13:20,092 INFO [train.py:823] (2/4) Epoch 20, batch 750, loss[loss=2.097, simple_loss=0.2658, pruned_loss=0.03841, codebook_loss=19.26, over 7283.00 frames.], tot_loss[loss=2.144, simple_loss=0.2558, pruned_loss=0.03993, codebook_loss=19.76, over 1389019.14 frames.], batch size: 21, lr: 8.35e-04
+2022-05-27 18:13:59,603 INFO [train.py:823] (2/4) Epoch 20, batch 800, loss[loss=1.99, simple_loss=0.2222, pruned_loss=0.01736, codebook_loss=18.62, over 7421.00 frames.], tot_loss[loss=2.142, simple_loss=0.2569, pruned_loss=0.03984, codebook_loss=19.73, over 1397374.09 frames.], batch size: 18, lr: 8.34e-04
+2022-05-27 18:14:41,123 INFO [train.py:823] (2/4) Epoch 20, batch 850, loss[loss=2.092, simple_loss=0.2642, pruned_loss=0.04419, codebook_loss=19.16, over 7067.00 frames.], tot_loss[loss=2.145, simple_loss=0.2567, pruned_loss=0.04007, codebook_loss=19.76, over 1401145.81 frames.], batch size: 26, lr: 8.33e-04
+2022-05-27 18:15:20,824 INFO [train.py:823] (2/4) Epoch 20, batch 900, loss[loss=2.003, simple_loss=0.2141, pruned_loss=0.02817, codebook_loss=18.68, over 6739.00 frames.], tot_loss[loss=2.145, simple_loss=0.257, pruned_loss=0.04036, codebook_loss=19.76, over 1398991.58 frames.], batch size: 15, lr: 8.31e-04
+2022-05-27 18:16:14,157 INFO [train.py:823] (2/4) Epoch 21, batch 0, loss[loss=2.06, simple_loss=0.2369, pruned_loss=0.03179, codebook_loss=19.1, over 7198.00 frames.], tot_loss[loss=2.06, simple_loss=0.2369, pruned_loss=0.03179, codebook_loss=19.1, over 7198.00 frames.], batch size: 18, lr: 8.11e-04
+2022-05-27 18:16:54,221 INFO [train.py:823] (2/4) Epoch 21, batch 50, loss[loss=2.089, simple_loss=0.27, pruned_loss=0.04149, codebook_loss=19.13, over 7211.00 frames.], tot_loss[loss=2.138, simple_loss=0.2567, pruned_loss=0.04056, codebook_loss=19.69, over 318253.31 frames.], batch size: 25, lr: 8.10e-04
+2022-05-27 18:17:33,851 INFO [train.py:823] (2/4) Epoch 21, batch 100, loss[loss=2.103, simple_loss=0.2628, pruned_loss=0.03191, codebook_loss=19.4, over 6457.00 frames.], tot_loss[loss=2.117, simple_loss=0.2524, pruned_loss=0.03806, codebook_loss=19.53, over 561620.87 frames.], batch size: 34, lr: 8.09e-04
+2022-05-27 18:18:14,078 INFO [train.py:823] (2/4) Epoch 21, batch 150, loss[loss=2.097, simple_loss=0.251, pruned_loss=0.03814, codebook_loss=19.33, over 7278.00 frames.], tot_loss[loss=2.119, simple_loss=0.2522, pruned_loss=0.03844, codebook_loss=19.54, over 755228.02 frames.], batch size: 20, lr: 8.08e-04
+2022-05-27 18:18:54,127 INFO [train.py:823] (2/4) Epoch 21, batch 200, loss[loss=2.096, simple_loss=0.2097, pruned_loss=0.03244, codebook_loss=19.59, over 7314.00 frames.], tot_loss[loss=2.122, simple_loss=0.2533, pruned_loss=0.03868, codebook_loss=19.56, over 904320.01 frames.], batch size: 18, lr: 8.07e-04
+2022-05-27 18:19:34,327 INFO [train.py:823] (2/4) Epoch 21, batch 250, loss[loss=2.14, simple_loss=0.2669, pruned_loss=0.05038, codebook_loss=19.56, over 7284.00 frames.], tot_loss[loss=2.122, simple_loss=0.2546, pruned_loss=0.03925, codebook_loss=19.55, over 1011675.67 frames.], batch size: 20, lr: 8.06e-04
+2022-05-27 18:20:13,830 INFO [train.py:823] (2/4) Epoch 21, batch 300, loss[loss=2.106, simple_loss=0.2584, pruned_loss=0.03717, codebook_loss=19.4, over 6465.00 frames.], tot_loss[loss=2.128, simple_loss=0.2552, pruned_loss=0.039, codebook_loss=19.61, over 1101161.62 frames.], batch size: 34, lr: 8.05e-04
+2022-05-27 18:20:53,798 INFO [train.py:823] (2/4) Epoch 21, batch 350, loss[loss=2.096, simple_loss=0.2583, pruned_loss=0.04111, codebook_loss=19.26, over 7427.00 frames.], tot_loss[loss=2.128, simple_loss=0.2557, pruned_loss=0.03896, codebook_loss=19.61, over 1171318.72 frames.], batch size: 22, lr: 8.04e-04
+2022-05-27 18:21:36,252 INFO [train.py:823] (2/4) Epoch 21, batch 400, loss[loss=2.023, simple_loss=0.2221, pruned_loss=0.02234, codebook_loss=18.89, over 7283.00 frames.], tot_loss[loss=2.13, simple_loss=0.2559, pruned_loss=0.03923, codebook_loss=19.63, over 1225941.17 frames.], batch size: 17, lr: 8.03e-04
+2022-05-27 18:22:17,599 INFO [train.py:823] (2/4) Epoch 21, batch 450, loss[loss=2.046, simple_loss=0.2586, pruned_loss=0.02882, codebook_loss=18.87, over 7190.00 frames.], tot_loss[loss=2.132, simple_loss=0.2552, pruned_loss=0.03917, codebook_loss=19.65, over 1270024.51 frames.], batch size: 21, lr: 8.02e-04
+2022-05-27 18:22:57,213 INFO [train.py:823] (2/4) Epoch 21, batch 500, loss[loss=2.167, simple_loss=0.257, pruned_loss=0.0476, codebook_loss=19.91, over 7189.00 frames.], tot_loss[loss=2.127, simple_loss=0.2545, pruned_loss=0.03867, codebook_loss=19.61, over 1303395.62 frames.], batch size: 18, lr: 8.01e-04
+2022-05-27 18:23:37,552 INFO [train.py:823] (2/4) Epoch 21, batch 550, loss[loss=2.077, simple_loss=0.2631, pruned_loss=0.03451, codebook_loss=19.11, over 7367.00 frames.], tot_loss[loss=2.124, simple_loss=0.2541, pruned_loss=0.03864, codebook_loss=19.59, over 1334899.12 frames.], batch size: 21, lr: 8.00e-04
+2022-05-27 18:24:17,347 INFO [train.py:823] (2/4) Epoch 21, batch 600, loss[loss=2.211, simple_loss=0.2794, pruned_loss=0.05102, codebook_loss=20.2, over 6433.00 frames.], tot_loss[loss=2.134, simple_loss=0.2562, pruned_loss=0.04013, codebook_loss=19.65, over 1353011.94 frames.], batch size: 34, lr: 8.00e-04
+2022-05-27 18:24:57,532 INFO [train.py:823] (2/4) Epoch 21, batch 650, loss[loss=2.175, simple_loss=0.2636, pruned_loss=0.05226, codebook_loss=19.91, over 7291.00 frames.], tot_loss[loss=2.139, simple_loss=0.2568, pruned_loss=0.04057, codebook_loss=19.7, over 1369277.73 frames.], batch size: 22, lr: 7.99e-04
+2022-05-27 18:25:36,982 INFO [train.py:823] (2/4) Epoch 21, batch 700, loss[loss=2.149, simple_loss=0.2533, pruned_loss=0.03616, codebook_loss=19.86, over 7197.00 frames.], tot_loss[loss=2.143, simple_loss=0.2574, pruned_loss=0.04106, codebook_loss=19.73, over 1379958.74 frames.], batch size: 20, lr: 7.98e-04
+2022-05-27 18:26:16,778 INFO [train.py:823] (2/4) Epoch 21, batch 750, loss[loss=2.482, simple_loss=0.3192, pruned_loss=0.09427, codebook_loss=22.28, over 7199.00 frames.], tot_loss[loss=2.136, simple_loss=0.2558, pruned_loss=0.04035, codebook_loss=19.68, over 1377666.62 frames.], batch size: 25, lr: 7.97e-04
+2022-05-27 18:26:56,250 INFO [train.py:823] (2/4) Epoch 21, batch 800, loss[loss=2.127, simple_loss=0.2553, pruned_loss=0.03964, codebook_loss=19.59, over 7333.00 frames.], tot_loss[loss=2.134, simple_loss=0.256, pruned_loss=0.03982, codebook_loss=19.66, over 1383349.38 frames.], batch size: 23, lr: 7.96e-04
+2022-05-27 18:27:36,610 INFO [train.py:823] (2/4) Epoch 21, batch 850, loss[loss=2.243, simple_loss=0.2626, pruned_loss=0.04253, codebook_loss=20.69, over 7195.00 frames.], tot_loss[loss=2.133, simple_loss=0.2555, pruned_loss=0.03952, codebook_loss=19.66, over 1388115.85 frames.], batch size: 20, lr: 7.95e-04
+2022-05-27 18:28:15,979 INFO [train.py:823] (2/4) Epoch 21, batch 900, loss[loss=2.008, simple_loss=0.2488, pruned_loss=0.0299, codebook_loss=18.54, over 7375.00 frames.], tot_loss[loss=2.13, simple_loss=0.2554, pruned_loss=0.03926, codebook_loss=19.63, over 1387285.08 frames.], batch size: 20, lr: 7.94e-04
+2022-05-27 18:29:10,581 INFO [train.py:823] (2/4) Epoch 22, batch 0, loss[loss=2, simple_loss=0.2461, pruned_loss=0.02712, codebook_loss=18.5, over 7383.00 frames.], tot_loss[loss=2, simple_loss=0.2461, pruned_loss=0.02712, codebook_loss=18.5, over 7383.00 frames.], batch size: 21, lr: 7.75e-04
+2022-05-27 18:29:50,461 INFO [train.py:823] (2/4) Epoch 22, batch 50, loss[loss=2.23, simple_loss=0.287, pruned_loss=0.05241, codebook_loss=20.34, over 7175.00 frames.], tot_loss[loss=2.091, simple_loss=0.2481, pruned_loss=0.0355, codebook_loss=19.32, over 321529.77 frames.], batch size: 22, lr: 7.74e-04
+2022-05-27 18:30:30,773 INFO [train.py:823] (2/4) Epoch 22, batch 100, loss[loss=2.125, simple_loss=0.2663, pruned_loss=0.03136, codebook_loss=19.61, over 7102.00 frames.], tot_loss[loss=2.103, simple_loss=0.2515, pruned_loss=0.03727, codebook_loss=19.4, over 567431.07 frames.], batch size: 20, lr: 7.73e-04
+2022-05-27 18:31:10,245 INFO [train.py:823] (2/4) Epoch 22, batch 150, loss[loss=2.272, simple_loss=0.2726, pruned_loss=0.06522, codebook_loss=20.7, over 4798.00 frames.], tot_loss[loss=2.12, simple_loss=0.2542, pruned_loss=0.03853, codebook_loss=19.54, over 753995.38 frames.], batch size: 46, lr: 7.73e-04
+2022-05-27 18:31:50,152 INFO [train.py:823] (2/4) Epoch 22, batch 200, loss[loss=2.132, simple_loss=0.2845, pruned_loss=0.04884, codebook_loss=19.41, over 7107.00 frames.], tot_loss[loss=2.122, simple_loss=0.2545, pruned_loss=0.03904, codebook_loss=19.56, over 899182.54 frames.], batch size: 20, lr: 7.72e-04
+2022-05-27 18:32:29,931 INFO [train.py:823] (2/4) Epoch 22, batch 250, loss[loss=2.27, simple_loss=0.2326, pruned_loss=0.03403, codebook_loss=21.2, over 7089.00 frames.], tot_loss[loss=2.117, simple_loss=0.2536, pruned_loss=0.0382, codebook_loss=19.53, over 1016989.90 frames.], batch size: 18, lr: 7.71e-04
+2022-05-27 18:33:09,999 INFO [train.py:823] (2/4) Epoch 22, batch 300, loss[loss=2.002, simple_loss=0.2442, pruned_loss=0.02702, codebook_loss=18.53, over 7182.00 frames.], tot_loss[loss=2.115, simple_loss=0.2534, pruned_loss=0.03798, codebook_loss=19.5, over 1103050.86 frames.], batch size: 18, lr: 7.70e-04
+2022-05-27 18:33:49,731 INFO [train.py:823] (2/4) Epoch 22, batch 350, loss[loss=2.121, simple_loss=0.2601, pruned_loss=0.03568, codebook_loss=19.55, over 6946.00 frames.], tot_loss[loss=2.114, simple_loss=0.2542, pruned_loss=0.03841, codebook_loss=19.49, over 1175054.00 frames.], batch size: 29, lr: 7.69e-04
+2022-05-27 18:34:29,886 INFO [train.py:823] (2/4) Epoch 22, batch 400, loss[loss=2.076, simple_loss=0.2803, pruned_loss=0.03204, codebook_loss=19.04, over 7185.00 frames.], tot_loss[loss=2.118, simple_loss=0.2542, pruned_loss=0.03892, codebook_loss=19.52, over 1231049.13 frames.], batch size: 21, lr: 7.68e-04
+2022-05-27 18:35:09,673 INFO [train.py:823] (2/4) Epoch 22, batch 450, loss[loss=2.174, simple_loss=0.2373, pruned_loss=0.04151, codebook_loss=20.13, over 7209.00 frames.], tot_loss[loss=2.118, simple_loss=0.2538, pruned_loss=0.03868, codebook_loss=19.53, over 1277095.01 frames.], batch size: 16, lr: 7.67e-04
+2022-05-27 18:35:49,510 INFO [train.py:823] (2/4) Epoch 22, batch 500, loss[loss=2.197, simple_loss=0.2591, pruned_loss=0.04687, codebook_loss=20.21, over 6662.00 frames.], tot_loss[loss=2.119, simple_loss=0.2538, pruned_loss=0.03887, codebook_loss=19.53, over 1303554.27 frames.], batch size: 34, lr: 7.66e-04
+2022-05-27 18:36:29,479 INFO [train.py:823] (2/4) Epoch 22, batch 550, loss[loss=2.103, simple_loss=0.2839, pruned_loss=0.05003, codebook_loss=19.11, over 6926.00 frames.], tot_loss[loss=2.118, simple_loss=0.2531, pruned_loss=0.03846, codebook_loss=19.53, over 1330271.59 frames.], batch size: 29, lr: 7.65e-04
+2022-05-27 18:37:09,849 INFO [train.py:823] (2/4) Epoch 22, batch 600, loss[loss=2.075, simple_loss=0.2341, pruned_loss=0.0374, codebook_loss=19.21, over 7006.00 frames.], tot_loss[loss=2.117, simple_loss=0.2525, pruned_loss=0.03775, codebook_loss=19.53, over 1349062.84 frames.], batch size: 17, lr: 7.65e-04
+2022-05-27 18:37:49,493 INFO [train.py:823] (2/4) Epoch 22, batch 650, loss[loss=2.15, simple_loss=0.2578, pruned_loss=0.03993, codebook_loss=19.81, over 7108.00 frames.], tot_loss[loss=2.122, simple_loss=0.2533, pruned_loss=0.03858, codebook_loss=19.57, over 1358461.34 frames.], batch size: 20, lr: 7.64e-04
+2022-05-27 18:38:29,555 INFO [train.py:823] (2/4) Epoch 22, batch 700, loss[loss=2.089, simple_loss=0.2632, pruned_loss=0.04098, codebook_loss=19.17, over 7104.00 frames.], tot_loss[loss=2.12, simple_loss=0.2534, pruned_loss=0.03837, codebook_loss=19.55, over 1371147.83 frames.], batch size: 19, lr: 7.63e-04
+2022-05-27 18:39:10,333 INFO [train.py:823] (2/4) Epoch 22, batch 750, loss[loss=2.069, simple_loss=0.2278, pruned_loss=0.02867, codebook_loss=19.27, over 7017.00 frames.], tot_loss[loss=2.116, simple_loss=0.2532, pruned_loss=0.03809, codebook_loss=19.51, over 1380876.96 frames.], batch size: 16, lr: 7.62e-04
+2022-05-27 18:39:50,600 INFO [train.py:823] (2/4) Epoch 22, batch 800, loss[loss=2.152, simple_loss=0.2548, pruned_loss=0.03742, codebook_loss=19.87, over 7373.00 frames.], tot_loss[loss=2.118, simple_loss=0.2528, pruned_loss=0.03773, codebook_loss=19.54, over 1390801.03 frames.], batch size: 20, lr: 7.61e-04
+2022-05-27 18:40:30,195 INFO [train.py:823] (2/4) Epoch 22, batch 850, loss[loss=2.092, simple_loss=0.2606, pruned_loss=0.03684, codebook_loss=19.25, over 6417.00 frames.], tot_loss[loss=2.11, simple_loss=0.2523, pruned_loss=0.03711, codebook_loss=19.47, over 1399257.20 frames.], batch size: 34, lr: 7.60e-04
+2022-05-27 18:41:10,120 INFO [train.py:823] (2/4) Epoch 22, batch 900, loss[loss=2.124, simple_loss=0.2901, pruned_loss=0.05395, codebook_loss=19.25, over 7149.00 frames.], tot_loss[loss=2.11, simple_loss=0.2533, pruned_loss=0.03765, codebook_loss=19.46, over 1403749.54 frames.], batch size: 23, lr: 7.59e-04
+2022-05-27 18:42:03,936 INFO [train.py:823] (2/4) Epoch 23, batch 0, loss[loss=2.028, simple_loss=0.22, pruned_loss=0.03063, codebook_loss=18.87, over 6798.00 frames.], tot_loss[loss=2.028, simple_loss=0.22, pruned_loss=0.03063, codebook_loss=18.87, over 6798.00 frames.], batch size: 15, lr: 7.42e-04
+2022-05-27 18:42:44,097 INFO [train.py:823] (2/4) Epoch 23, batch 50, loss[loss=2.343, simple_loss=0.273, pruned_loss=0.05342, codebook_loss=21.53, over 7375.00 frames.], tot_loss[loss=2.155, simple_loss=0.2527, pruned_loss=0.0389, codebook_loss=19.89, over 320400.55 frames.], batch size: 21, lr: 7.41e-04
+2022-05-27 18:43:23,804 INFO [train.py:823] (2/4) Epoch 23, batch 100, loss[loss=2.242, simple_loss=0.2459, pruned_loss=0.03061, codebook_loss=20.88, over 7379.00 frames.], tot_loss[loss=2.121, simple_loss=0.2536, pruned_loss=0.03857, codebook_loss=19.55, over 562691.38 frames.], batch size: 20, lr: 7.41e-04
+2022-05-27 18:44:03,965 INFO [train.py:823] (2/4) Epoch 23, batch 150, loss[loss=2.072, simple_loss=0.2202, pruned_loss=0.03393, codebook_loss=19.28, over 7289.00 frames.], tot_loss[loss=2.116, simple_loss=0.2536, pruned_loss=0.03818, codebook_loss=19.51, over 752503.41 frames.], batch size: 18, lr: 7.40e-04
+2022-05-27 18:44:43,909 INFO [train.py:823] (2/4) Epoch 23, batch 200, loss[loss=2.117, simple_loss=0.2748, pruned_loss=0.05223, codebook_loss=19.27, over 4960.00 frames.], tot_loss[loss=2.114, simple_loss=0.2534, pruned_loss=0.03796, codebook_loss=19.49, over 899592.05 frames.], batch size: 47, lr: 7.39e-04
+2022-05-27 18:45:24,175 INFO [train.py:823] (2/4) Epoch 23, batch 250, loss[loss=2.258, simple_loss=0.2367, pruned_loss=0.0412, codebook_loss=20.99, over 7098.00 frames.], tot_loss[loss=2.118, simple_loss=0.2535, pruned_loss=0.03794, codebook_loss=19.53, over 1019271.30 frames.], batch size: 18, lr: 7.38e-04
+2022-05-27 18:46:03,751 INFO [train.py:823] (2/4) Epoch 23, batch 300, loss[loss=2.044, simple_loss=0.2579, pruned_loss=0.03722, codebook_loss=18.78, over 7299.00 frames.], tot_loss[loss=2.112, simple_loss=0.2544, pruned_loss=0.03803, codebook_loss=19.47, over 1112204.45 frames.], batch size: 22, lr: 7.37e-04
+2022-05-27 18:46:48,079 INFO [train.py:823] (2/4) Epoch 23, batch 350, loss[loss=2.235, simple_loss=0.266, pruned_loss=0.05559, codebook_loss=20.46, over 7279.00 frames.], tot_loss[loss=2.105, simple_loss=0.2534, pruned_loss=0.03761, codebook_loss=19.41, over 1183018.63 frames.], batch size: 20, lr: 7.36e-04
+2022-05-27 18:47:28,146 INFO [train.py:823] (2/4) Epoch 23, batch 400, loss[loss=2.282, simple_loss=0.2325, pruned_loss=0.0348, codebook_loss=21.31, over 7303.00 frames.], tot_loss[loss=2.108, simple_loss=0.2522, pruned_loss=0.03707, codebook_loss=19.45, over 1235253.10 frames.], batch size: 17, lr: 7.36e-04
+2022-05-27 18:48:08,277 INFO [train.py:823] (2/4) Epoch 23, batch 450, loss[loss=2.2, simple_loss=0.2559, pruned_loss=0.03888, codebook_loss=20.33, over 4900.00 frames.], tot_loss[loss=2.111, simple_loss=0.2516, pruned_loss=0.03668, codebook_loss=19.48, over 1273782.47 frames.], batch size: 47, lr: 7.35e-04
+2022-05-27 18:48:47,872 INFO [train.py:823] (2/4) Epoch 23, batch 500, loss[loss=2.339, simple_loss=0.264, pruned_loss=0.0413, codebook_loss=21.66, over 6654.00 frames.], tot_loss[loss=2.114, simple_loss=0.2527, pruned_loss=0.03724, codebook_loss=19.51, over 1302548.31 frames.], batch size: 34, lr: 7.34e-04
+2022-05-27 18:49:28,074 INFO [train.py:823] (2/4) Epoch 23, batch 550, loss[loss=2.084, simple_loss=0.286, pruned_loss=0.04416, codebook_loss=18.97, over 7231.00 frames.], tot_loss[loss=2.113, simple_loss=0.2531, pruned_loss=0.03689, codebook_loss=19.5, over 1333553.45 frames.], batch size: 24, lr: 7.33e-04
+2022-05-27 18:50:07,712 INFO [train.py:823] (2/4) Epoch 23, batch 600, loss[loss=2.065, simple_loss=0.2577, pruned_loss=0.03895, codebook_loss=18.97, over 4936.00 frames.], tot_loss[loss=2.123, simple_loss=0.253, pruned_loss=0.0375, codebook_loss=19.59, over 1349643.48 frames.], batch size: 46, lr: 7.32e-04
+2022-05-27 18:50:47,673 INFO [train.py:823] (2/4) Epoch 23, batch 650, loss[loss=2.063, simple_loss=0.2252, pruned_loss=0.0291, codebook_loss=19.21, over 7099.00 frames.], tot_loss[loss=2.115, simple_loss=0.2527, pruned_loss=0.03734, codebook_loss=19.52, over 1364095.52 frames.], batch size: 19, lr: 7.32e-04
+2022-05-27 18:51:27,277 INFO [train.py:823] (2/4) Epoch 23, batch 700, loss[loss=2.077, simple_loss=0.2257, pruned_loss=0.03376, codebook_loss=19.31, over 7003.00 frames.], tot_loss[loss=2.117, simple_loss=0.2525, pruned_loss=0.03762, codebook_loss=19.54, over 1370864.20 frames.], batch size: 16, lr: 7.31e-04
+2022-05-27 18:52:07,629 INFO [train.py:823] (2/4) Epoch 23, batch 750, loss[loss=2.163, simple_loss=0.2654, pruned_loss=0.05219, codebook_loss=19.78, over 4925.00 frames.], tot_loss[loss=2.115, simple_loss=0.2525, pruned_loss=0.0375, codebook_loss=19.52, over 1375867.84 frames.], batch size: 48, lr: 7.30e-04
+2022-05-27 18:52:47,389 INFO [train.py:823] (2/4) Epoch 23, batch 800, loss[loss=2.147, simple_loss=0.2312, pruned_loss=0.03243, codebook_loss=19.99, over 7187.00 frames.], tot_loss[loss=2.112, simple_loss=0.2517, pruned_loss=0.03716, codebook_loss=19.49, over 1387544.87 frames.], batch size: 18, lr: 7.29e-04
+2022-05-27 18:53:27,288 INFO [train.py:823] (2/4) Epoch 23, batch 850, loss[loss=2.113, simple_loss=0.2605, pruned_loss=0.03849, codebook_loss=19.44, over 7148.00 frames.], tot_loss[loss=2.11, simple_loss=0.252, pruned_loss=0.03722, codebook_loss=19.47, over 1395425.13 frames.], batch size: 23, lr: 7.28e-04
+2022-05-27 18:54:07,048 INFO [train.py:823] (2/4) Epoch 23, batch 900, loss[loss=2.365, simple_loss=0.2575, pruned_loss=0.04593, codebook_loss=21.91, over 7013.00 frames.], tot_loss[loss=2.111, simple_loss=0.2514, pruned_loss=0.03727, codebook_loss=19.48, over 1400723.56 frames.], batch size: 17, lr: 7.28e-04
+2022-05-27 18:55:01,296 INFO [train.py:823] (2/4) Epoch 24, batch 0, loss[loss=2.005, simple_loss=0.2216, pruned_loss=0.0285, codebook_loss=18.65, over 7313.00 frames.], tot_loss[loss=2.005, simple_loss=0.2216, pruned_loss=0.0285, codebook_loss=18.65, over 7313.00 frames.], batch size: 18, lr: 7.12e-04
+2022-05-27 18:55:40,715 INFO [train.py:823] (2/4) Epoch 24, batch 50, loss[loss=2.072, simple_loss=0.245, pruned_loss=0.03273, codebook_loss=19.17, over 7157.00 frames.], tot_loss[loss=2.082, simple_loss=0.2526, pruned_loss=0.03549, codebook_loss=19.2, over 319565.04 frames.], batch size: 17, lr: 7.11e-04
+2022-05-27 18:56:20,790 INFO [train.py:823] (2/4) Epoch 24, batch 100, loss[loss=2.078, simple_loss=0.2411, pruned_loss=0.03282, codebook_loss=19.25, over 6548.00 frames.], tot_loss[loss=2.094, simple_loss=0.2531, pruned_loss=0.03777, codebook_loss=19.3, over 560300.64 frames.], batch size: 34, lr: 7.10e-04
+2022-05-27 18:57:00,439 INFO [train.py:823] (2/4) Epoch 24, batch 150, loss[loss=2.271, simple_loss=0.2519, pruned_loss=0.04067, codebook_loss=21.05, over 6996.00 frames.], tot_loss[loss=2.093, simple_loss=0.2534, pruned_loss=0.03765, codebook_loss=19.29, over 750894.71 frames.], batch size: 29, lr: 7.10e-04
+2022-05-27 18:57:40,640 INFO [train.py:823] (2/4) Epoch 24, batch 200, loss[loss=2.009, simple_loss=0.2565, pruned_loss=0.03085, codebook_loss=18.5, over 7280.00 frames.], tot_loss[loss=2.086, simple_loss=0.2522, pruned_loss=0.0366, codebook_loss=19.23, over 900466.69 frames.], batch size: 21, lr: 7.09e-04
+2022-05-27 18:58:20,124 INFO [train.py:823] (2/4) Epoch 24, batch 250, loss[loss=2.308, simple_loss=0.2259, pruned_loss=0.03996, codebook_loss=21.55, over 7312.00 frames.], tot_loss[loss=2.091, simple_loss=0.2508, pruned_loss=0.03601, codebook_loss=19.3, over 1016035.25 frames.], batch size: 17, lr: 7.08e-04
+2022-05-27 18:59:00,235 INFO [train.py:823] (2/4) Epoch 24, batch 300, loss[loss=2.109, simple_loss=0.2673, pruned_loss=0.03621, codebook_loss=19.39, over 7331.00 frames.], tot_loss[loss=2.103, simple_loss=0.2514, pruned_loss=0.0366, codebook_loss=19.4, over 1099920.42 frames.], batch size: 23, lr: 7.07e-04
+2022-05-27 18:59:40,282 INFO [train.py:823] (2/4) Epoch 24, batch 350, loss[loss=2.068, simple_loss=0.2389, pruned_loss=0.03648, codebook_loss=19.12, over 7300.00 frames.], tot_loss[loss=2.102, simple_loss=0.2508, pruned_loss=0.03648, codebook_loss=19.4, over 1175014.31 frames.], batch size: 17, lr: 7.07e-04
+2022-05-27 19:00:20,408 INFO [train.py:823] (2/4) Epoch 24, batch 400, loss[loss=2.143, simple_loss=0.2725, pruned_loss=0.0403, codebook_loss=19.66, over 7325.00 frames.], tot_loss[loss=2.099, simple_loss=0.25, pruned_loss=0.03662, codebook_loss=19.37, over 1226960.18 frames.], batch size: 23, lr: 7.06e-04
+2022-05-27 19:01:00,226 INFO [train.py:823] (2/4) Epoch 24, batch 450, loss[loss=2.211, simple_loss=0.2373, pruned_loss=0.04014, codebook_loss=20.52, over 7192.00 frames.], tot_loss[loss=2.098, simple_loss=0.2501, pruned_loss=0.03626, codebook_loss=19.36, over 1268047.42 frames.], batch size: 18, lr: 7.05e-04
+2022-05-27 19:01:40,605 INFO [train.py:823] (2/4) Epoch 24, batch 500, loss[loss=2.078, simple_loss=0.2644, pruned_loss=0.03903, codebook_loss=19.07, over 7275.00 frames.], tot_loss[loss=2.097, simple_loss=0.2509, pruned_loss=0.03643, codebook_loss=19.36, over 1303730.98 frames.], batch size: 21, lr: 7.04e-04
+2022-05-27 19:02:20,506 INFO [train.py:823] (2/4) Epoch 24, batch 550, loss[loss=2.028, simple_loss=0.2466, pruned_loss=0.02249, codebook_loss=18.83, over 6451.00 frames.], tot_loss[loss=2.099, simple_loss=0.2514, pruned_loss=0.03663, codebook_loss=19.37, over 1327863.35 frames.], batch size: 34, lr: 7.04e-04
+2022-05-27 19:03:01,845 INFO [train.py:823] (2/4) Epoch 24, batch 600, loss[loss=1.992, simple_loss=0.2635, pruned_loss=0.03052, codebook_loss=18.3, over 7168.00 frames.], tot_loss[loss=2.095, simple_loss=0.2513, pruned_loss=0.03596, codebook_loss=19.34, over 1346853.40 frames.], batch size: 23, lr: 7.03e-04
+2022-05-27 19:03:41,808 INFO [train.py:823] (2/4) Epoch 24, batch 650, loss[loss=2.068, simple_loss=0.2538, pruned_loss=0.02991, codebook_loss=19.11, over 7099.00 frames.], tot_loss[loss=2.095, simple_loss=0.2517, pruned_loss=0.03615, codebook_loss=19.33, over 1359080.63 frames.], batch size: 19, lr: 7.02e-04
+2022-05-27 19:04:21,931 INFO [train.py:823] (2/4) Epoch 24, batch 700, loss[loss=1.999, simple_loss=0.264, pruned_loss=0.03816, codebook_loss=18.29, over 7168.00 frames.], tot_loss[loss=2.094, simple_loss=0.2517, pruned_loss=0.03611, codebook_loss=19.32, over 1371980.17 frames.], batch size: 22, lr: 7.01e-04
+2022-05-27 19:05:01,653 INFO [train.py:823] (2/4) Epoch 24, batch 750, loss[loss=1.982, simple_loss=0.2536, pruned_loss=0.02297, codebook_loss=18.32, over 7108.00 frames.], tot_loss[loss=2.091, simple_loss=0.2515, pruned_loss=0.03605, codebook_loss=19.3, over 1384815.43 frames.], batch size: 20, lr: 7.01e-04
+2022-05-27 19:05:41,785 INFO [train.py:823] (2/4) Epoch 24, batch 800, loss[loss=2.213, simple_loss=0.2285, pruned_loss=0.0375, codebook_loss=20.61, over 6828.00 frames.], tot_loss[loss=2.098, simple_loss=0.2513, pruned_loss=0.03608, codebook_loss=19.36, over 1391688.33 frames.], batch size: 15, lr: 7.00e-04
+2022-05-27 19:06:21,572 INFO [train.py:823] (2/4) Epoch 24, batch 850, loss[loss=2.072, simple_loss=0.2566, pruned_loss=0.03961, codebook_loss=19.04, over 7112.00 frames.], tot_loss[loss=2.097, simple_loss=0.2513, pruned_loss=0.03651, codebook_loss=19.35, over 1395324.35 frames.], batch size: 20, lr: 6.99e-04
+2022-05-27 19:07:01,704 INFO [train.py:823] (2/4) Epoch 24, batch 900, loss[loss=2.23, simple_loss=0.2721, pruned_loss=0.04446, codebook_loss=20.5, over 6556.00 frames.], tot_loss[loss=2.101, simple_loss=0.252, pruned_loss=0.03689, codebook_loss=19.38, over 1398309.93 frames.], batch size: 34, lr: 6.98e-04
+2022-05-27 19:07:42,329 INFO [train.py:823] (2/4) Epoch 24, batch 950, loss[loss=2.087, simple_loss=0.2419, pruned_loss=0.03784, codebook_loss=19.29, over 7098.00 frames.], tot_loss[loss=2.107, simple_loss=0.2524, pruned_loss=0.03737, codebook_loss=19.43, over 1395538.50 frames.], batch size: 18, lr: 6.98e-04
+2022-05-27 19:07:57,262 INFO [train.py:823] (2/4) Epoch 25, batch 0, loss[loss=1.946, simple_loss=0.2449, pruned_loss=0.0192, codebook_loss=18.05, over 7274.00 frames.], tot_loss[loss=1.946, simple_loss=0.2449, pruned_loss=0.0192, codebook_loss=18.05, over 7274.00 frames.], batch size: 21, lr: 6.84e-04
+2022-05-27 19:08:37,516 INFO [train.py:823] (2/4) Epoch 25, batch 50, loss[loss=2.109, simple_loss=0.2213, pruned_loss=0.03586, codebook_loss=19.63, over 7284.00 frames.], tot_loss[loss=2.095, simple_loss=0.2513, pruned_loss=0.03625, codebook_loss=19.33, over 324545.41 frames.], batch size: 17, lr: 6.83e-04
+2022-05-27 19:09:17,673 INFO [train.py:823] (2/4) Epoch 25, batch 100, loss[loss=2.132, simple_loss=0.2513, pruned_loss=0.03913, codebook_loss=19.67, over 6806.00 frames.], tot_loss[loss=2.095, simple_loss=0.2498, pruned_loss=0.03652, codebook_loss=19.33, over 564672.71 frames.], batch size: 15, lr: 6.82e-04
+2022-05-27 19:09:58,095 INFO [train.py:823] (2/4) Epoch 25, batch 150, loss[loss=2.107, simple_loss=0.266, pruned_loss=0.03549, codebook_loss=19.39, over 7311.00 frames.], tot_loss[loss=2.096, simple_loss=0.2482, pruned_loss=0.03558, codebook_loss=19.36, over 759596.81 frames.], batch size: 22, lr: 6.82e-04
+2022-05-27 19:10:38,128 INFO [train.py:823] (2/4) Epoch 25, batch 200, loss[loss=2.119, simple_loss=0.2677, pruned_loss=0.04782, codebook_loss=19.37, over 7289.00 frames.], tot_loss[loss=2.086, simple_loss=0.2495, pruned_loss=0.03537, codebook_loss=19.26, over 912078.67 frames.], batch size: 21, lr: 6.81e-04
+2022-05-27 19:11:21,035 INFO [train.py:823] (2/4) Epoch 25, batch 250, loss[loss=2.094, simple_loss=0.2248, pruned_loss=0.03515, codebook_loss=19.46, over 7300.00 frames.], tot_loss[loss=2.079, simple_loss=0.2491, pruned_loss=0.03549, codebook_loss=19.19, over 1024214.63 frames.], batch size: 17, lr: 6.80e-04
+2022-05-27 19:12:03,741 INFO [train.py:823] (2/4) Epoch 25, batch 300, loss[loss=1.942, simple_loss=0.245, pruned_loss=0.02355, codebook_loss=17.96, over 7282.00 frames.], tot_loss[loss=2.081, simple_loss=0.249, pruned_loss=0.03564, codebook_loss=19.2, over 1117686.34 frames.], batch size: 21, lr: 6.80e-04
+2022-05-27 19:12:48,182 INFO [train.py:823] (2/4) Epoch 25, batch 350, loss[loss=2.36, simple_loss=0.2808, pruned_loss=0.05695, codebook_loss=21.62, over 7135.00 frames.], tot_loss[loss=2.078, simple_loss=0.2493, pruned_loss=0.03535, codebook_loss=19.18, over 1183891.47 frames.], batch size: 23, lr: 6.79e-04
+2022-05-27 19:13:30,505 INFO [train.py:823] (2/4) Epoch 25, batch 400, loss[loss=2.077, simple_loss=0.2669, pruned_loss=0.04324, codebook_loss=19, over 7214.00 frames.], tot_loss[loss=2.082, simple_loss=0.2515, pruned_loss=0.03629, codebook_loss=19.2, over 1239862.21 frames.], batch size: 25, lr: 6.78e-04
+2022-05-27 19:14:15,056 INFO [train.py:823] (2/4) Epoch 25, batch 450, loss[loss=2.03, simple_loss=0.2112, pruned_loss=0.02693, codebook_loss=18.97, over 7207.00 frames.], tot_loss[loss=2.089, simple_loss=0.2523, pruned_loss=0.03675, codebook_loss=19.27, over 1271775.27 frames.], batch size: 16, lr: 6.77e-04
+2022-05-27 19:14:56,677 INFO [train.py:823] (2/4) Epoch 25, batch 500, loss[loss=2.102, simple_loss=0.21, pruned_loss=0.03992, codebook_loss=19.57, over 6988.00 frames.], tot_loss[loss=2.089, simple_loss=0.2514, pruned_loss=0.03667, codebook_loss=19.26, over 1304391.06 frames.], batch size: 16, lr: 6.77e-04
+2022-05-27 19:15:42,065 INFO [train.py:823] (2/4) Epoch 25, batch 550, loss[loss=2.544, simple_loss=0.2841, pruned_loss=0.06652, codebook_loss=23.35, over 7188.00 frames.], tot_loss[loss=2.099, simple_loss=0.2509, pruned_loss=0.03686, codebook_loss=19.37, over 1330813.61 frames.], batch size: 21, lr: 6.76e-04
+2022-05-27 19:16:23,991 INFO [train.py:823] (2/4) Epoch 25, batch 600, loss[loss=2.029, simple_loss=0.2539, pruned_loss=0.02457, codebook_loss=18.78, over 7284.00 frames.], tot_loss[loss=2.097, simple_loss=0.2496, pruned_loss=0.03615, codebook_loss=19.36, over 1343552.27 frames.], batch size: 21, lr: 6.75e-04
+2022-05-27 19:17:05,137 INFO [train.py:823] (2/4) Epoch 25, batch 650, loss[loss=2.177, simple_loss=0.233, pruned_loss=0.02507, codebook_loss=20.35, over 7282.00 frames.], tot_loss[loss=2.095, simple_loss=0.2495, pruned_loss=0.03567, codebook_loss=19.35, over 1358380.89 frames.], batch size: 20, lr: 6.75e-04
+2022-05-27 19:17:47,805 INFO [train.py:823] (2/4) Epoch 25, batch 700, loss[loss=2.066, simple_loss=0.2256, pruned_loss=0.03014, codebook_loss=19.23, over 7153.00 frames.], tot_loss[loss=2.092, simple_loss=0.2495, pruned_loss=0.03564, codebook_loss=19.32, over 1370804.39 frames.], batch size: 17, lr: 6.74e-04
+2022-05-27 19:18:28,138 INFO [train.py:823] (2/4) Epoch 25, batch 750, loss[loss=2.081, simple_loss=0.2398, pruned_loss=0.03539, codebook_loss=19.25, over 7382.00 frames.], tot_loss[loss=2.088, simple_loss=0.2488, pruned_loss=0.03538, codebook_loss=19.29, over 1378657.19 frames.], batch size: 20, lr: 6.73e-04
+2022-05-27 19:19:08,117 INFO [train.py:823] (2/4) Epoch 25, batch 800, loss[loss=1.995, simple_loss=0.2496, pruned_loss=0.03019, codebook_loss=18.4, over 7180.00 frames.], tot_loss[loss=2.087, simple_loss=0.2484, pruned_loss=0.03546, codebook_loss=19.27, over 1390359.75 frames.], batch size: 21, lr: 6.73e-04
+2022-05-27 19:19:48,337 INFO [train.py:823] (2/4) Epoch 25, batch 850, loss[loss=2.264, simple_loss=0.2438, pruned_loss=0.04376, codebook_loss=20.98, over 7191.00 frames.], tot_loss[loss=2.089, simple_loss=0.2491, pruned_loss=0.03573, codebook_loss=19.29, over 1395545.93 frames.], batch size: 18, lr: 6.72e-04
+2022-05-27 19:20:27,863 INFO [train.py:823] (2/4) Epoch 25, batch 900, loss[loss=2.05, simple_loss=0.2587, pruned_loss=0.03395, codebook_loss=18.87, over 6548.00 frames.], tot_loss[loss=2.086, simple_loss=0.2489, pruned_loss=0.03556, codebook_loss=19.26, over 1394530.97 frames.], batch size: 34, lr: 6.71e-04
+2022-05-27 19:21:22,331 INFO [train.py:823] (2/4) Epoch 26, batch 0, loss[loss=2.363, simple_loss=0.2526, pruned_loss=0.03891, codebook_loss=21.98, over 7313.00 frames.], tot_loss[loss=2.363, simple_loss=0.2526, pruned_loss=0.03891, codebook_loss=21.98, over 7313.00 frames.], batch size: 18, lr: 6.58e-04
+2022-05-27 19:22:03,656 INFO [train.py:823] (2/4) Epoch 26, batch 50, loss[loss=2.007, simple_loss=0.2373, pruned_loss=0.02957, codebook_loss=18.58, over 7370.00 frames.], tot_loss[loss=2.063, simple_loss=0.2438, pruned_loss=0.03224, codebook_loss=19.09, over 323536.76 frames.], batch size: 20, lr: 6.57e-04
+2022-05-27 19:22:43,977 INFO [train.py:823] (2/4) Epoch 26, batch 100, loss[loss=1.982, simple_loss=0.2489, pruned_loss=0.03134, codebook_loss=18.26, over 7232.00 frames.], tot_loss[loss=2.072, simple_loss=0.2469, pruned_loss=0.03388, codebook_loss=19.15, over 567390.63 frames.], batch size: 25, lr: 6.56e-04
+2022-05-27 19:23:23,782 INFO [train.py:823] (2/4) Epoch 26, batch 150, loss[loss=2.088, simple_loss=0.2574, pruned_loss=0.04189, codebook_loss=19.17, over 7180.00 frames.], tot_loss[loss=2.079, simple_loss=0.2475, pruned_loss=0.03488, codebook_loss=19.21, over 753680.71 frames.], batch size: 25, lr: 6.56e-04
+2022-05-27 19:24:03,986 INFO [train.py:823] (2/4) Epoch 26, batch 200, loss[loss=2.233, simple_loss=0.2353, pruned_loss=0.03964, codebook_loss=20.76, over 7094.00 frames.], tot_loss[loss=2.085, simple_loss=0.2485, pruned_loss=0.03537, codebook_loss=19.25, over 900490.38 frames.], batch size: 18, lr: 6.55e-04
+2022-05-27 19:24:43,863 INFO [train.py:823] (2/4) Epoch 26, batch 250, loss[loss=2.01, simple_loss=0.2638, pruned_loss=0.03354, codebook_loss=18.44, over 7420.00 frames.], tot_loss[loss=2.087, simple_loss=0.2494, pruned_loss=0.03561, codebook_loss=19.27, over 1015893.39 frames.], batch size: 22, lr: 6.55e-04
+2022-05-27 19:25:27,420 INFO [train.py:823] (2/4) Epoch 26, batch 300, loss[loss=2.087, simple_loss=0.2275, pruned_loss=0.02526, codebook_loss=19.48, over 7122.00 frames.], tot_loss[loss=2.089, simple_loss=0.249, pruned_loss=0.03566, codebook_loss=19.29, over 1106097.86 frames.], batch size: 20, lr: 6.54e-04
+2022-05-27 19:26:07,488 INFO [train.py:823] (2/4) Epoch 26, batch 350, loss[loss=2.436, simple_loss=0.2676, pruned_loss=0.04578, codebook_loss=22.56, over 6468.00 frames.], tot_loss[loss=2.088, simple_loss=0.2487, pruned_loss=0.03555, codebook_loss=19.28, over 1177950.06 frames.], batch size: 34, lr: 6.53e-04
+2022-05-27 19:26:47,591 INFO [train.py:823] (2/4) Epoch 26, batch 400, loss[loss=2.033, simple_loss=0.2631, pruned_loss=0.04281, codebook_loss=18.59, over 7154.00 frames.], tot_loss[loss=2.079, simple_loss=0.2483, pruned_loss=0.03494, codebook_loss=19.2, over 1234215.13 frames.], batch size: 23, lr: 6.53e-04
+2022-05-27 19:27:28,683 INFO [train.py:823] (2/4) Epoch 26, batch 450, loss[loss=2.074, simple_loss=0.2694, pruned_loss=0.03974, codebook_loss=19, over 7190.00 frames.], tot_loss[loss=2.083, simple_loss=0.2486, pruned_loss=0.03509, codebook_loss=19.23, over 1273571.42 frames.], batch size: 21, lr: 6.52e-04
+2022-05-27 19:28:08,952 INFO [train.py:823] (2/4) Epoch 26, batch 500, loss[loss=2.072, simple_loss=0.2652, pruned_loss=0.03338, codebook_loss=19.06, over 6972.00 frames.], tot_loss[loss=2.082, simple_loss=0.2486, pruned_loss=0.03488, codebook_loss=19.23, over 1303778.05 frames.], batch size: 26, lr: 6.51e-04
+2022-05-27 19:28:49,087 INFO [train.py:823] (2/4) Epoch 26, batch 550, loss[loss=1.983, simple_loss=0.2156, pruned_loss=0.02713, codebook_loss=18.48, over 7001.00 frames.], tot_loss[loss=2.08, simple_loss=0.2476, pruned_loss=0.03447, codebook_loss=19.22, over 1326494.98 frames.], batch size: 16, lr: 6.51e-04
+2022-05-27 19:29:29,453 INFO [train.py:823] (2/4) Epoch 26, batch 600, loss[loss=2.127, simple_loss=0.2699, pruned_loss=0.03965, codebook_loss=19.52, over 7293.00 frames.], tot_loss[loss=2.076, simple_loss=0.2481, pruned_loss=0.03451, codebook_loss=19.18, over 1347001.42 frames.], batch size: 22, lr: 6.50e-04
+2022-05-27 19:30:09,299 INFO [train.py:823] (2/4) Epoch 26, batch 650, loss[loss=2.274, simple_loss=0.2662, pruned_loss=0.03793, codebook_loss=21.02, over 7339.00 frames.], tot_loss[loss=2.076, simple_loss=0.2473, pruned_loss=0.03462, codebook_loss=19.18, over 1355991.18 frames.], batch size: 23, lr: 6.49e-04
+2022-05-27 19:30:49,389 INFO [train.py:823] (2/4) Epoch 26, batch 700, loss[loss=2.161, simple_loss=0.246, pruned_loss=0.0446, codebook_loss=19.93, over 7026.00 frames.], tot_loss[loss=2.083, simple_loss=0.2483, pruned_loss=0.03499, codebook_loss=19.24, over 1369656.08 frames.], batch size: 26, lr: 6.49e-04
+2022-05-27 19:31:29,084 INFO [train.py:823] (2/4) Epoch 26, batch 750, loss[loss=2.049, simple_loss=0.2501, pruned_loss=0.02908, codebook_loss=18.95, over 7287.00 frames.], tot_loss[loss=2.088, simple_loss=0.2489, pruned_loss=0.0355, codebook_loss=19.28, over 1373264.90 frames.], batch size: 19, lr: 6.48e-04
+2022-05-27 19:32:09,215 INFO [train.py:823] (2/4) Epoch 26, batch 800, loss[loss=2.001, simple_loss=0.2167, pruned_loss=0.02472, codebook_loss=18.68, over 6788.00 frames.], tot_loss[loss=2.087, simple_loss=0.2487, pruned_loss=0.03542, codebook_loss=19.28, over 1381290.91 frames.], batch size: 15, lr: 6.47e-04
+2022-05-27 19:32:49,177 INFO [train.py:823] (2/4) Epoch 26, batch 850, loss[loss=2.039, simple_loss=0.2331, pruned_loss=0.03565, codebook_loss=18.86, over 6758.00 frames.], tot_loss[loss=2.078, simple_loss=0.2478, pruned_loss=0.0344, codebook_loss=19.2, over 1392900.52 frames.], batch size: 15, lr: 6.47e-04
+2022-05-27 19:33:29,196 INFO [train.py:823] (2/4) Epoch 26, batch 900, loss[loss=2.066, simple_loss=0.2229, pruned_loss=0.03076, codebook_loss=19.24, over 7024.00 frames.], tot_loss[loss=2.081, simple_loss=0.2485, pruned_loss=0.03447, codebook_loss=19.22, over 1395156.66 frames.], batch size: 17, lr: 6.46e-04
+2022-05-27 19:34:22,987 INFO [train.py:823] (2/4) Epoch 27, batch 0, loss[loss=2.048, simple_loss=0.2268, pruned_loss=0.03078, codebook_loss=19.04, over 7185.00 frames.], tot_loss[loss=2.048, simple_loss=0.2268, pruned_loss=0.03078, codebook_loss=19.04, over 7185.00 frames.], batch size: 18, lr: 6.34e-04
+2022-05-27 19:35:03,224 INFO [train.py:823] (2/4) Epoch 27, batch 50, loss[loss=2.054, simple_loss=0.2353, pruned_loss=0.03411, codebook_loss=19.02, over 7194.00 frames.], tot_loss[loss=2.058, simple_loss=0.2448, pruned_loss=0.03367, codebook_loss=19.01, over 321532.86 frames.], batch size: 18, lr: 6.33e-04
+2022-05-27 19:35:42,728 INFO [train.py:823] (2/4) Epoch 27, batch 100, loss[loss=2.027, simple_loss=0.258, pruned_loss=0.04974, codebook_loss=18.48, over 7222.00 frames.], tot_loss[loss=2.054, simple_loss=0.2471, pruned_loss=0.03411, codebook_loss=18.96, over 563690.85 frames.], batch size: 25, lr: 6.32e-04
+2022-05-27 19:36:26,847 INFO [train.py:823] (2/4) Epoch 27, batch 150, loss[loss=2.047, simple_loss=0.2202, pruned_loss=0.02314, codebook_loss=19.14, over 7295.00 frames.], tot_loss[loss=2.053, simple_loss=0.2473, pruned_loss=0.03399, codebook_loss=18.95, over 753281.56 frames.], batch size: 18, lr: 6.32e-04
+2022-05-27 19:37:06,339 INFO [train.py:823] (2/4) Epoch 27, batch 200, loss[loss=2.129, simple_loss=0.2711, pruned_loss=0.03642, codebook_loss=19.57, over 7424.00 frames.], tot_loss[loss=2.069, simple_loss=0.2495, pruned_loss=0.03537, codebook_loss=19.09, over 900275.41 frames.], batch size: 22, lr: 6.31e-04
+2022-05-27 19:37:46,510 INFO [train.py:823] (2/4) Epoch 27, batch 250, loss[loss=1.976, simple_loss=0.2144, pruned_loss=0.02459, codebook_loss=18.44, over 7024.00 frames.], tot_loss[loss=2.069, simple_loss=0.2496, pruned_loss=0.03519, codebook_loss=19.09, over 1013352.41 frames.], batch size: 17, lr: 6.31e-04
+2022-05-27 19:38:26,678 INFO [train.py:823] (2/4) Epoch 27, batch 300, loss[loss=2.034, simple_loss=0.2583, pruned_loss=0.02598, codebook_loss=18.78, over 7378.00 frames.], tot_loss[loss=2.072, simple_loss=0.2486, pruned_loss=0.0346, codebook_loss=19.13, over 1106925.30 frames.], batch size: 21, lr: 6.30e-04
+2022-05-27 19:39:06,898 INFO [train.py:823] (2/4) Epoch 27, batch 350, loss[loss=1.946, simple_loss=0.2081, pruned_loss=0.01895, codebook_loss=18.23, over 7294.00 frames.], tot_loss[loss=2.08, simple_loss=0.248, pruned_loss=0.03459, codebook_loss=19.21, over 1177097.05 frames.], batch size: 19, lr: 6.29e-04
+2022-05-27 19:39:46,734 INFO [train.py:823] (2/4) Epoch 27, batch 400, loss[loss=2.027, simple_loss=0.2525, pruned_loss=0.03452, codebook_loss=18.66, over 7281.00 frames.], tot_loss[loss=2.083, simple_loss=0.2476, pruned_loss=0.03452, codebook_loss=19.25, over 1231517.99 frames.], batch size: 20, lr: 6.29e-04
+2022-05-27 19:40:27,012 INFO [train.py:823] (2/4) Epoch 27, batch 450, loss[loss=2.124, simple_loss=0.2632, pruned_loss=0.04581, codebook_loss=19.47, over 4945.00 frames.], tot_loss[loss=2.081, simple_loss=0.2473, pruned_loss=0.03488, codebook_loss=19.23, over 1275178.40 frames.], batch size: 46, lr: 6.28e-04
+2022-05-27 19:41:06,533 INFO [train.py:823] (2/4) Epoch 27, batch 500, loss[loss=2.695, simple_loss=0.3271, pruned_loss=0.1023, codebook_loss=24.29, over 7151.00 frames.], tot_loss[loss=2.084, simple_loss=0.2474, pruned_loss=0.03506, codebook_loss=19.25, over 1299885.96 frames.], batch size: 23, lr: 6.28e-04
+2022-05-27 19:41:46,717 INFO [train.py:823] (2/4) Epoch 27, batch 550, loss[loss=2.027, simple_loss=0.234, pruned_loss=0.02839, codebook_loss=18.82, over 7275.00 frames.], tot_loss[loss=2.083, simple_loss=0.2488, pruned_loss=0.03526, codebook_loss=19.23, over 1328787.99 frames.], batch size: 20, lr: 6.27e-04
+2022-05-27 19:42:26,683 INFO [train.py:823] (2/4) Epoch 27, batch 600, loss[loss=2.028, simple_loss=0.2339, pruned_loss=0.0306, codebook_loss=18.8, over 7303.00 frames.], tot_loss[loss=2.081, simple_loss=0.2483, pruned_loss=0.03513, codebook_loss=19.21, over 1355176.92 frames.], batch size: 18, lr: 6.26e-04
+2022-05-27 19:43:06,778 INFO [train.py:823] (2/4) Epoch 27, batch 650, loss[loss=2.042, simple_loss=0.2227, pruned_loss=0.02415, codebook_loss=19.07, over 7188.00 frames.], tot_loss[loss=2.076, simple_loss=0.2484, pruned_loss=0.03483, codebook_loss=19.17, over 1374172.60 frames.], batch size: 19, lr: 6.26e-04
+2022-05-27 19:43:46,840 INFO [train.py:823] (2/4) Epoch 27, batch 700, loss[loss=2.106, simple_loss=0.2512, pruned_loss=0.02885, codebook_loss=19.52, over 7379.00 frames.], tot_loss[loss=2.078, simple_loss=0.2481, pruned_loss=0.03449, codebook_loss=19.19, over 1384558.41 frames.], batch size: 21, lr: 6.25e-04
+2022-05-27 19:44:26,940 INFO [train.py:823] (2/4) Epoch 27, batch 750, loss[loss=2.239, simple_loss=0.24, pruned_loss=0.03379, codebook_loss=20.85, over 7187.00 frames.], tot_loss[loss=2.08, simple_loss=0.2479, pruned_loss=0.03463, codebook_loss=19.22, over 1391737.70 frames.], batch size: 19, lr: 6.25e-04
+2022-05-27 19:45:06,634 INFO [train.py:823] (2/4) Epoch 27, batch 800, loss[loss=2.115, simple_loss=0.2526, pruned_loss=0.04504, codebook_loss=19.44, over 7164.00 frames.], tot_loss[loss=2.084, simple_loss=0.2482, pruned_loss=0.03527, codebook_loss=19.25, over 1393803.02 frames.], batch size: 23, lr: 6.24e-04
+2022-05-27 19:45:46,840 INFO [train.py:823] (2/4) Epoch 27, batch 850, loss[loss=1.947, simple_loss=0.2337, pruned_loss=0.02353, codebook_loss=18.07, over 7114.00 frames.], tot_loss[loss=2.078, simple_loss=0.247, pruned_loss=0.03504, codebook_loss=19.2, over 1396931.08 frames.], batch size: 20, lr: 6.23e-04
+2022-05-27 19:46:26,344 INFO [train.py:823] (2/4) Epoch 27, batch 900, loss[loss=2.012, simple_loss=0.2302, pruned_loss=0.02846, codebook_loss=18.69, over 7292.00 frames.], tot_loss[loss=2.078, simple_loss=0.2471, pruned_loss=0.03508, codebook_loss=19.19, over 1398837.82 frames.], batch size: 17, lr: 6.23e-04
+2022-05-27 19:47:20,729 INFO [train.py:823] (2/4) Epoch 28, batch 0, loss[loss=1.946, simple_loss=0.2399, pruned_loss=0.02711, codebook_loss=17.99, over 7199.00 frames.], tot_loss[loss=1.946, simple_loss=0.2399, pruned_loss=0.02711, codebook_loss=17.99, over 7199.00 frames.], batch size: 20, lr: 6.11e-04
+2022-05-27 19:48:00,117 INFO [train.py:823] (2/4) Epoch 28, batch 50, loss[loss=2.235, simple_loss=0.2556, pruned_loss=0.03858, codebook_loss=20.69, over 7107.00 frames.], tot_loss[loss=2.042, simple_loss=0.2427, pruned_loss=0.03318, codebook_loss=18.88, over 315571.51 frames.], batch size: 20, lr: 6.11e-04
+2022-05-27 19:48:40,432 INFO [train.py:823] (2/4) Epoch 28, batch 100, loss[loss=2.008, simple_loss=0.2597, pruned_loss=0.04629, codebook_loss=18.32, over 7026.00 frames.], tot_loss[loss=2.046, simple_loss=0.2456, pruned_loss=0.03335, codebook_loss=18.89, over 560884.03 frames.], batch size: 26, lr: 6.10e-04
+2022-05-27 19:49:20,191 INFO [train.py:823] (2/4) Epoch 28, batch 150, loss[loss=2.034, simple_loss=0.2476, pruned_loss=0.03765, codebook_loss=18.73, over 4691.00 frames.], tot_loss[loss=2.055, simple_loss=0.2459, pruned_loss=0.03389, codebook_loss=18.98, over 749279.09 frames.], batch size: 46, lr: 6.09e-04
+2022-05-27 19:50:00,330 INFO [train.py:823] (2/4) Epoch 28, batch 200, loss[loss=2.283, simple_loss=0.2471, pruned_loss=0.0331, codebook_loss=21.26, over 7191.00 frames.], tot_loss[loss=2.051, simple_loss=0.2449, pruned_loss=0.0335, codebook_loss=18.95, over 899370.59 frames.], batch size: 20, lr: 6.09e-04
+2022-05-27 19:50:40,295 INFO [train.py:823] (2/4) Epoch 28, batch 250, loss[loss=2.03, simple_loss=0.2316, pruned_loss=0.02883, codebook_loss=18.86, over 7329.00 frames.], tot_loss[loss=2.046, simple_loss=0.2447, pruned_loss=0.03297, codebook_loss=18.91, over 1015218.17 frames.], batch size: 23, lr: 6.08e-04
+2022-05-27 19:51:22,051 INFO [train.py:823] (2/4) Epoch 28, batch 300, loss[loss=2.079, simple_loss=0.2711, pruned_loss=0.04568, codebook_loss=18.98, over 6897.00 frames.], tot_loss[loss=2.049, simple_loss=0.2447, pruned_loss=0.03308, codebook_loss=18.94, over 1104447.21 frames.], batch size: 29, lr: 6.08e-04
+2022-05-27 19:52:01,910 INFO [train.py:823] (2/4) Epoch 28, batch 350, loss[loss=2.223, simple_loss=0.2888, pruned_loss=0.05499, codebook_loss=20.23, over 7313.00 frames.], tot_loss[loss=2.052, simple_loss=0.245, pruned_loss=0.03301, codebook_loss=18.97, over 1174300.12 frames.], batch size: 23, lr: 6.07e-04
+2022-05-27 19:52:42,297 INFO [train.py:823] (2/4) Epoch 28, batch 400, loss[loss=1.97, simple_loss=0.2586, pruned_loss=0.0307, codebook_loss=18.1, over 7288.00 frames.], tot_loss[loss=2.06, simple_loss=0.2458, pruned_loss=0.03359, codebook_loss=19.04, over 1229072.75 frames.], batch size: 21, lr: 6.07e-04
+2022-05-27 19:53:21,977 INFO [train.py:823] (2/4) Epoch 28, batch 450, loss[loss=2.051, simple_loss=0.2694, pruned_loss=0.03736, codebook_loss=18.79, over 6937.00 frames.], tot_loss[loss=2.059, simple_loss=0.2456, pruned_loss=0.03363, codebook_loss=19.03, over 1269734.63 frames.], batch size: 29, lr: 6.06e-04
+2022-05-27 19:54:02,151 INFO [train.py:823] (2/4) Epoch 28, batch 500, loss[loss=2.017, simple_loss=0.2494, pruned_loss=0.02762, codebook_loss=18.65, over 6993.00 frames.], tot_loss[loss=2.057, simple_loss=0.2456, pruned_loss=0.03389, codebook_loss=19.01, over 1306191.02 frames.], batch size: 29, lr: 6.06e-04
+2022-05-27 19:54:41,595 INFO [train.py:823] (2/4) Epoch 28, batch 550, loss[loss=1.981, simple_loss=0.248, pruned_loss=0.0346, codebook_loss=18.22, over 7104.00 frames.], tot_loss[loss=2.061, simple_loss=0.2467, pruned_loss=0.03436, codebook_loss=19.03, over 1329663.74 frames.], batch size: 20, lr: 6.05e-04
+2022-05-27 19:55:21,360 INFO [train.py:823] (2/4) Epoch 28, batch 600, loss[loss=2.055, simple_loss=0.231, pruned_loss=0.02442, codebook_loss=19.15, over 7198.00 frames.], tot_loss[loss=2.058, simple_loss=0.2471, pruned_loss=0.0339, codebook_loss=19, over 1347420.39 frames.], batch size: 19, lr: 6.04e-04
+2022-05-27 19:56:01,408 INFO [train.py:823] (2/4) Epoch 28, batch 650, loss[loss=2.063, simple_loss=0.2391, pruned_loss=0.03276, codebook_loss=19.11, over 7285.00 frames.], tot_loss[loss=2.06, simple_loss=0.247, pruned_loss=0.03407, codebook_loss=19.02, over 1365606.54 frames.], batch size: 19, lr: 6.04e-04
+2022-05-27 19:56:41,251 INFO [train.py:823] (2/4) Epoch 28, batch 700, loss[loss=2.022, simple_loss=0.2517, pruned_loss=0.0408, codebook_loss=18.55, over 7312.00 frames.], tot_loss[loss=2.064, simple_loss=0.2469, pruned_loss=0.03403, codebook_loss=19.07, over 1375687.45 frames.], batch size: 18, lr: 6.03e-04
+2022-05-27 19:57:20,985 INFO [train.py:823] (2/4) Epoch 28, batch 750, loss[loss=2.072, simple_loss=0.2597, pruned_loss=0.03781, codebook_loss=19.04, over 5030.00 frames.], tot_loss[loss=2.066, simple_loss=0.2468, pruned_loss=0.034, codebook_loss=19.09, over 1382447.37 frames.], batch size: 46, lr: 6.03e-04
+2022-05-27 19:58:00,961 INFO [train.py:823] (2/4) Epoch 28, batch 800, loss[loss=2.042, simple_loss=0.2099, pruned_loss=0.02429, codebook_loss=19.13, over 7011.00 frames.], tot_loss[loss=2.067, simple_loss=0.2469, pruned_loss=0.03395, codebook_loss=19.1, over 1394235.40 frames.], batch size: 16, lr: 6.02e-04
+2022-05-27 19:58:40,823 INFO [train.py:823] (2/4) Epoch 28, batch 850, loss[loss=2.004, simple_loss=0.2456, pruned_loss=0.03145, codebook_loss=18.5, over 7378.00 frames.], tot_loss[loss=2.064, simple_loss=0.2471, pruned_loss=0.03375, codebook_loss=19.07, over 1398526.04 frames.], batch size: 21, lr: 6.02e-04
+2022-05-27 19:59:20,862 INFO [train.py:823] (2/4) Epoch 28, batch 900, loss[loss=2.162, simple_loss=0.2709, pruned_loss=0.04544, codebook_loss=19.81, over 7369.00 frames.], tot_loss[loss=2.063, simple_loss=0.2472, pruned_loss=0.03393, codebook_loss=19.05, over 1400121.21 frames.], batch size: 21, lr: 6.01e-04
+2022-05-27 20:00:14,127 INFO [train.py:823] (2/4) Epoch 29, batch 0, loss[loss=1.979, simple_loss=0.2455, pruned_loss=0.03196, codebook_loss=18.24, over 7004.00 frames.], tot_loss[loss=1.979, simple_loss=0.2455, pruned_loss=0.03196, codebook_loss=18.24, over 7004.00 frames.], batch size: 26, lr: 5.90e-04
+2022-05-27 20:00:55,867 INFO [train.py:823] (2/4) Epoch 29, batch 50, loss[loss=1.988, simple_loss=0.2385, pruned_loss=0.02166, codebook_loss=18.47, over 7277.00 frames.], tot_loss[loss=2.044, simple_loss=0.2426, pruned_loss=0.03238, codebook_loss=18.9, over 320513.08 frames.], batch size: 21, lr: 5.90e-04
+2022-05-27 20:01:38,100 INFO [train.py:823] (2/4) Epoch 29, batch 100, loss[loss=2.049, simple_loss=0.248, pruned_loss=0.03696, codebook_loss=18.88, over 7236.00 frames.], tot_loss[loss=2.042, simple_loss=0.2449, pruned_loss=0.03298, codebook_loss=18.86, over 569493.04 frames.], batch size: 24, lr: 5.89e-04
+2022-05-27 20:02:18,481 INFO [train.py:823] (2/4) Epoch 29, batch 150, loss[loss=2.122, simple_loss=0.2225, pruned_loss=0.02451, codebook_loss=19.87, over 7289.00 frames.], tot_loss[loss=2.051, simple_loss=0.2456, pruned_loss=0.03414, codebook_loss=18.95, over 760209.60 frames.], batch size: 19, lr: 5.89e-04
+2022-05-27 20:02:58,079 INFO [train.py:823] (2/4) Epoch 29, batch 200, loss[loss=1.977, simple_loss=0.2673, pruned_loss=0.03421, codebook_loss=18.09, over 7331.00 frames.], tot_loss[loss=2.05, simple_loss=0.2462, pruned_loss=0.03376, codebook_loss=18.93, over 899095.75 frames.], batch size: 23, lr: 5.88e-04
+2022-05-27 20:03:38,422 INFO [train.py:823] (2/4) Epoch 29, batch 250, loss[loss=2.043, simple_loss=0.2332, pruned_loss=0.03088, codebook_loss=18.95, over 7396.00 frames.], tot_loss[loss=2.043, simple_loss=0.2439, pruned_loss=0.03308, codebook_loss=18.88, over 1015129.75 frames.], batch size: 19, lr: 5.88e-04
+2022-05-27 20:04:18,164 INFO [train.py:823] (2/4) Epoch 29, batch 300, loss[loss=1.95, simple_loss=0.2343, pruned_loss=0.02288, codebook_loss=18.1, over 7275.00 frames.], tot_loss[loss=2.051, simple_loss=0.2452, pruned_loss=0.0338, codebook_loss=18.95, over 1104975.68 frames.], batch size: 20, lr: 5.87e-04
+2022-05-27 20:04:58,350 INFO [train.py:823] (2/4) Epoch 29, batch 350, loss[loss=2.069, simple_loss=0.2399, pruned_loss=0.03997, codebook_loss=19.09, over 7258.00 frames.], tot_loss[loss=2.057, simple_loss=0.2458, pruned_loss=0.03399, codebook_loss=19, over 1173793.27 frames.], batch size: 16, lr: 5.87e-04
+2022-05-27 20:05:37,839 INFO [train.py:823] (2/4) Epoch 29, batch 400, loss[loss=1.993, simple_loss=0.209, pruned_loss=0.03098, codebook_loss=18.58, over 7303.00 frames.], tot_loss[loss=2.056, simple_loss=0.2465, pruned_loss=0.03392, codebook_loss=18.99, over 1229026.89 frames.], batch size: 17, lr: 5.86e-04
+2022-05-27 20:06:18,206 INFO [train.py:823] (2/4) Epoch 29, batch 450, loss[loss=2.084, simple_loss=0.2207, pruned_loss=0.03184, codebook_loss=19.42, over 7089.00 frames.], tot_loss[loss=2.054, simple_loss=0.2459, pruned_loss=0.03381, codebook_loss=18.98, over 1269323.58 frames.], batch size: 18, lr: 5.85e-04
+2022-05-27 20:06:57,631 INFO [train.py:823] (2/4) Epoch 29, batch 500, loss[loss=2.019, simple_loss=0.2467, pruned_loss=0.02633, codebook_loss=18.69, over 7116.00 frames.], tot_loss[loss=2.055, simple_loss=0.2457, pruned_loss=0.03375, codebook_loss=18.99, over 1296739.95 frames.], batch size: 20, lr: 5.85e-04
+2022-05-27 20:07:37,744 INFO [train.py:823] (2/4) Epoch 29, batch 550, loss[loss=1.972, simple_loss=0.2516, pruned_loss=0.02656, codebook_loss=18.2, over 6515.00 frames.], tot_loss[loss=2.056, simple_loss=0.2459, pruned_loss=0.03374, codebook_loss=19, over 1326362.21 frames.], batch size: 34, lr: 5.84e-04
+2022-05-27 20:08:17,445 INFO [train.py:823] (2/4) Epoch 29, batch 600, loss[loss=2.017, simple_loss=0.2494, pruned_loss=0.03302, codebook_loss=18.59, over 6569.00 frames.], tot_loss[loss=2.063, simple_loss=0.2473, pruned_loss=0.03414, codebook_loss=19.05, over 1347099.55 frames.], batch size: 34, lr: 5.84e-04
+2022-05-27 20:08:57,754 INFO [train.py:823] (2/4) Epoch 29, batch 650, loss[loss=1.994, simple_loss=0.2492, pruned_loss=0.03239, codebook_loss=18.37, over 7372.00 frames.], tot_loss[loss=2.06, simple_loss=0.2471, pruned_loss=0.03421, codebook_loss=19.03, over 1364121.20 frames.], batch size: 20, lr: 5.83e-04
+2022-05-27 20:09:37,315 INFO [train.py:823] (2/4) Epoch 29, batch 700, loss[loss=1.91, simple_loss=0.2236, pruned_loss=0.01942, codebook_loss=17.79, over 7185.00 frames.], tot_loss[loss=2.059, simple_loss=0.2465, pruned_loss=0.03405, codebook_loss=19.01, over 1372051.32 frames.], batch size: 19, lr: 5.83e-04
+2022-05-27 20:10:17,496 INFO [train.py:823] (2/4) Epoch 29, batch 750, loss[loss=2.112, simple_loss=0.2484, pruned_loss=0.05363, codebook_loss=19.34, over 4911.00 frames.], tot_loss[loss=2.064, simple_loss=0.2466, pruned_loss=0.03425, codebook_loss=19.07, over 1379026.07 frames.], batch size: 47, lr: 5.82e-04
+2022-05-27 20:10:57,081 INFO [train.py:823] (2/4) Epoch 29, batch 800, loss[loss=1.992, simple_loss=0.2165, pruned_loss=0.02802, codebook_loss=18.56, over 7191.00 frames.], tot_loss[loss=2.069, simple_loss=0.2461, pruned_loss=0.03442, codebook_loss=19.11, over 1387544.95 frames.], batch size: 18, lr: 5.82e-04
+2022-05-27 20:11:37,248 INFO [train.py:823] (2/4) Epoch 29, batch 850, loss[loss=2.044, simple_loss=0.2667, pruned_loss=0.03856, codebook_loss=18.72, over 7195.00 frames.], tot_loss[loss=2.067, simple_loss=0.2463, pruned_loss=0.03421, codebook_loss=19.1, over 1397220.18 frames.], batch size: 24, lr: 5.81e-04
+2022-05-27 20:12:16,636 INFO [train.py:823] (2/4) Epoch 29, batch 900, loss[loss=2.097, simple_loss=0.2592, pruned_loss=0.04557, codebook_loss=19.22, over 7153.00 frames.], tot_loss[loss=2.067, simple_loss=0.2466, pruned_loss=0.03439, codebook_loss=19.1, over 1396011.35 frames.], batch size: 22, lr: 5.81e-04
+2022-05-27 20:12:56,392 INFO [train.py:823] (2/4) Epoch 29, batch 950, loss[loss=2.934, simple_loss=0.2999, pruned_loss=0.09246, codebook_loss=26.91, over 5086.00 frames.], tot_loss[loss=2.073, simple_loss=0.2465, pruned_loss=0.03456, codebook_loss=19.16, over 1390099.84 frames.], batch size: 47, lr: 5.80e-04
+2022-05-27 20:13:08,686 INFO [train.py:823] (2/4) Epoch 30, batch 0, loss[loss=2.052, simple_loss=0.2501, pruned_loss=0.03039, codebook_loss=18.96, over 7382.00 frames.], tot_loss[loss=2.052, simple_loss=0.2501, pruned_loss=0.03039, codebook_loss=18.96, over 7382.00 frames.], batch size: 20, lr: 5.71e-04
+2022-05-27 20:13:48,293 INFO [train.py:823] (2/4) Epoch 30, batch 50, loss[loss=1.933, simple_loss=0.2158, pruned_loss=0.0247, codebook_loss=18.01, over 7094.00 frames.], tot_loss[loss=2.041, simple_loss=0.2433, pruned_loss=0.03344, codebook_loss=18.86, over 314435.34 frames.], batch size: 19, lr: 5.70e-04
+2022-05-27 20:14:28,409 INFO [train.py:823] (2/4) Epoch 30, batch 100, loss[loss=2.066, simple_loss=0.2286, pruned_loss=0.03573, codebook_loss=19.16, over 7286.00 frames.], tot_loss[loss=2.042, simple_loss=0.243, pruned_loss=0.0327, codebook_loss=18.88, over 561865.95 frames.], batch size: 17, lr: 5.70e-04
+2022-05-27 20:15:09,329 INFO [train.py:823] (2/4) Epoch 30, batch 150, loss[loss=2.057, simple_loss=0.2656, pruned_loss=0.03652, codebook_loss=18.87, over 7159.00 frames.], tot_loss[loss=2.047, simple_loss=0.2448, pruned_loss=0.03292, codebook_loss=18.92, over 753968.19 frames.], batch size: 23, lr: 5.69e-04
+2022-05-27 20:15:49,638 INFO [train.py:823] (2/4) Epoch 30, batch 200, loss[loss=2.011, simple_loss=0.2733, pruned_loss=0.04458, codebook_loss=18.3, over 7147.00 frames.], tot_loss[loss=2.05, simple_loss=0.246, pruned_loss=0.03327, codebook_loss=18.93, over 901544.82 frames.], batch size: 23, lr: 5.69e-04
+2022-05-27 20:16:29,378 INFO [train.py:823] (2/4) Epoch 30, batch 250, loss[loss=2.004, simple_loss=0.2496, pruned_loss=0.03532, codebook_loss=18.44, over 7107.00 frames.], tot_loss[loss=2.051, simple_loss=0.2466, pruned_loss=0.0334, codebook_loss=18.94, over 1013579.31 frames.], batch size: 19, lr: 5.68e-04
+2022-05-27 20:17:09,781 INFO [train.py:823] (2/4) Epoch 30, batch 300, loss[loss=2.007, simple_loss=0.214, pruned_loss=0.02639, codebook_loss=18.74, over 7156.00 frames.], tot_loss[loss=2.048, simple_loss=0.2474, pruned_loss=0.0334, codebook_loss=18.91, over 1106709.16 frames.], batch size: 17, lr: 5.68e-04
+2022-05-27 20:17:49,575 INFO [train.py:823] (2/4) Epoch 30, batch 350, loss[loss=2.299, simple_loss=0.2733, pruned_loss=0.04195, codebook_loss=21.21, over 7241.00 frames.], tot_loss[loss=2.055, simple_loss=0.2466, pruned_loss=0.03296, codebook_loss=18.99, over 1176568.90 frames.], batch size: 24, lr: 5.67e-04
+2022-05-27 20:18:29,831 INFO [train.py:823] (2/4) Epoch 30, batch 400, loss[loss=1.992, simple_loss=0.2577, pruned_loss=0.03731, codebook_loss=18.26, over 7063.00 frames.], tot_loss[loss=2.051, simple_loss=0.2461, pruned_loss=0.03285, codebook_loss=18.95, over 1230384.56 frames.], batch size: 26, lr: 5.67e-04
+2022-05-27 20:19:09,332 INFO [train.py:823] (2/4) Epoch 30, batch 450, loss[loss=2.082, simple_loss=0.2673, pruned_loss=0.03834, codebook_loss=19.1, over 6979.00 frames.], tot_loss[loss=2.053, simple_loss=0.246, pruned_loss=0.03309, codebook_loss=18.96, over 1268465.73 frames.], batch size: 29, lr: 5.66e-04
+2022-05-27 20:19:49,219 INFO [train.py:823] (2/4) Epoch 30, batch 500, loss[loss=2.247, simple_loss=0.2526, pruned_loss=0.03156, codebook_loss=20.89, over 7091.00 frames.], tot_loss[loss=2.057, simple_loss=0.246, pruned_loss=0.0329, codebook_loss=19.01, over 1301855.44 frames.], batch size: 19, lr: 5.66e-04
+2022-05-27 20:20:29,044 INFO [train.py:823] (2/4) Epoch 30, batch 550, loss[loss=2.341, simple_loss=0.2703, pruned_loss=0.03849, codebook_loss=21.67, over 7405.00 frames.], tot_loss[loss=2.058, simple_loss=0.2461, pruned_loss=0.03301, codebook_loss=19.02, over 1326758.10 frames.], batch size: 22, lr: 5.65e-04
+2022-05-27 20:21:09,004 INFO [train.py:823] (2/4) Epoch 30, batch 600, loss[loss=1.966, simple_loss=0.2185, pruned_loss=0.02272, codebook_loss=18.34, over 7194.00 frames.], tot_loss[loss=2.054, simple_loss=0.2454, pruned_loss=0.03267, codebook_loss=18.98, over 1344594.38 frames.], batch size: 19, lr: 5.65e-04
+2022-05-27 20:21:48,892 INFO [train.py:823] (2/4) Epoch 30, batch 650, loss[loss=1.967, simple_loss=0.2448, pruned_loss=0.01977, codebook_loss=18.25, over 7426.00 frames.], tot_loss[loss=2.053, simple_loss=0.2452, pruned_loss=0.03315, codebook_loss=18.97, over 1358411.79 frames.], batch size: 22, lr: 5.64e-04
+2022-05-27 20:22:29,358 INFO [train.py:823] (2/4) Epoch 30, batch 700, loss[loss=2.017, simple_loss=0.2317, pruned_loss=0.03119, codebook_loss=18.7, over 7286.00 frames.], tot_loss[loss=2.053, simple_loss=0.2438, pruned_loss=0.03292, codebook_loss=18.98, over 1376598.34 frames.], batch size: 19, lr: 5.64e-04
+2022-05-27 20:23:09,105 INFO [train.py:823] (2/4) Epoch 30, batch 750, loss[loss=1.986, simple_loss=0.2347, pruned_loss=0.03426, codebook_loss=18.34, over 7098.00 frames.], tot_loss[loss=2.057, simple_loss=0.2441, pruned_loss=0.03335, codebook_loss=19.01, over 1382256.31 frames.], batch size: 18, lr: 5.63e-04
+2022-05-27 20:23:48,818 INFO [train.py:823] (2/4) Epoch 30, batch 800, loss[loss=2.071, simple_loss=0.269, pruned_loss=0.04539, codebook_loss=18.92, over 6951.00 frames.], tot_loss[loss=2.054, simple_loss=0.2449, pruned_loss=0.03309, codebook_loss=18.98, over 1391375.38 frames.], batch size: 26, lr: 5.63e-04
+2022-05-27 20:24:28,411 INFO [train.py:823] (2/4) Epoch 30, batch 850, loss[loss=2.021, simple_loss=0.2233, pruned_loss=0.02895, codebook_loss=18.81, over 7188.00 frames.], tot_loss[loss=2.055, simple_loss=0.2443, pruned_loss=0.0328, codebook_loss=19, over 1390602.99 frames.], batch size: 18, lr: 5.62e-04
+2022-05-27 20:25:08,260 INFO [train.py:823] (2/4) Epoch 30, batch 900, loss[loss=2.019, simple_loss=0.227, pruned_loss=0.0189, codebook_loss=18.87, over 7283.00 frames.], tot_loss[loss=2.051, simple_loss=0.2444, pruned_loss=0.03271, codebook_loss=18.97, over 1395526.58 frames.], batch size: 19, lr: 5.62e-04
+2022-05-27 20:26:05,254 INFO [train.py:823] (2/4) Epoch 31, batch 0, loss[loss=2.186, simple_loss=0.2289, pruned_loss=0.02503, codebook_loss=20.47, over 7382.00 frames.], tot_loss[loss=2.186, simple_loss=0.2289, pruned_loss=0.02503, codebook_loss=20.47, over 7382.00 frames.], batch size: 20, lr: 5.52e-04
+2022-05-27 20:26:45,555 INFO [train.py:823] (2/4) Epoch 31, batch 50, loss[loss=1.939, simple_loss=0.2171, pruned_loss=0.01719, codebook_loss=18.13, over 7198.00 frames.], tot_loss[loss=2.032, simple_loss=0.2381, pruned_loss=0.02999, codebook_loss=18.83, over 324809.52 frames.], batch size: 18, lr: 5.52e-04
+2022-05-27 20:27:24,999 INFO [train.py:823] (2/4) Epoch 31, batch 100, loss[loss=2.488, simple_loss=0.2328, pruned_loss=0.03652, codebook_loss=23.35, over 7307.00 frames.], tot_loss[loss=2.044, simple_loss=0.2421, pruned_loss=0.03141, codebook_loss=18.91, over 565230.30 frames.], batch size: 16, lr: 5.51e-04
+2022-05-27 20:28:05,124 INFO [train.py:823] (2/4) Epoch 31, batch 150, loss[loss=2.014, simple_loss=0.2498, pruned_loss=0.02445, codebook_loss=18.64, over 7207.00 frames.], tot_loss[loss=2.045, simple_loss=0.2439, pruned_loss=0.03197, codebook_loss=18.91, over 754686.57 frames.], batch size: 25, lr: 5.51e-04
+2022-05-27 20:28:44,801 INFO [train.py:823] (2/4) Epoch 31, batch 200, loss[loss=1.923, simple_loss=0.2276, pruned_loss=0.0292, codebook_loss=17.8, over 7085.00 frames.], tot_loss[loss=2.044, simple_loss=0.2444, pruned_loss=0.03252, codebook_loss=18.9, over 899210.33 frames.], batch size: 18, lr: 5.50e-04
+2022-05-27 20:29:24,817 INFO [train.py:823] (2/4) Epoch 31, batch 250, loss[loss=1.981, simple_loss=0.2174, pruned_loss=0.01767, codebook_loss=18.55, over 7139.00 frames.], tot_loss[loss=2.05, simple_loss=0.2443, pruned_loss=0.03268, codebook_loss=18.95, over 1005405.15 frames.], batch size: 17, lr: 5.50e-04
+2022-05-27 20:30:04,912 INFO [train.py:823] (2/4) Epoch 31, batch 300, loss[loss=1.93, simple_loss=0.2578, pruned_loss=0.02188, codebook_loss=17.79, over 7302.00 frames.], tot_loss[loss=2.042, simple_loss=0.2437, pruned_loss=0.0322, codebook_loss=18.88, over 1097757.39 frames.], batch size: 22, lr: 5.49e-04
+2022-05-27 20:30:44,860 INFO [train.py:823] (2/4) Epoch 31, batch 350, loss[loss=2.08, simple_loss=0.2328, pruned_loss=0.033, codebook_loss=19.3, over 7155.00 frames.], tot_loss[loss=2.04, simple_loss=0.2434, pruned_loss=0.03197, codebook_loss=18.87, over 1164566.55 frames.], batch size: 17, lr: 5.49e-04
+2022-05-27 20:31:24,717 INFO [train.py:823] (2/4) Epoch 31, batch 400, loss[loss=2.005, simple_loss=0.24, pruned_loss=0.03221, codebook_loss=18.53, over 7399.00 frames.], tot_loss[loss=2.037, simple_loss=0.2435, pruned_loss=0.03151, codebook_loss=18.84, over 1225964.05 frames.], batch size: 19, lr: 5.49e-04
+2022-05-27 20:32:04,786 INFO [train.py:823] (2/4) Epoch 31, batch 450, loss[loss=2.03, simple_loss=0.2281, pruned_loss=0.03183, codebook_loss=18.84, over 7298.00 frames.], tot_loss[loss=2.036, simple_loss=0.2433, pruned_loss=0.03159, codebook_loss=18.82, over 1270341.18 frames.], batch size: 18, lr: 5.48e-04
+2022-05-27 20:32:44,613 INFO [train.py:823] (2/4) Epoch 31, batch 500, loss[loss=2.058, simple_loss=0.2404, pruned_loss=0.03093, codebook_loss=19.06, over 7102.00 frames.], tot_loss[loss=2.04, simple_loss=0.2421, pruned_loss=0.03148, codebook_loss=18.88, over 1303011.16 frames.], batch size: 18, lr: 5.48e-04
+2022-05-27 20:33:24,723 INFO [train.py:823] (2/4) Epoch 31, batch 550, loss[loss=2.152, simple_loss=0.2301, pruned_loss=0.02401, codebook_loss=20.13, over 7376.00 frames.], tot_loss[loss=2.045, simple_loss=0.2417, pruned_loss=0.03176, codebook_loss=18.92, over 1327201.45 frames.], batch size: 19, lr: 5.47e-04
+2022-05-27 20:34:04,423 INFO [train.py:823] (2/4) Epoch 31, batch 600, loss[loss=1.984, simple_loss=0.2122, pruned_loss=0.01932, codebook_loss=18.59, over 7176.00 frames.], tot_loss[loss=2.044, simple_loss=0.2428, pruned_loss=0.03217, codebook_loss=18.9, over 1347225.21 frames.], batch size: 16, lr: 5.47e-04
+2022-05-27 20:34:44,335 INFO [train.py:823] (2/4) Epoch 31, batch 650, loss[loss=2.043, simple_loss=0.2595, pruned_loss=0.04703, codebook_loss=18.66, over 7168.00 frames.], tot_loss[loss=2.041, simple_loss=0.2432, pruned_loss=0.03215, codebook_loss=18.87, over 1362573.88 frames.], batch size: 22, lr: 5.46e-04
+2022-05-27 20:35:24,056 INFO [train.py:823] (2/4) Epoch 31, batch 700, loss[loss=1.983, simple_loss=0.2167, pruned_loss=0.02452, codebook_loss=18.51, over 7283.00 frames.], tot_loss[loss=2.048, simple_loss=0.2445, pruned_loss=0.033, codebook_loss=18.92, over 1371563.19 frames.], batch size: 17, lr: 5.46e-04
+2022-05-27 20:36:04,276 INFO [train.py:823] (2/4) Epoch 31, batch 750, loss[loss=1.933, simple_loss=0.2043, pruned_loss=0.01667, codebook_loss=18.14, over 7288.00 frames.], tot_loss[loss=2.046, simple_loss=0.2447, pruned_loss=0.03248, codebook_loss=18.91, over 1382988.70 frames.], batch size: 18, lr: 5.45e-04
+2022-05-27 20:36:44,233 INFO [train.py:823] (2/4) Epoch 31, batch 800, loss[loss=2.041, simple_loss=0.2285, pruned_loss=0.03796, codebook_loss=18.89, over 7208.00 frames.], tot_loss[loss=2.047, simple_loss=0.2447, pruned_loss=0.03254, codebook_loss=18.92, over 1393501.86 frames.], batch size: 16, lr: 5.45e-04
+2022-05-27 20:37:23,977 INFO [train.py:823] (2/4) Epoch 31, batch 850, loss[loss=2.048, simple_loss=0.2674, pruned_loss=0.0378, codebook_loss=18.77, over 7033.00 frames.], tot_loss[loss=2.048, simple_loss=0.2453, pruned_loss=0.03304, codebook_loss=18.93, over 1391829.81 frames.], batch size: 26, lr: 5.44e-04
+2022-05-27 20:38:03,437 INFO [train.py:823] (2/4) Epoch 31, batch 900, loss[loss=1.972, simple_loss=0.2271, pruned_loss=0.0232, codebook_loss=18.36, over 7103.00 frames.], tot_loss[loss=2.048, simple_loss=0.2459, pruned_loss=0.03314, codebook_loss=18.92, over 1396902.48 frames.], batch size: 19, lr: 5.44e-04
+2022-05-27 20:38:58,921 INFO [train.py:823] (2/4) Epoch 32, batch 0, loss[loss=2.022, simple_loss=0.2575, pruned_loss=0.03419, codebook_loss=18.59, over 4747.00 frames.], tot_loss[loss=2.022, simple_loss=0.2575, pruned_loss=0.03419, codebook_loss=18.59, over 4747.00 frames.], batch size: 46, lr: 5.35e-04
+2022-05-27 20:39:38,612 INFO [train.py:823] (2/4) Epoch 32, batch 50, loss[loss=1.929, simple_loss=0.2125, pruned_loss=0.02534, codebook_loss=17.98, over 7311.00 frames.], tot_loss[loss=2.026, simple_loss=0.2453, pruned_loss=0.03231, codebook_loss=18.71, over 319710.22 frames.], batch size: 17, lr: 5.35e-04
+2022-05-27 20:40:18,785 INFO [train.py:823] (2/4) Epoch 32, batch 100, loss[loss=2.17, simple_loss=0.2692, pruned_loss=0.05173, codebook_loss=19.83, over 7174.00 frames.], tot_loss[loss=2.033, simple_loss=0.2455, pruned_loss=0.0326, codebook_loss=18.78, over 565586.01 frames.], batch size: 22, lr: 5.34e-04
+2022-05-27 20:40:58,678 INFO [train.py:823] (2/4) Epoch 32, batch 150, loss[loss=1.976, simple_loss=0.2468, pruned_loss=0.03102, codebook_loss=18.22, over 7204.00 frames.], tot_loss[loss=2.045, simple_loss=0.2451, pruned_loss=0.03284, codebook_loss=18.9, over 757923.54 frames.], batch size: 19, lr: 5.34e-04
+2022-05-27 20:41:38,649 INFO [train.py:823] (2/4) Epoch 32, batch 200, loss[loss=1.991, simple_loss=0.2478, pruned_loss=0.03659, codebook_loss=18.31, over 7204.00 frames.], tot_loss[loss=2.04, simple_loss=0.2453, pruned_loss=0.03263, codebook_loss=18.85, over 904350.91 frames.], batch size: 19, lr: 5.33e-04
+2022-05-27 20:42:18,574 INFO [train.py:823] (2/4) Epoch 32, batch 250, loss[loss=2.122, simple_loss=0.2556, pruned_loss=0.03732, codebook_loss=19.57, over 7197.00 frames.], tot_loss[loss=2.03, simple_loss=0.2431, pruned_loss=0.03155, codebook_loss=18.77, over 1021196.72 frames.], batch size: 19, lr: 5.33e-04
+2022-05-27 20:42:58,402 INFO [train.py:823] (2/4) Epoch 32, batch 300, loss[loss=2.049, simple_loss=0.2299, pruned_loss=0.02951, codebook_loss=19.05, over 7305.00 frames.], tot_loss[loss=2.029, simple_loss=0.2419, pruned_loss=0.0315, codebook_loss=18.77, over 1106577.36 frames.], batch size: 19, lr: 5.32e-04
+2022-05-27 20:43:38,304 INFO [train.py:823] (2/4) Epoch 32, batch 350, loss[loss=2.002, simple_loss=0.2193, pruned_loss=0.03056, codebook_loss=18.61, over 7003.00 frames.], tot_loss[loss=2.031, simple_loss=0.243, pruned_loss=0.03183, codebook_loss=18.78, over 1175944.63 frames.], batch size: 16, lr: 5.32e-04
+2022-05-27 20:44:18,234 INFO [train.py:823] (2/4) Epoch 32, batch 400, loss[loss=2.046, simple_loss=0.2561, pruned_loss=0.03366, codebook_loss=18.84, over 6498.00 frames.], tot_loss[loss=2.033, simple_loss=0.2441, pruned_loss=0.03215, codebook_loss=18.79, over 1225498.15 frames.], batch size: 34, lr: 5.32e-04
+2022-05-27 20:44:58,211 INFO [train.py:823] (2/4) Epoch 32, batch 450, loss[loss=1.984, simple_loss=0.2589, pruned_loss=0.03173, codebook_loss=18.23, over 7156.00 frames.], tot_loss[loss=2.036, simple_loss=0.2439, pruned_loss=0.03204, codebook_loss=18.82, over 1266697.99 frames.], batch size: 23, lr: 5.31e-04
+2022-05-27 20:45:38,549 INFO [train.py:823] (2/4) Epoch 32, batch 500, loss[loss=2.031, simple_loss=0.253, pruned_loss=0.03538, codebook_loss=18.69, over 7206.00 frames.], tot_loss[loss=2.037, simple_loss=0.2433, pruned_loss=0.03175, codebook_loss=18.83, over 1300322.64 frames.], batch size: 20, lr: 5.31e-04
+2022-05-27 20:46:18,543 INFO [train.py:823] (2/4) Epoch 32, batch 550, loss[loss=2.03, simple_loss=0.3051, pruned_loss=0.05515, codebook_loss=18.22, over 7219.00 frames.], tot_loss[loss=2.03, simple_loss=0.2441, pruned_loss=0.03171, codebook_loss=18.76, over 1328636.12 frames.], batch size: 25, lr: 5.30e-04
+2022-05-27 20:46:58,704 INFO [train.py:823] (2/4) Epoch 32, batch 600, loss[loss=1.911, simple_loss=0.2125, pruned_loss=0.01743, codebook_loss=17.88, over 7297.00 frames.], tot_loss[loss=2.034, simple_loss=0.2446, pruned_loss=0.03201, codebook_loss=18.8, over 1349853.40 frames.], batch size: 17, lr: 5.30e-04
+2022-05-27 20:47:38,436 INFO [train.py:823] (2/4) Epoch 32, batch 650, loss[loss=1.977, simple_loss=0.244, pruned_loss=0.02466, codebook_loss=18.3, over 7030.00 frames.], tot_loss[loss=2.038, simple_loss=0.2444, pruned_loss=0.03205, codebook_loss=18.84, over 1361824.58 frames.], batch size: 26, lr: 5.29e-04
+2022-05-27 20:48:18,779 INFO [train.py:823] (2/4) Epoch 32, batch 700, loss[loss=1.988, simple_loss=0.2498, pruned_loss=0.03218, codebook_loss=18.31, over 7113.00 frames.], tot_loss[loss=2.038, simple_loss=0.2436, pruned_loss=0.03213, codebook_loss=18.84, over 1378118.19 frames.], batch size: 20, lr: 5.29e-04
+2022-05-27 20:48:58,629 INFO [train.py:823] (2/4) Epoch 32, batch 750, loss[loss=1.987, simple_loss=0.2185, pruned_loss=0.02217, codebook_loss=18.55, over 7393.00 frames.], tot_loss[loss=2.041, simple_loss=0.244, pruned_loss=0.03244, codebook_loss=18.86, over 1387814.77 frames.], batch size: 19, lr: 5.29e-04
+2022-05-27 20:49:38,922 INFO [train.py:823] (2/4) Epoch 32, batch 800, loss[loss=1.997, simple_loss=0.2263, pruned_loss=0.02769, codebook_loss=18.56, over 7155.00 frames.], tot_loss[loss=2.039, simple_loss=0.2442, pruned_loss=0.03225, codebook_loss=18.85, over 1396044.36 frames.], batch size: 17, lr: 5.28e-04
+2022-05-27 20:50:20,033 INFO [train.py:823] (2/4) Epoch 32, batch 850, loss[loss=2.007, simple_loss=0.2201, pruned_loss=0.02923, codebook_loss=18.68, over 7022.00 frames.], tot_loss[loss=2.04, simple_loss=0.2438, pruned_loss=0.03215, codebook_loss=18.86, over 1399519.09 frames.], batch size: 17, lr: 5.28e-04
+2022-05-27 20:51:02,547 INFO [train.py:823] (2/4) Epoch 32, batch 900, loss[loss=1.968, simple_loss=0.2303, pruned_loss=0.02149, codebook_loss=18.31, over 7419.00 frames.], tot_loss[loss=2.039, simple_loss=0.2439, pruned_loss=0.0318, codebook_loss=18.85, over 1404830.74 frames.], batch size: 18, lr: 5.27e-04
+2022-05-27 20:51:56,396 INFO [train.py:823] (2/4) Epoch 33, batch 0, loss[loss=1.976, simple_loss=0.2467, pruned_loss=0.02649, codebook_loss=18.27, over 7027.00 frames.], tot_loss[loss=1.976, simple_loss=0.2467, pruned_loss=0.02649, codebook_loss=18.27, over 7027.00 frames.], batch size: 29, lr: 5.19e-04
+2022-05-27 20:52:36,645 INFO [train.py:823] (2/4) Epoch 33, batch 50, loss[loss=2.036, simple_loss=0.2315, pruned_loss=0.02987, codebook_loss=18.91, over 7154.00 frames.], tot_loss[loss=2.032, simple_loss=0.2436, pruned_loss=0.03184, codebook_loss=18.79, over 317800.88 frames.], batch size: 17, lr: 5.18e-04
+2022-05-27 20:53:16,494 INFO [train.py:823] (2/4) Epoch 33, batch 100, loss[loss=2.05, simple_loss=0.2286, pruned_loss=0.03584, codebook_loss=19, over 6803.00 frames.], tot_loss[loss=2.05, simple_loss=0.2431, pruned_loss=0.03208, codebook_loss=18.96, over 561397.18 frames.], batch size: 15, lr: 5.18e-04
+2022-05-27 20:53:56,614 INFO [train.py:823] (2/4) Epoch 33, batch 150, loss[loss=1.93, simple_loss=0.242, pruned_loss=0.0214, codebook_loss=17.87, over 7188.00 frames.], tot_loss[loss=2.044, simple_loss=0.2448, pruned_loss=0.0327, codebook_loss=18.88, over 749988.37 frames.], batch size: 21, lr: 5.18e-04
+2022-05-27 20:54:36,228 INFO [train.py:823] (2/4) Epoch 33, batch 200, loss[loss=2.129, simple_loss=0.2918, pruned_loss=0.0537, codebook_loss=19.29, over 7114.00 frames.], tot_loss[loss=2.043, simple_loss=0.2448, pruned_loss=0.03281, codebook_loss=18.88, over 892045.34 frames.], batch size: 20, lr: 5.17e-04
+2022-05-27 20:55:16,543 INFO [train.py:823] (2/4) Epoch 33, batch 250, loss[loss=2.048, simple_loss=0.2698, pruned_loss=0.04323, codebook_loss=18.7, over 7143.00 frames.], tot_loss[loss=2.04, simple_loss=0.244, pruned_loss=0.03239, codebook_loss=18.86, over 1013056.88 frames.], batch size: 23, lr: 5.17e-04
+2022-05-27 20:55:56,431 INFO [train.py:823] (2/4) Epoch 33, batch 300, loss[loss=2.379, simple_loss=0.2321, pruned_loss=0.04326, codebook_loss=22.2, over 7174.00 frames.], tot_loss[loss=2.036, simple_loss=0.2436, pruned_loss=0.03177, codebook_loss=18.82, over 1106910.66 frames.], batch size: 17, lr: 5.16e-04
+2022-05-27 20:56:36,517 INFO [train.py:823] (2/4) Epoch 33, batch 350, loss[loss=1.971, simple_loss=0.2573, pruned_loss=0.03851, codebook_loss=18.04, over 7351.00 frames.], tot_loss[loss=2.037, simple_loss=0.2442, pruned_loss=0.0319, codebook_loss=18.83, over 1176372.66 frames.], batch size: 23, lr: 5.16e-04
+2022-05-27 20:57:16,233 INFO [train.py:823] (2/4) Epoch 33, batch 400, loss[loss=2.042, simple_loss=0.2623, pruned_loss=0.03455, codebook_loss=18.76, over 7427.00 frames.], tot_loss[loss=2.04, simple_loss=0.2447, pruned_loss=0.03186, codebook_loss=18.86, over 1231260.38 frames.], batch size: 22, lr: 5.16e-04
+2022-05-27 20:57:56,216 INFO [train.py:823] (2/4) Epoch 33, batch 450, loss[loss=1.96, simple_loss=0.2152, pruned_loss=0.0229, codebook_loss=18.29, over 7291.00 frames.], tot_loss[loss=2.042, simple_loss=0.2447, pruned_loss=0.03213, codebook_loss=18.88, over 1272038.99 frames.], batch size: 19, lr: 5.15e-04
+2022-05-27 20:58:35,795 INFO [train.py:823] (2/4) Epoch 33, batch 500, loss[loss=2.013, simple_loss=0.2578, pruned_loss=0.02887, codebook_loss=18.55, over 6941.00 frames.], tot_loss[loss=2.046, simple_loss=0.2445, pruned_loss=0.03211, codebook_loss=18.92, over 1306519.08 frames.], batch size: 29, lr: 5.15e-04
+2022-05-27 20:59:15,996 INFO [train.py:823] (2/4) Epoch 33, batch 550, loss[loss=2.075, simple_loss=0.2344, pruned_loss=0.03377, codebook_loss=19.24, over 7381.00 frames.], tot_loss[loss=2.044, simple_loss=0.244, pruned_loss=0.03188, codebook_loss=18.9, over 1334440.00 frames.], batch size: 19, lr: 5.14e-04
+2022-05-27 20:59:56,123 INFO [train.py:823] (2/4) Epoch 33, batch 600, loss[loss=1.995, simple_loss=0.2661, pruned_loss=0.03443, codebook_loss=18.28, over 7419.00 frames.], tot_loss[loss=2.039, simple_loss=0.243, pruned_loss=0.03161, codebook_loss=18.86, over 1353972.87 frames.], batch size: 22, lr: 5.14e-04
+2022-05-27 21:00:36,439 INFO [train.py:823] (2/4) Epoch 33, batch 650, loss[loss=2.135, simple_loss=0.232, pruned_loss=0.03108, codebook_loss=19.88, over 7143.00 frames.], tot_loss[loss=2.043, simple_loss=0.2424, pruned_loss=0.03161, codebook_loss=18.9, over 1373077.89 frames.], batch size: 17, lr: 5.14e-04
+2022-05-27 21:01:16,079 INFO [train.py:823] (2/4) Epoch 33, batch 700, loss[loss=2.028, simple_loss=0.2544, pruned_loss=0.03019, codebook_loss=18.71, over 6404.00 frames.], tot_loss[loss=2.042, simple_loss=0.2426, pruned_loss=0.03153, codebook_loss=18.89, over 1384293.70 frames.], batch size: 34, lr: 5.13e-04
+2022-05-27 21:01:56,092 INFO [train.py:823] (2/4) Epoch 33, batch 750, loss[loss=2.142, simple_loss=0.277, pruned_loss=0.05806, codebook_loss=19.46, over 7169.00 frames.], tot_loss[loss=2.044, simple_loss=0.2436, pruned_loss=0.03204, codebook_loss=18.9, over 1391292.15 frames.], batch size: 25, lr: 5.13e-04
+2022-05-27 21:02:35,436 INFO [train.py:823] (2/4) Epoch 33, batch 800, loss[loss=2.016, simple_loss=0.2534, pruned_loss=0.04417, codebook_loss=18.45, over 7157.00 frames.], tot_loss[loss=2.038, simple_loss=0.2443, pruned_loss=0.03182, codebook_loss=18.84, over 1391776.62 frames.], batch size: 22, lr: 5.12e-04
+2022-05-27 21:03:16,833 INFO [train.py:823] (2/4) Epoch 33, batch 850, loss[loss=1.992, simple_loss=0.2149, pruned_loss=0.02154, codebook_loss=18.63, over 7097.00 frames.], tot_loss[loss=2.037, simple_loss=0.2437, pruned_loss=0.03191, codebook_loss=18.84, over 1400314.66 frames.], batch size: 18, lr: 5.12e-04
+2022-05-27 21:03:56,334 INFO [train.py:823] (2/4) Epoch 33, batch 900, loss[loss=2.112, simple_loss=0.2286, pruned_loss=0.03996, codebook_loss=19.57, over 7004.00 frames.], tot_loss[loss=2.043, simple_loss=0.2438, pruned_loss=0.03224, codebook_loss=18.88, over 1401693.02 frames.], batch size: 16, lr: 5.12e-04
+2022-05-27 21:04:47,349 INFO [train.py:823] (2/4) Epoch 34, batch 0, loss[loss=2.033, simple_loss=0.2472, pruned_loss=0.03291, codebook_loss=18.76, over 7252.00 frames.], tot_loss[loss=2.033, simple_loss=0.2472, pruned_loss=0.03291, codebook_loss=18.76, over 7252.00 frames.], batch size: 24, lr: 5.04e-04
+2022-05-27 21:05:27,119 INFO [train.py:823] (2/4) Epoch 34, batch 50, loss[loss=2.046, simple_loss=0.2203, pruned_loss=0.03661, codebook_loss=18.99, over 6781.00 frames.], tot_loss[loss=2.031, simple_loss=0.2412, pruned_loss=0.03084, codebook_loss=18.79, over 319856.55 frames.], batch size: 15, lr: 5.03e-04
+2022-05-27 21:06:07,168 INFO [train.py:823] (2/4) Epoch 34, batch 100, loss[loss=1.965, simple_loss=0.2335, pruned_loss=0.02585, codebook_loss=18.23, over 7282.00 frames.], tot_loss[loss=2.027, simple_loss=0.2404, pruned_loss=0.03001, codebook_loss=18.77, over 560131.09 frames.], batch size: 21, lr: 5.03e-04
+2022-05-27 21:06:47,145 INFO [train.py:823] (2/4) Epoch 34, batch 150, loss[loss=1.959, simple_loss=0.2539, pruned_loss=0.02528, codebook_loss=18.07, over 7298.00 frames.], tot_loss[loss=2.031, simple_loss=0.2427, pruned_loss=0.03016, codebook_loss=18.79, over 754299.95 frames.], batch size: 22, lr: 5.02e-04
+2022-05-27 21:07:27,064 INFO [train.py:823] (2/4) Epoch 34, batch 200, loss[loss=1.935, simple_loss=0.2397, pruned_loss=0.03113, codebook_loss=17.84, over 7020.00 frames.], tot_loss[loss=2.038, simple_loss=0.2436, pruned_loss=0.03145, codebook_loss=18.84, over 902430.22 frames.], batch size: 26, lr: 5.02e-04
+2022-05-27 21:08:06,785 INFO [train.py:823] (2/4) Epoch 34, batch 250, loss[loss=2.183, simple_loss=0.2431, pruned_loss=0.02933, codebook_loss=20.32, over 7054.00 frames.], tot_loss[loss=2.033, simple_loss=0.2431, pruned_loss=0.03133, codebook_loss=18.8, over 1013916.76 frames.], batch size: 26, lr: 5.02e-04
+2022-05-27 21:08:46,831 INFO [train.py:823] (2/4) Epoch 34, batch 300, loss[loss=2.067, simple_loss=0.2664, pruned_loss=0.03843, codebook_loss=18.95, over 7376.00 frames.], tot_loss[loss=2.033, simple_loss=0.2425, pruned_loss=0.03113, codebook_loss=18.81, over 1102846.28 frames.], batch size: 21, lr: 5.01e-04
+2022-05-27 21:09:26,858 INFO [train.py:823] (2/4) Epoch 34, batch 350, loss[loss=1.959, simple_loss=0.2229, pruned_loss=0.02246, codebook_loss=18.25, over 7098.00 frames.], tot_loss[loss=2.032, simple_loss=0.2423, pruned_loss=0.03141, codebook_loss=18.8, over 1169206.36 frames.], batch size: 19, lr: 5.01e-04
+2022-05-27 21:10:07,250 INFO [train.py:823] (2/4) Epoch 34, batch 400, loss[loss=1.961, simple_loss=0.2552, pruned_loss=0.0286, codebook_loss=18.05, over 7284.00 frames.], tot_loss[loss=2.029, simple_loss=0.2425, pruned_loss=0.03122, codebook_loss=18.77, over 1223984.83 frames.], batch size: 21, lr: 5.00e-04
+2022-05-27 21:10:46,989 INFO [train.py:823] (2/4) Epoch 34, batch 450, loss[loss=1.964, simple_loss=0.2665, pruned_loss=0.02576, codebook_loss=18.05, over 7280.00 frames.], tot_loss[loss=2.03, simple_loss=0.2428, pruned_loss=0.03115, codebook_loss=18.77, over 1269420.31 frames.], batch size: 20, lr: 5.00e-04
+2022-05-27 21:11:27,188 INFO [train.py:823] (2/4) Epoch 34, batch 500, loss[loss=1.995, simple_loss=0.2669, pruned_loss=0.03816, codebook_loss=18.24, over 7131.00 frames.], tot_loss[loss=2.034, simple_loss=0.2423, pruned_loss=0.03103, codebook_loss=18.82, over 1303131.46 frames.], batch size: 23, lr: 5.00e-04
+2022-05-27 21:12:07,369 INFO [train.py:823] (2/4) Epoch 34, batch 550, loss[loss=2.032, simple_loss=0.2592, pruned_loss=0.03618, codebook_loss=18.67, over 7213.00 frames.], tot_loss[loss=2.025, simple_loss=0.242, pruned_loss=0.03086, codebook_loss=18.73, over 1335288.50 frames.], batch size: 25, lr: 4.99e-04
+2022-05-27 21:12:47,512 INFO [train.py:823] (2/4) Epoch 34, batch 600, loss[loss=1.946, simple_loss=0.2185, pruned_loss=0.02749, codebook_loss=18.09, over 7273.00 frames.], tot_loss[loss=2.026, simple_loss=0.2424, pruned_loss=0.03093, codebook_loss=18.74, over 1353438.94 frames.], batch size: 17, lr: 4.99e-04
+2022-05-27 21:13:27,629 INFO [train.py:823] (2/4) Epoch 34, batch 650, loss[loss=2.099, simple_loss=0.243, pruned_loss=0.02968, codebook_loss=19.48, over 7042.00 frames.], tot_loss[loss=2.033, simple_loss=0.2416, pruned_loss=0.03116, codebook_loss=18.81, over 1367942.50 frames.], batch size: 29, lr: 4.99e-04
+2022-05-27 21:14:11,302 INFO [train.py:823] (2/4) Epoch 34, batch 700, loss[loss=1.909, simple_loss=0.2296, pruned_loss=0.02062, codebook_loss=17.73, over 7380.00 frames.], tot_loss[loss=2.035, simple_loss=0.2416, pruned_loss=0.03143, codebook_loss=18.83, over 1377475.78 frames.], batch size: 20, lr: 4.98e-04
+2022-05-27 21:14:51,476 INFO [train.py:823] (2/4) Epoch 34, batch 750, loss[loss=1.996, simple_loss=0.221, pruned_loss=0.02708, codebook_loss=18.59, over 7013.00 frames.], tot_loss[loss=2.042, simple_loss=0.242, pruned_loss=0.03206, codebook_loss=18.89, over 1388893.32 frames.], batch size: 16, lr: 4.98e-04
+2022-05-27 21:15:35,828 INFO [train.py:823] (2/4) Epoch 34, batch 800, loss[loss=2.119, simple_loss=0.2675, pruned_loss=0.04021, codebook_loss=19.45, over 7199.00 frames.], tot_loss[loss=2.044, simple_loss=0.2423, pruned_loss=0.03218, codebook_loss=18.91, over 1396389.98 frames.], batch size: 19, lr: 4.97e-04
+2022-05-27 21:16:15,604 INFO [train.py:823] (2/4) Epoch 34, batch 850, loss[loss=1.981, simple_loss=0.2464, pruned_loss=0.03564, codebook_loss=18.22, over 7373.00 frames.], tot_loss[loss=2.036, simple_loss=0.2427, pruned_loss=0.03187, codebook_loss=18.83, over 1396566.00 frames.], batch size: 21, lr: 4.97e-04
+2022-05-27 21:16:55,845 INFO [train.py:823] (2/4) Epoch 34, batch 900, loss[loss=1.92, simple_loss=0.229, pruned_loss=0.02408, codebook_loss=17.81, over 7106.00 frames.], tot_loss[loss=2.038, simple_loss=0.2421, pruned_loss=0.03174, codebook_loss=18.85, over 1400616.57 frames.], batch size: 18, lr: 4.97e-04
+2022-05-27 21:17:49,293 INFO [train.py:823] (2/4) Epoch 35, batch 0, loss[loss=2.136, simple_loss=0.2584, pruned_loss=0.01995, codebook_loss=19.87, over 7179.00 frames.], tot_loss[loss=2.136, simple_loss=0.2584, pruned_loss=0.01995, codebook_loss=19.87, over 7179.00 frames.], batch size: 21, lr: 4.89e-04
+2022-05-27 21:18:30,065 INFO [train.py:823] (2/4) Epoch 35, batch 50, loss[loss=2.105, simple_loss=0.2319, pruned_loss=0.03507, codebook_loss=19.54, over 7178.00 frames.], tot_loss[loss=2.028, simple_loss=0.2447, pruned_loss=0.03099, codebook_loss=18.75, over 323745.05 frames.], batch size: 18, lr: 4.89e-04
+2022-05-27 21:19:10,013 INFO [train.py:823] (2/4) Epoch 35, batch 100, loss[loss=2.018, simple_loss=0.2528, pruned_loss=0.03101, codebook_loss=18.6, over 6594.00 frames.], tot_loss[loss=2.034, simple_loss=0.2444, pruned_loss=0.03122, codebook_loss=18.8, over 568697.19 frames.], batch size: 34, lr: 4.88e-04
+2022-05-27 21:19:50,174 INFO [train.py:823] (2/4) Epoch 35, batch 150, loss[loss=2.068, simple_loss=0.2579, pruned_loss=0.03302, codebook_loss=19.06, over 7229.00 frames.], tot_loss[loss=2.027, simple_loss=0.2432, pruned_loss=0.03112, codebook_loss=18.74, over 755105.33 frames.], batch size: 25, lr: 4.88e-04
+2022-05-27 21:20:30,527 INFO [train.py:823] (2/4) Epoch 35, batch 200, loss[loss=1.959, simple_loss=0.2436, pruned_loss=0.02849, codebook_loss=18.09, over 6989.00 frames.], tot_loss[loss=2.032, simple_loss=0.2425, pruned_loss=0.03126, codebook_loss=18.79, over 904358.35 frames.], batch size: 29, lr: 4.88e-04
+2022-05-27 21:21:10,397 INFO [train.py:823] (2/4) Epoch 35, batch 250, loss[loss=2.036, simple_loss=0.2663, pruned_loss=0.04868, codebook_loss=18.54, over 7231.00 frames.], tot_loss[loss=2.022, simple_loss=0.2422, pruned_loss=0.03113, codebook_loss=18.7, over 1013782.06 frames.], batch size: 24, lr: 4.87e-04
+2022-05-27 21:21:50,272 INFO [train.py:823] (2/4) Epoch 35, batch 300, loss[loss=1.954, simple_loss=0.255, pruned_loss=0.03011, codebook_loss=17.96, over 7286.00 frames.], tot_loss[loss=2.021, simple_loss=0.2417, pruned_loss=0.03108, codebook_loss=18.69, over 1106242.18 frames.], batch size: 21, lr: 4.87e-04
+2022-05-27 21:22:30,347 INFO [train.py:823] (2/4) Epoch 35, batch 350, loss[loss=1.985, simple_loss=0.2261, pruned_loss=0.02758, codebook_loss=18.45, over 7089.00 frames.], tot_loss[loss=2.022, simple_loss=0.2424, pruned_loss=0.03129, codebook_loss=18.7, over 1172770.52 frames.], batch size: 18, lr: 4.87e-04
+2022-05-27 21:23:10,160 INFO [train.py:823] (2/4) Epoch 35, batch 400, loss[loss=2.06, simple_loss=0.2613, pruned_loss=0.03457, codebook_loss=18.95, over 7184.00 frames.], tot_loss[loss=2.024, simple_loss=0.2423, pruned_loss=0.03141, codebook_loss=18.72, over 1222872.20 frames.], batch size: 22, lr: 4.86e-04
+2022-05-27 21:23:50,296 INFO [train.py:823] (2/4) Epoch 35, batch 450, loss[loss=1.989, simple_loss=0.2267, pruned_loss=0.02901, codebook_loss=18.46, over 7293.00 frames.], tot_loss[loss=2.027, simple_loss=0.2423, pruned_loss=0.0316, codebook_loss=18.74, over 1270596.57 frames.], batch size: 17, lr: 4.86e-04
+2022-05-27 21:24:30,258 INFO [train.py:823] (2/4) Epoch 35, batch 500, loss[loss=2.04, simple_loss=0.2282, pruned_loss=0.03428, codebook_loss=18.92, over 7030.00 frames.], tot_loss[loss=2.022, simple_loss=0.2417, pruned_loss=0.03098, codebook_loss=18.71, over 1305484.56 frames.], batch size: 17, lr: 4.86e-04
+2022-05-27 21:25:10,223 INFO [train.py:823] (2/4) Epoch 35, batch 550, loss[loss=2.033, simple_loss=0.2226, pruned_loss=0.02743, codebook_loss=18.94, over 7014.00 frames.], tot_loss[loss=2.024, simple_loss=0.2408, pruned_loss=0.03093, codebook_loss=18.73, over 1328602.66 frames.], batch size: 17, lr: 4.85e-04
+2022-05-27 21:25:50,297 INFO [train.py:823] (2/4) Epoch 35, batch 600, loss[loss=2.089, simple_loss=0.2448, pruned_loss=0.03776, codebook_loss=19.28, over 7290.00 frames.], tot_loss[loss=2.028, simple_loss=0.2409, pruned_loss=0.03096, codebook_loss=18.76, over 1350042.42 frames.], batch size: 20, lr: 4.85e-04
+2022-05-27 21:26:30,418 INFO [train.py:823] (2/4) Epoch 35, batch 650, loss[loss=1.973, simple_loss=0.2439, pruned_loss=0.02196, codebook_loss=18.29, over 7056.00 frames.], tot_loss[loss=2.024, simple_loss=0.2394, pruned_loss=0.03029, codebook_loss=18.74, over 1368554.78 frames.], batch size: 26, lr: 4.84e-04
+2022-05-27 21:27:11,695 INFO [train.py:823] (2/4) Epoch 35, batch 700, loss[loss=1.977, simple_loss=0.2341, pruned_loss=0.03056, codebook_loss=18.29, over 7275.00 frames.], tot_loss[loss=2.027, simple_loss=0.2391, pruned_loss=0.03056, codebook_loss=18.77, over 1378338.09 frames.], batch size: 20, lr: 4.84e-04
+2022-05-27 21:27:51,841 INFO [train.py:823] (2/4) Epoch 35, batch 750, loss[loss=2.041, simple_loss=0.2459, pruned_loss=0.03074, codebook_loss=18.88, over 7101.00 frames.], tot_loss[loss=2.026, simple_loss=0.2405, pruned_loss=0.03078, codebook_loss=18.75, over 1390874.68 frames.], batch size: 19, lr: 4.84e-04
+2022-05-27 21:28:31,660 INFO [train.py:823] (2/4) Epoch 35, batch 800, loss[loss=2.03, simple_loss=0.2374, pruned_loss=0.02448, codebook_loss=18.86, over 7309.00 frames.], tot_loss[loss=2.026, simple_loss=0.2411, pruned_loss=0.03089, codebook_loss=18.74, over 1394914.47 frames.], batch size: 18, lr: 4.83e-04
+2022-05-27 21:29:11,848 INFO [train.py:823] (2/4) Epoch 35, batch 850, loss[loss=1.971, simple_loss=0.2439, pruned_loss=0.02489, codebook_loss=18.24, over 7419.00 frames.], tot_loss[loss=2.026, simple_loss=0.2413, pruned_loss=0.03074, codebook_loss=18.74, over 1404129.12 frames.], batch size: 22, lr: 4.83e-04
+2022-05-27 21:29:51,287 INFO [train.py:823] (2/4) Epoch 35, batch 900, loss[loss=2.089, simple_loss=0.2541, pruned_loss=0.03351, codebook_loss=19.29, over 6451.00 frames.], tot_loss[loss=2.023, simple_loss=0.2408, pruned_loss=0.0305, codebook_loss=18.72, over 1401226.39 frames.], batch size: 34, lr: 4.83e-04
+2022-05-27 21:30:31,013 INFO [train.py:823] (2/4) Epoch 35, batch 950, loss[loss=1.93, simple_loss=0.2335, pruned_loss=0.03111, codebook_loss=17.82, over 4808.00 frames.], tot_loss[loss=2.025, simple_loss=0.2418, pruned_loss=0.03088, codebook_loss=18.73, over 1381022.19 frames.], batch size: 48, lr: 4.82e-04
+2022-05-27 21:30:46,167 INFO [train.py:823] (2/4) Epoch 36, batch 0, loss[loss=1.959, simple_loss=0.2543, pruned_loss=0.02037, codebook_loss=18.12, over 7424.00 frames.], tot_loss[loss=1.959, simple_loss=0.2543, pruned_loss=0.02037, codebook_loss=18.12, over 7424.00 frames.], batch size: 22, lr: 4.76e-04
+2022-05-27 21:31:25,789 INFO [train.py:823] (2/4) Epoch 36, batch 50, loss[loss=1.962, simple_loss=0.2061, pruned_loss=0.02058, codebook_loss=18.38, over 7145.00 frames.], tot_loss[loss=2.015, simple_loss=0.2355, pruned_loss=0.02955, codebook_loss=18.68, over 320049.70 frames.], batch size: 17, lr: 4.75e-04
+2022-05-27 21:32:05,760 INFO [train.py:823] (2/4) Epoch 36, batch 100, loss[loss=1.949, simple_loss=0.2516, pruned_loss=0.0252, codebook_loss=17.98, over 6365.00 frames.], tot_loss[loss=2.01, simple_loss=0.237, pruned_loss=0.02878, codebook_loss=18.63, over 565179.13 frames.], batch size: 34, lr: 4.75e-04
+2022-05-27 21:32:45,256 INFO [train.py:823] (2/4) Epoch 36, batch 150, loss[loss=2.011, simple_loss=0.2572, pruned_loss=0.0329, codebook_loss=18.49, over 7215.00 frames.], tot_loss[loss=2.02, simple_loss=0.2398, pruned_loss=0.02984, codebook_loss=18.7, over 752641.99 frames.], batch size: 25, lr: 4.74e-04
+2022-05-27 21:33:25,497 INFO [train.py:823] (2/4) Epoch 36, batch 200, loss[loss=1.969, simple_loss=0.2121, pruned_loss=0.02285, codebook_loss=18.4, over 7304.00 frames.], tot_loss[loss=2.015, simple_loss=0.2397, pruned_loss=0.02952, codebook_loss=18.65, over 900012.87 frames.], batch size: 17, lr: 4.74e-04
+2022-05-27 21:34:05,047 INFO [train.py:823] (2/4) Epoch 36, batch 250, loss[loss=1.908, simple_loss=0.2296, pruned_loss=0.02688, codebook_loss=17.67, over 7403.00 frames.], tot_loss[loss=2.027, simple_loss=0.2404, pruned_loss=0.03033, codebook_loss=18.76, over 1013133.63 frames.], batch size: 19, lr: 4.74e-04
+2022-05-27 21:34:45,301 INFO [train.py:823] (2/4) Epoch 36, batch 300, loss[loss=2.041, simple_loss=0.2579, pruned_loss=0.03573, codebook_loss=18.77, over 7329.00 frames.], tot_loss[loss=2.022, simple_loss=0.2397, pruned_loss=0.0301, codebook_loss=18.72, over 1101637.31 frames.], batch size: 23, lr: 4.73e-04
+2022-05-27 21:35:25,040 INFO [train.py:823] (2/4) Epoch 36, batch 350, loss[loss=2.053, simple_loss=0.2474, pruned_loss=0.02939, codebook_loss=19, over 7369.00 frames.], tot_loss[loss=2.02, simple_loss=0.2404, pruned_loss=0.03025, codebook_loss=18.7, over 1171846.20 frames.], batch size: 20, lr: 4.73e-04
+2022-05-27 21:36:05,131 INFO [train.py:823] (2/4) Epoch 36, batch 400, loss[loss=2.148, simple_loss=0.2471, pruned_loss=0.04071, codebook_loss=19.84, over 7105.00 frames.], tot_loss[loss=2.015, simple_loss=0.2406, pruned_loss=0.03019, codebook_loss=18.65, over 1227679.88 frames.], batch size: 18, lr: 4.73e-04
+2022-05-27 21:36:44,918 INFO [train.py:823] (2/4) Epoch 36, batch 450, loss[loss=2.045, simple_loss=0.2437, pruned_loss=0.03889, codebook_loss=18.84, over 6984.00 frames.], tot_loss[loss=2.016, simple_loss=0.2404, pruned_loss=0.03046, codebook_loss=18.65, over 1269783.32 frames.], batch size: 26, lr: 4.72e-04
+2022-05-27 21:37:24,997 INFO [train.py:823] (2/4) Epoch 36, batch 500, loss[loss=2.108, simple_loss=0.2648, pruned_loss=0.03763, codebook_loss=19.38, over 7244.00 frames.], tot_loss[loss=2.014, simple_loss=0.24, pruned_loss=0.03044, codebook_loss=18.63, over 1300404.83 frames.], batch size: 24, lr: 4.72e-04
+2022-05-27 21:38:04,890 INFO [train.py:823] (2/4) Epoch 36, batch 550, loss[loss=1.95, simple_loss=0.1945, pruned_loss=0.01861, codebook_loss=18.34, over 7296.00 frames.], tot_loss[loss=2.015, simple_loss=0.2402, pruned_loss=0.03052, codebook_loss=18.65, over 1327396.06 frames.], batch size: 17, lr: 4.72e-04
+2022-05-27 21:38:45,252 INFO [train.py:823] (2/4) Epoch 36, batch 600, loss[loss=2.092, simple_loss=0.2185, pruned_loss=0.02964, codebook_loss=19.53, over 7290.00 frames.], tot_loss[loss=2.019, simple_loss=0.2404, pruned_loss=0.03083, codebook_loss=18.68, over 1346061.80 frames.], batch size: 17, lr: 4.71e-04
+2022-05-27 21:39:26,310 INFO [train.py:823] (2/4) Epoch 36, batch 650, loss[loss=2.115, simple_loss=0.2348, pruned_loss=0.02453, codebook_loss=19.73, over 7378.00 frames.], tot_loss[loss=2.023, simple_loss=0.2416, pruned_loss=0.03104, codebook_loss=18.71, over 1361750.57 frames.], batch size: 21, lr: 4.71e-04
+2022-05-27 21:40:09,239 INFO [train.py:823] (2/4) Epoch 36, batch 700, loss[loss=1.982, simple_loss=0.2115, pruned_loss=0.02523, codebook_loss=18.51, over 7299.00 frames.], tot_loss[loss=2.025, simple_loss=0.2418, pruned_loss=0.03133, codebook_loss=18.73, over 1378029.56 frames.], batch size: 17, lr: 4.71e-04
+2022-05-27 21:40:49,219 INFO [train.py:823] (2/4) Epoch 36, batch 750, loss[loss=2.063, simple_loss=0.247, pruned_loss=0.03347, codebook_loss=19.06, over 7288.00 frames.], tot_loss[loss=2.025, simple_loss=0.2405, pruned_loss=0.0306, codebook_loss=18.74, over 1387583.09 frames.], batch size: 21, lr: 4.70e-04
+2022-05-27 21:41:29,163 INFO [train.py:823] (2/4) Epoch 36, batch 800, loss[loss=1.952, simple_loss=0.2428, pruned_loss=0.02461, codebook_loss=18.06, over 7380.00 frames.], tot_loss[loss=2.023, simple_loss=0.241, pruned_loss=0.03045, codebook_loss=18.72, over 1387506.20 frames.], batch size: 21, lr: 4.70e-04
+2022-05-27 21:42:08,714 INFO [train.py:823] (2/4) Epoch 36, batch 850, loss[loss=1.984, simple_loss=0.2726, pruned_loss=0.04017, codebook_loss=18.07, over 7334.00 frames.], tot_loss[loss=2.028, simple_loss=0.2407, pruned_loss=0.03083, codebook_loss=18.76, over 1388168.41 frames.], batch size: 23, lr: 4.70e-04
+2022-05-27 21:42:48,764 INFO [train.py:823] (2/4) Epoch 36, batch 900, loss[loss=1.902, simple_loss=0.2362, pruned_loss=0.02166, codebook_loss=17.62, over 7431.00 frames.], tot_loss[loss=2.024, simple_loss=0.2411, pruned_loss=0.03048, codebook_loss=18.73, over 1396421.86 frames.], batch size: 22, lr: 4.69e-04
+2022-05-27 21:43:42,172 INFO [train.py:823] (2/4) Epoch 37, batch 0, loss[loss=1.991, simple_loss=0.2691, pruned_loss=0.03634, codebook_loss=18.2, over 6718.00 frames.], tot_loss[loss=1.991, simple_loss=0.2691, pruned_loss=0.03634, codebook_loss=18.2, over 6718.00 frames.], batch size: 34, lr: 4.63e-04
+2022-05-27 21:44:22,064 INFO [train.py:823] (2/4) Epoch 37, batch 50, loss[loss=2.337, simple_loss=0.2766, pruned_loss=0.05266, codebook_loss=21.46, over 7291.00 frames.], tot_loss[loss=2.022, simple_loss=0.2426, pruned_loss=0.03051, codebook_loss=18.7, over 318971.96 frames.], batch size: 22, lr: 4.62e-04
+2022-05-27 21:45:01,721 INFO [train.py:823] (2/4) Epoch 37, batch 100, loss[loss=2.022, simple_loss=0.2518, pruned_loss=0.03852, codebook_loss=18.58, over 7224.00 frames.], tot_loss[loss=2.01, simple_loss=0.2428, pruned_loss=0.03108, codebook_loss=18.57, over 561796.22 frames.], batch size: 24, lr: 4.62e-04
+2022-05-27 21:45:41,728 INFO [train.py:823] (2/4) Epoch 37, batch 150, loss[loss=2.078, simple_loss=0.2495, pruned_loss=0.03073, codebook_loss=19.23, over 7187.00 frames.], tot_loss[loss=2.011, simple_loss=0.2402, pruned_loss=0.02989, codebook_loss=18.61, over 750371.97 frames.], batch size: 21, lr: 4.62e-04
+2022-05-27 21:46:21,863 INFO [train.py:823] (2/4) Epoch 37, batch 200, loss[loss=1.986, simple_loss=0.2809, pruned_loss=0.04146, codebook_loss=18.04, over 7236.00 frames.], tot_loss[loss=2.014, simple_loss=0.2387, pruned_loss=0.02999, codebook_loss=18.65, over 903903.54 frames.], batch size: 24, lr: 4.61e-04
+2022-05-27 21:47:01,961 INFO [train.py:823] (2/4) Epoch 37, batch 250, loss[loss=1.982, simple_loss=0.2367, pruned_loss=0.02309, codebook_loss=18.41, over 6980.00 frames.], tot_loss[loss=2.009, simple_loss=0.2392, pruned_loss=0.02972, codebook_loss=18.6, over 1020638.91 frames.], batch size: 26, lr: 4.61e-04
+2022-05-27 21:47:41,867 INFO [train.py:823] (2/4) Epoch 37, batch 300, loss[loss=1.998, simple_loss=0.2233, pruned_loss=0.03638, codebook_loss=18.5, over 7025.00 frames.], tot_loss[loss=2.013, simple_loss=0.2382, pruned_loss=0.02986, codebook_loss=18.64, over 1107430.67 frames.], batch size: 16, lr: 4.61e-04
+2022-05-27 21:48:21,748 INFO [train.py:823] (2/4) Epoch 37, batch 350, loss[loss=2.074, simple_loss=0.253, pruned_loss=0.03304, codebook_loss=19.14, over 7165.00 frames.], tot_loss[loss=2.009, simple_loss=0.2388, pruned_loss=0.02954, codebook_loss=18.6, over 1174550.36 frames.], batch size: 25, lr: 4.60e-04
+2022-05-27 21:49:01,292 INFO [train.py:823] (2/4) Epoch 37, batch 400, loss[loss=1.972, simple_loss=0.2191, pruned_loss=0.03118, codebook_loss=18.31, over 7288.00 frames.], tot_loss[loss=2.01, simple_loss=0.2401, pruned_loss=0.0298, codebook_loss=18.6, over 1230031.48 frames.], batch size: 17, lr: 4.60e-04
+2022-05-27 21:49:41,269 INFO [train.py:823] (2/4) Epoch 37, batch 450, loss[loss=2.195, simple_loss=0.2415, pruned_loss=0.02486, codebook_loss=20.49, over 7197.00 frames.], tot_loss[loss=2.014, simple_loss=0.2408, pruned_loss=0.02981, codebook_loss=18.64, over 1268980.94 frames.], batch size: 19, lr: 4.60e-04
+2022-05-27 21:50:22,179 INFO [train.py:823] (2/4) Epoch 37, batch 500, loss[loss=1.996, simple_loss=0.23, pruned_loss=0.02588, codebook_loss=18.56, over 7020.00 frames.], tot_loss[loss=2.018, simple_loss=0.2411, pruned_loss=0.02994, codebook_loss=18.67, over 1304055.42 frames.], batch size: 16, lr: 4.59e-04
+2022-05-27 21:51:02,118 INFO [train.py:823] (2/4) Epoch 37, batch 550, loss[loss=2.005, simple_loss=0.2245, pruned_loss=0.0261, codebook_loss=18.67, over 7004.00 frames.], tot_loss[loss=2.019, simple_loss=0.2406, pruned_loss=0.0301, codebook_loss=18.69, over 1330236.33 frames.], batch size: 16, lr: 4.59e-04
+2022-05-27 21:51:41,636 INFO [train.py:823] (2/4) Epoch 37, batch 600, loss[loss=1.983, simple_loss=0.2372, pruned_loss=0.02977, codebook_loss=18.35, over 7338.00 frames.], tot_loss[loss=2.019, simple_loss=0.2415, pruned_loss=0.03051, codebook_loss=18.68, over 1349479.13 frames.], batch size: 23, lr: 4.59e-04
+2022-05-27 21:52:22,242 INFO [train.py:823] (2/4) Epoch 37, batch 650, loss[loss=1.971, simple_loss=0.2258, pruned_loss=0.02069, codebook_loss=18.38, over 7150.00 frames.], tot_loss[loss=2.017, simple_loss=0.2408, pruned_loss=0.03023, codebook_loss=18.67, over 1364863.46 frames.], batch size: 17, lr: 4.58e-04
+2022-05-27 21:53:01,927 INFO [train.py:823] (2/4) Epoch 37, batch 700, loss[loss=2.035, simple_loss=0.2544, pruned_loss=0.03439, codebook_loss=18.73, over 7423.00 frames.], tot_loss[loss=2.02, simple_loss=0.2415, pruned_loss=0.03036, codebook_loss=18.69, over 1373127.31 frames.], batch size: 22, lr: 4.58e-04
+2022-05-27 21:53:41,852 INFO [train.py:823] (2/4) Epoch 37, batch 750, loss[loss=1.988, simple_loss=0.2488, pruned_loss=0.02929, codebook_loss=18.35, over 4870.00 frames.], tot_loss[loss=2.023, simple_loss=0.2415, pruned_loss=0.03049, codebook_loss=18.72, over 1379619.74 frames.], batch size: 46, lr: 4.58e-04
+2022-05-27 21:54:21,480 INFO [train.py:823] (2/4) Epoch 37, batch 800, loss[loss=1.974, simple_loss=0.2728, pruned_loss=0.03817, codebook_loss=17.99, over 7285.00 frames.], tot_loss[loss=2.021, simple_loss=0.2414, pruned_loss=0.03031, codebook_loss=18.7, over 1383581.97 frames.], batch size: 21, lr: 4.57e-04
+2022-05-27 21:55:01,502 INFO [train.py:823] (2/4) Epoch 37, batch 850, loss[loss=2.18, simple_loss=0.2327, pruned_loss=0.04204, codebook_loss=20.21, over 6778.00 frames.], tot_loss[loss=2.023, simple_loss=0.2409, pruned_loss=0.03033, codebook_loss=18.72, over 1384467.32 frames.], batch size: 15, lr: 4.57e-04
+2022-05-27 21:55:41,438 INFO [train.py:823] (2/4) Epoch 37, batch 900, loss[loss=1.911, simple_loss=0.2713, pruned_loss=0.02798, codebook_loss=17.47, over 7145.00 frames.], tot_loss[loss=2.021, simple_loss=0.2402, pruned_loss=0.03022, codebook_loss=18.71, over 1391651.78 frames.], batch size: 23, lr: 4.57e-04
+2022-05-27 21:56:35,790 INFO [train.py:823] (2/4) Epoch 38, batch 0, loss[loss=1.896, simple_loss=0.2252, pruned_loss=0.02307, codebook_loss=17.6, over 7395.00 frames.], tot_loss[loss=1.896, simple_loss=0.2252, pruned_loss=0.02307, codebook_loss=17.6, over 7395.00 frames.], batch size: 19, lr: 4.50e-04
+2022-05-27 21:57:15,588 INFO [train.py:823] (2/4) Epoch 38, batch 50, loss[loss=1.995, simple_loss=0.2503, pruned_loss=0.03506, codebook_loss=18.35, over 7107.00 frames.], tot_loss[loss=1.992, simple_loss=0.2389, pruned_loss=0.02907, codebook_loss=18.43, over 322309.85 frames.], batch size: 19, lr: 4.50e-04
+2022-05-27 21:57:55,716 INFO [train.py:823] (2/4) Epoch 38, batch 100, loss[loss=1.994, simple_loss=0.2556, pruned_loss=0.04204, codebook_loss=18.25, over 7322.00 frames.], tot_loss[loss=2.007, simple_loss=0.2399, pruned_loss=0.03017, codebook_loss=18.57, over 565523.05 frames.], batch size: 23, lr: 4.50e-04
+2022-05-27 21:58:35,471 INFO [train.py:823] (2/4) Epoch 38, batch 150, loss[loss=2.025, simple_loss=0.2739, pruned_loss=0.03711, codebook_loss=18.51, over 7038.00 frames.], tot_loss[loss=2.001, simple_loss=0.2398, pruned_loss=0.02955, codebook_loss=18.52, over 754823.83 frames.], batch size: 26, lr: 4.50e-04
+2022-05-27 21:59:15,486 INFO [train.py:823] (2/4) Epoch 38, batch 200, loss[loss=2.077, simple_loss=0.2713, pruned_loss=0.04199, codebook_loss=19, over 6791.00 frames.], tot_loss[loss=2.002, simple_loss=0.2398, pruned_loss=0.02927, codebook_loss=18.52, over 903249.32 frames.], batch size: 34, lr: 4.49e-04
+2022-05-27 21:59:55,447 INFO [train.py:823] (2/4) Epoch 38, batch 250, loss[loss=2, simple_loss=0.2475, pruned_loss=0.03316, codebook_loss=18.43, over 7100.00 frames.], tot_loss[loss=1.992, simple_loss=0.2385, pruned_loss=0.02882, codebook_loss=18.44, over 1022458.61 frames.], batch size: 20, lr: 4.49e-04
+2022-05-27 22:00:35,327 INFO [train.py:823] (2/4) Epoch 38, batch 300, loss[loss=1.931, simple_loss=0.2423, pruned_loss=0.02761, codebook_loss=17.83, over 7283.00 frames.], tot_loss[loss=1.991, simple_loss=0.2391, pruned_loss=0.02899, codebook_loss=18.42, over 1108120.62 frames.], batch size: 21, lr: 4.49e-04
+2022-05-27 22:01:15,224 INFO [train.py:823] (2/4) Epoch 38, batch 350, loss[loss=1.906, simple_loss=0.2049, pruned_loss=0.01452, codebook_loss=17.89, over 6837.00 frames.], tot_loss[loss=1.994, simple_loss=0.2398, pruned_loss=0.0292, codebook_loss=18.45, over 1182476.41 frames.], batch size: 15, lr: 4.48e-04
+2022-05-27 22:01:55,558 INFO [train.py:823] (2/4) Epoch 38, batch 400, loss[loss=1.982, simple_loss=0.2484, pruned_loss=0.03112, codebook_loss=18.26, over 5132.00 frames.], tot_loss[loss=1.997, simple_loss=0.2398, pruned_loss=0.02929, codebook_loss=18.47, over 1235830.53 frames.], batch size: 46, lr: 4.48e-04
+2022-05-27 22:02:35,639 INFO [train.py:823] (2/4) Epoch 38, batch 450, loss[loss=1.981, simple_loss=0.2484, pruned_loss=0.02938, codebook_loss=18.27, over 7194.00 frames.], tot_loss[loss=2.006, simple_loss=0.2391, pruned_loss=0.0294, codebook_loss=18.57, over 1280930.98 frames.], batch size: 20, lr: 4.48e-04
+2022-05-27 22:03:16,100 INFO [train.py:823] (2/4) Epoch 38, batch 500, loss[loss=1.963, simple_loss=0.2799, pruned_loss=0.03361, codebook_loss=17.9, over 7275.00 frames.], tot_loss[loss=2.003, simple_loss=0.2379, pruned_loss=0.02905, codebook_loss=18.55, over 1314843.67 frames.], batch size: 21, lr: 4.47e-04
+2022-05-27 22:03:55,599 INFO [train.py:823] (2/4) Epoch 38, batch 550, loss[loss=1.956, simple_loss=0.2321, pruned_loss=0.0212, codebook_loss=18.18, over 7199.00 frames.], tot_loss[loss=2.007, simple_loss=0.2382, pruned_loss=0.02904, codebook_loss=18.58, over 1332558.80 frames.], batch size: 20, lr: 4.47e-04
+2022-05-27 22:04:38,500 INFO [train.py:823] (2/4) Epoch 38, batch 600, loss[loss=1.959, simple_loss=0.2407, pruned_loss=0.02577, codebook_loss=18.13, over 6492.00 frames.], tot_loss[loss=2.013, simple_loss=0.2394, pruned_loss=0.0299, codebook_loss=18.63, over 1350199.23 frames.], batch size: 34, lr: 4.47e-04
+2022-05-27 22:05:19,546 INFO [train.py:823] (2/4) Epoch 38, batch 650, loss[loss=1.944, simple_loss=0.2501, pruned_loss=0.02524, codebook_loss=17.94, over 7268.00 frames.], tot_loss[loss=2.006, simple_loss=0.2399, pruned_loss=0.02974, codebook_loss=18.56, over 1366728.10 frames.], batch size: 20, lr: 4.46e-04
+2022-05-27 22:05:59,572 INFO [train.py:823] (2/4) Epoch 38, batch 700, loss[loss=2.071, simple_loss=0.2583, pruned_loss=0.04474, codebook_loss=18.97, over 7157.00 frames.], tot_loss[loss=2.006, simple_loss=0.2403, pruned_loss=0.02972, codebook_loss=18.56, over 1377520.14 frames.], batch size: 22, lr: 4.46e-04
+2022-05-27 22:06:39,240 INFO [train.py:823] (2/4) Epoch 38, batch 750, loss[loss=1.96, simple_loss=0.2553, pruned_loss=0.03187, codebook_loss=18.01, over 7239.00 frames.], tot_loss[loss=2.004, simple_loss=0.2402, pruned_loss=0.02936, codebook_loss=18.55, over 1383952.48 frames.], batch size: 24, lr: 4.46e-04
+2022-05-27 22:07:19,344 INFO [train.py:823] (2/4) Epoch 38, batch 800, loss[loss=1.978, simple_loss=0.2478, pruned_loss=0.0202, codebook_loss=18.34, over 7371.00 frames.], tot_loss[loss=2.005, simple_loss=0.2402, pruned_loss=0.02958, codebook_loss=18.55, over 1386620.75 frames.], batch size: 21, lr: 4.45e-04
+2022-05-27 22:07:59,080 INFO [train.py:823] (2/4) Epoch 38, batch 850, loss[loss=2.136, simple_loss=0.2842, pruned_loss=0.04337, codebook_loss=19.5, over 7019.00 frames.], tot_loss[loss=2.007, simple_loss=0.2405, pruned_loss=0.02971, codebook_loss=18.57, over 1395745.73 frames.], batch size: 29, lr: 4.45e-04
+2022-05-27 22:08:39,064 INFO [train.py:823] (2/4) Epoch 38, batch 900, loss[loss=1.961, simple_loss=0.2261, pruned_loss=0.02526, codebook_loss=18.23, over 6990.00 frames.], tot_loss[loss=2.009, simple_loss=0.2403, pruned_loss=0.0293, codebook_loss=18.59, over 1399870.35 frames.], batch size: 16, lr: 4.45e-04
+2022-05-27 22:09:18,336 INFO [train.py:823] (2/4) Epoch 38, batch 950, loss[loss=1.971, simple_loss=0.2234, pruned_loss=0.02054, codebook_loss=18.39, over 4917.00 frames.], tot_loss[loss=2.01, simple_loss=0.2399, pruned_loss=0.02941, codebook_loss=18.61, over 1374581.31 frames.], batch size: 46, lr: 4.45e-04
+2022-05-27 22:09:30,201 INFO [train.py:823] (2/4) Epoch 39, batch 0, loss[loss=1.918, simple_loss=0.232, pruned_loss=0.02186, codebook_loss=17.81, over 7286.00 frames.], tot_loss[loss=1.918, simple_loss=0.232, pruned_loss=0.02186, codebook_loss=17.81, over 7286.00 frames.], batch size: 19, lr: 4.39e-04
+2022-05-27 22:10:10,197 INFO [train.py:823] (2/4) Epoch 39, batch 50, loss[loss=2.015, simple_loss=0.227, pruned_loss=0.02697, codebook_loss=18.74, over 7414.00 frames.], tot_loss[loss=1.995, simple_loss=0.2395, pruned_loss=0.03004, codebook_loss=18.45, over 322519.79 frames.], batch size: 22, lr: 4.39e-04
+2022-05-27 22:10:50,150 INFO [train.py:823] (2/4) Epoch 39, batch 100, loss[loss=2.01, simple_loss=0.2308, pruned_loss=0.03128, codebook_loss=18.63, over 7307.00 frames.], tot_loss[loss=2, simple_loss=0.2377, pruned_loss=0.02965, codebook_loss=18.52, over 567100.62 frames.], batch size: 18, lr: 4.38e-04
+2022-05-27 22:11:30,529 INFO [train.py:823] (2/4) Epoch 39, batch 150, loss[loss=1.973, simple_loss=0.2595, pruned_loss=0.03792, codebook_loss=18.05, over 7215.00 frames.], tot_loss[loss=1.998, simple_loss=0.2365, pruned_loss=0.0291, codebook_loss=18.51, over 755263.42 frames.], batch size: 25, lr: 4.38e-04
+2022-05-27 22:12:10,628 INFO [train.py:823] (2/4) Epoch 39, batch 200, loss[loss=1.961, simple_loss=0.2195, pruned_loss=0.02937, codebook_loss=18.22, over 7405.00 frames.], tot_loss[loss=2.008, simple_loss=0.2364, pruned_loss=0.02915, codebook_loss=18.61, over 906540.38 frames.], batch size: 19, lr: 4.38e-04
+2022-05-27 22:12:50,944 INFO [train.py:823] (2/4) Epoch 39, batch 250, loss[loss=2.213, simple_loss=0.2363, pruned_loss=0.03772, codebook_loss=20.57, over 7294.00 frames.], tot_loss[loss=2.013, simple_loss=0.2375, pruned_loss=0.02933, codebook_loss=18.65, over 1020833.53 frames.], batch size: 19, lr: 4.37e-04
+2022-05-27 22:13:31,026 INFO [train.py:823] (2/4) Epoch 39, batch 300, loss[loss=1.938, simple_loss=0.2163, pruned_loss=0.02411, codebook_loss=18.06, over 7298.00 frames.], tot_loss[loss=2.015, simple_loss=0.2375, pruned_loss=0.02961, codebook_loss=18.67, over 1113439.13 frames.], batch size: 19, lr: 4.37e-04
+2022-05-27 22:14:11,229 INFO [train.py:823] (2/4) Epoch 39, batch 350, loss[loss=1.924, simple_loss=0.222, pruned_loss=0.01487, codebook_loss=17.98, over 7386.00 frames.], tot_loss[loss=2.015, simple_loss=0.2381, pruned_loss=0.0296, codebook_loss=18.67, over 1184452.49 frames.], batch size: 20, lr: 4.37e-04
+2022-05-27 22:14:52,339 INFO [train.py:823] (2/4) Epoch 39, batch 400, loss[loss=2.087, simple_loss=0.203, pruned_loss=0.01548, codebook_loss=19.7, over 7031.00 frames.], tot_loss[loss=2.016, simple_loss=0.239, pruned_loss=0.02979, codebook_loss=18.67, over 1242141.35 frames.], batch size: 17, lr: 4.36e-04
+2022-05-27 22:15:32,463 INFO [train.py:823] (2/4) Epoch 39, batch 450, loss[loss=1.998, simple_loss=0.2565, pruned_loss=0.03527, codebook_loss=18.34, over 6960.00 frames.], tot_loss[loss=2.013, simple_loss=0.239, pruned_loss=0.02947, codebook_loss=18.64, over 1281383.06 frames.], batch size: 26, lr: 4.36e-04
+2022-05-27 22:16:12,044 INFO [train.py:823] (2/4) Epoch 39, batch 500, loss[loss=2.232, simple_loss=0.2557, pruned_loss=0.04382, codebook_loss=20.61, over 5302.00 frames.], tot_loss[loss=2.011, simple_loss=0.2384, pruned_loss=0.02917, codebook_loss=18.62, over 1310883.99 frames.], batch size: 48, lr: 4.36e-04
+2022-05-27 22:16:52,089 INFO [train.py:823] (2/4) Epoch 39, batch 550, loss[loss=1.95, simple_loss=0.2513, pruned_loss=0.03364, codebook_loss=17.91, over 7228.00 frames.], tot_loss[loss=2.008, simple_loss=0.2382, pruned_loss=0.02896, codebook_loss=18.6, over 1332022.89 frames.], batch size: 25, lr: 4.36e-04
+2022-05-27 22:17:32,020 INFO [train.py:823] (2/4) Epoch 39, batch 600, loss[loss=1.906, simple_loss=0.2161, pruned_loss=0.02302, codebook_loss=17.75, over 7437.00 frames.], tot_loss[loss=2.005, simple_loss=0.2382, pruned_loss=0.02875, codebook_loss=18.57, over 1355136.27 frames.], batch size: 18, lr: 4.35e-04
+2022-05-27 22:18:12,393 INFO [train.py:823] (2/4) Epoch 39, batch 650, loss[loss=2.048, simple_loss=0.2371, pruned_loss=0.03185, codebook_loss=18.98, over 7395.00 frames.], tot_loss[loss=2.007, simple_loss=0.2387, pruned_loss=0.02897, codebook_loss=18.58, over 1373949.39 frames.], batch size: 19, lr: 4.35e-04
+2022-05-27 22:18:52,194 INFO [train.py:823] (2/4) Epoch 39, batch 700, loss[loss=2.019, simple_loss=0.2628, pruned_loss=0.04583, codebook_loss=18.42, over 7233.00 frames.], tot_loss[loss=2.01, simple_loss=0.2393, pruned_loss=0.02925, codebook_loss=18.61, over 1383205.82 frames.], batch size: 24, lr: 4.35e-04
+2022-05-27 22:19:32,454 INFO [train.py:823] (2/4) Epoch 39, batch 750, loss[loss=1.976, simple_loss=0.2451, pruned_loss=0.02824, codebook_loss=18.25, over 7366.00 frames.], tot_loss[loss=2.016, simple_loss=0.2387, pruned_loss=0.02929, codebook_loss=18.67, over 1389558.60 frames.], batch size: 20, lr: 4.34e-04
+2022-05-27 22:20:12,028 INFO [train.py:823] (2/4) Epoch 39, batch 800, loss[loss=1.954, simple_loss=0.2207, pruned_loss=0.0201, codebook_loss=18.24, over 7194.00 frames.], tot_loss[loss=2.017, simple_loss=0.2388, pruned_loss=0.02916, codebook_loss=18.69, over 1398442.44 frames.], batch size: 18, lr: 4.34e-04
+2022-05-27 22:20:52,215 INFO [train.py:823] (2/4) Epoch 39, batch 850, loss[loss=1.991, simple_loss=0.2643, pruned_loss=0.03697, codebook_loss=18.22, over 7340.00 frames.], tot_loss[loss=2.017, simple_loss=0.2388, pruned_loss=0.02899, codebook_loss=18.68, over 1397190.38 frames.], batch size: 23, lr: 4.34e-04
+2022-05-27 22:21:31,555 INFO [train.py:823] (2/4) Epoch 39, batch 900, loss[loss=2.007, simple_loss=0.2565, pruned_loss=0.02819, codebook_loss=18.5, over 6957.00 frames.], tot_loss[loss=2.017, simple_loss=0.2403, pruned_loss=0.02926, codebook_loss=18.68, over 1390177.65 frames.], batch size: 29, lr: 4.34e-04
+2022-05-27 22:22:10,919 INFO [train.py:823] (2/4) Epoch 39, batch 950, loss[loss=1.973, simple_loss=0.2361, pruned_loss=0.03439, codebook_loss=18.2, over 4559.00 frames.], tot_loss[loss=2.015, simple_loss=0.24, pruned_loss=0.02969, codebook_loss=18.65, over 1363967.56 frames.], batch size: 46, lr: 4.33e-04
+2022-05-27 22:22:23,045 INFO [train.py:823] (2/4) Epoch 40, batch 0, loss[loss=1.979, simple_loss=0.2381, pruned_loss=0.0281, codebook_loss=18.31, over 7162.00 frames.], tot_loss[loss=1.979, simple_loss=0.2381, pruned_loss=0.0281, codebook_loss=18.31, over 7162.00 frames.], batch size: 23, lr: 4.28e-04
+2022-05-27 22:23:02,841 INFO [train.py:823] (2/4) Epoch 40, batch 50, loss[loss=1.939, simple_loss=0.2192, pruned_loss=0.02459, codebook_loss=18.05, over 7111.00 frames.], tot_loss[loss=2.012, simple_loss=0.2397, pruned_loss=0.03033, codebook_loss=18.62, over 317776.38 frames.], batch size: 20, lr: 4.28e-04
+2022-05-27 22:23:42,932 INFO [train.py:823] (2/4) Epoch 40, batch 100, loss[loss=2.049, simple_loss=0.2088, pruned_loss=0.02951, codebook_loss=19.15, over 7233.00 frames.], tot_loss[loss=2.004, simple_loss=0.2381, pruned_loss=0.02965, codebook_loss=18.55, over 558916.89 frames.], batch size: 16, lr: 4.27e-04
+2022-05-27 22:24:22,699 INFO [train.py:823] (2/4) Epoch 40, batch 150, loss[loss=1.998, simple_loss=0.2471, pruned_loss=0.02919, codebook_loss=18.45, over 6994.00 frames.], tot_loss[loss=2.006, simple_loss=0.2382, pruned_loss=0.02913, codebook_loss=18.58, over 746971.36 frames.], batch size: 29, lr: 4.27e-04
+2022-05-27 22:25:02,894 INFO [train.py:823] (2/4) Epoch 40, batch 200, loss[loss=2.078, simple_loss=0.2545, pruned_loss=0.03585, codebook_loss=19.15, over 7180.00 frames.], tot_loss[loss=2.014, simple_loss=0.2393, pruned_loss=0.02992, codebook_loss=18.64, over 898142.68 frames.], batch size: 21, lr: 4.27e-04
+2022-05-27 22:25:42,826 INFO [train.py:823] (2/4) Epoch 40, batch 250, loss[loss=1.987, simple_loss=0.2109, pruned_loss=0.01808, codebook_loss=18.64, over 7274.00 frames.], tot_loss[loss=2.002, simple_loss=0.2389, pruned_loss=0.02947, codebook_loss=18.53, over 1015214.19 frames.], batch size: 16, lr: 4.26e-04
+2022-05-27 22:26:23,210 INFO [train.py:823] (2/4) Epoch 40, batch 300, loss[loss=1.988, simple_loss=0.2275, pruned_loss=0.02581, codebook_loss=18.48, over 7375.00 frames.], tot_loss[loss=2.003, simple_loss=0.2379, pruned_loss=0.02891, codebook_loss=18.55, over 1105586.30 frames.], batch size: 20, lr: 4.26e-04
+2022-05-27 22:27:03,143 INFO [train.py:823] (2/4) Epoch 40, batch 350, loss[loss=1.936, simple_loss=0.2517, pruned_loss=0.01949, codebook_loss=17.9, over 6579.00 frames.], tot_loss[loss=2.005, simple_loss=0.2381, pruned_loss=0.02912, codebook_loss=18.57, over 1178081.12 frames.], batch size: 34, lr: 4.26e-04
+2022-05-27 22:27:43,316 INFO [train.py:823] (2/4) Epoch 40, batch 400, loss[loss=2.158, simple_loss=0.2208, pruned_loss=0.0323, codebook_loss=20.15, over 7001.00 frames.], tot_loss[loss=2.003, simple_loss=0.2376, pruned_loss=0.02874, codebook_loss=18.55, over 1236837.38 frames.], batch size: 16, lr: 4.26e-04
+2022-05-27 22:28:23,127 INFO [train.py:823] (2/4) Epoch 40, batch 450, loss[loss=1.97, simple_loss=0.2077, pruned_loss=0.02831, codebook_loss=18.38, over 6797.00 frames.], tot_loss[loss=2.002, simple_loss=0.2372, pruned_loss=0.02868, codebook_loss=18.54, over 1276629.99 frames.], batch size: 15, lr: 4.25e-04
+2022-05-27 22:29:05,772 INFO [train.py:823] (2/4) Epoch 40, batch 500, loss[loss=2.045, simple_loss=0.2477, pruned_loss=0.03448, codebook_loss=18.87, over 7373.00 frames.], tot_loss[loss=2.005, simple_loss=0.2382, pruned_loss=0.02914, codebook_loss=18.56, over 1308992.33 frames.], batch size: 20, lr: 4.25e-04
+2022-05-27 22:29:47,090 INFO [train.py:823] (2/4) Epoch 40, batch 550, loss[loss=1.899, simple_loss=0.2646, pruned_loss=0.01769, codebook_loss=17.49, over 7293.00 frames.], tot_loss[loss=2.003, simple_loss=0.2375, pruned_loss=0.029, codebook_loss=18.55, over 1336194.86 frames.], batch size: 22, lr: 4.25e-04
+2022-05-27 22:30:27,066 INFO [train.py:823] (2/4) Epoch 40, batch 600, loss[loss=1.968, simple_loss=0.2384, pruned_loss=0.02572, codebook_loss=18.23, over 7299.00 frames.], tot_loss[loss=2.001, simple_loss=0.238, pruned_loss=0.02875, codebook_loss=18.53, over 1355579.49 frames.], batch size: 22, lr: 4.24e-04
+2022-05-27 22:31:06,976 INFO [train.py:823] (2/4) Epoch 40, batch 650, loss[loss=1.97, simple_loss=0.232, pruned_loss=0.02949, codebook_loss=18.24, over 7198.00 frames.], tot_loss[loss=2.004, simple_loss=0.2386, pruned_loss=0.02918, codebook_loss=18.56, over 1366307.21 frames.], batch size: 19, lr: 4.24e-04
+2022-05-27 22:31:46,870 INFO [train.py:823] (2/4) Epoch 40, batch 700, loss[loss=2.103, simple_loss=0.245, pruned_loss=0.0248, codebook_loss=19.56, over 7204.00 frames.], tot_loss[loss=2.005, simple_loss=0.2405, pruned_loss=0.02948, codebook_loss=18.55, over 1379016.92 frames.], batch size: 20, lr: 4.24e-04
+2022-05-27 22:32:26,842 INFO [train.py:823] (2/4) Epoch 40, batch 750, loss[loss=1.931, simple_loss=0.2484, pruned_loss=0.02892, codebook_loss=17.78, over 4961.00 frames.], tot_loss[loss=2.007, simple_loss=0.2401, pruned_loss=0.02943, codebook_loss=18.57, over 1387943.29 frames.], batch size: 48, lr: 4.24e-04
+2022-05-27 22:33:07,181 INFO [train.py:823] (2/4) Epoch 40, batch 800, loss[loss=1.978, simple_loss=0.2561, pruned_loss=0.0303, codebook_loss=18.19, over 7187.00 frames.], tot_loss[loss=2.01, simple_loss=0.2399, pruned_loss=0.02955, codebook_loss=18.6, over 1388961.48 frames.], batch size: 21, lr: 4.23e-04
+2022-05-27 22:33:46,909 INFO [train.py:823] (2/4) Epoch 40, batch 850, loss[loss=2.01, simple_loss=0.2448, pruned_loss=0.0399, codebook_loss=18.48, over 7171.00 frames.], tot_loss[loss=2.013, simple_loss=0.2397, pruned_loss=0.02943, codebook_loss=18.64, over 1397182.15 frames.], batch size: 22, lr: 4.23e-04
+2022-05-27 22:34:26,956 INFO [train.py:823] (2/4) Epoch 40, batch 900, loss[loss=2.214, simple_loss=0.2369, pruned_loss=0.03081, codebook_loss=20.65, over 7364.00 frames.], tot_loss[loss=2.009, simple_loss=0.2399, pruned_loss=0.02954, codebook_loss=18.6, over 1389789.68 frames.], batch size: 20, lr: 4.23e-04
+2022-05-27 22:35:20,785 INFO [train.py:823] (2/4) Epoch 41, batch 0, loss[loss=1.871, simple_loss=0.2206, pruned_loss=0.01667, codebook_loss=17.45, over 7095.00 frames.], tot_loss[loss=1.871, simple_loss=0.2206, pruned_loss=0.01667, codebook_loss=17.45, over 7095.00 frames.], batch size: 19, lr: 4.17e-04
+2022-05-27 22:36:00,864 INFO [train.py:823] (2/4) Epoch 41, batch 50, loss[loss=2.057, simple_loss=0.2644, pruned_loss=0.04223, codebook_loss=18.82, over 7378.00 frames.], tot_loss[loss=2.012, simple_loss=0.2394, pruned_loss=0.02906, codebook_loss=18.63, over 321844.31 frames.], batch size: 20, lr: 4.17e-04
+2022-05-27 22:36:40,295 INFO [train.py:823] (2/4) Epoch 41, batch 100, loss[loss=1.907, simple_loss=0.2183, pruned_loss=0.02059, codebook_loss=17.77, over 7096.00 frames.], tot_loss[loss=2.005, simple_loss=0.2387, pruned_loss=0.02829, codebook_loss=18.58, over 561684.71 frames.], batch size: 18, lr: 4.17e-04
+2022-05-27 22:37:20,562 INFO [train.py:823] (2/4) Epoch 41, batch 150, loss[loss=1.961, simple_loss=0.2558, pruned_loss=0.03346, codebook_loss=18, over 7023.00 frames.], tot_loss[loss=1.995, simple_loss=0.2388, pruned_loss=0.02824, codebook_loss=18.47, over 753825.87 frames.], batch size: 26, lr: 4.17e-04
+2022-05-27 22:38:00,348 INFO [train.py:823] (2/4) Epoch 41, batch 200, loss[loss=2.008, simple_loss=0.2381, pruned_loss=0.0209, codebook_loss=18.68, over 7397.00 frames.], tot_loss[loss=1.993, simple_loss=0.2383, pruned_loss=0.02789, codebook_loss=18.46, over 905889.70 frames.], batch size: 19, lr: 4.16e-04
+2022-05-27 22:38:41,533 INFO [train.py:823] (2/4) Epoch 41, batch 250, loss[loss=1.963, simple_loss=0.2319, pruned_loss=0.0259, codebook_loss=18.21, over 7105.00 frames.], tot_loss[loss=1.99, simple_loss=0.2373, pruned_loss=0.02753, codebook_loss=18.44, over 1017259.74 frames.], batch size: 19, lr: 4.16e-04
+2022-05-27 22:39:21,240 INFO [train.py:823] (2/4) Epoch 41, batch 300, loss[loss=1.909, simple_loss=0.2193, pruned_loss=0.01887, codebook_loss=17.8, over 7374.00 frames.], tot_loss[loss=1.99, simple_loss=0.2368, pruned_loss=0.02726, codebook_loss=18.45, over 1107953.71 frames.], batch size: 20, lr: 4.16e-04
+2022-05-27 22:40:01,365 INFO [train.py:823] (2/4) Epoch 41, batch 350, loss[loss=1.981, simple_loss=0.2465, pruned_loss=0.03568, codebook_loss=18.22, over 7171.00 frames.], tot_loss[loss=1.989, simple_loss=0.2377, pruned_loss=0.02756, codebook_loss=18.43, over 1175488.16 frames.], batch size: 22, lr: 4.15e-04
+2022-05-27 22:40:41,045 INFO [train.py:823] (2/4) Epoch 41, batch 400, loss[loss=1.983, simple_loss=0.2541, pruned_loss=0.0321, codebook_loss=18.24, over 7162.00 frames.], tot_loss[loss=1.993, simple_loss=0.2378, pruned_loss=0.02775, codebook_loss=18.46, over 1223236.50 frames.], batch size: 23, lr: 4.15e-04
+2022-05-27 22:41:21,040 INFO [train.py:823] (2/4) Epoch 41, batch 450, loss[loss=2.068, simple_loss=0.2325, pruned_loss=0.03945, codebook_loss=19.12, over 7098.00 frames.], tot_loss[loss=2.001, simple_loss=0.2385, pruned_loss=0.02842, codebook_loss=18.53, over 1264989.55 frames.], batch size: 18, lr: 4.15e-04
+2022-05-27 22:42:00,715 INFO [train.py:823] (2/4) Epoch 41, batch 500, loss[loss=1.919, simple_loss=0.2353, pruned_loss=0.02083, codebook_loss=17.81, over 7312.00 frames.], tot_loss[loss=2.002, simple_loss=0.2399, pruned_loss=0.02883, codebook_loss=18.53, over 1299456.59 frames.], batch size: 22, lr: 4.15e-04
+2022-05-27 22:42:40,898 INFO [train.py:823] (2/4) Epoch 41, batch 550, loss[loss=1.932, simple_loss=0.2436, pruned_loss=0.02929, codebook_loss=17.81, over 7210.00 frames.], tot_loss[loss=2, simple_loss=0.2393, pruned_loss=0.02861, codebook_loss=18.51, over 1322169.16 frames.], batch size: 19, lr: 4.14e-04
+2022-05-27 22:43:20,791 INFO [train.py:823] (2/4) Epoch 41, batch 600, loss[loss=1.882, simple_loss=0.2586, pruned_loss=0.03074, codebook_loss=17.22, over 7169.00 frames.], tot_loss[loss=1.998, simple_loss=0.2388, pruned_loss=0.02852, codebook_loss=18.5, over 1339272.29 frames.], batch size: 21, lr: 4.14e-04
+2022-05-27 22:44:00,860 INFO [train.py:823] (2/4) Epoch 41, batch 650, loss[loss=1.954, simple_loss=0.2375, pruned_loss=0.02982, codebook_loss=18.05, over 7179.00 frames.], tot_loss[loss=1.996, simple_loss=0.2385, pruned_loss=0.02842, codebook_loss=18.48, over 1358189.09 frames.], batch size: 21, lr: 4.14e-04
+2022-05-27 22:44:40,533 INFO [train.py:823] (2/4) Epoch 41, batch 700, loss[loss=1.941, simple_loss=0.2199, pruned_loss=0.02104, codebook_loss=18.1, over 7232.00 frames.], tot_loss[loss=1.991, simple_loss=0.238, pruned_loss=0.02815, codebook_loss=18.44, over 1371333.20 frames.], batch size: 16, lr: 4.14e-04
+2022-05-27 22:45:20,390 INFO [train.py:823] (2/4) Epoch 41, batch 750, loss[loss=2.107, simple_loss=0.2369, pruned_loss=0.03866, codebook_loss=19.5, over 7186.00 frames.], tot_loss[loss=1.993, simple_loss=0.2382, pruned_loss=0.02836, codebook_loss=18.46, over 1380074.90 frames.], batch size: 18, lr: 4.13e-04
+2022-05-27 22:45:59,895 INFO [train.py:823] (2/4) Epoch 41, batch 800, loss[loss=2.018, simple_loss=0.2207, pruned_loss=0.02951, codebook_loss=18.78, over 7306.00 frames.], tot_loss[loss=1.996, simple_loss=0.2383, pruned_loss=0.02865, codebook_loss=18.48, over 1382295.94 frames.], batch size: 17, lr: 4.13e-04
+2022-05-27 22:46:40,281 INFO [train.py:823] (2/4) Epoch 41, batch 850, loss[loss=1.94, simple_loss=0.2229, pruned_loss=0.02661, codebook_loss=18.02, over 7294.00 frames.], tot_loss[loss=1.994, simple_loss=0.2391, pruned_loss=0.02879, codebook_loss=18.46, over 1394329.10 frames.], batch size: 19, lr: 4.13e-04
+2022-05-27 22:47:20,134 INFO [train.py:823] (2/4) Epoch 41, batch 900, loss[loss=1.94, simple_loss=0.1993, pruned_loss=0.02022, codebook_loss=18.2, over 7286.00 frames.], tot_loss[loss=1.999, simple_loss=0.2384, pruned_loss=0.0288, codebook_loss=18.51, over 1399417.71 frames.], batch size: 17, lr: 4.13e-04
+2022-05-27 22:48:13,563 INFO [train.py:823] (2/4) Epoch 42, batch 0, loss[loss=2.025, simple_loss=0.2607, pruned_loss=0.02021, codebook_loss=18.75, over 7290.00 frames.], tot_loss[loss=2.025, simple_loss=0.2607, pruned_loss=0.02021, codebook_loss=18.75, over 7290.00 frames.], batch size: 21, lr: 4.07e-04
+2022-05-27 22:48:53,513 INFO [train.py:823] (2/4) Epoch 42, batch 50, loss[loss=2.106, simple_loss=0.2319, pruned_loss=0.03054, codebook_loss=19.59, over 7379.00 frames.], tot_loss[loss=1.991, simple_loss=0.2359, pruned_loss=0.02751, codebook_loss=18.46, over 323064.14 frames.], batch size: 19, lr: 4.07e-04
+2022-05-27 22:49:33,736 INFO [train.py:823] (2/4) Epoch 42, batch 100, loss[loss=1.898, simple_loss=0.1996, pruned_loss=0.02273, codebook_loss=17.76, over 6806.00 frames.], tot_loss[loss=1.977, simple_loss=0.2362, pruned_loss=0.02717, codebook_loss=18.32, over 565756.10 frames.], batch size: 15, lr: 4.07e-04
+2022-05-27 22:50:13,502 INFO [train.py:823] (2/4) Epoch 42, batch 150, loss[loss=2.153, simple_loss=0.2752, pruned_loss=0.04125, codebook_loss=19.74, over 7165.00 frames.], tot_loss[loss=1.978, simple_loss=0.2361, pruned_loss=0.02732, codebook_loss=18.32, over 755606.38 frames.], batch size: 22, lr: 4.07e-04
+2022-05-27 22:50:53,440 INFO [train.py:823] (2/4) Epoch 42, batch 200, loss[loss=1.949, simple_loss=0.243, pruned_loss=0.03111, codebook_loss=17.97, over 7218.00 frames.], tot_loss[loss=1.984, simple_loss=0.2366, pruned_loss=0.02756, codebook_loss=18.38, over 900922.77 frames.], batch size: 24, lr: 4.06e-04
+2022-05-27 22:51:33,123 INFO [train.py:823] (2/4) Epoch 42, batch 250, loss[loss=2.117, simple_loss=0.2144, pruned_loss=0.02814, codebook_loss=19.82, over 7150.00 frames.], tot_loss[loss=1.992, simple_loss=0.2374, pruned_loss=0.02826, codebook_loss=18.45, over 1016898.70 frames.], batch size: 17, lr: 4.06e-04
+2022-05-27 22:52:13,191 INFO [train.py:823] (2/4) Epoch 42, batch 300, loss[loss=1.971, simple_loss=0.2534, pruned_loss=0.02817, codebook_loss=18.16, over 7187.00 frames.], tot_loss[loss=1.998, simple_loss=0.2378, pruned_loss=0.0285, codebook_loss=18.51, over 1100518.98 frames.], batch size: 21, lr: 4.06e-04
+2022-05-27 22:52:52,913 INFO [train.py:823] (2/4) Epoch 42, batch 350, loss[loss=1.982, simple_loss=0.2131, pruned_loss=0.02557, codebook_loss=18.49, over 7138.00 frames.], tot_loss[loss=1.995, simple_loss=0.2367, pruned_loss=0.02819, codebook_loss=18.48, over 1166990.24 frames.], batch size: 17, lr: 4.06e-04
+2022-05-27 22:53:35,684 INFO [train.py:823] (2/4) Epoch 42, batch 400, loss[loss=1.966, simple_loss=0.2241, pruned_loss=0.03036, codebook_loss=18.24, over 7308.00 frames.], tot_loss[loss=2, simple_loss=0.2365, pruned_loss=0.02789, codebook_loss=18.54, over 1217435.81 frames.], batch size: 17, lr: 4.05e-04
+2022-05-27 22:54:16,811 INFO [train.py:823] (2/4) Epoch 42, batch 450, loss[loss=1.976, simple_loss=0.2465, pruned_loss=0.0375, codebook_loss=18.15, over 7235.00 frames.], tot_loss[loss=1.998, simple_loss=0.238, pruned_loss=0.02832, codebook_loss=18.5, over 1267226.11 frames.], batch size: 25, lr: 4.05e-04
+2022-05-27 22:54:57,131 INFO [train.py:823] (2/4) Epoch 42, batch 500, loss[loss=1.996, simple_loss=0.2114, pruned_loss=0.02434, codebook_loss=18.66, over 7152.00 frames.], tot_loss[loss=1.997, simple_loss=0.2378, pruned_loss=0.02842, codebook_loss=18.5, over 1301206.65 frames.], batch size: 17, lr: 4.05e-04
+2022-05-27 22:55:36,607 INFO [train.py:823] (2/4) Epoch 42, batch 550, loss[loss=1.978, simple_loss=0.2381, pruned_loss=0.02653, codebook_loss=18.33, over 7203.00 frames.], tot_loss[loss=1.999, simple_loss=0.238, pruned_loss=0.02857, codebook_loss=18.51, over 1322155.82 frames.], batch size: 18, lr: 4.05e-04
+2022-05-27 22:56:16,721 INFO [train.py:823] (2/4) Epoch 42, batch 600, loss[loss=1.921, simple_loss=0.2302, pruned_loss=0.02229, codebook_loss=17.83, over 7198.00 frames.], tot_loss[loss=2.001, simple_loss=0.2385, pruned_loss=0.02854, codebook_loss=18.53, over 1343720.04 frames.], batch size: 20, lr: 4.04e-04
+2022-05-27 22:56:56,700 INFO [train.py:823] (2/4) Epoch 42, batch 650, loss[loss=1.889, simple_loss=0.2397, pruned_loss=0.02431, codebook_loss=17.45, over 7154.00 frames.], tot_loss[loss=1.999, simple_loss=0.2392, pruned_loss=0.02887, codebook_loss=18.51, over 1364333.07 frames.], batch size: 23, lr: 4.04e-04
+2022-05-27 22:57:36,485 INFO [train.py:823] (2/4) Epoch 42, batch 700, loss[loss=1.964, simple_loss=0.2555, pruned_loss=0.02631, codebook_loss=18.1, over 6795.00 frames.], tot_loss[loss=1.997, simple_loss=0.2393, pruned_loss=0.02892, codebook_loss=18.48, over 1370183.64 frames.], batch size: 29, lr: 4.04e-04
+2022-05-27 22:58:16,374 INFO [train.py:823] (2/4) Epoch 42, batch 750, loss[loss=2.035, simple_loss=0.251, pruned_loss=0.02671, codebook_loss=18.83, over 7371.00 frames.], tot_loss[loss=1.997, simple_loss=0.2388, pruned_loss=0.02857, codebook_loss=18.49, over 1384097.49 frames.], batch size: 21, lr: 4.04e-04
+2022-05-27 22:58:56,355 INFO [train.py:823] (2/4) Epoch 42, batch 800, loss[loss=2.183, simple_loss=0.2394, pruned_loss=0.02667, codebook_loss=20.36, over 6404.00 frames.], tot_loss[loss=2, simple_loss=0.2388, pruned_loss=0.02865, codebook_loss=18.52, over 1392350.50 frames.], batch size: 34, lr: 4.03e-04
+2022-05-27 22:59:36,108 INFO [train.py:823] (2/4) Epoch 42, batch 850, loss[loss=1.881, simple_loss=0.2064, pruned_loss=0.02014, codebook_loss=17.57, over 7434.00 frames.], tot_loss[loss=1.993, simple_loss=0.2381, pruned_loss=0.02814, codebook_loss=18.45, over 1398658.20 frames.], batch size: 18, lr: 4.03e-04
+2022-05-27 23:00:15,918 INFO [train.py:823] (2/4) Epoch 42, batch 900, loss[loss=2.001, simple_loss=0.2452, pruned_loss=0.03258, codebook_loss=18.46, over 4759.00 frames.], tot_loss[loss=1.989, simple_loss=0.2375, pruned_loss=0.02776, codebook_loss=18.42, over 1397288.89 frames.], batch size: 46, lr: 4.03e-04
+2022-05-27 23:01:10,039 INFO [train.py:823] (2/4) Epoch 43, batch 0, loss[loss=1.845, simple_loss=0.2131, pruned_loss=0.02119, codebook_loss=17.17, over 7289.00 frames.], tot_loss[loss=1.845, simple_loss=0.2131, pruned_loss=0.02119, codebook_loss=17.17, over 7289.00 frames.], batch size: 19, lr: 3.98e-04
+2022-05-27 23:01:50,294 INFO [train.py:823] (2/4) Epoch 43, batch 50, loss[loss=1.974, simple_loss=0.2515, pruned_loss=0.03248, codebook_loss=18.15, over 7386.00 frames.], tot_loss[loss=1.966, simple_loss=0.2355, pruned_loss=0.02743, codebook_loss=18.2, over 321739.62 frames.], batch size: 20, lr: 3.98e-04
+2022-05-27 23:02:31,486 INFO [train.py:823] (2/4) Epoch 43, batch 100, loss[loss=2.194, simple_loss=0.2574, pruned_loss=0.04169, codebook_loss=20.24, over 7200.00 frames.], tot_loss[loss=1.979, simple_loss=0.2349, pruned_loss=0.02753, codebook_loss=18.34, over 565553.90 frames.], batch size: 23, lr: 3.97e-04
+2022-05-27 23:03:15,175 INFO [train.py:823] (2/4) Epoch 43, batch 150, loss[loss=2.07, simple_loss=0.2708, pruned_loss=0.03924, codebook_loss=18.95, over 6501.00 frames.], tot_loss[loss=1.999, simple_loss=0.2358, pruned_loss=0.02855, codebook_loss=18.52, over 753813.18 frames.], batch size: 34, lr: 3.97e-04
+2022-05-27 23:03:55,326 INFO [train.py:823] (2/4) Epoch 43, batch 200, loss[loss=2.353, simple_loss=0.2756, pruned_loss=0.05321, codebook_loss=21.62, over 7349.00 frames.], tot_loss[loss=1.991, simple_loss=0.2359, pruned_loss=0.02809, codebook_loss=18.45, over 905368.35 frames.], batch size: 23, lr: 3.97e-04
+2022-05-27 23:04:35,696 INFO [train.py:823] (2/4) Epoch 43, batch 250, loss[loss=2.086, simple_loss=0.2225, pruned_loss=0.03771, codebook_loss=19.38, over 7291.00 frames.], tot_loss[loss=1.986, simple_loss=0.235, pruned_loss=0.02765, codebook_loss=18.4, over 1021519.30 frames.], batch size: 18, lr: 3.97e-04
+2022-05-27 23:05:15,233 INFO [train.py:823] (2/4) Epoch 43, batch 300, loss[loss=1.98, simple_loss=0.232, pruned_loss=0.02595, codebook_loss=18.38, over 7097.00 frames.], tot_loss[loss=1.981, simple_loss=0.2353, pruned_loss=0.02741, codebook_loss=18.36, over 1101795.68 frames.], batch size: 18, lr: 3.96e-04
+2022-05-27 23:05:55,390 INFO [train.py:823] (2/4) Epoch 43, batch 350, loss[loss=2.132, simple_loss=0.2521, pruned_loss=0.03706, codebook_loss=19.69, over 7345.00 frames.], tot_loss[loss=1.989, simple_loss=0.2365, pruned_loss=0.02808, codebook_loss=18.43, over 1174025.75 frames.], batch size: 23, lr: 3.96e-04
+2022-05-27 23:06:35,410 INFO [train.py:823] (2/4) Epoch 43, batch 400, loss[loss=2.017, simple_loss=0.253, pruned_loss=0.03244, codebook_loss=18.58, over 7198.00 frames.], tot_loss[loss=1.993, simple_loss=0.2364, pruned_loss=0.02816, codebook_loss=18.47, over 1228710.07 frames.], batch size: 20, lr: 3.96e-04
+2022-05-27 23:07:15,799 INFO [train.py:823] (2/4) Epoch 43, batch 450, loss[loss=1.925, simple_loss=0.2583, pruned_loss=0.02951, codebook_loss=17.66, over 7188.00 frames.], tot_loss[loss=1.994, simple_loss=0.2369, pruned_loss=0.02793, codebook_loss=18.48, over 1275722.46 frames.], batch size: 21, lr: 3.96e-04
+2022-05-27 23:07:55,851 INFO [train.py:823] (2/4) Epoch 43, batch 500, loss[loss=2.04, simple_loss=0.1943, pruned_loss=0.02081, codebook_loss=19.22, over 7024.00 frames.], tot_loss[loss=1.993, simple_loss=0.2369, pruned_loss=0.02799, codebook_loss=18.47, over 1307822.06 frames.], batch size: 17, lr: 3.95e-04
+2022-05-27 23:08:36,107 INFO [train.py:823] (2/4) Epoch 43, batch 550, loss[loss=1.913, simple_loss=0.2653, pruned_loss=0.02405, codebook_loss=17.56, over 7286.00 frames.], tot_loss[loss=1.99, simple_loss=0.238, pruned_loss=0.02786, codebook_loss=18.43, over 1337515.09 frames.], batch size: 21, lr: 3.95e-04
+2022-05-27 23:09:15,804 INFO [train.py:823] (2/4) Epoch 43, batch 600, loss[loss=2.087, simple_loss=0.2496, pruned_loss=0.02442, codebook_loss=19.38, over 7181.00 frames.], tot_loss[loss=1.991, simple_loss=0.2375, pruned_loss=0.02784, codebook_loss=18.44, over 1357618.60 frames.], batch size: 22, lr: 3.95e-04
+2022-05-27 23:09:55,882 INFO [train.py:823] (2/4) Epoch 43, batch 650, loss[loss=1.921, simple_loss=0.2501, pruned_loss=0.02639, codebook_loss=17.69, over 7189.00 frames.], tot_loss[loss=1.989, simple_loss=0.2378, pruned_loss=0.02772, codebook_loss=18.43, over 1374530.16 frames.], batch size: 20, lr: 3.95e-04
+2022-05-27 23:10:35,787 INFO [train.py:823] (2/4) Epoch 43, batch 700, loss[loss=1.923, simple_loss=0.2167, pruned_loss=0.02716, codebook_loss=17.87, over 7025.00 frames.], tot_loss[loss=1.995, simple_loss=0.2379, pruned_loss=0.02799, codebook_loss=18.48, over 1383462.69 frames.], batch size: 17, lr: 3.94e-04
+2022-05-27 23:11:16,031 INFO [train.py:823] (2/4) Epoch 43, batch 750, loss[loss=2.097, simple_loss=0.2359, pruned_loss=0.02482, codebook_loss=19.54, over 7194.00 frames.], tot_loss[loss=2, simple_loss=0.2382, pruned_loss=0.02835, codebook_loss=18.53, over 1392570.20 frames.], batch size: 21, lr: 3.94e-04
+2022-05-27 23:11:55,943 INFO [train.py:823] (2/4) Epoch 43, batch 800, loss[loss=1.873, simple_loss=0.2422, pruned_loss=0.01838, codebook_loss=17.33, over 7310.00 frames.], tot_loss[loss=1.996, simple_loss=0.2373, pruned_loss=0.02796, codebook_loss=18.5, over 1401375.89 frames.], batch size: 22, lr: 3.94e-04
+2022-05-27 23:12:36,074 INFO [train.py:823] (2/4) Epoch 43, batch 850, loss[loss=1.952, simple_loss=0.2411, pruned_loss=0.02706, codebook_loss=18.05, over 7171.00 frames.], tot_loss[loss=1.994, simple_loss=0.2374, pruned_loss=0.02773, codebook_loss=18.48, over 1403757.73 frames.], batch size: 22, lr: 3.94e-04
+2022-05-27 23:13:16,021 INFO [train.py:823] (2/4) Epoch 43, batch 900, loss[loss=1.926, simple_loss=0.2155, pruned_loss=0.02983, codebook_loss=17.88, over 6817.00 frames.], tot_loss[loss=1.996, simple_loss=0.2369, pruned_loss=0.02775, codebook_loss=18.49, over 1402849.50 frames.], batch size: 15, lr: 3.93e-04
+2022-05-27 23:14:05,785 INFO [train.py:823] (2/4) Epoch 44, batch 0, loss[loss=1.891, simple_loss=0.2367, pruned_loss=0.02199, codebook_loss=17.51, over 7302.00 frames.], tot_loss[loss=1.891, simple_loss=0.2367, pruned_loss=0.02199, codebook_loss=17.51, over 7302.00 frames.], batch size: 22, lr: 3.89e-04
+2022-05-27 23:14:46,502 INFO [train.py:823] (2/4) Epoch 44, batch 50, loss[loss=1.972, simple_loss=0.2214, pruned_loss=0.0291, codebook_loss=18.32, over 7033.00 frames.], tot_loss[loss=1.975, simple_loss=0.2321, pruned_loss=0.02691, codebook_loss=18.32, over 321769.30 frames.], batch size: 17, lr: 3.89e-04
+2022-05-27 23:15:26,619 INFO [train.py:823] (2/4) Epoch 44, batch 100, loss[loss=2.109, simple_loss=0.2604, pruned_loss=0.04197, codebook_loss=19.36, over 7275.00 frames.], tot_loss[loss=1.967, simple_loss=0.2349, pruned_loss=0.02724, codebook_loss=18.23, over 567243.14 frames.], batch size: 20, lr: 3.88e-04
+2022-05-27 23:16:06,720 INFO [train.py:823] (2/4) Epoch 44, batch 150, loss[loss=2.011, simple_loss=0.2586, pruned_loss=0.03565, codebook_loss=18.46, over 7284.00 frames.], tot_loss[loss=1.969, simple_loss=0.2353, pruned_loss=0.0271, codebook_loss=18.24, over 758161.53 frames.], batch size: 20, lr: 3.88e-04
+2022-05-27 23:16:46,971 INFO [train.py:823] (2/4) Epoch 44, batch 200, loss[loss=2.008, simple_loss=0.2634, pruned_loss=0.0416, codebook_loss=18.34, over 7229.00 frames.], tot_loss[loss=1.967, simple_loss=0.2353, pruned_loss=0.02692, codebook_loss=18.23, over 905893.93 frames.], batch size: 24, lr: 3.88e-04
+2022-05-27 23:17:26,782 INFO [train.py:823] (2/4) Epoch 44, batch 250, loss[loss=1.903, simple_loss=0.251, pruned_loss=0.02651, codebook_loss=17.51, over 7138.00 frames.], tot_loss[loss=1.977, simple_loss=0.2361, pruned_loss=0.02734, codebook_loss=18.31, over 1021274.96 frames.], batch size: 23, lr: 3.88e-04
+2022-05-27 23:18:08,118 INFO [train.py:823] (2/4) Epoch 44, batch 300, loss[loss=1.965, simple_loss=0.2512, pruned_loss=0.03156, codebook_loss=18.08, over 7280.00 frames.], tot_loss[loss=1.979, simple_loss=0.2365, pruned_loss=0.02769, codebook_loss=18.33, over 1108516.43 frames.], batch size: 21, lr: 3.87e-04
+2022-05-27 23:18:50,347 INFO [train.py:823] (2/4) Epoch 44, batch 350, loss[loss=2.025, simple_loss=0.2134, pruned_loss=0.02044, codebook_loss=18.98, over 7026.00 frames.], tot_loss[loss=1.984, simple_loss=0.2373, pruned_loss=0.02804, codebook_loss=18.37, over 1171072.44 frames.], batch size: 16, lr: 3.87e-04
+2022-05-27 23:19:30,573 INFO [train.py:823] (2/4) Epoch 44, batch 400, loss[loss=2.001, simple_loss=0.2484, pruned_loss=0.03602, codebook_loss=18.41, over 4690.00 frames.], tot_loss[loss=1.986, simple_loss=0.237, pruned_loss=0.02762, codebook_loss=18.4, over 1221850.68 frames.], batch size: 46, lr: 3.87e-04
+2022-05-27 23:20:10,457 INFO [train.py:823] (2/4) Epoch 44, batch 450, loss[loss=2.024, simple_loss=0.2573, pruned_loss=0.05232, codebook_loss=18.43, over 7228.00 frames.], tot_loss[loss=1.986, simple_loss=0.2379, pruned_loss=0.02804, codebook_loss=18.39, over 1265205.07 frames.], batch size: 25, lr: 3.87e-04
+2022-05-27 23:20:50,564 INFO [train.py:823] (2/4) Epoch 44, batch 500, loss[loss=1.987, simple_loss=0.2493, pruned_loss=0.03495, codebook_loss=18.27, over 7160.00 frames.], tot_loss[loss=1.987, simple_loss=0.2371, pruned_loss=0.02794, codebook_loss=18.4, over 1302161.77 frames.], batch size: 17, lr: 3.86e-04
+2022-05-27 23:21:30,260 INFO [train.py:823] (2/4) Epoch 44, batch 550, loss[loss=2.11, simple_loss=0.242, pruned_loss=0.02938, codebook_loss=19.59, over 7201.00 frames.], tot_loss[loss=1.982, simple_loss=0.2365, pruned_loss=0.02735, codebook_loss=18.37, over 1330436.22 frames.], batch size: 24, lr: 3.86e-04
+2022-05-27 23:22:10,612 INFO [train.py:823] (2/4) Epoch 44, batch 600, loss[loss=1.911, simple_loss=0.2217, pruned_loss=0.02433, codebook_loss=17.76, over 7388.00 frames.], tot_loss[loss=1.98, simple_loss=0.2364, pruned_loss=0.02705, codebook_loss=18.35, over 1352992.96 frames.], batch size: 19, lr: 3.86e-04
+2022-05-27 23:22:50,454 INFO [train.py:823] (2/4) Epoch 44, batch 650, loss[loss=2.012, simple_loss=0.2568, pruned_loss=0.03529, codebook_loss=18.48, over 7411.00 frames.], tot_loss[loss=1.989, simple_loss=0.2368, pruned_loss=0.02756, codebook_loss=18.43, over 1367394.37 frames.], batch size: 22, lr: 3.86e-04
+2022-05-27 23:23:30,760 INFO [train.py:823] (2/4) Epoch 44, batch 700, loss[loss=1.946, simple_loss=0.2479, pruned_loss=0.02753, codebook_loss=17.95, over 7160.00 frames.], tot_loss[loss=1.989, simple_loss=0.2366, pruned_loss=0.02733, codebook_loss=18.43, over 1378499.08 frames.], batch size: 23, lr: 3.85e-04
+2022-05-27 23:24:10,488 INFO [train.py:823] (2/4) Epoch 44, batch 750, loss[loss=2.213, simple_loss=0.2292, pruned_loss=0.03323, codebook_loss=20.66, over 7167.00 frames.], tot_loss[loss=1.989, simple_loss=0.2362, pruned_loss=0.02755, codebook_loss=18.44, over 1390633.46 frames.], batch size: 17, lr: 3.85e-04
+2022-05-27 23:24:50,889 INFO [train.py:823] (2/4) Epoch 44, batch 800, loss[loss=2.173, simple_loss=0.2585, pruned_loss=0.02656, codebook_loss=20.17, over 7214.00 frames.], tot_loss[loss=1.989, simple_loss=0.237, pruned_loss=0.02755, codebook_loss=18.43, over 1397356.89 frames.], batch size: 25, lr: 3.85e-04
+2022-05-27 23:25:30,963 INFO [train.py:823] (2/4) Epoch 44, batch 850, loss[loss=1.939, simple_loss=0.219, pruned_loss=0.02406, codebook_loss=18.06, over 6774.00 frames.], tot_loss[loss=1.989, simple_loss=0.2368, pruned_loss=0.02739, codebook_loss=18.43, over 1402905.10 frames.], batch size: 15, lr: 3.85e-04
+2022-05-27 23:26:12,391 INFO [train.py:823] (2/4) Epoch 44, batch 900, loss[loss=2.051, simple_loss=0.2064, pruned_loss=0.02711, codebook_loss=19.21, over 7292.00 frames.], tot_loss[loss=1.989, simple_loss=0.2362, pruned_loss=0.02732, codebook_loss=18.44, over 1400937.24 frames.], batch size: 17, lr: 3.85e-04
+2022-05-27 23:26:52,116 INFO [train.py:823] (2/4) Epoch 44, batch 950, loss[loss=1.976, simple_loss=0.2321, pruned_loss=0.02988, codebook_loss=18.31, over 5057.00 frames.], tot_loss[loss=1.993, simple_loss=0.2361, pruned_loss=0.02785, codebook_loss=18.47, over 1377121.19 frames.], batch size: 47, lr: 3.84e-04
+2022-05-27 23:27:07,449 INFO [train.py:823] (2/4) Epoch 45, batch 0, loss[loss=1.861, simple_loss=0.2284, pruned_loss=0.01406, codebook_loss=17.32, over 7270.00 frames.], tot_loss[loss=1.861, simple_loss=0.2284, pruned_loss=0.01406, codebook_loss=17.32, over 7270.00 frames.], batch size: 20, lr: 3.80e-04
+2022-05-27 23:27:47,713 INFO [train.py:823] (2/4) Epoch 45, batch 50, loss[loss=1.914, simple_loss=0.2341, pruned_loss=0.02435, codebook_loss=17.72, over 7299.00 frames.], tot_loss[loss=2.006, simple_loss=0.2362, pruned_loss=0.02832, codebook_loss=18.6, over 324050.05 frames.], batch size: 21, lr: 3.80e-04
+2022-05-27 23:28:27,600 INFO [train.py:823] (2/4) Epoch 45, batch 100, loss[loss=1.905, simple_loss=0.2517, pruned_loss=0.02625, codebook_loss=17.53, over 7380.00 frames.], tot_loss[loss=1.976, simple_loss=0.2359, pruned_loss=0.02753, codebook_loss=18.3, over 567212.27 frames.], batch size: 21, lr: 3.80e-04
+2022-05-27 23:29:07,795 INFO [train.py:823] (2/4) Epoch 45, batch 150, loss[loss=1.885, simple_loss=0.2105, pruned_loss=0.01597, codebook_loss=17.64, over 6785.00 frames.], tot_loss[loss=1.978, simple_loss=0.2358, pruned_loss=0.02771, codebook_loss=18.32, over 752280.75 frames.], batch size: 15, lr: 3.79e-04
+2022-05-27 23:29:47,564 INFO [train.py:823] (2/4) Epoch 45, batch 200, loss[loss=2.036, simple_loss=0.2644, pruned_loss=0.04064, codebook_loss=18.63, over 4615.00 frames.], tot_loss[loss=1.992, simple_loss=0.236, pruned_loss=0.02854, codebook_loss=18.45, over 896947.16 frames.], batch size: 47, lr: 3.79e-04
+2022-05-27 23:30:27,692 INFO [train.py:823] (2/4) Epoch 45, batch 250, loss[loss=1.908, simple_loss=0.2294, pruned_loss=0.01664, codebook_loss=17.77, over 6457.00 frames.], tot_loss[loss=1.989, simple_loss=0.2368, pruned_loss=0.02849, codebook_loss=18.42, over 1010252.02 frames.], batch size: 34, lr: 3.79e-04
+2022-05-27 23:31:07,615 INFO [train.py:823] (2/4) Epoch 45, batch 300, loss[loss=1.931, simple_loss=0.2491, pruned_loss=0.0308, codebook_loss=17.76, over 7156.00 frames.], tot_loss[loss=1.982, simple_loss=0.235, pruned_loss=0.02754, codebook_loss=18.37, over 1099559.97 frames.], batch size: 23, lr: 3.79e-04
+2022-05-27 23:31:47,885 INFO [train.py:823] (2/4) Epoch 45, batch 350, loss[loss=1.825, simple_loss=0.2303, pruned_loss=0.01952, codebook_loss=16.91, over 7426.00 frames.], tot_loss[loss=1.979, simple_loss=0.2349, pruned_loss=0.02712, codebook_loss=18.34, over 1171451.38 frames.], batch size: 22, lr: 3.78e-04
+2022-05-27 23:32:27,610 INFO [train.py:823] (2/4) Epoch 45, batch 400, loss[loss=1.849, simple_loss=0.2296, pruned_loss=0.01976, codebook_loss=17.15, over 7390.00 frames.], tot_loss[loss=1.979, simple_loss=0.2353, pruned_loss=0.02707, codebook_loss=18.34, over 1229212.79 frames.], batch size: 20, lr: 3.78e-04
+2022-05-27 23:33:07,577 INFO [train.py:823] (2/4) Epoch 45, batch 450, loss[loss=1.882, simple_loss=0.2161, pruned_loss=0.01686, codebook_loss=17.57, over 7192.00 frames.], tot_loss[loss=1.976, simple_loss=0.2353, pruned_loss=0.02709, codebook_loss=18.32, over 1270107.13 frames.], batch size: 18, lr: 3.78e-04
+2022-05-27 23:33:47,537 INFO [train.py:823] (2/4) Epoch 45, batch 500, loss[loss=1.892, simple_loss=0.2331, pruned_loss=0.02566, codebook_loss=17.49, over 7240.00 frames.], tot_loss[loss=1.982, simple_loss=0.236, pruned_loss=0.02748, codebook_loss=18.37, over 1309183.64 frames.], batch size: 24, lr: 3.78e-04
+2022-05-27 23:34:27,799 INFO [train.py:823] (2/4) Epoch 45, batch 550, loss[loss=1.937, simple_loss=0.223, pruned_loss=0.02792, codebook_loss=17.98, over 7194.00 frames.], tot_loss[loss=1.985, simple_loss=0.2353, pruned_loss=0.02759, codebook_loss=18.39, over 1334963.17 frames.], batch size: 18, lr: 3.78e-04
+2022-05-27 23:35:07,236 INFO [train.py:823] (2/4) Epoch 45, batch 600, loss[loss=1.95, simple_loss=0.2323, pruned_loss=0.02295, codebook_loss=18.11, over 6395.00 frames.], tot_loss[loss=1.978, simple_loss=0.2357, pruned_loss=0.02731, codebook_loss=18.33, over 1348513.21 frames.], batch size: 34, lr: 3.77e-04
+2022-05-27 23:35:47,193 INFO [train.py:823] (2/4) Epoch 45, batch 650, loss[loss=1.967, simple_loss=0.261, pruned_loss=0.03859, codebook_loss=17.98, over 7154.00 frames.], tot_loss[loss=1.983, simple_loss=0.2361, pruned_loss=0.02758, codebook_loss=18.38, over 1363589.54 frames.], batch size: 23, lr: 3.77e-04
+2022-05-27 23:36:26,950 INFO [train.py:823] (2/4) Epoch 45, batch 700, loss[loss=1.97, simple_loss=0.2321, pruned_loss=0.02233, codebook_loss=18.32, over 7312.00 frames.], tot_loss[loss=1.984, simple_loss=0.2362, pruned_loss=0.02769, codebook_loss=18.39, over 1377082.17 frames.], batch size: 22, lr: 3.77e-04
+2022-05-27 23:37:06,799 INFO [train.py:823] (2/4) Epoch 45, batch 750, loss[loss=1.933, simple_loss=0.2411, pruned_loss=0.03126, codebook_loss=17.81, over 6878.00 frames.], tot_loss[loss=1.984, simple_loss=0.2363, pruned_loss=0.02755, codebook_loss=18.39, over 1386267.01 frames.], batch size: 29, lr: 3.77e-04
+2022-05-27 23:37:46,669 INFO [train.py:823] (2/4) Epoch 45, batch 800, loss[loss=2.432, simple_loss=0.2834, pruned_loss=0.05595, codebook_loss=22.34, over 7326.00 frames.], tot_loss[loss=1.983, simple_loss=0.2364, pruned_loss=0.02724, codebook_loss=18.37, over 1395220.12 frames.], batch size: 23, lr: 3.77e-04
+2022-05-27 23:38:26,823 INFO [train.py:823] (2/4) Epoch 45, batch 850, loss[loss=1.968, simple_loss=0.2406, pruned_loss=0.03344, codebook_loss=18.14, over 7190.00 frames.], tot_loss[loss=1.985, simple_loss=0.2371, pruned_loss=0.02749, codebook_loss=18.39, over 1398065.56 frames.], batch size: 21, lr: 3.76e-04
+2022-05-27 23:39:06,643 INFO [train.py:823] (2/4) Epoch 45, batch 900, loss[loss=2.11, simple_loss=0.221, pruned_loss=0.01786, codebook_loss=19.81, over 7007.00 frames.], tot_loss[loss=1.987, simple_loss=0.2376, pruned_loss=0.02761, codebook_loss=18.4, over 1400753.71 frames.], batch size: 17, lr: 3.76e-04
+2022-05-27 23:40:00,613 INFO [train.py:823] (2/4) Epoch 46, batch 0, loss[loss=1.961, simple_loss=0.2396, pruned_loss=0.03292, codebook_loss=18.09, over 7164.00 frames.], tot_loss[loss=1.961, simple_loss=0.2396, pruned_loss=0.03292, codebook_loss=18.09, over 7164.00 frames.], batch size: 22, lr: 3.72e-04
+2022-05-27 23:40:40,262 INFO [train.py:823] (2/4) Epoch 46, batch 50, loss[loss=1.908, simple_loss=0.2333, pruned_loss=0.01724, codebook_loss=17.74, over 7287.00 frames.], tot_loss[loss=1.962, simple_loss=0.2331, pruned_loss=0.02565, codebook_loss=18.19, over 314797.45 frames.], batch size: 20, lr: 3.72e-04
+2022-05-27 23:41:20,232 INFO [train.py:823] (2/4) Epoch 46, batch 100, loss[loss=1.899, simple_loss=0.2059, pruned_loss=0.02482, codebook_loss=17.71, over 7019.00 frames.], tot_loss[loss=1.962, simple_loss=0.2324, pruned_loss=0.02568, codebook_loss=18.2, over 561025.48 frames.], batch size: 16, lr: 3.71e-04
+2022-05-27 23:42:00,064 INFO [train.py:823] (2/4) Epoch 46, batch 150, loss[loss=1.982, simple_loss=0.2366, pruned_loss=0.02437, codebook_loss=18.39, over 7103.00 frames.], tot_loss[loss=1.969, simple_loss=0.2343, pruned_loss=0.02674, codebook_loss=18.25, over 753475.24 frames.], batch size: 20, lr: 3.71e-04
+2022-05-27 23:42:40,051 INFO [train.py:823] (2/4) Epoch 46, batch 200, loss[loss=1.91, simple_loss=0.2309, pruned_loss=0.02597, codebook_loss=17.69, over 7332.00 frames.], tot_loss[loss=1.978, simple_loss=0.234, pruned_loss=0.02712, codebook_loss=18.34, over 905894.06 frames.], batch size: 23, lr: 3.71e-04
+2022-05-27 23:43:22,186 INFO [train.py:823] (2/4) Epoch 46, batch 250, loss[loss=1.91, simple_loss=0.236, pruned_loss=0.02712, codebook_loss=17.65, over 7124.00 frames.], tot_loss[loss=1.975, simple_loss=0.2349, pruned_loss=0.02715, codebook_loss=18.31, over 1019906.95 frames.], batch size: 23, lr: 3.71e-04
+2022-05-27 23:44:03,547 INFO [train.py:823] (2/4) Epoch 46, batch 300, loss[loss=1.989, simple_loss=0.2624, pruned_loss=0.03449, codebook_loss=18.23, over 6937.00 frames.], tot_loss[loss=1.975, simple_loss=0.2358, pruned_loss=0.0276, codebook_loss=18.29, over 1106665.84 frames.], batch size: 29, lr: 3.70e-04
+2022-05-27 23:44:43,212 INFO [train.py:823] (2/4) Epoch 46, batch 350, loss[loss=2.158, simple_loss=0.2647, pruned_loss=0.03183, codebook_loss=19.94, over 6529.00 frames.], tot_loss[loss=1.979, simple_loss=0.2367, pruned_loss=0.0279, codebook_loss=18.33, over 1178942.55 frames.], batch size: 34, lr: 3.70e-04
+2022-05-27 23:45:23,229 INFO [train.py:823] (2/4) Epoch 46, batch 400, loss[loss=1.891, simple_loss=0.2372, pruned_loss=0.01987, codebook_loss=17.53, over 7158.00 frames.], tot_loss[loss=1.977, simple_loss=0.2372, pruned_loss=0.02782, codebook_loss=18.3, over 1236076.13 frames.], batch size: 23, lr: 3.70e-04
+2022-05-27 23:46:03,179 INFO [train.py:823] (2/4) Epoch 46, batch 450, loss[loss=1.999, simple_loss=0.2382, pruned_loss=0.0268, codebook_loss=18.53, over 7275.00 frames.], tot_loss[loss=1.98, simple_loss=0.2363, pruned_loss=0.02743, codebook_loss=18.34, over 1278244.46 frames.], batch size: 20, lr: 3.70e-04
+2022-05-27 23:46:42,929 INFO [train.py:823] (2/4) Epoch 46, batch 500, loss[loss=1.962, simple_loss=0.2221, pruned_loss=0.0323, codebook_loss=18.19, over 6777.00 frames.], tot_loss[loss=1.983, simple_loss=0.2378, pruned_loss=0.02802, codebook_loss=18.36, over 1303720.00 frames.], batch size: 15, lr: 3.70e-04
+2022-05-27 23:47:22,924 INFO [train.py:823] (2/4) Epoch 46, batch 550, loss[loss=1.996, simple_loss=0.2474, pruned_loss=0.03253, codebook_loss=18.4, over 7311.00 frames.], tot_loss[loss=1.99, simple_loss=0.2376, pruned_loss=0.02811, codebook_loss=18.43, over 1333388.18 frames.], batch size: 22, lr: 3.69e-04
+2022-05-27 23:48:03,068 INFO [train.py:823] (2/4) Epoch 46, batch 600, loss[loss=1.889, simple_loss=0.2235, pruned_loss=0.02501, codebook_loss=17.52, over 7017.00 frames.], tot_loss[loss=1.985, simple_loss=0.2367, pruned_loss=0.02781, codebook_loss=18.38, over 1351795.70 frames.], batch size: 17, lr: 3.69e-04
+2022-05-27 23:48:42,894 INFO [train.py:823] (2/4) Epoch 46, batch 650, loss[loss=2.104, simple_loss=0.2683, pruned_loss=0.04559, codebook_loss=19.24, over 7150.00 frames.], tot_loss[loss=1.98, simple_loss=0.2361, pruned_loss=0.02743, codebook_loss=18.35, over 1365984.91 frames.], batch size: 23, lr: 3.69e-04
+2022-05-27 23:49:24,209 INFO [train.py:823] (2/4) Epoch 46, batch 700, loss[loss=2.052, simple_loss=0.2264, pruned_loss=0.03509, codebook_loss=19.03, over 7148.00 frames.], tot_loss[loss=1.981, simple_loss=0.2353, pruned_loss=0.02731, codebook_loss=18.37, over 1374440.10 frames.], batch size: 17, lr: 3.69e-04
+2022-05-27 23:50:04,153 INFO [train.py:823] (2/4) Epoch 46, batch 750, loss[loss=1.973, simple_loss=0.2425, pruned_loss=0.02753, codebook_loss=18.24, over 6462.00 frames.], tot_loss[loss=1.979, simple_loss=0.2345, pruned_loss=0.02699, codebook_loss=18.34, over 1382938.78 frames.], batch size: 34, lr: 3.69e-04
+2022-05-27 23:50:44,359 INFO [train.py:823] (2/4) Epoch 46, batch 800, loss[loss=2.021, simple_loss=0.2488, pruned_loss=0.0231, codebook_loss=18.73, over 7194.00 frames.], tot_loss[loss=1.986, simple_loss=0.2353, pruned_loss=0.02736, codebook_loss=18.41, over 1386682.15 frames.], batch size: 20, lr: 3.68e-04
+2022-05-27 23:51:24,079 INFO [train.py:823] (2/4) Epoch 46, batch 850, loss[loss=1.939, simple_loss=0.2362, pruned_loss=0.02683, codebook_loss=17.94, over 7343.00 frames.], tot_loss[loss=1.984, simple_loss=0.2343, pruned_loss=0.0271, codebook_loss=18.4, over 1389700.73 frames.], batch size: 23, lr: 3.68e-04
+2022-05-27 23:52:04,328 INFO [train.py:823] (2/4) Epoch 46, batch 900, loss[loss=1.885, simple_loss=0.2068, pruned_loss=0.01493, codebook_loss=17.67, over 7094.00 frames.], tot_loss[loss=1.987, simple_loss=0.2344, pruned_loss=0.02712, codebook_loss=18.42, over 1397191.76 frames.], batch size: 18, lr: 3.68e-04
+2022-05-27 23:52:54,925 INFO [train.py:823] (2/4) Epoch 47, batch 0, loss[loss=1.959, simple_loss=0.2174, pruned_loss=0.02645, codebook_loss=18.24, over 7002.00 frames.], tot_loss[loss=1.959, simple_loss=0.2174, pruned_loss=0.02645, codebook_loss=18.24, over 7002.00 frames.], batch size: 16, lr: 3.64e-04
+2022-05-27 23:53:35,049 INFO [train.py:823] (2/4) Epoch 47, batch 50, loss[loss=2.016, simple_loss=0.1977, pruned_loss=0.01903, codebook_loss=18.98, over 7273.00 frames.], tot_loss[loss=1.957, simple_loss=0.2324, pruned_loss=0.02534, codebook_loss=18.15, over 321774.82 frames.], batch size: 17, lr: 3.64e-04
+2022-05-27 23:54:15,097 INFO [train.py:823] (2/4) Epoch 47, batch 100, loss[loss=1.85, simple_loss=0.2133, pruned_loss=0.02171, codebook_loss=17.22, over 7300.00 frames.], tot_loss[loss=1.976, simple_loss=0.232, pruned_loss=0.02555, codebook_loss=18.34, over 565682.98 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:54:55,168 INFO [train.py:823] (2/4) Epoch 47, batch 150, loss[loss=2.151, simple_loss=0.2739, pruned_loss=0.03116, codebook_loss=19.83, over 7288.00 frames.], tot_loss[loss=1.974, simple_loss=0.2329, pruned_loss=0.02593, codebook_loss=18.32, over 757267.20 frames.], batch size: 22, lr: 3.63e-04
+2022-05-27 23:55:34,798 INFO [train.py:823] (2/4) Epoch 47, batch 200, loss[loss=1.951, simple_loss=0.2214, pruned_loss=0.01966, codebook_loss=18.21, over 7089.00 frames.], tot_loss[loss=1.968, simple_loss=0.2336, pruned_loss=0.02625, codebook_loss=18.25, over 901814.16 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:56:14,826 INFO [train.py:823] (2/4) Epoch 47, batch 250, loss[loss=1.908, simple_loss=0.2272, pruned_loss=0.0169, codebook_loss=17.77, over 7400.00 frames.], tot_loss[loss=1.969, simple_loss=0.2354, pruned_loss=0.02662, codebook_loss=18.24, over 1022714.83 frames.], batch size: 19, lr: 3.63e-04
+2022-05-27 23:56:54,278 INFO [train.py:823] (2/4) Epoch 47, batch 300, loss[loss=1.947, simple_loss=0.2125, pruned_loss=0.02299, codebook_loss=18.18, over 7190.00 frames.], tot_loss[loss=1.966, simple_loss=0.2355, pruned_loss=0.02635, codebook_loss=18.22, over 1111770.93 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:57:34,826 INFO [train.py:823] (2/4) Epoch 47, batch 350, loss[loss=1.959, simple_loss=0.229, pruned_loss=0.0208, codebook_loss=18.24, over 7287.00 frames.], tot_loss[loss=1.963, simple_loss=0.2351, pruned_loss=0.02626, codebook_loss=18.2, over 1179236.77 frames.], batch size: 20, lr: 3.62e-04
+2022-05-27 23:58:14,537 INFO [train.py:823] (2/4) Epoch 47, batch 400, loss[loss=1.946, simple_loss=0.2523, pruned_loss=0.02433, codebook_loss=17.96, over 7282.00 frames.], tot_loss[loss=1.961, simple_loss=0.2353, pruned_loss=0.02621, codebook_loss=18.17, over 1233158.69 frames.], batch size: 20, lr: 3.62e-04
+2022-05-27 23:58:54,552 INFO [train.py:823] (2/4) Epoch 47, batch 450, loss[loss=1.887, simple_loss=0.2116, pruned_loss=0.02001, codebook_loss=17.62, over 7152.00 frames.], tot_loss[loss=1.964, simple_loss=0.2357, pruned_loss=0.02645, codebook_loss=18.2, over 1273940.45 frames.], batch size: 17, lr: 3.62e-04
+2022-05-27 23:59:34,082 INFO [train.py:823] (2/4) Epoch 47, batch 500, loss[loss=1.928, simple_loss=0.2238, pruned_loss=0.02589, codebook_loss=17.9, over 7103.00 frames.], tot_loss[loss=1.968, simple_loss=0.2358, pruned_loss=0.02681, codebook_loss=18.24, over 1302146.15 frames.], batch size: 19, lr: 3.62e-04
+2022-05-28 00:00:14,263 INFO [train.py:823] (2/4) Epoch 47, batch 550, loss[loss=1.866, simple_loss=0.2225, pruned_loss=0.02238, codebook_loss=17.32, over 7384.00 frames.], tot_loss[loss=1.968, simple_loss=0.235, pruned_loss=0.02668, codebook_loss=18.24, over 1326606.42 frames.], batch size: 19, lr: 3.62e-04
+2022-05-28 00:00:54,088 INFO [train.py:823] (2/4) Epoch 47, batch 600, loss[loss=1.966, simple_loss=0.2635, pruned_loss=0.03237, codebook_loss=18.02, over 7022.00 frames.], tot_loss[loss=1.966, simple_loss=0.2353, pruned_loss=0.02647, codebook_loss=18.22, over 1345630.12 frames.], batch size: 26, lr: 3.61e-04
+2022-05-28 00:01:34,136 INFO [train.py:823] (2/4) Epoch 47, batch 650, loss[loss=1.885, simple_loss=0.213, pruned_loss=0.02513, codebook_loss=17.54, over 7306.00 frames.], tot_loss[loss=1.963, simple_loss=0.2357, pruned_loss=0.02624, codebook_loss=18.19, over 1363439.02 frames.], batch size: 17, lr: 3.61e-04
+2022-05-28 00:02:14,064 INFO [train.py:823] (2/4) Epoch 47, batch 700, loss[loss=1.955, simple_loss=0.2666, pruned_loss=0.04509, codebook_loss=17.76, over 7327.00 frames.], tot_loss[loss=1.969, simple_loss=0.2359, pruned_loss=0.02684, codebook_loss=18.24, over 1370700.87 frames.], batch size: 23, lr: 3.61e-04
+2022-05-28 00:02:54,280 INFO [train.py:823] (2/4) Epoch 47, batch 750, loss[loss=1.92, simple_loss=0.2342, pruned_loss=0.02523, codebook_loss=17.78, over 7289.00 frames.], tot_loss[loss=1.968, simple_loss=0.2357, pruned_loss=0.02683, codebook_loss=18.24, over 1382659.74 frames.], batch size: 19, lr: 3.61e-04
+2022-05-28 00:03:34,014 INFO [train.py:823] (2/4) Epoch 47, batch 800, loss[loss=1.908, simple_loss=0.2465, pruned_loss=0.0194, codebook_loss=17.66, over 7026.00 frames.], tot_loss[loss=1.968, simple_loss=0.2349, pruned_loss=0.02636, codebook_loss=18.24, over 1390392.22 frames.], batch size: 26, lr: 3.61e-04
+2022-05-28 00:04:13,983 INFO [train.py:823] (2/4) Epoch 47, batch 850, loss[loss=1.992, simple_loss=0.2258, pruned_loss=0.02563, codebook_loss=18.54, over 7187.00 frames.], tot_loss[loss=1.97, simple_loss=0.2352, pruned_loss=0.02671, codebook_loss=18.26, over 1391754.70 frames.], batch size: 18, lr: 3.60e-04
+2022-05-28 00:04:53,639 INFO [train.py:823] (2/4) Epoch 47, batch 900, loss[loss=2.034, simple_loss=0.2576, pruned_loss=0.04079, codebook_loss=18.65, over 7306.00 frames.], tot_loss[loss=1.969, simple_loss=0.2354, pruned_loss=0.02653, codebook_loss=18.24, over 1396969.89 frames.], batch size: 22, lr: 3.60e-04
+2022-05-28 00:05:47,400 INFO [train.py:823] (2/4) Epoch 48, batch 0, loss[loss=1.848, simple_loss=0.2263, pruned_loss=0.01433, codebook_loss=17.21, over 7184.00 frames.], tot_loss[loss=1.848, simple_loss=0.2263, pruned_loss=0.01433, codebook_loss=17.21, over 7184.00 frames.], batch size: 21, lr: 3.56e-04
+2022-05-28 00:06:27,207 INFO [train.py:823] (2/4) Epoch 48, batch 50, loss[loss=2.19, simple_loss=0.2298, pruned_loss=0.03306, codebook_loss=20.42, over 7139.00 frames.], tot_loss[loss=1.984, simple_loss=0.2337, pruned_loss=0.02687, codebook_loss=18.41, over 320058.32 frames.], batch size: 17, lr: 3.56e-04
+2022-05-28 00:07:07,663 INFO [train.py:823] (2/4) Epoch 48, batch 100, loss[loss=1.936, simple_loss=0.2353, pruned_loss=0.02507, codebook_loss=17.93, over 7195.00 frames.], tot_loss[loss=1.966, simple_loss=0.2336, pruned_loss=0.02634, codebook_loss=18.23, over 564668.80 frames.], batch size: 25, lr: 3.56e-04
+2022-05-28 00:07:49,911 INFO [train.py:823] (2/4) Epoch 48, batch 150, loss[loss=1.931, simple_loss=0.2117, pruned_loss=0.0258, codebook_loss=18, over 7291.00 frames.], tot_loss[loss=1.965, simple_loss=0.2348, pruned_loss=0.02639, codebook_loss=18.22, over 759044.07 frames.], batch size: 17, lr: 3.56e-04
+2022-05-28 00:08:31,450 INFO [train.py:823] (2/4) Epoch 48, batch 200, loss[loss=1.989, simple_loss=0.2783, pruned_loss=0.03764, codebook_loss=18.12, over 7303.00 frames.], tot_loss[loss=1.968, simple_loss=0.2341, pruned_loss=0.02608, codebook_loss=18.25, over 906866.83 frames.], batch size: 22, lr: 3.55e-04
+2022-05-28 00:09:11,314 INFO [train.py:823] (2/4) Epoch 48, batch 250, loss[loss=1.931, simple_loss=0.2265, pruned_loss=0.02898, codebook_loss=17.89, over 7200.00 frames.], tot_loss[loss=1.961, simple_loss=0.2325, pruned_loss=0.02574, codebook_loss=18.19, over 1022784.67 frames.], batch size: 19, lr: 3.55e-04
+2022-05-28 00:09:51,416 INFO [train.py:823] (2/4) Epoch 48, batch 300, loss[loss=2.005, simple_loss=0.2498, pruned_loss=0.03031, codebook_loss=18.5, over 7089.00 frames.], tot_loss[loss=1.958, simple_loss=0.2315, pruned_loss=0.02581, codebook_loss=18.17, over 1114965.97 frames.], batch size: 26, lr: 3.55e-04
+2022-05-28 00:10:30,853 INFO [train.py:823] (2/4) Epoch 48, batch 350, loss[loss=1.944, simple_loss=0.2485, pruned_loss=0.02398, codebook_loss=17.96, over 4955.00 frames.], tot_loss[loss=1.966, simple_loss=0.2319, pruned_loss=0.02595, codebook_loss=18.24, over 1181386.27 frames.], batch size: 48, lr: 3.55e-04
+2022-05-28 00:11:11,350 INFO [train.py:823] (2/4) Epoch 48, batch 400, loss[loss=1.939, simple_loss=0.227, pruned_loss=0.02239, codebook_loss=18.03, over 6387.00 frames.], tot_loss[loss=1.967, simple_loss=0.2324, pruned_loss=0.02605, codebook_loss=18.25, over 1235964.37 frames.], batch size: 34, lr: 3.55e-04
+2022-05-28 00:11:50,921 INFO [train.py:823] (2/4) Epoch 48, batch 450, loss[loss=1.86, simple_loss=0.2102, pruned_loss=0.01999, codebook_loss=17.35, over 7285.00 frames.], tot_loss[loss=1.966, simple_loss=0.2332, pruned_loss=0.02626, codebook_loss=18.23, over 1278765.13 frames.], batch size: 17, lr: 3.54e-04
+2022-05-28 00:12:31,152 INFO [train.py:823] (2/4) Epoch 48, batch 500, loss[loss=1.906, simple_loss=0.2353, pruned_loss=0.0274, codebook_loss=17.61, over 7200.00 frames.], tot_loss[loss=1.968, simple_loss=0.2339, pruned_loss=0.02654, codebook_loss=18.25, over 1308961.38 frames.], batch size: 20, lr: 3.54e-04
+2022-05-28 00:13:11,071 INFO [train.py:823] (2/4) Epoch 48, batch 550, loss[loss=1.946, simple_loss=0.2429, pruned_loss=0.02855, codebook_loss=17.96, over 7417.00 frames.], tot_loss[loss=1.968, simple_loss=0.234, pruned_loss=0.02653, codebook_loss=18.24, over 1329961.92 frames.], batch size: 22, lr: 3.54e-04
+2022-05-28 00:13:52,283 INFO [train.py:823] (2/4) Epoch 48, batch 600, loss[loss=1.979, simple_loss=0.2314, pruned_loss=0.02514, codebook_loss=18.38, over 7278.00 frames.], tot_loss[loss=1.97, simple_loss=0.2346, pruned_loss=0.02662, codebook_loss=18.26, over 1349044.76 frames.], batch size: 20, lr: 3.54e-04
+2022-05-28 00:14:32,034 INFO [train.py:823] (2/4) Epoch 48, batch 650, loss[loss=1.931, simple_loss=0.2573, pruned_loss=0.02578, codebook_loss=17.77, over 7383.00 frames.], tot_loss[loss=1.967, simple_loss=0.2347, pruned_loss=0.02647, codebook_loss=18.23, over 1363312.62 frames.], batch size: 21, lr: 3.54e-04
+2022-05-28 00:15:11,902 INFO [train.py:823] (2/4) Epoch 48, batch 700, loss[loss=1.892, simple_loss=0.2458, pruned_loss=0.0202, codebook_loss=17.49, over 7161.00 frames.], tot_loss[loss=1.965, simple_loss=0.2356, pruned_loss=0.02661, codebook_loss=18.2, over 1371159.72 frames.], batch size: 22, lr: 3.53e-04
+2022-05-28 00:15:51,675 INFO [train.py:823] (2/4) Epoch 48, batch 750, loss[loss=1.908, simple_loss=0.2258, pruned_loss=0.02025, codebook_loss=17.75, over 7103.00 frames.], tot_loss[loss=1.968, simple_loss=0.2353, pruned_loss=0.02663, codebook_loss=18.23, over 1383359.91 frames.], batch size: 19, lr: 3.53e-04
+2022-05-28 00:16:31,782 INFO [train.py:823] (2/4) Epoch 48, batch 800, loss[loss=1.867, simple_loss=0.234, pruned_loss=0.02935, codebook_loss=17.21, over 7335.00 frames.], tot_loss[loss=1.969, simple_loss=0.2353, pruned_loss=0.02659, codebook_loss=18.25, over 1390851.40 frames.], batch size: 23, lr: 3.53e-04
+2022-05-28 00:17:11,214 INFO [train.py:823] (2/4) Epoch 48, batch 850, loss[loss=2.031, simple_loss=0.2294, pruned_loss=0.02726, codebook_loss=18.89, over 7271.00 frames.], tot_loss[loss=1.975, simple_loss=0.2342, pruned_loss=0.02639, codebook_loss=18.31, over 1391103.74 frames.], batch size: 17, lr: 3.53e-04
+2022-05-28 00:17:51,121 INFO [train.py:823] (2/4) Epoch 48, batch 900, loss[loss=1.921, simple_loss=0.231, pruned_loss=0.0304, codebook_loss=17.75, over 7291.00 frames.], tot_loss[loss=1.972, simple_loss=0.2345, pruned_loss=0.02638, codebook_loss=18.28, over 1394671.34 frames.], batch size: 19, lr: 3.53e-04
+2022-05-28 00:18:41,955 INFO [train.py:823] (2/4) Epoch 49, batch 0, loss[loss=1.902, simple_loss=0.2368, pruned_loss=0.02089, codebook_loss=17.63, over 7383.00 frames.], tot_loss[loss=1.902, simple_loss=0.2368, pruned_loss=0.02089, codebook_loss=17.63, over 7383.00 frames.], batch size: 20, lr: 3.49e-04
+2022-05-28 00:19:21,912 INFO [train.py:823] (2/4) Epoch 49, batch 50, loss[loss=1.989, simple_loss=0.2586, pruned_loss=0.03326, codebook_loss=18.27, over 7287.00 frames.], tot_loss[loss=1.948, simple_loss=0.2352, pruned_loss=0.02653, codebook_loss=18.04, over 319059.04 frames.], batch size: 21, lr: 3.49e-04
+2022-05-28 00:20:01,475 INFO [train.py:823] (2/4) Epoch 49, batch 100, loss[loss=1.87, simple_loss=0.2088, pruned_loss=0.02159, codebook_loss=17.44, over 7186.00 frames.], tot_loss[loss=1.944, simple_loss=0.2339, pruned_loss=0.02553, codebook_loss=18.01, over 560953.40 frames.], batch size: 18, lr: 3.48e-04
+2022-05-28 00:20:41,938 INFO [train.py:823] (2/4) Epoch 49, batch 150, loss[loss=2.076, simple_loss=0.2264, pruned_loss=0.03185, codebook_loss=19.31, over 5431.00 frames.], tot_loss[loss=1.951, simple_loss=0.2334, pruned_loss=0.02534, codebook_loss=18.09, over 751657.48 frames.], batch size: 47, lr: 3.48e-04
+2022-05-28 00:21:21,723 INFO [train.py:823] (2/4) Epoch 49, batch 200, loss[loss=1.948, simple_loss=0.2362, pruned_loss=0.03067, codebook_loss=17.99, over 7158.00 frames.], tot_loss[loss=1.951, simple_loss=0.2326, pruned_loss=0.02495, codebook_loss=18.1, over 901870.09 frames.], batch size: 23, lr: 3.48e-04
+2022-05-28 00:22:01,855 INFO [train.py:823] (2/4) Epoch 49, batch 250, loss[loss=1.979, simple_loss=0.2372, pruned_loss=0.02534, codebook_loss=18.36, over 7191.00 frames.], tot_loss[loss=1.956, simple_loss=0.234, pruned_loss=0.02532, codebook_loss=18.14, over 1021921.78 frames.], batch size: 20, lr: 3.48e-04
+2022-05-28 00:22:41,586 INFO [train.py:823] (2/4) Epoch 49, batch 300, loss[loss=1.877, simple_loss=0.2056, pruned_loss=0.02764, codebook_loss=17.46, over 7305.00 frames.], tot_loss[loss=1.956, simple_loss=0.2324, pruned_loss=0.02495, codebook_loss=18.15, over 1113658.74 frames.], batch size: 18, lr: 3.48e-04
+2022-05-28 00:23:21,740 INFO [train.py:823] (2/4) Epoch 49, batch 350, loss[loss=2.149, simple_loss=0.2533, pruned_loss=0.03351, codebook_loss=19.88, over 7230.00 frames.], tot_loss[loss=1.956, simple_loss=0.2324, pruned_loss=0.02492, codebook_loss=18.15, over 1177265.59 frames.], batch size: 25, lr: 3.48e-04
+2022-05-28 00:24:01,384 INFO [train.py:823] (2/4) Epoch 49, batch 400, loss[loss=1.975, simple_loss=0.212, pruned_loss=0.02943, codebook_loss=18.4, over 7011.00 frames.], tot_loss[loss=1.965, simple_loss=0.2333, pruned_loss=0.02555, codebook_loss=18.23, over 1228308.05 frames.], batch size: 16, lr: 3.47e-04
+2022-05-28 00:24:41,435 INFO [train.py:823] (2/4) Epoch 49, batch 450, loss[loss=1.891, simple_loss=0.2493, pruned_loss=0.02755, codebook_loss=17.39, over 7204.00 frames.], tot_loss[loss=1.966, simple_loss=0.2336, pruned_loss=0.02567, codebook_loss=18.24, over 1273327.96 frames.], batch size: 24, lr: 3.47e-04
+2022-05-28 00:25:21,314 INFO [train.py:823] (2/4) Epoch 49, batch 500, loss[loss=1.961, simple_loss=0.2509, pruned_loss=0.02358, codebook_loss=18.12, over 6445.00 frames.], tot_loss[loss=1.962, simple_loss=0.2331, pruned_loss=0.02574, codebook_loss=18.2, over 1304803.67 frames.], batch size: 34, lr: 3.47e-04
+2022-05-28 00:26:01,617 INFO [train.py:823] (2/4) Epoch 49, batch 550, loss[loss=1.851, simple_loss=0.2045, pruned_loss=0.0172, codebook_loss=17.32, over 7288.00 frames.], tot_loss[loss=1.965, simple_loss=0.2324, pruned_loss=0.02566, codebook_loss=18.23, over 1332037.55 frames.], batch size: 17, lr: 3.47e-04
+2022-05-28 00:26:41,357 INFO [train.py:823] (2/4) Epoch 49, batch 600, loss[loss=1.907, simple_loss=0.2434, pruned_loss=0.0286, codebook_loss=17.57, over 7217.00 frames.], tot_loss[loss=1.968, simple_loss=0.2331, pruned_loss=0.02602, codebook_loss=18.26, over 1351463.65 frames.], batch size: 24, lr: 3.47e-04
+2022-05-28 00:27:21,546 INFO [train.py:823] (2/4) Epoch 49, batch 650, loss[loss=1.891, simple_loss=0.2061, pruned_loss=0.01525, codebook_loss=17.73, over 7163.00 frames.], tot_loss[loss=1.968, simple_loss=0.2336, pruned_loss=0.02628, codebook_loss=18.25, over 1366918.70 frames.], batch size: 17, lr: 3.46e-04
+2022-05-28 00:28:00,821 INFO [train.py:823] (2/4) Epoch 49, batch 700, loss[loss=1.964, simple_loss=0.2313, pruned_loss=0.01864, codebook_loss=18.29, over 7418.00 frames.], tot_loss[loss=1.977, simple_loss=0.2348, pruned_loss=0.02711, codebook_loss=18.32, over 1370258.42 frames.], batch size: 22, lr: 3.46e-04
+2022-05-28 00:28:40,795 INFO [train.py:823] (2/4) Epoch 49, batch 750, loss[loss=1.935, simple_loss=0.2232, pruned_loss=0.01906, codebook_loss=18.04, over 7300.00 frames.], tot_loss[loss=1.972, simple_loss=0.2352, pruned_loss=0.0268, codebook_loss=18.28, over 1380828.09 frames.], batch size: 19, lr: 3.46e-04
+2022-05-28 00:29:20,495 INFO [train.py:823] (2/4) Epoch 49, batch 800, loss[loss=1.894, simple_loss=0.2066, pruned_loss=0.02512, codebook_loss=17.66, over 7162.00 frames.], tot_loss[loss=1.969, simple_loss=0.235, pruned_loss=0.02659, codebook_loss=18.25, over 1384006.42 frames.], batch size: 17, lr: 3.46e-04
+2022-05-28 00:30:00,417 INFO [train.py:823] (2/4) Epoch 49, batch 850, loss[loss=1.867, simple_loss=0.2227, pruned_loss=0.02402, codebook_loss=17.32, over 7087.00 frames.], tot_loss[loss=1.967, simple_loss=0.2349, pruned_loss=0.0265, codebook_loss=18.23, over 1391736.31 frames.], batch size: 18, lr: 3.46e-04
+2022-05-28 00:30:40,052 INFO [train.py:823] (2/4) Epoch 49, batch 900, loss[loss=1.954, simple_loss=0.2301, pruned_loss=0.02505, codebook_loss=18.14, over 6468.00 frames.], tot_loss[loss=1.971, simple_loss=0.2353, pruned_loss=0.0266, codebook_loss=18.27, over 1394832.55 frames.], batch size: 34, lr: 3.45e-04
+2022-05-28 00:31:35,690 INFO [train.py:823] (2/4) Epoch 50, batch 0, loss[loss=1.997, simple_loss=0.2467, pruned_loss=0.02946, codebook_loss=18.44, over 6957.00 frames.], tot_loss[loss=1.997, simple_loss=0.2467, pruned_loss=0.02946, codebook_loss=18.44, over 6957.00 frames.], batch size: 29, lr: 3.42e-04
+2022-05-28 00:32:17,062 INFO [train.py:823] (2/4) Epoch 50, batch 50, loss[loss=2.042, simple_loss=0.2315, pruned_loss=0.02923, codebook_loss=18.97, over 7288.00 frames.], tot_loss[loss=1.966, simple_loss=0.2287, pruned_loss=0.02505, codebook_loss=18.26, over 320766.65 frames.], batch size: 20, lr: 3.42e-04
+2022-05-28 00:32:59,752 INFO [train.py:823] (2/4) Epoch 50, batch 100, loss[loss=1.963, simple_loss=0.2591, pruned_loss=0.04083, codebook_loss=17.93, over 7186.00 frames.], tot_loss[loss=1.949, simple_loss=0.231, pruned_loss=0.02529, codebook_loss=18.09, over 561358.11 frames.], batch size: 23, lr: 3.41e-04
+2022-05-28 00:33:39,329 INFO [train.py:823] (2/4) Epoch 50, batch 150, loss[loss=1.917, simple_loss=0.2521, pruned_loss=0.02097, codebook_loss=17.7, over 7371.00 frames.], tot_loss[loss=1.963, simple_loss=0.2339, pruned_loss=0.02602, codebook_loss=18.2, over 751560.77 frames.], batch size: 21, lr: 3.41e-04
+2022-05-28 00:34:19,388 INFO [train.py:823] (2/4) Epoch 50, batch 200, loss[loss=2.035, simple_loss=0.2018, pruned_loss=0.01551, codebook_loss=19.18, over 7089.00 frames.], tot_loss[loss=1.965, simple_loss=0.2342, pruned_loss=0.02618, codebook_loss=18.22, over 900701.76 frames.], batch size: 18, lr: 3.41e-04
+2022-05-28 00:34:59,310 INFO [train.py:823] (2/4) Epoch 50, batch 250, loss[loss=2.17, simple_loss=0.2931, pruned_loss=0.05323, codebook_loss=19.71, over 7176.00 frames.], tot_loss[loss=1.966, simple_loss=0.2345, pruned_loss=0.02632, codebook_loss=18.22, over 1018120.49 frames.], batch size: 22, lr: 3.41e-04
+2022-05-28 00:35:39,376 INFO [train.py:823] (2/4) Epoch 50, batch 300, loss[loss=1.904, simple_loss=0.2261, pruned_loss=0.02293, codebook_loss=17.68, over 7193.00 frames.], tot_loss[loss=1.97, simple_loss=0.2354, pruned_loss=0.02636, codebook_loss=18.26, over 1108905.32 frames.], batch size: 20, lr: 3.41e-04
+2022-05-28 00:36:19,037 INFO [train.py:823] (2/4) Epoch 50, batch 350, loss[loss=2.426, simple_loss=0.2391, pruned_loss=0.03301, codebook_loss=22.74, over 7408.00 frames.], tot_loss[loss=1.967, simple_loss=0.2349, pruned_loss=0.02633, codebook_loss=18.23, over 1177705.66 frames.], batch size: 22, lr: 3.41e-04
+2022-05-28 00:36:59,303 INFO [train.py:823] (2/4) Epoch 50, batch 400, loss[loss=1.905, simple_loss=0.2371, pruned_loss=0.02642, codebook_loss=17.6, over 7032.00 frames.], tot_loss[loss=1.967, simple_loss=0.2334, pruned_loss=0.02623, codebook_loss=18.24, over 1232248.22 frames.], batch size: 26, lr: 3.40e-04
+2022-05-28 00:37:40,216 INFO [train.py:823] (2/4) Epoch 50, batch 450, loss[loss=1.893, simple_loss=0.2404, pruned_loss=0.01577, codebook_loss=17.57, over 6610.00 frames.], tot_loss[loss=1.962, simple_loss=0.2335, pruned_loss=0.02577, codebook_loss=18.19, over 1273636.09 frames.], batch size: 34, lr: 3.40e-04
+2022-05-28 00:38:20,354 INFO [train.py:823] (2/4) Epoch 50, batch 500, loss[loss=1.919, simple_loss=0.219, pruned_loss=0.02424, codebook_loss=17.85, over 7287.00 frames.], tot_loss[loss=1.962, simple_loss=0.2336, pruned_loss=0.02576, codebook_loss=18.2, over 1306293.37 frames.], batch size: 19, lr: 3.40e-04
+2022-05-28 00:39:00,413 INFO [train.py:823] (2/4) Epoch 50, batch 550, loss[loss=2.031, simple_loss=0.2649, pruned_loss=0.03996, codebook_loss=18.58, over 7229.00 frames.], tot_loss[loss=1.963, simple_loss=0.2332, pruned_loss=0.02584, codebook_loss=18.2, over 1334059.99 frames.], batch size: 24, lr: 3.40e-04
+2022-05-28 00:39:40,461 INFO [train.py:823] (2/4) Epoch 50, batch 600, loss[loss=1.926, simple_loss=0.2075, pruned_loss=0.01412, codebook_loss=18.08, over 7019.00 frames.], tot_loss[loss=1.961, simple_loss=0.2334, pruned_loss=0.02568, codebook_loss=18.19, over 1353092.62 frames.], batch size: 16, lr: 3.40e-04
+2022-05-28 00:40:20,088 INFO [train.py:823] (2/4) Epoch 50, batch 650, loss[loss=1.89, simple_loss=0.1949, pruned_loss=0.02165, codebook_loss=17.71, over 7003.00 frames.], tot_loss[loss=1.96, simple_loss=0.234, pruned_loss=0.02581, codebook_loss=18.17, over 1363982.84 frames.], batch size: 16, lr: 3.39e-04
+2022-05-28 00:41:00,232 INFO [train.py:823] (2/4) Epoch 50, batch 700, loss[loss=1.915, simple_loss=0.1983, pruned_loss=0.01182, codebook_loss=18.04, over 7007.00 frames.], tot_loss[loss=1.961, simple_loss=0.2336, pruned_loss=0.02584, codebook_loss=18.18, over 1376263.93 frames.], batch size: 16, lr: 3.39e-04
+2022-05-28 00:41:39,952 INFO [train.py:823] (2/4) Epoch 50, batch 750, loss[loss=1.997, simple_loss=0.257, pruned_loss=0.03051, codebook_loss=18.38, over 7313.00 frames.], tot_loss[loss=1.962, simple_loss=0.2337, pruned_loss=0.02591, codebook_loss=18.19, over 1383274.17 frames.], batch size: 22, lr: 3.39e-04
+2022-05-28 00:42:20,185 INFO [train.py:823] (2/4) Epoch 50, batch 800, loss[loss=1.983, simple_loss=0.2325, pruned_loss=0.02945, codebook_loss=18.38, over 7097.00 frames.], tot_loss[loss=1.958, simple_loss=0.2331, pruned_loss=0.02564, codebook_loss=18.16, over 1390575.50 frames.], batch size: 19, lr: 3.39e-04
+2022-05-28 00:43:00,009 INFO [train.py:823] (2/4) Epoch 50, batch 850, loss[loss=1.98, simple_loss=0.2463, pruned_loss=0.02644, codebook_loss=18.3, over 4871.00 frames.], tot_loss[loss=1.966, simple_loss=0.2331, pruned_loss=0.02572, codebook_loss=18.24, over 1396563.15 frames.], batch size: 46, lr: 3.39e-04
+2022-05-28 00:43:39,826 INFO [train.py:823] (2/4) Epoch 50, batch 900, loss[loss=1.922, simple_loss=0.228, pruned_loss=0.01674, codebook_loss=17.91, over 6332.00 frames.], tot_loss[loss=1.964, simple_loss=0.2339, pruned_loss=0.02585, codebook_loss=18.21, over 1398816.82 frames.], batch size: 34, lr: 3.39e-04
+2022-05-28 00:44:19,568 INFO [train.py:1038] (2/4) Done!