diff --git "a/distillation/log/log-train-2022-05-27-13-56-55-0" "b/distillation/log/log-train-2022-05-27-13-56-55-0"
new file mode 100644--- /dev/null
+++ "b/distillation/log/log-train-2022-05-27-13-56-55-0"
@@ -0,0 +1,1037 @@
+2022-05-27 13:56:55,360 INFO [train.py:887] (0/4) Training started
+2022-05-27 13:56:55,362 INFO [train.py:897] (0/4) Device: cuda:0
+2022-05-27 13:56:55,365 INFO [train.py:906] (0/4) {'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 13:56:55,365 INFO [train.py:908] (0/4) About to create model
+2022-05-27 13:56:55,870 INFO [train.py:912] (0/4) Number of model parameters: 85075176
+2022-05-27 13:57:00,285 INFO [train.py:927] (0/4) Using DDP
+2022-05-27 13:57:00,571 INFO [asr_datamodule.py:408] (0/4) About to get train-clean-100 cuts
+2022-05-27 13:57:08,385 INFO [asr_datamodule.py:225] (0/4) Enable MUSAN
+2022-05-27 13:57:08,385 INFO [asr_datamodule.py:226] (0/4) About to get Musan cuts
+2022-05-27 13:57:11,840 INFO [asr_datamodule.py:254] (0/4) Enable SpecAugment
+2022-05-27 13:57:11,840 INFO [asr_datamodule.py:255] (0/4) Time warp factor: -1
+2022-05-27 13:57:11,840 INFO [asr_datamodule.py:267] (0/4) Num frame mask: 10
+2022-05-27 13:57:11,840 INFO [asr_datamodule.py:280] (0/4) About to create train dataset
+2022-05-27 13:57:11,840 INFO [asr_datamodule.py:309] (0/4) Using BucketingSampler.
+2022-05-27 13:57:12,189 INFO [asr_datamodule.py:325] (0/4) About to create train dataloader
+2022-05-27 13:57:12,190 INFO [asr_datamodule.py:429] (0/4) About to get dev-clean cuts
+2022-05-27 13:57:12,330 INFO [asr_datamodule.py:434] (0/4) About to get dev-other cuts
+2022-05-27 13:57:12,451 INFO [asr_datamodule.py:356] (0/4) About to create dev dataset
+2022-05-27 13:57:12,461 INFO [asr_datamodule.py:375] (0/4) About to create dev dataloader
+2022-05-27 13:57:12,462 INFO [train.py:1054] (0/4) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
+2022-05-27 13:57:15,194 INFO [distributed.py:874] (0/4) Reducer buckets have been rebuilt in this iteration.
+2022-05-27 13:57:27,688 INFO [train.py:823] (0/4) Epoch 1, batch 0, loss[loss=9.182, simple_loss=1.69, pruned_loss=6.611, codebook_loss=83.37, over 7282.00 frames.], tot_loss[loss=9.182, simple_loss=1.69, pruned_loss=6.611, codebook_loss=83.37, over 7282.00 frames.], batch size: 21, lr: 3.00e-03
+2022-05-27 13:58:08,133 INFO [train.py:823] (0/4) Epoch 1, batch 50, loss[loss=5.475, simple_loss=1.043, pruned_loss=6.847, codebook_loss=49.53, over 7130.00 frames.], tot_loss[loss=6.75, simple_loss=1.124, pruned_loss=6.797, codebook_loss=61.88, over 321419.36 frames.], batch size: 23, lr: 3.00e-03
+2022-05-27 13:58:49,199 INFO [train.py:823] (0/4) Epoch 1, batch 100, loss[loss=4.666, simple_loss=0.9283, pruned_loss=6.863, codebook_loss=42.01, over 7192.00 frames.], tot_loss[loss=5.709, simple_loss=1.014, pruned_loss=6.807, codebook_loss=52.02, over 563050.92 frames.], batch size: 20, lr: 3.00e-03
+2022-05-27 13:59:29,583 INFO [train.py:823] (0/4) Epoch 1, batch 150, loss[loss=4.312, simple_loss=0.9121, pruned_loss=6.891, codebook_loss=38.56, over 7347.00 frames.], tot_loss[loss=5.13, simple_loss=0.9479, pruned_loss=6.785, codebook_loss=46.57, over 753492.84 frames.], batch size: 23, lr: 3.00e-03
+2022-05-27 14:00:10,083 INFO [train.py:823] (0/4) Epoch 1, batch 200, loss[loss=3.932, simple_loss=0.7814, pruned_loss=6.623, codebook_loss=35.42, over 7289.00 frames.], tot_loss[loss=4.756, simple_loss=0.9052, pruned_loss=6.754, codebook_loss=43.03, over 903320.03 frames.], batch size: 19, lr: 3.00e-03
+2022-05-27 14:00:50,308 INFO [train.py:823] (0/4) Epoch 1, batch 250, loss[loss=3.808, simple_loss=0.6938, pruned_loss=6.538, codebook_loss=34.61, over 7314.00 frames.], tot_loss[loss=4.499, simple_loss=0.8696, pruned_loss=6.726, codebook_loss=40.64, over 1015539.07 frames.], batch size: 17, lr: 3.00e-03
+2022-05-27 14:01:30,772 INFO [train.py:823] (0/4) Epoch 1, batch 300, loss[loss=3.658, simple_loss=0.6924, pruned_loss=6.707, codebook_loss=33.12, over 7236.00 frames.], tot_loss[loss=4.284, simple_loss=0.8257, pruned_loss=6.692, codebook_loss=38.71, over 1107411.98 frames.], batch size: 24, lr: 3.00e-03
+2022-05-27 14:02:10,826 INFO [train.py:823] (0/4) Epoch 1, batch 350, loss[loss=3.641, simple_loss=0.6766, pruned_loss=6.563, codebook_loss=33.02, over 6281.00 frames.], tot_loss[loss=4.104, simple_loss=0.7803, pruned_loss=6.669, codebook_loss=37.14, over 1177683.71 frames.], batch size: 34, lr: 3.00e-03
+2022-05-27 14:02:51,178 INFO [train.py:823] (0/4) Epoch 1, batch 400, loss[loss=3.53, simple_loss=0.603, pruned_loss=6.553, codebook_loss=32.28, over 4486.00 frames.], tot_loss[loss=3.96, simple_loss=0.7387, pruned_loss=6.657, codebook_loss=35.9, over 1228099.51 frames.], batch size: 46, lr: 3.00e-03
+2022-05-27 14:03:31,151 INFO [train.py:823] (0/4) Epoch 1, batch 450, loss[loss=3.361, simple_loss=0.555, pruned_loss=6.561, codebook_loss=30.83, over 7204.00 frames.], tot_loss[loss=3.834, simple_loss=0.6991, pruned_loss=6.638, codebook_loss=34.84, over 1273735.05 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:04:11,767 INFO [train.py:823] (0/4) Epoch 1, batch 500, loss[loss=3.307, simple_loss=0.5465, pruned_loss=6.511, codebook_loss=30.34, over 7383.00 frames.], tot_loss[loss=3.725, simple_loss=0.6665, pruned_loss=6.628, codebook_loss=33.92, over 1308413.27 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:04:51,636 INFO [train.py:823] (0/4) Epoch 1, batch 550, loss[loss=3.328, simple_loss=0.548, pruned_loss=6.601, codebook_loss=30.54, over 7205.00 frames.], tot_loss[loss=3.639, simple_loss=0.6373, pruned_loss=6.618, codebook_loss=33.2, over 1329823.24 frames.], batch size: 25, lr: 2.99e-03
+2022-05-27 14:05:31,968 INFO [train.py:823] (0/4) Epoch 1, batch 600, loss[loss=3.155, simple_loss=0.4609, pruned_loss=6.53, codebook_loss=29.25, over 7297.00 frames.], tot_loss[loss=3.557, simple_loss=0.6091, pruned_loss=6.606, codebook_loss=32.52, over 1347320.99 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:06:11,924 INFO [train.py:823] (0/4) Epoch 1, batch 650, loss[loss=3.255, simple_loss=0.5191, pruned_loss=6.616, codebook_loss=29.96, over 7096.00 frames.], tot_loss[loss=3.482, simple_loss=0.5855, pruned_loss=6.604, codebook_loss=31.89, over 1361729.54 frames.], batch size: 19, lr: 2.99e-03
+2022-05-27 14:06:52,040 INFO [train.py:823] (0/4) Epoch 1, batch 700, loss[loss=3.157, simple_loss=0.4343, pruned_loss=6.415, codebook_loss=29.4, over 7158.00 frames.], tot_loss[loss=3.419, simple_loss=0.5628, pruned_loss=6.598, codebook_loss=31.38, over 1372893.15 frames.], batch size: 17, lr: 2.99e-03
+2022-05-27 14:07:31,808 INFO [train.py:823] (0/4) Epoch 1, batch 750, loss[loss=3.083, simple_loss=0.4158, pruned_loss=6.408, codebook_loss=28.75, over 6811.00 frames.], tot_loss[loss=3.358, simple_loss=0.5438, pruned_loss=6.595, codebook_loss=30.86, over 1385894.45 frames.], batch size: 15, lr: 2.98e-03
+2022-05-27 14:08:12,269 INFO [train.py:823] (0/4) Epoch 1, batch 800, loss[loss=3.182, simple_loss=0.4848, pruned_loss=6.621, codebook_loss=29.39, over 7146.00 frames.], tot_loss[loss=3.311, simple_loss=0.5289, pruned_loss=6.6, codebook_loss=30.46, over 1391450.48 frames.], batch size: 23, lr: 2.98e-03
+2022-05-27 14:08:52,263 INFO [train.py:823] (0/4) Epoch 1, batch 850, loss[loss=2.97, simple_loss=0.4066, pruned_loss=6.449, codebook_loss=27.67, over 7014.00 frames.], tot_loss[loss=3.261, simple_loss=0.5142, pruned_loss=6.599, codebook_loss=30.04, over 1399222.13 frames.], batch size: 16, lr: 2.98e-03
+2022-05-27 14:09:32,257 INFO [train.py:823] (0/4) Epoch 1, batch 900, loss[loss=2.961, simple_loss=0.4092, pruned_loss=6.584, codebook_loss=27.57, over 7293.00 frames.], tot_loss[loss=3.212, simple_loss=0.4994, pruned_loss=6.6, codebook_loss=29.62, over 1402692.29 frames.], batch size: 17, lr: 2.98e-03
+2022-05-27 14:10:11,253 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-1.pt
+2022-05-27 14:10:24,072 INFO [train.py:823] (0/4) Epoch 2, batch 0, loss[loss=2.959, simple_loss=0.4295, pruned_loss=6.622, codebook_loss=27.44, over 7099.00 frames.], tot_loss[loss=2.959, simple_loss=0.4295, pruned_loss=6.622, codebook_loss=27.44, over 7099.00 frames.], batch size: 19, lr: 2.95e-03
+2022-05-27 14:11:04,509 INFO [train.py:823] (0/4) Epoch 2, batch 50, loss[loss=3.092, simple_loss=0.4814, pruned_loss=6.684, codebook_loss=28.51, over 7380.00 frames.], tot_loss[loss=3.006, simple_loss=0.4326, pruned_loss=6.576, codebook_loss=27.89, over 322119.63 frames.], batch size: 21, lr: 2.95e-03
+2022-05-27 14:11:44,091 INFO [train.py:823] (0/4) Epoch 2, batch 100, loss[loss=2.837, simple_loss=0.4084, pruned_loss=6.596, codebook_loss=26.33, over 7042.00 frames.], tot_loss[loss=2.986, simple_loss=0.4276, pruned_loss=6.578, codebook_loss=27.72, over 564395.34 frames.], batch size: 26, lr: 2.95e-03
+2022-05-27 14:12:24,459 INFO [train.py:823] (0/4) Epoch 2, batch 150, loss[loss=3.056, simple_loss=0.4036, pruned_loss=6.472, codebook_loss=28.54, over 7285.00 frames.], tot_loss[loss=2.967, simple_loss=0.423, pruned_loss=6.579, codebook_loss=27.55, over 757905.99 frames.], batch size: 17, lr: 2.94e-03
+2022-05-27 14:13:04,788 INFO [train.py:823] (0/4) Epoch 2, batch 200, loss[loss=2.95, simple_loss=0.4163, pruned_loss=6.562, codebook_loss=27.42, over 7093.00 frames.], tot_loss[loss=2.949, simple_loss=0.4197, pruned_loss=6.579, codebook_loss=27.39, over 905530.69 frames.], batch size: 18, lr: 2.94e-03
+2022-05-27 14:13:45,220 INFO [train.py:823] (0/4) Epoch 2, batch 250, loss[loss=3.042, simple_loss=0.3941, pruned_loss=6.522, codebook_loss=28.45, over 7157.00 frames.], tot_loss[loss=2.939, simple_loss=0.4172, pruned_loss=6.576, codebook_loss=27.31, over 1016440.45 frames.], batch size: 17, lr: 2.94e-03
+2022-05-27 14:14:25,473 INFO [train.py:823] (0/4) Epoch 2, batch 300, loss[loss=2.914, simple_loss=0.3634, pruned_loss=6.481, codebook_loss=27.32, over 7013.00 frames.], tot_loss[loss=2.932, simple_loss=0.4146, pruned_loss=6.582, codebook_loss=27.25, over 1106875.89 frames.], batch size: 16, lr: 2.93e-03
+2022-05-27 14:15:07,446 INFO [train.py:823] (0/4) Epoch 2, batch 350, loss[loss=2.824, simple_loss=0.4191, pruned_loss=6.592, codebook_loss=26.15, over 7173.00 frames.], tot_loss[loss=2.93, simple_loss=0.4127, pruned_loss=6.583, codebook_loss=27.23, over 1174517.39 frames.], batch size: 23, lr: 2.93e-03
+2022-05-27 14:15:51,499 INFO [train.py:823] (0/4) Epoch 2, batch 400, loss[loss=2.856, simple_loss=0.4168, pruned_loss=6.564, codebook_loss=26.48, over 7091.00 frames.], tot_loss[loss=2.917, simple_loss=0.409, pruned_loss=6.58, codebook_loss=27.13, over 1224865.02 frames.], batch size: 18, lr: 2.93e-03
+2022-05-27 14:16:31,747 INFO [train.py:823] (0/4) Epoch 2, batch 450, loss[loss=2.892, simple_loss=0.4497, pruned_loss=6.679, codebook_loss=26.68, over 7272.00 frames.], tot_loss[loss=2.902, simple_loss=0.407, pruned_loss=6.581, codebook_loss=26.98, over 1265251.22 frames.], batch size: 21, lr: 2.92e-03
+2022-05-27 14:17:11,905 INFO [train.py:823] (0/4) Epoch 2, batch 500, loss[loss=2.808, simple_loss=0.4058, pruned_loss=6.632, codebook_loss=26.05, over 6857.00 frames.], tot_loss[loss=2.885, simple_loss=0.4046, pruned_loss=6.586, codebook_loss=26.82, over 1301605.69 frames.], batch size: 29, lr: 2.92e-03
+2022-05-27 14:17:52,173 INFO [train.py:823] (0/4) Epoch 2, batch 550, loss[loss=2.952, simple_loss=0.4474, pruned_loss=6.624, codebook_loss=27.29, over 4835.00 frames.], tot_loss[loss=2.881, simple_loss=0.403, pruned_loss=6.584, codebook_loss=26.79, over 1322781.31 frames.], batch size: 46, lr: 2.92e-03
+2022-05-27 14:18:32,331 INFO [train.py:823] (0/4) Epoch 2, batch 600, loss[loss=2.871, simple_loss=0.4304, pruned_loss=6.618, codebook_loss=26.56, over 7285.00 frames.], tot_loss[loss=2.87, simple_loss=0.401, pruned_loss=6.582, codebook_loss=26.69, over 1340084.42 frames.], batch size: 21, lr: 2.91e-03
+2022-05-27 14:19:12,804 INFO [train.py:823] (0/4) Epoch 2, batch 650, loss[loss=2.768, simple_loss=0.4194, pruned_loss=6.687, codebook_loss=25.58, over 7298.00 frames.], tot_loss[loss=2.854, simple_loss=0.3985, pruned_loss=6.589, codebook_loss=26.55, over 1358595.98 frames.], batch size: 22, lr: 2.91e-03
+2022-05-27 14:19:53,602 INFO [train.py:823] (0/4) Epoch 2, batch 700, loss[loss=2.752, simple_loss=0.3383, pruned_loss=6.48, codebook_loss=25.83, over 7008.00 frames.], tot_loss[loss=2.838, simple_loss=0.3954, pruned_loss=6.597, codebook_loss=26.4, over 1374114.72 frames.], batch size: 17, lr: 2.90e-03
+2022-05-27 14:20:34,626 INFO [train.py:823] (0/4) Epoch 2, batch 750, loss[loss=2.848, simple_loss=0.3912, pruned_loss=6.666, codebook_loss=26.52, over 7110.00 frames.], tot_loss[loss=2.818, simple_loss=0.3915, pruned_loss=6.598, codebook_loss=26.23, over 1382025.28 frames.], batch size: 20, lr: 2.90e-03
+2022-05-27 14:21:14,867 INFO [train.py:823] (0/4) Epoch 2, batch 800, loss[loss=2.946, simple_loss=0.3884, pruned_loss=6.624, codebook_loss=27.51, over 4442.00 frames.], tot_loss[loss=2.816, simple_loss=0.3894, pruned_loss=6.603, codebook_loss=26.21, over 1386964.03 frames.], batch size: 47, lr: 2.89e-03
+2022-05-27 14:21:56,427 INFO [train.py:823] (0/4) Epoch 2, batch 850, loss[loss=2.8, simple_loss=0.3776, pruned_loss=6.618, codebook_loss=26.11, over 7200.00 frames.], tot_loss[loss=2.803, simple_loss=0.3864, pruned_loss=6.604, codebook_loss=26.09, over 1390488.35 frames.], batch size: 20, lr: 2.89e-03
+2022-05-27 14:22:36,176 INFO [train.py:823] (0/4) Epoch 2, batch 900, loss[loss=2.667, simple_loss=0.3292, pruned_loss=6.483, codebook_loss=25.02, over 7311.00 frames.], tot_loss[loss=2.787, simple_loss=0.3838, pruned_loss=6.609, codebook_loss=25.95, over 1394268.29 frames.], batch size: 18, lr: 2.89e-03
+2022-05-27 14:23:15,613 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-2.pt
+2022-05-27 14:23:30,857 INFO [train.py:823] (0/4) Epoch 3, batch 0, loss[loss=2.681, simple_loss=0.3474, pruned_loss=6.591, codebook_loss=25.08, over 7289.00 frames.], tot_loss[loss=2.681, simple_loss=0.3474, pruned_loss=6.591, codebook_loss=25.08, over 7289.00 frames.], batch size: 17, lr: 2.83e-03
+2022-05-27 14:24:11,237 INFO [train.py:823] (0/4) Epoch 3, batch 50, loss[loss=2.875, simple_loss=0.4444, pruned_loss=6.616, codebook_loss=26.53, over 4797.00 frames.], tot_loss[loss=2.708, simple_loss=0.3675, pruned_loss=6.599, codebook_loss=25.24, over 319171.48 frames.], batch size: 46, lr: 2.82e-03
+2022-05-27 14:24:51,185 INFO [train.py:823] (0/4) Epoch 3, batch 100, loss[loss=2.675, simple_loss=0.3938, pruned_loss=6.704, codebook_loss=24.78, over 6967.00 frames.], tot_loss[loss=2.716, simple_loss=0.3673, pruned_loss=6.589, codebook_loss=25.32, over 564980.65 frames.], batch size: 26, lr: 2.82e-03
+2022-05-27 14:25:31,484 INFO [train.py:823] (0/4) Epoch 3, batch 150, loss[loss=2.747, simple_loss=0.4161, pruned_loss=6.697, codebook_loss=25.39, over 7367.00 frames.], tot_loss[loss=2.705, simple_loss=0.3656, pruned_loss=6.599, codebook_loss=25.22, over 755529.16 frames.], batch size: 20, lr: 2.81e-03
+2022-05-27 14:26:11,605 INFO [train.py:823] (0/4) Epoch 3, batch 200, loss[loss=2.597, simple_loss=0.3362, pruned_loss=6.589, codebook_loss=24.29, over 7107.00 frames.], tot_loss[loss=2.698, simple_loss=0.3639, pruned_loss=6.605, codebook_loss=25.16, over 906194.11 frames.], batch size: 20, lr: 2.81e-03
+2022-05-27 14:26:51,965 INFO [train.py:823] (0/4) Epoch 3, batch 250, loss[loss=2.634, simple_loss=0.3444, pruned_loss=6.599, codebook_loss=24.62, over 6953.00 frames.], tot_loss[loss=2.689, simple_loss=0.3618, pruned_loss=6.613, codebook_loss=25.08, over 1024131.91 frames.], batch size: 26, lr: 2.80e-03
+2022-05-27 14:27:31,798 INFO [train.py:823] (0/4) Epoch 3, batch 300, loss[loss=2.715, simple_loss=0.3726, pruned_loss=6.607, codebook_loss=25.29, over 7396.00 frames.], tot_loss[loss=2.686, simple_loss=0.3599, pruned_loss=6.616, codebook_loss=25.06, over 1114169.65 frames.], batch size: 19, lr: 2.80e-03
+2022-05-27 14:28:12,714 INFO [train.py:823] (0/4) Epoch 3, batch 350, loss[loss=2.635, simple_loss=0.367, pruned_loss=6.65, codebook_loss=24.51, over 7337.00 frames.], tot_loss[loss=2.695, simple_loss=0.3599, pruned_loss=6.616, codebook_loss=25.15, over 1186161.71 frames.], batch size: 23, lr: 2.79e-03
+2022-05-27 14:28:52,455 INFO [train.py:823] (0/4) Epoch 3, batch 400, loss[loss=2.527, simple_loss=0.2974, pruned_loss=6.463, codebook_loss=23.79, over 7316.00 frames.], tot_loss[loss=2.694, simple_loss=0.3611, pruned_loss=6.616, codebook_loss=25.14, over 1240032.58 frames.], batch size: 18, lr: 2.79e-03
+2022-05-27 14:29:32,957 INFO [train.py:823] (0/4) Epoch 3, batch 450, loss[loss=2.654, simple_loss=0.3514, pruned_loss=6.588, codebook_loss=24.79, over 7203.00 frames.], tot_loss[loss=2.695, simple_loss=0.3617, pruned_loss=6.617, codebook_loss=25.14, over 1273998.30 frames.], batch size: 18, lr: 2.78e-03
+2022-05-27 14:30:12,768 INFO [train.py:823] (0/4) Epoch 3, batch 500, loss[loss=2.664, simple_loss=0.3041, pruned_loss=6.594, codebook_loss=25.12, over 7307.00 frames.], tot_loss[loss=2.694, simple_loss=0.3596, pruned_loss=6.619, codebook_loss=25.14, over 1305396.37 frames.], batch size: 18, lr: 2.77e-03
+2022-05-27 14:30:52,962 INFO [train.py:823] (0/4) Epoch 3, batch 550, loss[loss=2.746, simple_loss=0.446, pruned_loss=6.872, codebook_loss=25.23, over 7176.00 frames.], tot_loss[loss=2.683, simple_loss=0.3594, pruned_loss=6.628, codebook_loss=25.04, over 1333504.39 frames.], batch size: 21, lr: 2.77e-03
+2022-05-27 14:31:32,953 INFO [train.py:823] (0/4) Epoch 3, batch 600, loss[loss=2.653, simple_loss=0.3903, pruned_loss=6.776, codebook_loss=24.58, over 7377.00 frames.], tot_loss[loss=2.678, simple_loss=0.3569, pruned_loss=6.627, codebook_loss=25, over 1346846.61 frames.], batch size: 20, lr: 2.76e-03
+2022-05-27 14:32:13,221 INFO [train.py:823] (0/4) Epoch 3, batch 650, loss[loss=2.83, simple_loss=0.3911, pruned_loss=6.659, codebook_loss=26.35, over 4591.00 frames.], tot_loss[loss=2.666, simple_loss=0.3553, pruned_loss=6.632, codebook_loss=24.89, over 1363202.46 frames.], batch size: 47, lr: 2.76e-03
+2022-05-27 14:32:52,989 INFO [train.py:823] (0/4) Epoch 3, batch 700, loss[loss=2.587, simple_loss=0.3499, pruned_loss=6.638, codebook_loss=24.12, over 7306.00 frames.], tot_loss[loss=2.656, simple_loss=0.3531, pruned_loss=6.625, codebook_loss=24.8, over 1376018.44 frames.], batch size: 22, lr: 2.75e-03
+2022-05-27 14:33:33,463 INFO [train.py:823] (0/4) Epoch 3, batch 750, loss[loss=2.568, simple_loss=0.3321, pruned_loss=6.579, codebook_loss=24.02, over 7177.00 frames.], tot_loss[loss=2.644, simple_loss=0.3507, pruned_loss=6.624, codebook_loss=24.69, over 1384610.56 frames.], batch size: 19, lr: 2.75e-03
+2022-05-27 14:34:13,282 INFO [train.py:823] (0/4) Epoch 3, batch 800, loss[loss=2.69, simple_loss=0.3898, pruned_loss=6.691, codebook_loss=24.95, over 7425.00 frames.], tot_loss[loss=2.638, simple_loss=0.3501, pruned_loss=6.628, codebook_loss=24.63, over 1394736.72 frames.], batch size: 22, lr: 2.74e-03
+2022-05-27 14:34:53,236 INFO [train.py:823] (0/4) Epoch 3, batch 850, loss[loss=2.565, simple_loss=0.3511, pruned_loss=6.657, codebook_loss=23.89, over 7098.00 frames.], tot_loss[loss=2.642, simple_loss=0.3496, pruned_loss=6.627, codebook_loss=24.67, over 1397192.95 frames.], batch size: 19, lr: 2.74e-03
+2022-05-27 14:35:32,631 INFO [train.py:823] (0/4) Epoch 3, batch 900, loss[loss=2.605, simple_loss=0.3605, pruned_loss=6.736, codebook_loss=24.25, over 4963.00 frames.], tot_loss[loss=2.643, simple_loss=0.3498, pruned_loss=6.634, codebook_loss=24.68, over 1392641.94 frames.], batch size: 47, lr: 2.73e-03
+2022-05-27 14:36:12,464 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-3.pt
+2022-05-27 14:36:26,040 INFO [train.py:823] (0/4) Epoch 4, batch 0, loss[loss=2.548, simple_loss=0.3409, pruned_loss=6.68, codebook_loss=23.78, over 7089.00 frames.], tot_loss[loss=2.548, simple_loss=0.3409, pruned_loss=6.68, codebook_loss=23.78, over 7089.00 frames.], batch size: 19, lr: 2.64e-03
+2022-05-27 14:37:06,179 INFO [train.py:823] (0/4) Epoch 4, batch 50, loss[loss=2.489, simple_loss=0.3068, pruned_loss=6.478, codebook_loss=23.36, over 7020.00 frames.], tot_loss[loss=2.566, simple_loss=0.3255, pruned_loss=6.595, codebook_loss=24.04, over 319743.39 frames.], batch size: 17, lr: 2.64e-03
+2022-05-27 14:37:46,120 INFO [train.py:823] (0/4) Epoch 4, batch 100, loss[loss=2.584, simple_loss=0.3435, pruned_loss=6.731, codebook_loss=24.12, over 7368.00 frames.], tot_loss[loss=2.57, simple_loss=0.3311, pruned_loss=6.622, codebook_loss=24.04, over 564735.01 frames.], batch size: 21, lr: 2.63e-03
+2022-05-27 14:38:25,733 INFO [train.py:823] (0/4) Epoch 4, batch 150, loss[loss=2.527, simple_loss=0.3098, pruned_loss=6.517, codebook_loss=23.72, over 7154.00 frames.], tot_loss[loss=2.586, simple_loss=0.3351, pruned_loss=6.631, codebook_loss=24.19, over 751645.67 frames.], batch size: 17, lr: 2.63e-03
+2022-05-27 14:39:07,309 INFO [train.py:823] (0/4) Epoch 4, batch 200, loss[loss=2.652, simple_loss=0.3322, pruned_loss=0.9882, codebook_loss=23.87, over 7171.00 frames.], tot_loss[loss=2.672, simple_loss=0.3461, pruned_loss=4.804, codebook_loss=24.1, over 904176.39 frames.], batch size: 18, lr: 2.62e-03
+2022-05-27 14:39:46,947 INFO [train.py:823] (0/4) Epoch 4, batch 250, loss[loss=2.671, simple_loss=0.3461, pruned_loss=0.6962, codebook_loss=24.29, over 7381.00 frames.], tot_loss[loss=2.672, simple_loss=0.3438, pruned_loss=3.564, codebook_loss=24.13, over 1023856.21 frames.], batch size: 21, lr: 2.62e-03
+2022-05-27 14:40:29,616 INFO [train.py:823] (0/4) Epoch 4, batch 300, loss[loss=2.687, simple_loss=0.3535, pruned_loss=0.4433, codebook_loss=24.66, over 7193.00 frames.], tot_loss[loss=2.655, simple_loss=0.3419, pruned_loss=2.706, codebook_loss=24.07, over 1108770.09 frames.], batch size: 20, lr: 2.61e-03
+2022-05-27 14:41:09,186 INFO [train.py:823] (0/4) Epoch 4, batch 350, loss[loss=2.599, simple_loss=0.3758, pruned_loss=0.3089, codebook_loss=23.8, over 7143.00 frames.], tot_loss[loss=2.636, simple_loss=0.3401, pruned_loss=2.076, codebook_loss=24, over 1174664.22 frames.], batch size: 23, lr: 2.60e-03
+2022-05-27 14:41:49,186 INFO [train.py:823] (0/4) Epoch 4, batch 400, loss[loss=2.558, simple_loss=0.3489, pruned_loss=0.2365, codebook_loss=23.6, over 7196.00 frames.], tot_loss[loss=2.625, simple_loss=0.3386, pruned_loss=1.608, codebook_loss=24.01, over 1227816.59 frames.], batch size: 25, lr: 2.60e-03
+2022-05-27 14:42:28,873 INFO [train.py:823] (0/4) Epoch 4, batch 450, loss[loss=2.531, simple_loss=0.3074, pruned_loss=0.1796, codebook_loss=23.59, over 7153.00 frames.], tot_loss[loss=2.615, simple_loss=0.3385, pruned_loss=1.263, codebook_loss=23.99, over 1269905.00 frames.], batch size: 17, lr: 2.59e-03
+2022-05-27 14:43:08,812 INFO [train.py:823] (0/4) Epoch 4, batch 500, loss[loss=2.512, simple_loss=0.3376, pruned_loss=0.1832, codebook_loss=23.25, over 7197.00 frames.], tot_loss[loss=2.603, simple_loss=0.3389, pruned_loss=1.003, codebook_loss=23.93, over 1306807.02 frames.], batch size: 25, lr: 2.59e-03
+2022-05-27 14:43:48,395 INFO [train.py:823] (0/4) Epoch 4, batch 550, loss[loss=2.546, simple_loss=0.3101, pruned_loss=0.1532, codebook_loss=23.76, over 7393.00 frames.], tot_loss[loss=2.59, simple_loss=0.3361, pruned_loss=0.8053, codebook_loss=23.88, over 1333739.50 frames.], batch size: 19, lr: 2.58e-03
+2022-05-27 14:44:28,571 INFO [train.py:823] (0/4) Epoch 4, batch 600, loss[loss=2.507, simple_loss=0.3347, pruned_loss=0.1518, codebook_loss=23.25, over 7182.00 frames.], tot_loss[loss=2.577, simple_loss=0.3346, pruned_loss=0.654, codebook_loss=23.8, over 1355588.96 frames.], batch size: 21, lr: 2.57e-03
+2022-05-27 14:45:08,622 INFO [train.py:823] (0/4) Epoch 4, batch 650, loss[loss=2.491, simple_loss=0.3137, pruned_loss=0.1344, codebook_loss=23.21, over 7378.00 frames.], tot_loss[loss=2.565, simple_loss=0.3334, pruned_loss=0.5385, codebook_loss=23.71, over 1371038.35 frames.], batch size: 20, lr: 2.57e-03
+2022-05-27 14:45:48,465 INFO [train.py:823] (0/4) Epoch 4, batch 700, loss[loss=2.608, simple_loss=0.3307, pruned_loss=0.1369, codebook_loss=24.29, over 5308.00 frames.], tot_loss[loss=2.571, simple_loss=0.336, pruned_loss=0.4542, codebook_loss=23.79, over 1376945.37 frames.], batch size: 47, lr: 2.56e-03
+2022-05-27 14:46:28,088 INFO [train.py:823] (0/4) Epoch 4, batch 750, loss[loss=2.492, simple_loss=0.3132, pruned_loss=0.1184, codebook_loss=23.24, over 7095.00 frames.], tot_loss[loss=2.581, simple_loss=0.3362, pruned_loss=0.3872, codebook_loss=23.9, over 1385200.14 frames.], batch size: 19, lr: 2.56e-03
+2022-05-27 14:47:08,127 INFO [train.py:823] (0/4) Epoch 4, batch 800, loss[loss=2.463, simple_loss=0.2754, pruned_loss=0.1028, codebook_loss=23.15, over 7011.00 frames.], tot_loss[loss=2.573, simple_loss=0.334, pruned_loss=0.3328, codebook_loss=23.85, over 1386689.69 frames.], batch size: 17, lr: 2.55e-03
+2022-05-27 14:47:47,743 INFO [train.py:823] (0/4) Epoch 4, batch 850, loss[loss=2.554, simple_loss=0.3696, pruned_loss=0.1617, codebook_loss=23.53, over 7296.00 frames.], tot_loss[loss=2.569, simple_loss=0.333, pruned_loss=0.2893, codebook_loss=23.83, over 1392078.99 frames.], batch size: 22, lr: 2.54e-03
+2022-05-27 14:48:27,885 INFO [train.py:823] (0/4) Epoch 4, batch 900, loss[loss=2.588, simple_loss=0.332, pruned_loss=0.1367, codebook_loss=24.08, over 7195.00 frames.], tot_loss[loss=2.569, simple_loss=0.3313, pruned_loss=0.2564, codebook_loss=23.86, over 1388559.96 frames.], batch size: 18, lr: 2.54e-03
+2022-05-27 14:49:07,815 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-4.pt
+2022-05-27 14:49:21,907 INFO [train.py:823] (0/4) Epoch 5, batch 0, loss[loss=2.395, simple_loss=0.3238, pruned_loss=0.1193, codebook_loss=22.21, over 7321.00 frames.], tot_loss[loss=2.395, simple_loss=0.3238, pruned_loss=0.1193, codebook_loss=22.21, over 7321.00 frames.], batch size: 23, lr: 2.44e-03
+2022-05-27 14:50:02,123 INFO [train.py:823] (0/4) Epoch 5, batch 50, loss[loss=2.417, simple_loss=0.3135, pruned_loss=0.1139, codebook_loss=22.49, over 6978.00 frames.], tot_loss[loss=2.505, simple_loss=0.3209, pruned_loss=0.1276, codebook_loss=23.31, over 326001.34 frames.], batch size: 26, lr: 2.44e-03
+2022-05-27 14:50:41,832 INFO [train.py:823] (0/4) Epoch 5, batch 100, loss[loss=2.591, simple_loss=0.3714, pruned_loss=0.1619, codebook_loss=23.89, over 7112.00 frames.], tot_loss[loss=2.499, simple_loss=0.3194, pruned_loss=0.1235, codebook_loss=23.27, over 570810.90 frames.], batch size: 20, lr: 2.43e-03
+2022-05-27 14:51:21,914 INFO [train.py:823] (0/4) Epoch 5, batch 150, loss[loss=2.481, simple_loss=0.3293, pruned_loss=0.1149, codebook_loss=23.05, over 7375.00 frames.], tot_loss[loss=2.517, simple_loss=0.3203, pruned_loss=0.1246, codebook_loss=23.44, over 759066.29 frames.], batch size: 20, lr: 2.42e-03
+2022-05-27 14:52:01,338 INFO [train.py:823] (0/4) Epoch 5, batch 200, loss[loss=2.496, simple_loss=0.3399, pruned_loss=0.1243, codebook_loss=23.14, over 7182.00 frames.], tot_loss[loss=2.516, simple_loss=0.3208, pruned_loss=0.1249, codebook_loss=23.43, over 905889.99 frames.], batch size: 22, lr: 2.42e-03
+2022-05-27 14:52:41,369 INFO [train.py:823] (0/4) Epoch 5, batch 250, loss[loss=2.538, simple_loss=0.3358, pruned_loss=0.1417, codebook_loss=23.56, over 5280.00 frames.], tot_loss[loss=2.51, simple_loss=0.3198, pruned_loss=0.1236, codebook_loss=23.38, over 1014645.04 frames.], batch size: 46, lr: 2.41e-03
+2022-05-27 14:53:20,949 INFO [train.py:823] (0/4) Epoch 5, batch 300, loss[loss=2.546, simple_loss=0.3665, pruned_loss=0.1632, codebook_loss=23.47, over 7141.00 frames.], tot_loss[loss=2.502, simple_loss=0.3199, pruned_loss=0.1217, codebook_loss=23.3, over 1105555.23 frames.], batch size: 23, lr: 2.41e-03
+2022-05-27 14:54:00,891 INFO [train.py:823] (0/4) Epoch 5, batch 350, loss[loss=2.423, simple_loss=0.3391, pruned_loss=0.1266, codebook_loss=22.41, over 7246.00 frames.], tot_loss[loss=2.499, simple_loss=0.3192, pruned_loss=0.1197, codebook_loss=23.27, over 1174961.11 frames.], batch size: 24, lr: 2.40e-03
+2022-05-27 14:54:40,905 INFO [train.py:823] (0/4) Epoch 5, batch 400, loss[loss=2.545, simple_loss=0.2893, pruned_loss=0.09882, codebook_loss=23.9, over 7017.00 frames.], tot_loss[loss=2.496, simple_loss=0.3184, pruned_loss=0.1185, codebook_loss=23.25, over 1234678.67 frames.], batch size: 17, lr: 2.39e-03
+2022-05-27 14:55:20,861 INFO [train.py:823] (0/4) Epoch 5, batch 450, loss[loss=2.428, simple_loss=0.3447, pruned_loss=0.125, codebook_loss=22.43, over 7022.00 frames.], tot_loss[loss=2.494, simple_loss=0.3185, pruned_loss=0.1186, codebook_loss=23.23, over 1271520.51 frames.], batch size: 26, lr: 2.39e-03
+2022-05-27 14:56:00,505 INFO [train.py:823] (0/4) Epoch 5, batch 500, loss[loss=2.334, simple_loss=0.2841, pruned_loss=0.07723, codebook_loss=21.85, over 7194.00 frames.], tot_loss[loss=2.491, simple_loss=0.3188, pruned_loss=0.118, codebook_loss=23.2, over 1306123.29 frames.], batch size: 19, lr: 2.38e-03
+2022-05-27 14:56:40,383 INFO [train.py:823] (0/4) Epoch 5, batch 550, loss[loss=2.493, simple_loss=0.3218, pruned_loss=0.1032, codebook_loss=23.22, over 6897.00 frames.], tot_loss[loss=2.488, simple_loss=0.3195, pruned_loss=0.1183, codebook_loss=23.17, over 1331245.78 frames.], batch size: 29, lr: 2.38e-03
+2022-05-27 14:57:20,185 INFO [train.py:823] (0/4) Epoch 5, batch 600, loss[loss=2.474, simple_loss=0.3574, pruned_loss=0.1387, codebook_loss=22.81, over 6616.00 frames.], tot_loss[loss=2.486, simple_loss=0.3191, pruned_loss=0.1172, codebook_loss=23.15, over 1349282.70 frames.], batch size: 34, lr: 2.37e-03
+2022-05-27 14:58:00,316 INFO [train.py:823] (0/4) Epoch 5, batch 650, loss[loss=2.429, simple_loss=0.3354, pruned_loss=0.1135, codebook_loss=22.5, over 7284.00 frames.], tot_loss[loss=2.485, simple_loss=0.3184, pruned_loss=0.1161, codebook_loss=23.14, over 1364778.27 frames.], batch size: 21, lr: 2.37e-03
+2022-05-27 14:58:39,916 INFO [train.py:823] (0/4) Epoch 5, batch 700, loss[loss=2.432, simple_loss=0.3484, pruned_loss=0.1282, codebook_loss=22.45, over 6989.00 frames.], tot_loss[loss=2.483, simple_loss=0.3178, pruned_loss=0.1146, codebook_loss=23.12, over 1374104.70 frames.], batch size: 26, lr: 2.36e-03
+2022-05-27 14:59:19,728 INFO [train.py:823] (0/4) Epoch 5, batch 750, loss[loss=2.628, simple_loss=0.365, pruned_loss=0.1652, codebook_loss=24.29, over 7129.00 frames.], tot_loss[loss=2.482, simple_loss=0.3187, pruned_loss=0.1144, codebook_loss=23.11, over 1381650.66 frames.], batch size: 23, lr: 2.35e-03
+2022-05-27 14:59:59,644 INFO [train.py:823] (0/4) Epoch 5, batch 800, loss[loss=2.43, simple_loss=0.2979, pruned_loss=0.09482, codebook_loss=22.71, over 4870.00 frames.], tot_loss[loss=2.478, simple_loss=0.3182, pruned_loss=0.1136, codebook_loss=23.07, over 1391075.86 frames.], batch size: 46, lr: 2.35e-03
+2022-05-27 15:00:39,937 INFO [train.py:823] (0/4) Epoch 5, batch 850, loss[loss=2.452, simple_loss=0.3198, pruned_loss=0.1195, codebook_loss=22.8, over 7155.00 frames.], tot_loss[loss=2.471, simple_loss=0.3165, pruned_loss=0.1121, codebook_loss=23.02, over 1397986.52 frames.], batch size: 17, lr: 2.34e-03
+2022-05-27 15:01:19,749 INFO [train.py:823] (0/4) Epoch 5, batch 900, loss[loss=2.599, simple_loss=0.3424, pruned_loss=0.1265, codebook_loss=24.15, over 6846.00 frames.], tot_loss[loss=2.468, simple_loss=0.3164, pruned_loss=0.1114, codebook_loss=22.99, over 1400068.50 frames.], batch size: 29, lr: 2.34e-03
+2022-05-27 15:01:59,558 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-5.pt
+2022-05-27 15:02:14,659 INFO [train.py:823] (0/4) Epoch 6, batch 0, loss[loss=2.479, simple_loss=0.3318, pruned_loss=0.09836, codebook_loss=23.03, over 7163.00 frames.], tot_loss[loss=2.479, simple_loss=0.3318, pruned_loss=0.09836, codebook_loss=23.03, over 7163.00 frames.], batch size: 22, lr: 2.24e-03
+2022-05-27 15:02:54,280 INFO [train.py:823] (0/4) Epoch 6, batch 50, loss[loss=2.436, simple_loss=0.3154, pruned_loss=0.088, codebook_loss=22.7, over 7205.00 frames.], tot_loss[loss=2.427, simple_loss=0.311, pruned_loss=0.1001, codebook_loss=22.61, over 319721.85 frames.], batch size: 21, lr: 2.23e-03
+2022-05-27 15:03:35,005 INFO [train.py:823] (0/4) Epoch 6, batch 100, loss[loss=2.359, simple_loss=0.3127, pruned_loss=0.09937, codebook_loss=21.93, over 7241.00 frames.], tot_loss[loss=2.421, simple_loss=0.305, pruned_loss=0.09726, codebook_loss=22.58, over 565386.28 frames.], batch size: 24, lr: 2.23e-03
+2022-05-27 15:04:14,716 INFO [train.py:823] (0/4) Epoch 6, batch 150, loss[loss=2.342, simple_loss=0.3063, pruned_loss=0.09086, codebook_loss=21.79, over 7294.00 frames.], tot_loss[loss=2.422, simple_loss=0.3053, pruned_loss=0.09727, codebook_loss=22.6, over 754866.26 frames.], batch size: 19, lr: 2.22e-03
+2022-05-27 15:04:56,241 INFO [train.py:823] (0/4) Epoch 6, batch 200, loss[loss=2.407, simple_loss=0.3194, pruned_loss=0.09892, codebook_loss=22.37, over 7191.00 frames.], tot_loss[loss=2.426, simple_loss=0.3064, pruned_loss=0.09798, codebook_loss=22.63, over 901340.08 frames.], batch size: 25, lr: 2.22e-03
+2022-05-27 15:05:38,506 INFO [train.py:823] (0/4) Epoch 6, batch 250, loss[loss=2.594, simple_loss=0.3195, pruned_loss=0.09793, codebook_loss=24.24, over 6523.00 frames.], tot_loss[loss=2.432, simple_loss=0.3082, pruned_loss=0.09908, codebook_loss=22.68, over 1017073.62 frames.], batch size: 34, lr: 2.21e-03
+2022-05-27 15:06:18,609 INFO [train.py:823] (0/4) Epoch 6, batch 300, loss[loss=2.38, simple_loss=0.3011, pruned_loss=0.08905, codebook_loss=22.21, over 7197.00 frames.], tot_loss[loss=2.432, simple_loss=0.3095, pruned_loss=0.09956, codebook_loss=22.67, over 1107695.46 frames.], batch size: 20, lr: 2.21e-03
+2022-05-27 15:06:58,767 INFO [train.py:823] (0/4) Epoch 6, batch 350, loss[loss=2.353, simple_loss=0.2855, pruned_loss=0.08289, codebook_loss=22.02, over 7103.00 frames.], tot_loss[loss=2.431, simple_loss=0.309, pruned_loss=0.09904, codebook_loss=22.67, over 1179330.01 frames.], batch size: 18, lr: 2.20e-03
+2022-05-27 15:07:39,162 INFO [train.py:823] (0/4) Epoch 6, batch 400, loss[loss=2.338, simple_loss=0.3133, pruned_loss=0.09253, codebook_loss=21.72, over 7174.00 frames.], tot_loss[loss=2.419, simple_loss=0.3061, pruned_loss=0.09677, codebook_loss=22.56, over 1234780.64 frames.], batch size: 22, lr: 2.19e-03
+2022-05-27 15:08:18,970 INFO [train.py:823] (0/4) Epoch 6, batch 450, loss[loss=2.405, simple_loss=0.3232, pruned_loss=0.09827, codebook_loss=22.33, over 6679.00 frames.], tot_loss[loss=2.421, simple_loss=0.3069, pruned_loss=0.09759, codebook_loss=22.58, over 1268213.95 frames.], batch size: 34, lr: 2.19e-03
+2022-05-27 15:08:59,144 INFO [train.py:823] (0/4) Epoch 6, batch 500, loss[loss=2.419, simple_loss=0.3157, pruned_loss=0.09846, codebook_loss=22.51, over 7139.00 frames.], tot_loss[loss=2.429, simple_loss=0.3077, pruned_loss=0.09863, codebook_loss=22.66, over 1297666.35 frames.], batch size: 23, lr: 2.18e-03
+2022-05-27 15:09:39,061 INFO [train.py:823] (0/4) Epoch 6, batch 550, loss[loss=2.337, simple_loss=0.2814, pruned_loss=0.08574, codebook_loss=21.88, over 7094.00 frames.], tot_loss[loss=2.426, simple_loss=0.3072, pruned_loss=0.09771, codebook_loss=22.62, over 1325109.64 frames.], batch size: 18, lr: 2.18e-03
+2022-05-27 15:10:19,169 INFO [train.py:823] (0/4) Epoch 6, batch 600, loss[loss=2.362, simple_loss=0.291, pruned_loss=0.0947, codebook_loss=22.07, over 7082.00 frames.], tot_loss[loss=2.426, simple_loss=0.3056, pruned_loss=0.09644, codebook_loss=22.63, over 1342810.58 frames.], batch size: 18, lr: 2.17e-03
+2022-05-27 15:10:58,928 INFO [train.py:823] (0/4) Epoch 6, batch 650, loss[loss=2.44, simple_loss=0.2897, pruned_loss=0.09223, codebook_loss=22.85, over 7405.00 frames.], tot_loss[loss=2.422, simple_loss=0.3043, pruned_loss=0.09533, codebook_loss=22.6, over 1359334.44 frames.], batch size: 19, lr: 2.17e-03
+2022-05-27 15:11:39,185 INFO [train.py:823] (0/4) Epoch 6, batch 700, loss[loss=2.426, simple_loss=0.2949, pruned_loss=0.0955, codebook_loss=22.69, over 7204.00 frames.], tot_loss[loss=2.419, simple_loss=0.3045, pruned_loss=0.09485, codebook_loss=22.57, over 1374894.53 frames.], batch size: 19, lr: 2.16e-03
+2022-05-27 15:12:18,881 INFO [train.py:823] (0/4) Epoch 6, batch 750, loss[loss=2.375, simple_loss=0.2898, pruned_loss=0.09214, codebook_loss=22.21, over 7103.00 frames.], tot_loss[loss=2.421, simple_loss=0.305, pruned_loss=0.09476, codebook_loss=22.59, over 1383355.77 frames.], batch size: 19, lr: 2.16e-03
+2022-05-27 15:12:59,160 INFO [train.py:823] (0/4) Epoch 6, batch 800, loss[loss=2.413, simple_loss=0.2841, pruned_loss=0.08206, codebook_loss=22.63, over 7017.00 frames.], tot_loss[loss=2.418, simple_loss=0.3034, pruned_loss=0.09382, codebook_loss=22.57, over 1390210.15 frames.], batch size: 16, lr: 2.15e-03
+2022-05-27 15:13:39,111 INFO [train.py:823] (0/4) Epoch 6, batch 850, loss[loss=2.421, simple_loss=0.285, pruned_loss=0.09574, codebook_loss=22.69, over 6804.00 frames.], tot_loss[loss=2.427, simple_loss=0.3043, pruned_loss=0.09469, codebook_loss=22.65, over 1394704.25 frames.], batch size: 15, lr: 2.15e-03
+2022-05-27 15:14:19,233 INFO [train.py:823] (0/4) Epoch 6, batch 900, loss[loss=2.384, simple_loss=0.2912, pruned_loss=0.09363, codebook_loss=22.29, over 7290.00 frames.], tot_loss[loss=2.422, simple_loss=0.3025, pruned_loss=0.09324, codebook_loss=22.61, over 1397222.65 frames.], batch size: 17, lr: 2.14e-03
+2022-05-27 15:14:59,205 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-6.pt
+2022-05-27 15:15:12,733 INFO [train.py:823] (0/4) Epoch 7, batch 0, loss[loss=2.276, simple_loss=0.2625, pruned_loss=0.0521, codebook_loss=21.39, over 7099.00 frames.], tot_loss[loss=2.276, simple_loss=0.2625, pruned_loss=0.0521, codebook_loss=21.39, over 7099.00 frames.], batch size: 19, lr: 2.05e-03
+2022-05-27 15:15:52,754 INFO [train.py:823] (0/4) Epoch 7, batch 50, loss[loss=2.357, simple_loss=0.2767, pruned_loss=0.08331, codebook_loss=22.1, over 7271.00 frames.], tot_loss[loss=2.4, simple_loss=0.2944, pruned_loss=0.08715, codebook_loss=22.44, over 322497.52 frames.], batch size: 16, lr: 2.04e-03
+2022-05-27 15:16:32,378 INFO [train.py:823] (0/4) Epoch 7, batch 100, loss[loss=2.381, simple_loss=0.3133, pruned_loss=0.09982, codebook_loss=22.14, over 7106.00 frames.], tot_loss[loss=2.374, simple_loss=0.292, pruned_loss=0.08391, codebook_loss=22.2, over 562126.43 frames.], batch size: 20, lr: 2.04e-03
+2022-05-27 15:17:12,516 INFO [train.py:823] (0/4) Epoch 7, batch 150, loss[loss=2.384, simple_loss=0.2979, pruned_loss=0.07473, codebook_loss=22.28, over 7366.00 frames.], tot_loss[loss=2.385, simple_loss=0.2955, pruned_loss=0.08694, codebook_loss=22.28, over 752329.94 frames.], batch size: 21, lr: 2.03e-03
+2022-05-27 15:17:52,334 INFO [train.py:823] (0/4) Epoch 7, batch 200, loss[loss=2.544, simple_loss=0.3164, pruned_loss=0.09564, codebook_loss=23.77, over 7056.00 frames.], tot_loss[loss=2.384, simple_loss=0.2963, pruned_loss=0.08683, codebook_loss=22.27, over 904106.01 frames.], batch size: 26, lr: 2.03e-03
+2022-05-27 15:18:32,544 INFO [train.py:823] (0/4) Epoch 7, batch 250, loss[loss=2.534, simple_loss=0.3195, pruned_loss=0.1023, codebook_loss=23.64, over 7305.00 frames.], tot_loss[loss=2.378, simple_loss=0.2957, pruned_loss=0.08584, codebook_loss=22.21, over 1019288.64 frames.], batch size: 22, lr: 2.02e-03
+2022-05-27 15:19:12,228 INFO [train.py:823] (0/4) Epoch 7, batch 300, loss[loss=2.339, simple_loss=0.27, pruned_loss=0.07615, codebook_loss=21.96, over 7167.00 frames.], tot_loss[loss=2.376, simple_loss=0.2959, pruned_loss=0.08543, codebook_loss=22.2, over 1108352.01 frames.], batch size: 17, lr: 2.02e-03
+2022-05-27 15:19:52,554 INFO [train.py:823] (0/4) Epoch 7, batch 350, loss[loss=2.55, simple_loss=0.3275, pruned_loss=0.1038, codebook_loss=22.82, over 7298.00 frames.], tot_loss[loss=2.418, simple_loss=0.2993, pruned_loss=0.08991, codebook_loss=22.35, over 1176384.51 frames.], batch size: 19, lr: 2.01e-03
+2022-05-27 15:20:32,258 INFO [train.py:823] (0/4) Epoch 7, batch 400, loss[loss=2.465, simple_loss=0.3355, pruned_loss=0.114, codebook_loss=21.83, over 7329.00 frames.], tot_loss[loss=2.443, simple_loss=0.3019, pruned_loss=0.09214, codebook_loss=22.42, over 1231323.26 frames.], batch size: 23, lr: 2.01e-03
+2022-05-27 15:21:12,315 INFO [train.py:823] (0/4) Epoch 7, batch 450, loss[loss=2.502, simple_loss=0.3294, pruned_loss=0.1141, codebook_loss=22.23, over 7170.00 frames.], tot_loss[loss=2.45, simple_loss=0.3026, pruned_loss=0.09204, codebook_loss=22.39, over 1268117.33 frames.], batch size: 22, lr: 2.00e-03
+2022-05-27 15:21:52,023 INFO [train.py:823] (0/4) Epoch 7, batch 500, loss[loss=2.789, simple_loss=0.3286, pruned_loss=0.1141, codebook_loss=25.11, over 6981.00 frames.], tot_loss[loss=2.454, simple_loss=0.3027, pruned_loss=0.0907, codebook_loss=22.36, over 1301981.99 frames.], batch size: 26, lr: 2.00e-03
+2022-05-27 15:22:32,326 INFO [train.py:823] (0/4) Epoch 7, batch 550, loss[loss=2.337, simple_loss=0.3032, pruned_loss=0.06295, codebook_loss=21.23, over 6613.00 frames.], tot_loss[loss=2.456, simple_loss=0.3013, pruned_loss=0.08914, codebook_loss=22.35, over 1326044.12 frames.], batch size: 34, lr: 1.99e-03
+2022-05-27 15:23:12,062 INFO [train.py:823] (0/4) Epoch 7, batch 600, loss[loss=2.464, simple_loss=0.3107, pruned_loss=0.0852, codebook_loss=22.24, over 7377.00 frames.], tot_loss[loss=2.465, simple_loss=0.3012, pruned_loss=0.08787, codebook_loss=22.41, over 1344122.94 frames.], batch size: 21, lr: 1.99e-03
+2022-05-27 15:23:52,219 INFO [train.py:823] (0/4) Epoch 7, batch 650, loss[loss=2.456, simple_loss=0.3021, pruned_loss=0.08121, codebook_loss=22.24, over 7111.00 frames.], tot_loss[loss=2.469, simple_loss=0.3019, pruned_loss=0.08785, codebook_loss=22.41, over 1360469.10 frames.], batch size: 20, lr: 1.98e-03
+2022-05-27 15:24:32,094 INFO [train.py:823] (0/4) Epoch 7, batch 700, loss[loss=2.407, simple_loss=0.2892, pruned_loss=0.07183, codebook_loss=21.9, over 7097.00 frames.], tot_loss[loss=2.471, simple_loss=0.3017, pruned_loss=0.08789, codebook_loss=22.41, over 1369613.37 frames.], batch size: 18, lr: 1.98e-03
+2022-05-27 15:25:12,103 INFO [train.py:823] (0/4) Epoch 7, batch 750, loss[loss=2.34, simple_loss=0.2998, pruned_loss=0.07559, codebook_loss=21.15, over 7053.00 frames.], tot_loss[loss=2.472, simple_loss=0.3016, pruned_loss=0.08765, codebook_loss=22.4, over 1378307.53 frames.], batch size: 26, lr: 1.97e-03
+2022-05-27 15:25:51,514 INFO [train.py:823] (0/4) Epoch 7, batch 800, loss[loss=2.46, simple_loss=0.3013, pruned_loss=0.08962, codebook_loss=22.2, over 7183.00 frames.], tot_loss[loss=2.47, simple_loss=0.3023, pruned_loss=0.08713, codebook_loss=22.37, over 1389336.64 frames.], batch size: 19, lr: 1.97e-03
+2022-05-27 15:26:31,114 INFO [train.py:823] (0/4) Epoch 7, batch 850, loss[loss=2.428, simple_loss=0.3097, pruned_loss=0.07734, codebook_loss=21.96, over 7375.00 frames.], tot_loss[loss=2.468, simple_loss=0.3026, pruned_loss=0.08648, codebook_loss=22.34, over 1389686.29 frames.], batch size: 21, lr: 1.97e-03
+2022-05-27 15:27:11,912 INFO [train.py:823] (0/4) Epoch 7, batch 900, loss[loss=2.413, simple_loss=0.3103, pruned_loss=0.07758, codebook_loss=21.8, over 6950.00 frames.], tot_loss[loss=2.464, simple_loss=0.3033, pruned_loss=0.08649, codebook_loss=22.29, over 1392275.27 frames.], batch size: 29, lr: 1.96e-03
+2022-05-27 15:27:52,291 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-7.pt
+2022-05-27 15:28:02,620 INFO [train.py:823] (0/4) Epoch 8, batch 0, loss[loss=2.333, simple_loss=0.2825, pruned_loss=0.05631, codebook_loss=21.35, over 7418.00 frames.], tot_loss[loss=2.333, simple_loss=0.2825, pruned_loss=0.05631, codebook_loss=21.35, over 7418.00 frames.], batch size: 22, lr: 1.88e-03
+2022-05-27 15:28:42,300 INFO [train.py:823] (0/4) Epoch 8, batch 50, loss[loss=2.334, simple_loss=0.304, pruned_loss=0.06564, codebook_loss=21.17, over 7210.00 frames.], tot_loss[loss=2.395, simple_loss=0.2973, pruned_loss=0.07465, codebook_loss=21.72, over 320597.49 frames.], batch size: 24, lr: 1.87e-03
+2022-05-27 15:29:23,700 INFO [train.py:823] (0/4) Epoch 8, batch 100, loss[loss=2.553, simple_loss=0.2822, pruned_loss=0.08264, codebook_loss=23.29, over 7034.00 frames.], tot_loss[loss=2.421, simple_loss=0.3012, pruned_loss=0.07885, codebook_loss=21.92, over 564097.10 frames.], batch size: 17, lr: 1.87e-03
+2022-05-27 15:30:05,849 INFO [train.py:823] (0/4) Epoch 8, batch 150, loss[loss=2.393, simple_loss=0.284, pruned_loss=0.06383, codebook_loss=21.87, over 7278.00 frames.], tot_loss[loss=2.421, simple_loss=0.2979, pruned_loss=0.07766, codebook_loss=21.94, over 753242.75 frames.], batch size: 20, lr: 1.86e-03
+2022-05-27 15:30:46,017 INFO [train.py:823] (0/4) Epoch 8, batch 200, loss[loss=2.41, simple_loss=0.2931, pruned_loss=0.08097, codebook_loss=21.83, over 7015.00 frames.], tot_loss[loss=2.416, simple_loss=0.2971, pruned_loss=0.07712, codebook_loss=21.9, over 898578.19 frames.], batch size: 16, lr: 1.86e-03
+2022-05-27 15:31:25,745 INFO [train.py:823] (0/4) Epoch 8, batch 250, loss[loss=2.456, simple_loss=0.3078, pruned_loss=0.09096, codebook_loss=22.12, over 7149.00 frames.], tot_loss[loss=2.418, simple_loss=0.2955, pruned_loss=0.07656, codebook_loss=21.94, over 1012516.25 frames.], batch size: 23, lr: 1.85e-03
+2022-05-27 15:32:06,063 INFO [train.py:823] (0/4) Epoch 8, batch 300, loss[loss=2.436, simple_loss=0.3159, pruned_loss=0.08422, codebook_loss=21.94, over 7387.00 frames.], tot_loss[loss=2.415, simple_loss=0.2958, pruned_loss=0.07652, codebook_loss=21.9, over 1105751.87 frames.], batch size: 19, lr: 1.85e-03
+2022-05-27 15:32:45,536 INFO [train.py:823] (0/4) Epoch 8, batch 350, loss[loss=2.447, simple_loss=0.2673, pruned_loss=0.07876, codebook_loss=22.34, over 7010.00 frames.], tot_loss[loss=2.418, simple_loss=0.295, pruned_loss=0.0766, codebook_loss=21.94, over 1166246.19 frames.], batch size: 16, lr: 1.85e-03
+2022-05-27 15:33:25,397 INFO [train.py:823] (0/4) Epoch 8, batch 400, loss[loss=2.428, simple_loss=0.3267, pruned_loss=0.09134, codebook_loss=21.73, over 7173.00 frames.], tot_loss[loss=2.42, simple_loss=0.296, pruned_loss=0.07672, codebook_loss=21.95, over 1221526.97 frames.], batch size: 22, lr: 1.84e-03
+2022-05-27 15:34:05,054 INFO [train.py:823] (0/4) Epoch 8, batch 450, loss[loss=3.016, simple_loss=0.3463, pruned_loss=0.125, codebook_loss=27.18, over 6560.00 frames.], tot_loss[loss=2.424, simple_loss=0.2962, pruned_loss=0.07655, codebook_loss=21.99, over 1264366.01 frames.], batch size: 34, lr: 1.84e-03
+2022-05-27 15:34:45,238 INFO [train.py:823] (0/4) Epoch 8, batch 500, loss[loss=2.475, simple_loss=0.2674, pruned_loss=0.08966, codebook_loss=22.52, over 7296.00 frames.], tot_loss[loss=2.426, simple_loss=0.2957, pruned_loss=0.07657, codebook_loss=22.02, over 1300633.97 frames.], batch size: 17, lr: 1.83e-03
+2022-05-27 15:35:24,769 INFO [train.py:823] (0/4) Epoch 8, batch 550, loss[loss=2.833, simple_loss=0.3307, pruned_loss=0.1071, codebook_loss=25.61, over 7182.00 frames.], tot_loss[loss=2.429, simple_loss=0.2963, pruned_loss=0.07628, codebook_loss=22.04, over 1325280.64 frames.], batch size: 22, lr: 1.83e-03
+2022-05-27 15:36:04,696 INFO [train.py:823] (0/4) Epoch 8, batch 600, loss[loss=2.558, simple_loss=0.2985, pruned_loss=0.07404, codebook_loss=23.35, over 7045.00 frames.], tot_loss[loss=2.434, simple_loss=0.296, pruned_loss=0.07602, codebook_loss=22.1, over 1343094.23 frames.], batch size: 17, lr: 1.82e-03
+2022-05-27 15:36:44,523 INFO [train.py:823] (0/4) Epoch 8, batch 650, loss[loss=2.339, simple_loss=0.3159, pruned_loss=0.06931, codebook_loss=21.12, over 6992.00 frames.], tot_loss[loss=2.427, simple_loss=0.2961, pruned_loss=0.07554, codebook_loss=22.03, over 1360455.81 frames.], batch size: 26, lr: 1.82e-03
+2022-05-27 15:37:24,990 INFO [train.py:823] (0/4) Epoch 8, batch 700, loss[loss=2.559, simple_loss=0.2933, pruned_loss=0.0767, codebook_loss=23.36, over 7278.00 frames.], tot_loss[loss=2.417, simple_loss=0.2948, pruned_loss=0.07481, codebook_loss=21.94, over 1379138.72 frames.], batch size: 19, lr: 1.82e-03
+2022-05-27 15:38:04,508 INFO [train.py:823] (0/4) Epoch 8, batch 750, loss[loss=2.418, simple_loss=0.2687, pruned_loss=0.05419, codebook_loss=22.3, over 7097.00 frames.], tot_loss[loss=2.412, simple_loss=0.2938, pruned_loss=0.07388, codebook_loss=21.91, over 1386181.96 frames.], batch size: 18, lr: 1.81e-03
+2022-05-27 15:38:44,431 INFO [train.py:823] (0/4) Epoch 8, batch 800, loss[loss=2.525, simple_loss=0.3101, pruned_loss=0.09204, codebook_loss=22.78, over 4802.00 frames.], tot_loss[loss=2.412, simple_loss=0.2946, pruned_loss=0.07409, codebook_loss=21.9, over 1387521.81 frames.], batch size: 47, lr: 1.81e-03
+2022-05-27 15:39:24,097 INFO [train.py:823] (0/4) Epoch 8, batch 850, loss[loss=2.484, simple_loss=0.319, pruned_loss=0.08156, codebook_loss=22.43, over 7197.00 frames.], tot_loss[loss=2.412, simple_loss=0.2937, pruned_loss=0.07389, codebook_loss=21.91, over 1391114.08 frames.], batch size: 20, lr: 1.80e-03
+2022-05-27 15:40:04,004 INFO [train.py:823] (0/4) Epoch 8, batch 900, loss[loss=2.319, simple_loss=0.285, pruned_loss=0.06802, codebook_loss=21.09, over 7096.00 frames.], tot_loss[loss=2.428, simple_loss=0.2966, pruned_loss=0.07586, codebook_loss=22.04, over 1394806.59 frames.], batch size: 18, lr: 1.80e-03
+2022-05-27 15:40:44,252 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-8.pt
+2022-05-27 15:40:54,951 INFO [train.py:823] (0/4) Epoch 9, batch 0, loss[loss=2.34, simple_loss=0.3194, pruned_loss=0.06664, codebook_loss=21.14, over 7191.00 frames.], tot_loss[loss=2.34, simple_loss=0.3194, pruned_loss=0.06664, codebook_loss=21.14, over 7191.00 frames.], batch size: 21, lr: 1.72e-03
+2022-05-27 15:41:35,077 INFO [train.py:823] (0/4) Epoch 9, batch 50, loss[loss=2.298, simple_loss=0.2767, pruned_loss=0.06018, codebook_loss=20.99, over 7392.00 frames.], tot_loss[loss=2.393, simple_loss=0.2882, pruned_loss=0.06953, codebook_loss=21.8, over 319727.14 frames.], batch size: 19, lr: 1.72e-03
+2022-05-27 15:42:14,606 INFO [train.py:823] (0/4) Epoch 9, batch 100, loss[loss=2.329, simple_loss=0.2998, pruned_loss=0.07413, codebook_loss=21.05, over 7286.00 frames.], tot_loss[loss=2.37, simple_loss=0.2888, pruned_loss=0.06867, codebook_loss=21.57, over 562944.57 frames.], batch size: 19, lr: 1.71e-03
+2022-05-27 15:42:54,769 INFO [train.py:823] (0/4) Epoch 9, batch 150, loss[loss=2.451, simple_loss=0.2723, pruned_loss=0.06017, codebook_loss=22.55, over 7102.00 frames.], tot_loss[loss=2.376, simple_loss=0.2902, pruned_loss=0.06901, codebook_loss=21.62, over 753056.35 frames.], batch size: 19, lr: 1.71e-03
+2022-05-27 15:43:34,131 INFO [train.py:823] (0/4) Epoch 9, batch 200, loss[loss=2.442, simple_loss=0.3032, pruned_loss=0.07533, codebook_loss=22.15, over 7288.00 frames.], tot_loss[loss=2.379, simple_loss=0.2908, pruned_loss=0.06907, codebook_loss=21.64, over 895064.84 frames.], batch size: 20, lr: 1.71e-03
+2022-05-27 15:44:14,343 INFO [train.py:823] (0/4) Epoch 9, batch 250, loss[loss=2.304, simple_loss=0.2877, pruned_loss=0.05743, codebook_loss=21.03, over 7201.00 frames.], tot_loss[loss=2.366, simple_loss=0.2895, pruned_loss=0.06779, codebook_loss=21.54, over 1011561.61 frames.], batch size: 20, lr: 1.70e-03
+2022-05-27 15:44:53,896 INFO [train.py:823] (0/4) Epoch 9, batch 300, loss[loss=2.303, simple_loss=0.2733, pruned_loss=0.06576, codebook_loss=21, over 7198.00 frames.], tot_loss[loss=2.372, simple_loss=0.2902, pruned_loss=0.06877, codebook_loss=21.58, over 1104404.54 frames.], batch size: 18, lr: 1.70e-03
+2022-05-27 15:45:34,255 INFO [train.py:823] (0/4) Epoch 9, batch 350, loss[loss=2.454, simple_loss=0.2764, pruned_loss=0.07249, codebook_loss=22.43, over 7283.00 frames.], tot_loss[loss=2.367, simple_loss=0.2891, pruned_loss=0.06796, codebook_loss=21.55, over 1173807.02 frames.], batch size: 17, lr: 1.70e-03
+2022-05-27 15:46:14,407 INFO [train.py:823] (0/4) Epoch 9, batch 400, loss[loss=2.321, simple_loss=0.2954, pruned_loss=0.06628, codebook_loss=21.07, over 7309.00 frames.], tot_loss[loss=2.368, simple_loss=0.288, pruned_loss=0.06703, codebook_loss=21.57, over 1229658.50 frames.], batch size: 22, lr: 1.69e-03
+2022-05-27 15:46:15,475 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/checkpoint-8000.pt
+2022-05-27 15:46:57,536 INFO [train.py:823] (0/4) Epoch 9, batch 450, loss[loss=2.388, simple_loss=0.2841, pruned_loss=0.06967, codebook_loss=21.76, over 7205.00 frames.], tot_loss[loss=2.377, simple_loss=0.2894, pruned_loss=0.06778, codebook_loss=21.65, over 1270999.59 frames.], batch size: 19, lr: 1.69e-03
+2022-05-27 15:47:37,341 INFO [train.py:823] (0/4) Epoch 9, batch 500, loss[loss=2.285, simple_loss=0.2901, pruned_loss=0.06849, codebook_loss=20.72, over 7239.00 frames.], tot_loss[loss=2.374, simple_loss=0.2901, pruned_loss=0.06772, codebook_loss=21.61, over 1304334.40 frames.], batch size: 24, lr: 1.68e-03
+2022-05-27 15:48:17,617 INFO [train.py:823] (0/4) Epoch 9, batch 550, loss[loss=2.64, simple_loss=0.3097, pruned_loss=0.08562, codebook_loss=24, over 7188.00 frames.], tot_loss[loss=2.373, simple_loss=0.2899, pruned_loss=0.06791, codebook_loss=21.6, over 1333764.13 frames.], batch size: 19, lr: 1.68e-03
+2022-05-27 15:48:57,598 INFO [train.py:823] (0/4) Epoch 9, batch 600, loss[loss=2.918, simple_loss=0.3074, pruned_loss=0.1002, codebook_loss=26.64, over 7145.00 frames.], tot_loss[loss=2.38, simple_loss=0.2896, pruned_loss=0.0683, codebook_loss=21.66, over 1354292.90 frames.], batch size: 17, lr: 1.68e-03
+2022-05-27 15:49:37,631 INFO [train.py:823] (0/4) Epoch 9, batch 650, loss[loss=2.339, simple_loss=0.2993, pruned_loss=0.0698, codebook_loss=21.2, over 6781.00 frames.], tot_loss[loss=2.381, simple_loss=0.2903, pruned_loss=0.06892, codebook_loss=21.67, over 1366920.89 frames.], batch size: 29, lr: 1.67e-03
+2022-05-27 15:50:17,589 INFO [train.py:823] (0/4) Epoch 9, batch 700, loss[loss=2.414, simple_loss=0.2923, pruned_loss=0.05832, codebook_loss=22.1, over 7300.00 frames.], tot_loss[loss=2.386, simple_loss=0.2907, pruned_loss=0.06903, codebook_loss=21.71, over 1374739.74 frames.], batch size: 22, lr: 1.67e-03
+2022-05-27 15:50:59,092 INFO [train.py:823] (0/4) Epoch 9, batch 750, loss[loss=2.263, simple_loss=0.259, pruned_loss=0.0441, codebook_loss=20.89, over 7199.00 frames.], tot_loss[loss=2.389, simple_loss=0.2921, pruned_loss=0.06991, codebook_loss=21.73, over 1385500.11 frames.], batch size: 18, lr: 1.67e-03
+2022-05-27 15:51:38,641 INFO [train.py:823] (0/4) Epoch 9, batch 800, loss[loss=2.335, simple_loss=0.2941, pruned_loss=0.06924, codebook_loss=21.19, over 7099.00 frames.], tot_loss[loss=2.385, simple_loss=0.2913, pruned_loss=0.06901, codebook_loss=21.71, over 1386877.50 frames.], batch size: 19, lr: 1.66e-03
+2022-05-27 15:52:18,637 INFO [train.py:823] (0/4) Epoch 9, batch 850, loss[loss=2.263, simple_loss=0.2447, pruned_loss=0.04432, codebook_loss=20.97, over 7228.00 frames.], tot_loss[loss=2.376, simple_loss=0.2902, pruned_loss=0.06848, codebook_loss=21.62, over 1397227.45 frames.], batch size: 16, lr: 1.66e-03
+2022-05-27 15:52:58,160 INFO [train.py:823] (0/4) Epoch 9, batch 900, loss[loss=2.413, simple_loss=0.2655, pruned_loss=0.06778, codebook_loss=22.12, over 6798.00 frames.], tot_loss[loss=2.38, simple_loss=0.2902, pruned_loss=0.06844, codebook_loss=21.67, over 1400112.47 frames.], batch size: 15, lr: 1.65e-03
+2022-05-27 15:53:41,027 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-9.pt
+2022-05-27 15:53:54,918 INFO [train.py:823] (0/4) Epoch 10, batch 0, loss[loss=2.362, simple_loss=0.2891, pruned_loss=0.07231, codebook_loss=21.45, over 7105.00 frames.], tot_loss[loss=2.362, simple_loss=0.2891, pruned_loss=0.07231, codebook_loss=21.45, over 7105.00 frames.], batch size: 20, lr: 1.59e-03
+2022-05-27 15:54:34,614 INFO [train.py:823] (0/4) Epoch 10, batch 50, loss[loss=2.511, simple_loss=0.2596, pruned_loss=0.06379, codebook_loss=23.17, over 7026.00 frames.], tot_loss[loss=2.356, simple_loss=0.2855, pruned_loss=0.065, codebook_loss=21.49, over 319276.30 frames.], batch size: 17, lr: 1.58e-03
+2022-05-27 15:55:15,565 INFO [train.py:823] (0/4) Epoch 10, batch 100, loss[loss=2.288, simple_loss=0.2741, pruned_loss=0.05418, codebook_loss=20.97, over 7378.00 frames.], tot_loss[loss=2.343, simple_loss=0.2854, pruned_loss=0.06401, codebook_loss=21.36, over 559832.53 frames.], batch size: 20, lr: 1.58e-03
+2022-05-27 15:55:54,951 INFO [train.py:823] (0/4) Epoch 10, batch 150, loss[loss=2.595, simple_loss=0.3179, pruned_loss=0.09897, codebook_loss=23.37, over 7277.00 frames.], tot_loss[loss=2.34, simple_loss=0.2866, pruned_loss=0.06428, codebook_loss=21.32, over 749113.03 frames.], batch size: 20, lr: 1.58e-03
+2022-05-27 15:56:35,123 INFO [train.py:823] (0/4) Epoch 10, batch 200, loss[loss=2.432, simple_loss=0.3306, pruned_loss=0.09413, codebook_loss=21.72, over 7274.00 frames.], tot_loss[loss=2.341, simple_loss=0.2852, pruned_loss=0.06311, codebook_loss=21.36, over 900515.57 frames.], batch size: 21, lr: 1.57e-03
+2022-05-27 15:57:14,775 INFO [train.py:823] (0/4) Epoch 10, batch 250, loss[loss=2.369, simple_loss=0.2826, pruned_loss=0.0648, codebook_loss=21.63, over 7381.00 frames.], tot_loss[loss=2.344, simple_loss=0.2867, pruned_loss=0.06381, codebook_loss=21.37, over 1016211.49 frames.], batch size: 21, lr: 1.57e-03
+2022-05-27 15:57:54,568 INFO [train.py:823] (0/4) Epoch 10, batch 300, loss[loss=2.295, simple_loss=0.3029, pruned_loss=0.06868, codebook_loss=20.74, over 7022.00 frames.], tot_loss[loss=2.346, simple_loss=0.2869, pruned_loss=0.06416, codebook_loss=21.39, over 1107388.77 frames.], batch size: 26, lr: 1.57e-03
+2022-05-27 15:58:34,248 INFO [train.py:823] (0/4) Epoch 10, batch 350, loss[loss=2.387, simple_loss=0.2738, pruned_loss=0.06343, codebook_loss=21.86, over 7218.00 frames.], tot_loss[loss=2.337, simple_loss=0.2854, pruned_loss=0.06261, codebook_loss=21.31, over 1174159.74 frames.], batch size: 16, lr: 1.56e-03
+2022-05-27 15:59:14,375 INFO [train.py:823] (0/4) Epoch 10, batch 400, loss[loss=2.409, simple_loss=0.3075, pruned_loss=0.07963, codebook_loss=21.76, over 7105.00 frames.], tot_loss[loss=2.349, simple_loss=0.2873, pruned_loss=0.06423, codebook_loss=21.41, over 1223698.95 frames.], batch size: 19, lr: 1.56e-03
+2022-05-27 15:59:54,074 INFO [train.py:823] (0/4) Epoch 10, batch 450, loss[loss=2.348, simple_loss=0.2978, pruned_loss=0.06455, codebook_loss=21.34, over 7274.00 frames.], tot_loss[loss=2.349, simple_loss=0.2866, pruned_loss=0.06402, codebook_loss=21.42, over 1265108.42 frames.], batch size: 20, lr: 1.56e-03
+2022-05-27 16:00:34,191 INFO [train.py:823] (0/4) Epoch 10, batch 500, loss[loss=2.321, simple_loss=0.296, pruned_loss=0.06648, codebook_loss=21.07, over 7280.00 frames.], tot_loss[loss=2.349, simple_loss=0.2862, pruned_loss=0.06435, codebook_loss=21.42, over 1298102.09 frames.], batch size: 20, lr: 1.55e-03
+2022-05-27 16:01:14,187 INFO [train.py:823] (0/4) Epoch 10, batch 550, loss[loss=2.235, simple_loss=0.2773, pruned_loss=0.04914, codebook_loss=20.48, over 7099.00 frames.], tot_loss[loss=2.349, simple_loss=0.2855, pruned_loss=0.06378, codebook_loss=21.43, over 1327992.01 frames.], batch size: 18, lr: 1.55e-03
+2022-05-27 16:01:54,261 INFO [train.py:823] (0/4) Epoch 10, batch 600, loss[loss=2.389, simple_loss=0.2867, pruned_loss=0.06003, codebook_loss=21.86, over 7288.00 frames.], tot_loss[loss=2.352, simple_loss=0.2861, pruned_loss=0.06365, codebook_loss=21.46, over 1352973.78 frames.], batch size: 19, lr: 1.55e-03
+2022-05-27 16:02:33,980 INFO [train.py:823] (0/4) Epoch 10, batch 650, loss[loss=2.304, simple_loss=0.2878, pruned_loss=0.05975, codebook_loss=21, over 7184.00 frames.], tot_loss[loss=2.349, simple_loss=0.2849, pruned_loss=0.0631, codebook_loss=21.43, over 1370457.37 frames.], batch size: 21, lr: 1.54e-03
+2022-05-27 16:03:14,286 INFO [train.py:823] (0/4) Epoch 10, batch 700, loss[loss=2.9, simple_loss=0.3117, pruned_loss=0.1035, codebook_loss=26.4, over 7002.00 frames.], tot_loss[loss=2.349, simple_loss=0.285, pruned_loss=0.06284, codebook_loss=21.43, over 1384586.48 frames.], batch size: 16, lr: 1.54e-03
+2022-05-27 16:03:53,948 INFO [train.py:823] (0/4) Epoch 10, batch 750, loss[loss=2.294, simple_loss=0.2752, pruned_loss=0.05741, codebook_loss=20.99, over 7190.00 frames.], tot_loss[loss=2.351, simple_loss=0.2844, pruned_loss=0.06282, codebook_loss=21.46, over 1392103.72 frames.], batch size: 18, lr: 1.54e-03
+2022-05-27 16:04:34,033 INFO [train.py:823] (0/4) Epoch 10, batch 800, loss[loss=2.251, simple_loss=0.2894, pruned_loss=0.05488, codebook_loss=20.52, over 7243.00 frames.], tot_loss[loss=2.345, simple_loss=0.2848, pruned_loss=0.06255, codebook_loss=21.4, over 1398892.82 frames.], batch size: 25, lr: 1.53e-03
+2022-05-27 16:05:13,991 INFO [train.py:823] (0/4) Epoch 10, batch 850, loss[loss=2.308, simple_loss=0.3032, pruned_loss=0.0617, codebook_loss=20.94, over 7163.00 frames.], tot_loss[loss=2.344, simple_loss=0.2837, pruned_loss=0.06198, codebook_loss=21.41, over 1405487.34 frames.], batch size: 22, lr: 1.53e-03
+2022-05-27 16:05:54,085 INFO [train.py:823] (0/4) Epoch 10, batch 900, loss[loss=2.438, simple_loss=0.2496, pruned_loss=0.0506, codebook_loss=22.62, over 7234.00 frames.], tot_loss[loss=2.346, simple_loss=0.2834, pruned_loss=0.06166, codebook_loss=21.42, over 1406851.46 frames.], batch size: 16, lr: 1.53e-03
+2022-05-27 16:06:33,131 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-10.pt
+2022-05-27 16:06:46,070 INFO [train.py:823] (0/4) Epoch 11, batch 0, loss[loss=2.526, simple_loss=0.288, pruned_loss=0.05523, codebook_loss=23.26, over 7098.00 frames.], tot_loss[loss=2.526, simple_loss=0.288, pruned_loss=0.05523, codebook_loss=23.26, over 7098.00 frames.], batch size: 19, lr: 1.47e-03
+2022-05-27 16:07:26,141 INFO [train.py:823] (0/4) Epoch 11, batch 50, loss[loss=2.307, simple_loss=0.2876, pruned_loss=0.06309, codebook_loss=21.01, over 6362.00 frames.], tot_loss[loss=2.321, simple_loss=0.2789, pruned_loss=0.05721, codebook_loss=21.24, over 323612.88 frames.], batch size: 34, lr: 1.47e-03
+2022-05-27 16:08:06,015 INFO [train.py:823] (0/4) Epoch 11, batch 100, loss[loss=2.323, simple_loss=0.2747, pruned_loss=0.05628, codebook_loss=21.3, over 7166.00 frames.], tot_loss[loss=2.314, simple_loss=0.278, pruned_loss=0.05826, codebook_loss=21.16, over 570541.92 frames.], batch size: 17, lr: 1.46e-03
+2022-05-27 16:08:46,154 INFO [train.py:823] (0/4) Epoch 11, batch 150, loss[loss=2.247, simple_loss=0.2974, pruned_loss=0.06074, codebook_loss=20.37, over 7238.00 frames.], tot_loss[loss=2.323, simple_loss=0.2798, pruned_loss=0.05923, codebook_loss=21.23, over 762032.97 frames.], batch size: 24, lr: 1.46e-03
+2022-05-27 16:09:25,522 INFO [train.py:823] (0/4) Epoch 11, batch 200, loss[loss=2.228, simple_loss=0.2698, pruned_loss=0.05082, codebook_loss=20.42, over 7101.00 frames.], tot_loss[loss=2.324, simple_loss=0.2825, pruned_loss=0.06013, codebook_loss=21.23, over 902108.06 frames.], batch size: 19, lr: 1.46e-03
+2022-05-27 16:10:05,748 INFO [train.py:823] (0/4) Epoch 11, batch 250, loss[loss=2.309, simple_loss=0.2805, pruned_loss=0.05586, codebook_loss=21.13, over 7102.00 frames.], tot_loss[loss=2.323, simple_loss=0.2813, pruned_loss=0.05923, codebook_loss=21.23, over 1015204.12 frames.], batch size: 18, lr: 1.45e-03
+2022-05-27 16:10:45,557 INFO [train.py:823] (0/4) Epoch 11, batch 300, loss[loss=2.388, simple_loss=0.3151, pruned_loss=0.08829, codebook_loss=21.42, over 7185.00 frames.], tot_loss[loss=2.33, simple_loss=0.2816, pruned_loss=0.06021, codebook_loss=21.29, over 1105979.83 frames.], batch size: 25, lr: 1.45e-03
+2022-05-27 16:11:25,746 INFO [train.py:823] (0/4) Epoch 11, batch 350, loss[loss=2.275, simple_loss=0.2908, pruned_loss=0.05512, codebook_loss=20.74, over 7227.00 frames.], tot_loss[loss=2.33, simple_loss=0.2813, pruned_loss=0.0599, codebook_loss=21.29, over 1177153.20 frames.], batch size: 25, lr: 1.45e-03
+2022-05-27 16:12:05,496 INFO [train.py:823] (0/4) Epoch 11, batch 400, loss[loss=2.299, simple_loss=0.311, pruned_loss=0.06406, codebook_loss=20.79, over 7095.00 frames.], tot_loss[loss=2.324, simple_loss=0.2811, pruned_loss=0.05947, codebook_loss=21.24, over 1231888.14 frames.], batch size: 19, lr: 1.44e-03
+2022-05-27 16:12:45,568 INFO [train.py:823] (0/4) Epoch 11, batch 450, loss[loss=2.258, simple_loss=0.2803, pruned_loss=0.04843, codebook_loss=20.7, over 7322.00 frames.], tot_loss[loss=2.318, simple_loss=0.2805, pruned_loss=0.05902, codebook_loss=21.19, over 1271004.69 frames.], batch size: 22, lr: 1.44e-03
+2022-05-27 16:13:25,304 INFO [train.py:823] (0/4) Epoch 11, batch 500, loss[loss=2.307, simple_loss=0.3038, pruned_loss=0.06087, codebook_loss=20.94, over 6444.00 frames.], tot_loss[loss=2.317, simple_loss=0.2811, pruned_loss=0.05924, codebook_loss=21.17, over 1304210.43 frames.], batch size: 34, lr: 1.44e-03
+2022-05-27 16:14:05,251 INFO [train.py:823] (0/4) Epoch 11, batch 550, loss[loss=2.485, simple_loss=0.296, pruned_loss=0.06314, codebook_loss=22.74, over 7409.00 frames.], tot_loss[loss=2.326, simple_loss=0.2832, pruned_loss=0.06042, codebook_loss=21.24, over 1332592.29 frames.], batch size: 22, lr: 1.44e-03
+2022-05-27 16:14:46,340 INFO [train.py:823] (0/4) Epoch 11, batch 600, loss[loss=2.219, simple_loss=0.2576, pruned_loss=0.04319, codebook_loss=20.47, over 7389.00 frames.], tot_loss[loss=2.328, simple_loss=0.2832, pruned_loss=0.06065, codebook_loss=21.26, over 1351233.92 frames.], batch size: 19, lr: 1.43e-03
+2022-05-27 16:15:26,709 INFO [train.py:823] (0/4) Epoch 11, batch 650, loss[loss=2.328, simple_loss=0.2625, pruned_loss=0.06703, codebook_loss=21.3, over 7310.00 frames.], tot_loss[loss=2.323, simple_loss=0.2821, pruned_loss=0.06024, codebook_loss=21.22, over 1368291.67 frames.], batch size: 18, lr: 1.43e-03
+2022-05-27 16:16:06,584 INFO [train.py:823] (0/4) Epoch 11, batch 700, loss[loss=2.523, simple_loss=0.3058, pruned_loss=0.09445, codebook_loss=22.76, over 7159.00 frames.], tot_loss[loss=2.318, simple_loss=0.2821, pruned_loss=0.06011, codebook_loss=21.17, over 1382418.52 frames.], batch size: 17, lr: 1.43e-03
+2022-05-27 16:16:46,849 INFO [train.py:823] (0/4) Epoch 11, batch 750, loss[loss=2.252, simple_loss=0.2473, pruned_loss=0.05213, codebook_loss=20.76, over 7297.00 frames.], tot_loss[loss=2.318, simple_loss=0.2808, pruned_loss=0.05946, codebook_loss=21.18, over 1390779.15 frames.], batch size: 17, lr: 1.42e-03
+2022-05-27 16:17:26,664 INFO [train.py:823] (0/4) Epoch 11, batch 800, loss[loss=2.407, simple_loss=0.2797, pruned_loss=0.05377, codebook_loss=22.13, over 7216.00 frames.], tot_loss[loss=2.32, simple_loss=0.2809, pruned_loss=0.05938, codebook_loss=21.2, over 1395711.64 frames.], batch size: 19, lr: 1.42e-03
+2022-05-27 16:18:08,323 INFO [train.py:823] (0/4) Epoch 11, batch 850, loss[loss=2.464, simple_loss=0.3263, pruned_loss=0.09132, codebook_loss=22.1, over 7124.00 frames.], tot_loss[loss=2.317, simple_loss=0.2811, pruned_loss=0.05929, codebook_loss=21.17, over 1398401.12 frames.], batch size: 20, lr: 1.42e-03
+2022-05-27 16:18:49,134 INFO [train.py:823] (0/4) Epoch 11, batch 900, loss[loss=2.223, simple_loss=0.2384, pruned_loss=0.04088, codebook_loss=20.63, over 7255.00 frames.], tot_loss[loss=2.309, simple_loss=0.2816, pruned_loss=0.05907, codebook_loss=21.09, over 1398612.58 frames.], batch size: 16, lr: 1.42e-03
+2022-05-27 16:19:30,577 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-11.pt
+2022-05-27 16:19:44,428 INFO [train.py:823] (0/4) Epoch 12, batch 0, loss[loss=2.19, simple_loss=0.2355, pruned_loss=0.04191, codebook_loss=20.3, over 7295.00 frames.], tot_loss[loss=2.19, simple_loss=0.2355, pruned_loss=0.04191, codebook_loss=20.3, over 7295.00 frames.], batch size: 17, lr: 1.36e-03
+2022-05-27 16:20:24,313 INFO [train.py:823] (0/4) Epoch 12, batch 50, loss[loss=2.223, simple_loss=0.2834, pruned_loss=0.0532, codebook_loss=20.28, over 7256.00 frames.], tot_loss[loss=2.332, simple_loss=0.2784, pruned_loss=0.06072, codebook_loss=21.32, over 318337.27 frames.], batch size: 24, lr: 1.36e-03
+2022-05-27 16:21:04,296 INFO [train.py:823] (0/4) Epoch 12, batch 100, loss[loss=2.541, simple_loss=0.2883, pruned_loss=0.05581, codebook_loss=23.41, over 7141.00 frames.], tot_loss[loss=2.31, simple_loss=0.2777, pruned_loss=0.05874, codebook_loss=21.13, over 562440.04 frames.], batch size: 23, lr: 1.36e-03
+2022-05-27 16:21:44,020 INFO [train.py:823] (0/4) Epoch 12, batch 150, loss[loss=2.245, simple_loss=0.2752, pruned_loss=0.05704, codebook_loss=20.51, over 7277.00 frames.], tot_loss[loss=2.304, simple_loss=0.2769, pruned_loss=0.05708, codebook_loss=21.09, over 752990.12 frames.], batch size: 20, lr: 1.36e-03
+2022-05-27 16:22:24,275 INFO [train.py:823] (0/4) Epoch 12, batch 200, loss[loss=2.296, simple_loss=0.2538, pruned_loss=0.03667, codebook_loss=21.33, over 6853.00 frames.], tot_loss[loss=2.302, simple_loss=0.2769, pruned_loss=0.05665, codebook_loss=21.07, over 899931.32 frames.], batch size: 15, lr: 1.35e-03
+2022-05-27 16:23:03,805 INFO [train.py:823] (0/4) Epoch 12, batch 250, loss[loss=2.326, simple_loss=0.2998, pruned_loss=0.06946, codebook_loss=21.07, over 7001.00 frames.], tot_loss[loss=2.304, simple_loss=0.2771, pruned_loss=0.05699, codebook_loss=21.09, over 1017017.68 frames.], batch size: 26, lr: 1.35e-03
+2022-05-27 16:23:43,705 INFO [train.py:823] (0/4) Epoch 12, batch 300, loss[loss=2.227, simple_loss=0.2598, pruned_loss=0.04019, codebook_loss=20.57, over 7198.00 frames.], tot_loss[loss=2.3, simple_loss=0.278, pruned_loss=0.05672, codebook_loss=21.05, over 1103632.00 frames.], batch size: 19, lr: 1.35e-03
+2022-05-27 16:24:23,586 INFO [train.py:823] (0/4) Epoch 12, batch 350, loss[loss=2.247, simple_loss=0.2801, pruned_loss=0.06137, codebook_loss=20.45, over 7333.00 frames.], tot_loss[loss=2.296, simple_loss=0.278, pruned_loss=0.05634, codebook_loss=21.01, over 1177241.99 frames.], batch size: 23, lr: 1.35e-03
+2022-05-27 16:25:03,589 INFO [train.py:823] (0/4) Epoch 12, batch 400, loss[loss=2.32, simple_loss=0.2938, pruned_loss=0.06103, codebook_loss=21.12, over 6912.00 frames.], tot_loss[loss=2.293, simple_loss=0.2773, pruned_loss=0.05558, codebook_loss=20.98, over 1231385.95 frames.], batch size: 29, lr: 1.34e-03
+2022-05-27 16:25:43,356 INFO [train.py:823] (0/4) Epoch 12, batch 450, loss[loss=2.712, simple_loss=0.2831, pruned_loss=0.06447, codebook_loss=25.06, over 7368.00 frames.], tot_loss[loss=2.289, simple_loss=0.2774, pruned_loss=0.05562, codebook_loss=20.94, over 1272878.51 frames.], batch size: 20, lr: 1.34e-03
+2022-05-27 16:26:23,672 INFO [train.py:823] (0/4) Epoch 12, batch 500, loss[loss=2.229, simple_loss=0.2885, pruned_loss=0.05305, codebook_loss=20.32, over 7286.00 frames.], tot_loss[loss=2.287, simple_loss=0.2771, pruned_loss=0.05522, codebook_loss=20.93, over 1310392.15 frames.], batch size: 20, lr: 1.34e-03
+2022-05-27 16:27:03,419 INFO [train.py:823] (0/4) Epoch 12, batch 550, loss[loss=2.267, simple_loss=0.2487, pruned_loss=0.03514, codebook_loss=21.07, over 7423.00 frames.], tot_loss[loss=2.286, simple_loss=0.2779, pruned_loss=0.05563, codebook_loss=20.92, over 1338250.71 frames.], batch size: 18, lr: 1.34e-03
+2022-05-27 16:27:43,507 INFO [train.py:823] (0/4) Epoch 12, batch 600, loss[loss=2.254, simple_loss=0.2684, pruned_loss=0.05756, codebook_loss=20.63, over 7207.00 frames.], tot_loss[loss=2.285, simple_loss=0.2772, pruned_loss=0.05533, codebook_loss=20.92, over 1358922.83 frames.], batch size: 16, lr: 1.33e-03
+2022-05-27 16:28:23,494 INFO [train.py:823] (0/4) Epoch 12, batch 650, loss[loss=2.252, simple_loss=0.3015, pruned_loss=0.05907, codebook_loss=20.42, over 7283.00 frames.], tot_loss[loss=2.286, simple_loss=0.2775, pruned_loss=0.0552, codebook_loss=20.92, over 1371291.09 frames.], batch size: 21, lr: 1.33e-03
+2022-05-27 16:29:04,025 INFO [train.py:823] (0/4) Epoch 12, batch 700, loss[loss=2.246, simple_loss=0.2586, pruned_loss=0.04672, codebook_loss=20.7, over 7283.00 frames.], tot_loss[loss=2.292, simple_loss=0.2777, pruned_loss=0.05528, codebook_loss=20.98, over 1382273.00 frames.], batch size: 20, lr: 1.33e-03
+2022-05-27 16:29:43,707 INFO [train.py:823] (0/4) Epoch 12, batch 750, loss[loss=2.197, simple_loss=0.2816, pruned_loss=0.05763, codebook_loss=19.98, over 7310.00 frames.], tot_loss[loss=2.288, simple_loss=0.2778, pruned_loss=0.05496, codebook_loss=20.94, over 1388624.78 frames.], batch size: 22, lr: 1.33e-03
+2022-05-27 16:30:23,752 INFO [train.py:823] (0/4) Epoch 12, batch 800, loss[loss=2.314, simple_loss=0.3147, pruned_loss=0.06024, codebook_loss=20.97, over 7299.00 frames.], tot_loss[loss=2.286, simple_loss=0.2771, pruned_loss=0.05456, codebook_loss=20.93, over 1395505.19 frames.], batch size: 22, lr: 1.32e-03
+2022-05-27 16:31:03,434 INFO [train.py:823] (0/4) Epoch 12, batch 850, loss[loss=2.213, simple_loss=0.2702, pruned_loss=0.0487, codebook_loss=20.29, over 7187.00 frames.], tot_loss[loss=2.28, simple_loss=0.2768, pruned_loss=0.0542, codebook_loss=20.88, over 1400624.21 frames.], batch size: 18, lr: 1.32e-03
+2022-05-27 16:31:43,305 INFO [train.py:823] (0/4) Epoch 12, batch 900, loss[loss=2.221, simple_loss=0.2755, pruned_loss=0.04863, codebook_loss=20.35, over 7096.00 frames.], tot_loss[loss=2.289, simple_loss=0.277, pruned_loss=0.05511, codebook_loss=20.95, over 1397287.80 frames.], batch size: 19, lr: 1.32e-03
+2022-05-27 16:32:23,458 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-12.pt
+2022-05-27 16:32:36,851 INFO [train.py:823] (0/4) Epoch 13, batch 0, loss[loss=2.243, simple_loss=0.2822, pruned_loss=0.06203, codebook_loss=20.4, over 7163.00 frames.], tot_loss[loss=2.243, simple_loss=0.2822, pruned_loss=0.06203, codebook_loss=20.4, over 7163.00 frames.], batch size: 22, lr: 1.27e-03
+2022-05-27 16:33:17,134 INFO [train.py:823] (0/4) Epoch 13, batch 50, loss[loss=2.168, simple_loss=0.2689, pruned_loss=0.03751, codebook_loss=19.96, over 7294.00 frames.], tot_loss[loss=2.267, simple_loss=0.2762, pruned_loss=0.05532, codebook_loss=20.73, over 317840.62 frames.], batch size: 19, lr: 1.27e-03
+2022-05-27 16:33:56,690 INFO [train.py:823] (0/4) Epoch 13, batch 100, loss[loss=2.175, simple_loss=0.2354, pruned_loss=0.03947, codebook_loss=20.18, over 7317.00 frames.], tot_loss[loss=2.277, simple_loss=0.2761, pruned_loss=0.05604, codebook_loss=20.83, over 561442.36 frames.], batch size: 18, lr: 1.27e-03
+2022-05-27 16:34:36,936 INFO [train.py:823] (0/4) Epoch 13, batch 150, loss[loss=2.265, simple_loss=0.2409, pruned_loss=0.04215, codebook_loss=21.03, over 7394.00 frames.], tot_loss[loss=2.281, simple_loss=0.2757, pruned_loss=0.05556, codebook_loss=20.88, over 752219.54 frames.], batch size: 19, lr: 1.26e-03
+2022-05-27 16:35:16,779 INFO [train.py:823] (0/4) Epoch 13, batch 200, loss[loss=2.254, simple_loss=0.2514, pruned_loss=0.04374, codebook_loss=20.84, over 7020.00 frames.], tot_loss[loss=2.275, simple_loss=0.2746, pruned_loss=0.05464, codebook_loss=20.83, over 903397.09 frames.], batch size: 17, lr: 1.26e-03
+2022-05-27 16:35:57,005 INFO [train.py:823] (0/4) Epoch 13, batch 250, loss[loss=2.337, simple_loss=0.2742, pruned_loss=0.04357, codebook_loss=21.57, over 7157.00 frames.], tot_loss[loss=2.263, simple_loss=0.273, pruned_loss=0.05301, codebook_loss=20.74, over 1016485.07 frames.], batch size: 22, lr: 1.26e-03
+2022-05-27 16:36:37,047 INFO [train.py:823] (0/4) Epoch 13, batch 300, loss[loss=2.167, simple_loss=0.2404, pruned_loss=0.04174, codebook_loss=20.05, over 7295.00 frames.], tot_loss[loss=2.264, simple_loss=0.273, pruned_loss=0.05318, codebook_loss=20.75, over 1111018.63 frames.], batch size: 17, lr: 1.26e-03
+2022-05-27 16:37:16,854 INFO [train.py:823] (0/4) Epoch 13, batch 350, loss[loss=2.33, simple_loss=0.2981, pruned_loss=0.05858, codebook_loss=21.23, over 6480.00 frames.], tot_loss[loss=2.254, simple_loss=0.2733, pruned_loss=0.05255, codebook_loss=20.64, over 1177334.45 frames.], batch size: 34, lr: 1.26e-03
+2022-05-27 16:37:56,768 INFO [train.py:823] (0/4) Epoch 13, batch 400, loss[loss=2.246, simple_loss=0.2855, pruned_loss=0.05529, codebook_loss=20.48, over 7012.00 frames.], tot_loss[loss=2.256, simple_loss=0.2735, pruned_loss=0.05249, codebook_loss=20.67, over 1230347.48 frames.], batch size: 26, lr: 1.25e-03
+2022-05-27 16:38:36,631 INFO [train.py:823] (0/4) Epoch 13, batch 450, loss[loss=2.233, simple_loss=0.2768, pruned_loss=0.04852, codebook_loss=20.46, over 6904.00 frames.], tot_loss[loss=2.257, simple_loss=0.2725, pruned_loss=0.05207, codebook_loss=20.69, over 1267737.77 frames.], batch size: 29, lr: 1.25e-03
+2022-05-27 16:39:17,522 INFO [train.py:823] (0/4) Epoch 13, batch 500, loss[loss=2.316, simple_loss=0.2842, pruned_loss=0.05331, codebook_loss=21.2, over 6918.00 frames.], tot_loss[loss=2.259, simple_loss=0.2723, pruned_loss=0.05241, codebook_loss=20.71, over 1300764.90 frames.], batch size: 29, lr: 1.25e-03
+2022-05-27 16:39:57,567 INFO [train.py:823] (0/4) Epoch 13, batch 550, loss[loss=2.201, simple_loss=0.2801, pruned_loss=0.0547, codebook_loss=20.06, over 7286.00 frames.], tot_loss[loss=2.266, simple_loss=0.2732, pruned_loss=0.05336, codebook_loss=20.76, over 1322395.18 frames.], batch size: 19, lr: 1.25e-03
+2022-05-27 16:40:37,169 INFO [train.py:823] (0/4) Epoch 13, batch 600, loss[loss=2.389, simple_loss=0.292, pruned_loss=0.06748, codebook_loss=21.76, over 7266.00 frames.], tot_loss[loss=2.266, simple_loss=0.2743, pruned_loss=0.05318, codebook_loss=20.76, over 1345047.16 frames.], batch size: 20, lr: 1.24e-03
+2022-05-27 16:41:17,350 INFO [train.py:823] (0/4) Epoch 13, batch 650, loss[loss=2.425, simple_loss=0.2672, pruned_loss=0.05122, codebook_loss=22.4, over 7197.00 frames.], tot_loss[loss=2.267, simple_loss=0.2745, pruned_loss=0.05289, codebook_loss=20.77, over 1362263.19 frames.], batch size: 19, lr: 1.24e-03
+2022-05-27 16:41:57,045 INFO [train.py:823] (0/4) Epoch 13, batch 700, loss[loss=2.21, simple_loss=0.2509, pruned_loss=0.05558, codebook_loss=20.29, over 7027.00 frames.], tot_loss[loss=2.27, simple_loss=0.2744, pruned_loss=0.05338, codebook_loss=20.8, over 1372604.05 frames.], batch size: 17, lr: 1.24e-03
+2022-05-27 16:42:38,228 INFO [train.py:823] (0/4) Epoch 13, batch 750, loss[loss=2.123, simple_loss=0.2576, pruned_loss=0.0328, codebook_loss=19.61, over 6908.00 frames.], tot_loss[loss=2.261, simple_loss=0.2744, pruned_loss=0.05271, codebook_loss=20.71, over 1380001.38 frames.], batch size: 29, lr: 1.24e-03
+2022-05-27 16:43:19,050 INFO [train.py:823] (0/4) Epoch 13, batch 800, loss[loss=2.205, simple_loss=0.283, pruned_loss=0.048, codebook_loss=20.15, over 7138.00 frames.], tot_loss[loss=2.26, simple_loss=0.2746, pruned_loss=0.05307, codebook_loss=20.7, over 1388194.11 frames.], batch size: 23, lr: 1.24e-03
+2022-05-27 16:44:00,614 INFO [train.py:823] (0/4) Epoch 13, batch 850, loss[loss=2.213, simple_loss=0.2826, pruned_loss=0.05639, codebook_loss=20.15, over 7288.00 frames.], tot_loss[loss=2.259, simple_loss=0.2742, pruned_loss=0.05288, codebook_loss=20.69, over 1397660.16 frames.], batch size: 20, lr: 1.23e-03
+2022-05-27 16:44:39,950 INFO [train.py:823] (0/4) Epoch 13, batch 900, loss[loss=2.207, simple_loss=0.2422, pruned_loss=0.03847, codebook_loss=20.47, over 7299.00 frames.], tot_loss[loss=2.258, simple_loss=0.275, pruned_loss=0.05299, codebook_loss=20.68, over 1396600.47 frames.], batch size: 19, lr: 1.23e-03
+2022-05-27 16:45:19,801 INFO [train.py:823] (0/4) Epoch 13, batch 950, loss[loss=2.185, simple_loss=0.2395, pruned_loss=0.04302, codebook_loss=20.22, over 6994.00 frames.], tot_loss[loss=2.258, simple_loss=0.2743, pruned_loss=0.05223, codebook_loss=20.69, over 1394877.55 frames.], batch size: 16, lr: 1.23e-03
+2022-05-27 16:45:20,992 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-13.pt
+2022-05-27 16:45:35,321 INFO [train.py:823] (0/4) Epoch 14, batch 0, loss[loss=2.125, simple_loss=0.2606, pruned_loss=0.03972, codebook_loss=19.55, over 7317.00 frames.], tot_loss[loss=2.125, simple_loss=0.2606, pruned_loss=0.03972, codebook_loss=19.55, over 7317.00 frames.], batch size: 22, lr: 1.19e-03
+2022-05-27 16:46:15,198 INFO [train.py:823] (0/4) Epoch 14, batch 50, loss[loss=2.218, simple_loss=0.2914, pruned_loss=0.05057, codebook_loss=20.21, over 7207.00 frames.], tot_loss[loss=2.228, simple_loss=0.2681, pruned_loss=0.04774, codebook_loss=20.46, over 324291.78 frames.], batch size: 25, lr: 1.19e-03
+2022-05-27 16:46:55,252 INFO [train.py:823] (0/4) Epoch 14, batch 100, loss[loss=2.197, simple_loss=0.2729, pruned_loss=0.04716, codebook_loss=20.14, over 7251.00 frames.], tot_loss[loss=2.247, simple_loss=0.2713, pruned_loss=0.05038, codebook_loss=20.61, over 570898.26 frames.], batch size: 24, lr: 1.19e-03
+2022-05-27 16:47:34,766 INFO [train.py:823] (0/4) Epoch 14, batch 150, loss[loss=2.248, simple_loss=0.2953, pruned_loss=0.06359, codebook_loss=20.37, over 7279.00 frames.], tot_loss[loss=2.257, simple_loss=0.273, pruned_loss=0.0515, codebook_loss=20.69, over 755846.64 frames.], batch size: 21, lr: 1.18e-03
+2022-05-27 16:48:14,994 INFO [train.py:823] (0/4) Epoch 14, batch 200, loss[loss=2.166, simple_loss=0.2704, pruned_loss=0.03895, codebook_loss=19.92, over 7372.00 frames.], tot_loss[loss=2.242, simple_loss=0.2711, pruned_loss=0.04994, codebook_loss=20.56, over 901321.54 frames.], batch size: 21, lr: 1.18e-03
+2022-05-27 16:48:54,989 INFO [train.py:823] (0/4) Epoch 14, batch 250, loss[loss=2.375, simple_loss=0.2941, pruned_loss=0.06697, codebook_loss=21.61, over 7288.00 frames.], tot_loss[loss=2.243, simple_loss=0.2702, pruned_loss=0.05059, codebook_loss=20.57, over 1019531.62 frames.], batch size: 19, lr: 1.18e-03
+2022-05-27 16:49:34,986 INFO [train.py:823] (0/4) Epoch 14, batch 300, loss[loss=2.247, simple_loss=0.2993, pruned_loss=0.04986, codebook_loss=20.47, over 6394.00 frames.], tot_loss[loss=2.24, simple_loss=0.2706, pruned_loss=0.05062, codebook_loss=20.54, over 1099565.31 frames.], batch size: 34, lr: 1.18e-03
+2022-05-27 16:50:14,792 INFO [train.py:823] (0/4) Epoch 14, batch 350, loss[loss=2.25, simple_loss=0.258, pruned_loss=0.05312, codebook_loss=20.68, over 7287.00 frames.], tot_loss[loss=2.235, simple_loss=0.2709, pruned_loss=0.05026, codebook_loss=20.5, over 1176075.43 frames.], batch size: 19, lr: 1.18e-03
+2022-05-27 16:50:54,545 INFO [train.py:823] (0/4) Epoch 14, batch 400, loss[loss=2.147, simple_loss=0.2626, pruned_loss=0.04119, codebook_loss=19.74, over 7294.00 frames.], tot_loss[loss=2.239, simple_loss=0.2716, pruned_loss=0.05079, codebook_loss=20.52, over 1230812.99 frames.], batch size: 19, lr: 1.17e-03
+2022-05-27 16:51:34,199 INFO [train.py:823] (0/4) Epoch 14, batch 450, loss[loss=2.126, simple_loss=0.2422, pruned_loss=0.04253, codebook_loss=19.63, over 7093.00 frames.], tot_loss[loss=2.238, simple_loss=0.2717, pruned_loss=0.05073, codebook_loss=20.52, over 1269522.44 frames.], batch size: 18, lr: 1.17e-03
+2022-05-27 16:52:14,443 INFO [train.py:823] (0/4) Epoch 14, batch 500, loss[loss=2.293, simple_loss=0.2833, pruned_loss=0.05634, codebook_loss=20.95, over 7186.00 frames.], tot_loss[loss=2.235, simple_loss=0.2714, pruned_loss=0.05051, codebook_loss=20.49, over 1304955.11 frames.], batch size: 21, lr: 1.17e-03
+2022-05-27 16:52:54,032 INFO [train.py:823] (0/4) Epoch 14, batch 550, loss[loss=2.296, simple_loss=0.3072, pruned_loss=0.071, codebook_loss=20.71, over 7194.00 frames.], tot_loss[loss=2.244, simple_loss=0.2721, pruned_loss=0.05114, codebook_loss=20.56, over 1335054.22 frames.], batch size: 25, lr: 1.17e-03
+2022-05-27 16:53:34,419 INFO [train.py:823] (0/4) Epoch 14, batch 600, loss[loss=2.407, simple_loss=0.283, pruned_loss=0.06263, codebook_loss=22.03, over 7406.00 frames.], tot_loss[loss=2.243, simple_loss=0.2704, pruned_loss=0.05047, codebook_loss=20.57, over 1355930.05 frames.], batch size: 19, lr: 1.17e-03
+2022-05-27 16:54:14,393 INFO [train.py:823] (0/4) Epoch 14, batch 650, loss[loss=2.187, simple_loss=0.2524, pruned_loss=0.04304, codebook_loss=20.18, over 7323.00 frames.], tot_loss[loss=2.242, simple_loss=0.2703, pruned_loss=0.05068, codebook_loss=20.56, over 1369720.52 frames.], batch size: 17, lr: 1.16e-03
+2022-05-27 16:54:54,553 INFO [train.py:823] (0/4) Epoch 14, batch 700, loss[loss=2.147, simple_loss=0.2626, pruned_loss=0.03501, codebook_loss=19.81, over 7284.00 frames.], tot_loss[loss=2.243, simple_loss=0.2698, pruned_loss=0.05055, codebook_loss=20.57, over 1378217.45 frames.], batch size: 21, lr: 1.16e-03
+2022-05-27 16:55:34,020 INFO [train.py:823] (0/4) Epoch 14, batch 750, loss[loss=2.171, simple_loss=0.2857, pruned_loss=0.04587, codebook_loss=19.82, over 7108.00 frames.], tot_loss[loss=2.243, simple_loss=0.27, pruned_loss=0.05042, codebook_loss=20.58, over 1388494.93 frames.], batch size: 20, lr: 1.16e-03
+2022-05-27 16:56:14,260 INFO [train.py:823] (0/4) Epoch 14, batch 800, loss[loss=2.202, simple_loss=0.2684, pruned_loss=0.04671, codebook_loss=20.21, over 7190.00 frames.], tot_loss[loss=2.243, simple_loss=0.2698, pruned_loss=0.05042, codebook_loss=20.58, over 1394670.82 frames.], batch size: 19, lr: 1.16e-03
+2022-05-27 16:56:54,036 INFO [train.py:823] (0/4) Epoch 14, batch 850, loss[loss=2.153, simple_loss=0.2682, pruned_loss=0.04387, codebook_loss=19.75, over 7284.00 frames.], tot_loss[loss=2.239, simple_loss=0.2694, pruned_loss=0.05022, codebook_loss=20.54, over 1397294.38 frames.], batch size: 20, lr: 1.16e-03
+2022-05-27 16:57:34,188 INFO [train.py:823] (0/4) Epoch 14, batch 900, loss[loss=2.204, simple_loss=0.2585, pruned_loss=0.05489, codebook_loss=20.2, over 7022.00 frames.], tot_loss[loss=2.243, simple_loss=0.2698, pruned_loss=0.05005, codebook_loss=20.58, over 1401028.46 frames.], batch size: 17, lr: 1.15e-03
+2022-05-27 16:58:13,884 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-14.pt
+2022-05-27 16:58:27,945 INFO [train.py:823] (0/4) Epoch 15, batch 0, loss[loss=2.172, simple_loss=0.2506, pruned_loss=0.03757, codebook_loss=20.09, over 7204.00 frames.], tot_loss[loss=2.172, simple_loss=0.2506, pruned_loss=0.03757, codebook_loss=20.09, over 7204.00 frames.], batch size: 19, lr: 1.12e-03
+2022-05-27 16:59:07,735 INFO [train.py:823] (0/4) Epoch 15, batch 50, loss[loss=2.223, simple_loss=0.2594, pruned_loss=0.05309, codebook_loss=20.41, over 7189.00 frames.], tot_loss[loss=2.223, simple_loss=0.2699, pruned_loss=0.04829, codebook_loss=20.4, over 319766.04 frames.], batch size: 18, lr: 1.12e-03
+2022-05-27 16:59:47,349 INFO [train.py:823] (0/4) Epoch 15, batch 100, loss[loss=2.413, simple_loss=0.2828, pruned_loss=0.0524, codebook_loss=22.19, over 7419.00 frames.], tot_loss[loss=2.217, simple_loss=0.2666, pruned_loss=0.04747, codebook_loss=20.36, over 559784.42 frames.], batch size: 22, lr: 1.11e-03
+2022-05-27 17:00:27,641 INFO [train.py:823] (0/4) Epoch 15, batch 150, loss[loss=2.437, simple_loss=0.2492, pruned_loss=0.05763, codebook_loss=22.55, over 7288.00 frames.], tot_loss[loss=2.216, simple_loss=0.2638, pruned_loss=0.04704, codebook_loss=20.37, over 751348.21 frames.], batch size: 17, lr: 1.11e-03
+2022-05-27 17:01:07,277 INFO [train.py:823] (0/4) Epoch 15, batch 200, loss[loss=2.234, simple_loss=0.2814, pruned_loss=0.05278, codebook_loss=20.41, over 7124.00 frames.], tot_loss[loss=2.232, simple_loss=0.2669, pruned_loss=0.04877, codebook_loss=20.49, over 898231.68 frames.], batch size: 23, lr: 1.11e-03
+2022-05-27 17:01:47,509 INFO [train.py:823] (0/4) Epoch 15, batch 250, loss[loss=2.204, simple_loss=0.2838, pruned_loss=0.05039, codebook_loss=20.11, over 6380.00 frames.], tot_loss[loss=2.231, simple_loss=0.2674, pruned_loss=0.04864, codebook_loss=20.48, over 1013890.90 frames.], batch size: 34, lr: 1.11e-03
+2022-05-27 17:02:27,349 INFO [train.py:823] (0/4) Epoch 15, batch 300, loss[loss=2.299, simple_loss=0.2907, pruned_loss=0.06722, codebook_loss=20.87, over 7199.00 frames.], tot_loss[loss=2.223, simple_loss=0.2659, pruned_loss=0.04789, codebook_loss=20.42, over 1104130.74 frames.], batch size: 18, lr: 1.11e-03
+2022-05-27 17:03:08,869 INFO [train.py:823] (0/4) Epoch 15, batch 350, loss[loss=2.211, simple_loss=0.2704, pruned_loss=0.04798, codebook_loss=20.28, over 7370.00 frames.], tot_loss[loss=2.216, simple_loss=0.2653, pruned_loss=0.04671, codebook_loss=20.37, over 1176752.87 frames.], batch size: 20, lr: 1.10e-03
+2022-05-27 17:03:48,662 INFO [train.py:823] (0/4) Epoch 15, batch 400, loss[loss=2.144, simple_loss=0.2766, pruned_loss=0.04422, codebook_loss=19.62, over 7095.00 frames.], tot_loss[loss=2.224, simple_loss=0.2658, pruned_loss=0.04699, codebook_loss=20.44, over 1228438.38 frames.], batch size: 19, lr: 1.10e-03
+2022-05-27 17:04:28,849 INFO [train.py:823] (0/4) Epoch 15, batch 450, loss[loss=2.22, simple_loss=0.2842, pruned_loss=0.05695, codebook_loss=20.21, over 7229.00 frames.], tot_loss[loss=2.22, simple_loss=0.2658, pruned_loss=0.04682, codebook_loss=20.4, over 1276095.57 frames.], batch size: 24, lr: 1.10e-03
+2022-05-27 17:05:08,648 INFO [train.py:823] (0/4) Epoch 15, batch 500, loss[loss=2.147, simple_loss=0.2636, pruned_loss=0.04404, codebook_loss=19.71, over 7106.00 frames.], tot_loss[loss=2.216, simple_loss=0.2668, pruned_loss=0.04726, codebook_loss=20.35, over 1311688.65 frames.], batch size: 20, lr: 1.10e-03
+2022-05-27 17:05:48,664 INFO [train.py:823] (0/4) Epoch 15, batch 550, loss[loss=2.055, simple_loss=0.227, pruned_loss=0.03134, codebook_loss=19.1, over 7436.00 frames.], tot_loss[loss=2.217, simple_loss=0.267, pruned_loss=0.04776, codebook_loss=20.36, over 1332014.79 frames.], batch size: 18, lr: 1.10e-03
+2022-05-27 17:06:28,750 INFO [train.py:823] (0/4) Epoch 15, batch 600, loss[loss=2.284, simple_loss=0.2836, pruned_loss=0.0578, codebook_loss=20.84, over 7299.00 frames.], tot_loss[loss=2.227, simple_loss=0.2681, pruned_loss=0.04814, codebook_loss=20.45, over 1356244.50 frames.], batch size: 19, lr: 1.10e-03
+2022-05-27 17:07:08,780 INFO [train.py:823] (0/4) Epoch 15, batch 650, loss[loss=2.376, simple_loss=0.3139, pruned_loss=0.08094, codebook_loss=21.38, over 7174.00 frames.], tot_loss[loss=2.222, simple_loss=0.2675, pruned_loss=0.04784, codebook_loss=20.41, over 1367230.40 frames.], batch size: 22, lr: 1.09e-03
+2022-05-27 17:07:51,620 INFO [train.py:823] (0/4) Epoch 15, batch 700, loss[loss=2.309, simple_loss=0.2942, pruned_loss=0.06384, codebook_loss=20.98, over 6971.00 frames.], tot_loss[loss=2.224, simple_loss=0.2676, pruned_loss=0.04786, codebook_loss=20.42, over 1381901.29 frames.], batch size: 29, lr: 1.09e-03
+2022-05-27 17:08:32,967 INFO [train.py:823] (0/4) Epoch 15, batch 750, loss[loss=2.182, simple_loss=0.2585, pruned_loss=0.0456, codebook_loss=20.07, over 4728.00 frames.], tot_loss[loss=2.223, simple_loss=0.2675, pruned_loss=0.04817, codebook_loss=20.41, over 1384849.99 frames.], batch size: 46, lr: 1.09e-03
+2022-05-27 17:09:12,719 INFO [train.py:823] (0/4) Epoch 15, batch 800, loss[loss=2.241, simple_loss=0.2697, pruned_loss=0.04783, codebook_loss=20.58, over 7195.00 frames.], tot_loss[loss=2.22, simple_loss=0.2677, pruned_loss=0.04784, codebook_loss=20.38, over 1390123.25 frames.], batch size: 19, lr: 1.09e-03
+2022-05-27 17:09:53,039 INFO [train.py:823] (0/4) Epoch 15, batch 850, loss[loss=2.343, simple_loss=0.2938, pruned_loss=0.05728, codebook_loss=21.39, over 7237.00 frames.], tot_loss[loss=2.222, simple_loss=0.2678, pruned_loss=0.0481, codebook_loss=20.4, over 1394603.10 frames.], batch size: 25, lr: 1.09e-03
+2022-05-27 17:10:33,286 INFO [train.py:823] (0/4) Epoch 15, batch 900, loss[loss=2.253, simple_loss=0.2847, pruned_loss=0.05981, codebook_loss=20.51, over 7110.00 frames.], tot_loss[loss=2.225, simple_loss=0.269, pruned_loss=0.04871, codebook_loss=20.41, over 1399998.41 frames.], batch size: 19, lr: 1.09e-03
+2022-05-27 17:11:13,318 INFO [train.py:823] (0/4) Epoch 15, batch 950, loss[loss=2.15, simple_loss=0.2521, pruned_loss=0.0434, codebook_loss=19.8, over 4862.00 frames.], tot_loss[loss=2.225, simple_loss=0.2691, pruned_loss=0.04878, codebook_loss=20.41, over 1381684.76 frames.], batch size: 47, lr: 1.08e-03
+2022-05-27 17:11:14,549 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-15.pt
+2022-05-27 17:11:28,485 INFO [train.py:823] (0/4) Epoch 16, batch 0, loss[loss=2.161, simple_loss=0.2596, pruned_loss=0.04687, codebook_loss=19.85, over 5095.00 frames.], tot_loss[loss=2.161, simple_loss=0.2596, pruned_loss=0.04687, codebook_loss=19.85, over 5095.00 frames.], batch size: 47, lr: 1.05e-03
+2022-05-27 17:12:08,658 INFO [train.py:823] (0/4) Epoch 16, batch 50, loss[loss=2.16, simple_loss=0.2333, pruned_loss=0.03321, codebook_loss=20.1, over 7001.00 frames.], tot_loss[loss=2.162, simple_loss=0.2616, pruned_loss=0.04405, codebook_loss=19.87, over 318526.77 frames.], batch size: 16, lr: 1.05e-03
+2022-05-27 17:12:48,675 INFO [train.py:823] (0/4) Epoch 16, batch 100, loss[loss=2.146, simple_loss=0.2658, pruned_loss=0.0428, codebook_loss=19.71, over 7198.00 frames.], tot_loss[loss=2.199, simple_loss=0.2636, pruned_loss=0.04618, codebook_loss=20.21, over 560996.02 frames.], batch size: 19, lr: 1.05e-03
+2022-05-27 17:13:29,326 INFO [train.py:823] (0/4) Epoch 16, batch 150, loss[loss=2.15, simple_loss=0.2746, pruned_loss=0.04769, codebook_loss=19.65, over 7381.00 frames.], tot_loss[loss=2.194, simple_loss=0.2645, pruned_loss=0.04592, codebook_loss=20.16, over 756152.27 frames.], batch size: 19, lr: 1.05e-03
+2022-05-27 17:14:09,504 INFO [train.py:823] (0/4) Epoch 16, batch 200, loss[loss=2.207, simple_loss=0.2901, pruned_loss=0.05013, codebook_loss=20.12, over 7167.00 frames.], tot_loss[loss=2.206, simple_loss=0.266, pruned_loss=0.04751, codebook_loss=20.26, over 903967.41 frames.], batch size: 23, lr: 1.05e-03
+2022-05-27 17:14:49,851 INFO [train.py:823] (0/4) Epoch 16, batch 250, loss[loss=2.161, simple_loss=0.2732, pruned_loss=0.05442, codebook_loss=19.7, over 7198.00 frames.], tot_loss[loss=2.202, simple_loss=0.2663, pruned_loss=0.04764, codebook_loss=20.21, over 1013375.97 frames.], batch size: 25, lr: 1.04e-03
+2022-05-27 17:15:29,984 INFO [train.py:823] (0/4) Epoch 16, batch 300, loss[loss=2.228, simple_loss=0.2713, pruned_loss=0.0449, codebook_loss=20.47, over 7268.00 frames.], tot_loss[loss=2.201, simple_loss=0.2642, pruned_loss=0.0468, codebook_loss=20.22, over 1105792.01 frames.], batch size: 24, lr: 1.04e-03
+2022-05-27 17:16:09,881 INFO [train.py:823] (0/4) Epoch 16, batch 350, loss[loss=2.214, simple_loss=0.289, pruned_loss=0.06481, codebook_loss=20.04, over 7352.00 frames.], tot_loss[loss=2.209, simple_loss=0.2658, pruned_loss=0.04753, codebook_loss=20.28, over 1173641.50 frames.], batch size: 23, lr: 1.04e-03
+2022-05-27 17:16:49,901 INFO [train.py:823] (0/4) Epoch 16, batch 400, loss[loss=2.177, simple_loss=0.2533, pruned_loss=0.03936, codebook_loss=20.11, over 7298.00 frames.], tot_loss[loss=2.201, simple_loss=0.2651, pruned_loss=0.04688, codebook_loss=20.22, over 1228199.73 frames.], batch size: 19, lr: 1.04e-03
+2022-05-27 17:17:30,119 INFO [train.py:823] (0/4) Epoch 16, batch 450, loss[loss=2.375, simple_loss=0.2939, pruned_loss=0.05562, codebook_loss=21.73, over 7420.00 frames.], tot_loss[loss=2.202, simple_loss=0.2652, pruned_loss=0.04642, codebook_loss=20.23, over 1275513.44 frames.], batch size: 22, lr: 1.04e-03
+2022-05-27 17:18:10,058 INFO [train.py:823] (0/4) Epoch 16, batch 500, loss[loss=2.167, simple_loss=0.278, pruned_loss=0.04667, codebook_loss=19.81, over 6933.00 frames.], tot_loss[loss=2.205, simple_loss=0.2653, pruned_loss=0.04647, codebook_loss=20.26, over 1311835.38 frames.], batch size: 29, lr: 1.04e-03
+2022-05-27 17:18:50,313 INFO [train.py:823] (0/4) Epoch 16, batch 550, loss[loss=2.333, simple_loss=0.3152, pruned_loss=0.06608, codebook_loss=21.09, over 7374.00 frames.], tot_loss[loss=2.202, simple_loss=0.2665, pruned_loss=0.04668, codebook_loss=20.22, over 1330599.95 frames.], batch size: 21, lr: 1.03e-03
+2022-05-27 17:19:30,253 INFO [train.py:823] (0/4) Epoch 16, batch 600, loss[loss=2.133, simple_loss=0.2457, pruned_loss=0.03318, codebook_loss=19.77, over 7102.00 frames.], tot_loss[loss=2.205, simple_loss=0.2664, pruned_loss=0.04672, codebook_loss=20.25, over 1345800.52 frames.], batch size: 19, lr: 1.03e-03
+2022-05-27 17:20:10,354 INFO [train.py:823] (0/4) Epoch 16, batch 650, loss[loss=2.318, simple_loss=0.27, pruned_loss=0.05351, codebook_loss=21.29, over 7213.00 frames.], tot_loss[loss=2.208, simple_loss=0.2671, pruned_loss=0.04681, codebook_loss=20.28, over 1362052.58 frames.], batch size: 16, lr: 1.03e-03
+2022-05-27 17:20:50,255 INFO [train.py:823] (0/4) Epoch 16, batch 700, loss[loss=2.142, simple_loss=0.2686, pruned_loss=0.04525, codebook_loss=19.62, over 7287.00 frames.], tot_loss[loss=2.208, simple_loss=0.2663, pruned_loss=0.04644, codebook_loss=20.29, over 1371167.51 frames.], batch size: 19, lr: 1.03e-03
+2022-05-27 17:21:30,276 INFO [train.py:823] (0/4) Epoch 16, batch 750, loss[loss=2.217, simple_loss=0.2593, pruned_loss=0.05245, codebook_loss=20.35, over 7192.00 frames.], tot_loss[loss=2.208, simple_loss=0.2666, pruned_loss=0.04648, codebook_loss=20.28, over 1384248.13 frames.], batch size: 18, lr: 1.03e-03
+2022-05-27 17:22:09,874 INFO [train.py:823] (0/4) Epoch 16, batch 800, loss[loss=2.297, simple_loss=0.2575, pruned_loss=0.04018, codebook_loss=21.28, over 7374.00 frames.], tot_loss[loss=2.206, simple_loss=0.2662, pruned_loss=0.04631, codebook_loss=20.26, over 1393902.45 frames.], batch size: 20, lr: 1.03e-03
+2022-05-27 17:22:50,002 INFO [train.py:823] (0/4) Epoch 16, batch 850, loss[loss=2.123, simple_loss=0.2582, pruned_loss=0.0389, codebook_loss=19.55, over 7191.00 frames.], tot_loss[loss=2.201, simple_loss=0.2659, pruned_loss=0.04624, codebook_loss=20.22, over 1400752.81 frames.], batch size: 21, lr: 1.03e-03
+2022-05-27 17:23:29,832 INFO [train.py:823] (0/4) Epoch 16, batch 900, loss[loss=2.087, simple_loss=0.2579, pruned_loss=0.03544, codebook_loss=19.23, over 7427.00 frames.], tot_loss[loss=2.195, simple_loss=0.2649, pruned_loss=0.04544, codebook_loss=20.17, over 1401128.73 frames.], batch size: 18, lr: 1.02e-03
+2022-05-27 17:24:09,390 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-16.pt
+2022-05-27 17:24:23,775 INFO [train.py:823] (0/4) Epoch 17, batch 0, loss[loss=2.121, simple_loss=0.2687, pruned_loss=0.03348, codebook_loss=19.53, over 7194.00 frames.], tot_loss[loss=2.121, simple_loss=0.2687, pruned_loss=0.03348, codebook_loss=19.53, over 7194.00 frames.], batch size: 21, lr: 9.94e-04
+2022-05-27 17:25:03,583 INFO [train.py:823] (0/4) Epoch 17, batch 50, loss[loss=2.184, simple_loss=0.2553, pruned_loss=0.04179, codebook_loss=20.15, over 7009.00 frames.], tot_loss[loss=2.202, simple_loss=0.2668, pruned_loss=0.04643, codebook_loss=20.22, over 315674.40 frames.], batch size: 26, lr: 9.92e-04
+2022-05-27 17:25:43,650 INFO [train.py:823] (0/4) Epoch 17, batch 100, loss[loss=2.133, simple_loss=0.2647, pruned_loss=0.03906, codebook_loss=19.62, over 7028.00 frames.], tot_loss[loss=2.189, simple_loss=0.2652, pruned_loss=0.04512, codebook_loss=20.12, over 561127.59 frames.], batch size: 26, lr: 9.91e-04
+2022-05-27 17:26:24,350 INFO [train.py:823] (0/4) Epoch 17, batch 150, loss[loss=2.184, simple_loss=0.2551, pruned_loss=0.04558, codebook_loss=20.11, over 7180.00 frames.], tot_loss[loss=2.182, simple_loss=0.2659, pruned_loss=0.04514, codebook_loss=20.04, over 748034.30 frames.], batch size: 18, lr: 9.89e-04
+2022-05-27 17:27:04,551 INFO [train.py:823] (0/4) Epoch 17, batch 200, loss[loss=2.159, simple_loss=0.2666, pruned_loss=0.04451, codebook_loss=19.81, over 6954.00 frames.], tot_loss[loss=2.187, simple_loss=0.2664, pruned_loss=0.04543, codebook_loss=20.09, over 897084.83 frames.], batch size: 29, lr: 9.88e-04
+2022-05-27 17:27:44,514 INFO [train.py:823] (0/4) Epoch 17, batch 250, loss[loss=2.17, simple_loss=0.2837, pruned_loss=0.04468, codebook_loss=19.84, over 7335.00 frames.], tot_loss[loss=2.182, simple_loss=0.266, pruned_loss=0.04549, codebook_loss=20.04, over 1017589.17 frames.], batch size: 23, lr: 9.86e-04
+2022-05-27 17:28:24,315 INFO [train.py:823] (0/4) Epoch 17, batch 300, loss[loss=2.11, simple_loss=0.2516, pruned_loss=0.03338, codebook_loss=19.5, over 7311.00 frames.], tot_loss[loss=2.179, simple_loss=0.2655, pruned_loss=0.04496, codebook_loss=20.01, over 1103993.07 frames.], batch size: 18, lr: 9.85e-04
+2022-05-27 17:29:04,142 INFO [train.py:823] (0/4) Epoch 17, batch 350, loss[loss=2.085, simple_loss=0.2378, pruned_loss=0.03525, codebook_loss=19.3, over 7386.00 frames.], tot_loss[loss=2.181, simple_loss=0.2642, pruned_loss=0.04499, codebook_loss=20.04, over 1170499.78 frames.], batch size: 19, lr: 9.84e-04
+2022-05-27 17:29:44,293 INFO [train.py:823] (0/4) Epoch 17, batch 400, loss[loss=2.118, simple_loss=0.2668, pruned_loss=0.04722, codebook_loss=19.38, over 7096.00 frames.], tot_loss[loss=2.191, simple_loss=0.263, pruned_loss=0.04513, codebook_loss=20.14, over 1226564.35 frames.], batch size: 19, lr: 9.82e-04
+2022-05-27 17:30:24,098 INFO [train.py:823] (0/4) Epoch 17, batch 450, loss[loss=2.18, simple_loss=0.2839, pruned_loss=0.06103, codebook_loss=19.77, over 5111.00 frames.], tot_loss[loss=2.194, simple_loss=0.2631, pruned_loss=0.04502, codebook_loss=20.18, over 1261236.01 frames.], batch size: 47, lr: 9.81e-04
+2022-05-27 17:31:04,081 INFO [train.py:823] (0/4) Epoch 17, batch 500, loss[loss=2.265, simple_loss=0.2384, pruned_loss=0.04117, codebook_loss=21.05, over 7024.00 frames.], tot_loss[loss=2.194, simple_loss=0.2636, pruned_loss=0.04525, codebook_loss=20.17, over 1296723.05 frames.], batch size: 16, lr: 9.79e-04
+2022-05-27 17:31:43,972 INFO [train.py:823] (0/4) Epoch 17, batch 550, loss[loss=2.172, simple_loss=0.2833, pruned_loss=0.04735, codebook_loss=19.83, over 7120.00 frames.], tot_loss[loss=2.192, simple_loss=0.2629, pruned_loss=0.04501, codebook_loss=20.15, over 1326053.24 frames.], batch size: 20, lr: 9.78e-04
+2022-05-27 17:32:26,573 INFO [train.py:823] (0/4) Epoch 17, batch 600, loss[loss=2.084, simple_loss=0.2523, pruned_loss=0.03387, codebook_loss=19.24, over 7290.00 frames.], tot_loss[loss=2.195, simple_loss=0.2626, pruned_loss=0.04451, codebook_loss=20.19, over 1348646.57 frames.], batch size: 22, lr: 9.76e-04
+2022-05-27 17:33:07,632 INFO [train.py:823] (0/4) Epoch 17, batch 650, loss[loss=2.153, simple_loss=0.2361, pruned_loss=0.03485, codebook_loss=20, over 7025.00 frames.], tot_loss[loss=2.194, simple_loss=0.2624, pruned_loss=0.0441, codebook_loss=20.19, over 1361831.91 frames.], batch size: 16, lr: 9.75e-04
+2022-05-27 17:33:47,708 INFO [train.py:823] (0/4) Epoch 17, batch 700, loss[loss=2.151, simple_loss=0.2441, pruned_loss=0.04074, codebook_loss=19.89, over 7218.00 frames.], tot_loss[loss=2.191, simple_loss=0.262, pruned_loss=0.04386, codebook_loss=20.17, over 1373935.38 frames.], batch size: 16, lr: 9.74e-04
+2022-05-27 17:34:27,720 INFO [train.py:823] (0/4) Epoch 17, batch 750, loss[loss=2.04, simple_loss=0.2291, pruned_loss=0.0284, codebook_loss=18.97, over 7146.00 frames.], tot_loss[loss=2.188, simple_loss=0.262, pruned_loss=0.04416, codebook_loss=20.13, over 1385769.99 frames.], batch size: 17, lr: 9.72e-04
+2022-05-27 17:35:07,902 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/checkpoint-16000.pt
+2022-05-27 17:35:10,962 INFO [train.py:823] (0/4) Epoch 17, batch 800, loss[loss=2.156, simple_loss=0.2457, pruned_loss=0.03634, codebook_loss=19.97, over 7006.00 frames.], tot_loss[loss=2.186, simple_loss=0.2622, pruned_loss=0.04391, codebook_loss=20.11, over 1388684.50 frames.], batch size: 16, lr: 9.71e-04
+2022-05-27 17:35:50,772 INFO [train.py:823] (0/4) Epoch 17, batch 850, loss[loss=2.219, simple_loss=0.2852, pruned_loss=0.05589, codebook_loss=20.2, over 7412.00 frames.], tot_loss[loss=2.181, simple_loss=0.2613, pruned_loss=0.04364, codebook_loss=20.07, over 1394909.89 frames.], batch size: 22, lr: 9.69e-04
+2022-05-27 17:36:31,170 INFO [train.py:823] (0/4) Epoch 17, batch 900, loss[loss=2.129, simple_loss=0.2331, pruned_loss=0.04026, codebook_loss=19.72, over 7281.00 frames.], tot_loss[loss=2.183, simple_loss=0.2613, pruned_loss=0.04403, codebook_loss=20.09, over 1401149.05 frames.], batch size: 17, lr: 9.68e-04
+2022-05-27 17:37:10,648 INFO [train.py:823] (0/4) Epoch 17, batch 950, loss[loss=2.164, simple_loss=0.266, pruned_loss=0.04875, codebook_loss=19.82, over 4736.00 frames.], tot_loss[loss=2.184, simple_loss=0.2618, pruned_loss=0.04466, codebook_loss=20.08, over 1396143.38 frames.], batch size: 48, lr: 9.67e-04
+2022-05-27 17:37:11,839 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-17.pt
+2022-05-27 17:37:26,032 INFO [train.py:823] (0/4) Epoch 18, batch 0, loss[loss=2.093, simple_loss=0.2702, pruned_loss=0.03377, codebook_loss=19.24, over 7377.00 frames.], tot_loss[loss=2.093, simple_loss=0.2702, pruned_loss=0.03377, codebook_loss=19.24, over 7377.00 frames.], batch size: 21, lr: 9.41e-04
+2022-05-27 17:38:06,267 INFO [train.py:823] (0/4) Epoch 18, batch 50, loss[loss=2.075, simple_loss=0.2571, pruned_loss=0.03864, codebook_loss=19.07, over 7346.00 frames.], tot_loss[loss=2.182, simple_loss=0.2597, pruned_loss=0.04278, codebook_loss=20.09, over 321569.21 frames.], batch size: 23, lr: 9.40e-04
+2022-05-27 17:38:46,066 INFO [train.py:823] (0/4) Epoch 18, batch 100, loss[loss=2.112, simple_loss=0.2646, pruned_loss=0.04257, codebook_loss=19.37, over 7280.00 frames.], tot_loss[loss=2.169, simple_loss=0.2616, pruned_loss=0.04316, codebook_loss=19.95, over 562834.09 frames.], batch size: 20, lr: 9.39e-04
+2022-05-27 17:39:26,375 INFO [train.py:823] (0/4) Epoch 18, batch 150, loss[loss=2.14, simple_loss=0.2732, pruned_loss=0.04624, codebook_loss=19.57, over 7191.00 frames.], tot_loss[loss=2.172, simple_loss=0.2614, pruned_loss=0.04318, codebook_loss=19.98, over 757500.62 frames.], batch size: 20, lr: 9.37e-04
+2022-05-27 17:40:06,111 INFO [train.py:823] (0/4) Epoch 18, batch 200, loss[loss=2.179, simple_loss=0.2702, pruned_loss=0.04749, codebook_loss=19.97, over 7287.00 frames.], tot_loss[loss=2.163, simple_loss=0.26, pruned_loss=0.0419, codebook_loss=19.91, over 907976.04 frames.], batch size: 21, lr: 9.36e-04
+2022-05-27 17:40:46,115 INFO [train.py:823] (0/4) Epoch 18, batch 250, loss[loss=2.126, simple_loss=0.262, pruned_loss=0.03997, codebook_loss=19.55, over 7314.00 frames.], tot_loss[loss=2.169, simple_loss=0.2622, pruned_loss=0.04319, codebook_loss=19.95, over 1016133.17 frames.], batch size: 22, lr: 9.35e-04
+2022-05-27 17:41:26,323 INFO [train.py:823] (0/4) Epoch 18, batch 300, loss[loss=2.406, simple_loss=0.2426, pruned_loss=0.04515, codebook_loss=22.4, over 7032.00 frames.], tot_loss[loss=2.17, simple_loss=0.2607, pruned_loss=0.04283, codebook_loss=19.97, over 1105769.61 frames.], batch size: 17, lr: 9.33e-04
+2022-05-27 17:42:06,868 INFO [train.py:823] (0/4) Epoch 18, batch 350, loss[loss=2.075, simple_loss=0.2509, pruned_loss=0.03071, codebook_loss=19.19, over 7296.00 frames.], tot_loss[loss=2.167, simple_loss=0.261, pruned_loss=0.04306, codebook_loss=19.93, over 1176114.49 frames.], batch size: 20, lr: 9.32e-04
+2022-05-27 17:42:46,648 INFO [train.py:823] (0/4) Epoch 18, batch 400, loss[loss=2.202, simple_loss=0.2581, pruned_loss=0.05154, codebook_loss=20.21, over 7390.00 frames.], tot_loss[loss=2.17, simple_loss=0.2625, pruned_loss=0.04384, codebook_loss=19.94, over 1227518.10 frames.], batch size: 19, lr: 9.31e-04
+2022-05-27 17:43:26,810 INFO [train.py:823] (0/4) Epoch 18, batch 450, loss[loss=2.141, simple_loss=0.26, pruned_loss=0.04616, codebook_loss=19.65, over 7144.00 frames.], tot_loss[loss=2.171, simple_loss=0.2627, pruned_loss=0.04374, codebook_loss=19.96, over 1269528.99 frames.], batch size: 23, lr: 9.29e-04
+2022-05-27 17:44:06,714 INFO [train.py:823] (0/4) Epoch 18, batch 500, loss[loss=2.157, simple_loss=0.2782, pruned_loss=0.0452, codebook_loss=19.73, over 7431.00 frames.], tot_loss[loss=2.169, simple_loss=0.262, pruned_loss=0.04324, codebook_loss=19.95, over 1307298.45 frames.], batch size: 22, lr: 9.28e-04
+2022-05-27 17:44:47,098 INFO [train.py:823] (0/4) Epoch 18, batch 550, loss[loss=2.074, simple_loss=0.2601, pruned_loss=0.04498, codebook_loss=18.99, over 7362.00 frames.], tot_loss[loss=2.167, simple_loss=0.2603, pruned_loss=0.04252, codebook_loss=19.94, over 1335421.71 frames.], batch size: 23, lr: 9.27e-04
+2022-05-27 17:45:26,632 INFO [train.py:823] (0/4) Epoch 18, batch 600, loss[loss=2.168, simple_loss=0.2502, pruned_loss=0.04373, codebook_loss=19.99, over 7296.00 frames.], tot_loss[loss=2.167, simple_loss=0.26, pruned_loss=0.0426, codebook_loss=19.94, over 1357597.31 frames.], batch size: 19, lr: 9.26e-04
+2022-05-27 17:46:06,503 INFO [train.py:823] (0/4) Epoch 18, batch 650, loss[loss=2.141, simple_loss=0.2668, pruned_loss=0.04645, codebook_loss=19.61, over 7095.00 frames.], tot_loss[loss=2.161, simple_loss=0.2601, pruned_loss=0.04224, codebook_loss=19.89, over 1371667.89 frames.], batch size: 19, lr: 9.24e-04
+2022-05-27 17:46:46,442 INFO [train.py:823] (0/4) Epoch 18, batch 700, loss[loss=2.099, simple_loss=0.246, pruned_loss=0.02995, codebook_loss=19.46, over 7191.00 frames.], tot_loss[loss=2.163, simple_loss=0.2601, pruned_loss=0.04283, codebook_loss=19.9, over 1375644.99 frames.], batch size: 19, lr: 9.23e-04
+2022-05-27 17:47:26,763 INFO [train.py:823] (0/4) Epoch 18, batch 750, loss[loss=2.209, simple_loss=0.2492, pruned_loss=0.04746, codebook_loss=20.37, over 7103.00 frames.], tot_loss[loss=2.166, simple_loss=0.2609, pruned_loss=0.04319, codebook_loss=19.93, over 1387610.18 frames.], batch size: 18, lr: 9.22e-04
+2022-05-27 17:48:06,482 INFO [train.py:823] (0/4) Epoch 18, batch 800, loss[loss=2.282, simple_loss=0.2503, pruned_loss=0.04051, codebook_loss=21.17, over 7199.00 frames.], tot_loss[loss=2.167, simple_loss=0.2605, pruned_loss=0.04313, codebook_loss=19.94, over 1391007.15 frames.], batch size: 20, lr: 9.21e-04
+2022-05-27 17:48:46,486 INFO [train.py:823] (0/4) Epoch 18, batch 850, loss[loss=2.078, simple_loss=0.268, pruned_loss=0.03107, codebook_loss=19.13, over 7183.00 frames.], tot_loss[loss=2.164, simple_loss=0.2597, pruned_loss=0.04286, codebook_loss=19.92, over 1395040.56 frames.], batch size: 21, lr: 9.19e-04
+2022-05-27 17:49:26,191 INFO [train.py:823] (0/4) Epoch 18, batch 900, loss[loss=2.206, simple_loss=0.2456, pruned_loss=0.03682, codebook_loss=20.46, over 7143.00 frames.], tot_loss[loss=2.172, simple_loss=0.2606, pruned_loss=0.0433, codebook_loss=19.98, over 1401683.63 frames.], batch size: 17, lr: 9.18e-04
+2022-05-27 17:50:07,349 INFO [train.py:823] (0/4) Epoch 18, batch 950, loss[loss=2.229, simple_loss=0.265, pruned_loss=0.06851, codebook_loss=20.28, over 4612.00 frames.], tot_loss[loss=2.172, simple_loss=0.2607, pruned_loss=0.04359, codebook_loss=19.98, over 1373629.33 frames.], batch size: 46, lr: 9.17e-04
+2022-05-27 17:50:08,584 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-18.pt
+2022-05-27 17:50:22,769 INFO [train.py:823] (0/4) Epoch 19, batch 0, loss[loss=2.095, simple_loss=0.2697, pruned_loss=0.04012, codebook_loss=19.2, over 7014.00 frames.], tot_loss[loss=2.095, simple_loss=0.2697, pruned_loss=0.04012, codebook_loss=19.2, over 7014.00 frames.], batch size: 26, lr: 8.94e-04
+2022-05-27 17:51:02,636 INFO [train.py:823] (0/4) Epoch 19, batch 50, loss[loss=2.08, simple_loss=0.2366, pruned_loss=0.03135, codebook_loss=19.31, over 7190.00 frames.], tot_loss[loss=2.155, simple_loss=0.2572, pruned_loss=0.04101, codebook_loss=19.85, over 325407.41 frames.], batch size: 19, lr: 8.92e-04
+2022-05-27 17:51:43,088 INFO [train.py:823] (0/4) Epoch 19, batch 100, loss[loss=2.066, simple_loss=0.2479, pruned_loss=0.0315, codebook_loss=19.11, over 6528.00 frames.], tot_loss[loss=2.159, simple_loss=0.2579, pruned_loss=0.04168, codebook_loss=19.88, over 565915.06 frames.], batch size: 34, lr: 8.91e-04
+2022-05-27 17:52:23,020 INFO [train.py:823] (0/4) Epoch 19, batch 150, loss[loss=2.042, simple_loss=0.2384, pruned_loss=0.02881, codebook_loss=18.94, over 7088.00 frames.], tot_loss[loss=2.159, simple_loss=0.256, pruned_loss=0.04152, codebook_loss=19.9, over 758742.98 frames.], batch size: 18, lr: 8.90e-04
+2022-05-27 17:53:03,219 INFO [train.py:823] (0/4) Epoch 19, batch 200, loss[loss=2.12, simple_loss=0.2774, pruned_loss=0.04433, codebook_loss=19.37, over 7153.00 frames.], tot_loss[loss=2.156, simple_loss=0.2563, pruned_loss=0.04104, codebook_loss=19.87, over 901426.56 frames.], batch size: 22, lr: 8.89e-04
+2022-05-27 17:53:42,984 INFO [train.py:823] (0/4) Epoch 19, batch 250, loss[loss=2.03, simple_loss=0.2498, pruned_loss=0.03438, codebook_loss=18.71, over 7091.00 frames.], tot_loss[loss=2.151, simple_loss=0.2576, pruned_loss=0.04103, codebook_loss=19.82, over 1017612.28 frames.], batch size: 19, lr: 8.88e-04
+2022-05-27 17:54:22,997 INFO [train.py:823] (0/4) Epoch 19, batch 300, loss[loss=2.093, simple_loss=0.2295, pruned_loss=0.03041, codebook_loss=19.47, over 7010.00 frames.], tot_loss[loss=2.161, simple_loss=0.2586, pruned_loss=0.04206, codebook_loss=19.9, over 1109230.37 frames.], batch size: 16, lr: 8.87e-04
+2022-05-27 17:55:02,847 INFO [train.py:823] (0/4) Epoch 19, batch 350, loss[loss=2.194, simple_loss=0.3238, pruned_loss=0.07975, codebook_loss=19.53, over 7311.00 frames.], tot_loss[loss=2.151, simple_loss=0.2588, pruned_loss=0.04171, codebook_loss=19.8, over 1176559.91 frames.], batch size: 18, lr: 8.85e-04
+2022-05-27 17:55:43,643 INFO [train.py:823] (0/4) Epoch 19, batch 400, loss[loss=2.23, simple_loss=0.2326, pruned_loss=0.04356, codebook_loss=20.7, over 7024.00 frames.], tot_loss[loss=2.152, simple_loss=0.2594, pruned_loss=0.04179, codebook_loss=19.8, over 1234519.25 frames.], batch size: 16, lr: 8.84e-04
+2022-05-27 17:56:23,356 INFO [train.py:823] (0/4) Epoch 19, batch 450, loss[loss=2.236, simple_loss=0.2707, pruned_loss=0.04962, codebook_loss=20.51, over 7143.00 frames.], tot_loss[loss=2.156, simple_loss=0.2602, pruned_loss=0.04215, codebook_loss=19.84, over 1276543.88 frames.], batch size: 23, lr: 8.83e-04
+2022-05-27 17:57:06,158 INFO [train.py:823] (0/4) Epoch 19, batch 500, loss[loss=2.253, simple_loss=0.2904, pruned_loss=0.05881, codebook_loss=20.49, over 6471.00 frames.], tot_loss[loss=2.154, simple_loss=0.2603, pruned_loss=0.04211, codebook_loss=19.82, over 1309654.32 frames.], batch size: 34, lr: 8.82e-04
+2022-05-27 17:57:47,321 INFO [train.py:823] (0/4) Epoch 19, batch 550, loss[loss=2.039, simple_loss=0.2346, pruned_loss=0.03509, codebook_loss=18.87, over 7024.00 frames.], tot_loss[loss=2.152, simple_loss=0.2598, pruned_loss=0.04193, codebook_loss=19.8, over 1331356.52 frames.], batch size: 17, lr: 8.81e-04
+2022-05-27 17:58:27,514 INFO [train.py:823] (0/4) Epoch 19, batch 600, loss[loss=2.603, simple_loss=0.2879, pruned_loss=0.08242, codebook_loss=23.77, over 7095.00 frames.], tot_loss[loss=2.155, simple_loss=0.261, pruned_loss=0.04254, codebook_loss=19.82, over 1351567.21 frames.], batch size: 19, lr: 8.80e-04
+2022-05-27 17:59:07,240 INFO [train.py:823] (0/4) Epoch 19, batch 650, loss[loss=2.069, simple_loss=0.2419, pruned_loss=0.04125, codebook_loss=19.07, over 7018.00 frames.], tot_loss[loss=2.157, simple_loss=0.2601, pruned_loss=0.0423, codebook_loss=19.85, over 1365541.40 frames.], batch size: 17, lr: 8.78e-04
+2022-05-27 17:59:47,322 INFO [train.py:823] (0/4) Epoch 19, batch 700, loss[loss=2.074, simple_loss=0.2476, pruned_loss=0.03889, codebook_loss=19.11, over 7038.00 frames.], tot_loss[loss=2.152, simple_loss=0.2589, pruned_loss=0.04174, codebook_loss=19.81, over 1377840.23 frames.], batch size: 26, lr: 8.77e-04
+2022-05-27 18:00:27,354 INFO [train.py:823] (0/4) Epoch 19, batch 750, loss[loss=2.156, simple_loss=0.2787, pruned_loss=0.04696, codebook_loss=19.69, over 7370.00 frames.], tot_loss[loss=2.155, simple_loss=0.2595, pruned_loss=0.04201, codebook_loss=19.83, over 1388028.33 frames.], batch size: 21, lr: 8.76e-04
+2022-05-27 18:01:07,500 INFO [train.py:823] (0/4) Epoch 19, batch 800, loss[loss=2.145, simple_loss=0.2712, pruned_loss=0.04465, codebook_loss=19.65, over 7301.00 frames.], tot_loss[loss=2.156, simple_loss=0.259, pruned_loss=0.04179, codebook_loss=19.84, over 1397424.01 frames.], batch size: 22, lr: 8.75e-04
+2022-05-27 18:01:47,268 INFO [train.py:823] (0/4) Epoch 19, batch 850, loss[loss=2.283, simple_loss=0.2858, pruned_loss=0.05441, codebook_loss=20.85, over 7369.00 frames.], tot_loss[loss=2.165, simple_loss=0.2601, pruned_loss=0.04261, codebook_loss=19.93, over 1402557.55 frames.], batch size: 21, lr: 8.74e-04
+2022-05-27 18:02:27,150 INFO [train.py:823] (0/4) Epoch 19, batch 900, loss[loss=2.142, simple_loss=0.2901, pruned_loss=0.04694, codebook_loss=19.5, over 6989.00 frames.], tot_loss[loss=2.165, simple_loss=0.2606, pruned_loss=0.04321, codebook_loss=19.92, over 1394423.79 frames.], batch size: 26, lr: 8.73e-04
+2022-05-27 18:03:06,125 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-19.pt
+2022-05-27 18:03:20,008 INFO [train.py:823] (0/4) Epoch 20, batch 0, loss[loss=2.071, simple_loss=0.2328, pruned_loss=0.02897, codebook_loss=19.25, over 6403.00 frames.], tot_loss[loss=2.071, simple_loss=0.2328, pruned_loss=0.02897, codebook_loss=19.25, over 6403.00 frames.], batch size: 34, lr: 8.51e-04
+2022-05-27 18:04:00,438 INFO [train.py:823] (0/4) Epoch 20, batch 50, loss[loss=2.021, simple_loss=0.2326, pruned_loss=0.03354, codebook_loss=18.71, over 7316.00 frames.], tot_loss[loss=2.128, simple_loss=0.2555, pruned_loss=0.03872, codebook_loss=19.61, over 322231.09 frames.], batch size: 18, lr: 8.49e-04
+2022-05-27 18:04:40,155 INFO [train.py:823] (0/4) Epoch 20, batch 100, loss[loss=2.162, simple_loss=0.2595, pruned_loss=0.05493, codebook_loss=19.78, over 5098.00 frames.], tot_loss[loss=2.142, simple_loss=0.2574, pruned_loss=0.0416, codebook_loss=19.71, over 562810.51 frames.], batch size: 47, lr: 8.48e-04
+2022-05-27 18:05:20,207 INFO [train.py:823] (0/4) Epoch 20, batch 150, loss[loss=2.128, simple_loss=0.2157, pruned_loss=0.02894, codebook_loss=19.91, over 7290.00 frames.], tot_loss[loss=2.146, simple_loss=0.2568, pruned_loss=0.04106, codebook_loss=19.76, over 750807.12 frames.], batch size: 17, lr: 8.47e-04
+2022-05-27 18:05:59,933 INFO [train.py:823] (0/4) Epoch 20, batch 200, loss[loss=2.075, simple_loss=0.2494, pruned_loss=0.03595, codebook_loss=19.14, over 7002.00 frames.], tot_loss[loss=2.139, simple_loss=0.2571, pruned_loss=0.04105, codebook_loss=19.69, over 902540.12 frames.], batch size: 16, lr: 8.46e-04
+2022-05-27 18:06:40,068 INFO [train.py:823] (0/4) Epoch 20, batch 250, loss[loss=2.345, simple_loss=0.2341, pruned_loss=0.03474, codebook_loss=21.93, over 7313.00 frames.], tot_loss[loss=2.159, simple_loss=0.2571, pruned_loss=0.04129, codebook_loss=19.89, over 1017391.23 frames.], batch size: 18, lr: 8.45e-04
+2022-05-27 18:07:19,806 INFO [train.py:823] (0/4) Epoch 20, batch 300, loss[loss=2.037, simple_loss=0.2617, pruned_loss=0.0398, codebook_loss=18.66, over 7301.00 frames.], tot_loss[loss=2.153, simple_loss=0.2572, pruned_loss=0.04058, codebook_loss=19.84, over 1107033.18 frames.], batch size: 22, lr: 8.44e-04
+2022-05-27 18:08:00,058 INFO [train.py:823] (0/4) Epoch 20, batch 350, loss[loss=2.07, simple_loss=0.2665, pruned_loss=0.03629, codebook_loss=19.01, over 7193.00 frames.], tot_loss[loss=2.147, simple_loss=0.2569, pruned_loss=0.04014, codebook_loss=19.79, over 1176627.07 frames.], batch size: 20, lr: 8.43e-04
+2022-05-27 18:08:40,162 INFO [train.py:823] (0/4) Epoch 20, batch 400, loss[loss=2.112, simple_loss=0.2782, pruned_loss=0.04275, codebook_loss=19.3, over 7167.00 frames.], tot_loss[loss=2.145, simple_loss=0.2566, pruned_loss=0.04008, codebook_loss=19.77, over 1231527.08 frames.], batch size: 23, lr: 8.42e-04
+2022-05-27 18:09:20,006 INFO [train.py:823] (0/4) Epoch 20, batch 450, loss[loss=2.121, simple_loss=0.2316, pruned_loss=0.03907, codebook_loss=19.66, over 7178.00 frames.], tot_loss[loss=2.148, simple_loss=0.2578, pruned_loss=0.04089, codebook_loss=19.78, over 1270008.98 frames.], batch size: 17, lr: 8.41e-04
+2022-05-27 18:09:59,740 INFO [train.py:823] (0/4) Epoch 20, batch 500, loss[loss=2.114, simple_loss=0.2456, pruned_loss=0.04135, codebook_loss=19.49, over 7430.00 frames.], tot_loss[loss=2.15, simple_loss=0.258, pruned_loss=0.04094, codebook_loss=19.8, over 1305734.98 frames.], batch size: 18, lr: 8.40e-04
+2022-05-27 18:10:40,050 INFO [train.py:823] (0/4) Epoch 20, batch 550, loss[loss=2.065, simple_loss=0.272, pruned_loss=0.04127, codebook_loss=18.88, over 7153.00 frames.], tot_loss[loss=2.15, simple_loss=0.2569, pruned_loss=0.0406, codebook_loss=19.81, over 1333804.95 frames.], batch size: 23, lr: 8.39e-04
+2022-05-27 18:11:19,647 INFO [train.py:823] (0/4) Epoch 20, batch 600, loss[loss=2.687, simple_loss=0.2628, pruned_loss=0.05788, codebook_loss=24.97, over 7095.00 frames.], tot_loss[loss=2.155, simple_loss=0.2571, pruned_loss=0.04089, codebook_loss=19.85, over 1348871.07 frames.], batch size: 18, lr: 8.38e-04
+2022-05-27 18:11:59,848 INFO [train.py:823] (0/4) Epoch 20, batch 650, loss[loss=2.171, simple_loss=0.2665, pruned_loss=0.04853, codebook_loss=19.9, over 6906.00 frames.], tot_loss[loss=2.15, simple_loss=0.257, pruned_loss=0.04062, codebook_loss=19.8, over 1364727.51 frames.], batch size: 29, lr: 8.37e-04
+2022-05-27 18:12:39,831 INFO [train.py:823] (0/4) Epoch 20, batch 700, loss[loss=2.09, simple_loss=0.2307, pruned_loss=0.03247, codebook_loss=19.42, over 7088.00 frames.], tot_loss[loss=2.148, simple_loss=0.2564, pruned_loss=0.04013, codebook_loss=19.8, over 1378908.50 frames.], batch size: 18, lr: 8.36e-04
+2022-05-27 18:13:20,096 INFO [train.py:823] (0/4) Epoch 20, batch 750, loss[loss=2.03, simple_loss=0.247, pruned_loss=0.03209, codebook_loss=18.74, over 7290.00 frames.], tot_loss[loss=2.14, simple_loss=0.2551, pruned_loss=0.03941, codebook_loss=19.73, over 1389389.22 frames.], batch size: 21, lr: 8.35e-04
+2022-05-27 18:13:59,603 INFO [train.py:823] (0/4) Epoch 20, batch 800, loss[loss=2.091, simple_loss=0.2134, pruned_loss=0.02828, codebook_loss=19.56, over 7019.00 frames.], tot_loss[loss=2.14, simple_loss=0.256, pruned_loss=0.03965, codebook_loss=19.72, over 1397525.28 frames.], batch size: 17, lr: 8.34e-04
+2022-05-27 18:14:41,119 INFO [train.py:823] (0/4) Epoch 20, batch 850, loss[loss=2.165, simple_loss=0.2723, pruned_loss=0.05349, codebook_loss=19.75, over 6998.00 frames.], tot_loss[loss=2.14, simple_loss=0.255, pruned_loss=0.03921, codebook_loss=19.73, over 1400422.08 frames.], batch size: 26, lr: 8.33e-04
+2022-05-27 18:15:20,827 INFO [train.py:823] (0/4) Epoch 20, batch 900, loss[loss=2.188, simple_loss=0.2353, pruned_loss=0.04515, codebook_loss=20.25, over 7201.00 frames.], tot_loss[loss=2.142, simple_loss=0.2553, pruned_loss=0.03981, codebook_loss=19.74, over 1397818.99 frames.], batch size: 16, lr: 8.31e-04
+2022-05-27 18:15:59,747 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-20.pt
+2022-05-27 18:16:14,489 INFO [train.py:823] (0/4) Epoch 21, batch 0, loss[loss=2.058, simple_loss=0.2395, pruned_loss=0.03559, codebook_loss=19.02, over 7187.00 frames.], tot_loss[loss=2.058, simple_loss=0.2395, pruned_loss=0.03559, codebook_loss=19.02, over 7187.00 frames.], batch size: 18, lr: 8.11e-04
+2022-05-27 18:16:54,220 INFO [train.py:823] (0/4) Epoch 21, batch 50, loss[loss=2.108, simple_loss=0.2703, pruned_loss=0.0444, codebook_loss=19.29, over 7203.00 frames.], tot_loss[loss=2.137, simple_loss=0.2525, pruned_loss=0.04, codebook_loss=19.71, over 317930.57 frames.], batch size: 25, lr: 8.10e-04
+2022-05-27 18:17:34,233 INFO [train.py:823] (0/4) Epoch 21, batch 100, loss[loss=2.059, simple_loss=0.254, pruned_loss=0.03198, codebook_loss=19, over 6585.00 frames.], tot_loss[loss=2.113, simple_loss=0.2518, pruned_loss=0.0381, codebook_loss=19.49, over 562256.16 frames.], batch size: 34, lr: 8.09e-04
+2022-05-27 18:18:14,066 INFO [train.py:823] (0/4) Epoch 21, batch 150, loss[loss=2.128, simple_loss=0.2434, pruned_loss=0.03895, codebook_loss=19.68, over 7277.00 frames.], tot_loss[loss=2.123, simple_loss=0.2531, pruned_loss=0.03909, codebook_loss=19.57, over 755931.62 frames.], batch size: 20, lr: 8.08e-04
+2022-05-27 18:18:54,503 INFO [train.py:823] (0/4) Epoch 21, batch 200, loss[loss=2.047, simple_loss=0.2149, pruned_loss=0.03162, codebook_loss=19.08, over 7306.00 frames.], tot_loss[loss=2.124, simple_loss=0.2535, pruned_loss=0.03887, codebook_loss=19.58, over 903699.51 frames.], batch size: 18, lr: 8.07e-04
+2022-05-27 18:19:34,327 INFO [train.py:823] (0/4) Epoch 21, batch 250, loss[loss=2.08, simple_loss=0.2524, pruned_loss=0.03581, codebook_loss=19.18, over 7284.00 frames.], tot_loss[loss=2.119, simple_loss=0.2534, pruned_loss=0.03875, codebook_loss=19.54, over 1011194.91 frames.], batch size: 20, lr: 8.06e-04
+2022-05-27 18:20:14,166 INFO [train.py:823] (0/4) Epoch 21, batch 300, loss[loss=2.1, simple_loss=0.2623, pruned_loss=0.03921, codebook_loss=19.29, over 6567.00 frames.], tot_loss[loss=2.125, simple_loss=0.2546, pruned_loss=0.03897, codebook_loss=19.59, over 1100172.24 frames.], batch size: 34, lr: 8.05e-04
+2022-05-27 18:20:53,789 INFO [train.py:823] (0/4) Epoch 21, batch 350, loss[loss=2.101, simple_loss=0.2628, pruned_loss=0.04372, codebook_loss=19.26, over 7415.00 frames.], tot_loss[loss=2.122, simple_loss=0.2548, pruned_loss=0.03885, codebook_loss=19.56, over 1171574.29 frames.], batch size: 22, lr: 8.04e-04
+2022-05-27 18:21:36,621 INFO [train.py:823] (0/4) Epoch 21, batch 400, loss[loss=2.052, simple_loss=0.2052, pruned_loss=0.02554, codebook_loss=19.23, over 7297.00 frames.], tot_loss[loss=2.132, simple_loss=0.2563, pruned_loss=0.03976, codebook_loss=19.64, over 1226977.76 frames.], batch size: 17, lr: 8.03e-04
+2022-05-27 18:22:17,599 INFO [train.py:823] (0/4) Epoch 21, batch 450, loss[loss=2.245, simple_loss=0.2839, pruned_loss=0.06, codebook_loss=20.43, over 7188.00 frames.], tot_loss[loss=2.136, simple_loss=0.2567, pruned_loss=0.0401, codebook_loss=19.67, over 1270534.63 frames.], batch size: 21, lr: 8.02e-04
+2022-05-27 18:22:57,628 INFO [train.py:823] (0/4) Epoch 21, batch 500, loss[loss=2.083, simple_loss=0.245, pruned_loss=0.03712, codebook_loss=19.23, over 7181.00 frames.], tot_loss[loss=2.134, simple_loss=0.2562, pruned_loss=0.03957, codebook_loss=19.66, over 1303721.79 frames.], batch size: 18, lr: 8.01e-04
+2022-05-27 18:23:37,552 INFO [train.py:823] (0/4) Epoch 21, batch 550, loss[loss=2.003, simple_loss=0.2428, pruned_loss=0.03409, codebook_loss=18.48, over 7380.00 frames.], tot_loss[loss=2.128, simple_loss=0.2555, pruned_loss=0.03929, codebook_loss=19.61, over 1335295.93 frames.], batch size: 21, lr: 8.00e-04
+2022-05-27 18:24:17,708 INFO [train.py:823] (0/4) Epoch 21, batch 600, loss[loss=2.271, simple_loss=0.2904, pruned_loss=0.05898, codebook_loss=20.67, over 6405.00 frames.], tot_loss[loss=2.132, simple_loss=0.2557, pruned_loss=0.03954, codebook_loss=19.64, over 1354161.81 frames.], batch size: 34, lr: 8.00e-04
+2022-05-27 18:24:57,532 INFO [train.py:823] (0/4) Epoch 21, batch 650, loss[loss=2.133, simple_loss=0.2677, pruned_loss=0.03715, codebook_loss=19.62, over 7291.00 frames.], tot_loss[loss=2.136, simple_loss=0.2565, pruned_loss=0.03992, codebook_loss=19.68, over 1369486.73 frames.], batch size: 22, lr: 7.99e-04
+2022-05-27 18:25:37,303 INFO [train.py:823] (0/4) Epoch 21, batch 700, loss[loss=2.131, simple_loss=0.248, pruned_loss=0.03463, codebook_loss=19.73, over 7194.00 frames.], tot_loss[loss=2.139, simple_loss=0.257, pruned_loss=0.04064, codebook_loss=19.7, over 1380593.03 frames.], batch size: 20, lr: 7.98e-04
+2022-05-27 18:26:16,777 INFO [train.py:823] (0/4) Epoch 21, batch 750, loss[loss=2.22, simple_loss=0.2789, pruned_loss=0.04864, codebook_loss=20.32, over 7212.00 frames.], tot_loss[loss=2.132, simple_loss=0.2556, pruned_loss=0.03987, codebook_loss=19.64, over 1379377.52 frames.], batch size: 25, lr: 7.97e-04
+2022-05-27 18:26:56,606 INFO [train.py:823] (0/4) Epoch 21, batch 800, loss[loss=2.211, simple_loss=0.2914, pruned_loss=0.05586, codebook_loss=20.1, over 7337.00 frames.], tot_loss[loss=2.13, simple_loss=0.2555, pruned_loss=0.03973, codebook_loss=19.63, over 1384859.83 frames.], batch size: 23, lr: 7.96e-04
+2022-05-27 18:27:36,610 INFO [train.py:823] (0/4) Epoch 21, batch 850, loss[loss=2.278, simple_loss=0.265, pruned_loss=0.03896, codebook_loss=21.06, over 7197.00 frames.], tot_loss[loss=2.129, simple_loss=0.2553, pruned_loss=0.03972, codebook_loss=19.61, over 1389671.90 frames.], batch size: 20, lr: 7.95e-04
+2022-05-27 18:28:16,401 INFO [train.py:823] (0/4) Epoch 21, batch 900, loss[loss=2.033, simple_loss=0.2332, pruned_loss=0.0304, codebook_loss=18.86, over 7383.00 frames.], tot_loss[loss=2.126, simple_loss=0.2552, pruned_loss=0.03963, codebook_loss=19.59, over 1388439.81 frames.], batch size: 20, lr: 7.94e-04
+2022-05-27 18:28:55,883 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-21.pt
+2022-05-27 18:29:10,581 INFO [train.py:823] (0/4) Epoch 22, batch 0, loss[loss=1.982, simple_loss=0.2512, pruned_loss=0.02818, codebook_loss=18.28, over 7372.00 frames.], tot_loss[loss=1.982, simple_loss=0.2512, pruned_loss=0.02818, codebook_loss=18.28, over 7372.00 frames.], batch size: 21, lr: 7.75e-04
+2022-05-27 18:29:50,491 INFO [train.py:823] (0/4) Epoch 22, batch 50, loss[loss=2.229, simple_loss=0.2749, pruned_loss=0.05253, codebook_loss=20.39, over 7175.00 frames.], tot_loss[loss=2.103, simple_loss=0.2526, pruned_loss=0.03723, codebook_loss=19.4, over 322024.20 frames.], batch size: 22, lr: 7.74e-04
+2022-05-27 18:30:30,762 INFO [train.py:823] (0/4) Epoch 22, batch 100, loss[loss=2.164, simple_loss=0.2562, pruned_loss=0.03585, codebook_loss=20, over 7110.00 frames.], tot_loss[loss=2.106, simple_loss=0.2539, pruned_loss=0.03816, codebook_loss=19.41, over 567534.92 frames.], batch size: 20, lr: 7.73e-04
+2022-05-27 18:31:10,245 INFO [train.py:823] (0/4) Epoch 22, batch 150, loss[loss=2.161, simple_loss=0.2547, pruned_loss=0.05073, codebook_loss=19.83, over 5241.00 frames.], tot_loss[loss=2.121, simple_loss=0.2552, pruned_loss=0.03923, codebook_loss=19.54, over 755485.70 frames.], batch size: 47, lr: 7.73e-04
+2022-05-27 18:31:50,140 INFO [train.py:823] (0/4) Epoch 22, batch 200, loss[loss=2.145, simple_loss=0.251, pruned_loss=0.03505, codebook_loss=19.84, over 7118.00 frames.], tot_loss[loss=2.121, simple_loss=0.2549, pruned_loss=0.03949, codebook_loss=19.54, over 899416.67 frames.], batch size: 20, lr: 7.72e-04
+2022-05-27 18:32:29,931 INFO [train.py:823] (0/4) Epoch 22, batch 250, loss[loss=2.253, simple_loss=0.2432, pruned_loss=0.02962, codebook_loss=21.02, over 7098.00 frames.], tot_loss[loss=2.117, simple_loss=0.2543, pruned_loss=0.03866, codebook_loss=19.51, over 1016438.08 frames.], batch size: 18, lr: 7.71e-04
+2022-05-27 18:33:09,999 INFO [train.py:823] (0/4) Epoch 22, batch 300, loss[loss=2.146, simple_loss=0.2617, pruned_loss=0.04542, codebook_loss=19.7, over 7193.00 frames.], tot_loss[loss=2.115, simple_loss=0.2547, pruned_loss=0.03851, codebook_loss=19.5, over 1103534.23 frames.], batch size: 18, lr: 7.70e-04
+2022-05-27 18:33:49,727 INFO [train.py:823] (0/4) Epoch 22, batch 350, loss[loss=2.056, simple_loss=0.2643, pruned_loss=0.02566, codebook_loss=18.98, over 6958.00 frames.], tot_loss[loss=2.119, simple_loss=0.2554, pruned_loss=0.03939, codebook_loss=19.52, over 1174556.41 frames.], batch size: 29, lr: 7.69e-04
+2022-05-27 18:34:29,896 INFO [train.py:823] (0/4) Epoch 22, batch 400, loss[loss=2.116, simple_loss=0.2511, pruned_loss=0.03888, codebook_loss=19.52, over 7184.00 frames.], tot_loss[loss=2.12, simple_loss=0.2537, pruned_loss=0.03918, codebook_loss=19.54, over 1230866.66 frames.], batch size: 21, lr: 7.68e-04
+2022-05-27 18:35:09,673 INFO [train.py:823] (0/4) Epoch 22, batch 450, loss[loss=2.218, simple_loss=0.2357, pruned_loss=0.04314, codebook_loss=20.57, over 7237.00 frames.], tot_loss[loss=2.118, simple_loss=0.2537, pruned_loss=0.03878, codebook_loss=19.52, over 1276971.09 frames.], batch size: 16, lr: 7.67e-04
+2022-05-27 18:35:49,509 INFO [train.py:823] (0/4) Epoch 22, batch 500, loss[loss=2.183, simple_loss=0.2621, pruned_loss=0.04031, codebook_loss=20.11, over 6512.00 frames.], tot_loss[loss=2.117, simple_loss=0.2533, pruned_loss=0.03861, codebook_loss=19.51, over 1302990.77 frames.], batch size: 34, lr: 7.66e-04
+2022-05-27 18:36:29,451 INFO [train.py:823] (0/4) Epoch 22, batch 550, loss[loss=2.06, simple_loss=0.2552, pruned_loss=0.04729, codebook_loss=18.85, over 6949.00 frames.], tot_loss[loss=2.115, simple_loss=0.2523, pruned_loss=0.03826, codebook_loss=19.51, over 1329987.47 frames.], batch size: 29, lr: 7.65e-04
+2022-05-27 18:37:09,850 INFO [train.py:823] (0/4) Epoch 22, batch 600, loss[loss=2.1, simple_loss=0.2463, pruned_loss=0.04337, codebook_loss=19.33, over 7038.00 frames.], tot_loss[loss=2.114, simple_loss=0.2514, pruned_loss=0.03768, codebook_loss=19.5, over 1349114.58 frames.], batch size: 17, lr: 7.65e-04
+2022-05-27 18:37:49,499 INFO [train.py:823] (0/4) Epoch 22, batch 650, loss[loss=2.205, simple_loss=0.2701, pruned_loss=0.03873, codebook_loss=20.31, over 7108.00 frames.], tot_loss[loss=2.12, simple_loss=0.2525, pruned_loss=0.03864, codebook_loss=19.55, over 1358675.83 frames.], batch size: 20, lr: 7.64e-04
+2022-05-27 18:38:29,563 INFO [train.py:823] (0/4) Epoch 22, batch 700, loss[loss=2.082, simple_loss=0.2531, pruned_loss=0.03823, codebook_loss=19.18, over 7097.00 frames.], tot_loss[loss=2.122, simple_loss=0.2531, pruned_loss=0.0389, codebook_loss=19.56, over 1371207.16 frames.], batch size: 19, lr: 7.63e-04
+2022-05-27 18:39:10,332 INFO [train.py:823] (0/4) Epoch 22, batch 750, loss[loss=2.108, simple_loss=0.2352, pruned_loss=0.03574, codebook_loss=19.54, over 7012.00 frames.], tot_loss[loss=2.117, simple_loss=0.2527, pruned_loss=0.03852, codebook_loss=19.53, over 1380743.17 frames.], batch size: 16, lr: 7.62e-04
+2022-05-27 18:39:50,578 INFO [train.py:823] (0/4) Epoch 22, batch 800, loss[loss=2.087, simple_loss=0.2325, pruned_loss=0.02998, codebook_loss=19.41, over 7381.00 frames.], tot_loss[loss=2.121, simple_loss=0.2533, pruned_loss=0.03852, codebook_loss=19.56, over 1390137.49 frames.], batch size: 20, lr: 7.61e-04
+2022-05-27 18:40:30,224 INFO [train.py:823] (0/4) Epoch 22, batch 850, loss[loss=2.084, simple_loss=0.2646, pruned_loss=0.03617, codebook_loss=19.16, over 6534.00 frames.], tot_loss[loss=2.117, simple_loss=0.2534, pruned_loss=0.03841, codebook_loss=19.52, over 1398696.02 frames.], batch size: 34, lr: 7.60e-04
+2022-05-27 18:41:10,116 INFO [train.py:823] (0/4) Epoch 22, batch 900, loss[loss=2.094, simple_loss=0.2729, pruned_loss=0.04911, codebook_loss=19.08, over 7151.00 frames.], tot_loss[loss=2.118, simple_loss=0.2547, pruned_loss=0.03899, codebook_loss=19.52, over 1403639.89 frames.], batch size: 23, lr: 7.59e-04
+2022-05-27 18:41:49,964 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-22.pt
+2022-05-27 18:42:03,940 INFO [train.py:823] (0/4) Epoch 23, batch 0, loss[loss=2.007, simple_loss=0.2246, pruned_loss=0.02999, codebook_loss=18.65, over 7217.00 frames.], tot_loss[loss=2.007, simple_loss=0.2246, pruned_loss=0.02999, codebook_loss=18.65, over 7217.00 frames.], batch size: 16, lr: 7.42e-04
+2022-05-27 18:42:44,097 INFO [train.py:823] (0/4) Epoch 23, batch 50, loss[loss=2.321, simple_loss=0.2771, pruned_loss=0.04444, codebook_loss=21.38, over 7369.00 frames.], tot_loss[loss=2.167, simple_loss=0.2589, pruned_loss=0.04205, codebook_loss=19.95, over 320355.90 frames.], batch size: 21, lr: 7.41e-04
+2022-05-27 18:43:23,805 INFO [train.py:823] (0/4) Epoch 23, batch 100, loss[loss=2.303, simple_loss=0.2516, pruned_loss=0.03261, codebook_loss=21.45, over 7380.00 frames.], tot_loss[loss=2.12, simple_loss=0.255, pruned_loss=0.03933, codebook_loss=19.53, over 561612.76 frames.], batch size: 20, lr: 7.41e-04
+2022-05-27 18:44:03,964 INFO [train.py:823] (0/4) Epoch 23, batch 150, loss[loss=2.102, simple_loss=0.239, pruned_loss=0.04659, codebook_loss=19.36, over 7306.00 frames.], tot_loss[loss=2.121, simple_loss=0.2552, pruned_loss=0.03932, codebook_loss=19.54, over 752438.03 frames.], batch size: 18, lr: 7.40e-04
+2022-05-27 18:44:43,909 INFO [train.py:823] (0/4) Epoch 23, batch 200, loss[loss=2.096, simple_loss=0.2656, pruned_loss=0.03079, codebook_loss=19.32, over 5231.00 frames.], tot_loss[loss=2.119, simple_loss=0.2538, pruned_loss=0.03848, codebook_loss=19.53, over 899493.95 frames.], batch size: 47, lr: 7.39e-04
+2022-05-27 18:45:24,175 INFO [train.py:823] (0/4) Epoch 23, batch 250, loss[loss=2.201, simple_loss=0.2359, pruned_loss=0.03159, codebook_loss=20.51, over 7094.00 frames.], tot_loss[loss=2.118, simple_loss=0.2534, pruned_loss=0.03806, codebook_loss=19.53, over 1018799.34 frames.], batch size: 18, lr: 7.38e-04
+2022-05-27 18:46:03,751 INFO [train.py:823] (0/4) Epoch 23, batch 300, loss[loss=2.042, simple_loss=0.2521, pruned_loss=0.0343, codebook_loss=18.82, over 7291.00 frames.], tot_loss[loss=2.11, simple_loss=0.254, pruned_loss=0.03761, codebook_loss=19.46, over 1112054.42 frames.], batch size: 22, lr: 7.37e-04
+2022-05-27 18:46:48,079 INFO [train.py:823] (0/4) Epoch 23, batch 350, loss[loss=2.107, simple_loss=0.252, pruned_loss=0.0323, codebook_loss=19.49, over 7273.00 frames.], tot_loss[loss=2.103, simple_loss=0.2526, pruned_loss=0.03708, codebook_loss=19.4, over 1182108.73 frames.], batch size: 20, lr: 7.36e-04
+2022-05-27 18:47:28,150 INFO [train.py:823] (0/4) Epoch 23, batch 400, loss[loss=2.214, simple_loss=0.2252, pruned_loss=0.02542, codebook_loss=20.76, over 7294.00 frames.], tot_loss[loss=2.107, simple_loss=0.2508, pruned_loss=0.03664, codebook_loss=19.45, over 1234502.28 frames.], batch size: 17, lr: 7.36e-04
+2022-05-27 18:48:08,277 INFO [train.py:823] (0/4) Epoch 23, batch 450, loss[loss=2.202, simple_loss=0.2477, pruned_loss=0.04386, codebook_loss=20.34, over 4806.00 frames.], tot_loss[loss=2.11, simple_loss=0.2504, pruned_loss=0.03649, codebook_loss=19.48, over 1273934.66 frames.], batch size: 47, lr: 7.35e-04
+2022-05-27 18:48:47,872 INFO [train.py:823] (0/4) Epoch 23, batch 500, loss[loss=2.291, simple_loss=0.2712, pruned_loss=0.04104, codebook_loss=21.14, over 6532.00 frames.], tot_loss[loss=2.114, simple_loss=0.2516, pruned_loss=0.03712, codebook_loss=19.51, over 1302600.23 frames.], batch size: 34, lr: 7.34e-04
+2022-05-27 18:49:28,073 INFO [train.py:823] (0/4) Epoch 23, batch 550, loss[loss=2.081, simple_loss=0.2626, pruned_loss=0.04501, codebook_loss=19.05, over 7237.00 frames.], tot_loss[loss=2.117, simple_loss=0.253, pruned_loss=0.03753, codebook_loss=19.53, over 1333231.73 frames.], batch size: 24, lr: 7.33e-04
+2022-05-27 18:50:07,713 INFO [train.py:823] (0/4) Epoch 23, batch 600, loss[loss=2.169, simple_loss=0.2729, pruned_loss=0.06081, codebook_loss=19.71, over 4998.00 frames.], tot_loss[loss=2.125, simple_loss=0.2527, pruned_loss=0.03762, codebook_loss=19.61, over 1348882.31 frames.], batch size: 46, lr: 7.32e-04
+2022-05-27 18:50:47,672 INFO [train.py:823] (0/4) Epoch 23, batch 650, loss[loss=2.082, simple_loss=0.2386, pruned_loss=0.0339, codebook_loss=19.29, over 7084.00 frames.], tot_loss[loss=2.116, simple_loss=0.2521, pruned_loss=0.03751, codebook_loss=19.53, over 1363145.61 frames.], batch size: 19, lr: 7.32e-04
+2022-05-27 18:51:27,277 INFO [train.py:823] (0/4) Epoch 23, batch 700, loss[loss=2.033, simple_loss=0.2489, pruned_loss=0.03015, codebook_loss=18.79, over 7000.00 frames.], tot_loss[loss=2.118, simple_loss=0.2521, pruned_loss=0.03768, codebook_loss=19.54, over 1369896.53 frames.], batch size: 16, lr: 7.31e-04
+2022-05-27 18:52:07,629 INFO [train.py:823] (0/4) Epoch 23, batch 750, loss[loss=2.17, simple_loss=0.2723, pruned_loss=0.0458, codebook_loss=19.88, over 5008.00 frames.], tot_loss[loss=2.118, simple_loss=0.2527, pruned_loss=0.03783, codebook_loss=19.54, over 1375698.31 frames.], batch size: 46, lr: 7.30e-04
+2022-05-27 18:52:47,389 INFO [train.py:823] (0/4) Epoch 23, batch 800, loss[loss=2.052, simple_loss=0.2508, pruned_loss=0.03156, codebook_loss=18.95, over 7185.00 frames.], tot_loss[loss=2.113, simple_loss=0.2518, pruned_loss=0.03751, codebook_loss=19.5, over 1388002.29 frames.], batch size: 18, lr: 7.29e-04
+2022-05-27 18:53:27,288 INFO [train.py:823] (0/4) Epoch 23, batch 850, loss[loss=2.062, simple_loss=0.2583, pruned_loss=0.0358, codebook_loss=18.98, over 7148.00 frames.], tot_loss[loss=2.113, simple_loss=0.2522, pruned_loss=0.03762, codebook_loss=19.49, over 1395267.33 frames.], batch size: 23, lr: 7.28e-04
+2022-05-27 18:54:07,048 INFO [train.py:823] (0/4) Epoch 23, batch 900, loss[loss=2.311, simple_loss=0.2272, pruned_loss=0.03517, codebook_loss=21.62, over 7021.00 frames.], tot_loss[loss=2.113, simple_loss=0.2511, pruned_loss=0.03725, codebook_loss=19.5, over 1399933.30 frames.], batch size: 17, lr: 7.28e-04
+2022-05-27 18:54:47,102 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-23.pt
+2022-05-27 18:55:01,286 INFO [train.py:823] (0/4) Epoch 24, batch 0, loss[loss=1.944, simple_loss=0.2082, pruned_loss=0.0214, codebook_loss=18.19, over 7298.00 frames.], tot_loss[loss=1.944, simple_loss=0.2082, pruned_loss=0.0214, codebook_loss=18.19, over 7298.00 frames.], batch size: 18, lr: 7.12e-04
+2022-05-27 18:55:40,715 INFO [train.py:823] (0/4) Epoch 24, batch 50, loss[loss=2.068, simple_loss=0.2319, pruned_loss=0.02759, codebook_loss=19.24, over 7160.00 frames.], tot_loss[loss=2.09, simple_loss=0.2542, pruned_loss=0.03791, codebook_loss=19.25, over 318944.66 frames.], batch size: 17, lr: 7.11e-04
+2022-05-27 18:56:20,767 INFO [train.py:823] (0/4) Epoch 24, batch 100, loss[loss=2.075, simple_loss=0.2507, pruned_loss=0.03422, codebook_loss=19.16, over 6529.00 frames.], tot_loss[loss=2.089, simple_loss=0.2529, pruned_loss=0.03754, codebook_loss=19.25, over 560042.34 frames.], batch size: 34, lr: 7.10e-04
+2022-05-27 18:57:00,454 INFO [train.py:823] (0/4) Epoch 24, batch 150, loss[loss=2.189, simple_loss=0.2604, pruned_loss=0.03429, codebook_loss=20.25, over 6935.00 frames.], tot_loss[loss=2.087, simple_loss=0.2524, pruned_loss=0.03739, codebook_loss=19.23, over 750756.44 frames.], batch size: 29, lr: 7.10e-04
+2022-05-27 18:57:40,624 INFO [train.py:823] (0/4) Epoch 24, batch 200, loss[loss=2.09, simple_loss=0.2548, pruned_loss=0.04002, codebook_loss=19.22, over 7278.00 frames.], tot_loss[loss=2.083, simple_loss=0.2507, pruned_loss=0.03651, codebook_loss=19.21, over 899419.48 frames.], batch size: 21, lr: 7.09e-04
+2022-05-27 18:58:20,122 INFO [train.py:823] (0/4) Epoch 24, batch 250, loss[loss=2.243, simple_loss=0.2285, pruned_loss=0.03154, codebook_loss=20.98, over 7301.00 frames.], tot_loss[loss=2.086, simple_loss=0.2506, pruned_loss=0.03622, codebook_loss=19.24, over 1014984.18 frames.], batch size: 17, lr: 7.08e-04
+2022-05-27 18:59:00,233 INFO [train.py:823] (0/4) Epoch 24, batch 300, loss[loss=2.001, simple_loss=0.2424, pruned_loss=0.02458, codebook_loss=18.55, over 7345.00 frames.], tot_loss[loss=2.099, simple_loss=0.2512, pruned_loss=0.03721, codebook_loss=19.36, over 1099976.33 frames.], batch size: 23, lr: 7.07e-04
+2022-05-27 18:59:40,295 INFO [train.py:823] (0/4) Epoch 24, batch 350, loss[loss=2.025, simple_loss=0.2253, pruned_loss=0.0303, codebook_loss=18.82, over 7284.00 frames.], tot_loss[loss=2.1, simple_loss=0.251, pruned_loss=0.03693, codebook_loss=19.38, over 1175030.11 frames.], batch size: 17, lr: 7.07e-04
+2022-05-27 19:00:20,408 INFO [train.py:823] (0/4) Epoch 24, batch 400, loss[loss=2.058, simple_loss=0.2719, pruned_loss=0.03293, codebook_loss=18.89, over 7342.00 frames.], tot_loss[loss=2.095, simple_loss=0.2502, pruned_loss=0.03685, codebook_loss=19.33, over 1227640.77 frames.], batch size: 23, lr: 7.06e-04
+2022-05-27 19:01:00,213 INFO [train.py:823] (0/4) Epoch 24, batch 450, loss[loss=2.237, simple_loss=0.2479, pruned_loss=0.03653, codebook_loss=20.77, over 7175.00 frames.], tot_loss[loss=2.093, simple_loss=0.2498, pruned_loss=0.03682, codebook_loss=19.32, over 1269126.81 frames.], batch size: 18, lr: 7.05e-04
+2022-05-27 19:01:40,601 INFO [train.py:823] (0/4) Epoch 24, batch 500, loss[loss=2.028, simple_loss=0.2425, pruned_loss=0.03395, codebook_loss=18.72, over 7278.00 frames.], tot_loss[loss=2.093, simple_loss=0.2508, pruned_loss=0.03715, codebook_loss=19.31, over 1304389.75 frames.], batch size: 21, lr: 7.04e-04
+2022-05-27 19:02:20,515 INFO [train.py:823] (0/4) Epoch 24, batch 550, loss[loss=2.024, simple_loss=0.2596, pruned_loss=0.02472, codebook_loss=18.7, over 6526.00 frames.], tot_loss[loss=2.097, simple_loss=0.2512, pruned_loss=0.03722, codebook_loss=19.34, over 1327589.75 frames.], batch size: 34, lr: 7.04e-04
+2022-05-27 19:03:01,844 INFO [train.py:823] (0/4) Epoch 24, batch 600, loss[loss=2.063, simple_loss=0.2527, pruned_loss=0.04293, codebook_loss=18.93, over 7145.00 frames.], tot_loss[loss=2.094, simple_loss=0.2509, pruned_loss=0.03688, codebook_loss=19.31, over 1345283.08 frames.], batch size: 23, lr: 7.03e-04
+2022-05-27 19:03:41,788 INFO [train.py:823] (0/4) Epoch 24, batch 650, loss[loss=2.079, simple_loss=0.239, pruned_loss=0.02797, codebook_loss=19.31, over 7106.00 frames.], tot_loss[loss=2.097, simple_loss=0.2511, pruned_loss=0.03719, codebook_loss=19.34, over 1357212.65 frames.], batch size: 19, lr: 7.02e-04
+2022-05-27 19:04:21,931 INFO [train.py:823] (0/4) Epoch 24, batch 700, loss[loss=2.017, simple_loss=0.236, pruned_loss=0.02742, codebook_loss=18.71, over 7179.00 frames.], tot_loss[loss=2.097, simple_loss=0.2516, pruned_loss=0.03699, codebook_loss=19.34, over 1371079.36 frames.], batch size: 22, lr: 7.01e-04
+2022-05-27 19:05:01,666 INFO [train.py:823] (0/4) Epoch 24, batch 750, loss[loss=2.102, simple_loss=0.2431, pruned_loss=0.03928, codebook_loss=19.41, over 7098.00 frames.], tot_loss[loss=2.092, simple_loss=0.2514, pruned_loss=0.03672, codebook_loss=19.29, over 1384734.85 frames.], batch size: 20, lr: 7.01e-04
+2022-05-27 19:05:41,784 INFO [train.py:823] (0/4) Epoch 24, batch 800, loss[loss=2.11, simple_loss=0.2105, pruned_loss=0.02543, codebook_loss=19.79, over 6869.00 frames.], tot_loss[loss=2.094, simple_loss=0.2505, pruned_loss=0.03644, codebook_loss=19.33, over 1392357.04 frames.], batch size: 15, lr: 7.00e-04
+2022-05-27 19:06:21,572 INFO [train.py:823] (0/4) Epoch 24, batch 850, loss[loss=1.998, simple_loss=0.249, pruned_loss=0.02696, codebook_loss=18.46, over 7112.00 frames.], tot_loss[loss=2.094, simple_loss=0.2501, pruned_loss=0.0363, codebook_loss=19.33, over 1395103.40 frames.], batch size: 20, lr: 6.99e-04
+2022-05-27 19:07:01,736 INFO [train.py:823] (0/4) Epoch 24, batch 900, loss[loss=2.309, simple_loss=0.2618, pruned_loss=0.04811, codebook_loss=21.3, over 6492.00 frames.], tot_loss[loss=2.097, simple_loss=0.2508, pruned_loss=0.03691, codebook_loss=19.35, over 1398601.38 frames.], batch size: 35, lr: 6.98e-04
+2022-05-27 19:07:42,329 INFO [train.py:823] (0/4) Epoch 24, batch 950, loss[loss=2.023, simple_loss=0.2321, pruned_loss=0.02937, codebook_loss=18.78, over 7093.00 frames.], tot_loss[loss=2.101, simple_loss=0.2513, pruned_loss=0.03693, codebook_loss=19.39, over 1393116.50 frames.], batch size: 18, lr: 6.98e-04
+2022-05-27 19:07:43,509 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-24.pt
+2022-05-27 19:07:57,696 INFO [train.py:823] (0/4) Epoch 25, batch 0, loss[loss=1.935, simple_loss=0.2519, pruned_loss=0.02589, codebook_loss=17.83, over 7276.00 frames.], tot_loss[loss=1.935, simple_loss=0.2519, pruned_loss=0.02589, codebook_loss=17.83, over 7276.00 frames.], batch size: 21, lr: 6.84e-04
+2022-05-27 19:08:37,516 INFO [train.py:823] (0/4) Epoch 25, batch 50, loss[loss=2.057, simple_loss=0.2309, pruned_loss=0.03467, codebook_loss=19.06, over 7312.00 frames.], tot_loss[loss=2.1, simple_loss=0.2518, pruned_loss=0.03607, codebook_loss=19.38, over 324407.99 frames.], batch size: 17, lr: 6.83e-04
+2022-05-27 19:09:17,978 INFO [train.py:823] (0/4) Epoch 25, batch 100, loss[loss=2.02, simple_loss=0.2391, pruned_loss=0.03738, codebook_loss=18.63, over 6853.00 frames.], tot_loss[loss=2.098, simple_loss=0.2503, pruned_loss=0.03624, codebook_loss=19.36, over 564700.38 frames.], batch size: 15, lr: 6.82e-04
+2022-05-27 19:09:58,097 INFO [train.py:823] (0/4) Epoch 25, batch 150, loss[loss=2.108, simple_loss=0.2703, pruned_loss=0.0288, codebook_loss=19.44, over 7303.00 frames.], tot_loss[loss=2.097, simple_loss=0.2489, pruned_loss=0.03568, codebook_loss=19.37, over 758738.38 frames.], batch size: 22, lr: 6.82e-04
+2022-05-27 19:10:38,453 INFO [train.py:823] (0/4) Epoch 25, batch 200, loss[loss=2.026, simple_loss=0.2631, pruned_loss=0.03726, codebook_loss=18.57, over 7285.00 frames.], tot_loss[loss=2.084, simple_loss=0.2486, pruned_loss=0.0348, codebook_loss=19.25, over 911267.01 frames.], batch size: 21, lr: 6.81e-04
+2022-05-27 19:11:21,035 INFO [train.py:823] (0/4) Epoch 25, batch 250, loss[loss=2.15, simple_loss=0.2384, pruned_loss=0.04122, codebook_loss=19.89, over 7295.00 frames.], tot_loss[loss=2.079, simple_loss=0.2486, pruned_loss=0.03506, codebook_loss=19.2, over 1022579.21 frames.], batch size: 17, lr: 6.80e-04
+2022-05-27 19:12:04,149 INFO [train.py:823] (0/4) Epoch 25, batch 300, loss[loss=1.983, simple_loss=0.2412, pruned_loss=0.02592, codebook_loss=18.37, over 7282.00 frames.], tot_loss[loss=2.079, simple_loss=0.2491, pruned_loss=0.03524, codebook_loss=19.19, over 1116799.39 frames.], batch size: 21, lr: 6.80e-04
+2022-05-27 19:12:48,196 INFO [train.py:823] (0/4) Epoch 25, batch 350, loss[loss=2.367, simple_loss=0.2921, pruned_loss=0.0611, codebook_loss=21.6, over 7125.00 frames.], tot_loss[loss=2.079, simple_loss=0.2493, pruned_loss=0.03531, codebook_loss=19.19, over 1182651.37 frames.], batch size: 23, lr: 6.79e-04
+2022-05-27 19:13:30,855 INFO [train.py:823] (0/4) Epoch 25, batch 400, loss[loss=1.934, simple_loss=0.2482, pruned_loss=0.02471, codebook_loss=17.85, over 7172.00 frames.], tot_loss[loss=2.079, simple_loss=0.2511, pruned_loss=0.03547, codebook_loss=19.18, over 1238642.61 frames.], batch size: 25, lr: 6.78e-04
+2022-05-27 19:14:15,079 INFO [train.py:823] (0/4) Epoch 25, batch 450, loss[loss=2.027, simple_loss=0.2091, pruned_loss=0.02679, codebook_loss=18.96, over 7215.00 frames.], tot_loss[loss=2.085, simple_loss=0.2517, pruned_loss=0.03574, codebook_loss=19.24, over 1269974.31 frames.], batch size: 16, lr: 6.77e-04
+2022-05-27 19:14:57,017 INFO [train.py:823] (0/4) Epoch 25, batch 500, loss[loss=2.148, simple_loss=0.2379, pruned_loss=0.04474, codebook_loss=19.84, over 7007.00 frames.], tot_loss[loss=2.084, simple_loss=0.2511, pruned_loss=0.03562, codebook_loss=19.22, over 1302845.67 frames.], batch size: 16, lr: 6.77e-04
+2022-05-27 19:15:42,066 INFO [train.py:823] (0/4) Epoch 25, batch 550, loss[loss=2.479, simple_loss=0.2687, pruned_loss=0.04638, codebook_loss=22.99, over 7181.00 frames.], tot_loss[loss=2.091, simple_loss=0.2501, pruned_loss=0.03562, codebook_loss=19.3, over 1330646.00 frames.], batch size: 21, lr: 6.76e-04
+2022-05-27 19:16:24,397 INFO [train.py:823] (0/4) Epoch 25, batch 600, loss[loss=2.017, simple_loss=0.2476, pruned_loss=0.02554, codebook_loss=18.67, over 7288.00 frames.], tot_loss[loss=2.094, simple_loss=0.2497, pruned_loss=0.03556, codebook_loss=19.33, over 1343376.85 frames.], batch size: 21, lr: 6.75e-04
+2022-05-27 19:17:05,138 INFO [train.py:823] (0/4) Epoch 25, batch 650, loss[loss=2.257, simple_loss=0.2523, pruned_loss=0.03379, codebook_loss=20.97, over 7271.00 frames.], tot_loss[loss=2.095, simple_loss=0.2504, pruned_loss=0.03564, codebook_loss=19.34, over 1357928.56 frames.], batch size: 20, lr: 6.75e-04
+2022-05-27 19:17:48,181 INFO [train.py:823] (0/4) Epoch 25, batch 700, loss[loss=1.96, simple_loss=0.2151, pruned_loss=0.0225, codebook_loss=18.3, over 7144.00 frames.], tot_loss[loss=2.092, simple_loss=0.2501, pruned_loss=0.03561, codebook_loss=19.31, over 1369519.92 frames.], batch size: 17, lr: 6.74e-04
+2022-05-27 19:18:28,138 INFO [train.py:823] (0/4) Epoch 25, batch 750, loss[loss=2.102, simple_loss=0.2468, pruned_loss=0.03399, codebook_loss=19.45, over 7373.00 frames.], tot_loss[loss=2.089, simple_loss=0.2487, pruned_loss=0.0352, codebook_loss=19.29, over 1377975.32 frames.], batch size: 20, lr: 6.73e-04
+2022-05-27 19:19:08,390 INFO [train.py:823] (0/4) Epoch 25, batch 800, loss[loss=2.058, simple_loss=0.2549, pruned_loss=0.0365, codebook_loss=18.94, over 7187.00 frames.], tot_loss[loss=2.088, simple_loss=0.2485, pruned_loss=0.03506, codebook_loss=19.29, over 1389944.32 frames.], batch size: 21, lr: 6.73e-04
+2022-05-27 19:19:48,338 INFO [train.py:823] (0/4) Epoch 25, batch 850, loss[loss=2.261, simple_loss=0.2588, pruned_loss=0.04181, codebook_loss=20.9, over 7203.00 frames.], tot_loss[loss=2.088, simple_loss=0.2495, pruned_loss=0.03536, codebook_loss=19.28, over 1396236.11 frames.], batch size: 18, lr: 6.72e-04
+2022-05-27 19:20:28,231 INFO [train.py:823] (0/4) Epoch 25, batch 900, loss[loss=2.007, simple_loss=0.2541, pruned_loss=0.02722, codebook_loss=18.53, over 6336.00 frames.], tot_loss[loss=2.088, simple_loss=0.2494, pruned_loss=0.03555, codebook_loss=19.28, over 1395536.40 frames.], batch size: 34, lr: 6.71e-04
+2022-05-27 19:21:08,755 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-25.pt
+2022-05-27 19:21:22,336 INFO [train.py:823] (0/4) Epoch 26, batch 0, loss[loss=2.294, simple_loss=0.2063, pruned_loss=0.02519, codebook_loss=21.66, over 7317.00 frames.], tot_loss[loss=2.294, simple_loss=0.2063, pruned_loss=0.02519, codebook_loss=21.66, over 7317.00 frames.], batch size: 18, lr: 6.58e-04
+2022-05-27 19:22:04,003 INFO [train.py:823] (0/4) Epoch 26, batch 50, loss[loss=1.968, simple_loss=0.2406, pruned_loss=0.03059, codebook_loss=18.17, over 7382.00 frames.], tot_loss[loss=2.064, simple_loss=0.2431, pruned_loss=0.03259, codebook_loss=19.1, over 323424.57 frames.], batch size: 20, lr: 6.57e-04
+2022-05-27 19:22:43,983 INFO [train.py:823] (0/4) Epoch 26, batch 100, loss[loss=1.995, simple_loss=0.2486, pruned_loss=0.03183, codebook_loss=18.39, over 7250.00 frames.], tot_loss[loss=2.068, simple_loss=0.246, pruned_loss=0.03378, codebook_loss=19.11, over 567408.38 frames.], batch size: 25, lr: 6.56e-04
+2022-05-27 19:23:24,144 INFO [train.py:823] (0/4) Epoch 26, batch 150, loss[loss=2.021, simple_loss=0.2525, pruned_loss=0.03714, codebook_loss=18.58, over 7192.00 frames.], tot_loss[loss=2.076, simple_loss=0.2449, pruned_loss=0.03391, codebook_loss=19.2, over 754237.90 frames.], batch size: 25, lr: 6.56e-04
+2022-05-27 19:24:03,986 INFO [train.py:823] (0/4) Epoch 26, batch 200, loss[loss=2.259, simple_loss=0.2326, pruned_loss=0.03257, codebook_loss=21.1, over 7103.00 frames.], tot_loss[loss=2.081, simple_loss=0.2457, pruned_loss=0.03429, codebook_loss=19.24, over 899819.24 frames.], batch size: 18, lr: 6.55e-04
+2022-05-27 19:24:44,127 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/checkpoint-24000.pt
+2022-05-27 19:24:47,077 INFO [train.py:823] (0/4) Epoch 26, batch 250, loss[loss=2.031, simple_loss=0.2564, pruned_loss=0.0314, codebook_loss=18.71, over 7444.00 frames.], tot_loss[loss=2.086, simple_loss=0.247, pruned_loss=0.03518, codebook_loss=19.27, over 1015963.08 frames.], batch size: 22, lr: 6.55e-04
+2022-05-27 19:25:27,420 INFO [train.py:823] (0/4) Epoch 26, batch 300, loss[loss=2.129, simple_loss=0.2465, pruned_loss=0.03151, codebook_loss=19.75, over 7112.00 frames.], tot_loss[loss=2.088, simple_loss=0.2479, pruned_loss=0.03518, codebook_loss=19.29, over 1106723.00 frames.], batch size: 20, lr: 6.54e-04
+2022-05-27 19:26:07,817 INFO [train.py:823] (0/4) Epoch 26, batch 350, loss[loss=2.502, simple_loss=0.2822, pruned_loss=0.05382, codebook_loss=23.07, over 6578.00 frames.], tot_loss[loss=2.088, simple_loss=0.2486, pruned_loss=0.03535, codebook_loss=19.28, over 1179176.84 frames.], batch size: 34, lr: 6.53e-04
+2022-05-27 19:26:47,591 INFO [train.py:823] (0/4) Epoch 26, batch 400, loss[loss=2.015, simple_loss=0.2568, pruned_loss=0.03709, codebook_loss=18.5, over 7161.00 frames.], tot_loss[loss=2.08, simple_loss=0.248, pruned_loss=0.03519, codebook_loss=19.21, over 1235298.68 frames.], batch size: 23, lr: 6.53e-04
+2022-05-27 19:27:29,052 INFO [train.py:823] (0/4) Epoch 26, batch 450, loss[loss=2.059, simple_loss=0.2541, pruned_loss=0.0318, codebook_loss=19, over 7186.00 frames.], tot_loss[loss=2.083, simple_loss=0.248, pruned_loss=0.03527, codebook_loss=19.24, over 1274916.24 frames.], batch size: 21, lr: 6.52e-04
+2022-05-27 19:28:08,952 INFO [train.py:823] (0/4) Epoch 26, batch 500, loss[loss=2.096, simple_loss=0.2868, pruned_loss=0.05005, codebook_loss=19.03, over 7053.00 frames.], tot_loss[loss=2.082, simple_loss=0.2489, pruned_loss=0.03557, codebook_loss=19.22, over 1305317.20 frames.], batch size: 26, lr: 6.51e-04
+2022-05-27 19:28:49,441 INFO [train.py:823] (0/4) Epoch 26, batch 550, loss[loss=2.037, simple_loss=0.2261, pruned_loss=0.03493, codebook_loss=18.89, over 7008.00 frames.], tot_loss[loss=2.081, simple_loss=0.2485, pruned_loss=0.03551, codebook_loss=19.22, over 1329279.99 frames.], batch size: 16, lr: 6.51e-04
+2022-05-27 19:29:29,452 INFO [train.py:823] (0/4) Epoch 26, batch 600, loss[loss=2.088, simple_loss=0.2599, pruned_loss=0.04069, codebook_loss=19.18, over 7308.00 frames.], tot_loss[loss=2.079, simple_loss=0.2485, pruned_loss=0.03527, codebook_loss=19.2, over 1348421.09 frames.], batch size: 22, lr: 6.50e-04
+2022-05-27 19:30:09,631 INFO [train.py:823] (0/4) Epoch 26, batch 650, loss[loss=2.222, simple_loss=0.2552, pruned_loss=0.04108, codebook_loss=20.53, over 7347.00 frames.], tot_loss[loss=2.079, simple_loss=0.2473, pruned_loss=0.03534, codebook_loss=19.2, over 1358421.28 frames.], batch size: 23, lr: 6.49e-04
+2022-05-27 19:30:49,388 INFO [train.py:823] (0/4) Epoch 26, batch 700, loss[loss=2.133, simple_loss=0.2725, pruned_loss=0.04068, codebook_loss=19.56, over 7072.00 frames.], tot_loss[loss=2.09, simple_loss=0.2495, pruned_loss=0.03613, codebook_loss=19.29, over 1371558.62 frames.], batch size: 26, lr: 6.49e-04
+2022-05-27 19:31:29,444 INFO [train.py:823] (0/4) Epoch 26, batch 750, loss[loss=2.004, simple_loss=0.2525, pruned_loss=0.03189, codebook_loss=18.46, over 7289.00 frames.], tot_loss[loss=2.093, simple_loss=0.2498, pruned_loss=0.03617, codebook_loss=19.32, over 1375501.51 frames.], batch size: 19, lr: 6.48e-04
+2022-05-27 19:32:09,214 INFO [train.py:823] (0/4) Epoch 26, batch 800, loss[loss=1.965, simple_loss=0.2097, pruned_loss=0.01884, codebook_loss=18.42, over 6828.00 frames.], tot_loss[loss=2.092, simple_loss=0.2494, pruned_loss=0.03612, codebook_loss=19.31, over 1383220.07 frames.], batch size: 15, lr: 6.47e-04
+2022-05-27 19:32:49,509 INFO [train.py:823] (0/4) Epoch 26, batch 850, loss[loss=2.022, simple_loss=0.2302, pruned_loss=0.02762, codebook_loss=18.79, over 7221.00 frames.], tot_loss[loss=2.084, simple_loss=0.2483, pruned_loss=0.03546, codebook_loss=19.24, over 1395019.81 frames.], batch size: 16, lr: 6.47e-04
+2022-05-27 19:33:29,196 INFO [train.py:823] (0/4) Epoch 26, batch 900, loss[loss=2.065, simple_loss=0.221, pruned_loss=0.02398, codebook_loss=19.3, over 7012.00 frames.], tot_loss[loss=2.086, simple_loss=0.2488, pruned_loss=0.03528, codebook_loss=19.26, over 1395743.60 frames.], batch size: 17, lr: 6.46e-04
+2022-05-27 19:34:08,977 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-26.pt
+2022-05-27 19:34:23,327 INFO [train.py:823] (0/4) Epoch 27, batch 0, loss[loss=2.05, simple_loss=0.2355, pruned_loss=0.02494, codebook_loss=19.08, over 7192.00 frames.], tot_loss[loss=2.05, simple_loss=0.2355, pruned_loss=0.02494, codebook_loss=19.08, over 7192.00 frames.], batch size: 18, lr: 6.34e-04
+2022-05-27 19:35:03,224 INFO [train.py:823] (0/4) Epoch 27, batch 50, loss[loss=2.03, simple_loss=0.2267, pruned_loss=0.02934, codebook_loss=18.87, over 7204.00 frames.], tot_loss[loss=2.049, simple_loss=0.245, pruned_loss=0.03253, codebook_loss=18.94, over 321783.46 frames.], batch size: 18, lr: 6.33e-04
+2022-05-27 19:35:43,058 INFO [train.py:823] (0/4) Epoch 27, batch 100, loss[loss=1.934, simple_loss=0.2413, pruned_loss=0.02203, codebook_loss=17.92, over 7183.00 frames.], tot_loss[loss=2.047, simple_loss=0.2472, pruned_loss=0.03276, codebook_loss=18.9, over 564393.39 frames.], batch size: 25, lr: 6.32e-04
+2022-05-27 19:36:26,846 INFO [train.py:823] (0/4) Epoch 27, batch 150, loss[loss=2.112, simple_loss=0.2355, pruned_loss=0.03294, codebook_loss=19.62, over 7303.00 frames.], tot_loss[loss=2.048, simple_loss=0.2467, pruned_loss=0.03288, codebook_loss=18.92, over 753814.56 frames.], batch size: 18, lr: 6.32e-04
+2022-05-27 19:37:06,684 INFO [train.py:823] (0/4) Epoch 27, batch 200, loss[loss=2.104, simple_loss=0.2523, pruned_loss=0.03736, codebook_loss=19.4, over 7418.00 frames.], tot_loss[loss=2.063, simple_loss=0.2484, pruned_loss=0.03387, codebook_loss=19.05, over 901278.48 frames.], batch size: 22, lr: 6.31e-04
+2022-05-27 19:37:46,510 INFO [train.py:823] (0/4) Epoch 27, batch 250, loss[loss=1.97, simple_loss=0.2345, pruned_loss=0.02633, codebook_loss=18.27, over 7016.00 frames.], tot_loss[loss=2.065, simple_loss=0.2495, pruned_loss=0.03433, codebook_loss=19.06, over 1013290.05 frames.], batch size: 17, lr: 6.31e-04
+2022-05-27 19:38:27,096 INFO [train.py:823] (0/4) Epoch 27, batch 300, loss[loss=1.974, simple_loss=0.2324, pruned_loss=0.02266, codebook_loss=18.35, over 7372.00 frames.], tot_loss[loss=2.07, simple_loss=0.2481, pruned_loss=0.03413, codebook_loss=19.12, over 1107020.83 frames.], batch size: 21, lr: 6.30e-04
+2022-05-27 19:39:06,908 INFO [train.py:823] (0/4) Epoch 27, batch 350, loss[loss=2.014, simple_loss=0.2354, pruned_loss=0.03543, codebook_loss=18.61, over 7290.00 frames.], tot_loss[loss=2.074, simple_loss=0.2472, pruned_loss=0.03364, codebook_loss=19.17, over 1177813.66 frames.], batch size: 19, lr: 6.29e-04
+2022-05-27 19:39:47,105 INFO [train.py:823] (0/4) Epoch 27, batch 400, loss[loss=2.004, simple_loss=0.2414, pruned_loss=0.03102, codebook_loss=18.52, over 7275.00 frames.], tot_loss[loss=2.082, simple_loss=0.2477, pruned_loss=0.0345, codebook_loss=19.23, over 1232280.29 frames.], batch size: 20, lr: 6.29e-04
+2022-05-27 19:40:27,038 INFO [train.py:823] (0/4) Epoch 27, batch 450, loss[loss=2.086, simple_loss=0.2549, pruned_loss=0.04692, codebook_loss=19.12, over 4852.00 frames.], tot_loss[loss=2.075, simple_loss=0.2461, pruned_loss=0.03362, codebook_loss=19.18, over 1275684.13 frames.], batch size: 46, lr: 6.28e-04
+2022-05-27 19:41:06,876 INFO [train.py:823] (0/4) Epoch 27, batch 500, loss[loss=2.851, simple_loss=0.3363, pruned_loss=0.1118, codebook_loss=25.71, over 7159.00 frames.], tot_loss[loss=2.083, simple_loss=0.2469, pruned_loss=0.03439, codebook_loss=19.26, over 1300678.73 frames.], batch size: 23, lr: 6.28e-04
+2022-05-27 19:41:46,717 INFO [train.py:823] (0/4) Epoch 27, batch 550, loss[loss=1.933, simple_loss=0.2405, pruned_loss=0.02412, codebook_loss=17.89, over 7294.00 frames.], tot_loss[loss=2.079, simple_loss=0.2481, pruned_loss=0.03471, codebook_loss=19.21, over 1329735.25 frames.], batch size: 20, lr: 6.27e-04
+2022-05-27 19:42:27,041 INFO [train.py:823] (0/4) Epoch 27, batch 600, loss[loss=1.954, simple_loss=0.2198, pruned_loss=0.02424, codebook_loss=18.2, over 7308.00 frames.], tot_loss[loss=2.08, simple_loss=0.248, pruned_loss=0.03454, codebook_loss=19.21, over 1356063.87 frames.], batch size: 18, lr: 6.26e-04
+2022-05-27 19:43:06,778 INFO [train.py:823] (0/4) Epoch 27, batch 650, loss[loss=2.148, simple_loss=0.2549, pruned_loss=0.02674, codebook_loss=19.94, over 7198.00 frames.], tot_loss[loss=2.075, simple_loss=0.2482, pruned_loss=0.03435, codebook_loss=19.16, over 1374137.74 frames.], batch size: 19, lr: 6.26e-04
+2022-05-27 19:43:47,242 INFO [train.py:823] (0/4) Epoch 27, batch 700, loss[loss=2.092, simple_loss=0.2651, pruned_loss=0.03308, codebook_loss=19.26, over 7375.00 frames.], tot_loss[loss=2.081, simple_loss=0.2484, pruned_loss=0.0348, codebook_loss=19.22, over 1384426.58 frames.], batch size: 21, lr: 6.25e-04
+2022-05-27 19:44:26,955 INFO [train.py:823] (0/4) Epoch 27, batch 750, loss[loss=2.244, simple_loss=0.2507, pruned_loss=0.0375, codebook_loss=20.81, over 7199.00 frames.], tot_loss[loss=2.08, simple_loss=0.248, pruned_loss=0.03473, codebook_loss=19.22, over 1391860.74 frames.], batch size: 19, lr: 6.25e-04
+2022-05-27 19:45:07,001 INFO [train.py:823] (0/4) Epoch 27, batch 800, loss[loss=2.074, simple_loss=0.273, pruned_loss=0.03775, codebook_loss=19, over 7159.00 frames.], tot_loss[loss=2.081, simple_loss=0.2491, pruned_loss=0.0352, codebook_loss=19.21, over 1393794.27 frames.], batch size: 23, lr: 6.24e-04
+2022-05-27 19:45:46,840 INFO [train.py:823] (0/4) Epoch 27, batch 850, loss[loss=2.012, simple_loss=0.2387, pruned_loss=0.02777, codebook_loss=18.65, over 7113.00 frames.], tot_loss[loss=2.075, simple_loss=0.2478, pruned_loss=0.03456, codebook_loss=19.16, over 1397120.42 frames.], batch size: 20, lr: 6.23e-04
+2022-05-27 19:46:26,671 INFO [train.py:823] (0/4) Epoch 27, batch 900, loss[loss=2.097, simple_loss=0.2138, pruned_loss=0.0258, codebook_loss=19.64, over 7295.00 frames.], tot_loss[loss=2.075, simple_loss=0.2472, pruned_loss=0.03437, codebook_loss=19.17, over 1398718.14 frames.], batch size: 17, lr: 6.23e-04
+2022-05-27 19:47:06,530 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-27.pt
+2022-05-27 19:47:20,706 INFO [train.py:823] (0/4) Epoch 28, batch 0, loss[loss=1.979, simple_loss=0.2403, pruned_loss=0.02785, codebook_loss=18.31, over 7193.00 frames.], tot_loss[loss=1.979, simple_loss=0.2403, pruned_loss=0.02785, codebook_loss=18.31, over 7193.00 frames.], batch size: 20, lr: 6.11e-04
+2022-05-27 19:48:00,489 INFO [train.py:823] (0/4) Epoch 28, batch 50, loss[loss=2.268, simple_loss=0.26, pruned_loss=0.04493, codebook_loss=20.93, over 7109.00 frames.], tot_loss[loss=2.046, simple_loss=0.2456, pruned_loss=0.0332, codebook_loss=18.9, over 315948.05 frames.], batch size: 20, lr: 6.11e-04
+2022-05-27 19:48:40,431 INFO [train.py:823] (0/4) Epoch 28, batch 100, loss[loss=1.964, simple_loss=0.2456, pruned_loss=0.02722, codebook_loss=18.14, over 7031.00 frames.], tot_loss[loss=2.049, simple_loss=0.2462, pruned_loss=0.03349, codebook_loss=18.92, over 561115.17 frames.], batch size: 26, lr: 6.10e-04
+2022-05-27 19:49:20,578 INFO [train.py:823] (0/4) Epoch 28, batch 150, loss[loss=2.091, simple_loss=0.2467, pruned_loss=0.05823, codebook_loss=19.09, over 4702.00 frames.], tot_loss[loss=2.059, simple_loss=0.2462, pruned_loss=0.03404, codebook_loss=19.01, over 749097.80 frames.], batch size: 46, lr: 6.09e-04
+2022-05-27 19:50:00,317 INFO [train.py:823] (0/4) Epoch 28, batch 200, loss[loss=2.258, simple_loss=0.2358, pruned_loss=0.0315, codebook_loss=21.08, over 7200.00 frames.], tot_loss[loss=2.054, simple_loss=0.2455, pruned_loss=0.03351, codebook_loss=18.97, over 900055.03 frames.], batch size: 20, lr: 6.09e-04
+2022-05-27 19:50:40,653 INFO [train.py:823] (0/4) Epoch 28, batch 250, loss[loss=2.066, simple_loss=0.2615, pruned_loss=0.04168, codebook_loss=18.94, over 7335.00 frames.], tot_loss[loss=2.051, simple_loss=0.2456, pruned_loss=0.03341, codebook_loss=18.95, over 1015074.57 frames.], batch size: 23, lr: 6.08e-04
+2022-05-27 19:51:22,048 INFO [train.py:823] (0/4) Epoch 28, batch 300, loss[loss=2.027, simple_loss=0.2559, pruned_loss=0.0374, codebook_loss=18.61, over 6951.00 frames.], tot_loss[loss=2.056, simple_loss=0.2464, pruned_loss=0.034, codebook_loss=18.99, over 1102984.22 frames.], batch size: 29, lr: 6.08e-04
+2022-05-27 19:52:02,235 INFO [train.py:823] (0/4) Epoch 28, batch 350, loss[loss=2.117, simple_loss=0.2574, pruned_loss=0.03615, codebook_loss=19.52, over 7347.00 frames.], tot_loss[loss=2.058, simple_loss=0.2458, pruned_loss=0.03377, codebook_loss=19.01, over 1173709.74 frames.], batch size: 23, lr: 6.07e-04
+2022-05-27 19:52:42,270 INFO [train.py:823] (0/4) Epoch 28, batch 400, loss[loss=1.93, simple_loss=0.2548, pruned_loss=0.02458, codebook_loss=17.78, over 7291.00 frames.], tot_loss[loss=2.061, simple_loss=0.2456, pruned_loss=0.03366, codebook_loss=19.04, over 1228175.41 frames.], batch size: 21, lr: 6.07e-04
+2022-05-27 19:53:22,309 INFO [train.py:823] (0/4) Epoch 28, batch 450, loss[loss=2.072, simple_loss=0.2536, pruned_loss=0.04216, codebook_loss=19.03, over 6877.00 frames.], tot_loss[loss=2.058, simple_loss=0.2455, pruned_loss=0.03348, codebook_loss=19.02, over 1268629.79 frames.], batch size: 29, lr: 6.06e-04
+2022-05-27 19:54:02,150 INFO [train.py:823] (0/4) Epoch 28, batch 500, loss[loss=2.051, simple_loss=0.2624, pruned_loss=0.03304, codebook_loss=18.87, over 6908.00 frames.], tot_loss[loss=2.053, simple_loss=0.2455, pruned_loss=0.03343, codebook_loss=18.97, over 1305951.96 frames.], batch size: 29, lr: 6.06e-04
+2022-05-27 19:54:42,005 INFO [train.py:823] (0/4) Epoch 28, batch 550, loss[loss=2.049, simple_loss=0.254, pruned_loss=0.026, codebook_loss=18.96, over 7111.00 frames.], tot_loss[loss=2.057, simple_loss=0.2462, pruned_loss=0.03394, codebook_loss=19, over 1330227.64 frames.], batch size: 20, lr: 6.05e-04
+2022-05-27 19:55:21,346 INFO [train.py:823] (0/4) Epoch 28, batch 600, loss[loss=2.065, simple_loss=0.2416, pruned_loss=0.02539, codebook_loss=19.19, over 7199.00 frames.], tot_loss[loss=2.058, simple_loss=0.2465, pruned_loss=0.03401, codebook_loss=19, over 1348680.01 frames.], batch size: 19, lr: 6.04e-04
+2022-05-27 19:56:01,817 INFO [train.py:823] (0/4) Epoch 28, batch 650, loss[loss=2.139, simple_loss=0.252, pruned_loss=0.05312, codebook_loss=19.6, over 7291.00 frames.], tot_loss[loss=2.062, simple_loss=0.2465, pruned_loss=0.03424, codebook_loss=19.04, over 1367169.26 frames.], batch size: 19, lr: 6.04e-04
+2022-05-27 19:56:41,251 INFO [train.py:823] (0/4) Epoch 28, batch 700, loss[loss=1.929, simple_loss=0.2302, pruned_loss=0.0251, codebook_loss=17.89, over 7306.00 frames.], tot_loss[loss=2.065, simple_loss=0.2465, pruned_loss=0.0342, codebook_loss=19.08, over 1376999.72 frames.], batch size: 18, lr: 6.03e-04
+2022-05-27 19:57:21,256 INFO [train.py:823] (0/4) Epoch 28, batch 750, loss[loss=2.116, simple_loss=0.2776, pruned_loss=0.05375, codebook_loss=19.24, over 4891.00 frames.], tot_loss[loss=2.065, simple_loss=0.2464, pruned_loss=0.03395, codebook_loss=19.08, over 1383023.62 frames.], batch size: 47, lr: 6.03e-04
+2022-05-27 19:58:00,961 INFO [train.py:823] (0/4) Epoch 28, batch 800, loss[loss=1.917, simple_loss=0.1992, pruned_loss=0.02077, codebook_loss=17.96, over 6995.00 frames.], tot_loss[loss=2.064, simple_loss=0.2465, pruned_loss=0.03369, codebook_loss=19.07, over 1395526.74 frames.], batch size: 16, lr: 6.02e-04
+2022-05-27 19:58:41,182 INFO [train.py:823] (0/4) Epoch 28, batch 850, loss[loss=2.005, simple_loss=0.2579, pruned_loss=0.03606, codebook_loss=18.4, over 7380.00 frames.], tot_loss[loss=2.063, simple_loss=0.2471, pruned_loss=0.03398, codebook_loss=19.05, over 1399713.80 frames.], batch size: 21, lr: 6.02e-04
+2022-05-27 19:59:20,849 INFO [train.py:823] (0/4) Epoch 28, batch 900, loss[loss=2.191, simple_loss=0.2668, pruned_loss=0.04865, codebook_loss=20.09, over 7375.00 frames.], tot_loss[loss=2.06, simple_loss=0.247, pruned_loss=0.03386, codebook_loss=19.03, over 1402062.24 frames.], batch size: 21, lr: 6.01e-04
+2022-05-27 19:59:59,918 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-28.pt
+2022-05-27 20:00:14,145 INFO [train.py:823] (0/4) Epoch 29, batch 0, loss[loss=2.009, simple_loss=0.2613, pruned_loss=0.03826, codebook_loss=18.41, over 7040.00 frames.], tot_loss[loss=2.009, simple_loss=0.2613, pruned_loss=0.03826, codebook_loss=18.41, over 7040.00 frames.], batch size: 26, lr: 5.90e-04
+2022-05-27 20:00:55,866 INFO [train.py:823] (0/4) Epoch 29, batch 50, loss[loss=2.036, simple_loss=0.2506, pruned_loss=0.03122, codebook_loss=18.79, over 7294.00 frames.], tot_loss[loss=2.042, simple_loss=0.2433, pruned_loss=0.03161, codebook_loss=18.88, over 321469.51 frames.], batch size: 21, lr: 5.90e-04
+2022-05-27 20:01:38,099 INFO [train.py:823] (0/4) Epoch 29, batch 100, loss[loss=2.033, simple_loss=0.2604, pruned_loss=0.03933, codebook_loss=18.64, over 7248.00 frames.], tot_loss[loss=2.042, simple_loss=0.2458, pruned_loss=0.03365, codebook_loss=18.85, over 570051.05 frames.], batch size: 24, lr: 5.89e-04
+2022-05-27 20:02:18,479 INFO [train.py:823] (0/4) Epoch 29, batch 150, loss[loss=2.195, simple_loss=0.2428, pruned_loss=0.03206, codebook_loss=20.41, over 7292.00 frames.], tot_loss[loss=2.047, simple_loss=0.2433, pruned_loss=0.03313, codebook_loss=18.92, over 760073.50 frames.], batch size: 19, lr: 5.89e-04
+2022-05-27 20:02:58,100 INFO [train.py:823] (0/4) Epoch 29, batch 200, loss[loss=2.035, simple_loss=0.2629, pruned_loss=0.04747, codebook_loss=18.56, over 7333.00 frames.], tot_loss[loss=2.05, simple_loss=0.2458, pruned_loss=0.03373, codebook_loss=18.93, over 900566.63 frames.], batch size: 23, lr: 5.88e-04
+2022-05-27 20:03:38,422 INFO [train.py:823] (0/4) Epoch 29, batch 250, loss[loss=1.963, simple_loss=0.2366, pruned_loss=0.03215, codebook_loss=18.13, over 7385.00 frames.], tot_loss[loss=2.046, simple_loss=0.2444, pruned_loss=0.03286, codebook_loss=18.9, over 1017449.36 frames.], batch size: 19, lr: 5.88e-04
+2022-05-27 20:04:18,180 INFO [train.py:823] (0/4) Epoch 29, batch 300, loss[loss=2.036, simple_loss=0.2415, pruned_loss=0.0313, codebook_loss=18.84, over 7290.00 frames.], tot_loss[loss=2.051, simple_loss=0.2451, pruned_loss=0.03371, codebook_loss=18.95, over 1106994.08 frames.], batch size: 20, lr: 5.87e-04
+2022-05-27 20:04:58,346 INFO [train.py:823] (0/4) Epoch 29, batch 350, loss[loss=2.013, simple_loss=0.2209, pruned_loss=0.0274, codebook_loss=18.75, over 6814.00 frames.], tot_loss[loss=2.053, simple_loss=0.2457, pruned_loss=0.03363, codebook_loss=18.97, over 1176117.79 frames.], batch size: 15, lr: 5.87e-04
+2022-05-27 20:05:37,839 INFO [train.py:823] (0/4) Epoch 29, batch 400, loss[loss=1.98, simple_loss=0.2133, pruned_loss=0.02542, codebook_loss=18.48, over 7297.00 frames.], tot_loss[loss=2.053, simple_loss=0.2466, pruned_loss=0.03347, codebook_loss=18.97, over 1231069.44 frames.], batch size: 17, lr: 5.86e-04
+2022-05-27 20:06:18,205 INFO [train.py:823] (0/4) Epoch 29, batch 450, loss[loss=2.169, simple_loss=0.2369, pruned_loss=0.03469, codebook_loss=20.16, over 7101.00 frames.], tot_loss[loss=2.053, simple_loss=0.2464, pruned_loss=0.03348, codebook_loss=18.96, over 1270954.49 frames.], batch size: 18, lr: 5.85e-04
+2022-05-27 20:06:57,631 INFO [train.py:823] (0/4) Epoch 29, batch 500, loss[loss=1.99, simple_loss=0.248, pruned_loss=0.03286, codebook_loss=18.33, over 7103.00 frames.], tot_loss[loss=2.052, simple_loss=0.2456, pruned_loss=0.03308, codebook_loss=18.96, over 1298016.06 frames.], batch size: 20, lr: 5.85e-04
+2022-05-27 20:07:37,737 INFO [train.py:823] (0/4) Epoch 29, batch 550, loss[loss=1.991, simple_loss=0.2567, pruned_loss=0.02582, codebook_loss=18.37, over 6585.00 frames.], tot_loss[loss=2.052, simple_loss=0.2459, pruned_loss=0.03293, codebook_loss=18.96, over 1327741.47 frames.], batch size: 34, lr: 5.84e-04
+2022-05-27 20:08:17,444 INFO [train.py:823] (0/4) Epoch 29, batch 600, loss[loss=2.034, simple_loss=0.2663, pruned_loss=0.02741, codebook_loss=18.73, over 6528.00 frames.], tot_loss[loss=2.06, simple_loss=0.2471, pruned_loss=0.03318, codebook_loss=19.03, over 1347958.75 frames.], batch size: 34, lr: 5.84e-04
+2022-05-27 20:08:57,754 INFO [train.py:823] (0/4) Epoch 29, batch 650, loss[loss=2.111, simple_loss=0.2757, pruned_loss=0.04583, codebook_loss=19.28, over 7367.00 frames.], tot_loss[loss=2.06, simple_loss=0.2474, pruned_loss=0.03364, codebook_loss=19.02, over 1364917.35 frames.], batch size: 20, lr: 5.83e-04
+2022-05-27 20:09:37,315 INFO [train.py:823] (0/4) Epoch 29, batch 700, loss[loss=1.952, simple_loss=0.2392, pruned_loss=0.02371, codebook_loss=18.08, over 7196.00 frames.], tot_loss[loss=2.056, simple_loss=0.2463, pruned_loss=0.03315, codebook_loss=18.99, over 1371729.99 frames.], batch size: 19, lr: 5.83e-04
+2022-05-27 20:10:17,496 INFO [train.py:823] (0/4) Epoch 29, batch 750, loss[loss=2.028, simple_loss=0.2493, pruned_loss=0.0405, codebook_loss=18.63, over 4947.00 frames.], tot_loss[loss=2.058, simple_loss=0.2466, pruned_loss=0.03314, codebook_loss=19.02, over 1379485.32 frames.], batch size: 47, lr: 5.82e-04
+2022-05-27 20:10:57,080 INFO [train.py:823] (0/4) Epoch 29, batch 800, loss[loss=2.035, simple_loss=0.2297, pruned_loss=0.03663, codebook_loss=18.83, over 7205.00 frames.], tot_loss[loss=2.057, simple_loss=0.2465, pruned_loss=0.03305, codebook_loss=19.01, over 1387828.67 frames.], batch size: 18, lr: 5.82e-04
+2022-05-27 20:11:37,228 INFO [train.py:823] (0/4) Epoch 29, batch 850, loss[loss=2.058, simple_loss=0.2672, pruned_loss=0.04295, codebook_loss=18.82, over 7230.00 frames.], tot_loss[loss=2.056, simple_loss=0.247, pruned_loss=0.03306, codebook_loss=18.99, over 1398123.25 frames.], batch size: 24, lr: 5.81e-04
+2022-05-27 20:12:16,636 INFO [train.py:823] (0/4) Epoch 29, batch 900, loss[loss=2.118, simple_loss=0.2794, pruned_loss=0.04062, codebook_loss=19.38, over 7174.00 frames.], tot_loss[loss=2.058, simple_loss=0.2475, pruned_loss=0.03326, codebook_loss=19.01, over 1396261.12 frames.], batch size: 22, lr: 5.81e-04
+2022-05-27 20:12:56,392 INFO [train.py:823] (0/4) Epoch 29, batch 950, loss[loss=2.752, simple_loss=0.2647, pruned_loss=0.05275, codebook_loss=25.66, over 4651.00 frames.], tot_loss[loss=2.068, simple_loss=0.2472, pruned_loss=0.03375, codebook_loss=19.11, over 1389420.44 frames.], batch size: 46, lr: 5.80e-04
+2022-05-27 20:12:57,624 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-29.pt
+2022-05-27 20:13:08,708 INFO [train.py:823] (0/4) Epoch 30, batch 0, loss[loss=2.094, simple_loss=0.2524, pruned_loss=0.03368, codebook_loss=19.34, over 7372.00 frames.], tot_loss[loss=2.094, simple_loss=0.2524, pruned_loss=0.03368, codebook_loss=19.34, over 7372.00 frames.], batch size: 20, lr: 5.71e-04
+2022-05-27 20:13:48,687 INFO [train.py:823] (0/4) Epoch 30, batch 50, loss[loss=2.028, simple_loss=0.2387, pruned_loss=0.02931, codebook_loss=18.8, over 7106.00 frames.], tot_loss[loss=2.038, simple_loss=0.243, pruned_loss=0.03115, codebook_loss=18.86, over 314588.25 frames.], batch size: 19, lr: 5.70e-04
+2022-05-27 20:14:28,409 INFO [train.py:823] (0/4) Epoch 30, batch 100, loss[loss=1.918, simple_loss=0.214, pruned_loss=0.02268, codebook_loss=17.88, over 7310.00 frames.], tot_loss[loss=2.031, simple_loss=0.2416, pruned_loss=0.03039, codebook_loss=18.79, over 561815.73 frames.], batch size: 17, lr: 5.70e-04
+2022-05-27 20:15:09,697 INFO [train.py:823] (0/4) Epoch 30, batch 150, loss[loss=1.978, simple_loss=0.2543, pruned_loss=0.03212, codebook_loss=18.18, over 7155.00 frames.], tot_loss[loss=2.042, simple_loss=0.2444, pruned_loss=0.03216, codebook_loss=18.88, over 754615.73 frames.], batch size: 23, lr: 5.69e-04
+2022-05-27 20:15:49,638 INFO [train.py:823] (0/4) Epoch 30, batch 200, loss[loss=2.029, simple_loss=0.2696, pruned_loss=0.0403, codebook_loss=18.54, over 7137.00 frames.], tot_loss[loss=2.049, simple_loss=0.2456, pruned_loss=0.03313, codebook_loss=18.94, over 901545.41 frames.], batch size: 23, lr: 5.69e-04
+2022-05-27 20:16:29,716 INFO [train.py:823] (0/4) Epoch 30, batch 250, loss[loss=2.016, simple_loss=0.2353, pruned_loss=0.03387, codebook_loss=18.65, over 7101.00 frames.], tot_loss[loss=2.048, simple_loss=0.246, pruned_loss=0.03302, codebook_loss=18.92, over 1013704.23 frames.], batch size: 19, lr: 5.68e-04
+2022-05-27 20:17:09,781 INFO [train.py:823] (0/4) Epoch 30, batch 300, loss[loss=2.07, simple_loss=0.2326, pruned_loss=0.02979, codebook_loss=19.24, over 7157.00 frames.], tot_loss[loss=2.046, simple_loss=0.2469, pruned_loss=0.03336, codebook_loss=18.9, over 1107099.45 frames.], batch size: 17, lr: 5.68e-04
+2022-05-27 20:17:49,917 INFO [train.py:823] (0/4) Epoch 30, batch 350, loss[loss=2.39, simple_loss=0.2671, pruned_loss=0.04766, codebook_loss=22.08, over 7245.00 frames.], tot_loss[loss=2.054, simple_loss=0.2455, pruned_loss=0.03291, codebook_loss=18.99, over 1177615.16 frames.], batch size: 24, lr: 5.67e-04
+2022-05-27 20:18:29,832 INFO [train.py:823] (0/4) Epoch 30, batch 400, loss[loss=1.983, simple_loss=0.2594, pruned_loss=0.03647, codebook_loss=18.17, over 7022.00 frames.], tot_loss[loss=2.054, simple_loss=0.2459, pruned_loss=0.03318, codebook_loss=18.98, over 1231683.91 frames.], batch size: 26, lr: 5.67e-04
+2022-05-27 20:19:09,692 INFO [train.py:823] (0/4) Epoch 30, batch 450, loss[loss=2.015, simple_loss=0.2506, pruned_loss=0.02375, codebook_loss=18.66, over 6904.00 frames.], tot_loss[loss=2.054, simple_loss=0.2458, pruned_loss=0.03322, codebook_loss=18.98, over 1270821.01 frames.], batch size: 29, lr: 5.66e-04
+2022-05-27 20:19:49,232 INFO [train.py:823] (0/4) Epoch 30, batch 500, loss[loss=2.224, simple_loss=0.2483, pruned_loss=0.03292, codebook_loss=20.67, over 7100.00 frames.], tot_loss[loss=2.058, simple_loss=0.2458, pruned_loss=0.03312, codebook_loss=19.02, over 1303192.22 frames.], batch size: 19, lr: 5.66e-04
+2022-05-27 20:20:29,397 INFO [train.py:823] (0/4) Epoch 30, batch 550, loss[loss=2.3, simple_loss=0.2477, pruned_loss=0.02837, codebook_loss=21.48, over 7416.00 frames.], tot_loss[loss=2.06, simple_loss=0.2458, pruned_loss=0.03319, codebook_loss=19.04, over 1327785.83 frames.], batch size: 22, lr: 5.65e-04
+2022-05-27 20:21:09,004 INFO [train.py:823] (0/4) Epoch 30, batch 600, loss[loss=2.034, simple_loss=0.2574, pruned_loss=0.03496, codebook_loss=18.7, over 7186.00 frames.], tot_loss[loss=2.059, simple_loss=0.2463, pruned_loss=0.03321, codebook_loss=19.02, over 1344922.30 frames.], batch size: 19, lr: 5.65e-04
+2022-05-27 20:21:49,283 INFO [train.py:823] (0/4) Epoch 30, batch 650, loss[loss=1.978, simple_loss=0.2561, pruned_loss=0.02835, codebook_loss=18.22, over 7415.00 frames.], tot_loss[loss=2.052, simple_loss=0.2452, pruned_loss=0.03287, codebook_loss=18.96, over 1358690.52 frames.], batch size: 22, lr: 5.64e-04
+2022-05-27 20:22:29,372 INFO [train.py:823] (0/4) Epoch 30, batch 700, loss[loss=1.998, simple_loss=0.2216, pruned_loss=0.02151, codebook_loss=18.66, over 7285.00 frames.], tot_loss[loss=2.05, simple_loss=0.244, pruned_loss=0.03263, codebook_loss=18.95, over 1376904.99 frames.], batch size: 19, lr: 5.64e-04
+2022-05-27 20:23:09,391 INFO [train.py:823] (0/4) Epoch 30, batch 750, loss[loss=1.926, simple_loss=0.2215, pruned_loss=0.01682, codebook_loss=17.99, over 7095.00 frames.], tot_loss[loss=2.053, simple_loss=0.2447, pruned_loss=0.03276, codebook_loss=18.98, over 1382787.94 frames.], batch size: 18, lr: 5.63e-04
+2022-05-27 20:23:48,805 INFO [train.py:823] (0/4) Epoch 30, batch 800, loss[loss=2.004, simple_loss=0.2456, pruned_loss=0.03584, codebook_loss=18.46, over 6965.00 frames.], tot_loss[loss=2.049, simple_loss=0.2442, pruned_loss=0.0322, codebook_loss=18.95, over 1392624.51 frames.], batch size: 26, lr: 5.63e-04
+2022-05-27 20:24:28,775 INFO [train.py:823] (0/4) Epoch 30, batch 850, loss[loss=2.082, simple_loss=0.2205, pruned_loss=0.02619, codebook_loss=19.45, over 7190.00 frames.], tot_loss[loss=2.051, simple_loss=0.2439, pruned_loss=0.03218, codebook_loss=18.97, over 1391376.60 frames.], batch size: 18, lr: 5.62e-04
+2022-05-27 20:25:08,260 INFO [train.py:823] (0/4) Epoch 30, batch 900, loss[loss=2.125, simple_loss=0.2395, pruned_loss=0.03857, codebook_loss=19.66, over 7288.00 frames.], tot_loss[loss=2.047, simple_loss=0.2439, pruned_loss=0.03214, codebook_loss=18.93, over 1395655.64 frames.], batch size: 19, lr: 5.62e-04
+2022-05-27 20:25:51,097 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-30.pt
+2022-05-27 20:26:05,260 INFO [train.py:823] (0/4) Epoch 31, batch 0, loss[loss=2.158, simple_loss=0.238, pruned_loss=0.02499, codebook_loss=20.14, over 7383.00 frames.], tot_loss[loss=2.158, simple_loss=0.238, pruned_loss=0.02499, codebook_loss=20.14, over 7383.00 frames.], batch size: 20, lr: 5.52e-04
+2022-05-27 20:26:45,554 INFO [train.py:823] (0/4) Epoch 31, batch 50, loss[loss=1.963, simple_loss=0.2301, pruned_loss=0.01922, codebook_loss=18.28, over 7187.00 frames.], tot_loss[loss=2.038, simple_loss=0.2418, pruned_loss=0.0315, codebook_loss=18.86, over 324952.09 frames.], batch size: 18, lr: 5.52e-04
+2022-05-27 20:27:25,000 INFO [train.py:823] (0/4) Epoch 31, batch 100, loss[loss=2.446, simple_loss=0.2277, pruned_loss=0.03058, codebook_loss=23.02, over 6820.00 frames.], tot_loss[loss=2.047, simple_loss=0.243, pruned_loss=0.03242, codebook_loss=18.93, over 565025.96 frames.], batch size: 15, lr: 5.51e-04
+2022-05-27 20:28:05,124 INFO [train.py:823] (0/4) Epoch 31, batch 150, loss[loss=2.078, simple_loss=0.2574, pruned_loss=0.03884, codebook_loss=19.11, over 7212.00 frames.], tot_loss[loss=2.043, simple_loss=0.2436, pruned_loss=0.03204, codebook_loss=18.89, over 753637.92 frames.], batch size: 25, lr: 5.51e-04
+2022-05-27 20:28:44,823 INFO [train.py:823] (0/4) Epoch 31, batch 200, loss[loss=1.949, simple_loss=0.2343, pruned_loss=0.02532, codebook_loss=18.06, over 7091.00 frames.], tot_loss[loss=2.043, simple_loss=0.2445, pruned_loss=0.03182, codebook_loss=18.89, over 898792.18 frames.], batch size: 18, lr: 5.50e-04
+2022-05-27 20:29:24,817 INFO [train.py:823] (0/4) Epoch 31, batch 250, loss[loss=1.994, simple_loss=0.224, pruned_loss=0.02535, codebook_loss=18.56, over 7146.00 frames.], tot_loss[loss=2.046, simple_loss=0.2436, pruned_loss=0.0319, codebook_loss=18.92, over 1006530.97 frames.], batch size: 17, lr: 5.50e-04
+2022-05-27 20:30:04,898 INFO [train.py:823] (0/4) Epoch 31, batch 300, loss[loss=1.896, simple_loss=0.2369, pruned_loss=0.01931, codebook_loss=17.58, over 7296.00 frames.], tot_loss[loss=2.039, simple_loss=0.2441, pruned_loss=0.03207, codebook_loss=18.84, over 1099320.29 frames.], batch size: 22, lr: 5.49e-04
+2022-05-27 20:30:44,859 INFO [train.py:823] (0/4) Epoch 31, batch 350, loss[loss=2.095, simple_loss=0.2136, pruned_loss=0.02866, codebook_loss=19.6, over 7152.00 frames.], tot_loss[loss=2.038, simple_loss=0.2438, pruned_loss=0.03197, codebook_loss=18.84, over 1165276.44 frames.], batch size: 17, lr: 5.49e-04
+2022-05-27 20:31:24,717 INFO [train.py:823] (0/4) Epoch 31, batch 400, loss[loss=1.977, simple_loss=0.2321, pruned_loss=0.02682, codebook_loss=18.34, over 7396.00 frames.], tot_loss[loss=2.034, simple_loss=0.2441, pruned_loss=0.03173, codebook_loss=18.8, over 1226818.06 frames.], batch size: 19, lr: 5.49e-04
+2022-05-27 20:32:04,786 INFO [train.py:823] (0/4) Epoch 31, batch 450, loss[loss=2.019, simple_loss=0.2303, pruned_loss=0.02341, codebook_loss=18.8, over 7307.00 frames.], tot_loss[loss=2.033, simple_loss=0.2442, pruned_loss=0.03183, codebook_loss=18.79, over 1270660.13 frames.], batch size: 18, lr: 5.48e-04
+2022-05-27 20:32:44,630 INFO [train.py:823] (0/4) Epoch 31, batch 500, loss[loss=1.992, simple_loss=0.2244, pruned_loss=0.01886, codebook_loss=18.61, over 7095.00 frames.], tot_loss[loss=2.043, simple_loss=0.244, pruned_loss=0.03232, codebook_loss=18.89, over 1302951.76 frames.], batch size: 18, lr: 5.48e-04
+2022-05-27 20:33:24,723 INFO [train.py:823] (0/4) Epoch 31, batch 550, loss[loss=2.137, simple_loss=0.2439, pruned_loss=0.03241, codebook_loss=19.83, over 7387.00 frames.], tot_loss[loss=2.048, simple_loss=0.2432, pruned_loss=0.03244, codebook_loss=18.94, over 1327195.68 frames.], batch size: 19, lr: 5.47e-04
+2022-05-27 20:34:04,424 INFO [train.py:823] (0/4) Epoch 31, batch 600, loss[loss=2.029, simple_loss=0.2146, pruned_loss=0.03803, codebook_loss=18.84, over 7194.00 frames.], tot_loss[loss=2.046, simple_loss=0.2436, pruned_loss=0.03252, codebook_loss=18.92, over 1346922.06 frames.], batch size: 16, lr: 5.47e-04
+2022-05-27 20:34:44,336 INFO [train.py:823] (0/4) Epoch 31, batch 650, loss[loss=1.968, simple_loss=0.2627, pruned_loss=0.03172, codebook_loss=18.05, over 7163.00 frames.], tot_loss[loss=2.043, simple_loss=0.2438, pruned_loss=0.03236, codebook_loss=18.89, over 1362299.99 frames.], batch size: 22, lr: 5.46e-04
+2022-05-27 20:35:24,056 INFO [train.py:823] (0/4) Epoch 31, batch 700, loss[loss=2.007, simple_loss=0.2305, pruned_loss=0.03008, codebook_loss=18.62, over 7295.00 frames.], tot_loss[loss=2.05, simple_loss=0.245, pruned_loss=0.03323, codebook_loss=18.95, over 1371187.81 frames.], batch size: 17, lr: 5.46e-04
+2022-05-27 20:36:04,250 INFO [train.py:823] (0/4) Epoch 31, batch 750, loss[loss=2.009, simple_loss=0.2402, pruned_loss=0.03921, codebook_loss=18.5, over 7307.00 frames.], tot_loss[loss=2.051, simple_loss=0.2451, pruned_loss=0.03311, codebook_loss=18.95, over 1382807.24 frames.], batch size: 18, lr: 5.45e-04
+2022-05-27 20:36:44,235 INFO [train.py:823] (0/4) Epoch 31, batch 800, loss[loss=2.016, simple_loss=0.2172, pruned_loss=0.02775, codebook_loss=18.79, over 6809.00 frames.], tot_loss[loss=2.05, simple_loss=0.2451, pruned_loss=0.03293, codebook_loss=18.95, over 1393016.38 frames.], batch size: 15, lr: 5.45e-04
+2022-05-27 20:37:23,977 INFO [train.py:823] (0/4) Epoch 31, batch 850, loss[loss=2.008, simple_loss=0.2375, pruned_loss=0.03, codebook_loss=18.59, over 7004.00 frames.], tot_loss[loss=2.053, simple_loss=0.2455, pruned_loss=0.03331, codebook_loss=18.97, over 1391702.94 frames.], batch size: 26, lr: 5.44e-04
+2022-05-27 20:38:03,437 INFO [train.py:823] (0/4) Epoch 31, batch 900, loss[loss=1.882, simple_loss=0.2211, pruned_loss=0.01566, codebook_loss=17.56, over 7095.00 frames.], tot_loss[loss=2.049, simple_loss=0.2459, pruned_loss=0.0333, codebook_loss=18.93, over 1397333.30 frames.], batch size: 19, lr: 5.44e-04
+2022-05-27 20:38:43,576 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-31.pt
+2022-05-27 20:38:58,909 INFO [train.py:823] (0/4) Epoch 32, batch 0, loss[loss=1.985, simple_loss=0.2389, pruned_loss=0.03295, codebook_loss=18.33, over 4702.00 frames.], tot_loss[loss=1.985, simple_loss=0.2389, pruned_loss=0.03295, codebook_loss=18.33, over 4702.00 frames.], batch size: 47, lr: 5.35e-04
+2022-05-27 20:39:38,631 INFO [train.py:823] (0/4) Epoch 32, batch 50, loss[loss=1.988, simple_loss=0.2253, pruned_loss=0.02841, codebook_loss=18.47, over 7293.00 frames.], tot_loss[loss=2.025, simple_loss=0.2449, pruned_loss=0.03172, codebook_loss=18.71, over 319621.29 frames.], batch size: 17, lr: 5.35e-04
+2022-05-27 20:40:18,785 INFO [train.py:823] (0/4) Epoch 32, batch 100, loss[loss=2.052, simple_loss=0.2504, pruned_loss=0.02723, codebook_loss=19, over 7162.00 frames.], tot_loss[loss=2.035, simple_loss=0.2447, pruned_loss=0.03211, codebook_loss=18.8, over 565057.22 frames.], batch size: 22, lr: 5.34e-04
+2022-05-27 20:40:58,679 INFO [train.py:823] (0/4) Epoch 32, batch 150, loss[loss=1.998, simple_loss=0.2339, pruned_loss=0.02036, codebook_loss=18.61, over 7204.00 frames.], tot_loss[loss=2.047, simple_loss=0.244, pruned_loss=0.03227, codebook_loss=18.93, over 758396.09 frames.], batch size: 19, lr: 5.34e-04
+2022-05-27 20:41:38,676 INFO [train.py:823] (0/4) Epoch 32, batch 200, loss[loss=2.027, simple_loss=0.2589, pruned_loss=0.0405, codebook_loss=18.57, over 7189.00 frames.], tot_loss[loss=2.038, simple_loss=0.2451, pruned_loss=0.03196, codebook_loss=18.83, over 904844.43 frames.], batch size: 19, lr: 5.33e-04
+2022-05-27 20:42:18,575 INFO [train.py:823] (0/4) Epoch 32, batch 250, loss[loss=2.04, simple_loss=0.2591, pruned_loss=0.03453, codebook_loss=18.76, over 7188.00 frames.], tot_loss[loss=2.032, simple_loss=0.244, pruned_loss=0.03157, codebook_loss=18.78, over 1021309.88 frames.], batch size: 19, lr: 5.33e-04
+2022-05-27 20:42:58,408 INFO [train.py:823] (0/4) Epoch 32, batch 300, loss[loss=1.972, simple_loss=0.2251, pruned_loss=0.02811, codebook_loss=18.32, over 7294.00 frames.], tot_loss[loss=2.029, simple_loss=0.2426, pruned_loss=0.0313, codebook_loss=18.77, over 1105912.18 frames.], batch size: 19, lr: 5.32e-04
+2022-05-27 20:43:38,304 INFO [train.py:823] (0/4) Epoch 32, batch 350, loss[loss=2.277, simple_loss=0.2674, pruned_loss=0.07456, codebook_loss=20.68, over 7010.00 frames.], tot_loss[loss=2.033, simple_loss=0.2436, pruned_loss=0.03187, codebook_loss=18.8, over 1175931.53 frames.], batch size: 16, lr: 5.32e-04
+2022-05-27 20:44:18,234 INFO [train.py:823] (0/4) Epoch 32, batch 400, loss[loss=1.95, simple_loss=0.236, pruned_loss=0.02374, codebook_loss=18.08, over 6414.00 frames.], tot_loss[loss=2.036, simple_loss=0.2448, pruned_loss=0.03204, codebook_loss=18.82, over 1225924.56 frames.], batch size: 34, lr: 5.32e-04
+2022-05-27 20:44:58,185 INFO [train.py:823] (0/4) Epoch 32, batch 450, loss[loss=1.999, simple_loss=0.2552, pruned_loss=0.03718, codebook_loss=18.34, over 7159.00 frames.], tot_loss[loss=2.036, simple_loss=0.2441, pruned_loss=0.03165, codebook_loss=18.82, over 1266801.13 frames.], batch size: 23, lr: 5.31e-04
+2022-05-27 20:45:38,579 INFO [train.py:823] (0/4) Epoch 32, batch 500, loss[loss=1.981, simple_loss=0.2362, pruned_loss=0.03119, codebook_loss=18.31, over 7206.00 frames.], tot_loss[loss=2.036, simple_loss=0.2431, pruned_loss=0.03165, codebook_loss=18.83, over 1300938.48 frames.], batch size: 20, lr: 5.31e-04
+2022-05-27 20:46:18,543 INFO [train.py:823] (0/4) Epoch 32, batch 550, loss[loss=1.951, simple_loss=0.2689, pruned_loss=0.03632, codebook_loss=17.8, over 7195.00 frames.], tot_loss[loss=2.03, simple_loss=0.2437, pruned_loss=0.03144, codebook_loss=18.77, over 1329452.44 frames.], batch size: 25, lr: 5.30e-04
+2022-05-27 20:46:58,693 INFO [train.py:823] (0/4) Epoch 32, batch 600, loss[loss=1.997, simple_loss=0.2117, pruned_loss=0.02686, codebook_loss=18.64, over 7299.00 frames.], tot_loss[loss=2.033, simple_loss=0.2439, pruned_loss=0.03145, codebook_loss=18.79, over 1350792.51 frames.], batch size: 17, lr: 5.30e-04
+2022-05-27 20:47:38,437 INFO [train.py:823] (0/4) Epoch 32, batch 650, loss[loss=2.031, simple_loss=0.2425, pruned_loss=0.02898, codebook_loss=18.81, over 7002.00 frames.], tot_loss[loss=2.039, simple_loss=0.2444, pruned_loss=0.03192, codebook_loss=18.85, over 1362551.42 frames.], batch size: 26, lr: 5.29e-04
+2022-05-27 20:48:18,752 INFO [train.py:823] (0/4) Epoch 32, batch 700, loss[loss=2.061, simple_loss=0.2462, pruned_loss=0.03565, codebook_loss=19.02, over 7099.00 frames.], tot_loss[loss=2.036, simple_loss=0.2432, pruned_loss=0.03182, codebook_loss=18.82, over 1378483.11 frames.], batch size: 20, lr: 5.29e-04
+2022-05-27 20:48:58,629 INFO [train.py:823] (0/4) Epoch 32, batch 750, loss[loss=1.949, simple_loss=0.2247, pruned_loss=0.02407, codebook_loss=18.13, over 7390.00 frames.], tot_loss[loss=2.037, simple_loss=0.2428, pruned_loss=0.03188, codebook_loss=18.84, over 1389326.82 frames.], batch size: 19, lr: 5.29e-04
+2022-05-27 20:49:38,925 INFO [train.py:823] (0/4) Epoch 32, batch 800, loss[loss=2.031, simple_loss=0.2435, pruned_loss=0.03608, codebook_loss=18.74, over 7147.00 frames.], tot_loss[loss=2.035, simple_loss=0.2427, pruned_loss=0.03191, codebook_loss=18.82, over 1397322.69 frames.], batch size: 17, lr: 5.28e-04
+2022-05-27 20:50:20,034 INFO [train.py:823] (0/4) Epoch 32, batch 850, loss[loss=1.969, simple_loss=0.2173, pruned_loss=0.0263, codebook_loss=18.34, over 7020.00 frames.], tot_loss[loss=2.036, simple_loss=0.2428, pruned_loss=0.03192, codebook_loss=18.82, over 1400670.05 frames.], batch size: 17, lr: 5.28e-04
+2022-05-27 20:51:02,543 INFO [train.py:823] (0/4) Epoch 32, batch 900, loss[loss=2.057, simple_loss=0.2335, pruned_loss=0.03182, codebook_loss=19.08, over 7024.00 frames.], tot_loss[loss=2.038, simple_loss=0.2442, pruned_loss=0.03206, codebook_loss=18.84, over 1405692.27 frames.], batch size: 17, lr: 5.27e-04
+2022-05-27 20:51:42,235 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-32.pt
+2022-05-27 20:51:56,396 INFO [train.py:823] (0/4) Epoch 33, batch 0, loss[loss=1.972, simple_loss=0.2454, pruned_loss=0.03188, codebook_loss=18.18, over 6970.00 frames.], tot_loss[loss=1.972, simple_loss=0.2454, pruned_loss=0.03188, codebook_loss=18.18, over 6970.00 frames.], batch size: 29, lr: 5.19e-04
+2022-05-27 20:52:36,646 INFO [train.py:823] (0/4) Epoch 33, batch 50, loss[loss=1.958, simple_loss=0.2243, pruned_loss=0.03036, codebook_loss=18.15, over 7160.00 frames.], tot_loss[loss=2.033, simple_loss=0.2424, pruned_loss=0.03178, codebook_loss=18.8, over 317199.37 frames.], batch size: 17, lr: 5.18e-04
+2022-05-27 20:53:16,495 INFO [train.py:823] (0/4) Epoch 33, batch 100, loss[loss=1.978, simple_loss=0.2232, pruned_loss=0.02692, codebook_loss=18.39, over 6829.00 frames.], tot_loss[loss=2.039, simple_loss=0.2385, pruned_loss=0.03051, codebook_loss=18.89, over 561428.41 frames.], batch size: 15, lr: 5.18e-04
+2022-05-27 20:53:56,616 INFO [train.py:823] (0/4) Epoch 33, batch 150, loss[loss=1.963, simple_loss=0.2534, pruned_loss=0.02104, codebook_loss=18.16, over 7183.00 frames.], tot_loss[loss=2.034, simple_loss=0.2411, pruned_loss=0.03081, codebook_loss=18.82, over 750234.80 frames.], batch size: 21, lr: 5.18e-04
+2022-05-27 20:54:36,228 INFO [train.py:823] (0/4) Epoch 33, batch 200, loss[loss=1.949, simple_loss=0.2598, pruned_loss=0.02676, codebook_loss=17.93, over 7114.00 frames.], tot_loss[loss=2.036, simple_loss=0.2419, pruned_loss=0.0316, codebook_loss=18.84, over 892690.36 frames.], batch size: 20, lr: 5.17e-04
+2022-05-27 20:55:16,531 INFO [train.py:823] (0/4) Epoch 33, batch 250, loss[loss=2.014, simple_loss=0.2556, pruned_loss=0.04036, codebook_loss=18.46, over 7126.00 frames.], tot_loss[loss=2.037, simple_loss=0.2413, pruned_loss=0.03144, codebook_loss=18.85, over 1013255.94 frames.], batch size: 23, lr: 5.17e-04
+2022-05-27 20:55:56,431 INFO [train.py:823] (0/4) Epoch 33, batch 300, loss[loss=2.27, simple_loss=0.2205, pruned_loss=0.02893, codebook_loss=21.31, over 7168.00 frames.], tot_loss[loss=2.035, simple_loss=0.2411, pruned_loss=0.03135, codebook_loss=18.83, over 1107317.93 frames.], batch size: 17, lr: 5.16e-04
+2022-05-27 20:56:36,519 INFO [train.py:823] (0/4) Epoch 33, batch 350, loss[loss=2.05, simple_loss=0.246, pruned_loss=0.04495, codebook_loss=18.82, over 7366.00 frames.], tot_loss[loss=2.034, simple_loss=0.2415, pruned_loss=0.03154, codebook_loss=18.82, over 1176926.25 frames.], batch size: 23, lr: 5.16e-04
+2022-05-27 20:57:16,234 INFO [train.py:823] (0/4) Epoch 33, batch 400, loss[loss=1.946, simple_loss=0.231, pruned_loss=0.02255, codebook_loss=18.08, over 7414.00 frames.], tot_loss[loss=2.04, simple_loss=0.2426, pruned_loss=0.03174, codebook_loss=18.87, over 1230503.01 frames.], batch size: 22, lr: 5.16e-04
+2022-05-27 20:57:56,217 INFO [train.py:823] (0/4) Epoch 33, batch 450, loss[loss=1.884, simple_loss=0.2133, pruned_loss=0.0188, codebook_loss=17.58, over 7294.00 frames.], tot_loss[loss=2.043, simple_loss=0.2428, pruned_loss=0.03173, codebook_loss=18.9, over 1272074.91 frames.], batch size: 19, lr: 5.15e-04
+2022-05-27 20:58:35,795 INFO [train.py:823] (0/4) Epoch 33, batch 500, loss[loss=2.094, simple_loss=0.2399, pruned_loss=0.03746, codebook_loss=19.37, over 6920.00 frames.], tot_loss[loss=2.048, simple_loss=0.2438, pruned_loss=0.032, codebook_loss=18.94, over 1306611.18 frames.], batch size: 29, lr: 5.15e-04
+2022-05-27 20:59:15,996 INFO [train.py:823] (0/4) Epoch 33, batch 550, loss[loss=2.073, simple_loss=0.2386, pruned_loss=0.03779, codebook_loss=19.16, over 7394.00 frames.], tot_loss[loss=2.044, simple_loss=0.2435, pruned_loss=0.03164, codebook_loss=18.91, over 1335300.26 frames.], batch size: 19, lr: 5.14e-04
+2022-05-27 20:59:56,126 INFO [train.py:823] (0/4) Epoch 33, batch 600, loss[loss=1.951, simple_loss=0.2522, pruned_loss=0.02589, codebook_loss=17.99, over 7416.00 frames.], tot_loss[loss=2.042, simple_loss=0.2425, pruned_loss=0.0313, codebook_loss=18.89, over 1355329.16 frames.], batch size: 22, lr: 5.14e-04
+2022-05-27 21:00:36,434 INFO [train.py:823] (0/4) Epoch 33, batch 650, loss[loss=2.193, simple_loss=0.233, pruned_loss=0.03496, codebook_loss=20.41, over 7158.00 frames.], tot_loss[loss=2.045, simple_loss=0.2416, pruned_loss=0.03126, codebook_loss=18.93, over 1374823.00 frames.], batch size: 17, lr: 5.14e-04
+2022-05-27 21:01:16,080 INFO [train.py:823] (0/4) Epoch 33, batch 700, loss[loss=2.084, simple_loss=0.2592, pruned_loss=0.03878, codebook_loss=19.16, over 6432.00 frames.], tot_loss[loss=2.043, simple_loss=0.2425, pruned_loss=0.03115, codebook_loss=18.91, over 1385985.10 frames.], batch size: 34, lr: 5.13e-04
+2022-05-27 21:01:56,095 INFO [train.py:823] (0/4) Epoch 33, batch 750, loss[loss=1.991, simple_loss=0.2435, pruned_loss=0.02716, codebook_loss=18.42, over 7189.00 frames.], tot_loss[loss=2.044, simple_loss=0.2432, pruned_loss=0.03136, codebook_loss=18.91, over 1392102.57 frames.], batch size: 25, lr: 5.13e-04
+2022-05-27 21:02:35,437 INFO [train.py:823] (0/4) Epoch 33, batch 800, loss[loss=2.029, simple_loss=0.2388, pruned_loss=0.03294, codebook_loss=18.77, over 7163.00 frames.], tot_loss[loss=2.04, simple_loss=0.2437, pruned_loss=0.03138, codebook_loss=18.87, over 1391299.93 frames.], batch size: 22, lr: 5.12e-04
+2022-05-27 21:03:16,834 INFO [train.py:823] (0/4) Epoch 33, batch 850, loss[loss=1.995, simple_loss=0.2398, pruned_loss=0.03446, codebook_loss=18.41, over 7084.00 frames.], tot_loss[loss=2.036, simple_loss=0.2433, pruned_loss=0.03145, codebook_loss=18.83, over 1400000.61 frames.], batch size: 18, lr: 5.12e-04
+2022-05-27 21:03:56,325 INFO [train.py:823] (0/4) Epoch 33, batch 900, loss[loss=2.08, simple_loss=0.2284, pruned_loss=0.03496, codebook_loss=19.31, over 7003.00 frames.], tot_loss[loss=2.041, simple_loss=0.2432, pruned_loss=0.0316, codebook_loss=18.88, over 1401501.18 frames.], batch size: 16, lr: 5.12e-04
+2022-05-27 21:04:36,614 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-33.pt
+2022-05-27 21:04:47,359 INFO [train.py:823] (0/4) Epoch 34, batch 0, loss[loss=2.057, simple_loss=0.2669, pruned_loss=0.03186, codebook_loss=18.92, over 7244.00 frames.], tot_loss[loss=2.057, simple_loss=0.2669, pruned_loss=0.03186, codebook_loss=18.92, over 7244.00 frames.], batch size: 24, lr: 5.04e-04
+2022-05-27 21:05:27,119 INFO [train.py:823] (0/4) Epoch 34, batch 50, loss[loss=1.992, simple_loss=0.2171, pruned_loss=0.0349, codebook_loss=18.48, over 6845.00 frames.], tot_loss[loss=2.03, simple_loss=0.2411, pruned_loss=0.03156, codebook_loss=18.78, over 320262.50 frames.], batch size: 15, lr: 5.03e-04
+2022-05-27 21:06:07,168 INFO [train.py:823] (0/4) Epoch 34, batch 100, loss[loss=1.912, simple_loss=0.2272, pruned_loss=0.02089, codebook_loss=17.77, over 7283.00 frames.], tot_loss[loss=2.03, simple_loss=0.2422, pruned_loss=0.03043, codebook_loss=18.78, over 560635.13 frames.], batch size: 21, lr: 5.03e-04
+2022-05-27 21:06:47,145 INFO [train.py:823] (0/4) Epoch 34, batch 150, loss[loss=1.959, simple_loss=0.2643, pruned_loss=0.02749, codebook_loss=18, over 7314.00 frames.], tot_loss[loss=2.035, simple_loss=0.2436, pruned_loss=0.03114, codebook_loss=18.82, over 754088.45 frames.], batch size: 22, lr: 5.02e-04
+2022-05-27 21:07:27,063 INFO [train.py:823] (0/4) Epoch 34, batch 200, loss[loss=1.911, simple_loss=0.2438, pruned_loss=0.02267, codebook_loss=17.67, over 7021.00 frames.], tot_loss[loss=2.035, simple_loss=0.2434, pruned_loss=0.03114, codebook_loss=18.82, over 901929.11 frames.], batch size: 26, lr: 5.02e-04
+2022-05-27 21:08:06,785 INFO [train.py:823] (0/4) Epoch 34, batch 250, loss[loss=2.212, simple_loss=0.2641, pruned_loss=0.03698, codebook_loss=20.43, over 7027.00 frames.], tot_loss[loss=2.034, simple_loss=0.2437, pruned_loss=0.03166, codebook_loss=18.81, over 1011771.95 frames.], batch size: 26, lr: 5.02e-04
+2022-05-27 21:08:46,831 INFO [train.py:823] (0/4) Epoch 34, batch 300, loss[loss=2.015, simple_loss=0.2449, pruned_loss=0.03072, codebook_loss=18.62, over 7371.00 frames.], tot_loss[loss=2.036, simple_loss=0.244, pruned_loss=0.03163, codebook_loss=18.83, over 1102177.77 frames.], batch size: 21, lr: 5.01e-04
+2022-05-27 21:09:26,872 INFO [train.py:823] (0/4) Epoch 34, batch 350, loss[loss=1.963, simple_loss=0.2349, pruned_loss=0.02232, codebook_loss=18.24, over 7084.00 frames.], tot_loss[loss=2.032, simple_loss=0.2434, pruned_loss=0.03148, codebook_loss=18.79, over 1169077.79 frames.], batch size: 19, lr: 5.01e-04
+2022-05-27 21:10:07,250 INFO [train.py:823] (0/4) Epoch 34, batch 400, loss[loss=1.991, simple_loss=0.2602, pruned_loss=0.03565, codebook_loss=18.25, over 7282.00 frames.], tot_loss[loss=2.028, simple_loss=0.2432, pruned_loss=0.03114, codebook_loss=18.75, over 1224470.91 frames.], batch size: 21, lr: 5.00e-04
+2022-05-27 21:10:46,989 INFO [train.py:823] (0/4) Epoch 34, batch 450, loss[loss=1.953, simple_loss=0.2676, pruned_loss=0.03167, codebook_loss=17.88, over 7275.00 frames.], tot_loss[loss=2.028, simple_loss=0.2432, pruned_loss=0.03097, codebook_loss=18.75, over 1270468.98 frames.], batch size: 20, lr: 5.00e-04
+2022-05-27 21:11:27,177 INFO [train.py:823] (0/4) Epoch 34, batch 500, loss[loss=1.959, simple_loss=0.2381, pruned_loss=0.02469, codebook_loss=18.15, over 7160.00 frames.], tot_loss[loss=2.035, simple_loss=0.2426, pruned_loss=0.03093, codebook_loss=18.82, over 1302683.62 frames.], batch size: 23, lr: 5.00e-04
+2022-05-27 21:12:07,369 INFO [train.py:823] (0/4) Epoch 34, batch 550, loss[loss=2.016, simple_loss=0.2877, pruned_loss=0.04316, codebook_loss=18.29, over 7210.00 frames.], tot_loss[loss=2.025, simple_loss=0.2423, pruned_loss=0.03047, codebook_loss=18.73, over 1334541.17 frames.], batch size: 25, lr: 4.99e-04
+2022-05-27 21:12:47,512 INFO [train.py:823] (0/4) Epoch 34, batch 600, loss[loss=1.968, simple_loss=0.2228, pruned_loss=0.02554, codebook_loss=18.31, over 7310.00 frames.], tot_loss[loss=2.026, simple_loss=0.2431, pruned_loss=0.03043, codebook_loss=18.74, over 1352715.69 frames.], batch size: 17, lr: 4.99e-04
+2022-05-27 21:13:27,629 INFO [train.py:823] (0/4) Epoch 34, batch 650, loss[loss=2.066, simple_loss=0.2484, pruned_loss=0.02796, codebook_loss=19.14, over 6964.00 frames.], tot_loss[loss=2.033, simple_loss=0.242, pruned_loss=0.03053, codebook_loss=18.81, over 1367416.29 frames.], batch size: 29, lr: 4.99e-04
+2022-05-27 21:13:28,713 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/checkpoint-32000.pt
+2022-05-27 21:14:11,302 INFO [train.py:823] (0/4) Epoch 34, batch 700, loss[loss=2.015, simple_loss=0.2432, pruned_loss=0.03206, codebook_loss=18.61, over 7378.00 frames.], tot_loss[loss=2.036, simple_loss=0.2422, pruned_loss=0.03115, codebook_loss=18.84, over 1377483.94 frames.], batch size: 20, lr: 4.98e-04
+2022-05-27 21:14:51,476 INFO [train.py:823] (0/4) Epoch 34, batch 750, loss[loss=1.989, simple_loss=0.2161, pruned_loss=0.02638, codebook_loss=18.54, over 7001.00 frames.], tot_loss[loss=2.042, simple_loss=0.2424, pruned_loss=0.03181, codebook_loss=18.89, over 1388964.78 frames.], batch size: 16, lr: 4.98e-04
+2022-05-27 21:15:35,808 INFO [train.py:823] (0/4) Epoch 34, batch 800, loss[loss=2.102, simple_loss=0.2564, pruned_loss=0.04702, codebook_loss=19.27, over 7202.00 frames.], tot_loss[loss=2.044, simple_loss=0.242, pruned_loss=0.03181, codebook_loss=18.91, over 1396582.02 frames.], batch size: 19, lr: 4.97e-04
+2022-05-27 21:16:15,606 INFO [train.py:823] (0/4) Epoch 34, batch 850, loss[loss=1.973, simple_loss=0.2311, pruned_loss=0.0284, codebook_loss=18.29, over 7373.00 frames.], tot_loss[loss=2.034, simple_loss=0.2422, pruned_loss=0.03106, codebook_loss=18.82, over 1396571.22 frames.], batch size: 21, lr: 4.97e-04
+2022-05-27 21:16:55,845 INFO [train.py:823] (0/4) Epoch 34, batch 900, loss[loss=1.945, simple_loss=0.2206, pruned_loss=0.02424, codebook_loss=18.11, over 7102.00 frames.], tot_loss[loss=2.035, simple_loss=0.2418, pruned_loss=0.03113, codebook_loss=18.83, over 1401153.96 frames.], batch size: 18, lr: 4.97e-04
+2022-05-27 21:17:34,545 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-34.pt
+2022-05-27 21:17:49,295 INFO [train.py:823] (0/4) Epoch 35, batch 0, loss[loss=2.12, simple_loss=0.2572, pruned_loss=0.02508, codebook_loss=19.66, over 7175.00 frames.], tot_loss[loss=2.12, simple_loss=0.2572, pruned_loss=0.02508, codebook_loss=19.66, over 7175.00 frames.], batch size: 21, lr: 4.89e-04
+2022-05-27 21:18:30,065 INFO [train.py:823] (0/4) Epoch 35, batch 50, loss[loss=2.064, simple_loss=0.2014, pruned_loss=0.01752, codebook_loss=19.46, over 7190.00 frames.], tot_loss[loss=2.023, simple_loss=0.2417, pruned_loss=0.03043, codebook_loss=18.72, over 323989.39 frames.], batch size: 18, lr: 4.89e-04
+2022-05-27 21:19:10,032 INFO [train.py:823] (0/4) Epoch 35, batch 100, loss[loss=2.015, simple_loss=0.2396, pruned_loss=0.03167, codebook_loss=18.63, over 6398.00 frames.], tot_loss[loss=2.028, simple_loss=0.2413, pruned_loss=0.03024, codebook_loss=18.77, over 568876.82 frames.], batch size: 34, lr: 4.88e-04
+2022-05-27 21:19:50,174 INFO [train.py:823] (0/4) Epoch 35, batch 150, loss[loss=2.104, simple_loss=0.2537, pruned_loss=0.04026, codebook_loss=19.37, over 7192.00 frames.], tot_loss[loss=2.023, simple_loss=0.2405, pruned_loss=0.03062, codebook_loss=18.72, over 754838.26 frames.], batch size: 25, lr: 4.88e-04
+2022-05-27 21:20:30,530 INFO [train.py:823] (0/4) Epoch 35, batch 200, loss[loss=1.938, simple_loss=0.2603, pruned_loss=0.02882, codebook_loss=17.79, over 6880.00 frames.], tot_loss[loss=2.027, simple_loss=0.2407, pruned_loss=0.03094, codebook_loss=18.76, over 904194.95 frames.], batch size: 29, lr: 4.88e-04
+2022-05-27 21:21:10,408 INFO [train.py:823] (0/4) Epoch 35, batch 250, loss[loss=1.911, simple_loss=0.2305, pruned_loss=0.02451, codebook_loss=17.71, over 7245.00 frames.], tot_loss[loss=2.02, simple_loss=0.2405, pruned_loss=0.03069, codebook_loss=18.69, over 1014115.61 frames.], batch size: 24, lr: 4.87e-04
+2022-05-27 21:21:50,256 INFO [train.py:823] (0/4) Epoch 35, batch 300, loss[loss=2.023, simple_loss=0.2601, pruned_loss=0.03494, codebook_loss=18.58, over 7285.00 frames.], tot_loss[loss=2.021, simple_loss=0.2409, pruned_loss=0.03105, codebook_loss=18.7, over 1105833.11 frames.], batch size: 21, lr: 4.87e-04
+2022-05-27 21:22:30,347 INFO [train.py:823] (0/4) Epoch 35, batch 350, loss[loss=1.944, simple_loss=0.2141, pruned_loss=0.0216, codebook_loss=18.15, over 7092.00 frames.], tot_loss[loss=2.016, simple_loss=0.2407, pruned_loss=0.03051, codebook_loss=18.65, over 1172053.64 frames.], batch size: 18, lr: 4.87e-04
+2022-05-27 21:23:10,160 INFO [train.py:823] (0/4) Epoch 35, batch 400, loss[loss=2.031, simple_loss=0.2364, pruned_loss=0.03791, codebook_loss=18.75, over 7157.00 frames.], tot_loss[loss=2.019, simple_loss=0.2411, pruned_loss=0.03071, codebook_loss=18.67, over 1222162.01 frames.], batch size: 22, lr: 4.86e-04
+2022-05-27 21:23:50,324 INFO [train.py:823] (0/4) Epoch 35, batch 450, loss[loss=1.997, simple_loss=0.2287, pruned_loss=0.03524, codebook_loss=18.47, over 7277.00 frames.], tot_loss[loss=2.022, simple_loss=0.2423, pruned_loss=0.03129, codebook_loss=18.7, over 1270070.17 frames.], batch size: 17, lr: 4.86e-04
+2022-05-27 21:24:30,258 INFO [train.py:823] (0/4) Epoch 35, batch 500, loss[loss=1.898, simple_loss=0.202, pruned_loss=0.01704, codebook_loss=17.8, over 7022.00 frames.], tot_loss[loss=2.017, simple_loss=0.2411, pruned_loss=0.03077, codebook_loss=18.66, over 1304531.32 frames.], batch size: 17, lr: 4.86e-04
+2022-05-27 21:25:10,223 INFO [train.py:823] (0/4) Epoch 35, batch 550, loss[loss=2.058, simple_loss=0.2275, pruned_loss=0.02817, codebook_loss=19.16, over 7021.00 frames.], tot_loss[loss=2.02, simple_loss=0.2409, pruned_loss=0.03082, codebook_loss=18.69, over 1328332.34 frames.], batch size: 17, lr: 4.85e-04
+2022-05-27 21:25:50,297 INFO [train.py:823] (0/4) Epoch 35, batch 600, loss[loss=2.17, simple_loss=0.266, pruned_loss=0.04655, codebook_loss=19.9, over 7283.00 frames.], tot_loss[loss=2.024, simple_loss=0.2412, pruned_loss=0.03093, codebook_loss=18.73, over 1349035.48 frames.], batch size: 20, lr: 4.85e-04
+2022-05-27 21:26:30,418 INFO [train.py:823] (0/4) Epoch 35, batch 650, loss[loss=1.99, simple_loss=0.2383, pruned_loss=0.0242, codebook_loss=18.47, over 7070.00 frames.], tot_loss[loss=2.025, simple_loss=0.2405, pruned_loss=0.03065, codebook_loss=18.74, over 1367443.08 frames.], batch size: 26, lr: 4.84e-04
+2022-05-27 21:27:11,668 INFO [train.py:823] (0/4) Epoch 35, batch 700, loss[loss=1.966, simple_loss=0.2435, pruned_loss=0.02244, codebook_loss=18.21, over 7281.00 frames.], tot_loss[loss=2.028, simple_loss=0.2404, pruned_loss=0.03063, codebook_loss=18.77, over 1377191.58 frames.], batch size: 20, lr: 4.84e-04
+2022-05-27 21:27:51,843 INFO [train.py:823] (0/4) Epoch 35, batch 750, loss[loss=2.04, simple_loss=0.2302, pruned_loss=0.02655, codebook_loss=18.98, over 7091.00 frames.], tot_loss[loss=2.024, simple_loss=0.241, pruned_loss=0.03044, codebook_loss=18.73, over 1389443.53 frames.], batch size: 19, lr: 4.84e-04
+2022-05-27 21:28:31,661 INFO [train.py:823] (0/4) Epoch 35, batch 800, loss[loss=1.945, simple_loss=0.2261, pruned_loss=0.02244, codebook_loss=18.09, over 7309.00 frames.], tot_loss[loss=2.021, simple_loss=0.2409, pruned_loss=0.03009, codebook_loss=18.7, over 1394033.84 frames.], batch size: 18, lr: 4.83e-04
+2022-05-27 21:29:11,854 INFO [train.py:823] (0/4) Epoch 35, batch 850, loss[loss=2.009, simple_loss=0.2394, pruned_loss=0.03034, codebook_loss=18.59, over 7422.00 frames.], tot_loss[loss=2.026, simple_loss=0.2413, pruned_loss=0.03043, codebook_loss=18.75, over 1401846.74 frames.], batch size: 22, lr: 4.83e-04
+2022-05-27 21:29:51,287 INFO [train.py:823] (0/4) Epoch 35, batch 900, loss[loss=2.026, simple_loss=0.2392, pruned_loss=0.02179, codebook_loss=18.84, over 6559.00 frames.], tot_loss[loss=2.024, simple_loss=0.2409, pruned_loss=0.03027, codebook_loss=18.73, over 1400056.92 frames.], batch size: 35, lr: 4.83e-04
+2022-05-27 21:30:31,013 INFO [train.py:823] (0/4) Epoch 35, batch 950, loss[loss=1.993, simple_loss=0.2631, pruned_loss=0.03414, codebook_loss=18.27, over 5315.00 frames.], tot_loss[loss=2.026, simple_loss=0.2419, pruned_loss=0.03081, codebook_loss=18.74, over 1379631.45 frames.], batch size: 48, lr: 4.82e-04
+2022-05-27 21:30:32,224 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-35.pt
+2022-05-27 21:30:46,170 INFO [train.py:823] (0/4) Epoch 36, batch 0, loss[loss=1.94, simple_loss=0.2481, pruned_loss=0.02234, codebook_loss=17.94, over 7422.00 frames.], tot_loss[loss=1.94, simple_loss=0.2481, pruned_loss=0.02234, codebook_loss=17.94, over 7422.00 frames.], batch size: 22, lr: 4.76e-04
+2022-05-27 21:31:25,789 INFO [train.py:823] (0/4) Epoch 36, batch 50, loss[loss=1.988, simple_loss=0.2178, pruned_loss=0.02619, codebook_loss=18.53, over 7148.00 frames.], tot_loss[loss=2.011, simple_loss=0.2381, pruned_loss=0.0294, codebook_loss=18.63, over 319378.23 frames.], batch size: 17, lr: 4.75e-04
+2022-05-27 21:32:05,760 INFO [train.py:823] (0/4) Epoch 36, batch 100, loss[loss=1.971, simple_loss=0.2506, pruned_loss=0.0251, codebook_loss=18.2, over 6697.00 frames.], tot_loss[loss=2.006, simple_loss=0.2391, pruned_loss=0.02949, codebook_loss=18.57, over 565123.46 frames.], batch size: 34, lr: 4.75e-04
+2022-05-27 21:32:45,256 INFO [train.py:823] (0/4) Epoch 36, batch 150, loss[loss=2.047, simple_loss=0.2579, pruned_loss=0.04218, codebook_loss=18.76, over 7173.00 frames.], tot_loss[loss=2.016, simple_loss=0.241, pruned_loss=0.03019, codebook_loss=18.65, over 752012.27 frames.], batch size: 25, lr: 4.74e-04
+2022-05-27 21:33:25,468 INFO [train.py:823] (0/4) Epoch 36, batch 200, loss[loss=1.964, simple_loss=0.2105, pruned_loss=0.02325, codebook_loss=18.35, over 7307.00 frames.], tot_loss[loss=2.012, simple_loss=0.2399, pruned_loss=0.02987, codebook_loss=18.63, over 899231.73 frames.], batch size: 17, lr: 4.74e-04
+2022-05-27 21:34:05,046 INFO [train.py:823] (0/4) Epoch 36, batch 250, loss[loss=1.892, simple_loss=0.2309, pruned_loss=0.02392, codebook_loss=17.53, over 7389.00 frames.], tot_loss[loss=2.028, simple_loss=0.2414, pruned_loss=0.03084, codebook_loss=18.76, over 1012557.00 frames.], batch size: 19, lr: 4.74e-04
+2022-05-27 21:34:45,301 INFO [train.py:823] (0/4) Epoch 36, batch 300, loss[loss=2.077, simple_loss=0.2613, pruned_loss=0.0488, codebook_loss=18.98, over 7331.00 frames.], tot_loss[loss=2.025, simple_loss=0.2408, pruned_loss=0.03092, codebook_loss=18.74, over 1101537.66 frames.], batch size: 23, lr: 4.73e-04
+2022-05-27 21:35:25,039 INFO [train.py:823] (0/4) Epoch 36, batch 350, loss[loss=2.054, simple_loss=0.2442, pruned_loss=0.03866, codebook_loss=18.94, over 7377.00 frames.], tot_loss[loss=2.023, simple_loss=0.2412, pruned_loss=0.03087, codebook_loss=18.72, over 1172013.22 frames.], batch size: 20, lr: 4.73e-04
+2022-05-27 21:36:05,131 INFO [train.py:823] (0/4) Epoch 36, batch 400, loss[loss=2.034, simple_loss=0.232, pruned_loss=0.02643, codebook_loss=18.92, over 7086.00 frames.], tot_loss[loss=2.018, simple_loss=0.2416, pruned_loss=0.03074, codebook_loss=18.66, over 1227459.55 frames.], batch size: 18, lr: 4.73e-04
+2022-05-27 21:36:44,918 INFO [train.py:823] (0/4) Epoch 36, batch 450, loss[loss=1.985, simple_loss=0.2531, pruned_loss=0.03124, codebook_loss=18.27, over 7050.00 frames.], tot_loss[loss=2.018, simple_loss=0.241, pruned_loss=0.03068, codebook_loss=18.67, over 1269986.73 frames.], batch size: 26, lr: 4.72e-04
+2022-05-27 21:37:24,996 INFO [train.py:823] (0/4) Epoch 36, batch 500, loss[loss=2.118, simple_loss=0.2362, pruned_loss=0.03063, codebook_loss=19.7, over 7222.00 frames.], tot_loss[loss=2.014, simple_loss=0.2399, pruned_loss=0.03051, codebook_loss=18.63, over 1301818.23 frames.], batch size: 24, lr: 4.72e-04
+2022-05-27 21:38:04,890 INFO [train.py:823] (0/4) Epoch 36, batch 550, loss[loss=1.945, simple_loss=0.2105, pruned_loss=0.02168, codebook_loss=18.18, over 7301.00 frames.], tot_loss[loss=2.012, simple_loss=0.2393, pruned_loss=0.03011, codebook_loss=18.63, over 1328292.89 frames.], batch size: 17, lr: 4.72e-04
+2022-05-27 21:38:45,253 INFO [train.py:823] (0/4) Epoch 36, batch 600, loss[loss=2.048, simple_loss=0.2111, pruned_loss=0.02619, codebook_loss=19.16, over 7296.00 frames.], tot_loss[loss=2.016, simple_loss=0.2389, pruned_loss=0.03, codebook_loss=18.67, over 1347300.39 frames.], batch size: 17, lr: 4.71e-04
+2022-05-27 21:39:26,310 INFO [train.py:823] (0/4) Epoch 36, batch 650, loss[loss=2.23, simple_loss=0.2596, pruned_loss=0.03691, codebook_loss=20.63, over 7378.00 frames.], tot_loss[loss=2.02, simple_loss=0.2405, pruned_loss=0.03021, codebook_loss=18.7, over 1362700.66 frames.], batch size: 21, lr: 4.71e-04
+2022-05-27 21:40:09,238 INFO [train.py:823] (0/4) Epoch 36, batch 700, loss[loss=1.972, simple_loss=0.2124, pruned_loss=0.0199, codebook_loss=18.46, over 7304.00 frames.], tot_loss[loss=2.021, simple_loss=0.2403, pruned_loss=0.03026, codebook_loss=18.7, over 1379204.29 frames.], batch size: 17, lr: 4.71e-04
+2022-05-27 21:40:49,239 INFO [train.py:823] (0/4) Epoch 36, batch 750, loss[loss=2.029, simple_loss=0.2458, pruned_loss=0.03102, codebook_loss=18.75, over 7284.00 frames.], tot_loss[loss=2.026, simple_loss=0.2398, pruned_loss=0.03025, codebook_loss=18.76, over 1387413.03 frames.], batch size: 21, lr: 4.70e-04
+2022-05-27 21:41:29,162 INFO [train.py:823] (0/4) Epoch 36, batch 800, loss[loss=2.011, simple_loss=0.2392, pruned_loss=0.03714, codebook_loss=18.54, over 7372.00 frames.], tot_loss[loss=2.022, simple_loss=0.2398, pruned_loss=0.03004, codebook_loss=18.72, over 1388803.54 frames.], batch size: 21, lr: 4.70e-04
+2022-05-27 21:42:08,713 INFO [train.py:823] (0/4) Epoch 36, batch 850, loss[loss=1.96, simple_loss=0.2532, pruned_loss=0.03368, codebook_loss=17.99, over 7353.00 frames.], tot_loss[loss=2.023, simple_loss=0.2398, pruned_loss=0.0301, codebook_loss=18.73, over 1389254.64 frames.], batch size: 23, lr: 4.70e-04
+2022-05-27 21:42:48,763 INFO [train.py:823] (0/4) Epoch 36, batch 900, loss[loss=1.947, simple_loss=0.2497, pruned_loss=0.02401, codebook_loss=17.98, over 7424.00 frames.], tot_loss[loss=2.022, simple_loss=0.2404, pruned_loss=0.03012, codebook_loss=18.72, over 1396881.66 frames.], batch size: 22, lr: 4.69e-04
+2022-05-27 21:43:27,975 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-36.pt
+2022-05-27 21:43:42,192 INFO [train.py:823] (0/4) Epoch 37, batch 0, loss[loss=1.998, simple_loss=0.278, pruned_loss=0.03534, codebook_loss=18.23, over 6635.00 frames.], tot_loss[loss=1.998, simple_loss=0.278, pruned_loss=0.03534, codebook_loss=18.23, over 6635.00 frames.], batch size: 34, lr: 4.63e-04
+2022-05-27 21:44:22,064 INFO [train.py:823] (0/4) Epoch 37, batch 50, loss[loss=2.203, simple_loss=0.2644, pruned_loss=0.04186, codebook_loss=20.29, over 7307.00 frames.], tot_loss[loss=2.02, simple_loss=0.2454, pruned_loss=0.03165, codebook_loss=18.65, over 318525.74 frames.], batch size: 22, lr: 4.62e-04
+2022-05-27 21:45:01,721 INFO [train.py:823] (0/4) Epoch 37, batch 100, loss[loss=2.033, simple_loss=0.2628, pruned_loss=0.04403, codebook_loss=18.57, over 7236.00 frames.], tot_loss[loss=2.005, simple_loss=0.2431, pruned_loss=0.03068, codebook_loss=18.53, over 561276.73 frames.], batch size: 24, lr: 4.62e-04
+2022-05-27 21:45:41,728 INFO [train.py:823] (0/4) Epoch 37, batch 150, loss[loss=2.014, simple_loss=0.2267, pruned_loss=0.01786, codebook_loss=18.82, over 7195.00 frames.], tot_loss[loss=2.008, simple_loss=0.2414, pruned_loss=0.02951, codebook_loss=18.58, over 749955.91 frames.], batch size: 21, lr: 4.62e-04
+2022-05-27 21:46:21,862 INFO [train.py:823] (0/4) Epoch 37, batch 200, loss[loss=1.97, simple_loss=0.2721, pruned_loss=0.0423, codebook_loss=17.92, over 7234.00 frames.], tot_loss[loss=2.013, simple_loss=0.2395, pruned_loss=0.02997, codebook_loss=18.63, over 902402.59 frames.], batch size: 24, lr: 4.61e-04
+2022-05-27 21:47:01,949 INFO [train.py:823] (0/4) Epoch 37, batch 250, loss[loss=1.955, simple_loss=0.2499, pruned_loss=0.03173, codebook_loss=17.99, over 7040.00 frames.], tot_loss[loss=2.009, simple_loss=0.2411, pruned_loss=0.03014, codebook_loss=18.58, over 1018745.61 frames.], batch size: 26, lr: 4.61e-04
+2022-05-27 21:47:41,866 INFO [train.py:823] (0/4) Epoch 37, batch 300, loss[loss=1.937, simple_loss=0.2079, pruned_loss=0.01858, codebook_loss=18.15, over 7017.00 frames.], tot_loss[loss=2.015, simple_loss=0.2403, pruned_loss=0.03046, codebook_loss=18.65, over 1104991.59 frames.], batch size: 16, lr: 4.61e-04
+2022-05-27 21:48:21,738 INFO [train.py:823] (0/4) Epoch 37, batch 350, loss[loss=2.127, simple_loss=0.2735, pruned_loss=0.04141, codebook_loss=19.48, over 7227.00 frames.], tot_loss[loss=2.013, simple_loss=0.2411, pruned_loss=0.03056, codebook_loss=18.61, over 1172141.29 frames.], batch size: 25, lr: 4.60e-04
+2022-05-27 21:49:01,279 INFO [train.py:823] (0/4) Epoch 37, batch 400, loss[loss=1.941, simple_loss=0.2136, pruned_loss=0.02635, codebook_loss=18.07, over 7302.00 frames.], tot_loss[loss=2.01, simple_loss=0.2415, pruned_loss=0.03014, codebook_loss=18.59, over 1228452.71 frames.], batch size: 17, lr: 4.60e-04
+2022-05-27 21:49:41,271 INFO [train.py:823] (0/4) Epoch 37, batch 450, loss[loss=2.243, simple_loss=0.2287, pruned_loss=0.02682, codebook_loss=21.02, over 7204.00 frames.], tot_loss[loss=2.013, simple_loss=0.2415, pruned_loss=0.02995, codebook_loss=18.62, over 1268148.21 frames.], batch size: 19, lr: 4.60e-04
+2022-05-27 21:50:22,191 INFO [train.py:823] (0/4) Epoch 37, batch 500, loss[loss=1.992, simple_loss=0.2288, pruned_loss=0.03458, codebook_loss=18.43, over 7017.00 frames.], tot_loss[loss=2.019, simple_loss=0.2417, pruned_loss=0.03013, codebook_loss=18.68, over 1303576.46 frames.], batch size: 16, lr: 4.59e-04
+2022-05-27 21:51:02,113 INFO [train.py:823] (0/4) Epoch 37, batch 550, loss[loss=1.881, simple_loss=0.207, pruned_loss=0.01678, codebook_loss=17.6, over 7009.00 frames.], tot_loss[loss=2.019, simple_loss=0.2412, pruned_loss=0.03009, codebook_loss=18.69, over 1329231.87 frames.], batch size: 16, lr: 4.59e-04
+2022-05-27 21:51:41,655 INFO [train.py:823] (0/4) Epoch 37, batch 600, loss[loss=2.054, simple_loss=0.2583, pruned_loss=0.04273, codebook_loss=18.82, over 7333.00 frames.], tot_loss[loss=2.018, simple_loss=0.2416, pruned_loss=0.03018, codebook_loss=18.67, over 1349029.63 frames.], batch size: 23, lr: 4.59e-04
+2022-05-27 21:52:22,240 INFO [train.py:823] (0/4) Epoch 37, batch 650, loss[loss=2.011, simple_loss=0.2217, pruned_loss=0.02496, codebook_loss=18.75, over 7163.00 frames.], tot_loss[loss=2.014, simple_loss=0.2404, pruned_loss=0.02967, codebook_loss=18.64, over 1364174.92 frames.], batch size: 17, lr: 4.58e-04
+2022-05-27 21:53:01,927 INFO [train.py:823] (0/4) Epoch 37, batch 700, loss[loss=1.951, simple_loss=0.233, pruned_loss=0.02007, codebook_loss=18.15, over 7424.00 frames.], tot_loss[loss=2.014, simple_loss=0.2406, pruned_loss=0.02963, codebook_loss=18.64, over 1371300.87 frames.], batch size: 22, lr: 4.58e-04
+2022-05-27 21:53:41,852 INFO [train.py:823] (0/4) Epoch 37, batch 750, loss[loss=1.942, simple_loss=0.2336, pruned_loss=0.02568, codebook_loss=17.99, over 5292.00 frames.], tot_loss[loss=2.015, simple_loss=0.241, pruned_loss=0.02986, codebook_loss=18.65, over 1378771.64 frames.], batch size: 46, lr: 4.58e-04
+2022-05-27 21:54:21,475 INFO [train.py:823] (0/4) Epoch 37, batch 800, loss[loss=1.946, simple_loss=0.2425, pruned_loss=0.03059, codebook_loss=17.94, over 7279.00 frames.], tot_loss[loss=2.013, simple_loss=0.241, pruned_loss=0.02983, codebook_loss=18.63, over 1383103.50 frames.], batch size: 21, lr: 4.57e-04
+2022-05-27 21:55:01,502 INFO [train.py:823] (0/4) Epoch 37, batch 850, loss[loss=2.013, simple_loss=0.2151, pruned_loss=0.02455, codebook_loss=18.81, over 7230.00 frames.], tot_loss[loss=2.016, simple_loss=0.2403, pruned_loss=0.02995, codebook_loss=18.66, over 1385080.33 frames.], batch size: 16, lr: 4.57e-04
+2022-05-27 21:55:41,456 INFO [train.py:823] (0/4) Epoch 37, batch 900, loss[loss=1.973, simple_loss=0.2722, pruned_loss=0.03811, codebook_loss=17.99, over 7140.00 frames.], tot_loss[loss=2.018, simple_loss=0.24, pruned_loss=0.03012, codebook_loss=18.68, over 1392564.63 frames.], batch size: 23, lr: 4.57e-04
+2022-05-27 21:56:22,112 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-37.pt
+2022-05-27 21:56:35,777 INFO [train.py:823] (0/4) Epoch 38, batch 0, loss[loss=1.976, simple_loss=0.2516, pruned_loss=0.03378, codebook_loss=18.17, over 7403.00 frames.], tot_loss[loss=1.976, simple_loss=0.2516, pruned_loss=0.03378, codebook_loss=18.17, over 7403.00 frames.], batch size: 19, lr: 4.50e-04
+2022-05-27 21:57:15,587 INFO [train.py:823] (0/4) Epoch 38, batch 50, loss[loss=1.97, simple_loss=0.2488, pruned_loss=0.0381, codebook_loss=18.07, over 7104.00 frames.], tot_loss[loss=1.995, simple_loss=0.2398, pruned_loss=0.0291, codebook_loss=18.46, over 321676.42 frames.], batch size: 19, lr: 4.50e-04
+2022-05-27 21:57:55,716 INFO [train.py:823] (0/4) Epoch 38, batch 100, loss[loss=2.013, simple_loss=0.2589, pruned_loss=0.04343, codebook_loss=18.41, over 7336.00 frames.], tot_loss[loss=2.006, simple_loss=0.2374, pruned_loss=0.02909, codebook_loss=18.58, over 564678.45 frames.], batch size: 23, lr: 4.50e-04
+2022-05-27 21:58:35,471 INFO [train.py:823] (0/4) Epoch 38, batch 150, loss[loss=1.94, simple_loss=0.2381, pruned_loss=0.02506, codebook_loss=17.96, over 7009.00 frames.], tot_loss[loss=2.001, simple_loss=0.2371, pruned_loss=0.02861, codebook_loss=18.54, over 753178.30 frames.], batch size: 26, lr: 4.50e-04
+2022-05-27 21:59:15,482 INFO [train.py:823] (0/4) Epoch 38, batch 200, loss[loss=2.022, simple_loss=0.2583, pruned_loss=0.03296, codebook_loss=18.6, over 6459.00 frames.], tot_loss[loss=2.002, simple_loss=0.2383, pruned_loss=0.0286, codebook_loss=18.54, over 901142.64 frames.], batch size: 34, lr: 4.49e-04
+2022-05-27 21:59:55,442 INFO [train.py:823] (0/4) Epoch 38, batch 250, loss[loss=1.954, simple_loss=0.2274, pruned_loss=0.02432, codebook_loss=18.16, over 7109.00 frames.], tot_loss[loss=1.997, simple_loss=0.2379, pruned_loss=0.0286, codebook_loss=18.49, over 1019923.08 frames.], batch size: 20, lr: 4.49e-04
+2022-05-27 22:00:35,327 INFO [train.py:823] (0/4) Epoch 38, batch 300, loss[loss=1.96, simple_loss=0.2183, pruned_loss=0.02952, codebook_loss=18.22, over 7280.00 frames.], tot_loss[loss=1.996, simple_loss=0.2388, pruned_loss=0.02924, codebook_loss=18.47, over 1107291.37 frames.], batch size: 21, lr: 4.49e-04
+2022-05-27 22:01:15,239 INFO [train.py:823] (0/4) Epoch 38, batch 350, loss[loss=1.909, simple_loss=0.2073, pruned_loss=0.02386, codebook_loss=17.81, over 6834.00 frames.], tot_loss[loss=1.997, simple_loss=0.2391, pruned_loss=0.02914, codebook_loss=18.48, over 1181692.81 frames.], batch size: 15, lr: 4.48e-04
+2022-05-27 22:01:55,558 INFO [train.py:823] (0/4) Epoch 38, batch 400, loss[loss=2.046, simple_loss=0.254, pruned_loss=0.04501, codebook_loss=18.74, over 4590.00 frames.], tot_loss[loss=1.997, simple_loss=0.2396, pruned_loss=0.02927, codebook_loss=18.48, over 1235126.87 frames.], batch size: 46, lr: 4.48e-04
+2022-05-27 22:02:35,638 INFO [train.py:823] (0/4) Epoch 38, batch 450, loss[loss=1.923, simple_loss=0.2429, pruned_loss=0.02612, codebook_loss=17.75, over 7189.00 frames.], tot_loss[loss=2.004, simple_loss=0.2389, pruned_loss=0.02934, codebook_loss=18.55, over 1279513.47 frames.], batch size: 20, lr: 4.48e-04
+2022-05-27 22:03:16,100 INFO [train.py:823] (0/4) Epoch 38, batch 500, loss[loss=2.038, simple_loss=0.2771, pruned_loss=0.04442, codebook_loss=18.55, over 7273.00 frames.], tot_loss[loss=2.003, simple_loss=0.2382, pruned_loss=0.02915, codebook_loss=18.55, over 1314383.28 frames.], batch size: 21, lr: 4.47e-04
+2022-05-27 22:03:55,598 INFO [train.py:823] (0/4) Epoch 38, batch 550, loss[loss=2.003, simple_loss=0.2498, pruned_loss=0.03304, codebook_loss=18.45, over 7197.00 frames.], tot_loss[loss=2.006, simple_loss=0.2391, pruned_loss=0.02966, codebook_loss=18.57, over 1332505.75 frames.], batch size: 20, lr: 4.47e-04
+2022-05-27 22:04:38,500 INFO [train.py:823] (0/4) Epoch 38, batch 600, loss[loss=1.968, simple_loss=0.2362, pruned_loss=0.02744, codebook_loss=18.22, over 6527.00 frames.], tot_loss[loss=2.01, simple_loss=0.2395, pruned_loss=0.02952, codebook_loss=18.61, over 1351308.73 frames.], batch size: 34, lr: 4.47e-04
+2022-05-27 22:05:19,562 INFO [train.py:823] (0/4) Epoch 38, batch 650, loss[loss=1.931, simple_loss=0.2179, pruned_loss=0.02846, codebook_loss=17.94, over 7285.00 frames.], tot_loss[loss=2.004, simple_loss=0.2393, pruned_loss=0.02918, codebook_loss=18.55, over 1367305.62 frames.], batch size: 20, lr: 4.46e-04
+2022-05-27 22:05:59,572 INFO [train.py:823] (0/4) Epoch 38, batch 700, loss[loss=2.064, simple_loss=0.2562, pruned_loss=0.03486, codebook_loss=19.01, over 7162.00 frames.], tot_loss[loss=2.005, simple_loss=0.2403, pruned_loss=0.02939, codebook_loss=18.56, over 1377496.31 frames.], batch size: 22, lr: 4.46e-04
+2022-05-27 22:06:39,239 INFO [train.py:823] (0/4) Epoch 38, batch 750, loss[loss=1.953, simple_loss=0.2578, pruned_loss=0.03068, codebook_loss=17.94, over 7241.00 frames.], tot_loss[loss=2.005, simple_loss=0.2399, pruned_loss=0.02927, codebook_loss=18.55, over 1382585.16 frames.], batch size: 24, lr: 4.46e-04
+2022-05-27 22:07:19,344 INFO [train.py:823] (0/4) Epoch 38, batch 800, loss[loss=2.011, simple_loss=0.2468, pruned_loss=0.02345, codebook_loss=18.64, over 7376.00 frames.], tot_loss[loss=2.006, simple_loss=0.2402, pruned_loss=0.02973, codebook_loss=18.56, over 1385576.74 frames.], batch size: 21, lr: 4.45e-04
+2022-05-27 22:07:59,078 INFO [train.py:823] (0/4) Epoch 38, batch 850, loss[loss=2.148, simple_loss=0.2771, pruned_loss=0.04932, codebook_loss=19.6, over 6921.00 frames.], tot_loss[loss=2.009, simple_loss=0.2403, pruned_loss=0.02979, codebook_loss=18.59, over 1395205.21 frames.], batch size: 29, lr: 4.45e-04
+2022-05-27 22:08:39,064 INFO [train.py:823] (0/4) Epoch 38, batch 900, loss[loss=1.996, simple_loss=0.2329, pruned_loss=0.02474, codebook_loss=18.54, over 7020.00 frames.], tot_loss[loss=2.012, simple_loss=0.2403, pruned_loss=0.02958, codebook_loss=18.62, over 1398915.83 frames.], batch size: 16, lr: 4.45e-04
+2022-05-27 22:09:18,349 INFO [train.py:823] (0/4) Epoch 38, batch 950, loss[loss=2.071, simple_loss=0.2465, pruned_loss=0.03429, codebook_loss=19.13, over 5243.00 frames.], tot_loss[loss=2.014, simple_loss=0.2406, pruned_loss=0.02992, codebook_loss=18.64, over 1375342.06 frames.], batch size: 46, lr: 4.45e-04
+2022-05-27 22:09:19,526 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-38.pt
+2022-05-27 22:09:30,202 INFO [train.py:823] (0/4) Epoch 39, batch 0, loss[loss=1.918, simple_loss=0.2262, pruned_loss=0.02017, codebook_loss=17.85, over 7298.00 frames.], tot_loss[loss=1.918, simple_loss=0.2262, pruned_loss=0.02017, codebook_loss=17.85, over 7298.00 frames.], batch size: 19, lr: 4.39e-04
+2022-05-27 22:10:10,198 INFO [train.py:823] (0/4) Epoch 39, batch 50, loss[loss=2.008, simple_loss=0.245, pruned_loss=0.02524, codebook_loss=18.6, over 7437.00 frames.], tot_loss[loss=2.002, simple_loss=0.2406, pruned_loss=0.02996, codebook_loss=18.52, over 322043.20 frames.], batch size: 22, lr: 4.39e-04
+2022-05-27 22:10:50,168 INFO [train.py:823] (0/4) Epoch 39, batch 100, loss[loss=1.911, simple_loss=0.2159, pruned_loss=0.02449, codebook_loss=17.79, over 7317.00 frames.], tot_loss[loss=1.999, simple_loss=0.2371, pruned_loss=0.02879, codebook_loss=18.52, over 566699.54 frames.], batch size: 18, lr: 4.38e-04
+2022-05-27 22:11:30,529 INFO [train.py:823] (0/4) Epoch 39, batch 150, loss[loss=1.934, simple_loss=0.2537, pruned_loss=0.03087, codebook_loss=17.76, over 7194.00 frames.], tot_loss[loss=1.99, simple_loss=0.2351, pruned_loss=0.02779, codebook_loss=18.45, over 755141.61 frames.], batch size: 25, lr: 4.38e-04
+2022-05-27 22:12:10,644 INFO [train.py:823] (0/4) Epoch 39, batch 200, loss[loss=2.008, simple_loss=0.241, pruned_loss=0.03168, codebook_loss=18.56, over 7386.00 frames.], tot_loss[loss=2.001, simple_loss=0.2354, pruned_loss=0.02801, codebook_loss=18.55, over 907062.08 frames.], batch size: 19, lr: 4.38e-04
+2022-05-27 22:12:50,944 INFO [train.py:823] (0/4) Epoch 39, batch 250, loss[loss=2.26, simple_loss=0.2539, pruned_loss=0.04363, codebook_loss=20.9, over 7285.00 frames.], tot_loss[loss=2.007, simple_loss=0.2377, pruned_loss=0.02884, codebook_loss=18.59, over 1021280.90 frames.], batch size: 19, lr: 4.37e-04
+2022-05-27 22:13:31,026 INFO [train.py:823] (0/4) Epoch 39, batch 300, loss[loss=2.014, simple_loss=0.2453, pruned_loss=0.034, codebook_loss=18.57, over 7295.00 frames.], tot_loss[loss=2.013, simple_loss=0.2387, pruned_loss=0.02935, codebook_loss=18.64, over 1113672.30 frames.], batch size: 19, lr: 4.37e-04
+2022-05-27 22:14:11,229 INFO [train.py:823] (0/4) Epoch 39, batch 350, loss[loss=1.994, simple_loss=0.2479, pruned_loss=0.02717, codebook_loss=18.43, over 7369.00 frames.], tot_loss[loss=2.009, simple_loss=0.2389, pruned_loss=0.02915, codebook_loss=18.61, over 1185595.53 frames.], batch size: 20, lr: 4.37e-04
+2022-05-27 22:14:52,343 INFO [train.py:823] (0/4) Epoch 39, batch 400, loss[loss=2.129, simple_loss=0.2212, pruned_loss=0.01885, codebook_loss=20, over 7020.00 frames.], tot_loss[loss=2.007, simple_loss=0.239, pruned_loss=0.02885, codebook_loss=18.59, over 1242631.43 frames.], batch size: 17, lr: 4.36e-04
+2022-05-27 22:15:32,463 INFO [train.py:823] (0/4) Epoch 39, batch 450, loss[loss=2.016, simple_loss=0.2565, pruned_loss=0.03218, codebook_loss=18.56, over 7070.00 frames.], tot_loss[loss=2.008, simple_loss=0.2391, pruned_loss=0.02882, codebook_loss=18.59, over 1281286.47 frames.], batch size: 26, lr: 4.36e-04
+2022-05-27 22:16:12,044 INFO [train.py:823] (0/4) Epoch 39, batch 500, loss[loss=2.258, simple_loss=0.259, pruned_loss=0.04428, codebook_loss=20.84, over 5084.00 frames.], tot_loss[loss=2.009, simple_loss=0.2386, pruned_loss=0.02881, codebook_loss=18.6, over 1311321.67 frames.], batch size: 48, lr: 4.36e-04
+2022-05-27 22:16:52,118 INFO [train.py:823] (0/4) Epoch 39, batch 550, loss[loss=1.977, simple_loss=0.2619, pruned_loss=0.03386, codebook_loss=18.13, over 7216.00 frames.], tot_loss[loss=2.008, simple_loss=0.2392, pruned_loss=0.02898, codebook_loss=18.59, over 1332058.43 frames.], batch size: 25, lr: 4.36e-04
+2022-05-27 22:17:32,016 INFO [train.py:823] (0/4) Epoch 39, batch 600, loss[loss=1.903, simple_loss=0.214, pruned_loss=0.02375, codebook_loss=17.72, over 7435.00 frames.], tot_loss[loss=2.005, simple_loss=0.2386, pruned_loss=0.02891, codebook_loss=18.57, over 1354644.76 frames.], batch size: 18, lr: 4.35e-04
+2022-05-27 22:18:12,408 INFO [train.py:823] (0/4) Epoch 39, batch 650, loss[loss=1.912, simple_loss=0.2247, pruned_loss=0.01828, codebook_loss=17.82, over 7403.00 frames.], tot_loss[loss=2.002, simple_loss=0.2379, pruned_loss=0.02842, codebook_loss=18.54, over 1373520.51 frames.], batch size: 19, lr: 4.35e-04
+2022-05-27 22:18:52,210 INFO [train.py:823] (0/4) Epoch 39, batch 700, loss[loss=1.925, simple_loss=0.2503, pruned_loss=0.0371, codebook_loss=17.63, over 7210.00 frames.], tot_loss[loss=2.01, simple_loss=0.2392, pruned_loss=0.02919, codebook_loss=18.61, over 1383565.62 frames.], batch size: 24, lr: 4.35e-04
+2022-05-27 22:19:32,455 INFO [train.py:823] (0/4) Epoch 39, batch 750, loss[loss=1.974, simple_loss=0.2358, pruned_loss=0.03111, codebook_loss=18.25, over 7367.00 frames.], tot_loss[loss=2.014, simple_loss=0.2383, pruned_loss=0.02876, codebook_loss=18.66, over 1390250.33 frames.], batch size: 20, lr: 4.34e-04
+2022-05-27 22:20:12,028 INFO [train.py:823] (0/4) Epoch 39, batch 800, loss[loss=1.959, simple_loss=0.2283, pruned_loss=0.02817, codebook_loss=18.17, over 7178.00 frames.], tot_loss[loss=2.019, simple_loss=0.2387, pruned_loss=0.02895, codebook_loss=18.7, over 1398989.09 frames.], batch size: 18, lr: 4.34e-04
+2022-05-27 22:20:52,205 INFO [train.py:823] (0/4) Epoch 39, batch 850, loss[loss=2.005, simple_loss=0.2541, pruned_loss=0.02819, codebook_loss=18.49, over 7332.00 frames.], tot_loss[loss=2.022, simple_loss=0.2398, pruned_loss=0.02929, codebook_loss=18.73, over 1398956.95 frames.], batch size: 23, lr: 4.34e-04
+2022-05-27 22:21:31,555 INFO [train.py:823] (0/4) Epoch 39, batch 900, loss[loss=1.987, simple_loss=0.2499, pruned_loss=0.0298, codebook_loss=18.32, over 6910.00 frames.], tot_loss[loss=2.022, simple_loss=0.2411, pruned_loss=0.02971, codebook_loss=18.72, over 1391846.10 frames.], batch size: 29, lr: 4.34e-04
+2022-05-27 22:22:10,947 INFO [train.py:823] (0/4) Epoch 39, batch 950, loss[loss=1.954, simple_loss=0.2372, pruned_loss=0.03057, codebook_loss=18.05, over 4951.00 frames.], tot_loss[loss=2.017, simple_loss=0.2406, pruned_loss=0.0299, codebook_loss=18.67, over 1365918.50 frames.], batch size: 47, lr: 4.33e-04
+2022-05-27 22:22:12,113 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-39.pt
+2022-05-27 22:22:23,049 INFO [train.py:823] (0/4) Epoch 40, batch 0, loss[loss=2.01, simple_loss=0.2575, pruned_loss=0.03216, codebook_loss=18.49, over 7124.00 frames.], tot_loss[loss=2.01, simple_loss=0.2575, pruned_loss=0.03216, codebook_loss=18.49, over 7124.00 frames.], batch size: 23, lr: 4.28e-04
+2022-05-27 22:23:03,251 INFO [train.py:823] (0/4) Epoch 40, batch 50, loss[loss=1.905, simple_loss=0.2372, pruned_loss=0.02507, codebook_loss=17.62, over 7108.00 frames.], tot_loss[loss=2.012, simple_loss=0.2382, pruned_loss=0.03041, codebook_loss=18.63, over 318936.26 frames.], batch size: 20, lr: 4.28e-04
+2022-05-27 22:23:42,932 INFO [train.py:823] (0/4) Epoch 40, batch 100, loss[loss=1.998, simple_loss=0.2333, pruned_loss=0.03655, codebook_loss=18.45, over 6791.00 frames.], tot_loss[loss=2.001, simple_loss=0.2373, pruned_loss=0.02874, codebook_loss=18.54, over 559988.89 frames.], batch size: 15, lr: 4.27e-04
+2022-05-27 22:24:23,042 INFO [train.py:823] (0/4) Epoch 40, batch 150, loss[loss=1.99, simple_loss=0.2411, pruned_loss=0.0322, codebook_loss=18.37, over 6875.00 frames.], tot_loss[loss=2.007, simple_loss=0.2375, pruned_loss=0.02911, codebook_loss=18.59, over 745706.84 frames.], batch size: 29, lr: 4.27e-04
+2022-05-27 22:25:02,890 INFO [train.py:823] (0/4) Epoch 40, batch 200, loss[loss=2.014, simple_loss=0.2514, pruned_loss=0.02744, codebook_loss=18.61, over 7177.00 frames.], tot_loss[loss=2.011, simple_loss=0.239, pruned_loss=0.03, codebook_loss=18.62, over 896891.11 frames.], batch size: 21, lr: 4.27e-04
+2022-05-27 22:25:43,178 INFO [train.py:823] (0/4) Epoch 40, batch 250, loss[loss=2.027, simple_loss=0.217, pruned_loss=0.02274, codebook_loss=18.96, over 6859.00 frames.], tot_loss[loss=1.999, simple_loss=0.2387, pruned_loss=0.02934, codebook_loss=18.51, over 1013886.90 frames.], batch size: 15, lr: 4.26e-04
+2022-05-27 22:26:23,210 INFO [train.py:823] (0/4) Epoch 40, batch 300, loss[loss=1.955, simple_loss=0.2401, pruned_loss=0.02278, codebook_loss=18.12, over 7380.00 frames.], tot_loss[loss=2.002, simple_loss=0.2383, pruned_loss=0.02885, codebook_loss=18.54, over 1104174.19 frames.], batch size: 20, lr: 4.26e-04
+2022-05-27 22:27:03,488 INFO [train.py:823] (0/4) Epoch 40, batch 350, loss[loss=1.909, simple_loss=0.2376, pruned_loss=0.01745, codebook_loss=17.73, over 6491.00 frames.], tot_loss[loss=2.003, simple_loss=0.2379, pruned_loss=0.02848, codebook_loss=18.55, over 1177283.89 frames.], batch size: 34, lr: 4.26e-04
+2022-05-27 22:27:43,316 INFO [train.py:823] (0/4) Epoch 40, batch 400, loss[loss=2.087, simple_loss=0.2204, pruned_loss=0.02693, codebook_loss=19.5, over 6986.00 frames.], tot_loss[loss=2, simple_loss=0.237, pruned_loss=0.02825, codebook_loss=18.53, over 1236329.16 frames.], batch size: 16, lr: 4.26e-04
+2022-05-27 22:28:23,549 INFO [train.py:823] (0/4) Epoch 40, batch 450, loss[loss=1.976, simple_loss=0.2139, pruned_loss=0.03115, codebook_loss=18.38, over 7226.00 frames.], tot_loss[loss=1.999, simple_loss=0.2372, pruned_loss=0.0283, codebook_loss=18.52, over 1276872.52 frames.], batch size: 16, lr: 4.25e-04
+2022-05-27 22:29:05,772 INFO [train.py:823] (0/4) Epoch 40, batch 500, loss[loss=1.977, simple_loss=0.229, pruned_loss=0.03617, codebook_loss=18.26, over 7374.00 frames.], tot_loss[loss=2.003, simple_loss=0.2385, pruned_loss=0.02922, codebook_loss=18.55, over 1309649.41 frames.], batch size: 20, lr: 4.25e-04
+2022-05-27 22:29:47,394 INFO [train.py:823] (0/4) Epoch 40, batch 550, loss[loss=1.902, simple_loss=0.2547, pruned_loss=0.02234, codebook_loss=17.52, over 7297.00 frames.], tot_loss[loss=1.999, simple_loss=0.2377, pruned_loss=0.02872, codebook_loss=18.52, over 1337346.11 frames.], batch size: 22, lr: 4.25e-04
+2022-05-27 22:30:27,081 INFO [train.py:823] (0/4) Epoch 40, batch 600, loss[loss=1.918, simple_loss=0.2452, pruned_loss=0.02509, codebook_loss=17.7, over 7306.00 frames.], tot_loss[loss=1.997, simple_loss=0.2378, pruned_loss=0.02836, codebook_loss=18.49, over 1356685.62 frames.], batch size: 22, lr: 4.24e-04
+2022-05-27 22:31:07,405 INFO [train.py:823] (0/4) Epoch 40, batch 650, loss[loss=1.879, simple_loss=0.2176, pruned_loss=0.02022, codebook_loss=17.5, over 7202.00 frames.], tot_loss[loss=1.999, simple_loss=0.2385, pruned_loss=0.02921, codebook_loss=18.51, over 1365442.55 frames.], batch size: 19, lr: 4.24e-04
+2022-05-27 22:31:46,870 INFO [train.py:823] (0/4) Epoch 40, batch 700, loss[loss=2.186, simple_loss=0.2869, pruned_loss=0.03965, codebook_loss=20.03, over 7197.00 frames.], tot_loss[loss=2.002, simple_loss=0.2399, pruned_loss=0.02941, codebook_loss=18.52, over 1377756.37 frames.], batch size: 20, lr: 4.24e-04
+2022-05-27 22:32:27,218 INFO [train.py:823] (0/4) Epoch 40, batch 750, loss[loss=1.932, simple_loss=0.2292, pruned_loss=0.02026, codebook_loss=17.97, over 4809.00 frames.], tot_loss[loss=2.005, simple_loss=0.2399, pruned_loss=0.02924, codebook_loss=18.56, over 1388436.92 frames.], batch size: 48, lr: 4.24e-04
+2022-05-27 22:33:07,181 INFO [train.py:823] (0/4) Epoch 40, batch 800, loss[loss=1.931, simple_loss=0.2393, pruned_loss=0.02789, codebook_loss=17.84, over 7190.00 frames.], tot_loss[loss=2.008, simple_loss=0.2398, pruned_loss=0.02914, codebook_loss=18.59, over 1388847.88 frames.], batch size: 21, lr: 4.23e-04
+2022-05-27 22:33:47,286 INFO [train.py:823] (0/4) Epoch 40, batch 850, loss[loss=1.982, simple_loss=0.2449, pruned_loss=0.03148, codebook_loss=18.28, over 7179.00 frames.], tot_loss[loss=2.013, simple_loss=0.2401, pruned_loss=0.02949, codebook_loss=18.64, over 1397844.88 frames.], batch size: 22, lr: 4.23e-04
+2022-05-27 22:34:26,956 INFO [train.py:823] (0/4) Epoch 40, batch 900, loss[loss=2.118, simple_loss=0.2119, pruned_loss=0.02049, codebook_loss=19.91, over 7373.00 frames.], tot_loss[loss=2.007, simple_loss=0.239, pruned_loss=0.02922, codebook_loss=18.58, over 1390177.13 frames.], batch size: 20, lr: 4.23e-04
+2022-05-27 22:35:07,185 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-40.pt
+2022-05-27 22:35:21,137 INFO [train.py:823] (0/4) Epoch 41, batch 0, loss[loss=1.933, simple_loss=0.2255, pruned_loss=0.02827, codebook_loss=17.92, over 7108.00 frames.], tot_loss[loss=1.933, simple_loss=0.2255, pruned_loss=0.02827, codebook_loss=17.92, over 7108.00 frames.], batch size: 19, lr: 4.17e-04
+2022-05-27 22:36:00,865 INFO [train.py:823] (0/4) Epoch 41, batch 50, loss[loss=1.99, simple_loss=0.2434, pruned_loss=0.02984, codebook_loss=18.39, over 7375.00 frames.], tot_loss[loss=2, simple_loss=0.2382, pruned_loss=0.02862, codebook_loss=18.53, over 321353.79 frames.], batch size: 20, lr: 4.17e-04
+2022-05-27 22:36:40,678 INFO [train.py:823] (0/4) Epoch 41, batch 100, loss[loss=1.93, simple_loss=0.2175, pruned_loss=0.01684, codebook_loss=18.04, over 7095.00 frames.], tot_loss[loss=2.008, simple_loss=0.2394, pruned_loss=0.02914, codebook_loss=18.59, over 560363.24 frames.], batch size: 18, lr: 4.17e-04
+2022-05-27 22:37:20,562 INFO [train.py:823] (0/4) Epoch 41, batch 150, loss[loss=1.937, simple_loss=0.2415, pruned_loss=0.02689, codebook_loss=17.89, over 7004.00 frames.], tot_loss[loss=1.995, simple_loss=0.2392, pruned_loss=0.02879, codebook_loss=18.47, over 752043.31 frames.], batch size: 26, lr: 4.17e-04
+2022-05-27 22:38:00,723 INFO [train.py:823] (0/4) Epoch 41, batch 200, loss[loss=2.121, simple_loss=0.2378, pruned_loss=0.02743, codebook_loss=19.74, over 7388.00 frames.], tot_loss[loss=1.996, simple_loss=0.2401, pruned_loss=0.02874, codebook_loss=18.47, over 904693.63 frames.], batch size: 19, lr: 4.16e-04
+2022-05-27 22:38:41,533 INFO [train.py:823] (0/4) Epoch 41, batch 250, loss[loss=2.058, simple_loss=0.2491, pruned_loss=0.03478, codebook_loss=18.98, over 7106.00 frames.], tot_loss[loss=1.992, simple_loss=0.2388, pruned_loss=0.02839, codebook_loss=18.44, over 1015772.12 frames.], batch size: 19, lr: 4.16e-04
+2022-05-27 22:39:21,597 INFO [train.py:823] (0/4) Epoch 41, batch 300, loss[loss=1.896, simple_loss=0.2331, pruned_loss=0.0251, codebook_loss=17.55, over 7384.00 frames.], tot_loss[loss=1.993, simple_loss=0.2384, pruned_loss=0.02809, codebook_loss=18.46, over 1106454.32 frames.], batch size: 20, lr: 4.16e-04
+2022-05-27 22:40:01,365 INFO [train.py:823] (0/4) Epoch 41, batch 350, loss[loss=2.033, simple_loss=0.2342, pruned_loss=0.02893, codebook_loss=18.87, over 7171.00 frames.], tot_loss[loss=1.991, simple_loss=0.2384, pruned_loss=0.02803, codebook_loss=18.44, over 1174310.19 frames.], batch size: 22, lr: 4.15e-04
+2022-05-27 22:40:41,387 INFO [train.py:823] (0/4) Epoch 41, batch 400, loss[loss=2.007, simple_loss=0.2667, pruned_loss=0.05148, codebook_loss=18.23, over 7175.00 frames.], tot_loss[loss=1.996, simple_loss=0.2388, pruned_loss=0.02863, codebook_loss=18.48, over 1221267.96 frames.], batch size: 23, lr: 4.15e-04
+2022-05-27 22:41:21,029 INFO [train.py:823] (0/4) Epoch 41, batch 450, loss[loss=1.943, simple_loss=0.2177, pruned_loss=0.02586, codebook_loss=18.08, over 7096.00 frames.], tot_loss[loss=2, simple_loss=0.2389, pruned_loss=0.02874, codebook_loss=18.52, over 1263337.49 frames.], batch size: 18, lr: 4.15e-04
+2022-05-27 22:42:01,063 INFO [train.py:823] (0/4) Epoch 41, batch 500, loss[loss=1.893, simple_loss=0.2444, pruned_loss=0.02268, codebook_loss=17.48, over 7302.00 frames.], tot_loss[loss=2.001, simple_loss=0.2396, pruned_loss=0.02911, codebook_loss=18.52, over 1298713.71 frames.], batch size: 22, lr: 4.15e-04
+2022-05-27 22:42:40,898 INFO [train.py:823] (0/4) Epoch 41, batch 550, loss[loss=1.898, simple_loss=0.2271, pruned_loss=0.02106, codebook_loss=17.64, over 7203.00 frames.], tot_loss[loss=2.001, simple_loss=0.2391, pruned_loss=0.02898, codebook_loss=18.53, over 1321892.44 frames.], batch size: 19, lr: 4.14e-04
+2022-05-27 22:43:21,182 INFO [train.py:823] (0/4) Epoch 41, batch 600, loss[loss=1.927, simple_loss=0.2477, pruned_loss=0.02633, codebook_loss=17.77, over 7180.00 frames.], tot_loss[loss=1.998, simple_loss=0.238, pruned_loss=0.02859, codebook_loss=18.5, over 1339357.68 frames.], batch size: 21, lr: 4.14e-04
+2022-05-27 22:44:00,846 INFO [train.py:823] (0/4) Epoch 41, batch 650, loss[loss=1.91, simple_loss=0.2325, pruned_loss=0.02114, codebook_loss=17.73, over 7192.00 frames.], tot_loss[loss=1.995, simple_loss=0.2374, pruned_loss=0.02815, codebook_loss=18.48, over 1358150.57 frames.], batch size: 21, lr: 4.14e-04
+2022-05-27 22:44:40,898 INFO [train.py:823] (0/4) Epoch 41, batch 700, loss[loss=1.983, simple_loss=0.2245, pruned_loss=0.02621, codebook_loss=18.44, over 6792.00 frames.], tot_loss[loss=1.992, simple_loss=0.2374, pruned_loss=0.02832, codebook_loss=18.45, over 1371297.74 frames.], batch size: 15, lr: 4.14e-04
+2022-05-27 22:45:20,391 INFO [train.py:823] (0/4) Epoch 41, batch 750, loss[loss=1.951, simple_loss=0.2128, pruned_loss=0.02659, codebook_loss=18.18, over 7187.00 frames.], tot_loss[loss=1.993, simple_loss=0.2374, pruned_loss=0.0284, codebook_loss=18.46, over 1379866.81 frames.], batch size: 18, lr: 4.13e-04
+2022-05-27 22:46:00,175 INFO [train.py:823] (0/4) Epoch 41, batch 800, loss[loss=1.978, simple_loss=0.2217, pruned_loss=0.02977, codebook_loss=18.37, over 7297.00 frames.], tot_loss[loss=1.994, simple_loss=0.238, pruned_loss=0.02878, codebook_loss=18.46, over 1381507.86 frames.], batch size: 17, lr: 4.13e-04
+2022-05-27 22:46:40,266 INFO [train.py:823] (0/4) Epoch 41, batch 850, loss[loss=1.968, simple_loss=0.2459, pruned_loss=0.03049, codebook_loss=18.15, over 7291.00 frames.], tot_loss[loss=1.99, simple_loss=0.2377, pruned_loss=0.02851, codebook_loss=18.43, over 1393888.11 frames.], batch size: 19, lr: 4.13e-04
+2022-05-27 22:47:20,511 INFO [train.py:823] (0/4) Epoch 41, batch 900, loss[loss=2.034, simple_loss=0.2104, pruned_loss=0.02768, codebook_loss=19.01, over 7316.00 frames.], tot_loss[loss=1.993, simple_loss=0.2372, pruned_loss=0.02836, codebook_loss=18.46, over 1399540.93 frames.], batch size: 17, lr: 4.13e-04
+2022-05-27 22:47:59,784 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-41.pt
+2022-05-27 22:48:13,567 INFO [train.py:823] (0/4) Epoch 42, batch 0, loss[loss=1.99, simple_loss=0.2546, pruned_loss=0.02021, codebook_loss=18.43, over 7284.00 frames.], tot_loss[loss=1.99, simple_loss=0.2546, pruned_loss=0.02021, codebook_loss=18.43, over 7284.00 frames.], batch size: 21, lr: 4.07e-04
+2022-05-27 22:48:53,518 INFO [train.py:823] (0/4) Epoch 42, batch 50, loss[loss=2.116, simple_loss=0.2256, pruned_loss=0.02578, codebook_loss=19.77, over 7394.00 frames.], tot_loss[loss=1.983, simple_loss=0.2333, pruned_loss=0.02691, codebook_loss=18.4, over 323246.46 frames.], batch size: 19, lr: 4.07e-04
+2022-05-27 22:49:33,736 INFO [train.py:823] (0/4) Epoch 42, batch 100, loss[loss=1.895, simple_loss=0.2113, pruned_loss=0.02381, codebook_loss=17.66, over 6795.00 frames.], tot_loss[loss=1.974, simple_loss=0.2339, pruned_loss=0.02656, codebook_loss=18.3, over 565981.69 frames.], batch size: 15, lr: 4.07e-04
+2022-05-27 22:50:13,500 INFO [train.py:823] (0/4) Epoch 42, batch 150, loss[loss=2.149, simple_loss=0.2481, pruned_loss=0.03684, codebook_loss=19.88, over 7170.00 frames.], tot_loss[loss=1.975, simple_loss=0.2339, pruned_loss=0.02693, codebook_loss=18.31, over 755012.00 frames.], batch size: 22, lr: 4.07e-04
+2022-05-27 22:50:53,459 INFO [train.py:823] (0/4) Epoch 42, batch 200, loss[loss=1.943, simple_loss=0.2622, pruned_loss=0.03706, codebook_loss=17.75, over 7183.00 frames.], tot_loss[loss=1.98, simple_loss=0.2348, pruned_loss=0.02709, codebook_loss=18.36, over 900917.02 frames.], batch size: 24, lr: 4.06e-04
+2022-05-27 22:51:33,123 INFO [train.py:823] (0/4) Epoch 42, batch 250, loss[loss=2.117, simple_loss=0.2101, pruned_loss=0.02998, codebook_loss=19.82, over 7142.00 frames.], tot_loss[loss=1.991, simple_loss=0.2366, pruned_loss=0.02793, codebook_loss=18.45, over 1016916.08 frames.], batch size: 17, lr: 4.06e-04
+2022-05-27 22:52:13,176 INFO [train.py:823] (0/4) Epoch 42, batch 300, loss[loss=1.892, simple_loss=0.2481, pruned_loss=0.01812, codebook_loss=17.5, over 7189.00 frames.], tot_loss[loss=1.998, simple_loss=0.2374, pruned_loss=0.02856, codebook_loss=18.51, over 1101041.61 frames.], batch size: 21, lr: 4.06e-04
+2022-05-27 22:52:52,912 INFO [train.py:823] (0/4) Epoch 42, batch 350, loss[loss=1.917, simple_loss=0.2188, pruned_loss=0.02691, codebook_loss=17.81, over 7171.00 frames.], tot_loss[loss=1.997, simple_loss=0.2368, pruned_loss=0.0286, codebook_loss=18.5, over 1167936.30 frames.], batch size: 17, lr: 4.06e-04
+2022-05-27 22:53:35,685 INFO [train.py:823] (0/4) Epoch 42, batch 400, loss[loss=2.042, simple_loss=0.2189, pruned_loss=0.0287, codebook_loss=19.04, over 7287.00 frames.], tot_loss[loss=2.004, simple_loss=0.2374, pruned_loss=0.02863, codebook_loss=18.57, over 1217745.55 frames.], batch size: 17, lr: 4.05e-04
+2022-05-27 22:54:16,811 INFO [train.py:823] (0/4) Epoch 42, batch 450, loss[loss=2.058, simple_loss=0.2651, pruned_loss=0.04636, codebook_loss=18.79, over 7237.00 frames.], tot_loss[loss=2.003, simple_loss=0.2391, pruned_loss=0.02915, codebook_loss=18.54, over 1267986.30 frames.], batch size: 25, lr: 4.05e-04
+2022-05-27 22:54:57,131 INFO [train.py:823] (0/4) Epoch 42, batch 500, loss[loss=2.103, simple_loss=0.2154, pruned_loss=0.03107, codebook_loss=19.64, over 7151.00 frames.], tot_loss[loss=2.003, simple_loss=0.2376, pruned_loss=0.02887, codebook_loss=18.55, over 1301995.06 frames.], batch size: 17, lr: 4.05e-04
+2022-05-27 22:55:36,607 INFO [train.py:823] (0/4) Epoch 42, batch 550, loss[loss=2.011, simple_loss=0.2314, pruned_loss=0.02487, codebook_loss=18.7, over 7182.00 frames.], tot_loss[loss=2.001, simple_loss=0.2375, pruned_loss=0.02891, codebook_loss=18.53, over 1321894.58 frames.], batch size: 18, lr: 4.05e-04
+2022-05-27 22:56:16,721 INFO [train.py:823] (0/4) Epoch 42, batch 600, loss[loss=1.927, simple_loss=0.2321, pruned_loss=0.02347, codebook_loss=17.87, over 7190.00 frames.], tot_loss[loss=2.002, simple_loss=0.2387, pruned_loss=0.029, codebook_loss=18.53, over 1343220.34 frames.], batch size: 20, lr: 4.04e-04
+2022-05-27 22:56:56,700 INFO [train.py:823] (0/4) Epoch 42, batch 650, loss[loss=1.902, simple_loss=0.2425, pruned_loss=0.02863, codebook_loss=17.52, over 7165.00 frames.], tot_loss[loss=1.996, simple_loss=0.2387, pruned_loss=0.02863, codebook_loss=18.48, over 1364515.32 frames.], batch size: 23, lr: 4.04e-04
+2022-05-27 22:57:36,485 INFO [train.py:823] (0/4) Epoch 42, batch 700, loss[loss=1.998, simple_loss=0.2708, pruned_loss=0.03761, codebook_loss=18.25, over 7014.00 frames.], tot_loss[loss=1.997, simple_loss=0.2392, pruned_loss=0.02897, codebook_loss=18.49, over 1371100.53 frames.], batch size: 29, lr: 4.04e-04
+2022-05-27 22:58:16,374 INFO [train.py:823] (0/4) Epoch 42, batch 750, loss[loss=2.109, simple_loss=0.2494, pruned_loss=0.03083, codebook_loss=19.53, over 7377.00 frames.], tot_loss[loss=1.999, simple_loss=0.2392, pruned_loss=0.02884, codebook_loss=18.51, over 1385142.02 frames.], batch size: 21, lr: 4.04e-04
+2022-05-27 22:58:56,355 INFO [train.py:823] (0/4) Epoch 42, batch 800, loss[loss=2.153, simple_loss=0.2379, pruned_loss=0.02127, codebook_loss=20.13, over 6573.00 frames.], tot_loss[loss=2, simple_loss=0.239, pruned_loss=0.02856, codebook_loss=18.52, over 1391991.95 frames.], batch size: 34, lr: 4.03e-04
+2022-05-27 22:59:36,097 INFO [train.py:823] (0/4) Epoch 42, batch 850, loss[loss=1.922, simple_loss=0.2173, pruned_loss=0.01973, codebook_loss=17.93, over 7033.00 frames.], tot_loss[loss=1.994, simple_loss=0.2384, pruned_loss=0.02845, codebook_loss=18.46, over 1397955.22 frames.], batch size: 17, lr: 4.03e-04
+2022-05-27 23:00:15,918 INFO [train.py:823] (0/4) Epoch 42, batch 900, loss[loss=1.947, simple_loss=0.2362, pruned_loss=0.02535, codebook_loss=18.04, over 4856.00 frames.], tot_loss[loss=1.993, simple_loss=0.238, pruned_loss=0.02847, codebook_loss=18.46, over 1397417.77 frames.], batch size: 47, lr: 4.03e-04
+2022-05-27 23:00:55,881 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-42.pt
+2022-05-27 23:01:10,031 INFO [train.py:823] (0/4) Epoch 43, batch 0, loss[loss=1.921, simple_loss=0.232, pruned_loss=0.02294, codebook_loss=17.82, over 7297.00 frames.], tot_loss[loss=1.921, simple_loss=0.232, pruned_loss=0.02294, codebook_loss=17.82, over 7297.00 frames.], batch size: 19, lr: 3.98e-04
+2022-05-27 23:01:50,292 INFO [train.py:823] (0/4) Epoch 43, batch 50, loss[loss=1.892, simple_loss=0.2378, pruned_loss=0.0264, codebook_loss=17.47, over 7375.00 frames.], tot_loss[loss=1.967, simple_loss=0.2372, pruned_loss=0.02741, codebook_loss=18.21, over 321901.53 frames.], batch size: 20, lr: 3.98e-04
+2022-05-27 23:02:31,471 INFO [train.py:823] (0/4) Epoch 43, batch 100, loss[loss=2.177, simple_loss=0.2542, pruned_loss=0.04191, codebook_loss=20.08, over 7149.00 frames.], tot_loss[loss=1.979, simple_loss=0.2356, pruned_loss=0.02779, codebook_loss=18.34, over 565716.87 frames.], batch size: 23, lr: 3.97e-04
+2022-05-27 23:02:32,554 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/checkpoint-40000.pt
+2022-05-27 23:03:15,174 INFO [train.py:823] (0/4) Epoch 43, batch 150, loss[loss=2.039, simple_loss=0.2459, pruned_loss=0.03284, codebook_loss=18.83, over 6578.00 frames.], tot_loss[loss=2.006, simple_loss=0.2381, pruned_loss=0.02973, codebook_loss=18.57, over 753548.29 frames.], batch size: 34, lr: 3.97e-04
+2022-05-27 23:03:55,325 INFO [train.py:823] (0/4) Epoch 43, batch 200, loss[loss=2.22, simple_loss=0.2602, pruned_loss=0.03839, codebook_loss=20.52, over 7335.00 frames.], tot_loss[loss=1.998, simple_loss=0.2383, pruned_loss=0.02939, codebook_loss=18.49, over 905090.65 frames.], batch size: 23, lr: 3.97e-04
+2022-05-27 23:04:35,694 INFO [train.py:823] (0/4) Epoch 43, batch 250, loss[loss=2.082, simple_loss=0.2168, pruned_loss=0.03115, codebook_loss=19.43, over 7314.00 frames.], tot_loss[loss=1.995, simple_loss=0.2378, pruned_loss=0.02897, codebook_loss=18.47, over 1021880.98 frames.], batch size: 18, lr: 3.97e-04
+2022-05-27 23:05:15,233 INFO [train.py:823] (0/4) Epoch 43, batch 300, loss[loss=1.866, simple_loss=0.2198, pruned_loss=0.01905, codebook_loss=17.37, over 7096.00 frames.], tot_loss[loss=1.989, simple_loss=0.2366, pruned_loss=0.02858, codebook_loss=18.42, over 1101874.69 frames.], batch size: 18, lr: 3.96e-04
+2022-05-27 23:05:55,396 INFO [train.py:823] (0/4) Epoch 43, batch 350, loss[loss=2.066, simple_loss=0.238, pruned_loss=0.02992, codebook_loss=19.18, over 7339.00 frames.], tot_loss[loss=1.992, simple_loss=0.2372, pruned_loss=0.02851, codebook_loss=18.45, over 1175233.88 frames.], batch size: 23, lr: 3.96e-04
+2022-05-27 23:06:35,409 INFO [train.py:823] (0/4) Epoch 43, batch 400, loss[loss=1.958, simple_loss=0.2412, pruned_loss=0.02271, codebook_loss=18.14, over 7197.00 frames.], tot_loss[loss=1.994, simple_loss=0.2374, pruned_loss=0.02853, codebook_loss=18.47, over 1230577.76 frames.], batch size: 20, lr: 3.96e-04
+2022-05-27 23:07:15,800 INFO [train.py:823] (0/4) Epoch 43, batch 450, loss[loss=1.966, simple_loss=0.2464, pruned_loss=0.03158, codebook_loss=18.11, over 7189.00 frames.], tot_loss[loss=1.997, simple_loss=0.2375, pruned_loss=0.02856, codebook_loss=18.5, over 1276892.97 frames.], batch size: 21, lr: 3.96e-04
+2022-05-27 23:07:55,854 INFO [train.py:823] (0/4) Epoch 43, batch 500, loss[loss=2.009, simple_loss=0.1875, pruned_loss=0.01261, codebook_loss=19.03, over 7443.00 frames.], tot_loss[loss=1.998, simple_loss=0.2375, pruned_loss=0.02858, codebook_loss=18.5, over 1308828.09 frames.], batch size: 18, lr: 3.95e-04
+2022-05-27 23:08:36,122 INFO [train.py:823] (0/4) Epoch 43, batch 550, loss[loss=1.963, simple_loss=0.2655, pruned_loss=0.03737, codebook_loss=17.93, over 7274.00 frames.], tot_loss[loss=1.995, simple_loss=0.2383, pruned_loss=0.02857, codebook_loss=18.47, over 1338344.39 frames.], batch size: 21, lr: 3.95e-04
+2022-05-27 23:09:15,804 INFO [train.py:823] (0/4) Epoch 43, batch 600, loss[loss=2.147, simple_loss=0.2518, pruned_loss=0.02995, codebook_loss=19.91, over 7163.00 frames.], tot_loss[loss=1.995, simple_loss=0.2386, pruned_loss=0.02851, codebook_loss=18.47, over 1357557.30 frames.], batch size: 22, lr: 3.95e-04
+2022-05-27 23:09:55,882 INFO [train.py:823] (0/4) Epoch 43, batch 650, loss[loss=1.93, simple_loss=0.2524, pruned_loss=0.03031, codebook_loss=17.74, over 7203.00 frames.], tot_loss[loss=1.991, simple_loss=0.238, pruned_loss=0.02804, codebook_loss=18.44, over 1374506.25 frames.], batch size: 20, lr: 3.95e-04
+2022-05-27 23:10:35,787 INFO [train.py:823] (0/4) Epoch 43, batch 700, loss[loss=1.901, simple_loss=0.2116, pruned_loss=0.01418, codebook_loss=17.81, over 7424.00 frames.], tot_loss[loss=1.994, simple_loss=0.2376, pruned_loss=0.02809, codebook_loss=18.47, over 1384408.40 frames.], batch size: 18, lr: 3.94e-04
+2022-05-27 23:11:16,031 INFO [train.py:823] (0/4) Epoch 43, batch 750, loss[loss=2.108, simple_loss=0.2428, pruned_loss=0.02106, codebook_loss=19.65, over 7194.00 frames.], tot_loss[loss=1.995, simple_loss=0.2374, pruned_loss=0.02775, codebook_loss=18.49, over 1394304.15 frames.], batch size: 21, lr: 3.94e-04
+2022-05-27 23:11:55,943 INFO [train.py:823] (0/4) Epoch 43, batch 800, loss[loss=1.91, simple_loss=0.245, pruned_loss=0.02449, codebook_loss=17.63, over 7302.00 frames.], tot_loss[loss=1.994, simple_loss=0.2369, pruned_loss=0.02775, codebook_loss=18.48, over 1402924.71 frames.], batch size: 22, lr: 3.94e-04
+2022-05-27 23:12:36,060 INFO [train.py:823] (0/4) Epoch 43, batch 850, loss[loss=2.049, simple_loss=0.2798, pruned_loss=0.05236, codebook_loss=18.57, over 7179.00 frames.], tot_loss[loss=1.992, simple_loss=0.2368, pruned_loss=0.02786, codebook_loss=18.46, over 1405254.16 frames.], batch size: 22, lr: 3.94e-04
+2022-05-27 23:13:16,020 INFO [train.py:823] (0/4) Epoch 43, batch 900, loss[loss=1.973, simple_loss=0.2147, pruned_loss=0.03183, codebook_loss=18.33, over 6846.00 frames.], tot_loss[loss=1.995, simple_loss=0.2366, pruned_loss=0.02822, codebook_loss=18.48, over 1402777.37 frames.], batch size: 15, lr: 3.93e-04
+2022-05-27 23:13:55,119 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-43.pt
+2022-05-27 23:14:05,785 INFO [train.py:823] (0/4) Epoch 44, batch 0, loss[loss=1.854, simple_loss=0.2236, pruned_loss=0.01643, codebook_loss=17.26, over 7295.00 frames.], tot_loss[loss=1.854, simple_loss=0.2236, pruned_loss=0.01643, codebook_loss=17.26, over 7295.00 frames.], batch size: 22, lr: 3.89e-04
+2022-05-27 23:14:46,503 INFO [train.py:823] (0/4) Epoch 44, batch 50, loss[loss=2.002, simple_loss=0.2358, pruned_loss=0.0317, codebook_loss=18.52, over 7023.00 frames.], tot_loss[loss=1.979, simple_loss=0.2333, pruned_loss=0.02665, codebook_loss=18.35, over 322105.05 frames.], batch size: 17, lr: 3.89e-04
+2022-05-27 23:15:26,589 INFO [train.py:823] (0/4) Epoch 44, batch 100, loss[loss=2.093, simple_loss=0.2439, pruned_loss=0.02939, codebook_loss=19.41, over 7285.00 frames.], tot_loss[loss=1.971, simple_loss=0.2364, pruned_loss=0.02712, codebook_loss=18.26, over 566839.97 frames.], batch size: 20, lr: 3.88e-04
+2022-05-27 23:16:06,703 INFO [train.py:823] (0/4) Epoch 44, batch 150, loss[loss=1.963, simple_loss=0.2355, pruned_loss=0.02939, codebook_loss=18.15, over 7284.00 frames.], tot_loss[loss=1.972, simple_loss=0.2352, pruned_loss=0.02711, codebook_loss=18.27, over 757939.06 frames.], batch size: 20, lr: 3.88e-04
+2022-05-27 23:16:46,972 INFO [train.py:823] (0/4) Epoch 44, batch 200, loss[loss=1.939, simple_loss=0.2557, pruned_loss=0.03431, codebook_loss=17.77, over 7244.00 frames.], tot_loss[loss=1.974, simple_loss=0.2363, pruned_loss=0.02771, codebook_loss=18.28, over 904131.59 frames.], batch size: 24, lr: 3.88e-04
+2022-05-27 23:17:26,782 INFO [train.py:823] (0/4) Epoch 44, batch 250, loss[loss=1.917, simple_loss=0.2262, pruned_loss=0.02358, codebook_loss=17.8, over 7133.00 frames.], tot_loss[loss=1.977, simple_loss=0.2362, pruned_loss=0.02764, codebook_loss=18.32, over 1021489.12 frames.], batch size: 23, lr: 3.88e-04
+2022-05-27 23:18:08,118 INFO [train.py:823] (0/4) Epoch 44, batch 300, loss[loss=1.893, simple_loss=0.2402, pruned_loss=0.02325, codebook_loss=17.49, over 7288.00 frames.], tot_loss[loss=1.981, simple_loss=0.2366, pruned_loss=0.02777, codebook_loss=18.35, over 1108121.61 frames.], batch size: 21, lr: 3.87e-04
+2022-05-27 23:18:50,348 INFO [train.py:823] (0/4) Epoch 44, batch 350, loss[loss=2.039, simple_loss=0.1987, pruned_loss=0.02411, codebook_loss=19.15, over 7022.00 frames.], tot_loss[loss=1.984, simple_loss=0.2366, pruned_loss=0.02798, codebook_loss=18.37, over 1170955.88 frames.], batch size: 16, lr: 3.87e-04
+2022-05-27 23:19:30,572 INFO [train.py:823] (0/4) Epoch 44, batch 400, loss[loss=1.875, simple_loss=0.2332, pruned_loss=0.01736, codebook_loss=17.41, over 5143.00 frames.], tot_loss[loss=1.983, simple_loss=0.2361, pruned_loss=0.0276, codebook_loss=18.38, over 1221155.96 frames.], batch size: 47, lr: 3.87e-04
+2022-05-27 23:20:10,457 INFO [train.py:823] (0/4) Epoch 44, batch 450, loss[loss=1.963, simple_loss=0.2587, pruned_loss=0.03516, codebook_loss=17.99, over 7181.00 frames.], tot_loss[loss=1.981, simple_loss=0.237, pruned_loss=0.02778, codebook_loss=18.35, over 1264806.40 frames.], batch size: 25, lr: 3.87e-04
+2022-05-27 23:20:50,565 INFO [train.py:823] (0/4) Epoch 44, batch 500, loss[loss=1.973, simple_loss=0.2571, pruned_loss=0.0312, codebook_loss=18.14, over 7146.00 frames.], tot_loss[loss=1.982, simple_loss=0.2364, pruned_loss=0.02767, codebook_loss=18.36, over 1302052.08 frames.], batch size: 17, lr: 3.86e-04
+2022-05-27 23:21:30,259 INFO [train.py:823] (0/4) Epoch 44, batch 550, loss[loss=2.113, simple_loss=0.2494, pruned_loss=0.03906, codebook_loss=19.49, over 7220.00 frames.], tot_loss[loss=1.982, simple_loss=0.237, pruned_loss=0.02745, codebook_loss=18.36, over 1330235.52 frames.], batch size: 24, lr: 3.86e-04
+2022-05-27 23:22:10,613 INFO [train.py:823] (0/4) Epoch 44, batch 600, loss[loss=1.879, simple_loss=0.2112, pruned_loss=0.01864, codebook_loss=17.54, over 7390.00 frames.], tot_loss[loss=1.981, simple_loss=0.2364, pruned_loss=0.02721, codebook_loss=18.35, over 1352655.45 frames.], batch size: 19, lr: 3.86e-04
+2022-05-27 23:22:50,454 INFO [train.py:823] (0/4) Epoch 44, batch 650, loss[loss=1.893, simple_loss=0.2413, pruned_loss=0.01929, codebook_loss=17.53, over 7422.00 frames.], tot_loss[loss=1.987, simple_loss=0.2363, pruned_loss=0.0274, codebook_loss=18.42, over 1367288.87 frames.], batch size: 22, lr: 3.86e-04
+2022-05-27 23:23:30,761 INFO [train.py:823] (0/4) Epoch 44, batch 700, loss[loss=1.915, simple_loss=0.2359, pruned_loss=0.02611, codebook_loss=17.71, over 7148.00 frames.], tot_loss[loss=1.986, simple_loss=0.2356, pruned_loss=0.02706, codebook_loss=18.42, over 1379223.05 frames.], batch size: 23, lr: 3.85e-04
+2022-05-27 23:24:10,473 INFO [train.py:823] (0/4) Epoch 44, batch 750, loss[loss=2.316, simple_loss=0.2558, pruned_loss=0.04426, codebook_loss=21.44, over 7136.00 frames.], tot_loss[loss=1.985, simple_loss=0.2359, pruned_loss=0.02691, codebook_loss=18.4, over 1390767.04 frames.], batch size: 17, lr: 3.85e-04
+2022-05-27 23:24:50,889 INFO [train.py:823] (0/4) Epoch 44, batch 800, loss[loss=2.233, simple_loss=0.2736, pruned_loss=0.04028, codebook_loss=20.56, over 7202.00 frames.], tot_loss[loss=1.984, simple_loss=0.2364, pruned_loss=0.02701, codebook_loss=18.39, over 1398016.34 frames.], batch size: 25, lr: 3.85e-04
+2022-05-27 23:25:30,978 INFO [train.py:823] (0/4) Epoch 44, batch 850, loss[loss=2.008, simple_loss=0.226, pruned_loss=0.03077, codebook_loss=18.64, over 6816.00 frames.], tot_loss[loss=1.988, simple_loss=0.2367, pruned_loss=0.02741, codebook_loss=18.42, over 1403199.70 frames.], batch size: 15, lr: 3.85e-04
+2022-05-27 23:26:12,391 INFO [train.py:823] (0/4) Epoch 44, batch 900, loss[loss=2.087, simple_loss=0.2078, pruned_loss=0.01783, codebook_loss=19.65, over 7281.00 frames.], tot_loss[loss=1.993, simple_loss=0.2369, pruned_loss=0.0276, codebook_loss=18.47, over 1400957.21 frames.], batch size: 17, lr: 3.85e-04
+2022-05-27 23:26:52,090 INFO [train.py:823] (0/4) Epoch 44, batch 950, loss[loss=1.881, simple_loss=0.2224, pruned_loss=0.01978, codebook_loss=17.5, over 4513.00 frames.], tot_loss[loss=1.991, simple_loss=0.2368, pruned_loss=0.02763, codebook_loss=18.45, over 1377270.62 frames.], batch size: 47, lr: 3.84e-04
+2022-05-27 23:26:53,294 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-44.pt
+2022-05-27 23:27:07,452 INFO [train.py:823] (0/4) Epoch 45, batch 0, loss[loss=1.858, simple_loss=0.236, pruned_loss=0.01561, codebook_loss=17.24, over 7271.00 frames.], tot_loss[loss=1.858, simple_loss=0.236, pruned_loss=0.01561, codebook_loss=17.24, over 7271.00 frames.], batch size: 20, lr: 3.80e-04
+2022-05-27 23:27:47,713 INFO [train.py:823] (0/4) Epoch 45, batch 50, loss[loss=1.91, simple_loss=0.2582, pruned_loss=0.02642, codebook_loss=17.54, over 7293.00 frames.], tot_loss[loss=2.008, simple_loss=0.2379, pruned_loss=0.02756, codebook_loss=18.62, over 323849.10 frames.], batch size: 21, lr: 3.80e-04
+2022-05-27 23:28:27,600 INFO [train.py:823] (0/4) Epoch 45, batch 100, loss[loss=1.918, simple_loss=0.2849, pruned_loss=0.02998, codebook_loss=17.45, over 7373.00 frames.], tot_loss[loss=1.978, simple_loss=0.2374, pruned_loss=0.02648, codebook_loss=18.33, over 567744.56 frames.], batch size: 21, lr: 3.80e-04
+2022-05-27 23:29:07,784 INFO [train.py:823] (0/4) Epoch 45, batch 150, loss[loss=1.889, simple_loss=0.2014, pruned_loss=0.01367, codebook_loss=17.75, over 7207.00 frames.], tot_loss[loss=1.973, simple_loss=0.2358, pruned_loss=0.02658, codebook_loss=18.29, over 752216.81 frames.], batch size: 16, lr: 3.79e-04
+2022-05-27 23:29:47,563 INFO [train.py:823] (0/4) Epoch 45, batch 200, loss[loss=1.981, simple_loss=0.2394, pruned_loss=0.03948, codebook_loss=18.22, over 4647.00 frames.], tot_loss[loss=1.988, simple_loss=0.2365, pruned_loss=0.02738, codebook_loss=18.42, over 896394.51 frames.], batch size: 46, lr: 3.79e-04
+2022-05-27 23:30:27,676 INFO [train.py:823] (0/4) Epoch 45, batch 250, loss[loss=1.917, simple_loss=0.2356, pruned_loss=0.02098, codebook_loss=17.78, over 6487.00 frames.], tot_loss[loss=1.985, simple_loss=0.2365, pruned_loss=0.02744, codebook_loss=18.4, over 1009429.22 frames.], batch size: 34, lr: 3.79e-04
+2022-05-27 23:31:07,615 INFO [train.py:823] (0/4) Epoch 45, batch 300, loss[loss=1.973, simple_loss=0.2384, pruned_loss=0.04171, codebook_loss=18.13, over 7148.00 frames.], tot_loss[loss=1.979, simple_loss=0.2346, pruned_loss=0.02692, codebook_loss=18.35, over 1098910.06 frames.], batch size: 23, lr: 3.79e-04
+2022-05-27 23:31:47,904 INFO [train.py:823] (0/4) Epoch 45, batch 350, loss[loss=1.869, simple_loss=0.2331, pruned_loss=0.0143, codebook_loss=17.38, over 7418.00 frames.], tot_loss[loss=1.98, simple_loss=0.2352, pruned_loss=0.02705, codebook_loss=18.35, over 1171370.75 frames.], batch size: 22, lr: 3.78e-04
+2022-05-27 23:32:27,594 INFO [train.py:823] (0/4) Epoch 45, batch 400, loss[loss=1.841, simple_loss=0.2318, pruned_loss=0.02366, codebook_loss=17.01, over 7378.00 frames.], tot_loss[loss=1.979, simple_loss=0.2353, pruned_loss=0.02723, codebook_loss=18.35, over 1228676.52 frames.], batch size: 20, lr: 3.78e-04
+2022-05-27 23:33:07,576 INFO [train.py:823] (0/4) Epoch 45, batch 450, loss[loss=1.909, simple_loss=0.2303, pruned_loss=0.03047, codebook_loss=17.63, over 7201.00 frames.], tot_loss[loss=1.978, simple_loss=0.2349, pruned_loss=0.02726, codebook_loss=18.33, over 1269799.76 frames.], batch size: 18, lr: 3.78e-04
+2022-05-27 23:33:47,536 INFO [train.py:823] (0/4) Epoch 45, batch 500, loss[loss=2.016, simple_loss=0.271, pruned_loss=0.04445, codebook_loss=18.36, over 7233.00 frames.], tot_loss[loss=1.985, simple_loss=0.236, pruned_loss=0.02784, codebook_loss=18.39, over 1308184.62 frames.], batch size: 24, lr: 3.78e-04
+2022-05-27 23:34:27,798 INFO [train.py:823] (0/4) Epoch 45, batch 550, loss[loss=1.878, simple_loss=0.2026, pruned_loss=0.01896, codebook_loss=17.58, over 7195.00 frames.], tot_loss[loss=1.983, simple_loss=0.2344, pruned_loss=0.02733, codebook_loss=18.39, over 1334160.52 frames.], batch size: 18, lr: 3.78e-04
+2022-05-27 23:35:07,235 INFO [train.py:823] (0/4) Epoch 45, batch 600, loss[loss=1.969, simple_loss=0.2382, pruned_loss=0.01705, codebook_loss=18.33, over 6360.00 frames.], tot_loss[loss=1.977, simple_loss=0.2353, pruned_loss=0.02746, codebook_loss=18.32, over 1346956.15 frames.], batch size: 34, lr: 3.77e-04
+2022-05-27 23:35:47,193 INFO [train.py:823] (0/4) Epoch 45, batch 650, loss[loss=2.009, simple_loss=0.266, pruned_loss=0.04117, codebook_loss=18.35, over 7154.00 frames.], tot_loss[loss=1.982, simple_loss=0.2354, pruned_loss=0.02763, codebook_loss=18.37, over 1362094.04 frames.], batch size: 23, lr: 3.77e-04
+2022-05-27 23:36:26,948 INFO [train.py:823] (0/4) Epoch 45, batch 700, loss[loss=2.018, simple_loss=0.2476, pruned_loss=0.03227, codebook_loss=18.62, over 7298.00 frames.], tot_loss[loss=1.988, simple_loss=0.2362, pruned_loss=0.02829, codebook_loss=18.41, over 1376186.33 frames.], batch size: 22, lr: 3.77e-04
+2022-05-27 23:37:06,798 INFO [train.py:823] (0/4) Epoch 45, batch 750, loss[loss=1.937, simple_loss=0.2521, pruned_loss=0.02731, codebook_loss=17.83, over 6892.00 frames.], tot_loss[loss=1.988, simple_loss=0.2371, pruned_loss=0.02819, codebook_loss=18.41, over 1385771.33 frames.], batch size: 29, lr: 3.77e-04
+2022-05-27 23:37:46,668 INFO [train.py:823] (0/4) Epoch 45, batch 800, loss[loss=2.444, simple_loss=0.2795, pruned_loss=0.04677, codebook_loss=22.58, over 7322.00 frames.], tot_loss[loss=1.987, simple_loss=0.2368, pruned_loss=0.02795, codebook_loss=18.41, over 1394755.45 frames.], batch size: 23, lr: 3.77e-04
+2022-05-27 23:38:26,822 INFO [train.py:823] (0/4) Epoch 45, batch 850, loss[loss=1.946, simple_loss=0.2403, pruned_loss=0.0272, codebook_loss=17.99, over 7175.00 frames.], tot_loss[loss=1.988, simple_loss=0.2371, pruned_loss=0.02774, codebook_loss=18.42, over 1397062.14 frames.], batch size: 21, lr: 3.76e-04
+2022-05-27 23:39:06,665 INFO [train.py:823] (0/4) Epoch 45, batch 900, loss[loss=2.117, simple_loss=0.2132, pruned_loss=0.02419, codebook_loss=19.86, over 7023.00 frames.], tot_loss[loss=1.989, simple_loss=0.2376, pruned_loss=0.02786, codebook_loss=18.43, over 1399288.82 frames.], batch size: 17, lr: 3.76e-04
+2022-05-27 23:39:46,942 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-45.pt
+2022-05-27 23:40:00,608 INFO [train.py:823] (0/4) Epoch 46, batch 0, loss[loss=1.975, simple_loss=0.2502, pruned_loss=0.03803, codebook_loss=18.12, over 7166.00 frames.], tot_loss[loss=1.975, simple_loss=0.2502, pruned_loss=0.03803, codebook_loss=18.12, over 7166.00 frames.], batch size: 22, lr: 3.72e-04
+2022-05-27 23:40:40,261 INFO [train.py:823] (0/4) Epoch 46, batch 50, loss[loss=1.934, simple_loss=0.2348, pruned_loss=0.02415, codebook_loss=17.93, over 7269.00 frames.], tot_loss[loss=1.968, simple_loss=0.2357, pruned_loss=0.02616, codebook_loss=18.24, over 315986.12 frames.], batch size: 20, lr: 3.72e-04
+2022-05-27 23:41:20,244 INFO [train.py:823] (0/4) Epoch 46, batch 100, loss[loss=1.908, simple_loss=0.2007, pruned_loss=0.02045, codebook_loss=17.88, over 7011.00 frames.], tot_loss[loss=1.961, simple_loss=0.233, pruned_loss=0.02589, codebook_loss=18.18, over 562500.83 frames.], batch size: 16, lr: 3.71e-04
+2022-05-27 23:42:00,063 INFO [train.py:823] (0/4) Epoch 46, batch 150, loss[loss=1.925, simple_loss=0.2438, pruned_loss=0.02402, codebook_loss=17.79, over 7117.00 frames.], tot_loss[loss=1.97, simple_loss=0.235, pruned_loss=0.02708, codebook_loss=18.25, over 754880.18 frames.], batch size: 20, lr: 3.71e-04
+2022-05-27 23:42:40,051 INFO [train.py:823] (0/4) Epoch 46, batch 200, loss[loss=1.994, simple_loss=0.2567, pruned_loss=0.03382, codebook_loss=18.31, over 7342.00 frames.], tot_loss[loss=1.976, simple_loss=0.2351, pruned_loss=0.02756, codebook_loss=18.31, over 907270.97 frames.], batch size: 23, lr: 3.71e-04
+2022-05-27 23:43:22,185 INFO [train.py:823] (0/4) Epoch 46, batch 250, loss[loss=1.93, simple_loss=0.2493, pruned_loss=0.03618, codebook_loss=17.69, over 7172.00 frames.], tot_loss[loss=1.976, simple_loss=0.236, pruned_loss=0.02784, codebook_loss=18.3, over 1021120.81 frames.], batch size: 23, lr: 3.71e-04
+2022-05-27 23:44:03,558 INFO [train.py:823] (0/4) Epoch 46, batch 300, loss[loss=1.919, simple_loss=0.2536, pruned_loss=0.02239, codebook_loss=17.7, over 6894.00 frames.], tot_loss[loss=1.973, simple_loss=0.2367, pruned_loss=0.02737, codebook_loss=18.27, over 1107492.87 frames.], batch size: 29, lr: 3.70e-04
+2022-05-27 23:44:43,201 INFO [train.py:823] (0/4) Epoch 46, batch 350, loss[loss=2.123, simple_loss=0.2719, pruned_loss=0.04513, codebook_loss=19.42, over 6487.00 frames.], tot_loss[loss=1.977, simple_loss=0.2377, pruned_loss=0.02751, codebook_loss=18.31, over 1179539.16 frames.], batch size: 34, lr: 3.70e-04
+2022-05-27 23:45:23,228 INFO [train.py:823] (0/4) Epoch 46, batch 400, loss[loss=1.958, simple_loss=0.2607, pruned_loss=0.03266, codebook_loss=17.95, over 7140.00 frames.], tot_loss[loss=1.974, simple_loss=0.2377, pruned_loss=0.0273, codebook_loss=18.28, over 1236144.05 frames.], batch size: 23, lr: 3.70e-04
+2022-05-27 23:46:03,178 INFO [train.py:823] (0/4) Epoch 46, batch 450, loss[loss=1.995, simple_loss=0.2509, pruned_loss=0.04019, codebook_loss=18.29, over 7269.00 frames.], tot_loss[loss=1.98, simple_loss=0.2374, pruned_loss=0.02728, codebook_loss=18.34, over 1279024.00 frames.], batch size: 20, lr: 3.70e-04
+2022-05-27 23:46:42,928 INFO [train.py:823] (0/4) Epoch 46, batch 500, loss[loss=1.896, simple_loss=0.1972, pruned_loss=0.01776, codebook_loss=17.8, over 6805.00 frames.], tot_loss[loss=1.984, simple_loss=0.2381, pruned_loss=0.02759, codebook_loss=18.37, over 1303752.55 frames.], batch size: 15, lr: 3.70e-04
+2022-05-27 23:47:22,910 INFO [train.py:823] (0/4) Epoch 46, batch 550, loss[loss=1.9, simple_loss=0.2426, pruned_loss=0.02517, codebook_loss=17.53, over 7317.00 frames.], tot_loss[loss=1.986, simple_loss=0.2377, pruned_loss=0.02748, codebook_loss=18.39, over 1333692.64 frames.], batch size: 22, lr: 3.69e-04
+2022-05-27 23:48:03,067 INFO [train.py:823] (0/4) Epoch 46, batch 600, loss[loss=1.943, simple_loss=0.2038, pruned_loss=0.01991, codebook_loss=18.21, over 7433.00 frames.], tot_loss[loss=1.98, simple_loss=0.2372, pruned_loss=0.02693, codebook_loss=18.35, over 1352113.16 frames.], batch size: 18, lr: 3.69e-04
+2022-05-27 23:48:42,889 INFO [train.py:823] (0/4) Epoch 46, batch 650, loss[loss=1.927, simple_loss=0.2487, pruned_loss=0.02758, codebook_loss=17.75, over 7142.00 frames.], tot_loss[loss=1.977, simple_loss=0.2363, pruned_loss=0.0267, codebook_loss=18.32, over 1365948.65 frames.], batch size: 23, lr: 3.69e-04
+2022-05-27 23:49:24,237 INFO [train.py:823] (0/4) Epoch 46, batch 700, loss[loss=1.884, simple_loss=0.2149, pruned_loss=0.01462, codebook_loss=17.62, over 7163.00 frames.], tot_loss[loss=1.978, simple_loss=0.2356, pruned_loss=0.02661, codebook_loss=18.34, over 1374444.14 frames.], batch size: 17, lr: 3.69e-04
+2022-05-27 23:50:04,152 INFO [train.py:823] (0/4) Epoch 46, batch 750, loss[loss=2.034, simple_loss=0.2635, pruned_loss=0.03149, codebook_loss=18.7, over 6501.00 frames.], tot_loss[loss=1.975, simple_loss=0.2354, pruned_loss=0.02669, codebook_loss=18.31, over 1383499.07 frames.], batch size: 34, lr: 3.69e-04
+2022-05-27 23:50:44,368 INFO [train.py:823] (0/4) Epoch 46, batch 800, loss[loss=2.027, simple_loss=0.2431, pruned_loss=0.02402, codebook_loss=18.82, over 7196.00 frames.], tot_loss[loss=1.981, simple_loss=0.2358, pruned_loss=0.02674, codebook_loss=18.36, over 1386470.32 frames.], batch size: 20, lr: 3.68e-04
+2022-05-27 23:51:24,078 INFO [train.py:823] (0/4) Epoch 46, batch 850, loss[loss=1.93, simple_loss=0.2473, pruned_loss=0.0354, codebook_loss=17.7, over 7354.00 frames.], tot_loss[loss=1.983, simple_loss=0.2353, pruned_loss=0.02676, codebook_loss=18.38, over 1389691.39 frames.], batch size: 23, lr: 3.68e-04
+2022-05-27 23:52:04,344 INFO [train.py:823] (0/4) Epoch 46, batch 900, loss[loss=1.87, simple_loss=0.2353, pruned_loss=0.02097, codebook_loss=17.31, over 7091.00 frames.], tot_loss[loss=1.983, simple_loss=0.2354, pruned_loss=0.02671, codebook_loss=18.38, over 1396323.31 frames.], batch size: 18, lr: 3.68e-04
+2022-05-27 23:52:43,450 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-46.pt
+2022-05-27 23:52:54,929 INFO [train.py:823] (0/4) Epoch 47, batch 0, loss[loss=1.891, simple_loss=0.2233, pruned_loss=0.02512, codebook_loss=17.54, over 7009.00 frames.], tot_loss[loss=1.891, simple_loss=0.2233, pruned_loss=0.02512, codebook_loss=17.54, over 7009.00 frames.], batch size: 16, lr: 3.64e-04
+2022-05-27 23:53:35,049 INFO [train.py:823] (0/4) Epoch 47, batch 50, loss[loss=2.014, simple_loss=0.2034, pruned_loss=0.02297, codebook_loss=18.89, over 7311.00 frames.], tot_loss[loss=1.953, simple_loss=0.2315, pruned_loss=0.02572, codebook_loss=18.11, over 321726.93 frames.], batch size: 17, lr: 3.64e-04
+2022-05-27 23:54:15,079 INFO [train.py:823] (0/4) Epoch 47, batch 100, loss[loss=1.842, simple_loss=0.2006, pruned_loss=0.01503, codebook_loss=17.26, over 7301.00 frames.], tot_loss[loss=1.982, simple_loss=0.2324, pruned_loss=0.02629, codebook_loss=18.39, over 565110.53 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:54:55,168 INFO [train.py:823] (0/4) Epoch 47, batch 150, loss[loss=2.08, simple_loss=0.2377, pruned_loss=0.0209, codebook_loss=19.4, over 7287.00 frames.], tot_loss[loss=1.975, simple_loss=0.2333, pruned_loss=0.02631, codebook_loss=18.32, over 756881.20 frames.], batch size: 22, lr: 3.63e-04
+2022-05-27 23:55:34,798 INFO [train.py:823] (0/4) Epoch 47, batch 200, loss[loss=2.041, simple_loss=0.2204, pruned_loss=0.01819, codebook_loss=19.12, over 7098.00 frames.], tot_loss[loss=1.974, simple_loss=0.2338, pruned_loss=0.02667, codebook_loss=18.3, over 901050.54 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:56:14,826 INFO [train.py:823] (0/4) Epoch 47, batch 250, loss[loss=1.863, simple_loss=0.222, pruned_loss=0.02365, codebook_loss=17.28, over 7392.00 frames.], tot_loss[loss=1.97, simple_loss=0.2344, pruned_loss=0.02643, codebook_loss=18.26, over 1022412.92 frames.], batch size: 19, lr: 3.63e-04
+2022-05-27 23:56:54,287 INFO [train.py:823] (0/4) Epoch 47, batch 300, loss[loss=1.857, simple_loss=0.222, pruned_loss=0.02225, codebook_loss=17.24, over 7198.00 frames.], tot_loss[loss=1.966, simple_loss=0.2349, pruned_loss=0.026, codebook_loss=18.23, over 1111511.40 frames.], batch size: 18, lr: 3.63e-04
+2022-05-27 23:57:34,845 INFO [train.py:823] (0/4) Epoch 47, batch 350, loss[loss=1.934, simple_loss=0.2348, pruned_loss=0.0221, codebook_loss=17.94, over 7272.00 frames.], tot_loss[loss=1.968, simple_loss=0.235, pruned_loss=0.02626, codebook_loss=18.24, over 1179178.14 frames.], batch size: 20, lr: 3.62e-04
+2022-05-27 23:58:14,537 INFO [train.py:823] (0/4) Epoch 47, batch 400, loss[loss=1.932, simple_loss=0.2245, pruned_loss=0.02163, codebook_loss=17.98, over 7289.00 frames.], tot_loss[loss=1.965, simple_loss=0.2352, pruned_loss=0.02628, codebook_loss=18.21, over 1233121.41 frames.], batch size: 20, lr: 3.62e-04
+2022-05-27 23:58:54,524 INFO [train.py:823] (0/4) Epoch 47, batch 450, loss[loss=1.905, simple_loss=0.2104, pruned_loss=0.02294, codebook_loss=17.77, over 7154.00 frames.], tot_loss[loss=1.965, simple_loss=0.2354, pruned_loss=0.02658, codebook_loss=18.2, over 1273718.03 frames.], batch size: 17, lr: 3.62e-04
+2022-05-27 23:59:34,083 INFO [train.py:823] (0/4) Epoch 47, batch 500, loss[loss=1.976, simple_loss=0.2474, pruned_loss=0.02999, codebook_loss=18.22, over 7100.00 frames.], tot_loss[loss=1.969, simple_loss=0.2359, pruned_loss=0.02687, codebook_loss=18.24, over 1302667.36 frames.], batch size: 19, lr: 3.62e-04
+2022-05-28 00:00:14,248 INFO [train.py:823] (0/4) Epoch 47, batch 550, loss[loss=1.913, simple_loss=0.2319, pruned_loss=0.0237, codebook_loss=17.73, over 7390.00 frames.], tot_loss[loss=1.969, simple_loss=0.2351, pruned_loss=0.02695, codebook_loss=18.25, over 1328655.86 frames.], batch size: 19, lr: 3.62e-04
+2022-05-28 00:00:54,088 INFO [train.py:823] (0/4) Epoch 47, batch 600, loss[loss=1.903, simple_loss=0.2277, pruned_loss=0.02308, codebook_loss=17.66, over 6996.00 frames.], tot_loss[loss=1.971, simple_loss=0.2351, pruned_loss=0.02692, codebook_loss=18.27, over 1347842.55 frames.], batch size: 26, lr: 3.61e-04
+2022-05-28 00:01:34,136 INFO [train.py:823] (0/4) Epoch 47, batch 650, loss[loss=1.942, simple_loss=0.205, pruned_loss=0.02668, codebook_loss=18.13, over 7281.00 frames.], tot_loss[loss=1.968, simple_loss=0.2356, pruned_loss=0.02688, codebook_loss=18.23, over 1364788.15 frames.], batch size: 17, lr: 3.61e-04
+2022-05-28 00:02:14,075 INFO [train.py:823] (0/4) Epoch 47, batch 700, loss[loss=1.906, simple_loss=0.2579, pruned_loss=0.03177, codebook_loss=17.46, over 7322.00 frames.], tot_loss[loss=1.971, simple_loss=0.2353, pruned_loss=0.02687, codebook_loss=18.26, over 1372043.92 frames.], batch size: 23, lr: 3.61e-04
+2022-05-28 00:02:54,281 INFO [train.py:823] (0/4) Epoch 47, batch 750, loss[loss=1.903, simple_loss=0.2142, pruned_loss=0.01519, codebook_loss=17.81, over 7280.00 frames.], tot_loss[loss=1.969, simple_loss=0.2349, pruned_loss=0.02677, codebook_loss=18.25, over 1384108.75 frames.], batch size: 19, lr: 3.61e-04
+2022-05-28 00:03:34,013 INFO [train.py:823] (0/4) Epoch 47, batch 800, loss[loss=2.018, simple_loss=0.254, pruned_loss=0.03449, codebook_loss=18.57, over 7036.00 frames.], tot_loss[loss=1.972, simple_loss=0.2348, pruned_loss=0.02676, codebook_loss=18.28, over 1390691.27 frames.], batch size: 26, lr: 3.61e-04
+2022-05-28 00:04:13,983 INFO [train.py:823] (0/4) Epoch 47, batch 850, loss[loss=1.995, simple_loss=0.2287, pruned_loss=0.02138, codebook_loss=18.59, over 7193.00 frames.], tot_loss[loss=1.974, simple_loss=0.2351, pruned_loss=0.02699, codebook_loss=18.29, over 1392890.41 frames.], batch size: 18, lr: 3.60e-04
+2022-05-28 00:04:53,638 INFO [train.py:823] (0/4) Epoch 47, batch 900, loss[loss=1.942, simple_loss=0.2406, pruned_loss=0.02972, codebook_loss=17.92, over 7292.00 frames.], tot_loss[loss=1.971, simple_loss=0.2355, pruned_loss=0.027, codebook_loss=18.26, over 1398562.43 frames.], batch size: 22, lr: 3.60e-04
+2022-05-28 00:05:33,124 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-47.pt
+2022-05-28 00:05:47,401 INFO [train.py:823] (0/4) Epoch 48, batch 0, loss[loss=1.851, simple_loss=0.2438, pruned_loss=0.02186, codebook_loss=17.07, over 7195.00 frames.], tot_loss[loss=1.851, simple_loss=0.2438, pruned_loss=0.02186, codebook_loss=17.07, over 7195.00 frames.], batch size: 21, lr: 3.56e-04
+2022-05-28 00:06:27,207 INFO [train.py:823] (0/4) Epoch 48, batch 50, loss[loss=2.069, simple_loss=0.2299, pruned_loss=0.02272, codebook_loss=19.31, over 7159.00 frames.], tot_loss[loss=1.968, simple_loss=0.2341, pruned_loss=0.02666, codebook_loss=18.24, over 320173.00 frames.], batch size: 17, lr: 3.56e-04
+2022-05-28 00:07:07,663 INFO [train.py:823] (0/4) Epoch 48, batch 100, loss[loss=1.958, simple_loss=0.2433, pruned_loss=0.03185, codebook_loss=18.04, over 7196.00 frames.], tot_loss[loss=1.962, simple_loss=0.2332, pruned_loss=0.02675, codebook_loss=18.19, over 564495.67 frames.], batch size: 25, lr: 3.56e-04
+2022-05-28 00:07:49,903 INFO [train.py:823] (0/4) Epoch 48, batch 150, loss[loss=1.834, simple_loss=0.2169, pruned_loss=0.02206, codebook_loss=17.04, over 7305.00 frames.], tot_loss[loss=1.966, simple_loss=0.2352, pruned_loss=0.02674, codebook_loss=18.21, over 759341.20 frames.], batch size: 17, lr: 3.56e-04
+2022-05-28 00:08:31,450 INFO [train.py:823] (0/4) Epoch 48, batch 200, loss[loss=1.985, simple_loss=0.272, pruned_loss=0.03851, codebook_loss=18.1, over 7291.00 frames.], tot_loss[loss=1.968, simple_loss=0.2347, pruned_loss=0.0265, codebook_loss=18.24, over 907416.47 frames.], batch size: 22, lr: 3.55e-04
+2022-05-28 00:09:11,314 INFO [train.py:823] (0/4) Epoch 48, batch 250, loss[loss=1.968, simple_loss=0.2385, pruned_loss=0.02649, codebook_loss=18.23, over 7199.00 frames.], tot_loss[loss=1.965, simple_loss=0.2332, pruned_loss=0.02605, codebook_loss=18.22, over 1023620.85 frames.], batch size: 19, lr: 3.55e-04
+2022-05-28 00:09:51,434 INFO [train.py:823] (0/4) Epoch 48, batch 300, loss[loss=1.938, simple_loss=0.2422, pruned_loss=0.02553, codebook_loss=17.91, over 7019.00 frames.], tot_loss[loss=1.964, simple_loss=0.2332, pruned_loss=0.02632, codebook_loss=18.21, over 1115623.53 frames.], batch size: 26, lr: 3.55e-04
+2022-05-28 00:10:30,853 INFO [train.py:823] (0/4) Epoch 48, batch 350, loss[loss=2.004, simple_loss=0.2289, pruned_loss=0.03392, codebook_loss=18.56, over 4911.00 frames.], tot_loss[loss=1.971, simple_loss=0.2333, pruned_loss=0.02662, codebook_loss=18.28, over 1182163.82 frames.], batch size: 46, lr: 3.55e-04
+2022-05-28 00:11:11,333 INFO [train.py:823] (0/4) Epoch 48, batch 400, loss[loss=1.929, simple_loss=0.2484, pruned_loss=0.02529, codebook_loss=17.79, over 6644.00 frames.], tot_loss[loss=1.967, simple_loss=0.233, pruned_loss=0.02625, codebook_loss=18.25, over 1237222.39 frames.], batch size: 34, lr: 3.55e-04
+2022-05-28 00:11:50,921 INFO [train.py:823] (0/4) Epoch 48, batch 450, loss[loss=1.912, simple_loss=0.219, pruned_loss=0.02567, codebook_loss=17.77, over 7307.00 frames.], tot_loss[loss=1.967, simple_loss=0.2339, pruned_loss=0.02645, codebook_loss=18.24, over 1280069.58 frames.], batch size: 17, lr: 3.54e-04
+2022-05-28 00:12:31,151 INFO [train.py:823] (0/4) Epoch 48, batch 500, loss[loss=1.865, simple_loss=0.2261, pruned_loss=0.01313, codebook_loss=17.39, over 7198.00 frames.], tot_loss[loss=1.969, simple_loss=0.2353, pruned_loss=0.02671, codebook_loss=18.25, over 1310316.33 frames.], batch size: 20, lr: 3.54e-04
+2022-05-28 00:13:11,070 INFO [train.py:823] (0/4) Epoch 48, batch 550, loss[loss=1.963, simple_loss=0.2423, pruned_loss=0.02132, codebook_loss=18.2, over 7425.00 frames.], tot_loss[loss=1.969, simple_loss=0.2354, pruned_loss=0.02684, codebook_loss=18.24, over 1329993.25 frames.], batch size: 22, lr: 3.54e-04
+2022-05-28 00:13:52,282 INFO [train.py:823] (0/4) Epoch 48, batch 600, loss[loss=1.982, simple_loss=0.2521, pruned_loss=0.02779, codebook_loss=18.28, over 7283.00 frames.], tot_loss[loss=1.972, simple_loss=0.2364, pruned_loss=0.02704, codebook_loss=18.27, over 1349384.58 frames.], batch size: 20, lr: 3.54e-04
+2022-05-28 00:14:32,034 INFO [train.py:823] (0/4) Epoch 48, batch 650, loss[loss=1.924, simple_loss=0.2414, pruned_loss=0.02463, codebook_loss=17.79, over 7379.00 frames.], tot_loss[loss=1.971, simple_loss=0.2365, pruned_loss=0.02678, codebook_loss=18.26, over 1363512.20 frames.], batch size: 21, lr: 3.54e-04
+2022-05-28 00:15:11,901 INFO [train.py:823] (0/4) Epoch 48, batch 700, loss[loss=1.994, simple_loss=0.2602, pruned_loss=0.04281, codebook_loss=18.21, over 7166.00 frames.], tot_loss[loss=1.965, simple_loss=0.2365, pruned_loss=0.0267, codebook_loss=18.2, over 1370530.19 frames.], batch size: 22, lr: 3.53e-04
+2022-05-28 00:15:51,675 INFO [train.py:823] (0/4) Epoch 48, batch 750, loss[loss=1.929, simple_loss=0.2293, pruned_loss=0.02008, codebook_loss=17.95, over 7094.00 frames.], tot_loss[loss=1.966, simple_loss=0.2359, pruned_loss=0.02654, codebook_loss=18.21, over 1383833.58 frames.], batch size: 19, lr: 3.53e-04
+2022-05-28 00:16:31,781 INFO [train.py:823] (0/4) Epoch 48, batch 800, loss[loss=1.898, simple_loss=0.2514, pruned_loss=0.02452, codebook_loss=17.48, over 7328.00 frames.], tot_loss[loss=1.966, simple_loss=0.2351, pruned_loss=0.02613, codebook_loss=18.22, over 1391569.18 frames.], batch size: 23, lr: 3.53e-04
+2022-05-28 00:17:11,213 INFO [train.py:823] (0/4) Epoch 48, batch 850, loss[loss=1.879, simple_loss=0.2024, pruned_loss=0.01265, codebook_loss=17.66, over 7287.00 frames.], tot_loss[loss=1.971, simple_loss=0.2346, pruned_loss=0.02602, codebook_loss=18.28, over 1392636.42 frames.], batch size: 17, lr: 3.53e-04
+2022-05-28 00:17:51,120 INFO [train.py:823] (0/4) Epoch 48, batch 900, loss[loss=2.01, simple_loss=0.2454, pruned_loss=0.03796, codebook_loss=18.49, over 7310.00 frames.], tot_loss[loss=1.97, simple_loss=0.2348, pruned_loss=0.02605, codebook_loss=18.27, over 1394687.01 frames.], batch size: 19, lr: 3.53e-04
+2022-05-28 00:18:30,997 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-48.pt
+2022-05-28 00:18:41,959 INFO [train.py:823] (0/4) Epoch 49, batch 0, loss[loss=1.853, simple_loss=0.2154, pruned_loss=0.01593, codebook_loss=17.29, over 7371.00 frames.], tot_loss[loss=1.853, simple_loss=0.2154, pruned_loss=0.01593, codebook_loss=17.29, over 7371.00 frames.], batch size: 20, lr: 3.49e-04
+2022-05-28 00:19:21,912 INFO [train.py:823] (0/4) Epoch 49, batch 50, loss[loss=2.012, simple_loss=0.2503, pruned_loss=0.03972, codebook_loss=18.47, over 7281.00 frames.], tot_loss[loss=1.937, simple_loss=0.2335, pruned_loss=0.02445, codebook_loss=17.96, over 318102.18 frames.], batch size: 21, lr: 3.49e-04
+2022-05-28 00:20:01,475 INFO [train.py:823] (0/4) Epoch 49, batch 100, loss[loss=1.879, simple_loss=0.2201, pruned_loss=0.01877, codebook_loss=17.5, over 7194.00 frames.], tot_loss[loss=1.935, simple_loss=0.2343, pruned_loss=0.02445, codebook_loss=17.94, over 560277.15 frames.], batch size: 18, lr: 3.48e-04
+2022-05-28 00:20:41,938 INFO [train.py:823] (0/4) Epoch 49, batch 150, loss[loss=2.15, simple_loss=0.2631, pruned_loss=0.05514, codebook_loss=19.63, over 5186.00 frames.], tot_loss[loss=1.945, simple_loss=0.2334, pruned_loss=0.02524, codebook_loss=18.03, over 751106.87 frames.], batch size: 46, lr: 3.48e-04
+2022-05-28 00:21:21,720 INFO [train.py:823] (0/4) Epoch 49, batch 200, loss[loss=1.937, simple_loss=0.2381, pruned_loss=0.02369, codebook_loss=17.94, over 7160.00 frames.], tot_loss[loss=1.95, simple_loss=0.2336, pruned_loss=0.02521, codebook_loss=18.08, over 901609.76 frames.], batch size: 23, lr: 3.48e-04
+2022-05-28 00:22:01,855 INFO [train.py:823] (0/4) Epoch 49, batch 250, loss[loss=2.066, simple_loss=0.2686, pruned_loss=0.03517, codebook_loss=18.97, over 7187.00 frames.], tot_loss[loss=1.961, simple_loss=0.2352, pruned_loss=0.02602, codebook_loss=18.17, over 1021960.72 frames.], batch size: 20, lr: 3.48e-04
+2022-05-28 00:22:41,586 INFO [train.py:823] (0/4) Epoch 49, batch 300, loss[loss=1.922, simple_loss=0.2105, pruned_loss=0.02048, codebook_loss=17.96, over 7313.00 frames.], tot_loss[loss=1.964, simple_loss=0.2348, pruned_loss=0.02603, codebook_loss=18.21, over 1114446.61 frames.], batch size: 18, lr: 3.48e-04
+2022-05-28 00:23:21,739 INFO [train.py:823] (0/4) Epoch 49, batch 350, loss[loss=2.108, simple_loss=0.2475, pruned_loss=0.03119, codebook_loss=19.53, over 7189.00 frames.], tot_loss[loss=1.962, simple_loss=0.2345, pruned_loss=0.02584, codebook_loss=18.19, over 1177291.43 frames.], batch size: 25, lr: 3.48e-04
+2022-05-28 00:24:01,399 INFO [train.py:823] (0/4) Epoch 49, batch 400, loss[loss=2.073, simple_loss=0.2219, pruned_loss=0.02973, codebook_loss=19.32, over 7014.00 frames.], tot_loss[loss=1.972, simple_loss=0.2355, pruned_loss=0.0267, codebook_loss=18.28, over 1228015.69 frames.], batch size: 16, lr: 3.47e-04
+2022-05-28 00:24:41,455 INFO [train.py:823] (0/4) Epoch 49, batch 450, loss[loss=1.928, simple_loss=0.2414, pruned_loss=0.02726, codebook_loss=17.8, over 7249.00 frames.], tot_loss[loss=1.971, simple_loss=0.2351, pruned_loss=0.02665, codebook_loss=18.27, over 1273180.16 frames.], batch size: 24, lr: 3.47e-04
+2022-05-28 00:25:21,312 INFO [train.py:823] (0/4) Epoch 49, batch 500, loss[loss=2.008, simple_loss=0.2335, pruned_loss=0.02879, codebook_loss=18.62, over 6412.00 frames.], tot_loss[loss=1.967, simple_loss=0.2349, pruned_loss=0.02671, codebook_loss=18.23, over 1304634.03 frames.], batch size: 34, lr: 3.47e-04
+2022-05-28 00:26:01,617 INFO [train.py:823] (0/4) Epoch 49, batch 550, loss[loss=1.895, simple_loss=0.2248, pruned_loss=0.02398, codebook_loss=17.58, over 7315.00 frames.], tot_loss[loss=1.967, simple_loss=0.2335, pruned_loss=0.02649, codebook_loss=18.23, over 1331619.58 frames.], batch size: 17, lr: 3.47e-04
+2022-05-28 00:26:41,357 INFO [train.py:823] (0/4) Epoch 49, batch 600, loss[loss=1.932, simple_loss=0.2474, pruned_loss=0.02685, codebook_loss=17.82, over 7228.00 frames.], tot_loss[loss=1.97, simple_loss=0.2338, pruned_loss=0.02657, codebook_loss=18.27, over 1351105.31 frames.], batch size: 24, lr: 3.47e-04
+2022-05-28 00:27:21,538 INFO [train.py:823] (0/4) Epoch 49, batch 650, loss[loss=1.93, simple_loss=0.2095, pruned_loss=0.0299, codebook_loss=17.95, over 7160.00 frames.], tot_loss[loss=1.969, simple_loss=0.2336, pruned_loss=0.02641, codebook_loss=18.26, over 1366843.44 frames.], batch size: 17, lr: 3.46e-04
+2022-05-28 00:28:00,821 INFO [train.py:823] (0/4) Epoch 49, batch 700, loss[loss=1.978, simple_loss=0.2449, pruned_loss=0.02705, codebook_loss=18.28, over 7406.00 frames.], tot_loss[loss=1.978, simple_loss=0.2351, pruned_loss=0.02727, codebook_loss=18.33, over 1369828.60 frames.], batch size: 22, lr: 3.46e-04
+2022-05-28 00:28:40,795 INFO [train.py:823] (0/4) Epoch 49, batch 750, loss[loss=1.903, simple_loss=0.2278, pruned_loss=0.01659, codebook_loss=17.73, over 7288.00 frames.], tot_loss[loss=1.972, simple_loss=0.2354, pruned_loss=0.02678, codebook_loss=18.28, over 1381073.50 frames.], batch size: 19, lr: 3.46e-04
+2022-05-28 00:29:20,489 INFO [train.py:823] (0/4) Epoch 49, batch 800, loss[loss=1.905, simple_loss=0.212, pruned_loss=0.0191, codebook_loss=17.8, over 7157.00 frames.], tot_loss[loss=1.97, simple_loss=0.2355, pruned_loss=0.02672, codebook_loss=18.25, over 1384229.71 frames.], batch size: 17, lr: 3.46e-04
+2022-05-28 00:30:00,445 INFO [train.py:823] (0/4) Epoch 49, batch 850, loss[loss=1.917, simple_loss=0.2074, pruned_loss=0.02723, codebook_loss=17.86, over 7096.00 frames.], tot_loss[loss=1.967, simple_loss=0.2346, pruned_loss=0.02667, codebook_loss=18.23, over 1390722.24 frames.], batch size: 18, lr: 3.46e-04
+2022-05-28 00:30:40,052 INFO [train.py:823] (0/4) Epoch 49, batch 900, loss[loss=2.106, simple_loss=0.258, pruned_loss=0.0417, codebook_loss=19.35, over 6506.00 frames.], tot_loss[loss=1.971, simple_loss=0.2352, pruned_loss=0.02691, codebook_loss=18.27, over 1394224.16 frames.], batch size: 34, lr: 3.45e-04
+2022-05-28 00:31:20,592 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-49.pt
+2022-05-28 00:31:35,678 INFO [train.py:823] (0/4) Epoch 50, batch 0, loss[loss=1.983, simple_loss=0.2456, pruned_loss=0.0337, codebook_loss=18.27, over 6911.00 frames.], tot_loss[loss=1.983, simple_loss=0.2456, pruned_loss=0.0337, codebook_loss=18.27, over 6911.00 frames.], batch size: 29, lr: 3.42e-04
+2022-05-28 00:32:17,062 INFO [train.py:823] (0/4) Epoch 50, batch 50, loss[loss=2.041, simple_loss=0.2508, pruned_loss=0.03302, codebook_loss=18.82, over 7279.00 frames.], tot_loss[loss=1.963, simple_loss=0.23, pruned_loss=0.02476, codebook_loss=18.23, over 322045.65 frames.], batch size: 20, lr: 3.42e-04
+2022-05-28 00:32:59,749 INFO [train.py:823] (0/4) Epoch 50, batch 100, loss[loss=1.993, simple_loss=0.2501, pruned_loss=0.04263, codebook_loss=18.25, over 7148.00 frames.], tot_loss[loss=1.944, simple_loss=0.2306, pruned_loss=0.0246, codebook_loss=18.04, over 564000.75 frames.], batch size: 23, lr: 3.41e-04
+2022-05-28 00:33:39,328 INFO [train.py:823] (0/4) Epoch 50, batch 150, loss[loss=1.927, simple_loss=0.2415, pruned_loss=0.01782, codebook_loss=17.89, over 7383.00 frames.], tot_loss[loss=1.956, simple_loss=0.2331, pruned_loss=0.0253, codebook_loss=18.15, over 753075.97 frames.], batch size: 21, lr: 3.41e-04
+2022-05-28 00:34:19,388 INFO [train.py:823] (0/4) Epoch 50, batch 200, loss[loss=2.026, simple_loss=0.2117, pruned_loss=0.02035, codebook_loss=19, over 7099.00 frames.], tot_loss[loss=1.959, simple_loss=0.2335, pruned_loss=0.02537, codebook_loss=18.17, over 902266.19 frames.], batch size: 18, lr: 3.41e-04
+2022-05-28 00:34:59,310 INFO [train.py:823] (0/4) Epoch 50, batch 250, loss[loss=2.032, simple_loss=0.2504, pruned_loss=0.04546, codebook_loss=18.62, over 7157.00 frames.], tot_loss[loss=1.963, simple_loss=0.234, pruned_loss=0.02611, codebook_loss=18.2, over 1019600.62 frames.], batch size: 22, lr: 3.41e-04
+2022-05-28 00:35:39,376 INFO [train.py:823] (0/4) Epoch 50, batch 300, loss[loss=2.064, simple_loss=0.2549, pruned_loss=0.04741, codebook_loss=18.89, over 7201.00 frames.], tot_loss[loss=1.967, simple_loss=0.2347, pruned_loss=0.02641, codebook_loss=18.23, over 1109959.62 frames.], batch size: 20, lr: 3.41e-04
+2022-05-28 00:36:19,037 INFO [train.py:823] (0/4) Epoch 50, batch 350, loss[loss=2.55, simple_loss=0.2724, pruned_loss=0.04023, codebook_loss=23.73, over 7421.00 frames.], tot_loss[loss=1.963, simple_loss=0.2344, pruned_loss=0.02625, codebook_loss=18.19, over 1178242.87 frames.], batch size: 22, lr: 3.41e-04
+2022-05-28 00:36:59,296 INFO [train.py:823] (0/4) Epoch 50, batch 400, loss[loss=1.911, simple_loss=0.2444, pruned_loss=0.02879, codebook_loss=17.6, over 6992.00 frames.], tot_loss[loss=1.966, simple_loss=0.234, pruned_loss=0.02604, codebook_loss=18.23, over 1232439.76 frames.], batch size: 26, lr: 3.40e-04
+2022-05-28 00:37:40,216 INFO [train.py:823] (0/4) Epoch 50, batch 450, loss[loss=1.921, simple_loss=0.2297, pruned_loss=0.02352, codebook_loss=17.83, over 6375.00 frames.], tot_loss[loss=1.963, simple_loss=0.2341, pruned_loss=0.02592, codebook_loss=18.21, over 1272771.14 frames.], batch size: 34, lr: 3.40e-04
+2022-05-28 00:38:20,354 INFO [train.py:823] (0/4) Epoch 50, batch 500, loss[loss=1.895, simple_loss=0.2253, pruned_loss=0.02209, codebook_loss=17.6, over 7302.00 frames.], tot_loss[loss=1.966, simple_loss=0.2349, pruned_loss=0.02603, codebook_loss=18.23, over 1306073.45 frames.], batch size: 19, lr: 3.40e-04
+2022-05-28 00:39:00,413 INFO [train.py:823] (0/4) Epoch 50, batch 550, loss[loss=1.944, simple_loss=0.2436, pruned_loss=0.02919, codebook_loss=17.93, over 7227.00 frames.], tot_loss[loss=1.969, simple_loss=0.2352, pruned_loss=0.02651, codebook_loss=18.25, over 1334295.84 frames.], batch size: 24, lr: 3.40e-04
+2022-05-28 00:39:40,461 INFO [train.py:823] (0/4) Epoch 50, batch 600, loss[loss=2.009, simple_loss=0.2262, pruned_loss=0.03255, codebook_loss=18.64, over 6985.00 frames.], tot_loss[loss=1.967, simple_loss=0.2348, pruned_loss=0.02614, codebook_loss=18.24, over 1353157.84 frames.], batch size: 16, lr: 3.40e-04
+2022-05-28 00:40:20,092 INFO [train.py:823] (0/4) Epoch 50, batch 650, loss[loss=2.028, simple_loss=0.2275, pruned_loss=0.02635, codebook_loss=18.88, over 7444.00 frames.], tot_loss[loss=1.965, simple_loss=0.2356, pruned_loss=0.02615, codebook_loss=18.21, over 1364313.78 frames.], batch size: 17, lr: 3.39e-04
+2022-05-28 00:41:00,231 INFO [train.py:823] (0/4) Epoch 50, batch 700, loss[loss=1.972, simple_loss=0.2108, pruned_loss=0.02934, codebook_loss=18.38, over 7026.00 frames.], tot_loss[loss=1.964, simple_loss=0.2345, pruned_loss=0.02608, codebook_loss=18.2, over 1376534.20 frames.], batch size: 16, lr: 3.39e-04
+2022-05-28 00:41:39,952 INFO [train.py:823] (0/4) Epoch 50, batch 750, loss[loss=1.984, simple_loss=0.2442, pruned_loss=0.02809, codebook_loss=18.34, over 7313.00 frames.], tot_loss[loss=1.964, simple_loss=0.2352, pruned_loss=0.02625, codebook_loss=18.2, over 1383040.10 frames.], batch size: 22, lr: 3.39e-04
+2022-05-28 00:42:20,193 INFO [train.py:823] (0/4) Epoch 50, batch 800, loss[loss=1.923, simple_loss=0.2215, pruned_loss=0.01724, codebook_loss=17.95, over 7099.00 frames.], tot_loss[loss=1.963, simple_loss=0.234, pruned_loss=0.02627, codebook_loss=18.2, over 1390710.21 frames.], batch size: 19, lr: 3.39e-04
+2022-05-28 00:43:00,009 INFO [train.py:823] (0/4) Epoch 50, batch 850, loss[loss=1.914, simple_loss=0.2375, pruned_loss=0.02802, codebook_loss=17.67, over 4569.00 frames.], tot_loss[loss=1.97, simple_loss=0.2343, pruned_loss=0.02656, codebook_loss=18.26, over 1396382.68 frames.], batch size: 46, lr: 3.39e-04
+2022-05-28 00:43:39,821 INFO [train.py:823] (0/4) Epoch 50, batch 900, loss[loss=1.963, simple_loss=0.2547, pruned_loss=0.02881, codebook_loss=18.07, over 6435.00 frames.], tot_loss[loss=1.967, simple_loss=0.2346, pruned_loss=0.02639, codebook_loss=18.23, over 1398511.42 frames.], batch size: 34, lr: 3.39e-04
+2022-05-28 00:44:19,530 INFO [checkpoint.py:75] (0/4) Saving checkpoint to pruned_transducer_stateless6/exp/epoch-50.pt
+2022-05-28 00:44:22,560 INFO [train.py:1038] (0/4) Done!