diff --git "a/exp/log/log-train-2022-05-13-19-15-59-0" "b/exp/log/log-train-2022-05-13-19-15-59-0"
new file mode 100644--- /dev/null
+++ "b/exp/log/log-train-2022-05-13-19-15-59-0"
@@ -0,0 +1,3869 @@
+2022-05-13 19:15:59,512 INFO [train.py:876] (0/8) Training started
+2022-05-13 19:15:59,516 INFO [train.py:886] (0/8) Device: cuda:0
+2022-05-13 19:15:59,519 INFO [train.py:895] (0/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.1.0.dev+missing.version.file', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'deeper-conformer-without-random-combiner', 'icefall-git-sha1': '7b786ce-dirty', 'icefall-git-date': 'Fri May 13 18:53:22 2022', 'icefall-path': '/ceph-fj/fangjun/open-source-2/icefall-deeper-conformer-2', 'k2-path': '/ceph-fj/fangjun/open-source-2/k2-multi-22/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-fj/fangjun/open-source-2/lhotse-multi-3/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-6-0415002726-7dc5bf9fdc-w24k9', 'IP address': '10.177.28.71'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 1, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp-L'), '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, 'seed': 42, 'print_diagnostics': False, 'save_every_n': 4000, 'keep_last_k': 30, 'average_period': 100, 'use_fp16': False, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'full_libri': True, 'manifest_dir': PosixPath('data/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, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'blank_id': 0, 'vocab_size': 500}
+2022-05-13 19:15:59,520 INFO [train.py:897] (0/8) About to create model
+2022-05-13 19:16:00,249 INFO [train.py:901] (0/8) Number of model parameters: 116553580
+2022-05-13 19:16:07,895 INFO [train.py:916] (0/8) Using DDP
+2022-05-13 19:16:09,395 INFO [asr_datamodule.py:391] (0/8) About to get train-clean-100 cuts
+2022-05-13 19:16:18,446 INFO [asr_datamodule.py:398] (0/8) About to get train-clean-360 cuts
+2022-05-13 19:16:54,671 INFO [asr_datamodule.py:405] (0/8) About to get train-other-500 cuts
+2022-05-13 19:17:55,570 INFO [asr_datamodule.py:209] (0/8) Enable MUSAN
+2022-05-13 19:17:55,570 INFO [asr_datamodule.py:210] (0/8) About to get Musan cuts
+2022-05-13 19:17:57,746 INFO [asr_datamodule.py:238] (0/8) Enable SpecAugment
+2022-05-13 19:17:57,746 INFO [asr_datamodule.py:239] (0/8) Time warp factor: 80
+2022-05-13 19:17:57,746 INFO [asr_datamodule.py:251] (0/8) Num frame mask: 10
+2022-05-13 19:17:57,746 INFO [asr_datamodule.py:264] (0/8) About to create train dataset
+2022-05-13 19:17:57,747 INFO [asr_datamodule.py:292] (0/8) Using BucketingSampler.
+2022-05-13 19:18:04,093 INFO [asr_datamodule.py:308] (0/8) About to create train dataloader
+2022-05-13 19:18:04,094 INFO [asr_datamodule.py:412] (0/8) About to get dev-clean cuts
+2022-05-13 19:18:04,440 INFO [asr_datamodule.py:417] (0/8) About to get dev-other cuts
+2022-05-13 19:18:04,642 INFO [asr_datamodule.py:339] (0/8) About to create dev dataset
+2022-05-13 19:18:04,654 INFO [asr_datamodule.py:358] (0/8) About to create dev dataloader
+2022-05-13 19:18:04,654 INFO [train.py:1078] (0/8) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
+2022-05-13 19:18:18,393 INFO [distributed.py:874] (0/8) Reducer buckets have been rebuilt in this iteration.
+2022-05-13 19:18:41,995 INFO [train.py:812] (0/8) Epoch 1, batch 0, loss[loss=0.7812, simple_loss=1.562, pruned_loss=6.677, over 7290.00 frames.], tot_loss[loss=0.7812, simple_loss=1.562, pruned_loss=6.677, over 7290.00 frames.], batch size: 17, lr: 3.00e-03
+2022-05-13 19:19:41,274 INFO [train.py:812] (0/8) Epoch 1, batch 50, loss[loss=0.5018, simple_loss=1.004, pruned_loss=7.101, over 7154.00 frames.], tot_loss[loss=0.5518, simple_loss=1.104, pruned_loss=7.103, over 324226.35 frames.], batch size: 19, lr: 3.00e-03
+2022-05-13 19:20:39,817 INFO [train.py:812] (0/8) Epoch 1, batch 100, loss[loss=0.3693, simple_loss=0.7385, pruned_loss=6.522, over 6992.00 frames.], tot_loss[loss=0.4935, simple_loss=0.9871, pruned_loss=6.961, over 566699.90 frames.], batch size: 16, lr: 3.00e-03
+2022-05-13 19:21:38,651 INFO [train.py:812] (0/8) Epoch 1, batch 150, loss[loss=0.3827, simple_loss=0.7654, pruned_loss=6.762, over 6996.00 frames.], tot_loss[loss=0.4641, simple_loss=0.9282, pruned_loss=6.876, over 757952.98 frames.], batch size: 16, lr: 3.00e-03
+2022-05-13 19:22:36,955 INFO [train.py:812] (0/8) Epoch 1, batch 200, loss[loss=0.4263, simple_loss=0.8525, pruned_loss=6.785, over 7316.00 frames.], tot_loss[loss=0.4436, simple_loss=0.8872, pruned_loss=6.842, over 908488.44 frames.], batch size: 25, lr: 3.00e-03
+2022-05-13 19:23:35,677 INFO [train.py:812] (0/8) Epoch 1, batch 250, loss[loss=0.384, simple_loss=0.768, pruned_loss=6.842, over 7333.00 frames.], tot_loss[loss=0.431, simple_loss=0.862, pruned_loss=6.839, over 1016999.81 frames.], batch size: 21, lr: 3.00e-03
+2022-05-13 19:24:34,034 INFO [train.py:812] (0/8) Epoch 1, batch 300, loss[loss=0.3988, simple_loss=0.7977, pruned_loss=6.912, over 7291.00 frames.], tot_loss[loss=0.4204, simple_loss=0.8408, pruned_loss=6.833, over 1108811.87 frames.], batch size: 25, lr: 3.00e-03
+2022-05-13 19:25:33,444 INFO [train.py:812] (0/8) Epoch 1, batch 350, loss[loss=0.4098, simple_loss=0.8196, pruned_loss=6.87, over 7255.00 frames.], tot_loss[loss=0.4115, simple_loss=0.823, pruned_loss=6.824, over 1178668.25 frames.], batch size: 19, lr: 3.00e-03
+2022-05-13 19:26:31,637 INFO [train.py:812] (0/8) Epoch 1, batch 400, loss[loss=0.3999, simple_loss=0.7998, pruned_loss=6.924, over 7409.00 frames.], tot_loss[loss=0.4031, simple_loss=0.8062, pruned_loss=6.806, over 1231926.34 frames.], batch size: 21, lr: 3.00e-03
+2022-05-13 19:27:30,035 INFO [train.py:812] (0/8) Epoch 1, batch 450, loss[loss=0.3628, simple_loss=0.7256, pruned_loss=6.833, over 7408.00 frames.], tot_loss[loss=0.3939, simple_loss=0.7878, pruned_loss=6.791, over 1268151.27 frames.], batch size: 21, lr: 2.99e-03
+2022-05-13 19:28:29,388 INFO [train.py:812] (0/8) Epoch 1, batch 500, loss[loss=0.3118, simple_loss=0.6235, pruned_loss=6.694, over 7204.00 frames.], tot_loss[loss=0.3787, simple_loss=0.7575, pruned_loss=6.777, over 1304139.11 frames.], batch size: 22, lr: 2.99e-03
+2022-05-13 19:29:27,217 INFO [train.py:812] (0/8) Epoch 1, batch 550, loss[loss=0.2915, simple_loss=0.583, pruned_loss=6.77, over 7340.00 frames.], tot_loss[loss=0.3643, simple_loss=0.7285, pruned_loss=6.771, over 1329852.13 frames.], batch size: 22, lr: 2.99e-03
+2022-05-13 19:30:26,694 INFO [train.py:812] (0/8) Epoch 1, batch 600, loss[loss=0.2815, simple_loss=0.5631, pruned_loss=6.709, over 7111.00 frames.], tot_loss[loss=0.3476, simple_loss=0.6951, pruned_loss=6.763, over 1349991.24 frames.], batch size: 21, lr: 2.99e-03
+2022-05-13 19:31:24,363 INFO [train.py:812] (0/8) Epoch 1, batch 650, loss[loss=0.2369, simple_loss=0.4739, pruned_loss=6.586, over 6990.00 frames.], tot_loss[loss=0.3315, simple_loss=0.663, pruned_loss=6.756, over 1368558.64 frames.], batch size: 16, lr: 2.99e-03
+2022-05-13 19:32:22,796 INFO [train.py:812] (0/8) Epoch 1, batch 700, loss[loss=0.2761, simple_loss=0.5523, pruned_loss=6.876, over 7205.00 frames.], tot_loss[loss=0.3163, simple_loss=0.6326, pruned_loss=6.747, over 1380389.26 frames.], batch size: 23, lr: 2.99e-03
+2022-05-13 19:33:21,789 INFO [train.py:812] (0/8) Epoch 1, batch 750, loss[loss=0.2196, simple_loss=0.4391, pruned_loss=6.509, over 7286.00 frames.], tot_loss[loss=0.3017, simple_loss=0.6035, pruned_loss=6.736, over 1392227.11 frames.], batch size: 17, lr: 2.98e-03
+2022-05-13 19:34:19,621 INFO [train.py:812] (0/8) Epoch 1, batch 800, loss[loss=0.2549, simple_loss=0.5098, pruned_loss=6.652, over 7119.00 frames.], tot_loss[loss=0.2902, simple_loss=0.5804, pruned_loss=6.732, over 1397492.92 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:35:17,948 INFO [train.py:812] (0/8) Epoch 1, batch 850, loss[loss=0.2721, simple_loss=0.5443, pruned_loss=6.841, over 7221.00 frames.], tot_loss[loss=0.2803, simple_loss=0.5605, pruned_loss=6.733, over 1402951.77 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:36:17,473 INFO [train.py:812] (0/8) Epoch 1, batch 900, loss[loss=0.2454, simple_loss=0.4908, pruned_loss=6.82, over 7304.00 frames.], tot_loss[loss=0.27, simple_loss=0.5401, pruned_loss=6.73, over 1407271.55 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:37:15,523 INFO [train.py:812] (0/8) Epoch 1, batch 950, loss[loss=0.2186, simple_loss=0.4373, pruned_loss=6.611, over 6962.00 frames.], tot_loss[loss=0.2632, simple_loss=0.5263, pruned_loss=6.735, over 1403944.86 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:38:15,212 INFO [train.py:812] (0/8) Epoch 1, batch 1000, loss[loss=0.1981, simple_loss=0.3961, pruned_loss=6.552, over 6998.00 frames.], tot_loss[loss=0.2567, simple_loss=0.5133, pruned_loss=6.737, over 1404219.51 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:39:14,152 INFO [train.py:812] (0/8) Epoch 1, batch 1050, loss[loss=0.1853, simple_loss=0.3706, pruned_loss=6.569, over 7001.00 frames.], tot_loss[loss=0.251, simple_loss=0.502, pruned_loss=6.746, over 1406064.05 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:40:12,436 INFO [train.py:812] (0/8) Epoch 1, batch 1100, loss[loss=0.2171, simple_loss=0.4342, pruned_loss=6.797, over 7208.00 frames.], tot_loss[loss=0.2455, simple_loss=0.491, pruned_loss=6.751, over 1410469.51 frames.], batch size: 22, lr: 2.96e-03
+2022-05-13 19:41:10,436 INFO [train.py:812] (0/8) Epoch 1, batch 1150, loss[loss=0.2504, simple_loss=0.5007, pruned_loss=6.919, over 6748.00 frames.], tot_loss[loss=0.2396, simple_loss=0.4792, pruned_loss=6.751, over 1412731.36 frames.], batch size: 31, lr: 2.96e-03
+2022-05-13 19:42:08,522 INFO [train.py:812] (0/8) Epoch 1, batch 1200, loss[loss=0.2386, simple_loss=0.4773, pruned_loss=6.898, over 7179.00 frames.], tot_loss[loss=0.2349, simple_loss=0.4699, pruned_loss=6.756, over 1420372.99 frames.], batch size: 26, lr: 2.96e-03
+2022-05-13 19:43:07,165 INFO [train.py:812] (0/8) Epoch 1, batch 1250, loss[loss=0.2196, simple_loss=0.4391, pruned_loss=6.74, over 7376.00 frames.], tot_loss[loss=0.2315, simple_loss=0.463, pruned_loss=6.758, over 1414033.16 frames.], batch size: 23, lr: 2.95e-03
+2022-05-13 19:44:06,123 INFO [train.py:812] (0/8) Epoch 1, batch 1300, loss[loss=0.217, simple_loss=0.434, pruned_loss=6.887, over 7294.00 frames.], tot_loss[loss=0.2278, simple_loss=0.4555, pruned_loss=6.761, over 1421353.02 frames.], batch size: 24, lr: 2.95e-03
+2022-05-13 19:45:04,271 INFO [train.py:812] (0/8) Epoch 1, batch 1350, loss[loss=0.2219, simple_loss=0.4437, pruned_loss=6.777, over 7146.00 frames.], tot_loss[loss=0.2233, simple_loss=0.4466, pruned_loss=6.757, over 1422868.22 frames.], batch size: 20, lr: 2.95e-03
+2022-05-13 19:46:03,475 INFO [train.py:812] (0/8) Epoch 1, batch 1400, loss[loss=0.2085, simple_loss=0.4169, pruned_loss=6.807, over 7286.00 frames.], tot_loss[loss=0.2213, simple_loss=0.4425, pruned_loss=6.763, over 1418745.68 frames.], batch size: 24, lr: 2.94e-03
+2022-05-13 19:47:02,121 INFO [train.py:812] (0/8) Epoch 1, batch 1450, loss[loss=0.1797, simple_loss=0.3594, pruned_loss=6.712, over 7132.00 frames.], tot_loss[loss=0.2182, simple_loss=0.4363, pruned_loss=6.763, over 1419529.47 frames.], batch size: 17, lr: 2.94e-03
+2022-05-13 19:48:00,924 INFO [train.py:812] (0/8) Epoch 1, batch 1500, loss[loss=0.1975, simple_loss=0.395, pruned_loss=6.781, over 7270.00 frames.], tot_loss[loss=0.2159, simple_loss=0.4318, pruned_loss=6.763, over 1423078.74 frames.], batch size: 24, lr: 2.94e-03
+2022-05-13 19:48:59,488 INFO [train.py:812] (0/8) Epoch 1, batch 1550, loss[loss=0.1951, simple_loss=0.3902, pruned_loss=6.737, over 7117.00 frames.], tot_loss[loss=0.2131, simple_loss=0.4261, pruned_loss=6.761, over 1423255.85 frames.], batch size: 21, lr: 2.93e-03
+2022-05-13 19:49:59,137 INFO [train.py:812] (0/8) Epoch 1, batch 1600, loss[loss=0.1998, simple_loss=0.3996, pruned_loss=6.719, over 7319.00 frames.], tot_loss[loss=0.2102, simple_loss=0.4205, pruned_loss=6.756, over 1420576.14 frames.], batch size: 20, lr: 2.93e-03
+2022-05-13 19:50:59,012 INFO [train.py:812] (0/8) Epoch 1, batch 1650, loss[loss=0.1778, simple_loss=0.3555, pruned_loss=6.591, over 7156.00 frames.], tot_loss[loss=0.2081, simple_loss=0.4162, pruned_loss=6.753, over 1422457.41 frames.], batch size: 18, lr: 2.92e-03
+2022-05-13 19:51:59,056 INFO [train.py:812] (0/8) Epoch 1, batch 1700, loss[loss=0.2203, simple_loss=0.4406, pruned_loss=6.838, over 6419.00 frames.], tot_loss[loss=0.207, simple_loss=0.414, pruned_loss=6.76, over 1416495.48 frames.], batch size: 37, lr: 2.92e-03
+2022-05-13 19:52:58,920 INFO [train.py:812] (0/8) Epoch 1, batch 1750, loss[loss=0.2137, simple_loss=0.4274, pruned_loss=6.798, over 6560.00 frames.], tot_loss[loss=0.2043, simple_loss=0.4087, pruned_loss=6.757, over 1417000.61 frames.], batch size: 38, lr: 2.91e-03
+2022-05-13 19:54:00,188 INFO [train.py:812] (0/8) Epoch 1, batch 1800, loss[loss=0.2045, simple_loss=0.409, pruned_loss=6.811, over 7018.00 frames.], tot_loss[loss=0.2038, simple_loss=0.4076, pruned_loss=6.762, over 1417420.93 frames.], batch size: 28, lr: 2.91e-03
+2022-05-13 19:54:58,675 INFO [train.py:812] (0/8) Epoch 1, batch 1850, loss[loss=0.2008, simple_loss=0.4016, pruned_loss=6.737, over 5097.00 frames.], tot_loss[loss=0.2016, simple_loss=0.4031, pruned_loss=6.761, over 1417902.09 frames.], batch size: 52, lr: 2.91e-03
+2022-05-13 19:55:56,996 INFO [train.py:812] (0/8) Epoch 1, batch 1900, loss[loss=0.1738, simple_loss=0.3477, pruned_loss=6.735, over 7262.00 frames.], tot_loss[loss=0.2005, simple_loss=0.401, pruned_loss=6.762, over 1419689.33 frames.], batch size: 19, lr: 2.90e-03
+2022-05-13 19:56:55,445 INFO [train.py:812] (0/8) Epoch 1, batch 1950, loss[loss=0.1961, simple_loss=0.3923, pruned_loss=6.77, over 7330.00 frames.], tot_loss[loss=0.199, simple_loss=0.398, pruned_loss=6.762, over 1421898.91 frames.], batch size: 21, lr: 2.90e-03
+2022-05-13 19:57:54,266 INFO [train.py:812] (0/8) Epoch 1, batch 2000, loss[loss=0.1807, simple_loss=0.3614, pruned_loss=6.684, over 6779.00 frames.], tot_loss[loss=0.1974, simple_loss=0.3949, pruned_loss=6.761, over 1422753.03 frames.], batch size: 15, lr: 2.89e-03
+2022-05-13 19:58:53,055 INFO [train.py:812] (0/8) Epoch 1, batch 2050, loss[loss=0.2019, simple_loss=0.4037, pruned_loss=6.912, over 7220.00 frames.], tot_loss[loss=0.1961, simple_loss=0.3922, pruned_loss=6.762, over 1420794.33 frames.], batch size: 26, lr: 2.89e-03
+2022-05-13 19:59:51,481 INFO [train.py:812] (0/8) Epoch 1, batch 2100, loss[loss=0.171, simple_loss=0.342, pruned_loss=6.655, over 7165.00 frames.], tot_loss[loss=0.1955, simple_loss=0.3909, pruned_loss=6.761, over 1418406.34 frames.], batch size: 18, lr: 2.88e-03
+2022-05-13 20:00:49,528 INFO [train.py:812] (0/8) Epoch 1, batch 2150, loss[loss=0.1917, simple_loss=0.3834, pruned_loss=6.78, over 7343.00 frames.], tot_loss[loss=0.1934, simple_loss=0.3869, pruned_loss=6.757, over 1421402.40 frames.], batch size: 22, lr: 2.88e-03
+2022-05-13 20:01:48,631 INFO [train.py:812] (0/8) Epoch 1, batch 2200, loss[loss=0.1926, simple_loss=0.3852, pruned_loss=6.735, over 7287.00 frames.], tot_loss[loss=0.1929, simple_loss=0.3857, pruned_loss=6.757, over 1421184.50 frames.], batch size: 25, lr: 2.87e-03
+2022-05-13 20:02:47,471 INFO [train.py:812] (0/8) Epoch 1, batch 2250, loss[loss=0.1783, simple_loss=0.3565, pruned_loss=6.813, over 7229.00 frames.], tot_loss[loss=0.1918, simple_loss=0.3836, pruned_loss=6.752, over 1419686.93 frames.], batch size: 21, lr: 2.86e-03
+2022-05-13 20:03:45,868 INFO [train.py:812] (0/8) Epoch 1, batch 2300, loss[loss=0.1697, simple_loss=0.3394, pruned_loss=6.689, over 7259.00 frames.], tot_loss[loss=0.1909, simple_loss=0.3819, pruned_loss=6.749, over 1413953.57 frames.], batch size: 19, lr: 2.86e-03
+2022-05-13 20:04:43,218 INFO [train.py:812] (0/8) Epoch 1, batch 2350, loss[loss=0.2363, simple_loss=0.4726, pruned_loss=6.869, over 5026.00 frames.], tot_loss[loss=0.1906, simple_loss=0.3811, pruned_loss=6.755, over 1414196.41 frames.], batch size: 52, lr: 2.85e-03
+2022-05-13 20:05:42,847 INFO [train.py:812] (0/8) Epoch 1, batch 2400, loss[loss=0.1811, simple_loss=0.3621, pruned_loss=6.784, over 7428.00 frames.], tot_loss[loss=0.19, simple_loss=0.38, pruned_loss=6.757, over 1410121.97 frames.], batch size: 20, lr: 2.85e-03
+2022-05-13 20:06:41,413 INFO [train.py:812] (0/8) Epoch 1, batch 2450, loss[loss=0.223, simple_loss=0.4459, pruned_loss=6.838, over 5196.00 frames.], tot_loss[loss=0.1887, simple_loss=0.3775, pruned_loss=6.758, over 1411170.63 frames.], batch size: 53, lr: 2.84e-03
+2022-05-13 20:07:40,731 INFO [train.py:812] (0/8) Epoch 1, batch 2500, loss[loss=0.1868, simple_loss=0.3736, pruned_loss=6.8, over 7335.00 frames.], tot_loss[loss=0.1874, simple_loss=0.3747, pruned_loss=6.75, over 1417536.80 frames.], batch size: 20, lr: 2.84e-03
+2022-05-13 20:08:39,340 INFO [train.py:812] (0/8) Epoch 1, batch 2550, loss[loss=0.1645, simple_loss=0.329, pruned_loss=6.678, over 7419.00 frames.], tot_loss[loss=0.1876, simple_loss=0.3751, pruned_loss=6.749, over 1417949.07 frames.], batch size: 18, lr: 2.83e-03
+2022-05-13 20:09:37,899 INFO [train.py:812] (0/8) Epoch 1, batch 2600, loss[loss=0.191, simple_loss=0.382, pruned_loss=6.776, over 7225.00 frames.], tot_loss[loss=0.1865, simple_loss=0.3729, pruned_loss=6.742, over 1420716.07 frames.], batch size: 20, lr: 2.83e-03
+2022-05-13 20:10:35,871 INFO [train.py:812] (0/8) Epoch 1, batch 2650, loss[loss=0.1821, simple_loss=0.3643, pruned_loss=6.706, over 7223.00 frames.], tot_loss[loss=0.1851, simple_loss=0.3702, pruned_loss=6.742, over 1421770.42 frames.], batch size: 20, lr: 2.82e-03
+2022-05-13 20:11:35,625 INFO [train.py:812] (0/8) Epoch 1, batch 2700, loss[loss=0.1881, simple_loss=0.3763, pruned_loss=6.746, over 7142.00 frames.], tot_loss[loss=0.1852, simple_loss=0.3703, pruned_loss=6.745, over 1421216.53 frames.], batch size: 20, lr: 2.81e-03
+2022-05-13 20:12:32,558 INFO [train.py:812] (0/8) Epoch 1, batch 2750, loss[loss=0.1999, simple_loss=0.3999, pruned_loss=6.832, over 7322.00 frames.], tot_loss[loss=0.1845, simple_loss=0.369, pruned_loss=6.747, over 1421954.98 frames.], batch size: 20, lr: 2.81e-03
+2022-05-13 20:13:32,044 INFO [train.py:812] (0/8) Epoch 1, batch 2800, loss[loss=0.18, simple_loss=0.3601, pruned_loss=6.824, over 7151.00 frames.], tot_loss[loss=0.184, simple_loss=0.3681, pruned_loss=6.743, over 1421280.91 frames.], batch size: 20, lr: 2.80e-03
+2022-05-13 20:14:31,042 INFO [train.py:812] (0/8) Epoch 1, batch 2850, loss[loss=0.181, simple_loss=0.3619, pruned_loss=6.657, over 7348.00 frames.], tot_loss[loss=0.1832, simple_loss=0.3665, pruned_loss=6.74, over 1424701.26 frames.], batch size: 19, lr: 2.80e-03
+2022-05-13 20:15:28,495 INFO [train.py:812] (0/8) Epoch 1, batch 2900, loss[loss=0.1941, simple_loss=0.3882, pruned_loss=6.712, over 7331.00 frames.], tot_loss[loss=0.1839, simple_loss=0.3678, pruned_loss=6.741, over 1420572.24 frames.], batch size: 20, lr: 2.79e-03
+2022-05-13 20:16:27,644 INFO [train.py:812] (0/8) Epoch 1, batch 2950, loss[loss=0.1914, simple_loss=0.3829, pruned_loss=6.801, over 7107.00 frames.], tot_loss[loss=0.1832, simple_loss=0.3664, pruned_loss=6.741, over 1417015.68 frames.], batch size: 26, lr: 2.78e-03
+2022-05-13 20:17:26,742 INFO [train.py:812] (0/8) Epoch 1, batch 3000, loss[loss=0.3133, simple_loss=0.3297, pruned_loss=1.485, over 7290.00 frames.], tot_loss[loss=0.2159, simple_loss=0.365, pruned_loss=6.715, over 1421439.69 frames.], batch size: 17, lr: 2.78e-03
+2022-05-13 20:17:26,743 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-13 20:17:34,928 INFO [train.py:841] (0/8) Epoch 1, validation: loss=2.094, simple_loss=0.4148, pruned_loss=1.887, over 698248.00 frames.
+2022-05-13 20:18:33,866 INFO [train.py:812] (0/8) Epoch 1, batch 3050, loss[loss=0.3094, simple_loss=0.4099, pruned_loss=1.045, over 6288.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3728, pruned_loss=5.505, over 1420041.50 frames.], batch size: 37, lr: 2.77e-03
+2022-05-13 20:19:33,996 INFO [train.py:812] (0/8) Epoch 1, batch 3100, loss[loss=0.2293, simple_loss=0.3484, pruned_loss=0.5509, over 7415.00 frames.], tot_loss[loss=0.2421, simple_loss=0.369, pruned_loss=4.428, over 1425959.27 frames.], batch size: 21, lr: 2.77e-03
+2022-05-13 20:20:32,559 INFO [train.py:812] (0/8) Epoch 1, batch 3150, loss[loss=0.2386, simple_loss=0.3961, pruned_loss=0.4055, over 7418.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3672, pruned_loss=3.542, over 1426877.58 frames.], batch size: 21, lr: 2.76e-03
+2022-05-13 20:21:30,628 INFO [train.py:812] (0/8) Epoch 1, batch 3200, loss[loss=0.2278, simple_loss=0.3933, pruned_loss=0.3108, over 7299.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3657, pruned_loss=2.832, over 1422699.73 frames.], batch size: 24, lr: 2.75e-03
+2022-05-13 20:22:29,480 INFO [train.py:812] (0/8) Epoch 1, batch 3250, loss[loss=0.1918, simple_loss=0.3448, pruned_loss=0.1945, over 7144.00 frames.], tot_loss[loss=0.226, simple_loss=0.364, pruned_loss=2.261, over 1422688.52 frames.], batch size: 20, lr: 2.75e-03
+2022-05-13 20:23:28,332 INFO [train.py:812] (0/8) Epoch 1, batch 3300, loss[loss=0.1929, simple_loss=0.3458, pruned_loss=0.2, over 7379.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3623, pruned_loss=1.814, over 1418034.22 frames.], batch size: 23, lr: 2.74e-03
+2022-05-13 20:24:25,732 INFO [train.py:812] (0/8) Epoch 1, batch 3350, loss[loss=0.2149, simple_loss=0.3869, pruned_loss=0.2147, over 7290.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3606, pruned_loss=1.453, over 1422980.14 frames.], batch size: 24, lr: 2.73e-03
+2022-05-13 20:25:24,298 INFO [train.py:812] (0/8) Epoch 1, batch 3400, loss[loss=0.1919, simple_loss=0.3468, pruned_loss=0.1851, over 7258.00 frames.], tot_loss[loss=0.2119, simple_loss=0.3604, pruned_loss=1.175, over 1423439.90 frames.], batch size: 19, lr: 2.73e-03
+2022-05-13 20:26:22,143 INFO [train.py:812] (0/8) Epoch 1, batch 3450, loss[loss=0.1974, simple_loss=0.3587, pruned_loss=0.1802, over 7273.00 frames.], tot_loss[loss=0.209, simple_loss=0.3601, pruned_loss=0.9572, over 1422585.42 frames.], batch size: 25, lr: 2.72e-03
+2022-05-13 20:27:20,154 INFO [train.py:812] (0/8) Epoch 1, batch 3500, loss[loss=0.1953, simple_loss=0.3575, pruned_loss=0.1661, over 7173.00 frames.], tot_loss[loss=0.2052, simple_loss=0.3577, pruned_loss=0.7841, over 1420848.78 frames.], batch size: 26, lr: 2.72e-03
+2022-05-13 20:28:19,218 INFO [train.py:812] (0/8) Epoch 1, batch 3550, loss[loss=0.1963, simple_loss=0.3609, pruned_loss=0.1584, over 7216.00 frames.], tot_loss[loss=0.2018, simple_loss=0.355, pruned_loss=0.6478, over 1422438.97 frames.], batch size: 21, lr: 2.71e-03
+2022-05-13 20:29:18,164 INFO [train.py:812] (0/8) Epoch 1, batch 3600, loss[loss=0.1728, simple_loss=0.3164, pruned_loss=0.1459, over 7008.00 frames.], tot_loss[loss=0.1997, simple_loss=0.3539, pruned_loss=0.5427, over 1421168.15 frames.], batch size: 16, lr: 2.70e-03
+2022-05-13 20:30:25,533 INFO [train.py:812] (0/8) Epoch 1, batch 3650, loss[loss=0.1927, simple_loss=0.3549, pruned_loss=0.1524, over 7219.00 frames.], tot_loss[loss=0.1978, simple_loss=0.3528, pruned_loss=0.4592, over 1421704.12 frames.], batch size: 21, lr: 2.70e-03
+2022-05-13 20:32:10,015 INFO [train.py:812] (0/8) Epoch 1, batch 3700, loss[loss=0.1881, simple_loss=0.3447, pruned_loss=0.1578, over 6645.00 frames.], tot_loss[loss=0.1961, simple_loss=0.3516, pruned_loss=0.3929, over 1426308.93 frames.], batch size: 31, lr: 2.69e-03
+2022-05-13 20:33:27,100 INFO [train.py:812] (0/8) Epoch 1, batch 3750, loss[loss=0.1891, simple_loss=0.3441, pruned_loss=0.1707, over 7285.00 frames.], tot_loss[loss=0.1937, simple_loss=0.349, pruned_loss=0.341, over 1418925.19 frames.], batch size: 18, lr: 2.68e-03
+2022-05-13 20:34:26,722 INFO [train.py:812] (0/8) Epoch 1, batch 3800, loss[loss=0.1613, simple_loss=0.2979, pruned_loss=0.124, over 7126.00 frames.], tot_loss[loss=0.1929, simple_loss=0.3489, pruned_loss=0.301, over 1418792.80 frames.], batch size: 17, lr: 2.68e-03
+2022-05-13 20:35:25,755 INFO [train.py:812] (0/8) Epoch 1, batch 3850, loss[loss=0.1558, simple_loss=0.2908, pruned_loss=0.104, over 7157.00 frames.], tot_loss[loss=0.1917, simple_loss=0.348, pruned_loss=0.2673, over 1423726.89 frames.], batch size: 17, lr: 2.67e-03
+2022-05-13 20:36:24,113 INFO [train.py:812] (0/8) Epoch 1, batch 3900, loss[loss=0.1673, simple_loss=0.3101, pruned_loss=0.1226, over 6824.00 frames.], tot_loss[loss=0.1909, simple_loss=0.3476, pruned_loss=0.2418, over 1419970.89 frames.], batch size: 15, lr: 2.66e-03
+2022-05-13 20:37:21,123 INFO [train.py:812] (0/8) Epoch 1, batch 3950, loss[loss=0.1654, simple_loss=0.3033, pruned_loss=0.1371, over 6786.00 frames.], tot_loss[loss=0.1895, simple_loss=0.3458, pruned_loss=0.2208, over 1418469.82 frames.], batch size: 15, lr: 2.66e-03
+2022-05-13 20:38:18,601 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-4000.pt
+2022-05-13 20:38:27,959 INFO [train.py:812] (0/8) Epoch 1, batch 4000, loss[loss=0.1991, simple_loss=0.3663, pruned_loss=0.1599, over 7312.00 frames.], tot_loss[loss=0.1895, simple_loss=0.3464, pruned_loss=0.2057, over 1420668.84 frames.], batch size: 21, lr: 2.65e-03
+2022-05-13 20:39:26,730 INFO [train.py:812] (0/8) Epoch 1, batch 4050, loss[loss=0.194, simple_loss=0.3585, pruned_loss=0.1477, over 7081.00 frames.], tot_loss[loss=0.1897, simple_loss=0.3472, pruned_loss=0.1938, over 1421522.45 frames.], batch size: 28, lr: 2.64e-03
+2022-05-13 20:40:25,268 INFO [train.py:812] (0/8) Epoch 1, batch 4100, loss[loss=0.1808, simple_loss=0.3334, pruned_loss=0.1407, over 7257.00 frames.], tot_loss[loss=0.1881, simple_loss=0.3449, pruned_loss=0.1826, over 1421099.38 frames.], batch size: 19, lr: 2.64e-03
+2022-05-13 20:41:23,999 INFO [train.py:812] (0/8) Epoch 1, batch 4150, loss[loss=0.1765, simple_loss=0.3276, pruned_loss=0.127, over 7070.00 frames.], tot_loss[loss=0.1884, simple_loss=0.3459, pruned_loss=0.175, over 1425557.11 frames.], batch size: 18, lr: 2.63e-03
+2022-05-13 20:42:23,058 INFO [train.py:812] (0/8) Epoch 1, batch 4200, loss[loss=0.1927, simple_loss=0.355, pruned_loss=0.1519, over 7209.00 frames.], tot_loss[loss=0.1881, simple_loss=0.3457, pruned_loss=0.168, over 1425015.78 frames.], batch size: 22, lr: 2.63e-03
+2022-05-13 20:43:21,511 INFO [train.py:812] (0/8) Epoch 1, batch 4250, loss[loss=0.1681, simple_loss=0.315, pruned_loss=0.1062, over 7419.00 frames.], tot_loss[loss=0.1874, simple_loss=0.3447, pruned_loss=0.1622, over 1423487.14 frames.], batch size: 20, lr: 2.62e-03
+2022-05-13 20:44:20,463 INFO [train.py:812] (0/8) Epoch 1, batch 4300, loss[loss=0.1936, simple_loss=0.3562, pruned_loss=0.1554, over 7060.00 frames.], tot_loss[loss=0.1876, simple_loss=0.3454, pruned_loss=0.1586, over 1422795.64 frames.], batch size: 28, lr: 2.61e-03
+2022-05-13 20:45:18,960 INFO [train.py:812] (0/8) Epoch 1, batch 4350, loss[loss=0.1816, simple_loss=0.3358, pruned_loss=0.1374, over 7426.00 frames.], tot_loss[loss=0.1871, simple_loss=0.3448, pruned_loss=0.1543, over 1426345.13 frames.], batch size: 20, lr: 2.61e-03
+2022-05-13 20:46:18,355 INFO [train.py:812] (0/8) Epoch 1, batch 4400, loss[loss=0.1914, simple_loss=0.352, pruned_loss=0.1543, over 7273.00 frames.], tot_loss[loss=0.1876, simple_loss=0.3459, pruned_loss=0.1525, over 1424277.72 frames.], batch size: 18, lr: 2.60e-03
+2022-05-13 20:47:17,287 INFO [train.py:812] (0/8) Epoch 1, batch 4450, loss[loss=0.1684, simple_loss=0.3157, pruned_loss=0.1057, over 7421.00 frames.], tot_loss[loss=0.188, simple_loss=0.3467, pruned_loss=0.1511, over 1423360.08 frames.], batch size: 20, lr: 2.59e-03
+2022-05-13 20:48:16,743 INFO [train.py:812] (0/8) Epoch 1, batch 4500, loss[loss=0.2087, simple_loss=0.3838, pruned_loss=0.1678, over 6485.00 frames.], tot_loss[loss=0.1881, simple_loss=0.347, pruned_loss=0.1493, over 1414058.75 frames.], batch size: 38, lr: 2.59e-03
+2022-05-13 20:49:13,812 INFO [train.py:812] (0/8) Epoch 1, batch 4550, loss[loss=0.189, simple_loss=0.348, pruned_loss=0.1504, over 5215.00 frames.], tot_loss[loss=0.1887, simple_loss=0.3482, pruned_loss=0.1487, over 1394835.05 frames.], batch size: 52, lr: 2.58e-03
+2022-05-13 20:49:57,658 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-1.pt
+2022-05-13 20:50:25,947 INFO [train.py:812] (0/8) Epoch 2, batch 0, loss[loss=0.1898, simple_loss=0.3478, pruned_loss=0.1592, over 7160.00 frames.], tot_loss[loss=0.1898, simple_loss=0.3478, pruned_loss=0.1592, over 7160.00 frames.], batch size: 26, lr: 2.56e-03
+2022-05-13 20:51:25,845 INFO [train.py:812] (0/8) Epoch 2, batch 50, loss[loss=0.203, simple_loss=0.3733, pruned_loss=0.1634, over 7242.00 frames.], tot_loss[loss=0.1856, simple_loss=0.3428, pruned_loss=0.1413, over 311855.47 frames.], batch size: 20, lr: 2.55e-03
+2022-05-13 20:52:24,852 INFO [train.py:812] (0/8) Epoch 2, batch 100, loss[loss=0.162, simple_loss=0.3037, pruned_loss=0.1018, over 7425.00 frames.], tot_loss[loss=0.1829, simple_loss=0.3388, pruned_loss=0.135, over 559745.45 frames.], batch size: 20, lr: 2.54e-03
+2022-05-13 20:53:23,904 INFO [train.py:812] (0/8) Epoch 2, batch 150, loss[loss=0.1652, simple_loss=0.3106, pruned_loss=0.09965, over 7342.00 frames.], tot_loss[loss=0.182, simple_loss=0.3375, pruned_loss=0.1328, over 750552.75 frames.], batch size: 20, lr: 2.54e-03
+2022-05-13 20:54:21,310 INFO [train.py:812] (0/8) Epoch 2, batch 200, loss[loss=0.1748, simple_loss=0.3222, pruned_loss=0.1374, over 7166.00 frames.], tot_loss[loss=0.181, simple_loss=0.3358, pruned_loss=0.131, over 900226.90 frames.], batch size: 19, lr: 2.53e-03
+2022-05-13 20:55:19,901 INFO [train.py:812] (0/8) Epoch 2, batch 250, loss[loss=0.1831, simple_loss=0.3426, pruned_loss=0.1184, over 7379.00 frames.], tot_loss[loss=0.1819, simple_loss=0.3373, pruned_loss=0.1323, over 1015025.03 frames.], batch size: 23, lr: 2.53e-03
+2022-05-13 20:56:18,124 INFO [train.py:812] (0/8) Epoch 2, batch 300, loss[loss=0.179, simple_loss=0.3328, pruned_loss=0.1256, over 7259.00 frames.], tot_loss[loss=0.1823, simple_loss=0.3381, pruned_loss=0.132, over 1104885.98 frames.], batch size: 19, lr: 2.52e-03
+2022-05-13 20:57:16,227 INFO [train.py:812] (0/8) Epoch 2, batch 350, loss[loss=0.1784, simple_loss=0.3349, pruned_loss=0.1099, over 7208.00 frames.], tot_loss[loss=0.1816, simple_loss=0.3369, pruned_loss=0.1318, over 1173402.46 frames.], batch size: 21, lr: 2.51e-03
+2022-05-13 20:58:14,745 INFO [train.py:812] (0/8) Epoch 2, batch 400, loss[loss=0.1979, simple_loss=0.3655, pruned_loss=0.1512, over 7145.00 frames.], tot_loss[loss=0.181, simple_loss=0.3358, pruned_loss=0.1308, over 1230512.12 frames.], batch size: 20, lr: 2.51e-03
+2022-05-13 20:59:13,908 INFO [train.py:812] (0/8) Epoch 2, batch 450, loss[loss=0.1707, simple_loss=0.3207, pruned_loss=0.1031, over 7162.00 frames.], tot_loss[loss=0.1812, simple_loss=0.3363, pruned_loss=0.1301, over 1275815.00 frames.], batch size: 19, lr: 2.50e-03
+2022-05-13 21:00:12,341 INFO [train.py:812] (0/8) Epoch 2, batch 500, loss[loss=0.1672, simple_loss=0.3133, pruned_loss=0.1055, over 7165.00 frames.], tot_loss[loss=0.1811, simple_loss=0.3363, pruned_loss=0.1297, over 1307010.19 frames.], batch size: 18, lr: 2.49e-03
+2022-05-13 21:01:12,105 INFO [train.py:812] (0/8) Epoch 2, batch 550, loss[loss=0.1591, simple_loss=0.2991, pruned_loss=0.09617, over 7364.00 frames.], tot_loss[loss=0.1803, simple_loss=0.3349, pruned_loss=0.1284, over 1331676.19 frames.], batch size: 19, lr: 2.49e-03
+2022-05-13 21:02:09,996 INFO [train.py:812] (0/8) Epoch 2, batch 600, loss[loss=0.1887, simple_loss=0.351, pruned_loss=0.132, over 7375.00 frames.], tot_loss[loss=0.1809, simple_loss=0.3361, pruned_loss=0.1287, over 1353597.05 frames.], batch size: 23, lr: 2.48e-03
+2022-05-13 21:03:08,993 INFO [train.py:812] (0/8) Epoch 2, batch 650, loss[loss=0.1592, simple_loss=0.2979, pruned_loss=0.103, over 7288.00 frames.], tot_loss[loss=0.1808, simple_loss=0.3358, pruned_loss=0.129, over 1367970.49 frames.], batch size: 18, lr: 2.48e-03
+2022-05-13 21:04:08,339 INFO [train.py:812] (0/8) Epoch 2, batch 700, loss[loss=0.1885, simple_loss=0.3458, pruned_loss=0.1559, over 4882.00 frames.], tot_loss[loss=0.18, simple_loss=0.3344, pruned_loss=0.1279, over 1379447.40 frames.], batch size: 53, lr: 2.47e-03
+2022-05-13 21:05:07,229 INFO [train.py:812] (0/8) Epoch 2, batch 750, loss[loss=0.1763, simple_loss=0.3268, pruned_loss=0.1288, over 7245.00 frames.], tot_loss[loss=0.1795, simple_loss=0.3337, pruned_loss=0.1266, over 1390244.62 frames.], batch size: 19, lr: 2.46e-03
+2022-05-13 21:06:06,460 INFO [train.py:812] (0/8) Epoch 2, batch 800, loss[loss=0.1779, simple_loss=0.3317, pruned_loss=0.1206, over 7064.00 frames.], tot_loss[loss=0.1785, simple_loss=0.332, pruned_loss=0.1248, over 1399985.28 frames.], batch size: 18, lr: 2.46e-03
+2022-05-13 21:07:06,092 INFO [train.py:812] (0/8) Epoch 2, batch 850, loss[loss=0.1679, simple_loss=0.3126, pruned_loss=0.116, over 7328.00 frames.], tot_loss[loss=0.178, simple_loss=0.3311, pruned_loss=0.1242, over 1408189.89 frames.], batch size: 20, lr: 2.45e-03
+2022-05-13 21:08:05,127 INFO [train.py:812] (0/8) Epoch 2, batch 900, loss[loss=0.1855, simple_loss=0.3436, pruned_loss=0.1369, over 7435.00 frames.], tot_loss[loss=0.1781, simple_loss=0.3313, pruned_loss=0.1245, over 1413131.24 frames.], batch size: 20, lr: 2.45e-03
+2022-05-13 21:09:04,199 INFO [train.py:812] (0/8) Epoch 2, batch 950, loss[loss=0.1553, simple_loss=0.2897, pruned_loss=0.1045, over 7258.00 frames.], tot_loss[loss=0.178, simple_loss=0.3311, pruned_loss=0.1242, over 1414747.54 frames.], batch size: 19, lr: 2.44e-03
+2022-05-13 21:10:02,113 INFO [train.py:812] (0/8) Epoch 2, batch 1000, loss[loss=0.1871, simple_loss=0.3448, pruned_loss=0.1471, over 6664.00 frames.], tot_loss[loss=0.1777, simple_loss=0.3306, pruned_loss=0.1235, over 1416177.82 frames.], batch size: 31, lr: 2.43e-03
+2022-05-13 21:11:00,254 INFO [train.py:812] (0/8) Epoch 2, batch 1050, loss[loss=0.172, simple_loss=0.3204, pruned_loss=0.1184, over 7429.00 frames.], tot_loss[loss=0.1774, simple_loss=0.3302, pruned_loss=0.1231, over 1418890.59 frames.], batch size: 20, lr: 2.43e-03
+2022-05-13 21:11:59,259 INFO [train.py:812] (0/8) Epoch 2, batch 1100, loss[loss=0.176, simple_loss=0.3277, pruned_loss=0.1212, over 7162.00 frames.], tot_loss[loss=0.1773, simple_loss=0.3301, pruned_loss=0.1223, over 1420632.50 frames.], batch size: 18, lr: 2.42e-03
+2022-05-13 21:12:57,568 INFO [train.py:812] (0/8) Epoch 2, batch 1150, loss[loss=0.1776, simple_loss=0.3324, pruned_loss=0.1144, over 7241.00 frames.], tot_loss[loss=0.1766, simple_loss=0.329, pruned_loss=0.1214, over 1423816.84 frames.], batch size: 20, lr: 2.41e-03
+2022-05-13 21:13:56,178 INFO [train.py:812] (0/8) Epoch 2, batch 1200, loss[loss=0.1702, simple_loss=0.3203, pruned_loss=0.1007, over 7091.00 frames.], tot_loss[loss=0.1772, simple_loss=0.3302, pruned_loss=0.1217, over 1423126.82 frames.], batch size: 28, lr: 2.41e-03
+2022-05-13 21:14:54,781 INFO [train.py:812] (0/8) Epoch 2, batch 1250, loss[loss=0.152, simple_loss=0.2876, pruned_loss=0.08143, over 7285.00 frames.], tot_loss[loss=0.1776, simple_loss=0.3308, pruned_loss=0.1218, over 1422568.38 frames.], batch size: 18, lr: 2.40e-03
+2022-05-13 21:15:53,350 INFO [train.py:812] (0/8) Epoch 2, batch 1300, loss[loss=0.1792, simple_loss=0.3377, pruned_loss=0.1032, over 7224.00 frames.], tot_loss[loss=0.1779, simple_loss=0.3313, pruned_loss=0.1225, over 1416803.11 frames.], batch size: 21, lr: 2.40e-03
+2022-05-13 21:16:52,358 INFO [train.py:812] (0/8) Epoch 2, batch 1350, loss[loss=0.1551, simple_loss=0.2907, pruned_loss=0.0978, over 7281.00 frames.], tot_loss[loss=0.1765, simple_loss=0.3289, pruned_loss=0.1207, over 1420152.50 frames.], batch size: 17, lr: 2.39e-03
+2022-05-13 21:17:49,941 INFO [train.py:812] (0/8) Epoch 2, batch 1400, loss[loss=0.1562, simple_loss=0.2968, pruned_loss=0.07855, over 7224.00 frames.], tot_loss[loss=0.1764, simple_loss=0.3288, pruned_loss=0.12, over 1418397.34 frames.], batch size: 21, lr: 2.39e-03
+2022-05-13 21:18:49,260 INFO [train.py:812] (0/8) Epoch 2, batch 1450, loss[loss=0.294, simple_loss=0.3314, pruned_loss=0.1283, over 7155.00 frames.], tot_loss[loss=0.2001, simple_loss=0.3308, pruned_loss=0.1229, over 1422618.42 frames.], batch size: 26, lr: 2.38e-03
+2022-05-13 21:19:47,678 INFO [train.py:812] (0/8) Epoch 2, batch 1500, loss[loss=0.2959, simple_loss=0.3385, pruned_loss=0.1266, over 6514.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3325, pruned_loss=0.1239, over 1422021.15 frames.], batch size: 38, lr: 2.37e-03
+2022-05-13 21:20:45,899 INFO [train.py:812] (0/8) Epoch 2, batch 1550, loss[loss=0.2723, simple_loss=0.3126, pruned_loss=0.116, over 7437.00 frames.], tot_loss[loss=0.238, simple_loss=0.3343, pruned_loss=0.1242, over 1425968.91 frames.], batch size: 20, lr: 2.37e-03
+2022-05-13 21:21:43,120 INFO [train.py:812] (0/8) Epoch 2, batch 1600, loss[loss=0.2804, simple_loss=0.3207, pruned_loss=0.1201, over 7159.00 frames.], tot_loss[loss=0.249, simple_loss=0.3344, pruned_loss=0.1233, over 1425285.39 frames.], batch size: 18, lr: 2.36e-03
+2022-05-13 21:22:41,916 INFO [train.py:812] (0/8) Epoch 2, batch 1650, loss[loss=0.2861, simple_loss=0.3338, pruned_loss=0.1192, over 7432.00 frames.], tot_loss[loss=0.2566, simple_loss=0.3336, pruned_loss=0.1221, over 1425417.30 frames.], batch size: 20, lr: 2.36e-03
+2022-05-13 21:23:40,008 INFO [train.py:812] (0/8) Epoch 2, batch 1700, loss[loss=0.3382, simple_loss=0.3739, pruned_loss=0.1513, over 7404.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3337, pruned_loss=0.121, over 1424434.93 frames.], batch size: 21, lr: 2.35e-03
+2022-05-13 21:24:38,979 INFO [train.py:812] (0/8) Epoch 2, batch 1750, loss[loss=0.2538, simple_loss=0.3075, pruned_loss=0.1001, over 7275.00 frames.], tot_loss[loss=0.268, simple_loss=0.3348, pruned_loss=0.1202, over 1423760.49 frames.], batch size: 18, lr: 2.34e-03
+2022-05-13 21:25:38,306 INFO [train.py:812] (0/8) Epoch 2, batch 1800, loss[loss=0.232, simple_loss=0.2912, pruned_loss=0.08644, over 7364.00 frames.], tot_loss[loss=0.2712, simple_loss=0.3346, pruned_loss=0.1191, over 1424964.15 frames.], batch size: 19, lr: 2.34e-03
+2022-05-13 21:26:37,483 INFO [train.py:812] (0/8) Epoch 2, batch 1850, loss[loss=0.2537, simple_loss=0.3147, pruned_loss=0.0964, over 7332.00 frames.], tot_loss[loss=0.2711, simple_loss=0.3324, pruned_loss=0.1167, over 1425525.59 frames.], batch size: 20, lr: 2.33e-03
+2022-05-13 21:27:35,691 INFO [train.py:812] (0/8) Epoch 2, batch 1900, loss[loss=0.2796, simple_loss=0.3202, pruned_loss=0.1195, over 7006.00 frames.], tot_loss[loss=0.274, simple_loss=0.3332, pruned_loss=0.1166, over 1428836.39 frames.], batch size: 16, lr: 2.33e-03
+2022-05-13 21:28:33,668 INFO [train.py:812] (0/8) Epoch 2, batch 1950, loss[loss=0.2273, simple_loss=0.2834, pruned_loss=0.08554, over 7272.00 frames.], tot_loss[loss=0.2758, simple_loss=0.3337, pruned_loss=0.1161, over 1428895.54 frames.], batch size: 18, lr: 2.32e-03
+2022-05-13 21:29:31,851 INFO [train.py:812] (0/8) Epoch 2, batch 2000, loss[loss=0.2701, simple_loss=0.3295, pruned_loss=0.1053, over 7118.00 frames.], tot_loss[loss=0.2798, simple_loss=0.3361, pruned_loss=0.1174, over 1423621.53 frames.], batch size: 21, lr: 2.32e-03
+2022-05-13 21:30:31,616 INFO [train.py:812] (0/8) Epoch 2, batch 2050, loss[loss=0.3605, simple_loss=0.3996, pruned_loss=0.1607, over 7090.00 frames.], tot_loss[loss=0.28, simple_loss=0.3355, pruned_loss=0.1166, over 1425250.68 frames.], batch size: 28, lr: 2.31e-03
+2022-05-13 21:31:31,041 INFO [train.py:812] (0/8) Epoch 2, batch 2100, loss[loss=0.2724, simple_loss=0.317, pruned_loss=0.1139, over 7414.00 frames.], tot_loss[loss=0.2775, simple_loss=0.3331, pruned_loss=0.1144, over 1425737.50 frames.], batch size: 18, lr: 2.31e-03
+2022-05-13 21:32:30,578 INFO [train.py:812] (0/8) Epoch 2, batch 2150, loss[loss=0.2457, simple_loss=0.3115, pruned_loss=0.08993, over 7424.00 frames.], tot_loss[loss=0.2772, simple_loss=0.3323, pruned_loss=0.1137, over 1424421.00 frames.], batch size: 21, lr: 2.30e-03
+2022-05-13 21:33:29,451 INFO [train.py:812] (0/8) Epoch 2, batch 2200, loss[loss=0.3154, simple_loss=0.3593, pruned_loss=0.1358, over 7118.00 frames.], tot_loss[loss=0.2763, simple_loss=0.3313, pruned_loss=0.1127, over 1422530.91 frames.], batch size: 21, lr: 2.29e-03
+2022-05-13 21:34:29,305 INFO [train.py:812] (0/8) Epoch 2, batch 2250, loss[loss=0.3061, simple_loss=0.3639, pruned_loss=0.1241, over 7219.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3308, pruned_loss=0.1118, over 1423813.01 frames.], batch size: 21, lr: 2.29e-03
+2022-05-13 21:35:27,785 INFO [train.py:812] (0/8) Epoch 2, batch 2300, loss[loss=0.3143, simple_loss=0.3657, pruned_loss=0.1315, over 7201.00 frames.], tot_loss[loss=0.2758, simple_loss=0.3309, pruned_loss=0.1116, over 1424964.24 frames.], batch size: 22, lr: 2.28e-03
+2022-05-13 21:36:26,838 INFO [train.py:812] (0/8) Epoch 2, batch 2350, loss[loss=0.2692, simple_loss=0.3313, pruned_loss=0.1035, over 7226.00 frames.], tot_loss[loss=0.2767, simple_loss=0.3317, pruned_loss=0.1118, over 1423344.59 frames.], batch size: 20, lr: 2.28e-03
+2022-05-13 21:37:24,980 INFO [train.py:812] (0/8) Epoch 2, batch 2400, loss[loss=0.3027, simple_loss=0.3572, pruned_loss=0.1241, over 7317.00 frames.], tot_loss[loss=0.2765, simple_loss=0.332, pruned_loss=0.1113, over 1422714.65 frames.], batch size: 21, lr: 2.27e-03
+2022-05-13 21:38:23,792 INFO [train.py:812] (0/8) Epoch 2, batch 2450, loss[loss=0.2829, simple_loss=0.3441, pruned_loss=0.1108, over 7314.00 frames.], tot_loss[loss=0.277, simple_loss=0.3328, pruned_loss=0.1112, over 1426108.71 frames.], batch size: 21, lr: 2.27e-03
+2022-05-13 21:39:23,345 INFO [train.py:812] (0/8) Epoch 2, batch 2500, loss[loss=0.2821, simple_loss=0.3413, pruned_loss=0.1115, over 7191.00 frames.], tot_loss[loss=0.2748, simple_loss=0.3315, pruned_loss=0.1095, over 1426394.07 frames.], batch size: 26, lr: 2.26e-03
+2022-05-13 21:40:21,932 INFO [train.py:812] (0/8) Epoch 2, batch 2550, loss[loss=0.2464, simple_loss=0.3028, pruned_loss=0.09499, over 6999.00 frames.], tot_loss[loss=0.2727, simple_loss=0.3297, pruned_loss=0.1082, over 1426427.10 frames.], batch size: 16, lr: 2.26e-03
+2022-05-13 21:41:21,069 INFO [train.py:812] (0/8) Epoch 2, batch 2600, loss[loss=0.3083, simple_loss=0.3607, pruned_loss=0.1279, over 7194.00 frames.], tot_loss[loss=0.273, simple_loss=0.3295, pruned_loss=0.1085, over 1428811.52 frames.], batch size: 26, lr: 2.25e-03
+2022-05-13 21:42:20,628 INFO [train.py:812] (0/8) Epoch 2, batch 2650, loss[loss=0.3494, simple_loss=0.3843, pruned_loss=0.1572, over 6291.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3308, pruned_loss=0.1091, over 1427162.76 frames.], batch size: 37, lr: 2.25e-03
+2022-05-13 21:43:18,322 INFO [train.py:812] (0/8) Epoch 2, batch 2700, loss[loss=0.3672, simple_loss=0.4053, pruned_loss=0.1645, over 6716.00 frames.], tot_loss[loss=0.2728, simple_loss=0.3295, pruned_loss=0.1083, over 1426406.18 frames.], batch size: 31, lr: 2.24e-03
+2022-05-13 21:44:17,958 INFO [train.py:812] (0/8) Epoch 2, batch 2750, loss[loss=0.2604, simple_loss=0.3205, pruned_loss=0.1002, over 7260.00 frames.], tot_loss[loss=0.2732, simple_loss=0.3297, pruned_loss=0.1085, over 1423410.66 frames.], batch size: 24, lr: 2.24e-03
+2022-05-13 21:45:15,693 INFO [train.py:812] (0/8) Epoch 2, batch 2800, loss[loss=0.2931, simple_loss=0.3568, pruned_loss=0.1147, over 7197.00 frames.], tot_loss[loss=0.2715, simple_loss=0.3288, pruned_loss=0.1072, over 1426925.71 frames.], batch size: 23, lr: 2.23e-03
+2022-05-13 21:46:14,843 INFO [train.py:812] (0/8) Epoch 2, batch 2850, loss[loss=0.2979, simple_loss=0.3559, pruned_loss=0.12, over 7277.00 frames.], tot_loss[loss=0.2725, simple_loss=0.3295, pruned_loss=0.1079, over 1426440.59 frames.], batch size: 24, lr: 2.23e-03
+2022-05-13 21:47:13,545 INFO [train.py:812] (0/8) Epoch 2, batch 2900, loss[loss=0.2637, simple_loss=0.3277, pruned_loss=0.09985, over 7220.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3303, pruned_loss=0.1084, over 1422919.77 frames.], batch size: 20, lr: 2.22e-03
+2022-05-13 21:48:11,755 INFO [train.py:812] (0/8) Epoch 2, batch 2950, loss[loss=0.2562, simple_loss=0.3357, pruned_loss=0.08834, over 7239.00 frames.], tot_loss[loss=0.2719, simple_loss=0.3292, pruned_loss=0.1073, over 1424016.81 frames.], batch size: 20, lr: 2.22e-03
+2022-05-13 21:49:10,837 INFO [train.py:812] (0/8) Epoch 2, batch 3000, loss[loss=0.2737, simple_loss=0.3158, pruned_loss=0.1158, over 7290.00 frames.], tot_loss[loss=0.2713, simple_loss=0.3291, pruned_loss=0.1068, over 1426619.93 frames.], batch size: 17, lr: 2.21e-03
+2022-05-13 21:49:10,839 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-13 21:49:18,580 INFO [train.py:841] (0/8) Epoch 2, validation: loss=0.2016, simple_loss=0.2977, pruned_loss=0.0527, over 698248.00 frames.
+2022-05-13 21:50:17,417 INFO [train.py:812] (0/8) Epoch 2, batch 3050, loss[loss=0.2461, simple_loss=0.3076, pruned_loss=0.09232, over 7289.00 frames.], tot_loss[loss=0.27, simple_loss=0.3284, pruned_loss=0.1058, over 1421759.65 frames.], batch size: 18, lr: 2.20e-03
+2022-05-13 21:51:15,128 INFO [train.py:812] (0/8) Epoch 2, batch 3100, loss[loss=0.3127, simple_loss=0.3521, pruned_loss=0.1366, over 5086.00 frames.], tot_loss[loss=0.2713, simple_loss=0.3295, pruned_loss=0.1065, over 1422107.05 frames.], batch size: 52, lr: 2.20e-03
+2022-05-13 21:52:13,942 INFO [train.py:812] (0/8) Epoch 2, batch 3150, loss[loss=0.2449, simple_loss=0.2891, pruned_loss=0.1003, over 6771.00 frames.], tot_loss[loss=0.27, simple_loss=0.3286, pruned_loss=0.1057, over 1423869.33 frames.], batch size: 15, lr: 2.19e-03
+2022-05-13 21:53:13,038 INFO [train.py:812] (0/8) Epoch 2, batch 3200, loss[loss=0.3399, simple_loss=0.3786, pruned_loss=0.1506, over 4936.00 frames.], tot_loss[loss=0.2712, simple_loss=0.3297, pruned_loss=0.1063, over 1413273.66 frames.], batch size: 52, lr: 2.19e-03
+2022-05-13 21:54:12,613 INFO [train.py:812] (0/8) Epoch 2, batch 3250, loss[loss=0.2814, simple_loss=0.3324, pruned_loss=0.1152, over 7196.00 frames.], tot_loss[loss=0.2712, simple_loss=0.3296, pruned_loss=0.1065, over 1415630.59 frames.], batch size: 23, lr: 2.18e-03
+2022-05-13 21:55:12,233 INFO [train.py:812] (0/8) Epoch 2, batch 3300, loss[loss=0.2923, simple_loss=0.347, pruned_loss=0.1188, over 7195.00 frames.], tot_loss[loss=0.2708, simple_loss=0.3295, pruned_loss=0.1061, over 1420034.29 frames.], batch size: 22, lr: 2.18e-03
+2022-05-13 21:56:11,988 INFO [train.py:812] (0/8) Epoch 2, batch 3350, loss[loss=0.3392, simple_loss=0.3951, pruned_loss=0.1416, over 7141.00 frames.], tot_loss[loss=0.2709, simple_loss=0.3301, pruned_loss=0.1058, over 1423457.43 frames.], batch size: 26, lr: 2.18e-03
+2022-05-13 21:57:11,192 INFO [train.py:812] (0/8) Epoch 2, batch 3400, loss[loss=0.1976, simple_loss=0.2667, pruned_loss=0.06424, over 7127.00 frames.], tot_loss[loss=0.2676, simple_loss=0.3276, pruned_loss=0.1038, over 1424925.33 frames.], batch size: 17, lr: 2.17e-03
+2022-05-13 21:57:24,098 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-8000.pt
+2022-05-13 21:58:14,488 INFO [train.py:812] (0/8) Epoch 2, batch 3450, loss[loss=0.3157, simple_loss=0.3603, pruned_loss=0.1355, over 7295.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3272, pruned_loss=0.1033, over 1427035.29 frames.], batch size: 24, lr: 2.17e-03
+2022-05-13 21:59:13,382 INFO [train.py:812] (0/8) Epoch 2, batch 3500, loss[loss=0.3084, simple_loss=0.3641, pruned_loss=0.1263, over 6425.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3278, pruned_loss=0.1034, over 1424956.32 frames.], batch size: 38, lr: 2.16e-03
+2022-05-13 22:00:12,704 INFO [train.py:812] (0/8) Epoch 2, batch 3550, loss[loss=0.2698, simple_loss=0.3282, pruned_loss=0.1057, over 7314.00 frames.], tot_loss[loss=0.2659, simple_loss=0.3267, pruned_loss=0.1025, over 1424396.73 frames.], batch size: 25, lr: 2.16e-03
+2022-05-13 22:01:11,596 INFO [train.py:812] (0/8) Epoch 2, batch 3600, loss[loss=0.2316, simple_loss=0.3105, pruned_loss=0.07635, over 7234.00 frames.], tot_loss[loss=0.2651, simple_loss=0.3264, pruned_loss=0.1019, over 1425811.43 frames.], batch size: 20, lr: 2.15e-03
+2022-05-13 22:02:11,441 INFO [train.py:812] (0/8) Epoch 2, batch 3650, loss[loss=0.2756, simple_loss=0.3177, pruned_loss=0.1168, over 6830.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3276, pruned_loss=0.1031, over 1426907.80 frames.], batch size: 15, lr: 2.15e-03
+2022-05-13 22:03:10,447 INFO [train.py:812] (0/8) Epoch 2, batch 3700, loss[loss=0.2449, simple_loss=0.3051, pruned_loss=0.09233, over 7167.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3286, pruned_loss=0.1032, over 1428723.53 frames.], batch size: 19, lr: 2.14e-03
+2022-05-13 22:04:09,800 INFO [train.py:812] (0/8) Epoch 2, batch 3750, loss[loss=0.2908, simple_loss=0.3643, pruned_loss=0.1086, over 7281.00 frames.], tot_loss[loss=0.2668, simple_loss=0.3284, pruned_loss=0.1026, over 1429652.86 frames.], batch size: 24, lr: 2.14e-03
+2022-05-13 22:05:09,270 INFO [train.py:812] (0/8) Epoch 2, batch 3800, loss[loss=0.2437, simple_loss=0.2928, pruned_loss=0.0973, over 6783.00 frames.], tot_loss[loss=0.266, simple_loss=0.3279, pruned_loss=0.1021, over 1428776.73 frames.], batch size: 15, lr: 2.13e-03
+2022-05-13 22:06:07,964 INFO [train.py:812] (0/8) Epoch 2, batch 3850, loss[loss=0.3728, simple_loss=0.4, pruned_loss=0.1728, over 7168.00 frames.], tot_loss[loss=0.2655, simple_loss=0.3279, pruned_loss=0.1015, over 1431082.28 frames.], batch size: 26, lr: 2.13e-03
+2022-05-13 22:07:06,194 INFO [train.py:812] (0/8) Epoch 2, batch 3900, loss[loss=0.2567, simple_loss=0.3341, pruned_loss=0.0896, over 7318.00 frames.], tot_loss[loss=0.2635, simple_loss=0.3266, pruned_loss=0.1002, over 1430219.86 frames.], batch size: 24, lr: 2.12e-03
+2022-05-13 22:08:05,667 INFO [train.py:812] (0/8) Epoch 2, batch 3950, loss[loss=0.2737, simple_loss=0.3359, pruned_loss=0.1058, over 7114.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3266, pruned_loss=0.1005, over 1427912.46 frames.], batch size: 21, lr: 2.12e-03
+2022-05-13 22:09:04,764 INFO [train.py:812] (0/8) Epoch 2, batch 4000, loss[loss=0.2566, simple_loss=0.329, pruned_loss=0.09213, over 7211.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3252, pruned_loss=0.09925, over 1428151.45 frames.], batch size: 22, lr: 2.11e-03
+2022-05-13 22:10:02,688 INFO [train.py:812] (0/8) Epoch 2, batch 4050, loss[loss=0.3037, simple_loss=0.3611, pruned_loss=0.1231, over 6773.00 frames.], tot_loss[loss=0.2633, simple_loss=0.3261, pruned_loss=0.1002, over 1426121.28 frames.], batch size: 31, lr: 2.11e-03
+2022-05-13 22:11:01,284 INFO [train.py:812] (0/8) Epoch 2, batch 4100, loss[loss=0.2981, simple_loss=0.3516, pruned_loss=0.1223, over 7220.00 frames.], tot_loss[loss=0.2644, simple_loss=0.327, pruned_loss=0.1009, over 1420460.72 frames.], batch size: 21, lr: 2.10e-03
+2022-05-13 22:11:59,871 INFO [train.py:812] (0/8) Epoch 2, batch 4150, loss[loss=0.292, simple_loss=0.3478, pruned_loss=0.1181, over 6780.00 frames.], tot_loss[loss=0.2637, simple_loss=0.3263, pruned_loss=0.1006, over 1419972.99 frames.], batch size: 31, lr: 2.10e-03
+2022-05-13 22:12:58,518 INFO [train.py:812] (0/8) Epoch 2, batch 4200, loss[loss=0.2444, simple_loss=0.312, pruned_loss=0.08838, over 7275.00 frames.], tot_loss[loss=0.2631, simple_loss=0.3256, pruned_loss=0.1003, over 1418669.90 frames.], batch size: 18, lr: 2.10e-03
+2022-05-13 22:13:58,156 INFO [train.py:812] (0/8) Epoch 2, batch 4250, loss[loss=0.2021, simple_loss=0.2692, pruned_loss=0.06748, over 7289.00 frames.], tot_loss[loss=0.2644, simple_loss=0.3261, pruned_loss=0.1013, over 1413637.46 frames.], batch size: 18, lr: 2.09e-03
+2022-05-13 22:14:56,711 INFO [train.py:812] (0/8) Epoch 2, batch 4300, loss[loss=0.2411, simple_loss=0.3214, pruned_loss=0.08038, over 7287.00 frames.], tot_loss[loss=0.2644, simple_loss=0.3259, pruned_loss=0.1014, over 1413282.85 frames.], batch size: 25, lr: 2.09e-03
+2022-05-13 22:15:55,434 INFO [train.py:812] (0/8) Epoch 2, batch 4350, loss[loss=0.1948, simple_loss=0.2693, pruned_loss=0.0602, over 7007.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3255, pruned_loss=0.1005, over 1413448.77 frames.], batch size: 16, lr: 2.08e-03
+2022-05-13 22:16:54,277 INFO [train.py:812] (0/8) Epoch 2, batch 4400, loss[loss=0.2723, simple_loss=0.3516, pruned_loss=0.09655, over 7323.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3251, pruned_loss=0.1003, over 1408617.83 frames.], batch size: 21, lr: 2.08e-03
+2022-05-13 22:17:52,727 INFO [train.py:812] (0/8) Epoch 2, batch 4450, loss[loss=0.3128, simple_loss=0.3534, pruned_loss=0.1361, over 6462.00 frames.], tot_loss[loss=0.2622, simple_loss=0.3247, pruned_loss=0.0999, over 1401496.50 frames.], batch size: 37, lr: 2.07e-03
+2022-05-13 22:18:50,558 INFO [train.py:812] (0/8) Epoch 2, batch 4500, loss[loss=0.3122, simple_loss=0.3649, pruned_loss=0.1298, over 6537.00 frames.], tot_loss[loss=0.2616, simple_loss=0.3239, pruned_loss=0.09967, over 1386978.24 frames.], batch size: 38, lr: 2.07e-03
+2022-05-13 22:19:49,299 INFO [train.py:812] (0/8) Epoch 2, batch 4550, loss[loss=0.3045, simple_loss=0.3544, pruned_loss=0.1272, over 5629.00 frames.], tot_loss[loss=0.2657, simple_loss=0.327, pruned_loss=0.1022, over 1357489.48 frames.], batch size: 52, lr: 2.06e-03
+2022-05-13 22:20:34,169 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-2.pt
+2022-05-13 22:20:58,925 INFO [train.py:812] (0/8) Epoch 3, batch 0, loss[loss=0.2087, simple_loss=0.2698, pruned_loss=0.07381, over 7278.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2698, pruned_loss=0.07381, over 7278.00 frames.], batch size: 17, lr: 2.02e-03
+2022-05-13 22:21:58,065 INFO [train.py:812] (0/8) Epoch 3, batch 50, loss[loss=0.2969, simple_loss=0.3539, pruned_loss=0.12, over 7292.00 frames.], tot_loss[loss=0.2535, simple_loss=0.317, pruned_loss=0.09502, over 321427.60 frames.], batch size: 25, lr: 2.02e-03
+2022-05-13 22:22:56,159 INFO [train.py:812] (0/8) Epoch 3, batch 100, loss[loss=0.2192, simple_loss=0.2859, pruned_loss=0.07621, over 7006.00 frames.], tot_loss[loss=0.254, simple_loss=0.319, pruned_loss=0.09452, over 568376.61 frames.], batch size: 16, lr: 2.01e-03
+2022-05-13 22:23:56,092 INFO [train.py:812] (0/8) Epoch 3, batch 150, loss[loss=0.2686, simple_loss=0.3377, pruned_loss=0.09979, over 6869.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3161, pruned_loss=0.09218, over 761124.08 frames.], batch size: 31, lr: 2.01e-03
+2022-05-13 22:24:53,592 INFO [train.py:812] (0/8) Epoch 3, batch 200, loss[loss=0.2603, simple_loss=0.3052, pruned_loss=0.1077, over 7225.00 frames.], tot_loss[loss=0.253, simple_loss=0.3183, pruned_loss=0.09387, over 899581.72 frames.], batch size: 16, lr: 2.00e-03
+2022-05-13 22:25:53,018 INFO [train.py:812] (0/8) Epoch 3, batch 250, loss[loss=0.2261, simple_loss=0.2987, pruned_loss=0.07674, over 7356.00 frames.], tot_loss[loss=0.2558, simple_loss=0.3207, pruned_loss=0.09541, over 1009971.06 frames.], batch size: 19, lr: 2.00e-03
+2022-05-13 22:26:52,183 INFO [train.py:812] (0/8) Epoch 3, batch 300, loss[loss=0.2493, simple_loss=0.3114, pruned_loss=0.09362, over 6671.00 frames.], tot_loss[loss=0.2578, simple_loss=0.3229, pruned_loss=0.09632, over 1100054.34 frames.], batch size: 31, lr: 2.00e-03
+2022-05-13 22:27:51,979 INFO [train.py:812] (0/8) Epoch 3, batch 350, loss[loss=0.2795, simple_loss=0.3395, pruned_loss=0.1098, over 7321.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3232, pruned_loss=0.09649, over 1170440.02 frames.], batch size: 21, lr: 1.99e-03
+2022-05-13 22:29:00,811 INFO [train.py:812] (0/8) Epoch 3, batch 400, loss[loss=0.2697, simple_loss=0.3456, pruned_loss=0.09688, over 7265.00 frames.], tot_loss[loss=0.2578, simple_loss=0.3228, pruned_loss=0.09641, over 1221694.92 frames.], batch size: 24, lr: 1.99e-03
+2022-05-13 22:29:59,466 INFO [train.py:812] (0/8) Epoch 3, batch 450, loss[loss=0.293, simple_loss=0.358, pruned_loss=0.114, over 7206.00 frames.], tot_loss[loss=0.2576, simple_loss=0.3231, pruned_loss=0.09602, over 1263692.57 frames.], batch size: 22, lr: 1.98e-03
+2022-05-13 22:31:07,388 INFO [train.py:812] (0/8) Epoch 3, batch 500, loss[loss=0.2346, simple_loss=0.2971, pruned_loss=0.08603, over 6991.00 frames.], tot_loss[loss=0.257, simple_loss=0.3226, pruned_loss=0.09571, over 1302207.80 frames.], batch size: 16, lr: 1.98e-03
+2022-05-13 22:32:54,329 INFO [train.py:812] (0/8) Epoch 3, batch 550, loss[loss=0.2278, simple_loss=0.3047, pruned_loss=0.07538, over 7225.00 frames.], tot_loss[loss=0.2549, simple_loss=0.321, pruned_loss=0.09442, over 1332015.14 frames.], batch size: 21, lr: 1.98e-03
+2022-05-13 22:34:03,096 INFO [train.py:812] (0/8) Epoch 3, batch 600, loss[loss=0.3212, simple_loss=0.3756, pruned_loss=0.1334, over 7304.00 frames.], tot_loss[loss=0.2544, simple_loss=0.3202, pruned_loss=0.09431, over 1353396.38 frames.], batch size: 25, lr: 1.97e-03
+2022-05-13 22:35:02,724 INFO [train.py:812] (0/8) Epoch 3, batch 650, loss[loss=0.2783, simple_loss=0.3281, pruned_loss=0.1142, over 7368.00 frames.], tot_loss[loss=0.2536, simple_loss=0.3189, pruned_loss=0.09414, over 1367542.24 frames.], batch size: 19, lr: 1.97e-03
+2022-05-13 22:36:02,123 INFO [train.py:812] (0/8) Epoch 3, batch 700, loss[loss=0.2573, simple_loss=0.3276, pruned_loss=0.09345, over 7218.00 frames.], tot_loss[loss=0.255, simple_loss=0.3204, pruned_loss=0.09486, over 1378368.59 frames.], batch size: 21, lr: 1.96e-03
+2022-05-13 22:37:01,895 INFO [train.py:812] (0/8) Epoch 3, batch 750, loss[loss=0.2163, simple_loss=0.2911, pruned_loss=0.0708, over 7214.00 frames.], tot_loss[loss=0.2544, simple_loss=0.3199, pruned_loss=0.09448, over 1391788.55 frames.], batch size: 23, lr: 1.96e-03
+2022-05-13 22:38:00,548 INFO [train.py:812] (0/8) Epoch 3, batch 800, loss[loss=0.2348, simple_loss=0.3115, pruned_loss=0.07902, over 7196.00 frames.], tot_loss[loss=0.2544, simple_loss=0.3201, pruned_loss=0.09439, over 1402272.07 frames.], batch size: 23, lr: 1.96e-03
+2022-05-13 22:38:59,712 INFO [train.py:812] (0/8) Epoch 3, batch 850, loss[loss=0.2573, simple_loss=0.3301, pruned_loss=0.09221, over 7286.00 frames.], tot_loss[loss=0.2518, simple_loss=0.318, pruned_loss=0.09274, over 1410174.78 frames.], batch size: 25, lr: 1.95e-03
+2022-05-13 22:39:58,495 INFO [train.py:812] (0/8) Epoch 3, batch 900, loss[loss=0.2083, simple_loss=0.2813, pruned_loss=0.06768, over 7056.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3194, pruned_loss=0.09361, over 1412364.58 frames.], batch size: 18, lr: 1.95e-03
+2022-05-13 22:40:58,630 INFO [train.py:812] (0/8) Epoch 3, batch 950, loss[loss=0.2371, simple_loss=0.3216, pruned_loss=0.07628, over 7144.00 frames.], tot_loss[loss=0.2538, simple_loss=0.3197, pruned_loss=0.09399, over 1417483.63 frames.], batch size: 20, lr: 1.94e-03
+2022-05-13 22:41:58,343 INFO [train.py:812] (0/8) Epoch 3, batch 1000, loss[loss=0.319, simple_loss=0.3688, pruned_loss=0.1346, over 6691.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3199, pruned_loss=0.09373, over 1417390.79 frames.], batch size: 31, lr: 1.94e-03
+2022-05-13 22:42:57,561 INFO [train.py:812] (0/8) Epoch 3, batch 1050, loss[loss=0.2431, simple_loss=0.2983, pruned_loss=0.09395, over 7272.00 frames.], tot_loss[loss=0.2538, simple_loss=0.3197, pruned_loss=0.09389, over 1415379.57 frames.], batch size: 18, lr: 1.94e-03
+2022-05-13 22:43:56,792 INFO [train.py:812] (0/8) Epoch 3, batch 1100, loss[loss=0.2445, simple_loss=0.3256, pruned_loss=0.08177, over 7201.00 frames.], tot_loss[loss=0.254, simple_loss=0.3204, pruned_loss=0.09374, over 1420602.78 frames.], batch size: 21, lr: 1.93e-03
+2022-05-13 22:44:56,336 INFO [train.py:812] (0/8) Epoch 3, batch 1150, loss[loss=0.2593, simple_loss=0.3311, pruned_loss=0.09374, over 7237.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3201, pruned_loss=0.09368, over 1421134.56 frames.], batch size: 20, lr: 1.93e-03
+2022-05-13 22:45:54,827 INFO [train.py:812] (0/8) Epoch 3, batch 1200, loss[loss=0.2338, simple_loss=0.2983, pruned_loss=0.08462, over 7436.00 frames.], tot_loss[loss=0.2535, simple_loss=0.3198, pruned_loss=0.09366, over 1424169.88 frames.], batch size: 20, lr: 1.93e-03
+2022-05-13 22:46:52,753 INFO [train.py:812] (0/8) Epoch 3, batch 1250, loss[loss=0.2446, simple_loss=0.3141, pruned_loss=0.08757, over 7409.00 frames.], tot_loss[loss=0.2531, simple_loss=0.3195, pruned_loss=0.09334, over 1424804.05 frames.], batch size: 21, lr: 1.92e-03
+2022-05-13 22:47:52,025 INFO [train.py:812] (0/8) Epoch 3, batch 1300, loss[loss=0.2368, simple_loss=0.3183, pruned_loss=0.07768, over 7330.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3193, pruned_loss=0.09366, over 1426791.66 frames.], batch size: 21, lr: 1.92e-03
+2022-05-13 22:48:50,088 INFO [train.py:812] (0/8) Epoch 3, batch 1350, loss[loss=0.2279, simple_loss=0.2993, pruned_loss=0.07826, over 7427.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3201, pruned_loss=0.09361, over 1425927.91 frames.], batch size: 20, lr: 1.91e-03
+2022-05-13 22:49:48,131 INFO [train.py:812] (0/8) Epoch 3, batch 1400, loss[loss=0.2216, simple_loss=0.2975, pruned_loss=0.07288, over 7163.00 frames.], tot_loss[loss=0.2528, simple_loss=0.3198, pruned_loss=0.0929, over 1423603.50 frames.], batch size: 19, lr: 1.91e-03
+2022-05-13 22:50:48,078 INFO [train.py:812] (0/8) Epoch 3, batch 1450, loss[loss=0.2111, simple_loss=0.2762, pruned_loss=0.07298, over 7125.00 frames.], tot_loss[loss=0.2517, simple_loss=0.3187, pruned_loss=0.09231, over 1420296.04 frames.], batch size: 17, lr: 1.91e-03
+2022-05-13 22:51:46,940 INFO [train.py:812] (0/8) Epoch 3, batch 1500, loss[loss=0.2841, simple_loss=0.3416, pruned_loss=0.1133, over 7317.00 frames.], tot_loss[loss=0.2523, simple_loss=0.3189, pruned_loss=0.09283, over 1418718.46 frames.], batch size: 21, lr: 1.90e-03
+2022-05-13 22:52:47,272 INFO [train.py:812] (0/8) Epoch 3, batch 1550, loss[loss=0.2139, simple_loss=0.298, pruned_loss=0.06493, over 7156.00 frames.], tot_loss[loss=0.2509, simple_loss=0.3181, pruned_loss=0.09184, over 1422668.05 frames.], batch size: 19, lr: 1.90e-03
+2022-05-13 22:53:45,779 INFO [train.py:812] (0/8) Epoch 3, batch 1600, loss[loss=0.2242, simple_loss=0.294, pruned_loss=0.07718, over 7178.00 frames.], tot_loss[loss=0.251, simple_loss=0.3184, pruned_loss=0.09177, over 1424882.16 frames.], batch size: 19, lr: 1.90e-03
+2022-05-13 22:54:44,635 INFO [train.py:812] (0/8) Epoch 3, batch 1650, loss[loss=0.1961, simple_loss=0.2794, pruned_loss=0.05644, over 7433.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3179, pruned_loss=0.09183, over 1428047.62 frames.], batch size: 20, lr: 1.89e-03
+2022-05-13 22:55:42,303 INFO [train.py:812] (0/8) Epoch 3, batch 1700, loss[loss=0.2347, simple_loss=0.3161, pruned_loss=0.07671, over 7152.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3176, pruned_loss=0.09164, over 1417442.34 frames.], batch size: 20, lr: 1.89e-03
+2022-05-13 22:56:41,865 INFO [train.py:812] (0/8) Epoch 3, batch 1750, loss[loss=0.2486, simple_loss=0.3191, pruned_loss=0.089, over 7237.00 frames.], tot_loss[loss=0.248, simple_loss=0.316, pruned_loss=0.09001, over 1424852.33 frames.], batch size: 20, lr: 1.88e-03
+2022-05-13 22:57:40,359 INFO [train.py:812] (0/8) Epoch 3, batch 1800, loss[loss=0.2855, simple_loss=0.3546, pruned_loss=0.1082, over 7108.00 frames.], tot_loss[loss=0.2483, simple_loss=0.316, pruned_loss=0.09033, over 1417379.74 frames.], batch size: 21, lr: 1.88e-03
+2022-05-13 22:58:39,760 INFO [train.py:812] (0/8) Epoch 3, batch 1850, loss[loss=0.2644, simple_loss=0.328, pruned_loss=0.1004, over 7409.00 frames.], tot_loss[loss=0.2473, simple_loss=0.3153, pruned_loss=0.08968, over 1419418.08 frames.], batch size: 21, lr: 1.88e-03
+2022-05-13 22:59:38,877 INFO [train.py:812] (0/8) Epoch 3, batch 1900, loss[loss=0.2531, simple_loss=0.314, pruned_loss=0.09613, over 7173.00 frames.], tot_loss[loss=0.247, simple_loss=0.315, pruned_loss=0.08944, over 1417187.67 frames.], batch size: 18, lr: 1.87e-03
+2022-05-13 23:00:38,435 INFO [train.py:812] (0/8) Epoch 3, batch 1950, loss[loss=0.2859, simple_loss=0.3569, pruned_loss=0.1075, over 6732.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3144, pruned_loss=0.0887, over 1418686.73 frames.], batch size: 31, lr: 1.87e-03
+2022-05-13 23:01:37,609 INFO [train.py:812] (0/8) Epoch 3, batch 2000, loss[loss=0.2668, simple_loss=0.3293, pruned_loss=0.1021, over 7157.00 frames.], tot_loss[loss=0.245, simple_loss=0.3137, pruned_loss=0.08818, over 1423116.33 frames.], batch size: 19, lr: 1.87e-03
+2022-05-13 23:02:36,942 INFO [train.py:812] (0/8) Epoch 3, batch 2050, loss[loss=0.3335, simple_loss=0.3677, pruned_loss=0.1496, over 4995.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3153, pruned_loss=0.08898, over 1422527.94 frames.], batch size: 52, lr: 1.86e-03
+2022-05-13 23:03:35,455 INFO [train.py:812] (0/8) Epoch 3, batch 2100, loss[loss=0.2768, simple_loss=0.3386, pruned_loss=0.1075, over 7324.00 frames.], tot_loss[loss=0.247, simple_loss=0.3159, pruned_loss=0.08908, over 1425566.82 frames.], batch size: 21, lr: 1.86e-03
+2022-05-13 23:04:34,069 INFO [train.py:812] (0/8) Epoch 3, batch 2150, loss[loss=0.275, simple_loss=0.3344, pruned_loss=0.1078, over 7231.00 frames.], tot_loss[loss=0.246, simple_loss=0.315, pruned_loss=0.08851, over 1426807.72 frames.], batch size: 20, lr: 1.86e-03
+2022-05-13 23:05:32,772 INFO [train.py:812] (0/8) Epoch 3, batch 2200, loss[loss=0.2843, simple_loss=0.358, pruned_loss=0.1054, over 7153.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3156, pruned_loss=0.08881, over 1426286.21 frames.], batch size: 20, lr: 1.85e-03
+2022-05-13 23:06:32,202 INFO [train.py:812] (0/8) Epoch 3, batch 2250, loss[loss=0.2492, simple_loss=0.3223, pruned_loss=0.08801, over 7332.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3161, pruned_loss=0.08901, over 1425643.00 frames.], batch size: 20, lr: 1.85e-03
+2022-05-13 23:07:31,629 INFO [train.py:812] (0/8) Epoch 3, batch 2300, loss[loss=0.2201, simple_loss=0.2824, pruned_loss=0.07893, over 7360.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3159, pruned_loss=0.08944, over 1413083.61 frames.], batch size: 19, lr: 1.85e-03
+2022-05-13 23:08:31,272 INFO [train.py:812] (0/8) Epoch 3, batch 2350, loss[loss=0.2122, simple_loss=0.2874, pruned_loss=0.06849, over 7254.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3151, pruned_loss=0.08951, over 1414938.38 frames.], batch size: 19, lr: 1.84e-03
+2022-05-13 23:09:29,605 INFO [train.py:812] (0/8) Epoch 3, batch 2400, loss[loss=0.2543, simple_loss=0.3271, pruned_loss=0.09076, over 7259.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3156, pruned_loss=0.08929, over 1418679.69 frames.], batch size: 19, lr: 1.84e-03
+2022-05-13 23:10:29,174 INFO [train.py:812] (0/8) Epoch 3, batch 2450, loss[loss=0.2794, simple_loss=0.3368, pruned_loss=0.111, over 7237.00 frames.], tot_loss[loss=0.2488, simple_loss=0.3168, pruned_loss=0.09044, over 1415653.95 frames.], batch size: 20, lr: 1.84e-03
+2022-05-13 23:11:28,083 INFO [train.py:812] (0/8) Epoch 3, batch 2500, loss[loss=0.2439, simple_loss=0.3031, pruned_loss=0.09238, over 7166.00 frames.], tot_loss[loss=0.2464, simple_loss=0.3148, pruned_loss=0.08898, over 1414449.12 frames.], batch size: 19, lr: 1.83e-03
+2022-05-13 23:12:27,742 INFO [train.py:812] (0/8) Epoch 3, batch 2550, loss[loss=0.2378, simple_loss=0.3093, pruned_loss=0.08312, over 7209.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3132, pruned_loss=0.08806, over 1413051.18 frames.], batch size: 21, lr: 1.83e-03
+2022-05-13 23:13:27,067 INFO [train.py:812] (0/8) Epoch 3, batch 2600, loss[loss=0.2199, simple_loss=0.2863, pruned_loss=0.07678, over 7282.00 frames.], tot_loss[loss=0.2436, simple_loss=0.3123, pruned_loss=0.08745, over 1418828.31 frames.], batch size: 18, lr: 1.83e-03
+2022-05-13 23:14:26,418 INFO [train.py:812] (0/8) Epoch 3, batch 2650, loss[loss=0.2668, simple_loss=0.3252, pruned_loss=0.1043, over 7330.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3117, pruned_loss=0.0874, over 1418692.85 frames.], batch size: 20, lr: 1.82e-03
+2022-05-13 23:15:24,404 INFO [train.py:812] (0/8) Epoch 3, batch 2700, loss[loss=0.2554, simple_loss=0.3171, pruned_loss=0.09689, over 7071.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3135, pruned_loss=0.08793, over 1419898.21 frames.], batch size: 18, lr: 1.82e-03
+2022-05-13 23:16:24,001 INFO [train.py:812] (0/8) Epoch 3, batch 2750, loss[loss=0.2707, simple_loss=0.3482, pruned_loss=0.09663, over 7170.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3127, pruned_loss=0.08738, over 1418921.04 frames.], batch size: 26, lr: 1.82e-03
+2022-05-13 23:17:22,912 INFO [train.py:812] (0/8) Epoch 3, batch 2800, loss[loss=0.3382, simple_loss=0.3719, pruned_loss=0.1522, over 4582.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3125, pruned_loss=0.08721, over 1418367.30 frames.], batch size: 52, lr: 1.81e-03
+2022-05-13 23:17:50,682 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-12000.pt
+2022-05-13 23:18:30,780 INFO [train.py:812] (0/8) Epoch 3, batch 2850, loss[loss=0.2862, simple_loss=0.3578, pruned_loss=0.1073, over 7219.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3115, pruned_loss=0.08679, over 1420528.94 frames.], batch size: 21, lr: 1.81e-03
+2022-05-13 23:19:29,906 INFO [train.py:812] (0/8) Epoch 3, batch 2900, loss[loss=0.2396, simple_loss=0.305, pruned_loss=0.08711, over 6585.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3112, pruned_loss=0.08699, over 1418437.26 frames.], batch size: 38, lr: 1.81e-03
+2022-05-13 23:20:29,312 INFO [train.py:812] (0/8) Epoch 3, batch 2950, loss[loss=0.2726, simple_loss=0.3266, pruned_loss=0.1093, over 7104.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3116, pruned_loss=0.08698, over 1417658.93 frames.], batch size: 26, lr: 1.80e-03
+2022-05-13 23:21:28,541 INFO [train.py:812] (0/8) Epoch 3, batch 3000, loss[loss=0.2357, simple_loss=0.3117, pruned_loss=0.07987, over 7333.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3114, pruned_loss=0.08646, over 1420822.82 frames.], batch size: 22, lr: 1.80e-03
+2022-05-13 23:21:28,542 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-13 23:21:36,069 INFO [train.py:841] (0/8) Epoch 3, validation: loss=0.1862, simple_loss=0.2867, pruned_loss=0.04278, over 698248.00 frames.
+2022-05-13 23:22:33,847 INFO [train.py:812] (0/8) Epoch 3, batch 3050, loss[loss=0.2445, simple_loss=0.3286, pruned_loss=0.0802, over 7408.00 frames.], tot_loss[loss=0.2436, simple_loss=0.3129, pruned_loss=0.08713, over 1425582.97 frames.], batch size: 21, lr: 1.80e-03
+2022-05-13 23:23:30,796 INFO [train.py:812] (0/8) Epoch 3, batch 3100, loss[loss=0.264, simple_loss=0.3355, pruned_loss=0.09631, over 7271.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3119, pruned_loss=0.08632, over 1428270.58 frames.], batch size: 18, lr: 1.79e-03
+2022-05-13 23:24:30,032 INFO [train.py:812] (0/8) Epoch 3, batch 3150, loss[loss=0.2284, simple_loss=0.3189, pruned_loss=0.06892, over 7215.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3117, pruned_loss=0.08671, over 1422188.97 frames.], batch size: 21, lr: 1.79e-03
+2022-05-13 23:25:29,458 INFO [train.py:812] (0/8) Epoch 3, batch 3200, loss[loss=0.2411, simple_loss=0.3173, pruned_loss=0.08247, over 7385.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3126, pruned_loss=0.08682, over 1425202.49 frames.], batch size: 23, lr: 1.79e-03
+2022-05-13 23:26:29,124 INFO [train.py:812] (0/8) Epoch 3, batch 3250, loss[loss=0.2114, simple_loss=0.2896, pruned_loss=0.06658, over 7145.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3131, pruned_loss=0.08697, over 1426390.46 frames.], batch size: 19, lr: 1.79e-03
+2022-05-13 23:27:27,194 INFO [train.py:812] (0/8) Epoch 3, batch 3300, loss[loss=0.2357, simple_loss=0.3135, pruned_loss=0.07895, over 7237.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3114, pruned_loss=0.08584, over 1428836.49 frames.], batch size: 26, lr: 1.78e-03
+2022-05-13 23:28:26,184 INFO [train.py:812] (0/8) Epoch 3, batch 3350, loss[loss=0.2067, simple_loss=0.2862, pruned_loss=0.06355, over 7297.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3122, pruned_loss=0.08619, over 1425416.78 frames.], batch size: 18, lr: 1.78e-03
+2022-05-13 23:29:23,913 INFO [train.py:812] (0/8) Epoch 3, batch 3400, loss[loss=0.1702, simple_loss=0.2492, pruned_loss=0.0456, over 7430.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3127, pruned_loss=0.08639, over 1423627.02 frames.], batch size: 18, lr: 1.78e-03
+2022-05-13 23:30:22,220 INFO [train.py:812] (0/8) Epoch 3, batch 3450, loss[loss=0.2387, simple_loss=0.2972, pruned_loss=0.09007, over 7258.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3125, pruned_loss=0.08615, over 1420865.36 frames.], batch size: 19, lr: 1.77e-03
+2022-05-13 23:31:20,914 INFO [train.py:812] (0/8) Epoch 3, batch 3500, loss[loss=0.2562, simple_loss=0.317, pruned_loss=0.09772, over 7343.00 frames.], tot_loss[loss=0.2408, simple_loss=0.3113, pruned_loss=0.0851, over 1421651.24 frames.], batch size: 25, lr: 1.77e-03
+2022-05-13 23:32:20,544 INFO [train.py:812] (0/8) Epoch 3, batch 3550, loss[loss=0.2106, simple_loss=0.2877, pruned_loss=0.06673, over 7217.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3108, pruned_loss=0.08436, over 1420275.64 frames.], batch size: 21, lr: 1.77e-03
+2022-05-13 23:33:19,835 INFO [train.py:812] (0/8) Epoch 3, batch 3600, loss[loss=0.2273, simple_loss=0.3144, pruned_loss=0.07009, over 7285.00 frames.], tot_loss[loss=0.2403, simple_loss=0.3106, pruned_loss=0.08495, over 1421657.07 frames.], batch size: 24, lr: 1.76e-03
+2022-05-13 23:34:19,469 INFO [train.py:812] (0/8) Epoch 3, batch 3650, loss[loss=0.2368, simple_loss=0.3061, pruned_loss=0.08373, over 7383.00 frames.], tot_loss[loss=0.2396, simple_loss=0.3098, pruned_loss=0.08471, over 1421691.33 frames.], batch size: 23, lr: 1.76e-03
+2022-05-13 23:35:18,545 INFO [train.py:812] (0/8) Epoch 3, batch 3700, loss[loss=0.2262, simple_loss=0.2868, pruned_loss=0.08282, over 7398.00 frames.], tot_loss[loss=0.2387, simple_loss=0.3092, pruned_loss=0.08409, over 1417105.25 frames.], batch size: 18, lr: 1.76e-03
+2022-05-13 23:36:18,208 INFO [train.py:812] (0/8) Epoch 3, batch 3750, loss[loss=0.1936, simple_loss=0.2678, pruned_loss=0.05973, over 7273.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3089, pruned_loss=0.08339, over 1423283.58 frames.], batch size: 18, lr: 1.76e-03
+2022-05-13 23:37:16,802 INFO [train.py:812] (0/8) Epoch 3, batch 3800, loss[loss=0.2069, simple_loss=0.2847, pruned_loss=0.06451, over 7161.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3079, pruned_loss=0.08292, over 1423296.35 frames.], batch size: 18, lr: 1.75e-03
+2022-05-13 23:38:16,206 INFO [train.py:812] (0/8) Epoch 3, batch 3850, loss[loss=0.2057, simple_loss=0.2999, pruned_loss=0.05575, over 7325.00 frames.], tot_loss[loss=0.2366, simple_loss=0.308, pruned_loss=0.08256, over 1421513.96 frames.], batch size: 22, lr: 1.75e-03
+2022-05-13 23:39:15,479 INFO [train.py:812] (0/8) Epoch 3, batch 3900, loss[loss=0.2029, simple_loss=0.2767, pruned_loss=0.06457, over 7321.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3076, pruned_loss=0.08259, over 1423294.93 frames.], batch size: 20, lr: 1.75e-03
+2022-05-13 23:40:14,817 INFO [train.py:812] (0/8) Epoch 3, batch 3950, loss[loss=0.2214, simple_loss=0.2904, pruned_loss=0.07622, over 7320.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3074, pruned_loss=0.08256, over 1420332.38 frames.], batch size: 21, lr: 1.74e-03
+2022-05-13 23:41:13,967 INFO [train.py:812] (0/8) Epoch 3, batch 4000, loss[loss=0.2579, simple_loss=0.336, pruned_loss=0.08988, over 7329.00 frames.], tot_loss[loss=0.238, simple_loss=0.3089, pruned_loss=0.08352, over 1425248.68 frames.], batch size: 22, lr: 1.74e-03
+2022-05-13 23:42:13,683 INFO [train.py:812] (0/8) Epoch 3, batch 4050, loss[loss=0.2376, simple_loss=0.3084, pruned_loss=0.08343, over 7434.00 frames.], tot_loss[loss=0.2366, simple_loss=0.3077, pruned_loss=0.08273, over 1425537.04 frames.], batch size: 20, lr: 1.74e-03
+2022-05-13 23:43:12,855 INFO [train.py:812] (0/8) Epoch 3, batch 4100, loss[loss=0.1836, simple_loss=0.259, pruned_loss=0.05415, over 7081.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3089, pruned_loss=0.08411, over 1417394.85 frames.], batch size: 18, lr: 1.73e-03
+2022-05-13 23:44:12,533 INFO [train.py:812] (0/8) Epoch 3, batch 4150, loss[loss=0.2293, simple_loss=0.3077, pruned_loss=0.07547, over 7118.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3085, pruned_loss=0.08314, over 1421990.28 frames.], batch size: 21, lr: 1.73e-03
+2022-05-13 23:45:10,724 INFO [train.py:812] (0/8) Epoch 3, batch 4200, loss[loss=0.2797, simple_loss=0.3674, pruned_loss=0.09605, over 7112.00 frames.], tot_loss[loss=0.2373, simple_loss=0.3085, pruned_loss=0.08307, over 1420808.67 frames.], batch size: 28, lr: 1.73e-03
+2022-05-13 23:46:09,930 INFO [train.py:812] (0/8) Epoch 3, batch 4250, loss[loss=0.2584, simple_loss=0.3159, pruned_loss=0.1004, over 7216.00 frames.], tot_loss[loss=0.237, simple_loss=0.3084, pruned_loss=0.08279, over 1421069.74 frames.], batch size: 22, lr: 1.73e-03
+2022-05-13 23:47:09,138 INFO [train.py:812] (0/8) Epoch 3, batch 4300, loss[loss=0.2114, simple_loss=0.2909, pruned_loss=0.06595, over 7066.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3092, pruned_loss=0.08299, over 1423018.16 frames.], batch size: 18, lr: 1.72e-03
+2022-05-13 23:48:08,229 INFO [train.py:812] (0/8) Epoch 3, batch 4350, loss[loss=0.289, simple_loss=0.35, pruned_loss=0.114, over 7151.00 frames.], tot_loss[loss=0.2372, simple_loss=0.3086, pruned_loss=0.08285, over 1424399.23 frames.], batch size: 20, lr: 1.72e-03
+2022-05-13 23:49:06,726 INFO [train.py:812] (0/8) Epoch 3, batch 4400, loss[loss=0.2744, simple_loss=0.3427, pruned_loss=0.1031, over 7303.00 frames.], tot_loss[loss=0.237, simple_loss=0.3081, pruned_loss=0.08296, over 1419196.31 frames.], batch size: 25, lr: 1.72e-03
+2022-05-13 23:50:05,739 INFO [train.py:812] (0/8) Epoch 3, batch 4450, loss[loss=0.2322, simple_loss=0.3149, pruned_loss=0.07481, over 7338.00 frames.], tot_loss[loss=0.2394, simple_loss=0.3104, pruned_loss=0.08426, over 1412201.36 frames.], batch size: 22, lr: 1.71e-03
+2022-05-13 23:51:04,264 INFO [train.py:812] (0/8) Epoch 3, batch 4500, loss[loss=0.2225, simple_loss=0.3129, pruned_loss=0.06609, over 7116.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3112, pruned_loss=0.08418, over 1405838.51 frames.], batch size: 21, lr: 1.71e-03
+2022-05-13 23:52:01,831 INFO [train.py:812] (0/8) Epoch 3, batch 4550, loss[loss=0.2794, simple_loss=0.3476, pruned_loss=0.1056, over 6246.00 frames.], tot_loss[loss=0.2425, simple_loss=0.3134, pruned_loss=0.08586, over 1377435.41 frames.], batch size: 37, lr: 1.71e-03
+2022-05-13 23:52:46,429 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-3.pt
+2022-05-13 23:53:11,489 INFO [train.py:812] (0/8) Epoch 4, batch 0, loss[loss=0.2731, simple_loss=0.3412, pruned_loss=0.1025, over 7190.00 frames.], tot_loss[loss=0.2731, simple_loss=0.3412, pruned_loss=0.1025, over 7190.00 frames.], batch size: 23, lr: 1.66e-03
+2022-05-13 23:54:10,701 INFO [train.py:812] (0/8) Epoch 4, batch 50, loss[loss=0.1959, simple_loss=0.2617, pruned_loss=0.06506, over 7300.00 frames.], tot_loss[loss=0.2337, simple_loss=0.3058, pruned_loss=0.0808, over 317196.41 frames.], batch size: 17, lr: 1.66e-03
+2022-05-13 23:55:09,412 INFO [train.py:812] (0/8) Epoch 4, batch 100, loss[loss=0.1892, simple_loss=0.2633, pruned_loss=0.05754, over 7279.00 frames.], tot_loss[loss=0.2361, simple_loss=0.307, pruned_loss=0.0826, over 564328.15 frames.], batch size: 17, lr: 1.65e-03
+2022-05-13 23:56:09,412 INFO [train.py:812] (0/8) Epoch 4, batch 150, loss[loss=0.213, simple_loss=0.3045, pruned_loss=0.06074, over 7337.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3059, pruned_loss=0.08048, over 755205.07 frames.], batch size: 22, lr: 1.65e-03
+2022-05-13 23:57:08,455 INFO [train.py:812] (0/8) Epoch 4, batch 200, loss[loss=0.2848, simple_loss=0.3481, pruned_loss=0.1108, over 7210.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3072, pruned_loss=0.08096, over 903901.05 frames.], batch size: 23, lr: 1.65e-03
+2022-05-13 23:58:07,153 INFO [train.py:812] (0/8) Epoch 4, batch 250, loss[loss=0.1894, simple_loss=0.2842, pruned_loss=0.0473, over 7332.00 frames.], tot_loss[loss=0.2344, simple_loss=0.307, pruned_loss=0.08089, over 1015791.98 frames.], batch size: 22, lr: 1.64e-03
+2022-05-13 23:59:06,606 INFO [train.py:812] (0/8) Epoch 4, batch 300, loss[loss=0.247, simple_loss=0.3255, pruned_loss=0.08424, over 7386.00 frames.], tot_loss[loss=0.234, simple_loss=0.3066, pruned_loss=0.08069, over 1110407.77 frames.], batch size: 23, lr: 1.64e-03
+2022-05-14 00:00:06,131 INFO [train.py:812] (0/8) Epoch 4, batch 350, loss[loss=0.2148, simple_loss=0.2967, pruned_loss=0.06647, over 7316.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3053, pruned_loss=0.07924, over 1182298.99 frames.], batch size: 21, lr: 1.64e-03
+2022-05-14 00:01:05,122 INFO [train.py:812] (0/8) Epoch 4, batch 400, loss[loss=0.2532, simple_loss=0.3099, pruned_loss=0.09819, over 7240.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3046, pruned_loss=0.07899, over 1233662.27 frames.], batch size: 20, lr: 1.64e-03
+2022-05-14 00:02:04,519 INFO [train.py:812] (0/8) Epoch 4, batch 450, loss[loss=0.2346, simple_loss=0.3113, pruned_loss=0.07897, over 7135.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3046, pruned_loss=0.07929, over 1275559.81 frames.], batch size: 20, lr: 1.63e-03
+2022-05-14 00:03:03,237 INFO [train.py:812] (0/8) Epoch 4, batch 500, loss[loss=0.1978, simple_loss=0.2758, pruned_loss=0.05992, over 7154.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3059, pruned_loss=0.07994, over 1304620.24 frames.], batch size: 19, lr: 1.63e-03
+2022-05-14 00:04:02,751 INFO [train.py:812] (0/8) Epoch 4, batch 550, loss[loss=0.245, simple_loss=0.3219, pruned_loss=0.08403, over 7166.00 frames.], tot_loss[loss=0.2332, simple_loss=0.306, pruned_loss=0.0802, over 1329918.33 frames.], batch size: 18, lr: 1.63e-03
+2022-05-14 00:05:01,379 INFO [train.py:812] (0/8) Epoch 4, batch 600, loss[loss=0.2747, simple_loss=0.3347, pruned_loss=0.1074, over 6486.00 frames.], tot_loss[loss=0.2336, simple_loss=0.306, pruned_loss=0.08058, over 1347544.63 frames.], batch size: 38, lr: 1.63e-03
+2022-05-14 00:06:00,843 INFO [train.py:812] (0/8) Epoch 4, batch 650, loss[loss=0.2201, simple_loss=0.3095, pruned_loss=0.0654, over 7429.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3055, pruned_loss=0.08017, over 1367933.01 frames.], batch size: 20, lr: 1.62e-03
+2022-05-14 00:07:00,178 INFO [train.py:812] (0/8) Epoch 4, batch 700, loss[loss=0.219, simple_loss=0.2974, pruned_loss=0.07026, over 7246.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3037, pruned_loss=0.07896, over 1385365.45 frames.], batch size: 24, lr: 1.62e-03
+2022-05-14 00:07:59,214 INFO [train.py:812] (0/8) Epoch 4, batch 750, loss[loss=0.3088, simple_loss=0.3651, pruned_loss=0.1262, over 7297.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3036, pruned_loss=0.07904, over 1393015.03 frames.], batch size: 24, lr: 1.62e-03
+2022-05-14 00:08:58,536 INFO [train.py:812] (0/8) Epoch 4, batch 800, loss[loss=0.2081, simple_loss=0.2866, pruned_loss=0.06478, over 7256.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3049, pruned_loss=0.07992, over 1396748.02 frames.], batch size: 19, lr: 1.62e-03
+2022-05-14 00:09:58,467 INFO [train.py:812] (0/8) Epoch 4, batch 850, loss[loss=0.2159, simple_loss=0.2878, pruned_loss=0.07196, over 7070.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3051, pruned_loss=0.07983, over 1407212.07 frames.], batch size: 18, lr: 1.61e-03
+2022-05-14 00:10:57,804 INFO [train.py:812] (0/8) Epoch 4, batch 900, loss[loss=0.2062, simple_loss=0.2952, pruned_loss=0.05862, over 7112.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3046, pruned_loss=0.07954, over 1414624.73 frames.], batch size: 21, lr: 1.61e-03
+2022-05-14 00:11:56,771 INFO [train.py:812] (0/8) Epoch 4, batch 950, loss[loss=0.2804, simple_loss=0.3448, pruned_loss=0.1079, over 7142.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3047, pruned_loss=0.07997, over 1420082.76 frames.], batch size: 26, lr: 1.61e-03
+2022-05-14 00:12:55,426 INFO [train.py:812] (0/8) Epoch 4, batch 1000, loss[loss=0.2506, simple_loss=0.3215, pruned_loss=0.08981, over 7270.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3041, pruned_loss=0.07948, over 1420113.08 frames.], batch size: 18, lr: 1.61e-03
+2022-05-14 00:13:54,499 INFO [train.py:812] (0/8) Epoch 4, batch 1050, loss[loss=0.2517, simple_loss=0.3234, pruned_loss=0.08999, over 6764.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3046, pruned_loss=0.07941, over 1418697.78 frames.], batch size: 31, lr: 1.60e-03
+2022-05-14 00:14:53,491 INFO [train.py:812] (0/8) Epoch 4, batch 1100, loss[loss=0.2317, simple_loss=0.317, pruned_loss=0.07323, over 7413.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3038, pruned_loss=0.07874, over 1420146.94 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:15:52,716 INFO [train.py:812] (0/8) Epoch 4, batch 1150, loss[loss=0.3189, simple_loss=0.3748, pruned_loss=0.1316, over 7323.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3058, pruned_loss=0.07969, over 1417986.17 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:16:51,455 INFO [train.py:812] (0/8) Epoch 4, batch 1200, loss[loss=0.2363, simple_loss=0.3148, pruned_loss=0.0789, over 7316.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3066, pruned_loss=0.08024, over 1416233.50 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:17:50,407 INFO [train.py:812] (0/8) Epoch 4, batch 1250, loss[loss=0.2097, simple_loss=0.2692, pruned_loss=0.07507, over 7230.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3062, pruned_loss=0.08029, over 1414594.47 frames.], batch size: 16, lr: 1.59e-03
+2022-05-14 00:18:48,735 INFO [train.py:812] (0/8) Epoch 4, batch 1300, loss[loss=0.2315, simple_loss=0.3149, pruned_loss=0.074, over 7217.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3052, pruned_loss=0.08005, over 1417609.81 frames.], batch size: 23, lr: 1.59e-03
+2022-05-14 00:19:47,562 INFO [train.py:812] (0/8) Epoch 4, batch 1350, loss[loss=0.2086, simple_loss=0.3029, pruned_loss=0.05721, over 7232.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3053, pruned_loss=0.07973, over 1416748.33 frames.], batch size: 20, lr: 1.59e-03
+2022-05-14 00:20:44,851 INFO [train.py:812] (0/8) Epoch 4, batch 1400, loss[loss=0.2358, simple_loss=0.3127, pruned_loss=0.0795, over 7214.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3039, pruned_loss=0.07933, over 1419424.67 frames.], batch size: 22, lr: 1.59e-03
+2022-05-14 00:21:44,655 INFO [train.py:812] (0/8) Epoch 4, batch 1450, loss[loss=0.2183, simple_loss=0.3157, pruned_loss=0.06051, over 7289.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3062, pruned_loss=0.08001, over 1421665.18 frames.], batch size: 24, lr: 1.59e-03
+2022-05-14 00:22:43,710 INFO [train.py:812] (0/8) Epoch 4, batch 1500, loss[loss=0.1984, simple_loss=0.2797, pruned_loss=0.05856, over 7294.00 frames.], tot_loss[loss=0.232, simple_loss=0.3053, pruned_loss=0.07937, over 1419716.46 frames.], batch size: 24, lr: 1.58e-03
+2022-05-14 00:23:43,518 INFO [train.py:812] (0/8) Epoch 4, batch 1550, loss[loss=0.2894, simple_loss=0.3377, pruned_loss=0.1205, over 5032.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3055, pruned_loss=0.07978, over 1418378.13 frames.], batch size: 52, lr: 1.58e-03
+2022-05-14 00:24:41,303 INFO [train.py:812] (0/8) Epoch 4, batch 1600, loss[loss=0.2129, simple_loss=0.3038, pruned_loss=0.06105, over 7280.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3055, pruned_loss=0.07934, over 1415463.74 frames.], batch size: 25, lr: 1.58e-03
+2022-05-14 00:25:40,747 INFO [train.py:812] (0/8) Epoch 4, batch 1650, loss[loss=0.2471, simple_loss=0.3172, pruned_loss=0.08847, over 7332.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3041, pruned_loss=0.07902, over 1416308.61 frames.], batch size: 20, lr: 1.58e-03
+2022-05-14 00:26:39,536 INFO [train.py:812] (0/8) Epoch 4, batch 1700, loss[loss=0.2509, simple_loss=0.3269, pruned_loss=0.08751, over 7151.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3042, pruned_loss=0.07883, over 1419923.54 frames.], batch size: 20, lr: 1.57e-03
+2022-05-14 00:27:38,788 INFO [train.py:812] (0/8) Epoch 4, batch 1750, loss[loss=0.2264, simple_loss=0.3029, pruned_loss=0.07491, over 7213.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3044, pruned_loss=0.07871, over 1419599.45 frames.], batch size: 22, lr: 1.57e-03
+2022-05-14 00:28:45,598 INFO [train.py:812] (0/8) Epoch 4, batch 1800, loss[loss=0.238, simple_loss=0.3204, pruned_loss=0.07779, over 7222.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3054, pruned_loss=0.079, over 1421875.53 frames.], batch size: 21, lr: 1.57e-03
+2022-05-14 00:29:45,226 INFO [train.py:812] (0/8) Epoch 4, batch 1850, loss[loss=0.2052, simple_loss=0.2788, pruned_loss=0.06576, over 7117.00 frames.], tot_loss[loss=0.2301, simple_loss=0.3045, pruned_loss=0.07781, over 1420862.07 frames.], batch size: 17, lr: 1.57e-03
+2022-05-14 00:30:44,401 INFO [train.py:812] (0/8) Epoch 4, batch 1900, loss[loss=0.2106, simple_loss=0.2911, pruned_loss=0.06503, over 7158.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3041, pruned_loss=0.07774, over 1423719.97 frames.], batch size: 19, lr: 1.56e-03
+2022-05-14 00:31:43,805 INFO [train.py:812] (0/8) Epoch 4, batch 1950, loss[loss=0.308, simple_loss=0.3537, pruned_loss=0.1311, over 6431.00 frames.], tot_loss[loss=0.2301, simple_loss=0.3043, pruned_loss=0.07792, over 1428599.79 frames.], batch size: 38, lr: 1.56e-03
+2022-05-14 00:32:40,434 INFO [train.py:812] (0/8) Epoch 4, batch 2000, loss[loss=0.2318, simple_loss=0.3092, pruned_loss=0.07717, over 7115.00 frames.], tot_loss[loss=0.2308, simple_loss=0.305, pruned_loss=0.07829, over 1425955.91 frames.], batch size: 21, lr: 1.56e-03
+2022-05-14 00:34:15,595 INFO [train.py:812] (0/8) Epoch 4, batch 2050, loss[loss=0.2515, simple_loss=0.3273, pruned_loss=0.08787, over 6777.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3056, pruned_loss=0.079, over 1422042.54 frames.], batch size: 31, lr: 1.56e-03
+2022-05-14 00:35:41,886 INFO [train.py:812] (0/8) Epoch 4, batch 2100, loss[loss=0.192, simple_loss=0.2754, pruned_loss=0.05431, over 7322.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3043, pruned_loss=0.07822, over 1420198.03 frames.], batch size: 21, lr: 1.56e-03
+2022-05-14 00:36:41,410 INFO [train.py:812] (0/8) Epoch 4, batch 2150, loss[loss=0.2479, simple_loss=0.3209, pruned_loss=0.08745, over 7327.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3033, pruned_loss=0.0776, over 1422683.28 frames.], batch size: 22, lr: 1.55e-03
+2022-05-14 00:37:40,372 INFO [train.py:812] (0/8) Epoch 4, batch 2200, loss[loss=0.2525, simple_loss=0.3336, pruned_loss=0.08571, over 7212.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3031, pruned_loss=0.07749, over 1425350.73 frames.], batch size: 21, lr: 1.55e-03
+2022-05-14 00:38:22,037 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-16000.pt
+2022-05-14 00:38:47,650 INFO [train.py:812] (0/8) Epoch 4, batch 2250, loss[loss=0.3386, simple_loss=0.367, pruned_loss=0.1551, over 4997.00 frames.], tot_loss[loss=0.2298, simple_loss=0.304, pruned_loss=0.07782, over 1426768.16 frames.], batch size: 52, lr: 1.55e-03
+2022-05-14 00:39:45,550 INFO [train.py:812] (0/8) Epoch 4, batch 2300, loss[loss=0.2434, simple_loss=0.3135, pruned_loss=0.08662, over 7147.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3034, pruned_loss=0.07748, over 1429779.60 frames.], batch size: 19, lr: 1.55e-03
+2022-05-14 00:40:45,375 INFO [train.py:812] (0/8) Epoch 4, batch 2350, loss[loss=0.2182, simple_loss=0.2918, pruned_loss=0.07228, over 7328.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3023, pruned_loss=0.07651, over 1430843.98 frames.], batch size: 20, lr: 1.54e-03
+2022-05-14 00:41:44,134 INFO [train.py:812] (0/8) Epoch 4, batch 2400, loss[loss=0.2748, simple_loss=0.3493, pruned_loss=0.1002, over 7242.00 frames.], tot_loss[loss=0.2287, simple_loss=0.3037, pruned_loss=0.07684, over 1433170.35 frames.], batch size: 25, lr: 1.54e-03
+2022-05-14 00:42:43,279 INFO [train.py:812] (0/8) Epoch 4, batch 2450, loss[loss=0.2225, simple_loss=0.3043, pruned_loss=0.07038, over 7382.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3048, pruned_loss=0.07741, over 1436045.97 frames.], batch size: 23, lr: 1.54e-03
+2022-05-14 00:43:42,442 INFO [train.py:812] (0/8) Epoch 4, batch 2500, loss[loss=0.2251, simple_loss=0.2932, pruned_loss=0.07849, over 7144.00 frames.], tot_loss[loss=0.2289, simple_loss=0.304, pruned_loss=0.07692, over 1433981.31 frames.], batch size: 19, lr: 1.54e-03
+2022-05-14 00:44:40,447 INFO [train.py:812] (0/8) Epoch 4, batch 2550, loss[loss=0.1922, simple_loss=0.2702, pruned_loss=0.05709, over 7406.00 frames.], tot_loss[loss=0.2295, simple_loss=0.304, pruned_loss=0.0775, over 1426440.40 frames.], batch size: 18, lr: 1.54e-03
+2022-05-14 00:45:38,436 INFO [train.py:812] (0/8) Epoch 4, batch 2600, loss[loss=0.2248, simple_loss=0.3048, pruned_loss=0.07242, over 7237.00 frames.], tot_loss[loss=0.231, simple_loss=0.3053, pruned_loss=0.07835, over 1425893.66 frames.], batch size: 20, lr: 1.53e-03
+2022-05-14 00:46:37,776 INFO [train.py:812] (0/8) Epoch 4, batch 2650, loss[loss=0.1666, simple_loss=0.2378, pruned_loss=0.04769, over 6973.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3055, pruned_loss=0.07843, over 1419358.80 frames.], batch size: 16, lr: 1.53e-03
+2022-05-14 00:47:36,825 INFO [train.py:812] (0/8) Epoch 4, batch 2700, loss[loss=0.1775, simple_loss=0.2578, pruned_loss=0.04857, over 7206.00 frames.], tot_loss[loss=0.231, simple_loss=0.3052, pruned_loss=0.07846, over 1418121.41 frames.], batch size: 16, lr: 1.53e-03
+2022-05-14 00:48:35,474 INFO [train.py:812] (0/8) Epoch 4, batch 2750, loss[loss=0.2298, simple_loss=0.3006, pruned_loss=0.07951, over 7248.00 frames.], tot_loss[loss=0.2304, simple_loss=0.305, pruned_loss=0.07793, over 1421584.57 frames.], batch size: 19, lr: 1.53e-03
+2022-05-14 00:49:34,108 INFO [train.py:812] (0/8) Epoch 4, batch 2800, loss[loss=0.2012, simple_loss=0.2782, pruned_loss=0.06213, over 7157.00 frames.], tot_loss[loss=0.229, simple_loss=0.304, pruned_loss=0.07701, over 1424365.01 frames.], batch size: 19, lr: 1.53e-03
+2022-05-14 00:50:32,976 INFO [train.py:812] (0/8) Epoch 4, batch 2850, loss[loss=0.3031, simple_loss=0.3566, pruned_loss=0.1248, over 5264.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3034, pruned_loss=0.07735, over 1424015.61 frames.], batch size: 54, lr: 1.52e-03
+2022-05-14 00:51:31,211 INFO [train.py:812] (0/8) Epoch 4, batch 2900, loss[loss=0.2299, simple_loss=0.3131, pruned_loss=0.07338, over 6761.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3039, pruned_loss=0.07741, over 1424230.61 frames.], batch size: 31, lr: 1.52e-03
+2022-05-14 00:52:31,097 INFO [train.py:812] (0/8) Epoch 4, batch 2950, loss[loss=0.2242, simple_loss=0.3061, pruned_loss=0.07115, over 7158.00 frames.], tot_loss[loss=0.2287, simple_loss=0.3031, pruned_loss=0.07717, over 1428571.29 frames.], batch size: 28, lr: 1.52e-03
+2022-05-14 00:53:30,060 INFO [train.py:812] (0/8) Epoch 4, batch 3000, loss[loss=0.2436, simple_loss=0.3178, pruned_loss=0.08469, over 7154.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3033, pruned_loss=0.07682, over 1426256.56 frames.], batch size: 20, lr: 1.52e-03
+2022-05-14 00:53:30,061 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 00:53:37,753 INFO [train.py:841] (0/8) Epoch 4, validation: loss=0.1771, simple_loss=0.279, pruned_loss=0.03761, over 698248.00 frames.
+2022-05-14 00:54:36,389 INFO [train.py:812] (0/8) Epoch 4, batch 3050, loss[loss=0.2446, simple_loss=0.3164, pruned_loss=0.08637, over 7112.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3032, pruned_loss=0.077, over 1421133.75 frames.], batch size: 21, lr: 1.51e-03
+2022-05-14 00:55:35,281 INFO [train.py:812] (0/8) Epoch 4, batch 3100, loss[loss=0.2349, simple_loss=0.3125, pruned_loss=0.07865, over 7275.00 frames.], tot_loss[loss=0.2287, simple_loss=0.3029, pruned_loss=0.07727, over 1417441.33 frames.], batch size: 24, lr: 1.51e-03
+2022-05-14 00:56:35,141 INFO [train.py:812] (0/8) Epoch 4, batch 3150, loss[loss=0.2419, simple_loss=0.3198, pruned_loss=0.08203, over 7275.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3018, pruned_loss=0.07634, over 1422454.04 frames.], batch size: 25, lr: 1.51e-03
+2022-05-14 00:57:33,590 INFO [train.py:812] (0/8) Epoch 4, batch 3200, loss[loss=0.209, simple_loss=0.2836, pruned_loss=0.06724, over 7058.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3012, pruned_loss=0.07577, over 1423024.03 frames.], batch size: 18, lr: 1.51e-03
+2022-05-14 00:58:32,695 INFO [train.py:812] (0/8) Epoch 4, batch 3250, loss[loss=0.1903, simple_loss=0.2664, pruned_loss=0.05706, over 7251.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3009, pruned_loss=0.07571, over 1423880.75 frames.], batch size: 19, lr: 1.51e-03
+2022-05-14 00:59:30,517 INFO [train.py:812] (0/8) Epoch 4, batch 3300, loss[loss=0.2926, simple_loss=0.3449, pruned_loss=0.1201, over 7177.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3014, pruned_loss=0.07539, over 1421959.82 frames.], batch size: 23, lr: 1.50e-03
+2022-05-14 01:00:29,644 INFO [train.py:812] (0/8) Epoch 4, batch 3350, loss[loss=0.2852, simple_loss=0.3538, pruned_loss=0.1084, over 6248.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3005, pruned_loss=0.07483, over 1419691.77 frames.], batch size: 37, lr: 1.50e-03
+2022-05-14 01:01:28,330 INFO [train.py:812] (0/8) Epoch 4, batch 3400, loss[loss=0.1782, simple_loss=0.2518, pruned_loss=0.05229, over 7016.00 frames.], tot_loss[loss=0.2244, simple_loss=0.2995, pruned_loss=0.07465, over 1420418.01 frames.], batch size: 16, lr: 1.50e-03
+2022-05-14 01:02:28,060 INFO [train.py:812] (0/8) Epoch 4, batch 3450, loss[loss=0.179, simple_loss=0.2566, pruned_loss=0.05068, over 7167.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2983, pruned_loss=0.07353, over 1425634.72 frames.], batch size: 18, lr: 1.50e-03
+2022-05-14 01:03:26,381 INFO [train.py:812] (0/8) Epoch 4, batch 3500, loss[loss=0.2153, simple_loss=0.2863, pruned_loss=0.07216, over 7366.00 frames.], tot_loss[loss=0.223, simple_loss=0.2981, pruned_loss=0.07392, over 1427263.56 frames.], batch size: 23, lr: 1.50e-03
+2022-05-14 01:04:26,017 INFO [train.py:812] (0/8) Epoch 4, batch 3550, loss[loss=0.2585, simple_loss=0.3236, pruned_loss=0.09674, over 7288.00 frames.], tot_loss[loss=0.2223, simple_loss=0.2971, pruned_loss=0.07374, over 1427782.35 frames.], batch size: 24, lr: 1.49e-03
+2022-05-14 01:05:25,242 INFO [train.py:812] (0/8) Epoch 4, batch 3600, loss[loss=0.2027, simple_loss=0.268, pruned_loss=0.06876, over 7006.00 frames.], tot_loss[loss=0.2239, simple_loss=0.2986, pruned_loss=0.07459, over 1426524.48 frames.], batch size: 16, lr: 1.49e-03
+2022-05-14 01:06:24,741 INFO [train.py:812] (0/8) Epoch 4, batch 3650, loss[loss=0.2303, simple_loss=0.295, pruned_loss=0.08281, over 7142.00 frames.], tot_loss[loss=0.2245, simple_loss=0.2996, pruned_loss=0.07472, over 1426906.47 frames.], batch size: 17, lr: 1.49e-03
+2022-05-14 01:07:24,227 INFO [train.py:812] (0/8) Epoch 4, batch 3700, loss[loss=0.175, simple_loss=0.2484, pruned_loss=0.0508, over 7007.00 frames.], tot_loss[loss=0.2243, simple_loss=0.299, pruned_loss=0.07479, over 1426165.43 frames.], batch size: 16, lr: 1.49e-03
+2022-05-14 01:08:24,375 INFO [train.py:812] (0/8) Epoch 4, batch 3750, loss[loss=0.2075, simple_loss=0.2903, pruned_loss=0.06237, over 7429.00 frames.], tot_loss[loss=0.2224, simple_loss=0.297, pruned_loss=0.07387, over 1425011.67 frames.], batch size: 20, lr: 1.49e-03
+2022-05-14 01:09:22,839 INFO [train.py:812] (0/8) Epoch 4, batch 3800, loss[loss=0.1861, simple_loss=0.2664, pruned_loss=0.05287, over 7066.00 frames.], tot_loss[loss=0.2233, simple_loss=0.298, pruned_loss=0.0743, over 1421130.81 frames.], batch size: 18, lr: 1.48e-03
+2022-05-14 01:10:22,682 INFO [train.py:812] (0/8) Epoch 4, batch 3850, loss[loss=0.2378, simple_loss=0.3033, pruned_loss=0.08619, over 7408.00 frames.], tot_loss[loss=0.2235, simple_loss=0.2983, pruned_loss=0.07436, over 1425275.55 frames.], batch size: 18, lr: 1.48e-03
+2022-05-14 01:11:21,434 INFO [train.py:812] (0/8) Epoch 4, batch 3900, loss[loss=0.2974, simple_loss=0.356, pruned_loss=0.1194, over 4955.00 frames.], tot_loss[loss=0.2232, simple_loss=0.2985, pruned_loss=0.07399, over 1426044.47 frames.], batch size: 52, lr: 1.48e-03
+2022-05-14 01:12:20,482 INFO [train.py:812] (0/8) Epoch 4, batch 3950, loss[loss=0.1994, simple_loss=0.2626, pruned_loss=0.06807, over 7241.00 frames.], tot_loss[loss=0.2237, simple_loss=0.2984, pruned_loss=0.07449, over 1424831.02 frames.], batch size: 16, lr: 1.48e-03
+2022-05-14 01:13:19,410 INFO [train.py:812] (0/8) Epoch 4, batch 4000, loss[loss=0.2172, simple_loss=0.2955, pruned_loss=0.06946, over 7226.00 frames.], tot_loss[loss=0.2237, simple_loss=0.2985, pruned_loss=0.07446, over 1417686.31 frames.], batch size: 21, lr: 1.48e-03
+2022-05-14 01:14:18,985 INFO [train.py:812] (0/8) Epoch 4, batch 4050, loss[loss=0.2474, simple_loss=0.3242, pruned_loss=0.08531, over 7418.00 frames.], tot_loss[loss=0.2241, simple_loss=0.2989, pruned_loss=0.07461, over 1419727.17 frames.], batch size: 21, lr: 1.47e-03
+2022-05-14 01:15:18,306 INFO [train.py:812] (0/8) Epoch 4, batch 4100, loss[loss=0.2325, simple_loss=0.3053, pruned_loss=0.07981, over 6388.00 frames.], tot_loss[loss=0.225, simple_loss=0.3, pruned_loss=0.07497, over 1421399.10 frames.], batch size: 38, lr: 1.47e-03
+2022-05-14 01:16:17,161 INFO [train.py:812] (0/8) Epoch 4, batch 4150, loss[loss=0.1631, simple_loss=0.2435, pruned_loss=0.04133, over 7001.00 frames.], tot_loss[loss=0.2242, simple_loss=0.299, pruned_loss=0.07477, over 1423213.01 frames.], batch size: 16, lr: 1.47e-03
+2022-05-14 01:17:15,918 INFO [train.py:812] (0/8) Epoch 4, batch 4200, loss[loss=0.2203, simple_loss=0.3, pruned_loss=0.07028, over 7160.00 frames.], tot_loss[loss=0.2244, simple_loss=0.299, pruned_loss=0.07488, over 1422072.00 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:18:15,833 INFO [train.py:812] (0/8) Epoch 4, batch 4250, loss[loss=0.1975, simple_loss=0.2758, pruned_loss=0.05962, over 7359.00 frames.], tot_loss[loss=0.2234, simple_loss=0.298, pruned_loss=0.07443, over 1414770.53 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:19:14,761 INFO [train.py:812] (0/8) Epoch 4, batch 4300, loss[loss=0.1963, simple_loss=0.2742, pruned_loss=0.05921, over 7363.00 frames.], tot_loss[loss=0.2231, simple_loss=0.297, pruned_loss=0.07458, over 1413389.27 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:20:14,299 INFO [train.py:812] (0/8) Epoch 4, batch 4350, loss[loss=0.2253, simple_loss=0.3047, pruned_loss=0.07293, over 6392.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2963, pruned_loss=0.07453, over 1410823.52 frames.], batch size: 37, lr: 1.46e-03
+2022-05-14 01:21:13,824 INFO [train.py:812] (0/8) Epoch 4, batch 4400, loss[loss=0.2071, simple_loss=0.2758, pruned_loss=0.06921, over 7069.00 frames.], tot_loss[loss=0.2218, simple_loss=0.2953, pruned_loss=0.07412, over 1409828.20 frames.], batch size: 18, lr: 1.46e-03
+2022-05-14 01:22:13,437 INFO [train.py:812] (0/8) Epoch 4, batch 4450, loss[loss=0.2097, simple_loss=0.2864, pruned_loss=0.06649, over 7357.00 frames.], tot_loss[loss=0.2223, simple_loss=0.2956, pruned_loss=0.07453, over 1400682.89 frames.], batch size: 23, lr: 1.46e-03
+2022-05-14 01:23:11,877 INFO [train.py:812] (0/8) Epoch 4, batch 4500, loss[loss=0.2191, simple_loss=0.2942, pruned_loss=0.07202, over 6380.00 frames.], tot_loss[loss=0.2228, simple_loss=0.2964, pruned_loss=0.07457, over 1395209.88 frames.], batch size: 37, lr: 1.46e-03
+2022-05-14 01:24:10,624 INFO [train.py:812] (0/8) Epoch 4, batch 4550, loss[loss=0.2339, simple_loss=0.3027, pruned_loss=0.08248, over 5216.00 frames.], tot_loss[loss=0.226, simple_loss=0.299, pruned_loss=0.07647, over 1361290.03 frames.], batch size: 52, lr: 1.46e-03
+2022-05-14 01:24:54,427 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-4.pt
+2022-05-14 01:25:17,969 INFO [train.py:812] (0/8) Epoch 5, batch 0, loss[loss=0.2484, simple_loss=0.3247, pruned_loss=0.0861, over 7200.00 frames.], tot_loss[loss=0.2484, simple_loss=0.3247, pruned_loss=0.0861, over 7200.00 frames.], batch size: 23, lr: 1.40e-03
+2022-05-14 01:26:16,023 INFO [train.py:812] (0/8) Epoch 5, batch 50, loss[loss=0.2358, simple_loss=0.3205, pruned_loss=0.07553, over 7337.00 frames.], tot_loss[loss=0.2221, simple_loss=0.2968, pruned_loss=0.07367, over 320386.75 frames.], batch size: 22, lr: 1.40e-03
+2022-05-14 01:27:13,779 INFO [train.py:812] (0/8) Epoch 5, batch 100, loss[loss=0.2229, simple_loss=0.3074, pruned_loss=0.06924, over 7325.00 frames.], tot_loss[loss=0.2224, simple_loss=0.2981, pruned_loss=0.07337, over 566165.30 frames.], batch size: 22, lr: 1.40e-03
+2022-05-14 01:28:13,021 INFO [train.py:812] (0/8) Epoch 5, batch 150, loss[loss=0.2852, simple_loss=0.3376, pruned_loss=0.1164, over 5449.00 frames.], tot_loss[loss=0.2224, simple_loss=0.2989, pruned_loss=0.07302, over 755937.25 frames.], batch size: 52, lr: 1.40e-03
+2022-05-14 01:29:12,390 INFO [train.py:812] (0/8) Epoch 5, batch 200, loss[loss=0.2564, simple_loss=0.3214, pruned_loss=0.09568, over 7165.00 frames.], tot_loss[loss=0.2234, simple_loss=0.2993, pruned_loss=0.07375, over 903921.48 frames.], batch size: 19, lr: 1.40e-03
+2022-05-14 01:30:11,967 INFO [train.py:812] (0/8) Epoch 5, batch 250, loss[loss=0.2395, simple_loss=0.3036, pruned_loss=0.08768, over 7325.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3013, pruned_loss=0.07411, over 1021748.35 frames.], batch size: 22, lr: 1.39e-03
+2022-05-14 01:31:10,411 INFO [train.py:812] (0/8) Epoch 5, batch 300, loss[loss=0.2106, simple_loss=0.28, pruned_loss=0.07057, over 7264.00 frames.], tot_loss[loss=0.222, simple_loss=0.2982, pruned_loss=0.07286, over 1113876.38 frames.], batch size: 17, lr: 1.39e-03
+2022-05-14 01:32:09,315 INFO [train.py:812] (0/8) Epoch 5, batch 350, loss[loss=0.2088, simple_loss=0.2901, pruned_loss=0.06371, over 7165.00 frames.], tot_loss[loss=0.2209, simple_loss=0.2971, pruned_loss=0.07241, over 1181043.06 frames.], batch size: 19, lr: 1.39e-03
+2022-05-14 01:33:06,926 INFO [train.py:812] (0/8) Epoch 5, batch 400, loss[loss=0.2157, simple_loss=0.2997, pruned_loss=0.06586, over 7058.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2964, pruned_loss=0.07235, over 1232315.34 frames.], batch size: 28, lr: 1.39e-03
+2022-05-14 01:34:05,731 INFO [train.py:812] (0/8) Epoch 5, batch 450, loss[loss=0.2433, simple_loss=0.3117, pruned_loss=0.08748, over 7102.00 frames.], tot_loss[loss=0.2203, simple_loss=0.2961, pruned_loss=0.07224, over 1274555.24 frames.], batch size: 28, lr: 1.39e-03
+2022-05-14 01:35:05,165 INFO [train.py:812] (0/8) Epoch 5, batch 500, loss[loss=0.2091, simple_loss=0.2939, pruned_loss=0.06213, over 7319.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2946, pruned_loss=0.07117, over 1310791.41 frames.], batch size: 21, lr: 1.39e-03
+2022-05-14 01:36:04,761 INFO [train.py:812] (0/8) Epoch 5, batch 550, loss[loss=0.2387, simple_loss=0.3096, pruned_loss=0.08389, over 6746.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2944, pruned_loss=0.07116, over 1335237.37 frames.], batch size: 31, lr: 1.38e-03
+2022-05-14 01:37:04,158 INFO [train.py:812] (0/8) Epoch 5, batch 600, loss[loss=0.2144, simple_loss=0.273, pruned_loss=0.07786, over 6992.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2944, pruned_loss=0.07152, over 1356798.70 frames.], batch size: 16, lr: 1.38e-03
+2022-05-14 01:38:03,178 INFO [train.py:812] (0/8) Epoch 5, batch 650, loss[loss=0.2048, simple_loss=0.2829, pruned_loss=0.06333, over 7333.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2935, pruned_loss=0.07062, over 1371524.91 frames.], batch size: 20, lr: 1.38e-03
+2022-05-14 01:39:02,105 INFO [train.py:812] (0/8) Epoch 5, batch 700, loss[loss=0.2391, simple_loss=0.3263, pruned_loss=0.07599, over 7300.00 frames.], tot_loss[loss=0.2191, simple_loss=0.2953, pruned_loss=0.0714, over 1380659.80 frames.], batch size: 25, lr: 1.38e-03
+2022-05-14 01:40:01,975 INFO [train.py:812] (0/8) Epoch 5, batch 750, loss[loss=0.2215, simple_loss=0.2887, pruned_loss=0.07717, over 7063.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2946, pruned_loss=0.07144, over 1384841.80 frames.], batch size: 18, lr: 1.38e-03
+2022-05-14 01:40:59,753 INFO [train.py:812] (0/8) Epoch 5, batch 800, loss[loss=0.205, simple_loss=0.2827, pruned_loss=0.06358, over 7062.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2937, pruned_loss=0.07129, over 1396885.73 frames.], batch size: 18, lr: 1.38e-03
+2022-05-14 01:41:57,351 INFO [train.py:812] (0/8) Epoch 5, batch 850, loss[loss=0.1837, simple_loss=0.267, pruned_loss=0.05025, over 7064.00 frames.], tot_loss[loss=0.218, simple_loss=0.2937, pruned_loss=0.07114, over 1394627.83 frames.], batch size: 18, lr: 1.37e-03
+2022-05-14 01:42:55,836 INFO [train.py:812] (0/8) Epoch 5, batch 900, loss[loss=0.2506, simple_loss=0.3198, pruned_loss=0.09073, over 7322.00 frames.], tot_loss[loss=0.217, simple_loss=0.2933, pruned_loss=0.07039, over 1401747.92 frames.], batch size: 21, lr: 1.37e-03
+2022-05-14 01:43:53,347 INFO [train.py:812] (0/8) Epoch 5, batch 950, loss[loss=0.2322, simple_loss=0.314, pruned_loss=0.07521, over 7109.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2947, pruned_loss=0.07117, over 1405407.12 frames.], batch size: 28, lr: 1.37e-03
+2022-05-14 01:44:52,094 INFO [train.py:812] (0/8) Epoch 5, batch 1000, loss[loss=0.1909, simple_loss=0.2743, pruned_loss=0.05371, over 7075.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2937, pruned_loss=0.07062, over 1411386.54 frames.], batch size: 18, lr: 1.37e-03
+2022-05-14 01:45:49,417 INFO [train.py:812] (0/8) Epoch 5, batch 1050, loss[loss=0.2623, simple_loss=0.3391, pruned_loss=0.09277, over 7302.00 frames.], tot_loss[loss=0.2176, simple_loss=0.294, pruned_loss=0.07058, over 1416671.39 frames.], batch size: 24, lr: 1.37e-03
+2022-05-14 01:46:47,403 INFO [train.py:812] (0/8) Epoch 5, batch 1100, loss[loss=0.2235, simple_loss=0.2963, pruned_loss=0.07536, over 6404.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2955, pruned_loss=0.07153, over 1412998.89 frames.], batch size: 38, lr: 1.37e-03
+2022-05-14 01:47:47,035 INFO [train.py:812] (0/8) Epoch 5, batch 1150, loss[loss=0.2438, simple_loss=0.3147, pruned_loss=0.08651, over 7425.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2956, pruned_loss=0.07107, over 1415449.79 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:48:45,947 INFO [train.py:812] (0/8) Epoch 5, batch 1200, loss[loss=0.2283, simple_loss=0.3074, pruned_loss=0.07455, over 6446.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2941, pruned_loss=0.07022, over 1417549.14 frames.], batch size: 38, lr: 1.36e-03
+2022-05-14 01:49:45,510 INFO [train.py:812] (0/8) Epoch 5, batch 1250, loss[loss=0.2197, simple_loss=0.2936, pruned_loss=0.0729, over 7267.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2951, pruned_loss=0.07125, over 1413668.10 frames.], batch size: 19, lr: 1.36e-03
+2022-05-14 01:50:43,660 INFO [train.py:812] (0/8) Epoch 5, batch 1300, loss[loss=0.2085, simple_loss=0.291, pruned_loss=0.06303, over 7328.00 frames.], tot_loss[loss=0.2178, simple_loss=0.295, pruned_loss=0.07031, over 1416918.25 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:51:42,404 INFO [train.py:812] (0/8) Epoch 5, batch 1350, loss[loss=0.2141, simple_loss=0.2766, pruned_loss=0.07583, over 7138.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2948, pruned_loss=0.06998, over 1423745.75 frames.], batch size: 17, lr: 1.36e-03
+2022-05-14 01:52:39,822 INFO [train.py:812] (0/8) Epoch 5, batch 1400, loss[loss=0.199, simple_loss=0.2876, pruned_loss=0.0552, over 7246.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2962, pruned_loss=0.07063, over 1419203.26 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:53:37,456 INFO [train.py:812] (0/8) Epoch 5, batch 1450, loss[loss=0.2207, simple_loss=0.2803, pruned_loss=0.08055, over 7014.00 frames.], tot_loss[loss=0.2202, simple_loss=0.2973, pruned_loss=0.0715, over 1419869.47 frames.], batch size: 16, lr: 1.35e-03
+2022-05-14 01:54:35,092 INFO [train.py:812] (0/8) Epoch 5, batch 1500, loss[loss=0.1917, simple_loss=0.2712, pruned_loss=0.05603, over 7321.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2959, pruned_loss=0.07076, over 1423441.68 frames.], batch size: 20, lr: 1.35e-03
+2022-05-14 01:55:34,682 INFO [train.py:812] (0/8) Epoch 5, batch 1550, loss[loss=0.2234, simple_loss=0.3012, pruned_loss=0.07273, over 7378.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2945, pruned_loss=0.07017, over 1425591.80 frames.], batch size: 23, lr: 1.35e-03
+2022-05-14 01:56:33,048 INFO [train.py:812] (0/8) Epoch 5, batch 1600, loss[loss=0.2224, simple_loss=0.2974, pruned_loss=0.07367, over 7312.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2943, pruned_loss=0.07009, over 1424199.42 frames.], batch size: 25, lr: 1.35e-03
+2022-05-14 01:57:28,688 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-20000.pt
+2022-05-14 01:57:37,137 INFO [train.py:812] (0/8) Epoch 5, batch 1650, loss[loss=0.2632, simple_loss=0.3293, pruned_loss=0.09857, over 7106.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2944, pruned_loss=0.06994, over 1422349.65 frames.], batch size: 21, lr: 1.35e-03
+2022-05-14 01:58:36,671 INFO [train.py:812] (0/8) Epoch 5, batch 1700, loss[loss=0.2096, simple_loss=0.2907, pruned_loss=0.06422, over 7334.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2934, pruned_loss=0.06946, over 1424314.65 frames.], batch size: 22, lr: 1.35e-03
+2022-05-14 01:59:35,629 INFO [train.py:812] (0/8) Epoch 5, batch 1750, loss[loss=0.2194, simple_loss=0.3072, pruned_loss=0.06576, over 7256.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2926, pruned_loss=0.06902, over 1423623.27 frames.], batch size: 24, lr: 1.34e-03
+2022-05-14 02:00:34,958 INFO [train.py:812] (0/8) Epoch 5, batch 1800, loss[loss=0.2746, simple_loss=0.3603, pruned_loss=0.09444, over 7328.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2934, pruned_loss=0.06921, over 1426170.22 frames.], batch size: 21, lr: 1.34e-03
+2022-05-14 02:01:33,480 INFO [train.py:812] (0/8) Epoch 5, batch 1850, loss[loss=0.2709, simple_loss=0.3428, pruned_loss=0.09949, over 6530.00 frames.], tot_loss[loss=0.2165, simple_loss=0.294, pruned_loss=0.06953, over 1426584.62 frames.], batch size: 39, lr: 1.34e-03
+2022-05-14 02:02:31,906 INFO [train.py:812] (0/8) Epoch 5, batch 1900, loss[loss=0.2565, simple_loss=0.3342, pruned_loss=0.08937, over 7111.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2938, pruned_loss=0.06906, over 1427642.25 frames.], batch size: 21, lr: 1.34e-03
+2022-05-14 02:03:30,594 INFO [train.py:812] (0/8) Epoch 5, batch 1950, loss[loss=0.2096, simple_loss=0.2874, pruned_loss=0.06588, over 7167.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2931, pruned_loss=0.06835, over 1428129.89 frames.], batch size: 18, lr: 1.34e-03
+2022-05-14 02:04:28,240 INFO [train.py:812] (0/8) Epoch 5, batch 2000, loss[loss=0.2369, simple_loss=0.3066, pruned_loss=0.08358, over 7312.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2932, pruned_loss=0.06921, over 1425976.07 frames.], batch size: 25, lr: 1.34e-03
+2022-05-14 02:05:26,860 INFO [train.py:812] (0/8) Epoch 5, batch 2050, loss[loss=0.26, simple_loss=0.3169, pruned_loss=0.1016, over 7294.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2928, pruned_loss=0.06891, over 1430689.38 frames.], batch size: 24, lr: 1.34e-03
+2022-05-14 02:06:25,388 INFO [train.py:812] (0/8) Epoch 5, batch 2100, loss[loss=0.2101, simple_loss=0.276, pruned_loss=0.07206, over 7414.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2932, pruned_loss=0.069, over 1433427.88 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:07:23,971 INFO [train.py:812] (0/8) Epoch 5, batch 2150, loss[loss=0.1972, simple_loss=0.2723, pruned_loss=0.06103, over 7061.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2944, pruned_loss=0.06914, over 1432056.26 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:08:21,803 INFO [train.py:812] (0/8) Epoch 5, batch 2200, loss[loss=0.2493, simple_loss=0.3085, pruned_loss=0.09504, over 7342.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2933, pruned_loss=0.06911, over 1434018.10 frames.], batch size: 22, lr: 1.33e-03
+2022-05-14 02:09:20,787 INFO [train.py:812] (0/8) Epoch 5, batch 2250, loss[loss=0.209, simple_loss=0.2924, pruned_loss=0.06278, over 7388.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2927, pruned_loss=0.06874, over 1432263.38 frames.], batch size: 23, lr: 1.33e-03
+2022-05-14 02:10:20,258 INFO [train.py:812] (0/8) Epoch 5, batch 2300, loss[loss=0.1692, simple_loss=0.248, pruned_loss=0.04523, over 7303.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2938, pruned_loss=0.06949, over 1429813.47 frames.], batch size: 17, lr: 1.33e-03
+2022-05-14 02:11:18,993 INFO [train.py:812] (0/8) Epoch 5, batch 2350, loss[loss=0.2025, simple_loss=0.2766, pruned_loss=0.06416, over 7415.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2937, pruned_loss=0.06895, over 1433011.43 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:12:18,655 INFO [train.py:812] (0/8) Epoch 5, batch 2400, loss[loss=0.2293, simple_loss=0.31, pruned_loss=0.07429, over 7225.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2931, pruned_loss=0.06892, over 1434142.39 frames.], batch size: 21, lr: 1.32e-03
+2022-05-14 02:13:16,804 INFO [train.py:812] (0/8) Epoch 5, batch 2450, loss[loss=0.1818, simple_loss=0.2584, pruned_loss=0.05262, over 7268.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2937, pruned_loss=0.06891, over 1434151.56 frames.], batch size: 18, lr: 1.32e-03
+2022-05-14 02:14:14,197 INFO [train.py:812] (0/8) Epoch 5, batch 2500, loss[loss=0.2137, simple_loss=0.2966, pruned_loss=0.06538, over 7219.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2928, pruned_loss=0.06874, over 1431562.31 frames.], batch size: 22, lr: 1.32e-03
+2022-05-14 02:15:13,112 INFO [train.py:812] (0/8) Epoch 5, batch 2550, loss[loss=0.2094, simple_loss=0.3053, pruned_loss=0.05678, over 7144.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2934, pruned_loss=0.06869, over 1432159.35 frames.], batch size: 20, lr: 1.32e-03
+2022-05-14 02:16:11,201 INFO [train.py:812] (0/8) Epoch 5, batch 2600, loss[loss=0.1831, simple_loss=0.2801, pruned_loss=0.04307, over 7325.00 frames.], tot_loss[loss=0.2161, simple_loss=0.294, pruned_loss=0.06906, over 1430468.47 frames.], batch size: 21, lr: 1.32e-03
+2022-05-14 02:17:10,916 INFO [train.py:812] (0/8) Epoch 5, batch 2650, loss[loss=0.2252, simple_loss=0.2871, pruned_loss=0.08165, over 7438.00 frames.], tot_loss[loss=0.216, simple_loss=0.294, pruned_loss=0.06906, over 1429676.63 frames.], batch size: 17, lr: 1.32e-03
+2022-05-14 02:18:10,458 INFO [train.py:812] (0/8) Epoch 5, batch 2700, loss[loss=0.1729, simple_loss=0.2498, pruned_loss=0.04799, over 7284.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2929, pruned_loss=0.06866, over 1432224.36 frames.], batch size: 18, lr: 1.32e-03
+2022-05-14 02:19:10,225 INFO [train.py:812] (0/8) Epoch 5, batch 2750, loss[loss=0.2574, simple_loss=0.328, pruned_loss=0.09345, over 7352.00 frames.], tot_loss[loss=0.2153, simple_loss=0.293, pruned_loss=0.06881, over 1433112.52 frames.], batch size: 19, lr: 1.31e-03
+2022-05-14 02:20:09,509 INFO [train.py:812] (0/8) Epoch 5, batch 2800, loss[loss=0.1998, simple_loss=0.2676, pruned_loss=0.06598, over 7137.00 frames.], tot_loss[loss=0.214, simple_loss=0.2919, pruned_loss=0.06812, over 1434381.09 frames.], batch size: 17, lr: 1.31e-03
+2022-05-14 02:21:07,405 INFO [train.py:812] (0/8) Epoch 5, batch 2850, loss[loss=0.2275, simple_loss=0.3093, pruned_loss=0.0728, over 6693.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2919, pruned_loss=0.06826, over 1431261.77 frames.], batch size: 31, lr: 1.31e-03
+2022-05-14 02:22:06,256 INFO [train.py:812] (0/8) Epoch 5, batch 2900, loss[loss=0.2504, simple_loss=0.3214, pruned_loss=0.08972, over 7282.00 frames.], tot_loss[loss=0.215, simple_loss=0.2929, pruned_loss=0.06861, over 1429140.93 frames.], batch size: 24, lr: 1.31e-03
+2022-05-14 02:23:05,635 INFO [train.py:812] (0/8) Epoch 5, batch 2950, loss[loss=0.2144, simple_loss=0.2894, pruned_loss=0.06968, over 7342.00 frames.], tot_loss[loss=0.2133, simple_loss=0.291, pruned_loss=0.06785, over 1429092.12 frames.], batch size: 22, lr: 1.31e-03
+2022-05-14 02:24:04,413 INFO [train.py:812] (0/8) Epoch 5, batch 3000, loss[loss=0.1932, simple_loss=0.2868, pruned_loss=0.04982, over 7200.00 frames.], tot_loss[loss=0.2134, simple_loss=0.291, pruned_loss=0.06786, over 1425036.34 frames.], batch size: 26, lr: 1.31e-03
+2022-05-14 02:24:04,415 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 02:24:12,114 INFO [train.py:841] (0/8) Epoch 5, validation: loss=0.1705, simple_loss=0.2732, pruned_loss=0.03391, over 698248.00 frames.
+2022-05-14 02:25:11,799 INFO [train.py:812] (0/8) Epoch 5, batch 3050, loss[loss=0.2555, simple_loss=0.331, pruned_loss=0.09002, over 7200.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2917, pruned_loss=0.06761, over 1428630.93 frames.], batch size: 22, lr: 1.31e-03
+2022-05-14 02:26:09,567 INFO [train.py:812] (0/8) Epoch 5, batch 3100, loss[loss=0.1928, simple_loss=0.2875, pruned_loss=0.04909, over 7234.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2927, pruned_loss=0.06826, over 1427308.09 frames.], batch size: 20, lr: 1.30e-03
+2022-05-14 02:27:19,076 INFO [train.py:812] (0/8) Epoch 5, batch 3150, loss[loss=0.2178, simple_loss=0.3041, pruned_loss=0.06577, over 7277.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2925, pruned_loss=0.06805, over 1428074.72 frames.], batch size: 25, lr: 1.30e-03
+2022-05-14 02:28:18,318 INFO [train.py:812] (0/8) Epoch 5, batch 3200, loss[loss=0.1885, simple_loss=0.2668, pruned_loss=0.05513, over 7361.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2923, pruned_loss=0.0686, over 1429338.23 frames.], batch size: 19, lr: 1.30e-03
+2022-05-14 02:29:17,244 INFO [train.py:812] (0/8) Epoch 5, batch 3250, loss[loss=0.2022, simple_loss=0.2715, pruned_loss=0.06649, over 7170.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2922, pruned_loss=0.06867, over 1427967.71 frames.], batch size: 18, lr: 1.30e-03
+2022-05-14 02:30:15,407 INFO [train.py:812] (0/8) Epoch 5, batch 3300, loss[loss=0.2106, simple_loss=0.2893, pruned_loss=0.06598, over 7146.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2939, pruned_loss=0.06962, over 1422187.49 frames.], batch size: 26, lr: 1.30e-03
+2022-05-14 02:31:14,131 INFO [train.py:812] (0/8) Epoch 5, batch 3350, loss[loss=0.2606, simple_loss=0.3309, pruned_loss=0.09516, over 7116.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2934, pruned_loss=0.06895, over 1425085.82 frames.], batch size: 21, lr: 1.30e-03
+2022-05-14 02:32:12,607 INFO [train.py:812] (0/8) Epoch 5, batch 3400, loss[loss=0.2305, simple_loss=0.3086, pruned_loss=0.0762, over 7237.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2941, pruned_loss=0.06925, over 1426760.32 frames.], batch size: 20, lr: 1.30e-03
+2022-05-14 02:33:11,743 INFO [train.py:812] (0/8) Epoch 5, batch 3450, loss[loss=0.2132, simple_loss=0.3008, pruned_loss=0.06277, over 7194.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2932, pruned_loss=0.06914, over 1427596.53 frames.], batch size: 23, lr: 1.29e-03
+2022-05-14 02:34:10,772 INFO [train.py:812] (0/8) Epoch 5, batch 3500, loss[loss=0.2095, simple_loss=0.2893, pruned_loss=0.06485, over 7327.00 frames.], tot_loss[loss=0.2155, simple_loss=0.293, pruned_loss=0.06899, over 1429796.95 frames.], batch size: 20, lr: 1.29e-03
+2022-05-14 02:35:38,311 INFO [train.py:812] (0/8) Epoch 5, batch 3550, loss[loss=0.2384, simple_loss=0.3064, pruned_loss=0.08524, over 7412.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2935, pruned_loss=0.06915, over 1424273.36 frames.], batch size: 21, lr: 1.29e-03
+2022-05-14 02:36:46,049 INFO [train.py:812] (0/8) Epoch 5, batch 3600, loss[loss=0.216, simple_loss=0.3005, pruned_loss=0.06574, over 7263.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2924, pruned_loss=0.0687, over 1421212.23 frames.], batch size: 19, lr: 1.29e-03
+2022-05-14 02:38:13,277 INFO [train.py:812] (0/8) Epoch 5, batch 3650, loss[loss=0.262, simple_loss=0.3309, pruned_loss=0.09654, over 6717.00 frames.], tot_loss[loss=0.214, simple_loss=0.292, pruned_loss=0.06804, over 1415498.80 frames.], batch size: 31, lr: 1.29e-03
+2022-05-14 02:39:12,926 INFO [train.py:812] (0/8) Epoch 5, batch 3700, loss[loss=0.2036, simple_loss=0.2771, pruned_loss=0.06509, over 7166.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2899, pruned_loss=0.06724, over 1419678.16 frames.], batch size: 18, lr: 1.29e-03
+2022-05-14 02:40:11,639 INFO [train.py:812] (0/8) Epoch 5, batch 3750, loss[loss=0.2069, simple_loss=0.2724, pruned_loss=0.07071, over 6750.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2907, pruned_loss=0.06744, over 1419658.09 frames.], batch size: 15, lr: 1.29e-03
+2022-05-14 02:41:10,021 INFO [train.py:812] (0/8) Epoch 5, batch 3800, loss[loss=0.1917, simple_loss=0.2722, pruned_loss=0.05565, over 7287.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2915, pruned_loss=0.06789, over 1420693.06 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:42:07,612 INFO [train.py:812] (0/8) Epoch 5, batch 3850, loss[loss=0.2122, simple_loss=0.3082, pruned_loss=0.05811, over 7410.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2916, pruned_loss=0.06786, over 1419217.70 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:43:06,315 INFO [train.py:812] (0/8) Epoch 5, batch 3900, loss[loss=0.21, simple_loss=0.2824, pruned_loss=0.06877, over 7157.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2911, pruned_loss=0.0677, over 1416102.58 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:44:04,237 INFO [train.py:812] (0/8) Epoch 5, batch 3950, loss[loss=0.2057, simple_loss=0.2928, pruned_loss=0.05931, over 7416.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2912, pruned_loss=0.06756, over 1413239.55 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:45:02,163 INFO [train.py:812] (0/8) Epoch 5, batch 4000, loss[loss=0.2095, simple_loss=0.2889, pruned_loss=0.06511, over 7426.00 frames.], tot_loss[loss=0.2139, simple_loss=0.292, pruned_loss=0.06788, over 1416297.71 frames.], batch size: 20, lr: 1.28e-03
+2022-05-14 02:46:01,621 INFO [train.py:812] (0/8) Epoch 5, batch 4050, loss[loss=0.2394, simple_loss=0.3312, pruned_loss=0.07376, over 7212.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2907, pruned_loss=0.06687, over 1419169.33 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:46:59,628 INFO [train.py:812] (0/8) Epoch 5, batch 4100, loss[loss=0.1808, simple_loss=0.2644, pruned_loss=0.04856, over 7299.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2932, pruned_loss=0.06772, over 1415803.25 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:47:58,850 INFO [train.py:812] (0/8) Epoch 5, batch 4150, loss[loss=0.2311, simple_loss=0.3089, pruned_loss=0.07668, over 7192.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2937, pruned_loss=0.06851, over 1415007.46 frames.], batch size: 22, lr: 1.27e-03
+2022-05-14 02:48:57,882 INFO [train.py:812] (0/8) Epoch 5, batch 4200, loss[loss=0.2252, simple_loss=0.2939, pruned_loss=0.07825, over 7150.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2938, pruned_loss=0.06843, over 1413898.09 frames.], batch size: 17, lr: 1.27e-03
+2022-05-14 02:49:57,148 INFO [train.py:812] (0/8) Epoch 5, batch 4250, loss[loss=0.1898, simple_loss=0.2643, pruned_loss=0.05765, over 7064.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2937, pruned_loss=0.06864, over 1414393.84 frames.], batch size: 18, lr: 1.27e-03
+2022-05-14 02:50:54,445 INFO [train.py:812] (0/8) Epoch 5, batch 4300, loss[loss=0.1925, simple_loss=0.2815, pruned_loss=0.05181, over 7146.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2935, pruned_loss=0.06808, over 1414554.06 frames.], batch size: 20, lr: 1.27e-03
+2022-05-14 02:51:52,655 INFO [train.py:812] (0/8) Epoch 5, batch 4350, loss[loss=0.2488, simple_loss=0.3168, pruned_loss=0.09046, over 7421.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2948, pruned_loss=0.0689, over 1413267.93 frames.], batch size: 21, lr: 1.27e-03
+2022-05-14 02:52:52,057 INFO [train.py:812] (0/8) Epoch 5, batch 4400, loss[loss=0.1984, simple_loss=0.2705, pruned_loss=0.06315, over 7265.00 frames.], tot_loss[loss=0.2156, simple_loss=0.294, pruned_loss=0.0686, over 1410126.95 frames.], batch size: 19, lr: 1.27e-03
+2022-05-14 02:53:51,752 INFO [train.py:812] (0/8) Epoch 5, batch 4450, loss[loss=0.2299, simple_loss=0.3152, pruned_loss=0.07234, over 6744.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2938, pruned_loss=0.06825, over 1403887.95 frames.], batch size: 31, lr: 1.27e-03
+2022-05-14 02:54:49,526 INFO [train.py:812] (0/8) Epoch 5, batch 4500, loss[loss=0.2841, simple_loss=0.3395, pruned_loss=0.1144, over 4830.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2957, pruned_loss=0.06962, over 1394431.43 frames.], batch size: 52, lr: 1.27e-03
+2022-05-14 02:55:48,806 INFO [train.py:812] (0/8) Epoch 5, batch 4550, loss[loss=0.2511, simple_loss=0.3112, pruned_loss=0.09552, over 5008.00 frames.], tot_loss[loss=0.2222, simple_loss=0.2988, pruned_loss=0.07284, over 1339023.25 frames.], batch size: 52, lr: 1.26e-03
+2022-05-14 02:56:33,564 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-5.pt
+2022-05-14 02:56:57,122 INFO [train.py:812] (0/8) Epoch 6, batch 0, loss[loss=0.2009, simple_loss=0.2792, pruned_loss=0.06126, over 7158.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2792, pruned_loss=0.06126, over 7158.00 frames.], batch size: 19, lr: 1.21e-03
+2022-05-14 02:57:56,755 INFO [train.py:812] (0/8) Epoch 6, batch 50, loss[loss=0.2566, simple_loss=0.316, pruned_loss=0.09856, over 4900.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2925, pruned_loss=0.06657, over 318034.48 frames.], batch size: 52, lr: 1.21e-03
+2022-05-14 02:58:56,405 INFO [train.py:812] (0/8) Epoch 6, batch 100, loss[loss=0.2505, simple_loss=0.3251, pruned_loss=0.08796, over 7143.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2927, pruned_loss=0.06634, over 561737.03 frames.], batch size: 20, lr: 1.21e-03
+2022-05-14 02:59:55,394 INFO [train.py:812] (0/8) Epoch 6, batch 150, loss[loss=0.2458, simple_loss=0.3213, pruned_loss=0.08517, over 6767.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2918, pruned_loss=0.06667, over 749438.81 frames.], batch size: 31, lr: 1.21e-03
+2022-05-14 03:00:54,858 INFO [train.py:812] (0/8) Epoch 6, batch 200, loss[loss=0.2328, simple_loss=0.296, pruned_loss=0.08475, over 7421.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2914, pruned_loss=0.06669, over 898913.59 frames.], batch size: 18, lr: 1.21e-03
+2022-05-14 03:01:54,417 INFO [train.py:812] (0/8) Epoch 6, batch 250, loss[loss=0.2085, simple_loss=0.2935, pruned_loss=0.06174, over 7336.00 frames.], tot_loss[loss=0.209, simple_loss=0.2889, pruned_loss=0.06455, over 1018815.97 frames.], batch size: 22, lr: 1.21e-03
+2022-05-14 03:02:54,509 INFO [train.py:812] (0/8) Epoch 6, batch 300, loss[loss=0.2067, simple_loss=0.2986, pruned_loss=0.05739, over 7236.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2895, pruned_loss=0.06498, over 1111577.88 frames.], batch size: 20, lr: 1.21e-03
+2022-05-14 03:03:51,874 INFO [train.py:812] (0/8) Epoch 6, batch 350, loss[loss=0.2219, simple_loss=0.301, pruned_loss=0.07141, over 7315.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2897, pruned_loss=0.06579, over 1184333.22 frames.], batch size: 20, lr: 1.20e-03
+2022-05-14 03:04:49,937 INFO [train.py:812] (0/8) Epoch 6, batch 400, loss[loss=0.2416, simple_loss=0.3176, pruned_loss=0.08282, over 7379.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2904, pruned_loss=0.06562, over 1235842.96 frames.], batch size: 23, lr: 1.20e-03
+2022-05-14 03:05:47,798 INFO [train.py:812] (0/8) Epoch 6, batch 450, loss[loss=0.1946, simple_loss=0.2685, pruned_loss=0.06032, over 7232.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2899, pruned_loss=0.06479, over 1279428.50 frames.], batch size: 16, lr: 1.20e-03
+2022-05-14 03:06:47,288 INFO [train.py:812] (0/8) Epoch 6, batch 500, loss[loss=0.2374, simple_loss=0.3024, pruned_loss=0.0862, over 4797.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2904, pruned_loss=0.06504, over 1308005.27 frames.], batch size: 52, lr: 1.20e-03
+2022-05-14 03:07:45,167 INFO [train.py:812] (0/8) Epoch 6, batch 550, loss[loss=0.2614, simple_loss=0.3373, pruned_loss=0.0928, over 6481.00 frames.], tot_loss[loss=0.2119, simple_loss=0.2919, pruned_loss=0.06601, over 1332036.55 frames.], batch size: 38, lr: 1.20e-03
+2022-05-14 03:08:44,001 INFO [train.py:812] (0/8) Epoch 6, batch 600, loss[loss=0.2058, simple_loss=0.289, pruned_loss=0.06127, over 7141.00 frames.], tot_loss[loss=0.209, simple_loss=0.2889, pruned_loss=0.06461, over 1350590.90 frames.], batch size: 20, lr: 1.20e-03
+2022-05-14 03:09:42,705 INFO [train.py:812] (0/8) Epoch 6, batch 650, loss[loss=0.2218, simple_loss=0.3112, pruned_loss=0.06619, over 7406.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2885, pruned_loss=0.06435, over 1365801.23 frames.], batch size: 21, lr: 1.20e-03
+2022-05-14 03:10:42,143 INFO [train.py:812] (0/8) Epoch 6, batch 700, loss[loss=0.2471, simple_loss=0.307, pruned_loss=0.09361, over 6816.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2888, pruned_loss=0.06414, over 1377775.54 frames.], batch size: 15, lr: 1.20e-03
+2022-05-14 03:11:41,177 INFO [train.py:812] (0/8) Epoch 6, batch 750, loss[loss=0.2192, simple_loss=0.3084, pruned_loss=0.065, over 7218.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2901, pruned_loss=0.065, over 1388272.27 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:12:41,095 INFO [train.py:812] (0/8) Epoch 6, batch 800, loss[loss=0.2351, simple_loss=0.312, pruned_loss=0.0791, over 7216.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2898, pruned_loss=0.06494, over 1399167.42 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:13:40,478 INFO [train.py:812] (0/8) Epoch 6, batch 850, loss[loss=0.2688, simple_loss=0.3304, pruned_loss=0.1036, over 7194.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2896, pruned_loss=0.06526, over 1404114.88 frames.], batch size: 23, lr: 1.19e-03
+2022-05-14 03:14:39,811 INFO [train.py:812] (0/8) Epoch 6, batch 900, loss[loss=0.2581, simple_loss=0.3364, pruned_loss=0.08984, over 7413.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2897, pruned_loss=0.06522, over 1405894.66 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:15:38,549 INFO [train.py:812] (0/8) Epoch 6, batch 950, loss[loss=0.2232, simple_loss=0.2875, pruned_loss=0.07945, over 7143.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2902, pruned_loss=0.06562, over 1406949.38 frames.], batch size: 17, lr: 1.19e-03
+2022-05-14 03:16:37,954 INFO [train.py:812] (0/8) Epoch 6, batch 1000, loss[loss=0.2272, simple_loss=0.306, pruned_loss=0.07417, over 7412.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2904, pruned_loss=0.06589, over 1408401.69 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:17:36,235 INFO [train.py:812] (0/8) Epoch 6, batch 1050, loss[loss=0.2235, simple_loss=0.2941, pruned_loss=0.07644, over 7326.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2898, pruned_loss=0.06565, over 1413161.95 frames.], batch size: 20, lr: 1.19e-03
+2022-05-14 03:17:47,007 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-24000.pt
+2022-05-14 03:18:39,073 INFO [train.py:812] (0/8) Epoch 6, batch 1100, loss[loss=0.2398, simple_loss=0.3128, pruned_loss=0.08335, over 7318.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2914, pruned_loss=0.06645, over 1408539.71 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:19:37,376 INFO [train.py:812] (0/8) Epoch 6, batch 1150, loss[loss=0.2164, simple_loss=0.2849, pruned_loss=0.07401, over 7144.00 frames.], tot_loss[loss=0.2123, simple_loss=0.2916, pruned_loss=0.06656, over 1412591.63 frames.], batch size: 20, lr: 1.19e-03
+2022-05-14 03:20:36,646 INFO [train.py:812] (0/8) Epoch 6, batch 1200, loss[loss=0.2298, simple_loss=0.3121, pruned_loss=0.07379, over 7148.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2908, pruned_loss=0.06603, over 1413384.98 frames.], batch size: 26, lr: 1.18e-03
+2022-05-14 03:21:34,756 INFO [train.py:812] (0/8) Epoch 6, batch 1250, loss[loss=0.1988, simple_loss=0.2828, pruned_loss=0.05741, over 7145.00 frames.], tot_loss[loss=0.212, simple_loss=0.2914, pruned_loss=0.06625, over 1413211.51 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:22:34,645 INFO [train.py:812] (0/8) Epoch 6, batch 1300, loss[loss=0.1568, simple_loss=0.2474, pruned_loss=0.03309, over 7356.00 frames.], tot_loss[loss=0.2113, simple_loss=0.2906, pruned_loss=0.06601, over 1411602.02 frames.], batch size: 19, lr: 1.18e-03
+2022-05-14 03:23:33,538 INFO [train.py:812] (0/8) Epoch 6, batch 1350, loss[loss=0.2441, simple_loss=0.3182, pruned_loss=0.08497, over 7061.00 frames.], tot_loss[loss=0.21, simple_loss=0.2892, pruned_loss=0.06537, over 1415006.67 frames.], batch size: 28, lr: 1.18e-03
+2022-05-14 03:24:32,612 INFO [train.py:812] (0/8) Epoch 6, batch 1400, loss[loss=0.2103, simple_loss=0.3006, pruned_loss=0.06003, over 7321.00 frames.], tot_loss[loss=0.209, simple_loss=0.2883, pruned_loss=0.06487, over 1419112.47 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:25:31,687 INFO [train.py:812] (0/8) Epoch 6, batch 1450, loss[loss=0.2156, simple_loss=0.3029, pruned_loss=0.06418, over 7435.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2885, pruned_loss=0.06454, over 1420124.69 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:26:31,148 INFO [train.py:812] (0/8) Epoch 6, batch 1500, loss[loss=0.2349, simple_loss=0.321, pruned_loss=0.0744, over 7148.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2888, pruned_loss=0.06491, over 1419974.05 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:27:30,162 INFO [train.py:812] (0/8) Epoch 6, batch 1550, loss[loss=0.1663, simple_loss=0.2447, pruned_loss=0.04394, over 7293.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2887, pruned_loss=0.06433, over 1421908.99 frames.], batch size: 17, lr: 1.18e-03
+2022-05-14 03:28:29,749 INFO [train.py:812] (0/8) Epoch 6, batch 1600, loss[loss=0.237, simple_loss=0.3031, pruned_loss=0.08549, over 7429.00 frames.], tot_loss[loss=0.2093, simple_loss=0.289, pruned_loss=0.06484, over 1415462.35 frames.], batch size: 20, lr: 1.17e-03
+2022-05-14 03:29:29,249 INFO [train.py:812] (0/8) Epoch 6, batch 1650, loss[loss=0.2149, simple_loss=0.3082, pruned_loss=0.06074, over 7288.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2882, pruned_loss=0.06438, over 1415158.85 frames.], batch size: 25, lr: 1.17e-03
+2022-05-14 03:30:27,823 INFO [train.py:812] (0/8) Epoch 6, batch 1700, loss[loss=0.2169, simple_loss=0.2951, pruned_loss=0.06929, over 7201.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2882, pruned_loss=0.06447, over 1413881.79 frames.], batch size: 22, lr: 1.17e-03
+2022-05-14 03:31:26,970 INFO [train.py:812] (0/8) Epoch 6, batch 1750, loss[loss=0.1826, simple_loss=0.267, pruned_loss=0.04913, over 7283.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2893, pruned_loss=0.06494, over 1411530.67 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:32:26,450 INFO [train.py:812] (0/8) Epoch 6, batch 1800, loss[loss=0.2439, simple_loss=0.3083, pruned_loss=0.08975, over 5206.00 frames.], tot_loss[loss=0.2093, simple_loss=0.289, pruned_loss=0.06481, over 1413643.79 frames.], batch size: 52, lr: 1.17e-03
+2022-05-14 03:33:25,526 INFO [train.py:812] (0/8) Epoch 6, batch 1850, loss[loss=0.1563, simple_loss=0.2401, pruned_loss=0.03622, over 7161.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2885, pruned_loss=0.0644, over 1416530.98 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:34:24,875 INFO [train.py:812] (0/8) Epoch 6, batch 1900, loss[loss=0.2208, simple_loss=0.2819, pruned_loss=0.07979, over 7122.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2887, pruned_loss=0.06472, over 1415065.87 frames.], batch size: 17, lr: 1.17e-03
+2022-05-14 03:35:23,962 INFO [train.py:812] (0/8) Epoch 6, batch 1950, loss[loss=0.1695, simple_loss=0.2574, pruned_loss=0.04082, over 7120.00 frames.], tot_loss[loss=0.209, simple_loss=0.289, pruned_loss=0.06447, over 1420700.68 frames.], batch size: 21, lr: 1.17e-03
+2022-05-14 03:36:21,522 INFO [train.py:812] (0/8) Epoch 6, batch 2000, loss[loss=0.1946, simple_loss=0.2673, pruned_loss=0.06094, over 7260.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2889, pruned_loss=0.06419, over 1424095.15 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:37:19,513 INFO [train.py:812] (0/8) Epoch 6, batch 2050, loss[loss=0.2478, simple_loss=0.3265, pruned_loss=0.08458, over 7124.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2894, pruned_loss=0.0644, over 1424184.23 frames.], batch size: 28, lr: 1.16e-03
+2022-05-14 03:38:19,351 INFO [train.py:812] (0/8) Epoch 6, batch 2100, loss[loss=0.2013, simple_loss=0.2748, pruned_loss=0.06392, over 6460.00 frames.], tot_loss[loss=0.209, simple_loss=0.2891, pruned_loss=0.06441, over 1426312.59 frames.], batch size: 38, lr: 1.16e-03
+2022-05-14 03:39:18,984 INFO [train.py:812] (0/8) Epoch 6, batch 2150, loss[loss=0.1974, simple_loss=0.2817, pruned_loss=0.05654, over 7144.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2879, pruned_loss=0.06337, over 1431075.78 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:40:18,674 INFO [train.py:812] (0/8) Epoch 6, batch 2200, loss[loss=0.2141, simple_loss=0.2861, pruned_loss=0.07103, over 7144.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2869, pruned_loss=0.06308, over 1427715.35 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:41:17,638 INFO [train.py:812] (0/8) Epoch 6, batch 2250, loss[loss=0.2047, simple_loss=0.2831, pruned_loss=0.06313, over 7357.00 frames.], tot_loss[loss=0.207, simple_loss=0.287, pruned_loss=0.06345, over 1425901.66 frames.], batch size: 19, lr: 1.16e-03
+2022-05-14 03:42:16,653 INFO [train.py:812] (0/8) Epoch 6, batch 2300, loss[loss=0.2043, simple_loss=0.2814, pruned_loss=0.06358, over 7290.00 frames.], tot_loss[loss=0.2071, simple_loss=0.287, pruned_loss=0.06358, over 1423307.06 frames.], batch size: 24, lr: 1.16e-03
+2022-05-14 03:43:15,822 INFO [train.py:812] (0/8) Epoch 6, batch 2350, loss[loss=0.1875, simple_loss=0.269, pruned_loss=0.05303, over 7210.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2866, pruned_loss=0.06376, over 1422643.41 frames.], batch size: 21, lr: 1.16e-03
+2022-05-14 03:44:15,947 INFO [train.py:812] (0/8) Epoch 6, batch 2400, loss[loss=0.1871, simple_loss=0.2713, pruned_loss=0.05143, over 7328.00 frames.], tot_loss[loss=0.2066, simple_loss=0.286, pruned_loss=0.06362, over 1422525.64 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:45:14,484 INFO [train.py:812] (0/8) Epoch 6, batch 2450, loss[loss=0.1984, simple_loss=0.2716, pruned_loss=0.06262, over 6803.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2853, pruned_loss=0.06326, over 1421023.29 frames.], batch size: 15, lr: 1.16e-03
+2022-05-14 03:46:13,713 INFO [train.py:812] (0/8) Epoch 6, batch 2500, loss[loss=0.1982, simple_loss=0.2845, pruned_loss=0.0559, over 7327.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2859, pruned_loss=0.06353, over 1420493.45 frames.], batch size: 22, lr: 1.15e-03
+2022-05-14 03:47:11,217 INFO [train.py:812] (0/8) Epoch 6, batch 2550, loss[loss=0.1972, simple_loss=0.2692, pruned_loss=0.0626, over 6868.00 frames.], tot_loss[loss=0.206, simple_loss=0.2856, pruned_loss=0.06324, over 1422562.49 frames.], batch size: 15, lr: 1.15e-03
+2022-05-14 03:48:09,672 INFO [train.py:812] (0/8) Epoch 6, batch 2600, loss[loss=0.1923, simple_loss=0.2801, pruned_loss=0.0522, over 7319.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2864, pruned_loss=0.06333, over 1425133.98 frames.], batch size: 21, lr: 1.15e-03
+2022-05-14 03:49:08,387 INFO [train.py:812] (0/8) Epoch 6, batch 2650, loss[loss=0.2026, simple_loss=0.2978, pruned_loss=0.05372, over 7314.00 frames.], tot_loss[loss=0.207, simple_loss=0.287, pruned_loss=0.06349, over 1423616.05 frames.], batch size: 25, lr: 1.15e-03
+2022-05-14 03:50:08,409 INFO [train.py:812] (0/8) Epoch 6, batch 2700, loss[loss=0.1952, simple_loss=0.2612, pruned_loss=0.06458, over 6790.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2871, pruned_loss=0.06308, over 1425398.60 frames.], batch size: 15, lr: 1.15e-03
+2022-05-14 03:51:06,474 INFO [train.py:812] (0/8) Epoch 6, batch 2750, loss[loss=0.185, simple_loss=0.2744, pruned_loss=0.04783, over 7239.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2868, pruned_loss=0.06273, over 1423431.32 frames.], batch size: 20, lr: 1.15e-03
+2022-05-14 03:52:05,462 INFO [train.py:812] (0/8) Epoch 6, batch 2800, loss[loss=0.1969, simple_loss=0.2692, pruned_loss=0.06235, over 7272.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2869, pruned_loss=0.06318, over 1421135.27 frames.], batch size: 18, lr: 1.15e-03
+2022-05-14 03:53:03,380 INFO [train.py:812] (0/8) Epoch 6, batch 2850, loss[loss=0.1965, simple_loss=0.2744, pruned_loss=0.05936, over 7261.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2875, pruned_loss=0.06354, over 1417979.10 frames.], batch size: 17, lr: 1.15e-03
+2022-05-14 03:54:00,910 INFO [train.py:812] (0/8) Epoch 6, batch 2900, loss[loss=0.2289, simple_loss=0.302, pruned_loss=0.07789, over 6725.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2866, pruned_loss=0.06281, over 1419851.28 frames.], batch size: 31, lr: 1.15e-03
+2022-05-14 03:54:58,716 INFO [train.py:812] (0/8) Epoch 6, batch 2950, loss[loss=0.2233, simple_loss=0.2953, pruned_loss=0.07562, over 7142.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2861, pruned_loss=0.06254, over 1420996.19 frames.], batch size: 20, lr: 1.14e-03
+2022-05-14 03:55:55,719 INFO [train.py:812] (0/8) Epoch 6, batch 3000, loss[loss=0.2143, simple_loss=0.2893, pruned_loss=0.06962, over 7245.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2862, pruned_loss=0.06273, over 1420668.07 frames.], batch size: 20, lr: 1.14e-03
+2022-05-14 03:55:55,721 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 03:56:03,338 INFO [train.py:841] (0/8) Epoch 6, validation: loss=0.1668, simple_loss=0.2696, pruned_loss=0.03205, over 698248.00 frames.
+2022-05-14 03:57:02,147 INFO [train.py:812] (0/8) Epoch 6, batch 3050, loss[loss=0.2253, simple_loss=0.3093, pruned_loss=0.07068, over 7215.00 frames.], tot_loss[loss=0.205, simple_loss=0.2854, pruned_loss=0.06228, over 1426048.37 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 03:58:01,672 INFO [train.py:812] (0/8) Epoch 6, batch 3100, loss[loss=0.1805, simple_loss=0.2752, pruned_loss=0.04293, over 7342.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2848, pruned_loss=0.06214, over 1423364.73 frames.], batch size: 22, lr: 1.14e-03
+2022-05-14 03:58:58,851 INFO [train.py:812] (0/8) Epoch 6, batch 3150, loss[loss=0.2143, simple_loss=0.2956, pruned_loss=0.0665, over 7175.00 frames.], tot_loss[loss=0.206, simple_loss=0.2862, pruned_loss=0.06286, over 1423358.54 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 03:59:57,543 INFO [train.py:812] (0/8) Epoch 6, batch 3200, loss[loss=0.2062, simple_loss=0.2919, pruned_loss=0.06027, over 7222.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2872, pruned_loss=0.06347, over 1424827.76 frames.], batch size: 21, lr: 1.14e-03
+2022-05-14 04:00:56,363 INFO [train.py:812] (0/8) Epoch 6, batch 3250, loss[loss=0.1923, simple_loss=0.2792, pruned_loss=0.05267, over 7361.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2869, pruned_loss=0.063, over 1424755.72 frames.], batch size: 19, lr: 1.14e-03
+2022-05-14 04:01:55,490 INFO [train.py:812] (0/8) Epoch 6, batch 3300, loss[loss=0.2011, simple_loss=0.2778, pruned_loss=0.06215, over 7192.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2866, pruned_loss=0.06287, over 1420842.30 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 04:02:54,510 INFO [train.py:812] (0/8) Epoch 6, batch 3350, loss[loss=0.193, simple_loss=0.2759, pruned_loss=0.05502, over 7258.00 frames.], tot_loss[loss=0.204, simple_loss=0.2848, pruned_loss=0.06162, over 1425583.94 frames.], batch size: 19, lr: 1.14e-03
+2022-05-14 04:03:53,911 INFO [train.py:812] (0/8) Epoch 6, batch 3400, loss[loss=0.2184, simple_loss=0.308, pruned_loss=0.06445, over 7302.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2844, pruned_loss=0.0615, over 1426202.05 frames.], batch size: 24, lr: 1.14e-03
+2022-05-14 04:04:52,402 INFO [train.py:812] (0/8) Epoch 6, batch 3450, loss[loss=0.223, simple_loss=0.3172, pruned_loss=0.06441, over 7416.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2859, pruned_loss=0.06211, over 1427561.34 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:05:50,780 INFO [train.py:812] (0/8) Epoch 6, batch 3500, loss[loss=0.2167, simple_loss=0.2986, pruned_loss=0.0674, over 7190.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2857, pruned_loss=0.06247, over 1424649.88 frames.], batch size: 22, lr: 1.13e-03
+2022-05-14 04:06:49,085 INFO [train.py:812] (0/8) Epoch 6, batch 3550, loss[loss=0.2042, simple_loss=0.2928, pruned_loss=0.05781, over 7310.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2856, pruned_loss=0.06208, over 1427539.27 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:07:47,618 INFO [train.py:812] (0/8) Epoch 6, batch 3600, loss[loss=0.1655, simple_loss=0.2435, pruned_loss=0.04374, over 7177.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2851, pruned_loss=0.06195, over 1428564.42 frames.], batch size: 18, lr: 1.13e-03
+2022-05-14 04:08:46,806 INFO [train.py:812] (0/8) Epoch 6, batch 3650, loss[loss=0.22, simple_loss=0.2974, pruned_loss=0.07127, over 7413.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2851, pruned_loss=0.06209, over 1427951.59 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:09:44,216 INFO [train.py:812] (0/8) Epoch 6, batch 3700, loss[loss=0.2153, simple_loss=0.2984, pruned_loss=0.06617, over 7243.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2851, pruned_loss=0.06204, over 1426285.15 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:10:41,359 INFO [train.py:812] (0/8) Epoch 6, batch 3750, loss[loss=0.2306, simple_loss=0.2943, pruned_loss=0.08349, over 7381.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2852, pruned_loss=0.06257, over 1424206.49 frames.], batch size: 23, lr: 1.13e-03
+2022-05-14 04:11:40,653 INFO [train.py:812] (0/8) Epoch 6, batch 3800, loss[loss=0.1818, simple_loss=0.2571, pruned_loss=0.05328, over 7234.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2845, pruned_loss=0.06237, over 1421653.35 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:12:39,817 INFO [train.py:812] (0/8) Epoch 6, batch 3850, loss[loss=0.1713, simple_loss=0.2558, pruned_loss=0.04336, over 7443.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2855, pruned_loss=0.06254, over 1421972.13 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:13:39,011 INFO [train.py:812] (0/8) Epoch 6, batch 3900, loss[loss=0.1628, simple_loss=0.2485, pruned_loss=0.03853, over 7398.00 frames.], tot_loss[loss=0.2058, simple_loss=0.286, pruned_loss=0.06277, over 1426699.31 frames.], batch size: 18, lr: 1.13e-03
+2022-05-14 04:14:38,399 INFO [train.py:812] (0/8) Epoch 6, batch 3950, loss[loss=0.2172, simple_loss=0.2982, pruned_loss=0.06813, over 7308.00 frames.], tot_loss[loss=0.205, simple_loss=0.2851, pruned_loss=0.0625, over 1425589.12 frames.], batch size: 24, lr: 1.12e-03
+2022-05-14 04:15:37,085 INFO [train.py:812] (0/8) Epoch 6, batch 4000, loss[loss=0.2197, simple_loss=0.3063, pruned_loss=0.0665, over 7205.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2857, pruned_loss=0.06289, over 1427331.74 frames.], batch size: 23, lr: 1.12e-03
+2022-05-14 04:16:34,884 INFO [train.py:812] (0/8) Epoch 6, batch 4050, loss[loss=0.2603, simple_loss=0.3391, pruned_loss=0.09078, over 7321.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2854, pruned_loss=0.06279, over 1427745.03 frames.], batch size: 24, lr: 1.12e-03
+2022-05-14 04:17:34,614 INFO [train.py:812] (0/8) Epoch 6, batch 4100, loss[loss=0.2031, simple_loss=0.2779, pruned_loss=0.06415, over 7395.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2846, pruned_loss=0.06252, over 1428048.50 frames.], batch size: 18, lr: 1.12e-03
+2022-05-14 04:18:33,835 INFO [train.py:812] (0/8) Epoch 6, batch 4150, loss[loss=0.2406, simple_loss=0.3236, pruned_loss=0.07886, over 6673.00 frames.], tot_loss[loss=0.2047, simple_loss=0.284, pruned_loss=0.06268, over 1427316.45 frames.], batch size: 31, lr: 1.12e-03
+2022-05-14 04:19:32,911 INFO [train.py:812] (0/8) Epoch 6, batch 4200, loss[loss=0.2216, simple_loss=0.3135, pruned_loss=0.0649, over 7119.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2834, pruned_loss=0.0625, over 1428946.38 frames.], batch size: 21, lr: 1.12e-03
+2022-05-14 04:20:33,094 INFO [train.py:812] (0/8) Epoch 6, batch 4250, loss[loss=0.2212, simple_loss=0.3047, pruned_loss=0.06888, over 7379.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2836, pruned_loss=0.0624, over 1429843.68 frames.], batch size: 23, lr: 1.12e-03
+2022-05-14 04:21:32,381 INFO [train.py:812] (0/8) Epoch 6, batch 4300, loss[loss=0.1868, simple_loss=0.2701, pruned_loss=0.05169, over 7065.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2837, pruned_loss=0.06273, over 1424751.01 frames.], batch size: 18, lr: 1.12e-03
+2022-05-14 04:22:31,647 INFO [train.py:812] (0/8) Epoch 6, batch 4350, loss[loss=0.218, simple_loss=0.3032, pruned_loss=0.06641, over 7239.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2827, pruned_loss=0.06187, over 1424513.78 frames.], batch size: 21, lr: 1.12e-03
+2022-05-14 04:23:31,429 INFO [train.py:812] (0/8) Epoch 6, batch 4400, loss[loss=0.2107, simple_loss=0.2938, pruned_loss=0.06381, over 7431.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2823, pruned_loss=0.06162, over 1423475.60 frames.], batch size: 20, lr: 1.12e-03
+2022-05-14 04:24:30,572 INFO [train.py:812] (0/8) Epoch 6, batch 4450, loss[loss=0.1688, simple_loss=0.239, pruned_loss=0.0493, over 7275.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2832, pruned_loss=0.06202, over 1409547.82 frames.], batch size: 17, lr: 1.11e-03
+2022-05-14 04:25:38,564 INFO [train.py:812] (0/8) Epoch 6, batch 4500, loss[loss=0.1767, simple_loss=0.2609, pruned_loss=0.0463, over 7231.00 frames.], tot_loss[loss=0.2018, simple_loss=0.281, pruned_loss=0.0613, over 1408710.88 frames.], batch size: 20, lr: 1.11e-03
+2022-05-14 04:26:36,426 INFO [train.py:812] (0/8) Epoch 6, batch 4550, loss[loss=0.3121, simple_loss=0.3641, pruned_loss=0.13, over 5076.00 frames.], tot_loss[loss=0.2061, simple_loss=0.284, pruned_loss=0.06412, over 1358931.15 frames.], batch size: 52, lr: 1.11e-03
+2022-05-14 04:27:21,235 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-6.pt
+2022-05-14 04:27:44,626 INFO [train.py:812] (0/8) Epoch 7, batch 0, loss[loss=0.1981, simple_loss=0.2762, pruned_loss=0.06, over 7407.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2762, pruned_loss=0.06, over 7407.00 frames.], batch size: 18, lr: 1.07e-03
+2022-05-14 04:28:43,244 INFO [train.py:812] (0/8) Epoch 7, batch 50, loss[loss=0.1752, simple_loss=0.2576, pruned_loss=0.04642, over 7406.00 frames.], tot_loss[loss=0.2011, simple_loss=0.281, pruned_loss=0.06064, over 322011.22 frames.], batch size: 18, lr: 1.07e-03
+2022-05-14 04:29:42,464 INFO [train.py:812] (0/8) Epoch 7, batch 100, loss[loss=0.2133, simple_loss=0.2845, pruned_loss=0.07108, over 7153.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2811, pruned_loss=0.06032, over 565640.50 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:30:41,846 INFO [train.py:812] (0/8) Epoch 7, batch 150, loss[loss=0.2292, simple_loss=0.3056, pruned_loss=0.07638, over 7158.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2833, pruned_loss=0.06128, over 755063.52 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:31:41,682 INFO [train.py:812] (0/8) Epoch 7, batch 200, loss[loss=0.191, simple_loss=0.2737, pruned_loss=0.05411, over 7386.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2833, pruned_loss=0.06075, over 905418.96 frames.], batch size: 23, lr: 1.06e-03
+2022-05-14 04:32:39,997 INFO [train.py:812] (0/8) Epoch 7, batch 250, loss[loss=0.2238, simple_loss=0.3055, pruned_loss=0.07105, over 7149.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2836, pruned_loss=0.06062, over 1020114.07 frames.], batch size: 20, lr: 1.06e-03
+2022-05-14 04:33:39,353 INFO [train.py:812] (0/8) Epoch 7, batch 300, loss[loss=0.1714, simple_loss=0.2493, pruned_loss=0.04672, over 6829.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2844, pruned_loss=0.06121, over 1106611.16 frames.], batch size: 15, lr: 1.06e-03
+2022-05-14 04:34:57,035 INFO [train.py:812] (0/8) Epoch 7, batch 350, loss[loss=0.2224, simple_loss=0.2987, pruned_loss=0.07307, over 7118.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2842, pruned_loss=0.06077, over 1177548.92 frames.], batch size: 21, lr: 1.06e-03
+2022-05-14 04:35:53,859 INFO [train.py:812] (0/8) Epoch 7, batch 400, loss[loss=0.1816, simple_loss=0.2593, pruned_loss=0.05194, over 7156.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2847, pruned_loss=0.06047, over 1230399.02 frames.], batch size: 18, lr: 1.06e-03
+2022-05-14 04:37:20,605 INFO [train.py:812] (0/8) Epoch 7, batch 450, loss[loss=0.1559, simple_loss=0.2354, pruned_loss=0.03818, over 7357.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2842, pruned_loss=0.06045, over 1275737.21 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:38:04,466 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-28000.pt
+2022-05-14 04:38:43,161 INFO [train.py:812] (0/8) Epoch 7, batch 500, loss[loss=0.2249, simple_loss=0.3013, pruned_loss=0.07419, over 6476.00 frames.], tot_loss[loss=0.202, simple_loss=0.2836, pruned_loss=0.06021, over 1305814.25 frames.], batch size: 38, lr: 1.06e-03
+2022-05-14 04:39:42,052 INFO [train.py:812] (0/8) Epoch 7, batch 550, loss[loss=0.2191, simple_loss=0.2972, pruned_loss=0.07043, over 7116.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2832, pruned_loss=0.06021, over 1330668.92 frames.], batch size: 21, lr: 1.06e-03
+2022-05-14 04:40:39,505 INFO [train.py:812] (0/8) Epoch 7, batch 600, loss[loss=0.2209, simple_loss=0.2956, pruned_loss=0.07315, over 7134.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2844, pruned_loss=0.06065, over 1349425.56 frames.], batch size: 28, lr: 1.06e-03
+2022-05-14 04:41:38,883 INFO [train.py:812] (0/8) Epoch 7, batch 650, loss[loss=0.2308, simple_loss=0.3054, pruned_loss=0.07806, over 5157.00 frames.], tot_loss[loss=0.2028, simple_loss=0.284, pruned_loss=0.06075, over 1364577.37 frames.], batch size: 52, lr: 1.05e-03
+2022-05-14 04:42:37,555 INFO [train.py:812] (0/8) Epoch 7, batch 700, loss[loss=0.1831, simple_loss=0.2695, pruned_loss=0.04838, over 7155.00 frames.], tot_loss[loss=0.2006, simple_loss=0.282, pruned_loss=0.05959, over 1378558.71 frames.], batch size: 18, lr: 1.05e-03
+2022-05-14 04:43:36,174 INFO [train.py:812] (0/8) Epoch 7, batch 750, loss[loss=0.1979, simple_loss=0.2806, pruned_loss=0.05766, over 6792.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2812, pruned_loss=0.05891, over 1391900.98 frames.], batch size: 31, lr: 1.05e-03
+2022-05-14 04:44:33,656 INFO [train.py:812] (0/8) Epoch 7, batch 800, loss[loss=0.2095, simple_loss=0.2835, pruned_loss=0.06775, over 7316.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2806, pruned_loss=0.05884, over 1391981.75 frames.], batch size: 20, lr: 1.05e-03
+2022-05-14 04:45:32,930 INFO [train.py:812] (0/8) Epoch 7, batch 850, loss[loss=0.2325, simple_loss=0.3077, pruned_loss=0.0786, over 7290.00 frames.], tot_loss[loss=0.1983, simple_loss=0.28, pruned_loss=0.05832, over 1398310.21 frames.], batch size: 24, lr: 1.05e-03
+2022-05-14 04:46:32,281 INFO [train.py:812] (0/8) Epoch 7, batch 900, loss[loss=0.2898, simple_loss=0.3574, pruned_loss=0.1111, over 7378.00 frames.], tot_loss[loss=0.199, simple_loss=0.2805, pruned_loss=0.05877, over 1404159.82 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:47:31,176 INFO [train.py:812] (0/8) Epoch 7, batch 950, loss[loss=0.2553, simple_loss=0.3364, pruned_loss=0.08704, over 7378.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2821, pruned_loss=0.05955, over 1408256.82 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:48:29,684 INFO [train.py:812] (0/8) Epoch 7, batch 1000, loss[loss=0.1793, simple_loss=0.2678, pruned_loss=0.04541, over 7371.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2818, pruned_loss=0.05955, over 1408893.69 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:49:29,137 INFO [train.py:812] (0/8) Epoch 7, batch 1050, loss[loss=0.2101, simple_loss=0.2893, pruned_loss=0.06542, over 7157.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2821, pruned_loss=0.05989, over 1415855.76 frames.], batch size: 19, lr: 1.05e-03
+2022-05-14 04:50:29,062 INFO [train.py:812] (0/8) Epoch 7, batch 1100, loss[loss=0.2368, simple_loss=0.3219, pruned_loss=0.07592, over 7301.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2819, pruned_loss=0.05968, over 1419512.31 frames.], batch size: 25, lr: 1.05e-03
+2022-05-14 04:51:28,382 INFO [train.py:812] (0/8) Epoch 7, batch 1150, loss[loss=0.2053, simple_loss=0.2784, pruned_loss=0.06605, over 7140.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2824, pruned_loss=0.05996, over 1417617.72 frames.], batch size: 17, lr: 1.05e-03
+2022-05-14 04:52:28,290 INFO [train.py:812] (0/8) Epoch 7, batch 1200, loss[loss=0.1991, simple_loss=0.2765, pruned_loss=0.06091, over 6844.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2829, pruned_loss=0.06029, over 1412480.54 frames.], batch size: 15, lr: 1.04e-03
+2022-05-14 04:53:27,871 INFO [train.py:812] (0/8) Epoch 7, batch 1250, loss[loss=0.2011, simple_loss=0.28, pruned_loss=0.06105, over 7230.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2833, pruned_loss=0.06091, over 1413915.14 frames.], batch size: 20, lr: 1.04e-03
+2022-05-14 04:54:25,664 INFO [train.py:812] (0/8) Epoch 7, batch 1300, loss[loss=0.1812, simple_loss=0.2645, pruned_loss=0.04898, over 7274.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2828, pruned_loss=0.06066, over 1415265.68 frames.], batch size: 17, lr: 1.04e-03
+2022-05-14 04:55:24,144 INFO [train.py:812] (0/8) Epoch 7, batch 1350, loss[loss=0.2319, simple_loss=0.3078, pruned_loss=0.07801, over 7431.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2831, pruned_loss=0.06023, over 1420904.05 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 04:56:22,888 INFO [train.py:812] (0/8) Epoch 7, batch 1400, loss[loss=0.2223, simple_loss=0.291, pruned_loss=0.07676, over 7168.00 frames.], tot_loss[loss=0.2028, simple_loss=0.284, pruned_loss=0.06077, over 1419321.92 frames.], batch size: 19, lr: 1.04e-03
+2022-05-14 04:57:22,098 INFO [train.py:812] (0/8) Epoch 7, batch 1450, loss[loss=0.2001, simple_loss=0.29, pruned_loss=0.0551, over 6818.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2832, pruned_loss=0.06023, over 1418630.83 frames.], batch size: 31, lr: 1.04e-03
+2022-05-14 04:58:20,156 INFO [train.py:812] (0/8) Epoch 7, batch 1500, loss[loss=0.1676, simple_loss=0.253, pruned_loss=0.04117, over 7413.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2822, pruned_loss=0.05885, over 1422605.27 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 04:59:18,942 INFO [train.py:812] (0/8) Epoch 7, batch 1550, loss[loss=0.2373, simple_loss=0.2994, pruned_loss=0.08758, over 7156.00 frames.], tot_loss[loss=0.2002, simple_loss=0.282, pruned_loss=0.0592, over 1416614.61 frames.], batch size: 26, lr: 1.04e-03
+2022-05-14 05:00:18,981 INFO [train.py:812] (0/8) Epoch 7, batch 1600, loss[loss=0.1956, simple_loss=0.2927, pruned_loss=0.04919, over 7117.00 frames.], tot_loss[loss=0.201, simple_loss=0.2829, pruned_loss=0.05957, over 1422922.81 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 05:01:18,304 INFO [train.py:812] (0/8) Epoch 7, batch 1650, loss[loss=0.1758, simple_loss=0.2652, pruned_loss=0.04321, over 7066.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2816, pruned_loss=0.05955, over 1417649.83 frames.], batch size: 18, lr: 1.04e-03
+2022-05-14 05:02:16,878 INFO [train.py:812] (0/8) Epoch 7, batch 1700, loss[loss=0.1982, simple_loss=0.285, pruned_loss=0.05569, over 7216.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2808, pruned_loss=0.05894, over 1416613.31 frames.], batch size: 22, lr: 1.04e-03
+2022-05-14 05:03:15,984 INFO [train.py:812] (0/8) Epoch 7, batch 1750, loss[loss=0.2438, simple_loss=0.3066, pruned_loss=0.09054, over 7340.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2811, pruned_loss=0.05919, over 1411891.85 frames.], batch size: 22, lr: 1.04e-03
+2022-05-14 05:04:14,618 INFO [train.py:812] (0/8) Epoch 7, batch 1800, loss[loss=0.2257, simple_loss=0.3074, pruned_loss=0.07202, over 7282.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2831, pruned_loss=0.05992, over 1414498.95 frames.], batch size: 25, lr: 1.03e-03
+2022-05-14 05:05:13,138 INFO [train.py:812] (0/8) Epoch 7, batch 1850, loss[loss=0.2069, simple_loss=0.2771, pruned_loss=0.06831, over 7015.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2831, pruned_loss=0.06028, over 1416256.81 frames.], batch size: 16, lr: 1.03e-03
+2022-05-14 05:06:10,574 INFO [train.py:812] (0/8) Epoch 7, batch 1900, loss[loss=0.2129, simple_loss=0.2766, pruned_loss=0.07461, over 7064.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2831, pruned_loss=0.06059, over 1413326.70 frames.], batch size: 18, lr: 1.03e-03
+2022-05-14 05:07:08,603 INFO [train.py:812] (0/8) Epoch 7, batch 1950, loss[loss=0.2117, simple_loss=0.2909, pruned_loss=0.06625, over 7268.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2819, pruned_loss=0.05973, over 1417746.95 frames.], batch size: 18, lr: 1.03e-03
+2022-05-14 05:08:07,329 INFO [train.py:812] (0/8) Epoch 7, batch 2000, loss[loss=0.2355, simple_loss=0.3204, pruned_loss=0.07535, over 7282.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2817, pruned_loss=0.05983, over 1418173.57 frames.], batch size: 25, lr: 1.03e-03
+2022-05-14 05:09:04,295 INFO [train.py:812] (0/8) Epoch 7, batch 2050, loss[loss=0.1855, simple_loss=0.2743, pruned_loss=0.04831, over 7323.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2818, pruned_loss=0.05953, over 1414445.09 frames.], batch size: 24, lr: 1.03e-03
+2022-05-14 05:10:01,682 INFO [train.py:812] (0/8) Epoch 7, batch 2100, loss[loss=0.1714, simple_loss=0.2414, pruned_loss=0.05068, over 6994.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2813, pruned_loss=0.05945, over 1418088.97 frames.], batch size: 16, lr: 1.03e-03
+2022-05-14 05:11:00,093 INFO [train.py:812] (0/8) Epoch 7, batch 2150, loss[loss=0.2155, simple_loss=0.3004, pruned_loss=0.06526, over 7418.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2812, pruned_loss=0.059, over 1424091.21 frames.], batch size: 21, lr: 1.03e-03
+2022-05-14 05:11:57,830 INFO [train.py:812] (0/8) Epoch 7, batch 2200, loss[loss=0.1877, simple_loss=0.2609, pruned_loss=0.05724, over 7124.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2812, pruned_loss=0.05932, over 1422055.84 frames.], batch size: 17, lr: 1.03e-03
+2022-05-14 05:12:56,725 INFO [train.py:812] (0/8) Epoch 7, batch 2250, loss[loss=0.1921, simple_loss=0.2695, pruned_loss=0.05729, over 7294.00 frames.], tot_loss[loss=0.1995, simple_loss=0.281, pruned_loss=0.05902, over 1416802.19 frames.], batch size: 17, lr: 1.03e-03
+2022-05-14 05:13:54,333 INFO [train.py:812] (0/8) Epoch 7, batch 2300, loss[loss=0.2146, simple_loss=0.2931, pruned_loss=0.06803, over 7211.00 frames.], tot_loss[loss=0.1992, simple_loss=0.281, pruned_loss=0.05866, over 1420114.14 frames.], batch size: 23, lr: 1.03e-03
+2022-05-14 05:14:53,677 INFO [train.py:812] (0/8) Epoch 7, batch 2350, loss[loss=0.1948, simple_loss=0.2792, pruned_loss=0.05524, over 7414.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2809, pruned_loss=0.05865, over 1417742.20 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:15:53,754 INFO [train.py:812] (0/8) Epoch 7, batch 2400, loss[loss=0.1607, simple_loss=0.2354, pruned_loss=0.04299, over 7289.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2808, pruned_loss=0.05879, over 1421444.98 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:16:51,041 INFO [train.py:812] (0/8) Epoch 7, batch 2450, loss[loss=0.2483, simple_loss=0.3153, pruned_loss=0.09068, over 7421.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2819, pruned_loss=0.05923, over 1416745.16 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:17:49,553 INFO [train.py:812] (0/8) Epoch 7, batch 2500, loss[loss=0.1968, simple_loss=0.2777, pruned_loss=0.05793, over 7318.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2825, pruned_loss=0.05961, over 1416301.05 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:18:48,415 INFO [train.py:812] (0/8) Epoch 7, batch 2550, loss[loss=0.176, simple_loss=0.2681, pruned_loss=0.04196, over 7427.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2823, pruned_loss=0.05893, over 1422885.73 frames.], batch size: 20, lr: 1.02e-03
+2022-05-14 05:19:47,249 INFO [train.py:812] (0/8) Epoch 7, batch 2600, loss[loss=0.1753, simple_loss=0.2653, pruned_loss=0.04266, over 7171.00 frames.], tot_loss[loss=0.1999, simple_loss=0.282, pruned_loss=0.05893, over 1417142.78 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:20:45,639 INFO [train.py:812] (0/8) Epoch 7, batch 2650, loss[loss=0.1928, simple_loss=0.2728, pruned_loss=0.0564, over 7154.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2815, pruned_loss=0.05896, over 1416844.69 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:21:44,775 INFO [train.py:812] (0/8) Epoch 7, batch 2700, loss[loss=0.1813, simple_loss=0.2444, pruned_loss=0.05907, over 7202.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2816, pruned_loss=0.0591, over 1418783.90 frames.], batch size: 16, lr: 1.02e-03
+2022-05-14 05:22:44,470 INFO [train.py:812] (0/8) Epoch 7, batch 2750, loss[loss=0.1679, simple_loss=0.2435, pruned_loss=0.04619, over 7417.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2819, pruned_loss=0.05897, over 1419425.40 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:23:44,353 INFO [train.py:812] (0/8) Epoch 7, batch 2800, loss[loss=0.1701, simple_loss=0.246, pruned_loss=0.04716, over 7013.00 frames.], tot_loss[loss=0.1994, simple_loss=0.281, pruned_loss=0.05885, over 1417308.38 frames.], batch size: 16, lr: 1.02e-03
+2022-05-14 05:24:43,920 INFO [train.py:812] (0/8) Epoch 7, batch 2850, loss[loss=0.1755, simple_loss=0.2588, pruned_loss=0.04609, over 7323.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2795, pruned_loss=0.05844, over 1422106.58 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:25:43,801 INFO [train.py:812] (0/8) Epoch 7, batch 2900, loss[loss=0.2695, simple_loss=0.3259, pruned_loss=0.1066, over 5558.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2796, pruned_loss=0.05853, over 1424008.98 frames.], batch size: 53, lr: 1.02e-03
+2022-05-14 05:26:42,817 INFO [train.py:812] (0/8) Epoch 7, batch 2950, loss[loss=0.1914, simple_loss=0.2784, pruned_loss=0.0522, over 7297.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2803, pruned_loss=0.05867, over 1424060.73 frames.], batch size: 25, lr: 1.01e-03
+2022-05-14 05:27:42,373 INFO [train.py:812] (0/8) Epoch 7, batch 3000, loss[loss=0.2255, simple_loss=0.2977, pruned_loss=0.07665, over 7186.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2803, pruned_loss=0.05819, over 1425529.71 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:27:42,374 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 05:27:49,661 INFO [train.py:841] (0/8) Epoch 7, validation: loss=0.1637, simple_loss=0.2662, pruned_loss=0.03066, over 698248.00 frames.
+2022-05-14 05:28:48,978 INFO [train.py:812] (0/8) Epoch 7, batch 3050, loss[loss=0.1866, simple_loss=0.2785, pruned_loss=0.04735, over 7182.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2805, pruned_loss=0.05824, over 1425915.72 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:29:48,809 INFO [train.py:812] (0/8) Epoch 7, batch 3100, loss[loss=0.2014, simple_loss=0.2831, pruned_loss=0.05986, over 7122.00 frames.], tot_loss[loss=0.1994, simple_loss=0.281, pruned_loss=0.05891, over 1423573.41 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:30:48,420 INFO [train.py:812] (0/8) Epoch 7, batch 3150, loss[loss=0.2469, simple_loss=0.3284, pruned_loss=0.08277, over 7101.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2814, pruned_loss=0.05908, over 1427182.36 frames.], batch size: 28, lr: 1.01e-03
+2022-05-14 05:31:47,451 INFO [train.py:812] (0/8) Epoch 7, batch 3200, loss[loss=0.1843, simple_loss=0.2735, pruned_loss=0.04758, over 7329.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2814, pruned_loss=0.05911, over 1423710.52 frames.], batch size: 22, lr: 1.01e-03
+2022-05-14 05:32:46,881 INFO [train.py:812] (0/8) Epoch 7, batch 3250, loss[loss=0.2388, simple_loss=0.3271, pruned_loss=0.07523, over 7056.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2815, pruned_loss=0.05968, over 1422693.63 frames.], batch size: 28, lr: 1.01e-03
+2022-05-14 05:33:46,248 INFO [train.py:812] (0/8) Epoch 7, batch 3300, loss[loss=0.1948, simple_loss=0.2931, pruned_loss=0.04823, over 7144.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2817, pruned_loss=0.05962, over 1417943.91 frames.], batch size: 20, lr: 1.01e-03
+2022-05-14 05:34:45,875 INFO [train.py:812] (0/8) Epoch 7, batch 3350, loss[loss=0.1788, simple_loss=0.2681, pruned_loss=0.04476, over 7162.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2812, pruned_loss=0.05931, over 1418623.25 frames.], batch size: 19, lr: 1.01e-03
+2022-05-14 05:35:44,955 INFO [train.py:812] (0/8) Epoch 7, batch 3400, loss[loss=0.1775, simple_loss=0.2737, pruned_loss=0.04065, over 7115.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2814, pruned_loss=0.05899, over 1421607.69 frames.], batch size: 21, lr: 1.01e-03
+2022-05-14 05:36:43,522 INFO [train.py:812] (0/8) Epoch 7, batch 3450, loss[loss=0.2356, simple_loss=0.3247, pruned_loss=0.07323, over 7297.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2824, pruned_loss=0.05954, over 1420031.87 frames.], batch size: 24, lr: 1.01e-03
+2022-05-14 05:37:43,006 INFO [train.py:812] (0/8) Epoch 7, batch 3500, loss[loss=0.2323, simple_loss=0.3074, pruned_loss=0.07865, over 7208.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2825, pruned_loss=0.05929, over 1422619.02 frames.], batch size: 21, lr: 1.01e-03
+2022-05-14 05:38:41,463 INFO [train.py:812] (0/8) Epoch 7, batch 3550, loss[loss=0.2304, simple_loss=0.3112, pruned_loss=0.07482, over 7379.00 frames.], tot_loss[loss=0.2004, simple_loss=0.282, pruned_loss=0.05943, over 1424959.25 frames.], batch size: 23, lr: 1.01e-03
+2022-05-14 05:39:40,561 INFO [train.py:812] (0/8) Epoch 7, batch 3600, loss[loss=0.1917, simple_loss=0.2721, pruned_loss=0.05565, over 7228.00 frames.], tot_loss[loss=0.2002, simple_loss=0.282, pruned_loss=0.05917, over 1426464.22 frames.], batch size: 21, lr: 1.00e-03
+2022-05-14 05:40:39,014 INFO [train.py:812] (0/8) Epoch 7, batch 3650, loss[loss=0.1913, simple_loss=0.285, pruned_loss=0.04881, over 7030.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2816, pruned_loss=0.05912, over 1423844.14 frames.], batch size: 28, lr: 1.00e-03
+2022-05-14 05:41:38,735 INFO [train.py:812] (0/8) Epoch 7, batch 3700, loss[loss=0.1781, simple_loss=0.2642, pruned_loss=0.04595, over 7438.00 frames.], tot_loss[loss=0.199, simple_loss=0.2805, pruned_loss=0.05873, over 1424532.86 frames.], batch size: 20, lr: 1.00e-03
+2022-05-14 05:42:37,956 INFO [train.py:812] (0/8) Epoch 7, batch 3750, loss[loss=0.2425, simple_loss=0.3164, pruned_loss=0.08429, over 4880.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2807, pruned_loss=0.05883, over 1424399.06 frames.], batch size: 52, lr: 1.00e-03
+2022-05-14 05:43:37,503 INFO [train.py:812] (0/8) Epoch 7, batch 3800, loss[loss=0.1779, simple_loss=0.2684, pruned_loss=0.04372, over 7360.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2813, pruned_loss=0.05893, over 1421839.33 frames.], batch size: 19, lr: 1.00e-03
+2022-05-14 05:44:35,595 INFO [train.py:812] (0/8) Epoch 7, batch 3850, loss[loss=0.1673, simple_loss=0.2462, pruned_loss=0.04418, over 7144.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2801, pruned_loss=0.05839, over 1424559.25 frames.], batch size: 17, lr: 1.00e-03
+2022-05-14 05:45:34,808 INFO [train.py:812] (0/8) Epoch 7, batch 3900, loss[loss=0.1751, simple_loss=0.2642, pruned_loss=0.04298, over 7164.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2803, pruned_loss=0.05872, over 1424957.78 frames.], batch size: 18, lr: 1.00e-03
+2022-05-14 05:46:31,678 INFO [train.py:812] (0/8) Epoch 7, batch 3950, loss[loss=0.2252, simple_loss=0.3093, pruned_loss=0.07056, over 7350.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2811, pruned_loss=0.05936, over 1426569.98 frames.], batch size: 22, lr: 9.99e-04
+2022-05-14 05:47:30,574 INFO [train.py:812] (0/8) Epoch 7, batch 4000, loss[loss=0.2043, simple_loss=0.2889, pruned_loss=0.05988, over 6739.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2805, pruned_loss=0.05865, over 1430961.43 frames.], batch size: 31, lr: 9.98e-04
+2022-05-14 05:48:29,673 INFO [train.py:812] (0/8) Epoch 7, batch 4050, loss[loss=0.1825, simple_loss=0.2705, pruned_loss=0.04729, over 7159.00 frames.], tot_loss[loss=0.1972, simple_loss=0.279, pruned_loss=0.05769, over 1428657.79 frames.], batch size: 18, lr: 9.98e-04
+2022-05-14 05:49:28,795 INFO [train.py:812] (0/8) Epoch 7, batch 4100, loss[loss=0.2164, simple_loss=0.3003, pruned_loss=0.06624, over 7443.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2795, pruned_loss=0.05854, over 1424476.39 frames.], batch size: 22, lr: 9.97e-04
+2022-05-14 05:50:26,075 INFO [train.py:812] (0/8) Epoch 7, batch 4150, loss[loss=0.2128, simple_loss=0.3091, pruned_loss=0.05825, over 7202.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2793, pruned_loss=0.0582, over 1425611.96 frames.], batch size: 23, lr: 9.96e-04
+2022-05-14 05:51:25,276 INFO [train.py:812] (0/8) Epoch 7, batch 4200, loss[loss=0.1918, simple_loss=0.2569, pruned_loss=0.06333, over 7285.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2781, pruned_loss=0.05743, over 1427828.43 frames.], batch size: 17, lr: 9.95e-04
+2022-05-14 05:52:24,619 INFO [train.py:812] (0/8) Epoch 7, batch 4250, loss[loss=0.187, simple_loss=0.2706, pruned_loss=0.05169, over 7430.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2787, pruned_loss=0.0574, over 1422086.00 frames.], batch size: 20, lr: 9.95e-04
+2022-05-14 05:53:23,914 INFO [train.py:812] (0/8) Epoch 7, batch 4300, loss[loss=0.1909, simple_loss=0.2851, pruned_loss=0.04838, over 7229.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2807, pruned_loss=0.05796, over 1416247.33 frames.], batch size: 20, lr: 9.94e-04
+2022-05-14 05:54:23,292 INFO [train.py:812] (0/8) Epoch 7, batch 4350, loss[loss=0.1868, simple_loss=0.278, pruned_loss=0.04784, over 6516.00 frames.], tot_loss[loss=0.199, simple_loss=0.2814, pruned_loss=0.05833, over 1410386.88 frames.], batch size: 38, lr: 9.93e-04
+2022-05-14 05:55:22,290 INFO [train.py:812] (0/8) Epoch 7, batch 4400, loss[loss=0.267, simple_loss=0.3516, pruned_loss=0.09123, over 6826.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2813, pruned_loss=0.05853, over 1411374.76 frames.], batch size: 31, lr: 9.92e-04
+2022-05-14 05:56:20,593 INFO [train.py:812] (0/8) Epoch 7, batch 4450, loss[loss=0.2225, simple_loss=0.3119, pruned_loss=0.06651, over 7204.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2818, pruned_loss=0.05895, over 1406743.87 frames.], batch size: 22, lr: 9.92e-04
+2022-05-14 05:56:45,820 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-32000.pt
+2022-05-14 05:57:24,495 INFO [train.py:812] (0/8) Epoch 7, batch 4500, loss[loss=0.2125, simple_loss=0.2967, pruned_loss=0.06416, over 7202.00 frames.], tot_loss[loss=0.201, simple_loss=0.2828, pruned_loss=0.05958, over 1404259.15 frames.], batch size: 22, lr: 9.91e-04
+2022-05-14 05:58:22,213 INFO [train.py:812] (0/8) Epoch 7, batch 4550, loss[loss=0.2814, simple_loss=0.348, pruned_loss=0.1074, over 4717.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2846, pruned_loss=0.06038, over 1389573.89 frames.], batch size: 53, lr: 9.90e-04
+2022-05-14 05:59:07,222 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-7.pt
+2022-05-14 05:59:32,592 INFO [train.py:812] (0/8) Epoch 8, batch 0, loss[loss=0.1788, simple_loss=0.2726, pruned_loss=0.04246, over 7331.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2726, pruned_loss=0.04246, over 7331.00 frames.], batch size: 22, lr: 9.49e-04
+2022-05-14 06:00:31,157 INFO [train.py:812] (0/8) Epoch 8, batch 50, loss[loss=0.1833, simple_loss=0.2576, pruned_loss=0.05445, over 7147.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2803, pruned_loss=0.05591, over 320774.19 frames.], batch size: 17, lr: 9.48e-04
+2022-05-14 06:01:30,397 INFO [train.py:812] (0/8) Epoch 8, batch 100, loss[loss=0.2042, simple_loss=0.2891, pruned_loss=0.05968, over 7278.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2774, pruned_loss=0.05383, over 568866.91 frames.], batch size: 25, lr: 9.48e-04
+2022-05-14 06:02:29,678 INFO [train.py:812] (0/8) Epoch 8, batch 150, loss[loss=0.184, simple_loss=0.2621, pruned_loss=0.05298, over 7116.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2763, pruned_loss=0.05411, over 758204.88 frames.], batch size: 21, lr: 9.47e-04
+2022-05-14 06:03:26,761 INFO [train.py:812] (0/8) Epoch 8, batch 200, loss[loss=0.196, simple_loss=0.2798, pruned_loss=0.05614, over 7198.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2776, pruned_loss=0.05496, over 907247.38 frames.], batch size: 22, lr: 9.46e-04
+2022-05-14 06:04:24,430 INFO [train.py:812] (0/8) Epoch 8, batch 250, loss[loss=0.1905, simple_loss=0.2827, pruned_loss=0.04912, over 7114.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2784, pruned_loss=0.05487, over 1020715.68 frames.], batch size: 21, lr: 9.46e-04
+2022-05-14 06:05:21,326 INFO [train.py:812] (0/8) Epoch 8, batch 300, loss[loss=0.1811, simple_loss=0.2613, pruned_loss=0.05042, over 7071.00 frames.], tot_loss[loss=0.1949, simple_loss=0.279, pruned_loss=0.05541, over 1106000.92 frames.], batch size: 18, lr: 9.45e-04
+2022-05-14 06:06:19,952 INFO [train.py:812] (0/8) Epoch 8, batch 350, loss[loss=0.2427, simple_loss=0.3264, pruned_loss=0.07952, over 7115.00 frames.], tot_loss[loss=0.1954, simple_loss=0.279, pruned_loss=0.05589, over 1177735.17 frames.], batch size: 21, lr: 9.44e-04
+2022-05-14 06:07:19,568 INFO [train.py:812] (0/8) Epoch 8, batch 400, loss[loss=0.2691, simple_loss=0.3186, pruned_loss=0.1098, over 4949.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2797, pruned_loss=0.05667, over 1231673.76 frames.], batch size: 52, lr: 9.43e-04
+2022-05-14 06:08:18,802 INFO [train.py:812] (0/8) Epoch 8, batch 450, loss[loss=0.1762, simple_loss=0.2572, pruned_loss=0.04765, over 6803.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2788, pruned_loss=0.05642, over 1272379.34 frames.], batch size: 15, lr: 9.43e-04
+2022-05-14 06:09:18,365 INFO [train.py:812] (0/8) Epoch 8, batch 500, loss[loss=0.1921, simple_loss=0.2816, pruned_loss=0.05125, over 7188.00 frames.], tot_loss[loss=0.195, simple_loss=0.2777, pruned_loss=0.05614, over 1305553.83 frames.], batch size: 23, lr: 9.42e-04
+2022-05-14 06:10:16,957 INFO [train.py:812] (0/8) Epoch 8, batch 550, loss[loss=0.2204, simple_loss=0.2946, pruned_loss=0.07305, over 7206.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2774, pruned_loss=0.05599, over 1333607.38 frames.], batch size: 23, lr: 9.41e-04
+2022-05-14 06:11:16,908 INFO [train.py:812] (0/8) Epoch 8, batch 600, loss[loss=0.2094, simple_loss=0.2887, pruned_loss=0.06505, over 7213.00 frames.], tot_loss[loss=0.196, simple_loss=0.2789, pruned_loss=0.05655, over 1353275.37 frames.], batch size: 21, lr: 9.41e-04
+2022-05-14 06:12:15,259 INFO [train.py:812] (0/8) Epoch 8, batch 650, loss[loss=0.2017, simple_loss=0.2834, pruned_loss=0.06002, over 7262.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2785, pruned_loss=0.05639, over 1368517.46 frames.], batch size: 19, lr: 9.40e-04
+2022-05-14 06:13:14,183 INFO [train.py:812] (0/8) Epoch 8, batch 700, loss[loss=0.2193, simple_loss=0.2852, pruned_loss=0.07669, over 5140.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2797, pruned_loss=0.05692, over 1376366.56 frames.], batch size: 52, lr: 9.39e-04
+2022-05-14 06:14:13,341 INFO [train.py:812] (0/8) Epoch 8, batch 750, loss[loss=0.1712, simple_loss=0.2547, pruned_loss=0.04382, over 7361.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2791, pruned_loss=0.05696, over 1384515.42 frames.], batch size: 19, lr: 9.39e-04
+2022-05-14 06:15:12,881 INFO [train.py:812] (0/8) Epoch 8, batch 800, loss[loss=0.2016, simple_loss=0.284, pruned_loss=0.05959, over 6552.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2802, pruned_loss=0.05697, over 1389570.35 frames.], batch size: 38, lr: 9.38e-04
+2022-05-14 06:16:12,301 INFO [train.py:812] (0/8) Epoch 8, batch 850, loss[loss=0.1647, simple_loss=0.2416, pruned_loss=0.0439, over 7412.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2781, pruned_loss=0.05575, over 1398543.40 frames.], batch size: 18, lr: 9.37e-04
+2022-05-14 06:17:11,307 INFO [train.py:812] (0/8) Epoch 8, batch 900, loss[loss=0.2229, simple_loss=0.3031, pruned_loss=0.07134, over 6739.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2786, pruned_loss=0.05632, over 1398178.40 frames.], batch size: 31, lr: 9.36e-04
+2022-05-14 06:18:09,032 INFO [train.py:812] (0/8) Epoch 8, batch 950, loss[loss=0.1879, simple_loss=0.2687, pruned_loss=0.05355, over 7239.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2789, pruned_loss=0.05615, over 1404323.51 frames.], batch size: 20, lr: 9.36e-04
+2022-05-14 06:19:08,070 INFO [train.py:812] (0/8) Epoch 8, batch 1000, loss[loss=0.225, simple_loss=0.2908, pruned_loss=0.0796, over 7229.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2801, pruned_loss=0.05655, over 1408652.09 frames.], batch size: 21, lr: 9.35e-04
+2022-05-14 06:20:06,292 INFO [train.py:812] (0/8) Epoch 8, batch 1050, loss[loss=0.1652, simple_loss=0.2408, pruned_loss=0.04473, over 7144.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2808, pruned_loss=0.05682, over 1406094.45 frames.], batch size: 17, lr: 9.34e-04
+2022-05-14 06:21:04,833 INFO [train.py:812] (0/8) Epoch 8, batch 1100, loss[loss=0.2263, simple_loss=0.3057, pruned_loss=0.07348, over 7202.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2796, pruned_loss=0.05679, over 1409613.65 frames.], batch size: 22, lr: 9.34e-04
+2022-05-14 06:22:02,868 INFO [train.py:812] (0/8) Epoch 8, batch 1150, loss[loss=0.1918, simple_loss=0.2683, pruned_loss=0.05769, over 5152.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2799, pruned_loss=0.05662, over 1415700.06 frames.], batch size: 52, lr: 9.33e-04
+2022-05-14 06:23:10,858 INFO [train.py:812] (0/8) Epoch 8, batch 1200, loss[loss=0.1796, simple_loss=0.2783, pruned_loss=0.04044, over 7156.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2799, pruned_loss=0.05669, over 1419766.65 frames.], batch size: 20, lr: 9.32e-04
+2022-05-14 06:24:10,073 INFO [train.py:812] (0/8) Epoch 8, batch 1250, loss[loss=0.173, simple_loss=0.263, pruned_loss=0.04148, over 7282.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2783, pruned_loss=0.05599, over 1418991.71 frames.], batch size: 18, lr: 9.32e-04
+2022-05-14 06:25:09,376 INFO [train.py:812] (0/8) Epoch 8, batch 1300, loss[loss=0.2115, simple_loss=0.2859, pruned_loss=0.0685, over 7150.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2784, pruned_loss=0.05601, over 1415802.77 frames.], batch size: 20, lr: 9.31e-04
+2022-05-14 06:26:08,271 INFO [train.py:812] (0/8) Epoch 8, batch 1350, loss[loss=0.2128, simple_loss=0.2875, pruned_loss=0.06907, over 7155.00 frames.], tot_loss[loss=0.1961, simple_loss=0.279, pruned_loss=0.05664, over 1414777.20 frames.], batch size: 19, lr: 9.30e-04
+2022-05-14 06:27:08,003 INFO [train.py:812] (0/8) Epoch 8, batch 1400, loss[loss=0.1683, simple_loss=0.2505, pruned_loss=0.04301, over 7286.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2786, pruned_loss=0.05611, over 1416523.83 frames.], batch size: 18, lr: 9.30e-04
+2022-05-14 06:28:06,825 INFO [train.py:812] (0/8) Epoch 8, batch 1450, loss[loss=0.1968, simple_loss=0.2722, pruned_loss=0.06076, over 7182.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2785, pruned_loss=0.05632, over 1416293.82 frames.], batch size: 18, lr: 9.29e-04
+2022-05-14 06:29:06,641 INFO [train.py:812] (0/8) Epoch 8, batch 1500, loss[loss=0.1845, simple_loss=0.2672, pruned_loss=0.05084, over 7433.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2773, pruned_loss=0.05573, over 1415460.99 frames.], batch size: 18, lr: 9.28e-04
+2022-05-14 06:30:05,620 INFO [train.py:812] (0/8) Epoch 8, batch 1550, loss[loss=0.203, simple_loss=0.2812, pruned_loss=0.06242, over 7215.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2764, pruned_loss=0.05465, over 1420516.03 frames.], batch size: 22, lr: 9.28e-04
+2022-05-14 06:31:05,205 INFO [train.py:812] (0/8) Epoch 8, batch 1600, loss[loss=0.2302, simple_loss=0.3117, pruned_loss=0.0743, over 6300.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2774, pruned_loss=0.05493, over 1421078.89 frames.], batch size: 37, lr: 9.27e-04
+2022-05-14 06:32:04,366 INFO [train.py:812] (0/8) Epoch 8, batch 1650, loss[loss=0.2178, simple_loss=0.293, pruned_loss=0.0713, over 7286.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2783, pruned_loss=0.05551, over 1419747.46 frames.], batch size: 24, lr: 9.26e-04
+2022-05-14 06:33:04,111 INFO [train.py:812] (0/8) Epoch 8, batch 1700, loss[loss=0.1841, simple_loss=0.2772, pruned_loss=0.04548, over 7323.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2786, pruned_loss=0.05545, over 1419575.93 frames.], batch size: 21, lr: 9.26e-04
+2022-05-14 06:34:03,594 INFO [train.py:812] (0/8) Epoch 8, batch 1750, loss[loss=0.2086, simple_loss=0.2897, pruned_loss=0.06375, over 7340.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2781, pruned_loss=0.05564, over 1420497.62 frames.], batch size: 22, lr: 9.25e-04
+2022-05-14 06:35:12,515 INFO [train.py:812] (0/8) Epoch 8, batch 1800, loss[loss=0.1945, simple_loss=0.2835, pruned_loss=0.05269, over 7331.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2768, pruned_loss=0.05521, over 1421744.65 frames.], batch size: 22, lr: 9.24e-04
+2022-05-14 06:36:21,366 INFO [train.py:812] (0/8) Epoch 8, batch 1850, loss[loss=0.1855, simple_loss=0.2813, pruned_loss=0.04487, over 7235.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2782, pruned_loss=0.05576, over 1423215.76 frames.], batch size: 20, lr: 9.24e-04
+2022-05-14 06:37:30,724 INFO [train.py:812] (0/8) Epoch 8, batch 1900, loss[loss=0.1938, simple_loss=0.2804, pruned_loss=0.05362, over 7331.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2777, pruned_loss=0.0558, over 1421488.60 frames.], batch size: 25, lr: 9.23e-04
+2022-05-14 06:38:48,462 INFO [train.py:812] (0/8) Epoch 8, batch 1950, loss[loss=0.2116, simple_loss=0.2788, pruned_loss=0.07216, over 7011.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2773, pruned_loss=0.05567, over 1426338.43 frames.], batch size: 16, lr: 9.22e-04
+2022-05-14 06:40:06,955 INFO [train.py:812] (0/8) Epoch 8, batch 2000, loss[loss=0.2408, simple_loss=0.3178, pruned_loss=0.08187, over 7117.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2777, pruned_loss=0.05624, over 1427218.11 frames.], batch size: 21, lr: 9.22e-04
+2022-05-14 06:41:06,018 INFO [train.py:812] (0/8) Epoch 8, batch 2050, loss[loss=0.2389, simple_loss=0.2969, pruned_loss=0.09041, over 4960.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2787, pruned_loss=0.05671, over 1421068.68 frames.], batch size: 52, lr: 9.21e-04
+2022-05-14 06:42:04,901 INFO [train.py:812] (0/8) Epoch 8, batch 2100, loss[loss=0.2037, simple_loss=0.2814, pruned_loss=0.06304, over 7232.00 frames.], tot_loss[loss=0.1962, simple_loss=0.279, pruned_loss=0.05674, over 1417750.09 frames.], batch size: 20, lr: 9.20e-04
+2022-05-14 06:43:03,994 INFO [train.py:812] (0/8) Epoch 8, batch 2150, loss[loss=0.1912, simple_loss=0.2825, pruned_loss=0.04998, over 7191.00 frames.], tot_loss[loss=0.1966, simple_loss=0.279, pruned_loss=0.05707, over 1419444.56 frames.], batch size: 22, lr: 9.20e-04
+2022-05-14 06:44:02,972 INFO [train.py:812] (0/8) Epoch 8, batch 2200, loss[loss=0.2584, simple_loss=0.3444, pruned_loss=0.08615, over 7296.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2784, pruned_loss=0.05723, over 1417416.95 frames.], batch size: 24, lr: 9.19e-04
+2022-05-14 06:45:01,881 INFO [train.py:812] (0/8) Epoch 8, batch 2250, loss[loss=0.1876, simple_loss=0.272, pruned_loss=0.05155, over 7184.00 frames.], tot_loss[loss=0.1961, simple_loss=0.278, pruned_loss=0.05709, over 1411893.66 frames.], batch size: 23, lr: 9.18e-04
+2022-05-14 06:46:00,790 INFO [train.py:812] (0/8) Epoch 8, batch 2300, loss[loss=0.1561, simple_loss=0.2493, pruned_loss=0.03149, over 7401.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2777, pruned_loss=0.05659, over 1412147.78 frames.], batch size: 18, lr: 9.18e-04
+2022-05-14 06:46:59,517 INFO [train.py:812] (0/8) Epoch 8, batch 2350, loss[loss=0.2032, simple_loss=0.2682, pruned_loss=0.06908, over 7071.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2783, pruned_loss=0.05664, over 1412095.32 frames.], batch size: 18, lr: 9.17e-04
+2022-05-14 06:47:58,466 INFO [train.py:812] (0/8) Epoch 8, batch 2400, loss[loss=0.1745, simple_loss=0.2612, pruned_loss=0.04395, over 7262.00 frames.], tot_loss[loss=0.195, simple_loss=0.2778, pruned_loss=0.05613, over 1415836.47 frames.], batch size: 19, lr: 9.16e-04
+2022-05-14 06:48:57,529 INFO [train.py:812] (0/8) Epoch 8, batch 2450, loss[loss=0.218, simple_loss=0.3027, pruned_loss=0.06671, over 7317.00 frames.], tot_loss[loss=0.195, simple_loss=0.2779, pruned_loss=0.05604, over 1422472.55 frames.], batch size: 24, lr: 9.16e-04
+2022-05-14 06:49:57,067 INFO [train.py:812] (0/8) Epoch 8, batch 2500, loss[loss=0.2262, simple_loss=0.3063, pruned_loss=0.07302, over 7317.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2774, pruned_loss=0.05574, over 1420222.50 frames.], batch size: 21, lr: 9.15e-04
+2022-05-14 06:50:55,691 INFO [train.py:812] (0/8) Epoch 8, batch 2550, loss[loss=0.1909, simple_loss=0.2716, pruned_loss=0.05512, over 7360.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2776, pruned_loss=0.05597, over 1424592.50 frames.], batch size: 19, lr: 9.14e-04
+2022-05-14 06:51:54,442 INFO [train.py:812] (0/8) Epoch 8, batch 2600, loss[loss=0.2114, simple_loss=0.2787, pruned_loss=0.07208, over 6789.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2779, pruned_loss=0.05635, over 1424921.81 frames.], batch size: 15, lr: 9.14e-04
+2022-05-14 06:52:51,854 INFO [train.py:812] (0/8) Epoch 8, batch 2650, loss[loss=0.1865, simple_loss=0.2788, pruned_loss=0.04711, over 7120.00 frames.], tot_loss[loss=0.194, simple_loss=0.2772, pruned_loss=0.05542, over 1426161.01 frames.], batch size: 21, lr: 9.13e-04
+2022-05-14 06:53:49,760 INFO [train.py:812] (0/8) Epoch 8, batch 2700, loss[loss=0.179, simple_loss=0.2536, pruned_loss=0.05225, over 6835.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2765, pruned_loss=0.05515, over 1428413.94 frames.], batch size: 15, lr: 9.12e-04
+2022-05-14 06:54:48,259 INFO [train.py:812] (0/8) Epoch 8, batch 2750, loss[loss=0.2169, simple_loss=0.2842, pruned_loss=0.0748, over 6995.00 frames.], tot_loss[loss=0.193, simple_loss=0.2759, pruned_loss=0.05501, over 1427693.70 frames.], batch size: 16, lr: 9.12e-04
+2022-05-14 06:55:46,857 INFO [train.py:812] (0/8) Epoch 8, batch 2800, loss[loss=0.1907, simple_loss=0.2753, pruned_loss=0.05302, over 7155.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2761, pruned_loss=0.05487, over 1428183.49 frames.], batch size: 20, lr: 9.11e-04
+2022-05-14 06:56:44,501 INFO [train.py:812] (0/8) Epoch 8, batch 2850, loss[loss=0.2602, simple_loss=0.338, pruned_loss=0.09118, over 7216.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2767, pruned_loss=0.05541, over 1426401.73 frames.], batch size: 22, lr: 9.11e-04
+2022-05-14 06:57:43,811 INFO [train.py:812] (0/8) Epoch 8, batch 2900, loss[loss=0.1722, simple_loss=0.2578, pruned_loss=0.04326, over 7126.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2786, pruned_loss=0.05603, over 1425811.93 frames.], batch size: 17, lr: 9.10e-04
+2022-05-14 06:58:42,823 INFO [train.py:812] (0/8) Epoch 8, batch 2950, loss[loss=0.1922, simple_loss=0.2779, pruned_loss=0.05326, over 7067.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2774, pruned_loss=0.05592, over 1424748.76 frames.], batch size: 18, lr: 9.09e-04
+2022-05-14 06:59:42,247 INFO [train.py:812] (0/8) Epoch 8, batch 3000, loss[loss=0.2343, simple_loss=0.3125, pruned_loss=0.07807, over 5237.00 frames.], tot_loss[loss=0.194, simple_loss=0.2769, pruned_loss=0.05558, over 1421481.52 frames.], batch size: 52, lr: 9.09e-04
+2022-05-14 06:59:42,248 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 06:59:50,552 INFO [train.py:841] (0/8) Epoch 8, validation: loss=0.1612, simple_loss=0.2635, pruned_loss=0.0294, over 698248.00 frames.
+2022-05-14 07:00:48,448 INFO [train.py:812] (0/8) Epoch 8, batch 3050, loss[loss=0.2237, simple_loss=0.3073, pruned_loss=0.07001, over 6687.00 frames.], tot_loss[loss=0.1945, simple_loss=0.277, pruned_loss=0.05597, over 1414031.27 frames.], batch size: 38, lr: 9.08e-04
+2022-05-14 07:01:48,158 INFO [train.py:812] (0/8) Epoch 8, batch 3100, loss[loss=0.2025, simple_loss=0.2777, pruned_loss=0.06365, over 7266.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2771, pruned_loss=0.0558, over 1418748.63 frames.], batch size: 19, lr: 9.07e-04
+2022-05-14 07:02:45,297 INFO [train.py:812] (0/8) Epoch 8, batch 3150, loss[loss=0.1852, simple_loss=0.2656, pruned_loss=0.05239, over 7427.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2767, pruned_loss=0.05608, over 1420467.79 frames.], batch size: 20, lr: 9.07e-04
+2022-05-14 07:03:44,421 INFO [train.py:812] (0/8) Epoch 8, batch 3200, loss[loss=0.1774, simple_loss=0.2636, pruned_loss=0.04562, over 7433.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2762, pruned_loss=0.05521, over 1423997.87 frames.], batch size: 20, lr: 9.06e-04
+2022-05-14 07:04:43,314 INFO [train.py:812] (0/8) Epoch 8, batch 3250, loss[loss=0.223, simple_loss=0.3063, pruned_loss=0.06979, over 7034.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2773, pruned_loss=0.05578, over 1422539.13 frames.], batch size: 28, lr: 9.05e-04
+2022-05-14 07:05:41,207 INFO [train.py:812] (0/8) Epoch 8, batch 3300, loss[loss=0.2167, simple_loss=0.3086, pruned_loss=0.06239, over 6727.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2762, pruned_loss=0.05502, over 1422641.55 frames.], batch size: 31, lr: 9.05e-04
+2022-05-14 07:06:40,365 INFO [train.py:812] (0/8) Epoch 8, batch 3350, loss[loss=0.1958, simple_loss=0.2794, pruned_loss=0.05607, over 7426.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2761, pruned_loss=0.05509, over 1420371.19 frames.], batch size: 20, lr: 9.04e-04
+2022-05-14 07:07:39,824 INFO [train.py:812] (0/8) Epoch 8, batch 3400, loss[loss=0.1746, simple_loss=0.256, pruned_loss=0.04659, over 6740.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2754, pruned_loss=0.05491, over 1419446.26 frames.], batch size: 31, lr: 9.04e-04
+2022-05-14 07:08:38,478 INFO [train.py:812] (0/8) Epoch 8, batch 3450, loss[loss=0.1713, simple_loss=0.2583, pruned_loss=0.04212, over 7405.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2774, pruned_loss=0.05586, over 1422368.91 frames.], batch size: 18, lr: 9.03e-04
+2022-05-14 07:09:37,920 INFO [train.py:812] (0/8) Epoch 8, batch 3500, loss[loss=0.1828, simple_loss=0.2711, pruned_loss=0.04729, over 7381.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2776, pruned_loss=0.05562, over 1422619.59 frames.], batch size: 23, lr: 9.02e-04
+2022-05-14 07:10:37,099 INFO [train.py:812] (0/8) Epoch 8, batch 3550, loss[loss=0.2018, simple_loss=0.2895, pruned_loss=0.05702, over 7259.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2772, pruned_loss=0.05524, over 1423741.32 frames.], batch size: 19, lr: 9.02e-04
+2022-05-14 07:11:36,661 INFO [train.py:812] (0/8) Epoch 8, batch 3600, loss[loss=0.1732, simple_loss=0.2533, pruned_loss=0.0466, over 7272.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2765, pruned_loss=0.05504, over 1420983.25 frames.], batch size: 17, lr: 9.01e-04
+2022-05-14 07:12:33,634 INFO [train.py:812] (0/8) Epoch 8, batch 3650, loss[loss=0.1833, simple_loss=0.2785, pruned_loss=0.04404, over 7408.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2772, pruned_loss=0.05534, over 1415437.87 frames.], batch size: 21, lr: 9.01e-04
+2022-05-14 07:13:32,604 INFO [train.py:812] (0/8) Epoch 8, batch 3700, loss[loss=0.2016, simple_loss=0.2807, pruned_loss=0.06125, over 7224.00 frames.], tot_loss[loss=0.193, simple_loss=0.2764, pruned_loss=0.05482, over 1419175.16 frames.], batch size: 21, lr: 9.00e-04
+2022-05-14 07:14:31,476 INFO [train.py:812] (0/8) Epoch 8, batch 3750, loss[loss=0.2038, simple_loss=0.2892, pruned_loss=0.05924, over 7162.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2763, pruned_loss=0.05513, over 1416024.02 frames.], batch size: 19, lr: 8.99e-04
+2022-05-14 07:15:30,676 INFO [train.py:812] (0/8) Epoch 8, batch 3800, loss[loss=0.1984, simple_loss=0.2851, pruned_loss=0.05579, over 7289.00 frames.], tot_loss[loss=0.194, simple_loss=0.2773, pruned_loss=0.05528, over 1419714.45 frames.], batch size: 24, lr: 8.99e-04
+2022-05-14 07:16:28,814 INFO [train.py:812] (0/8) Epoch 8, batch 3850, loss[loss=0.1825, simple_loss=0.2833, pruned_loss=0.04084, over 7205.00 frames.], tot_loss[loss=0.1942, simple_loss=0.278, pruned_loss=0.05518, over 1417696.72 frames.], batch size: 21, lr: 8.98e-04
+2022-05-14 07:17:08,106 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-36000.pt
+2022-05-14 07:17:33,253 INFO [train.py:812] (0/8) Epoch 8, batch 3900, loss[loss=0.1816, simple_loss=0.2633, pruned_loss=0.04997, over 7417.00 frames.], tot_loss[loss=0.1925, simple_loss=0.276, pruned_loss=0.05444, over 1421985.56 frames.], batch size: 20, lr: 8.97e-04
+2022-05-14 07:18:32,352 INFO [train.py:812] (0/8) Epoch 8, batch 3950, loss[loss=0.1504, simple_loss=0.2356, pruned_loss=0.03258, over 7420.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2755, pruned_loss=0.05432, over 1424899.01 frames.], batch size: 17, lr: 8.97e-04
+2022-05-14 07:19:31,319 INFO [train.py:812] (0/8) Epoch 8, batch 4000, loss[loss=0.2092, simple_loss=0.2929, pruned_loss=0.06271, over 7145.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2763, pruned_loss=0.05453, over 1424036.23 frames.], batch size: 20, lr: 8.96e-04
+2022-05-14 07:20:29,761 INFO [train.py:812] (0/8) Epoch 8, batch 4050, loss[loss=0.1882, simple_loss=0.2813, pruned_loss=0.04755, over 7407.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2762, pruned_loss=0.05443, over 1426831.64 frames.], batch size: 21, lr: 8.96e-04
+2022-05-14 07:21:29,536 INFO [train.py:812] (0/8) Epoch 8, batch 4100, loss[loss=0.1615, simple_loss=0.2445, pruned_loss=0.03925, over 7277.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2764, pruned_loss=0.0543, over 1419948.92 frames.], batch size: 17, lr: 8.95e-04
+2022-05-14 07:22:28,495 INFO [train.py:812] (0/8) Epoch 8, batch 4150, loss[loss=0.2081, simple_loss=0.2937, pruned_loss=0.06122, over 7340.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2777, pruned_loss=0.05521, over 1414365.46 frames.], batch size: 22, lr: 8.94e-04
+2022-05-14 07:23:28,036 INFO [train.py:812] (0/8) Epoch 8, batch 4200, loss[loss=0.1985, simple_loss=0.2841, pruned_loss=0.05646, over 7142.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2779, pruned_loss=0.05511, over 1417133.37 frames.], batch size: 20, lr: 8.94e-04
+2022-05-14 07:24:27,286 INFO [train.py:812] (0/8) Epoch 8, batch 4250, loss[loss=0.1945, simple_loss=0.2816, pruned_loss=0.05369, over 7201.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2772, pruned_loss=0.05477, over 1420615.05 frames.], batch size: 22, lr: 8.93e-04
+2022-05-14 07:25:26,239 INFO [train.py:812] (0/8) Epoch 8, batch 4300, loss[loss=0.1713, simple_loss=0.262, pruned_loss=0.04032, over 7323.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2759, pruned_loss=0.05442, over 1419015.87 frames.], batch size: 21, lr: 8.93e-04
+2022-05-14 07:26:25,340 INFO [train.py:812] (0/8) Epoch 8, batch 4350, loss[loss=0.2176, simple_loss=0.3, pruned_loss=0.06765, over 7121.00 frames.], tot_loss[loss=0.191, simple_loss=0.2748, pruned_loss=0.05364, over 1414431.18 frames.], batch size: 21, lr: 8.92e-04
+2022-05-14 07:27:24,383 INFO [train.py:812] (0/8) Epoch 8, batch 4400, loss[loss=0.2499, simple_loss=0.3239, pruned_loss=0.08792, over 7015.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2744, pruned_loss=0.05365, over 1417531.60 frames.], batch size: 28, lr: 8.91e-04
+2022-05-14 07:28:23,663 INFO [train.py:812] (0/8) Epoch 8, batch 4450, loss[loss=0.1993, simple_loss=0.281, pruned_loss=0.0588, over 7333.00 frames.], tot_loss[loss=0.191, simple_loss=0.2743, pruned_loss=0.05385, over 1416638.00 frames.], batch size: 20, lr: 8.91e-04
+2022-05-14 07:29:23,660 INFO [train.py:812] (0/8) Epoch 8, batch 4500, loss[loss=0.2113, simple_loss=0.2895, pruned_loss=0.0666, over 7169.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2733, pruned_loss=0.05342, over 1414884.95 frames.], batch size: 18, lr: 8.90e-04
+2022-05-14 07:30:22,971 INFO [train.py:812] (0/8) Epoch 8, batch 4550, loss[loss=0.1846, simple_loss=0.2541, pruned_loss=0.0575, over 7274.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2726, pruned_loss=0.05416, over 1397950.53 frames.], batch size: 17, lr: 8.90e-04
+2022-05-14 07:31:08,578 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-8.pt
+2022-05-14 07:31:33,301 INFO [train.py:812] (0/8) Epoch 9, batch 0, loss[loss=0.2181, simple_loss=0.2993, pruned_loss=0.06842, over 7190.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2993, pruned_loss=0.06842, over 7190.00 frames.], batch size: 23, lr: 8.54e-04
+2022-05-14 07:32:31,242 INFO [train.py:812] (0/8) Epoch 9, batch 50, loss[loss=0.2041, simple_loss=0.2981, pruned_loss=0.05498, over 7044.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2768, pruned_loss=0.05548, over 318982.26 frames.], batch size: 28, lr: 8.53e-04
+2022-05-14 07:33:31,083 INFO [train.py:812] (0/8) Epoch 9, batch 100, loss[loss=0.1637, simple_loss=0.258, pruned_loss=0.03473, over 7241.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2741, pruned_loss=0.05359, over 566750.51 frames.], batch size: 20, lr: 8.53e-04
+2022-05-14 07:34:29,325 INFO [train.py:812] (0/8) Epoch 9, batch 150, loss[loss=0.2395, simple_loss=0.3166, pruned_loss=0.0812, over 4991.00 frames.], tot_loss[loss=0.19, simple_loss=0.2743, pruned_loss=0.05287, over 754668.79 frames.], batch size: 52, lr: 8.52e-04
+2022-05-14 07:35:29,137 INFO [train.py:812] (0/8) Epoch 9, batch 200, loss[loss=0.2219, simple_loss=0.299, pruned_loss=0.07235, over 7215.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2745, pruned_loss=0.05311, over 903026.48 frames.], batch size: 22, lr: 8.51e-04
+2022-05-14 07:36:28,080 INFO [train.py:812] (0/8) Epoch 9, batch 250, loss[loss=0.1794, simple_loss=0.2583, pruned_loss=0.05031, over 7438.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2739, pruned_loss=0.05248, over 1018923.74 frames.], batch size: 20, lr: 8.51e-04
+2022-05-14 07:37:25,193 INFO [train.py:812] (0/8) Epoch 9, batch 300, loss[loss=0.1944, simple_loss=0.2746, pruned_loss=0.0571, over 7337.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2745, pruned_loss=0.05301, over 1104921.08 frames.], batch size: 22, lr: 8.50e-04
+2022-05-14 07:38:24,948 INFO [train.py:812] (0/8) Epoch 9, batch 350, loss[loss=0.1992, simple_loss=0.281, pruned_loss=0.05873, over 7167.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2722, pruned_loss=0.05212, over 1178485.42 frames.], batch size: 19, lr: 8.50e-04
+2022-05-14 07:39:24,185 INFO [train.py:812] (0/8) Epoch 9, batch 400, loss[loss=0.1647, simple_loss=0.251, pruned_loss=0.03921, over 7130.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2732, pruned_loss=0.05262, over 1237548.71 frames.], batch size: 17, lr: 8.49e-04
+2022-05-14 07:40:21,417 INFO [train.py:812] (0/8) Epoch 9, batch 450, loss[loss=0.1687, simple_loss=0.2515, pruned_loss=0.04298, over 7248.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2731, pruned_loss=0.05261, over 1278439.98 frames.], batch size: 19, lr: 8.49e-04
+2022-05-14 07:41:19,786 INFO [train.py:812] (0/8) Epoch 9, batch 500, loss[loss=0.1559, simple_loss=0.242, pruned_loss=0.0349, over 7413.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2742, pruned_loss=0.05277, over 1310632.45 frames.], batch size: 18, lr: 8.48e-04
+2022-05-14 07:42:19,034 INFO [train.py:812] (0/8) Epoch 9, batch 550, loss[loss=0.1704, simple_loss=0.243, pruned_loss=0.04896, over 7054.00 frames.], tot_loss[loss=0.1888, simple_loss=0.273, pruned_loss=0.05225, over 1338812.45 frames.], batch size: 18, lr: 8.48e-04
+2022-05-14 07:43:17,528 INFO [train.py:812] (0/8) Epoch 9, batch 600, loss[loss=0.2028, simple_loss=0.2748, pruned_loss=0.06535, over 7070.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2733, pruned_loss=0.05257, over 1360396.84 frames.], batch size: 18, lr: 8.47e-04
+2022-05-14 07:44:16,643 INFO [train.py:812] (0/8) Epoch 9, batch 650, loss[loss=0.1814, simple_loss=0.2695, pruned_loss=0.04663, over 7360.00 frames.], tot_loss[loss=0.1891, simple_loss=0.273, pruned_loss=0.05255, over 1373653.11 frames.], batch size: 19, lr: 8.46e-04
+2022-05-14 07:45:15,377 INFO [train.py:812] (0/8) Epoch 9, batch 700, loss[loss=0.2007, simple_loss=0.2814, pruned_loss=0.06001, over 7435.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2729, pruned_loss=0.05217, over 1386418.96 frames.], batch size: 20, lr: 8.46e-04
+2022-05-14 07:46:13,731 INFO [train.py:812] (0/8) Epoch 9, batch 750, loss[loss=0.1669, simple_loss=0.2553, pruned_loss=0.0392, over 7166.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2744, pruned_loss=0.05303, over 1389385.99 frames.], batch size: 18, lr: 8.45e-04
+2022-05-14 07:47:13,059 INFO [train.py:812] (0/8) Epoch 9, batch 800, loss[loss=0.2248, simple_loss=0.3068, pruned_loss=0.07142, over 7382.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2739, pruned_loss=0.05289, over 1396095.42 frames.], batch size: 23, lr: 8.45e-04
+2022-05-14 07:48:11,322 INFO [train.py:812] (0/8) Epoch 9, batch 850, loss[loss=0.1616, simple_loss=0.2488, pruned_loss=0.03724, over 7310.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2744, pruned_loss=0.05334, over 1401291.18 frames.], batch size: 21, lr: 8.44e-04
+2022-05-14 07:49:11,283 INFO [train.py:812] (0/8) Epoch 9, batch 900, loss[loss=0.2217, simple_loss=0.3014, pruned_loss=0.07103, over 7215.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2746, pruned_loss=0.05276, over 1410842.01 frames.], batch size: 21, lr: 8.44e-04
+2022-05-14 07:50:10,499 INFO [train.py:812] (0/8) Epoch 9, batch 950, loss[loss=0.1747, simple_loss=0.2742, pruned_loss=0.03761, over 7327.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2749, pruned_loss=0.05304, over 1409086.09 frames.], batch size: 20, lr: 8.43e-04
+2022-05-14 07:51:10,496 INFO [train.py:812] (0/8) Epoch 9, batch 1000, loss[loss=0.1621, simple_loss=0.2499, pruned_loss=0.03718, over 7432.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2749, pruned_loss=0.05343, over 1412626.32 frames.], batch size: 20, lr: 8.43e-04
+2022-05-14 07:52:08,961 INFO [train.py:812] (0/8) Epoch 9, batch 1050, loss[loss=0.1759, simple_loss=0.2614, pruned_loss=0.04519, over 7271.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2754, pruned_loss=0.05351, over 1417670.64 frames.], batch size: 19, lr: 8.42e-04
+2022-05-14 07:53:07,742 INFO [train.py:812] (0/8) Epoch 9, batch 1100, loss[loss=0.1498, simple_loss=0.2328, pruned_loss=0.03345, over 7284.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2766, pruned_loss=0.05378, over 1420314.59 frames.], batch size: 17, lr: 8.41e-04
+2022-05-14 07:54:04,929 INFO [train.py:812] (0/8) Epoch 9, batch 1150, loss[loss=0.2014, simple_loss=0.2941, pruned_loss=0.05434, over 7322.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2753, pruned_loss=0.05322, over 1420725.65 frames.], batch size: 25, lr: 8.41e-04
+2022-05-14 07:55:04,993 INFO [train.py:812] (0/8) Epoch 9, batch 1200, loss[loss=0.191, simple_loss=0.2759, pruned_loss=0.05299, over 7446.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2752, pruned_loss=0.05298, over 1420806.74 frames.], batch size: 20, lr: 8.40e-04
+2022-05-14 07:56:02,844 INFO [train.py:812] (0/8) Epoch 9, batch 1250, loss[loss=0.1698, simple_loss=0.24, pruned_loss=0.04977, over 6845.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2751, pruned_loss=0.05332, over 1416696.98 frames.], batch size: 15, lr: 8.40e-04
+2022-05-14 07:57:02,080 INFO [train.py:812] (0/8) Epoch 9, batch 1300, loss[loss=0.2253, simple_loss=0.3169, pruned_loss=0.06687, over 7151.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2749, pruned_loss=0.05308, over 1413236.54 frames.], batch size: 19, lr: 8.39e-04
+2022-05-14 07:58:01,342 INFO [train.py:812] (0/8) Epoch 9, batch 1350, loss[loss=0.1993, simple_loss=0.282, pruned_loss=0.05832, over 7438.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2746, pruned_loss=0.05297, over 1417741.87 frames.], batch size: 20, lr: 8.39e-04
+2022-05-14 07:59:00,870 INFO [train.py:812] (0/8) Epoch 9, batch 1400, loss[loss=0.1779, simple_loss=0.2678, pruned_loss=0.04397, over 7207.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2748, pruned_loss=0.05353, over 1414879.05 frames.], batch size: 21, lr: 8.38e-04
+2022-05-14 07:59:57,894 INFO [train.py:812] (0/8) Epoch 9, batch 1450, loss[loss=0.2001, simple_loss=0.2842, pruned_loss=0.05802, over 7314.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2734, pruned_loss=0.05281, over 1420079.54 frames.], batch size: 21, lr: 8.38e-04
+2022-05-14 08:00:55,529 INFO [train.py:812] (0/8) Epoch 9, batch 1500, loss[loss=0.2065, simple_loss=0.296, pruned_loss=0.05856, over 7238.00 frames.], tot_loss[loss=0.1896, simple_loss=0.274, pruned_loss=0.05267, over 1422759.60 frames.], batch size: 20, lr: 8.37e-04
+2022-05-14 08:01:53,802 INFO [train.py:812] (0/8) Epoch 9, batch 1550, loss[loss=0.2065, simple_loss=0.2939, pruned_loss=0.05959, over 7212.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2734, pruned_loss=0.0524, over 1422281.91 frames.], batch size: 22, lr: 8.37e-04
+2022-05-14 08:02:52,002 INFO [train.py:812] (0/8) Epoch 9, batch 1600, loss[loss=0.1792, simple_loss=0.2666, pruned_loss=0.04588, over 7061.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2738, pruned_loss=0.05263, over 1419612.84 frames.], batch size: 18, lr: 8.36e-04
+2022-05-14 08:03:49,575 INFO [train.py:812] (0/8) Epoch 9, batch 1650, loss[loss=0.1847, simple_loss=0.2756, pruned_loss=0.04689, over 7118.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2744, pruned_loss=0.05292, over 1420459.13 frames.], batch size: 21, lr: 8.35e-04
+2022-05-14 08:04:47,973 INFO [train.py:812] (0/8) Epoch 9, batch 1700, loss[loss=0.1898, simple_loss=0.2778, pruned_loss=0.05094, over 7145.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2744, pruned_loss=0.05268, over 1419177.42 frames.], batch size: 20, lr: 8.35e-04
+2022-05-14 08:05:46,614 INFO [train.py:812] (0/8) Epoch 9, batch 1750, loss[loss=0.2048, simple_loss=0.2942, pruned_loss=0.05776, over 7314.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2743, pruned_loss=0.05299, over 1420531.03 frames.], batch size: 21, lr: 8.34e-04
+2022-05-14 08:06:45,600 INFO [train.py:812] (0/8) Epoch 9, batch 1800, loss[loss=0.1673, simple_loss=0.2553, pruned_loss=0.03967, over 7242.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2745, pruned_loss=0.0532, over 1417283.33 frames.], batch size: 20, lr: 8.34e-04
+2022-05-14 08:07:44,988 INFO [train.py:812] (0/8) Epoch 9, batch 1850, loss[loss=0.2162, simple_loss=0.2909, pruned_loss=0.0707, over 7239.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2747, pruned_loss=0.05315, over 1420761.28 frames.], batch size: 20, lr: 8.33e-04
+2022-05-14 08:08:44,855 INFO [train.py:812] (0/8) Epoch 9, batch 1900, loss[loss=0.1969, simple_loss=0.2827, pruned_loss=0.05549, over 7159.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2751, pruned_loss=0.0534, over 1419246.03 frames.], batch size: 19, lr: 8.33e-04
+2022-05-14 08:09:44,223 INFO [train.py:812] (0/8) Epoch 9, batch 1950, loss[loss=0.189, simple_loss=0.2662, pruned_loss=0.05585, over 7106.00 frames.], tot_loss[loss=0.1904, simple_loss=0.275, pruned_loss=0.05287, over 1420511.70 frames.], batch size: 21, lr: 8.32e-04
+2022-05-14 08:10:44,116 INFO [train.py:812] (0/8) Epoch 9, batch 2000, loss[loss=0.1893, simple_loss=0.2708, pruned_loss=0.05386, over 7279.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2737, pruned_loss=0.05234, over 1422360.68 frames.], batch size: 24, lr: 8.32e-04
+2022-05-14 08:11:43,573 INFO [train.py:812] (0/8) Epoch 9, batch 2050, loss[loss=0.1493, simple_loss=0.2253, pruned_loss=0.0367, over 7269.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2737, pruned_loss=0.05288, over 1421764.51 frames.], batch size: 17, lr: 8.31e-04
+2022-05-14 08:12:43,232 INFO [train.py:812] (0/8) Epoch 9, batch 2100, loss[loss=0.1792, simple_loss=0.2569, pruned_loss=0.05074, over 7265.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2739, pruned_loss=0.05308, over 1424105.48 frames.], batch size: 19, lr: 8.31e-04
+2022-05-14 08:13:42,068 INFO [train.py:812] (0/8) Epoch 9, batch 2150, loss[loss=0.1706, simple_loss=0.2521, pruned_loss=0.04453, over 7071.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2742, pruned_loss=0.0531, over 1426060.28 frames.], batch size: 18, lr: 8.30e-04
+2022-05-14 08:14:40,897 INFO [train.py:812] (0/8) Epoch 9, batch 2200, loss[loss=0.1829, simple_loss=0.2513, pruned_loss=0.05719, over 7285.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2735, pruned_loss=0.05275, over 1423419.06 frames.], batch size: 17, lr: 8.30e-04
+2022-05-14 08:15:40,383 INFO [train.py:812] (0/8) Epoch 9, batch 2250, loss[loss=0.1962, simple_loss=0.277, pruned_loss=0.05766, over 7159.00 frames.], tot_loss[loss=0.189, simple_loss=0.2733, pruned_loss=0.05231, over 1424133.66 frames.], batch size: 18, lr: 8.29e-04
+2022-05-14 08:16:40,190 INFO [train.py:812] (0/8) Epoch 9, batch 2300, loss[loss=0.1597, simple_loss=0.252, pruned_loss=0.03364, over 7150.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2735, pruned_loss=0.05246, over 1425409.05 frames.], batch size: 20, lr: 8.29e-04
+2022-05-14 08:17:37,528 INFO [train.py:812] (0/8) Epoch 9, batch 2350, loss[loss=0.1792, simple_loss=0.2759, pruned_loss=0.0413, over 6737.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2737, pruned_loss=0.05262, over 1424097.02 frames.], batch size: 31, lr: 8.28e-04
+2022-05-14 08:18:37,026 INFO [train.py:812] (0/8) Epoch 9, batch 2400, loss[loss=0.1799, simple_loss=0.2556, pruned_loss=0.05209, over 7277.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2734, pruned_loss=0.05244, over 1424746.24 frames.], batch size: 18, lr: 8.28e-04
+2022-05-14 08:19:36,151 INFO [train.py:812] (0/8) Epoch 9, batch 2450, loss[loss=0.1749, simple_loss=0.251, pruned_loss=0.04941, over 7404.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2733, pruned_loss=0.05196, over 1425899.66 frames.], batch size: 18, lr: 8.27e-04
+2022-05-14 08:20:34,800 INFO [train.py:812] (0/8) Epoch 9, batch 2500, loss[loss=0.1949, simple_loss=0.2737, pruned_loss=0.05805, over 7214.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2729, pruned_loss=0.05159, over 1423647.30 frames.], batch size: 22, lr: 8.27e-04
+2022-05-14 08:21:44,057 INFO [train.py:812] (0/8) Epoch 9, batch 2550, loss[loss=0.2041, simple_loss=0.2824, pruned_loss=0.0629, over 7132.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2724, pruned_loss=0.05165, over 1419987.73 frames.], batch size: 17, lr: 8.26e-04
+2022-05-14 08:22:42,420 INFO [train.py:812] (0/8) Epoch 9, batch 2600, loss[loss=0.212, simple_loss=0.2925, pruned_loss=0.06571, over 7392.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2736, pruned_loss=0.05231, over 1416989.21 frames.], batch size: 23, lr: 8.25e-04
+2022-05-14 08:23:41,195 INFO [train.py:812] (0/8) Epoch 9, batch 2650, loss[loss=0.2174, simple_loss=0.2906, pruned_loss=0.07211, over 4824.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2736, pruned_loss=0.05238, over 1415831.01 frames.], batch size: 52, lr: 8.25e-04
+2022-05-14 08:24:39,373 INFO [train.py:812] (0/8) Epoch 9, batch 2700, loss[loss=0.1785, simple_loss=0.2661, pruned_loss=0.04542, over 7327.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2736, pruned_loss=0.052, over 1417541.50 frames.], batch size: 22, lr: 8.24e-04
+2022-05-14 08:25:38,209 INFO [train.py:812] (0/8) Epoch 9, batch 2750, loss[loss=0.1715, simple_loss=0.2489, pruned_loss=0.04706, over 7332.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2728, pruned_loss=0.05155, over 1422057.58 frames.], batch size: 20, lr: 8.24e-04
+2022-05-14 08:26:37,730 INFO [train.py:812] (0/8) Epoch 9, batch 2800, loss[loss=0.2188, simple_loss=0.3103, pruned_loss=0.06366, over 7198.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2726, pruned_loss=0.0516, over 1425686.88 frames.], batch size: 22, lr: 8.23e-04
+2022-05-14 08:27:35,911 INFO [train.py:812] (0/8) Epoch 9, batch 2850, loss[loss=0.1653, simple_loss=0.2434, pruned_loss=0.04356, over 7169.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2722, pruned_loss=0.05117, over 1427612.51 frames.], batch size: 19, lr: 8.23e-04
+2022-05-14 08:28:34,017 INFO [train.py:812] (0/8) Epoch 9, batch 2900, loss[loss=0.1748, simple_loss=0.2666, pruned_loss=0.04153, over 7330.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2721, pruned_loss=0.05108, over 1426721.98 frames.], batch size: 21, lr: 8.22e-04
+2022-05-14 08:29:31,240 INFO [train.py:812] (0/8) Epoch 9, batch 2950, loss[loss=0.1771, simple_loss=0.2572, pruned_loss=0.04849, over 7285.00 frames.], tot_loss[loss=0.1887, simple_loss=0.273, pruned_loss=0.05215, over 1422211.86 frames.], batch size: 18, lr: 8.22e-04
+2022-05-14 08:30:30,204 INFO [train.py:812] (0/8) Epoch 9, batch 3000, loss[loss=0.2011, simple_loss=0.2865, pruned_loss=0.05785, over 7290.00 frames.], tot_loss[loss=0.188, simple_loss=0.2724, pruned_loss=0.05185, over 1420755.70 frames.], batch size: 24, lr: 8.21e-04
+2022-05-14 08:30:30,205 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 08:30:38,337 INFO [train.py:841] (0/8) Epoch 9, validation: loss=0.1602, simple_loss=0.262, pruned_loss=0.0292, over 698248.00 frames.
+2022-05-14 08:31:37,159 INFO [train.py:812] (0/8) Epoch 9, batch 3050, loss[loss=0.1578, simple_loss=0.2442, pruned_loss=0.0357, over 7316.00 frames.], tot_loss[loss=0.1878, simple_loss=0.272, pruned_loss=0.05183, over 1417912.20 frames.], batch size: 20, lr: 8.21e-04
+2022-05-14 08:32:34,694 INFO [train.py:812] (0/8) Epoch 9, batch 3100, loss[loss=0.2607, simple_loss=0.3261, pruned_loss=0.0977, over 6729.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2746, pruned_loss=0.05297, over 1413742.37 frames.], batch size: 31, lr: 8.20e-04
+2022-05-14 08:33:32,684 INFO [train.py:812] (0/8) Epoch 9, batch 3150, loss[loss=0.1872, simple_loss=0.2716, pruned_loss=0.05143, over 7162.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2739, pruned_loss=0.05271, over 1417542.36 frames.], batch size: 19, lr: 8.20e-04
+2022-05-14 08:34:32,440 INFO [train.py:812] (0/8) Epoch 9, batch 3200, loss[loss=0.1532, simple_loss=0.2416, pruned_loss=0.0324, over 7149.00 frames.], tot_loss[loss=0.1897, simple_loss=0.274, pruned_loss=0.05269, over 1422271.72 frames.], batch size: 20, lr: 8.19e-04
+2022-05-14 08:35:31,365 INFO [train.py:812] (0/8) Epoch 9, batch 3250, loss[loss=0.2286, simple_loss=0.31, pruned_loss=0.07361, over 5066.00 frames.], tot_loss[loss=0.1898, simple_loss=0.274, pruned_loss=0.05281, over 1420367.47 frames.], batch size: 52, lr: 8.19e-04
+2022-05-14 08:36:34,429 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-40000.pt
+2022-05-14 08:36:46,157 INFO [train.py:812] (0/8) Epoch 9, batch 3300, loss[loss=0.2068, simple_loss=0.2906, pruned_loss=0.06145, over 7200.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2731, pruned_loss=0.05223, over 1420462.63 frames.], batch size: 22, lr: 8.18e-04
+2022-05-14 08:37:52,678 INFO [train.py:812] (0/8) Epoch 9, batch 3350, loss[loss=0.1789, simple_loss=0.2592, pruned_loss=0.04931, over 7264.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2729, pruned_loss=0.05219, over 1423966.16 frames.], batch size: 19, lr: 8.18e-04
+2022-05-14 08:38:51,552 INFO [train.py:812] (0/8) Epoch 9, batch 3400, loss[loss=0.1797, simple_loss=0.2756, pruned_loss=0.04193, over 6766.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2739, pruned_loss=0.05285, over 1421424.93 frames.], batch size: 31, lr: 8.17e-04
+2022-05-14 08:39:59,371 INFO [train.py:812] (0/8) Epoch 9, batch 3450, loss[loss=0.1612, simple_loss=0.2327, pruned_loss=0.04488, over 7420.00 frames.], tot_loss[loss=0.189, simple_loss=0.2732, pruned_loss=0.05243, over 1424005.16 frames.], batch size: 18, lr: 8.17e-04
+2022-05-14 08:41:27,456 INFO [train.py:812] (0/8) Epoch 9, batch 3500, loss[loss=0.1888, simple_loss=0.2762, pruned_loss=0.05074, over 7153.00 frames.], tot_loss[loss=0.1886, simple_loss=0.273, pruned_loss=0.05214, over 1425010.78 frames.], batch size: 19, lr: 8.16e-04
+2022-05-14 08:42:35,809 INFO [train.py:812] (0/8) Epoch 9, batch 3550, loss[loss=0.1642, simple_loss=0.2447, pruned_loss=0.04188, over 7168.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2722, pruned_loss=0.0518, over 1426258.76 frames.], batch size: 18, lr: 8.16e-04
+2022-05-14 08:43:34,798 INFO [train.py:812] (0/8) Epoch 9, batch 3600, loss[loss=0.1524, simple_loss=0.2357, pruned_loss=0.03449, over 7288.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2721, pruned_loss=0.05126, over 1424509.36 frames.], batch size: 18, lr: 8.15e-04
+2022-05-14 08:44:32,182 INFO [train.py:812] (0/8) Epoch 9, batch 3650, loss[loss=0.162, simple_loss=0.2324, pruned_loss=0.04578, over 7134.00 frames.], tot_loss[loss=0.1871, simple_loss=0.272, pruned_loss=0.05114, over 1425448.96 frames.], batch size: 17, lr: 8.15e-04
+2022-05-14 08:45:31,378 INFO [train.py:812] (0/8) Epoch 9, batch 3700, loss[loss=0.1958, simple_loss=0.292, pruned_loss=0.04981, over 7295.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2728, pruned_loss=0.05138, over 1425920.36 frames.], batch size: 25, lr: 8.14e-04
+2022-05-14 08:46:29,963 INFO [train.py:812] (0/8) Epoch 9, batch 3750, loss[loss=0.1639, simple_loss=0.2522, pruned_loss=0.03778, over 7437.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2742, pruned_loss=0.05227, over 1424925.26 frames.], batch size: 20, lr: 8.14e-04
+2022-05-14 08:47:28,943 INFO [train.py:812] (0/8) Epoch 9, batch 3800, loss[loss=0.1817, simple_loss=0.2672, pruned_loss=0.04812, over 7411.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2738, pruned_loss=0.0519, over 1426693.43 frames.], batch size: 18, lr: 8.13e-04
+2022-05-14 08:48:27,805 INFO [train.py:812] (0/8) Epoch 9, batch 3850, loss[loss=0.1853, simple_loss=0.2679, pruned_loss=0.05139, over 7279.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2734, pruned_loss=0.05166, over 1428707.52 frames.], batch size: 17, lr: 8.13e-04
+2022-05-14 08:49:26,811 INFO [train.py:812] (0/8) Epoch 9, batch 3900, loss[loss=0.248, simple_loss=0.3219, pruned_loss=0.08709, over 4912.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2739, pruned_loss=0.05165, over 1425856.74 frames.], batch size: 54, lr: 8.12e-04
+2022-05-14 08:50:26,265 INFO [train.py:812] (0/8) Epoch 9, batch 3950, loss[loss=0.2063, simple_loss=0.2926, pruned_loss=0.05997, over 6772.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2728, pruned_loss=0.05124, over 1426406.69 frames.], batch size: 31, lr: 8.12e-04
+2022-05-14 08:51:25,867 INFO [train.py:812] (0/8) Epoch 9, batch 4000, loss[loss=0.1647, simple_loss=0.257, pruned_loss=0.03619, over 7223.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2741, pruned_loss=0.05167, over 1425939.14 frames.], batch size: 21, lr: 8.11e-04
+2022-05-14 08:52:25,283 INFO [train.py:812] (0/8) Epoch 9, batch 4050, loss[loss=0.1711, simple_loss=0.2497, pruned_loss=0.04628, over 7419.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2727, pruned_loss=0.05128, over 1425491.88 frames.], batch size: 18, lr: 8.11e-04
+2022-05-14 08:53:24,993 INFO [train.py:812] (0/8) Epoch 9, batch 4100, loss[loss=0.171, simple_loss=0.2533, pruned_loss=0.04439, over 7140.00 frames.], tot_loss[loss=0.187, simple_loss=0.2724, pruned_loss=0.05076, over 1426616.10 frames.], batch size: 17, lr: 8.10e-04
+2022-05-14 08:54:24,682 INFO [train.py:812] (0/8) Epoch 9, batch 4150, loss[loss=0.2025, simple_loss=0.2876, pruned_loss=0.05871, over 7071.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2718, pruned_loss=0.05087, over 1422086.98 frames.], batch size: 28, lr: 8.10e-04
+2022-05-14 08:55:24,457 INFO [train.py:812] (0/8) Epoch 9, batch 4200, loss[loss=0.1567, simple_loss=0.2433, pruned_loss=0.035, over 7319.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2704, pruned_loss=0.05037, over 1423466.75 frames.], batch size: 20, lr: 8.09e-04
+2022-05-14 08:56:23,007 INFO [train.py:812] (0/8) Epoch 9, batch 4250, loss[loss=0.1648, simple_loss=0.2528, pruned_loss=0.03838, over 7135.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2698, pruned_loss=0.05058, over 1419527.55 frames.], batch size: 17, lr: 8.09e-04
+2022-05-14 08:57:22,989 INFO [train.py:812] (0/8) Epoch 9, batch 4300, loss[loss=0.1977, simple_loss=0.2842, pruned_loss=0.05565, over 7413.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2706, pruned_loss=0.05133, over 1414057.96 frames.], batch size: 21, lr: 8.08e-04
+2022-05-14 08:58:21,479 INFO [train.py:812] (0/8) Epoch 9, batch 4350, loss[loss=0.1523, simple_loss=0.2264, pruned_loss=0.03912, over 7282.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2699, pruned_loss=0.05098, over 1420284.10 frames.], batch size: 17, lr: 8.08e-04
+2022-05-14 08:59:21,259 INFO [train.py:812] (0/8) Epoch 9, batch 4400, loss[loss=0.1666, simple_loss=0.252, pruned_loss=0.04065, over 7042.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2703, pruned_loss=0.05166, over 1416675.36 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:00:19,270 INFO [train.py:812] (0/8) Epoch 9, batch 4450, loss[loss=0.2005, simple_loss=0.2853, pruned_loss=0.05784, over 6981.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2688, pruned_loss=0.05122, over 1411177.64 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:01:19,154 INFO [train.py:812] (0/8) Epoch 9, batch 4500, loss[loss=0.1971, simple_loss=0.2879, pruned_loss=0.0531, over 7059.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2705, pruned_loss=0.05235, over 1393241.81 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:02:17,088 INFO [train.py:812] (0/8) Epoch 9, batch 4550, loss[loss=0.1707, simple_loss=0.2592, pruned_loss=0.04116, over 6454.00 frames.], tot_loss[loss=0.1913, simple_loss=0.274, pruned_loss=0.0543, over 1353052.46 frames.], batch size: 38, lr: 8.06e-04
+2022-05-14 09:03:01,163 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-9.pt
+2022-05-14 09:03:24,798 INFO [train.py:812] (0/8) Epoch 10, batch 0, loss[loss=0.1944, simple_loss=0.2838, pruned_loss=0.05254, over 7421.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2838, pruned_loss=0.05254, over 7421.00 frames.], batch size: 21, lr: 7.75e-04
+2022-05-14 09:04:24,007 INFO [train.py:812] (0/8) Epoch 10, batch 50, loss[loss=0.2196, simple_loss=0.315, pruned_loss=0.06209, over 7207.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2718, pruned_loss=0.05142, over 321892.53 frames.], batch size: 23, lr: 7.74e-04
+2022-05-14 09:05:23,093 INFO [train.py:812] (0/8) Epoch 10, batch 100, loss[loss=0.2216, simple_loss=0.2959, pruned_loss=0.07367, over 4942.00 frames.], tot_loss[loss=0.184, simple_loss=0.2686, pruned_loss=0.0497, over 557450.22 frames.], batch size: 52, lr: 7.74e-04
+2022-05-14 09:06:22,307 INFO [train.py:812] (0/8) Epoch 10, batch 150, loss[loss=0.1634, simple_loss=0.2486, pruned_loss=0.03908, over 7424.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2688, pruned_loss=0.04886, over 750879.81 frames.], batch size: 20, lr: 7.73e-04
+2022-05-14 09:07:20,645 INFO [train.py:812] (0/8) Epoch 10, batch 200, loss[loss=0.1805, simple_loss=0.2719, pruned_loss=0.04455, over 7432.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2705, pruned_loss=0.04951, over 898060.74 frames.], batch size: 20, lr: 7.73e-04
+2022-05-14 09:08:19,892 INFO [train.py:812] (0/8) Epoch 10, batch 250, loss[loss=0.1921, simple_loss=0.2704, pruned_loss=0.05687, over 7154.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2712, pruned_loss=0.05013, over 1010484.15 frames.], batch size: 18, lr: 7.72e-04
+2022-05-14 09:09:19,084 INFO [train.py:812] (0/8) Epoch 10, batch 300, loss[loss=0.2014, simple_loss=0.2862, pruned_loss=0.05827, over 7337.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2703, pruned_loss=0.04991, over 1103861.34 frames.], batch size: 20, lr: 7.72e-04
+2022-05-14 09:10:16,339 INFO [train.py:812] (0/8) Epoch 10, batch 350, loss[loss=0.185, simple_loss=0.2717, pruned_loss=0.04918, over 7210.00 frames.], tot_loss[loss=0.1844, simple_loss=0.27, pruned_loss=0.04937, over 1171976.74 frames.], batch size: 23, lr: 7.71e-04
+2022-05-14 09:11:15,057 INFO [train.py:812] (0/8) Epoch 10, batch 400, loss[loss=0.2348, simple_loss=0.3227, pruned_loss=0.07345, over 7213.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2715, pruned_loss=0.05006, over 1222546.13 frames.], batch size: 26, lr: 7.71e-04
+2022-05-14 09:12:14,065 INFO [train.py:812] (0/8) Epoch 10, batch 450, loss[loss=0.1903, simple_loss=0.2828, pruned_loss=0.04883, over 6360.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2715, pruned_loss=0.05028, over 1261656.20 frames.], batch size: 38, lr: 7.71e-04
+2022-05-14 09:13:13,636 INFO [train.py:812] (0/8) Epoch 10, batch 500, loss[loss=0.2035, simple_loss=0.2837, pruned_loss=0.06162, over 7173.00 frames.], tot_loss[loss=0.1864, simple_loss=0.272, pruned_loss=0.05044, over 1297186.38 frames.], batch size: 19, lr: 7.70e-04
+2022-05-14 09:14:12,274 INFO [train.py:812] (0/8) Epoch 10, batch 550, loss[loss=0.1621, simple_loss=0.2407, pruned_loss=0.04177, over 7131.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2714, pruned_loss=0.05062, over 1324997.84 frames.], batch size: 17, lr: 7.70e-04
+2022-05-14 09:15:10,141 INFO [train.py:812] (0/8) Epoch 10, batch 600, loss[loss=0.1861, simple_loss=0.2636, pruned_loss=0.05434, over 7274.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2707, pruned_loss=0.05012, over 1345965.78 frames.], batch size: 18, lr: 7.69e-04
+2022-05-14 09:16:08,327 INFO [train.py:812] (0/8) Epoch 10, batch 650, loss[loss=0.1999, simple_loss=0.2894, pruned_loss=0.05522, over 7175.00 frames.], tot_loss[loss=0.186, simple_loss=0.271, pruned_loss=0.05052, over 1361916.56 frames.], batch size: 26, lr: 7.69e-04
+2022-05-14 09:17:07,945 INFO [train.py:812] (0/8) Epoch 10, batch 700, loss[loss=0.1639, simple_loss=0.2606, pruned_loss=0.03362, over 7283.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2698, pruned_loss=0.04959, over 1377133.46 frames.], batch size: 25, lr: 7.68e-04
+2022-05-14 09:18:07,543 INFO [train.py:812] (0/8) Epoch 10, batch 750, loss[loss=0.1585, simple_loss=0.2362, pruned_loss=0.04041, over 7429.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2697, pruned_loss=0.04951, over 1387016.75 frames.], batch size: 20, lr: 7.68e-04
+2022-05-14 09:19:06,538 INFO [train.py:812] (0/8) Epoch 10, batch 800, loss[loss=0.1962, simple_loss=0.2808, pruned_loss=0.05575, over 7287.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2692, pruned_loss=0.04929, over 1394615.24 frames.], batch size: 24, lr: 7.67e-04
+2022-05-14 09:20:05,998 INFO [train.py:812] (0/8) Epoch 10, batch 850, loss[loss=0.2031, simple_loss=0.2844, pruned_loss=0.06096, over 6380.00 frames.], tot_loss[loss=0.1844, simple_loss=0.27, pruned_loss=0.04943, over 1397601.33 frames.], batch size: 38, lr: 7.67e-04
+2022-05-14 09:21:05,079 INFO [train.py:812] (0/8) Epoch 10, batch 900, loss[loss=0.1745, simple_loss=0.2599, pruned_loss=0.04456, over 7330.00 frames.], tot_loss[loss=0.1841, simple_loss=0.27, pruned_loss=0.04914, over 1407863.49 frames.], batch size: 21, lr: 7.66e-04
+2022-05-14 09:22:03,852 INFO [train.py:812] (0/8) Epoch 10, batch 950, loss[loss=0.2065, simple_loss=0.2895, pruned_loss=0.06173, over 7141.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2709, pruned_loss=0.0499, over 1406463.80 frames.], batch size: 26, lr: 7.66e-04
+2022-05-14 09:23:02,625 INFO [train.py:812] (0/8) Epoch 10, batch 1000, loss[loss=0.1805, simple_loss=0.2704, pruned_loss=0.0453, over 7331.00 frames.], tot_loss[loss=0.185, simple_loss=0.2704, pruned_loss=0.04978, over 1413786.54 frames.], batch size: 20, lr: 7.66e-04
+2022-05-14 09:24:00,826 INFO [train.py:812] (0/8) Epoch 10, batch 1050, loss[loss=0.2073, simple_loss=0.2954, pruned_loss=0.05964, over 7039.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2704, pruned_loss=0.04995, over 1416217.09 frames.], batch size: 28, lr: 7.65e-04
+2022-05-14 09:24:59,378 INFO [train.py:812] (0/8) Epoch 10, batch 1100, loss[loss=0.1987, simple_loss=0.278, pruned_loss=0.05972, over 7097.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2712, pruned_loss=0.05056, over 1417899.63 frames.], batch size: 28, lr: 7.65e-04
+2022-05-14 09:25:57,294 INFO [train.py:812] (0/8) Epoch 10, batch 1150, loss[loss=0.1895, simple_loss=0.2799, pruned_loss=0.04956, over 7321.00 frames.], tot_loss[loss=0.1869, simple_loss=0.272, pruned_loss=0.05087, over 1422296.82 frames.], batch size: 20, lr: 7.64e-04
+2022-05-14 09:26:55,698 INFO [train.py:812] (0/8) Epoch 10, batch 1200, loss[loss=0.2269, simple_loss=0.3268, pruned_loss=0.06346, over 7196.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2726, pruned_loss=0.05084, over 1421260.94 frames.], batch size: 23, lr: 7.64e-04
+2022-05-14 09:27:55,415 INFO [train.py:812] (0/8) Epoch 10, batch 1250, loss[loss=0.1667, simple_loss=0.2441, pruned_loss=0.04463, over 7286.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2728, pruned_loss=0.05097, over 1419045.71 frames.], batch size: 17, lr: 7.63e-04
+2022-05-14 09:28:54,699 INFO [train.py:812] (0/8) Epoch 10, batch 1300, loss[loss=0.1813, simple_loss=0.2491, pruned_loss=0.05671, over 7026.00 frames.], tot_loss[loss=0.187, simple_loss=0.272, pruned_loss=0.051, over 1416997.85 frames.], batch size: 16, lr: 7.63e-04
+2022-05-14 09:29:54,187 INFO [train.py:812] (0/8) Epoch 10, batch 1350, loss[loss=0.1858, simple_loss=0.2835, pruned_loss=0.044, over 7309.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2714, pruned_loss=0.05061, over 1416691.23 frames.], batch size: 21, lr: 7.62e-04
+2022-05-14 09:30:53,017 INFO [train.py:812] (0/8) Epoch 10, batch 1400, loss[loss=0.2089, simple_loss=0.2942, pruned_loss=0.06184, over 7118.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2722, pruned_loss=0.05063, over 1419896.26 frames.], batch size: 21, lr: 7.62e-04
+2022-05-14 09:31:52,533 INFO [train.py:812] (0/8) Epoch 10, batch 1450, loss[loss=0.2025, simple_loss=0.2816, pruned_loss=0.06173, over 7301.00 frames.], tot_loss[loss=0.1857, simple_loss=0.271, pruned_loss=0.0502, over 1420570.41 frames.], batch size: 25, lr: 7.62e-04
+2022-05-14 09:32:51,544 INFO [train.py:812] (0/8) Epoch 10, batch 1500, loss[loss=0.2415, simple_loss=0.3122, pruned_loss=0.08539, over 5169.00 frames.], tot_loss[loss=0.1856, simple_loss=0.271, pruned_loss=0.0501, over 1416099.55 frames.], batch size: 52, lr: 7.61e-04
+2022-05-14 09:33:51,499 INFO [train.py:812] (0/8) Epoch 10, batch 1550, loss[loss=0.1918, simple_loss=0.2713, pruned_loss=0.05614, over 7367.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2707, pruned_loss=0.04989, over 1419065.72 frames.], batch size: 19, lr: 7.61e-04
+2022-05-14 09:34:49,181 INFO [train.py:812] (0/8) Epoch 10, batch 1600, loss[loss=0.2213, simple_loss=0.2958, pruned_loss=0.07334, over 7260.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2706, pruned_loss=0.04999, over 1417669.04 frames.], batch size: 19, lr: 7.60e-04
+2022-05-14 09:35:46,393 INFO [train.py:812] (0/8) Epoch 10, batch 1650, loss[loss=0.1828, simple_loss=0.2795, pruned_loss=0.04306, over 7414.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2712, pruned_loss=0.05053, over 1415678.78 frames.], batch size: 21, lr: 7.60e-04
+2022-05-14 09:36:44,489 INFO [train.py:812] (0/8) Epoch 10, batch 1700, loss[loss=0.1789, simple_loss=0.2744, pruned_loss=0.04172, over 7301.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2699, pruned_loss=0.04995, over 1413265.32 frames.], batch size: 24, lr: 7.59e-04
+2022-05-14 09:37:43,628 INFO [train.py:812] (0/8) Epoch 10, batch 1750, loss[loss=0.1465, simple_loss=0.2263, pruned_loss=0.03341, over 7247.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2708, pruned_loss=0.05043, over 1405870.73 frames.], batch size: 16, lr: 7.59e-04
+2022-05-14 09:38:41,650 INFO [train.py:812] (0/8) Epoch 10, batch 1800, loss[loss=0.2072, simple_loss=0.2939, pruned_loss=0.06023, over 7346.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2701, pruned_loss=0.05005, over 1410310.48 frames.], batch size: 19, lr: 7.59e-04
+2022-05-14 09:39:39,842 INFO [train.py:812] (0/8) Epoch 10, batch 1850, loss[loss=0.1927, simple_loss=0.2701, pruned_loss=0.05762, over 7371.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2711, pruned_loss=0.05061, over 1410725.89 frames.], batch size: 19, lr: 7.58e-04
+2022-05-14 09:40:38,496 INFO [train.py:812] (0/8) Epoch 10, batch 1900, loss[loss=0.188, simple_loss=0.2623, pruned_loss=0.05681, over 7271.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2703, pruned_loss=0.05013, over 1414442.63 frames.], batch size: 18, lr: 7.58e-04
+2022-05-14 09:41:37,150 INFO [train.py:812] (0/8) Epoch 10, batch 1950, loss[loss=0.2189, simple_loss=0.3077, pruned_loss=0.06502, over 7203.00 frames.], tot_loss[loss=0.185, simple_loss=0.2703, pruned_loss=0.04983, over 1413450.71 frames.], batch size: 23, lr: 7.57e-04
+2022-05-14 09:42:35,062 INFO [train.py:812] (0/8) Epoch 10, batch 2000, loss[loss=0.1868, simple_loss=0.2733, pruned_loss=0.05014, over 7227.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2698, pruned_loss=0.04936, over 1416698.54 frames.], batch size: 20, lr: 7.57e-04
+2022-05-14 09:43:34,858 INFO [train.py:812] (0/8) Epoch 10, batch 2050, loss[loss=0.1871, simple_loss=0.2677, pruned_loss=0.05329, over 7194.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2701, pruned_loss=0.04955, over 1419504.78 frames.], batch size: 23, lr: 7.56e-04
+2022-05-14 09:44:34,087 INFO [train.py:812] (0/8) Epoch 10, batch 2100, loss[loss=0.1761, simple_loss=0.2674, pruned_loss=0.04246, over 7140.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2698, pruned_loss=0.04929, over 1424322.27 frames.], batch size: 20, lr: 7.56e-04
+2022-05-14 09:45:31,448 INFO [train.py:812] (0/8) Epoch 10, batch 2150, loss[loss=0.1588, simple_loss=0.2373, pruned_loss=0.04018, over 7424.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2685, pruned_loss=0.04888, over 1425723.66 frames.], batch size: 18, lr: 7.56e-04
+2022-05-14 09:46:28,649 INFO [train.py:812] (0/8) Epoch 10, batch 2200, loss[loss=0.2089, simple_loss=0.2883, pruned_loss=0.0648, over 6480.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2691, pruned_loss=0.04902, over 1426103.23 frames.], batch size: 38, lr: 7.55e-04
+2022-05-14 09:47:27,359 INFO [train.py:812] (0/8) Epoch 10, batch 2250, loss[loss=0.1792, simple_loss=0.2756, pruned_loss=0.04134, over 7321.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2697, pruned_loss=0.04948, over 1428458.27 frames.], batch size: 21, lr: 7.55e-04
+2022-05-14 09:48:25,577 INFO [train.py:812] (0/8) Epoch 10, batch 2300, loss[loss=0.2053, simple_loss=0.292, pruned_loss=0.05927, over 7147.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2703, pruned_loss=0.04963, over 1426151.78 frames.], batch size: 20, lr: 7.54e-04
+2022-05-14 09:49:24,923 INFO [train.py:812] (0/8) Epoch 10, batch 2350, loss[loss=0.1741, simple_loss=0.2691, pruned_loss=0.03957, over 7182.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2694, pruned_loss=0.04923, over 1424837.18 frames.], batch size: 22, lr: 7.54e-04
+2022-05-14 09:50:22,202 INFO [train.py:812] (0/8) Epoch 10, batch 2400, loss[loss=0.1959, simple_loss=0.2661, pruned_loss=0.06288, over 7269.00 frames.], tot_loss[loss=0.1831, simple_loss=0.269, pruned_loss=0.04855, over 1427032.79 frames.], batch size: 18, lr: 7.53e-04
+2022-05-14 09:51:20,801 INFO [train.py:812] (0/8) Epoch 10, batch 2450, loss[loss=0.1573, simple_loss=0.2361, pruned_loss=0.03931, over 7068.00 frames.], tot_loss[loss=0.1833, simple_loss=0.269, pruned_loss=0.0488, over 1430162.09 frames.], batch size: 18, lr: 7.53e-04
+2022-05-14 09:52:18,415 INFO [train.py:812] (0/8) Epoch 10, batch 2500, loss[loss=0.166, simple_loss=0.2616, pruned_loss=0.03522, over 7322.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2681, pruned_loss=0.0483, over 1428172.16 frames.], batch size: 21, lr: 7.53e-04
+2022-05-14 09:53:18,326 INFO [train.py:812] (0/8) Epoch 10, batch 2550, loss[loss=0.2145, simple_loss=0.2986, pruned_loss=0.06517, over 7213.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2686, pruned_loss=0.04881, over 1426922.53 frames.], batch size: 21, lr: 7.52e-04
+2022-05-14 09:54:18,079 INFO [train.py:812] (0/8) Epoch 10, batch 2600, loss[loss=0.2229, simple_loss=0.3057, pruned_loss=0.07008, over 7119.00 frames.], tot_loss[loss=0.1835, simple_loss=0.269, pruned_loss=0.04899, over 1429913.57 frames.], batch size: 26, lr: 7.52e-04
+2022-05-14 09:55:17,723 INFO [train.py:812] (0/8) Epoch 10, batch 2650, loss[loss=0.2033, simple_loss=0.2889, pruned_loss=0.05889, over 7338.00 frames.], tot_loss[loss=0.185, simple_loss=0.2706, pruned_loss=0.04966, over 1426578.72 frames.], batch size: 22, lr: 7.51e-04
+2022-05-14 09:56:16,820 INFO [train.py:812] (0/8) Epoch 10, batch 2700, loss[loss=0.1617, simple_loss=0.2548, pruned_loss=0.03426, over 6730.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2701, pruned_loss=0.04958, over 1426871.92 frames.], batch size: 31, lr: 7.51e-04
+2022-05-14 09:56:25,608 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-44000.pt
+2022-05-14 09:57:23,699 INFO [train.py:812] (0/8) Epoch 10, batch 2750, loss[loss=0.2014, simple_loss=0.2819, pruned_loss=0.06044, over 6764.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2687, pruned_loss=0.04919, over 1424379.79 frames.], batch size: 31, lr: 7.50e-04
+2022-05-14 09:58:22,161 INFO [train.py:812] (0/8) Epoch 10, batch 2800, loss[loss=0.2131, simple_loss=0.2941, pruned_loss=0.06603, over 7364.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2684, pruned_loss=0.0491, over 1429000.13 frames.], batch size: 23, lr: 7.50e-04
+2022-05-14 09:59:21,343 INFO [train.py:812] (0/8) Epoch 10, batch 2850, loss[loss=0.1654, simple_loss=0.2658, pruned_loss=0.03246, over 7359.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2684, pruned_loss=0.04893, over 1426801.56 frames.], batch size: 22, lr: 7.50e-04
+2022-05-14 10:00:20,873 INFO [train.py:812] (0/8) Epoch 10, batch 2900, loss[loss=0.1761, simple_loss=0.2711, pruned_loss=0.04051, over 7111.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2687, pruned_loss=0.04887, over 1425382.00 frames.], batch size: 21, lr: 7.49e-04
+2022-05-14 10:01:19,226 INFO [train.py:812] (0/8) Epoch 10, batch 2950, loss[loss=0.1541, simple_loss=0.2368, pruned_loss=0.03571, over 7275.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2684, pruned_loss=0.04907, over 1425578.14 frames.], batch size: 18, lr: 7.49e-04
+2022-05-14 10:02:18,294 INFO [train.py:812] (0/8) Epoch 10, batch 3000, loss[loss=0.1805, simple_loss=0.2557, pruned_loss=0.05261, over 7278.00 frames.], tot_loss[loss=0.1828, simple_loss=0.268, pruned_loss=0.04876, over 1425453.27 frames.], batch size: 17, lr: 7.48e-04
+2022-05-14 10:02:18,295 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 10:02:25,810 INFO [train.py:841] (0/8) Epoch 10, validation: loss=0.1584, simple_loss=0.26, pruned_loss=0.0284, over 698248.00 frames.
+2022-05-14 10:03:25,478 INFO [train.py:812] (0/8) Epoch 10, batch 3050, loss[loss=0.2102, simple_loss=0.2911, pruned_loss=0.06465, over 7160.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2685, pruned_loss=0.04929, over 1425515.29 frames.], batch size: 19, lr: 7.48e-04
+2022-05-14 10:04:24,552 INFO [train.py:812] (0/8) Epoch 10, batch 3100, loss[loss=0.1891, simple_loss=0.2836, pruned_loss=0.0473, over 7114.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2682, pruned_loss=0.04854, over 1428170.47 frames.], batch size: 21, lr: 7.47e-04
+2022-05-14 10:05:24,315 INFO [train.py:812] (0/8) Epoch 10, batch 3150, loss[loss=0.1903, simple_loss=0.2811, pruned_loss=0.04979, over 7328.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2688, pruned_loss=0.04892, over 1424536.33 frames.], batch size: 21, lr: 7.47e-04
+2022-05-14 10:06:23,650 INFO [train.py:812] (0/8) Epoch 10, batch 3200, loss[loss=0.2188, simple_loss=0.2965, pruned_loss=0.0706, over 7234.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2676, pruned_loss=0.04842, over 1424890.04 frames.], batch size: 20, lr: 7.47e-04
+2022-05-14 10:07:23,097 INFO [train.py:812] (0/8) Epoch 10, batch 3250, loss[loss=0.1998, simple_loss=0.2951, pruned_loss=0.05229, over 7411.00 frames.], tot_loss[loss=0.183, simple_loss=0.2689, pruned_loss=0.0486, over 1426228.13 frames.], batch size: 21, lr: 7.46e-04
+2022-05-14 10:08:22,151 INFO [train.py:812] (0/8) Epoch 10, batch 3300, loss[loss=0.1628, simple_loss=0.2618, pruned_loss=0.03194, over 7199.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2687, pruned_loss=0.04836, over 1427639.01 frames.], batch size: 22, lr: 7.46e-04
+2022-05-14 10:09:21,714 INFO [train.py:812] (0/8) Epoch 10, batch 3350, loss[loss=0.1941, simple_loss=0.2819, pruned_loss=0.05311, over 7202.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2695, pruned_loss=0.04895, over 1429044.02 frames.], batch size: 23, lr: 7.45e-04
+2022-05-14 10:10:20,620 INFO [train.py:812] (0/8) Epoch 10, batch 3400, loss[loss=0.1493, simple_loss=0.2259, pruned_loss=0.03636, over 7295.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2692, pruned_loss=0.04904, over 1425150.42 frames.], batch size: 17, lr: 7.45e-04
+2022-05-14 10:11:20,106 INFO [train.py:812] (0/8) Epoch 10, batch 3450, loss[loss=0.1823, simple_loss=0.2733, pruned_loss=0.04563, over 7297.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2689, pruned_loss=0.04899, over 1424410.29 frames.], batch size: 24, lr: 7.45e-04
+2022-05-14 10:12:19,154 INFO [train.py:812] (0/8) Epoch 10, batch 3500, loss[loss=0.2153, simple_loss=0.3074, pruned_loss=0.06153, over 7422.00 frames.], tot_loss[loss=0.1835, simple_loss=0.269, pruned_loss=0.04894, over 1424841.56 frames.], batch size: 21, lr: 7.44e-04
+2022-05-14 10:13:18,712 INFO [train.py:812] (0/8) Epoch 10, batch 3550, loss[loss=0.1801, simple_loss=0.2761, pruned_loss=0.04207, over 7029.00 frames.], tot_loss[loss=0.183, simple_loss=0.2682, pruned_loss=0.04889, over 1427609.04 frames.], batch size: 28, lr: 7.44e-04
+2022-05-14 10:14:16,915 INFO [train.py:812] (0/8) Epoch 10, batch 3600, loss[loss=0.2233, simple_loss=0.2936, pruned_loss=0.07652, over 7075.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2686, pruned_loss=0.04894, over 1427213.27 frames.], batch size: 28, lr: 7.43e-04
+2022-05-14 10:15:16,525 INFO [train.py:812] (0/8) Epoch 10, batch 3650, loss[loss=0.1995, simple_loss=0.2724, pruned_loss=0.06329, over 7066.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2675, pruned_loss=0.04853, over 1422782.29 frames.], batch size: 18, lr: 7.43e-04
+2022-05-14 10:16:15,568 INFO [train.py:812] (0/8) Epoch 10, batch 3700, loss[loss=0.162, simple_loss=0.249, pruned_loss=0.03747, over 7276.00 frames.], tot_loss[loss=0.1824, simple_loss=0.268, pruned_loss=0.04846, over 1425650.31 frames.], batch size: 17, lr: 7.43e-04
+2022-05-14 10:17:15,266 INFO [train.py:812] (0/8) Epoch 10, batch 3750, loss[loss=0.1706, simple_loss=0.2672, pruned_loss=0.03699, over 7155.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2689, pruned_loss=0.04878, over 1428205.23 frames.], batch size: 19, lr: 7.42e-04
+2022-05-14 10:18:14,390 INFO [train.py:812] (0/8) Epoch 10, batch 3800, loss[loss=0.19, simple_loss=0.2595, pruned_loss=0.06025, over 7429.00 frames.], tot_loss[loss=0.1832, simple_loss=0.269, pruned_loss=0.0487, over 1426118.72 frames.], batch size: 20, lr: 7.42e-04
+2022-05-14 10:19:12,961 INFO [train.py:812] (0/8) Epoch 10, batch 3850, loss[loss=0.1607, simple_loss=0.2477, pruned_loss=0.03685, over 7454.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2693, pruned_loss=0.04862, over 1425940.40 frames.], batch size: 19, lr: 7.41e-04
+2022-05-14 10:20:21,761 INFO [train.py:812] (0/8) Epoch 10, batch 3900, loss[loss=0.167, simple_loss=0.2493, pruned_loss=0.04231, over 7150.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2683, pruned_loss=0.0484, over 1427709.74 frames.], batch size: 19, lr: 7.41e-04
+2022-05-14 10:21:21,326 INFO [train.py:812] (0/8) Epoch 10, batch 3950, loss[loss=0.209, simple_loss=0.2783, pruned_loss=0.06981, over 5134.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2681, pruned_loss=0.04852, over 1422405.05 frames.], batch size: 54, lr: 7.41e-04
+2022-05-14 10:22:19,969 INFO [train.py:812] (0/8) Epoch 10, batch 4000, loss[loss=0.1887, simple_loss=0.2732, pruned_loss=0.05209, over 7266.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2695, pruned_loss=0.04936, over 1423563.24 frames.], batch size: 19, lr: 7.40e-04
+2022-05-14 10:23:18,886 INFO [train.py:812] (0/8) Epoch 10, batch 4050, loss[loss=0.1857, simple_loss=0.2672, pruned_loss=0.05209, over 7144.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2687, pruned_loss=0.04888, over 1423274.78 frames.], batch size: 17, lr: 7.40e-04
+2022-05-14 10:24:16,989 INFO [train.py:812] (0/8) Epoch 10, batch 4100, loss[loss=0.1895, simple_loss=0.2804, pruned_loss=0.04929, over 7312.00 frames.], tot_loss[loss=0.1832, simple_loss=0.269, pruned_loss=0.04866, over 1425533.39 frames.], batch size: 21, lr: 7.39e-04
+2022-05-14 10:25:16,588 INFO [train.py:812] (0/8) Epoch 10, batch 4150, loss[loss=0.1599, simple_loss=0.2358, pruned_loss=0.04196, over 7405.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2687, pruned_loss=0.04854, over 1425565.43 frames.], batch size: 18, lr: 7.39e-04
+2022-05-14 10:26:14,803 INFO [train.py:812] (0/8) Epoch 10, batch 4200, loss[loss=0.1754, simple_loss=0.2623, pruned_loss=0.04429, over 7274.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2695, pruned_loss=0.04918, over 1427135.31 frames.], batch size: 24, lr: 7.39e-04
+2022-05-14 10:27:13,947 INFO [train.py:812] (0/8) Epoch 10, batch 4250, loss[loss=0.1542, simple_loss=0.2379, pruned_loss=0.03528, over 7258.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2702, pruned_loss=0.04952, over 1422855.58 frames.], batch size: 17, lr: 7.38e-04
+2022-05-14 10:28:13,106 INFO [train.py:812] (0/8) Epoch 10, batch 4300, loss[loss=0.1985, simple_loss=0.2921, pruned_loss=0.05243, over 7295.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2701, pruned_loss=0.04977, over 1418125.99 frames.], batch size: 24, lr: 7.38e-04
+2022-05-14 10:29:11,051 INFO [train.py:812] (0/8) Epoch 10, batch 4350, loss[loss=0.1938, simple_loss=0.2664, pruned_loss=0.06057, over 5079.00 frames.], tot_loss[loss=0.186, simple_loss=0.2716, pruned_loss=0.05019, over 1408028.83 frames.], batch size: 53, lr: 7.37e-04
+2022-05-14 10:30:10,249 INFO [train.py:812] (0/8) Epoch 10, batch 4400, loss[loss=0.1789, simple_loss=0.2687, pruned_loss=0.04453, over 7220.00 frames.], tot_loss[loss=0.186, simple_loss=0.2718, pruned_loss=0.05016, over 1410840.23 frames.], batch size: 22, lr: 7.37e-04
+2022-05-14 10:31:10,032 INFO [train.py:812] (0/8) Epoch 10, batch 4450, loss[loss=0.2761, simple_loss=0.3304, pruned_loss=0.1109, over 4821.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2725, pruned_loss=0.05071, over 1395904.35 frames.], batch size: 52, lr: 7.37e-04
+2022-05-14 10:32:09,205 INFO [train.py:812] (0/8) Epoch 10, batch 4500, loss[loss=0.2149, simple_loss=0.2931, pruned_loss=0.06835, over 7143.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2715, pruned_loss=0.05081, over 1391778.99 frames.], batch size: 20, lr: 7.36e-04
+2022-05-14 10:33:08,605 INFO [train.py:812] (0/8) Epoch 10, batch 4550, loss[loss=0.1904, simple_loss=0.2819, pruned_loss=0.04941, over 7117.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2713, pruned_loss=0.05102, over 1373898.48 frames.], batch size: 26, lr: 7.36e-04
+2022-05-14 10:33:53,807 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-10.pt
+2022-05-14 10:34:22,341 INFO [train.py:812] (0/8) Epoch 11, batch 0, loss[loss=0.215, simple_loss=0.2978, pruned_loss=0.06608, over 7440.00 frames.], tot_loss[loss=0.215, simple_loss=0.2978, pruned_loss=0.06608, over 7440.00 frames.], batch size: 20, lr: 7.08e-04
+2022-05-14 10:35:21,208 INFO [train.py:812] (0/8) Epoch 11, batch 50, loss[loss=0.1479, simple_loss=0.2342, pruned_loss=0.03077, over 7433.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2699, pruned_loss=0.0471, over 322475.31 frames.], batch size: 20, lr: 7.08e-04
+2022-05-14 10:36:19,851 INFO [train.py:812] (0/8) Epoch 11, batch 100, loss[loss=0.1694, simple_loss=0.2521, pruned_loss=0.04329, over 7289.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2695, pruned_loss=0.04818, over 566858.02 frames.], batch size: 18, lr: 7.08e-04
+2022-05-14 10:37:28,460 INFO [train.py:812] (0/8) Epoch 11, batch 150, loss[loss=0.1663, simple_loss=0.2416, pruned_loss=0.04552, over 6791.00 frames.], tot_loss[loss=0.185, simple_loss=0.2717, pruned_loss=0.04913, over 759661.63 frames.], batch size: 15, lr: 7.07e-04
+2022-05-14 10:38:36,341 INFO [train.py:812] (0/8) Epoch 11, batch 200, loss[loss=0.1435, simple_loss=0.2327, pruned_loss=0.02717, over 7410.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2703, pruned_loss=0.04804, over 907534.29 frames.], batch size: 18, lr: 7.07e-04
+2022-05-14 10:39:34,538 INFO [train.py:812] (0/8) Epoch 11, batch 250, loss[loss=0.1667, simple_loss=0.2518, pruned_loss=0.04085, over 6465.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2685, pruned_loss=0.04741, over 1023533.26 frames.], batch size: 38, lr: 7.06e-04
+2022-05-14 10:40:50,469 INFO [train.py:812] (0/8) Epoch 11, batch 300, loss[loss=0.2275, simple_loss=0.2939, pruned_loss=0.0805, over 4992.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2683, pruned_loss=0.04748, over 1114490.14 frames.], batch size: 52, lr: 7.06e-04
+2022-05-14 10:41:47,786 INFO [train.py:812] (0/8) Epoch 11, batch 350, loss[loss=0.205, simple_loss=0.2975, pruned_loss=0.05621, over 6762.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2685, pruned_loss=0.04729, over 1186860.54 frames.], batch size: 31, lr: 7.06e-04
+2022-05-14 10:43:03,917 INFO [train.py:812] (0/8) Epoch 11, batch 400, loss[loss=0.1847, simple_loss=0.2725, pruned_loss=0.04848, over 7420.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2685, pruned_loss=0.04755, over 1241069.72 frames.], batch size: 20, lr: 7.05e-04
+2022-05-14 10:44:13,235 INFO [train.py:812] (0/8) Epoch 11, batch 450, loss[loss=0.1874, simple_loss=0.2723, pruned_loss=0.05124, over 7235.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2675, pruned_loss=0.04782, over 1280930.50 frames.], batch size: 20, lr: 7.05e-04
+2022-05-14 10:45:12,579 INFO [train.py:812] (0/8) Epoch 11, batch 500, loss[loss=0.1961, simple_loss=0.2813, pruned_loss=0.05552, over 7333.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2665, pruned_loss=0.047, over 1315415.49 frames.], batch size: 20, lr: 7.04e-04
+2022-05-14 10:46:12,011 INFO [train.py:812] (0/8) Epoch 11, batch 550, loss[loss=0.1739, simple_loss=0.2607, pruned_loss=0.04356, over 7072.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2662, pruned_loss=0.04696, over 1340521.52 frames.], batch size: 18, lr: 7.04e-04
+2022-05-14 10:47:11,312 INFO [train.py:812] (0/8) Epoch 11, batch 600, loss[loss=0.1637, simple_loss=0.2434, pruned_loss=0.04202, over 6998.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2664, pruned_loss=0.0473, over 1359663.32 frames.], batch size: 16, lr: 7.04e-04
+2022-05-14 10:48:09,760 INFO [train.py:812] (0/8) Epoch 11, batch 650, loss[loss=0.1559, simple_loss=0.2343, pruned_loss=0.03873, over 7122.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2664, pruned_loss=0.04755, over 1366014.91 frames.], batch size: 17, lr: 7.03e-04
+2022-05-14 10:49:08,402 INFO [train.py:812] (0/8) Epoch 11, batch 700, loss[loss=0.1576, simple_loss=0.2416, pruned_loss=0.03684, over 6754.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2674, pruned_loss=0.04753, over 1376094.32 frames.], batch size: 15, lr: 7.03e-04
+2022-05-14 10:50:07,758 INFO [train.py:812] (0/8) Epoch 11, batch 750, loss[loss=0.1845, simple_loss=0.2777, pruned_loss=0.04568, over 7147.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2679, pruned_loss=0.0479, over 1382448.38 frames.], batch size: 20, lr: 7.03e-04
+2022-05-14 10:51:05,918 INFO [train.py:812] (0/8) Epoch 11, batch 800, loss[loss=0.2133, simple_loss=0.3012, pruned_loss=0.06272, over 7167.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2674, pruned_loss=0.0477, over 1394159.37 frames.], batch size: 26, lr: 7.02e-04
+2022-05-14 10:52:03,634 INFO [train.py:812] (0/8) Epoch 11, batch 850, loss[loss=0.1874, simple_loss=0.2834, pruned_loss=0.04568, over 7326.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2679, pruned_loss=0.04765, over 1398376.29 frames.], batch size: 20, lr: 7.02e-04
+2022-05-14 10:53:01,752 INFO [train.py:812] (0/8) Epoch 11, batch 900, loss[loss=0.1795, simple_loss=0.2566, pruned_loss=0.05116, over 7423.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2674, pruned_loss=0.04777, over 1406891.60 frames.], batch size: 20, lr: 7.02e-04
+2022-05-14 10:54:00,381 INFO [train.py:812] (0/8) Epoch 11, batch 950, loss[loss=0.1775, simple_loss=0.2484, pruned_loss=0.05326, over 6981.00 frames.], tot_loss[loss=0.181, simple_loss=0.267, pruned_loss=0.04755, over 1408575.85 frames.], batch size: 16, lr: 7.01e-04
+2022-05-14 10:54:58,952 INFO [train.py:812] (0/8) Epoch 11, batch 1000, loss[loss=0.1831, simple_loss=0.2763, pruned_loss=0.04497, over 7309.00 frames.], tot_loss[loss=0.1801, simple_loss=0.266, pruned_loss=0.04708, over 1413543.60 frames.], batch size: 25, lr: 7.01e-04
+2022-05-14 10:55:58,045 INFO [train.py:812] (0/8) Epoch 11, batch 1050, loss[loss=0.1704, simple_loss=0.2518, pruned_loss=0.04447, over 7258.00 frames.], tot_loss[loss=0.181, simple_loss=0.2672, pruned_loss=0.04744, over 1408141.84 frames.], batch size: 19, lr: 7.00e-04
+2022-05-14 10:56:57,223 INFO [train.py:812] (0/8) Epoch 11, batch 1100, loss[loss=0.167, simple_loss=0.2527, pruned_loss=0.04064, over 7161.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2671, pruned_loss=0.04739, over 1413079.13 frames.], batch size: 18, lr: 7.00e-04
+2022-05-14 10:57:56,857 INFO [train.py:812] (0/8) Epoch 11, batch 1150, loss[loss=0.1832, simple_loss=0.2611, pruned_loss=0.05265, over 7068.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2667, pruned_loss=0.04736, over 1416632.23 frames.], batch size: 18, lr: 7.00e-04
+2022-05-14 10:58:55,459 INFO [train.py:812] (0/8) Epoch 11, batch 1200, loss[loss=0.1577, simple_loss=0.2371, pruned_loss=0.03919, over 6769.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2653, pruned_loss=0.04665, over 1419289.51 frames.], batch size: 15, lr: 6.99e-04
+2022-05-14 10:59:53,784 INFO [train.py:812] (0/8) Epoch 11, batch 1250, loss[loss=0.1678, simple_loss=0.2532, pruned_loss=0.04125, over 7123.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2654, pruned_loss=0.04677, over 1423333.47 frames.], batch size: 17, lr: 6.99e-04
+2022-05-14 11:00:50,428 INFO [train.py:812] (0/8) Epoch 11, batch 1300, loss[loss=0.1725, simple_loss=0.2622, pruned_loss=0.04146, over 7314.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2653, pruned_loss=0.04655, over 1419701.60 frames.], batch size: 21, lr: 6.99e-04
+2022-05-14 11:01:49,332 INFO [train.py:812] (0/8) Epoch 11, batch 1350, loss[loss=0.1858, simple_loss=0.2771, pruned_loss=0.0473, over 7327.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2655, pruned_loss=0.04648, over 1423902.26 frames.], batch size: 21, lr: 6.98e-04
+2022-05-14 11:02:46,393 INFO [train.py:812] (0/8) Epoch 11, batch 1400, loss[loss=0.1746, simple_loss=0.2625, pruned_loss=0.04334, over 7157.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2654, pruned_loss=0.04649, over 1426937.83 frames.], batch size: 19, lr: 6.98e-04
+2022-05-14 11:03:44,651 INFO [train.py:812] (0/8) Epoch 11, batch 1450, loss[loss=0.1889, simple_loss=0.2684, pruned_loss=0.05469, over 7290.00 frames.], tot_loss[loss=0.18, simple_loss=0.2663, pruned_loss=0.04689, over 1427418.62 frames.], batch size: 17, lr: 6.97e-04
+2022-05-14 11:04:41,619 INFO [train.py:812] (0/8) Epoch 11, batch 1500, loss[loss=0.1645, simple_loss=0.2657, pruned_loss=0.03167, over 7035.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2663, pruned_loss=0.04678, over 1425660.27 frames.], batch size: 28, lr: 6.97e-04
+2022-05-14 11:05:41,424 INFO [train.py:812] (0/8) Epoch 11, batch 1550, loss[loss=0.1528, simple_loss=0.2452, pruned_loss=0.03024, over 7427.00 frames.], tot_loss[loss=0.18, simple_loss=0.2664, pruned_loss=0.0468, over 1424103.98 frames.], batch size: 20, lr: 6.97e-04
+2022-05-14 11:06:38,924 INFO [train.py:812] (0/8) Epoch 11, batch 1600, loss[loss=0.202, simple_loss=0.2809, pruned_loss=0.06157, over 6736.00 frames.], tot_loss[loss=0.18, simple_loss=0.2661, pruned_loss=0.04696, over 1418526.83 frames.], batch size: 31, lr: 6.96e-04
+2022-05-14 11:07:38,315 INFO [train.py:812] (0/8) Epoch 11, batch 1650, loss[loss=0.1677, simple_loss=0.2473, pruned_loss=0.04407, over 6759.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2671, pruned_loss=0.04729, over 1418154.02 frames.], batch size: 15, lr: 6.96e-04
+2022-05-14 11:08:37,065 INFO [train.py:812] (0/8) Epoch 11, batch 1700, loss[loss=0.1628, simple_loss=0.2449, pruned_loss=0.04031, over 6785.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2673, pruned_loss=0.04713, over 1417796.59 frames.], batch size: 15, lr: 6.96e-04
+2022-05-14 11:09:36,815 INFO [train.py:812] (0/8) Epoch 11, batch 1750, loss[loss=0.189, simple_loss=0.2787, pruned_loss=0.0497, over 7103.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2667, pruned_loss=0.04723, over 1414512.33 frames.], batch size: 21, lr: 6.95e-04
+2022-05-14 11:10:35,673 INFO [train.py:812] (0/8) Epoch 11, batch 1800, loss[loss=0.2249, simple_loss=0.2928, pruned_loss=0.07853, over 4836.00 frames.], tot_loss[loss=0.181, simple_loss=0.2672, pruned_loss=0.04741, over 1414899.15 frames.], batch size: 53, lr: 6.95e-04
+2022-05-14 11:11:35,359 INFO [train.py:812] (0/8) Epoch 11, batch 1850, loss[loss=0.2125, simple_loss=0.2914, pruned_loss=0.06682, over 6569.00 frames.], tot_loss[loss=0.1809, simple_loss=0.267, pruned_loss=0.04736, over 1418855.16 frames.], batch size: 38, lr: 6.95e-04
+2022-05-14 11:12:33,306 INFO [train.py:812] (0/8) Epoch 11, batch 1900, loss[loss=0.1848, simple_loss=0.2887, pruned_loss=0.04047, over 7320.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2674, pruned_loss=0.04753, over 1423070.42 frames.], batch size: 21, lr: 6.94e-04
+2022-05-14 11:13:32,939 INFO [train.py:812] (0/8) Epoch 11, batch 1950, loss[loss=0.1979, simple_loss=0.285, pruned_loss=0.05535, over 7364.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2679, pruned_loss=0.0484, over 1422125.92 frames.], batch size: 19, lr: 6.94e-04
+2022-05-14 11:14:32,014 INFO [train.py:812] (0/8) Epoch 11, batch 2000, loss[loss=0.1703, simple_loss=0.258, pruned_loss=0.04125, over 7166.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2682, pruned_loss=0.04809, over 1423030.41 frames.], batch size: 18, lr: 6.93e-04
+2022-05-14 11:15:30,950 INFO [train.py:812] (0/8) Epoch 11, batch 2050, loss[loss=0.1538, simple_loss=0.229, pruned_loss=0.03936, over 7290.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2678, pruned_loss=0.0477, over 1424577.31 frames.], batch size: 17, lr: 6.93e-04
+2022-05-14 11:16:30,458 INFO [train.py:812] (0/8) Epoch 11, batch 2100, loss[loss=0.195, simple_loss=0.2815, pruned_loss=0.05427, over 7382.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2669, pruned_loss=0.04702, over 1425088.36 frames.], batch size: 23, lr: 6.93e-04
+2022-05-14 11:16:53,170 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-48000.pt
+2022-05-14 11:17:37,656 INFO [train.py:812] (0/8) Epoch 11, batch 2150, loss[loss=0.1741, simple_loss=0.2673, pruned_loss=0.0405, over 7175.00 frames.], tot_loss[loss=0.1806, simple_loss=0.267, pruned_loss=0.04711, over 1425356.96 frames.], batch size: 18, lr: 6.92e-04
+2022-05-14 11:18:36,038 INFO [train.py:812] (0/8) Epoch 11, batch 2200, loss[loss=0.1714, simple_loss=0.265, pruned_loss=0.03895, over 7232.00 frames.], tot_loss[loss=0.181, simple_loss=0.2674, pruned_loss=0.04729, over 1422673.48 frames.], batch size: 20, lr: 6.92e-04
+2022-05-14 11:19:35,097 INFO [train.py:812] (0/8) Epoch 11, batch 2250, loss[loss=0.1807, simple_loss=0.2725, pruned_loss=0.0444, over 7325.00 frames.], tot_loss[loss=0.1825, simple_loss=0.269, pruned_loss=0.04794, over 1425762.11 frames.], batch size: 22, lr: 6.92e-04
+2022-05-14 11:20:34,448 INFO [train.py:812] (0/8) Epoch 11, batch 2300, loss[loss=0.2173, simple_loss=0.3088, pruned_loss=0.06294, over 7155.00 frames.], tot_loss[loss=0.1827, simple_loss=0.269, pruned_loss=0.04822, over 1426329.76 frames.], batch size: 26, lr: 6.91e-04
+2022-05-14 11:21:33,291 INFO [train.py:812] (0/8) Epoch 11, batch 2350, loss[loss=0.1989, simple_loss=0.2844, pruned_loss=0.05665, over 6781.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2673, pruned_loss=0.04742, over 1428576.31 frames.], batch size: 31, lr: 6.91e-04
+2022-05-14 11:22:32,010 INFO [train.py:812] (0/8) Epoch 11, batch 2400, loss[loss=0.2, simple_loss=0.2859, pruned_loss=0.05708, over 7323.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2665, pruned_loss=0.04699, over 1423568.37 frames.], batch size: 21, lr: 6.91e-04
+2022-05-14 11:23:31,113 INFO [train.py:812] (0/8) Epoch 11, batch 2450, loss[loss=0.156, simple_loss=0.2532, pruned_loss=0.02937, over 6992.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2666, pruned_loss=0.04712, over 1424787.59 frames.], batch size: 16, lr: 6.90e-04
+2022-05-14 11:24:30,205 INFO [train.py:812] (0/8) Epoch 11, batch 2500, loss[loss=0.1838, simple_loss=0.2591, pruned_loss=0.0542, over 7165.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2679, pruned_loss=0.04793, over 1423065.10 frames.], batch size: 19, lr: 6.90e-04
+2022-05-14 11:25:29,315 INFO [train.py:812] (0/8) Epoch 11, batch 2550, loss[loss=0.1755, simple_loss=0.2575, pruned_loss=0.04678, over 6791.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2678, pruned_loss=0.04781, over 1426579.98 frames.], batch size: 15, lr: 6.90e-04
+2022-05-14 11:26:27,804 INFO [train.py:812] (0/8) Epoch 11, batch 2600, loss[loss=0.2117, simple_loss=0.2973, pruned_loss=0.06302, over 7372.00 frames.], tot_loss[loss=0.182, simple_loss=0.2678, pruned_loss=0.04805, over 1427613.22 frames.], batch size: 23, lr: 6.89e-04
+2022-05-14 11:27:26,095 INFO [train.py:812] (0/8) Epoch 11, batch 2650, loss[loss=0.1328, simple_loss=0.2167, pruned_loss=0.0245, over 6995.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2679, pruned_loss=0.04789, over 1423258.61 frames.], batch size: 16, lr: 6.89e-04
+2022-05-14 11:28:23,550 INFO [train.py:812] (0/8) Epoch 11, batch 2700, loss[loss=0.1675, simple_loss=0.2624, pruned_loss=0.0363, over 7420.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2678, pruned_loss=0.04758, over 1426064.44 frames.], batch size: 21, lr: 6.89e-04
+2022-05-14 11:29:21,000 INFO [train.py:812] (0/8) Epoch 11, batch 2750, loss[loss=0.1598, simple_loss=0.2511, pruned_loss=0.03425, over 7307.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2671, pruned_loss=0.04735, over 1424925.31 frames.], batch size: 18, lr: 6.88e-04
+2022-05-14 11:30:17,964 INFO [train.py:812] (0/8) Epoch 11, batch 2800, loss[loss=0.1936, simple_loss=0.2803, pruned_loss=0.05341, over 7161.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2678, pruned_loss=0.04786, over 1423783.52 frames.], batch size: 19, lr: 6.88e-04
+2022-05-14 11:31:17,635 INFO [train.py:812] (0/8) Epoch 11, batch 2850, loss[loss=0.1636, simple_loss=0.2517, pruned_loss=0.03779, over 7317.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2671, pruned_loss=0.04787, over 1424885.36 frames.], batch size: 21, lr: 6.87e-04
+2022-05-14 11:32:14,491 INFO [train.py:812] (0/8) Epoch 11, batch 2900, loss[loss=0.1834, simple_loss=0.2682, pruned_loss=0.04931, over 7206.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2668, pruned_loss=0.04757, over 1427735.29 frames.], batch size: 23, lr: 6.87e-04
+2022-05-14 11:33:13,348 INFO [train.py:812] (0/8) Epoch 11, batch 2950, loss[loss=0.2156, simple_loss=0.3067, pruned_loss=0.06231, over 7195.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2676, pruned_loss=0.0477, over 1424803.70 frames.], batch size: 22, lr: 6.87e-04
+2022-05-14 11:34:12,258 INFO [train.py:812] (0/8) Epoch 11, batch 3000, loss[loss=0.1443, simple_loss=0.2352, pruned_loss=0.02665, over 7160.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2678, pruned_loss=0.04779, over 1423667.30 frames.], batch size: 18, lr: 6.86e-04
+2022-05-14 11:34:12,259 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 11:34:19,822 INFO [train.py:841] (0/8) Epoch 11, validation: loss=0.1564, simple_loss=0.2581, pruned_loss=0.02737, over 698248.00 frames.
+2022-05-14 11:35:18,261 INFO [train.py:812] (0/8) Epoch 11, batch 3050, loss[loss=0.2169, simple_loss=0.3032, pruned_loss=0.06531, over 7158.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2663, pruned_loss=0.04723, over 1428098.31 frames.], batch size: 26, lr: 6.86e-04
+2022-05-14 11:36:16,795 INFO [train.py:812] (0/8) Epoch 11, batch 3100, loss[loss=0.1911, simple_loss=0.2685, pruned_loss=0.05683, over 7426.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2664, pruned_loss=0.047, over 1426267.82 frames.], batch size: 18, lr: 6.86e-04
+2022-05-14 11:37:16,184 INFO [train.py:812] (0/8) Epoch 11, batch 3150, loss[loss=0.1595, simple_loss=0.2485, pruned_loss=0.03525, over 7268.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2656, pruned_loss=0.04667, over 1428246.18 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:38:15,169 INFO [train.py:812] (0/8) Epoch 11, batch 3200, loss[loss=0.1743, simple_loss=0.259, pruned_loss=0.04483, over 7167.00 frames.], tot_loss[loss=0.179, simple_loss=0.2649, pruned_loss=0.04661, over 1429476.94 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:39:14,954 INFO [train.py:812] (0/8) Epoch 11, batch 3250, loss[loss=0.1811, simple_loss=0.2704, pruned_loss=0.04592, over 7074.00 frames.], tot_loss[loss=0.1793, simple_loss=0.265, pruned_loss=0.04675, over 1430891.70 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:40:14,329 INFO [train.py:812] (0/8) Epoch 11, batch 3300, loss[loss=0.1903, simple_loss=0.2787, pruned_loss=0.05092, over 6384.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2645, pruned_loss=0.04614, over 1430357.54 frames.], batch size: 37, lr: 6.84e-04
+2022-05-14 11:41:13,908 INFO [train.py:812] (0/8) Epoch 11, batch 3350, loss[loss=0.1924, simple_loss=0.2933, pruned_loss=0.04574, over 7106.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2652, pruned_loss=0.0463, over 1423855.11 frames.], batch size: 21, lr: 6.84e-04
+2022-05-14 11:42:12,468 INFO [train.py:812] (0/8) Epoch 11, batch 3400, loss[loss=0.1514, simple_loss=0.2284, pruned_loss=0.03716, over 6990.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2658, pruned_loss=0.04669, over 1422003.34 frames.], batch size: 16, lr: 6.84e-04
+2022-05-14 11:43:11,486 INFO [train.py:812] (0/8) Epoch 11, batch 3450, loss[loss=0.1996, simple_loss=0.2916, pruned_loss=0.05379, over 7106.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2662, pruned_loss=0.04672, over 1425052.44 frames.], batch size: 21, lr: 6.83e-04
+2022-05-14 11:44:10,165 INFO [train.py:812] (0/8) Epoch 11, batch 3500, loss[loss=0.1508, simple_loss=0.2339, pruned_loss=0.03386, over 7419.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2657, pruned_loss=0.0467, over 1425703.80 frames.], batch size: 18, lr: 6.83e-04
+2022-05-14 11:45:10,017 INFO [train.py:812] (0/8) Epoch 11, batch 3550, loss[loss=0.1777, simple_loss=0.2669, pruned_loss=0.0443, over 6436.00 frames.], tot_loss[loss=0.1797, simple_loss=0.266, pruned_loss=0.0467, over 1424054.46 frames.], batch size: 38, lr: 6.83e-04
+2022-05-14 11:46:08,745 INFO [train.py:812] (0/8) Epoch 11, batch 3600, loss[loss=0.1739, simple_loss=0.2626, pruned_loss=0.04258, over 6418.00 frames.], tot_loss[loss=0.18, simple_loss=0.2665, pruned_loss=0.04674, over 1419899.56 frames.], batch size: 38, lr: 6.82e-04
+2022-05-14 11:47:07,790 INFO [train.py:812] (0/8) Epoch 11, batch 3650, loss[loss=0.2031, simple_loss=0.2932, pruned_loss=0.05651, over 7127.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2664, pruned_loss=0.04654, over 1422356.39 frames.], batch size: 21, lr: 6.82e-04
+2022-05-14 11:48:06,828 INFO [train.py:812] (0/8) Epoch 11, batch 3700, loss[loss=0.1729, simple_loss=0.2606, pruned_loss=0.04263, over 7116.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2665, pruned_loss=0.04664, over 1418461.51 frames.], batch size: 21, lr: 6.82e-04
+2022-05-14 11:49:06,465 INFO [train.py:812] (0/8) Epoch 11, batch 3750, loss[loss=0.1666, simple_loss=0.2581, pruned_loss=0.03755, over 7431.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2664, pruned_loss=0.04658, over 1424016.92 frames.], batch size: 20, lr: 6.81e-04
+2022-05-14 11:50:05,388 INFO [train.py:812] (0/8) Epoch 11, batch 3800, loss[loss=0.1851, simple_loss=0.2713, pruned_loss=0.04942, over 7279.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2662, pruned_loss=0.04666, over 1422294.08 frames.], batch size: 24, lr: 6.81e-04
+2022-05-14 11:51:04,556 INFO [train.py:812] (0/8) Epoch 11, batch 3850, loss[loss=0.2175, simple_loss=0.3025, pruned_loss=0.06628, over 7213.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2661, pruned_loss=0.04649, over 1426467.93 frames.], batch size: 22, lr: 6.81e-04
+2022-05-14 11:52:01,419 INFO [train.py:812] (0/8) Epoch 11, batch 3900, loss[loss=0.1632, simple_loss=0.2551, pruned_loss=0.03568, over 7376.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2658, pruned_loss=0.04631, over 1427294.10 frames.], batch size: 23, lr: 6.80e-04
+2022-05-14 11:53:00,852 INFO [train.py:812] (0/8) Epoch 11, batch 3950, loss[loss=0.186, simple_loss=0.2708, pruned_loss=0.05056, over 7430.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2661, pruned_loss=0.04675, over 1426676.38 frames.], batch size: 20, lr: 6.80e-04
+2022-05-14 11:53:59,469 INFO [train.py:812] (0/8) Epoch 11, batch 4000, loss[loss=0.164, simple_loss=0.2577, pruned_loss=0.03518, over 7218.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2663, pruned_loss=0.04715, over 1417055.03 frames.], batch size: 21, lr: 6.80e-04
+2022-05-14 11:54:58,914 INFO [train.py:812] (0/8) Epoch 11, batch 4050, loss[loss=0.1958, simple_loss=0.2808, pruned_loss=0.05545, over 7214.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2663, pruned_loss=0.04708, over 1416945.37 frames.], batch size: 22, lr: 6.79e-04
+2022-05-14 11:55:57,972 INFO [train.py:812] (0/8) Epoch 11, batch 4100, loss[loss=0.1814, simple_loss=0.2604, pruned_loss=0.05121, over 7199.00 frames.], tot_loss[loss=0.181, simple_loss=0.2668, pruned_loss=0.04765, over 1417574.98 frames.], batch size: 22, lr: 6.79e-04
+2022-05-14 11:56:56,090 INFO [train.py:812] (0/8) Epoch 11, batch 4150, loss[loss=0.2071, simple_loss=0.2964, pruned_loss=0.05891, over 6721.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2682, pruned_loss=0.04819, over 1414992.90 frames.], batch size: 31, lr: 6.79e-04
+2022-05-14 11:57:54,848 INFO [train.py:812] (0/8) Epoch 11, batch 4200, loss[loss=0.1643, simple_loss=0.2559, pruned_loss=0.03636, over 7082.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2678, pruned_loss=0.04758, over 1416116.13 frames.], batch size: 28, lr: 6.78e-04
+2022-05-14 11:58:54,360 INFO [train.py:812] (0/8) Epoch 11, batch 4250, loss[loss=0.2351, simple_loss=0.3069, pruned_loss=0.08162, over 4977.00 frames.], tot_loss[loss=0.18, simple_loss=0.2663, pruned_loss=0.04688, over 1415244.25 frames.], batch size: 52, lr: 6.78e-04
+2022-05-14 11:59:53,062 INFO [train.py:812] (0/8) Epoch 11, batch 4300, loss[loss=0.2404, simple_loss=0.3141, pruned_loss=0.0833, over 4861.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2669, pruned_loss=0.0476, over 1410682.26 frames.], batch size: 55, lr: 6.78e-04
+2022-05-14 12:00:52,215 INFO [train.py:812] (0/8) Epoch 11, batch 4350, loss[loss=0.1862, simple_loss=0.2743, pruned_loss=0.04906, over 7232.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2674, pruned_loss=0.04793, over 1409233.39 frames.], batch size: 20, lr: 6.77e-04
+2022-05-14 12:01:50,103 INFO [train.py:812] (0/8) Epoch 11, batch 4400, loss[loss=0.1813, simple_loss=0.2666, pruned_loss=0.04802, over 7188.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2675, pruned_loss=0.04762, over 1414755.54 frames.], batch size: 22, lr: 6.77e-04
+2022-05-14 12:02:49,052 INFO [train.py:812] (0/8) Epoch 11, batch 4450, loss[loss=0.2132, simple_loss=0.2983, pruned_loss=0.064, over 7236.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2692, pruned_loss=0.04817, over 1417657.54 frames.], batch size: 20, lr: 6.77e-04
+2022-05-14 12:03:48,060 INFO [train.py:812] (0/8) Epoch 11, batch 4500, loss[loss=0.2141, simple_loss=0.2958, pruned_loss=0.06624, over 5371.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2702, pruned_loss=0.04871, over 1410156.40 frames.], batch size: 54, lr: 6.76e-04
+2022-05-14 12:04:46,785 INFO [train.py:812] (0/8) Epoch 11, batch 4550, loss[loss=0.2135, simple_loss=0.2871, pruned_loss=0.07, over 4961.00 frames.], tot_loss[loss=0.187, simple_loss=0.2722, pruned_loss=0.05087, over 1347080.60 frames.], batch size: 52, lr: 6.76e-04
+2022-05-14 12:05:31,691 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-11.pt
+2022-05-14 12:05:55,028 INFO [train.py:812] (0/8) Epoch 12, batch 0, loss[loss=0.1852, simple_loss=0.2772, pruned_loss=0.0466, over 7418.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2772, pruned_loss=0.0466, over 7418.00 frames.], batch size: 21, lr: 6.52e-04
+2022-05-14 12:06:54,742 INFO [train.py:812] (0/8) Epoch 12, batch 50, loss[loss=0.2306, simple_loss=0.3099, pruned_loss=0.07566, over 5076.00 frames.], tot_loss[loss=0.178, simple_loss=0.2648, pruned_loss=0.04562, over 319225.36 frames.], batch size: 52, lr: 6.52e-04
+2022-05-14 12:07:53,903 INFO [train.py:812] (0/8) Epoch 12, batch 100, loss[loss=0.171, simple_loss=0.2549, pruned_loss=0.04359, over 6271.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2672, pruned_loss=0.04616, over 558381.74 frames.], batch size: 37, lr: 6.51e-04
+2022-05-14 12:08:53,516 INFO [train.py:812] (0/8) Epoch 12, batch 150, loss[loss=0.1662, simple_loss=0.2479, pruned_loss=0.04228, over 7270.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2687, pruned_loss=0.04679, over 748147.53 frames.], batch size: 17, lr: 6.51e-04
+2022-05-14 12:09:52,556 INFO [train.py:812] (0/8) Epoch 12, batch 200, loss[loss=0.1916, simple_loss=0.2887, pruned_loss=0.04726, over 7199.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2687, pruned_loss=0.04732, over 895629.10 frames.], batch size: 22, lr: 6.51e-04
+2022-05-14 12:10:51,851 INFO [train.py:812] (0/8) Epoch 12, batch 250, loss[loss=0.1875, simple_loss=0.2802, pruned_loss=0.04744, over 6762.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2679, pruned_loss=0.04695, over 1013738.91 frames.], batch size: 31, lr: 6.50e-04
+2022-05-14 12:11:51,030 INFO [train.py:812] (0/8) Epoch 12, batch 300, loss[loss=0.1835, simple_loss=0.2786, pruned_loss=0.04421, over 7197.00 frames.], tot_loss[loss=0.1809, simple_loss=0.268, pruned_loss=0.0469, over 1097870.99 frames.], batch size: 22, lr: 6.50e-04
+2022-05-14 12:12:50,777 INFO [train.py:812] (0/8) Epoch 12, batch 350, loss[loss=0.1615, simple_loss=0.2527, pruned_loss=0.03517, over 7332.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2663, pruned_loss=0.04637, over 1165411.71 frames.], batch size: 22, lr: 6.50e-04
+2022-05-14 12:13:50,254 INFO [train.py:812] (0/8) Epoch 12, batch 400, loss[loss=0.1616, simple_loss=0.2537, pruned_loss=0.03477, over 7349.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2667, pruned_loss=0.04636, over 1220739.45 frames.], batch size: 22, lr: 6.49e-04
+2022-05-14 12:14:48,420 INFO [train.py:812] (0/8) Epoch 12, batch 450, loss[loss=0.151, simple_loss=0.2416, pruned_loss=0.03018, over 7153.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2668, pruned_loss=0.04636, over 1268801.24 frames.], batch size: 19, lr: 6.49e-04
+2022-05-14 12:15:47,356 INFO [train.py:812] (0/8) Epoch 12, batch 500, loss[loss=0.2553, simple_loss=0.3273, pruned_loss=0.09171, over 7382.00 frames.], tot_loss[loss=0.179, simple_loss=0.2659, pruned_loss=0.046, over 1302499.94 frames.], batch size: 23, lr: 6.49e-04
+2022-05-14 12:16:45,618 INFO [train.py:812] (0/8) Epoch 12, batch 550, loss[loss=0.1809, simple_loss=0.2788, pruned_loss=0.04147, over 7411.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2653, pruned_loss=0.04554, over 1328573.96 frames.], batch size: 21, lr: 6.48e-04
+2022-05-14 12:17:43,499 INFO [train.py:812] (0/8) Epoch 12, batch 600, loss[loss=0.1804, simple_loss=0.2745, pruned_loss=0.0431, over 7349.00 frames.], tot_loss[loss=0.178, simple_loss=0.2648, pruned_loss=0.04561, over 1349090.38 frames.], batch size: 22, lr: 6.48e-04
+2022-05-14 12:18:41,732 INFO [train.py:812] (0/8) Epoch 12, batch 650, loss[loss=0.1946, simple_loss=0.2863, pruned_loss=0.05147, over 7378.00 frames.], tot_loss[loss=0.1764, simple_loss=0.263, pruned_loss=0.04487, over 1370113.27 frames.], batch size: 23, lr: 6.48e-04
+2022-05-14 12:19:49,849 INFO [train.py:812] (0/8) Epoch 12, batch 700, loss[loss=0.2225, simple_loss=0.3063, pruned_loss=0.06935, over 7300.00 frames.], tot_loss[loss=0.177, simple_loss=0.2638, pruned_loss=0.04508, over 1380065.05 frames.], batch size: 24, lr: 6.47e-04
+2022-05-14 12:20:48,646 INFO [train.py:812] (0/8) Epoch 12, batch 750, loss[loss=0.1734, simple_loss=0.2715, pruned_loss=0.03764, over 7321.00 frames.], tot_loss[loss=0.1786, simple_loss=0.265, pruned_loss=0.04609, over 1385805.71 frames.], batch size: 20, lr: 6.47e-04
+2022-05-14 12:21:47,947 INFO [train.py:812] (0/8) Epoch 12, batch 800, loss[loss=0.1558, simple_loss=0.2318, pruned_loss=0.03987, over 7414.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2651, pruned_loss=0.04617, over 1398002.24 frames.], batch size: 18, lr: 6.47e-04
+2022-05-14 12:22:46,130 INFO [train.py:812] (0/8) Epoch 12, batch 850, loss[loss=0.1903, simple_loss=0.2824, pruned_loss=0.0491, over 7003.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2652, pruned_loss=0.04603, over 1403870.01 frames.], batch size: 32, lr: 6.46e-04
+2022-05-14 12:23:43,968 INFO [train.py:812] (0/8) Epoch 12, batch 900, loss[loss=0.1837, simple_loss=0.2811, pruned_loss=0.04321, over 7336.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2654, pruned_loss=0.04584, over 1407846.40 frames.], batch size: 22, lr: 6.46e-04
+2022-05-14 12:24:43,677 INFO [train.py:812] (0/8) Epoch 12, batch 950, loss[loss=0.1605, simple_loss=0.2414, pruned_loss=0.03981, over 7441.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2654, pruned_loss=0.04585, over 1412705.96 frames.], batch size: 20, lr: 6.46e-04
+2022-05-14 12:25:42,162 INFO [train.py:812] (0/8) Epoch 12, batch 1000, loss[loss=0.1541, simple_loss=0.2449, pruned_loss=0.03167, over 7148.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2657, pruned_loss=0.04589, over 1415593.69 frames.], batch size: 19, lr: 6.46e-04
+2022-05-14 12:26:41,688 INFO [train.py:812] (0/8) Epoch 12, batch 1050, loss[loss=0.1452, simple_loss=0.2266, pruned_loss=0.03191, over 7000.00 frames.], tot_loss[loss=0.1789, simple_loss=0.266, pruned_loss=0.0459, over 1415008.20 frames.], batch size: 16, lr: 6.45e-04
+2022-05-14 12:27:40,717 INFO [train.py:812] (0/8) Epoch 12, batch 1100, loss[loss=0.1812, simple_loss=0.2665, pruned_loss=0.04795, over 7157.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2666, pruned_loss=0.04626, over 1417417.70 frames.], batch size: 19, lr: 6.45e-04
+2022-05-14 12:28:40,250 INFO [train.py:812] (0/8) Epoch 12, batch 1150, loss[loss=0.244, simple_loss=0.3117, pruned_loss=0.08817, over 5331.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2662, pruned_loss=0.04613, over 1420930.72 frames.], batch size: 53, lr: 6.45e-04
+2022-05-14 12:29:38,129 INFO [train.py:812] (0/8) Epoch 12, batch 1200, loss[loss=0.1698, simple_loss=0.2624, pruned_loss=0.03857, over 7117.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2659, pruned_loss=0.04629, over 1423349.54 frames.], batch size: 21, lr: 6.44e-04
+2022-05-14 12:30:37,009 INFO [train.py:812] (0/8) Epoch 12, batch 1250, loss[loss=0.1623, simple_loss=0.2418, pruned_loss=0.0414, over 6994.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2646, pruned_loss=0.04541, over 1424588.71 frames.], batch size: 16, lr: 6.44e-04
+2022-05-14 12:31:36,633 INFO [train.py:812] (0/8) Epoch 12, batch 1300, loss[loss=0.1682, simple_loss=0.2617, pruned_loss=0.03732, over 7321.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2647, pruned_loss=0.04552, over 1426483.67 frames.], batch size: 20, lr: 6.44e-04
+2022-05-14 12:32:34,807 INFO [train.py:812] (0/8) Epoch 12, batch 1350, loss[loss=0.1625, simple_loss=0.2506, pruned_loss=0.03718, over 7324.00 frames.], tot_loss[loss=0.178, simple_loss=0.2649, pruned_loss=0.04555, over 1423356.29 frames.], batch size: 21, lr: 6.43e-04
+2022-05-14 12:33:34,080 INFO [train.py:812] (0/8) Epoch 12, batch 1400, loss[loss=0.173, simple_loss=0.2681, pruned_loss=0.03892, over 7325.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2643, pruned_loss=0.04551, over 1420465.13 frames.], batch size: 21, lr: 6.43e-04
+2022-05-14 12:34:33,343 INFO [train.py:812] (0/8) Epoch 12, batch 1450, loss[loss=0.1823, simple_loss=0.2673, pruned_loss=0.04867, over 7067.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2648, pruned_loss=0.04593, over 1420486.04 frames.], batch size: 18, lr: 6.43e-04
+2022-05-14 12:35:32,024 INFO [train.py:812] (0/8) Epoch 12, batch 1500, loss[loss=0.1837, simple_loss=0.2737, pruned_loss=0.04688, over 7205.00 frames.], tot_loss[loss=0.178, simple_loss=0.2644, pruned_loss=0.04581, over 1424486.08 frames.], batch size: 23, lr: 6.42e-04
+2022-05-14 12:36:09,401 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-52000.pt
+2022-05-14 12:36:36,797 INFO [train.py:812] (0/8) Epoch 12, batch 1550, loss[loss=0.1768, simple_loss=0.2587, pruned_loss=0.04751, over 7236.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2646, pruned_loss=0.04633, over 1423899.74 frames.], batch size: 20, lr: 6.42e-04
+2022-05-14 12:37:35,854 INFO [train.py:812] (0/8) Epoch 12, batch 1600, loss[loss=0.1437, simple_loss=0.2433, pruned_loss=0.02205, over 7354.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2654, pruned_loss=0.04643, over 1424987.23 frames.], batch size: 19, lr: 6.42e-04
+2022-05-14 12:38:44,918 INFO [train.py:812] (0/8) Epoch 12, batch 1650, loss[loss=0.1702, simple_loss=0.264, pruned_loss=0.03821, over 7374.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2653, pruned_loss=0.04655, over 1425873.60 frames.], batch size: 23, lr: 6.42e-04
+2022-05-14 12:39:52,046 INFO [train.py:812] (0/8) Epoch 12, batch 1700, loss[loss=0.1798, simple_loss=0.2704, pruned_loss=0.0446, over 7227.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2654, pruned_loss=0.0462, over 1426784.00 frames.], batch size: 21, lr: 6.41e-04
+2022-05-14 12:40:51,340 INFO [train.py:812] (0/8) Epoch 12, batch 1750, loss[loss=0.1737, simple_loss=0.2612, pruned_loss=0.04311, over 7161.00 frames.], tot_loss[loss=0.1782, simple_loss=0.265, pruned_loss=0.04568, over 1427442.14 frames.], batch size: 26, lr: 6.41e-04
+2022-05-14 12:41:58,739 INFO [train.py:812] (0/8) Epoch 12, batch 1800, loss[loss=0.1466, simple_loss=0.2376, pruned_loss=0.02783, over 6988.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2641, pruned_loss=0.0454, over 1427600.55 frames.], batch size: 16, lr: 6.41e-04
+2022-05-14 12:43:07,988 INFO [train.py:812] (0/8) Epoch 12, batch 1850, loss[loss=0.1678, simple_loss=0.2625, pruned_loss=0.03654, over 7146.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2642, pruned_loss=0.04548, over 1426058.27 frames.], batch size: 26, lr: 6.40e-04
+2022-05-14 12:44:16,792 INFO [train.py:812] (0/8) Epoch 12, batch 1900, loss[loss=0.1727, simple_loss=0.2572, pruned_loss=0.04407, over 7439.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2636, pruned_loss=0.04551, over 1428587.03 frames.], batch size: 20, lr: 6.40e-04
+2022-05-14 12:45:34,897 INFO [train.py:812] (0/8) Epoch 12, batch 1950, loss[loss=0.2074, simple_loss=0.2772, pruned_loss=0.06876, over 7012.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2642, pruned_loss=0.04584, over 1427351.09 frames.], batch size: 16, lr: 6.40e-04
+2022-05-14 12:46:34,648 INFO [train.py:812] (0/8) Epoch 12, batch 2000, loss[loss=0.1919, simple_loss=0.2801, pruned_loss=0.05181, over 6386.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2648, pruned_loss=0.04609, over 1425927.22 frames.], batch size: 38, lr: 6.39e-04
+2022-05-14 12:47:34,838 INFO [train.py:812] (0/8) Epoch 12, batch 2050, loss[loss=0.2062, simple_loss=0.2863, pruned_loss=0.06302, over 7382.00 frames.], tot_loss[loss=0.178, simple_loss=0.2645, pruned_loss=0.04573, over 1423712.53 frames.], batch size: 23, lr: 6.39e-04
+2022-05-14 12:48:34,310 INFO [train.py:812] (0/8) Epoch 12, batch 2100, loss[loss=0.1987, simple_loss=0.2812, pruned_loss=0.05813, over 6816.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2652, pruned_loss=0.04611, over 1427558.88 frames.], batch size: 31, lr: 6.39e-04
+2022-05-14 12:49:34,322 INFO [train.py:812] (0/8) Epoch 12, batch 2150, loss[loss=0.1783, simple_loss=0.2665, pruned_loss=0.04506, over 6814.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2654, pruned_loss=0.04616, over 1422447.65 frames.], batch size: 15, lr: 6.38e-04
+2022-05-14 12:50:33,511 INFO [train.py:812] (0/8) Epoch 12, batch 2200, loss[loss=0.155, simple_loss=0.2406, pruned_loss=0.03473, over 7430.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2649, pruned_loss=0.04588, over 1426780.24 frames.], batch size: 20, lr: 6.38e-04
+2022-05-14 12:51:31,622 INFO [train.py:812] (0/8) Epoch 12, batch 2250, loss[loss=0.1953, simple_loss=0.2774, pruned_loss=0.05656, over 7139.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2641, pruned_loss=0.04565, over 1425539.17 frames.], batch size: 17, lr: 6.38e-04
+2022-05-14 12:52:29,473 INFO [train.py:812] (0/8) Epoch 12, batch 2300, loss[loss=0.1585, simple_loss=0.2439, pruned_loss=0.03653, over 7361.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2646, pruned_loss=0.04556, over 1424094.98 frames.], batch size: 19, lr: 6.38e-04
+2022-05-14 12:53:28,619 INFO [train.py:812] (0/8) Epoch 12, batch 2350, loss[loss=0.1872, simple_loss=0.279, pruned_loss=0.0477, over 7285.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2647, pruned_loss=0.0453, over 1425801.00 frames.], batch size: 24, lr: 6.37e-04
+2022-05-14 12:54:27,655 INFO [train.py:812] (0/8) Epoch 12, batch 2400, loss[loss=0.1746, simple_loss=0.2568, pruned_loss=0.04618, over 7111.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2649, pruned_loss=0.04514, over 1428128.25 frames.], batch size: 21, lr: 6.37e-04
+2022-05-14 12:55:26,376 INFO [train.py:812] (0/8) Epoch 12, batch 2450, loss[loss=0.1874, simple_loss=0.2752, pruned_loss=0.04979, over 7241.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2655, pruned_loss=0.0454, over 1426157.51 frames.], batch size: 20, lr: 6.37e-04
+2022-05-14 12:56:25,425 INFO [train.py:812] (0/8) Epoch 12, batch 2500, loss[loss=0.167, simple_loss=0.2398, pruned_loss=0.04708, over 7069.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2648, pruned_loss=0.04521, over 1425624.31 frames.], batch size: 18, lr: 6.36e-04
+2022-05-14 12:57:25,036 INFO [train.py:812] (0/8) Epoch 12, batch 2550, loss[loss=0.1477, simple_loss=0.2289, pruned_loss=0.03319, over 7265.00 frames.], tot_loss[loss=0.1779, simple_loss=0.265, pruned_loss=0.04538, over 1427970.36 frames.], batch size: 17, lr: 6.36e-04
+2022-05-14 12:58:23,568 INFO [train.py:812] (0/8) Epoch 12, batch 2600, loss[loss=0.1937, simple_loss=0.2796, pruned_loss=0.05391, over 7288.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2649, pruned_loss=0.04568, over 1422766.53 frames.], batch size: 24, lr: 6.36e-04
+2022-05-14 12:59:22,465 INFO [train.py:812] (0/8) Epoch 12, batch 2650, loss[loss=0.1618, simple_loss=0.252, pruned_loss=0.03584, over 7271.00 frames.], tot_loss[loss=0.1792, simple_loss=0.266, pruned_loss=0.04623, over 1419429.91 frames.], batch size: 19, lr: 6.36e-04
+2022-05-14 13:00:21,647 INFO [train.py:812] (0/8) Epoch 12, batch 2700, loss[loss=0.2111, simple_loss=0.2933, pruned_loss=0.0645, over 7305.00 frames.], tot_loss[loss=0.179, simple_loss=0.2659, pruned_loss=0.04601, over 1423600.31 frames.], batch size: 25, lr: 6.35e-04
+2022-05-14 13:01:21,314 INFO [train.py:812] (0/8) Epoch 12, batch 2750, loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03253, over 7438.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2652, pruned_loss=0.0457, over 1426188.88 frames.], batch size: 20, lr: 6.35e-04
+2022-05-14 13:02:20,419 INFO [train.py:812] (0/8) Epoch 12, batch 2800, loss[loss=0.1893, simple_loss=0.279, pruned_loss=0.0498, over 7113.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2657, pruned_loss=0.04588, over 1427234.15 frames.], batch size: 21, lr: 6.35e-04
+2022-05-14 13:03:19,805 INFO [train.py:812] (0/8) Epoch 12, batch 2850, loss[loss=0.1817, simple_loss=0.2721, pruned_loss=0.04563, over 7314.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2651, pruned_loss=0.04601, over 1428951.81 frames.], batch size: 21, lr: 6.34e-04
+2022-05-14 13:04:18,952 INFO [train.py:812] (0/8) Epoch 12, batch 2900, loss[loss=0.179, simple_loss=0.2712, pruned_loss=0.04346, over 7277.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2659, pruned_loss=0.0462, over 1425000.62 frames.], batch size: 24, lr: 6.34e-04
+2022-05-14 13:05:18,604 INFO [train.py:812] (0/8) Epoch 12, batch 2950, loss[loss=0.1799, simple_loss=0.2766, pruned_loss=0.04161, over 7206.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2658, pruned_loss=0.04621, over 1420880.56 frames.], batch size: 21, lr: 6.34e-04
+2022-05-14 13:06:17,606 INFO [train.py:812] (0/8) Epoch 12, batch 3000, loss[loss=0.1839, simple_loss=0.28, pruned_loss=0.04389, over 7291.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2654, pruned_loss=0.04558, over 1422330.70 frames.], batch size: 25, lr: 6.33e-04
+2022-05-14 13:06:17,607 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 13:06:26,033 INFO [train.py:841] (0/8) Epoch 12, validation: loss=0.1553, simple_loss=0.2571, pruned_loss=0.02678, over 698248.00 frames.
+2022-05-14 13:07:25,166 INFO [train.py:812] (0/8) Epoch 12, batch 3050, loss[loss=0.1855, simple_loss=0.2778, pruned_loss=0.04656, over 7390.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2664, pruned_loss=0.04607, over 1419895.15 frames.], batch size: 23, lr: 6.33e-04
+2022-05-14 13:08:24,602 INFO [train.py:812] (0/8) Epoch 12, batch 3100, loss[loss=0.1766, simple_loss=0.2615, pruned_loss=0.04585, over 7320.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2653, pruned_loss=0.04584, over 1423030.49 frames.], batch size: 20, lr: 6.33e-04
+2022-05-14 13:09:23,897 INFO [train.py:812] (0/8) Epoch 12, batch 3150, loss[loss=0.1816, simple_loss=0.2748, pruned_loss=0.04416, over 7393.00 frames.], tot_loss[loss=0.1782, simple_loss=0.265, pruned_loss=0.04567, over 1425854.04 frames.], batch size: 23, lr: 6.33e-04
+2022-05-14 13:10:22,787 INFO [train.py:812] (0/8) Epoch 12, batch 3200, loss[loss=0.1694, simple_loss=0.2614, pruned_loss=0.03876, over 7119.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2645, pruned_loss=0.04553, over 1425260.73 frames.], batch size: 21, lr: 6.32e-04
+2022-05-14 13:11:22,009 INFO [train.py:812] (0/8) Epoch 12, batch 3250, loss[loss=0.1595, simple_loss=0.2527, pruned_loss=0.03314, over 7407.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2639, pruned_loss=0.04512, over 1425894.41 frames.], batch size: 21, lr: 6.32e-04
+2022-05-14 13:12:21,130 INFO [train.py:812] (0/8) Epoch 12, batch 3300, loss[loss=0.1882, simple_loss=0.2514, pruned_loss=0.06243, over 7459.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2655, pruned_loss=0.04581, over 1425824.05 frames.], batch size: 17, lr: 6.32e-04
+2022-05-14 13:13:18,552 INFO [train.py:812] (0/8) Epoch 12, batch 3350, loss[loss=0.1681, simple_loss=0.2528, pruned_loss=0.04175, over 7280.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2654, pruned_loss=0.04596, over 1426630.92 frames.], batch size: 18, lr: 6.31e-04
+2022-05-14 13:14:17,105 INFO [train.py:812] (0/8) Epoch 12, batch 3400, loss[loss=0.2005, simple_loss=0.2907, pruned_loss=0.05521, over 6427.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2654, pruned_loss=0.04582, over 1420843.86 frames.], batch size: 38, lr: 6.31e-04
+2022-05-14 13:15:16,671 INFO [train.py:812] (0/8) Epoch 12, batch 3450, loss[loss=0.167, simple_loss=0.2614, pruned_loss=0.03626, over 7124.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2641, pruned_loss=0.04503, over 1419104.11 frames.], batch size: 21, lr: 6.31e-04
+2022-05-14 13:16:15,093 INFO [train.py:812] (0/8) Epoch 12, batch 3500, loss[loss=0.1641, simple_loss=0.2621, pruned_loss=0.03302, over 7325.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2639, pruned_loss=0.04471, over 1425024.92 frames.], batch size: 21, lr: 6.31e-04
+2022-05-14 13:17:13,770 INFO [train.py:812] (0/8) Epoch 12, batch 3550, loss[loss=0.1368, simple_loss=0.2229, pruned_loss=0.02535, over 6987.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2638, pruned_loss=0.04461, over 1423566.89 frames.], batch size: 16, lr: 6.30e-04
+2022-05-14 13:18:12,625 INFO [train.py:812] (0/8) Epoch 12, batch 3600, loss[loss=0.1607, simple_loss=0.248, pruned_loss=0.03669, over 7242.00 frames.], tot_loss[loss=0.1762, simple_loss=0.264, pruned_loss=0.0442, over 1425236.98 frames.], batch size: 20, lr: 6.30e-04
+2022-05-14 13:19:11,477 INFO [train.py:812] (0/8) Epoch 12, batch 3650, loss[loss=0.1624, simple_loss=0.2569, pruned_loss=0.03394, over 7428.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2638, pruned_loss=0.04426, over 1424713.83 frames.], batch size: 20, lr: 6.30e-04
+2022-05-14 13:20:08,354 INFO [train.py:812] (0/8) Epoch 12, batch 3700, loss[loss=0.1924, simple_loss=0.2869, pruned_loss=0.0489, over 6787.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2641, pruned_loss=0.04423, over 1421584.43 frames.], batch size: 31, lr: 6.29e-04
+2022-05-14 13:21:06,355 INFO [train.py:812] (0/8) Epoch 12, batch 3750, loss[loss=0.1947, simple_loss=0.2732, pruned_loss=0.05813, over 7377.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2642, pruned_loss=0.04446, over 1425598.18 frames.], batch size: 23, lr: 6.29e-04
+2022-05-14 13:22:05,786 INFO [train.py:812] (0/8) Epoch 12, batch 3800, loss[loss=0.2021, simple_loss=0.3039, pruned_loss=0.05015, over 7138.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2637, pruned_loss=0.04439, over 1427400.08 frames.], batch size: 26, lr: 6.29e-04
+2022-05-14 13:23:04,540 INFO [train.py:812] (0/8) Epoch 12, batch 3850, loss[loss=0.1795, simple_loss=0.2625, pruned_loss=0.04823, over 7098.00 frames.], tot_loss[loss=0.176, simple_loss=0.2638, pruned_loss=0.04409, over 1428558.78 frames.], batch size: 21, lr: 6.29e-04
+2022-05-14 13:24:03,539 INFO [train.py:812] (0/8) Epoch 12, batch 3900, loss[loss=0.166, simple_loss=0.2443, pruned_loss=0.04384, over 7433.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2636, pruned_loss=0.04404, over 1429900.86 frames.], batch size: 20, lr: 6.28e-04
+2022-05-14 13:25:02,795 INFO [train.py:812] (0/8) Epoch 12, batch 3950, loss[loss=0.1993, simple_loss=0.2856, pruned_loss=0.0565, over 7231.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2632, pruned_loss=0.04434, over 1431483.17 frames.], batch size: 20, lr: 6.28e-04
+2022-05-14 13:26:01,740 INFO [train.py:812] (0/8) Epoch 12, batch 4000, loss[loss=0.1639, simple_loss=0.2544, pruned_loss=0.03668, over 7408.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2635, pruned_loss=0.04482, over 1426180.85 frames.], batch size: 21, lr: 6.28e-04
+2022-05-14 13:27:01,231 INFO [train.py:812] (0/8) Epoch 12, batch 4050, loss[loss=0.1814, simple_loss=0.2729, pruned_loss=0.045, over 7427.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2638, pruned_loss=0.04498, over 1424299.30 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:28:00,391 INFO [train.py:812] (0/8) Epoch 12, batch 4100, loss[loss=0.1751, simple_loss=0.2635, pruned_loss=0.04335, over 7326.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2633, pruned_loss=0.04484, over 1420676.25 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:28:59,921 INFO [train.py:812] (0/8) Epoch 12, batch 4150, loss[loss=0.1549, simple_loss=0.2475, pruned_loss=0.03117, over 7238.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2641, pruned_loss=0.04515, over 1421365.55 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:29:59,289 INFO [train.py:812] (0/8) Epoch 12, batch 4200, loss[loss=0.1772, simple_loss=0.2682, pruned_loss=0.04309, over 7335.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2653, pruned_loss=0.04574, over 1421859.34 frames.], batch size: 22, lr: 6.27e-04
+2022-05-14 13:30:59,242 INFO [train.py:812] (0/8) Epoch 12, batch 4250, loss[loss=0.1621, simple_loss=0.2303, pruned_loss=0.04694, over 7401.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2647, pruned_loss=0.0459, over 1424705.42 frames.], batch size: 18, lr: 6.26e-04
+2022-05-14 13:31:58,487 INFO [train.py:812] (0/8) Epoch 12, batch 4300, loss[loss=0.1571, simple_loss=0.2454, pruned_loss=0.03437, over 7237.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2648, pruned_loss=0.04635, over 1418570.95 frames.], batch size: 20, lr: 6.26e-04
+2022-05-14 13:32:57,467 INFO [train.py:812] (0/8) Epoch 12, batch 4350, loss[loss=0.1992, simple_loss=0.2797, pruned_loss=0.05938, over 7214.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2633, pruned_loss=0.04578, over 1420362.85 frames.], batch size: 22, lr: 6.26e-04
+2022-05-14 13:33:56,596 INFO [train.py:812] (0/8) Epoch 12, batch 4400, loss[loss=0.1991, simple_loss=0.289, pruned_loss=0.05458, over 7319.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2631, pruned_loss=0.04561, over 1418719.45 frames.], batch size: 21, lr: 6.25e-04
+2022-05-14 13:34:56,715 INFO [train.py:812] (0/8) Epoch 12, batch 4450, loss[loss=0.1817, simple_loss=0.2678, pruned_loss=0.04779, over 6561.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2624, pruned_loss=0.04554, over 1407549.13 frames.], batch size: 38, lr: 6.25e-04
+2022-05-14 13:35:55,818 INFO [train.py:812] (0/8) Epoch 12, batch 4500, loss[loss=0.1658, simple_loss=0.2548, pruned_loss=0.03838, over 6279.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2622, pruned_loss=0.04605, over 1390102.57 frames.], batch size: 38, lr: 6.25e-04
+2022-05-14 13:36:54,590 INFO [train.py:812] (0/8) Epoch 12, batch 4550, loss[loss=0.2216, simple_loss=0.3054, pruned_loss=0.06883, over 5242.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2652, pruned_loss=0.04828, over 1349867.08 frames.], batch size: 52, lr: 6.25e-04
+2022-05-14 13:37:39,693 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-12.pt
+2022-05-14 13:38:08,557 INFO [train.py:812] (0/8) Epoch 13, batch 0, loss[loss=0.1983, simple_loss=0.2875, pruned_loss=0.05459, over 7144.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2875, pruned_loss=0.05459, over 7144.00 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:39:08,087 INFO [train.py:812] (0/8) Epoch 13, batch 50, loss[loss=0.1822, simple_loss=0.2607, pruned_loss=0.05181, over 7235.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2631, pruned_loss=0.0437, over 318101.29 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:40:06,195 INFO [train.py:812] (0/8) Epoch 13, batch 100, loss[loss=0.1906, simple_loss=0.2739, pruned_loss=0.05365, over 7205.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2625, pruned_loss=0.04318, over 564417.40 frames.], batch size: 23, lr: 6.03e-04
+2022-05-14 13:41:05,085 INFO [train.py:812] (0/8) Epoch 13, batch 150, loss[loss=0.1706, simple_loss=0.2621, pruned_loss=0.03952, over 7143.00 frames.], tot_loss[loss=0.1757, simple_loss=0.264, pruned_loss=0.04365, over 753385.41 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:42:04,233 INFO [train.py:812] (0/8) Epoch 13, batch 200, loss[loss=0.1548, simple_loss=0.2467, pruned_loss=0.03148, over 7145.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2629, pruned_loss=0.04332, over 900422.75 frames.], batch size: 20, lr: 6.02e-04
+2022-05-14 13:43:03,741 INFO [train.py:812] (0/8) Epoch 13, batch 250, loss[loss=0.1385, simple_loss=0.2165, pruned_loss=0.03026, over 6771.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2622, pruned_loss=0.04319, over 1013403.34 frames.], batch size: 15, lr: 6.02e-04
+2022-05-14 13:44:02,593 INFO [train.py:812] (0/8) Epoch 13, batch 300, loss[loss=0.1798, simple_loss=0.2673, pruned_loss=0.04617, over 7150.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2625, pruned_loss=0.04308, over 1102772.02 frames.], batch size: 20, lr: 6.02e-04
+2022-05-14 13:45:01,885 INFO [train.py:812] (0/8) Epoch 13, batch 350, loss[loss=0.1891, simple_loss=0.2729, pruned_loss=0.05262, over 7079.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2635, pruned_loss=0.04342, over 1175023.08 frames.], batch size: 28, lr: 6.01e-04
+2022-05-14 13:46:00,665 INFO [train.py:812] (0/8) Epoch 13, batch 400, loss[loss=0.1706, simple_loss=0.2481, pruned_loss=0.04658, over 7353.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2633, pruned_loss=0.04377, over 1232317.36 frames.], batch size: 19, lr: 6.01e-04
+2022-05-14 13:46:57,911 INFO [train.py:812] (0/8) Epoch 13, batch 450, loss[loss=0.178, simple_loss=0.2637, pruned_loss=0.04609, over 7300.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2632, pruned_loss=0.04395, over 1276482.84 frames.], batch size: 21, lr: 6.01e-04
+2022-05-14 13:47:55,569 INFO [train.py:812] (0/8) Epoch 13, batch 500, loss[loss=0.176, simple_loss=0.2694, pruned_loss=0.04126, over 6616.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2614, pruned_loss=0.04342, over 1310378.24 frames.], batch size: 38, lr: 6.01e-04
+2022-05-14 13:48:55,225 INFO [train.py:812] (0/8) Epoch 13, batch 550, loss[loss=0.1891, simple_loss=0.2808, pruned_loss=0.04868, over 7372.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2618, pruned_loss=0.04356, over 1332844.19 frames.], batch size: 23, lr: 6.00e-04
+2022-05-14 13:49:53,965 INFO [train.py:812] (0/8) Epoch 13, batch 600, loss[loss=0.1367, simple_loss=0.2148, pruned_loss=0.0293, over 6769.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2616, pruned_loss=0.04362, over 1346536.57 frames.], batch size: 15, lr: 6.00e-04
+2022-05-14 13:50:53,075 INFO [train.py:812] (0/8) Epoch 13, batch 650, loss[loss=0.179, simple_loss=0.2628, pruned_loss=0.0476, over 7279.00 frames.], tot_loss[loss=0.1744, simple_loss=0.262, pruned_loss=0.04343, over 1365807.10 frames.], batch size: 18, lr: 6.00e-04
+2022-05-14 13:51:52,379 INFO [train.py:812] (0/8) Epoch 13, batch 700, loss[loss=0.1823, simple_loss=0.2525, pruned_loss=0.05605, over 6776.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2628, pruned_loss=0.04365, over 1382661.43 frames.], batch size: 15, lr: 6.00e-04
+2022-05-14 13:52:51,786 INFO [train.py:812] (0/8) Epoch 13, batch 750, loss[loss=0.1841, simple_loss=0.2767, pruned_loss=0.04569, over 7199.00 frames.], tot_loss[loss=0.1748, simple_loss=0.263, pruned_loss=0.04335, over 1394830.84 frames.], batch size: 23, lr: 5.99e-04
+2022-05-14 13:53:50,474 INFO [train.py:812] (0/8) Epoch 13, batch 800, loss[loss=0.1687, simple_loss=0.2572, pruned_loss=0.04008, over 7207.00 frames.], tot_loss[loss=0.1736, simple_loss=0.262, pruned_loss=0.04258, over 1404180.38 frames.], batch size: 22, lr: 5.99e-04
+2022-05-14 13:54:49,210 INFO [train.py:812] (0/8) Epoch 13, batch 850, loss[loss=0.1665, simple_loss=0.2519, pruned_loss=0.04056, over 7128.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2631, pruned_loss=0.04327, over 1410243.05 frames.], batch size: 17, lr: 5.99e-04
+2022-05-14 13:55:48,206 INFO [train.py:812] (0/8) Epoch 13, batch 900, loss[loss=0.1779, simple_loss=0.2632, pruned_loss=0.0463, over 7325.00 frames.], tot_loss[loss=0.174, simple_loss=0.2621, pruned_loss=0.04292, over 1413236.03 frames.], batch size: 20, lr: 5.99e-04
+2022-05-14 13:56:39,875 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-56000.pt
+2022-05-14 13:56:52,997 INFO [train.py:812] (0/8) Epoch 13, batch 950, loss[loss=0.1813, simple_loss=0.2783, pruned_loss=0.0421, over 7184.00 frames.], tot_loss[loss=0.1741, simple_loss=0.262, pruned_loss=0.04309, over 1413912.97 frames.], batch size: 26, lr: 5.98e-04
+2022-05-14 13:57:52,234 INFO [train.py:812] (0/8) Epoch 13, batch 1000, loss[loss=0.185, simple_loss=0.2633, pruned_loss=0.05335, over 6267.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2621, pruned_loss=0.04303, over 1414412.83 frames.], batch size: 38, lr: 5.98e-04
+2022-05-14 13:58:51,942 INFO [train.py:812] (0/8) Epoch 13, batch 1050, loss[loss=0.1723, simple_loss=0.2566, pruned_loss=0.04403, over 7265.00 frames.], tot_loss[loss=0.1743, simple_loss=0.262, pruned_loss=0.04333, over 1415203.49 frames.], batch size: 19, lr: 5.98e-04
+2022-05-14 13:59:49,630 INFO [train.py:812] (0/8) Epoch 13, batch 1100, loss[loss=0.1824, simple_loss=0.2701, pruned_loss=0.04729, over 7378.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2625, pruned_loss=0.04351, over 1421567.84 frames.], batch size: 23, lr: 5.97e-04
+2022-05-14 14:00:49,260 INFO [train.py:812] (0/8) Epoch 13, batch 1150, loss[loss=0.1569, simple_loss=0.2454, pruned_loss=0.03416, over 7323.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2625, pruned_loss=0.04364, over 1424045.73 frames.], batch size: 20, lr: 5.97e-04
+2022-05-14 14:01:48,646 INFO [train.py:812] (0/8) Epoch 13, batch 1200, loss[loss=0.1943, simple_loss=0.2773, pruned_loss=0.05562, over 5171.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2624, pruned_loss=0.04405, over 1420538.63 frames.], batch size: 52, lr: 5.97e-04
+2022-05-14 14:02:48,262 INFO [train.py:812] (0/8) Epoch 13, batch 1250, loss[loss=0.1601, simple_loss=0.2413, pruned_loss=0.0394, over 7156.00 frames.], tot_loss[loss=0.175, simple_loss=0.2619, pruned_loss=0.04402, over 1417644.17 frames.], batch size: 19, lr: 5.97e-04
+2022-05-14 14:03:47,382 INFO [train.py:812] (0/8) Epoch 13, batch 1300, loss[loss=0.1677, simple_loss=0.2499, pruned_loss=0.04271, over 7073.00 frames.], tot_loss[loss=0.1741, simple_loss=0.261, pruned_loss=0.04362, over 1418388.43 frames.], batch size: 18, lr: 5.96e-04
+2022-05-14 14:04:46,580 INFO [train.py:812] (0/8) Epoch 13, batch 1350, loss[loss=0.2038, simple_loss=0.2779, pruned_loss=0.06484, over 4879.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2624, pruned_loss=0.04432, over 1416410.07 frames.], batch size: 52, lr: 5.96e-04
+2022-05-14 14:05:45,494 INFO [train.py:812] (0/8) Epoch 13, batch 1400, loss[loss=0.172, simple_loss=0.2564, pruned_loss=0.04384, over 7324.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2642, pruned_loss=0.04516, over 1415293.92 frames.], batch size: 25, lr: 5.96e-04
+2022-05-14 14:06:43,981 INFO [train.py:812] (0/8) Epoch 13, batch 1450, loss[loss=0.1667, simple_loss=0.2551, pruned_loss=0.03919, over 7323.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2642, pruned_loss=0.045, over 1413693.32 frames.], batch size: 21, lr: 5.96e-04
+2022-05-14 14:07:42,547 INFO [train.py:812] (0/8) Epoch 13, batch 1500, loss[loss=0.1983, simple_loss=0.2841, pruned_loss=0.05624, over 7200.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2639, pruned_loss=0.04448, over 1417157.25 frames.], batch size: 23, lr: 5.95e-04
+2022-05-14 14:08:42,621 INFO [train.py:812] (0/8) Epoch 13, batch 1550, loss[loss=0.22, simple_loss=0.3168, pruned_loss=0.06161, over 7051.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2636, pruned_loss=0.04432, over 1419353.50 frames.], batch size: 28, lr: 5.95e-04
+2022-05-14 14:09:41,284 INFO [train.py:812] (0/8) Epoch 13, batch 1600, loss[loss=0.1934, simple_loss=0.2832, pruned_loss=0.05177, over 7266.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2632, pruned_loss=0.04408, over 1418840.61 frames.], batch size: 25, lr: 5.95e-04
+2022-05-14 14:10:39,362 INFO [train.py:812] (0/8) Epoch 13, batch 1650, loss[loss=0.1965, simple_loss=0.281, pruned_loss=0.05598, over 7296.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2634, pruned_loss=0.04398, over 1422396.23 frames.], batch size: 24, lr: 5.95e-04
+2022-05-14 14:11:36,466 INFO [train.py:812] (0/8) Epoch 13, batch 1700, loss[loss=0.146, simple_loss=0.2268, pruned_loss=0.03256, over 7138.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2628, pruned_loss=0.04367, over 1418861.20 frames.], batch size: 17, lr: 5.94e-04
+2022-05-14 14:12:34,775 INFO [train.py:812] (0/8) Epoch 13, batch 1750, loss[loss=0.201, simple_loss=0.2855, pruned_loss=0.05821, over 7163.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2621, pruned_loss=0.04353, over 1422358.33 frames.], batch size: 26, lr: 5.94e-04
+2022-05-14 14:13:34,193 INFO [train.py:812] (0/8) Epoch 13, batch 1800, loss[loss=0.1583, simple_loss=0.236, pruned_loss=0.04029, over 7001.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2616, pruned_loss=0.04359, over 1427430.37 frames.], batch size: 16, lr: 5.94e-04
+2022-05-14 14:14:33,811 INFO [train.py:812] (0/8) Epoch 13, batch 1850, loss[loss=0.1849, simple_loss=0.2779, pruned_loss=0.04595, over 7342.00 frames.], tot_loss[loss=0.1733, simple_loss=0.261, pruned_loss=0.04283, over 1428044.54 frames.], batch size: 22, lr: 5.94e-04
+2022-05-14 14:15:33,207 INFO [train.py:812] (0/8) Epoch 13, batch 1900, loss[loss=0.1579, simple_loss=0.2496, pruned_loss=0.03308, over 7231.00 frames.], tot_loss[loss=0.174, simple_loss=0.2617, pruned_loss=0.04315, over 1428543.01 frames.], batch size: 20, lr: 5.93e-04
+2022-05-14 14:16:32,243 INFO [train.py:812] (0/8) Epoch 13, batch 1950, loss[loss=0.1549, simple_loss=0.2329, pruned_loss=0.03843, over 7267.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2622, pruned_loss=0.0433, over 1428649.50 frames.], batch size: 17, lr: 5.93e-04
+2022-05-14 14:17:31,591 INFO [train.py:812] (0/8) Epoch 13, batch 2000, loss[loss=0.1758, simple_loss=0.2469, pruned_loss=0.05239, over 6999.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2621, pruned_loss=0.04368, over 1427667.42 frames.], batch size: 16, lr: 5.93e-04
+2022-05-14 14:18:40,070 INFO [train.py:812] (0/8) Epoch 13, batch 2050, loss[loss=0.166, simple_loss=0.2567, pruned_loss=0.03762, over 7156.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2615, pruned_loss=0.04334, over 1420350.49 frames.], batch size: 19, lr: 5.93e-04
+2022-05-14 14:19:39,660 INFO [train.py:812] (0/8) Epoch 13, batch 2100, loss[loss=0.1731, simple_loss=0.264, pruned_loss=0.04113, over 7155.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2618, pruned_loss=0.0438, over 1421492.44 frames.], batch size: 19, lr: 5.92e-04
+2022-05-14 14:20:39,431 INFO [train.py:812] (0/8) Epoch 13, batch 2150, loss[loss=0.1673, simple_loss=0.2426, pruned_loss=0.04602, over 7261.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2629, pruned_loss=0.04389, over 1422181.43 frames.], batch size: 18, lr: 5.92e-04
+2022-05-14 14:21:36,891 INFO [train.py:812] (0/8) Epoch 13, batch 2200, loss[loss=0.1707, simple_loss=0.2548, pruned_loss=0.0433, over 7320.00 frames.], tot_loss[loss=0.175, simple_loss=0.2625, pruned_loss=0.04374, over 1422659.14 frames.], batch size: 20, lr: 5.92e-04
+2022-05-14 14:22:35,526 INFO [train.py:812] (0/8) Epoch 13, batch 2250, loss[loss=0.1939, simple_loss=0.2884, pruned_loss=0.04969, over 6990.00 frames.], tot_loss[loss=0.1747, simple_loss=0.262, pruned_loss=0.04368, over 1420914.97 frames.], batch size: 28, lr: 5.91e-04
+2022-05-14 14:23:34,333 INFO [train.py:812] (0/8) Epoch 13, batch 2300, loss[loss=0.1773, simple_loss=0.2756, pruned_loss=0.03946, over 7114.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2631, pruned_loss=0.04414, over 1424685.44 frames.], batch size: 21, lr: 5.91e-04
+2022-05-14 14:24:34,135 INFO [train.py:812] (0/8) Epoch 13, batch 2350, loss[loss=0.1784, simple_loss=0.2667, pruned_loss=0.04503, over 7157.00 frames.], tot_loss[loss=0.175, simple_loss=0.2625, pruned_loss=0.04375, over 1425605.12 frames.], batch size: 19, lr: 5.91e-04
+2022-05-14 14:25:33,547 INFO [train.py:812] (0/8) Epoch 13, batch 2400, loss[loss=0.1712, simple_loss=0.2548, pruned_loss=0.04381, over 7156.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2622, pruned_loss=0.04338, over 1426036.72 frames.], batch size: 17, lr: 5.91e-04
+2022-05-14 14:26:31,977 INFO [train.py:812] (0/8) Epoch 13, batch 2450, loss[loss=0.1698, simple_loss=0.2624, pruned_loss=0.03862, over 7221.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2623, pruned_loss=0.04352, over 1425742.49 frames.], batch size: 21, lr: 5.90e-04
+2022-05-14 14:27:30,755 INFO [train.py:812] (0/8) Epoch 13, batch 2500, loss[loss=0.1597, simple_loss=0.2359, pruned_loss=0.04176, over 7280.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2635, pruned_loss=0.04396, over 1427034.88 frames.], batch size: 18, lr: 5.90e-04
+2022-05-14 14:28:30,426 INFO [train.py:812] (0/8) Epoch 13, batch 2550, loss[loss=0.1798, simple_loss=0.2657, pruned_loss=0.04699, over 7228.00 frames.], tot_loss[loss=0.177, simple_loss=0.2644, pruned_loss=0.04481, over 1429004.49 frames.], batch size: 16, lr: 5.90e-04
+2022-05-14 14:29:29,692 INFO [train.py:812] (0/8) Epoch 13, batch 2600, loss[loss=0.1619, simple_loss=0.252, pruned_loss=0.03591, over 6776.00 frames.], tot_loss[loss=0.1759, simple_loss=0.263, pruned_loss=0.04439, over 1424752.56 frames.], batch size: 15, lr: 5.90e-04
+2022-05-14 14:30:29,032 INFO [train.py:812] (0/8) Epoch 13, batch 2650, loss[loss=0.1271, simple_loss=0.2136, pruned_loss=0.02035, over 7018.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2625, pruned_loss=0.04431, over 1422866.63 frames.], batch size: 16, lr: 5.89e-04
+2022-05-14 14:31:27,776 INFO [train.py:812] (0/8) Epoch 13, batch 2700, loss[loss=0.148, simple_loss=0.2343, pruned_loss=0.03083, over 7011.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2625, pruned_loss=0.04439, over 1423569.33 frames.], batch size: 16, lr: 5.89e-04
+2022-05-14 14:32:27,136 INFO [train.py:812] (0/8) Epoch 13, batch 2750, loss[loss=0.1997, simple_loss=0.2791, pruned_loss=0.06018, over 7116.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2623, pruned_loss=0.04413, over 1420875.79 frames.], batch size: 21, lr: 5.89e-04
+2022-05-14 14:33:24,876 INFO [train.py:812] (0/8) Epoch 13, batch 2800, loss[loss=0.1525, simple_loss=0.2348, pruned_loss=0.03505, over 7126.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2639, pruned_loss=0.04451, over 1421131.80 frames.], batch size: 17, lr: 5.89e-04
+2022-05-14 14:34:24,904 INFO [train.py:812] (0/8) Epoch 13, batch 2850, loss[loss=0.1747, simple_loss=0.2668, pruned_loss=0.04127, over 7380.00 frames.], tot_loss[loss=0.1764, simple_loss=0.264, pruned_loss=0.0444, over 1426659.46 frames.], batch size: 23, lr: 5.88e-04
+2022-05-14 14:35:22,588 INFO [train.py:812] (0/8) Epoch 13, batch 2900, loss[loss=0.1523, simple_loss=0.2365, pruned_loss=0.03404, over 7351.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2642, pruned_loss=0.04447, over 1424032.45 frames.], batch size: 19, lr: 5.88e-04
+2022-05-14 14:36:21,964 INFO [train.py:812] (0/8) Epoch 13, batch 2950, loss[loss=0.1684, simple_loss=0.262, pruned_loss=0.0374, over 7113.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2633, pruned_loss=0.04405, over 1425568.83 frames.], batch size: 21, lr: 5.88e-04
+2022-05-14 14:37:20,736 INFO [train.py:812] (0/8) Epoch 13, batch 3000, loss[loss=0.1734, simple_loss=0.2485, pruned_loss=0.0491, over 7285.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2636, pruned_loss=0.04434, over 1426465.80 frames.], batch size: 17, lr: 5.88e-04
+2022-05-14 14:37:20,738 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 14:37:28,227 INFO [train.py:841] (0/8) Epoch 13, validation: loss=0.1549, simple_loss=0.2559, pruned_loss=0.02694, over 698248.00 frames.
+2022-05-14 14:38:28,321 INFO [train.py:812] (0/8) Epoch 13, batch 3050, loss[loss=0.1489, simple_loss=0.235, pruned_loss=0.03144, over 7134.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2622, pruned_loss=0.04371, over 1427511.98 frames.], batch size: 17, lr: 5.87e-04
+2022-05-14 14:39:27,849 INFO [train.py:812] (0/8) Epoch 13, batch 3100, loss[loss=0.1828, simple_loss=0.2759, pruned_loss=0.04488, over 7119.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2616, pruned_loss=0.04327, over 1427251.71 frames.], batch size: 21, lr: 5.87e-04
+2022-05-14 14:40:36,451 INFO [train.py:812] (0/8) Epoch 13, batch 3150, loss[loss=0.2018, simple_loss=0.2793, pruned_loss=0.06211, over 7307.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2628, pruned_loss=0.04416, over 1424285.18 frames.], batch size: 25, lr: 5.87e-04
+2022-05-14 14:41:35,465 INFO [train.py:812] (0/8) Epoch 13, batch 3200, loss[loss=0.2382, simple_loss=0.3057, pruned_loss=0.08531, over 5194.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2634, pruned_loss=0.04408, over 1425465.54 frames.], batch size: 52, lr: 5.87e-04
+2022-05-14 14:42:44,504 INFO [train.py:812] (0/8) Epoch 13, batch 3250, loss[loss=0.1434, simple_loss=0.2307, pruned_loss=0.02807, over 7278.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2623, pruned_loss=0.04325, over 1427947.33 frames.], batch size: 17, lr: 5.86e-04
+2022-05-14 14:43:53,094 INFO [train.py:812] (0/8) Epoch 13, batch 3300, loss[loss=0.1553, simple_loss=0.2438, pruned_loss=0.03337, over 7321.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2615, pruned_loss=0.04282, over 1429027.57 frames.], batch size: 20, lr: 5.86e-04
+2022-05-14 14:44:51,658 INFO [train.py:812] (0/8) Epoch 13, batch 3350, loss[loss=0.1627, simple_loss=0.2482, pruned_loss=0.03858, over 7002.00 frames.], tot_loss[loss=0.1743, simple_loss=0.262, pruned_loss=0.04328, over 1421042.40 frames.], batch size: 16, lr: 5.86e-04
+2022-05-14 14:46:18,918 INFO [train.py:812] (0/8) Epoch 13, batch 3400, loss[loss=0.1661, simple_loss=0.2635, pruned_loss=0.03436, over 7387.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2626, pruned_loss=0.04359, over 1425738.32 frames.], batch size: 23, lr: 5.86e-04
+2022-05-14 14:47:27,728 INFO [train.py:812] (0/8) Epoch 13, batch 3450, loss[loss=0.1499, simple_loss=0.2383, pruned_loss=0.03076, over 7393.00 frames.], tot_loss[loss=0.1754, simple_loss=0.263, pruned_loss=0.04389, over 1415223.96 frames.], batch size: 18, lr: 5.85e-04
+2022-05-14 14:48:26,514 INFO [train.py:812] (0/8) Epoch 13, batch 3500, loss[loss=0.2017, simple_loss=0.2819, pruned_loss=0.06076, over 6710.00 frames.], tot_loss[loss=0.1754, simple_loss=0.263, pruned_loss=0.04388, over 1416751.42 frames.], batch size: 31, lr: 5.85e-04
+2022-05-14 14:49:26,042 INFO [train.py:812] (0/8) Epoch 13, batch 3550, loss[loss=0.1476, simple_loss=0.2293, pruned_loss=0.03297, over 7001.00 frames.], tot_loss[loss=0.1753, simple_loss=0.263, pruned_loss=0.04386, over 1422131.63 frames.], batch size: 16, lr: 5.85e-04
+2022-05-14 14:50:24,015 INFO [train.py:812] (0/8) Epoch 13, batch 3600, loss[loss=0.1658, simple_loss=0.2425, pruned_loss=0.04455, over 7269.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2628, pruned_loss=0.0439, over 1421937.73 frames.], batch size: 18, lr: 5.85e-04
+2022-05-14 14:51:22,123 INFO [train.py:812] (0/8) Epoch 13, batch 3650, loss[loss=0.1725, simple_loss=0.2663, pruned_loss=0.03934, over 7422.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2623, pruned_loss=0.04318, over 1424834.92 frames.], batch size: 21, lr: 5.84e-04
+2022-05-14 14:52:20,923 INFO [train.py:812] (0/8) Epoch 13, batch 3700, loss[loss=0.1647, simple_loss=0.256, pruned_loss=0.03669, over 7266.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2612, pruned_loss=0.04292, over 1425387.88 frames.], batch size: 19, lr: 5.84e-04
+2022-05-14 14:53:20,281 INFO [train.py:812] (0/8) Epoch 13, batch 3750, loss[loss=0.1824, simple_loss=0.2819, pruned_loss=0.04144, over 7411.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2614, pruned_loss=0.04291, over 1425133.29 frames.], batch size: 21, lr: 5.84e-04
+2022-05-14 14:54:19,256 INFO [train.py:812] (0/8) Epoch 13, batch 3800, loss[loss=0.1952, simple_loss=0.2863, pruned_loss=0.05201, over 7106.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2618, pruned_loss=0.04296, over 1429674.22 frames.], batch size: 28, lr: 5.84e-04
+2022-05-14 14:55:18,386 INFO [train.py:812] (0/8) Epoch 13, batch 3850, loss[loss=0.1927, simple_loss=0.2797, pruned_loss=0.05282, over 7189.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2631, pruned_loss=0.04333, over 1426785.89 frames.], batch size: 22, lr: 5.83e-04
+2022-05-14 14:56:16,997 INFO [train.py:812] (0/8) Epoch 13, batch 3900, loss[loss=0.1866, simple_loss=0.2782, pruned_loss=0.04755, over 7303.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2626, pruned_loss=0.04292, over 1425817.71 frames.], batch size: 24, lr: 5.83e-04
+2022-05-14 14:57:16,819 INFO [train.py:812] (0/8) Epoch 13, batch 3950, loss[loss=0.181, simple_loss=0.2649, pruned_loss=0.04853, over 7204.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2626, pruned_loss=0.04332, over 1424134.00 frames.], batch size: 23, lr: 5.83e-04
+2022-05-14 14:58:15,074 INFO [train.py:812] (0/8) Epoch 13, batch 4000, loss[loss=0.1802, simple_loss=0.2553, pruned_loss=0.0525, over 7147.00 frames.], tot_loss[loss=0.174, simple_loss=0.2618, pruned_loss=0.04309, over 1424204.38 frames.], batch size: 17, lr: 5.83e-04
+2022-05-14 14:59:14,565 INFO [train.py:812] (0/8) Epoch 13, batch 4050, loss[loss=0.1742, simple_loss=0.2689, pruned_loss=0.03975, over 7233.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2622, pruned_loss=0.04337, over 1425858.33 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:00:14,083 INFO [train.py:812] (0/8) Epoch 13, batch 4100, loss[loss=0.1847, simple_loss=0.2879, pruned_loss=0.04079, over 7136.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2615, pruned_loss=0.04303, over 1425758.25 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:01:13,266 INFO [train.py:812] (0/8) Epoch 13, batch 4150, loss[loss=0.1419, simple_loss=0.2397, pruned_loss=0.0221, over 7423.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2633, pruned_loss=0.04365, over 1421036.33 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:02:11,351 INFO [train.py:812] (0/8) Epoch 13, batch 4200, loss[loss=0.178, simple_loss=0.2678, pruned_loss=0.04411, over 7144.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2627, pruned_loss=0.04355, over 1422365.14 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:03:10,129 INFO [train.py:812] (0/8) Epoch 13, batch 4250, loss[loss=0.1709, simple_loss=0.261, pruned_loss=0.04034, over 7171.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2621, pruned_loss=0.04343, over 1420051.71 frames.], batch size: 26, lr: 5.81e-04
+2022-05-14 15:04:08,189 INFO [train.py:812] (0/8) Epoch 13, batch 4300, loss[loss=0.1855, simple_loss=0.2652, pruned_loss=0.0529, over 7429.00 frames.], tot_loss[loss=0.176, simple_loss=0.2635, pruned_loss=0.04425, over 1416417.92 frames.], batch size: 20, lr: 5.81e-04
+2022-05-14 15:05:06,770 INFO [train.py:812] (0/8) Epoch 13, batch 4350, loss[loss=0.1431, simple_loss=0.2241, pruned_loss=0.03108, over 7006.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2628, pruned_loss=0.04405, over 1410900.62 frames.], batch size: 16, lr: 5.81e-04
+2022-05-14 15:06:06,042 INFO [train.py:812] (0/8) Epoch 13, batch 4400, loss[loss=0.2195, simple_loss=0.285, pruned_loss=0.07705, over 5354.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2615, pruned_loss=0.04351, over 1410022.32 frames.], batch size: 53, lr: 5.81e-04
+2022-05-14 15:07:04,934 INFO [train.py:812] (0/8) Epoch 13, batch 4450, loss[loss=0.214, simple_loss=0.2954, pruned_loss=0.06635, over 7302.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2603, pruned_loss=0.04314, over 1408859.77 frames.], batch size: 24, lr: 5.81e-04
+2022-05-14 15:08:03,269 INFO [train.py:812] (0/8) Epoch 13, batch 4500, loss[loss=0.1725, simple_loss=0.2651, pruned_loss=0.03997, over 7403.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2614, pruned_loss=0.04385, over 1389710.96 frames.], batch size: 21, lr: 5.80e-04
+2022-05-14 15:09:01,454 INFO [train.py:812] (0/8) Epoch 13, batch 4550, loss[loss=0.2164, simple_loss=0.292, pruned_loss=0.07036, over 4796.00 frames.], tot_loss[loss=0.1772, simple_loss=0.264, pruned_loss=0.04518, over 1354973.79 frames.], batch size: 52, lr: 5.80e-04
+2022-05-14 15:09:46,647 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-13.pt
+2022-05-14 15:10:14,175 INFO [train.py:812] (0/8) Epoch 14, batch 0, loss[loss=0.179, simple_loss=0.2676, pruned_loss=0.04524, over 7393.00 frames.], tot_loss[loss=0.179, simple_loss=0.2676, pruned_loss=0.04524, over 7393.00 frames.], batch size: 23, lr: 5.61e-04
+2022-05-14 15:11:14,036 INFO [train.py:812] (0/8) Epoch 14, batch 50, loss[loss=0.1725, simple_loss=0.2741, pruned_loss=0.03542, over 7110.00 frames.], tot_loss[loss=0.173, simple_loss=0.2599, pruned_loss=0.04305, over 321833.13 frames.], batch size: 21, lr: 5.61e-04
+2022-05-14 15:12:13,749 INFO [train.py:812] (0/8) Epoch 14, batch 100, loss[loss=0.195, simple_loss=0.2819, pruned_loss=0.05409, over 7144.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2613, pruned_loss=0.0427, over 571819.45 frames.], batch size: 20, lr: 5.61e-04
+2022-05-14 15:13:13,202 INFO [train.py:812] (0/8) Epoch 14, batch 150, loss[loss=0.1626, simple_loss=0.244, pruned_loss=0.04062, over 7006.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2603, pruned_loss=0.0431, over 762204.09 frames.], batch size: 16, lr: 5.61e-04
+2022-05-14 15:14:11,676 INFO [train.py:812] (0/8) Epoch 14, batch 200, loss[loss=0.1829, simple_loss=0.2788, pruned_loss=0.04351, over 7203.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2613, pruned_loss=0.04303, over 909695.10 frames.], batch size: 22, lr: 5.60e-04
+2022-05-14 15:15:09,282 INFO [train.py:812] (0/8) Epoch 14, batch 250, loss[loss=0.1945, simple_loss=0.28, pruned_loss=0.05455, over 7198.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2605, pruned_loss=0.04211, over 1025694.42 frames.], batch size: 22, lr: 5.60e-04
+2022-05-14 15:16:07,663 INFO [train.py:812] (0/8) Epoch 14, batch 300, loss[loss=0.1707, simple_loss=0.2661, pruned_loss=0.03771, over 7408.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2613, pruned_loss=0.04221, over 1112486.84 frames.], batch size: 21, lr: 5.60e-04
+2022-05-14 15:17:06,886 INFO [train.py:812] (0/8) Epoch 14, batch 350, loss[loss=0.166, simple_loss=0.2612, pruned_loss=0.03544, over 7423.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2605, pruned_loss=0.04224, over 1181508.51 frames.], batch size: 20, lr: 5.60e-04
+2022-05-14 15:17:13,302 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-60000.pt
+2022-05-14 15:18:11,718 INFO [train.py:812] (0/8) Epoch 14, batch 400, loss[loss=0.18, simple_loss=0.2692, pruned_loss=0.04542, over 7065.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2604, pruned_loss=0.04241, over 1231744.14 frames.], batch size: 28, lr: 5.59e-04
+2022-05-14 15:19:10,164 INFO [train.py:812] (0/8) Epoch 14, batch 450, loss[loss=0.2108, simple_loss=0.2951, pruned_loss=0.06324, over 6157.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2607, pruned_loss=0.04242, over 1273063.58 frames.], batch size: 37, lr: 5.59e-04
+2022-05-14 15:20:09,610 INFO [train.py:812] (0/8) Epoch 14, batch 500, loss[loss=0.2164, simple_loss=0.3069, pruned_loss=0.06293, over 7006.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2604, pruned_loss=0.04222, over 1300639.86 frames.], batch size: 28, lr: 5.59e-04
+2022-05-14 15:21:08,775 INFO [train.py:812] (0/8) Epoch 14, batch 550, loss[loss=0.1644, simple_loss=0.2548, pruned_loss=0.03706, over 6297.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2597, pruned_loss=0.04169, over 1325499.68 frames.], batch size: 37, lr: 5.59e-04
+2022-05-14 15:22:08,320 INFO [train.py:812] (0/8) Epoch 14, batch 600, loss[loss=0.1882, simple_loss=0.28, pruned_loss=0.04821, over 7317.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2599, pruned_loss=0.04184, over 1347369.57 frames.], batch size: 21, lr: 5.59e-04
+2022-05-14 15:23:07,037 INFO [train.py:812] (0/8) Epoch 14, batch 650, loss[loss=0.1762, simple_loss=0.2707, pruned_loss=0.04082, over 7065.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2606, pruned_loss=0.04224, over 1360200.22 frames.], batch size: 18, lr: 5.58e-04
+2022-05-14 15:24:06,554 INFO [train.py:812] (0/8) Epoch 14, batch 700, loss[loss=0.1449, simple_loss=0.2356, pruned_loss=0.02711, over 7278.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2601, pruned_loss=0.04219, over 1375730.75 frames.], batch size: 18, lr: 5.58e-04
+2022-05-14 15:25:05,445 INFO [train.py:812] (0/8) Epoch 14, batch 750, loss[loss=0.1762, simple_loss=0.2695, pruned_loss=0.04148, over 7175.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2594, pruned_loss=0.0419, over 1382423.85 frames.], batch size: 23, lr: 5.58e-04
+2022-05-14 15:26:04,464 INFO [train.py:812] (0/8) Epoch 14, batch 800, loss[loss=0.1635, simple_loss=0.2567, pruned_loss=0.03516, over 7279.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2605, pruned_loss=0.04244, over 1391920.90 frames.], batch size: 25, lr: 5.58e-04
+2022-05-14 15:27:03,662 INFO [train.py:812] (0/8) Epoch 14, batch 850, loss[loss=0.1686, simple_loss=0.2708, pruned_loss=0.03316, over 7211.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2605, pruned_loss=0.04211, over 1401019.20 frames.], batch size: 21, lr: 5.57e-04
+2022-05-14 15:28:02,990 INFO [train.py:812] (0/8) Epoch 14, batch 900, loss[loss=0.1542, simple_loss=0.2455, pruned_loss=0.03143, over 7160.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2609, pruned_loss=0.04204, over 1403657.13 frames.], batch size: 18, lr: 5.57e-04
+2022-05-14 15:29:01,732 INFO [train.py:812] (0/8) Epoch 14, batch 950, loss[loss=0.1823, simple_loss=0.2669, pruned_loss=0.04882, over 7212.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2614, pruned_loss=0.04206, over 1404199.36 frames.], batch size: 21, lr: 5.57e-04
+2022-05-14 15:30:01,404 INFO [train.py:812] (0/8) Epoch 14, batch 1000, loss[loss=0.1813, simple_loss=0.2754, pruned_loss=0.04357, over 7208.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2612, pruned_loss=0.042, over 1410907.07 frames.], batch size: 22, lr: 5.57e-04
+2022-05-14 15:31:00,121 INFO [train.py:812] (0/8) Epoch 14, batch 1050, loss[loss=0.1771, simple_loss=0.2695, pruned_loss=0.04234, over 7406.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2604, pruned_loss=0.04175, over 1411127.91 frames.], batch size: 21, lr: 5.56e-04
+2022-05-14 15:31:57,362 INFO [train.py:812] (0/8) Epoch 14, batch 1100, loss[loss=0.1732, simple_loss=0.2675, pruned_loss=0.03949, over 6832.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2594, pruned_loss=0.04136, over 1410814.56 frames.], batch size: 31, lr: 5.56e-04
+2022-05-14 15:32:55,036 INFO [train.py:812] (0/8) Epoch 14, batch 1150, loss[loss=0.1673, simple_loss=0.2606, pruned_loss=0.03705, over 7328.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2608, pruned_loss=0.0418, over 1410291.18 frames.], batch size: 22, lr: 5.56e-04
+2022-05-14 15:33:54,459 INFO [train.py:812] (0/8) Epoch 14, batch 1200, loss[loss=0.2167, simple_loss=0.2908, pruned_loss=0.07128, over 5046.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2611, pruned_loss=0.04224, over 1409920.86 frames.], batch size: 52, lr: 5.56e-04
+2022-05-14 15:34:52,748 INFO [train.py:812] (0/8) Epoch 14, batch 1250, loss[loss=0.1511, simple_loss=0.2404, pruned_loss=0.03094, over 7432.00 frames.], tot_loss[loss=0.173, simple_loss=0.2615, pruned_loss=0.04219, over 1414408.76 frames.], batch size: 20, lr: 5.56e-04
+2022-05-14 15:35:51,136 INFO [train.py:812] (0/8) Epoch 14, batch 1300, loss[loss=0.1553, simple_loss=0.2484, pruned_loss=0.03104, over 7244.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2613, pruned_loss=0.0418, over 1418027.80 frames.], batch size: 19, lr: 5.55e-04
+2022-05-14 15:36:49,460 INFO [train.py:812] (0/8) Epoch 14, batch 1350, loss[loss=0.1551, simple_loss=0.2361, pruned_loss=0.03706, over 7279.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2606, pruned_loss=0.04156, over 1422412.19 frames.], batch size: 18, lr: 5.55e-04
+2022-05-14 15:37:48,226 INFO [train.py:812] (0/8) Epoch 14, batch 1400, loss[loss=0.1626, simple_loss=0.2495, pruned_loss=0.03783, over 7159.00 frames.], tot_loss[loss=0.1728, simple_loss=0.261, pruned_loss=0.04225, over 1418580.50 frames.], batch size: 18, lr: 5.55e-04
+2022-05-14 15:38:45,097 INFO [train.py:812] (0/8) Epoch 14, batch 1450, loss[loss=0.1426, simple_loss=0.2277, pruned_loss=0.02879, over 7284.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2609, pruned_loss=0.04211, over 1422140.30 frames.], batch size: 17, lr: 5.55e-04
+2022-05-14 15:39:43,873 INFO [train.py:812] (0/8) Epoch 14, batch 1500, loss[loss=0.149, simple_loss=0.2354, pruned_loss=0.03134, over 7276.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2598, pruned_loss=0.04155, over 1423267.99 frames.], batch size: 17, lr: 5.54e-04
+2022-05-14 15:40:42,055 INFO [train.py:812] (0/8) Epoch 14, batch 1550, loss[loss=0.1554, simple_loss=0.2479, pruned_loss=0.03152, over 6328.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2606, pruned_loss=0.04223, over 1418415.41 frames.], batch size: 37, lr: 5.54e-04
+2022-05-14 15:41:40,204 INFO [train.py:812] (0/8) Epoch 14, batch 1600, loss[loss=0.1692, simple_loss=0.2757, pruned_loss=0.03138, over 7400.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2612, pruned_loss=0.04212, over 1417217.72 frames.], batch size: 21, lr: 5.54e-04
+2022-05-14 15:42:38,997 INFO [train.py:812] (0/8) Epoch 14, batch 1650, loss[loss=0.1739, simple_loss=0.2631, pruned_loss=0.04237, over 7239.00 frames.], tot_loss[loss=0.173, simple_loss=0.2615, pruned_loss=0.04228, over 1418845.70 frames.], batch size: 20, lr: 5.54e-04
+2022-05-14 15:43:38,196 INFO [train.py:812] (0/8) Epoch 14, batch 1700, loss[loss=0.175, simple_loss=0.2741, pruned_loss=0.038, over 6344.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2611, pruned_loss=0.04197, over 1418300.26 frames.], batch size: 37, lr: 5.54e-04
+2022-05-14 15:44:37,143 INFO [train.py:812] (0/8) Epoch 14, batch 1750, loss[loss=0.1466, simple_loss=0.2258, pruned_loss=0.03374, over 7276.00 frames.], tot_loss[loss=0.172, simple_loss=0.2607, pruned_loss=0.04167, over 1420722.30 frames.], batch size: 17, lr: 5.53e-04
+2022-05-14 15:45:37,326 INFO [train.py:812] (0/8) Epoch 14, batch 1800, loss[loss=0.166, simple_loss=0.2521, pruned_loss=0.03995, over 7150.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2604, pruned_loss=0.04153, over 1424994.84 frames.], batch size: 20, lr: 5.53e-04
+2022-05-14 15:46:35,088 INFO [train.py:812] (0/8) Epoch 14, batch 1850, loss[loss=0.1777, simple_loss=0.2688, pruned_loss=0.04329, over 7256.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2611, pruned_loss=0.04184, over 1424767.65 frames.], batch size: 25, lr: 5.53e-04
+2022-05-14 15:47:33,722 INFO [train.py:812] (0/8) Epoch 14, batch 1900, loss[loss=0.2032, simple_loss=0.3037, pruned_loss=0.05138, over 6410.00 frames.], tot_loss[loss=0.173, simple_loss=0.2617, pruned_loss=0.04221, over 1419691.37 frames.], batch size: 38, lr: 5.53e-04
+2022-05-14 15:48:32,630 INFO [train.py:812] (0/8) Epoch 14, batch 1950, loss[loss=0.1425, simple_loss=0.243, pruned_loss=0.02101, over 7266.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2622, pruned_loss=0.04244, over 1421169.65 frames.], batch size: 19, lr: 5.52e-04
+2022-05-14 15:49:32,351 INFO [train.py:812] (0/8) Epoch 14, batch 2000, loss[loss=0.173, simple_loss=0.2671, pruned_loss=0.03943, over 7352.00 frames.], tot_loss[loss=0.1737, simple_loss=0.262, pruned_loss=0.04267, over 1422250.25 frames.], batch size: 22, lr: 5.52e-04
+2022-05-14 15:50:31,352 INFO [train.py:812] (0/8) Epoch 14, batch 2050, loss[loss=0.1611, simple_loss=0.2601, pruned_loss=0.03107, over 7367.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2616, pruned_loss=0.04269, over 1424398.82 frames.], batch size: 23, lr: 5.52e-04
+2022-05-14 15:51:31,087 INFO [train.py:812] (0/8) Epoch 14, batch 2100, loss[loss=0.1637, simple_loss=0.2586, pruned_loss=0.03442, over 7220.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2623, pruned_loss=0.04298, over 1424389.14 frames.], batch size: 20, lr: 5.52e-04
+2022-05-14 15:52:30,492 INFO [train.py:812] (0/8) Epoch 14, batch 2150, loss[loss=0.163, simple_loss=0.267, pruned_loss=0.02943, over 7134.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2613, pruned_loss=0.04247, over 1427192.77 frames.], batch size: 26, lr: 5.52e-04
+2022-05-14 15:53:29,899 INFO [train.py:812] (0/8) Epoch 14, batch 2200, loss[loss=0.1722, simple_loss=0.26, pruned_loss=0.04218, over 7441.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2616, pruned_loss=0.04245, over 1425628.10 frames.], batch size: 20, lr: 5.51e-04
+2022-05-14 15:54:28,347 INFO [train.py:812] (0/8) Epoch 14, batch 2250, loss[loss=0.1635, simple_loss=0.2547, pruned_loss=0.03612, over 7229.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2611, pruned_loss=0.04224, over 1427137.34 frames.], batch size: 20, lr: 5.51e-04
+2022-05-14 15:55:26,960 INFO [train.py:812] (0/8) Epoch 14, batch 2300, loss[loss=0.1896, simple_loss=0.2791, pruned_loss=0.05006, over 7054.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2603, pruned_loss=0.04171, over 1427428.21 frames.], batch size: 28, lr: 5.51e-04
+2022-05-14 15:56:25,008 INFO [train.py:812] (0/8) Epoch 14, batch 2350, loss[loss=0.247, simple_loss=0.3163, pruned_loss=0.08887, over 5426.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2607, pruned_loss=0.04177, over 1427282.15 frames.], batch size: 53, lr: 5.51e-04
+2022-05-14 15:57:24,242 INFO [train.py:812] (0/8) Epoch 14, batch 2400, loss[loss=0.1769, simple_loss=0.2508, pruned_loss=0.05149, over 7286.00 frames.], tot_loss[loss=0.1717, simple_loss=0.26, pruned_loss=0.04171, over 1428788.95 frames.], batch size: 17, lr: 5.50e-04
+2022-05-14 15:58:23,282 INFO [train.py:812] (0/8) Epoch 14, batch 2450, loss[loss=0.1809, simple_loss=0.2737, pruned_loss=0.04407, over 6822.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2612, pruned_loss=0.04213, over 1431180.07 frames.], batch size: 31, lr: 5.50e-04
+2022-05-14 15:59:21,601 INFO [train.py:812] (0/8) Epoch 14, batch 2500, loss[loss=0.1398, simple_loss=0.2272, pruned_loss=0.02617, over 7292.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2611, pruned_loss=0.04217, over 1426981.60 frames.], batch size: 17, lr: 5.50e-04
+2022-05-14 16:00:19,956 INFO [train.py:812] (0/8) Epoch 14, batch 2550, loss[loss=0.1883, simple_loss=0.2665, pruned_loss=0.05507, over 7290.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2619, pruned_loss=0.04271, over 1423366.03 frames.], batch size: 25, lr: 5.50e-04
+2022-05-14 16:01:19,222 INFO [train.py:812] (0/8) Epoch 14, batch 2600, loss[loss=0.1874, simple_loss=0.2786, pruned_loss=0.04805, over 7410.00 frames.], tot_loss[loss=0.173, simple_loss=0.2612, pruned_loss=0.04241, over 1420412.76 frames.], batch size: 21, lr: 5.50e-04
+2022-05-14 16:02:16,352 INFO [train.py:812] (0/8) Epoch 14, batch 2650, loss[loss=0.168, simple_loss=0.2582, pruned_loss=0.03888, over 7119.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2611, pruned_loss=0.04253, over 1418946.06 frames.], batch size: 21, lr: 5.49e-04
+2022-05-14 16:03:15,380 INFO [train.py:812] (0/8) Epoch 14, batch 2700, loss[loss=0.1465, simple_loss=0.225, pruned_loss=0.03402, over 6982.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2607, pruned_loss=0.04234, over 1422437.30 frames.], batch size: 16, lr: 5.49e-04
+2022-05-14 16:04:13,420 INFO [train.py:812] (0/8) Epoch 14, batch 2750, loss[loss=0.1525, simple_loss=0.2479, pruned_loss=0.02855, over 7308.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2605, pruned_loss=0.04211, over 1427196.16 frames.], batch size: 24, lr: 5.49e-04
+2022-05-14 16:05:11,586 INFO [train.py:812] (0/8) Epoch 14, batch 2800, loss[loss=0.162, simple_loss=0.2414, pruned_loss=0.04132, over 7139.00 frames.], tot_loss[loss=0.1719, simple_loss=0.26, pruned_loss=0.04186, over 1426088.11 frames.], batch size: 17, lr: 5.49e-04
+2022-05-14 16:06:10,651 INFO [train.py:812] (0/8) Epoch 14, batch 2850, loss[loss=0.1636, simple_loss=0.2659, pruned_loss=0.03068, over 7417.00 frames.], tot_loss[loss=0.171, simple_loss=0.2592, pruned_loss=0.04135, over 1426997.12 frames.], batch size: 21, lr: 5.48e-04
+2022-05-14 16:07:10,184 INFO [train.py:812] (0/8) Epoch 14, batch 2900, loss[loss=0.1831, simple_loss=0.2746, pruned_loss=0.04575, over 7106.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2602, pruned_loss=0.04161, over 1427851.98 frames.], batch size: 21, lr: 5.48e-04
+2022-05-14 16:08:08,880 INFO [train.py:812] (0/8) Epoch 14, batch 2950, loss[loss=0.1903, simple_loss=0.2831, pruned_loss=0.04876, over 7187.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2606, pruned_loss=0.0416, over 1429543.69 frames.], batch size: 23, lr: 5.48e-04
+2022-05-14 16:09:07,579 INFO [train.py:812] (0/8) Epoch 14, batch 3000, loss[loss=0.2011, simple_loss=0.2907, pruned_loss=0.05572, over 7287.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2596, pruned_loss=0.04126, over 1430550.34 frames.], batch size: 24, lr: 5.48e-04
+2022-05-14 16:09:07,581 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 16:09:15,054 INFO [train.py:841] (0/8) Epoch 14, validation: loss=0.1549, simple_loss=0.2556, pruned_loss=0.02713, over 698248.00 frames.
+2022-05-14 16:10:14,272 INFO [train.py:812] (0/8) Epoch 14, batch 3050, loss[loss=0.1497, simple_loss=0.2325, pruned_loss=0.03341, over 7278.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2603, pruned_loss=0.04171, over 1430206.84 frames.], batch size: 17, lr: 5.48e-04
+2022-05-14 16:11:13,757 INFO [train.py:812] (0/8) Epoch 14, batch 3100, loss[loss=0.2184, simple_loss=0.3095, pruned_loss=0.06363, over 7207.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2606, pruned_loss=0.04215, over 1431076.56 frames.], batch size: 23, lr: 5.47e-04
+2022-05-14 16:12:13,365 INFO [train.py:812] (0/8) Epoch 14, batch 3150, loss[loss=0.2135, simple_loss=0.2844, pruned_loss=0.07132, over 5017.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2597, pruned_loss=0.04185, over 1429709.50 frames.], batch size: 52, lr: 5.47e-04
+2022-05-14 16:13:13,718 INFO [train.py:812] (0/8) Epoch 14, batch 3200, loss[loss=0.1861, simple_loss=0.2725, pruned_loss=0.04983, over 7339.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2603, pruned_loss=0.04191, over 1430092.84 frames.], batch size: 22, lr: 5.47e-04
+2022-05-14 16:14:11,655 INFO [train.py:812] (0/8) Epoch 14, batch 3250, loss[loss=0.1695, simple_loss=0.2596, pruned_loss=0.03968, over 7138.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2606, pruned_loss=0.04231, over 1427265.70 frames.], batch size: 26, lr: 5.47e-04
+2022-05-14 16:15:10,521 INFO [train.py:812] (0/8) Epoch 14, batch 3300, loss[loss=0.1732, simple_loss=0.2534, pruned_loss=0.04653, over 7166.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2601, pruned_loss=0.04226, over 1423873.96 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:16:09,532 INFO [train.py:812] (0/8) Epoch 14, batch 3350, loss[loss=0.1448, simple_loss=0.2315, pruned_loss=0.02906, over 7432.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2594, pruned_loss=0.04194, over 1425549.55 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:17:08,394 INFO [train.py:812] (0/8) Epoch 14, batch 3400, loss[loss=0.1658, simple_loss=0.2647, pruned_loss=0.03347, over 7173.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2598, pruned_loss=0.04201, over 1426143.09 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:18:17,674 INFO [train.py:812] (0/8) Epoch 14, batch 3450, loss[loss=0.1701, simple_loss=0.2694, pruned_loss=0.03541, over 7109.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2608, pruned_loss=0.04229, over 1425655.16 frames.], batch size: 21, lr: 5.46e-04
+2022-05-14 16:19:16,717 INFO [train.py:812] (0/8) Epoch 14, batch 3500, loss[loss=0.1661, simple_loss=0.2541, pruned_loss=0.03903, over 7344.00 frames.], tot_loss[loss=0.172, simple_loss=0.2599, pruned_loss=0.04202, over 1426952.63 frames.], batch size: 22, lr: 5.46e-04
+2022-05-14 16:20:15,515 INFO [train.py:812] (0/8) Epoch 14, batch 3550, loss[loss=0.1675, simple_loss=0.2672, pruned_loss=0.03394, over 7320.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2598, pruned_loss=0.04157, over 1426355.29 frames.], batch size: 21, lr: 5.45e-04
+2022-05-14 16:21:14,187 INFO [train.py:812] (0/8) Epoch 14, batch 3600, loss[loss=0.1532, simple_loss=0.2431, pruned_loss=0.03159, over 7354.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2579, pruned_loss=0.04065, over 1429366.25 frames.], batch size: 19, lr: 5.45e-04
+2022-05-14 16:22:13,045 INFO [train.py:812] (0/8) Epoch 14, batch 3650, loss[loss=0.1594, simple_loss=0.2468, pruned_loss=0.036, over 7232.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2583, pruned_loss=0.04095, over 1428666.62 frames.], batch size: 20, lr: 5.45e-04
+2022-05-14 16:23:12,477 INFO [train.py:812] (0/8) Epoch 14, batch 3700, loss[loss=0.2173, simple_loss=0.2932, pruned_loss=0.07077, over 7304.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2594, pruned_loss=0.04165, over 1420603.72 frames.], batch size: 24, lr: 5.45e-04
+2022-05-14 16:24:11,503 INFO [train.py:812] (0/8) Epoch 14, batch 3750, loss[loss=0.166, simple_loss=0.2478, pruned_loss=0.04217, over 4837.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2602, pruned_loss=0.0422, over 1419025.75 frames.], batch size: 54, lr: 5.45e-04
+2022-05-14 16:25:11,109 INFO [train.py:812] (0/8) Epoch 14, batch 3800, loss[loss=0.1357, simple_loss=0.2225, pruned_loss=0.02445, over 6991.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2606, pruned_loss=0.04225, over 1418254.27 frames.], batch size: 16, lr: 5.44e-04
+2022-05-14 16:26:09,752 INFO [train.py:812] (0/8) Epoch 14, batch 3850, loss[loss=0.174, simple_loss=0.2595, pruned_loss=0.04421, over 7216.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2606, pruned_loss=0.04226, over 1419903.84 frames.], batch size: 22, lr: 5.44e-04
+2022-05-14 16:27:08,430 INFO [train.py:812] (0/8) Epoch 14, batch 3900, loss[loss=0.1841, simple_loss=0.2689, pruned_loss=0.0497, over 7315.00 frames.], tot_loss[loss=0.1719, simple_loss=0.26, pruned_loss=0.04192, over 1422624.01 frames.], batch size: 21, lr: 5.44e-04
+2022-05-14 16:28:07,618 INFO [train.py:812] (0/8) Epoch 14, batch 3950, loss[loss=0.2359, simple_loss=0.31, pruned_loss=0.08085, over 4775.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2593, pruned_loss=0.04171, over 1420450.63 frames.], batch size: 52, lr: 5.44e-04
+2022-05-14 16:29:06,376 INFO [train.py:812] (0/8) Epoch 14, batch 4000, loss[loss=0.2026, simple_loss=0.2869, pruned_loss=0.05912, over 7340.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2602, pruned_loss=0.04212, over 1422635.29 frames.], batch size: 22, lr: 5.43e-04
+2022-05-14 16:30:03,964 INFO [train.py:812] (0/8) Epoch 14, batch 4050, loss[loss=0.1526, simple_loss=0.2312, pruned_loss=0.03697, over 6760.00 frames.], tot_loss[loss=0.1711, simple_loss=0.259, pruned_loss=0.04161, over 1423686.32 frames.], batch size: 15, lr: 5.43e-04
+2022-05-14 16:31:03,492 INFO [train.py:812] (0/8) Epoch 14, batch 4100, loss[loss=0.1882, simple_loss=0.2793, pruned_loss=0.0485, over 6825.00 frames.], tot_loss[loss=0.1723, simple_loss=0.26, pruned_loss=0.04232, over 1420373.33 frames.], batch size: 31, lr: 5.43e-04
+2022-05-14 16:32:02,262 INFO [train.py:812] (0/8) Epoch 14, batch 4150, loss[loss=0.1655, simple_loss=0.2599, pruned_loss=0.03556, over 7218.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2592, pruned_loss=0.04213, over 1419650.83 frames.], batch size: 21, lr: 5.43e-04
+2022-05-14 16:33:01,709 INFO [train.py:812] (0/8) Epoch 14, batch 4200, loss[loss=0.1801, simple_loss=0.2532, pruned_loss=0.05349, over 7260.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2578, pruned_loss=0.04172, over 1422029.16 frames.], batch size: 17, lr: 5.43e-04
+2022-05-14 16:34:00,225 INFO [train.py:812] (0/8) Epoch 14, batch 4250, loss[loss=0.1939, simple_loss=0.2844, pruned_loss=0.05172, over 6546.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2581, pruned_loss=0.04181, over 1415615.72 frames.], batch size: 38, lr: 5.42e-04
+2022-05-14 16:34:59,092 INFO [train.py:812] (0/8) Epoch 14, batch 4300, loss[loss=0.1521, simple_loss=0.238, pruned_loss=0.0331, over 7220.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2587, pruned_loss=0.04217, over 1411877.20 frames.], batch size: 21, lr: 5.42e-04
+2022-05-14 16:35:56,837 INFO [train.py:812] (0/8) Epoch 14, batch 4350, loss[loss=0.1494, simple_loss=0.232, pruned_loss=0.03334, over 6803.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2581, pruned_loss=0.04149, over 1408451.20 frames.], batch size: 15, lr: 5.42e-04
+2022-05-14 16:36:03,249 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-64000.pt
+2022-05-14 16:37:01,591 INFO [train.py:812] (0/8) Epoch 14, batch 4400, loss[loss=0.1688, simple_loss=0.2631, pruned_loss=0.03727, over 7147.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2576, pruned_loss=0.04152, over 1401960.73 frames.], batch size: 20, lr: 5.42e-04
+2022-05-14 16:38:00,473 INFO [train.py:812] (0/8) Epoch 14, batch 4450, loss[loss=0.2043, simple_loss=0.2767, pruned_loss=0.06592, over 5150.00 frames.], tot_loss[loss=0.1711, simple_loss=0.259, pruned_loss=0.04161, over 1393230.48 frames.], batch size: 53, lr: 5.42e-04
+2022-05-14 16:38:59,753 INFO [train.py:812] (0/8) Epoch 14, batch 4500, loss[loss=0.1873, simple_loss=0.2694, pruned_loss=0.05257, over 5077.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2602, pruned_loss=0.0425, over 1379276.55 frames.], batch size: 52, lr: 5.41e-04
+2022-05-14 16:40:07,820 INFO [train.py:812] (0/8) Epoch 14, batch 4550, loss[loss=0.1706, simple_loss=0.2654, pruned_loss=0.03792, over 6763.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2601, pruned_loss=0.04255, over 1370260.68 frames.], batch size: 31, lr: 5.41e-04
+2022-05-14 16:40:53,069 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-14.pt
+2022-05-14 16:41:16,670 INFO [train.py:812] (0/8) Epoch 15, batch 0, loss[loss=0.1712, simple_loss=0.2706, pruned_loss=0.03587, over 7004.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2706, pruned_loss=0.03587, over 7004.00 frames.], batch size: 28, lr: 5.25e-04
+2022-05-14 16:42:15,479 INFO [train.py:812] (0/8) Epoch 15, batch 50, loss[loss=0.1869, simple_loss=0.2736, pruned_loss=0.05005, over 5073.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2616, pruned_loss=0.04263, over 321760.44 frames.], batch size: 52, lr: 5.24e-04
+2022-05-14 16:43:15,475 INFO [train.py:812] (0/8) Epoch 15, batch 100, loss[loss=0.1711, simple_loss=0.2639, pruned_loss=0.03912, over 7160.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2593, pruned_loss=0.04055, over 569053.91 frames.], batch size: 18, lr: 5.24e-04
+2022-05-14 16:44:31,097 INFO [train.py:812] (0/8) Epoch 15, batch 150, loss[loss=0.2139, simple_loss=0.3023, pruned_loss=0.0627, over 7126.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2611, pruned_loss=0.04192, over 759299.89 frames.], batch size: 21, lr: 5.24e-04
+2022-05-14 16:45:30,979 INFO [train.py:812] (0/8) Epoch 15, batch 200, loss[loss=0.1585, simple_loss=0.251, pruned_loss=0.03306, over 7328.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2612, pruned_loss=0.04193, over 902425.38 frames.], batch size: 20, lr: 5.24e-04
+2022-05-14 16:46:49,165 INFO [train.py:812] (0/8) Epoch 15, batch 250, loss[loss=0.2011, simple_loss=0.2961, pruned_loss=0.05311, over 6438.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2607, pruned_loss=0.04108, over 1019649.84 frames.], batch size: 37, lr: 5.24e-04
+2022-05-14 16:48:07,493 INFO [train.py:812] (0/8) Epoch 15, batch 300, loss[loss=0.1515, simple_loss=0.2342, pruned_loss=0.03439, over 7147.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2589, pruned_loss=0.04063, over 1109252.80 frames.], batch size: 17, lr: 5.23e-04
+2022-05-14 16:49:06,739 INFO [train.py:812] (0/8) Epoch 15, batch 350, loss[loss=0.1599, simple_loss=0.2365, pruned_loss=0.04164, over 6806.00 frames.], tot_loss[loss=0.171, simple_loss=0.259, pruned_loss=0.04145, over 1172110.64 frames.], batch size: 15, lr: 5.23e-04
+2022-05-14 16:50:06,778 INFO [train.py:812] (0/8) Epoch 15, batch 400, loss[loss=0.1715, simple_loss=0.2559, pruned_loss=0.04358, over 7151.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2594, pruned_loss=0.04141, over 1226929.74 frames.], batch size: 20, lr: 5.23e-04
+2022-05-14 16:51:05,953 INFO [train.py:812] (0/8) Epoch 15, batch 450, loss[loss=0.1641, simple_loss=0.2523, pruned_loss=0.03796, over 7154.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2589, pruned_loss=0.04074, over 1271194.30 frames.], batch size: 19, lr: 5.23e-04
+2022-05-14 16:52:05,459 INFO [train.py:812] (0/8) Epoch 15, batch 500, loss[loss=0.1606, simple_loss=0.2485, pruned_loss=0.03641, over 7428.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2594, pruned_loss=0.04089, over 1303231.16 frames.], batch size: 20, lr: 5.23e-04
+2022-05-14 16:53:04,818 INFO [train.py:812] (0/8) Epoch 15, batch 550, loss[loss=0.1506, simple_loss=0.2298, pruned_loss=0.03569, over 7280.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2588, pruned_loss=0.0408, over 1332063.84 frames.], batch size: 18, lr: 5.22e-04
+2022-05-14 16:54:04,512 INFO [train.py:812] (0/8) Epoch 15, batch 600, loss[loss=0.1397, simple_loss=0.2331, pruned_loss=0.02319, over 7234.00 frames.], tot_loss[loss=0.17, simple_loss=0.2587, pruned_loss=0.04063, over 1354625.59 frames.], batch size: 20, lr: 5.22e-04
+2022-05-14 16:55:03,786 INFO [train.py:812] (0/8) Epoch 15, batch 650, loss[loss=0.1635, simple_loss=0.2549, pruned_loss=0.03603, over 7333.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2589, pruned_loss=0.04079, over 1370039.79 frames.], batch size: 22, lr: 5.22e-04
+2022-05-14 16:56:03,043 INFO [train.py:812] (0/8) Epoch 15, batch 700, loss[loss=0.1847, simple_loss=0.2738, pruned_loss=0.04774, over 7319.00 frames.], tot_loss[loss=0.171, simple_loss=0.2599, pruned_loss=0.04104, over 1383111.63 frames.], batch size: 20, lr: 5.22e-04
+2022-05-14 16:57:02,254 INFO [train.py:812] (0/8) Epoch 15, batch 750, loss[loss=0.1615, simple_loss=0.2516, pruned_loss=0.03568, over 7340.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2598, pruned_loss=0.04102, over 1391187.39 frames.], batch size: 22, lr: 5.22e-04
+2022-05-14 16:58:01,660 INFO [train.py:812] (0/8) Epoch 15, batch 800, loss[loss=0.1824, simple_loss=0.2826, pruned_loss=0.04112, over 7346.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2586, pruned_loss=0.04017, over 1399623.69 frames.], batch size: 22, lr: 5.21e-04
+2022-05-14 16:59:00,994 INFO [train.py:812] (0/8) Epoch 15, batch 850, loss[loss=0.1344, simple_loss=0.2133, pruned_loss=0.02777, over 7128.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2587, pruned_loss=0.04026, over 1402698.16 frames.], batch size: 17, lr: 5.21e-04
+2022-05-14 17:00:00,533 INFO [train.py:812] (0/8) Epoch 15, batch 900, loss[loss=0.1696, simple_loss=0.2577, pruned_loss=0.04071, over 7253.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2587, pruned_loss=0.04033, over 1396898.41 frames.], batch size: 19, lr: 5.21e-04
+2022-05-14 17:00:59,820 INFO [train.py:812] (0/8) Epoch 15, batch 950, loss[loss=0.187, simple_loss=0.2718, pruned_loss=0.05112, over 7325.00 frames.], tot_loss[loss=0.171, simple_loss=0.2599, pruned_loss=0.04104, over 1405756.84 frames.], batch size: 22, lr: 5.21e-04
+2022-05-14 17:01:59,704 INFO [train.py:812] (0/8) Epoch 15, batch 1000, loss[loss=0.1521, simple_loss=0.2466, pruned_loss=0.02877, over 7017.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2604, pruned_loss=0.04146, over 1407219.67 frames.], batch size: 28, lr: 5.21e-04
+2022-05-14 17:02:57,918 INFO [train.py:812] (0/8) Epoch 15, batch 1050, loss[loss=0.1311, simple_loss=0.2131, pruned_loss=0.02455, over 7270.00 frames.], tot_loss[loss=0.171, simple_loss=0.2598, pruned_loss=0.04106, over 1412514.43 frames.], batch size: 18, lr: 5.20e-04
+2022-05-14 17:03:56,819 INFO [train.py:812] (0/8) Epoch 15, batch 1100, loss[loss=0.1684, simple_loss=0.2518, pruned_loss=0.04251, over 7294.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2597, pruned_loss=0.04137, over 1416842.60 frames.], batch size: 17, lr: 5.20e-04
+2022-05-14 17:04:54,404 INFO [train.py:812] (0/8) Epoch 15, batch 1150, loss[loss=0.1559, simple_loss=0.2534, pruned_loss=0.02921, over 7417.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2587, pruned_loss=0.04075, over 1421772.17 frames.], batch size: 21, lr: 5.20e-04
+2022-05-14 17:05:54,074 INFO [train.py:812] (0/8) Epoch 15, batch 1200, loss[loss=0.1686, simple_loss=0.2647, pruned_loss=0.03622, over 7427.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2577, pruned_loss=0.04055, over 1424070.53 frames.], batch size: 20, lr: 5.20e-04
+2022-05-14 17:06:52,040 INFO [train.py:812] (0/8) Epoch 15, batch 1250, loss[loss=0.1622, simple_loss=0.248, pruned_loss=0.03822, over 7358.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2583, pruned_loss=0.0407, over 1427031.40 frames.], batch size: 19, lr: 5.20e-04
+2022-05-14 17:07:51,283 INFO [train.py:812] (0/8) Epoch 15, batch 1300, loss[loss=0.166, simple_loss=0.2549, pruned_loss=0.03857, over 6376.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2583, pruned_loss=0.04062, over 1420409.79 frames.], batch size: 38, lr: 5.19e-04
+2022-05-14 17:08:51,287 INFO [train.py:812] (0/8) Epoch 15, batch 1350, loss[loss=0.1656, simple_loss=0.2406, pruned_loss=0.04533, over 6994.00 frames.], tot_loss[loss=0.17, simple_loss=0.2587, pruned_loss=0.04061, over 1423003.53 frames.], batch size: 16, lr: 5.19e-04
+2022-05-14 17:09:50,452 INFO [train.py:812] (0/8) Epoch 15, batch 1400, loss[loss=0.181, simple_loss=0.2675, pruned_loss=0.0472, over 7301.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2579, pruned_loss=0.0406, over 1422290.38 frames.], batch size: 24, lr: 5.19e-04
+2022-05-14 17:10:49,201 INFO [train.py:812] (0/8) Epoch 15, batch 1450, loss[loss=0.1944, simple_loss=0.2887, pruned_loss=0.04999, over 7380.00 frames.], tot_loss[loss=0.1697, simple_loss=0.258, pruned_loss=0.04069, over 1419080.16 frames.], batch size: 23, lr: 5.19e-04
+2022-05-14 17:11:46,392 INFO [train.py:812] (0/8) Epoch 15, batch 1500, loss[loss=0.1664, simple_loss=0.2519, pruned_loss=0.04043, over 7144.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2588, pruned_loss=0.04128, over 1413362.63 frames.], batch size: 20, lr: 5.19e-04
+2022-05-14 17:12:45,470 INFO [train.py:812] (0/8) Epoch 15, batch 1550, loss[loss=0.1952, simple_loss=0.2804, pruned_loss=0.05507, over 7110.00 frames.], tot_loss[loss=0.17, simple_loss=0.2578, pruned_loss=0.04109, over 1417177.48 frames.], batch size: 21, lr: 5.18e-04
+2022-05-14 17:13:44,513 INFO [train.py:812] (0/8) Epoch 15, batch 1600, loss[loss=0.192, simple_loss=0.2815, pruned_loss=0.05122, over 7413.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2577, pruned_loss=0.04106, over 1419261.24 frames.], batch size: 21, lr: 5.18e-04
+2022-05-14 17:14:43,365 INFO [train.py:812] (0/8) Epoch 15, batch 1650, loss[loss=0.203, simple_loss=0.2969, pruned_loss=0.05461, over 7199.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2578, pruned_loss=0.04051, over 1424484.46 frames.], batch size: 23, lr: 5.18e-04
+2022-05-14 17:15:42,310 INFO [train.py:812] (0/8) Epoch 15, batch 1700, loss[loss=0.2233, simple_loss=0.2995, pruned_loss=0.07358, over 7325.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2579, pruned_loss=0.04063, over 1428290.94 frames.], batch size: 25, lr: 5.18e-04
+2022-05-14 17:16:41,860 INFO [train.py:812] (0/8) Epoch 15, batch 1750, loss[loss=0.197, simple_loss=0.2965, pruned_loss=0.04881, over 7115.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2575, pruned_loss=0.04048, over 1431167.44 frames.], batch size: 28, lr: 5.18e-04
+2022-05-14 17:17:41,478 INFO [train.py:812] (0/8) Epoch 15, batch 1800, loss[loss=0.1619, simple_loss=0.2484, pruned_loss=0.03767, over 7273.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2575, pruned_loss=0.04039, over 1428431.32 frames.], batch size: 17, lr: 5.17e-04
+2022-05-14 17:18:41,019 INFO [train.py:812] (0/8) Epoch 15, batch 1850, loss[loss=0.1354, simple_loss=0.2255, pruned_loss=0.02261, over 7159.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2578, pruned_loss=0.04031, over 1432658.23 frames.], batch size: 18, lr: 5.17e-04
+2022-05-14 17:19:40,980 INFO [train.py:812] (0/8) Epoch 15, batch 1900, loss[loss=0.1753, simple_loss=0.2698, pruned_loss=0.04038, over 7117.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2575, pruned_loss=0.04003, over 1432477.63 frames.], batch size: 21, lr: 5.17e-04
+2022-05-14 17:20:40,391 INFO [train.py:812] (0/8) Epoch 15, batch 1950, loss[loss=0.1793, simple_loss=0.2734, pruned_loss=0.04263, over 7279.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2571, pruned_loss=0.03968, over 1432104.53 frames.], batch size: 18, lr: 5.17e-04
+2022-05-14 17:21:39,006 INFO [train.py:812] (0/8) Epoch 15, batch 2000, loss[loss=0.1714, simple_loss=0.2757, pruned_loss=0.03357, over 6530.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2575, pruned_loss=0.03976, over 1427991.00 frames.], batch size: 38, lr: 5.17e-04
+2022-05-14 17:22:38,283 INFO [train.py:812] (0/8) Epoch 15, batch 2050, loss[loss=0.1607, simple_loss=0.2627, pruned_loss=0.02933, over 7294.00 frames.], tot_loss[loss=0.1687, simple_loss=0.258, pruned_loss=0.03977, over 1429604.73 frames.], batch size: 25, lr: 5.16e-04
+2022-05-14 17:23:37,396 INFO [train.py:812] (0/8) Epoch 15, batch 2100, loss[loss=0.1656, simple_loss=0.2456, pruned_loss=0.04282, over 7412.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2574, pruned_loss=0.03981, over 1423080.48 frames.], batch size: 18, lr: 5.16e-04
+2022-05-14 17:24:36,097 INFO [train.py:812] (0/8) Epoch 15, batch 2150, loss[loss=0.1822, simple_loss=0.277, pruned_loss=0.04373, over 7193.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2573, pruned_loss=0.03978, over 1420605.67 frames.], batch size: 22, lr: 5.16e-04
+2022-05-14 17:25:35,529 INFO [train.py:812] (0/8) Epoch 15, batch 2200, loss[loss=0.1779, simple_loss=0.2659, pruned_loss=0.04492, over 7421.00 frames.], tot_loss[loss=0.169, simple_loss=0.2576, pruned_loss=0.04023, over 1420564.45 frames.], batch size: 20, lr: 5.16e-04
+2022-05-14 17:26:33,945 INFO [train.py:812] (0/8) Epoch 15, batch 2250, loss[loss=0.19, simple_loss=0.2779, pruned_loss=0.05107, over 7042.00 frames.], tot_loss[loss=0.169, simple_loss=0.2575, pruned_loss=0.04027, over 1421000.70 frames.], batch size: 28, lr: 5.16e-04
+2022-05-14 17:27:32,325 INFO [train.py:812] (0/8) Epoch 15, batch 2300, loss[loss=0.1493, simple_loss=0.2261, pruned_loss=0.0363, over 6775.00 frames.], tot_loss[loss=0.169, simple_loss=0.2578, pruned_loss=0.04013, over 1420114.35 frames.], batch size: 15, lr: 5.15e-04
+2022-05-14 17:28:30,788 INFO [train.py:812] (0/8) Epoch 15, batch 2350, loss[loss=0.1525, simple_loss=0.2228, pruned_loss=0.04106, over 7387.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2581, pruned_loss=0.0406, over 1423283.01 frames.], batch size: 18, lr: 5.15e-04
+2022-05-14 17:29:30,879 INFO [train.py:812] (0/8) Epoch 15, batch 2400, loss[loss=0.17, simple_loss=0.2482, pruned_loss=0.04593, over 7417.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2594, pruned_loss=0.04109, over 1420936.70 frames.], batch size: 18, lr: 5.15e-04
+2022-05-14 17:30:30,099 INFO [train.py:812] (0/8) Epoch 15, batch 2450, loss[loss=0.1964, simple_loss=0.2884, pruned_loss=0.05225, over 7415.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2599, pruned_loss=0.04136, over 1422122.12 frames.], batch size: 21, lr: 5.15e-04
+2022-05-14 17:31:29,562 INFO [train.py:812] (0/8) Epoch 15, batch 2500, loss[loss=0.1559, simple_loss=0.2628, pruned_loss=0.0245, over 7315.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2606, pruned_loss=0.04155, over 1424461.07 frames.], batch size: 21, lr: 5.15e-04
+2022-05-14 17:32:27,884 INFO [train.py:812] (0/8) Epoch 15, batch 2550, loss[loss=0.1613, simple_loss=0.2524, pruned_loss=0.03507, over 7163.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2599, pruned_loss=0.04115, over 1427151.78 frames.], batch size: 18, lr: 5.14e-04
+2022-05-14 17:33:27,561 INFO [train.py:812] (0/8) Epoch 15, batch 2600, loss[loss=0.1963, simple_loss=0.2839, pruned_loss=0.05434, over 7200.00 frames.], tot_loss[loss=0.172, simple_loss=0.2606, pruned_loss=0.04173, over 1421337.02 frames.], batch size: 23, lr: 5.14e-04
+2022-05-14 17:34:25,780 INFO [train.py:812] (0/8) Epoch 15, batch 2650, loss[loss=0.1555, simple_loss=0.2577, pruned_loss=0.02669, over 7321.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2598, pruned_loss=0.04139, over 1421953.88 frames.], batch size: 25, lr: 5.14e-04
+2022-05-14 17:35:25,129 INFO [train.py:812] (0/8) Epoch 15, batch 2700, loss[loss=0.1735, simple_loss=0.274, pruned_loss=0.03648, over 7314.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2602, pruned_loss=0.04125, over 1424190.28 frames.], batch size: 21, lr: 5.14e-04
+2022-05-14 17:36:24,191 INFO [train.py:812] (0/8) Epoch 15, batch 2750, loss[loss=0.1921, simple_loss=0.2746, pruned_loss=0.05474, over 7284.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2599, pruned_loss=0.04081, over 1425141.03 frames.], batch size: 24, lr: 5.14e-04
+2022-05-14 17:37:23,472 INFO [train.py:812] (0/8) Epoch 15, batch 2800, loss[loss=0.1691, simple_loss=0.2549, pruned_loss=0.0416, over 7150.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2593, pruned_loss=0.04056, over 1427951.03 frames.], batch size: 20, lr: 5.14e-04
+2022-05-14 17:38:20,794 INFO [train.py:812] (0/8) Epoch 15, batch 2850, loss[loss=0.1793, simple_loss=0.2651, pruned_loss=0.0468, over 7225.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2597, pruned_loss=0.04094, over 1428347.30 frames.], batch size: 16, lr: 5.13e-04
+2022-05-14 17:39:21,015 INFO [train.py:812] (0/8) Epoch 15, batch 2900, loss[loss=0.1851, simple_loss=0.2751, pruned_loss=0.04752, over 7388.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2595, pruned_loss=0.04091, over 1424238.83 frames.], batch size: 23, lr: 5.13e-04
+2022-05-14 17:40:20,000 INFO [train.py:812] (0/8) Epoch 15, batch 2950, loss[loss=0.1576, simple_loss=0.2484, pruned_loss=0.03342, over 7436.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2601, pruned_loss=0.04113, over 1425477.28 frames.], batch size: 20, lr: 5.13e-04
+2022-05-14 17:41:19,151 INFO [train.py:812] (0/8) Epoch 15, batch 3000, loss[loss=0.1766, simple_loss=0.2836, pruned_loss=0.03485, over 7164.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2591, pruned_loss=0.04089, over 1423115.72 frames.], batch size: 19, lr: 5.13e-04
+2022-05-14 17:41:19,152 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 17:41:26,768 INFO [train.py:841] (0/8) Epoch 15, validation: loss=0.1543, simple_loss=0.2544, pruned_loss=0.02713, over 698248.00 frames.
+2022-05-14 17:42:25,699 INFO [train.py:812] (0/8) Epoch 15, batch 3050, loss[loss=0.1438, simple_loss=0.2292, pruned_loss=0.02917, over 7212.00 frames.], tot_loss[loss=0.1702, simple_loss=0.259, pruned_loss=0.04069, over 1426071.90 frames.], batch size: 16, lr: 5.13e-04
+2022-05-14 17:43:23,123 INFO [train.py:812] (0/8) Epoch 15, batch 3100, loss[loss=0.1477, simple_loss=0.2393, pruned_loss=0.02801, over 7329.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2592, pruned_loss=0.04112, over 1423203.20 frames.], batch size: 20, lr: 5.12e-04
+2022-05-14 17:44:22,014 INFO [train.py:812] (0/8) Epoch 15, batch 3150, loss[loss=0.142, simple_loss=0.2282, pruned_loss=0.0279, over 7289.00 frames.], tot_loss[loss=0.1693, simple_loss=0.258, pruned_loss=0.04036, over 1427567.38 frames.], batch size: 17, lr: 5.12e-04
+2022-05-14 17:45:20,565 INFO [train.py:812] (0/8) Epoch 15, batch 3200, loss[loss=0.1915, simple_loss=0.2773, pruned_loss=0.05289, over 7115.00 frames.], tot_loss[loss=0.17, simple_loss=0.2582, pruned_loss=0.04087, over 1428227.49 frames.], batch size: 28, lr: 5.12e-04
+2022-05-14 17:46:20,252 INFO [train.py:812] (0/8) Epoch 15, batch 3250, loss[loss=0.1337, simple_loss=0.2294, pruned_loss=0.01901, over 7068.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2576, pruned_loss=0.04051, over 1428226.41 frames.], batch size: 18, lr: 5.12e-04
+2022-05-14 17:47:18,747 INFO [train.py:812] (0/8) Epoch 15, batch 3300, loss[loss=0.1458, simple_loss=0.2328, pruned_loss=0.02938, over 7305.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2566, pruned_loss=0.04031, over 1427772.49 frames.], batch size: 17, lr: 5.12e-04
+2022-05-14 17:48:17,426 INFO [train.py:812] (0/8) Epoch 15, batch 3350, loss[loss=0.2103, simple_loss=0.2897, pruned_loss=0.06548, over 7218.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2585, pruned_loss=0.04131, over 1427622.06 frames.], batch size: 23, lr: 5.11e-04
+2022-05-14 17:49:14,693 INFO [train.py:812] (0/8) Epoch 15, batch 3400, loss[loss=0.1751, simple_loss=0.2687, pruned_loss=0.04071, over 7228.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2599, pruned_loss=0.04191, over 1424753.16 frames.], batch size: 21, lr: 5.11e-04
+2022-05-14 17:50:13,426 INFO [train.py:812] (0/8) Epoch 15, batch 3450, loss[loss=0.1884, simple_loss=0.275, pruned_loss=0.05091, over 7058.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2605, pruned_loss=0.04214, over 1421885.18 frames.], batch size: 28, lr: 5.11e-04
+2022-05-14 17:51:13,179 INFO [train.py:812] (0/8) Epoch 15, batch 3500, loss[loss=0.1755, simple_loss=0.2606, pruned_loss=0.04518, over 7186.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2596, pruned_loss=0.04176, over 1426792.00 frames.], batch size: 26, lr: 5.11e-04
+2022-05-14 17:52:12,818 INFO [train.py:812] (0/8) Epoch 15, batch 3550, loss[loss=0.163, simple_loss=0.258, pruned_loss=0.03397, over 7236.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2593, pruned_loss=0.04146, over 1428404.28 frames.], batch size: 20, lr: 5.11e-04
+2022-05-14 17:53:11,372 INFO [train.py:812] (0/8) Epoch 15, batch 3600, loss[loss=0.1889, simple_loss=0.2773, pruned_loss=0.0503, over 7322.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2595, pruned_loss=0.0418, over 1424169.80 frames.], batch size: 21, lr: 5.11e-04
+2022-05-14 17:54:10,618 INFO [train.py:812] (0/8) Epoch 15, batch 3650, loss[loss=0.1572, simple_loss=0.2409, pruned_loss=0.03675, over 7256.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2598, pruned_loss=0.042, over 1425395.82 frames.], batch size: 19, lr: 5.10e-04
+2022-05-14 17:55:10,189 INFO [train.py:812] (0/8) Epoch 15, batch 3700, loss[loss=0.1543, simple_loss=0.2432, pruned_loss=0.03275, over 7427.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2599, pruned_loss=0.04176, over 1421750.10 frames.], batch size: 20, lr: 5.10e-04
+2022-05-14 17:56:09,540 INFO [train.py:812] (0/8) Epoch 15, batch 3750, loss[loss=0.1602, simple_loss=0.2548, pruned_loss=0.03276, over 5330.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2593, pruned_loss=0.04161, over 1423475.52 frames.], batch size: 53, lr: 5.10e-04
+2022-05-14 17:56:29,961 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-68000.pt
+2022-05-14 17:57:14,312 INFO [train.py:812] (0/8) Epoch 15, batch 3800, loss[loss=0.1737, simple_loss=0.2555, pruned_loss=0.04597, over 7059.00 frames.], tot_loss[loss=0.171, simple_loss=0.2595, pruned_loss=0.04129, over 1425893.77 frames.], batch size: 18, lr: 5.10e-04
+2022-05-14 17:58:12,040 INFO [train.py:812] (0/8) Epoch 15, batch 3850, loss[loss=0.1623, simple_loss=0.2576, pruned_loss=0.03351, over 7240.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2591, pruned_loss=0.04063, over 1428634.78 frames.], batch size: 20, lr: 5.10e-04
+2022-05-14 17:59:11,792 INFO [train.py:812] (0/8) Epoch 15, batch 3900, loss[loss=0.1563, simple_loss=0.2485, pruned_loss=0.03205, over 7268.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2583, pruned_loss=0.04066, over 1426550.36 frames.], batch size: 19, lr: 5.09e-04
+2022-05-14 18:00:10,972 INFO [train.py:812] (0/8) Epoch 15, batch 3950, loss[loss=0.1576, simple_loss=0.255, pruned_loss=0.03012, over 7357.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2583, pruned_loss=0.04056, over 1423643.94 frames.], batch size: 19, lr: 5.09e-04
+2022-05-14 18:01:10,514 INFO [train.py:812] (0/8) Epoch 15, batch 4000, loss[loss=0.1742, simple_loss=0.2613, pruned_loss=0.04356, over 7219.00 frames.], tot_loss[loss=0.169, simple_loss=0.2577, pruned_loss=0.04013, over 1423380.22 frames.], batch size: 21, lr: 5.09e-04
+2022-05-14 18:02:09,516 INFO [train.py:812] (0/8) Epoch 15, batch 4050, loss[loss=0.1592, simple_loss=0.2532, pruned_loss=0.03257, over 7222.00 frames.], tot_loss[loss=0.169, simple_loss=0.2581, pruned_loss=0.03988, over 1427197.30 frames.], batch size: 21, lr: 5.09e-04
+2022-05-14 18:03:08,725 INFO [train.py:812] (0/8) Epoch 15, batch 4100, loss[loss=0.1635, simple_loss=0.2589, pruned_loss=0.03406, over 7213.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2587, pruned_loss=0.04041, over 1419228.16 frames.], batch size: 23, lr: 5.09e-04
+2022-05-14 18:04:07,542 INFO [train.py:812] (0/8) Epoch 15, batch 4150, loss[loss=0.1782, simple_loss=0.2657, pruned_loss=0.04536, over 4720.00 frames.], tot_loss[loss=0.1695, simple_loss=0.258, pruned_loss=0.04047, over 1412691.96 frames.], batch size: 52, lr: 5.08e-04
+2022-05-14 18:05:07,007 INFO [train.py:812] (0/8) Epoch 15, batch 4200, loss[loss=0.1834, simple_loss=0.2737, pruned_loss=0.04656, over 7230.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2565, pruned_loss=0.03992, over 1410280.95 frames.], batch size: 20, lr: 5.08e-04
+2022-05-14 18:06:05,954 INFO [train.py:812] (0/8) Epoch 15, batch 4250, loss[loss=0.1646, simple_loss=0.2524, pruned_loss=0.03837, over 7068.00 frames.], tot_loss[loss=0.1684, simple_loss=0.257, pruned_loss=0.03987, over 1408339.19 frames.], batch size: 18, lr: 5.08e-04
+2022-05-14 18:07:05,135 INFO [train.py:812] (0/8) Epoch 15, batch 4300, loss[loss=0.1433, simple_loss=0.2213, pruned_loss=0.03261, over 6784.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2575, pruned_loss=0.04, over 1403583.53 frames.], batch size: 15, lr: 5.08e-04
+2022-05-14 18:08:04,064 INFO [train.py:812] (0/8) Epoch 15, batch 4350, loss[loss=0.1706, simple_loss=0.2666, pruned_loss=0.0373, over 7330.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2581, pruned_loss=0.03985, over 1407609.60 frames.], batch size: 21, lr: 5.08e-04
+2022-05-14 18:09:03,498 INFO [train.py:812] (0/8) Epoch 15, batch 4400, loss[loss=0.1546, simple_loss=0.2428, pruned_loss=0.03323, over 7164.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2574, pruned_loss=0.03959, over 1409870.35 frames.], batch size: 19, lr: 5.08e-04
+2022-05-14 18:10:02,431 INFO [train.py:812] (0/8) Epoch 15, batch 4450, loss[loss=0.1588, simple_loss=0.2339, pruned_loss=0.04183, over 7154.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2565, pruned_loss=0.03988, over 1402435.77 frames.], batch size: 18, lr: 5.07e-04
+2022-05-14 18:11:01,293 INFO [train.py:812] (0/8) Epoch 15, batch 4500, loss[loss=0.1319, simple_loss=0.2224, pruned_loss=0.02076, over 7053.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2579, pruned_loss=0.04085, over 1393774.50 frames.], batch size: 18, lr: 5.07e-04
+2022-05-14 18:11:59,583 INFO [train.py:812] (0/8) Epoch 15, batch 4550, loss[loss=0.2319, simple_loss=0.3081, pruned_loss=0.07782, over 5117.00 frames.], tot_loss[loss=0.172, simple_loss=0.2594, pruned_loss=0.04228, over 1366263.63 frames.], batch size: 52, lr: 5.07e-04
+2022-05-14 18:12:45,057 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-15.pt
+2022-05-14 18:13:08,803 INFO [train.py:812] (0/8) Epoch 16, batch 0, loss[loss=0.1861, simple_loss=0.2775, pruned_loss=0.04736, over 7314.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2775, pruned_loss=0.04736, over 7314.00 frames.], batch size: 24, lr: 4.92e-04
+2022-05-14 18:14:08,052 INFO [train.py:812] (0/8) Epoch 16, batch 50, loss[loss=0.1525, simple_loss=0.2347, pruned_loss=0.03513, over 7409.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2598, pruned_loss=0.03964, over 320644.02 frames.], batch size: 18, lr: 4.92e-04
+2022-05-14 18:15:07,117 INFO [train.py:812] (0/8) Epoch 16, batch 100, loss[loss=0.1541, simple_loss=0.2486, pruned_loss=0.02977, over 7322.00 frames.], tot_loss[loss=0.1676, simple_loss=0.257, pruned_loss=0.03913, over 563906.91 frames.], batch size: 20, lr: 4.92e-04
+2022-05-14 18:16:06,273 INFO [train.py:812] (0/8) Epoch 16, batch 150, loss[loss=0.1561, simple_loss=0.2468, pruned_loss=0.03273, over 7147.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2584, pruned_loss=0.04073, over 754104.57 frames.], batch size: 20, lr: 4.92e-04
+2022-05-14 18:17:15,110 INFO [train.py:812] (0/8) Epoch 16, batch 200, loss[loss=0.1823, simple_loss=0.2753, pruned_loss=0.04464, over 7126.00 frames.], tot_loss[loss=0.169, simple_loss=0.2572, pruned_loss=0.0404, over 897916.16 frames.], batch size: 21, lr: 4.91e-04
+2022-05-14 18:18:13,069 INFO [train.py:812] (0/8) Epoch 16, batch 250, loss[loss=0.1527, simple_loss=0.2428, pruned_loss=0.03134, over 7165.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2568, pruned_loss=0.04016, over 1015025.77 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:19:12,329 INFO [train.py:812] (0/8) Epoch 16, batch 300, loss[loss=0.1472, simple_loss=0.2404, pruned_loss=0.02699, over 7162.00 frames.], tot_loss[loss=0.1679, simple_loss=0.256, pruned_loss=0.03986, over 1109151.04 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:20:11,384 INFO [train.py:812] (0/8) Epoch 16, batch 350, loss[loss=0.1565, simple_loss=0.2366, pruned_loss=0.03818, over 7264.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2564, pruned_loss=0.0401, over 1179861.55 frames.], batch size: 18, lr: 4.91e-04
+2022-05-14 18:21:11,295 INFO [train.py:812] (0/8) Epoch 16, batch 400, loss[loss=0.1694, simple_loss=0.2613, pruned_loss=0.0388, over 7250.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2571, pruned_loss=0.03985, over 1233585.30 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:22:10,131 INFO [train.py:812] (0/8) Epoch 16, batch 450, loss[loss=0.1704, simple_loss=0.2529, pruned_loss=0.04392, over 7430.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2581, pruned_loss=0.04044, over 1281202.98 frames.], batch size: 20, lr: 4.91e-04
+2022-05-14 18:23:09,258 INFO [train.py:812] (0/8) Epoch 16, batch 500, loss[loss=0.1671, simple_loss=0.2547, pruned_loss=0.03978, over 7202.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2584, pruned_loss=0.04019, over 1317772.24 frames.], batch size: 23, lr: 4.90e-04
+2022-05-14 18:24:07,720 INFO [train.py:812] (0/8) Epoch 16, batch 550, loss[loss=0.1318, simple_loss=0.2194, pruned_loss=0.02216, over 7269.00 frames.], tot_loss[loss=0.1678, simple_loss=0.257, pruned_loss=0.03932, over 1344931.20 frames.], batch size: 18, lr: 4.90e-04
+2022-05-14 18:25:07,719 INFO [train.py:812] (0/8) Epoch 16, batch 600, loss[loss=0.1541, simple_loss=0.2403, pruned_loss=0.03393, over 7160.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2572, pruned_loss=0.03948, over 1360162.94 frames.], batch size: 19, lr: 4.90e-04
+2022-05-14 18:26:06,742 INFO [train.py:812] (0/8) Epoch 16, batch 650, loss[loss=0.1685, simple_loss=0.2654, pruned_loss=0.03577, over 6421.00 frames.], tot_loss[loss=0.168, simple_loss=0.2571, pruned_loss=0.03951, over 1373732.19 frames.], batch size: 38, lr: 4.90e-04
+2022-05-14 18:27:05,472 INFO [train.py:812] (0/8) Epoch 16, batch 700, loss[loss=0.1482, simple_loss=0.241, pruned_loss=0.02765, over 7043.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2572, pruned_loss=0.03949, over 1386461.20 frames.], batch size: 28, lr: 4.90e-04
+2022-05-14 18:28:04,353 INFO [train.py:812] (0/8) Epoch 16, batch 750, loss[loss=0.1591, simple_loss=0.2432, pruned_loss=0.03748, over 7155.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2566, pruned_loss=0.03941, over 1395378.02 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:29:03,805 INFO [train.py:812] (0/8) Epoch 16, batch 800, loss[loss=0.1404, simple_loss=0.2356, pruned_loss=0.0226, over 7263.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2567, pruned_loss=0.03921, over 1402612.64 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:30:02,504 INFO [train.py:812] (0/8) Epoch 16, batch 850, loss[loss=0.1676, simple_loss=0.2603, pruned_loss=0.03748, over 7152.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2576, pruned_loss=0.03975, over 1404181.83 frames.], batch size: 20, lr: 4.89e-04
+2022-05-14 18:31:02,366 INFO [train.py:812] (0/8) Epoch 16, batch 900, loss[loss=0.1795, simple_loss=0.268, pruned_loss=0.04546, over 7363.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2579, pruned_loss=0.04029, over 1403357.13 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:32:01,907 INFO [train.py:812] (0/8) Epoch 16, batch 950, loss[loss=0.197, simple_loss=0.2785, pruned_loss=0.05778, over 7426.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2583, pruned_loss=0.04101, over 1406808.34 frames.], batch size: 20, lr: 4.89e-04
+2022-05-14 18:33:00,790 INFO [train.py:812] (0/8) Epoch 16, batch 1000, loss[loss=0.1976, simple_loss=0.2871, pruned_loss=0.05403, over 7310.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2572, pruned_loss=0.04047, over 1411962.31 frames.], batch size: 25, lr: 4.89e-04
+2022-05-14 18:33:59,601 INFO [train.py:812] (0/8) Epoch 16, batch 1050, loss[loss=0.1699, simple_loss=0.2525, pruned_loss=0.04371, over 7332.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2575, pruned_loss=0.04073, over 1417126.40 frames.], batch size: 20, lr: 4.88e-04
+2022-05-14 18:34:59,557 INFO [train.py:812] (0/8) Epoch 16, batch 1100, loss[loss=0.1691, simple_loss=0.2659, pruned_loss=0.03613, over 7362.00 frames.], tot_loss[loss=0.169, simple_loss=0.2575, pruned_loss=0.04031, over 1420857.68 frames.], batch size: 19, lr: 4.88e-04
+2022-05-14 18:35:59,303 INFO [train.py:812] (0/8) Epoch 16, batch 1150, loss[loss=0.1696, simple_loss=0.2676, pruned_loss=0.03582, over 5234.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2571, pruned_loss=0.04036, over 1421144.87 frames.], batch size: 52, lr: 4.88e-04
+2022-05-14 18:36:59,223 INFO [train.py:812] (0/8) Epoch 16, batch 1200, loss[loss=0.1655, simple_loss=0.2587, pruned_loss=0.03615, over 7109.00 frames.], tot_loss[loss=0.169, simple_loss=0.2571, pruned_loss=0.0404, over 1418633.28 frames.], batch size: 21, lr: 4.88e-04
+2022-05-14 18:37:58,852 INFO [train.py:812] (0/8) Epoch 16, batch 1250, loss[loss=0.1333, simple_loss=0.219, pruned_loss=0.02383, over 6798.00 frames.], tot_loss[loss=0.1689, simple_loss=0.257, pruned_loss=0.04039, over 1418664.66 frames.], batch size: 15, lr: 4.88e-04
+2022-05-14 18:38:58,785 INFO [train.py:812] (0/8) Epoch 16, batch 1300, loss[loss=0.1733, simple_loss=0.2671, pruned_loss=0.03968, over 7211.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2581, pruned_loss=0.04024, over 1424741.32 frames.], batch size: 22, lr: 4.88e-04
+2022-05-14 18:39:58,300 INFO [train.py:812] (0/8) Epoch 16, batch 1350, loss[loss=0.1515, simple_loss=0.2384, pruned_loss=0.03225, over 7173.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2579, pruned_loss=0.04016, over 1417897.02 frames.], batch size: 19, lr: 4.87e-04
+2022-05-14 18:40:58,009 INFO [train.py:812] (0/8) Epoch 16, batch 1400, loss[loss=0.1731, simple_loss=0.2582, pruned_loss=0.044, over 7348.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2592, pruned_loss=0.04059, over 1416365.89 frames.], batch size: 22, lr: 4.87e-04
+2022-05-14 18:41:57,512 INFO [train.py:812] (0/8) Epoch 16, batch 1450, loss[loss=0.1617, simple_loss=0.2524, pruned_loss=0.03546, over 7420.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2591, pruned_loss=0.04011, over 1422554.12 frames.], batch size: 21, lr: 4.87e-04
+2022-05-14 18:43:06,576 INFO [train.py:812] (0/8) Epoch 16, batch 1500, loss[loss=0.1954, simple_loss=0.299, pruned_loss=0.04589, over 7194.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2581, pruned_loss=0.03952, over 1421851.05 frames.], batch size: 23, lr: 4.87e-04
+2022-05-14 18:44:06,048 INFO [train.py:812] (0/8) Epoch 16, batch 1550, loss[loss=0.1568, simple_loss=0.2365, pruned_loss=0.03857, over 6824.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2574, pruned_loss=0.03954, over 1420207.77 frames.], batch size: 15, lr: 4.87e-04
+2022-05-14 18:45:05,961 INFO [train.py:812] (0/8) Epoch 16, batch 1600, loss[loss=0.1727, simple_loss=0.2543, pruned_loss=0.04557, over 6774.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2582, pruned_loss=0.04024, over 1422264.73 frames.], batch size: 15, lr: 4.87e-04
+2022-05-14 18:46:05,455 INFO [train.py:812] (0/8) Epoch 16, batch 1650, loss[loss=0.1602, simple_loss=0.2581, pruned_loss=0.03121, over 7140.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2591, pruned_loss=0.04053, over 1424019.53 frames.], batch size: 20, lr: 4.86e-04
+2022-05-14 18:47:14,902 INFO [train.py:812] (0/8) Epoch 16, batch 1700, loss[loss=0.1544, simple_loss=0.2402, pruned_loss=0.03432, over 7418.00 frames.], tot_loss[loss=0.169, simple_loss=0.2579, pruned_loss=0.0401, over 1424522.77 frames.], batch size: 18, lr: 4.86e-04
+2022-05-14 18:48:31,553 INFO [train.py:812] (0/8) Epoch 16, batch 1750, loss[loss=0.1983, simple_loss=0.2877, pruned_loss=0.05446, over 7376.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2587, pruned_loss=0.04034, over 1424206.30 frames.], batch size: 23, lr: 4.86e-04
+2022-05-14 18:49:49,345 INFO [train.py:812] (0/8) Epoch 16, batch 1800, loss[loss=0.1516, simple_loss=0.2326, pruned_loss=0.03527, over 7360.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2586, pruned_loss=0.04033, over 1422759.80 frames.], batch size: 19, lr: 4.86e-04
+2022-05-14 18:50:57,670 INFO [train.py:812] (0/8) Epoch 16, batch 1850, loss[loss=0.1899, simple_loss=0.2808, pruned_loss=0.0495, over 7146.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2575, pruned_loss=0.04017, over 1424820.45 frames.], batch size: 20, lr: 4.86e-04
+2022-05-14 18:51:57,513 INFO [train.py:812] (0/8) Epoch 16, batch 1900, loss[loss=0.2079, simple_loss=0.3095, pruned_loss=0.05316, over 7269.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2579, pruned_loss=0.04064, over 1428582.50 frames.], batch size: 25, lr: 4.86e-04
+2022-05-14 18:52:55,101 INFO [train.py:812] (0/8) Epoch 16, batch 1950, loss[loss=0.1836, simple_loss=0.2754, pruned_loss=0.04586, over 7188.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2576, pruned_loss=0.04058, over 1429883.12 frames.], batch size: 23, lr: 4.85e-04
+2022-05-14 18:53:54,402 INFO [train.py:812] (0/8) Epoch 16, batch 2000, loss[loss=0.2212, simple_loss=0.3017, pruned_loss=0.07034, over 5053.00 frames.], tot_loss[loss=0.1695, simple_loss=0.258, pruned_loss=0.04052, over 1423870.58 frames.], batch size: 53, lr: 4.85e-04
+2022-05-14 18:54:53,353 INFO [train.py:812] (0/8) Epoch 16, batch 2050, loss[loss=0.1757, simple_loss=0.2757, pruned_loss=0.03782, over 6611.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2582, pruned_loss=0.04081, over 1422358.35 frames.], batch size: 38, lr: 4.85e-04
+2022-05-14 18:55:52,716 INFO [train.py:812] (0/8) Epoch 16, batch 2100, loss[loss=0.1602, simple_loss=0.2554, pruned_loss=0.03247, over 7104.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2595, pruned_loss=0.0414, over 1422860.29 frames.], batch size: 21, lr: 4.85e-04
+2022-05-14 18:56:51,654 INFO [train.py:812] (0/8) Epoch 16, batch 2150, loss[loss=0.1377, simple_loss=0.2262, pruned_loss=0.02462, over 7255.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2593, pruned_loss=0.04076, over 1417881.31 frames.], batch size: 19, lr: 4.85e-04
+2022-05-14 18:57:50,987 INFO [train.py:812] (0/8) Epoch 16, batch 2200, loss[loss=0.1738, simple_loss=0.2594, pruned_loss=0.04412, over 7209.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2587, pruned_loss=0.04052, over 1416429.78 frames.], batch size: 22, lr: 4.84e-04
+2022-05-14 18:58:50,178 INFO [train.py:812] (0/8) Epoch 16, batch 2250, loss[loss=0.1657, simple_loss=0.2671, pruned_loss=0.03218, over 7417.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2583, pruned_loss=0.04064, over 1417540.12 frames.], batch size: 21, lr: 4.84e-04
+2022-05-14 18:59:49,556 INFO [train.py:812] (0/8) Epoch 16, batch 2300, loss[loss=0.1995, simple_loss=0.2877, pruned_loss=0.0556, over 7184.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2587, pruned_loss=0.0407, over 1419541.62 frames.], batch size: 23, lr: 4.84e-04
+2022-05-14 19:00:48,681 INFO [train.py:812] (0/8) Epoch 16, batch 2350, loss[loss=0.2107, simple_loss=0.2991, pruned_loss=0.06113, over 7275.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2584, pruned_loss=0.04063, over 1421554.65 frames.], batch size: 25, lr: 4.84e-04
+2022-05-14 19:01:48,351 INFO [train.py:812] (0/8) Epoch 16, batch 2400, loss[loss=0.2004, simple_loss=0.2832, pruned_loss=0.05881, over 7310.00 frames.], tot_loss[loss=0.169, simple_loss=0.2575, pruned_loss=0.04023, over 1425343.09 frames.], batch size: 25, lr: 4.84e-04
+2022-05-14 19:02:47,252 INFO [train.py:812] (0/8) Epoch 16, batch 2450, loss[loss=0.1753, simple_loss=0.2673, pruned_loss=0.04165, over 6658.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2571, pruned_loss=0.03994, over 1424342.46 frames.], batch size: 31, lr: 4.84e-04
+2022-05-14 19:03:46,831 INFO [train.py:812] (0/8) Epoch 16, batch 2500, loss[loss=0.1388, simple_loss=0.2319, pruned_loss=0.0228, over 7238.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2562, pruned_loss=0.03966, over 1426931.13 frames.], batch size: 21, lr: 4.83e-04
+2022-05-14 19:04:46,103 INFO [train.py:812] (0/8) Epoch 16, batch 2550, loss[loss=0.1852, simple_loss=0.2748, pruned_loss=0.04781, over 7153.00 frames.], tot_loss[loss=0.167, simple_loss=0.2553, pruned_loss=0.03938, over 1423647.46 frames.], batch size: 20, lr: 4.83e-04
+2022-05-14 19:05:45,578 INFO [train.py:812] (0/8) Epoch 16, batch 2600, loss[loss=0.1584, simple_loss=0.2426, pruned_loss=0.03708, over 7357.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2556, pruned_loss=0.0395, over 1421642.59 frames.], batch size: 19, lr: 4.83e-04
+2022-05-14 19:06:45,338 INFO [train.py:812] (0/8) Epoch 16, batch 2650, loss[loss=0.1525, simple_loss=0.2439, pruned_loss=0.03061, over 7375.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2562, pruned_loss=0.03951, over 1421980.51 frames.], batch size: 23, lr: 4.83e-04
+2022-05-14 19:07:45,168 INFO [train.py:812] (0/8) Epoch 16, batch 2700, loss[loss=0.1923, simple_loss=0.2923, pruned_loss=0.04612, over 7178.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2573, pruned_loss=0.03981, over 1419710.95 frames.], batch size: 26, lr: 4.83e-04
+2022-05-14 19:08:44,233 INFO [train.py:812] (0/8) Epoch 16, batch 2750, loss[loss=0.1512, simple_loss=0.2316, pruned_loss=0.03545, over 7266.00 frames.], tot_loss[loss=0.1677, simple_loss=0.257, pruned_loss=0.03923, over 1423878.62 frames.], batch size: 18, lr: 4.83e-04
+2022-05-14 19:09:44,112 INFO [train.py:812] (0/8) Epoch 16, batch 2800, loss[loss=0.1654, simple_loss=0.2597, pruned_loss=0.03555, over 7228.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2573, pruned_loss=0.03923, over 1426156.21 frames.], batch size: 21, lr: 4.82e-04
+2022-05-14 19:10:43,381 INFO [train.py:812] (0/8) Epoch 16, batch 2850, loss[loss=0.1914, simple_loss=0.2767, pruned_loss=0.05299, over 7166.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2575, pruned_loss=0.03952, over 1425224.58 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:11:42,825 INFO [train.py:812] (0/8) Epoch 16, batch 2900, loss[loss=0.1492, simple_loss=0.2424, pruned_loss=0.02805, over 7166.00 frames.], tot_loss[loss=0.1676, simple_loss=0.257, pruned_loss=0.03909, over 1427419.37 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:12:41,629 INFO [train.py:812] (0/8) Epoch 16, batch 2950, loss[loss=0.1583, simple_loss=0.2616, pruned_loss=0.02751, over 7342.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2573, pruned_loss=0.03922, over 1423768.94 frames.], batch size: 22, lr: 4.82e-04
+2022-05-14 19:13:40,838 INFO [train.py:812] (0/8) Epoch 16, batch 3000, loss[loss=0.194, simple_loss=0.2878, pruned_loss=0.05014, over 7412.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2574, pruned_loss=0.03946, over 1427828.87 frames.], batch size: 21, lr: 4.82e-04
+2022-05-14 19:13:40,839 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 19:13:48,992 INFO [train.py:841] (0/8) Epoch 16, validation: loss=0.1537, simple_loss=0.2535, pruned_loss=0.02695, over 698248.00 frames.
+2022-05-14 19:14:47,140 INFO [train.py:812] (0/8) Epoch 16, batch 3050, loss[loss=0.1574, simple_loss=0.2399, pruned_loss=0.03747, over 7413.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2565, pruned_loss=0.03932, over 1426814.81 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:15:46,670 INFO [train.py:812] (0/8) Epoch 16, batch 3100, loss[loss=0.1972, simple_loss=0.2709, pruned_loss=0.06179, over 7187.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2563, pruned_loss=0.03959, over 1426403.44 frames.], batch size: 23, lr: 4.81e-04
+2022-05-14 19:16:44,981 INFO [train.py:812] (0/8) Epoch 16, batch 3150, loss[loss=0.1455, simple_loss=0.2401, pruned_loss=0.02548, over 7172.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2567, pruned_loss=0.03957, over 1423427.81 frames.], batch size: 18, lr: 4.81e-04
+2022-05-14 19:17:18,467 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-72000.pt
+2022-05-14 19:17:47,927 INFO [train.py:812] (0/8) Epoch 16, batch 3200, loss[loss=0.181, simple_loss=0.2671, pruned_loss=0.04748, over 7291.00 frames.], tot_loss[loss=0.1692, simple_loss=0.258, pruned_loss=0.04025, over 1423831.87 frames.], batch size: 24, lr: 4.81e-04
+2022-05-14 19:18:47,232 INFO [train.py:812] (0/8) Epoch 16, batch 3250, loss[loss=0.1528, simple_loss=0.2473, pruned_loss=0.02913, over 7301.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2576, pruned_loss=0.04004, over 1425258.61 frames.], batch size: 21, lr: 4.81e-04
+2022-05-14 19:19:45,418 INFO [train.py:812] (0/8) Epoch 16, batch 3300, loss[loss=0.1746, simple_loss=0.2755, pruned_loss=0.03685, over 7253.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2581, pruned_loss=0.04, over 1429193.99 frames.], batch size: 25, lr: 4.81e-04
+2022-05-14 19:20:42,557 INFO [train.py:812] (0/8) Epoch 16, batch 3350, loss[loss=0.1463, simple_loss=0.2507, pruned_loss=0.0209, over 7227.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2575, pruned_loss=0.03979, over 1431236.70 frames.], batch size: 20, lr: 4.81e-04
+2022-05-14 19:21:41,259 INFO [train.py:812] (0/8) Epoch 16, batch 3400, loss[loss=0.1802, simple_loss=0.2649, pruned_loss=0.04776, over 6987.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2582, pruned_loss=0.0397, over 1428297.70 frames.], batch size: 28, lr: 4.80e-04
+2022-05-14 19:22:40,326 INFO [train.py:812] (0/8) Epoch 16, batch 3450, loss[loss=0.1579, simple_loss=0.2441, pruned_loss=0.03588, over 7370.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2583, pruned_loss=0.04005, over 1429178.40 frames.], batch size: 19, lr: 4.80e-04
+2022-05-14 19:23:40,271 INFO [train.py:812] (0/8) Epoch 16, batch 3500, loss[loss=0.1648, simple_loss=0.2531, pruned_loss=0.03822, over 7308.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2584, pruned_loss=0.04007, over 1427719.08 frames.], batch size: 21, lr: 4.80e-04
+2022-05-14 19:24:39,220 INFO [train.py:812] (0/8) Epoch 16, batch 3550, loss[loss=0.1873, simple_loss=0.2831, pruned_loss=0.04576, over 7158.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2592, pruned_loss=0.0403, over 1423279.00 frames.], batch size: 26, lr: 4.80e-04
+2022-05-14 19:25:38,811 INFO [train.py:812] (0/8) Epoch 16, batch 3600, loss[loss=0.1775, simple_loss=0.2792, pruned_loss=0.03793, over 7325.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2579, pruned_loss=0.03973, over 1424976.43 frames.], batch size: 21, lr: 4.80e-04
+2022-05-14 19:26:37,925 INFO [train.py:812] (0/8) Epoch 16, batch 3650, loss[loss=0.171, simple_loss=0.2429, pruned_loss=0.04952, over 7282.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2576, pruned_loss=0.03967, over 1426024.24 frames.], batch size: 18, lr: 4.80e-04
+2022-05-14 19:27:36,141 INFO [train.py:812] (0/8) Epoch 16, batch 3700, loss[loss=0.1897, simple_loss=0.2666, pruned_loss=0.0564, over 7271.00 frames.], tot_loss[loss=0.169, simple_loss=0.258, pruned_loss=0.04, over 1423601.80 frames.], batch size: 16, lr: 4.79e-04
+2022-05-14 19:28:35,379 INFO [train.py:812] (0/8) Epoch 16, batch 3750, loss[loss=0.1774, simple_loss=0.2772, pruned_loss=0.03882, over 7290.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2575, pruned_loss=0.03965, over 1421224.02 frames.], batch size: 25, lr: 4.79e-04
+2022-05-14 19:29:33,343 INFO [train.py:812] (0/8) Epoch 16, batch 3800, loss[loss=0.1682, simple_loss=0.2488, pruned_loss=0.04383, over 7150.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2576, pruned_loss=0.03924, over 1424978.34 frames.], batch size: 17, lr: 4.79e-04
+2022-05-14 19:30:31,485 INFO [train.py:812] (0/8) Epoch 16, batch 3850, loss[loss=0.1601, simple_loss=0.2469, pruned_loss=0.03669, over 7273.00 frames.], tot_loss[loss=0.1683, simple_loss=0.258, pruned_loss=0.03929, over 1421952.47 frames.], batch size: 18, lr: 4.79e-04
+2022-05-14 19:31:29,702 INFO [train.py:812] (0/8) Epoch 16, batch 3900, loss[loss=0.189, simple_loss=0.2851, pruned_loss=0.04646, over 7224.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2571, pruned_loss=0.03882, over 1423226.99 frames.], batch size: 21, lr: 4.79e-04
+2022-05-14 19:32:28,902 INFO [train.py:812] (0/8) Epoch 16, batch 3950, loss[loss=0.1731, simple_loss=0.2639, pruned_loss=0.0411, over 7233.00 frames.], tot_loss[loss=0.168, simple_loss=0.2576, pruned_loss=0.03925, over 1421335.43 frames.], batch size: 20, lr: 4.79e-04
+2022-05-14 19:33:27,632 INFO [train.py:812] (0/8) Epoch 16, batch 4000, loss[loss=0.1784, simple_loss=0.2728, pruned_loss=0.04199, over 7318.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2573, pruned_loss=0.03927, over 1419156.29 frames.], batch size: 21, lr: 4.79e-04
+2022-05-14 19:34:27,160 INFO [train.py:812] (0/8) Epoch 16, batch 4050, loss[loss=0.149, simple_loss=0.2469, pruned_loss=0.0255, over 7168.00 frames.], tot_loss[loss=0.1675, simple_loss=0.257, pruned_loss=0.039, over 1418559.84 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:35:27,341 INFO [train.py:812] (0/8) Epoch 16, batch 4100, loss[loss=0.1519, simple_loss=0.245, pruned_loss=0.0294, over 7163.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2565, pruned_loss=0.03899, over 1423713.59 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:36:26,213 INFO [train.py:812] (0/8) Epoch 16, batch 4150, loss[loss=0.1521, simple_loss=0.2403, pruned_loss=0.03194, over 7061.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2567, pruned_loss=0.0389, over 1417708.32 frames.], batch size: 28, lr: 4.78e-04
+2022-05-14 19:37:25,179 INFO [train.py:812] (0/8) Epoch 16, batch 4200, loss[loss=0.1322, simple_loss=0.2196, pruned_loss=0.02239, over 6990.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2558, pruned_loss=0.03859, over 1417059.50 frames.], batch size: 16, lr: 4.78e-04
+2022-05-14 19:38:24,505 INFO [train.py:812] (0/8) Epoch 16, batch 4250, loss[loss=0.1564, simple_loss=0.2478, pruned_loss=0.03246, over 7160.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2547, pruned_loss=0.03858, over 1416112.21 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:39:23,904 INFO [train.py:812] (0/8) Epoch 16, batch 4300, loss[loss=0.1614, simple_loss=0.249, pruned_loss=0.03689, over 6850.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2545, pruned_loss=0.03821, over 1411798.73 frames.], batch size: 31, lr: 4.78e-04
+2022-05-14 19:40:22,795 INFO [train.py:812] (0/8) Epoch 16, batch 4350, loss[loss=0.1461, simple_loss=0.235, pruned_loss=0.02859, over 7170.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2547, pruned_loss=0.03805, over 1415288.38 frames.], batch size: 18, lr: 4.77e-04
+2022-05-14 19:41:21,970 INFO [train.py:812] (0/8) Epoch 16, batch 4400, loss[loss=0.1568, simple_loss=0.2498, pruned_loss=0.03185, over 7118.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2545, pruned_loss=0.03806, over 1415844.46 frames.], batch size: 21, lr: 4.77e-04
+2022-05-14 19:42:18,617 INFO [train.py:812] (0/8) Epoch 16, batch 4450, loss[loss=0.1849, simple_loss=0.2698, pruned_loss=0.05, over 7212.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2551, pruned_loss=0.03868, over 1411259.18 frames.], batch size: 22, lr: 4.77e-04
+2022-05-14 19:43:16,038 INFO [train.py:812] (0/8) Epoch 16, batch 4500, loss[loss=0.1562, simple_loss=0.2427, pruned_loss=0.03485, over 7111.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2549, pruned_loss=0.03867, over 1400946.44 frames.], batch size: 17, lr: 4.77e-04
+2022-05-14 19:44:12,835 INFO [train.py:812] (0/8) Epoch 16, batch 4550, loss[loss=0.206, simple_loss=0.2869, pruned_loss=0.06257, over 4928.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2585, pruned_loss=0.04092, over 1350870.49 frames.], batch size: 52, lr: 4.77e-04
+2022-05-14 19:44:58,544 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-16.pt
+2022-05-14 19:45:27,026 INFO [train.py:812] (0/8) Epoch 17, batch 0, loss[loss=0.1727, simple_loss=0.2583, pruned_loss=0.04358, over 7104.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2583, pruned_loss=0.04358, over 7104.00 frames.], batch size: 21, lr: 4.63e-04
+2022-05-14 19:46:26,104 INFO [train.py:812] (0/8) Epoch 17, batch 50, loss[loss=0.1746, simple_loss=0.2723, pruned_loss=0.03848, over 7314.00 frames.], tot_loss[loss=0.172, simple_loss=0.2608, pruned_loss=0.04166, over 317404.23 frames.], batch size: 21, lr: 4.63e-04
+2022-05-14 19:47:25,014 INFO [train.py:812] (0/8) Epoch 17, batch 100, loss[loss=0.1639, simple_loss=0.2508, pruned_loss=0.03854, over 7143.00 frames.], tot_loss[loss=0.1703, simple_loss=0.259, pruned_loss=0.04078, over 559345.24 frames.], batch size: 20, lr: 4.63e-04
+2022-05-14 19:48:23,536 INFO [train.py:812] (0/8) Epoch 17, batch 150, loss[loss=0.1309, simple_loss=0.2103, pruned_loss=0.02576, over 7430.00 frames.], tot_loss[loss=0.167, simple_loss=0.2558, pruned_loss=0.03906, over 747332.08 frames.], batch size: 17, lr: 4.63e-04
+2022-05-14 19:49:23,000 INFO [train.py:812] (0/8) Epoch 17, batch 200, loss[loss=0.1597, simple_loss=0.2385, pruned_loss=0.04045, over 7144.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2577, pruned_loss=0.03941, over 896400.85 frames.], batch size: 17, lr: 4.63e-04
+2022-05-14 19:50:21,370 INFO [train.py:812] (0/8) Epoch 17, batch 250, loss[loss=0.1644, simple_loss=0.2625, pruned_loss=0.03319, over 7268.00 frames.], tot_loss[loss=0.169, simple_loss=0.2586, pruned_loss=0.03972, over 1015422.63 frames.], batch size: 19, lr: 4.63e-04
+2022-05-14 19:51:20,293 INFO [train.py:812] (0/8) Epoch 17, batch 300, loss[loss=0.1571, simple_loss=0.2452, pruned_loss=0.03444, over 7077.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2585, pruned_loss=0.03943, over 1101092.16 frames.], batch size: 18, lr: 4.62e-04
+2022-05-14 19:52:19,496 INFO [train.py:812] (0/8) Epoch 17, batch 350, loss[loss=0.1576, simple_loss=0.2401, pruned_loss=0.03755, over 6890.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2577, pruned_loss=0.03981, over 1171416.98 frames.], batch size: 15, lr: 4.62e-04
+2022-05-14 19:53:18,624 INFO [train.py:812] (0/8) Epoch 17, batch 400, loss[loss=0.2012, simple_loss=0.2827, pruned_loss=0.05992, over 4815.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2568, pruned_loss=0.03917, over 1227209.63 frames.], batch size: 52, lr: 4.62e-04
+2022-05-14 19:54:16,197 INFO [train.py:812] (0/8) Epoch 17, batch 450, loss[loss=0.1802, simple_loss=0.2657, pruned_loss=0.04736, over 7353.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2567, pruned_loss=0.03954, over 1267837.37 frames.], batch size: 19, lr: 4.62e-04
+2022-05-14 19:55:14,833 INFO [train.py:812] (0/8) Epoch 17, batch 500, loss[loss=0.144, simple_loss=0.2331, pruned_loss=0.02742, over 7160.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2556, pruned_loss=0.03896, over 1301434.59 frames.], batch size: 18, lr: 4.62e-04
+2022-05-14 19:56:13,763 INFO [train.py:812] (0/8) Epoch 17, batch 550, loss[loss=0.1499, simple_loss=0.2344, pruned_loss=0.03273, over 7135.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2555, pruned_loss=0.03892, over 1327551.88 frames.], batch size: 17, lr: 4.62e-04
+2022-05-14 19:57:12,595 INFO [train.py:812] (0/8) Epoch 17, batch 600, loss[loss=0.173, simple_loss=0.2575, pruned_loss=0.04425, over 7034.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2563, pruned_loss=0.03949, over 1342651.33 frames.], batch size: 28, lr: 4.62e-04
+2022-05-14 19:58:11,556 INFO [train.py:812] (0/8) Epoch 17, batch 650, loss[loss=0.1746, simple_loss=0.2632, pruned_loss=0.04304, over 7326.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2571, pruned_loss=0.03997, over 1360631.64 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 19:59:10,344 INFO [train.py:812] (0/8) Epoch 17, batch 700, loss[loss=0.1494, simple_loss=0.2326, pruned_loss=0.03317, over 7261.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2575, pruned_loss=0.0399, over 1367424.30 frames.], batch size: 19, lr: 4.61e-04
+2022-05-14 20:00:09,412 INFO [train.py:812] (0/8) Epoch 17, batch 750, loss[loss=0.1751, simple_loss=0.2681, pruned_loss=0.0411, over 7154.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2579, pruned_loss=0.04011, over 1376459.33 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 20:01:08,215 INFO [train.py:812] (0/8) Epoch 17, batch 800, loss[loss=0.1585, simple_loss=0.2395, pruned_loss=0.03879, over 7160.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2573, pruned_loss=0.03993, over 1387026.29 frames.], batch size: 19, lr: 4.61e-04
+2022-05-14 20:02:07,158 INFO [train.py:812] (0/8) Epoch 17, batch 850, loss[loss=0.1833, simple_loss=0.2712, pruned_loss=0.04771, over 6374.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2562, pruned_loss=0.03947, over 1395053.25 frames.], batch size: 38, lr: 4.61e-04
+2022-05-14 20:03:05,140 INFO [train.py:812] (0/8) Epoch 17, batch 900, loss[loss=0.1861, simple_loss=0.2724, pruned_loss=0.04984, over 7334.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2567, pruned_loss=0.03946, over 1406773.02 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 20:04:03,148 INFO [train.py:812] (0/8) Epoch 17, batch 950, loss[loss=0.1491, simple_loss=0.2349, pruned_loss=0.03164, over 7158.00 frames.], tot_loss[loss=0.167, simple_loss=0.2562, pruned_loss=0.03888, over 1411286.54 frames.], batch size: 17, lr: 4.60e-04
+2022-05-14 20:05:01,750 INFO [train.py:812] (0/8) Epoch 17, batch 1000, loss[loss=0.1418, simple_loss=0.237, pruned_loss=0.02328, over 7112.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2561, pruned_loss=0.03883, over 1415187.38 frames.], batch size: 21, lr: 4.60e-04
+2022-05-14 20:06:00,348 INFO [train.py:812] (0/8) Epoch 17, batch 1050, loss[loss=0.1697, simple_loss=0.2714, pruned_loss=0.03395, over 7333.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2555, pruned_loss=0.03865, over 1419799.90 frames.], batch size: 22, lr: 4.60e-04
+2022-05-14 20:06:59,568 INFO [train.py:812] (0/8) Epoch 17, batch 1100, loss[loss=0.1687, simple_loss=0.2547, pruned_loss=0.04137, over 7285.00 frames.], tot_loss[loss=0.166, simple_loss=0.255, pruned_loss=0.03852, over 1420746.23 frames.], batch size: 24, lr: 4.60e-04
+2022-05-14 20:07:58,277 INFO [train.py:812] (0/8) Epoch 17, batch 1150, loss[loss=0.1887, simple_loss=0.2756, pruned_loss=0.05094, over 7277.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2558, pruned_loss=0.03853, over 1422077.25 frames.], batch size: 24, lr: 4.60e-04
+2022-05-14 20:08:57,627 INFO [train.py:812] (0/8) Epoch 17, batch 1200, loss[loss=0.2555, simple_loss=0.352, pruned_loss=0.07944, over 7295.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2572, pruned_loss=0.03908, over 1419753.25 frames.], batch size: 25, lr: 4.60e-04
+2022-05-14 20:09:55,624 INFO [train.py:812] (0/8) Epoch 17, batch 1250, loss[loss=0.1375, simple_loss=0.2291, pruned_loss=0.02289, over 7276.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2566, pruned_loss=0.03906, over 1415069.90 frames.], batch size: 18, lr: 4.60e-04
+2022-05-14 20:10:53,592 INFO [train.py:812] (0/8) Epoch 17, batch 1300, loss[loss=0.1948, simple_loss=0.2886, pruned_loss=0.05051, over 7341.00 frames.], tot_loss[loss=0.168, simple_loss=0.257, pruned_loss=0.03952, over 1412684.01 frames.], batch size: 22, lr: 4.59e-04
+2022-05-14 20:11:51,651 INFO [train.py:812] (0/8) Epoch 17, batch 1350, loss[loss=0.1453, simple_loss=0.2354, pruned_loss=0.02764, over 7002.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2565, pruned_loss=0.03905, over 1418665.53 frames.], batch size: 16, lr: 4.59e-04
+2022-05-14 20:12:51,103 INFO [train.py:812] (0/8) Epoch 17, batch 1400, loss[loss=0.203, simple_loss=0.3018, pruned_loss=0.05214, over 7140.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2547, pruned_loss=0.03823, over 1420192.42 frames.], batch size: 20, lr: 4.59e-04
+2022-05-14 20:13:49,603 INFO [train.py:812] (0/8) Epoch 17, batch 1450, loss[loss=0.1833, simple_loss=0.279, pruned_loss=0.04381, over 7345.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2565, pruned_loss=0.03901, over 1418530.11 frames.], batch size: 22, lr: 4.59e-04
+2022-05-14 20:14:49,014 INFO [train.py:812] (0/8) Epoch 17, batch 1500, loss[loss=0.1701, simple_loss=0.2511, pruned_loss=0.04456, over 7264.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2553, pruned_loss=0.03867, over 1424649.06 frames.], batch size: 19, lr: 4.59e-04
+2022-05-14 20:15:57,420 INFO [train.py:812] (0/8) Epoch 17, batch 1550, loss[loss=0.1839, simple_loss=0.2735, pruned_loss=0.0472, over 7226.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2554, pruned_loss=0.03884, over 1422024.48 frames.], batch size: 21, lr: 4.59e-04
+2022-05-14 20:16:56,746 INFO [train.py:812] (0/8) Epoch 17, batch 1600, loss[loss=0.1583, simple_loss=0.253, pruned_loss=0.03185, over 7425.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2555, pruned_loss=0.03871, over 1427050.57 frames.], batch size: 20, lr: 4.58e-04
+2022-05-14 20:17:55,352 INFO [train.py:812] (0/8) Epoch 17, batch 1650, loss[loss=0.165, simple_loss=0.2549, pruned_loss=0.03759, over 7414.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2555, pruned_loss=0.03843, over 1428897.92 frames.], batch size: 21, lr: 4.58e-04
+2022-05-14 20:18:53,756 INFO [train.py:812] (0/8) Epoch 17, batch 1700, loss[loss=0.1845, simple_loss=0.2643, pruned_loss=0.05239, over 5071.00 frames.], tot_loss[loss=0.167, simple_loss=0.2561, pruned_loss=0.03894, over 1421985.63 frames.], batch size: 52, lr: 4.58e-04
+2022-05-14 20:19:52,400 INFO [train.py:812] (0/8) Epoch 17, batch 1750, loss[loss=0.1884, simple_loss=0.2834, pruned_loss=0.04671, over 7377.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2572, pruned_loss=0.03928, over 1413309.57 frames.], batch size: 23, lr: 4.58e-04
+2022-05-14 20:20:51,614 INFO [train.py:812] (0/8) Epoch 17, batch 1800, loss[loss=0.1743, simple_loss=0.2609, pruned_loss=0.04382, over 7195.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2572, pruned_loss=0.03885, over 1413627.99 frames.], batch size: 23, lr: 4.58e-04
+2022-05-14 20:21:48,761 INFO [train.py:812] (0/8) Epoch 17, batch 1850, loss[loss=0.1482, simple_loss=0.2358, pruned_loss=0.03034, over 6302.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2571, pruned_loss=0.03884, over 1414210.43 frames.], batch size: 37, lr: 4.58e-04
+2022-05-14 20:22:47,370 INFO [train.py:812] (0/8) Epoch 17, batch 1900, loss[loss=0.1586, simple_loss=0.2379, pruned_loss=0.03969, over 7425.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2571, pruned_loss=0.03896, over 1419355.18 frames.], batch size: 20, lr: 4.58e-04
+2022-05-14 20:23:46,067 INFO [train.py:812] (0/8) Epoch 17, batch 1950, loss[loss=0.1779, simple_loss=0.2735, pruned_loss=0.04119, over 7320.00 frames.], tot_loss[loss=0.1674, simple_loss=0.257, pruned_loss=0.03894, over 1422283.16 frames.], batch size: 21, lr: 4.57e-04
+2022-05-14 20:24:44,618 INFO [train.py:812] (0/8) Epoch 17, batch 2000, loss[loss=0.1601, simple_loss=0.2514, pruned_loss=0.03439, over 7256.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2577, pruned_loss=0.0392, over 1424546.24 frames.], batch size: 19, lr: 4.57e-04
+2022-05-14 20:25:43,662 INFO [train.py:812] (0/8) Epoch 17, batch 2050, loss[loss=0.1621, simple_loss=0.2461, pruned_loss=0.03904, over 7412.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2562, pruned_loss=0.03869, over 1428101.69 frames.], batch size: 18, lr: 4.57e-04
+2022-05-14 20:26:43,361 INFO [train.py:812] (0/8) Epoch 17, batch 2100, loss[loss=0.176, simple_loss=0.2624, pruned_loss=0.04483, over 7416.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2562, pruned_loss=0.03853, over 1428530.92 frames.], batch size: 21, lr: 4.57e-04
+2022-05-14 20:27:42,657 INFO [train.py:812] (0/8) Epoch 17, batch 2150, loss[loss=0.1626, simple_loss=0.2465, pruned_loss=0.03931, over 7362.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2568, pruned_loss=0.03876, over 1423807.76 frames.], batch size: 19, lr: 4.57e-04
+2022-05-14 20:28:40,069 INFO [train.py:812] (0/8) Epoch 17, batch 2200, loss[loss=0.1592, simple_loss=0.2568, pruned_loss=0.03077, over 7339.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2569, pruned_loss=0.03839, over 1421058.58 frames.], batch size: 22, lr: 4.57e-04
+2022-05-14 20:29:39,213 INFO [train.py:812] (0/8) Epoch 17, batch 2250, loss[loss=0.1567, simple_loss=0.2526, pruned_loss=0.03034, over 7421.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2571, pruned_loss=0.03838, over 1423393.32 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:30:37,978 INFO [train.py:812] (0/8) Epoch 17, batch 2300, loss[loss=0.1843, simple_loss=0.279, pruned_loss=0.04474, over 7292.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2569, pruned_loss=0.03869, over 1422534.96 frames.], batch size: 24, lr: 4.56e-04
+2022-05-14 20:31:36,707 INFO [train.py:812] (0/8) Epoch 17, batch 2350, loss[loss=0.1758, simple_loss=0.2713, pruned_loss=0.04019, over 7389.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2564, pruned_loss=0.03866, over 1426435.37 frames.], batch size: 23, lr: 4.56e-04
+2022-05-14 20:32:36,109 INFO [train.py:812] (0/8) Epoch 17, batch 2400, loss[loss=0.1446, simple_loss=0.2217, pruned_loss=0.03374, over 7010.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2562, pruned_loss=0.03871, over 1424133.03 frames.], batch size: 16, lr: 4.56e-04
+2022-05-14 20:33:34,527 INFO [train.py:812] (0/8) Epoch 17, batch 2450, loss[loss=0.1611, simple_loss=0.2593, pruned_loss=0.03142, over 7329.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2556, pruned_loss=0.03845, over 1422971.21 frames.], batch size: 22, lr: 4.56e-04
+2022-05-14 20:34:34,268 INFO [train.py:812] (0/8) Epoch 17, batch 2500, loss[loss=0.1767, simple_loss=0.2726, pruned_loss=0.04039, over 7222.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2541, pruned_loss=0.03798, over 1422759.13 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:35:31,628 INFO [train.py:812] (0/8) Epoch 17, batch 2550, loss[loss=0.163, simple_loss=0.2478, pruned_loss=0.03906, over 7222.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2541, pruned_loss=0.03821, over 1418058.21 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:36:19,461 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-76000.pt
+2022-05-14 20:36:37,550 INFO [train.py:812] (0/8) Epoch 17, batch 2600, loss[loss=0.1712, simple_loss=0.2683, pruned_loss=0.03702, over 7037.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2553, pruned_loss=0.03842, over 1421248.54 frames.], batch size: 28, lr: 4.55e-04
+2022-05-14 20:37:36,694 INFO [train.py:812] (0/8) Epoch 17, batch 2650, loss[loss=0.1465, simple_loss=0.2349, pruned_loss=0.0291, over 7357.00 frames.], tot_loss[loss=0.167, simple_loss=0.2562, pruned_loss=0.0389, over 1420160.77 frames.], batch size: 19, lr: 4.55e-04
+2022-05-14 20:38:34,786 INFO [train.py:812] (0/8) Epoch 17, batch 2700, loss[loss=0.1694, simple_loss=0.2546, pruned_loss=0.04211, over 7337.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2554, pruned_loss=0.03866, over 1423854.20 frames.], batch size: 22, lr: 4.55e-04
+2022-05-14 20:39:32,813 INFO [train.py:812] (0/8) Epoch 17, batch 2750, loss[loss=0.1664, simple_loss=0.2505, pruned_loss=0.04117, over 7155.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2551, pruned_loss=0.03882, over 1423042.07 frames.], batch size: 19, lr: 4.55e-04
+2022-05-14 20:40:31,882 INFO [train.py:812] (0/8) Epoch 17, batch 2800, loss[loss=0.1868, simple_loss=0.2653, pruned_loss=0.05418, over 5030.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2547, pruned_loss=0.03861, over 1422067.31 frames.], batch size: 52, lr: 4.55e-04
+2022-05-14 20:41:30,551 INFO [train.py:812] (0/8) Epoch 17, batch 2850, loss[loss=0.1629, simple_loss=0.2537, pruned_loss=0.036, over 7319.00 frames.], tot_loss[loss=0.1663, simple_loss=0.255, pruned_loss=0.03879, over 1421777.98 frames.], batch size: 21, lr: 4.55e-04
+2022-05-14 20:42:28,889 INFO [train.py:812] (0/8) Epoch 17, batch 2900, loss[loss=0.1553, simple_loss=0.2506, pruned_loss=0.02993, over 7227.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2553, pruned_loss=0.03879, over 1418062.23 frames.], batch size: 20, lr: 4.55e-04
+2022-05-14 20:43:27,755 INFO [train.py:812] (0/8) Epoch 17, batch 2950, loss[loss=0.1459, simple_loss=0.238, pruned_loss=0.02689, over 7274.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2562, pruned_loss=0.0388, over 1418450.43 frames.], batch size: 18, lr: 4.54e-04
+2022-05-14 20:44:36,158 INFO [train.py:812] (0/8) Epoch 17, batch 3000, loss[loss=0.169, simple_loss=0.2668, pruned_loss=0.03563, over 7144.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2562, pruned_loss=0.03859, over 1423206.20 frames.], batch size: 20, lr: 4.54e-04
+2022-05-14 20:44:36,160 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 20:44:43,902 INFO [train.py:841] (0/8) Epoch 17, validation: loss=0.1538, simple_loss=0.2534, pruned_loss=0.02708, over 698248.00 frames.
+2022-05-14 20:45:42,772 INFO [train.py:812] (0/8) Epoch 17, batch 3050, loss[loss=0.1989, simple_loss=0.2817, pruned_loss=0.05804, over 6568.00 frames.], tot_loss[loss=0.1666, simple_loss=0.256, pruned_loss=0.03861, over 1422712.14 frames.], batch size: 38, lr: 4.54e-04
+2022-05-14 20:46:41,080 INFO [train.py:812] (0/8) Epoch 17, batch 3100, loss[loss=0.2018, simple_loss=0.294, pruned_loss=0.05478, over 7262.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2571, pruned_loss=0.03913, over 1419624.27 frames.], batch size: 25, lr: 4.54e-04
+2022-05-14 20:47:58,694 INFO [train.py:812] (0/8) Epoch 17, batch 3150, loss[loss=0.1672, simple_loss=0.262, pruned_loss=0.03617, over 7326.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2567, pruned_loss=0.03944, over 1419234.33 frames.], batch size: 20, lr: 4.54e-04
+2022-05-14 20:49:07,269 INFO [train.py:812] (0/8) Epoch 17, batch 3200, loss[loss=0.1524, simple_loss=0.2465, pruned_loss=0.02916, over 7360.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2566, pruned_loss=0.03949, over 1419709.46 frames.], batch size: 19, lr: 4.54e-04
+2022-05-14 20:50:25,524 INFO [train.py:812] (0/8) Epoch 17, batch 3250, loss[loss=0.178, simple_loss=0.2649, pruned_loss=0.04558, over 7061.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2558, pruned_loss=0.03882, over 1424826.41 frames.], batch size: 18, lr: 4.54e-04
+2022-05-14 20:51:34,396 INFO [train.py:812] (0/8) Epoch 17, batch 3300, loss[loss=0.2163, simple_loss=0.3064, pruned_loss=0.06312, over 7166.00 frames.], tot_loss[loss=0.167, simple_loss=0.2565, pruned_loss=0.03877, over 1425526.11 frames.], batch size: 19, lr: 4.53e-04
+2022-05-14 20:52:33,315 INFO [train.py:812] (0/8) Epoch 17, batch 3350, loss[loss=0.1559, simple_loss=0.2497, pruned_loss=0.03105, over 7336.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2571, pruned_loss=0.03894, over 1426489.77 frames.], batch size: 22, lr: 4.53e-04
+2022-05-14 20:53:32,419 INFO [train.py:812] (0/8) Epoch 17, batch 3400, loss[loss=0.1475, simple_loss=0.2414, pruned_loss=0.02681, over 7155.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2563, pruned_loss=0.03868, over 1422621.89 frames.], batch size: 20, lr: 4.53e-04
+2022-05-14 20:54:31,753 INFO [train.py:812] (0/8) Epoch 17, batch 3450, loss[loss=0.1624, simple_loss=0.2498, pruned_loss=0.03748, over 7327.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2548, pruned_loss=0.03821, over 1424009.06 frames.], batch size: 20, lr: 4.53e-04
+2022-05-14 20:55:30,347 INFO [train.py:812] (0/8) Epoch 17, batch 3500, loss[loss=0.1899, simple_loss=0.2851, pruned_loss=0.0473, over 7212.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2548, pruned_loss=0.03815, over 1423619.97 frames.], batch size: 22, lr: 4.53e-04
+2022-05-14 20:56:29,300 INFO [train.py:812] (0/8) Epoch 17, batch 3550, loss[loss=0.1757, simple_loss=0.266, pruned_loss=0.04267, over 7127.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2549, pruned_loss=0.03792, over 1425981.08 frames.], batch size: 21, lr: 4.53e-04
+2022-05-14 20:57:28,814 INFO [train.py:812] (0/8) Epoch 17, batch 3600, loss[loss=0.1413, simple_loss=0.2265, pruned_loss=0.02799, over 7291.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2551, pruned_loss=0.0379, over 1427374.17 frames.], batch size: 18, lr: 4.52e-04
+2022-05-14 20:58:27,774 INFO [train.py:812] (0/8) Epoch 17, batch 3650, loss[loss=0.1633, simple_loss=0.2602, pruned_loss=0.03321, over 7325.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2549, pruned_loss=0.03807, over 1430658.99 frames.], batch size: 21, lr: 4.52e-04
+2022-05-14 20:59:27,708 INFO [train.py:812] (0/8) Epoch 17, batch 3700, loss[loss=0.1666, simple_loss=0.2604, pruned_loss=0.03639, over 7141.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2556, pruned_loss=0.03834, over 1430378.44 frames.], batch size: 20, lr: 4.52e-04
+2022-05-14 21:00:26,358 INFO [train.py:812] (0/8) Epoch 17, batch 3750, loss[loss=0.1702, simple_loss=0.2649, pruned_loss=0.03772, over 6293.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2557, pruned_loss=0.03849, over 1427689.21 frames.], batch size: 37, lr: 4.52e-04
+2022-05-14 21:01:24,385 INFO [train.py:812] (0/8) Epoch 17, batch 3800, loss[loss=0.1565, simple_loss=0.2392, pruned_loss=0.0369, over 6435.00 frames.], tot_loss[loss=0.1653, simple_loss=0.255, pruned_loss=0.03783, over 1426097.62 frames.], batch size: 38, lr: 4.52e-04
+2022-05-14 21:02:23,091 INFO [train.py:812] (0/8) Epoch 17, batch 3850, loss[loss=0.1617, simple_loss=0.2437, pruned_loss=0.03981, over 7014.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2551, pruned_loss=0.03771, over 1426034.25 frames.], batch size: 16, lr: 4.52e-04
+2022-05-14 21:03:22,490 INFO [train.py:812] (0/8) Epoch 17, batch 3900, loss[loss=0.197, simple_loss=0.2819, pruned_loss=0.05604, over 7213.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2544, pruned_loss=0.03755, over 1428471.53 frames.], batch size: 22, lr: 4.52e-04
+2022-05-14 21:04:21,557 INFO [train.py:812] (0/8) Epoch 17, batch 3950, loss[loss=0.1732, simple_loss=0.2592, pruned_loss=0.0436, over 7193.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2553, pruned_loss=0.03801, over 1428768.37 frames.], batch size: 23, lr: 4.51e-04
+2022-05-14 21:05:20,840 INFO [train.py:812] (0/8) Epoch 17, batch 4000, loss[loss=0.1389, simple_loss=0.2216, pruned_loss=0.02808, over 7286.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2551, pruned_loss=0.03822, over 1428728.57 frames.], batch size: 18, lr: 4.51e-04
+2022-05-14 21:06:19,997 INFO [train.py:812] (0/8) Epoch 17, batch 4050, loss[loss=0.1898, simple_loss=0.2834, pruned_loss=0.04809, over 6881.00 frames.], tot_loss[loss=0.1656, simple_loss=0.255, pruned_loss=0.03807, over 1426263.88 frames.], batch size: 31, lr: 4.51e-04
+2022-05-14 21:07:19,061 INFO [train.py:812] (0/8) Epoch 17, batch 4100, loss[loss=0.2003, simple_loss=0.2692, pruned_loss=0.06571, over 6347.00 frames.], tot_loss[loss=0.1665, simple_loss=0.256, pruned_loss=0.03849, over 1425596.37 frames.], batch size: 37, lr: 4.51e-04
+2022-05-14 21:08:18,342 INFO [train.py:812] (0/8) Epoch 17, batch 4150, loss[loss=0.1557, simple_loss=0.2277, pruned_loss=0.04184, over 7151.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2552, pruned_loss=0.03854, over 1424043.71 frames.], batch size: 17, lr: 4.51e-04
+2022-05-14 21:09:17,052 INFO [train.py:812] (0/8) Epoch 17, batch 4200, loss[loss=0.1772, simple_loss=0.267, pruned_loss=0.04367, over 7132.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2561, pruned_loss=0.03922, over 1422486.20 frames.], batch size: 26, lr: 4.51e-04
+2022-05-14 21:10:16,287 INFO [train.py:812] (0/8) Epoch 17, batch 4250, loss[loss=0.1701, simple_loss=0.2637, pruned_loss=0.03825, over 7267.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2576, pruned_loss=0.03953, over 1423449.56 frames.], batch size: 18, lr: 4.51e-04
+2022-05-14 21:11:15,335 INFO [train.py:812] (0/8) Epoch 17, batch 4300, loss[loss=0.1763, simple_loss=0.2676, pruned_loss=0.04245, over 7073.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2561, pruned_loss=0.03886, over 1422023.58 frames.], batch size: 18, lr: 4.50e-04
+2022-05-14 21:12:14,020 INFO [train.py:812] (0/8) Epoch 17, batch 4350, loss[loss=0.1418, simple_loss=0.2242, pruned_loss=0.0297, over 7165.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2551, pruned_loss=0.03861, over 1420477.27 frames.], batch size: 18, lr: 4.50e-04
+2022-05-14 21:13:12,855 INFO [train.py:812] (0/8) Epoch 17, batch 4400, loss[loss=0.1756, simple_loss=0.2729, pruned_loss=0.03915, over 7221.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2553, pruned_loss=0.03894, over 1419558.16 frames.], batch size: 21, lr: 4.50e-04
+2022-05-14 21:14:12,277 INFO [train.py:812] (0/8) Epoch 17, batch 4450, loss[loss=0.1575, simple_loss=0.2412, pruned_loss=0.03693, over 7141.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2565, pruned_loss=0.03941, over 1415508.24 frames.], batch size: 17, lr: 4.50e-04
+2022-05-14 21:15:12,248 INFO [train.py:812] (0/8) Epoch 17, batch 4500, loss[loss=0.1548, simple_loss=0.2572, pruned_loss=0.02617, over 7243.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2554, pruned_loss=0.0391, over 1413971.36 frames.], batch size: 20, lr: 4.50e-04
+2022-05-14 21:16:11,612 INFO [train.py:812] (0/8) Epoch 17, batch 4550, loss[loss=0.1988, simple_loss=0.2742, pruned_loss=0.06169, over 4737.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2553, pruned_loss=0.03997, over 1380251.69 frames.], batch size: 52, lr: 4.50e-04
+2022-05-14 21:16:55,097 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-17.pt
+2022-05-14 21:17:18,367 INFO [train.py:812] (0/8) Epoch 18, batch 0, loss[loss=0.1658, simple_loss=0.2597, pruned_loss=0.03597, over 7231.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2597, pruned_loss=0.03597, over 7231.00 frames.], batch size: 20, lr: 4.38e-04
+2022-05-14 21:18:18,230 INFO [train.py:812] (0/8) Epoch 18, batch 50, loss[loss=0.1614, simple_loss=0.2369, pruned_loss=0.04299, over 6990.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2533, pruned_loss=0.0386, over 324444.89 frames.], batch size: 16, lr: 4.38e-04
+2022-05-14 21:19:17,442 INFO [train.py:812] (0/8) Epoch 18, batch 100, loss[loss=0.14, simple_loss=0.2313, pruned_loss=0.02429, over 7161.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2541, pruned_loss=0.03799, over 565528.47 frames.], batch size: 18, lr: 4.37e-04
+2022-05-14 21:20:15,792 INFO [train.py:812] (0/8) Epoch 18, batch 150, loss[loss=0.1638, simple_loss=0.2643, pruned_loss=0.03161, over 7144.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2546, pruned_loss=0.03848, over 752956.63 frames.], batch size: 20, lr: 4.37e-04
+2022-05-14 21:21:13,513 INFO [train.py:812] (0/8) Epoch 18, batch 200, loss[loss=0.1568, simple_loss=0.2433, pruned_loss=0.03518, over 7155.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2557, pruned_loss=0.03849, over 903768.40 frames.], batch size: 18, lr: 4.37e-04
+2022-05-14 21:22:12,909 INFO [train.py:812] (0/8) Epoch 18, batch 250, loss[loss=0.1625, simple_loss=0.2588, pruned_loss=0.03307, over 6720.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2555, pruned_loss=0.03766, over 1021183.24 frames.], batch size: 31, lr: 4.37e-04
+2022-05-14 21:23:11,987 INFO [train.py:812] (0/8) Epoch 18, batch 300, loss[loss=0.1577, simple_loss=0.2477, pruned_loss=0.03387, over 7077.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2553, pruned_loss=0.03807, over 1104906.11 frames.], batch size: 28, lr: 4.37e-04
+2022-05-14 21:24:11,079 INFO [train.py:812] (0/8) Epoch 18, batch 350, loss[loss=0.178, simple_loss=0.2666, pruned_loss=0.04468, over 7342.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2538, pruned_loss=0.03752, over 1173092.82 frames.], batch size: 22, lr: 4.37e-04
+2022-05-14 21:25:08,900 INFO [train.py:812] (0/8) Epoch 18, batch 400, loss[loss=0.1533, simple_loss=0.2342, pruned_loss=0.03622, over 6829.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2554, pruned_loss=0.03785, over 1232909.04 frames.], batch size: 15, lr: 4.37e-04
+2022-05-14 21:26:06,614 INFO [train.py:812] (0/8) Epoch 18, batch 450, loss[loss=0.1527, simple_loss=0.237, pruned_loss=0.03419, over 7208.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2563, pruned_loss=0.03821, over 1276807.70 frames.], batch size: 22, lr: 4.36e-04
+2022-05-14 21:27:06,223 INFO [train.py:812] (0/8) Epoch 18, batch 500, loss[loss=0.1654, simple_loss=0.2616, pruned_loss=0.03461, over 7336.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2563, pruned_loss=0.03863, over 1313573.99 frames.], batch size: 22, lr: 4.36e-04
+2022-05-14 21:28:04,629 INFO [train.py:812] (0/8) Epoch 18, batch 550, loss[loss=0.1374, simple_loss=0.2299, pruned_loss=0.02247, over 7130.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2552, pruned_loss=0.03832, over 1339617.35 frames.], batch size: 17, lr: 4.36e-04
+2022-05-14 21:29:02,260 INFO [train.py:812] (0/8) Epoch 18, batch 600, loss[loss=0.1563, simple_loss=0.2513, pruned_loss=0.03065, over 6577.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2566, pruned_loss=0.03924, over 1357253.44 frames.], batch size: 38, lr: 4.36e-04
+2022-05-14 21:30:01,328 INFO [train.py:812] (0/8) Epoch 18, batch 650, loss[loss=0.1781, simple_loss=0.2673, pruned_loss=0.04448, over 5191.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2563, pruned_loss=0.03876, over 1370000.19 frames.], batch size: 52, lr: 4.36e-04
+2022-05-14 21:30:59,622 INFO [train.py:812] (0/8) Epoch 18, batch 700, loss[loss=0.1718, simple_loss=0.2715, pruned_loss=0.03604, over 7315.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2563, pruned_loss=0.03873, over 1381630.76 frames.], batch size: 21, lr: 4.36e-04
+2022-05-14 21:31:59,625 INFO [train.py:812] (0/8) Epoch 18, batch 750, loss[loss=0.1294, simple_loss=0.222, pruned_loss=0.0184, over 7413.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2547, pruned_loss=0.03827, over 1391294.70 frames.], batch size: 18, lr: 4.36e-04
+2022-05-14 21:32:57,575 INFO [train.py:812] (0/8) Epoch 18, batch 800, loss[loss=0.1711, simple_loss=0.2649, pruned_loss=0.03866, over 7320.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2547, pruned_loss=0.03808, over 1402988.98 frames.], batch size: 21, lr: 4.36e-04
+2022-05-14 21:33:57,266 INFO [train.py:812] (0/8) Epoch 18, batch 850, loss[loss=0.1609, simple_loss=0.2525, pruned_loss=0.03467, over 7411.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2547, pruned_loss=0.03796, over 1406559.97 frames.], batch size: 21, lr: 4.35e-04
+2022-05-14 21:34:56,238 INFO [train.py:812] (0/8) Epoch 18, batch 900, loss[loss=0.1629, simple_loss=0.2551, pruned_loss=0.03533, over 7211.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2564, pruned_loss=0.03826, over 1406539.56 frames.], batch size: 22, lr: 4.35e-04
+2022-05-14 21:35:54,606 INFO [train.py:812] (0/8) Epoch 18, batch 950, loss[loss=0.1431, simple_loss=0.2395, pruned_loss=0.02332, over 7250.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2564, pruned_loss=0.03805, over 1408608.58 frames.], batch size: 19, lr: 4.35e-04
+2022-05-14 21:36:52,336 INFO [train.py:812] (0/8) Epoch 18, batch 1000, loss[loss=0.1693, simple_loss=0.2669, pruned_loss=0.03583, over 7283.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2555, pruned_loss=0.03791, over 1413272.07 frames.], batch size: 24, lr: 4.35e-04
+2022-05-14 21:37:51,919 INFO [train.py:812] (0/8) Epoch 18, batch 1050, loss[loss=0.1617, simple_loss=0.2333, pruned_loss=0.04511, over 7276.00 frames.], tot_loss[loss=0.1658, simple_loss=0.255, pruned_loss=0.03828, over 1416005.08 frames.], batch size: 17, lr: 4.35e-04
+2022-05-14 21:38:50,483 INFO [train.py:812] (0/8) Epoch 18, batch 1100, loss[loss=0.1651, simple_loss=0.2613, pruned_loss=0.03442, over 7297.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2554, pruned_loss=0.03825, over 1419414.32 frames.], batch size: 25, lr: 4.35e-04
+2022-05-14 21:39:48,092 INFO [train.py:812] (0/8) Epoch 18, batch 1150, loss[loss=0.2045, simple_loss=0.289, pruned_loss=0.05997, over 7390.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2547, pruned_loss=0.038, over 1417429.85 frames.], batch size: 23, lr: 4.35e-04
+2022-05-14 21:40:45,341 INFO [train.py:812] (0/8) Epoch 18, batch 1200, loss[loss=0.1819, simple_loss=0.269, pruned_loss=0.04735, over 7284.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2547, pruned_loss=0.03826, over 1414845.18 frames.], batch size: 18, lr: 4.34e-04
+2022-05-14 21:41:44,679 INFO [train.py:812] (0/8) Epoch 18, batch 1250, loss[loss=0.1583, simple_loss=0.2515, pruned_loss=0.03256, over 7424.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2544, pruned_loss=0.03823, over 1416778.39 frames.], batch size: 21, lr: 4.34e-04
+2022-05-14 21:42:42,170 INFO [train.py:812] (0/8) Epoch 18, batch 1300, loss[loss=0.1824, simple_loss=0.2603, pruned_loss=0.0523, over 7182.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2545, pruned_loss=0.03853, over 1417694.86 frames.], batch size: 26, lr: 4.34e-04
+2022-05-14 21:43:41,335 INFO [train.py:812] (0/8) Epoch 18, batch 1350, loss[loss=0.1434, simple_loss=0.2298, pruned_loss=0.02856, over 6996.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2546, pruned_loss=0.03804, over 1420539.80 frames.], batch size: 16, lr: 4.34e-04
+2022-05-14 21:44:39,586 INFO [train.py:812] (0/8) Epoch 18, batch 1400, loss[loss=0.1693, simple_loss=0.2677, pruned_loss=0.03548, over 7121.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2554, pruned_loss=0.03801, over 1422822.86 frames.], batch size: 21, lr: 4.34e-04
+2022-05-14 21:45:38,209 INFO [train.py:812] (0/8) Epoch 18, batch 1450, loss[loss=0.1584, simple_loss=0.2534, pruned_loss=0.03177, over 7139.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2555, pruned_loss=0.03802, over 1421233.35 frames.], batch size: 20, lr: 4.34e-04
+2022-05-14 21:46:36,978 INFO [train.py:812] (0/8) Epoch 18, batch 1500, loss[loss=0.1752, simple_loss=0.2657, pruned_loss=0.04233, over 7320.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2555, pruned_loss=0.03821, over 1412780.82 frames.], batch size: 25, lr: 4.34e-04
+2022-05-14 21:47:35,828 INFO [train.py:812] (0/8) Epoch 18, batch 1550, loss[loss=0.1855, simple_loss=0.2623, pruned_loss=0.0544, over 7149.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2548, pruned_loss=0.03783, over 1420130.23 frames.], batch size: 19, lr: 4.33e-04
+2022-05-14 21:48:33,668 INFO [train.py:812] (0/8) Epoch 18, batch 1600, loss[loss=0.1598, simple_loss=0.2428, pruned_loss=0.03843, over 7427.00 frames.], tot_loss[loss=0.165, simple_loss=0.2546, pruned_loss=0.0377, over 1421483.08 frames.], batch size: 20, lr: 4.33e-04
+2022-05-14 21:49:33,350 INFO [train.py:812] (0/8) Epoch 18, batch 1650, loss[loss=0.1684, simple_loss=0.2444, pruned_loss=0.04621, over 7287.00 frames.], tot_loss[loss=0.1647, simple_loss=0.254, pruned_loss=0.03773, over 1421033.54 frames.], batch size: 17, lr: 4.33e-04
+2022-05-14 21:50:30,810 INFO [train.py:812] (0/8) Epoch 18, batch 1700, loss[loss=0.1322, simple_loss=0.2198, pruned_loss=0.02225, over 7364.00 frames.], tot_loss[loss=0.165, simple_loss=0.2544, pruned_loss=0.03778, over 1423774.14 frames.], batch size: 19, lr: 4.33e-04
+2022-05-14 21:51:29,628 INFO [train.py:812] (0/8) Epoch 18, batch 1750, loss[loss=0.1701, simple_loss=0.2724, pruned_loss=0.03392, over 7322.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2538, pruned_loss=0.03754, over 1424516.73 frames.], batch size: 21, lr: 4.33e-04
+2022-05-14 21:52:27,479 INFO [train.py:812] (0/8) Epoch 18, batch 1800, loss[loss=0.1496, simple_loss=0.2442, pruned_loss=0.02748, over 7233.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2535, pruned_loss=0.03762, over 1428548.37 frames.], batch size: 20, lr: 4.33e-04
+2022-05-14 21:53:27,317 INFO [train.py:812] (0/8) Epoch 18, batch 1850, loss[loss=0.1841, simple_loss=0.2722, pruned_loss=0.04803, over 5268.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2526, pruned_loss=0.03734, over 1426857.18 frames.], batch size: 52, lr: 4.33e-04
+2022-05-14 21:54:25,967 INFO [train.py:812] (0/8) Epoch 18, batch 1900, loss[loss=0.1579, simple_loss=0.2607, pruned_loss=0.02751, over 7324.00 frames.], tot_loss[loss=0.1651, simple_loss=0.255, pruned_loss=0.03764, over 1426914.97 frames.], batch size: 21, lr: 4.33e-04
+2022-05-14 21:55:25,332 INFO [train.py:812] (0/8) Epoch 18, batch 1950, loss[loss=0.1683, simple_loss=0.2606, pruned_loss=0.03804, over 7314.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2559, pruned_loss=0.0382, over 1424354.84 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 21:56:23,561 INFO [train.py:812] (0/8) Epoch 18, batch 2000, loss[loss=0.1854, simple_loss=0.263, pruned_loss=0.0539, over 5031.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2552, pruned_loss=0.03818, over 1425024.19 frames.], batch size: 52, lr: 4.32e-04
+2022-05-14 21:56:27,509 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-80000.pt
+2022-05-14 21:57:27,188 INFO [train.py:812] (0/8) Epoch 18, batch 2050, loss[loss=0.1496, simple_loss=0.2481, pruned_loss=0.02558, over 7116.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2553, pruned_loss=0.03823, over 1420660.70 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 21:58:25,552 INFO [train.py:812] (0/8) Epoch 18, batch 2100, loss[loss=0.1979, simple_loss=0.2988, pruned_loss=0.04852, over 6808.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2553, pruned_loss=0.03819, over 1415591.64 frames.], batch size: 31, lr: 4.32e-04
+2022-05-14 21:59:24,608 INFO [train.py:812] (0/8) Epoch 18, batch 2150, loss[loss=0.1639, simple_loss=0.2676, pruned_loss=0.0301, over 7222.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2556, pruned_loss=0.03796, over 1417493.39 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 22:00:22,623 INFO [train.py:812] (0/8) Epoch 18, batch 2200, loss[loss=0.1401, simple_loss=0.2315, pruned_loss=0.02431, over 6799.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2554, pruned_loss=0.03776, over 1419818.62 frames.], batch size: 15, lr: 4.32e-04
+2022-05-14 22:01:22,061 INFO [train.py:812] (0/8) Epoch 18, batch 2250, loss[loss=0.1298, simple_loss=0.219, pruned_loss=0.02031, over 6991.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2542, pruned_loss=0.0375, over 1423293.22 frames.], batch size: 16, lr: 4.32e-04
+2022-05-14 22:02:21,439 INFO [train.py:812] (0/8) Epoch 18, batch 2300, loss[loss=0.1605, simple_loss=0.2536, pruned_loss=0.0337, over 7149.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2553, pruned_loss=0.03785, over 1425606.81 frames.], batch size: 20, lr: 4.31e-04
+2022-05-14 22:03:21,212 INFO [train.py:812] (0/8) Epoch 18, batch 2350, loss[loss=0.237, simple_loss=0.3202, pruned_loss=0.07692, over 7190.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2546, pruned_loss=0.03777, over 1424735.69 frames.], batch size: 26, lr: 4.31e-04
+2022-05-14 22:04:20,398 INFO [train.py:812] (0/8) Epoch 18, batch 2400, loss[loss=0.1749, simple_loss=0.2564, pruned_loss=0.04667, over 6240.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2548, pruned_loss=0.03799, over 1422406.31 frames.], batch size: 37, lr: 4.31e-04
+2022-05-14 22:05:18,778 INFO [train.py:812] (0/8) Epoch 18, batch 2450, loss[loss=0.1491, simple_loss=0.2371, pruned_loss=0.03053, over 7150.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2549, pruned_loss=0.038, over 1424194.94 frames.], batch size: 19, lr: 4.31e-04
+2022-05-14 22:06:16,640 INFO [train.py:812] (0/8) Epoch 18, batch 2500, loss[loss=0.1492, simple_loss=0.2362, pruned_loss=0.03114, over 7130.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2555, pruned_loss=0.03846, over 1416752.52 frames.], batch size: 21, lr: 4.31e-04
+2022-05-14 22:07:15,279 INFO [train.py:812] (0/8) Epoch 18, batch 2550, loss[loss=0.1571, simple_loss=0.2632, pruned_loss=0.02551, over 7322.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2545, pruned_loss=0.03783, over 1417859.04 frames.], batch size: 21, lr: 4.31e-04
+2022-05-14 22:08:14,571 INFO [train.py:812] (0/8) Epoch 18, batch 2600, loss[loss=0.133, simple_loss=0.2159, pruned_loss=0.02506, over 6749.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03804, over 1417513.49 frames.], batch size: 15, lr: 4.31e-04
+2022-05-14 22:09:14,551 INFO [train.py:812] (0/8) Epoch 18, batch 2650, loss[loss=0.1604, simple_loss=0.2389, pruned_loss=0.04092, over 7361.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2546, pruned_loss=0.03798, over 1418177.73 frames.], batch size: 19, lr: 4.31e-04
+2022-05-14 22:10:13,421 INFO [train.py:812] (0/8) Epoch 18, batch 2700, loss[loss=0.1474, simple_loss=0.2231, pruned_loss=0.03579, over 7279.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2539, pruned_loss=0.03777, over 1417915.32 frames.], batch size: 18, lr: 4.30e-04
+2022-05-14 22:11:12,965 INFO [train.py:812] (0/8) Epoch 18, batch 2750, loss[loss=0.1779, simple_loss=0.2702, pruned_loss=0.04282, over 7143.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2541, pruned_loss=0.03775, over 1416210.59 frames.], batch size: 20, lr: 4.30e-04
+2022-05-14 22:12:10,430 INFO [train.py:812] (0/8) Epoch 18, batch 2800, loss[loss=0.1514, simple_loss=0.2461, pruned_loss=0.02841, over 7321.00 frames.], tot_loss[loss=0.164, simple_loss=0.2534, pruned_loss=0.03725, over 1417012.50 frames.], batch size: 21, lr: 4.30e-04
+2022-05-14 22:13:09,206 INFO [train.py:812] (0/8) Epoch 18, batch 2850, loss[loss=0.165, simple_loss=0.2586, pruned_loss=0.03569, over 7288.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2536, pruned_loss=0.03695, over 1419997.84 frames.], batch size: 25, lr: 4.30e-04
+2022-05-14 22:14:17,876 INFO [train.py:812] (0/8) Epoch 18, batch 2900, loss[loss=0.1886, simple_loss=0.2899, pruned_loss=0.04362, over 7196.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2541, pruned_loss=0.03726, over 1422216.42 frames.], batch size: 22, lr: 4.30e-04
+2022-05-14 22:15:17,296 INFO [train.py:812] (0/8) Epoch 18, batch 2950, loss[loss=0.1703, simple_loss=0.2717, pruned_loss=0.03444, over 6403.00 frames.], tot_loss[loss=0.1639, simple_loss=0.254, pruned_loss=0.03694, over 1419698.34 frames.], batch size: 37, lr: 4.30e-04
+2022-05-14 22:16:16,203 INFO [train.py:812] (0/8) Epoch 18, batch 3000, loss[loss=0.182, simple_loss=0.2827, pruned_loss=0.04067, over 7293.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2533, pruned_loss=0.03649, over 1418783.33 frames.], batch size: 25, lr: 4.30e-04
+2022-05-14 22:16:16,205 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 22:16:23,834 INFO [train.py:841] (0/8) Epoch 18, validation: loss=0.153, simple_loss=0.2523, pruned_loss=0.02686, over 698248.00 frames.
+2022-05-14 22:17:22,909 INFO [train.py:812] (0/8) Epoch 18, batch 3050, loss[loss=0.2231, simple_loss=0.3033, pruned_loss=0.07146, over 7120.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2541, pruned_loss=0.03704, over 1417915.48 frames.], batch size: 21, lr: 4.29e-04
+2022-05-14 22:18:21,145 INFO [train.py:812] (0/8) Epoch 18, batch 3100, loss[loss=0.1506, simple_loss=0.2408, pruned_loss=0.03019, over 7226.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2545, pruned_loss=0.03719, over 1419253.61 frames.], batch size: 20, lr: 4.29e-04
+2022-05-14 22:19:19,575 INFO [train.py:812] (0/8) Epoch 18, batch 3150, loss[loss=0.1495, simple_loss=0.247, pruned_loss=0.02602, over 7262.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2548, pruned_loss=0.03777, over 1421877.58 frames.], batch size: 19, lr: 4.29e-04
+2022-05-14 22:20:18,606 INFO [train.py:812] (0/8) Epoch 18, batch 3200, loss[loss=0.1926, simple_loss=0.2796, pruned_loss=0.05276, over 6787.00 frames.], tot_loss[loss=0.1656, simple_loss=0.255, pruned_loss=0.03809, over 1419675.87 frames.], batch size: 31, lr: 4.29e-04
+2022-05-14 22:21:17,370 INFO [train.py:812] (0/8) Epoch 18, batch 3250, loss[loss=0.1682, simple_loss=0.2584, pruned_loss=0.039, over 7369.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2538, pruned_loss=0.03755, over 1422885.49 frames.], batch size: 23, lr: 4.29e-04
+2022-05-14 22:22:16,102 INFO [train.py:812] (0/8) Epoch 18, batch 3300, loss[loss=0.1438, simple_loss=0.2292, pruned_loss=0.02918, over 7157.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2535, pruned_loss=0.03736, over 1427352.64 frames.], batch size: 18, lr: 4.29e-04
+2022-05-14 22:23:15,285 INFO [train.py:812] (0/8) Epoch 18, batch 3350, loss[loss=0.1653, simple_loss=0.2468, pruned_loss=0.04186, over 7390.00 frames.], tot_loss[loss=0.164, simple_loss=0.2538, pruned_loss=0.03711, over 1427534.86 frames.], batch size: 18, lr: 4.29e-04
+2022-05-14 22:24:13,634 INFO [train.py:812] (0/8) Epoch 18, batch 3400, loss[loss=0.1696, simple_loss=0.2529, pruned_loss=0.04312, over 7371.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2546, pruned_loss=0.03763, over 1430463.50 frames.], batch size: 23, lr: 4.29e-04
+2022-05-14 22:25:13,488 INFO [train.py:812] (0/8) Epoch 18, batch 3450, loss[loss=0.1546, simple_loss=0.2446, pruned_loss=0.03228, over 7408.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2557, pruned_loss=0.03794, over 1430768.51 frames.], batch size: 18, lr: 4.28e-04
+2022-05-14 22:26:12,117 INFO [train.py:812] (0/8) Epoch 18, batch 3500, loss[loss=0.1838, simple_loss=0.2755, pruned_loss=0.04607, over 6371.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2555, pruned_loss=0.03774, over 1433117.52 frames.], batch size: 38, lr: 4.28e-04
+2022-05-14 22:27:09,544 INFO [train.py:812] (0/8) Epoch 18, batch 3550, loss[loss=0.1826, simple_loss=0.2684, pruned_loss=0.04834, over 7199.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2558, pruned_loss=0.03787, over 1431561.23 frames.], batch size: 23, lr: 4.28e-04
+2022-05-14 22:28:09,171 INFO [train.py:812] (0/8) Epoch 18, batch 3600, loss[loss=0.1974, simple_loss=0.289, pruned_loss=0.0529, over 7222.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2563, pruned_loss=0.0384, over 1432624.33 frames.], batch size: 21, lr: 4.28e-04
+2022-05-14 22:29:07,999 INFO [train.py:812] (0/8) Epoch 18, batch 3650, loss[loss=0.1747, simple_loss=0.2698, pruned_loss=0.03981, over 7333.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2558, pruned_loss=0.03831, over 1424301.93 frames.], batch size: 22, lr: 4.28e-04
+2022-05-14 22:30:06,439 INFO [train.py:812] (0/8) Epoch 18, batch 3700, loss[loss=0.127, simple_loss=0.2119, pruned_loss=0.02102, over 7000.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2555, pruned_loss=0.0379, over 1425357.93 frames.], batch size: 16, lr: 4.28e-04
+2022-05-14 22:31:03,707 INFO [train.py:812] (0/8) Epoch 18, batch 3750, loss[loss=0.179, simple_loss=0.2703, pruned_loss=0.04384, over 7290.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2557, pruned_loss=0.03785, over 1427107.68 frames.], batch size: 25, lr: 4.28e-04
+2022-05-14 22:32:02,180 INFO [train.py:812] (0/8) Epoch 18, batch 3800, loss[loss=0.1837, simple_loss=0.2761, pruned_loss=0.04568, over 7359.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2556, pruned_loss=0.03798, over 1427437.99 frames.], batch size: 19, lr: 4.28e-04
+2022-05-14 22:33:01,937 INFO [train.py:812] (0/8) Epoch 18, batch 3850, loss[loss=0.1464, simple_loss=0.2456, pruned_loss=0.02356, over 7402.00 frames.], tot_loss[loss=0.165, simple_loss=0.2549, pruned_loss=0.0375, over 1426253.77 frames.], batch size: 18, lr: 4.27e-04
+2022-05-14 22:34:01,051 INFO [train.py:812] (0/8) Epoch 18, batch 3900, loss[loss=0.1375, simple_loss=0.2316, pruned_loss=0.02167, over 7114.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2549, pruned_loss=0.0377, over 1421402.46 frames.], batch size: 21, lr: 4.27e-04
+2022-05-14 22:35:00,748 INFO [train.py:812] (0/8) Epoch 18, batch 3950, loss[loss=0.1688, simple_loss=0.2604, pruned_loss=0.03855, over 7054.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2548, pruned_loss=0.03794, over 1422547.36 frames.], batch size: 28, lr: 4.27e-04
+2022-05-14 22:35:58,138 INFO [train.py:812] (0/8) Epoch 18, batch 4000, loss[loss=0.1455, simple_loss=0.2386, pruned_loss=0.02619, over 6818.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2554, pruned_loss=0.03846, over 1423676.96 frames.], batch size: 15, lr: 4.27e-04
+2022-05-14 22:36:56,609 INFO [train.py:812] (0/8) Epoch 18, batch 4050, loss[loss=0.1668, simple_loss=0.2675, pruned_loss=0.03305, over 7055.00 frames.], tot_loss[loss=0.166, simple_loss=0.2555, pruned_loss=0.0383, over 1427176.87 frames.], batch size: 28, lr: 4.27e-04
+2022-05-14 22:37:55,335 INFO [train.py:812] (0/8) Epoch 18, batch 4100, loss[loss=0.1598, simple_loss=0.2591, pruned_loss=0.03024, over 7147.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2549, pruned_loss=0.03812, over 1424034.33 frames.], batch size: 20, lr: 4.27e-04
+2022-05-14 22:38:54,559 INFO [train.py:812] (0/8) Epoch 18, batch 4150, loss[loss=0.1608, simple_loss=0.2508, pruned_loss=0.03534, over 7329.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2548, pruned_loss=0.03798, over 1423577.37 frames.], batch size: 20, lr: 4.27e-04
+2022-05-14 22:39:53,787 INFO [train.py:812] (0/8) Epoch 18, batch 4200, loss[loss=0.1356, simple_loss=0.2246, pruned_loss=0.02332, over 6993.00 frames.], tot_loss[loss=0.1646, simple_loss=0.254, pruned_loss=0.03756, over 1423095.72 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:40:53,138 INFO [train.py:812] (0/8) Epoch 18, batch 4250, loss[loss=0.1876, simple_loss=0.2724, pruned_loss=0.05142, over 6756.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2538, pruned_loss=0.03757, over 1417798.39 frames.], batch size: 31, lr: 4.26e-04
+2022-05-14 22:41:52,048 INFO [train.py:812] (0/8) Epoch 18, batch 4300, loss[loss=0.1381, simple_loss=0.2214, pruned_loss=0.0274, over 7008.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2526, pruned_loss=0.03721, over 1418663.08 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:42:51,531 INFO [train.py:812] (0/8) Epoch 18, batch 4350, loss[loss=0.1689, simple_loss=0.2617, pruned_loss=0.03808, over 7227.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2533, pruned_loss=0.03791, over 1405952.33 frames.], batch size: 21, lr: 4.26e-04
+2022-05-14 22:43:50,334 INFO [train.py:812] (0/8) Epoch 18, batch 4400, loss[loss=0.1509, simple_loss=0.2468, pruned_loss=0.02748, over 7072.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2546, pruned_loss=0.03843, over 1399834.42 frames.], batch size: 18, lr: 4.26e-04
+2022-05-14 22:44:47,957 INFO [train.py:812] (0/8) Epoch 18, batch 4450, loss[loss=0.1586, simple_loss=0.2553, pruned_loss=0.03096, over 6518.00 frames.], tot_loss[loss=0.167, simple_loss=0.2558, pruned_loss=0.03911, over 1391693.50 frames.], batch size: 38, lr: 4.26e-04
+2022-05-14 22:45:55,864 INFO [train.py:812] (0/8) Epoch 18, batch 4500, loss[loss=0.1347, simple_loss=0.2173, pruned_loss=0.02609, over 7021.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2568, pruned_loss=0.03928, over 1379031.62 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:46:55,057 INFO [train.py:812] (0/8) Epoch 18, batch 4550, loss[loss=0.1686, simple_loss=0.2655, pruned_loss=0.03587, over 7167.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2563, pruned_loss=0.03921, over 1368128.36 frames.], batch size: 19, lr: 4.26e-04
+2022-05-14 22:47:39,661 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-18.pt
+2022-05-14 22:48:10,146 INFO [train.py:812] (0/8) Epoch 19, batch 0, loss[loss=0.1863, simple_loss=0.2761, pruned_loss=0.04824, over 7337.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2761, pruned_loss=0.04824, over 7337.00 frames.], batch size: 25, lr: 4.15e-04
+2022-05-14 22:49:27,399 INFO [train.py:812] (0/8) Epoch 19, batch 50, loss[loss=0.1739, simple_loss=0.2773, pruned_loss=0.0352, over 7333.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2569, pruned_loss=0.03915, over 325386.02 frames.], batch size: 22, lr: 4.15e-04
+2022-05-14 22:50:35,552 INFO [train.py:812] (0/8) Epoch 19, batch 100, loss[loss=0.1716, simple_loss=0.2627, pruned_loss=0.0403, over 7333.00 frames.], tot_loss[loss=0.164, simple_loss=0.254, pruned_loss=0.03699, over 574894.93 frames.], batch size: 22, lr: 4.14e-04
+2022-05-14 22:51:34,865 INFO [train.py:812] (0/8) Epoch 19, batch 150, loss[loss=0.1822, simple_loss=0.2823, pruned_loss=0.04101, over 7220.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2529, pruned_loss=0.0368, over 764449.21 frames.], batch size: 21, lr: 4.14e-04
+2022-05-14 22:53:02,396 INFO [train.py:812] (0/8) Epoch 19, batch 200, loss[loss=0.1552, simple_loss=0.2388, pruned_loss=0.03581, over 7283.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2535, pruned_loss=0.03719, over 909618.18 frames.], batch size: 17, lr: 4.14e-04
+2022-05-14 22:54:01,872 INFO [train.py:812] (0/8) Epoch 19, batch 250, loss[loss=0.1549, simple_loss=0.2486, pruned_loss=0.03056, over 6716.00 frames.], tot_loss[loss=0.164, simple_loss=0.2533, pruned_loss=0.03733, over 1024550.79 frames.], batch size: 31, lr: 4.14e-04
+2022-05-14 22:55:01,090 INFO [train.py:812] (0/8) Epoch 19, batch 300, loss[loss=0.1597, simple_loss=0.2511, pruned_loss=0.03414, over 7233.00 frames.], tot_loss[loss=0.1642, simple_loss=0.254, pruned_loss=0.03722, over 1115350.43 frames.], batch size: 20, lr: 4.14e-04
+2022-05-14 22:56:00,987 INFO [train.py:812] (0/8) Epoch 19, batch 350, loss[loss=0.1589, simple_loss=0.2513, pruned_loss=0.03326, over 6695.00 frames.], tot_loss[loss=0.1631, simple_loss=0.253, pruned_loss=0.03666, over 1181460.98 frames.], batch size: 31, lr: 4.14e-04
+2022-05-14 22:56:59,182 INFO [train.py:812] (0/8) Epoch 19, batch 400, loss[loss=0.1643, simple_loss=0.2507, pruned_loss=0.03892, over 7067.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2543, pruned_loss=0.03751, over 1232339.95 frames.], batch size: 18, lr: 4.14e-04
+2022-05-14 22:57:58,714 INFO [train.py:812] (0/8) Epoch 19, batch 450, loss[loss=0.1778, simple_loss=0.2716, pruned_loss=0.04206, over 7342.00 frames.], tot_loss[loss=0.165, simple_loss=0.2547, pruned_loss=0.03763, over 1274207.23 frames.], batch size: 22, lr: 4.14e-04
+2022-05-14 22:58:57,677 INFO [train.py:812] (0/8) Epoch 19, batch 500, loss[loss=0.1337, simple_loss=0.216, pruned_loss=0.02573, over 7147.00 frames.], tot_loss[loss=0.1651, simple_loss=0.255, pruned_loss=0.03756, over 1305202.53 frames.], batch size: 17, lr: 4.13e-04
+2022-05-14 22:59:57,549 INFO [train.py:812] (0/8) Epoch 19, batch 550, loss[loss=0.1625, simple_loss=0.2471, pruned_loss=0.0389, over 7288.00 frames.], tot_loss[loss=0.1642, simple_loss=0.254, pruned_loss=0.03722, over 1335817.32 frames.], batch size: 17, lr: 4.13e-04
+2022-05-14 23:00:56,149 INFO [train.py:812] (0/8) Epoch 19, batch 600, loss[loss=0.1524, simple_loss=0.2413, pruned_loss=0.03169, over 7267.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2534, pruned_loss=0.03714, over 1356411.57 frames.], batch size: 18, lr: 4.13e-04
+2022-05-14 23:01:55,607 INFO [train.py:812] (0/8) Epoch 19, batch 650, loss[loss=0.1774, simple_loss=0.2797, pruned_loss=0.03754, over 7434.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2528, pruned_loss=0.03672, over 1375598.06 frames.], batch size: 22, lr: 4.13e-04
+2022-05-14 23:02:54,270 INFO [train.py:812] (0/8) Epoch 19, batch 700, loss[loss=0.1959, simple_loss=0.2867, pruned_loss=0.0525, over 5111.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2533, pruned_loss=0.03676, over 1385835.50 frames.], batch size: 53, lr: 4.13e-04
+2022-05-14 23:03:53,342 INFO [train.py:812] (0/8) Epoch 19, batch 750, loss[loss=0.152, simple_loss=0.2403, pruned_loss=0.03183, over 7163.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2534, pruned_loss=0.0369, over 1394331.34 frames.], batch size: 19, lr: 4.13e-04
+2022-05-14 23:04:52,301 INFO [train.py:812] (0/8) Epoch 19, batch 800, loss[loss=0.1751, simple_loss=0.2702, pruned_loss=0.04003, over 6739.00 frames.], tot_loss[loss=0.164, simple_loss=0.254, pruned_loss=0.037, over 1397139.86 frames.], batch size: 31, lr: 4.13e-04
+2022-05-14 23:05:50,866 INFO [train.py:812] (0/8) Epoch 19, batch 850, loss[loss=0.1543, simple_loss=0.2386, pruned_loss=0.03494, over 7060.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2543, pruned_loss=0.03711, over 1404658.41 frames.], batch size: 18, lr: 4.13e-04
+2022-05-14 23:06:49,945 INFO [train.py:812] (0/8) Epoch 19, batch 900, loss[loss=0.1386, simple_loss=0.2261, pruned_loss=0.02562, over 6828.00 frames.], tot_loss[loss=0.165, simple_loss=0.255, pruned_loss=0.03743, over 1410225.77 frames.], batch size: 15, lr: 4.12e-04
+2022-05-14 23:07:49,372 INFO [train.py:812] (0/8) Epoch 19, batch 950, loss[loss=0.1781, simple_loss=0.2643, pruned_loss=0.04591, over 7385.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2546, pruned_loss=0.03709, over 1413659.48 frames.], batch size: 23, lr: 4.12e-04
+2022-05-14 23:08:48,627 INFO [train.py:812] (0/8) Epoch 19, batch 1000, loss[loss=0.1474, simple_loss=0.2437, pruned_loss=0.02558, over 7142.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2545, pruned_loss=0.03664, over 1420049.81 frames.], batch size: 20, lr: 4.12e-04
+2022-05-14 23:09:47,736 INFO [train.py:812] (0/8) Epoch 19, batch 1050, loss[loss=0.1861, simple_loss=0.2763, pruned_loss=0.04791, over 7302.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2544, pruned_loss=0.03717, over 1417353.64 frames.], batch size: 25, lr: 4.12e-04
+2022-05-14 23:10:45,901 INFO [train.py:812] (0/8) Epoch 19, batch 1100, loss[loss=0.1579, simple_loss=0.2537, pruned_loss=0.03106, over 7326.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2536, pruned_loss=0.03698, over 1418122.20 frames.], batch size: 20, lr: 4.12e-04
+2022-05-14 23:11:43,629 INFO [train.py:812] (0/8) Epoch 19, batch 1150, loss[loss=0.1708, simple_loss=0.2607, pruned_loss=0.04045, over 7278.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2539, pruned_loss=0.03693, over 1419005.67 frames.], batch size: 24, lr: 4.12e-04
+2022-05-14 23:12:42,332 INFO [train.py:812] (0/8) Epoch 19, batch 1200, loss[loss=0.1949, simple_loss=0.2769, pruned_loss=0.05641, over 4968.00 frames.], tot_loss[loss=0.1641, simple_loss=0.254, pruned_loss=0.03706, over 1414075.47 frames.], batch size: 53, lr: 4.12e-04
+2022-05-14 23:13:40,372 INFO [train.py:812] (0/8) Epoch 19, batch 1250, loss[loss=0.1559, simple_loss=0.2605, pruned_loss=0.02565, over 7112.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2536, pruned_loss=0.03681, over 1414620.97 frames.], batch size: 21, lr: 4.12e-04
+2022-05-14 23:14:39,566 INFO [train.py:812] (0/8) Epoch 19, batch 1300, loss[loss=0.1704, simple_loss=0.2513, pruned_loss=0.04477, over 7161.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2545, pruned_loss=0.03714, over 1413101.67 frames.], batch size: 19, lr: 4.12e-04
+2022-05-14 23:15:38,785 INFO [train.py:812] (0/8) Epoch 19, batch 1350, loss[loss=0.176, simple_loss=0.263, pruned_loss=0.04453, over 7010.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2553, pruned_loss=0.03758, over 1411587.28 frames.], batch size: 28, lr: 4.11e-04
+2022-05-14 23:16:38,069 INFO [train.py:812] (0/8) Epoch 19, batch 1400, loss[loss=0.1522, simple_loss=0.2407, pruned_loss=0.0318, over 7064.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2542, pruned_loss=0.0374, over 1409858.17 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:16:56,459 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-84000.pt
+2022-05-14 23:17:42,355 INFO [train.py:812] (0/8) Epoch 19, batch 1450, loss[loss=0.1687, simple_loss=0.2552, pruned_loss=0.0411, over 7333.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2536, pruned_loss=0.03749, over 1417154.65 frames.], batch size: 21, lr: 4.11e-04
+2022-05-14 23:18:41,292 INFO [train.py:812] (0/8) Epoch 19, batch 1500, loss[loss=0.1443, simple_loss=0.2409, pruned_loss=0.02385, over 7268.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2545, pruned_loss=0.03762, over 1420653.02 frames.], batch size: 19, lr: 4.11e-04
+2022-05-14 23:19:40,512 INFO [train.py:812] (0/8) Epoch 19, batch 1550, loss[loss=0.1628, simple_loss=0.257, pruned_loss=0.03432, over 7416.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2542, pruned_loss=0.03765, over 1424152.76 frames.], batch size: 21, lr: 4.11e-04
+2022-05-14 23:20:39,972 INFO [train.py:812] (0/8) Epoch 19, batch 1600, loss[loss=0.1598, simple_loss=0.2542, pruned_loss=0.03271, over 7216.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2538, pruned_loss=0.03747, over 1423376.28 frames.], batch size: 22, lr: 4.11e-04
+2022-05-14 23:21:39,584 INFO [train.py:812] (0/8) Epoch 19, batch 1650, loss[loss=0.164, simple_loss=0.2437, pruned_loss=0.0421, over 7168.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2539, pruned_loss=0.0375, over 1422647.45 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:22:38,866 INFO [train.py:812] (0/8) Epoch 19, batch 1700, loss[loss=0.1552, simple_loss=0.2375, pruned_loss=0.03641, over 7156.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2545, pruned_loss=0.0379, over 1423703.15 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:23:37,791 INFO [train.py:812] (0/8) Epoch 19, batch 1750, loss[loss=0.1731, simple_loss=0.2645, pruned_loss=0.04084, over 7142.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2553, pruned_loss=0.03786, over 1416592.89 frames.], batch size: 20, lr: 4.10e-04
+2022-05-14 23:24:36,415 INFO [train.py:812] (0/8) Epoch 19, batch 1800, loss[loss=0.1781, simple_loss=0.2677, pruned_loss=0.04418, over 7253.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2559, pruned_loss=0.03766, over 1417162.38 frames.], batch size: 19, lr: 4.10e-04
+2022-05-14 23:25:35,719 INFO [train.py:812] (0/8) Epoch 19, batch 1850, loss[loss=0.1746, simple_loss=0.2719, pruned_loss=0.03866, over 7325.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2558, pruned_loss=0.03725, over 1422953.34 frames.], batch size: 24, lr: 4.10e-04
+2022-05-14 23:26:34,570 INFO [train.py:812] (0/8) Epoch 19, batch 1900, loss[loss=0.167, simple_loss=0.2586, pruned_loss=0.03769, over 7065.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2563, pruned_loss=0.0378, over 1419820.43 frames.], batch size: 28, lr: 4.10e-04
+2022-05-14 23:27:34,101 INFO [train.py:812] (0/8) Epoch 19, batch 1950, loss[loss=0.1393, simple_loss=0.2233, pruned_loss=0.02771, over 6995.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2561, pruned_loss=0.03762, over 1421047.43 frames.], batch size: 16, lr: 4.10e-04
+2022-05-14 23:28:32,969 INFO [train.py:812] (0/8) Epoch 19, batch 2000, loss[loss=0.1811, simple_loss=0.283, pruned_loss=0.03959, over 7141.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2557, pruned_loss=0.03748, over 1424087.14 frames.], batch size: 20, lr: 4.10e-04
+2022-05-14 23:29:32,752 INFO [train.py:812] (0/8) Epoch 19, batch 2050, loss[loss=0.174, simple_loss=0.2689, pruned_loss=0.03952, over 7315.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2548, pruned_loss=0.03747, over 1423608.88 frames.], batch size: 25, lr: 4.10e-04
+2022-05-14 23:30:30,657 INFO [train.py:812] (0/8) Epoch 19, batch 2100, loss[loss=0.162, simple_loss=0.2515, pruned_loss=0.03626, over 7150.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2543, pruned_loss=0.03719, over 1424720.24 frames.], batch size: 19, lr: 4.10e-04
+2022-05-14 23:31:30,574 INFO [train.py:812] (0/8) Epoch 19, batch 2150, loss[loss=0.1583, simple_loss=0.2493, pruned_loss=0.03364, over 7211.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2538, pruned_loss=0.03717, over 1421121.19 frames.], batch size: 21, lr: 4.09e-04
+2022-05-14 23:32:30,024 INFO [train.py:812] (0/8) Epoch 19, batch 2200, loss[loss=0.1837, simple_loss=0.2808, pruned_loss=0.04325, over 7105.00 frames.], tot_loss[loss=0.1631, simple_loss=0.253, pruned_loss=0.03654, over 1425052.34 frames.], batch size: 21, lr: 4.09e-04
+2022-05-14 23:33:29,355 INFO [train.py:812] (0/8) Epoch 19, batch 2250, loss[loss=0.1803, simple_loss=0.2695, pruned_loss=0.04559, over 6650.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2531, pruned_loss=0.03668, over 1424655.77 frames.], batch size: 38, lr: 4.09e-04
+2022-05-14 23:34:27,802 INFO [train.py:812] (0/8) Epoch 19, batch 2300, loss[loss=0.1776, simple_loss=0.2601, pruned_loss=0.04751, over 7389.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2525, pruned_loss=0.03655, over 1425894.71 frames.], batch size: 23, lr: 4.09e-04
+2022-05-14 23:35:26,031 INFO [train.py:812] (0/8) Epoch 19, batch 2350, loss[loss=0.1475, simple_loss=0.2299, pruned_loss=0.03256, over 7271.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2525, pruned_loss=0.03629, over 1422827.30 frames.], batch size: 17, lr: 4.09e-04
+2022-05-14 23:36:25,343 INFO [train.py:812] (0/8) Epoch 19, batch 2400, loss[loss=0.177, simple_loss=0.2579, pruned_loss=0.04809, over 7140.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2528, pruned_loss=0.03676, over 1418929.98 frames.], batch size: 20, lr: 4.09e-04
+2022-05-14 23:37:24,205 INFO [train.py:812] (0/8) Epoch 19, batch 2450, loss[loss=0.2047, simple_loss=0.2957, pruned_loss=0.05686, over 7151.00 frames.], tot_loss[loss=0.163, simple_loss=0.2527, pruned_loss=0.03663, over 1422572.70 frames.], batch size: 20, lr: 4.09e-04
+2022-05-14 23:38:23,515 INFO [train.py:812] (0/8) Epoch 19, batch 2500, loss[loss=0.1805, simple_loss=0.2807, pruned_loss=0.04013, over 7192.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2526, pruned_loss=0.03686, over 1421991.06 frames.], batch size: 26, lr: 4.09e-04
+2022-05-14 23:39:22,982 INFO [train.py:812] (0/8) Epoch 19, batch 2550, loss[loss=0.2214, simple_loss=0.3114, pruned_loss=0.06568, over 7279.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2526, pruned_loss=0.03694, over 1422096.96 frames.], batch size: 24, lr: 4.08e-04
+2022-05-14 23:40:21,748 INFO [train.py:812] (0/8) Epoch 19, batch 2600, loss[loss=0.1212, simple_loss=0.2086, pruned_loss=0.01692, over 6991.00 frames.], tot_loss[loss=0.1643, simple_loss=0.254, pruned_loss=0.03726, over 1425746.31 frames.], batch size: 16, lr: 4.08e-04
+2022-05-14 23:41:20,978 INFO [train.py:812] (0/8) Epoch 19, batch 2650, loss[loss=0.1917, simple_loss=0.2795, pruned_loss=0.052, over 7283.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2538, pruned_loss=0.03687, over 1427266.20 frames.], batch size: 24, lr: 4.08e-04
+2022-05-14 23:42:20,838 INFO [train.py:812] (0/8) Epoch 19, batch 2700, loss[loss=0.183, simple_loss=0.2706, pruned_loss=0.04773, over 7321.00 frames.], tot_loss[loss=0.1629, simple_loss=0.253, pruned_loss=0.03643, over 1431018.79 frames.], batch size: 25, lr: 4.08e-04
+2022-05-14 23:43:20,347 INFO [train.py:812] (0/8) Epoch 19, batch 2750, loss[loss=0.1642, simple_loss=0.2512, pruned_loss=0.03858, over 7412.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2534, pruned_loss=0.03644, over 1430084.86 frames.], batch size: 21, lr: 4.08e-04
+2022-05-14 23:44:19,808 INFO [train.py:812] (0/8) Epoch 19, batch 2800, loss[loss=0.1669, simple_loss=0.2487, pruned_loss=0.0425, over 7072.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2536, pruned_loss=0.03654, over 1430550.71 frames.], batch size: 18, lr: 4.08e-04
+2022-05-14 23:45:18,697 INFO [train.py:812] (0/8) Epoch 19, batch 2850, loss[loss=0.1629, simple_loss=0.2554, pruned_loss=0.03522, over 7157.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2541, pruned_loss=0.03685, over 1427448.42 frames.], batch size: 19, lr: 4.08e-04
+2022-05-14 23:46:17,156 INFO [train.py:812] (0/8) Epoch 19, batch 2900, loss[loss=0.1736, simple_loss=0.2642, pruned_loss=0.04151, over 7117.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2538, pruned_loss=0.03689, over 1424925.21 frames.], batch size: 26, lr: 4.08e-04
+2022-05-14 23:47:15,876 INFO [train.py:812] (0/8) Epoch 19, batch 2950, loss[loss=0.1616, simple_loss=0.2411, pruned_loss=0.04101, over 7274.00 frames.], tot_loss[loss=0.1637, simple_loss=0.254, pruned_loss=0.03671, over 1430429.27 frames.], batch size: 17, lr: 4.08e-04
+2022-05-14 23:48:15,180 INFO [train.py:812] (0/8) Epoch 19, batch 3000, loss[loss=0.2263, simple_loss=0.2989, pruned_loss=0.07688, over 5090.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2537, pruned_loss=0.03671, over 1430184.30 frames.], batch size: 53, lr: 4.07e-04
+2022-05-14 23:48:15,182 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-14 23:48:22,684 INFO [train.py:841] (0/8) Epoch 19, validation: loss=0.1531, simple_loss=0.2523, pruned_loss=0.02694, over 698248.00 frames.
+2022-05-14 23:49:22,461 INFO [train.py:812] (0/8) Epoch 19, batch 3050, loss[loss=0.1993, simple_loss=0.2831, pruned_loss=0.05777, over 7176.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2543, pruned_loss=0.03664, over 1430557.81 frames.], batch size: 23, lr: 4.07e-04
+2022-05-14 23:50:21,425 INFO [train.py:812] (0/8) Epoch 19, batch 3100, loss[loss=0.2136, simple_loss=0.2955, pruned_loss=0.06585, over 6456.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2539, pruned_loss=0.03651, over 1432149.73 frames.], batch size: 38, lr: 4.07e-04
+2022-05-14 23:51:20,047 INFO [train.py:812] (0/8) Epoch 19, batch 3150, loss[loss=0.1755, simple_loss=0.2546, pruned_loss=0.0482, over 7274.00 frames.], tot_loss[loss=0.1649, simple_loss=0.255, pruned_loss=0.03746, over 1429105.61 frames.], batch size: 18, lr: 4.07e-04
+2022-05-14 23:52:18,560 INFO [train.py:812] (0/8) Epoch 19, batch 3200, loss[loss=0.1569, simple_loss=0.2455, pruned_loss=0.03412, over 7162.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2545, pruned_loss=0.03702, over 1427808.16 frames.], batch size: 19, lr: 4.07e-04
+2022-05-14 23:53:18,083 INFO [train.py:812] (0/8) Epoch 19, batch 3250, loss[loss=0.1532, simple_loss=0.2364, pruned_loss=0.03502, over 7355.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2553, pruned_loss=0.03707, over 1425465.38 frames.], batch size: 19, lr: 4.07e-04
+2022-05-14 23:54:16,325 INFO [train.py:812] (0/8) Epoch 19, batch 3300, loss[loss=0.1501, simple_loss=0.2459, pruned_loss=0.02712, over 6468.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2554, pruned_loss=0.0369, over 1425502.48 frames.], batch size: 38, lr: 4.07e-04
+2022-05-14 23:55:15,390 INFO [train.py:812] (0/8) Epoch 19, batch 3350, loss[loss=0.1611, simple_loss=0.2559, pruned_loss=0.03319, over 7121.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2547, pruned_loss=0.0369, over 1424294.04 frames.], batch size: 21, lr: 4.07e-04
+2022-05-14 23:56:14,420 INFO [train.py:812] (0/8) Epoch 19, batch 3400, loss[loss=0.1392, simple_loss=0.2295, pruned_loss=0.02446, over 7282.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2544, pruned_loss=0.03661, over 1425099.39 frames.], batch size: 18, lr: 4.06e-04
+2022-05-14 23:57:14,013 INFO [train.py:812] (0/8) Epoch 19, batch 3450, loss[loss=0.1495, simple_loss=0.2357, pruned_loss=0.03165, over 7356.00 frames.], tot_loss[loss=0.1627, simple_loss=0.253, pruned_loss=0.03624, over 1421444.02 frames.], batch size: 19, lr: 4.06e-04
+2022-05-14 23:58:13,010 INFO [train.py:812] (0/8) Epoch 19, batch 3500, loss[loss=0.1553, simple_loss=0.2404, pruned_loss=0.03511, over 7269.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2524, pruned_loss=0.03587, over 1423843.96 frames.], batch size: 18, lr: 4.06e-04
+2022-05-14 23:59:12,605 INFO [train.py:812] (0/8) Epoch 19, batch 3550, loss[loss=0.1517, simple_loss=0.2307, pruned_loss=0.03634, over 7158.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2523, pruned_loss=0.03594, over 1422972.93 frames.], batch size: 17, lr: 4.06e-04
+2022-05-15 00:00:11,600 INFO [train.py:812] (0/8) Epoch 19, batch 3600, loss[loss=0.2255, simple_loss=0.3059, pruned_loss=0.07254, over 7203.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2529, pruned_loss=0.03628, over 1421141.30 frames.], batch size: 23, lr: 4.06e-04
+2022-05-15 00:01:10,994 INFO [train.py:812] (0/8) Epoch 19, batch 3650, loss[loss=0.1745, simple_loss=0.2658, pruned_loss=0.04154, over 7327.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2533, pruned_loss=0.03659, over 1414834.48 frames.], batch size: 20, lr: 4.06e-04
+2022-05-15 00:02:10,009 INFO [train.py:812] (0/8) Epoch 19, batch 3700, loss[loss=0.1674, simple_loss=0.2658, pruned_loss=0.03451, over 7412.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2544, pruned_loss=0.03738, over 1417614.34 frames.], batch size: 21, lr: 4.06e-04
+2022-05-15 00:03:09,416 INFO [train.py:812] (0/8) Epoch 19, batch 3750, loss[loss=0.1827, simple_loss=0.2693, pruned_loss=0.04811, over 7393.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2542, pruned_loss=0.0376, over 1414111.46 frames.], batch size: 23, lr: 4.06e-04
+2022-05-15 00:04:08,150 INFO [train.py:812] (0/8) Epoch 19, batch 3800, loss[loss=0.1801, simple_loss=0.2619, pruned_loss=0.04918, over 7356.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2546, pruned_loss=0.03738, over 1419435.24 frames.], batch size: 19, lr: 4.06e-04
+2022-05-15 00:05:06,753 INFO [train.py:812] (0/8) Epoch 19, batch 3850, loss[loss=0.1337, simple_loss=0.2144, pruned_loss=0.02646, over 7168.00 frames.], tot_loss[loss=0.165, simple_loss=0.2547, pruned_loss=0.03763, over 1416586.33 frames.], batch size: 18, lr: 4.05e-04
+2022-05-15 00:06:04,371 INFO [train.py:812] (0/8) Epoch 19, batch 3900, loss[loss=0.1706, simple_loss=0.2574, pruned_loss=0.04193, over 7115.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2551, pruned_loss=0.03782, over 1414526.88 frames.], batch size: 21, lr: 4.05e-04
+2022-05-15 00:07:04,141 INFO [train.py:812] (0/8) Epoch 19, batch 3950, loss[loss=0.1895, simple_loss=0.282, pruned_loss=0.04851, over 7162.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2552, pruned_loss=0.03767, over 1416449.38 frames.], batch size: 18, lr: 4.05e-04
+2022-05-15 00:08:03,348 INFO [train.py:812] (0/8) Epoch 19, batch 4000, loss[loss=0.1887, simple_loss=0.2717, pruned_loss=0.05288, over 5372.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2547, pruned_loss=0.03744, over 1418121.84 frames.], batch size: 52, lr: 4.05e-04
+2022-05-15 00:09:00,798 INFO [train.py:812] (0/8) Epoch 19, batch 4050, loss[loss=0.1532, simple_loss=0.229, pruned_loss=0.03869, over 7229.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2536, pruned_loss=0.03682, over 1415758.59 frames.], batch size: 16, lr: 4.05e-04
+2022-05-15 00:09:59,541 INFO [train.py:812] (0/8) Epoch 19, batch 4100, loss[loss=0.1808, simple_loss=0.2658, pruned_loss=0.04792, over 5299.00 frames.], tot_loss[loss=0.1641, simple_loss=0.254, pruned_loss=0.03716, over 1416893.66 frames.], batch size: 52, lr: 4.05e-04
+2022-05-15 00:10:57,147 INFO [train.py:812] (0/8) Epoch 19, batch 4150, loss[loss=0.1829, simple_loss=0.2753, pruned_loss=0.04519, over 7385.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2532, pruned_loss=0.03691, over 1422263.37 frames.], batch size: 23, lr: 4.05e-04
+2022-05-15 00:11:56,834 INFO [train.py:812] (0/8) Epoch 19, batch 4200, loss[loss=0.1632, simple_loss=0.253, pruned_loss=0.03664, over 7195.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2532, pruned_loss=0.03665, over 1420822.55 frames.], batch size: 23, lr: 4.05e-04
+2022-05-15 00:12:56,147 INFO [train.py:812] (0/8) Epoch 19, batch 4250, loss[loss=0.1582, simple_loss=0.232, pruned_loss=0.0422, over 6768.00 frames.], tot_loss[loss=0.1632, simple_loss=0.253, pruned_loss=0.03669, over 1419995.32 frames.], batch size: 15, lr: 4.04e-04
+2022-05-15 00:14:05,102 INFO [train.py:812] (0/8) Epoch 19, batch 4300, loss[loss=0.1629, simple_loss=0.2474, pruned_loss=0.03919, over 7128.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2536, pruned_loss=0.03684, over 1419688.94 frames.], batch size: 26, lr: 4.04e-04
+2022-05-15 00:15:05,014 INFO [train.py:812] (0/8) Epoch 19, batch 4350, loss[loss=0.1722, simple_loss=0.2594, pruned_loss=0.04247, over 7158.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2533, pruned_loss=0.0368, over 1417858.70 frames.], batch size: 18, lr: 4.04e-04
+2022-05-15 00:16:03,308 INFO [train.py:812] (0/8) Epoch 19, batch 4400, loss[loss=0.1863, simple_loss=0.2665, pruned_loss=0.05299, over 6346.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2531, pruned_loss=0.03693, over 1413733.04 frames.], batch size: 37, lr: 4.04e-04
+2022-05-15 00:17:02,480 INFO [train.py:812] (0/8) Epoch 19, batch 4450, loss[loss=0.1505, simple_loss=0.2317, pruned_loss=0.03468, over 6797.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2525, pruned_loss=0.03707, over 1408414.93 frames.], batch size: 15, lr: 4.04e-04
+2022-05-15 00:18:02,039 INFO [train.py:812] (0/8) Epoch 19, batch 4500, loss[loss=0.1631, simple_loss=0.252, pruned_loss=0.0371, over 7143.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2541, pruned_loss=0.03831, over 1394442.86 frames.], batch size: 20, lr: 4.04e-04
+2022-05-15 00:19:01,072 INFO [train.py:812] (0/8) Epoch 19, batch 4550, loss[loss=0.1728, simple_loss=0.2618, pruned_loss=0.04189, over 6242.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2532, pruned_loss=0.03849, over 1368316.49 frames.], batch size: 38, lr: 4.04e-04
+2022-05-15 00:19:45,371 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-19.pt
+2022-05-15 00:20:09,413 INFO [train.py:812] (0/8) Epoch 20, batch 0, loss[loss=0.1466, simple_loss=0.2333, pruned_loss=0.02992, over 7351.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2333, pruned_loss=0.02992, over 7351.00 frames.], batch size: 19, lr: 3.94e-04
+2022-05-15 00:21:09,536 INFO [train.py:812] (0/8) Epoch 20, batch 50, loss[loss=0.1406, simple_loss=0.2298, pruned_loss=0.02567, over 7276.00 frames.], tot_loss[loss=0.161, simple_loss=0.2537, pruned_loss=0.03417, over 320199.41 frames.], batch size: 18, lr: 3.94e-04
+2022-05-15 00:22:08,832 INFO [train.py:812] (0/8) Epoch 20, batch 100, loss[loss=0.2066, simple_loss=0.283, pruned_loss=0.06511, over 4870.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2532, pruned_loss=0.03522, over 566190.12 frames.], batch size: 52, lr: 3.94e-04
+2022-05-15 00:23:08,482 INFO [train.py:812] (0/8) Epoch 20, batch 150, loss[loss=0.1538, simple_loss=0.2532, pruned_loss=0.0272, over 7322.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2548, pruned_loss=0.03604, over 756620.16 frames.], batch size: 21, lr: 3.94e-04
+2022-05-15 00:24:07,747 INFO [train.py:812] (0/8) Epoch 20, batch 200, loss[loss=0.1613, simple_loss=0.2568, pruned_loss=0.03287, over 7348.00 frames.], tot_loss[loss=0.1639, simple_loss=0.255, pruned_loss=0.03636, over 903963.09 frames.], batch size: 22, lr: 3.93e-04
+2022-05-15 00:25:08,004 INFO [train.py:812] (0/8) Epoch 20, batch 250, loss[loss=0.1912, simple_loss=0.2851, pruned_loss=0.04861, over 7325.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2537, pruned_loss=0.03628, over 1023128.49 frames.], batch size: 22, lr: 3.93e-04
+2022-05-15 00:26:07,271 INFO [train.py:812] (0/8) Epoch 20, batch 300, loss[loss=0.1712, simple_loss=0.2606, pruned_loss=0.04091, over 7200.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2535, pruned_loss=0.03574, over 1113363.74 frames.], batch size: 23, lr: 3.93e-04
+2022-05-15 00:27:07,175 INFO [train.py:812] (0/8) Epoch 20, batch 350, loss[loss=0.1874, simple_loss=0.2772, pruned_loss=0.04879, over 7142.00 frames.], tot_loss[loss=0.163, simple_loss=0.2541, pruned_loss=0.03596, over 1186005.61 frames.], batch size: 20, lr: 3.93e-04
+2022-05-15 00:28:05,121 INFO [train.py:812] (0/8) Epoch 20, batch 400, loss[loss=0.1729, simple_loss=0.262, pruned_loss=0.04193, over 7143.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2546, pruned_loss=0.03618, over 1237966.12 frames.], batch size: 20, lr: 3.93e-04
+2022-05-15 00:29:03,592 INFO [train.py:812] (0/8) Epoch 20, batch 450, loss[loss=0.1767, simple_loss=0.2776, pruned_loss=0.03789, over 7369.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2547, pruned_loss=0.03614, over 1275789.04 frames.], batch size: 23, lr: 3.93e-04
+2022-05-15 00:30:01,853 INFO [train.py:812] (0/8) Epoch 20, batch 500, loss[loss=0.169, simple_loss=0.2692, pruned_loss=0.0344, over 7222.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2545, pruned_loss=0.03599, over 1306879.79 frames.], batch size: 21, lr: 3.93e-04
+2022-05-15 00:31:00,458 INFO [train.py:812] (0/8) Epoch 20, batch 550, loss[loss=0.1657, simple_loss=0.2664, pruned_loss=0.03247, over 6824.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2538, pruned_loss=0.03551, over 1333457.25 frames.], batch size: 31, lr: 3.93e-04
+2022-05-15 00:32:00,101 INFO [train.py:812] (0/8) Epoch 20, batch 600, loss[loss=0.153, simple_loss=0.24, pruned_loss=0.03298, over 7160.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2529, pruned_loss=0.03597, over 1356087.40 frames.], batch size: 18, lr: 3.93e-04
+2022-05-15 00:32:59,171 INFO [train.py:812] (0/8) Epoch 20, batch 650, loss[loss=0.1493, simple_loss=0.2406, pruned_loss=0.02902, over 7161.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2531, pruned_loss=0.03594, over 1370573.01 frames.], batch size: 18, lr: 3.92e-04
+2022-05-15 00:33:55,667 INFO [train.py:812] (0/8) Epoch 20, batch 700, loss[loss=0.1579, simple_loss=0.2536, pruned_loss=0.03108, over 7246.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2537, pruned_loss=0.03585, over 1384022.21 frames.], batch size: 20, lr: 3.92e-04
+2022-05-15 00:34:54,552 INFO [train.py:812] (0/8) Epoch 20, batch 750, loss[loss=0.1752, simple_loss=0.2536, pruned_loss=0.0484, over 7294.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2524, pruned_loss=0.03561, over 1394618.19 frames.], batch size: 25, lr: 3.92e-04
+2022-05-15 00:35:51,669 INFO [train.py:812] (0/8) Epoch 20, batch 800, loss[loss=0.1295, simple_loss=0.2155, pruned_loss=0.02172, over 7419.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2519, pruned_loss=0.03569, over 1403989.42 frames.], batch size: 18, lr: 3.92e-04
+2022-05-15 00:36:24,102 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-88000.pt
+2022-05-15 00:36:56,559 INFO [train.py:812] (0/8) Epoch 20, batch 850, loss[loss=0.1707, simple_loss=0.2618, pruned_loss=0.0398, over 7028.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2523, pruned_loss=0.03581, over 1411653.35 frames.], batch size: 28, lr: 3.92e-04
+2022-05-15 00:37:55,359 INFO [train.py:812] (0/8) Epoch 20, batch 900, loss[loss=0.1376, simple_loss=0.2186, pruned_loss=0.02831, over 7352.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2518, pruned_loss=0.03587, over 1417148.46 frames.], batch size: 19, lr: 3.92e-04
+2022-05-15 00:38:53,706 INFO [train.py:812] (0/8) Epoch 20, batch 950, loss[loss=0.1535, simple_loss=0.2499, pruned_loss=0.02851, over 7240.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2522, pruned_loss=0.03631, over 1420598.80 frames.], batch size: 20, lr: 3.92e-04
+2022-05-15 00:39:52,446 INFO [train.py:812] (0/8) Epoch 20, batch 1000, loss[loss=0.1743, simple_loss=0.2681, pruned_loss=0.04024, over 7285.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2525, pruned_loss=0.03611, over 1421124.01 frames.], batch size: 24, lr: 3.92e-04
+2022-05-15 00:40:51,830 INFO [train.py:812] (0/8) Epoch 20, batch 1050, loss[loss=0.1745, simple_loss=0.2588, pruned_loss=0.04512, over 7219.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2527, pruned_loss=0.03648, over 1420881.10 frames.], batch size: 22, lr: 3.92e-04
+2022-05-15 00:41:50,557 INFO [train.py:812] (0/8) Epoch 20, batch 1100, loss[loss=0.2025, simple_loss=0.2835, pruned_loss=0.06072, over 7211.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2531, pruned_loss=0.03673, over 1416362.90 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:42:49,024 INFO [train.py:812] (0/8) Epoch 20, batch 1150, loss[loss=0.1956, simple_loss=0.2924, pruned_loss=0.04938, over 7280.00 frames.], tot_loss[loss=0.164, simple_loss=0.254, pruned_loss=0.03703, over 1420361.73 frames.], batch size: 24, lr: 3.91e-04
+2022-05-15 00:43:48,216 INFO [train.py:812] (0/8) Epoch 20, batch 1200, loss[loss=0.1668, simple_loss=0.2664, pruned_loss=0.03366, over 7329.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2526, pruned_loss=0.03631, over 1425440.04 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:44:47,687 INFO [train.py:812] (0/8) Epoch 20, batch 1250, loss[loss=0.1501, simple_loss=0.2348, pruned_loss=0.0327, over 7146.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2521, pruned_loss=0.03628, over 1426085.83 frames.], batch size: 17, lr: 3.91e-04
+2022-05-15 00:45:46,805 INFO [train.py:812] (0/8) Epoch 20, batch 1300, loss[loss=0.1679, simple_loss=0.2515, pruned_loss=0.04217, over 7124.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2515, pruned_loss=0.03596, over 1427682.27 frames.], batch size: 21, lr: 3.91e-04
+2022-05-15 00:46:46,852 INFO [train.py:812] (0/8) Epoch 20, batch 1350, loss[loss=0.1852, simple_loss=0.2727, pruned_loss=0.04889, over 7202.00 frames.], tot_loss[loss=0.1619, simple_loss=0.252, pruned_loss=0.03591, over 1429902.31 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:47:55,891 INFO [train.py:812] (0/8) Epoch 20, batch 1400, loss[loss=0.1788, simple_loss=0.2598, pruned_loss=0.04885, over 7195.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2519, pruned_loss=0.0362, over 1431274.45 frames.], batch size: 26, lr: 3.91e-04
+2022-05-15 00:48:55,616 INFO [train.py:812] (0/8) Epoch 20, batch 1450, loss[loss=0.1619, simple_loss=0.2487, pruned_loss=0.03754, over 7207.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2537, pruned_loss=0.03705, over 1429453.91 frames.], batch size: 26, lr: 3.91e-04
+2022-05-15 00:49:54,734 INFO [train.py:812] (0/8) Epoch 20, batch 1500, loss[loss=0.1685, simple_loss=0.2571, pruned_loss=0.03992, over 7401.00 frames.], tot_loss[loss=0.164, simple_loss=0.2538, pruned_loss=0.03703, over 1426301.17 frames.], batch size: 23, lr: 3.91e-04
+2022-05-15 00:51:04,079 INFO [train.py:812] (0/8) Epoch 20, batch 1550, loss[loss=0.1477, simple_loss=0.2365, pruned_loss=0.0294, over 7440.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2534, pruned_loss=0.03673, over 1428766.20 frames.], batch size: 20, lr: 3.91e-04
+2022-05-15 00:52:22,069 INFO [train.py:812] (0/8) Epoch 20, batch 1600, loss[loss=0.1749, simple_loss=0.275, pruned_loss=0.03738, over 7344.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2531, pruned_loss=0.0363, over 1423885.02 frames.], batch size: 22, lr: 3.90e-04
+2022-05-15 00:53:19,539 INFO [train.py:812] (0/8) Epoch 20, batch 1650, loss[loss=0.1845, simple_loss=0.2742, pruned_loss=0.04736, over 7209.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2538, pruned_loss=0.03664, over 1420777.84 frames.], batch size: 23, lr: 3.90e-04
+2022-05-15 00:54:36,075 INFO [train.py:812] (0/8) Epoch 20, batch 1700, loss[loss=0.1451, simple_loss=0.2284, pruned_loss=0.03093, over 7158.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2528, pruned_loss=0.03605, over 1420400.74 frames.], batch size: 19, lr: 3.90e-04
+2022-05-15 00:55:43,693 INFO [train.py:812] (0/8) Epoch 20, batch 1750, loss[loss=0.1505, simple_loss=0.2537, pruned_loss=0.02368, over 7321.00 frames.], tot_loss[loss=0.162, simple_loss=0.2525, pruned_loss=0.0358, over 1425694.92 frames.], batch size: 22, lr: 3.90e-04
+2022-05-15 00:56:42,587 INFO [train.py:812] (0/8) Epoch 20, batch 1800, loss[loss=0.174, simple_loss=0.2717, pruned_loss=0.03814, over 7280.00 frames.], tot_loss[loss=0.1624, simple_loss=0.253, pruned_loss=0.03586, over 1425589.80 frames.], batch size: 25, lr: 3.90e-04
+2022-05-15 00:57:42,324 INFO [train.py:812] (0/8) Epoch 20, batch 1850, loss[loss=0.1436, simple_loss=0.2348, pruned_loss=0.02618, over 7065.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2534, pruned_loss=0.03598, over 1428672.87 frames.], batch size: 18, lr: 3.90e-04
+2022-05-15 00:58:41,675 INFO [train.py:812] (0/8) Epoch 20, batch 1900, loss[loss=0.1758, simple_loss=0.2596, pruned_loss=0.04598, over 7229.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2537, pruned_loss=0.03607, over 1429041.29 frames.], batch size: 20, lr: 3.90e-04
+2022-05-15 00:59:40,054 INFO [train.py:812] (0/8) Epoch 20, batch 1950, loss[loss=0.1692, simple_loss=0.2637, pruned_loss=0.03731, over 6266.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2523, pruned_loss=0.03563, over 1429497.41 frames.], batch size: 37, lr: 3.90e-04
+2022-05-15 01:00:37,506 INFO [train.py:812] (0/8) Epoch 20, batch 2000, loss[loss=0.1509, simple_loss=0.247, pruned_loss=0.0274, over 7234.00 frames.], tot_loss[loss=0.1617, simple_loss=0.252, pruned_loss=0.0357, over 1430354.92 frames.], batch size: 20, lr: 3.90e-04
+2022-05-15 01:01:35,463 INFO [train.py:812] (0/8) Epoch 20, batch 2050, loss[loss=0.1547, simple_loss=0.253, pruned_loss=0.02821, over 7214.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2519, pruned_loss=0.03615, over 1429547.39 frames.], batch size: 21, lr: 3.89e-04
+2022-05-15 01:02:33,044 INFO [train.py:812] (0/8) Epoch 20, batch 2100, loss[loss=0.1708, simple_loss=0.2567, pruned_loss=0.04244, over 7419.00 frames.], tot_loss[loss=0.1621, simple_loss=0.252, pruned_loss=0.03614, over 1431644.38 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:03:30,906 INFO [train.py:812] (0/8) Epoch 20, batch 2150, loss[loss=0.1734, simple_loss=0.2688, pruned_loss=0.03903, over 7205.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2517, pruned_loss=0.03631, over 1425280.19 frames.], batch size: 22, lr: 3.89e-04
+2022-05-15 01:04:30,269 INFO [train.py:812] (0/8) Epoch 20, batch 2200, loss[loss=0.1587, simple_loss=0.2297, pruned_loss=0.04386, over 6796.00 frames.], tot_loss[loss=0.162, simple_loss=0.2514, pruned_loss=0.03629, over 1420086.71 frames.], batch size: 15, lr: 3.89e-04
+2022-05-15 01:05:28,869 INFO [train.py:812] (0/8) Epoch 20, batch 2250, loss[loss=0.1571, simple_loss=0.2529, pruned_loss=0.03062, over 7156.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2506, pruned_loss=0.03589, over 1422856.01 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:06:27,818 INFO [train.py:812] (0/8) Epoch 20, batch 2300, loss[loss=0.1806, simple_loss=0.2745, pruned_loss=0.04334, over 7387.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2508, pruned_loss=0.03613, over 1422942.18 frames.], batch size: 23, lr: 3.89e-04
+2022-05-15 01:07:25,467 INFO [train.py:812] (0/8) Epoch 20, batch 2350, loss[loss=0.149, simple_loss=0.2486, pruned_loss=0.02472, over 7313.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2511, pruned_loss=0.0357, over 1421578.22 frames.], batch size: 21, lr: 3.89e-04
+2022-05-15 01:08:24,204 INFO [train.py:812] (0/8) Epoch 20, batch 2400, loss[loss=0.1483, simple_loss=0.2433, pruned_loss=0.02661, over 7419.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2515, pruned_loss=0.03607, over 1424025.95 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:09:23,968 INFO [train.py:812] (0/8) Epoch 20, batch 2450, loss[loss=0.1782, simple_loss=0.2688, pruned_loss=0.04378, over 7121.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2507, pruned_loss=0.03583, over 1427200.58 frames.], batch size: 28, lr: 3.89e-04
+2022-05-15 01:10:23,011 INFO [train.py:812] (0/8) Epoch 20, batch 2500, loss[loss=0.1604, simple_loss=0.2523, pruned_loss=0.03426, over 7118.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2509, pruned_loss=0.03578, over 1426830.32 frames.], batch size: 26, lr: 3.88e-04
+2022-05-15 01:11:22,814 INFO [train.py:812] (0/8) Epoch 20, batch 2550, loss[loss=0.1744, simple_loss=0.2712, pruned_loss=0.03878, over 7332.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2513, pruned_loss=0.03605, over 1425602.88 frames.], batch size: 20, lr: 3.88e-04
+2022-05-15 01:12:22,064 INFO [train.py:812] (0/8) Epoch 20, batch 2600, loss[loss=0.1974, simple_loss=0.2879, pruned_loss=0.05344, over 6810.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2521, pruned_loss=0.03615, over 1426712.13 frames.], batch size: 31, lr: 3.88e-04
+2022-05-15 01:13:22,175 INFO [train.py:812] (0/8) Epoch 20, batch 2650, loss[loss=0.1293, simple_loss=0.2046, pruned_loss=0.02698, over 7024.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2514, pruned_loss=0.03578, over 1427390.17 frames.], batch size: 16, lr: 3.88e-04
+2022-05-15 01:14:21,648 INFO [train.py:812] (0/8) Epoch 20, batch 2700, loss[loss=0.179, simple_loss=0.2606, pruned_loss=0.04868, over 7389.00 frames.], tot_loss[loss=0.1613, simple_loss=0.251, pruned_loss=0.03576, over 1428493.63 frames.], batch size: 23, lr: 3.88e-04
+2022-05-15 01:15:21,494 INFO [train.py:812] (0/8) Epoch 20, batch 2750, loss[loss=0.1865, simple_loss=0.2825, pruned_loss=0.04527, over 7200.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2519, pruned_loss=0.0359, over 1426731.38 frames.], batch size: 23, lr: 3.88e-04
+2022-05-15 01:16:20,980 INFO [train.py:812] (0/8) Epoch 20, batch 2800, loss[loss=0.1494, simple_loss=0.234, pruned_loss=0.03245, over 7165.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2519, pruned_loss=0.03551, over 1430744.99 frames.], batch size: 18, lr: 3.88e-04
+2022-05-15 01:17:20,836 INFO [train.py:812] (0/8) Epoch 20, batch 2850, loss[loss=0.1503, simple_loss=0.2513, pruned_loss=0.02465, over 7415.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2513, pruned_loss=0.03528, over 1432490.15 frames.], batch size: 21, lr: 3.88e-04
+2022-05-15 01:18:20,011 INFO [train.py:812] (0/8) Epoch 20, batch 2900, loss[loss=0.1666, simple_loss=0.2564, pruned_loss=0.03836, over 7120.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2509, pruned_loss=0.03506, over 1428299.85 frames.], batch size: 26, lr: 3.88e-04
+2022-05-15 01:19:19,540 INFO [train.py:812] (0/8) Epoch 20, batch 2950, loss[loss=0.1522, simple_loss=0.2522, pruned_loss=0.02612, over 7228.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2516, pruned_loss=0.03512, over 1432209.51 frames.], batch size: 20, lr: 3.87e-04
+2022-05-15 01:20:18,594 INFO [train.py:812] (0/8) Epoch 20, batch 3000, loss[loss=0.2144, simple_loss=0.3051, pruned_loss=0.0619, over 7380.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2533, pruned_loss=0.03583, over 1431645.75 frames.], batch size: 23, lr: 3.87e-04
+2022-05-15 01:20:18,596 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 01:20:27,134 INFO [train.py:841] (0/8) Epoch 20, validation: loss=0.1532, simple_loss=0.2519, pruned_loss=0.02723, over 698248.00 frames.
+2022-05-15 01:21:26,364 INFO [train.py:812] (0/8) Epoch 20, batch 3050, loss[loss=0.1673, simple_loss=0.2622, pruned_loss=0.03619, over 7159.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2537, pruned_loss=0.03587, over 1433327.87 frames.], batch size: 19, lr: 3.87e-04
+2022-05-15 01:22:25,315 INFO [train.py:812] (0/8) Epoch 20, batch 3100, loss[loss=0.1627, simple_loss=0.2545, pruned_loss=0.03546, over 7117.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2535, pruned_loss=0.03561, over 1431960.42 frames.], batch size: 21, lr: 3.87e-04
+2022-05-15 01:23:24,539 INFO [train.py:812] (0/8) Epoch 20, batch 3150, loss[loss=0.1549, simple_loss=0.2424, pruned_loss=0.03369, over 7291.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2528, pruned_loss=0.03566, over 1432939.81 frames.], batch size: 18, lr: 3.87e-04
+2022-05-15 01:24:21,340 INFO [train.py:812] (0/8) Epoch 20, batch 3200, loss[loss=0.1692, simple_loss=0.2662, pruned_loss=0.0361, over 6727.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2523, pruned_loss=0.03552, over 1431981.42 frames.], batch size: 31, lr: 3.87e-04
+2022-05-15 01:25:18,813 INFO [train.py:812] (0/8) Epoch 20, batch 3250, loss[loss=0.1606, simple_loss=0.2563, pruned_loss=0.03238, over 7071.00 frames.], tot_loss[loss=0.1623, simple_loss=0.253, pruned_loss=0.03586, over 1429033.30 frames.], batch size: 18, lr: 3.87e-04
+2022-05-15 01:26:16,478 INFO [train.py:812] (0/8) Epoch 20, batch 3300, loss[loss=0.1568, simple_loss=0.2433, pruned_loss=0.03517, over 7127.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2527, pruned_loss=0.03599, over 1427477.21 frames.], batch size: 17, lr: 3.87e-04
+2022-05-15 01:27:14,063 INFO [train.py:812] (0/8) Epoch 20, batch 3350, loss[loss=0.1712, simple_loss=0.2725, pruned_loss=0.03492, over 7148.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2527, pruned_loss=0.03601, over 1427488.38 frames.], batch size: 20, lr: 3.87e-04
+2022-05-15 01:28:13,197 INFO [train.py:812] (0/8) Epoch 20, batch 3400, loss[loss=0.1389, simple_loss=0.2211, pruned_loss=0.02838, over 7268.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2526, pruned_loss=0.0359, over 1426832.61 frames.], batch size: 17, lr: 3.87e-04
+2022-05-15 01:29:12,295 INFO [train.py:812] (0/8) Epoch 20, batch 3450, loss[loss=0.1631, simple_loss=0.2495, pruned_loss=0.03837, over 7239.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2531, pruned_loss=0.03603, over 1425688.70 frames.], batch size: 20, lr: 3.86e-04
+2022-05-15 01:30:11,784 INFO [train.py:812] (0/8) Epoch 20, batch 3500, loss[loss=0.1521, simple_loss=0.2238, pruned_loss=0.04014, over 7261.00 frames.], tot_loss[loss=0.162, simple_loss=0.2524, pruned_loss=0.03577, over 1424204.14 frames.], batch size: 19, lr: 3.86e-04
+2022-05-15 01:31:11,499 INFO [train.py:812] (0/8) Epoch 20, batch 3550, loss[loss=0.1482, simple_loss=0.2439, pruned_loss=0.02622, over 7106.00 frames.], tot_loss[loss=0.1625, simple_loss=0.253, pruned_loss=0.03599, over 1427085.34 frames.], batch size: 21, lr: 3.86e-04
+2022-05-15 01:32:11,000 INFO [train.py:812] (0/8) Epoch 20, batch 3600, loss[loss=0.1749, simple_loss=0.2637, pruned_loss=0.04307, over 7214.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2528, pruned_loss=0.03592, over 1429670.61 frames.], batch size: 23, lr: 3.86e-04
+2022-05-15 01:33:10,980 INFO [train.py:812] (0/8) Epoch 20, batch 3650, loss[loss=0.1732, simple_loss=0.274, pruned_loss=0.03618, over 7325.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2528, pruned_loss=0.03586, over 1430193.44 frames.], batch size: 21, lr: 3.86e-04
+2022-05-15 01:34:09,099 INFO [train.py:812] (0/8) Epoch 20, batch 3700, loss[loss=0.1688, simple_loss=0.2544, pruned_loss=0.04164, over 7156.00 frames.], tot_loss[loss=0.1624, simple_loss=0.253, pruned_loss=0.0359, over 1432200.76 frames.], batch size: 18, lr: 3.86e-04
+2022-05-15 01:35:08,005 INFO [train.py:812] (0/8) Epoch 20, batch 3750, loss[loss=0.1715, simple_loss=0.2538, pruned_loss=0.04457, over 7104.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2519, pruned_loss=0.0353, over 1426536.48 frames.], batch size: 28, lr: 3.86e-04
+2022-05-15 01:36:06,437 INFO [train.py:812] (0/8) Epoch 20, batch 3800, loss[loss=0.1494, simple_loss=0.2425, pruned_loss=0.02809, over 7323.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2513, pruned_loss=0.03552, over 1422077.50 frames.], batch size: 20, lr: 3.86e-04
+2022-05-15 01:37:04,401 INFO [train.py:812] (0/8) Epoch 20, batch 3850, loss[loss=0.1475, simple_loss=0.2317, pruned_loss=0.03169, over 7283.00 frames.], tot_loss[loss=0.16, simple_loss=0.2499, pruned_loss=0.03506, over 1420543.55 frames.], batch size: 17, lr: 3.86e-04
+2022-05-15 01:38:02,161 INFO [train.py:812] (0/8) Epoch 20, batch 3900, loss[loss=0.1716, simple_loss=0.2804, pruned_loss=0.0314, over 7129.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2514, pruned_loss=0.03565, over 1417592.85 frames.], batch size: 21, lr: 3.85e-04
+2022-05-15 01:39:01,285 INFO [train.py:812] (0/8) Epoch 20, batch 3950, loss[loss=0.1558, simple_loss=0.2511, pruned_loss=0.03029, over 7345.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2516, pruned_loss=0.03604, over 1412193.18 frames.], batch size: 20, lr: 3.85e-04
+2022-05-15 01:39:59,107 INFO [train.py:812] (0/8) Epoch 20, batch 4000, loss[loss=0.1534, simple_loss=0.239, pruned_loss=0.03389, over 7160.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2514, pruned_loss=0.03576, over 1409794.45 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:40:58,250 INFO [train.py:812] (0/8) Epoch 20, batch 4050, loss[loss=0.1761, simple_loss=0.2654, pruned_loss=0.04339, over 7331.00 frames.], tot_loss[loss=0.1625, simple_loss=0.252, pruned_loss=0.03651, over 1406632.91 frames.], batch size: 20, lr: 3.85e-04
+2022-05-15 01:41:57,206 INFO [train.py:812] (0/8) Epoch 20, batch 4100, loss[loss=0.1327, simple_loss=0.2127, pruned_loss=0.02637, over 7277.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2511, pruned_loss=0.03624, over 1406559.56 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:42:56,569 INFO [train.py:812] (0/8) Epoch 20, batch 4150, loss[loss=0.1543, simple_loss=0.2433, pruned_loss=0.03261, over 7074.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2512, pruned_loss=0.03626, over 1410681.58 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:43:53,656 INFO [train.py:812] (0/8) Epoch 20, batch 4200, loss[loss=0.1539, simple_loss=0.2308, pruned_loss=0.03852, over 6722.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2517, pruned_loss=0.0366, over 1405060.94 frames.], batch size: 15, lr: 3.85e-04
+2022-05-15 01:44:52,600 INFO [train.py:812] (0/8) Epoch 20, batch 4250, loss[loss=0.1766, simple_loss=0.2671, pruned_loss=0.04309, over 7199.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2507, pruned_loss=0.03635, over 1403671.28 frames.], batch size: 23, lr: 3.85e-04
+2022-05-15 01:45:49,951 INFO [train.py:812] (0/8) Epoch 20, batch 4300, loss[loss=0.2199, simple_loss=0.3009, pruned_loss=0.06941, over 7219.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2516, pruned_loss=0.03658, over 1402144.33 frames.], batch size: 21, lr: 3.85e-04
+2022-05-15 01:46:48,976 INFO [train.py:812] (0/8) Epoch 20, batch 4350, loss[loss=0.2287, simple_loss=0.2997, pruned_loss=0.0788, over 5170.00 frames.], tot_loss[loss=0.161, simple_loss=0.25, pruned_loss=0.036, over 1404629.75 frames.], batch size: 55, lr: 3.84e-04
+2022-05-15 01:47:48,098 INFO [train.py:812] (0/8) Epoch 20, batch 4400, loss[loss=0.1555, simple_loss=0.2476, pruned_loss=0.03174, over 7162.00 frames.], tot_loss[loss=0.1608, simple_loss=0.25, pruned_loss=0.03585, over 1398291.76 frames.], batch size: 19, lr: 3.84e-04
+2022-05-15 01:48:47,111 INFO [train.py:812] (0/8) Epoch 20, batch 4450, loss[loss=0.1573, simple_loss=0.2352, pruned_loss=0.03974, over 6770.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2495, pruned_loss=0.03593, over 1389396.14 frames.], batch size: 15, lr: 3.84e-04
+2022-05-15 01:49:45,779 INFO [train.py:812] (0/8) Epoch 20, batch 4500, loss[loss=0.1823, simple_loss=0.2728, pruned_loss=0.04597, over 7198.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2507, pruned_loss=0.03611, over 1382631.02 frames.], batch size: 23, lr: 3.84e-04
+2022-05-15 01:50:44,390 INFO [train.py:812] (0/8) Epoch 20, batch 4550, loss[loss=0.1511, simple_loss=0.2363, pruned_loss=0.03298, over 6466.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2535, pruned_loss=0.03803, over 1335229.22 frames.], batch size: 38, lr: 3.84e-04
+2022-05-15 01:51:29,395 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-20.pt
+2022-05-15 01:51:55,168 INFO [train.py:812] (0/8) Epoch 21, batch 0, loss[loss=0.1455, simple_loss=0.2369, pruned_loss=0.02705, over 7008.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2369, pruned_loss=0.02705, over 7008.00 frames.], batch size: 16, lr: 3.75e-04
+2022-05-15 01:52:54,956 INFO [train.py:812] (0/8) Epoch 21, batch 50, loss[loss=0.1476, simple_loss=0.2415, pruned_loss=0.02683, over 6388.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2521, pruned_loss=0.03686, over 322612.21 frames.], batch size: 37, lr: 3.75e-04
+2022-05-15 01:53:53,841 INFO [train.py:812] (0/8) Epoch 21, batch 100, loss[loss=0.1688, simple_loss=0.2595, pruned_loss=0.03899, over 7236.00 frames.], tot_loss[loss=0.1626, simple_loss=0.252, pruned_loss=0.03653, over 566679.29 frames.], batch size: 16, lr: 3.75e-04
+2022-05-15 01:54:52,696 INFO [train.py:812] (0/8) Epoch 21, batch 150, loss[loss=0.1622, simple_loss=0.2476, pruned_loss=0.03835, over 7148.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2509, pruned_loss=0.03531, over 755748.65 frames.], batch size: 18, lr: 3.75e-04
+2022-05-15 01:55:51,322 INFO [train.py:812] (0/8) Epoch 21, batch 200, loss[loss=0.1765, simple_loss=0.2831, pruned_loss=0.03494, over 6763.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2527, pruned_loss=0.03606, over 900773.30 frames.], batch size: 31, lr: 3.75e-04
+2022-05-15 01:56:36,010 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-92000.pt
+2022-05-15 01:56:53,961 INFO [train.py:812] (0/8) Epoch 21, batch 250, loss[loss=0.1692, simple_loss=0.2519, pruned_loss=0.04328, over 7152.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2515, pruned_loss=0.03585, over 1013737.18 frames.], batch size: 19, lr: 3.75e-04
+2022-05-15 01:57:52,821 INFO [train.py:812] (0/8) Epoch 21, batch 300, loss[loss=0.1697, simple_loss=0.2517, pruned_loss=0.04391, over 7272.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2525, pruned_loss=0.03606, over 1102783.16 frames.], batch size: 18, lr: 3.75e-04
+2022-05-15 01:58:49,829 INFO [train.py:812] (0/8) Epoch 21, batch 350, loss[loss=0.142, simple_loss=0.2376, pruned_loss=0.02321, over 7264.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2527, pruned_loss=0.03618, over 1171748.39 frames.], batch size: 19, lr: 3.74e-04
+2022-05-15 01:59:47,324 INFO [train.py:812] (0/8) Epoch 21, batch 400, loss[loss=0.1436, simple_loss=0.2328, pruned_loss=0.02722, over 7056.00 frames.], tot_loss[loss=0.162, simple_loss=0.252, pruned_loss=0.03604, over 1230208.96 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:00:46,711 INFO [train.py:812] (0/8) Epoch 21, batch 450, loss[loss=0.1405, simple_loss=0.2338, pruned_loss=0.02361, over 7075.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2515, pruned_loss=0.03541, over 1272124.75 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:01:45,878 INFO [train.py:812] (0/8) Epoch 21, batch 500, loss[loss=0.1607, simple_loss=0.2554, pruned_loss=0.03301, over 7094.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2512, pruned_loss=0.03514, over 1310784.47 frames.], batch size: 28, lr: 3.74e-04
+2022-05-15 02:02:44,639 INFO [train.py:812] (0/8) Epoch 21, batch 550, loss[loss=0.1347, simple_loss=0.2246, pruned_loss=0.02241, over 6814.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2516, pruned_loss=0.03538, over 1336446.23 frames.], batch size: 15, lr: 3.74e-04
+2022-05-15 02:03:42,718 INFO [train.py:812] (0/8) Epoch 21, batch 600, loss[loss=0.1795, simple_loss=0.2762, pruned_loss=0.04138, over 7219.00 frames.], tot_loss[loss=0.161, simple_loss=0.2516, pruned_loss=0.03522, over 1354414.01 frames.], batch size: 22, lr: 3.74e-04
+2022-05-15 02:04:42,157 INFO [train.py:812] (0/8) Epoch 21, batch 650, loss[loss=0.1552, simple_loss=0.2332, pruned_loss=0.03856, over 7136.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2497, pruned_loss=0.03504, over 1369241.62 frames.], batch size: 17, lr: 3.74e-04
+2022-05-15 02:05:41,120 INFO [train.py:812] (0/8) Epoch 21, batch 700, loss[loss=0.1789, simple_loss=0.2733, pruned_loss=0.04225, over 7234.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2509, pruned_loss=0.03525, over 1380278.29 frames.], batch size: 20, lr: 3.74e-04
+2022-05-15 02:06:40,203 INFO [train.py:812] (0/8) Epoch 21, batch 750, loss[loss=0.1457, simple_loss=0.2393, pruned_loss=0.026, over 7403.00 frames.], tot_loss[loss=0.162, simple_loss=0.2524, pruned_loss=0.03581, over 1385871.93 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:07:37,583 INFO [train.py:812] (0/8) Epoch 21, batch 800, loss[loss=0.1569, simple_loss=0.2532, pruned_loss=0.03036, over 7234.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2512, pruned_loss=0.03566, over 1384655.47 frames.], batch size: 20, lr: 3.73e-04
+2022-05-15 02:08:37,256 INFO [train.py:812] (0/8) Epoch 21, batch 850, loss[loss=0.1716, simple_loss=0.2676, pruned_loss=0.03782, over 7282.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2501, pruned_loss=0.03549, over 1390988.92 frames.], batch size: 25, lr: 3.73e-04
+2022-05-15 02:09:36,855 INFO [train.py:812] (0/8) Epoch 21, batch 900, loss[loss=0.1825, simple_loss=0.2765, pruned_loss=0.0442, over 7232.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2497, pruned_loss=0.03534, over 1399409.13 frames.], batch size: 20, lr: 3.73e-04
+2022-05-15 02:10:36,708 INFO [train.py:812] (0/8) Epoch 21, batch 950, loss[loss=0.1933, simple_loss=0.2788, pruned_loss=0.05387, over 7336.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2499, pruned_loss=0.03528, over 1406148.92 frames.], batch size: 22, lr: 3.73e-04
+2022-05-15 02:11:34,909 INFO [train.py:812] (0/8) Epoch 21, batch 1000, loss[loss=0.1881, simple_loss=0.2801, pruned_loss=0.04803, over 7203.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2506, pruned_loss=0.03545, over 1405416.10 frames.], batch size: 23, lr: 3.73e-04
+2022-05-15 02:12:42,505 INFO [train.py:812] (0/8) Epoch 21, batch 1050, loss[loss=0.163, simple_loss=0.2476, pruned_loss=0.03922, over 7424.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2518, pruned_loss=0.0356, over 1406975.82 frames.], batch size: 21, lr: 3.73e-04
+2022-05-15 02:13:41,822 INFO [train.py:812] (0/8) Epoch 21, batch 1100, loss[loss=0.1522, simple_loss=0.231, pruned_loss=0.03671, over 6783.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2509, pruned_loss=0.0355, over 1408214.69 frames.], batch size: 15, lr: 3.73e-04
+2022-05-15 02:14:40,540 INFO [train.py:812] (0/8) Epoch 21, batch 1150, loss[loss=0.1948, simple_loss=0.2794, pruned_loss=0.05509, over 7306.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2507, pruned_loss=0.03525, over 1413362.93 frames.], batch size: 24, lr: 3.73e-04
+2022-05-15 02:15:37,797 INFO [train.py:812] (0/8) Epoch 21, batch 1200, loss[loss=0.1565, simple_loss=0.2389, pruned_loss=0.03708, over 7286.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2518, pruned_loss=0.03566, over 1415664.82 frames.], batch size: 18, lr: 3.73e-04
+2022-05-15 02:16:37,258 INFO [train.py:812] (0/8) Epoch 21, batch 1250, loss[loss=0.175, simple_loss=0.2735, pruned_loss=0.03826, over 7311.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2512, pruned_loss=0.03546, over 1417797.38 frames.], batch size: 24, lr: 3.73e-04
+2022-05-15 02:17:36,529 INFO [train.py:812] (0/8) Epoch 21, batch 1300, loss[loss=0.1501, simple_loss=0.2346, pruned_loss=0.03276, over 7070.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2512, pruned_loss=0.03554, over 1417087.41 frames.], batch size: 18, lr: 3.72e-04
+2022-05-15 02:18:34,033 INFO [train.py:812] (0/8) Epoch 21, batch 1350, loss[loss=0.1696, simple_loss=0.2693, pruned_loss=0.03494, over 7343.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2512, pruned_loss=0.03545, over 1423789.15 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:19:32,985 INFO [train.py:812] (0/8) Epoch 21, batch 1400, loss[loss=0.1554, simple_loss=0.2488, pruned_loss=0.03102, over 7380.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2506, pruned_loss=0.03512, over 1426160.32 frames.], batch size: 23, lr: 3.72e-04
+2022-05-15 02:20:31,798 INFO [train.py:812] (0/8) Epoch 21, batch 1450, loss[loss=0.1847, simple_loss=0.268, pruned_loss=0.0507, over 4866.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2504, pruned_loss=0.03533, over 1420361.55 frames.], batch size: 52, lr: 3.72e-04
+2022-05-15 02:21:30,232 INFO [train.py:812] (0/8) Epoch 21, batch 1500, loss[loss=0.1609, simple_loss=0.2537, pruned_loss=0.034, over 7328.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2504, pruned_loss=0.03527, over 1418367.66 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:22:29,839 INFO [train.py:812] (0/8) Epoch 21, batch 1550, loss[loss=0.1858, simple_loss=0.2751, pruned_loss=0.0483, over 6694.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2504, pruned_loss=0.03523, over 1420716.72 frames.], batch size: 31, lr: 3.72e-04
+2022-05-15 02:23:26,748 INFO [train.py:812] (0/8) Epoch 21, batch 1600, loss[loss=0.1708, simple_loss=0.2637, pruned_loss=0.03892, over 7340.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2505, pruned_loss=0.03501, over 1421953.35 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:24:25,700 INFO [train.py:812] (0/8) Epoch 21, batch 1650, loss[loss=0.1424, simple_loss=0.2348, pruned_loss=0.02503, over 7332.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2499, pruned_loss=0.03491, over 1422628.01 frames.], batch size: 20, lr: 3.72e-04
+2022-05-15 02:25:24,262 INFO [train.py:812] (0/8) Epoch 21, batch 1700, loss[loss=0.1914, simple_loss=0.2797, pruned_loss=0.05151, over 7332.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2498, pruned_loss=0.03487, over 1422410.16 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:26:22,315 INFO [train.py:812] (0/8) Epoch 21, batch 1750, loss[loss=0.1467, simple_loss=0.2319, pruned_loss=0.03079, over 7406.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2503, pruned_loss=0.03513, over 1423700.06 frames.], batch size: 18, lr: 3.72e-04
+2022-05-15 02:27:21,203 INFO [train.py:812] (0/8) Epoch 21, batch 1800, loss[loss=0.1829, simple_loss=0.272, pruned_loss=0.04692, over 7221.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2502, pruned_loss=0.03507, over 1424806.74 frames.], batch size: 23, lr: 3.71e-04
+2022-05-15 02:28:20,366 INFO [train.py:812] (0/8) Epoch 21, batch 1850, loss[loss=0.1801, simple_loss=0.2691, pruned_loss=0.04561, over 7414.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2511, pruned_loss=0.03571, over 1424411.40 frames.], batch size: 18, lr: 3.71e-04
+2022-05-15 02:29:19,170 INFO [train.py:812] (0/8) Epoch 21, batch 1900, loss[loss=0.1471, simple_loss=0.2293, pruned_loss=0.03242, over 7170.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2512, pruned_loss=0.0357, over 1425733.34 frames.], batch size: 19, lr: 3.71e-04
+2022-05-15 02:30:18,944 INFO [train.py:812] (0/8) Epoch 21, batch 1950, loss[loss=0.1468, simple_loss=0.2408, pruned_loss=0.0264, over 7254.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2515, pruned_loss=0.0356, over 1429412.48 frames.], batch size: 19, lr: 3.71e-04
+2022-05-15 02:31:18,444 INFO [train.py:812] (0/8) Epoch 21, batch 2000, loss[loss=0.1666, simple_loss=0.2626, pruned_loss=0.03526, over 6728.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2512, pruned_loss=0.03577, over 1426157.37 frames.], batch size: 31, lr: 3.71e-04
+2022-05-15 02:32:18,216 INFO [train.py:812] (0/8) Epoch 21, batch 2050, loss[loss=0.1669, simple_loss=0.2558, pruned_loss=0.03898, over 7228.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2517, pruned_loss=0.03608, over 1425321.02 frames.], batch size: 21, lr: 3.71e-04
+2022-05-15 02:33:17,432 INFO [train.py:812] (0/8) Epoch 21, batch 2100, loss[loss=0.1656, simple_loss=0.2614, pruned_loss=0.03496, over 7073.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2514, pruned_loss=0.03599, over 1424603.89 frames.], batch size: 18, lr: 3.71e-04
+2022-05-15 02:34:16,884 INFO [train.py:812] (0/8) Epoch 21, batch 2150, loss[loss=0.1847, simple_loss=0.2508, pruned_loss=0.05927, over 6799.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2516, pruned_loss=0.03578, over 1422278.90 frames.], batch size: 15, lr: 3.71e-04
+2022-05-15 02:35:14,486 INFO [train.py:812] (0/8) Epoch 21, batch 2200, loss[loss=0.1879, simple_loss=0.2869, pruned_loss=0.0444, over 7217.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2514, pruned_loss=0.03588, over 1425072.72 frames.], batch size: 22, lr: 3.71e-04
+2022-05-15 02:36:12,371 INFO [train.py:812] (0/8) Epoch 21, batch 2250, loss[loss=0.1663, simple_loss=0.2595, pruned_loss=0.0366, over 7203.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2517, pruned_loss=0.0359, over 1425776.25 frames.], batch size: 22, lr: 3.71e-04
+2022-05-15 02:37:12,526 INFO [train.py:812] (0/8) Epoch 21, batch 2300, loss[loss=0.209, simple_loss=0.2755, pruned_loss=0.07126, over 5083.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2508, pruned_loss=0.0358, over 1422344.74 frames.], batch size: 52, lr: 3.71e-04
+2022-05-15 02:38:11,397 INFO [train.py:812] (0/8) Epoch 21, batch 2350, loss[loss=0.1718, simple_loss=0.2554, pruned_loss=0.04411, over 7288.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2517, pruned_loss=0.03606, over 1417238.38 frames.], batch size: 24, lr: 3.70e-04
+2022-05-15 02:39:10,739 INFO [train.py:812] (0/8) Epoch 21, batch 2400, loss[loss=0.1714, simple_loss=0.2585, pruned_loss=0.0422, over 7207.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2509, pruned_loss=0.03561, over 1420446.53 frames.], batch size: 23, lr: 3.70e-04
+2022-05-15 02:40:10,452 INFO [train.py:812] (0/8) Epoch 21, batch 2450, loss[loss=0.1696, simple_loss=0.2656, pruned_loss=0.0368, over 7161.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2502, pruned_loss=0.03474, over 1421088.64 frames.], batch size: 19, lr: 3.70e-04
+2022-05-15 02:41:09,426 INFO [train.py:812] (0/8) Epoch 21, batch 2500, loss[loss=0.1586, simple_loss=0.2576, pruned_loss=0.02976, over 7418.00 frames.], tot_loss[loss=0.16, simple_loss=0.2503, pruned_loss=0.03489, over 1422519.16 frames.], batch size: 21, lr: 3.70e-04
+2022-05-15 02:42:07,849 INFO [train.py:812] (0/8) Epoch 21, batch 2550, loss[loss=0.1787, simple_loss=0.2632, pruned_loss=0.0471, over 5231.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2508, pruned_loss=0.03504, over 1420414.27 frames.], batch size: 52, lr: 3.70e-04
+2022-05-15 02:43:06,161 INFO [train.py:812] (0/8) Epoch 21, batch 2600, loss[loss=0.1449, simple_loss=0.2381, pruned_loss=0.0258, over 7075.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2516, pruned_loss=0.03539, over 1421408.10 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:44:05,988 INFO [train.py:812] (0/8) Epoch 21, batch 2650, loss[loss=0.1382, simple_loss=0.2296, pruned_loss=0.02337, over 7331.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2517, pruned_loss=0.03573, over 1416791.49 frames.], batch size: 20, lr: 3.70e-04
+2022-05-15 02:45:04,658 INFO [train.py:812] (0/8) Epoch 21, batch 2700, loss[loss=0.1328, simple_loss=0.2154, pruned_loss=0.02514, over 7418.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2516, pruned_loss=0.03591, over 1420697.93 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:46:03,778 INFO [train.py:812] (0/8) Epoch 21, batch 2750, loss[loss=0.156, simple_loss=0.2474, pruned_loss=0.03229, over 7165.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2511, pruned_loss=0.03567, over 1422479.95 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:47:03,047 INFO [train.py:812] (0/8) Epoch 21, batch 2800, loss[loss=0.1697, simple_loss=0.2666, pruned_loss=0.03645, over 7378.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2505, pruned_loss=0.03512, over 1426042.48 frames.], batch size: 23, lr: 3.70e-04
+2022-05-15 02:48:12,156 INFO [train.py:812] (0/8) Epoch 21, batch 2850, loss[loss=0.1666, simple_loss=0.2549, pruned_loss=0.03914, over 7211.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2508, pruned_loss=0.03539, over 1420779.74 frames.], batch size: 23, lr: 3.69e-04
+2022-05-15 02:49:11,142 INFO [train.py:812] (0/8) Epoch 21, batch 2900, loss[loss=0.152, simple_loss=0.2544, pruned_loss=0.02482, over 7077.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2507, pruned_loss=0.03536, over 1417118.60 frames.], batch size: 28, lr: 3.69e-04
+2022-05-15 02:50:09,819 INFO [train.py:812] (0/8) Epoch 21, batch 2950, loss[loss=0.1542, simple_loss=0.2336, pruned_loss=0.03736, over 7348.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2512, pruned_loss=0.03515, over 1415874.70 frames.], batch size: 19, lr: 3.69e-04
+2022-05-15 02:51:09,044 INFO [train.py:812] (0/8) Epoch 21, batch 3000, loss[loss=0.1821, simple_loss=0.2816, pruned_loss=0.04129, over 6781.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2509, pruned_loss=0.03537, over 1414508.35 frames.], batch size: 31, lr: 3.69e-04
+2022-05-15 02:51:09,045 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 02:51:16,350 INFO [train.py:841] (0/8) Epoch 21, validation: loss=0.153, simple_loss=0.2519, pruned_loss=0.02704, over 698248.00 frames.
+2022-05-15 02:52:35,375 INFO [train.py:812] (0/8) Epoch 21, batch 3050, loss[loss=0.1528, simple_loss=0.2415, pruned_loss=0.03201, over 7284.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2504, pruned_loss=0.03505, over 1414947.17 frames.], batch size: 18, lr: 3.69e-04
+2022-05-15 02:53:32,969 INFO [train.py:812] (0/8) Epoch 21, batch 3100, loss[loss=0.157, simple_loss=0.2478, pruned_loss=0.03307, over 7361.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2504, pruned_loss=0.03519, over 1413502.30 frames.], batch size: 23, lr: 3.69e-04
+2022-05-15 02:55:01,534 INFO [train.py:812] (0/8) Epoch 21, batch 3150, loss[loss=0.1678, simple_loss=0.2631, pruned_loss=0.03629, over 7276.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2513, pruned_loss=0.03566, over 1418755.13 frames.], batch size: 24, lr: 3.69e-04
+2022-05-15 02:56:00,726 INFO [train.py:812] (0/8) Epoch 21, batch 3200, loss[loss=0.1543, simple_loss=0.2582, pruned_loss=0.02514, over 7311.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2527, pruned_loss=0.03613, over 1423464.43 frames.], batch size: 21, lr: 3.69e-04
+2022-05-15 02:57:00,459 INFO [train.py:812] (0/8) Epoch 21, batch 3250, loss[loss=0.132, simple_loss=0.2199, pruned_loss=0.02199, over 7075.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2523, pruned_loss=0.03618, over 1422850.56 frames.], batch size: 18, lr: 3.69e-04
+2022-05-15 02:58:08,767 INFO [train.py:812] (0/8) Epoch 21, batch 3300, loss[loss=0.1283, simple_loss=0.2122, pruned_loss=0.02222, over 7128.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2516, pruned_loss=0.03569, over 1423933.48 frames.], batch size: 17, lr: 3.69e-04
+2022-05-15 02:59:08,444 INFO [train.py:812] (0/8) Epoch 21, batch 3350, loss[loss=0.1619, simple_loss=0.2536, pruned_loss=0.03504, over 7238.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2511, pruned_loss=0.03549, over 1419593.76 frames.], batch size: 20, lr: 3.68e-04
+2022-05-15 03:00:06,801 INFO [train.py:812] (0/8) Epoch 21, batch 3400, loss[loss=0.1842, simple_loss=0.2733, pruned_loss=0.0475, over 6646.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2521, pruned_loss=0.03568, over 1416671.90 frames.], batch size: 38, lr: 3.68e-04
+2022-05-15 03:01:06,182 INFO [train.py:812] (0/8) Epoch 21, batch 3450, loss[loss=0.15, simple_loss=0.246, pruned_loss=0.02706, over 7324.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2528, pruned_loss=0.03647, over 1414497.55 frames.], batch size: 21, lr: 3.68e-04
+2022-05-15 03:02:05,069 INFO [train.py:812] (0/8) Epoch 21, batch 3500, loss[loss=0.1453, simple_loss=0.24, pruned_loss=0.02534, over 7006.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2527, pruned_loss=0.03607, over 1410090.51 frames.], batch size: 28, lr: 3.68e-04
+2022-05-15 03:03:04,199 INFO [train.py:812] (0/8) Epoch 21, batch 3550, loss[loss=0.1402, simple_loss=0.2223, pruned_loss=0.02904, over 7267.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2518, pruned_loss=0.03591, over 1414481.96 frames.], batch size: 17, lr: 3.68e-04
+2022-05-15 03:04:02,909 INFO [train.py:812] (0/8) Epoch 21, batch 3600, loss[loss=0.1672, simple_loss=0.2583, pruned_loss=0.03802, over 7397.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2531, pruned_loss=0.03653, over 1412894.51 frames.], batch size: 23, lr: 3.68e-04
+2022-05-15 03:05:02,878 INFO [train.py:812] (0/8) Epoch 21, batch 3650, loss[loss=0.1529, simple_loss=0.2404, pruned_loss=0.03266, over 7154.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2525, pruned_loss=0.03615, over 1414967.59 frames.], batch size: 26, lr: 3.68e-04
+2022-05-15 03:06:01,338 INFO [train.py:812] (0/8) Epoch 21, batch 3700, loss[loss=0.173, simple_loss=0.2687, pruned_loss=0.03864, over 7320.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2527, pruned_loss=0.03602, over 1414525.77 frames.], batch size: 21, lr: 3.68e-04
+2022-05-15 03:07:01,113 INFO [train.py:812] (0/8) Epoch 21, batch 3750, loss[loss=0.1919, simple_loss=0.2855, pruned_loss=0.04919, over 7289.00 frames.], tot_loss[loss=0.1617, simple_loss=0.252, pruned_loss=0.03568, over 1418118.13 frames.], batch size: 25, lr: 3.68e-04
+2022-05-15 03:07:59,610 INFO [train.py:812] (0/8) Epoch 21, batch 3800, loss[loss=0.1783, simple_loss=0.2623, pruned_loss=0.04715, over 7160.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2513, pruned_loss=0.03548, over 1419016.22 frames.], batch size: 26, lr: 3.68e-04
+2022-05-15 03:08:58,694 INFO [train.py:812] (0/8) Epoch 21, batch 3850, loss[loss=0.1772, simple_loss=0.2765, pruned_loss=0.03895, over 7331.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2517, pruned_loss=0.03524, over 1419122.06 frames.], batch size: 20, lr: 3.68e-04
+2022-05-15 03:09:55,535 INFO [train.py:812] (0/8) Epoch 21, batch 3900, loss[loss=0.152, simple_loss=0.2421, pruned_loss=0.03096, over 7264.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2514, pruned_loss=0.03498, over 1423751.43 frames.], batch size: 19, lr: 3.67e-04
+2022-05-15 03:10:53,474 INFO [train.py:812] (0/8) Epoch 21, batch 3950, loss[loss=0.1592, simple_loss=0.245, pruned_loss=0.03673, over 7414.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2526, pruned_loss=0.03529, over 1419196.64 frames.], batch size: 18, lr: 3.67e-04
+2022-05-15 03:11:51,923 INFO [train.py:812] (0/8) Epoch 21, batch 4000, loss[loss=0.1608, simple_loss=0.2568, pruned_loss=0.03243, over 7356.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2523, pruned_loss=0.03541, over 1422774.83 frames.], batch size: 19, lr: 3.67e-04
+2022-05-15 03:12:50,952 INFO [train.py:812] (0/8) Epoch 21, batch 4050, loss[loss=0.2019, simple_loss=0.2932, pruned_loss=0.05527, over 5123.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2509, pruned_loss=0.03505, over 1419550.01 frames.], batch size: 52, lr: 3.67e-04
+2022-05-15 03:13:49,288 INFO [train.py:812] (0/8) Epoch 21, batch 4100, loss[loss=0.1483, simple_loss=0.2409, pruned_loss=0.02782, over 7223.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2514, pruned_loss=0.03567, over 1412116.53 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:14:46,147 INFO [train.py:812] (0/8) Epoch 21, batch 4150, loss[loss=0.1508, simple_loss=0.2528, pruned_loss=0.02442, over 7065.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2522, pruned_loss=0.03581, over 1413234.30 frames.], batch size: 18, lr: 3.67e-04
+2022-05-15 03:15:44,003 INFO [train.py:812] (0/8) Epoch 21, batch 4200, loss[loss=0.1604, simple_loss=0.252, pruned_loss=0.0344, over 6773.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2523, pruned_loss=0.03599, over 1412435.73 frames.], batch size: 31, lr: 3.67e-04
+2022-05-15 03:16:29,196 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-96000.pt
+2022-05-15 03:16:47,804 INFO [train.py:812] (0/8) Epoch 21, batch 4250, loss[loss=0.1638, simple_loss=0.2579, pruned_loss=0.03479, over 7225.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2512, pruned_loss=0.03556, over 1416782.50 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:17:46,890 INFO [train.py:812] (0/8) Epoch 21, batch 4300, loss[loss=0.1936, simple_loss=0.2824, pruned_loss=0.0524, over 7289.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2504, pruned_loss=0.03517, over 1418196.72 frames.], batch size: 24, lr: 3.67e-04
+2022-05-15 03:18:45,856 INFO [train.py:812] (0/8) Epoch 21, batch 4350, loss[loss=0.2136, simple_loss=0.2806, pruned_loss=0.07334, over 7223.00 frames.], tot_loss[loss=0.1609, simple_loss=0.251, pruned_loss=0.03545, over 1417830.40 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:19:43,103 INFO [train.py:812] (0/8) Epoch 21, batch 4400, loss[loss=0.1473, simple_loss=0.2331, pruned_loss=0.0307, over 7162.00 frames.], tot_loss[loss=0.161, simple_loss=0.2512, pruned_loss=0.03542, over 1415575.94 frames.], batch size: 18, lr: 3.66e-04
+2022-05-15 03:20:42,007 INFO [train.py:812] (0/8) Epoch 21, batch 4450, loss[loss=0.1573, simple_loss=0.2343, pruned_loss=0.04016, over 6989.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2519, pruned_loss=0.03584, over 1407817.88 frames.], batch size: 16, lr: 3.66e-04
+2022-05-15 03:21:40,277 INFO [train.py:812] (0/8) Epoch 21, batch 4500, loss[loss=0.1359, simple_loss=0.2162, pruned_loss=0.02774, over 7016.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2522, pruned_loss=0.03583, over 1410191.59 frames.], batch size: 16, lr: 3.66e-04
+2022-05-15 03:22:40,011 INFO [train.py:812] (0/8) Epoch 21, batch 4550, loss[loss=0.1887, simple_loss=0.2701, pruned_loss=0.05367, over 5090.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2513, pruned_loss=0.03593, over 1394283.07 frames.], batch size: 53, lr: 3.66e-04
+2022-05-15 03:23:24,885 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-21.pt
+2022-05-15 03:23:52,239 INFO [train.py:812] (0/8) Epoch 22, batch 0, loss[loss=0.1698, simple_loss=0.2679, pruned_loss=0.03582, over 7270.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2679, pruned_loss=0.03582, over 7270.00 frames.], batch size: 25, lr: 3.58e-04
+2022-05-15 03:24:50,212 INFO [train.py:812] (0/8) Epoch 22, batch 50, loss[loss=0.136, simple_loss=0.2282, pruned_loss=0.02189, over 7158.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2528, pruned_loss=0.03508, over 318144.76 frames.], batch size: 18, lr: 3.58e-04
+2022-05-15 03:25:49,151 INFO [train.py:812] (0/8) Epoch 22, batch 100, loss[loss=0.1719, simple_loss=0.2642, pruned_loss=0.03975, over 7118.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2522, pruned_loss=0.03581, over 564371.45 frames.], batch size: 21, lr: 3.58e-04
+2022-05-15 03:26:47,181 INFO [train.py:812] (0/8) Epoch 22, batch 150, loss[loss=0.1729, simple_loss=0.2694, pruned_loss=0.03823, over 7313.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2512, pruned_loss=0.03507, over 753791.24 frames.], batch size: 21, lr: 3.58e-04
+2022-05-15 03:27:46,074 INFO [train.py:812] (0/8) Epoch 22, batch 200, loss[loss=0.1504, simple_loss=0.2484, pruned_loss=0.02621, over 7332.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2494, pruned_loss=0.03384, over 901565.87 frames.], batch size: 22, lr: 3.58e-04
+2022-05-15 03:28:43,580 INFO [train.py:812] (0/8) Epoch 22, batch 250, loss[loss=0.1544, simple_loss=0.2391, pruned_loss=0.03484, over 7259.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2505, pruned_loss=0.03483, over 1015242.33 frames.], batch size: 19, lr: 3.57e-04
+2022-05-15 03:29:41,565 INFO [train.py:812] (0/8) Epoch 22, batch 300, loss[loss=0.1603, simple_loss=0.2534, pruned_loss=0.03362, over 7232.00 frames.], tot_loss[loss=0.1607, simple_loss=0.251, pruned_loss=0.03525, over 1107851.42 frames.], batch size: 20, lr: 3.57e-04
+2022-05-15 03:30:39,462 INFO [train.py:812] (0/8) Epoch 22, batch 350, loss[loss=0.1578, simple_loss=0.2521, pruned_loss=0.03178, over 7169.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2495, pruned_loss=0.03457, over 1178682.68 frames.], batch size: 19, lr: 3.57e-04
+2022-05-15 03:31:38,300 INFO [train.py:812] (0/8) Epoch 22, batch 400, loss[loss=0.1784, simple_loss=0.2846, pruned_loss=0.0361, over 7219.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2494, pruned_loss=0.03416, over 1230699.90 frames.], batch size: 21, lr: 3.57e-04
+2022-05-15 03:32:37,208 INFO [train.py:812] (0/8) Epoch 22, batch 450, loss[loss=0.2012, simple_loss=0.2922, pruned_loss=0.0551, over 5165.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2483, pruned_loss=0.0336, over 1274005.11 frames.], batch size: 52, lr: 3.57e-04
+2022-05-15 03:33:36,426 INFO [train.py:812] (0/8) Epoch 22, batch 500, loss[loss=0.2122, simple_loss=0.3017, pruned_loss=0.06135, over 7299.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2499, pruned_loss=0.03409, over 1309812.64 frames.], batch size: 25, lr: 3.57e-04
+2022-05-15 03:34:33,239 INFO [train.py:812] (0/8) Epoch 22, batch 550, loss[loss=0.1372, simple_loss=0.2252, pruned_loss=0.0246, over 7422.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2506, pruned_loss=0.03451, over 1332493.03 frames.], batch size: 20, lr: 3.57e-04
+2022-05-15 03:35:32,159 INFO [train.py:812] (0/8) Epoch 22, batch 600, loss[loss=0.172, simple_loss=0.2635, pruned_loss=0.04024, over 7346.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2494, pruned_loss=0.03437, over 1354047.84 frames.], batch size: 22, lr: 3.57e-04
+2022-05-15 03:36:31,009 INFO [train.py:812] (0/8) Epoch 22, batch 650, loss[loss=0.1534, simple_loss=0.2582, pruned_loss=0.02433, over 7344.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2503, pruned_loss=0.03443, over 1370401.22 frames.], batch size: 22, lr: 3.57e-04
+2022-05-15 03:37:30,481 INFO [train.py:812] (0/8) Epoch 22, batch 700, loss[loss=0.1937, simple_loss=0.2887, pruned_loss=0.04931, over 7300.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2509, pruned_loss=0.03463, over 1379278.87 frames.], batch size: 25, lr: 3.57e-04
+2022-05-15 03:38:28,461 INFO [train.py:812] (0/8) Epoch 22, batch 750, loss[loss=0.1646, simple_loss=0.241, pruned_loss=0.04407, over 7170.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2511, pruned_loss=0.03491, over 1387061.08 frames.], batch size: 18, lr: 3.57e-04
+2022-05-15 03:39:28,329 INFO [train.py:812] (0/8) Epoch 22, batch 800, loss[loss=0.1941, simple_loss=0.2806, pruned_loss=0.05382, over 7318.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2514, pruned_loss=0.03501, over 1399551.97 frames.], batch size: 25, lr: 3.56e-04
+2022-05-15 03:40:27,683 INFO [train.py:812] (0/8) Epoch 22, batch 850, loss[loss=0.1444, simple_loss=0.2336, pruned_loss=0.02762, over 7409.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2501, pruned_loss=0.0345, over 1404933.79 frames.], batch size: 18, lr: 3.56e-04
+2022-05-15 03:41:26,076 INFO [train.py:812] (0/8) Epoch 22, batch 900, loss[loss=0.1719, simple_loss=0.2634, pruned_loss=0.04018, over 6104.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2501, pruned_loss=0.03421, over 1407838.55 frames.], batch size: 37, lr: 3.56e-04
+2022-05-15 03:42:25,446 INFO [train.py:812] (0/8) Epoch 22, batch 950, loss[loss=0.1257, simple_loss=0.2133, pruned_loss=0.01909, over 7277.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2503, pruned_loss=0.03451, over 1410275.44 frames.], batch size: 18, lr: 3.56e-04
+2022-05-15 03:43:24,214 INFO [train.py:812] (0/8) Epoch 22, batch 1000, loss[loss=0.1613, simple_loss=0.2627, pruned_loss=0.02998, over 7162.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2517, pruned_loss=0.03506, over 1410997.28 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:44:23,518 INFO [train.py:812] (0/8) Epoch 22, batch 1050, loss[loss=0.1605, simple_loss=0.2515, pruned_loss=0.03474, over 7328.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2501, pruned_loss=0.03482, over 1414722.78 frames.], batch size: 22, lr: 3.56e-04
+2022-05-15 03:45:23,075 INFO [train.py:812] (0/8) Epoch 22, batch 1100, loss[loss=0.2087, simple_loss=0.2908, pruned_loss=0.06326, over 6389.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2505, pruned_loss=0.03491, over 1418522.43 frames.], batch size: 38, lr: 3.56e-04
+2022-05-15 03:46:20,337 INFO [train.py:812] (0/8) Epoch 22, batch 1150, loss[loss=0.1694, simple_loss=0.2474, pruned_loss=0.04569, over 7257.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2507, pruned_loss=0.03473, over 1419511.17 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:47:19,431 INFO [train.py:812] (0/8) Epoch 22, batch 1200, loss[loss=0.1583, simple_loss=0.241, pruned_loss=0.03778, over 7319.00 frames.], tot_loss[loss=0.1598, simple_loss=0.25, pruned_loss=0.03481, over 1420926.20 frames.], batch size: 25, lr: 3.56e-04
+2022-05-15 03:48:18,940 INFO [train.py:812] (0/8) Epoch 22, batch 1250, loss[loss=0.1346, simple_loss=0.2159, pruned_loss=0.02669, over 7009.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2504, pruned_loss=0.03521, over 1419442.43 frames.], batch size: 16, lr: 3.56e-04
+2022-05-15 03:49:19,106 INFO [train.py:812] (0/8) Epoch 22, batch 1300, loss[loss=0.1539, simple_loss=0.2451, pruned_loss=0.03132, over 7150.00 frames.], tot_loss[loss=0.16, simple_loss=0.2501, pruned_loss=0.035, over 1418956.51 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:50:16,172 INFO [train.py:812] (0/8) Epoch 22, batch 1350, loss[loss=0.1808, simple_loss=0.2689, pruned_loss=0.04634, over 7411.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2493, pruned_loss=0.03486, over 1423440.23 frames.], batch size: 21, lr: 3.55e-04
+2022-05-15 03:51:15,336 INFO [train.py:812] (0/8) Epoch 22, batch 1400, loss[loss=0.1905, simple_loss=0.2791, pruned_loss=0.05096, over 7211.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2493, pruned_loss=0.03491, over 1419770.30 frames.], batch size: 22, lr: 3.55e-04
+2022-05-15 03:52:14,151 INFO [train.py:812] (0/8) Epoch 22, batch 1450, loss[loss=0.1614, simple_loss=0.2466, pruned_loss=0.03813, over 7439.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2495, pruned_loss=0.03481, over 1424245.30 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:53:13,892 INFO [train.py:812] (0/8) Epoch 22, batch 1500, loss[loss=0.1521, simple_loss=0.238, pruned_loss=0.03307, over 7238.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2492, pruned_loss=0.03464, over 1427365.93 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:54:13,330 INFO [train.py:812] (0/8) Epoch 22, batch 1550, loss[loss=0.1652, simple_loss=0.2601, pruned_loss=0.03511, over 7230.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2487, pruned_loss=0.03459, over 1429555.65 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:55:12,243 INFO [train.py:812] (0/8) Epoch 22, batch 1600, loss[loss=0.1212, simple_loss=0.2075, pruned_loss=0.01751, over 6777.00 frames.], tot_loss[loss=0.159, simple_loss=0.2488, pruned_loss=0.03465, over 1430407.77 frames.], batch size: 15, lr: 3.55e-04
+2022-05-15 03:56:08,994 INFO [train.py:812] (0/8) Epoch 22, batch 1650, loss[loss=0.1717, simple_loss=0.2678, pruned_loss=0.03776, over 6715.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2493, pruned_loss=0.03456, over 1432272.34 frames.], batch size: 31, lr: 3.55e-04
+2022-05-15 03:57:06,975 INFO [train.py:812] (0/8) Epoch 22, batch 1700, loss[loss=0.1662, simple_loss=0.2601, pruned_loss=0.03611, over 7344.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2487, pruned_loss=0.03435, over 1434627.54 frames.], batch size: 22, lr: 3.55e-04
+2022-05-15 03:58:03,880 INFO [train.py:812] (0/8) Epoch 22, batch 1750, loss[loss=0.1693, simple_loss=0.2669, pruned_loss=0.03587, over 7235.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2489, pruned_loss=0.03416, over 1433535.44 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:59:03,624 INFO [train.py:812] (0/8) Epoch 22, batch 1800, loss[loss=0.1239, simple_loss=0.2034, pruned_loss=0.02213, over 7289.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2484, pruned_loss=0.03442, over 1430937.87 frames.], batch size: 17, lr: 3.55e-04
+2022-05-15 04:00:02,104 INFO [train.py:812] (0/8) Epoch 22, batch 1850, loss[loss=0.1567, simple_loss=0.2526, pruned_loss=0.03038, over 6280.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2494, pruned_loss=0.0347, over 1426459.59 frames.], batch size: 37, lr: 3.55e-04
+2022-05-15 04:01:00,928 INFO [train.py:812] (0/8) Epoch 22, batch 1900, loss[loss=0.1964, simple_loss=0.2742, pruned_loss=0.05927, over 4890.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2494, pruned_loss=0.0347, over 1424590.42 frames.], batch size: 52, lr: 3.54e-04
+2022-05-15 04:02:00,206 INFO [train.py:812] (0/8) Epoch 22, batch 1950, loss[loss=0.1678, simple_loss=0.2333, pruned_loss=0.05113, over 7289.00 frames.], tot_loss[loss=0.16, simple_loss=0.2498, pruned_loss=0.03514, over 1425204.47 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:02:59,572 INFO [train.py:812] (0/8) Epoch 22, batch 2000, loss[loss=0.1812, simple_loss=0.2835, pruned_loss=0.03951, over 7329.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2498, pruned_loss=0.03476, over 1427730.47 frames.], batch size: 20, lr: 3.54e-04
+2022-05-15 04:03:58,500 INFO [train.py:812] (0/8) Epoch 22, batch 2050, loss[loss=0.1531, simple_loss=0.2364, pruned_loss=0.03488, over 7264.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2505, pruned_loss=0.03484, over 1429067.72 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:04:58,171 INFO [train.py:812] (0/8) Epoch 22, batch 2100, loss[loss=0.1649, simple_loss=0.2442, pruned_loss=0.04284, over 7427.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2511, pruned_loss=0.03466, over 1428230.82 frames.], batch size: 18, lr: 3.54e-04
+2022-05-15 04:05:56,579 INFO [train.py:812] (0/8) Epoch 22, batch 2150, loss[loss=0.1408, simple_loss=0.2316, pruned_loss=0.02496, over 7181.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2508, pruned_loss=0.03481, over 1424338.45 frames.], batch size: 18, lr: 3.54e-04
+2022-05-15 04:06:54,944 INFO [train.py:812] (0/8) Epoch 22, batch 2200, loss[loss=0.17, simple_loss=0.2631, pruned_loss=0.03844, over 7115.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2502, pruned_loss=0.03418, over 1426337.98 frames.], batch size: 21, lr: 3.54e-04
+2022-05-15 04:07:52,610 INFO [train.py:812] (0/8) Epoch 22, batch 2250, loss[loss=0.1461, simple_loss=0.2353, pruned_loss=0.02852, over 6842.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2505, pruned_loss=0.03443, over 1423704.79 frames.], batch size: 15, lr: 3.54e-04
+2022-05-15 04:08:49,583 INFO [train.py:812] (0/8) Epoch 22, batch 2300, loss[loss=0.2014, simple_loss=0.286, pruned_loss=0.05842, over 4962.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2505, pruned_loss=0.0346, over 1425022.43 frames.], batch size: 53, lr: 3.54e-04
+2022-05-15 04:09:47,971 INFO [train.py:812] (0/8) Epoch 22, batch 2350, loss[loss=0.1627, simple_loss=0.2548, pruned_loss=0.0353, over 6347.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2501, pruned_loss=0.03481, over 1426685.64 frames.], batch size: 38, lr: 3.54e-04
+2022-05-15 04:10:57,206 INFO [train.py:812] (0/8) Epoch 22, batch 2400, loss[loss=0.1582, simple_loss=0.2432, pruned_loss=0.03663, over 7134.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2502, pruned_loss=0.03503, over 1426372.92 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:11:56,415 INFO [train.py:812] (0/8) Epoch 22, batch 2450, loss[loss=0.131, simple_loss=0.2182, pruned_loss=0.02194, over 7263.00 frames.], tot_loss[loss=0.1597, simple_loss=0.25, pruned_loss=0.03466, over 1425068.84 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:12:56,105 INFO [train.py:812] (0/8) Epoch 22, batch 2500, loss[loss=0.1605, simple_loss=0.2462, pruned_loss=0.03737, over 7406.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2499, pruned_loss=0.0344, over 1423964.00 frames.], batch size: 21, lr: 3.53e-04
+2022-05-15 04:13:55,276 INFO [train.py:812] (0/8) Epoch 22, batch 2550, loss[loss=0.1883, simple_loss=0.2718, pruned_loss=0.05238, over 7064.00 frames.], tot_loss[loss=0.16, simple_loss=0.2503, pruned_loss=0.03482, over 1421901.34 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:14:54,427 INFO [train.py:812] (0/8) Epoch 22, batch 2600, loss[loss=0.1508, simple_loss=0.2397, pruned_loss=0.03091, over 7159.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2512, pruned_loss=0.03488, over 1417912.01 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:15:53,313 INFO [train.py:812] (0/8) Epoch 22, batch 2650, loss[loss=0.1528, simple_loss=0.2523, pruned_loss=0.02667, over 7250.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2499, pruned_loss=0.03436, over 1421390.10 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:16:52,247 INFO [train.py:812] (0/8) Epoch 22, batch 2700, loss[loss=0.145, simple_loss=0.2301, pruned_loss=0.02993, over 7149.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2488, pruned_loss=0.03404, over 1420282.30 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:17:51,009 INFO [train.py:812] (0/8) Epoch 22, batch 2750, loss[loss=0.1643, simple_loss=0.2514, pruned_loss=0.03858, over 7065.00 frames.], tot_loss[loss=0.1583, simple_loss=0.249, pruned_loss=0.03382, over 1420318.54 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:18:49,820 INFO [train.py:812] (0/8) Epoch 22, batch 2800, loss[loss=0.1307, simple_loss=0.2193, pruned_loss=0.02106, over 7277.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2489, pruned_loss=0.034, over 1420383.54 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:19:48,486 INFO [train.py:812] (0/8) Epoch 22, batch 2850, loss[loss=0.1716, simple_loss=0.2694, pruned_loss=0.03687, over 7153.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2489, pruned_loss=0.03441, over 1418873.03 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:20:47,853 INFO [train.py:812] (0/8) Epoch 22, batch 2900, loss[loss=0.1448, simple_loss=0.2359, pruned_loss=0.02683, over 7171.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2492, pruned_loss=0.03432, over 1421080.44 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:21:47,291 INFO [train.py:812] (0/8) Epoch 22, batch 2950, loss[loss=0.152, simple_loss=0.2485, pruned_loss=0.02773, over 7424.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2487, pruned_loss=0.03425, over 1421234.05 frames.], batch size: 21, lr: 3.53e-04
+2022-05-15 04:22:47,056 INFO [train.py:812] (0/8) Epoch 22, batch 3000, loss[loss=0.136, simple_loss=0.2216, pruned_loss=0.02521, over 7161.00 frames.], tot_loss[loss=0.1586, simple_loss=0.249, pruned_loss=0.03412, over 1424997.17 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:22:47,057 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 04:22:54,482 INFO [train.py:841] (0/8) Epoch 22, validation: loss=0.1529, simple_loss=0.2512, pruned_loss=0.02731, over 698248.00 frames.
+2022-05-15 04:23:53,733 INFO [train.py:812] (0/8) Epoch 22, batch 3050, loss[loss=0.174, simple_loss=0.2722, pruned_loss=0.03785, over 7079.00 frames.], tot_loss[loss=0.159, simple_loss=0.2492, pruned_loss=0.03437, over 1426839.57 frames.], batch size: 28, lr: 3.52e-04
+2022-05-15 04:24:53,790 INFO [train.py:812] (0/8) Epoch 22, batch 3100, loss[loss=0.1797, simple_loss=0.2657, pruned_loss=0.04685, over 5060.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2495, pruned_loss=0.03452, over 1427349.75 frames.], batch size: 52, lr: 3.52e-04
+2022-05-15 04:25:52,322 INFO [train.py:812] (0/8) Epoch 22, batch 3150, loss[loss=0.2001, simple_loss=0.2807, pruned_loss=0.05972, over 7422.00 frames.], tot_loss[loss=0.159, simple_loss=0.249, pruned_loss=0.03451, over 1424964.38 frames.], batch size: 21, lr: 3.52e-04
+2022-05-15 04:26:51,070 INFO [train.py:812] (0/8) Epoch 22, batch 3200, loss[loss=0.1562, simple_loss=0.2501, pruned_loss=0.03112, over 7068.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2494, pruned_loss=0.03481, over 1426489.42 frames.], batch size: 18, lr: 3.52e-04
+2022-05-15 04:27:50,267 INFO [train.py:812] (0/8) Epoch 22, batch 3250, loss[loss=0.1473, simple_loss=0.2256, pruned_loss=0.03447, over 7009.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2507, pruned_loss=0.03514, over 1427445.49 frames.], batch size: 16, lr: 3.52e-04
+2022-05-15 04:28:47,782 INFO [train.py:812] (0/8) Epoch 22, batch 3300, loss[loss=0.1611, simple_loss=0.2469, pruned_loss=0.03765, over 7427.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2514, pruned_loss=0.03518, over 1429396.68 frames.], batch size: 20, lr: 3.52e-04
+2022-05-15 04:29:46,916 INFO [train.py:812] (0/8) Epoch 22, batch 3350, loss[loss=0.1489, simple_loss=0.2376, pruned_loss=0.03009, over 7362.00 frames.], tot_loss[loss=0.1614, simple_loss=0.252, pruned_loss=0.03539, over 1428446.15 frames.], batch size: 19, lr: 3.52e-04
+2022-05-15 04:30:46,470 INFO [train.py:812] (0/8) Epoch 22, batch 3400, loss[loss=0.1851, simple_loss=0.259, pruned_loss=0.05561, over 7143.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2511, pruned_loss=0.03497, over 1425472.47 frames.], batch size: 17, lr: 3.52e-04
+2022-05-15 04:31:45,547 INFO [train.py:812] (0/8) Epoch 22, batch 3450, loss[loss=0.1713, simple_loss=0.2701, pruned_loss=0.03623, over 7333.00 frames.], tot_loss[loss=0.1611, simple_loss=0.252, pruned_loss=0.03504, over 1426624.71 frames.], batch size: 22, lr: 3.52e-04
+2022-05-15 04:32:45,114 INFO [train.py:812] (0/8) Epoch 22, batch 3500, loss[loss=0.1539, simple_loss=0.2523, pruned_loss=0.02771, over 7332.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2514, pruned_loss=0.035, over 1429660.53 frames.], batch size: 22, lr: 3.52e-04
+2022-05-15 04:33:44,159 INFO [train.py:812] (0/8) Epoch 22, batch 3550, loss[loss=0.1699, simple_loss=0.2678, pruned_loss=0.03597, over 6779.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2527, pruned_loss=0.03546, over 1427684.15 frames.], batch size: 31, lr: 3.52e-04
+2022-05-15 04:34:43,562 INFO [train.py:812] (0/8) Epoch 22, batch 3600, loss[loss=0.1566, simple_loss=0.2372, pruned_loss=0.03799, over 7298.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2518, pruned_loss=0.03539, over 1422156.55 frames.], batch size: 17, lr: 3.51e-04
+2022-05-15 04:35:42,254 INFO [train.py:812] (0/8) Epoch 22, batch 3650, loss[loss=0.1867, simple_loss=0.2795, pruned_loss=0.047, over 7397.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2515, pruned_loss=0.03495, over 1424324.31 frames.], batch size: 23, lr: 3.51e-04
+2022-05-15 04:35:43,900 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-100000.pt
+2022-05-15 04:36:47,253 INFO [train.py:812] (0/8) Epoch 22, batch 3700, loss[loss=0.1721, simple_loss=0.2709, pruned_loss=0.03663, over 7222.00 frames.], tot_loss[loss=0.16, simple_loss=0.251, pruned_loss=0.03448, over 1426279.99 frames.], batch size: 21, lr: 3.51e-04
+2022-05-15 04:37:46,564 INFO [train.py:812] (0/8) Epoch 22, batch 3750, loss[loss=0.1711, simple_loss=0.241, pruned_loss=0.05064, over 6998.00 frames.], tot_loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03431, over 1430742.17 frames.], batch size: 16, lr: 3.51e-04
+2022-05-15 04:38:46,118 INFO [train.py:812] (0/8) Epoch 22, batch 3800, loss[loss=0.2041, simple_loss=0.274, pruned_loss=0.06713, over 4820.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03428, over 1424706.90 frames.], batch size: 52, lr: 3.51e-04
+2022-05-15 04:39:43,945 INFO [train.py:812] (0/8) Epoch 22, batch 3850, loss[loss=0.1982, simple_loss=0.2863, pruned_loss=0.05504, over 7224.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2499, pruned_loss=0.03429, over 1427519.22 frames.], batch size: 20, lr: 3.51e-04
+2022-05-15 04:40:43,465 INFO [train.py:812] (0/8) Epoch 22, batch 3900, loss[loss=0.1415, simple_loss=0.2423, pruned_loss=0.0204, over 6296.00 frames.], tot_loss[loss=0.159, simple_loss=0.2496, pruned_loss=0.03422, over 1427660.22 frames.], batch size: 37, lr: 3.51e-04
+2022-05-15 04:41:41,333 INFO [train.py:812] (0/8) Epoch 22, batch 3950, loss[loss=0.1397, simple_loss=0.2215, pruned_loss=0.02899, over 7273.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2491, pruned_loss=0.03427, over 1425637.83 frames.], batch size: 17, lr: 3.51e-04
+2022-05-15 04:42:39,862 INFO [train.py:812] (0/8) Epoch 22, batch 4000, loss[loss=0.1619, simple_loss=0.2619, pruned_loss=0.03091, over 7318.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2503, pruned_loss=0.03456, over 1425230.95 frames.], batch size: 21, lr: 3.51e-04
+2022-05-15 04:43:37,306 INFO [train.py:812] (0/8) Epoch 22, batch 4050, loss[loss=0.1329, simple_loss=0.2313, pruned_loss=0.01724, over 7347.00 frames.], tot_loss[loss=0.159, simple_loss=0.2497, pruned_loss=0.03418, over 1423339.48 frames.], batch size: 19, lr: 3.51e-04
+2022-05-15 04:44:35,688 INFO [train.py:812] (0/8) Epoch 22, batch 4100, loss[loss=0.1352, simple_loss=0.2264, pruned_loss=0.02199, over 7318.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2502, pruned_loss=0.03408, over 1425126.73 frames.], batch size: 20, lr: 3.51e-04
+2022-05-15 04:45:34,867 INFO [train.py:812] (0/8) Epoch 22, batch 4150, loss[loss=0.1482, simple_loss=0.2422, pruned_loss=0.0271, over 7070.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2494, pruned_loss=0.03414, over 1419445.19 frames.], batch size: 18, lr: 3.51e-04
+2022-05-15 04:46:33,516 INFO [train.py:812] (0/8) Epoch 22, batch 4200, loss[loss=0.1869, simple_loss=0.2719, pruned_loss=0.05093, over 7148.00 frames.], tot_loss[loss=0.1595, simple_loss=0.25, pruned_loss=0.03452, over 1414960.84 frames.], batch size: 20, lr: 3.50e-04
+2022-05-15 04:47:30,297 INFO [train.py:812] (0/8) Epoch 22, batch 4250, loss[loss=0.1489, simple_loss=0.2464, pruned_loss=0.02566, over 6786.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2512, pruned_loss=0.03509, over 1408503.89 frames.], batch size: 31, lr: 3.50e-04
+2022-05-15 04:48:27,357 INFO [train.py:812] (0/8) Epoch 22, batch 4300, loss[loss=0.1861, simple_loss=0.2818, pruned_loss=0.04518, over 7289.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2513, pruned_loss=0.03472, over 1410659.12 frames.], batch size: 24, lr: 3.50e-04
+2022-05-15 04:49:26,474 INFO [train.py:812] (0/8) Epoch 22, batch 4350, loss[loss=0.1661, simple_loss=0.2589, pruned_loss=0.0366, over 7336.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2514, pruned_loss=0.03465, over 1407820.43 frames.], batch size: 22, lr: 3.50e-04
+2022-05-15 04:50:35,268 INFO [train.py:812] (0/8) Epoch 22, batch 4400, loss[loss=0.1514, simple_loss=0.2372, pruned_loss=0.03276, over 7113.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2511, pruned_loss=0.03458, over 1403059.59 frames.], batch size: 21, lr: 3.50e-04
+2022-05-15 04:51:33,775 INFO [train.py:812] (0/8) Epoch 22, batch 4450, loss[loss=0.1745, simple_loss=0.2707, pruned_loss=0.03917, over 7347.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2516, pruned_loss=0.03474, over 1398735.89 frames.], batch size: 22, lr: 3.50e-04
+2022-05-15 04:52:33,289 INFO [train.py:812] (0/8) Epoch 22, batch 4500, loss[loss=0.1704, simple_loss=0.262, pruned_loss=0.03939, over 7076.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2532, pruned_loss=0.03563, over 1388719.78 frames.], batch size: 28, lr: 3.50e-04
+2022-05-15 04:53:50,565 INFO [train.py:812] (0/8) Epoch 22, batch 4550, loss[loss=0.1856, simple_loss=0.2644, pruned_loss=0.05346, over 4891.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2554, pruned_loss=0.03711, over 1349490.90 frames.], batch size: 53, lr: 3.50e-04
+2022-05-15 04:55:04,210 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-22.pt
+2022-05-15 04:55:29,969 INFO [train.py:812] (0/8) Epoch 23, batch 0, loss[loss=0.1395, simple_loss=0.2192, pruned_loss=0.02992, over 6831.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2192, pruned_loss=0.02992, over 6831.00 frames.], batch size: 15, lr: 3.42e-04
+2022-05-15 04:56:28,540 INFO [train.py:812] (0/8) Epoch 23, batch 50, loss[loss=0.1463, simple_loss=0.2429, pruned_loss=0.02488, over 7153.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2499, pruned_loss=0.03385, over 319144.94 frames.], batch size: 19, lr: 3.42e-04
+2022-05-15 04:57:26,786 INFO [train.py:812] (0/8) Epoch 23, batch 100, loss[loss=0.1511, simple_loss=0.2335, pruned_loss=0.03435, over 7280.00 frames.], tot_loss[loss=0.16, simple_loss=0.2518, pruned_loss=0.0341, over 566358.21 frames.], batch size: 18, lr: 3.42e-04
+2022-05-15 04:58:25,159 INFO [train.py:812] (0/8) Epoch 23, batch 150, loss[loss=0.1584, simple_loss=0.2579, pruned_loss=0.02945, over 7281.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2523, pruned_loss=0.03474, over 753487.48 frames.], batch size: 24, lr: 3.42e-04
+2022-05-15 04:59:34,125 INFO [train.py:812] (0/8) Epoch 23, batch 200, loss[loss=0.1819, simple_loss=0.273, pruned_loss=0.04535, over 6492.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2523, pruned_loss=0.03472, over 901800.17 frames.], batch size: 38, lr: 3.42e-04
+2022-05-15 05:00:33,218 INFO [train.py:812] (0/8) Epoch 23, batch 250, loss[loss=0.1811, simple_loss=0.2782, pruned_loss=0.04198, over 7189.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2519, pruned_loss=0.03439, over 1017299.80 frames.], batch size: 23, lr: 3.42e-04
+2022-05-15 05:01:30,502 INFO [train.py:812] (0/8) Epoch 23, batch 300, loss[loss=0.1473, simple_loss=0.2293, pruned_loss=0.03262, over 7162.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2512, pruned_loss=0.03416, over 1103117.33 frames.], batch size: 19, lr: 3.42e-04
+2022-05-15 05:02:29,197 INFO [train.py:812] (0/8) Epoch 23, batch 350, loss[loss=0.1375, simple_loss=0.2312, pruned_loss=0.0219, over 7330.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2504, pruned_loss=0.03375, over 1178305.47 frames.], batch size: 22, lr: 3.42e-04
+2022-05-15 05:03:27,249 INFO [train.py:812] (0/8) Epoch 23, batch 400, loss[loss=0.1509, simple_loss=0.2383, pruned_loss=0.03179, over 7205.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2498, pruned_loss=0.03359, over 1232074.92 frames.], batch size: 23, lr: 3.42e-04
+2022-05-15 05:04:26,523 INFO [train.py:812] (0/8) Epoch 23, batch 450, loss[loss=0.1764, simple_loss=0.2668, pruned_loss=0.04297, over 7292.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2506, pruned_loss=0.03391, over 1273365.67 frames.], batch size: 24, lr: 3.42e-04
+2022-05-15 05:05:24,827 INFO [train.py:812] (0/8) Epoch 23, batch 500, loss[loss=0.1408, simple_loss=0.2258, pruned_loss=0.02788, over 6812.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2502, pruned_loss=0.03362, over 1308037.04 frames.], batch size: 15, lr: 3.41e-04
+2022-05-15 05:06:21,993 INFO [train.py:812] (0/8) Epoch 23, batch 550, loss[loss=0.1847, simple_loss=0.2763, pruned_loss=0.04659, over 7296.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2493, pruned_loss=0.03354, over 1337363.80 frames.], batch size: 24, lr: 3.41e-04
+2022-05-15 05:07:20,812 INFO [train.py:812] (0/8) Epoch 23, batch 600, loss[loss=0.1658, simple_loss=0.2687, pruned_loss=0.03142, over 7127.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03365, over 1359853.02 frames.], batch size: 21, lr: 3.41e-04
+2022-05-15 05:08:19,857 INFO [train.py:812] (0/8) Epoch 23, batch 650, loss[loss=0.1567, simple_loss=0.2498, pruned_loss=0.03183, over 6769.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2505, pruned_loss=0.03395, over 1374797.18 frames.], batch size: 31, lr: 3.41e-04
+2022-05-15 05:09:19,427 INFO [train.py:812] (0/8) Epoch 23, batch 700, loss[loss=0.1991, simple_loss=0.2872, pruned_loss=0.05551, over 5221.00 frames.], tot_loss[loss=0.1586, simple_loss=0.25, pruned_loss=0.03361, over 1380539.73 frames.], batch size: 53, lr: 3.41e-04
+2022-05-15 05:10:18,453 INFO [train.py:812] (0/8) Epoch 23, batch 750, loss[loss=0.155, simple_loss=0.2493, pruned_loss=0.03032, over 7195.00 frames.], tot_loss[loss=0.159, simple_loss=0.2506, pruned_loss=0.03367, over 1391784.03 frames.], batch size: 23, lr: 3.41e-04
+2022-05-15 05:11:17,826 INFO [train.py:812] (0/8) Epoch 23, batch 800, loss[loss=0.1511, simple_loss=0.2394, pruned_loss=0.03136, over 7366.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2507, pruned_loss=0.03403, over 1395946.46 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:12:15,507 INFO [train.py:812] (0/8) Epoch 23, batch 850, loss[loss=0.1633, simple_loss=0.2523, pruned_loss=0.0371, over 7442.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2506, pruned_loss=0.03413, over 1404552.63 frames.], batch size: 20, lr: 3.41e-04
+2022-05-15 05:13:14,530 INFO [train.py:812] (0/8) Epoch 23, batch 900, loss[loss=0.1516, simple_loss=0.2381, pruned_loss=0.03259, over 7153.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2509, pruned_loss=0.03415, over 1408397.25 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:14:13,167 INFO [train.py:812] (0/8) Epoch 23, batch 950, loss[loss=0.178, simple_loss=0.28, pruned_loss=0.03802, over 6969.00 frames.], tot_loss[loss=0.1596, simple_loss=0.251, pruned_loss=0.0341, over 1410585.17 frames.], batch size: 28, lr: 3.41e-04
+2022-05-15 05:15:13,182 INFO [train.py:812] (0/8) Epoch 23, batch 1000, loss[loss=0.1662, simple_loss=0.2553, pruned_loss=0.03856, over 7350.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2506, pruned_loss=0.03387, over 1417766.14 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:16:12,065 INFO [train.py:812] (0/8) Epoch 23, batch 1050, loss[loss=0.1801, simple_loss=0.2654, pruned_loss=0.04738, over 5226.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2502, pruned_loss=0.03413, over 1419003.19 frames.], batch size: 52, lr: 3.41e-04
+2022-05-15 05:17:10,932 INFO [train.py:812] (0/8) Epoch 23, batch 1100, loss[loss=0.1517, simple_loss=0.2321, pruned_loss=0.03567, over 7282.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2513, pruned_loss=0.0345, over 1418438.58 frames.], batch size: 17, lr: 3.40e-04
+2022-05-15 05:18:09,938 INFO [train.py:812] (0/8) Epoch 23, batch 1150, loss[loss=0.1599, simple_loss=0.2595, pruned_loss=0.03019, over 7417.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2523, pruned_loss=0.03495, over 1421882.88 frames.], batch size: 20, lr: 3.40e-04
+2022-05-15 05:19:09,540 INFO [train.py:812] (0/8) Epoch 23, batch 1200, loss[loss=0.1478, simple_loss=0.2357, pruned_loss=0.02991, over 7283.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2522, pruned_loss=0.03516, over 1420311.36 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:20:07,297 INFO [train.py:812] (0/8) Epoch 23, batch 1250, loss[loss=0.1411, simple_loss=0.2177, pruned_loss=0.03218, over 6797.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2504, pruned_loss=0.03452, over 1423288.92 frames.], batch size: 15, lr: 3.40e-04
+2022-05-15 05:21:05,552 INFO [train.py:812] (0/8) Epoch 23, batch 1300, loss[loss=0.1734, simple_loss=0.2594, pruned_loss=0.04373, over 7192.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2491, pruned_loss=0.03399, over 1426270.77 frames.], batch size: 23, lr: 3.40e-04
+2022-05-15 05:22:03,013 INFO [train.py:812] (0/8) Epoch 23, batch 1350, loss[loss=0.1488, simple_loss=0.2358, pruned_loss=0.03089, over 7279.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2489, pruned_loss=0.03395, over 1426847.86 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:23:02,503 INFO [train.py:812] (0/8) Epoch 23, batch 1400, loss[loss=0.1563, simple_loss=0.2593, pruned_loss=0.02669, over 7124.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2492, pruned_loss=0.03402, over 1426596.17 frames.], batch size: 21, lr: 3.40e-04
+2022-05-15 05:24:01,072 INFO [train.py:812] (0/8) Epoch 23, batch 1450, loss[loss=0.1454, simple_loss=0.2309, pruned_loss=0.02998, over 7419.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2492, pruned_loss=0.03397, over 1421239.71 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:24:59,727 INFO [train.py:812] (0/8) Epoch 23, batch 1500, loss[loss=0.1793, simple_loss=0.2681, pruned_loss=0.04524, over 7128.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2485, pruned_loss=0.03385, over 1423140.51 frames.], batch size: 28, lr: 3.40e-04
+2022-05-15 05:25:58,349 INFO [train.py:812] (0/8) Epoch 23, batch 1550, loss[loss=0.136, simple_loss=0.2248, pruned_loss=0.0236, over 7365.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2489, pruned_loss=0.03426, over 1412712.99 frames.], batch size: 19, lr: 3.40e-04
+2022-05-15 05:26:57,174 INFO [train.py:812] (0/8) Epoch 23, batch 1600, loss[loss=0.1719, simple_loss=0.2666, pruned_loss=0.03859, over 7225.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2494, pruned_loss=0.03436, over 1411266.82 frames.], batch size: 21, lr: 3.40e-04
+2022-05-15 05:27:55,186 INFO [train.py:812] (0/8) Epoch 23, batch 1650, loss[loss=0.1793, simple_loss=0.2766, pruned_loss=0.04096, over 7393.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2489, pruned_loss=0.03437, over 1414624.78 frames.], batch size: 23, lr: 3.40e-04
+2022-05-15 05:28:54,104 INFO [train.py:812] (0/8) Epoch 23, batch 1700, loss[loss=0.135, simple_loss=0.2201, pruned_loss=0.02496, over 7422.00 frames.], tot_loss[loss=0.159, simple_loss=0.2493, pruned_loss=0.0343, over 1415528.43 frames.], batch size: 18, lr: 3.39e-04
+2022-05-15 05:29:50,567 INFO [train.py:812] (0/8) Epoch 23, batch 1750, loss[loss=0.1902, simple_loss=0.2688, pruned_loss=0.05582, over 7203.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.0343, over 1414458.33 frames.], batch size: 26, lr: 3.39e-04
+2022-05-15 05:30:48,707 INFO [train.py:812] (0/8) Epoch 23, batch 1800, loss[loss=0.2026, simple_loss=0.2921, pruned_loss=0.05658, over 5003.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2499, pruned_loss=0.03441, over 1412433.99 frames.], batch size: 52, lr: 3.39e-04
+2022-05-15 05:31:46,094 INFO [train.py:812] (0/8) Epoch 23, batch 1850, loss[loss=0.1634, simple_loss=0.2475, pruned_loss=0.03968, over 7426.00 frames.], tot_loss[loss=0.1595, simple_loss=0.25, pruned_loss=0.03452, over 1417407.50 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:32:44,006 INFO [train.py:812] (0/8) Epoch 23, batch 1900, loss[loss=0.1819, simple_loss=0.2814, pruned_loss=0.04118, over 7141.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03431, over 1420728.23 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:33:42,345 INFO [train.py:812] (0/8) Epoch 23, batch 1950, loss[loss=0.1555, simple_loss=0.2594, pruned_loss=0.02579, over 7135.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2493, pruned_loss=0.03402, over 1417996.39 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:34:41,192 INFO [train.py:812] (0/8) Epoch 23, batch 2000, loss[loss=0.1614, simple_loss=0.2504, pruned_loss=0.03615, over 7255.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2504, pruned_loss=0.03398, over 1421440.52 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:35:40,291 INFO [train.py:812] (0/8) Epoch 23, batch 2050, loss[loss=0.1678, simple_loss=0.2571, pruned_loss=0.03928, over 7231.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03361, over 1425718.46 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:36:39,534 INFO [train.py:812] (0/8) Epoch 23, batch 2100, loss[loss=0.1791, simple_loss=0.281, pruned_loss=0.0386, over 7185.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2491, pruned_loss=0.03368, over 1420599.49 frames.], batch size: 23, lr: 3.39e-04
+2022-05-15 05:37:37,946 INFO [train.py:812] (0/8) Epoch 23, batch 2150, loss[loss=0.1645, simple_loss=0.2541, pruned_loss=0.03746, over 7154.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2494, pruned_loss=0.03374, over 1422038.72 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:38:37,635 INFO [train.py:812] (0/8) Epoch 23, batch 2200, loss[loss=0.1717, simple_loss=0.2621, pruned_loss=0.04065, over 7151.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2493, pruned_loss=0.03417, over 1417740.25 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:39:36,706 INFO [train.py:812] (0/8) Epoch 23, batch 2250, loss[loss=0.1505, simple_loss=0.2473, pruned_loss=0.02685, over 7164.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2494, pruned_loss=0.03411, over 1413438.38 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:40:35,652 INFO [train.py:812] (0/8) Epoch 23, batch 2300, loss[loss=0.1737, simple_loss=0.2675, pruned_loss=0.03995, over 7320.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2485, pruned_loss=0.0339, over 1414710.13 frames.], batch size: 21, lr: 3.38e-04
+2022-05-15 05:41:34,392 INFO [train.py:812] (0/8) Epoch 23, batch 2350, loss[loss=0.1526, simple_loss=0.2494, pruned_loss=0.0279, over 7333.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2489, pruned_loss=0.03393, over 1416387.23 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:42:33,210 INFO [train.py:812] (0/8) Epoch 23, batch 2400, loss[loss=0.1723, simple_loss=0.2617, pruned_loss=0.0415, over 7294.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2502, pruned_loss=0.03451, over 1419328.75 frames.], batch size: 24, lr: 3.38e-04
+2022-05-15 05:43:31,226 INFO [train.py:812] (0/8) Epoch 23, batch 2450, loss[loss=0.181, simple_loss=0.2683, pruned_loss=0.04682, over 7195.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2507, pruned_loss=0.03457, over 1423216.19 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:44:30,337 INFO [train.py:812] (0/8) Epoch 23, batch 2500, loss[loss=0.1278, simple_loss=0.2299, pruned_loss=0.01282, over 6631.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2493, pruned_loss=0.03401, over 1421043.91 frames.], batch size: 38, lr: 3.38e-04
+2022-05-15 05:45:29,336 INFO [train.py:812] (0/8) Epoch 23, batch 2550, loss[loss=0.1836, simple_loss=0.2648, pruned_loss=0.0512, over 7387.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2494, pruned_loss=0.03412, over 1422011.48 frames.], batch size: 23, lr: 3.38e-04
+2022-05-15 05:46:26,776 INFO [train.py:812] (0/8) Epoch 23, batch 2600, loss[loss=0.1653, simple_loss=0.2576, pruned_loss=0.03647, over 7327.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2492, pruned_loss=0.03391, over 1426186.46 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:47:25,307 INFO [train.py:812] (0/8) Epoch 23, batch 2650, loss[loss=0.1608, simple_loss=0.2552, pruned_loss=0.03324, over 7292.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2477, pruned_loss=0.03379, over 1423481.88 frames.], batch size: 25, lr: 3.38e-04
+2022-05-15 05:48:25,316 INFO [train.py:812] (0/8) Epoch 23, batch 2700, loss[loss=0.1681, simple_loss=0.2545, pruned_loss=0.0408, over 7163.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2487, pruned_loss=0.03406, over 1422724.69 frames.], batch size: 19, lr: 3.38e-04
+2022-05-15 05:49:24,355 INFO [train.py:812] (0/8) Epoch 23, batch 2750, loss[loss=0.1541, simple_loss=0.2371, pruned_loss=0.03551, over 7156.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2486, pruned_loss=0.03439, over 1421110.76 frames.], batch size: 18, lr: 3.38e-04
+2022-05-15 05:50:23,650 INFO [train.py:812] (0/8) Epoch 23, batch 2800, loss[loss=0.1447, simple_loss=0.2265, pruned_loss=0.03149, over 7160.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2485, pruned_loss=0.03449, over 1420433.44 frames.], batch size: 18, lr: 3.38e-04
+2022-05-15 05:51:22,697 INFO [train.py:812] (0/8) Epoch 23, batch 2850, loss[loss=0.1945, simple_loss=0.2945, pruned_loss=0.04727, over 7089.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2481, pruned_loss=0.03406, over 1421667.61 frames.], batch size: 28, lr: 3.38e-04
+2022-05-15 05:52:22,380 INFO [train.py:812] (0/8) Epoch 23, batch 2900, loss[loss=0.1737, simple_loss=0.2737, pruned_loss=0.03685, over 7339.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2491, pruned_loss=0.0341, over 1423706.22 frames.], batch size: 25, lr: 3.37e-04
+2022-05-15 05:53:20,354 INFO [train.py:812] (0/8) Epoch 23, batch 2950, loss[loss=0.1774, simple_loss=0.2735, pruned_loss=0.04063, over 7217.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03424, over 1424099.84 frames.], batch size: 22, lr: 3.37e-04
+2022-05-15 05:54:18,723 INFO [train.py:812] (0/8) Epoch 23, batch 3000, loss[loss=0.1278, simple_loss=0.2097, pruned_loss=0.02295, over 7007.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2498, pruned_loss=0.03443, over 1424288.99 frames.], batch size: 16, lr: 3.37e-04
+2022-05-15 05:54:18,724 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 05:54:28,115 INFO [train.py:841] (0/8) Epoch 23, validation: loss=0.153, simple_loss=0.251, pruned_loss=0.02752, over 698248.00 frames.
+2022-05-15 05:55:26,760 INFO [train.py:812] (0/8) Epoch 23, batch 3050, loss[loss=0.149, simple_loss=0.244, pruned_loss=0.02703, over 7160.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2497, pruned_loss=0.03425, over 1426825.46 frames.], batch size: 19, lr: 3.37e-04
+2022-05-15 05:55:42,750 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-104000.pt
+2022-05-15 05:56:31,534 INFO [train.py:812] (0/8) Epoch 23, batch 3100, loss[loss=0.1542, simple_loss=0.2524, pruned_loss=0.02802, over 7234.00 frames.], tot_loss[loss=0.1584, simple_loss=0.249, pruned_loss=0.0339, over 1426052.01 frames.], batch size: 20, lr: 3.37e-04
+2022-05-15 05:57:30,936 INFO [train.py:812] (0/8) Epoch 23, batch 3150, loss[loss=0.1475, simple_loss=0.2511, pruned_loss=0.02193, over 7324.00 frames.], tot_loss[loss=0.1584, simple_loss=0.249, pruned_loss=0.03391, over 1427570.22 frames.], batch size: 20, lr: 3.37e-04
+2022-05-15 05:58:30,585 INFO [train.py:812] (0/8) Epoch 23, batch 3200, loss[loss=0.1544, simple_loss=0.2587, pruned_loss=0.02501, over 7115.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2493, pruned_loss=0.03381, over 1427908.72 frames.], batch size: 21, lr: 3.37e-04
+2022-05-15 05:59:29,510 INFO [train.py:812] (0/8) Epoch 23, batch 3250, loss[loss=0.1467, simple_loss=0.2457, pruned_loss=0.02391, over 6367.00 frames.], tot_loss[loss=0.1581, simple_loss=0.249, pruned_loss=0.03364, over 1422452.36 frames.], batch size: 37, lr: 3.37e-04
+2022-05-15 06:00:29,698 INFO [train.py:812] (0/8) Epoch 23, batch 3300, loss[loss=0.1661, simple_loss=0.2546, pruned_loss=0.03879, over 7311.00 frames.], tot_loss[loss=0.159, simple_loss=0.2501, pruned_loss=0.03399, over 1422797.82 frames.], batch size: 24, lr: 3.37e-04
+2022-05-15 06:01:29,022 INFO [train.py:812] (0/8) Epoch 23, batch 3350, loss[loss=0.1666, simple_loss=0.2668, pruned_loss=0.03317, over 7239.00 frames.], tot_loss[loss=0.1582, simple_loss=0.249, pruned_loss=0.03366, over 1427288.01 frames.], batch size: 26, lr: 3.37e-04
+2022-05-15 06:02:28,575 INFO [train.py:812] (0/8) Epoch 23, batch 3400, loss[loss=0.169, simple_loss=0.2522, pruned_loss=0.04289, over 7159.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03354, over 1428367.65 frames.], batch size: 19, lr: 3.37e-04
+2022-05-15 06:03:27,789 INFO [train.py:812] (0/8) Epoch 23, batch 3450, loss[loss=0.1563, simple_loss=0.2399, pruned_loss=0.03632, over 6876.00 frames.], tot_loss[loss=0.157, simple_loss=0.2475, pruned_loss=0.03321, over 1429829.15 frames.], batch size: 15, lr: 3.37e-04
+2022-05-15 06:04:27,365 INFO [train.py:812] (0/8) Epoch 23, batch 3500, loss[loss=0.1428, simple_loss=0.2175, pruned_loss=0.03404, over 6838.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2475, pruned_loss=0.03334, over 1430769.79 frames.], batch size: 15, lr: 3.37e-04
+2022-05-15 06:05:25,895 INFO [train.py:812] (0/8) Epoch 23, batch 3550, loss[loss=0.1535, simple_loss=0.2359, pruned_loss=0.03558, over 7429.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2475, pruned_loss=0.03334, over 1430882.78 frames.], batch size: 18, lr: 3.36e-04
+2022-05-15 06:06:25,043 INFO [train.py:812] (0/8) Epoch 23, batch 3600, loss[loss=0.1419, simple_loss=0.2161, pruned_loss=0.03385, over 7284.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2492, pruned_loss=0.03364, over 1431961.95 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:07:24,124 INFO [train.py:812] (0/8) Epoch 23, batch 3650, loss[loss=0.144, simple_loss=0.2407, pruned_loss=0.02364, over 6416.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2496, pruned_loss=0.03369, over 1431868.00 frames.], batch size: 37, lr: 3.36e-04
+2022-05-15 06:08:33,460 INFO [train.py:812] (0/8) Epoch 23, batch 3700, loss[loss=0.1475, simple_loss=0.2432, pruned_loss=0.02596, over 7157.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2491, pruned_loss=0.03321, over 1430208.91 frames.], batch size: 19, lr: 3.36e-04
+2022-05-15 06:09:32,123 INFO [train.py:812] (0/8) Epoch 23, batch 3750, loss[loss=0.1336, simple_loss=0.2195, pruned_loss=0.02387, over 7295.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2496, pruned_loss=0.03352, over 1427791.24 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:10:31,414 INFO [train.py:812] (0/8) Epoch 23, batch 3800, loss[loss=0.1482, simple_loss=0.2356, pruned_loss=0.03034, over 7377.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.0336, over 1428926.03 frames.], batch size: 23, lr: 3.36e-04
+2022-05-15 06:11:30,121 INFO [train.py:812] (0/8) Epoch 23, batch 3850, loss[loss=0.1703, simple_loss=0.2621, pruned_loss=0.03919, over 6987.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2489, pruned_loss=0.03332, over 1429675.08 frames.], batch size: 28, lr: 3.36e-04
+2022-05-15 06:12:28,295 INFO [train.py:812] (0/8) Epoch 23, batch 3900, loss[loss=0.1717, simple_loss=0.2703, pruned_loss=0.03654, over 7441.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2498, pruned_loss=0.03397, over 1430184.95 frames.], batch size: 22, lr: 3.36e-04
+2022-05-15 06:13:25,771 INFO [train.py:812] (0/8) Epoch 23, batch 3950, loss[loss=0.1444, simple_loss=0.2337, pruned_loss=0.02749, over 7171.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2501, pruned_loss=0.03404, over 1429810.98 frames.], batch size: 19, lr: 3.36e-04
+2022-05-15 06:14:22,988 INFO [train.py:812] (0/8) Epoch 23, batch 4000, loss[loss=0.1586, simple_loss=0.2373, pruned_loss=0.03998, over 7253.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2497, pruned_loss=0.03395, over 1426185.15 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:15:21,465 INFO [train.py:812] (0/8) Epoch 23, batch 4050, loss[loss=0.139, simple_loss=0.2179, pruned_loss=0.02999, over 7171.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2498, pruned_loss=0.03388, over 1421318.61 frames.], batch size: 16, lr: 3.36e-04
+2022-05-15 06:16:21,796 INFO [train.py:812] (0/8) Epoch 23, batch 4100, loss[loss=0.1434, simple_loss=0.2228, pruned_loss=0.032, over 7247.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2497, pruned_loss=0.0345, over 1417674.42 frames.], batch size: 16, lr: 3.36e-04
+2022-05-15 06:17:19,463 INFO [train.py:812] (0/8) Epoch 23, batch 4150, loss[loss=0.1537, simple_loss=0.2572, pruned_loss=0.02507, over 7324.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2504, pruned_loss=0.03439, over 1416288.77 frames.], batch size: 21, lr: 3.35e-04
+2022-05-15 06:18:18,884 INFO [train.py:812] (0/8) Epoch 23, batch 4200, loss[loss=0.141, simple_loss=0.2246, pruned_loss=0.0287, over 7008.00 frames.], tot_loss[loss=0.1589, simple_loss=0.25, pruned_loss=0.03392, over 1420829.92 frames.], batch size: 16, lr: 3.35e-04
+2022-05-15 06:19:17,844 INFO [train.py:812] (0/8) Epoch 23, batch 4250, loss[loss=0.1624, simple_loss=0.2607, pruned_loss=0.03208, over 7233.00 frames.], tot_loss[loss=0.159, simple_loss=0.25, pruned_loss=0.03403, over 1422424.20 frames.], batch size: 20, lr: 3.35e-04
+2022-05-15 06:20:16,265 INFO [train.py:812] (0/8) Epoch 23, batch 4300, loss[loss=0.1451, simple_loss=0.232, pruned_loss=0.0291, over 7149.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2479, pruned_loss=0.03352, over 1419424.74 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:21:15,849 INFO [train.py:812] (0/8) Epoch 23, batch 4350, loss[loss=0.1332, simple_loss=0.2204, pruned_loss=0.02302, over 7260.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2477, pruned_loss=0.03355, over 1421305.70 frames.], batch size: 16, lr: 3.35e-04
+2022-05-15 06:22:15,639 INFO [train.py:812] (0/8) Epoch 23, batch 4400, loss[loss=0.1416, simple_loss=0.2346, pruned_loss=0.02431, over 7069.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2475, pruned_loss=0.03349, over 1419064.73 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:23:14,856 INFO [train.py:812] (0/8) Epoch 23, batch 4450, loss[loss=0.221, simple_loss=0.3035, pruned_loss=0.0693, over 5269.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2482, pruned_loss=0.03369, over 1413310.72 frames.], batch size: 52, lr: 3.35e-04
+2022-05-15 06:24:13,019 INFO [train.py:812] (0/8) Epoch 23, batch 4500, loss[loss=0.1227, simple_loss=0.2153, pruned_loss=0.01506, over 7063.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2482, pruned_loss=0.03369, over 1412686.54 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:25:11,002 INFO [train.py:812] (0/8) Epoch 23, batch 4550, loss[loss=0.1683, simple_loss=0.2619, pruned_loss=0.03731, over 5257.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2511, pruned_loss=0.03575, over 1356591.00 frames.], batch size: 52, lr: 3.35e-04
+2022-05-15 06:25:56,515 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-23.pt
+2022-05-15 06:26:16,424 INFO [train.py:812] (0/8) Epoch 24, batch 0, loss[loss=0.1329, simple_loss=0.2212, pruned_loss=0.02232, over 6826.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2212, pruned_loss=0.02232, over 6826.00 frames.], batch size: 15, lr: 3.28e-04
+2022-05-15 06:27:14,053 INFO [train.py:812] (0/8) Epoch 24, batch 50, loss[loss=0.1283, simple_loss=0.21, pruned_loss=0.02326, over 7280.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2475, pruned_loss=0.03203, over 316699.52 frames.], batch size: 17, lr: 3.28e-04
+2022-05-15 06:28:13,399 INFO [train.py:812] (0/8) Epoch 24, batch 100, loss[loss=0.1748, simple_loss=0.2689, pruned_loss=0.0404, over 7335.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2494, pruned_loss=0.03278, over 567132.79 frames.], batch size: 20, lr: 3.28e-04
+2022-05-15 06:29:11,106 INFO [train.py:812] (0/8) Epoch 24, batch 150, loss[loss=0.1569, simple_loss=0.2533, pruned_loss=0.03026, over 7383.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2502, pruned_loss=0.03356, over 752744.06 frames.], batch size: 23, lr: 3.28e-04
+2022-05-15 06:30:10,085 INFO [train.py:812] (0/8) Epoch 24, batch 200, loss[loss=0.1611, simple_loss=0.2545, pruned_loss=0.03386, over 7204.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2495, pruned_loss=0.03352, over 903516.07 frames.], batch size: 22, lr: 3.28e-04
+2022-05-15 06:31:07,703 INFO [train.py:812] (0/8) Epoch 24, batch 250, loss[loss=0.1337, simple_loss=0.2371, pruned_loss=0.01515, over 7415.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2496, pruned_loss=0.0338, over 1015321.43 frames.], batch size: 21, lr: 3.28e-04
+2022-05-15 06:32:07,188 INFO [train.py:812] (0/8) Epoch 24, batch 300, loss[loss=0.1332, simple_loss=0.2313, pruned_loss=0.01754, over 7148.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2484, pruned_loss=0.0333, over 1107314.49 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:33:03,995 INFO [train.py:812] (0/8) Epoch 24, batch 350, loss[loss=0.1551, simple_loss=0.2545, pruned_loss=0.02783, over 7283.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2481, pruned_loss=0.03359, over 1179085.43 frames.], batch size: 25, lr: 3.27e-04
+2022-05-15 06:34:01,081 INFO [train.py:812] (0/8) Epoch 24, batch 400, loss[loss=0.1587, simple_loss=0.2505, pruned_loss=0.03341, over 7267.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2485, pruned_loss=0.034, over 1230556.03 frames.], batch size: 24, lr: 3.27e-04
+2022-05-15 06:34:58,893 INFO [train.py:812] (0/8) Epoch 24, batch 450, loss[loss=0.1579, simple_loss=0.2482, pruned_loss=0.0338, over 7151.00 frames.], tot_loss[loss=0.158, simple_loss=0.2487, pruned_loss=0.0336, over 1276565.50 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:35:57,364 INFO [train.py:812] (0/8) Epoch 24, batch 500, loss[loss=0.1504, simple_loss=0.2487, pruned_loss=0.02605, over 7349.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2487, pruned_loss=0.03331, over 1308047.80 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:36:55,887 INFO [train.py:812] (0/8) Epoch 24, batch 550, loss[loss=0.1731, simple_loss=0.269, pruned_loss=0.03866, over 7205.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2487, pruned_loss=0.03332, over 1337236.11 frames.], batch size: 22, lr: 3.27e-04
+2022-05-15 06:37:55,357 INFO [train.py:812] (0/8) Epoch 24, batch 600, loss[loss=0.1385, simple_loss=0.2208, pruned_loss=0.02813, over 7359.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2481, pruned_loss=0.03353, over 1354641.98 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:38:54,593 INFO [train.py:812] (0/8) Epoch 24, batch 650, loss[loss=0.1308, simple_loss=0.2207, pruned_loss=0.02047, over 7361.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2476, pruned_loss=0.03303, over 1365285.08 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:39:54,712 INFO [train.py:812] (0/8) Epoch 24, batch 700, loss[loss=0.1656, simple_loss=0.2673, pruned_loss=0.03195, over 7200.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2459, pruned_loss=0.03224, over 1382867.42 frames.], batch size: 26, lr: 3.27e-04
+2022-05-15 06:40:53,884 INFO [train.py:812] (0/8) Epoch 24, batch 750, loss[loss=0.1377, simple_loss=0.2168, pruned_loss=0.0293, over 6990.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2468, pruned_loss=0.0325, over 1393470.31 frames.], batch size: 16, lr: 3.27e-04
+2022-05-15 06:41:53,030 INFO [train.py:812] (0/8) Epoch 24, batch 800, loss[loss=0.1598, simple_loss=0.2476, pruned_loss=0.036, over 7258.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2466, pruned_loss=0.03246, over 1400477.51 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:42:52,274 INFO [train.py:812] (0/8) Epoch 24, batch 850, loss[loss=0.1496, simple_loss=0.2474, pruned_loss=0.02593, over 6729.00 frames.], tot_loss[loss=0.1559, simple_loss=0.247, pruned_loss=0.03242, over 1407243.97 frames.], batch size: 31, lr: 3.27e-04
+2022-05-15 06:43:51,534 INFO [train.py:812] (0/8) Epoch 24, batch 900, loss[loss=0.1411, simple_loss=0.2339, pruned_loss=0.02412, over 7425.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2468, pruned_loss=0.03251, over 1413073.99 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:44:50,512 INFO [train.py:812] (0/8) Epoch 24, batch 950, loss[loss=0.1916, simple_loss=0.2781, pruned_loss=0.05261, over 6491.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2461, pruned_loss=0.03256, over 1418280.53 frames.], batch size: 38, lr: 3.26e-04
+2022-05-15 06:45:49,538 INFO [train.py:812] (0/8) Epoch 24, batch 1000, loss[loss=0.1667, simple_loss=0.2608, pruned_loss=0.03636, over 7323.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2464, pruned_loss=0.03275, over 1419835.87 frames.], batch size: 21, lr: 3.26e-04
+2022-05-15 06:46:47,308 INFO [train.py:812] (0/8) Epoch 24, batch 1050, loss[loss=0.1469, simple_loss=0.2399, pruned_loss=0.02701, over 7228.00 frames.], tot_loss[loss=0.157, simple_loss=0.2473, pruned_loss=0.03336, over 1413265.37 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:47:46,415 INFO [train.py:812] (0/8) Epoch 24, batch 1100, loss[loss=0.1406, simple_loss=0.2317, pruned_loss=0.02476, over 7147.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2476, pruned_loss=0.03349, over 1412384.98 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:48:44,897 INFO [train.py:812] (0/8) Epoch 24, batch 1150, loss[loss=0.1651, simple_loss=0.2556, pruned_loss=0.03728, over 6266.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2469, pruned_loss=0.03318, over 1415494.80 frames.], batch size: 37, lr: 3.26e-04
+2022-05-15 06:49:42,948 INFO [train.py:812] (0/8) Epoch 24, batch 1200, loss[loss=0.1562, simple_loss=0.2408, pruned_loss=0.03578, over 7164.00 frames.], tot_loss[loss=0.157, simple_loss=0.2473, pruned_loss=0.03329, over 1417935.89 frames.], batch size: 18, lr: 3.26e-04
+2022-05-15 06:50:50,709 INFO [train.py:812] (0/8) Epoch 24, batch 1250, loss[loss=0.1302, simple_loss=0.2161, pruned_loss=0.02211, over 7319.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2478, pruned_loss=0.03379, over 1419011.35 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:51:49,905 INFO [train.py:812] (0/8) Epoch 24, batch 1300, loss[loss=0.1581, simple_loss=0.2568, pruned_loss=0.02974, over 6863.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2484, pruned_loss=0.03401, over 1420356.64 frames.], batch size: 31, lr: 3.26e-04
+2022-05-15 06:52:48,895 INFO [train.py:812] (0/8) Epoch 24, batch 1350, loss[loss=0.147, simple_loss=0.2289, pruned_loss=0.03257, over 7418.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2491, pruned_loss=0.03439, over 1425758.40 frames.], batch size: 18, lr: 3.26e-04
+2022-05-15 06:53:46,292 INFO [train.py:812] (0/8) Epoch 24, batch 1400, loss[loss=0.2057, simple_loss=0.2852, pruned_loss=0.06308, over 7167.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2489, pruned_loss=0.03462, over 1423716.07 frames.], batch size: 26, lr: 3.26e-04
+2022-05-15 06:55:13,454 INFO [train.py:812] (0/8) Epoch 24, batch 1450, loss[loss=0.1435, simple_loss=0.2295, pruned_loss=0.02882, over 7154.00 frames.], tot_loss[loss=0.1591, simple_loss=0.249, pruned_loss=0.03457, over 1421398.86 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:56:22,004 INFO [train.py:812] (0/8) Epoch 24, batch 1500, loss[loss=0.1419, simple_loss=0.241, pruned_loss=0.02142, over 7141.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2491, pruned_loss=0.03486, over 1419699.67 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:57:21,297 INFO [train.py:812] (0/8) Epoch 24, batch 1550, loss[loss=0.1932, simple_loss=0.2886, pruned_loss=0.04885, over 6834.00 frames.], tot_loss[loss=0.159, simple_loss=0.2486, pruned_loss=0.03475, over 1420442.61 frames.], batch size: 31, lr: 3.26e-04
+2022-05-15 06:58:39,401 INFO [train.py:812] (0/8) Epoch 24, batch 1600, loss[loss=0.1655, simple_loss=0.2603, pruned_loss=0.03538, over 7325.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2494, pruned_loss=0.03458, over 1422116.73 frames.], batch size: 20, lr: 3.25e-04
+2022-05-15 06:59:37,792 INFO [train.py:812] (0/8) Epoch 24, batch 1650, loss[loss=0.1342, simple_loss=0.2182, pruned_loss=0.02508, over 6855.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2496, pruned_loss=0.03455, over 1413670.19 frames.], batch size: 15, lr: 3.25e-04
+2022-05-15 07:00:36,795 INFO [train.py:812] (0/8) Epoch 24, batch 1700, loss[loss=0.1843, simple_loss=0.2829, pruned_loss=0.04284, over 7309.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2492, pruned_loss=0.03409, over 1417385.45 frames.], batch size: 21, lr: 3.25e-04
+2022-05-15 07:01:34,452 INFO [train.py:812] (0/8) Epoch 24, batch 1750, loss[loss=0.143, simple_loss=0.2202, pruned_loss=0.03286, over 7068.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2491, pruned_loss=0.03413, over 1419024.67 frames.], batch size: 18, lr: 3.25e-04
+2022-05-15 07:02:33,276 INFO [train.py:812] (0/8) Epoch 24, batch 1800, loss[loss=0.1643, simple_loss=0.2635, pruned_loss=0.03254, over 7323.00 frames.], tot_loss[loss=0.1583, simple_loss=0.249, pruned_loss=0.03378, over 1418997.71 frames.], batch size: 22, lr: 3.25e-04
+2022-05-15 07:03:31,391 INFO [train.py:812] (0/8) Epoch 24, batch 1850, loss[loss=0.156, simple_loss=0.2523, pruned_loss=0.02984, over 7293.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2493, pruned_loss=0.03375, over 1422979.55 frames.], batch size: 24, lr: 3.25e-04
+2022-05-15 07:04:30,283 INFO [train.py:812] (0/8) Epoch 24, batch 1900, loss[loss=0.1538, simple_loss=0.2539, pruned_loss=0.0268, over 7071.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2495, pruned_loss=0.03395, over 1422121.99 frames.], batch size: 28, lr: 3.25e-04
+2022-05-15 07:05:29,097 INFO [train.py:812] (0/8) Epoch 24, batch 1950, loss[loss=0.1354, simple_loss=0.2304, pruned_loss=0.0202, over 7103.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2498, pruned_loss=0.03377, over 1423652.28 frames.], batch size: 21, lr: 3.25e-04
+2022-05-15 07:06:27,358 INFO [train.py:812] (0/8) Epoch 24, batch 2000, loss[loss=0.206, simple_loss=0.2867, pruned_loss=0.06263, over 4822.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2506, pruned_loss=0.03418, over 1421551.90 frames.], batch size: 52, lr: 3.25e-04
+2022-05-15 07:07:25,879 INFO [train.py:812] (0/8) Epoch 24, batch 2050, loss[loss=0.168, simple_loss=0.2524, pruned_loss=0.04182, over 7438.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2509, pruned_loss=0.03445, over 1421451.41 frames.], batch size: 20, lr: 3.25e-04
+2022-05-15 07:08:23,654 INFO [train.py:812] (0/8) Epoch 24, batch 2100, loss[loss=0.1554, simple_loss=0.2423, pruned_loss=0.03426, over 6996.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2503, pruned_loss=0.03401, over 1422632.27 frames.], batch size: 16, lr: 3.25e-04
+2022-05-15 07:09:22,550 INFO [train.py:812] (0/8) Epoch 24, batch 2150, loss[loss=0.1814, simple_loss=0.2641, pruned_loss=0.04932, over 4972.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2499, pruned_loss=0.03412, over 1420235.83 frames.], batch size: 52, lr: 3.25e-04
+2022-05-15 07:10:21,851 INFO [train.py:812] (0/8) Epoch 24, batch 2200, loss[loss=0.1485, simple_loss=0.2321, pruned_loss=0.0324, over 7125.00 frames.], tot_loss[loss=0.1584, simple_loss=0.249, pruned_loss=0.03389, over 1419877.61 frames.], batch size: 17, lr: 3.25e-04
+2022-05-15 07:11:20,849 INFO [train.py:812] (0/8) Epoch 24, batch 2250, loss[loss=0.1813, simple_loss=0.2822, pruned_loss=0.04018, over 7311.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2501, pruned_loss=0.03436, over 1410233.83 frames.], batch size: 25, lr: 3.24e-04
+2022-05-15 07:12:19,951 INFO [train.py:812] (0/8) Epoch 24, batch 2300, loss[loss=0.1346, simple_loss=0.2165, pruned_loss=0.02632, over 7274.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2484, pruned_loss=0.03347, over 1417316.50 frames.], batch size: 17, lr: 3.24e-04
+2022-05-15 07:13:18,772 INFO [train.py:812] (0/8) Epoch 24, batch 2350, loss[loss=0.1772, simple_loss=0.2762, pruned_loss=0.03909, over 7343.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2498, pruned_loss=0.03397, over 1418692.61 frames.], batch size: 22, lr: 3.24e-04
+2022-05-15 07:14:18,390 INFO [train.py:812] (0/8) Epoch 24, batch 2400, loss[loss=0.1503, simple_loss=0.2362, pruned_loss=0.03214, over 7240.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2498, pruned_loss=0.03356, over 1421759.30 frames.], batch size: 16, lr: 3.24e-04
+2022-05-15 07:15:15,758 INFO [train.py:812] (0/8) Epoch 24, batch 2450, loss[loss=0.1631, simple_loss=0.246, pruned_loss=0.04012, over 7233.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2498, pruned_loss=0.03339, over 1418186.08 frames.], batch size: 20, lr: 3.24e-04
+2022-05-15 07:15:44,526 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-108000.pt
+2022-05-15 07:16:21,374 INFO [train.py:812] (0/8) Epoch 24, batch 2500, loss[loss=0.1626, simple_loss=0.2581, pruned_loss=0.03352, over 7311.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2495, pruned_loss=0.03353, over 1418954.18 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:17:19,924 INFO [train.py:812] (0/8) Epoch 24, batch 2550, loss[loss=0.178, simple_loss=0.2656, pruned_loss=0.04516, over 5254.00 frames.], tot_loss[loss=0.158, simple_loss=0.249, pruned_loss=0.03344, over 1415231.70 frames.], batch size: 52, lr: 3.24e-04
+2022-05-15 07:18:18,704 INFO [train.py:812] (0/8) Epoch 24, batch 2600, loss[loss=0.1457, simple_loss=0.2404, pruned_loss=0.02547, over 7270.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2502, pruned_loss=0.03351, over 1419396.13 frames.], batch size: 18, lr: 3.24e-04
+2022-05-15 07:19:17,376 INFO [train.py:812] (0/8) Epoch 24, batch 2650, loss[loss=0.1441, simple_loss=0.2374, pruned_loss=0.02541, over 7323.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2488, pruned_loss=0.03306, over 1418578.00 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:20:16,536 INFO [train.py:812] (0/8) Epoch 24, batch 2700, loss[loss=0.1524, simple_loss=0.257, pruned_loss=0.02393, over 7341.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2494, pruned_loss=0.03348, over 1423035.99 frames.], batch size: 22, lr: 3.24e-04
+2022-05-15 07:21:15,968 INFO [train.py:812] (0/8) Epoch 24, batch 2750, loss[loss=0.1562, simple_loss=0.2464, pruned_loss=0.03299, over 7416.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2486, pruned_loss=0.03301, over 1425788.79 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:22:15,117 INFO [train.py:812] (0/8) Epoch 24, batch 2800, loss[loss=0.1487, simple_loss=0.2403, pruned_loss=0.02856, over 7237.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2492, pruned_loss=0.03353, over 1422340.86 frames.], batch size: 20, lr: 3.24e-04
+2022-05-15 07:23:13,220 INFO [train.py:812] (0/8) Epoch 24, batch 2850, loss[loss=0.15, simple_loss=0.2447, pruned_loss=0.02763, over 7353.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2508, pruned_loss=0.03396, over 1422315.60 frames.], batch size: 19, lr: 3.24e-04
+2022-05-15 07:24:12,086 INFO [train.py:812] (0/8) Epoch 24, batch 2900, loss[loss=0.163, simple_loss=0.2578, pruned_loss=0.03407, over 7299.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2507, pruned_loss=0.03358, over 1421613.57 frames.], batch size: 25, lr: 3.24e-04
+2022-05-15 07:25:09,865 INFO [train.py:812] (0/8) Epoch 24, batch 2950, loss[loss=0.1463, simple_loss=0.2253, pruned_loss=0.03366, over 7277.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2506, pruned_loss=0.03349, over 1425758.53 frames.], batch size: 17, lr: 3.23e-04
+2022-05-15 07:26:08,037 INFO [train.py:812] (0/8) Epoch 24, batch 3000, loss[loss=0.1519, simple_loss=0.2496, pruned_loss=0.02711, over 7115.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2504, pruned_loss=0.03351, over 1421201.66 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:26:08,039 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 07:26:15,602 INFO [train.py:841] (0/8) Epoch 24, validation: loss=0.1537, simple_loss=0.2513, pruned_loss=0.02802, over 698248.00 frames.
+2022-05-15 07:27:14,999 INFO [train.py:812] (0/8) Epoch 24, batch 3050, loss[loss=0.1432, simple_loss=0.2317, pruned_loss=0.02733, over 7277.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2502, pruned_loss=0.03359, over 1416659.17 frames.], batch size: 18, lr: 3.23e-04
+2022-05-15 07:28:13,640 INFO [train.py:812] (0/8) Epoch 24, batch 3100, loss[loss=0.1536, simple_loss=0.2438, pruned_loss=0.03171, over 6841.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2494, pruned_loss=0.03353, over 1419887.20 frames.], batch size: 31, lr: 3.23e-04
+2022-05-15 07:29:12,198 INFO [train.py:812] (0/8) Epoch 24, batch 3150, loss[loss=0.1355, simple_loss=0.2169, pruned_loss=0.02705, over 6993.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2491, pruned_loss=0.03332, over 1421744.39 frames.], batch size: 16, lr: 3.23e-04
+2022-05-15 07:30:11,690 INFO [train.py:812] (0/8) Epoch 24, batch 3200, loss[loss=0.1661, simple_loss=0.2704, pruned_loss=0.03085, over 7313.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2485, pruned_loss=0.03288, over 1425965.68 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:31:10,168 INFO [train.py:812] (0/8) Epoch 24, batch 3250, loss[loss=0.1465, simple_loss=0.2423, pruned_loss=0.02534, over 7154.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2491, pruned_loss=0.03327, over 1427684.70 frames.], batch size: 18, lr: 3.23e-04
+2022-05-15 07:32:09,042 INFO [train.py:812] (0/8) Epoch 24, batch 3300, loss[loss=0.177, simple_loss=0.2757, pruned_loss=0.03916, over 7299.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2489, pruned_loss=0.03293, over 1427140.90 frames.], batch size: 24, lr: 3.23e-04
+2022-05-15 07:33:06,617 INFO [train.py:812] (0/8) Epoch 24, batch 3350, loss[loss=0.1357, simple_loss=0.2327, pruned_loss=0.01938, over 7310.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2489, pruned_loss=0.0328, over 1423171.94 frames.], batch size: 24, lr: 3.23e-04
+2022-05-15 07:34:04,977 INFO [train.py:812] (0/8) Epoch 24, batch 3400, loss[loss=0.1396, simple_loss=0.2246, pruned_loss=0.02732, over 7363.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2487, pruned_loss=0.0326, over 1427258.07 frames.], batch size: 19, lr: 3.23e-04
+2022-05-15 07:35:03,134 INFO [train.py:812] (0/8) Epoch 24, batch 3450, loss[loss=0.148, simple_loss=0.2491, pruned_loss=0.0235, over 7320.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2486, pruned_loss=0.03263, over 1422831.48 frames.], batch size: 22, lr: 3.23e-04
+2022-05-15 07:36:01,846 INFO [train.py:812] (0/8) Epoch 24, batch 3500, loss[loss=0.1525, simple_loss=0.2333, pruned_loss=0.03586, over 6801.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2478, pruned_loss=0.03252, over 1422154.72 frames.], batch size: 15, lr: 3.23e-04
+2022-05-15 07:37:00,424 INFO [train.py:812] (0/8) Epoch 24, batch 3550, loss[loss=0.1634, simple_loss=0.2553, pruned_loss=0.03573, over 7120.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2488, pruned_loss=0.03308, over 1423702.74 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:38:00,121 INFO [train.py:812] (0/8) Epoch 24, batch 3600, loss[loss=0.1482, simple_loss=0.2366, pruned_loss=0.02984, over 7448.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2491, pruned_loss=0.033, over 1423313.38 frames.], batch size: 19, lr: 3.22e-04
+2022-05-15 07:38:57,462 INFO [train.py:812] (0/8) Epoch 24, batch 3650, loss[loss=0.1424, simple_loss=0.2291, pruned_loss=0.02786, over 7347.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2494, pruned_loss=0.03319, over 1424261.39 frames.], batch size: 19, lr: 3.22e-04
+2022-05-15 07:39:55,870 INFO [train.py:812] (0/8) Epoch 24, batch 3700, loss[loss=0.1644, simple_loss=0.2606, pruned_loss=0.03411, over 6431.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2502, pruned_loss=0.03367, over 1421256.80 frames.], batch size: 38, lr: 3.22e-04
+2022-05-15 07:40:52,807 INFO [train.py:812] (0/8) Epoch 24, batch 3750, loss[loss=0.1488, simple_loss=0.2365, pruned_loss=0.03056, over 7279.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2503, pruned_loss=0.03333, over 1422646.69 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:41:51,837 INFO [train.py:812] (0/8) Epoch 24, batch 3800, loss[loss=0.17, simple_loss=0.2512, pruned_loss=0.04434, over 7440.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2492, pruned_loss=0.03311, over 1424546.65 frames.], batch size: 20, lr: 3.22e-04
+2022-05-15 07:42:51,142 INFO [train.py:812] (0/8) Epoch 24, batch 3850, loss[loss=0.183, simple_loss=0.271, pruned_loss=0.04747, over 4975.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2488, pruned_loss=0.03275, over 1421026.30 frames.], batch size: 52, lr: 3.22e-04
+2022-05-15 07:43:50,674 INFO [train.py:812] (0/8) Epoch 24, batch 3900, loss[loss=0.1797, simple_loss=0.2762, pruned_loss=0.04157, over 6704.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2497, pruned_loss=0.03336, over 1416489.51 frames.], batch size: 31, lr: 3.22e-04
+2022-05-15 07:44:49,738 INFO [train.py:812] (0/8) Epoch 24, batch 3950, loss[loss=0.1397, simple_loss=0.2279, pruned_loss=0.02579, over 7133.00 frames.], tot_loss[loss=0.159, simple_loss=0.2506, pruned_loss=0.03367, over 1416677.25 frames.], batch size: 17, lr: 3.22e-04
+2022-05-15 07:45:48,717 INFO [train.py:812] (0/8) Epoch 24, batch 4000, loss[loss=0.1783, simple_loss=0.2747, pruned_loss=0.04096, over 7203.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2513, pruned_loss=0.034, over 1415153.26 frames.], batch size: 22, lr: 3.22e-04
+2022-05-15 07:46:47,069 INFO [train.py:812] (0/8) Epoch 24, batch 4050, loss[loss=0.1605, simple_loss=0.2566, pruned_loss=0.0322, over 5281.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2502, pruned_loss=0.03364, over 1416521.02 frames.], batch size: 52, lr: 3.22e-04
+2022-05-15 07:47:46,726 INFO [train.py:812] (0/8) Epoch 24, batch 4100, loss[loss=0.1358, simple_loss=0.2248, pruned_loss=0.0234, over 7270.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2499, pruned_loss=0.03351, over 1415973.44 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:48:45,822 INFO [train.py:812] (0/8) Epoch 24, batch 4150, loss[loss=0.1422, simple_loss=0.2293, pruned_loss=0.0276, over 6996.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2502, pruned_loss=0.03386, over 1417946.99 frames.], batch size: 16, lr: 3.22e-04
+2022-05-15 07:49:44,933 INFO [train.py:812] (0/8) Epoch 24, batch 4200, loss[loss=0.1457, simple_loss=0.2326, pruned_loss=0.02942, over 7284.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2509, pruned_loss=0.03405, over 1418578.34 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:50:44,107 INFO [train.py:812] (0/8) Epoch 24, batch 4250, loss[loss=0.1828, simple_loss=0.2868, pruned_loss=0.03935, over 7390.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2504, pruned_loss=0.03415, over 1416904.91 frames.], batch size: 23, lr: 3.22e-04
+2022-05-15 07:51:43,365 INFO [train.py:812] (0/8) Epoch 24, batch 4300, loss[loss=0.1285, simple_loss=0.2089, pruned_loss=0.02401, over 6745.00 frames.], tot_loss[loss=0.1583, simple_loss=0.249, pruned_loss=0.0338, over 1415644.56 frames.], batch size: 15, lr: 3.21e-04
+2022-05-15 07:52:41,816 INFO [train.py:812] (0/8) Epoch 24, batch 4350, loss[loss=0.1623, simple_loss=0.2563, pruned_loss=0.03409, over 6904.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2496, pruned_loss=0.0338, over 1413260.55 frames.], batch size: 32, lr: 3.21e-04
+2022-05-15 07:53:40,607 INFO [train.py:812] (0/8) Epoch 24, batch 4400, loss[loss=0.1621, simple_loss=0.2534, pruned_loss=0.03546, over 6311.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2495, pruned_loss=0.03409, over 1406157.46 frames.], batch size: 37, lr: 3.21e-04
+2022-05-15 07:54:38,515 INFO [train.py:812] (0/8) Epoch 24, batch 4450, loss[loss=0.1568, simple_loss=0.2554, pruned_loss=0.02914, over 6199.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2494, pruned_loss=0.03407, over 1409269.69 frames.], batch size: 37, lr: 3.21e-04
+2022-05-15 07:55:37,560 INFO [train.py:812] (0/8) Epoch 24, batch 4500, loss[loss=0.1704, simple_loss=0.2619, pruned_loss=0.03945, over 6343.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2498, pruned_loss=0.03455, over 1396018.81 frames.], batch size: 37, lr: 3.21e-04
+2022-05-15 07:56:36,612 INFO [train.py:812] (0/8) Epoch 24, batch 4550, loss[loss=0.163, simple_loss=0.2603, pruned_loss=0.03285, over 7301.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2505, pruned_loss=0.03498, over 1384803.15 frames.], batch size: 24, lr: 3.21e-04
+2022-05-15 07:57:22,327 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-24.pt
+2022-05-15 07:57:47,759 INFO [train.py:812] (0/8) Epoch 25, batch 0, loss[loss=0.1645, simple_loss=0.2609, pruned_loss=0.03402, over 7077.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2609, pruned_loss=0.03402, over 7077.00 frames.], batch size: 18, lr: 3.15e-04
+2022-05-15 07:58:47,069 INFO [train.py:812] (0/8) Epoch 25, batch 50, loss[loss=0.1378, simple_loss=0.2286, pruned_loss=0.02345, over 7234.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2528, pruned_loss=0.03534, over 321318.33 frames.], batch size: 19, lr: 3.15e-04
+2022-05-15 07:59:46,721 INFO [train.py:812] (0/8) Epoch 25, batch 100, loss[loss=0.1734, simple_loss=0.273, pruned_loss=0.03691, over 7320.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2514, pruned_loss=0.03503, over 569742.11 frames.], batch size: 20, lr: 3.15e-04
+2022-05-15 08:00:45,690 INFO [train.py:812] (0/8) Epoch 25, batch 150, loss[loss=0.1553, simple_loss=0.2532, pruned_loss=0.02871, over 7319.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2496, pruned_loss=0.03373, over 761133.33 frames.], batch size: 21, lr: 3.14e-04
+2022-05-15 08:01:45,470 INFO [train.py:812] (0/8) Epoch 25, batch 200, loss[loss=0.1543, simple_loss=0.2375, pruned_loss=0.03559, over 6785.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2483, pruned_loss=0.0332, over 906101.16 frames.], batch size: 15, lr: 3.14e-04
+2022-05-15 08:02:44,398 INFO [train.py:812] (0/8) Epoch 25, batch 250, loss[loss=0.1789, simple_loss=0.2707, pruned_loss=0.04359, over 7240.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2487, pruned_loss=0.03316, over 1018670.77 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:03:43,887 INFO [train.py:812] (0/8) Epoch 25, batch 300, loss[loss=0.1728, simple_loss=0.2547, pruned_loss=0.04542, over 7158.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03355, over 1112303.19 frames.], batch size: 19, lr: 3.14e-04
+2022-05-15 08:04:42,716 INFO [train.py:812] (0/8) Epoch 25, batch 350, loss[loss=0.1605, simple_loss=0.2503, pruned_loss=0.03532, over 7226.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2495, pruned_loss=0.03375, over 1182480.41 frames.], batch size: 23, lr: 3.14e-04
+2022-05-15 08:05:50,984 INFO [train.py:812] (0/8) Epoch 25, batch 400, loss[loss=0.165, simple_loss=0.26, pruned_loss=0.03506, over 7235.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2484, pruned_loss=0.03311, over 1237159.02 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:06:49,205 INFO [train.py:812] (0/8) Epoch 25, batch 450, loss[loss=0.1597, simple_loss=0.2488, pruned_loss=0.03526, over 7181.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2473, pruned_loss=0.03293, over 1277527.21 frames.], batch size: 28, lr: 3.14e-04
+2022-05-15 08:07:48,609 INFO [train.py:812] (0/8) Epoch 25, batch 500, loss[loss=0.1584, simple_loss=0.2478, pruned_loss=0.03451, over 7182.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03259, over 1312372.92 frames.], batch size: 18, lr: 3.14e-04
+2022-05-15 08:08:47,658 INFO [train.py:812] (0/8) Epoch 25, batch 550, loss[loss=0.149, simple_loss=0.2402, pruned_loss=0.02892, over 7168.00 frames.], tot_loss[loss=0.156, simple_loss=0.2471, pruned_loss=0.03252, over 1339506.32 frames.], batch size: 18, lr: 3.14e-04
+2022-05-15 08:09:45,686 INFO [train.py:812] (0/8) Epoch 25, batch 600, loss[loss=0.173, simple_loss=0.2575, pruned_loss=0.04424, over 7203.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2471, pruned_loss=0.03268, over 1359301.51 frames.], batch size: 23, lr: 3.14e-04
+2022-05-15 08:10:45,072 INFO [train.py:812] (0/8) Epoch 25, batch 650, loss[loss=0.1418, simple_loss=0.2181, pruned_loss=0.03274, over 7291.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2469, pruned_loss=0.03286, over 1371535.42 frames.], batch size: 17, lr: 3.14e-04
+2022-05-15 08:11:43,796 INFO [train.py:812] (0/8) Epoch 25, batch 700, loss[loss=0.1314, simple_loss=0.213, pruned_loss=0.0249, over 6761.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2469, pruned_loss=0.03284, over 1387474.68 frames.], batch size: 15, lr: 3.14e-04
+2022-05-15 08:12:42,948 INFO [train.py:812] (0/8) Epoch 25, batch 750, loss[loss=0.1468, simple_loss=0.2411, pruned_loss=0.02623, over 7234.00 frames.], tot_loss[loss=0.157, simple_loss=0.248, pruned_loss=0.03299, over 1397880.25 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:13:42,680 INFO [train.py:812] (0/8) Epoch 25, batch 800, loss[loss=0.1622, simple_loss=0.2592, pruned_loss=0.03259, over 7415.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2491, pruned_loss=0.03327, over 1405275.48 frames.], batch size: 21, lr: 3.14e-04
+2022-05-15 08:14:42,243 INFO [train.py:812] (0/8) Epoch 25, batch 850, loss[loss=0.1641, simple_loss=0.2563, pruned_loss=0.03596, over 7314.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2488, pruned_loss=0.03276, over 1407320.23 frames.], batch size: 21, lr: 3.13e-04
+2022-05-15 08:15:39,812 INFO [train.py:812] (0/8) Epoch 25, batch 900, loss[loss=0.1849, simple_loss=0.288, pruned_loss=0.04093, over 7332.00 frames.], tot_loss[loss=0.1573, simple_loss=0.249, pruned_loss=0.03284, over 1410757.31 frames.], batch size: 25, lr: 3.13e-04
+2022-05-15 08:16:38,337 INFO [train.py:812] (0/8) Epoch 25, batch 950, loss[loss=0.2049, simple_loss=0.2833, pruned_loss=0.06327, over 5037.00 frames.], tot_loss[loss=0.158, simple_loss=0.2492, pruned_loss=0.03341, over 1405475.30 frames.], batch size: 52, lr: 3.13e-04
+2022-05-15 08:17:38,347 INFO [train.py:812] (0/8) Epoch 25, batch 1000, loss[loss=0.1759, simple_loss=0.2633, pruned_loss=0.04424, over 7411.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2499, pruned_loss=0.03369, over 1412132.56 frames.], batch size: 21, lr: 3.13e-04
+2022-05-15 08:18:37,740 INFO [train.py:812] (0/8) Epoch 25, batch 1050, loss[loss=0.1356, simple_loss=0.2361, pruned_loss=0.01753, over 7335.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2493, pruned_loss=0.03324, over 1418897.37 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:19:35,304 INFO [train.py:812] (0/8) Epoch 25, batch 1100, loss[loss=0.1576, simple_loss=0.2513, pruned_loss=0.03194, over 7338.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2489, pruned_loss=0.03312, over 1421015.23 frames.], batch size: 22, lr: 3.13e-04
+2022-05-15 08:20:32,129 INFO [train.py:812] (0/8) Epoch 25, batch 1150, loss[loss=0.1816, simple_loss=0.2865, pruned_loss=0.03832, over 7221.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2487, pruned_loss=0.0334, over 1423288.62 frames.], batch size: 23, lr: 3.13e-04
+2022-05-15 08:21:31,796 INFO [train.py:812] (0/8) Epoch 25, batch 1200, loss[loss=0.1876, simple_loss=0.2703, pruned_loss=0.05246, over 7377.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2495, pruned_loss=0.03393, over 1422987.72 frames.], batch size: 23, lr: 3.13e-04
+2022-05-15 08:22:29,887 INFO [train.py:812] (0/8) Epoch 25, batch 1250, loss[loss=0.1476, simple_loss=0.2415, pruned_loss=0.02687, over 7139.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2493, pruned_loss=0.03414, over 1421744.70 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:23:28,187 INFO [train.py:812] (0/8) Epoch 25, batch 1300, loss[loss=0.1473, simple_loss=0.2196, pruned_loss=0.03746, over 6767.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2485, pruned_loss=0.03391, over 1420306.26 frames.], batch size: 15, lr: 3.13e-04
+2022-05-15 08:24:27,531 INFO [train.py:812] (0/8) Epoch 25, batch 1350, loss[loss=0.1591, simple_loss=0.2538, pruned_loss=0.03215, over 6471.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2485, pruned_loss=0.03359, over 1420737.63 frames.], batch size: 38, lr: 3.13e-04
+2022-05-15 08:25:26,986 INFO [train.py:812] (0/8) Epoch 25, batch 1400, loss[loss=0.1225, simple_loss=0.2156, pruned_loss=0.01467, over 7271.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2483, pruned_loss=0.0332, over 1425703.64 frames.], batch size: 17, lr: 3.13e-04
+2022-05-15 08:26:26,004 INFO [train.py:812] (0/8) Epoch 25, batch 1450, loss[loss=0.1657, simple_loss=0.2664, pruned_loss=0.03249, over 7140.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2479, pruned_loss=0.03318, over 1421938.65 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:27:24,400 INFO [train.py:812] (0/8) Epoch 25, batch 1500, loss[loss=0.1549, simple_loss=0.2543, pruned_loss=0.02773, over 6770.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2482, pruned_loss=0.03326, over 1420315.45 frames.], batch size: 31, lr: 3.13e-04
+2022-05-15 08:28:23,097 INFO [train.py:812] (0/8) Epoch 25, batch 1550, loss[loss=0.1289, simple_loss=0.221, pruned_loss=0.01844, over 7272.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2494, pruned_loss=0.03364, over 1421646.91 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:29:22,770 INFO [train.py:812] (0/8) Epoch 25, batch 1600, loss[loss=0.1625, simple_loss=0.2541, pruned_loss=0.03546, over 7196.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2499, pruned_loss=0.03381, over 1419979.92 frames.], batch size: 16, lr: 3.12e-04
+2022-05-15 08:30:21,912 INFO [train.py:812] (0/8) Epoch 25, batch 1650, loss[loss=0.1687, simple_loss=0.2675, pruned_loss=0.03489, over 7225.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2496, pruned_loss=0.03374, over 1421203.90 frames.], batch size: 21, lr: 3.12e-04
+2022-05-15 08:31:21,145 INFO [train.py:812] (0/8) Epoch 25, batch 1700, loss[loss=0.1739, simple_loss=0.2654, pruned_loss=0.04121, over 7381.00 frames.], tot_loss[loss=0.159, simple_loss=0.2499, pruned_loss=0.03403, over 1419583.42 frames.], batch size: 23, lr: 3.12e-04
+2022-05-15 08:32:19,166 INFO [train.py:812] (0/8) Epoch 25, batch 1750, loss[loss=0.123, simple_loss=0.2166, pruned_loss=0.01477, over 7125.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2489, pruned_loss=0.03339, over 1422784.39 frames.], batch size: 17, lr: 3.12e-04
+2022-05-15 08:33:18,626 INFO [train.py:812] (0/8) Epoch 25, batch 1800, loss[loss=0.1498, simple_loss=0.2209, pruned_loss=0.03935, over 6985.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2488, pruned_loss=0.03311, over 1422660.90 frames.], batch size: 16, lr: 3.12e-04
+2022-05-15 08:34:17,239 INFO [train.py:812] (0/8) Epoch 25, batch 1850, loss[loss=0.1564, simple_loss=0.2355, pruned_loss=0.03865, over 6796.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2478, pruned_loss=0.03298, over 1419937.91 frames.], batch size: 15, lr: 3.12e-04
+2022-05-15 08:35:00,298 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-112000.pt
+2022-05-15 08:35:21,026 INFO [train.py:812] (0/8) Epoch 25, batch 1900, loss[loss=0.1862, simple_loss=0.2802, pruned_loss=0.04609, over 7299.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03263, over 1421909.75 frames.], batch size: 25, lr: 3.12e-04
+2022-05-15 08:36:19,543 INFO [train.py:812] (0/8) Epoch 25, batch 1950, loss[loss=0.1385, simple_loss=0.226, pruned_loss=0.02554, over 7267.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2482, pruned_loss=0.03315, over 1423751.32 frames.], batch size: 19, lr: 3.12e-04
+2022-05-15 08:37:18,257 INFO [train.py:812] (0/8) Epoch 25, batch 2000, loss[loss=0.1641, simple_loss=0.2603, pruned_loss=0.03395, over 7165.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2483, pruned_loss=0.03302, over 1424307.05 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:38:16,614 INFO [train.py:812] (0/8) Epoch 25, batch 2050, loss[loss=0.1952, simple_loss=0.2962, pruned_loss=0.04709, over 7330.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2474, pruned_loss=0.03291, over 1427336.39 frames.], batch size: 21, lr: 3.12e-04
+2022-05-15 08:39:15,903 INFO [train.py:812] (0/8) Epoch 25, batch 2100, loss[loss=0.1557, simple_loss=0.2477, pruned_loss=0.03185, over 7265.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2472, pruned_loss=0.0326, over 1423807.09 frames.], batch size: 19, lr: 3.12e-04
+2022-05-15 08:40:13,572 INFO [train.py:812] (0/8) Epoch 25, batch 2150, loss[loss=0.1543, simple_loss=0.2441, pruned_loss=0.03229, over 7438.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2473, pruned_loss=0.03257, over 1422502.35 frames.], batch size: 20, lr: 3.12e-04
+2022-05-15 08:41:13,432 INFO [train.py:812] (0/8) Epoch 25, batch 2200, loss[loss=0.1279, simple_loss=0.2127, pruned_loss=0.02157, over 6826.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.03223, over 1421153.45 frames.], batch size: 15, lr: 3.12e-04
+2022-05-15 08:42:11,778 INFO [train.py:812] (0/8) Epoch 25, batch 2250, loss[loss=0.1432, simple_loss=0.2381, pruned_loss=0.02417, over 7073.00 frames.], tot_loss[loss=0.1568, simple_loss=0.248, pruned_loss=0.03282, over 1417279.34 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:43:09,217 INFO [train.py:812] (0/8) Epoch 25, batch 2300, loss[loss=0.1293, simple_loss=0.2147, pruned_loss=0.02193, over 6780.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.03225, over 1418376.94 frames.], batch size: 15, lr: 3.11e-04
+2022-05-15 08:44:06,020 INFO [train.py:812] (0/8) Epoch 25, batch 2350, loss[loss=0.1543, simple_loss=0.2513, pruned_loss=0.02862, over 7311.00 frames.], tot_loss[loss=0.1557, simple_loss=0.247, pruned_loss=0.03221, over 1419551.97 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:45:05,374 INFO [train.py:812] (0/8) Epoch 25, batch 2400, loss[loss=0.1481, simple_loss=0.2295, pruned_loss=0.03333, over 7360.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03259, over 1424701.05 frames.], batch size: 19, lr: 3.11e-04
+2022-05-15 08:46:04,782 INFO [train.py:812] (0/8) Epoch 25, batch 2450, loss[loss=0.1359, simple_loss=0.2271, pruned_loss=0.02235, over 7154.00 frames.], tot_loss[loss=0.1567, simple_loss=0.248, pruned_loss=0.0327, over 1423717.09 frames.], batch size: 17, lr: 3.11e-04
+2022-05-15 08:47:04,376 INFO [train.py:812] (0/8) Epoch 25, batch 2500, loss[loss=0.185, simple_loss=0.2782, pruned_loss=0.04587, over 7414.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2482, pruned_loss=0.0331, over 1424379.97 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:48:03,389 INFO [train.py:812] (0/8) Epoch 25, batch 2550, loss[loss=0.1619, simple_loss=0.2609, pruned_loss=0.03139, over 7433.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2492, pruned_loss=0.03331, over 1425584.83 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:49:03,058 INFO [train.py:812] (0/8) Epoch 25, batch 2600, loss[loss=0.1402, simple_loss=0.2178, pruned_loss=0.03135, over 7134.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2496, pruned_loss=0.03385, over 1422452.17 frames.], batch size: 17, lr: 3.11e-04
+2022-05-15 08:50:01,832 INFO [train.py:812] (0/8) Epoch 25, batch 2650, loss[loss=0.165, simple_loss=0.2519, pruned_loss=0.03907, over 7207.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2497, pruned_loss=0.03352, over 1424155.11 frames.], batch size: 22, lr: 3.11e-04
+2022-05-15 08:51:09,555 INFO [train.py:812] (0/8) Epoch 25, batch 2700, loss[loss=0.1379, simple_loss=0.2237, pruned_loss=0.02603, over 7075.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2489, pruned_loss=0.03326, over 1426737.70 frames.], batch size: 18, lr: 3.11e-04
+2022-05-15 08:52:06,906 INFO [train.py:812] (0/8) Epoch 25, batch 2750, loss[loss=0.1781, simple_loss=0.2697, pruned_loss=0.04325, over 7141.00 frames.], tot_loss[loss=0.157, simple_loss=0.2479, pruned_loss=0.033, over 1421106.84 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:53:06,500 INFO [train.py:812] (0/8) Epoch 25, batch 2800, loss[loss=0.1679, simple_loss=0.25, pruned_loss=0.04292, over 7256.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.03269, over 1421310.18 frames.], batch size: 19, lr: 3.11e-04
+2022-05-15 08:54:05,448 INFO [train.py:812] (0/8) Epoch 25, batch 2850, loss[loss=0.156, simple_loss=0.2471, pruned_loss=0.03247, over 7422.00 frames.], tot_loss[loss=0.156, simple_loss=0.2475, pruned_loss=0.03228, over 1419021.19 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:55:04,572 INFO [train.py:812] (0/8) Epoch 25, batch 2900, loss[loss=0.1682, simple_loss=0.2649, pruned_loss=0.03578, over 7207.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2485, pruned_loss=0.03309, over 1420232.11 frames.], batch size: 23, lr: 3.11e-04
+2022-05-15 08:56:02,081 INFO [train.py:812] (0/8) Epoch 25, batch 2950, loss[loss=0.1384, simple_loss=0.2301, pruned_loss=0.02341, over 7124.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2486, pruned_loss=0.03277, over 1426069.39 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:57:29,011 INFO [train.py:812] (0/8) Epoch 25, batch 3000, loss[loss=0.148, simple_loss=0.2463, pruned_loss=0.02488, over 6908.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2472, pruned_loss=0.03259, over 1428824.06 frames.], batch size: 32, lr: 3.10e-04
+2022-05-15 08:57:29,012 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 08:57:46,643 INFO [train.py:841] (0/8) Epoch 25, validation: loss=0.1532, simple_loss=0.2507, pruned_loss=0.02787, over 698248.00 frames.
+2022-05-15 08:58:45,991 INFO [train.py:812] (0/8) Epoch 25, batch 3050, loss[loss=0.1501, simple_loss=0.2516, pruned_loss=0.02435, over 7119.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2473, pruned_loss=0.03262, over 1428734.37 frames.], batch size: 21, lr: 3.10e-04
+2022-05-15 08:59:53,863 INFO [train.py:812] (0/8) Epoch 25, batch 3100, loss[loss=0.1327, simple_loss=0.2128, pruned_loss=0.02631, over 6790.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2464, pruned_loss=0.0325, over 1428577.57 frames.], batch size: 15, lr: 3.10e-04
+2022-05-15 09:01:01,452 INFO [train.py:812] (0/8) Epoch 25, batch 3150, loss[loss=0.164, simple_loss=0.2512, pruned_loss=0.03842, over 7251.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2472, pruned_loss=0.03285, over 1430116.59 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:02:01,435 INFO [train.py:812] (0/8) Epoch 25, batch 3200, loss[loss=0.19, simple_loss=0.2656, pruned_loss=0.05715, over 5167.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2469, pruned_loss=0.03295, over 1428621.37 frames.], batch size: 54, lr: 3.10e-04
+2022-05-15 09:03:00,343 INFO [train.py:812] (0/8) Epoch 25, batch 3250, loss[loss=0.1835, simple_loss=0.2828, pruned_loss=0.0421, over 7235.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2471, pruned_loss=0.03318, over 1426259.24 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:03:59,273 INFO [train.py:812] (0/8) Epoch 25, batch 3300, loss[loss=0.1318, simple_loss=0.2243, pruned_loss=0.01966, over 7166.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2476, pruned_loss=0.03345, over 1426105.49 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:04:58,413 INFO [train.py:812] (0/8) Epoch 25, batch 3350, loss[loss=0.135, simple_loss=0.2375, pruned_loss=0.01629, over 7262.00 frames.], tot_loss[loss=0.1574, simple_loss=0.248, pruned_loss=0.03342, over 1422762.90 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:05:57,608 INFO [train.py:812] (0/8) Epoch 25, batch 3400, loss[loss=0.1379, simple_loss=0.2262, pruned_loss=0.02483, over 7276.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2473, pruned_loss=0.03319, over 1424156.98 frames.], batch size: 17, lr: 3.10e-04
+2022-05-15 09:06:55,958 INFO [train.py:812] (0/8) Epoch 25, batch 3450, loss[loss=0.1391, simple_loss=0.2355, pruned_loss=0.02135, over 7220.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2477, pruned_loss=0.03339, over 1420867.55 frames.], batch size: 21, lr: 3.10e-04
+2022-05-15 09:07:54,088 INFO [train.py:812] (0/8) Epoch 25, batch 3500, loss[loss=0.1303, simple_loss=0.2165, pruned_loss=0.02204, over 7137.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03286, over 1422322.30 frames.], batch size: 17, lr: 3.10e-04
+2022-05-15 09:08:53,534 INFO [train.py:812] (0/8) Epoch 25, batch 3550, loss[loss=0.1557, simple_loss=0.2572, pruned_loss=0.02716, over 7320.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2485, pruned_loss=0.03305, over 1423349.13 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:09:52,747 INFO [train.py:812] (0/8) Epoch 25, batch 3600, loss[loss=0.1629, simple_loss=0.2585, pruned_loss=0.03365, over 7201.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2484, pruned_loss=0.03294, over 1421668.10 frames.], batch size: 23, lr: 3.10e-04
+2022-05-15 09:10:51,685 INFO [train.py:812] (0/8) Epoch 25, batch 3650, loss[loss=0.1628, simple_loss=0.2602, pruned_loss=0.03264, over 6657.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2489, pruned_loss=0.03321, over 1418210.01 frames.], batch size: 38, lr: 3.10e-04
+2022-05-15 09:11:51,259 INFO [train.py:812] (0/8) Epoch 25, batch 3700, loss[loss=0.1295, simple_loss=0.221, pruned_loss=0.01901, over 7431.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2486, pruned_loss=0.03357, over 1421575.38 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:12:50,494 INFO [train.py:812] (0/8) Epoch 25, batch 3750, loss[loss=0.162, simple_loss=0.2592, pruned_loss=0.03238, over 7384.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2484, pruned_loss=0.03328, over 1424397.70 frames.], batch size: 23, lr: 3.09e-04
+2022-05-15 09:13:50,117 INFO [train.py:812] (0/8) Epoch 25, batch 3800, loss[loss=0.1607, simple_loss=0.2428, pruned_loss=0.03936, over 4922.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2483, pruned_loss=0.03338, over 1421571.55 frames.], batch size: 52, lr: 3.09e-04
+2022-05-15 09:14:48,007 INFO [train.py:812] (0/8) Epoch 25, batch 3850, loss[loss=0.1509, simple_loss=0.2317, pruned_loss=0.03503, over 7272.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2482, pruned_loss=0.03311, over 1421087.05 frames.], batch size: 18, lr: 3.09e-04
+2022-05-15 09:15:47,045 INFO [train.py:812] (0/8) Epoch 25, batch 3900, loss[loss=0.158, simple_loss=0.2493, pruned_loss=0.03332, over 7265.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2485, pruned_loss=0.03332, over 1420221.94 frames.], batch size: 19, lr: 3.09e-04
+2022-05-15 09:16:44,713 INFO [train.py:812] (0/8) Epoch 25, batch 3950, loss[loss=0.1411, simple_loss=0.226, pruned_loss=0.02809, over 7394.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2483, pruned_loss=0.03311, over 1422822.86 frames.], batch size: 18, lr: 3.09e-04
+2022-05-15 09:17:43,660 INFO [train.py:812] (0/8) Epoch 25, batch 4000, loss[loss=0.1739, simple_loss=0.2731, pruned_loss=0.03734, over 7319.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2487, pruned_loss=0.03315, over 1422907.68 frames.], batch size: 21, lr: 3.09e-04
+2022-05-15 09:18:42,641 INFO [train.py:812] (0/8) Epoch 25, batch 4050, loss[loss=0.1483, simple_loss=0.2346, pruned_loss=0.03095, over 7421.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.0327, over 1421319.75 frames.], batch size: 20, lr: 3.09e-04
+2022-05-15 09:19:41,937 INFO [train.py:812] (0/8) Epoch 25, batch 4100, loss[loss=0.1626, simple_loss=0.2554, pruned_loss=0.03487, over 6370.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2485, pruned_loss=0.0331, over 1421625.79 frames.], batch size: 37, lr: 3.09e-04
+2022-05-15 09:20:41,037 INFO [train.py:812] (0/8) Epoch 25, batch 4150, loss[loss=0.171, simple_loss=0.2647, pruned_loss=0.03867, over 7214.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03326, over 1417913.38 frames.], batch size: 21, lr: 3.09e-04
+2022-05-15 09:21:39,846 INFO [train.py:812] (0/8) Epoch 25, batch 4200, loss[loss=0.1774, simple_loss=0.2733, pruned_loss=0.0407, over 7201.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2498, pruned_loss=0.03377, over 1419515.15 frames.], batch size: 23, lr: 3.09e-04
+2022-05-15 09:22:38,492 INFO [train.py:812] (0/8) Epoch 25, batch 4250, loss[loss=0.1529, simple_loss=0.2545, pruned_loss=0.02561, over 6367.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2488, pruned_loss=0.03345, over 1414501.74 frames.], batch size: 38, lr: 3.09e-04
+2022-05-15 09:23:37,026 INFO [train.py:812] (0/8) Epoch 25, batch 4300, loss[loss=0.1521, simple_loss=0.2482, pruned_loss=0.02799, over 7164.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2478, pruned_loss=0.03321, over 1414825.56 frames.], batch size: 19, lr: 3.09e-04
+2022-05-15 09:24:36,159 INFO [train.py:812] (0/8) Epoch 25, batch 4350, loss[loss=0.1572, simple_loss=0.2514, pruned_loss=0.03151, over 7326.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2469, pruned_loss=0.03297, over 1414616.53 frames.], batch size: 25, lr: 3.09e-04
+2022-05-15 09:25:35,364 INFO [train.py:812] (0/8) Epoch 25, batch 4400, loss[loss=0.1725, simple_loss=0.2608, pruned_loss=0.04212, over 7286.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2481, pruned_loss=0.0332, over 1413542.81 frames.], batch size: 24, lr: 3.09e-04
+2022-05-15 09:26:34,023 INFO [train.py:812] (0/8) Epoch 25, batch 4450, loss[loss=0.1648, simple_loss=0.2625, pruned_loss=0.03357, over 7265.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2502, pruned_loss=0.03397, over 1405280.68 frames.], batch size: 25, lr: 3.09e-04
+2022-05-15 09:27:33,014 INFO [train.py:812] (0/8) Epoch 25, batch 4500, loss[loss=0.1612, simple_loss=0.2475, pruned_loss=0.03739, over 5160.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2522, pruned_loss=0.0346, over 1390368.19 frames.], batch size: 52, lr: 3.08e-04
+2022-05-15 09:28:30,322 INFO [train.py:812] (0/8) Epoch 25, batch 4550, loss[loss=0.2032, simple_loss=0.2818, pruned_loss=0.06227, over 4888.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2534, pruned_loss=0.03494, over 1352626.16 frames.], batch size: 53, lr: 3.08e-04
+2022-05-15 09:29:15,293 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-25.pt
+2022-05-15 09:29:36,607 INFO [train.py:812] (0/8) Epoch 26, batch 0, loss[loss=0.1609, simple_loss=0.2525, pruned_loss=0.03465, over 7221.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2525, pruned_loss=0.03465, over 7221.00 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:30:35,849 INFO [train.py:812] (0/8) Epoch 26, batch 50, loss[loss=0.1556, simple_loss=0.248, pruned_loss=0.03158, over 7323.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2449, pruned_loss=0.0308, over 322727.58 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:31:35,514 INFO [train.py:812] (0/8) Epoch 26, batch 100, loss[loss=0.2069, simple_loss=0.2838, pruned_loss=0.06496, over 4935.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2481, pruned_loss=0.03215, over 566465.17 frames.], batch size: 53, lr: 3.02e-04
+2022-05-15 09:32:35,330 INFO [train.py:812] (0/8) Epoch 26, batch 150, loss[loss=0.1677, simple_loss=0.2437, pruned_loss=0.04583, over 7273.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2485, pruned_loss=0.03328, over 759810.14 frames.], batch size: 17, lr: 3.02e-04
+2022-05-15 09:33:34,915 INFO [train.py:812] (0/8) Epoch 26, batch 200, loss[loss=0.1679, simple_loss=0.2682, pruned_loss=0.03384, over 7359.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.03257, over 907383.74 frames.], batch size: 23, lr: 3.02e-04
+2022-05-15 09:34:32,609 INFO [train.py:812] (0/8) Epoch 26, batch 250, loss[loss=0.1619, simple_loss=0.2564, pruned_loss=0.03374, over 7218.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2484, pruned_loss=0.03363, over 1020820.22 frames.], batch size: 22, lr: 3.02e-04
+2022-05-15 09:35:31,865 INFO [train.py:812] (0/8) Epoch 26, batch 300, loss[loss=0.1683, simple_loss=0.2618, pruned_loss=0.0374, over 7320.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2487, pruned_loss=0.0335, over 1106930.31 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:36:29,848 INFO [train.py:812] (0/8) Epoch 26, batch 350, loss[loss=0.1452, simple_loss=0.2414, pruned_loss=0.02445, over 7165.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2473, pruned_loss=0.03271, over 1176034.47 frames.], batch size: 18, lr: 3.02e-04
+2022-05-15 09:37:29,641 INFO [train.py:812] (0/8) Epoch 26, batch 400, loss[loss=0.1338, simple_loss=0.2132, pruned_loss=0.02715, over 7391.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2476, pruned_loss=0.03275, over 1233814.84 frames.], batch size: 18, lr: 3.02e-04
+2022-05-15 09:38:28,205 INFO [train.py:812] (0/8) Epoch 26, batch 450, loss[loss=0.1697, simple_loss=0.2666, pruned_loss=0.03642, over 7421.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2469, pruned_loss=0.03234, over 1274826.20 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:39:25,642 INFO [train.py:812] (0/8) Epoch 26, batch 500, loss[loss=0.1485, simple_loss=0.2407, pruned_loss=0.02815, over 7378.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.03229, over 1302495.68 frames.], batch size: 23, lr: 3.02e-04
+2022-05-15 09:40:22,336 INFO [train.py:812] (0/8) Epoch 26, batch 550, loss[loss=0.1775, simple_loss=0.2674, pruned_loss=0.04375, over 7237.00 frames.], tot_loss[loss=0.1547, simple_loss=0.246, pruned_loss=0.03169, over 1328296.08 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:41:20,613 INFO [train.py:812] (0/8) Epoch 26, batch 600, loss[loss=0.1459, simple_loss=0.2407, pruned_loss=0.02558, over 7099.00 frames.], tot_loss[loss=0.1547, simple_loss=0.246, pruned_loss=0.03166, over 1346557.43 frames.], batch size: 28, lr: 3.02e-04
+2022-05-15 09:42:19,342 INFO [train.py:812] (0/8) Epoch 26, batch 650, loss[loss=0.1415, simple_loss=0.2366, pruned_loss=0.02313, over 7332.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2457, pruned_loss=0.03173, over 1360613.98 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:43:17,906 INFO [train.py:812] (0/8) Epoch 26, batch 700, loss[loss=0.1561, simple_loss=0.2509, pruned_loss=0.03062, over 7146.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2457, pruned_loss=0.03187, over 1373810.17 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:44:17,488 INFO [train.py:812] (0/8) Epoch 26, batch 750, loss[loss=0.1581, simple_loss=0.2532, pruned_loss=0.03153, over 7436.00 frames.], tot_loss[loss=0.155, simple_loss=0.2461, pruned_loss=0.03192, over 1389838.73 frames.], batch size: 20, lr: 3.01e-04
+2022-05-15 09:45:17,288 INFO [train.py:812] (0/8) Epoch 26, batch 800, loss[loss=0.1566, simple_loss=0.2515, pruned_loss=0.03086, over 6806.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2468, pruned_loss=0.03206, over 1395117.45 frames.], batch size: 31, lr: 3.01e-04
+2022-05-15 09:46:14,826 INFO [train.py:812] (0/8) Epoch 26, batch 850, loss[loss=0.1672, simple_loss=0.258, pruned_loss=0.03825, over 7121.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2481, pruned_loss=0.03257, over 1405702.54 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:47:13,158 INFO [train.py:812] (0/8) Epoch 26, batch 900, loss[loss=0.1326, simple_loss=0.2199, pruned_loss=0.02269, over 7214.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.0324, over 1405967.27 frames.], batch size: 16, lr: 3.01e-04
+2022-05-15 09:48:12,134 INFO [train.py:812] (0/8) Epoch 26, batch 950, loss[loss=0.1355, simple_loss=0.2208, pruned_loss=0.02506, over 7276.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2477, pruned_loss=0.03241, over 1412214.71 frames.], batch size: 17, lr: 3.01e-04
+2022-05-15 09:49:11,022 INFO [train.py:812] (0/8) Epoch 26, batch 1000, loss[loss=0.142, simple_loss=0.2383, pruned_loss=0.02281, over 7119.00 frames.], tot_loss[loss=0.1568, simple_loss=0.248, pruned_loss=0.0328, over 1410857.69 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:50:10,510 INFO [train.py:812] (0/8) Epoch 26, batch 1050, loss[loss=0.1805, simple_loss=0.2659, pruned_loss=0.04753, over 4932.00 frames.], tot_loss[loss=0.157, simple_loss=0.2482, pruned_loss=0.03292, over 1411927.79 frames.], batch size: 53, lr: 3.01e-04
+2022-05-15 09:51:08,593 INFO [train.py:812] (0/8) Epoch 26, batch 1100, loss[loss=0.1615, simple_loss=0.2608, pruned_loss=0.03115, over 7113.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2486, pruned_loss=0.03306, over 1413209.16 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:52:08,134 INFO [train.py:812] (0/8) Epoch 26, batch 1150, loss[loss=0.1752, simple_loss=0.2637, pruned_loss=0.04335, over 7379.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2484, pruned_loss=0.03315, over 1417786.91 frames.], batch size: 23, lr: 3.01e-04
+2022-05-15 09:53:08,326 INFO [train.py:812] (0/8) Epoch 26, batch 1200, loss[loss=0.1398, simple_loss=0.2209, pruned_loss=0.02935, over 7119.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2475, pruned_loss=0.03285, over 1421593.88 frames.], batch size: 17, lr: 3.01e-04
+2022-05-15 09:54:07,427 INFO [train.py:812] (0/8) Epoch 26, batch 1250, loss[loss=0.1456, simple_loss=0.2384, pruned_loss=0.02639, over 7321.00 frames.], tot_loss[loss=0.157, simple_loss=0.248, pruned_loss=0.03296, over 1423368.14 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:55:04,600 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-116000.pt
+2022-05-15 09:55:11,141 INFO [train.py:812] (0/8) Epoch 26, batch 1300, loss[loss=0.1549, simple_loss=0.2389, pruned_loss=0.03545, over 7431.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2478, pruned_loss=0.03274, over 1426674.34 frames.], batch size: 20, lr: 3.01e-04
+2022-05-15 09:56:09,605 INFO [train.py:812] (0/8) Epoch 26, batch 1350, loss[loss=0.1588, simple_loss=0.2486, pruned_loss=0.03447, over 7332.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2487, pruned_loss=0.03277, over 1426719.17 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:57:07,836 INFO [train.py:812] (0/8) Epoch 26, batch 1400, loss[loss=0.1612, simple_loss=0.2581, pruned_loss=0.03214, over 7343.00 frames.], tot_loss[loss=0.157, simple_loss=0.2486, pruned_loss=0.03269, over 1427105.04 frames.], batch size: 22, lr: 3.01e-04
+2022-05-15 09:58:05,708 INFO [train.py:812] (0/8) Epoch 26, batch 1450, loss[loss=0.1256, simple_loss=0.2125, pruned_loss=0.01934, over 6994.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2475, pruned_loss=0.0325, over 1428697.25 frames.], batch size: 16, lr: 3.01e-04
+2022-05-15 09:59:03,792 INFO [train.py:812] (0/8) Epoch 26, batch 1500, loss[loss=0.1428, simple_loss=0.24, pruned_loss=0.02273, over 7215.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2471, pruned_loss=0.03253, over 1428047.86 frames.], batch size: 21, lr: 3.00e-04
+2022-05-15 10:00:02,491 INFO [train.py:812] (0/8) Epoch 26, batch 1550, loss[loss=0.1291, simple_loss=0.214, pruned_loss=0.0221, over 7139.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2474, pruned_loss=0.03294, over 1427361.92 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:01:01,518 INFO [train.py:812] (0/8) Epoch 26, batch 1600, loss[loss=0.1728, simple_loss=0.2631, pruned_loss=0.04129, over 7152.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2487, pruned_loss=0.03335, over 1424739.54 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:02:00,506 INFO [train.py:812] (0/8) Epoch 26, batch 1650, loss[loss=0.2043, simple_loss=0.3007, pruned_loss=0.054, over 7098.00 frames.], tot_loss[loss=0.1563, simple_loss=0.247, pruned_loss=0.03274, over 1426111.02 frames.], batch size: 28, lr: 3.00e-04
+2022-05-15 10:02:59,721 INFO [train.py:812] (0/8) Epoch 26, batch 1700, loss[loss=0.1536, simple_loss=0.2462, pruned_loss=0.03053, over 7324.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2471, pruned_loss=0.03257, over 1425791.41 frames.], batch size: 21, lr: 3.00e-04
+2022-05-15 10:04:07,542 INFO [train.py:812] (0/8) Epoch 26, batch 1750, loss[loss=0.1329, simple_loss=0.2214, pruned_loss=0.02217, over 7132.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2464, pruned_loss=0.03184, over 1425329.92 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:05:06,528 INFO [train.py:812] (0/8) Epoch 26, batch 1800, loss[loss=0.1463, simple_loss=0.2427, pruned_loss=0.02493, over 7148.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2462, pruned_loss=0.03201, over 1422430.91 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:06:05,323 INFO [train.py:812] (0/8) Epoch 26, batch 1850, loss[loss=0.1506, simple_loss=0.2483, pruned_loss=0.02647, over 7435.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2465, pruned_loss=0.03229, over 1422984.77 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:07:04,880 INFO [train.py:812] (0/8) Epoch 26, batch 1900, loss[loss=0.1336, simple_loss=0.2182, pruned_loss=0.02453, over 7126.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2468, pruned_loss=0.03226, over 1424975.14 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:08:02,585 INFO [train.py:812] (0/8) Epoch 26, batch 1950, loss[loss=0.1629, simple_loss=0.2581, pruned_loss=0.03388, over 5200.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2464, pruned_loss=0.03239, over 1422058.89 frames.], batch size: 52, lr: 3.00e-04
+2022-05-15 10:09:00,910 INFO [train.py:812] (0/8) Epoch 26, batch 2000, loss[loss=0.1477, simple_loss=0.2323, pruned_loss=0.03157, over 7156.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03261, over 1418375.60 frames.], batch size: 19, lr: 3.00e-04
+2022-05-15 10:10:00,183 INFO [train.py:812] (0/8) Epoch 26, batch 2050, loss[loss=0.1646, simple_loss=0.2531, pruned_loss=0.03803, over 7333.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2461, pruned_loss=0.0324, over 1419612.32 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:10:59,281 INFO [train.py:812] (0/8) Epoch 26, batch 2100, loss[loss=0.1847, simple_loss=0.2731, pruned_loss=0.04817, over 7196.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2475, pruned_loss=0.03281, over 1418237.32 frames.], batch size: 22, lr: 3.00e-04
+2022-05-15 10:11:58,206 INFO [train.py:812] (0/8) Epoch 26, batch 2150, loss[loss=0.1239, simple_loss=0.2164, pruned_loss=0.01565, over 7173.00 frames.], tot_loss[loss=0.156, simple_loss=0.2472, pruned_loss=0.03236, over 1419703.27 frames.], batch size: 18, lr: 3.00e-04
+2022-05-15 10:12:57,685 INFO [train.py:812] (0/8) Epoch 26, batch 2200, loss[loss=0.1544, simple_loss=0.2512, pruned_loss=0.02879, over 7074.00 frames.], tot_loss[loss=0.1567, simple_loss=0.248, pruned_loss=0.03271, over 1422035.22 frames.], batch size: 28, lr: 3.00e-04
+2022-05-15 10:13:56,497 INFO [train.py:812] (0/8) Epoch 26, batch 2250, loss[loss=0.1771, simple_loss=0.2654, pruned_loss=0.04439, over 7370.00 frames.], tot_loss[loss=0.1558, simple_loss=0.247, pruned_loss=0.03228, over 1424661.07 frames.], batch size: 23, lr: 3.00e-04
+2022-05-15 10:14:54,808 INFO [train.py:812] (0/8) Epoch 26, batch 2300, loss[loss=0.1421, simple_loss=0.2391, pruned_loss=0.0225, over 7064.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2486, pruned_loss=0.03295, over 1424696.42 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:15:54,078 INFO [train.py:812] (0/8) Epoch 26, batch 2350, loss[loss=0.1533, simple_loss=0.2405, pruned_loss=0.03303, over 7267.00 frames.], tot_loss[loss=0.1566, simple_loss=0.248, pruned_loss=0.03266, over 1424530.30 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:16:53,708 INFO [train.py:812] (0/8) Epoch 26, batch 2400, loss[loss=0.1774, simple_loss=0.2751, pruned_loss=0.03989, over 7380.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03269, over 1422541.33 frames.], batch size: 23, lr: 2.99e-04
+2022-05-15 10:17:52,701 INFO [train.py:812] (0/8) Epoch 26, batch 2450, loss[loss=0.1448, simple_loss=0.2391, pruned_loss=0.02525, over 6712.00 frames.], tot_loss[loss=0.157, simple_loss=0.248, pruned_loss=0.03296, over 1421283.02 frames.], batch size: 31, lr: 2.99e-04
+2022-05-15 10:18:50,828 INFO [train.py:812] (0/8) Epoch 26, batch 2500, loss[loss=0.1382, simple_loss=0.2317, pruned_loss=0.02232, over 7367.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2475, pruned_loss=0.03287, over 1423353.62 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:19:48,019 INFO [train.py:812] (0/8) Epoch 26, batch 2550, loss[loss=0.1333, simple_loss=0.2217, pruned_loss=0.02249, over 7411.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2474, pruned_loss=0.03273, over 1426641.48 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:20:46,858 INFO [train.py:812] (0/8) Epoch 26, batch 2600, loss[loss=0.1701, simple_loss=0.2562, pruned_loss=0.04207, over 7168.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03271, over 1424665.95 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:21:44,711 INFO [train.py:812] (0/8) Epoch 26, batch 2650, loss[loss=0.1794, simple_loss=0.2728, pruned_loss=0.04305, over 7008.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2477, pruned_loss=0.03279, over 1419770.55 frames.], batch size: 28, lr: 2.99e-04
+2022-05-15 10:22:43,794 INFO [train.py:812] (0/8) Epoch 26, batch 2700, loss[loss=0.1464, simple_loss=0.2343, pruned_loss=0.02924, over 7258.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2474, pruned_loss=0.03248, over 1420438.96 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:23:42,373 INFO [train.py:812] (0/8) Epoch 26, batch 2750, loss[loss=0.1951, simple_loss=0.287, pruned_loss=0.05161, over 7277.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.03266, over 1413498.47 frames.], batch size: 25, lr: 2.99e-04
+2022-05-15 10:24:40,556 INFO [train.py:812] (0/8) Epoch 26, batch 2800, loss[loss=0.1496, simple_loss=0.2419, pruned_loss=0.02861, over 7265.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2469, pruned_loss=0.03224, over 1415409.96 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:25:38,075 INFO [train.py:812] (0/8) Epoch 26, batch 2850, loss[loss=0.1505, simple_loss=0.2415, pruned_loss=0.02972, over 7412.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2464, pruned_loss=0.0323, over 1411190.57 frames.], batch size: 21, lr: 2.99e-04
+2022-05-15 10:26:37,831 INFO [train.py:812] (0/8) Epoch 26, batch 2900, loss[loss=0.136, simple_loss=0.2407, pruned_loss=0.01563, over 7144.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2465, pruned_loss=0.03224, over 1417491.11 frames.], batch size: 20, lr: 2.99e-04
+2022-05-15 10:27:35,346 INFO [train.py:812] (0/8) Epoch 26, batch 2950, loss[loss=0.1487, simple_loss=0.2509, pruned_loss=0.02329, over 7323.00 frames.], tot_loss[loss=0.1558, simple_loss=0.247, pruned_loss=0.03235, over 1418288.24 frames.], batch size: 20, lr: 2.99e-04
+2022-05-15 10:28:33,201 INFO [train.py:812] (0/8) Epoch 26, batch 3000, loss[loss=0.1513, simple_loss=0.2467, pruned_loss=0.02796, over 6322.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.03191, over 1422281.64 frames.], batch size: 37, lr: 2.99e-04
+2022-05-15 10:28:33,203 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 10:28:40,783 INFO [train.py:841] (0/8) Epoch 26, validation: loss=0.1534, simple_loss=0.2507, pruned_loss=0.02805, over 698248.00 frames.
+2022-05-15 10:29:38,761 INFO [train.py:812] (0/8) Epoch 26, batch 3050, loss[loss=0.1543, simple_loss=0.2457, pruned_loss=0.03145, over 7348.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2484, pruned_loss=0.03288, over 1422000.80 frames.], batch size: 22, lr: 2.99e-04
+2022-05-15 10:30:38,716 INFO [train.py:812] (0/8) Epoch 26, batch 3100, loss[loss=0.1475, simple_loss=0.2394, pruned_loss=0.02783, over 7254.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2489, pruned_loss=0.03339, over 1420011.71 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:31:36,301 INFO [train.py:812] (0/8) Epoch 26, batch 3150, loss[loss=0.1453, simple_loss=0.2301, pruned_loss=0.03027, over 7120.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2484, pruned_loss=0.03344, over 1419197.83 frames.], batch size: 17, lr: 2.98e-04
+2022-05-15 10:32:35,714 INFO [train.py:812] (0/8) Epoch 26, batch 3200, loss[loss=0.1637, simple_loss=0.245, pruned_loss=0.04117, over 7167.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2487, pruned_loss=0.03345, over 1421523.14 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:33:35,049 INFO [train.py:812] (0/8) Epoch 26, batch 3250, loss[loss=0.1424, simple_loss=0.2352, pruned_loss=0.02478, over 7268.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2465, pruned_loss=0.03286, over 1424616.47 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:34:33,020 INFO [train.py:812] (0/8) Epoch 26, batch 3300, loss[loss=0.155, simple_loss=0.2462, pruned_loss=0.03185, over 7205.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2468, pruned_loss=0.03272, over 1416767.62 frames.], batch size: 26, lr: 2.98e-04
+2022-05-15 10:35:31,809 INFO [train.py:812] (0/8) Epoch 26, batch 3350, loss[loss=0.1712, simple_loss=0.2765, pruned_loss=0.03299, over 7326.00 frames.], tot_loss[loss=0.1561, simple_loss=0.247, pruned_loss=0.03263, over 1412954.53 frames.], batch size: 21, lr: 2.98e-04
+2022-05-15 10:36:31,833 INFO [train.py:812] (0/8) Epoch 26, batch 3400, loss[loss=0.1722, simple_loss=0.2668, pruned_loss=0.0388, over 6339.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2458, pruned_loss=0.03252, over 1418336.06 frames.], batch size: 38, lr: 2.98e-04
+2022-05-15 10:37:30,492 INFO [train.py:812] (0/8) Epoch 26, batch 3450, loss[loss=0.1525, simple_loss=0.2472, pruned_loss=0.02885, over 7162.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2459, pruned_loss=0.03251, over 1418387.48 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:38:29,820 INFO [train.py:812] (0/8) Epoch 26, batch 3500, loss[loss=0.1592, simple_loss=0.2615, pruned_loss=0.02846, over 7385.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2464, pruned_loss=0.03229, over 1417786.05 frames.], batch size: 23, lr: 2.98e-04
+2022-05-15 10:39:28,319 INFO [train.py:812] (0/8) Epoch 26, batch 3550, loss[loss=0.1445, simple_loss=0.2426, pruned_loss=0.02322, over 7415.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03209, over 1420269.58 frames.], batch size: 21, lr: 2.98e-04
+2022-05-15 10:40:26,270 INFO [train.py:812] (0/8) Epoch 26, batch 3600, loss[loss=0.1697, simple_loss=0.2617, pruned_loss=0.0388, over 7203.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2453, pruned_loss=0.03187, over 1425413.18 frames.], batch size: 23, lr: 2.98e-04
+2022-05-15 10:41:25,802 INFO [train.py:812] (0/8) Epoch 26, batch 3650, loss[loss=0.1565, simple_loss=0.2417, pruned_loss=0.0357, over 7257.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2464, pruned_loss=0.03211, over 1427619.72 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:42:23,892 INFO [train.py:812] (0/8) Epoch 26, batch 3700, loss[loss=0.14, simple_loss=0.2261, pruned_loss=0.02695, over 7067.00 frames.], tot_loss[loss=0.155, simple_loss=0.246, pruned_loss=0.03198, over 1424804.40 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:43:23,032 INFO [train.py:812] (0/8) Epoch 26, batch 3750, loss[loss=0.1664, simple_loss=0.2602, pruned_loss=0.03629, over 7155.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2462, pruned_loss=0.03212, over 1423751.80 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:44:21,307 INFO [train.py:812] (0/8) Epoch 26, batch 3800, loss[loss=0.1343, simple_loss=0.2379, pruned_loss=0.01534, over 6231.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2463, pruned_loss=0.03216, over 1421225.53 frames.], batch size: 37, lr: 2.98e-04
+2022-05-15 10:45:20,470 INFO [train.py:812] (0/8) Epoch 26, batch 3850, loss[loss=0.1596, simple_loss=0.2593, pruned_loss=0.02996, over 7149.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.03247, over 1418770.30 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:46:20,033 INFO [train.py:812] (0/8) Epoch 26, batch 3900, loss[loss=0.1519, simple_loss=0.239, pruned_loss=0.03245, over 7396.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2472, pruned_loss=0.03255, over 1421088.41 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:47:17,433 INFO [train.py:812] (0/8) Epoch 26, batch 3950, loss[loss=0.1573, simple_loss=0.2612, pruned_loss=0.02664, over 7238.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2469, pruned_loss=0.03228, over 1425570.82 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:48:16,825 INFO [train.py:812] (0/8) Epoch 26, batch 4000, loss[loss=0.1463, simple_loss=0.2384, pruned_loss=0.02714, over 7431.00 frames.], tot_loss[loss=0.1559, simple_loss=0.247, pruned_loss=0.03234, over 1419503.45 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:49:15,562 INFO [train.py:812] (0/8) Epoch 26, batch 4050, loss[loss=0.1485, simple_loss=0.2484, pruned_loss=0.02426, over 7416.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2477, pruned_loss=0.03258, over 1421480.49 frames.], batch size: 21, lr: 2.97e-04
+2022-05-15 10:50:14,944 INFO [train.py:812] (0/8) Epoch 26, batch 4100, loss[loss=0.15, simple_loss=0.2488, pruned_loss=0.02557, over 7412.00 frames.], tot_loss[loss=0.1574, simple_loss=0.249, pruned_loss=0.0329, over 1419775.08 frames.], batch size: 21, lr: 2.97e-04
+2022-05-15 10:51:14,789 INFO [train.py:812] (0/8) Epoch 26, batch 4150, loss[loss=0.1518, simple_loss=0.2435, pruned_loss=0.03006, over 7250.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2484, pruned_loss=0.03258, over 1424539.81 frames.], batch size: 19, lr: 2.97e-04
+2022-05-15 10:52:13,204 INFO [train.py:812] (0/8) Epoch 26, batch 4200, loss[loss=0.1581, simple_loss=0.2536, pruned_loss=0.03128, over 7018.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2487, pruned_loss=0.03271, over 1420403.96 frames.], batch size: 28, lr: 2.97e-04
+2022-05-15 10:53:19,323 INFO [train.py:812] (0/8) Epoch 26, batch 4250, loss[loss=0.1568, simple_loss=0.2469, pruned_loss=0.03333, over 7173.00 frames.], tot_loss[loss=0.157, simple_loss=0.2482, pruned_loss=0.03289, over 1419966.93 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:54:17,955 INFO [train.py:812] (0/8) Epoch 26, batch 4300, loss[loss=0.162, simple_loss=0.2627, pruned_loss=0.03067, over 7165.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2482, pruned_loss=0.03275, over 1422903.00 frames.], batch size: 26, lr: 2.97e-04
+2022-05-15 10:55:15,837 INFO [train.py:812] (0/8) Epoch 26, batch 4350, loss[loss=0.1613, simple_loss=0.2574, pruned_loss=0.0326, over 7231.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2482, pruned_loss=0.03276, over 1416146.85 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:56:15,064 INFO [train.py:812] (0/8) Epoch 26, batch 4400, loss[loss=0.1521, simple_loss=0.2409, pruned_loss=0.03162, over 7070.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2493, pruned_loss=0.03308, over 1415243.01 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:57:23,163 INFO [train.py:812] (0/8) Epoch 26, batch 4450, loss[loss=0.149, simple_loss=0.2451, pruned_loss=0.0264, over 7287.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2488, pruned_loss=0.03281, over 1414125.74 frames.], batch size: 24, lr: 2.97e-04
+2022-05-15 10:58:40,685 INFO [train.py:812] (0/8) Epoch 26, batch 4500, loss[loss=0.1373, simple_loss=0.2379, pruned_loss=0.01835, over 7332.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2487, pruned_loss=0.03294, over 1398675.71 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:59:48,358 INFO [train.py:812] (0/8) Epoch 26, batch 4550, loss[loss=0.1861, simple_loss=0.2724, pruned_loss=0.04992, over 5393.00 frames.], tot_loss[loss=0.1579, simple_loss=0.249, pruned_loss=0.03342, over 1389667.99 frames.], batch size: 53, lr: 2.97e-04
+2022-05-15 11:00:42,203 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-26.pt
+2022-05-15 11:01:05,808 INFO [train.py:812] (0/8) Epoch 27, batch 0, loss[loss=0.1305, simple_loss=0.2122, pruned_loss=0.02447, over 7161.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2122, pruned_loss=0.02447, over 7161.00 frames.], batch size: 18, lr: 2.91e-04
+2022-05-15 11:02:14,193 INFO [train.py:812] (0/8) Epoch 27, batch 50, loss[loss=0.1413, simple_loss=0.2276, pruned_loss=0.02753, over 7268.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2427, pruned_loss=0.03121, over 318683.69 frames.], batch size: 17, lr: 2.91e-04
+2022-05-15 11:03:12,400 INFO [train.py:812] (0/8) Epoch 27, batch 100, loss[loss=0.1248, simple_loss=0.2123, pruned_loss=0.01862, over 7270.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2453, pruned_loss=0.03219, over 562659.31 frames.], batch size: 17, lr: 2.91e-04
+2022-05-15 11:04:11,552 INFO [train.py:812] (0/8) Epoch 27, batch 150, loss[loss=0.1611, simple_loss=0.2553, pruned_loss=0.03344, over 6309.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2462, pruned_loss=0.03221, over 751176.56 frames.], batch size: 37, lr: 2.91e-04
+2022-05-15 11:05:08,369 INFO [train.py:812] (0/8) Epoch 27, batch 200, loss[loss=0.1768, simple_loss=0.2711, pruned_loss=0.0413, over 7161.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2469, pruned_loss=0.03239, over 894486.09 frames.], batch size: 26, lr: 2.91e-04
+2022-05-15 11:06:06,640 INFO [train.py:812] (0/8) Epoch 27, batch 250, loss[loss=0.1562, simple_loss=0.2489, pruned_loss=0.03173, over 6173.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2474, pruned_loss=0.03267, over 1006397.62 frames.], batch size: 37, lr: 2.91e-04
+2022-05-15 11:07:05,794 INFO [train.py:812] (0/8) Epoch 27, batch 300, loss[loss=0.1881, simple_loss=0.286, pruned_loss=0.04512, over 6385.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2476, pruned_loss=0.03267, over 1100207.58 frames.], batch size: 37, lr: 2.91e-04
+2022-05-15 11:08:04,238 INFO [train.py:812] (0/8) Epoch 27, batch 350, loss[loss=0.1628, simple_loss=0.2539, pruned_loss=0.0359, over 6802.00 frames.], tot_loss[loss=0.156, simple_loss=0.247, pruned_loss=0.03254, over 1167973.78 frames.], batch size: 31, lr: 2.91e-04
+2022-05-15 11:09:03,276 INFO [train.py:812] (0/8) Epoch 27, batch 400, loss[loss=0.1473, simple_loss=0.2389, pruned_loss=0.02788, over 7153.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2458, pruned_loss=0.03177, over 1228108.85 frames.], batch size: 20, lr: 2.91e-04
+2022-05-15 11:10:01,855 INFO [train.py:812] (0/8) Epoch 27, batch 450, loss[loss=0.1491, simple_loss=0.2441, pruned_loss=0.02708, over 7236.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2457, pruned_loss=0.0316, over 1275600.31 frames.], batch size: 20, lr: 2.91e-04
+2022-05-15 11:10:59,676 INFO [train.py:812] (0/8) Epoch 27, batch 500, loss[loss=0.1862, simple_loss=0.2662, pruned_loss=0.05308, over 4904.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2456, pruned_loss=0.03163, over 1307284.81 frames.], batch size: 52, lr: 2.91e-04
+2022-05-15 11:11:59,498 INFO [train.py:812] (0/8) Epoch 27, batch 550, loss[loss=0.1627, simple_loss=0.2538, pruned_loss=0.03581, over 7202.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2465, pruned_loss=0.03211, over 1332638.13 frames.], batch size: 22, lr: 2.90e-04
+2022-05-15 11:12:58,962 INFO [train.py:812] (0/8) Epoch 27, batch 600, loss[loss=0.1538, simple_loss=0.2464, pruned_loss=0.03065, over 7268.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2464, pruned_loss=0.03193, over 1355752.78 frames.], batch size: 19, lr: 2.90e-04
+2022-05-15 11:13:58,728 INFO [train.py:812] (0/8) Epoch 27, batch 650, loss[loss=0.1383, simple_loss=0.2292, pruned_loss=0.02364, over 7286.00 frames.], tot_loss[loss=0.154, simple_loss=0.2452, pruned_loss=0.03143, over 1372070.36 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:14:57,696 INFO [train.py:812] (0/8) Epoch 27, batch 700, loss[loss=0.1504, simple_loss=0.2408, pruned_loss=0.02996, over 7124.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2462, pruned_loss=0.03149, over 1382151.38 frames.], batch size: 21, lr: 2.90e-04
+2022-05-15 11:15:11,088 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-120000.pt
+2022-05-15 11:16:01,099 INFO [train.py:812] (0/8) Epoch 27, batch 750, loss[loss=0.1352, simple_loss=0.2324, pruned_loss=0.01899, over 7139.00 frames.], tot_loss[loss=0.154, simple_loss=0.2457, pruned_loss=0.03118, over 1390188.76 frames.], batch size: 20, lr: 2.90e-04
+2022-05-15 11:17:00,042 INFO [train.py:812] (0/8) Epoch 27, batch 800, loss[loss=0.1412, simple_loss=0.2358, pruned_loss=0.02329, over 7233.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2458, pruned_loss=0.03151, over 1395707.44 frames.], batch size: 20, lr: 2.90e-04
+2022-05-15 11:17:59,351 INFO [train.py:812] (0/8) Epoch 27, batch 850, loss[loss=0.1747, simple_loss=0.2615, pruned_loss=0.04397, over 4971.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2474, pruned_loss=0.03185, over 1398517.03 frames.], batch size: 52, lr: 2.90e-04
+2022-05-15 11:18:57,710 INFO [train.py:812] (0/8) Epoch 27, batch 900, loss[loss=0.1257, simple_loss=0.2089, pruned_loss=0.02126, over 7416.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.03188, over 1407258.18 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:19:56,346 INFO [train.py:812] (0/8) Epoch 27, batch 950, loss[loss=0.137, simple_loss=0.2146, pruned_loss=0.02967, over 6754.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2473, pruned_loss=0.03186, over 1408063.43 frames.], batch size: 15, lr: 2.90e-04
+2022-05-15 11:20:55,292 INFO [train.py:812] (0/8) Epoch 27, batch 1000, loss[loss=0.2033, simple_loss=0.2957, pruned_loss=0.05543, over 7295.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2485, pruned_loss=0.03254, over 1411402.02 frames.], batch size: 24, lr: 2.90e-04
+2022-05-15 11:21:53,188 INFO [train.py:812] (0/8) Epoch 27, batch 1050, loss[loss=0.1529, simple_loss=0.2475, pruned_loss=0.02915, over 7193.00 frames.], tot_loss[loss=0.1563, simple_loss=0.248, pruned_loss=0.03229, over 1416533.20 frames.], batch size: 23, lr: 2.90e-04
+2022-05-15 11:22:52,445 INFO [train.py:812] (0/8) Epoch 27, batch 1100, loss[loss=0.1695, simple_loss=0.2656, pruned_loss=0.03667, over 7200.00 frames.], tot_loss[loss=0.155, simple_loss=0.2464, pruned_loss=0.03175, over 1421564.10 frames.], batch size: 22, lr: 2.90e-04
+2022-05-15 11:23:52,071 INFO [train.py:812] (0/8) Epoch 27, batch 1150, loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.02993, over 7163.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2473, pruned_loss=0.03209, over 1423282.29 frames.], batch size: 19, lr: 2.90e-04
+2022-05-15 11:24:50,273 INFO [train.py:812] (0/8) Epoch 27, batch 1200, loss[loss=0.1741, simple_loss=0.2616, pruned_loss=0.04333, over 7299.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2472, pruned_loss=0.03203, over 1427357.40 frames.], batch size: 24, lr: 2.90e-04
+2022-05-15 11:25:49,857 INFO [train.py:812] (0/8) Epoch 27, batch 1250, loss[loss=0.183, simple_loss=0.2831, pruned_loss=0.04146, over 6609.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2474, pruned_loss=0.0322, over 1426794.29 frames.], batch size: 39, lr: 2.90e-04
+2022-05-15 11:26:48,360 INFO [train.py:812] (0/8) Epoch 27, batch 1300, loss[loss=0.1333, simple_loss=0.2198, pruned_loss=0.02342, over 7277.00 frames.], tot_loss[loss=0.156, simple_loss=0.2474, pruned_loss=0.03236, over 1422661.55 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:27:46,500 INFO [train.py:812] (0/8) Epoch 27, batch 1350, loss[loss=0.1291, simple_loss=0.2196, pruned_loss=0.01929, over 7418.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2456, pruned_loss=0.03201, over 1426024.12 frames.], batch size: 18, lr: 2.89e-04
+2022-05-15 11:28:44,276 INFO [train.py:812] (0/8) Epoch 27, batch 1400, loss[loss=0.1733, simple_loss=0.2813, pruned_loss=0.03264, over 7212.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2456, pruned_loss=0.03208, over 1418261.51 frames.], batch size: 23, lr: 2.89e-04
+2022-05-15 11:29:43,240 INFO [train.py:812] (0/8) Epoch 27, batch 1450, loss[loss=0.1508, simple_loss=0.2351, pruned_loss=0.03331, over 7279.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2463, pruned_loss=0.03229, over 1420623.83 frames.], batch size: 18, lr: 2.89e-04
+2022-05-15 11:30:41,587 INFO [train.py:812] (0/8) Epoch 27, batch 1500, loss[loss=0.1653, simple_loss=0.246, pruned_loss=0.04235, over 4679.00 frames.], tot_loss[loss=0.1549, simple_loss=0.246, pruned_loss=0.03189, over 1416240.33 frames.], batch size: 52, lr: 2.89e-04
+2022-05-15 11:31:41,139 INFO [train.py:812] (0/8) Epoch 27, batch 1550, loss[loss=0.163, simple_loss=0.2618, pruned_loss=0.03207, over 7123.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2464, pruned_loss=0.03222, over 1420495.75 frames.], batch size: 21, lr: 2.89e-04
+2022-05-15 11:32:40,520 INFO [train.py:812] (0/8) Epoch 27, batch 1600, loss[loss=0.1577, simple_loss=0.2492, pruned_loss=0.03312, over 7253.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2456, pruned_loss=0.03213, over 1424218.31 frames.], batch size: 19, lr: 2.89e-04
+2022-05-15 11:33:39,616 INFO [train.py:812] (0/8) Epoch 27, batch 1650, loss[loss=0.2031, simple_loss=0.3049, pruned_loss=0.0506, over 7171.00 frames.], tot_loss[loss=0.155, simple_loss=0.2456, pruned_loss=0.03219, over 1428012.18 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:34:37,981 INFO [train.py:812] (0/8) Epoch 27, batch 1700, loss[loss=0.1655, simple_loss=0.2594, pruned_loss=0.03581, over 7335.00 frames.], tot_loss[loss=0.155, simple_loss=0.2458, pruned_loss=0.03207, over 1429913.49 frames.], batch size: 22, lr: 2.89e-04
+2022-05-15 11:35:35,794 INFO [train.py:812] (0/8) Epoch 27, batch 1750, loss[loss=0.1644, simple_loss=0.2613, pruned_loss=0.03381, over 7179.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2469, pruned_loss=0.03228, over 1431037.02 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:36:34,354 INFO [train.py:812] (0/8) Epoch 27, batch 1800, loss[loss=0.1399, simple_loss=0.2347, pruned_loss=0.02258, over 7118.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.03248, over 1428957.91 frames.], batch size: 21, lr: 2.89e-04
+2022-05-15 11:37:32,441 INFO [train.py:812] (0/8) Epoch 27, batch 1850, loss[loss=0.2008, simple_loss=0.2815, pruned_loss=0.06007, over 4831.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03206, over 1428443.49 frames.], batch size: 52, lr: 2.89e-04
+2022-05-15 11:38:30,733 INFO [train.py:812] (0/8) Epoch 27, batch 1900, loss[loss=0.1427, simple_loss=0.2355, pruned_loss=0.02493, over 7361.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2458, pruned_loss=0.03165, over 1427443.16 frames.], batch size: 19, lr: 2.89e-04
+2022-05-15 11:39:30,041 INFO [train.py:812] (0/8) Epoch 27, batch 1950, loss[loss=0.1561, simple_loss=0.2447, pruned_loss=0.0338, over 6435.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2459, pruned_loss=0.03163, over 1424328.00 frames.], batch size: 38, lr: 2.89e-04
+2022-05-15 11:40:29,351 INFO [train.py:812] (0/8) Epoch 27, batch 2000, loss[loss=0.1513, simple_loss=0.2579, pruned_loss=0.02232, over 6816.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2452, pruned_loss=0.03167, over 1423709.74 frames.], batch size: 31, lr: 2.89e-04
+2022-05-15 11:41:28,622 INFO [train.py:812] (0/8) Epoch 27, batch 2050, loss[loss=0.1625, simple_loss=0.2472, pruned_loss=0.03884, over 7207.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2464, pruned_loss=0.03199, over 1427149.97 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:42:27,676 INFO [train.py:812] (0/8) Epoch 27, batch 2100, loss[loss=0.1752, simple_loss=0.2604, pruned_loss=0.04502, over 7217.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2461, pruned_loss=0.03208, over 1424475.37 frames.], batch size: 22, lr: 2.89e-04
+2022-05-15 11:43:25,349 INFO [train.py:812] (0/8) Epoch 27, batch 2150, loss[loss=0.1878, simple_loss=0.2766, pruned_loss=0.04948, over 7278.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2473, pruned_loss=0.03242, over 1427725.49 frames.], batch size: 25, lr: 2.89e-04
+2022-05-15 11:44:23,702 INFO [train.py:812] (0/8) Epoch 27, batch 2200, loss[loss=0.1487, simple_loss=0.2444, pruned_loss=0.0265, over 7249.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2467, pruned_loss=0.03223, over 1426389.88 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:45:23,009 INFO [train.py:812] (0/8) Epoch 27, batch 2250, loss[loss=0.1542, simple_loss=0.2357, pruned_loss=0.03635, over 7001.00 frames.], tot_loss[loss=0.1558, simple_loss=0.247, pruned_loss=0.03227, over 1431381.31 frames.], batch size: 16, lr: 2.88e-04
+2022-05-15 11:46:21,525 INFO [train.py:812] (0/8) Epoch 27, batch 2300, loss[loss=0.1162, simple_loss=0.2063, pruned_loss=0.01301, over 7131.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2468, pruned_loss=0.03203, over 1432814.98 frames.], batch size: 17, lr: 2.88e-04
+2022-05-15 11:47:19,550 INFO [train.py:812] (0/8) Epoch 27, batch 2350, loss[loss=0.1602, simple_loss=0.272, pruned_loss=0.0242, over 7144.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2476, pruned_loss=0.03207, over 1431210.68 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:48:16,532 INFO [train.py:812] (0/8) Epoch 27, batch 2400, loss[loss=0.1425, simple_loss=0.2393, pruned_loss=0.02285, over 7278.00 frames.], tot_loss[loss=0.1562, simple_loss=0.248, pruned_loss=0.03219, over 1433016.37 frames.], batch size: 24, lr: 2.88e-04
+2022-05-15 11:49:16,162 INFO [train.py:812] (0/8) Epoch 27, batch 2450, loss[loss=0.155, simple_loss=0.2469, pruned_loss=0.0316, over 7226.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2472, pruned_loss=0.03164, over 1436019.32 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:50:15,238 INFO [train.py:812] (0/8) Epoch 27, batch 2500, loss[loss=0.156, simple_loss=0.2535, pruned_loss=0.02923, over 7222.00 frames.], tot_loss[loss=0.1554, simple_loss=0.247, pruned_loss=0.03192, over 1437407.35 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 11:51:13,613 INFO [train.py:812] (0/8) Epoch 27, batch 2550, loss[loss=0.1551, simple_loss=0.2504, pruned_loss=0.02986, over 6700.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2464, pruned_loss=0.03161, over 1434672.14 frames.], batch size: 31, lr: 2.88e-04
+2022-05-15 11:52:12,746 INFO [train.py:812] (0/8) Epoch 27, batch 2600, loss[loss=0.1409, simple_loss=0.2296, pruned_loss=0.02609, over 7213.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03168, over 1434950.06 frames.], batch size: 16, lr: 2.88e-04
+2022-05-15 11:53:12,232 INFO [train.py:812] (0/8) Epoch 27, batch 2650, loss[loss=0.1548, simple_loss=0.2606, pruned_loss=0.02448, over 7278.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2461, pruned_loss=0.03121, over 1430733.56 frames.], batch size: 24, lr: 2.88e-04
+2022-05-15 11:54:11,598 INFO [train.py:812] (0/8) Epoch 27, batch 2700, loss[loss=0.1545, simple_loss=0.2505, pruned_loss=0.02931, over 7332.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2462, pruned_loss=0.03134, over 1428807.15 frames.], batch size: 22, lr: 2.88e-04
+2022-05-15 11:55:10,416 INFO [train.py:812] (0/8) Epoch 27, batch 2750, loss[loss=0.1584, simple_loss=0.2469, pruned_loss=0.03495, over 7154.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2457, pruned_loss=0.03122, over 1428094.33 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:56:08,650 INFO [train.py:812] (0/8) Epoch 27, batch 2800, loss[loss=0.1732, simple_loss=0.2626, pruned_loss=0.04191, over 7308.00 frames.], tot_loss[loss=0.1542, simple_loss=0.246, pruned_loss=0.03117, over 1426657.52 frames.], batch size: 25, lr: 2.88e-04
+2022-05-15 11:57:08,081 INFO [train.py:812] (0/8) Epoch 27, batch 2850, loss[loss=0.1357, simple_loss=0.2215, pruned_loss=0.02492, over 7259.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2471, pruned_loss=0.03179, over 1425863.83 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:58:06,916 INFO [train.py:812] (0/8) Epoch 27, batch 2900, loss[loss=0.1431, simple_loss=0.2365, pruned_loss=0.0248, over 7173.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03179, over 1425318.31 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:59:06,479 INFO [train.py:812] (0/8) Epoch 27, batch 2950, loss[loss=0.1559, simple_loss=0.2594, pruned_loss=0.02619, over 7120.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2469, pruned_loss=0.03195, over 1420125.37 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 12:00:05,425 INFO [train.py:812] (0/8) Epoch 27, batch 3000, loss[loss=0.1593, simple_loss=0.2526, pruned_loss=0.03302, over 7411.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2469, pruned_loss=0.03205, over 1419564.25 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 12:00:05,427 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 12:00:12,944 INFO [train.py:841] (0/8) Epoch 27, validation: loss=0.1528, simple_loss=0.25, pruned_loss=0.02785, over 698248.00 frames.
+2022-05-15 12:01:11,828 INFO [train.py:812] (0/8) Epoch 27, batch 3050, loss[loss=0.1669, simple_loss=0.2775, pruned_loss=0.02817, over 7118.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2469, pruned_loss=0.03271, over 1410144.66 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:02:10,769 INFO [train.py:812] (0/8) Epoch 27, batch 3100, loss[loss=0.1545, simple_loss=0.2486, pruned_loss=0.03019, over 7322.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2473, pruned_loss=0.03275, over 1416536.87 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:03:20,244 INFO [train.py:812] (0/8) Epoch 27, batch 3150, loss[loss=0.1549, simple_loss=0.2455, pruned_loss=0.03218, over 7212.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03293, over 1417205.14 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:04:19,259 INFO [train.py:812] (0/8) Epoch 27, batch 3200, loss[loss=0.1502, simple_loss=0.2535, pruned_loss=0.0235, over 7209.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2484, pruned_loss=0.0333, over 1419361.58 frames.], batch size: 23, lr: 2.87e-04
+2022-05-15 12:05:18,853 INFO [train.py:812] (0/8) Epoch 27, batch 3250, loss[loss=0.188, simple_loss=0.2786, pruned_loss=0.04875, over 6574.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2484, pruned_loss=0.0335, over 1419864.38 frames.], batch size: 38, lr: 2.87e-04
+2022-05-15 12:06:17,718 INFO [train.py:812] (0/8) Epoch 27, batch 3300, loss[loss=0.1492, simple_loss=0.2432, pruned_loss=0.02755, over 6823.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2486, pruned_loss=0.03357, over 1418973.11 frames.], batch size: 31, lr: 2.87e-04
+2022-05-15 12:07:17,052 INFO [train.py:812] (0/8) Epoch 27, batch 3350, loss[loss=0.1416, simple_loss=0.2436, pruned_loss=0.01981, over 7325.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2492, pruned_loss=0.03328, over 1419321.29 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:08:16,173 INFO [train.py:812] (0/8) Epoch 27, batch 3400, loss[loss=0.1495, simple_loss=0.2418, pruned_loss=0.02858, over 7153.00 frames.], tot_loss[loss=0.158, simple_loss=0.2493, pruned_loss=0.03334, over 1416887.74 frames.], batch size: 20, lr: 2.87e-04
+2022-05-15 12:09:14,983 INFO [train.py:812] (0/8) Epoch 27, batch 3450, loss[loss=0.1674, simple_loss=0.2691, pruned_loss=0.03287, over 7338.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2491, pruned_loss=0.03302, over 1420481.24 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:10:13,333 INFO [train.py:812] (0/8) Epoch 27, batch 3500, loss[loss=0.1489, simple_loss=0.2249, pruned_loss=0.03645, over 7235.00 frames.], tot_loss[loss=0.157, simple_loss=0.2483, pruned_loss=0.0329, over 1423286.83 frames.], batch size: 16, lr: 2.87e-04
+2022-05-15 12:11:13,076 INFO [train.py:812] (0/8) Epoch 27, batch 3550, loss[loss=0.167, simple_loss=0.2483, pruned_loss=0.04291, over 4904.00 frames.], tot_loss[loss=0.1558, simple_loss=0.247, pruned_loss=0.03229, over 1415944.26 frames.], batch size: 52, lr: 2.87e-04
+2022-05-15 12:12:10,935 INFO [train.py:812] (0/8) Epoch 27, batch 3600, loss[loss=0.1483, simple_loss=0.2537, pruned_loss=0.02148, over 7169.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03224, over 1413435.39 frames.], batch size: 19, lr: 2.87e-04
+2022-05-15 12:13:10,315 INFO [train.py:812] (0/8) Epoch 27, batch 3650, loss[loss=0.1313, simple_loss=0.2143, pruned_loss=0.02414, over 7063.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.03218, over 1413149.09 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:14:09,326 INFO [train.py:812] (0/8) Epoch 27, batch 3700, loss[loss=0.1381, simple_loss=0.2191, pruned_loss=0.0286, over 7271.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2473, pruned_loss=0.03212, over 1412269.27 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:15:08,324 INFO [train.py:812] (0/8) Epoch 27, batch 3750, loss[loss=0.1644, simple_loss=0.258, pruned_loss=0.03539, over 7227.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2466, pruned_loss=0.03231, over 1416728.47 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:16:08,058 INFO [train.py:812] (0/8) Epoch 27, batch 3800, loss[loss=0.1382, simple_loss=0.2309, pruned_loss=0.02274, over 7343.00 frames.], tot_loss[loss=0.154, simple_loss=0.2448, pruned_loss=0.03164, over 1420642.06 frames.], batch size: 20, lr: 2.87e-04
+2022-05-15 12:17:07,773 INFO [train.py:812] (0/8) Epoch 27, batch 3850, loss[loss=0.1142, simple_loss=0.197, pruned_loss=0.01576, over 7414.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2459, pruned_loss=0.03193, over 1414351.31 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:18:06,249 INFO [train.py:812] (0/8) Epoch 27, batch 3900, loss[loss=0.1597, simple_loss=0.2447, pruned_loss=0.03736, over 7004.00 frames.], tot_loss[loss=0.155, simple_loss=0.2463, pruned_loss=0.03183, over 1415551.25 frames.], batch size: 28, lr: 2.86e-04
+2022-05-15 12:19:04,966 INFO [train.py:812] (0/8) Epoch 27, batch 3950, loss[loss=0.1453, simple_loss=0.2376, pruned_loss=0.02646, over 7364.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2469, pruned_loss=0.03194, over 1419890.48 frames.], batch size: 19, lr: 2.86e-04
+2022-05-15 12:20:04,219 INFO [train.py:812] (0/8) Epoch 27, batch 4000, loss[loss=0.1692, simple_loss=0.2627, pruned_loss=0.03787, over 7150.00 frames.], tot_loss[loss=0.1547, simple_loss=0.246, pruned_loss=0.03171, over 1425307.57 frames.], batch size: 28, lr: 2.86e-04
+2022-05-15 12:21:04,109 INFO [train.py:812] (0/8) Epoch 27, batch 4050, loss[loss=0.1574, simple_loss=0.247, pruned_loss=0.03389, over 7323.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2464, pruned_loss=0.03219, over 1426139.68 frames.], batch size: 20, lr: 2.86e-04
+2022-05-15 12:22:03,546 INFO [train.py:812] (0/8) Epoch 27, batch 4100, loss[loss=0.1443, simple_loss=0.2317, pruned_loss=0.02843, over 7327.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2461, pruned_loss=0.03207, over 1424109.87 frames.], batch size: 20, lr: 2.86e-04
+2022-05-15 12:23:02,363 INFO [train.py:812] (0/8) Epoch 27, batch 4150, loss[loss=0.1505, simple_loss=0.2581, pruned_loss=0.02145, over 7112.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2468, pruned_loss=0.03218, over 1421337.44 frames.], batch size: 21, lr: 2.86e-04
+2022-05-15 12:23:59,503 INFO [train.py:812] (0/8) Epoch 27, batch 4200, loss[loss=0.1675, simple_loss=0.258, pruned_loss=0.03853, over 7339.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03199, over 1422825.45 frames.], batch size: 22, lr: 2.86e-04
+2022-05-15 12:24:57,511 INFO [train.py:812] (0/8) Epoch 27, batch 4250, loss[loss=0.1547, simple_loss=0.2468, pruned_loss=0.03137, over 7411.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2474, pruned_loss=0.03203, over 1415701.32 frames.], batch size: 21, lr: 2.86e-04
+2022-05-15 12:25:55,492 INFO [train.py:812] (0/8) Epoch 27, batch 4300, loss[loss=0.1684, simple_loss=0.2644, pruned_loss=0.03619, over 6836.00 frames.], tot_loss[loss=0.1563, simple_loss=0.248, pruned_loss=0.03226, over 1413874.06 frames.], batch size: 31, lr: 2.86e-04
+2022-05-15 12:26:54,837 INFO [train.py:812] (0/8) Epoch 27, batch 4350, loss[loss=0.1544, simple_loss=0.2394, pruned_loss=0.03467, over 6982.00 frames.], tot_loss[loss=0.1561, simple_loss=0.248, pruned_loss=0.03213, over 1413916.30 frames.], batch size: 16, lr: 2.86e-04
+2022-05-15 12:27:53,346 INFO [train.py:812] (0/8) Epoch 27, batch 4400, loss[loss=0.15, simple_loss=0.2472, pruned_loss=0.02642, over 6351.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2487, pruned_loss=0.03239, over 1400820.87 frames.], batch size: 37, lr: 2.86e-04
+2022-05-15 12:28:51,267 INFO [train.py:812] (0/8) Epoch 27, batch 4450, loss[loss=0.1646, simple_loss=0.2693, pruned_loss=0.02993, over 7333.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2478, pruned_loss=0.03239, over 1395644.25 frames.], batch size: 22, lr: 2.86e-04
+2022-05-15 12:29:50,411 INFO [train.py:812] (0/8) Epoch 27, batch 4500, loss[loss=0.1808, simple_loss=0.2734, pruned_loss=0.04406, over 7155.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2482, pruned_loss=0.03299, over 1387344.62 frames.], batch size: 18, lr: 2.86e-04
+2022-05-15 12:30:49,358 INFO [train.py:812] (0/8) Epoch 27, batch 4550, loss[loss=0.1881, simple_loss=0.2698, pruned_loss=0.05321, over 4806.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2472, pruned_loss=0.03319, over 1371546.61 frames.], batch size: 52, lr: 2.86e-04
+2022-05-15 12:31:32,904 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-27.pt
+2022-05-15 12:32:00,087 INFO [train.py:812] (0/8) Epoch 28, batch 0, loss[loss=0.1529, simple_loss=0.246, pruned_loss=0.02995, over 7259.00 frames.], tot_loss[loss=0.1529, simple_loss=0.246, pruned_loss=0.02995, over 7259.00 frames.], batch size: 19, lr: 2.81e-04
+2022-05-15 12:32:59,359 INFO [train.py:812] (0/8) Epoch 28, batch 50, loss[loss=0.1556, simple_loss=0.2457, pruned_loss=0.03273, over 7258.00 frames.], tot_loss[loss=0.152, simple_loss=0.2436, pruned_loss=0.03018, over 321373.27 frames.], batch size: 19, lr: 2.81e-04
+2022-05-15 12:33:58,532 INFO [train.py:812] (0/8) Epoch 28, batch 100, loss[loss=0.1657, simple_loss=0.2644, pruned_loss=0.03345, over 7152.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2464, pruned_loss=0.03123, over 565354.89 frames.], batch size: 20, lr: 2.80e-04
+2022-05-15 12:34:26,061 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-124000.pt
+2022-05-15 12:35:03,296 INFO [train.py:812] (0/8) Epoch 28, batch 150, loss[loss=0.1484, simple_loss=0.2488, pruned_loss=0.02396, over 6642.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2468, pruned_loss=0.0312, over 753432.25 frames.], batch size: 38, lr: 2.80e-04
+2022-05-15 12:36:01,539 INFO [train.py:812] (0/8) Epoch 28, batch 200, loss[loss=0.1645, simple_loss=0.2692, pruned_loss=0.02992, over 7182.00 frames.], tot_loss[loss=0.1548, simple_loss=0.247, pruned_loss=0.03135, over 899174.35 frames.], batch size: 23, lr: 2.80e-04
+2022-05-15 12:36:59,614 INFO [train.py:812] (0/8) Epoch 28, batch 250, loss[loss=0.1513, simple_loss=0.2482, pruned_loss=0.02722, over 7293.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2465, pruned_loss=0.03081, over 1015423.68 frames.], batch size: 24, lr: 2.80e-04
+2022-05-15 12:37:58,307 INFO [train.py:812] (0/8) Epoch 28, batch 300, loss[loss=0.1449, simple_loss=0.2409, pruned_loss=0.02449, over 6642.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2465, pruned_loss=0.03087, over 1104764.46 frames.], batch size: 31, lr: 2.80e-04
+2022-05-15 12:38:57,250 INFO [train.py:812] (0/8) Epoch 28, batch 350, loss[loss=0.1371, simple_loss=0.2327, pruned_loss=0.02073, over 7169.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2458, pruned_loss=0.03063, over 1177213.70 frames.], batch size: 19, lr: 2.80e-04
+2022-05-15 12:39:55,228 INFO [train.py:812] (0/8) Epoch 28, batch 400, loss[loss=0.1416, simple_loss=0.2308, pruned_loss=0.02621, over 7127.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2464, pruned_loss=0.03141, over 1233498.47 frames.], batch size: 17, lr: 2.80e-04
+2022-05-15 12:40:54,503 INFO [train.py:812] (0/8) Epoch 28, batch 450, loss[loss=0.171, simple_loss=0.2634, pruned_loss=0.0393, over 7278.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03216, over 1269907.00 frames.], batch size: 25, lr: 2.80e-04
+2022-05-15 12:41:53,065 INFO [train.py:812] (0/8) Epoch 28, batch 500, loss[loss=0.1509, simple_loss=0.2493, pruned_loss=0.02626, over 7311.00 frames.], tot_loss[loss=0.155, simple_loss=0.2467, pruned_loss=0.03161, over 1307564.62 frames.], batch size: 21, lr: 2.80e-04
+2022-05-15 12:42:52,286 INFO [train.py:812] (0/8) Epoch 28, batch 550, loss[loss=0.1382, simple_loss=0.2323, pruned_loss=0.02206, over 7066.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03205, over 1329635.37 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:43:51,390 INFO [train.py:812] (0/8) Epoch 28, batch 600, loss[loss=0.1448, simple_loss=0.23, pruned_loss=0.02978, over 7329.00 frames.], tot_loss[loss=0.155, simple_loss=0.2461, pruned_loss=0.03198, over 1348484.70 frames.], batch size: 20, lr: 2.80e-04
+2022-05-15 12:44:49,242 INFO [train.py:812] (0/8) Epoch 28, batch 650, loss[loss=0.1779, simple_loss=0.2799, pruned_loss=0.03791, over 7088.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2468, pruned_loss=0.0321, over 1366453.52 frames.], batch size: 28, lr: 2.80e-04
+2022-05-15 12:45:47,942 INFO [train.py:812] (0/8) Epoch 28, batch 700, loss[loss=0.1515, simple_loss=0.2399, pruned_loss=0.03155, over 7070.00 frames.], tot_loss[loss=0.155, simple_loss=0.2464, pruned_loss=0.03177, over 1380879.42 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:46:48,081 INFO [train.py:812] (0/8) Epoch 28, batch 750, loss[loss=0.1553, simple_loss=0.2585, pruned_loss=0.02602, over 7218.00 frames.], tot_loss[loss=0.154, simple_loss=0.2453, pruned_loss=0.03135, over 1391983.36 frames.], batch size: 21, lr: 2.80e-04
+2022-05-15 12:47:47,172 INFO [train.py:812] (0/8) Epoch 28, batch 800, loss[loss=0.1819, simple_loss=0.2703, pruned_loss=0.04677, over 7071.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03136, over 1398521.47 frames.], batch size: 28, lr: 2.80e-04
+2022-05-15 12:48:46,801 INFO [train.py:812] (0/8) Epoch 28, batch 850, loss[loss=0.1722, simple_loss=0.2614, pruned_loss=0.04151, over 7326.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2464, pruned_loss=0.03164, over 1406096.75 frames.], batch size: 25, lr: 2.80e-04
+2022-05-15 12:49:45,708 INFO [train.py:812] (0/8) Epoch 28, batch 900, loss[loss=0.1353, simple_loss=0.216, pruned_loss=0.02729, over 6992.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2467, pruned_loss=0.03174, over 1407961.42 frames.], batch size: 16, lr: 2.80e-04
+2022-05-15 12:50:45,000 INFO [train.py:812] (0/8) Epoch 28, batch 950, loss[loss=0.1407, simple_loss=0.2291, pruned_loss=0.02612, over 7168.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2466, pruned_loss=0.03189, over 1410163.49 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:51:43,939 INFO [train.py:812] (0/8) Epoch 28, batch 1000, loss[loss=0.1551, simple_loss=0.244, pruned_loss=0.0331, over 7429.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2468, pruned_loss=0.0322, over 1415552.57 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 12:52:42,470 INFO [train.py:812] (0/8) Epoch 28, batch 1050, loss[loss=0.1636, simple_loss=0.262, pruned_loss=0.03256, over 7408.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2466, pruned_loss=0.03204, over 1415491.09 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 12:53:50,434 INFO [train.py:812] (0/8) Epoch 28, batch 1100, loss[loss=0.1362, simple_loss=0.2213, pruned_loss=0.02558, over 7444.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.03222, over 1416731.28 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 12:54:49,768 INFO [train.py:812] (0/8) Epoch 28, batch 1150, loss[loss=0.1566, simple_loss=0.2579, pruned_loss=0.02767, over 7206.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2459, pruned_loss=0.0319, over 1421502.29 frames.], batch size: 23, lr: 2.79e-04
+2022-05-15 12:55:48,242 INFO [train.py:812] (0/8) Epoch 28, batch 1200, loss[loss=0.153, simple_loss=0.2442, pruned_loss=0.03084, over 7150.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2454, pruned_loss=0.03187, over 1425616.39 frames.], batch size: 17, lr: 2.79e-04
+2022-05-15 12:56:47,568 INFO [train.py:812] (0/8) Epoch 28, batch 1250, loss[loss=0.1492, simple_loss=0.2353, pruned_loss=0.03156, over 7127.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2461, pruned_loss=0.0318, over 1423209.61 frames.], batch size: 17, lr: 2.79e-04
+2022-05-15 12:57:56,276 INFO [train.py:812] (0/8) Epoch 28, batch 1300, loss[loss=0.1421, simple_loss=0.2398, pruned_loss=0.02219, over 7289.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03137, over 1419558.68 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 12:58:55,616 INFO [train.py:812] (0/8) Epoch 28, batch 1350, loss[loss=0.1781, simple_loss=0.2686, pruned_loss=0.04376, over 7344.00 frames.], tot_loss[loss=0.1545, simple_loss=0.246, pruned_loss=0.03153, over 1419150.69 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:00:02,703 INFO [train.py:812] (0/8) Epoch 28, batch 1400, loss[loss=0.1376, simple_loss=0.2246, pruned_loss=0.02529, over 7064.00 frames.], tot_loss[loss=0.1546, simple_loss=0.246, pruned_loss=0.03166, over 1419745.06 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 13:01:30,546 INFO [train.py:812] (0/8) Epoch 28, batch 1450, loss[loss=0.1511, simple_loss=0.2461, pruned_loss=0.02804, over 7324.00 frames.], tot_loss[loss=0.1531, simple_loss=0.244, pruned_loss=0.03113, over 1421909.15 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 13:02:27,767 INFO [train.py:812] (0/8) Epoch 28, batch 1500, loss[loss=0.1512, simple_loss=0.2542, pruned_loss=0.02408, over 7118.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2454, pruned_loss=0.03117, over 1423460.57 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 13:03:25,149 INFO [train.py:812] (0/8) Epoch 28, batch 1550, loss[loss=0.1143, simple_loss=0.191, pruned_loss=0.01884, over 6841.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2457, pruned_loss=0.03145, over 1421039.57 frames.], batch size: 15, lr: 2.79e-04
+2022-05-15 13:04:33,744 INFO [train.py:812] (0/8) Epoch 28, batch 1600, loss[loss=0.1438, simple_loss=0.2413, pruned_loss=0.02315, over 7425.00 frames.], tot_loss[loss=0.1543, simple_loss=0.246, pruned_loss=0.03133, over 1424669.66 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 13:05:32,188 INFO [train.py:812] (0/8) Epoch 28, batch 1650, loss[loss=0.1612, simple_loss=0.2449, pruned_loss=0.03879, over 7072.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2456, pruned_loss=0.03143, over 1425676.57 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 13:06:30,580 INFO [train.py:812] (0/8) Epoch 28, batch 1700, loss[loss=0.1588, simple_loss=0.247, pruned_loss=0.03527, over 7352.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2463, pruned_loss=0.03142, over 1427116.78 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:07:29,477 INFO [train.py:812] (0/8) Epoch 28, batch 1750, loss[loss=0.1448, simple_loss=0.2381, pruned_loss=0.02581, over 6839.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2459, pruned_loss=0.03117, over 1428888.47 frames.], batch size: 31, lr: 2.79e-04
+2022-05-15 13:08:28,871 INFO [train.py:812] (0/8) Epoch 28, batch 1800, loss[loss=0.1617, simple_loss=0.2586, pruned_loss=0.03238, over 7236.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2462, pruned_loss=0.03159, over 1428501.70 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 13:09:27,231 INFO [train.py:812] (0/8) Epoch 28, batch 1850, loss[loss=0.135, simple_loss=0.2317, pruned_loss=0.01908, over 7157.00 frames.], tot_loss[loss=0.1544, simple_loss=0.246, pruned_loss=0.03137, over 1431329.36 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:10:26,379 INFO [train.py:812] (0/8) Epoch 28, batch 1900, loss[loss=0.1687, simple_loss=0.2571, pruned_loss=0.04012, over 7293.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2463, pruned_loss=0.03163, over 1431862.89 frames.], batch size: 17, lr: 2.78e-04
+2022-05-15 13:11:24,502 INFO [train.py:812] (0/8) Epoch 28, batch 1950, loss[loss=0.1453, simple_loss=0.2527, pruned_loss=0.01901, over 6148.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2467, pruned_loss=0.03174, over 1425856.19 frames.], batch size: 37, lr: 2.78e-04
+2022-05-15 13:12:23,338 INFO [train.py:812] (0/8) Epoch 28, batch 2000, loss[loss=0.1566, simple_loss=0.2529, pruned_loss=0.03009, over 7222.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2459, pruned_loss=0.03151, over 1424965.62 frames.], batch size: 21, lr: 2.78e-04
+2022-05-15 13:13:21,534 INFO [train.py:812] (0/8) Epoch 28, batch 2050, loss[loss=0.1881, simple_loss=0.279, pruned_loss=0.04864, over 7195.00 frames.], tot_loss[loss=0.1555, simple_loss=0.247, pruned_loss=0.03198, over 1423330.88 frames.], batch size: 23, lr: 2.78e-04
+2022-05-15 13:14:21,064 INFO [train.py:812] (0/8) Epoch 28, batch 2100, loss[loss=0.1593, simple_loss=0.2571, pruned_loss=0.03072, over 7324.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.0322, over 1423414.97 frames.], batch size: 25, lr: 2.78e-04
+2022-05-15 13:15:20,718 INFO [train.py:812] (0/8) Epoch 28, batch 2150, loss[loss=0.1521, simple_loss=0.2319, pruned_loss=0.03611, over 7137.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2474, pruned_loss=0.03192, over 1422967.04 frames.], batch size: 17, lr: 2.78e-04
+2022-05-15 13:16:19,065 INFO [train.py:812] (0/8) Epoch 28, batch 2200, loss[loss=0.1418, simple_loss=0.2395, pruned_loss=0.02203, over 7314.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2472, pruned_loss=0.03178, over 1421463.04 frames.], batch size: 24, lr: 2.78e-04
+2022-05-15 13:17:18,168 INFO [train.py:812] (0/8) Epoch 28, batch 2250, loss[loss=0.1433, simple_loss=0.2347, pruned_loss=0.02597, over 7319.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2469, pruned_loss=0.03168, over 1424882.29 frames.], batch size: 22, lr: 2.78e-04
+2022-05-15 13:18:16,821 INFO [train.py:812] (0/8) Epoch 28, batch 2300, loss[loss=0.1652, simple_loss=0.2568, pruned_loss=0.03678, over 7148.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2474, pruned_loss=0.03199, over 1421229.82 frames.], batch size: 20, lr: 2.78e-04
+2022-05-15 13:19:16,288 INFO [train.py:812] (0/8) Epoch 28, batch 2350, loss[loss=0.159, simple_loss=0.2445, pruned_loss=0.03669, over 7150.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2468, pruned_loss=0.03183, over 1419352.88 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:20:14,233 INFO [train.py:812] (0/8) Epoch 28, batch 2400, loss[loss=0.1643, simple_loss=0.2513, pruned_loss=0.03858, over 7179.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.03232, over 1422566.51 frames.], batch size: 23, lr: 2.78e-04
+2022-05-15 13:21:14,149 INFO [train.py:812] (0/8) Epoch 28, batch 2450, loss[loss=0.1695, simple_loss=0.2626, pruned_loss=0.03816, over 6558.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2459, pruned_loss=0.03163, over 1424395.90 frames.], batch size: 38, lr: 2.78e-04
+2022-05-15 13:22:13,014 INFO [train.py:812] (0/8) Epoch 28, batch 2500, loss[loss=0.1646, simple_loss=0.2511, pruned_loss=0.03901, over 7221.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2456, pruned_loss=0.0319, over 1421437.54 frames.], batch size: 16, lr: 2.78e-04
+2022-05-15 13:23:12,407 INFO [train.py:812] (0/8) Epoch 28, batch 2550, loss[loss=0.1212, simple_loss=0.2125, pruned_loss=0.01495, over 7259.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2454, pruned_loss=0.03165, over 1422480.01 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:24:10,653 INFO [train.py:812] (0/8) Epoch 28, batch 2600, loss[loss=0.1374, simple_loss=0.2392, pruned_loss=0.01781, over 7231.00 frames.], tot_loss[loss=0.154, simple_loss=0.2453, pruned_loss=0.03133, over 1422205.32 frames.], batch size: 20, lr: 2.78e-04
+2022-05-15 13:25:09,881 INFO [train.py:812] (0/8) Epoch 28, batch 2650, loss[loss=0.1404, simple_loss=0.2313, pruned_loss=0.02475, over 7008.00 frames.], tot_loss[loss=0.1536, simple_loss=0.245, pruned_loss=0.0311, over 1419906.13 frames.], batch size: 16, lr: 2.78e-04
+2022-05-15 13:26:08,935 INFO [train.py:812] (0/8) Epoch 28, batch 2700, loss[loss=0.1645, simple_loss=0.2552, pruned_loss=0.03691, over 7329.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.03091, over 1422495.56 frames.], batch size: 21, lr: 2.78e-04
+2022-05-15 13:27:07,606 INFO [train.py:812] (0/8) Epoch 28, batch 2750, loss[loss=0.1329, simple_loss=0.223, pruned_loss=0.02143, over 7262.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2452, pruned_loss=0.03128, over 1420972.17 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:28:05,904 INFO [train.py:812] (0/8) Epoch 28, batch 2800, loss[loss=0.1578, simple_loss=0.2485, pruned_loss=0.03356, over 7238.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2456, pruned_loss=0.0313, over 1416699.69 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:29:05,088 INFO [train.py:812] (0/8) Epoch 28, batch 2850, loss[loss=0.1425, simple_loss=0.2299, pruned_loss=0.02758, over 7131.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2455, pruned_loss=0.03163, over 1421149.47 frames.], batch size: 17, lr: 2.77e-04
+2022-05-15 13:30:03,010 INFO [train.py:812] (0/8) Epoch 28, batch 2900, loss[loss=0.1547, simple_loss=0.2558, pruned_loss=0.02685, over 7291.00 frames.], tot_loss[loss=0.1548, simple_loss=0.246, pruned_loss=0.03179, over 1420532.64 frames.], batch size: 25, lr: 2.77e-04
+2022-05-15 13:31:01,469 INFO [train.py:812] (0/8) Epoch 28, batch 2950, loss[loss=0.1839, simple_loss=0.2826, pruned_loss=0.04256, over 7208.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2467, pruned_loss=0.03203, over 1423104.43 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:32:00,614 INFO [train.py:812] (0/8) Epoch 28, batch 3000, loss[loss=0.1833, simple_loss=0.2723, pruned_loss=0.04717, over 7058.00 frames.], tot_loss[loss=0.1554, simple_loss=0.247, pruned_loss=0.03194, over 1425127.90 frames.], batch size: 28, lr: 2.77e-04
+2022-05-15 13:32:00,615 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 13:32:08,091 INFO [train.py:841] (0/8) Epoch 28, validation: loss=0.1523, simple_loss=0.2496, pruned_loss=0.02748, over 698248.00 frames.
+2022-05-15 13:33:05,918 INFO [train.py:812] (0/8) Epoch 28, batch 3050, loss[loss=0.1308, simple_loss=0.2229, pruned_loss=0.01932, over 7138.00 frames.], tot_loss[loss=0.155, simple_loss=0.2465, pruned_loss=0.03179, over 1427252.64 frames.], batch size: 17, lr: 2.77e-04
+2022-05-15 13:34:04,038 INFO [train.py:812] (0/8) Epoch 28, batch 3100, loss[loss=0.1679, simple_loss=0.2527, pruned_loss=0.04159, over 7366.00 frames.], tot_loss[loss=0.154, simple_loss=0.2451, pruned_loss=0.03149, over 1426433.51 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:35:03,674 INFO [train.py:812] (0/8) Epoch 28, batch 3150, loss[loss=0.1491, simple_loss=0.2241, pruned_loss=0.03703, over 7386.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2451, pruned_loss=0.0315, over 1423943.12 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:36:02,624 INFO [train.py:812] (0/8) Epoch 28, batch 3200, loss[loss=0.1538, simple_loss=0.2584, pruned_loss=0.02466, over 7330.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2461, pruned_loss=0.03164, over 1424470.83 frames.], batch size: 21, lr: 2.77e-04
+2022-05-15 13:37:02,639 INFO [train.py:812] (0/8) Epoch 28, batch 3250, loss[loss=0.1571, simple_loss=0.2477, pruned_loss=0.0332, over 7173.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2453, pruned_loss=0.03167, over 1424106.56 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:37:59,656 INFO [train.py:812] (0/8) Epoch 28, batch 3300, loss[loss=0.1411, simple_loss=0.2288, pruned_loss=0.02673, over 6997.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2454, pruned_loss=0.03162, over 1423549.93 frames.], batch size: 16, lr: 2.77e-04
+2022-05-15 13:38:57,850 INFO [train.py:812] (0/8) Epoch 28, batch 3350, loss[loss=0.1754, simple_loss=0.2674, pruned_loss=0.04175, over 7375.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2453, pruned_loss=0.03151, over 1420847.08 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:39:56,999 INFO [train.py:812] (0/8) Epoch 28, batch 3400, loss[loss=0.1446, simple_loss=0.2439, pruned_loss=0.02265, over 7329.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2459, pruned_loss=0.03174, over 1422740.58 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:40:56,426 INFO [train.py:812] (0/8) Epoch 28, batch 3450, loss[loss=0.2037, simple_loss=0.2878, pruned_loss=0.05986, over 7203.00 frames.], tot_loss[loss=0.1548, simple_loss=0.246, pruned_loss=0.03176, over 1424213.32 frames.], batch size: 22, lr: 2.77e-04
+2022-05-15 13:41:55,526 INFO [train.py:812] (0/8) Epoch 28, batch 3500, loss[loss=0.145, simple_loss=0.2378, pruned_loss=0.02613, over 7063.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03171, over 1423012.29 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:42:54,663 INFO [train.py:812] (0/8) Epoch 28, batch 3550, loss[loss=0.1535, simple_loss=0.2447, pruned_loss=0.03118, over 7334.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2465, pruned_loss=0.03159, over 1423821.05 frames.], batch size: 22, lr: 2.77e-04
+2022-05-15 13:43:53,715 INFO [train.py:812] (0/8) Epoch 28, batch 3600, loss[loss=0.1764, simple_loss=0.2744, pruned_loss=0.03922, over 7064.00 frames.], tot_loss[loss=0.155, simple_loss=0.2468, pruned_loss=0.03157, over 1423770.74 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:44:53,068 INFO [train.py:812] (0/8) Epoch 28, batch 3650, loss[loss=0.185, simple_loss=0.2707, pruned_loss=0.04964, over 7415.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2453, pruned_loss=0.03099, over 1424464.16 frames.], batch size: 21, lr: 2.77e-04
+2022-05-15 13:45:51,488 INFO [train.py:812] (0/8) Epoch 28, batch 3700, loss[loss=0.1581, simple_loss=0.2526, pruned_loss=0.03187, over 7425.00 frames.], tot_loss[loss=0.1543, simple_loss=0.246, pruned_loss=0.03133, over 1424757.85 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:46:50,217 INFO [train.py:812] (0/8) Epoch 28, batch 3750, loss[loss=0.1818, simple_loss=0.2614, pruned_loss=0.05112, over 5416.00 frames.], tot_loss[loss=0.155, simple_loss=0.2466, pruned_loss=0.03171, over 1420423.41 frames.], batch size: 52, lr: 2.76e-04
+2022-05-15 13:47:49,316 INFO [train.py:812] (0/8) Epoch 28, batch 3800, loss[loss=0.1333, simple_loss=0.2209, pruned_loss=0.02284, over 7287.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2472, pruned_loss=0.03191, over 1422350.67 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:48:48,417 INFO [train.py:812] (0/8) Epoch 28, batch 3850, loss[loss=0.1617, simple_loss=0.2606, pruned_loss=0.03137, over 7153.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2464, pruned_loss=0.03144, over 1426922.22 frames.], batch size: 19, lr: 2.76e-04
+2022-05-15 13:49:47,527 INFO [train.py:812] (0/8) Epoch 28, batch 3900, loss[loss=0.1423, simple_loss=0.2421, pruned_loss=0.02121, over 7205.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2462, pruned_loss=0.03134, over 1425221.33 frames.], batch size: 22, lr: 2.76e-04
+2022-05-15 13:50:47,299 INFO [train.py:812] (0/8) Epoch 28, batch 3950, loss[loss=0.1614, simple_loss=0.25, pruned_loss=0.03642, over 7197.00 frames.], tot_loss[loss=0.1542, simple_loss=0.246, pruned_loss=0.03119, over 1426259.61 frames.], batch size: 22, lr: 2.76e-04
+2022-05-15 13:51:46,238 INFO [train.py:812] (0/8) Epoch 28, batch 4000, loss[loss=0.1607, simple_loss=0.2563, pruned_loss=0.03256, over 6837.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2448, pruned_loss=0.03114, over 1423202.89 frames.], batch size: 31, lr: 2.76e-04
+2022-05-15 13:52:45,783 INFO [train.py:812] (0/8) Epoch 28, batch 4050, loss[loss=0.1862, simple_loss=0.2666, pruned_loss=0.05286, over 4725.00 frames.], tot_loss[loss=0.154, simple_loss=0.2453, pruned_loss=0.03138, over 1416138.37 frames.], batch size: 52, lr: 2.76e-04
+2022-05-15 13:53:44,876 INFO [train.py:812] (0/8) Epoch 28, batch 4100, loss[loss=0.1367, simple_loss=0.2234, pruned_loss=0.02497, over 7125.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2447, pruned_loss=0.0311, over 1418618.05 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:54:12,682 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-128000.pt
+2022-05-15 13:54:49,276 INFO [train.py:812] (0/8) Epoch 28, batch 4150, loss[loss=0.1337, simple_loss=0.2208, pruned_loss=0.02327, over 7153.00 frames.], tot_loss[loss=0.154, simple_loss=0.2455, pruned_loss=0.03125, over 1423179.88 frames.], batch size: 19, lr: 2.76e-04
+2022-05-15 13:55:47,971 INFO [train.py:812] (0/8) Epoch 28, batch 4200, loss[loss=0.181, simple_loss=0.2683, pruned_loss=0.04691, over 5069.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03171, over 1416777.54 frames.], batch size: 52, lr: 2.76e-04
+2022-05-15 13:56:46,295 INFO [train.py:812] (0/8) Epoch 28, batch 4250, loss[loss=0.1319, simple_loss=0.2255, pruned_loss=0.01915, over 7457.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03186, over 1415218.77 frames.], batch size: 19, lr: 2.76e-04
+2022-05-15 13:57:45,183 INFO [train.py:812] (0/8) Epoch 28, batch 4300, loss[loss=0.147, simple_loss=0.2274, pruned_loss=0.03331, over 7144.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2469, pruned_loss=0.03195, over 1416363.67 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:58:44,139 INFO [train.py:812] (0/8) Epoch 28, batch 4350, loss[loss=0.1639, simple_loss=0.261, pruned_loss=0.03343, over 7219.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2469, pruned_loss=0.0319, over 1416950.56 frames.], batch size: 21, lr: 2.76e-04
+2022-05-15 13:59:42,361 INFO [train.py:812] (0/8) Epoch 28, batch 4400, loss[loss=0.143, simple_loss=0.232, pruned_loss=0.02702, over 6436.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2463, pruned_loss=0.03167, over 1408731.23 frames.], batch size: 38, lr: 2.76e-04
+2022-05-15 14:00:51,455 INFO [train.py:812] (0/8) Epoch 28, batch 4450, loss[loss=0.145, simple_loss=0.2235, pruned_loss=0.03321, over 7174.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2466, pruned_loss=0.03198, over 1402873.92 frames.], batch size: 16, lr: 2.76e-04
+2022-05-15 14:01:50,406 INFO [train.py:812] (0/8) Epoch 28, batch 4500, loss[loss=0.1451, simple_loss=0.2367, pruned_loss=0.02678, over 7232.00 frames.], tot_loss[loss=0.1558, simple_loss=0.247, pruned_loss=0.03225, over 1393355.29 frames.], batch size: 21, lr: 2.76e-04
+2022-05-15 14:02:49,653 INFO [train.py:812] (0/8) Epoch 28, batch 4550, loss[loss=0.1642, simple_loss=0.2562, pruned_loss=0.03609, over 6432.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.03265, over 1361666.34 frames.], batch size: 38, lr: 2.76e-04
+2022-05-15 14:03:34,374 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-28.pt
+2022-05-15 14:04:01,549 INFO [train.py:812] (0/8) Epoch 29, batch 0, loss[loss=0.1521, simple_loss=0.2471, pruned_loss=0.02859, over 7067.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2471, pruned_loss=0.02859, over 7067.00 frames.], batch size: 28, lr: 2.71e-04
+2022-05-15 14:05:00,858 INFO [train.py:812] (0/8) Epoch 29, batch 50, loss[loss=0.169, simple_loss=0.2663, pruned_loss=0.03585, over 7305.00 frames.], tot_loss[loss=0.155, simple_loss=0.2469, pruned_loss=0.03156, over 323244.22 frames.], batch size: 24, lr: 2.71e-04
+2022-05-15 14:05:59,915 INFO [train.py:812] (0/8) Epoch 29, batch 100, loss[loss=0.1479, simple_loss=0.235, pruned_loss=0.03041, over 7318.00 frames.], tot_loss[loss=0.154, simple_loss=0.2456, pruned_loss=0.03118, over 569344.83 frames.], batch size: 21, lr: 2.71e-04
+2022-05-15 14:06:58,563 INFO [train.py:812] (0/8) Epoch 29, batch 150, loss[loss=0.1212, simple_loss=0.2136, pruned_loss=0.01443, over 7232.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2456, pruned_loss=0.03081, over 759957.17 frames.], batch size: 20, lr: 2.71e-04
+2022-05-15 14:07:56,836 INFO [train.py:812] (0/8) Epoch 29, batch 200, loss[loss=0.1375, simple_loss=0.2252, pruned_loss=0.02493, over 7072.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.03053, over 908913.15 frames.], batch size: 18, lr: 2.71e-04
+2022-05-15 14:08:56,089 INFO [train.py:812] (0/8) Epoch 29, batch 250, loss[loss=0.1765, simple_loss=0.2657, pruned_loss=0.04368, over 4932.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2454, pruned_loss=0.03083, over 1019761.54 frames.], batch size: 52, lr: 2.71e-04
+2022-05-15 14:09:54,906 INFO [train.py:812] (0/8) Epoch 29, batch 300, loss[loss=0.1559, simple_loss=0.2457, pruned_loss=0.03304, over 7172.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2455, pruned_loss=0.03086, over 1109253.74 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:10:53,170 INFO [train.py:812] (0/8) Epoch 29, batch 350, loss[loss=0.1496, simple_loss=0.2457, pruned_loss=0.02677, over 7061.00 frames.], tot_loss[loss=0.1538, simple_loss=0.246, pruned_loss=0.03083, over 1180500.82 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:11:51,409 INFO [train.py:812] (0/8) Epoch 29, batch 400, loss[loss=0.1531, simple_loss=0.2507, pruned_loss=0.02773, over 7142.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2462, pruned_loss=0.0311, over 1236136.99 frames.], batch size: 20, lr: 2.70e-04
+2022-05-15 14:12:49,832 INFO [train.py:812] (0/8) Epoch 29, batch 450, loss[loss=0.1496, simple_loss=0.2444, pruned_loss=0.02738, over 7118.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2472, pruned_loss=0.03154, over 1281853.15 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:13:47,313 INFO [train.py:812] (0/8) Epoch 29, batch 500, loss[loss=0.1801, simple_loss=0.2735, pruned_loss=0.04339, over 5196.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2477, pruned_loss=0.03211, over 1308896.85 frames.], batch size: 53, lr: 2.70e-04
+2022-05-15 14:14:46,140 INFO [train.py:812] (0/8) Epoch 29, batch 550, loss[loss=0.1457, simple_loss=0.2507, pruned_loss=0.02039, over 7216.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2479, pruned_loss=0.03197, over 1331472.77 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:15:44,278 INFO [train.py:812] (0/8) Epoch 29, batch 600, loss[loss=0.1533, simple_loss=0.2343, pruned_loss=0.03616, over 7264.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2464, pruned_loss=0.03167, over 1348669.66 frames.], batch size: 19, lr: 2.70e-04
+2022-05-15 14:16:43,653 INFO [train.py:812] (0/8) Epoch 29, batch 650, loss[loss=0.1392, simple_loss=0.2305, pruned_loss=0.02397, over 7070.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2453, pruned_loss=0.03156, over 1367087.21 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:17:43,336 INFO [train.py:812] (0/8) Epoch 29, batch 700, loss[loss=0.2189, simple_loss=0.2892, pruned_loss=0.07432, over 5087.00 frames.], tot_loss[loss=0.155, simple_loss=0.2461, pruned_loss=0.03192, over 1376389.51 frames.], batch size: 52, lr: 2.70e-04
+2022-05-15 14:18:41,551 INFO [train.py:812] (0/8) Epoch 29, batch 750, loss[loss=0.1536, simple_loss=0.2535, pruned_loss=0.02685, over 7434.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2455, pruned_loss=0.03135, over 1383361.67 frames.], batch size: 20, lr: 2.70e-04
+2022-05-15 14:19:40,277 INFO [train.py:812] (0/8) Epoch 29, batch 800, loss[loss=0.1626, simple_loss=0.2599, pruned_loss=0.03262, over 7111.00 frames.], tot_loss[loss=0.1543, simple_loss=0.246, pruned_loss=0.03126, over 1388468.52 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:20:39,290 INFO [train.py:812] (0/8) Epoch 29, batch 850, loss[loss=0.1571, simple_loss=0.242, pruned_loss=0.03613, over 6348.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2464, pruned_loss=0.03129, over 1392738.92 frames.], batch size: 37, lr: 2.70e-04
+2022-05-15 14:21:38,036 INFO [train.py:812] (0/8) Epoch 29, batch 900, loss[loss=0.1672, simple_loss=0.2588, pruned_loss=0.0378, over 6724.00 frames.], tot_loss[loss=0.1543, simple_loss=0.246, pruned_loss=0.03124, over 1399135.91 frames.], batch size: 31, lr: 2.70e-04
+2022-05-15 14:22:37,041 INFO [train.py:812] (0/8) Epoch 29, batch 950, loss[loss=0.1407, simple_loss=0.2417, pruned_loss=0.01986, over 7208.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2458, pruned_loss=0.03144, over 1408107.73 frames.], batch size: 22, lr: 2.70e-04
+2022-05-15 14:23:36,696 INFO [train.py:812] (0/8) Epoch 29, batch 1000, loss[loss=0.1339, simple_loss=0.2125, pruned_loss=0.0277, over 6826.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2443, pruned_loss=0.03075, over 1414494.69 frames.], batch size: 15, lr: 2.70e-04
+2022-05-15 14:24:36,128 INFO [train.py:812] (0/8) Epoch 29, batch 1050, loss[loss=0.153, simple_loss=0.2522, pruned_loss=0.02689, over 7406.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03071, over 1419910.29 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:25:35,345 INFO [train.py:812] (0/8) Epoch 29, batch 1100, loss[loss=0.1521, simple_loss=0.2365, pruned_loss=0.0339, over 7278.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2448, pruned_loss=0.03098, over 1423705.56 frames.], batch size: 17, lr: 2.70e-04
+2022-05-15 14:26:34,875 INFO [train.py:812] (0/8) Epoch 29, batch 1150, loss[loss=0.1569, simple_loss=0.2536, pruned_loss=0.03007, over 7081.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2453, pruned_loss=0.03153, over 1421699.95 frames.], batch size: 28, lr: 2.70e-04
+2022-05-15 14:27:33,674 INFO [train.py:812] (0/8) Epoch 29, batch 1200, loss[loss=0.1541, simple_loss=0.2503, pruned_loss=0.02893, over 7137.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03186, over 1423742.90 frames.], batch size: 28, lr: 2.70e-04
+2022-05-15 14:28:32,479 INFO [train.py:812] (0/8) Epoch 29, batch 1250, loss[loss=0.163, simple_loss=0.253, pruned_loss=0.03648, over 7196.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2465, pruned_loss=0.03192, over 1417842.43 frames.], batch size: 22, lr: 2.70e-04
+2022-05-15 14:29:29,507 INFO [train.py:812] (0/8) Epoch 29, batch 1300, loss[loss=0.1499, simple_loss=0.2513, pruned_loss=0.02428, over 7162.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2461, pruned_loss=0.03137, over 1421072.48 frames.], batch size: 20, lr: 2.69e-04
+2022-05-15 14:30:28,487 INFO [train.py:812] (0/8) Epoch 29, batch 1350, loss[loss=0.1546, simple_loss=0.2458, pruned_loss=0.03168, over 7108.00 frames.], tot_loss[loss=0.154, simple_loss=0.2459, pruned_loss=0.03111, over 1425986.71 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:31:27,429 INFO [train.py:812] (0/8) Epoch 29, batch 1400, loss[loss=0.145, simple_loss=0.2253, pruned_loss=0.03241, over 7275.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2454, pruned_loss=0.03094, over 1427557.81 frames.], batch size: 17, lr: 2.69e-04
+2022-05-15 14:32:26,335 INFO [train.py:812] (0/8) Epoch 29, batch 1450, loss[loss=0.1605, simple_loss=0.2528, pruned_loss=0.03406, over 7308.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.03078, over 1431387.14 frames.], batch size: 24, lr: 2.69e-04
+2022-05-15 14:33:24,393 INFO [train.py:812] (0/8) Epoch 29, batch 1500, loss[loss=0.1476, simple_loss=0.2371, pruned_loss=0.02902, over 7339.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2449, pruned_loss=0.03078, over 1428140.62 frames.], batch size: 20, lr: 2.69e-04
+2022-05-15 14:34:23,841 INFO [train.py:812] (0/8) Epoch 29, batch 1550, loss[loss=0.1485, simple_loss=0.2391, pruned_loss=0.02898, over 7211.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2451, pruned_loss=0.03089, over 1429670.58 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:35:22,637 INFO [train.py:812] (0/8) Epoch 29, batch 1600, loss[loss=0.1391, simple_loss=0.2258, pruned_loss=0.02624, over 6806.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2459, pruned_loss=0.03093, over 1426265.24 frames.], batch size: 15, lr: 2.69e-04
+2022-05-15 14:36:22,722 INFO [train.py:812] (0/8) Epoch 29, batch 1650, loss[loss=0.1424, simple_loss=0.2243, pruned_loss=0.03024, over 7227.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2452, pruned_loss=0.03101, over 1428027.61 frames.], batch size: 16, lr: 2.69e-04
+2022-05-15 14:37:22,109 INFO [train.py:812] (0/8) Epoch 29, batch 1700, loss[loss=0.1636, simple_loss=0.2455, pruned_loss=0.04081, over 7251.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2451, pruned_loss=0.03119, over 1430623.81 frames.], batch size: 19, lr: 2.69e-04
+2022-05-15 14:38:21,796 INFO [train.py:812] (0/8) Epoch 29, batch 1750, loss[loss=0.1251, simple_loss=0.225, pruned_loss=0.01264, over 7115.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2447, pruned_loss=0.0311, over 1432646.91 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:39:20,833 INFO [train.py:812] (0/8) Epoch 29, batch 1800, loss[loss=0.1569, simple_loss=0.2464, pruned_loss=0.03373, over 6991.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2446, pruned_loss=0.03104, over 1422818.55 frames.], batch size: 16, lr: 2.69e-04
+2022-05-15 14:40:20,271 INFO [train.py:812] (0/8) Epoch 29, batch 1850, loss[loss=0.1369, simple_loss=0.2118, pruned_loss=0.03102, over 7403.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2456, pruned_loss=0.03153, over 1425606.67 frames.], batch size: 18, lr: 2.69e-04
+2022-05-15 14:41:18,728 INFO [train.py:812] (0/8) Epoch 29, batch 1900, loss[loss=0.165, simple_loss=0.2561, pruned_loss=0.03692, over 7152.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2453, pruned_loss=0.03146, over 1425904.17 frames.], batch size: 26, lr: 2.69e-04
+2022-05-15 14:42:17,746 INFO [train.py:812] (0/8) Epoch 29, batch 1950, loss[loss=0.159, simple_loss=0.254, pruned_loss=0.03196, over 7296.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2455, pruned_loss=0.03155, over 1428058.24 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:43:16,654 INFO [train.py:812] (0/8) Epoch 29, batch 2000, loss[loss=0.182, simple_loss=0.2806, pruned_loss=0.04173, over 7207.00 frames.], tot_loss[loss=0.1538, simple_loss=0.245, pruned_loss=0.03127, over 1431044.98 frames.], batch size: 23, lr: 2.69e-04
+2022-05-15 14:44:14,143 INFO [train.py:812] (0/8) Epoch 29, batch 2050, loss[loss=0.1823, simple_loss=0.2744, pruned_loss=0.04512, over 7314.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2458, pruned_loss=0.0318, over 1424160.77 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:45:11,934 INFO [train.py:812] (0/8) Epoch 29, batch 2100, loss[loss=0.1911, simple_loss=0.274, pruned_loss=0.05412, over 7329.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2452, pruned_loss=0.03185, over 1426207.82 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:46:11,764 INFO [train.py:812] (0/8) Epoch 29, batch 2150, loss[loss=0.153, simple_loss=0.2497, pruned_loss=0.02816, over 7212.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2449, pruned_loss=0.03118, over 1427697.11 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:47:09,932 INFO [train.py:812] (0/8) Epoch 29, batch 2200, loss[loss=0.174, simple_loss=0.2692, pruned_loss=0.03943, over 7301.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2448, pruned_loss=0.03128, over 1423043.00 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:48:08,382 INFO [train.py:812] (0/8) Epoch 29, batch 2250, loss[loss=0.1427, simple_loss=0.2368, pruned_loss=0.02435, over 7115.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03082, over 1426622.85 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:49:05,834 INFO [train.py:812] (0/8) Epoch 29, batch 2300, loss[loss=0.1799, simple_loss=0.2765, pruned_loss=0.04162, over 7305.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.03102, over 1427552.70 frames.], batch size: 24, lr: 2.68e-04
+2022-05-15 14:50:03,879 INFO [train.py:812] (0/8) Epoch 29, batch 2350, loss[loss=0.1476, simple_loss=0.2352, pruned_loss=0.03002, over 7076.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2458, pruned_loss=0.03128, over 1424690.32 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:51:02,206 INFO [train.py:812] (0/8) Epoch 29, batch 2400, loss[loss=0.1513, simple_loss=0.2396, pruned_loss=0.03146, over 7351.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03117, over 1425906.36 frames.], batch size: 19, lr: 2.68e-04
+2022-05-15 14:51:59,578 INFO [train.py:812] (0/8) Epoch 29, batch 2450, loss[loss=0.1286, simple_loss=0.2265, pruned_loss=0.01533, over 7122.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2462, pruned_loss=0.03179, over 1416315.57 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:52:57,608 INFO [train.py:812] (0/8) Epoch 29, batch 2500, loss[loss=0.1246, simple_loss=0.2008, pruned_loss=0.0242, over 7417.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2449, pruned_loss=0.03109, over 1419925.33 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:53:56,700 INFO [train.py:812] (0/8) Epoch 29, batch 2550, loss[loss=0.1438, simple_loss=0.2284, pruned_loss=0.02964, over 7167.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2447, pruned_loss=0.03088, over 1417484.59 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:54:55,311 INFO [train.py:812] (0/8) Epoch 29, batch 2600, loss[loss=0.1647, simple_loss=0.2589, pruned_loss=0.03526, over 7214.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2446, pruned_loss=0.03093, over 1416975.34 frames.], batch size: 23, lr: 2.68e-04
+2022-05-15 14:56:04,287 INFO [train.py:812] (0/8) Epoch 29, batch 2650, loss[loss=0.1388, simple_loss=0.2312, pruned_loss=0.02319, over 7416.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03076, over 1420256.20 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:57:02,549 INFO [train.py:812] (0/8) Epoch 29, batch 2700, loss[loss=0.1733, simple_loss=0.2543, pruned_loss=0.04613, over 5295.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2437, pruned_loss=0.03061, over 1420761.00 frames.], batch size: 52, lr: 2.68e-04
+2022-05-15 14:58:00,094 INFO [train.py:812] (0/8) Epoch 29, batch 2750, loss[loss=0.1579, simple_loss=0.2501, pruned_loss=0.03289, over 7323.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2447, pruned_loss=0.03097, over 1416763.16 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:59:08,037 INFO [train.py:812] (0/8) Epoch 29, batch 2800, loss[loss=0.1519, simple_loss=0.2458, pruned_loss=0.02898, over 7345.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.03108, over 1419775.42 frames.], batch size: 22, lr: 2.68e-04
+2022-05-15 15:00:06,416 INFO [train.py:812] (0/8) Epoch 29, batch 2850, loss[loss=0.1541, simple_loss=0.2495, pruned_loss=0.02941, over 7268.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2454, pruned_loss=0.03141, over 1420008.23 frames.], batch size: 19, lr: 2.68e-04
+2022-05-15 15:01:14,248 INFO [train.py:812] (0/8) Epoch 29, batch 2900, loss[loss=0.135, simple_loss=0.2219, pruned_loss=0.02407, over 7273.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2449, pruned_loss=0.03105, over 1418522.43 frames.], batch size: 17, lr: 2.68e-04
+2022-05-15 15:02:42,659 INFO [train.py:812] (0/8) Epoch 29, batch 2950, loss[loss=0.1258, simple_loss=0.2164, pruned_loss=0.01764, over 7148.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2436, pruned_loss=0.03108, over 1418123.09 frames.], batch size: 17, lr: 2.68e-04
+2022-05-15 15:03:40,402 INFO [train.py:812] (0/8) Epoch 29, batch 3000, loss[loss=0.1534, simple_loss=0.2553, pruned_loss=0.02573, over 7236.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2448, pruned_loss=0.03122, over 1418517.49 frames.], batch size: 20, lr: 2.68e-04
+2022-05-15 15:03:40,404 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 15:03:47,851 INFO [train.py:841] (0/8) Epoch 29, validation: loss=0.153, simple_loss=0.2498, pruned_loss=0.02809, over 698248.00 frames.
+2022-05-15 15:04:46,860 INFO [train.py:812] (0/8) Epoch 29, batch 3050, loss[loss=0.1369, simple_loss=0.2213, pruned_loss=0.02623, over 7164.00 frames.], tot_loss[loss=0.153, simple_loss=0.2441, pruned_loss=0.03093, over 1421912.56 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 15:05:54,524 INFO [train.py:812] (0/8) Epoch 29, batch 3100, loss[loss=0.1554, simple_loss=0.2397, pruned_loss=0.0355, over 7268.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2437, pruned_loss=0.03108, over 1418595.50 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 15:06:53,591 INFO [train.py:812] (0/8) Epoch 29, batch 3150, loss[loss=0.1745, simple_loss=0.2705, pruned_loss=0.03925, over 7212.00 frames.], tot_loss[loss=0.154, simple_loss=0.2451, pruned_loss=0.03143, over 1422340.68 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 15:07:52,386 INFO [train.py:812] (0/8) Epoch 29, batch 3200, loss[loss=0.1436, simple_loss=0.2452, pruned_loss=0.02098, over 7128.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2452, pruned_loss=0.03115, over 1422266.79 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 15:08:52,058 INFO [train.py:812] (0/8) Epoch 29, batch 3250, loss[loss=0.1317, simple_loss=0.2126, pruned_loss=0.02542, over 6804.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2446, pruned_loss=0.03095, over 1421560.68 frames.], batch size: 15, lr: 2.67e-04
+2022-05-15 15:09:50,368 INFO [train.py:812] (0/8) Epoch 29, batch 3300, loss[loss=0.1686, simple_loss=0.2592, pruned_loss=0.03895, over 7231.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2461, pruned_loss=0.03161, over 1421634.05 frames.], batch size: 21, lr: 2.67e-04
+2022-05-15 15:10:48,412 INFO [train.py:812] (0/8) Epoch 29, batch 3350, loss[loss=0.1538, simple_loss=0.2424, pruned_loss=0.03256, over 7070.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2458, pruned_loss=0.03175, over 1418959.42 frames.], batch size: 28, lr: 2.67e-04
+2022-05-15 15:11:47,203 INFO [train.py:812] (0/8) Epoch 29, batch 3400, loss[loss=0.1376, simple_loss=0.2295, pruned_loss=0.02286, over 7066.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2454, pruned_loss=0.03159, over 1418048.30 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:12:46,908 INFO [train.py:812] (0/8) Epoch 29, batch 3450, loss[loss=0.1386, simple_loss=0.2218, pruned_loss=0.02766, over 7272.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2451, pruned_loss=0.03158, over 1420091.76 frames.], batch size: 17, lr: 2.67e-04
+2022-05-15 15:13:45,916 INFO [train.py:812] (0/8) Epoch 29, batch 3500, loss[loss=0.1444, simple_loss=0.2464, pruned_loss=0.02123, over 6976.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2456, pruned_loss=0.0316, over 1420046.99 frames.], batch size: 32, lr: 2.67e-04
+2022-05-15 15:14:27,525 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-132000.pt
+2022-05-15 15:14:51,778 INFO [train.py:812] (0/8) Epoch 29, batch 3550, loss[loss=0.1354, simple_loss=0.2235, pruned_loss=0.02368, over 7262.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2456, pruned_loss=0.03154, over 1423268.24 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:15:51,038 INFO [train.py:812] (0/8) Epoch 29, batch 3600, loss[loss=0.1487, simple_loss=0.2293, pruned_loss=0.03406, over 7205.00 frames.], tot_loss[loss=0.1546, simple_loss=0.246, pruned_loss=0.03164, over 1423819.07 frames.], batch size: 16, lr: 2.67e-04
+2022-05-15 15:16:50,739 INFO [train.py:812] (0/8) Epoch 29, batch 3650, loss[loss=0.1447, simple_loss=0.2494, pruned_loss=0.02004, over 7344.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2453, pruned_loss=0.03125, over 1426914.23 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:17:49,902 INFO [train.py:812] (0/8) Epoch 29, batch 3700, loss[loss=0.1847, simple_loss=0.2721, pruned_loss=0.04865, over 7202.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03121, over 1426533.57 frames.], batch size: 23, lr: 2.67e-04
+2022-05-15 15:18:49,104 INFO [train.py:812] (0/8) Epoch 29, batch 3750, loss[loss=0.2082, simple_loss=0.2913, pruned_loss=0.06259, over 5120.00 frames.], tot_loss[loss=0.154, simple_loss=0.245, pruned_loss=0.03151, over 1426101.74 frames.], batch size: 52, lr: 2.67e-04
+2022-05-15 15:19:48,135 INFO [train.py:812] (0/8) Epoch 29, batch 3800, loss[loss=0.13, simple_loss=0.2266, pruned_loss=0.01668, over 7428.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.03158, over 1426097.49 frames.], batch size: 20, lr: 2.67e-04
+2022-05-15 15:20:46,937 INFO [train.py:812] (0/8) Epoch 29, batch 3850, loss[loss=0.1443, simple_loss=0.2355, pruned_loss=0.02654, over 7384.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2462, pruned_loss=0.03161, over 1426646.51 frames.], batch size: 23, lr: 2.67e-04
+2022-05-15 15:21:44,962 INFO [train.py:812] (0/8) Epoch 29, batch 3900, loss[loss=0.1622, simple_loss=0.2552, pruned_loss=0.03459, over 7268.00 frames.], tot_loss[loss=0.1544, simple_loss=0.246, pruned_loss=0.03142, over 1429235.92 frames.], batch size: 24, lr: 2.67e-04
+2022-05-15 15:22:44,169 INFO [train.py:812] (0/8) Epoch 29, batch 3950, loss[loss=0.1309, simple_loss=0.2186, pruned_loss=0.02166, over 7412.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2467, pruned_loss=0.03127, over 1430478.13 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:23:43,074 INFO [train.py:812] (0/8) Epoch 29, batch 4000, loss[loss=0.1527, simple_loss=0.2425, pruned_loss=0.03141, over 7317.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2466, pruned_loss=0.03133, over 1430277.53 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:24:42,298 INFO [train.py:812] (0/8) Epoch 29, batch 4050, loss[loss=0.1376, simple_loss=0.2151, pruned_loss=0.03008, over 7273.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2464, pruned_loss=0.03131, over 1429425.63 frames.], batch size: 17, lr: 2.67e-04
+2022-05-15 15:25:40,974 INFO [train.py:812] (0/8) Epoch 29, batch 4100, loss[loss=0.1639, simple_loss=0.2629, pruned_loss=0.03242, over 7322.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2463, pruned_loss=0.03109, over 1430776.47 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:26:40,462 INFO [train.py:812] (0/8) Epoch 29, batch 4150, loss[loss=0.1478, simple_loss=0.2458, pruned_loss=0.02495, over 7321.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2457, pruned_loss=0.03102, over 1423898.95 frames.], batch size: 21, lr: 2.67e-04
+2022-05-15 15:27:39,244 INFO [train.py:812] (0/8) Epoch 29, batch 4200, loss[loss=0.1515, simple_loss=0.2444, pruned_loss=0.02923, over 7261.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2465, pruned_loss=0.03121, over 1420784.63 frames.], batch size: 19, lr: 2.66e-04
+2022-05-15 15:28:38,734 INFO [train.py:812] (0/8) Epoch 29, batch 4250, loss[loss=0.1647, simple_loss=0.2646, pruned_loss=0.03242, over 6712.00 frames.], tot_loss[loss=0.1539, simple_loss=0.246, pruned_loss=0.03093, over 1421499.08 frames.], batch size: 31, lr: 2.66e-04
+2022-05-15 15:29:36,726 INFO [train.py:812] (0/8) Epoch 29, batch 4300, loss[loss=0.1496, simple_loss=0.2326, pruned_loss=0.03332, over 7168.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2455, pruned_loss=0.03076, over 1416845.75 frames.], batch size: 18, lr: 2.66e-04
+2022-05-15 15:30:35,685 INFO [train.py:812] (0/8) Epoch 29, batch 4350, loss[loss=0.1494, simple_loss=0.2576, pruned_loss=0.02066, over 7324.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2443, pruned_loss=0.02991, over 1417591.57 frames.], batch size: 21, lr: 2.66e-04
+2022-05-15 15:31:34,530 INFO [train.py:812] (0/8) Epoch 29, batch 4400, loss[loss=0.1903, simple_loss=0.2897, pruned_loss=0.04543, over 7274.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2451, pruned_loss=0.03016, over 1409569.11 frames.], batch size: 24, lr: 2.66e-04
+2022-05-15 15:32:33,461 INFO [train.py:812] (0/8) Epoch 29, batch 4450, loss[loss=0.1471, simple_loss=0.237, pruned_loss=0.02856, over 6341.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2446, pruned_loss=0.03043, over 1400530.07 frames.], batch size: 38, lr: 2.66e-04
+2022-05-15 15:33:31,980 INFO [train.py:812] (0/8) Epoch 29, batch 4500, loss[loss=0.1945, simple_loss=0.2857, pruned_loss=0.05167, over 7201.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2462, pruned_loss=0.03129, over 1378013.24 frames.], batch size: 22, lr: 2.66e-04
+2022-05-15 15:34:29,709 INFO [train.py:812] (0/8) Epoch 29, batch 4550, loss[loss=0.1706, simple_loss=0.2541, pruned_loss=0.0435, over 5125.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2476, pruned_loss=0.03195, over 1359059.75 frames.], batch size: 52, lr: 2.66e-04
+2022-05-15 15:35:14,094 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-29.pt
+2022-05-15 15:35:40,752 INFO [train.py:812] (0/8) Epoch 30, batch 0, loss[loss=0.1425, simple_loss=0.2331, pruned_loss=0.02591, over 7317.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2331, pruned_loss=0.02591, over 7317.00 frames.], batch size: 20, lr: 2.62e-04
+2022-05-15 15:36:39,961 INFO [train.py:812] (0/8) Epoch 30, batch 50, loss[loss=0.1396, simple_loss=0.232, pruned_loss=0.02362, over 7294.00 frames.], tot_loss[loss=0.155, simple_loss=0.2481, pruned_loss=0.03096, over 324712.85 frames.], batch size: 18, lr: 2.62e-04
+2022-05-15 15:37:39,027 INFO [train.py:812] (0/8) Epoch 30, batch 100, loss[loss=0.1247, simple_loss=0.2113, pruned_loss=0.01898, over 7289.00 frames.], tot_loss[loss=0.1527, simple_loss=0.244, pruned_loss=0.03066, over 572534.15 frames.], batch size: 17, lr: 2.62e-04
+2022-05-15 15:38:38,754 INFO [train.py:812] (0/8) Epoch 30, batch 150, loss[loss=0.1669, simple_loss=0.2694, pruned_loss=0.03216, over 7290.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2452, pruned_loss=0.03147, over 749807.85 frames.], batch size: 24, lr: 2.62e-04
+2022-05-15 15:39:36,197 INFO [train.py:812] (0/8) Epoch 30, batch 200, loss[loss=0.1395, simple_loss=0.2318, pruned_loss=0.02358, over 7362.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03086, over 899776.74 frames.], batch size: 19, lr: 2.61e-04
+2022-05-15 15:40:35,791 INFO [train.py:812] (0/8) Epoch 30, batch 250, loss[loss=0.1291, simple_loss=0.2103, pruned_loss=0.02391, over 6808.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03026, over 1015464.03 frames.], batch size: 15, lr: 2.61e-04
+2022-05-15 15:41:34,961 INFO [train.py:812] (0/8) Epoch 30, batch 300, loss[loss=0.1505, simple_loss=0.227, pruned_loss=0.03704, over 7275.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2457, pruned_loss=0.0308, over 1107724.48 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:42:33,928 INFO [train.py:812] (0/8) Epoch 30, batch 350, loss[loss=0.1514, simple_loss=0.2431, pruned_loss=0.02986, over 7333.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2443, pruned_loss=0.03065, over 1180543.31 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:43:32,158 INFO [train.py:812] (0/8) Epoch 30, batch 400, loss[loss=0.1858, simple_loss=0.2829, pruned_loss=0.04432, over 7318.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2444, pruned_loss=0.03029, over 1236771.70 frames.], batch size: 24, lr: 2.61e-04
+2022-05-15 15:44:30,956 INFO [train.py:812] (0/8) Epoch 30, batch 450, loss[loss=0.1425, simple_loss=0.2356, pruned_loss=0.02474, over 7411.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2444, pruned_loss=0.03069, over 1279561.91 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:45:28,634 INFO [train.py:812] (0/8) Epoch 30, batch 500, loss[loss=0.1441, simple_loss=0.2382, pruned_loss=0.02499, over 7327.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2444, pruned_loss=0.03055, over 1307634.82 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:46:27,395 INFO [train.py:812] (0/8) Epoch 30, batch 550, loss[loss=0.1774, simple_loss=0.27, pruned_loss=0.04245, over 7325.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2456, pruned_loss=0.03102, over 1335687.41 frames.], batch size: 24, lr: 2.61e-04
+2022-05-15 15:47:24,867 INFO [train.py:812] (0/8) Epoch 30, batch 600, loss[loss=0.1693, simple_loss=0.2611, pruned_loss=0.0387, over 7210.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.03101, over 1351612.98 frames.], batch size: 22, lr: 2.61e-04
+2022-05-15 15:48:22,455 INFO [train.py:812] (0/8) Epoch 30, batch 650, loss[loss=0.1335, simple_loss=0.2199, pruned_loss=0.02354, over 7455.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2447, pruned_loss=0.03094, over 1366467.26 frames.], batch size: 19, lr: 2.61e-04
+2022-05-15 15:49:20,302 INFO [train.py:812] (0/8) Epoch 30, batch 700, loss[loss=0.1505, simple_loss=0.244, pruned_loss=0.02851, over 7310.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03077, over 1375585.84 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:50:18,927 INFO [train.py:812] (0/8) Epoch 30, batch 750, loss[loss=0.1663, simple_loss=0.2617, pruned_loss=0.03543, over 7229.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2459, pruned_loss=0.03077, over 1382253.18 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:51:17,426 INFO [train.py:812] (0/8) Epoch 30, batch 800, loss[loss=0.1503, simple_loss=0.246, pruned_loss=0.02733, over 7342.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.03077, over 1387798.01 frames.], batch size: 22, lr: 2.61e-04
+2022-05-15 15:52:16,590 INFO [train.py:812] (0/8) Epoch 30, batch 850, loss[loss=0.1618, simple_loss=0.2478, pruned_loss=0.03785, over 7066.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2444, pruned_loss=0.03059, over 1396493.53 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:53:14,245 INFO [train.py:812] (0/8) Epoch 30, batch 900, loss[loss=0.1741, simple_loss=0.2552, pruned_loss=0.04648, over 7215.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2448, pruned_loss=0.0309, over 1400193.14 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:54:13,175 INFO [train.py:812] (0/8) Epoch 30, batch 950, loss[loss=0.1562, simple_loss=0.255, pruned_loss=0.02871, over 7117.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2446, pruned_loss=0.03102, over 1406395.20 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:55:11,573 INFO [train.py:812] (0/8) Epoch 30, batch 1000, loss[loss=0.1449, simple_loss=0.2285, pruned_loss=0.03065, over 7139.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2454, pruned_loss=0.03135, over 1410584.84 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:56:10,061 INFO [train.py:812] (0/8) Epoch 30, batch 1050, loss[loss=0.1583, simple_loss=0.2491, pruned_loss=0.03376, over 7275.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2457, pruned_loss=0.0315, over 1407512.04 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:57:08,265 INFO [train.py:812] (0/8) Epoch 30, batch 1100, loss[loss=0.1666, simple_loss=0.2597, pruned_loss=0.03679, over 7317.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2469, pruned_loss=0.03148, over 1416942.31 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:58:07,692 INFO [train.py:812] (0/8) Epoch 30, batch 1150, loss[loss=0.1517, simple_loss=0.2317, pruned_loss=0.03585, over 6981.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2468, pruned_loss=0.03106, over 1418015.36 frames.], batch size: 16, lr: 2.61e-04
+2022-05-15 15:59:06,165 INFO [train.py:812] (0/8) Epoch 30, batch 1200, loss[loss=0.1609, simple_loss=0.2516, pruned_loss=0.03508, over 7166.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2459, pruned_loss=0.03056, over 1422798.20 frames.], batch size: 19, lr: 2.61e-04
+2022-05-15 16:00:14,953 INFO [train.py:812] (0/8) Epoch 30, batch 1250, loss[loss=0.1568, simple_loss=0.2482, pruned_loss=0.03271, over 5354.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2449, pruned_loss=0.03067, over 1418201.34 frames.], batch size: 53, lr: 2.60e-04
+2022-05-15 16:01:13,722 INFO [train.py:812] (0/8) Epoch 30, batch 1300, loss[loss=0.1616, simple_loss=0.2576, pruned_loss=0.03284, over 7342.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03079, over 1418585.38 frames.], batch size: 22, lr: 2.60e-04
+2022-05-15 16:02:13,352 INFO [train.py:812] (0/8) Epoch 30, batch 1350, loss[loss=0.1516, simple_loss=0.2451, pruned_loss=0.02908, over 6125.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2457, pruned_loss=0.03095, over 1418694.86 frames.], batch size: 37, lr: 2.60e-04
+2022-05-15 16:03:12,418 INFO [train.py:812] (0/8) Epoch 30, batch 1400, loss[loss=0.1332, simple_loss=0.2133, pruned_loss=0.02658, over 6842.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03078, over 1418934.32 frames.], batch size: 15, lr: 2.60e-04
+2022-05-15 16:04:10,792 INFO [train.py:812] (0/8) Epoch 30, batch 1450, loss[loss=0.1372, simple_loss=0.2367, pruned_loss=0.01888, over 7119.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2448, pruned_loss=0.03046, over 1417165.82 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:05:09,031 INFO [train.py:812] (0/8) Epoch 30, batch 1500, loss[loss=0.149, simple_loss=0.2363, pruned_loss=0.03083, over 7257.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.03017, over 1417256.63 frames.], batch size: 19, lr: 2.60e-04
+2022-05-15 16:06:06,399 INFO [train.py:812] (0/8) Epoch 30, batch 1550, loss[loss=0.1772, simple_loss=0.2611, pruned_loss=0.04663, over 7156.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2449, pruned_loss=0.03032, over 1418018.87 frames.], batch size: 23, lr: 2.60e-04
+2022-05-15 16:07:03,135 INFO [train.py:812] (0/8) Epoch 30, batch 1600, loss[loss=0.1585, simple_loss=0.2677, pruned_loss=0.02469, over 7320.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2457, pruned_loss=0.03055, over 1419379.51 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:08:02,800 INFO [train.py:812] (0/8) Epoch 30, batch 1650, loss[loss=0.1713, simple_loss=0.2692, pruned_loss=0.03671, over 7208.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2455, pruned_loss=0.03059, over 1423424.59 frames.], batch size: 26, lr: 2.60e-04
+2022-05-15 16:09:00,190 INFO [train.py:812] (0/8) Epoch 30, batch 1700, loss[loss=0.1636, simple_loss=0.2471, pruned_loss=0.04003, over 7128.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2464, pruned_loss=0.031, over 1426080.08 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:09:58,749 INFO [train.py:812] (0/8) Epoch 30, batch 1750, loss[loss=0.165, simple_loss=0.2526, pruned_loss=0.03873, over 7140.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.0309, over 1423215.00 frames.], batch size: 20, lr: 2.60e-04
+2022-05-15 16:10:56,860 INFO [train.py:812] (0/8) Epoch 30, batch 1800, loss[loss=0.1794, simple_loss=0.2744, pruned_loss=0.04217, over 5218.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2461, pruned_loss=0.03112, over 1420051.18 frames.], batch size: 53, lr: 2.60e-04
+2022-05-15 16:11:55,119 INFO [train.py:812] (0/8) Epoch 30, batch 1850, loss[loss=0.1614, simple_loss=0.2554, pruned_loss=0.03367, over 7110.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03078, over 1424327.98 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:12:53,322 INFO [train.py:812] (0/8) Epoch 30, batch 1900, loss[loss=0.1576, simple_loss=0.2364, pruned_loss=0.03939, over 6820.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2456, pruned_loss=0.03102, over 1426169.68 frames.], batch size: 15, lr: 2.60e-04
+2022-05-15 16:13:52,843 INFO [train.py:812] (0/8) Epoch 30, batch 1950, loss[loss=0.1258, simple_loss=0.2075, pruned_loss=0.02207, over 7268.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2454, pruned_loss=0.03091, over 1427372.71 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:14:51,452 INFO [train.py:812] (0/8) Epoch 30, batch 2000, loss[loss=0.1516, simple_loss=0.2524, pruned_loss=0.02539, over 7334.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2458, pruned_loss=0.03099, over 1429964.78 frames.], batch size: 22, lr: 2.60e-04
+2022-05-15 16:15:50,897 INFO [train.py:812] (0/8) Epoch 30, batch 2050, loss[loss=0.2118, simple_loss=0.3078, pruned_loss=0.0579, over 7205.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2457, pruned_loss=0.03088, over 1430168.31 frames.], batch size: 23, lr: 2.60e-04
+2022-05-15 16:16:49,854 INFO [train.py:812] (0/8) Epoch 30, batch 2100, loss[loss=0.1474, simple_loss=0.2483, pruned_loss=0.02326, over 7148.00 frames.], tot_loss[loss=0.1541, simple_loss=0.246, pruned_loss=0.03112, over 1429697.89 frames.], batch size: 20, lr: 2.60e-04
+2022-05-15 16:17:48,125 INFO [train.py:812] (0/8) Epoch 30, batch 2150, loss[loss=0.1344, simple_loss=0.2213, pruned_loss=0.02375, over 7133.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2455, pruned_loss=0.03114, over 1428585.59 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:18:47,074 INFO [train.py:812] (0/8) Epoch 30, batch 2200, loss[loss=0.1471, simple_loss=0.2394, pruned_loss=0.02742, over 7289.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2448, pruned_loss=0.03109, over 1423837.45 frames.], batch size: 24, lr: 2.60e-04
+2022-05-15 16:19:45,950 INFO [train.py:812] (0/8) Epoch 30, batch 2250, loss[loss=0.1569, simple_loss=0.2484, pruned_loss=0.03272, over 7168.00 frames.], tot_loss[loss=0.1538, simple_loss=0.245, pruned_loss=0.03129, over 1422464.91 frames.], batch size: 26, lr: 2.59e-04
+2022-05-15 16:20:43,574 INFO [train.py:812] (0/8) Epoch 30, batch 2300, loss[loss=0.1271, simple_loss=0.2162, pruned_loss=0.01897, over 7350.00 frames.], tot_loss[loss=0.1535, simple_loss=0.245, pruned_loss=0.03105, over 1419619.93 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:21:42,618 INFO [train.py:812] (0/8) Epoch 30, batch 2350, loss[loss=0.1659, simple_loss=0.2653, pruned_loss=0.03331, over 7331.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2445, pruned_loss=0.03096, over 1420811.70 frames.], batch size: 22, lr: 2.59e-04
+2022-05-15 16:22:41,684 INFO [train.py:812] (0/8) Epoch 30, batch 2400, loss[loss=0.174, simple_loss=0.2678, pruned_loss=0.04011, over 7271.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2452, pruned_loss=0.03125, over 1422503.82 frames.], batch size: 25, lr: 2.59e-04
+2022-05-15 16:23:41,323 INFO [train.py:812] (0/8) Epoch 30, batch 2450, loss[loss=0.1558, simple_loss=0.2502, pruned_loss=0.03065, over 7148.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.03057, over 1426588.53 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:24:39,655 INFO [train.py:812] (0/8) Epoch 30, batch 2500, loss[loss=0.1272, simple_loss=0.2114, pruned_loss=0.02147, over 7167.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.03066, over 1430415.91 frames.], batch size: 16, lr: 2.59e-04
+2022-05-15 16:25:39,024 INFO [train.py:812] (0/8) Epoch 30, batch 2550, loss[loss=0.1307, simple_loss=0.2236, pruned_loss=0.0189, over 7409.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2435, pruned_loss=0.03067, over 1427024.16 frames.], batch size: 18, lr: 2.59e-04
+2022-05-15 16:26:37,719 INFO [train.py:812] (0/8) Epoch 30, batch 2600, loss[loss=0.1208, simple_loss=0.2184, pruned_loss=0.01162, over 7447.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2438, pruned_loss=0.03035, over 1426773.84 frames.], batch size: 22, lr: 2.59e-04
+2022-05-15 16:27:37,200 INFO [train.py:812] (0/8) Epoch 30, batch 2650, loss[loss=0.1315, simple_loss=0.2099, pruned_loss=0.02655, over 7141.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.03059, over 1429526.10 frames.], batch size: 17, lr: 2.59e-04
+2022-05-15 16:28:36,164 INFO [train.py:812] (0/8) Epoch 30, batch 2700, loss[loss=0.1689, simple_loss=0.2582, pruned_loss=0.03982, over 7116.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2455, pruned_loss=0.03115, over 1429455.57 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:29:34,400 INFO [train.py:812] (0/8) Epoch 30, batch 2750, loss[loss=0.141, simple_loss=0.2375, pruned_loss=0.02221, over 7233.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2458, pruned_loss=0.03121, over 1425580.18 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:30:32,050 INFO [train.py:812] (0/8) Epoch 30, batch 2800, loss[loss=0.1467, simple_loss=0.2439, pruned_loss=0.02477, over 7329.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2456, pruned_loss=0.03111, over 1424964.33 frames.], batch size: 22, lr: 2.59e-04
+2022-05-15 16:31:31,688 INFO [train.py:812] (0/8) Epoch 30, batch 2850, loss[loss=0.1663, simple_loss=0.2679, pruned_loss=0.03238, over 7219.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2449, pruned_loss=0.03105, over 1419147.31 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:32:29,827 INFO [train.py:812] (0/8) Epoch 30, batch 2900, loss[loss=0.1219, simple_loss=0.2027, pruned_loss=0.0206, over 6978.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2444, pruned_loss=0.031, over 1421608.17 frames.], batch size: 16, lr: 2.59e-04
+2022-05-15 16:33:25,187 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-136000.pt
+2022-05-15 16:33:36,390 INFO [train.py:812] (0/8) Epoch 30, batch 2950, loss[loss=0.1658, simple_loss=0.264, pruned_loss=0.03386, over 6424.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2438, pruned_loss=0.03084, over 1422657.37 frames.], batch size: 39, lr: 2.59e-04
+2022-05-15 16:34:35,489 INFO [train.py:812] (0/8) Epoch 30, batch 3000, loss[loss=0.1427, simple_loss=0.2382, pruned_loss=0.02363, over 7105.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2437, pruned_loss=0.03077, over 1425421.70 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:34:35,490 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 16:34:43,057 INFO [train.py:841] (0/8) Epoch 30, validation: loss=0.1528, simple_loss=0.2494, pruned_loss=0.02809, over 698248.00 frames.
+2022-05-15 16:35:41,856 INFO [train.py:812] (0/8) Epoch 30, batch 3050, loss[loss=0.1355, simple_loss=0.2383, pruned_loss=0.01639, over 7109.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03082, over 1427238.86 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:36:40,915 INFO [train.py:812] (0/8) Epoch 30, batch 3100, loss[loss=0.1392, simple_loss=0.2301, pruned_loss=0.02421, over 7419.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2448, pruned_loss=0.03084, over 1427394.20 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:37:40,500 INFO [train.py:812] (0/8) Epoch 30, batch 3150, loss[loss=0.1576, simple_loss=0.2468, pruned_loss=0.03421, over 7170.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2447, pruned_loss=0.03105, over 1422912.40 frames.], batch size: 18, lr: 2.59e-04
+2022-05-15 16:38:39,745 INFO [train.py:812] (0/8) Epoch 30, batch 3200, loss[loss=0.1335, simple_loss=0.2219, pruned_loss=0.02258, over 7256.00 frames.], tot_loss[loss=0.1521, simple_loss=0.243, pruned_loss=0.03062, over 1425768.78 frames.], batch size: 19, lr: 2.59e-04
+2022-05-15 16:39:38,880 INFO [train.py:812] (0/8) Epoch 30, batch 3250, loss[loss=0.1735, simple_loss=0.2635, pruned_loss=0.04181, over 7033.00 frames.], tot_loss[loss=0.152, simple_loss=0.2427, pruned_loss=0.03064, over 1421129.63 frames.], batch size: 28, lr: 2.59e-04
+2022-05-15 16:40:36,607 INFO [train.py:812] (0/8) Epoch 30, batch 3300, loss[loss=0.1495, simple_loss=0.2427, pruned_loss=0.02811, over 7325.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2434, pruned_loss=0.03058, over 1423908.19 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 16:41:35,370 INFO [train.py:812] (0/8) Epoch 30, batch 3350, loss[loss=0.1252, simple_loss=0.2119, pruned_loss=0.01931, over 7282.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2426, pruned_loss=0.03011, over 1427686.73 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:42:33,415 INFO [train.py:812] (0/8) Epoch 30, batch 3400, loss[loss=0.1714, simple_loss=0.2648, pruned_loss=0.03894, over 4990.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2431, pruned_loss=0.03062, over 1424178.60 frames.], batch size: 52, lr: 2.58e-04
+2022-05-15 16:43:31,881 INFO [train.py:812] (0/8) Epoch 30, batch 3450, loss[loss=0.156, simple_loss=0.2448, pruned_loss=0.03363, over 7299.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2437, pruned_loss=0.03081, over 1420675.24 frames.], batch size: 24, lr: 2.58e-04
+2022-05-15 16:44:30,301 INFO [train.py:812] (0/8) Epoch 30, batch 3500, loss[loss=0.2162, simple_loss=0.3189, pruned_loss=0.05675, over 7153.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.0308, over 1422749.90 frames.], batch size: 26, lr: 2.58e-04
+2022-05-15 16:45:29,363 INFO [train.py:812] (0/8) Epoch 30, batch 3550, loss[loss=0.1534, simple_loss=0.2406, pruned_loss=0.03306, over 7173.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2443, pruned_loss=0.03043, over 1421477.12 frames.], batch size: 18, lr: 2.58e-04
+2022-05-15 16:46:28,235 INFO [train.py:812] (0/8) Epoch 30, batch 3600, loss[loss=0.1356, simple_loss=0.2287, pruned_loss=0.02123, over 7252.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.03049, over 1425932.12 frames.], batch size: 19, lr: 2.58e-04
+2022-05-15 16:47:27,375 INFO [train.py:812] (0/8) Epoch 30, batch 3650, loss[loss=0.1533, simple_loss=0.25, pruned_loss=0.02826, over 6766.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2446, pruned_loss=0.03089, over 1428015.77 frames.], batch size: 31, lr: 2.58e-04
+2022-05-15 16:48:25,015 INFO [train.py:812] (0/8) Epoch 30, batch 3700, loss[loss=0.1318, simple_loss=0.2069, pruned_loss=0.0284, over 7291.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2446, pruned_loss=0.03093, over 1429211.21 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:49:23,805 INFO [train.py:812] (0/8) Epoch 30, batch 3750, loss[loss=0.1572, simple_loss=0.2578, pruned_loss=0.0283, over 7082.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2448, pruned_loss=0.0309, over 1432039.96 frames.], batch size: 28, lr: 2.58e-04
+2022-05-15 16:50:21,268 INFO [train.py:812] (0/8) Epoch 30, batch 3800, loss[loss=0.1969, simple_loss=0.2967, pruned_loss=0.04855, over 7199.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2461, pruned_loss=0.03123, over 1425884.87 frames.], batch size: 22, lr: 2.58e-04
+2022-05-15 16:51:18,878 INFO [train.py:812] (0/8) Epoch 30, batch 3850, loss[loss=0.1318, simple_loss=0.2161, pruned_loss=0.02373, over 6795.00 frames.], tot_loss[loss=0.153, simple_loss=0.245, pruned_loss=0.0305, over 1426521.55 frames.], batch size: 15, lr: 2.58e-04
+2022-05-15 16:52:16,795 INFO [train.py:812] (0/8) Epoch 30, batch 3900, loss[loss=0.1454, simple_loss=0.2196, pruned_loss=0.03556, over 7119.00 frames.], tot_loss[loss=0.1529, simple_loss=0.245, pruned_loss=0.0304, over 1426345.71 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:53:15,080 INFO [train.py:812] (0/8) Epoch 30, batch 3950, loss[loss=0.156, simple_loss=0.249, pruned_loss=0.0315, over 7352.00 frames.], tot_loss[loss=0.1537, simple_loss=0.246, pruned_loss=0.03068, over 1420927.94 frames.], batch size: 23, lr: 2.58e-04
+2022-05-15 16:54:13,792 INFO [train.py:812] (0/8) Epoch 30, batch 4000, loss[loss=0.1662, simple_loss=0.2562, pruned_loss=0.03808, over 7301.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2465, pruned_loss=0.03115, over 1419186.73 frames.], batch size: 25, lr: 2.58e-04
+2022-05-15 16:55:12,871 INFO [train.py:812] (0/8) Epoch 30, batch 4050, loss[loss=0.1596, simple_loss=0.2591, pruned_loss=0.0301, over 7039.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2464, pruned_loss=0.03129, over 1418205.35 frames.], batch size: 28, lr: 2.58e-04
+2022-05-15 16:56:10,893 INFO [train.py:812] (0/8) Epoch 30, batch 4100, loss[loss=0.1666, simple_loss=0.2516, pruned_loss=0.0408, over 7313.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2456, pruned_loss=0.03067, over 1420167.33 frames.], batch size: 21, lr: 2.58e-04
+2022-05-15 16:57:19,275 INFO [train.py:812] (0/8) Epoch 30, batch 4150, loss[loss=0.1651, simple_loss=0.2583, pruned_loss=0.036, over 7220.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03071, over 1420963.51 frames.], batch size: 21, lr: 2.58e-04
+2022-05-15 16:58:17,929 INFO [train.py:812] (0/8) Epoch 30, batch 4200, loss[loss=0.1472, simple_loss=0.234, pruned_loss=0.03023, over 7420.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2452, pruned_loss=0.03095, over 1420982.99 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 16:59:24,875 INFO [train.py:812] (0/8) Epoch 30, batch 4250, loss[loss=0.1378, simple_loss=0.2318, pruned_loss=0.02188, over 7378.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2472, pruned_loss=0.0316, over 1415767.35 frames.], batch size: 23, lr: 2.58e-04
+2022-05-15 17:00:23,118 INFO [train.py:812] (0/8) Epoch 30, batch 4300, loss[loss=0.1354, simple_loss=0.2149, pruned_loss=0.02795, over 7294.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2466, pruned_loss=0.03139, over 1419573.72 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 17:01:31,688 INFO [train.py:812] (0/8) Epoch 30, batch 4350, loss[loss=0.1389, simple_loss=0.2332, pruned_loss=0.02232, over 7241.00 frames.], tot_loss[loss=0.154, simple_loss=0.2457, pruned_loss=0.03118, over 1422024.49 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 17:02:30,802 INFO [train.py:812] (0/8) Epoch 30, batch 4400, loss[loss=0.1695, simple_loss=0.2574, pruned_loss=0.04079, over 7230.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2453, pruned_loss=0.03126, over 1418907.70 frames.], batch size: 20, lr: 2.57e-04
+2022-05-15 17:03:47,896 INFO [train.py:812] (0/8) Epoch 30, batch 4450, loss[loss=0.1512, simple_loss=0.2431, pruned_loss=0.0297, over 6546.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.03103, over 1413752.98 frames.], batch size: 38, lr: 2.57e-04
+2022-05-15 17:04:54,687 INFO [train.py:812] (0/8) Epoch 30, batch 4500, loss[loss=0.1942, simple_loss=0.2791, pruned_loss=0.05467, over 5040.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.03151, over 1398903.20 frames.], batch size: 52, lr: 2.57e-04
+2022-05-15 17:05:52,206 INFO [train.py:812] (0/8) Epoch 30, batch 4550, loss[loss=0.1579, simple_loss=0.2413, pruned_loss=0.03724, over 5025.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2489, pruned_loss=0.0326, over 1358818.15 frames.], batch size: 52, lr: 2.57e-04
+2022-05-15 17:06:46,693 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-30.pt
+2022-05-15 17:07:08,135 INFO [train.py:812] (0/8) Epoch 31, batch 0, loss[loss=0.1466, simple_loss=0.2371, pruned_loss=0.02805, over 7336.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2371, pruned_loss=0.02805, over 7336.00 frames.], batch size: 20, lr: 2.53e-04
+2022-05-15 17:08:07,470 INFO [train.py:812] (0/8) Epoch 31, batch 50, loss[loss=0.1472, simple_loss=0.2496, pruned_loss=0.0224, over 7259.00 frames.], tot_loss[loss=0.155, simple_loss=0.2457, pruned_loss=0.03212, over 316705.30 frames.], batch size: 19, lr: 2.53e-04
+2022-05-15 17:09:06,195 INFO [train.py:812] (0/8) Epoch 31, batch 100, loss[loss=0.1598, simple_loss=0.2543, pruned_loss=0.03265, over 7377.00 frames.], tot_loss[loss=0.156, simple_loss=0.2479, pruned_loss=0.03202, over 560838.75 frames.], batch size: 23, lr: 2.53e-04
+2022-05-15 17:10:05,002 INFO [train.py:812] (0/8) Epoch 31, batch 150, loss[loss=0.1749, simple_loss=0.269, pruned_loss=0.04037, over 7201.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2464, pruned_loss=0.03164, over 755618.21 frames.], batch size: 22, lr: 2.53e-04
+2022-05-15 17:11:03,945 INFO [train.py:812] (0/8) Epoch 31, batch 200, loss[loss=0.1964, simple_loss=0.2785, pruned_loss=0.05716, over 5348.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.03112, over 901112.47 frames.], batch size: 52, lr: 2.53e-04
+2022-05-15 17:12:02,397 INFO [train.py:812] (0/8) Epoch 31, batch 250, loss[loss=0.1435, simple_loss=0.2323, pruned_loss=0.02739, over 7280.00 frames.], tot_loss[loss=0.1535, simple_loss=0.246, pruned_loss=0.03054, over 1015586.91 frames.], batch size: 25, lr: 2.53e-04
+2022-05-15 17:13:01,755 INFO [train.py:812] (0/8) Epoch 31, batch 300, loss[loss=0.1406, simple_loss=0.2347, pruned_loss=0.02322, over 7314.00 frames.], tot_loss[loss=0.153, simple_loss=0.245, pruned_loss=0.03053, over 1107140.65 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:13:59,731 INFO [train.py:812] (0/8) Epoch 31, batch 350, loss[loss=0.1395, simple_loss=0.2217, pruned_loss=0.02867, over 7154.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03082, over 1174214.21 frames.], batch size: 18, lr: 2.53e-04
+2022-05-15 17:14:57,255 INFO [train.py:812] (0/8) Epoch 31, batch 400, loss[loss=0.1419, simple_loss=0.2455, pruned_loss=0.01919, over 7219.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03068, over 1225232.58 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:15:56,168 INFO [train.py:812] (0/8) Epoch 31, batch 450, loss[loss=0.1924, simple_loss=0.2886, pruned_loss=0.04808, over 7163.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.03151, over 1265525.92 frames.], batch size: 26, lr: 2.53e-04
+2022-05-15 17:16:55,562 INFO [train.py:812] (0/8) Epoch 31, batch 500, loss[loss=0.1251, simple_loss=0.214, pruned_loss=0.01811, over 7279.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2455, pruned_loss=0.03087, over 1301067.29 frames.], batch size: 17, lr: 2.53e-04
+2022-05-15 17:17:54,438 INFO [train.py:812] (0/8) Epoch 31, batch 550, loss[loss=0.16, simple_loss=0.2576, pruned_loss=0.03116, over 7403.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2463, pruned_loss=0.03122, over 1327924.30 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:18:53,056 INFO [train.py:812] (0/8) Epoch 31, batch 600, loss[loss=0.1447, simple_loss=0.2294, pruned_loss=0.02994, over 7059.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2468, pruned_loss=0.03164, over 1347175.18 frames.], batch size: 18, lr: 2.53e-04
+2022-05-15 17:19:50,587 INFO [train.py:812] (0/8) Epoch 31, batch 650, loss[loss=0.1455, simple_loss=0.2426, pruned_loss=0.02421, over 7148.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2457, pruned_loss=0.03088, over 1368963.86 frames.], batch size: 20, lr: 2.53e-04
+2022-05-15 17:20:49,417 INFO [train.py:812] (0/8) Epoch 31, batch 700, loss[loss=0.1403, simple_loss=0.2264, pruned_loss=0.0271, over 6797.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2452, pruned_loss=0.03089, over 1378826.84 frames.], batch size: 15, lr: 2.52e-04
+2022-05-15 17:21:47,367 INFO [train.py:812] (0/8) Epoch 31, batch 750, loss[loss=0.1354, simple_loss=0.2296, pruned_loss=0.02059, over 7229.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2441, pruned_loss=0.03036, over 1387217.58 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:22:46,095 INFO [train.py:812] (0/8) Epoch 31, batch 800, loss[loss=0.1384, simple_loss=0.2385, pruned_loss=0.0192, over 7328.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2451, pruned_loss=0.03053, over 1395258.81 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:23:44,798 INFO [train.py:812] (0/8) Epoch 31, batch 850, loss[loss=0.1415, simple_loss=0.2423, pruned_loss=0.02032, over 7423.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2443, pruned_loss=0.03034, over 1399571.03 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:24:43,291 INFO [train.py:812] (0/8) Epoch 31, batch 900, loss[loss=0.1238, simple_loss=0.2016, pruned_loss=0.02293, over 6755.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2441, pruned_loss=0.03037, over 1404311.09 frames.], batch size: 15, lr: 2.52e-04
+2022-05-15 17:25:42,271 INFO [train.py:812] (0/8) Epoch 31, batch 950, loss[loss=0.1575, simple_loss=0.2507, pruned_loss=0.03219, over 7056.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2441, pruned_loss=0.03067, over 1405540.35 frames.], batch size: 28, lr: 2.52e-04
+2022-05-15 17:26:41,396 INFO [train.py:812] (0/8) Epoch 31, batch 1000, loss[loss=0.1424, simple_loss=0.2408, pruned_loss=0.02193, over 7337.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2448, pruned_loss=0.03094, over 1408724.70 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:27:40,593 INFO [train.py:812] (0/8) Epoch 31, batch 1050, loss[loss=0.1555, simple_loss=0.2488, pruned_loss=0.03113, over 7060.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03084, over 1410554.15 frames.], batch size: 28, lr: 2.52e-04
+2022-05-15 17:28:39,468 INFO [train.py:812] (0/8) Epoch 31, batch 1100, loss[loss=0.14, simple_loss=0.2287, pruned_loss=0.02568, over 7070.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2449, pruned_loss=0.031, over 1415488.02 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:29:38,116 INFO [train.py:812] (0/8) Epoch 31, batch 1150, loss[loss=0.1399, simple_loss=0.2286, pruned_loss=0.02562, over 7060.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2441, pruned_loss=0.03082, over 1416636.56 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:30:36,854 INFO [train.py:812] (0/8) Epoch 31, batch 1200, loss[loss=0.1665, simple_loss=0.2566, pruned_loss=0.03824, over 7207.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2436, pruned_loss=0.03056, over 1418660.76 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:31:36,137 INFO [train.py:812] (0/8) Epoch 31, batch 1250, loss[loss=0.1504, simple_loss=0.2398, pruned_loss=0.0305, over 7404.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2439, pruned_loss=0.03062, over 1418228.35 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:32:35,749 INFO [train.py:812] (0/8) Epoch 31, batch 1300, loss[loss=0.1742, simple_loss=0.2843, pruned_loss=0.03209, over 7145.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03044, over 1417636.48 frames.], batch size: 26, lr: 2.52e-04
+2022-05-15 17:33:34,081 INFO [train.py:812] (0/8) Epoch 31, batch 1350, loss[loss=0.1365, simple_loss=0.2276, pruned_loss=0.02273, over 7151.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2455, pruned_loss=0.0308, over 1414956.93 frames.], batch size: 17, lr: 2.52e-04
+2022-05-15 17:34:32,689 INFO [train.py:812] (0/8) Epoch 31, batch 1400, loss[loss=0.1893, simple_loss=0.2871, pruned_loss=0.04571, over 7314.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2461, pruned_loss=0.03086, over 1418529.17 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:35:31,467 INFO [train.py:812] (0/8) Epoch 31, batch 1450, loss[loss=0.1346, simple_loss=0.2286, pruned_loss=0.02028, over 7143.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2461, pruned_loss=0.03068, over 1420388.22 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:36:30,344 INFO [train.py:812] (0/8) Epoch 31, batch 1500, loss[loss=0.1681, simple_loss=0.2655, pruned_loss=0.03531, over 7295.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2465, pruned_loss=0.0307, over 1426054.90 frames.], batch size: 25, lr: 2.52e-04
+2022-05-15 17:37:27,931 INFO [train.py:812] (0/8) Epoch 31, batch 1550, loss[loss=0.163, simple_loss=0.267, pruned_loss=0.02947, over 7304.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.03005, over 1427692.08 frames.], batch size: 25, lr: 2.52e-04
+2022-05-15 17:38:27,306 INFO [train.py:812] (0/8) Epoch 31, batch 1600, loss[loss=0.1462, simple_loss=0.2393, pruned_loss=0.02662, over 7257.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02962, over 1428499.10 frames.], batch size: 19, lr: 2.52e-04
+2022-05-15 17:39:26,041 INFO [train.py:812] (0/8) Epoch 31, batch 1650, loss[loss=0.156, simple_loss=0.2609, pruned_loss=0.02553, over 7107.00 frames.], tot_loss[loss=0.153, simple_loss=0.2454, pruned_loss=0.03028, over 1428032.48 frames.], batch size: 21, lr: 2.52e-04
+2022-05-15 17:40:24,535 INFO [train.py:812] (0/8) Epoch 31, batch 1700, loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03138, over 7291.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.03004, over 1424408.50 frames.], batch size: 24, lr: 2.52e-04
+2022-05-15 17:41:22,575 INFO [train.py:812] (0/8) Epoch 31, batch 1750, loss[loss=0.1729, simple_loss=0.2643, pruned_loss=0.04076, over 7378.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2443, pruned_loss=0.03023, over 1427160.84 frames.], batch size: 23, lr: 2.52e-04
+2022-05-15 17:42:21,644 INFO [train.py:812] (0/8) Epoch 31, batch 1800, loss[loss=0.1415, simple_loss=0.2349, pruned_loss=0.02401, over 7422.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02978, over 1423689.50 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 17:43:20,015 INFO [train.py:812] (0/8) Epoch 31, batch 1850, loss[loss=0.1483, simple_loss=0.2299, pruned_loss=0.03337, over 7134.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2427, pruned_loss=0.02951, over 1421442.13 frames.], batch size: 17, lr: 2.51e-04
+2022-05-15 17:44:19,007 INFO [train.py:812] (0/8) Epoch 31, batch 1900, loss[loss=0.1568, simple_loss=0.2533, pruned_loss=0.03015, over 7325.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02944, over 1424529.22 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 17:45:17,755 INFO [train.py:812] (0/8) Epoch 31, batch 1950, loss[loss=0.1385, simple_loss=0.2319, pruned_loss=0.02254, over 7381.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.02935, over 1424946.69 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:46:16,471 INFO [train.py:812] (0/8) Epoch 31, batch 2000, loss[loss=0.15, simple_loss=0.2404, pruned_loss=0.02976, over 7162.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2421, pruned_loss=0.0293, over 1426309.20 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:47:15,231 INFO [train.py:812] (0/8) Epoch 31, batch 2050, loss[loss=0.1493, simple_loss=0.2516, pruned_loss=0.0235, over 7202.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2422, pruned_loss=0.0297, over 1423702.31 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 17:48:13,815 INFO [train.py:812] (0/8) Epoch 31, batch 2100, loss[loss=0.1416, simple_loss=0.2278, pruned_loss=0.02772, over 7161.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2433, pruned_loss=0.03, over 1422366.22 frames.], batch size: 19, lr: 2.51e-04
+2022-05-15 17:49:12,918 INFO [train.py:812] (0/8) Epoch 31, batch 2150, loss[loss=0.1301, simple_loss=0.2211, pruned_loss=0.01958, over 7165.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.02921, over 1426470.46 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:50:11,057 INFO [train.py:812] (0/8) Epoch 31, batch 2200, loss[loss=0.1285, simple_loss=0.2136, pruned_loss=0.02168, over 7072.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2438, pruned_loss=0.02966, over 1428402.23 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:51:08,604 INFO [train.py:812] (0/8) Epoch 31, batch 2250, loss[loss=0.2098, simple_loss=0.3125, pruned_loss=0.05352, over 7185.00 frames.], tot_loss[loss=0.1525, simple_loss=0.245, pruned_loss=0.03003, over 1427523.31 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:52:08,116 INFO [train.py:812] (0/8) Epoch 31, batch 2300, loss[loss=0.154, simple_loss=0.2357, pruned_loss=0.03617, over 7263.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03013, over 1430094.54 frames.], batch size: 19, lr: 2.51e-04
+2022-05-15 17:53:06,337 INFO [train.py:812] (0/8) Epoch 31, batch 2350, loss[loss=0.1331, simple_loss=0.2215, pruned_loss=0.02236, over 7071.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03017, over 1430828.96 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:53:17,451 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-140000.pt
+2022-05-15 17:54:10,966 INFO [train.py:812] (0/8) Epoch 31, batch 2400, loss[loss=0.132, simple_loss=0.2364, pruned_loss=0.01381, over 7224.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03015, over 1428798.43 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 17:55:08,465 INFO [train.py:812] (0/8) Epoch 31, batch 2450, loss[loss=0.1528, simple_loss=0.2467, pruned_loss=0.02951, over 7234.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2449, pruned_loss=0.03, over 1425321.77 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 17:56:07,150 INFO [train.py:812] (0/8) Epoch 31, batch 2500, loss[loss=0.1444, simple_loss=0.241, pruned_loss=0.02385, over 7331.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.03004, over 1428059.98 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 17:57:05,822 INFO [train.py:812] (0/8) Epoch 31, batch 2550, loss[loss=0.1697, simple_loss=0.2635, pruned_loss=0.03792, over 7177.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.02999, over 1429657.83 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:58:14,109 INFO [train.py:812] (0/8) Epoch 31, batch 2600, loss[loss=0.1359, simple_loss=0.2263, pruned_loss=0.02276, over 7409.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2447, pruned_loss=0.03058, over 1429086.59 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:59:11,566 INFO [train.py:812] (0/8) Epoch 31, batch 2650, loss[loss=0.1624, simple_loss=0.2673, pruned_loss=0.02869, over 7408.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2451, pruned_loss=0.03056, over 1426143.63 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 18:00:10,462 INFO [train.py:812] (0/8) Epoch 31, batch 2700, loss[loss=0.1828, simple_loss=0.2843, pruned_loss=0.04068, over 7260.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2454, pruned_loss=0.03066, over 1419908.12 frames.], batch size: 25, lr: 2.51e-04
+2022-05-15 18:01:09,744 INFO [train.py:812] (0/8) Epoch 31, batch 2750, loss[loss=0.1543, simple_loss=0.2516, pruned_loss=0.02854, over 7142.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2458, pruned_loss=0.03118, over 1420180.89 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 18:02:08,940 INFO [train.py:812] (0/8) Epoch 31, batch 2800, loss[loss=0.1414, simple_loss=0.238, pruned_loss=0.0224, over 7164.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2458, pruned_loss=0.03121, over 1422082.23 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 18:03:06,853 INFO [train.py:812] (0/8) Epoch 31, batch 2850, loss[loss=0.2201, simple_loss=0.2893, pruned_loss=0.07548, over 7220.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2463, pruned_loss=0.03132, over 1420125.36 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 18:04:06,617 INFO [train.py:812] (0/8) Epoch 31, batch 2900, loss[loss=0.1595, simple_loss=0.2582, pruned_loss=0.03038, over 7123.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2466, pruned_loss=0.03148, over 1424293.28 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 18:05:04,896 INFO [train.py:812] (0/8) Epoch 31, batch 2950, loss[loss=0.1505, simple_loss=0.2536, pruned_loss=0.02371, over 7263.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2464, pruned_loss=0.0311, over 1423703.87 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:06:03,443 INFO [train.py:812] (0/8) Epoch 31, batch 3000, loss[loss=0.1695, simple_loss=0.254, pruned_loss=0.04249, over 7334.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03082, over 1423607.59 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:06:03,444 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 18:06:10,972 INFO [train.py:841] (0/8) Epoch 31, validation: loss=0.1541, simple_loss=0.25, pruned_loss=0.02913, over 698248.00 frames.
+2022-05-15 18:07:09,595 INFO [train.py:812] (0/8) Epoch 31, batch 3050, loss[loss=0.1432, simple_loss=0.225, pruned_loss=0.03071, over 7427.00 frames.], tot_loss[loss=0.154, simple_loss=0.2458, pruned_loss=0.03116, over 1423540.15 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:08:09,147 INFO [train.py:812] (0/8) Epoch 31, batch 3100, loss[loss=0.1718, simple_loss=0.2637, pruned_loss=0.03994, over 7324.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.0307, over 1426548.10 frames.], batch size: 25, lr: 2.50e-04
+2022-05-15 18:09:08,138 INFO [train.py:812] (0/8) Epoch 31, batch 3150, loss[loss=0.1519, simple_loss=0.2366, pruned_loss=0.03355, over 6993.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2442, pruned_loss=0.03072, over 1426132.96 frames.], batch size: 16, lr: 2.50e-04
+2022-05-15 18:10:05,066 INFO [train.py:812] (0/8) Epoch 31, batch 3200, loss[loss=0.16, simple_loss=0.253, pruned_loss=0.03347, over 7203.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.03105, over 1417055.69 frames.], batch size: 23, lr: 2.50e-04
+2022-05-15 18:11:03,067 INFO [train.py:812] (0/8) Epoch 31, batch 3250, loss[loss=0.1633, simple_loss=0.2659, pruned_loss=0.03036, over 7151.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2459, pruned_loss=0.03152, over 1416677.78 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:12:02,652 INFO [train.py:812] (0/8) Epoch 31, batch 3300, loss[loss=0.1316, simple_loss=0.2112, pruned_loss=0.02599, over 7284.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2446, pruned_loss=0.03099, over 1422809.29 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:13:01,585 INFO [train.py:812] (0/8) Epoch 31, batch 3350, loss[loss=0.1327, simple_loss=0.2248, pruned_loss=0.02033, over 7233.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2441, pruned_loss=0.03066, over 1422150.93 frames.], batch size: 21, lr: 2.50e-04
+2022-05-15 18:14:00,862 INFO [train.py:812] (0/8) Epoch 31, batch 3400, loss[loss=0.1739, simple_loss=0.2641, pruned_loss=0.04184, over 7296.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03041, over 1421876.10 frames.], batch size: 25, lr: 2.50e-04
+2022-05-15 18:14:57,854 INFO [train.py:812] (0/8) Epoch 31, batch 3450, loss[loss=0.152, simple_loss=0.258, pruned_loss=0.02297, over 6491.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2443, pruned_loss=0.03051, over 1425945.44 frames.], batch size: 38, lr: 2.50e-04
+2022-05-15 18:15:56,009 INFO [train.py:812] (0/8) Epoch 31, batch 3500, loss[loss=0.1858, simple_loss=0.2751, pruned_loss=0.04824, over 7387.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03013, over 1427105.78 frames.], batch size: 23, lr: 2.50e-04
+2022-05-15 18:16:54,980 INFO [train.py:812] (0/8) Epoch 31, batch 3550, loss[loss=0.1453, simple_loss=0.2289, pruned_loss=0.03084, over 7422.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02984, over 1428391.84 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:17:52,434 INFO [train.py:812] (0/8) Epoch 31, batch 3600, loss[loss=0.1485, simple_loss=0.2406, pruned_loss=0.02825, over 7314.00 frames.], tot_loss[loss=0.1526, simple_loss=0.245, pruned_loss=0.03008, over 1423511.75 frames.], batch size: 24, lr: 2.50e-04
+2022-05-15 18:18:51,246 INFO [train.py:812] (0/8) Epoch 31, batch 3650, loss[loss=0.1382, simple_loss=0.2297, pruned_loss=0.02331, over 7125.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2455, pruned_loss=0.03065, over 1422403.48 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:19:50,478 INFO [train.py:812] (0/8) Epoch 31, batch 3700, loss[loss=0.1199, simple_loss=0.2048, pruned_loss=0.01748, over 7289.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2442, pruned_loss=0.03034, over 1424876.12 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:20:49,307 INFO [train.py:812] (0/8) Epoch 31, batch 3750, loss[loss=0.1427, simple_loss=0.2296, pruned_loss=0.02791, over 7263.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2443, pruned_loss=0.03064, over 1423324.45 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:21:49,356 INFO [train.py:812] (0/8) Epoch 31, batch 3800, loss[loss=0.1415, simple_loss=0.2267, pruned_loss=0.02812, over 7258.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2445, pruned_loss=0.03053, over 1425516.27 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:22:47,385 INFO [train.py:812] (0/8) Epoch 31, batch 3850, loss[loss=0.1442, simple_loss=0.2416, pruned_loss=0.02345, over 7070.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2449, pruned_loss=0.03073, over 1425102.58 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:23:45,784 INFO [train.py:812] (0/8) Epoch 31, batch 3900, loss[loss=0.1576, simple_loss=0.256, pruned_loss=0.02958, over 7287.00 frames.], tot_loss[loss=0.153, simple_loss=0.2447, pruned_loss=0.0306, over 1428804.56 frames.], batch size: 24, lr: 2.50e-04
+2022-05-15 18:24:43,601 INFO [train.py:812] (0/8) Epoch 31, batch 3950, loss[loss=0.1504, simple_loss=0.2327, pruned_loss=0.03409, over 7358.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2443, pruned_loss=0.03056, over 1429165.97 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:25:41,716 INFO [train.py:812] (0/8) Epoch 31, batch 4000, loss[loss=0.1246, simple_loss=0.2154, pruned_loss=0.0169, over 7161.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03082, over 1426824.63 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:26:41,004 INFO [train.py:812] (0/8) Epoch 31, batch 4050, loss[loss=0.1718, simple_loss=0.2531, pruned_loss=0.04524, over 7317.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2456, pruned_loss=0.0308, over 1426086.10 frames.], batch size: 24, lr: 2.49e-04
+2022-05-15 18:27:40,591 INFO [train.py:812] (0/8) Epoch 31, batch 4100, loss[loss=0.1463, simple_loss=0.2424, pruned_loss=0.02507, over 7172.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2457, pruned_loss=0.03071, over 1427610.86 frames.], batch size: 19, lr: 2.49e-04
+2022-05-15 18:28:39,594 INFO [train.py:812] (0/8) Epoch 31, batch 4150, loss[loss=0.1733, simple_loss=0.2806, pruned_loss=0.03295, over 7121.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2448, pruned_loss=0.03022, over 1429514.14 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:29:38,563 INFO [train.py:812] (0/8) Epoch 31, batch 4200, loss[loss=0.1114, simple_loss=0.1912, pruned_loss=0.01582, over 6800.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.03009, over 1430304.41 frames.], batch size: 15, lr: 2.49e-04
+2022-05-15 18:30:36,492 INFO [train.py:812] (0/8) Epoch 31, batch 4250, loss[loss=0.1639, simple_loss=0.2533, pruned_loss=0.03728, over 7159.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2439, pruned_loss=0.02998, over 1427397.03 frames.], batch size: 26, lr: 2.49e-04
+2022-05-15 18:31:35,774 INFO [train.py:812] (0/8) Epoch 31, batch 4300, loss[loss=0.1717, simple_loss=0.2664, pruned_loss=0.03853, over 7299.00 frames.], tot_loss[loss=0.1513, simple_loss=0.243, pruned_loss=0.02978, over 1430244.26 frames.], batch size: 24, lr: 2.49e-04
+2022-05-15 18:32:33,483 INFO [train.py:812] (0/8) Epoch 31, batch 4350, loss[loss=0.15, simple_loss=0.2537, pruned_loss=0.02311, over 7101.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2437, pruned_loss=0.02997, over 1421595.43 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:33:32,236 INFO [train.py:812] (0/8) Epoch 31, batch 4400, loss[loss=0.142, simple_loss=0.2447, pruned_loss=0.01972, over 7108.00 frames.], tot_loss[loss=0.1522, simple_loss=0.244, pruned_loss=0.03017, over 1411606.20 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:34:30,881 INFO [train.py:812] (0/8) Epoch 31, batch 4450, loss[loss=0.167, simple_loss=0.2584, pruned_loss=0.03777, over 6275.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2445, pruned_loss=0.03054, over 1410293.19 frames.], batch size: 37, lr: 2.49e-04
+2022-05-15 18:35:30,062 INFO [train.py:812] (0/8) Epoch 31, batch 4500, loss[loss=0.1511, simple_loss=0.2457, pruned_loss=0.02826, over 6292.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.03107, over 1387066.70 frames.], batch size: 37, lr: 2.49e-04
+2022-05-15 18:36:28,937 INFO [train.py:812] (0/8) Epoch 31, batch 4550, loss[loss=0.1681, simple_loss=0.2638, pruned_loss=0.0362, over 4962.00 frames.], tot_loss[loss=0.156, simple_loss=0.2478, pruned_loss=0.03214, over 1357738.12 frames.], batch size: 53, lr: 2.49e-04
+2022-05-15 18:37:15,025 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-31.pt
+2022-05-15 18:37:36,638 INFO [train.py:812] (0/8) Epoch 32, batch 0, loss[loss=0.1537, simple_loss=0.2597, pruned_loss=0.02384, over 5112.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2597, pruned_loss=0.02384, over 5112.00 frames.], batch size: 52, lr: 2.45e-04
+2022-05-15 18:38:34,878 INFO [train.py:812] (0/8) Epoch 32, batch 50, loss[loss=0.1438, simple_loss=0.2361, pruned_loss=0.02575, over 6522.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2496, pruned_loss=0.02982, over 319908.04 frames.], batch size: 38, lr: 2.45e-04
+2022-05-15 18:39:33,412 INFO [train.py:812] (0/8) Epoch 32, batch 100, loss[loss=0.1479, simple_loss=0.2402, pruned_loss=0.02778, over 7303.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2462, pruned_loss=0.03009, over 566265.88 frames.], batch size: 25, lr: 2.45e-04
+2022-05-15 18:40:32,475 INFO [train.py:812] (0/8) Epoch 32, batch 150, loss[loss=0.1416, simple_loss=0.2379, pruned_loss=0.02261, over 7156.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2451, pruned_loss=0.03014, over 757687.06 frames.], batch size: 26, lr: 2.45e-04
+2022-05-15 18:41:31,067 INFO [train.py:812] (0/8) Epoch 32, batch 200, loss[loss=0.1266, simple_loss=0.2167, pruned_loss=0.01829, over 6981.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.02977, over 902588.09 frames.], batch size: 16, lr: 2.45e-04
+2022-05-15 18:42:29,419 INFO [train.py:812] (0/8) Epoch 32, batch 250, loss[loss=0.1513, simple_loss=0.2496, pruned_loss=0.02651, over 7290.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2449, pruned_loss=0.02991, over 1022537.45 frames.], batch size: 24, lr: 2.45e-04
+2022-05-15 18:43:28,992 INFO [train.py:812] (0/8) Epoch 32, batch 300, loss[loss=0.18, simple_loss=0.262, pruned_loss=0.04897, over 7288.00 frames.], tot_loss[loss=0.153, simple_loss=0.2452, pruned_loss=0.03041, over 1113242.89 frames.], batch size: 24, lr: 2.45e-04
+2022-05-15 18:44:28,380 INFO [train.py:812] (0/8) Epoch 32, batch 350, loss[loss=0.1529, simple_loss=0.2486, pruned_loss=0.02862, over 7039.00 frames.], tot_loss[loss=0.152, simple_loss=0.2443, pruned_loss=0.02984, over 1181086.07 frames.], batch size: 28, lr: 2.45e-04
+2022-05-15 18:45:27,137 INFO [train.py:812] (0/8) Epoch 32, batch 400, loss[loss=0.1532, simple_loss=0.2496, pruned_loss=0.02839, over 7209.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.03004, over 1237155.15 frames.], batch size: 26, lr: 2.45e-04
+2022-05-15 18:46:25,914 INFO [train.py:812] (0/8) Epoch 32, batch 450, loss[loss=0.1652, simple_loss=0.266, pruned_loss=0.03222, over 7313.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.03014, over 1277938.95 frames.], batch size: 21, lr: 2.45e-04
+2022-05-15 18:47:25,082 INFO [train.py:812] (0/8) Epoch 32, batch 500, loss[loss=0.1586, simple_loss=0.2483, pruned_loss=0.03449, over 7322.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2437, pruned_loss=0.02984, over 1313639.61 frames.], batch size: 22, lr: 2.45e-04
+2022-05-15 18:48:23,149 INFO [train.py:812] (0/8) Epoch 32, batch 550, loss[loss=0.1487, simple_loss=0.2519, pruned_loss=0.02276, over 7331.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2444, pruned_loss=0.03017, over 1341519.68 frames.], batch size: 22, lr: 2.45e-04
+2022-05-15 18:49:22,850 INFO [train.py:812] (0/8) Epoch 32, batch 600, loss[loss=0.1322, simple_loss=0.2089, pruned_loss=0.02778, over 7150.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.02997, over 1364200.87 frames.], batch size: 17, lr: 2.45e-04
+2022-05-15 18:50:21,227 INFO [train.py:812] (0/8) Epoch 32, batch 650, loss[loss=0.1169, simple_loss=0.2, pruned_loss=0.01692, over 6998.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2435, pruned_loss=0.02979, over 1380085.74 frames.], batch size: 16, lr: 2.45e-04
+2022-05-15 18:51:18,894 INFO [train.py:812] (0/8) Epoch 32, batch 700, loss[loss=0.1484, simple_loss=0.237, pruned_loss=0.02988, over 7202.00 frames.], tot_loss[loss=0.152, simple_loss=0.2439, pruned_loss=0.03003, over 1387803.98 frames.], batch size: 23, lr: 2.45e-04
+2022-05-15 18:52:17,786 INFO [train.py:812] (0/8) Epoch 32, batch 750, loss[loss=0.1616, simple_loss=0.259, pruned_loss=0.03211, over 7116.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.0297, over 1395602.64 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 18:53:17,311 INFO [train.py:812] (0/8) Epoch 32, batch 800, loss[loss=0.2052, simple_loss=0.2718, pruned_loss=0.06936, over 7281.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.0299, over 1401134.01 frames.], batch size: 18, lr: 2.44e-04
+2022-05-15 18:54:15,838 INFO [train.py:812] (0/8) Epoch 32, batch 850, loss[loss=0.1915, simple_loss=0.2793, pruned_loss=0.05181, over 7305.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2446, pruned_loss=0.03004, over 1407917.56 frames.], batch size: 25, lr: 2.44e-04
+2022-05-15 18:55:14,220 INFO [train.py:812] (0/8) Epoch 32, batch 900, loss[loss=0.1421, simple_loss=0.2391, pruned_loss=0.02261, over 7344.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2458, pruned_loss=0.03025, over 1410214.55 frames.], batch size: 22, lr: 2.44e-04
+2022-05-15 18:56:22,080 INFO [train.py:812] (0/8) Epoch 32, batch 950, loss[loss=0.1473, simple_loss=0.2275, pruned_loss=0.03358, over 6842.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2443, pruned_loss=0.03008, over 1411595.38 frames.], batch size: 15, lr: 2.44e-04
+2022-05-15 18:57:31,120 INFO [train.py:812] (0/8) Epoch 32, batch 1000, loss[loss=0.15, simple_loss=0.2304, pruned_loss=0.03484, over 7423.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.03004, over 1416069.83 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 18:58:30,369 INFO [train.py:812] (0/8) Epoch 32, batch 1050, loss[loss=0.1505, simple_loss=0.2462, pruned_loss=0.02747, over 7244.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.03037, over 1419780.77 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 18:59:29,293 INFO [train.py:812] (0/8) Epoch 32, batch 1100, loss[loss=0.158, simple_loss=0.2519, pruned_loss=0.03206, over 7193.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2437, pruned_loss=0.03007, over 1417930.11 frames.], batch size: 22, lr: 2.44e-04
+2022-05-15 19:00:36,803 INFO [train.py:812] (0/8) Epoch 32, batch 1150, loss[loss=0.1226, simple_loss=0.21, pruned_loss=0.01766, over 7149.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.03017, over 1421598.20 frames.], batch size: 17, lr: 2.44e-04
+2022-05-15 19:01:36,554 INFO [train.py:812] (0/8) Epoch 32, batch 1200, loss[loss=0.1616, simple_loss=0.2651, pruned_loss=0.02906, over 7407.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.0298, over 1424317.51 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:02:45,179 INFO [train.py:812] (0/8) Epoch 32, batch 1250, loss[loss=0.1644, simple_loss=0.2561, pruned_loss=0.0364, over 7197.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.03003, over 1417497.79 frames.], batch size: 23, lr: 2.44e-04
+2022-05-15 19:03:53,733 INFO [train.py:812] (0/8) Epoch 32, batch 1300, loss[loss=0.1571, simple_loss=0.2509, pruned_loss=0.03159, over 7143.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03009, over 1422964.77 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:05:00,940 INFO [train.py:812] (0/8) Epoch 32, batch 1350, loss[loss=0.1423, simple_loss=0.2337, pruned_loss=0.02543, over 7336.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02979, over 1421833.20 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:05:59,799 INFO [train.py:812] (0/8) Epoch 32, batch 1400, loss[loss=0.1397, simple_loss=0.2284, pruned_loss=0.02546, over 7229.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2427, pruned_loss=0.02991, over 1422362.13 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:06:57,259 INFO [train.py:812] (0/8) Epoch 32, batch 1450, loss[loss=0.1268, simple_loss=0.2231, pruned_loss=0.01523, over 7333.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.03026, over 1423944.91 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:08:05,679 INFO [train.py:812] (0/8) Epoch 32, batch 1500, loss[loss=0.1791, simple_loss=0.2612, pruned_loss=0.04851, over 5263.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2426, pruned_loss=0.02995, over 1422767.29 frames.], batch size: 52, lr: 2.44e-04
+2022-05-15 19:09:04,126 INFO [train.py:812] (0/8) Epoch 32, batch 1550, loss[loss=0.1402, simple_loss=0.2237, pruned_loss=0.02834, over 7416.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2425, pruned_loss=0.02989, over 1422460.46 frames.], batch size: 18, lr: 2.44e-04
+2022-05-15 19:10:03,423 INFO [train.py:812] (0/8) Epoch 32, batch 1600, loss[loss=0.189, simple_loss=0.2771, pruned_loss=0.05043, over 7212.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.03, over 1418850.87 frames.], batch size: 23, lr: 2.44e-04
+2022-05-15 19:11:01,564 INFO [train.py:812] (0/8) Epoch 32, batch 1650, loss[loss=0.1459, simple_loss=0.2476, pruned_loss=0.02215, over 7404.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03017, over 1417806.10 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:12:00,756 INFO [train.py:812] (0/8) Epoch 32, batch 1700, loss[loss=0.1569, simple_loss=0.2596, pruned_loss=0.02714, over 7101.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2439, pruned_loss=0.03022, over 1413662.17 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:12:59,769 INFO [train.py:812] (0/8) Epoch 32, batch 1750, loss[loss=0.1883, simple_loss=0.2605, pruned_loss=0.05806, over 4664.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2435, pruned_loss=0.03002, over 1410524.59 frames.], batch size: 52, lr: 2.44e-04
+2022-05-15 19:13:25,088 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-144000.pt
+2022-05-15 19:14:04,601 INFO [train.py:812] (0/8) Epoch 32, batch 1800, loss[loss=0.1621, simple_loss=0.2589, pruned_loss=0.03262, over 7230.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03033, over 1411812.88 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:15:03,153 INFO [train.py:812] (0/8) Epoch 32, batch 1850, loss[loss=0.1374, simple_loss=0.2224, pruned_loss=0.02619, over 7004.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03025, over 1405913.84 frames.], batch size: 16, lr: 2.44e-04
+2022-05-15 19:16:02,084 INFO [train.py:812] (0/8) Epoch 32, batch 1900, loss[loss=0.1496, simple_loss=0.2387, pruned_loss=0.03028, over 7362.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2437, pruned_loss=0.03, over 1412932.99 frames.], batch size: 19, lr: 2.44e-04
+2022-05-15 19:17:00,596 INFO [train.py:812] (0/8) Epoch 32, batch 1950, loss[loss=0.1498, simple_loss=0.2353, pruned_loss=0.03218, over 7348.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02985, over 1418975.93 frames.], batch size: 19, lr: 2.43e-04
+2022-05-15 19:18:00,431 INFO [train.py:812] (0/8) Epoch 32, batch 2000, loss[loss=0.1375, simple_loss=0.2289, pruned_loss=0.02307, over 7284.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02985, over 1419786.03 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:18:57,506 INFO [train.py:812] (0/8) Epoch 32, batch 2050, loss[loss=0.163, simple_loss=0.2776, pruned_loss=0.02421, over 7139.00 frames.], tot_loss[loss=0.1526, simple_loss=0.245, pruned_loss=0.03006, over 1416130.87 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:19:56,214 INFO [train.py:812] (0/8) Epoch 32, batch 2100, loss[loss=0.1282, simple_loss=0.2147, pruned_loss=0.02088, over 7232.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2462, pruned_loss=0.03049, over 1416394.37 frames.], batch size: 16, lr: 2.43e-04
+2022-05-15 19:20:54,967 INFO [train.py:812] (0/8) Epoch 32, batch 2150, loss[loss=0.1506, simple_loss=0.2521, pruned_loss=0.02459, over 7220.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2462, pruned_loss=0.03044, over 1420745.76 frames.], batch size: 21, lr: 2.43e-04
+2022-05-15 19:21:53,672 INFO [train.py:812] (0/8) Epoch 32, batch 2200, loss[loss=0.1668, simple_loss=0.2575, pruned_loss=0.03803, over 7134.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2451, pruned_loss=0.03018, over 1423498.81 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:22:52,822 INFO [train.py:812] (0/8) Epoch 32, batch 2250, loss[loss=0.1326, simple_loss=0.2216, pruned_loss=0.02177, over 7071.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2444, pruned_loss=0.02984, over 1424209.14 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:23:52,311 INFO [train.py:812] (0/8) Epoch 32, batch 2300, loss[loss=0.1383, simple_loss=0.236, pruned_loss=0.02036, over 7347.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02995, over 1421348.06 frames.], batch size: 22, lr: 2.43e-04
+2022-05-15 19:24:49,709 INFO [train.py:812] (0/8) Epoch 32, batch 2350, loss[loss=0.1297, simple_loss=0.2081, pruned_loss=0.02566, over 7299.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03029, over 1424938.42 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:25:48,453 INFO [train.py:812] (0/8) Epoch 32, batch 2400, loss[loss=0.1512, simple_loss=0.2465, pruned_loss=0.02794, over 7326.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2447, pruned_loss=0.03044, over 1420395.53 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:26:47,723 INFO [train.py:812] (0/8) Epoch 32, batch 2450, loss[loss=0.1739, simple_loss=0.2822, pruned_loss=0.0328, over 7176.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03047, over 1421453.17 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:27:46,278 INFO [train.py:812] (0/8) Epoch 32, batch 2500, loss[loss=0.1434, simple_loss=0.2256, pruned_loss=0.03059, over 7283.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.03011, over 1424304.29 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:28:44,152 INFO [train.py:812] (0/8) Epoch 32, batch 2550, loss[loss=0.1178, simple_loss=0.2158, pruned_loss=0.009942, over 7314.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02988, over 1422176.93 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:29:41,342 INFO [train.py:812] (0/8) Epoch 32, batch 2600, loss[loss=0.1263, simple_loss=0.2114, pruned_loss=0.02059, over 7144.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2436, pruned_loss=0.02992, over 1421383.78 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:30:39,820 INFO [train.py:812] (0/8) Epoch 32, batch 2650, loss[loss=0.1671, simple_loss=0.2679, pruned_loss=0.03314, over 7147.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02975, over 1423765.58 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:31:39,427 INFO [train.py:812] (0/8) Epoch 32, batch 2700, loss[loss=0.1542, simple_loss=0.2456, pruned_loss=0.03141, over 7329.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02984, over 1422516.28 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:32:37,295 INFO [train.py:812] (0/8) Epoch 32, batch 2750, loss[loss=0.1686, simple_loss=0.2639, pruned_loss=0.03664, over 7159.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2436, pruned_loss=0.02967, over 1425153.39 frames.], batch size: 28, lr: 2.43e-04
+2022-05-15 19:33:35,467 INFO [train.py:812] (0/8) Epoch 32, batch 2800, loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.03553, over 7425.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02982, over 1424098.97 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:34:34,358 INFO [train.py:812] (0/8) Epoch 32, batch 2850, loss[loss=0.1601, simple_loss=0.2666, pruned_loss=0.02683, over 6372.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2433, pruned_loss=0.02995, over 1421294.58 frames.], batch size: 38, lr: 2.43e-04
+2022-05-15 19:35:32,673 INFO [train.py:812] (0/8) Epoch 32, batch 2900, loss[loss=0.1469, simple_loss=0.2417, pruned_loss=0.02607, over 7222.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.02996, over 1425759.51 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:36:30,932 INFO [train.py:812] (0/8) Epoch 32, batch 2950, loss[loss=0.1668, simple_loss=0.2607, pruned_loss=0.03648, over 7198.00 frames.], tot_loss[loss=0.153, simple_loss=0.245, pruned_loss=0.03045, over 1419463.34 frames.], batch size: 23, lr: 2.43e-04
+2022-05-15 19:37:29,686 INFO [train.py:812] (0/8) Epoch 32, batch 3000, loss[loss=0.1618, simple_loss=0.2611, pruned_loss=0.03123, over 7424.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2452, pruned_loss=0.03047, over 1420081.76 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:37:29,687 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 19:37:37,094 INFO [train.py:841] (0/8) Epoch 32, validation: loss=0.1532, simple_loss=0.2494, pruned_loss=0.02852, over 698248.00 frames.
+2022-05-15 19:38:35,486 INFO [train.py:812] (0/8) Epoch 32, batch 3050, loss[loss=0.1722, simple_loss=0.2778, pruned_loss=0.03335, over 7263.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2447, pruned_loss=0.03044, over 1423802.53 frames.], batch size: 25, lr: 2.43e-04
+2022-05-15 19:39:34,740 INFO [train.py:812] (0/8) Epoch 32, batch 3100, loss[loss=0.1748, simple_loss=0.2741, pruned_loss=0.03775, over 7005.00 frames.], tot_loss[loss=0.1532, simple_loss=0.245, pruned_loss=0.03066, over 1426747.56 frames.], batch size: 28, lr: 2.42e-04
+2022-05-15 19:40:34,128 INFO [train.py:812] (0/8) Epoch 32, batch 3150, loss[loss=0.1412, simple_loss=0.2251, pruned_loss=0.02865, over 7282.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2443, pruned_loss=0.03064, over 1423851.34 frames.], batch size: 17, lr: 2.42e-04
+2022-05-15 19:41:32,537 INFO [train.py:812] (0/8) Epoch 32, batch 3200, loss[loss=0.1334, simple_loss=0.2303, pruned_loss=0.01824, over 7110.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03062, over 1426620.01 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:42:31,695 INFO [train.py:812] (0/8) Epoch 32, batch 3250, loss[loss=0.1439, simple_loss=0.2356, pruned_loss=0.02607, over 7339.00 frames.], tot_loss[loss=0.153, simple_loss=0.2451, pruned_loss=0.03049, over 1427079.74 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 19:43:31,328 INFO [train.py:812] (0/8) Epoch 32, batch 3300, loss[loss=0.1456, simple_loss=0.2435, pruned_loss=0.02389, over 7435.00 frames.], tot_loss[loss=0.153, simple_loss=0.2447, pruned_loss=0.03062, over 1423190.74 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:44:30,445 INFO [train.py:812] (0/8) Epoch 32, batch 3350, loss[loss=0.1531, simple_loss=0.2475, pruned_loss=0.02934, over 7322.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2441, pruned_loss=0.03062, over 1424293.09 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:45:29,619 INFO [train.py:812] (0/8) Epoch 32, batch 3400, loss[loss=0.1339, simple_loss=0.2243, pruned_loss=0.02178, over 7326.00 frames.], tot_loss[loss=0.153, simple_loss=0.2448, pruned_loss=0.03053, over 1421604.93 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:46:27,579 INFO [train.py:812] (0/8) Epoch 32, batch 3450, loss[loss=0.1623, simple_loss=0.2557, pruned_loss=0.0345, over 7206.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2449, pruned_loss=0.03031, over 1424225.39 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 19:47:26,349 INFO [train.py:812] (0/8) Epoch 32, batch 3500, loss[loss=0.1577, simple_loss=0.2549, pruned_loss=0.03027, over 7285.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2452, pruned_loss=0.03025, over 1427833.89 frames.], batch size: 24, lr: 2.42e-04
+2022-05-15 19:48:25,210 INFO [train.py:812] (0/8) Epoch 32, batch 3550, loss[loss=0.16, simple_loss=0.2503, pruned_loss=0.03488, over 7391.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03066, over 1430682.29 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:49:24,689 INFO [train.py:812] (0/8) Epoch 32, batch 3600, loss[loss=0.1493, simple_loss=0.245, pruned_loss=0.02682, over 6382.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2443, pruned_loss=0.03043, over 1427928.50 frames.], batch size: 38, lr: 2.42e-04
+2022-05-15 19:50:24,026 INFO [train.py:812] (0/8) Epoch 32, batch 3650, loss[loss=0.1491, simple_loss=0.2473, pruned_loss=0.0255, over 7234.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2449, pruned_loss=0.03045, over 1428243.15 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:51:24,139 INFO [train.py:812] (0/8) Epoch 32, batch 3700, loss[loss=0.1377, simple_loss=0.2163, pruned_loss=0.02957, over 7133.00 frames.], tot_loss[loss=0.1522, simple_loss=0.244, pruned_loss=0.03019, over 1430354.72 frames.], batch size: 17, lr: 2.42e-04
+2022-05-15 19:52:22,799 INFO [train.py:812] (0/8) Epoch 32, batch 3750, loss[loss=0.1645, simple_loss=0.2517, pruned_loss=0.03866, over 7223.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2445, pruned_loss=0.0303, over 1423965.26 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:53:21,694 INFO [train.py:812] (0/8) Epoch 32, batch 3800, loss[loss=0.1752, simple_loss=0.2693, pruned_loss=0.04053, over 7376.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.02998, over 1425866.13 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:54:19,349 INFO [train.py:812] (0/8) Epoch 32, batch 3850, loss[loss=0.1795, simple_loss=0.2724, pruned_loss=0.04325, over 7424.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2447, pruned_loss=0.03006, over 1428092.54 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:55:27,957 INFO [train.py:812] (0/8) Epoch 32, batch 3900, loss[loss=0.1645, simple_loss=0.242, pruned_loss=0.04351, over 7173.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2444, pruned_loss=0.02991, over 1429338.17 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 19:56:25,390 INFO [train.py:812] (0/8) Epoch 32, batch 3950, loss[loss=0.1597, simple_loss=0.2584, pruned_loss=0.03055, over 7219.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2448, pruned_loss=0.03041, over 1424316.23 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:57:24,488 INFO [train.py:812] (0/8) Epoch 32, batch 4000, loss[loss=0.1369, simple_loss=0.2266, pruned_loss=0.02362, over 7409.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.0301, over 1422138.74 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 19:58:22,816 INFO [train.py:812] (0/8) Epoch 32, batch 4050, loss[loss=0.2061, simple_loss=0.2988, pruned_loss=0.05671, over 7388.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03012, over 1419835.07 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:59:20,908 INFO [train.py:812] (0/8) Epoch 32, batch 4100, loss[loss=0.174, simple_loss=0.2609, pruned_loss=0.04357, over 7218.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2444, pruned_loss=0.03034, over 1417715.94 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 20:00:19,815 INFO [train.py:812] (0/8) Epoch 32, batch 4150, loss[loss=0.1725, simple_loss=0.2658, pruned_loss=0.03963, over 7223.00 frames.], tot_loss[loss=0.153, simple_loss=0.2448, pruned_loss=0.03063, over 1421471.65 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 20:01:19,538 INFO [train.py:812] (0/8) Epoch 32, batch 4200, loss[loss=0.1403, simple_loss=0.2305, pruned_loss=0.02507, over 7324.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2435, pruned_loss=0.03068, over 1421177.52 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 20:02:17,890 INFO [train.py:812] (0/8) Epoch 32, batch 4250, loss[loss=0.1464, simple_loss=0.2341, pruned_loss=0.0293, over 7250.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2436, pruned_loss=0.03051, over 1419381.53 frames.], batch size: 19, lr: 2.42e-04
+2022-05-15 20:03:17,479 INFO [train.py:812] (0/8) Epoch 32, batch 4300, loss[loss=0.1515, simple_loss=0.2361, pruned_loss=0.03346, over 7416.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2434, pruned_loss=0.03054, over 1418818.87 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 20:04:16,090 INFO [train.py:812] (0/8) Epoch 32, batch 4350, loss[loss=0.137, simple_loss=0.2202, pruned_loss=0.02692, over 7182.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2442, pruned_loss=0.03084, over 1419161.71 frames.], batch size: 18, lr: 2.41e-04
+2022-05-15 20:05:14,957 INFO [train.py:812] (0/8) Epoch 32, batch 4400, loss[loss=0.1763, simple_loss=0.2743, pruned_loss=0.03915, over 7264.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2447, pruned_loss=0.03101, over 1405462.31 frames.], batch size: 25, lr: 2.41e-04
+2022-05-15 20:06:12,562 INFO [train.py:812] (0/8) Epoch 32, batch 4450, loss[loss=0.1369, simple_loss=0.2182, pruned_loss=0.02781, over 7206.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2446, pruned_loss=0.03085, over 1402893.66 frames.], batch size: 16, lr: 2.41e-04
+2022-05-15 20:07:11,390 INFO [train.py:812] (0/8) Epoch 32, batch 4500, loss[loss=0.1509, simple_loss=0.25, pruned_loss=0.02585, over 6675.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03072, over 1395961.88 frames.], batch size: 31, lr: 2.41e-04
+2022-05-15 20:08:09,895 INFO [train.py:812] (0/8) Epoch 32, batch 4550, loss[loss=0.1722, simple_loss=0.2602, pruned_loss=0.0421, over 5220.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2451, pruned_loss=0.03136, over 1358016.40 frames.], batch size: 52, lr: 2.41e-04
+2022-05-15 20:08:54,176 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-32.pt
+2022-05-15 20:09:17,615 INFO [train.py:812] (0/8) Epoch 33, batch 0, loss[loss=0.1558, simple_loss=0.2523, pruned_loss=0.02971, over 6741.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2523, pruned_loss=0.02971, over 6741.00 frames.], batch size: 31, lr: 2.38e-04
+2022-05-15 20:10:15,666 INFO [train.py:812] (0/8) Epoch 33, batch 50, loss[loss=0.1631, simple_loss=0.2491, pruned_loss=0.03852, over 5098.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.03019, over 313831.21 frames.], batch size: 52, lr: 2.38e-04
+2022-05-15 20:11:14,515 INFO [train.py:812] (0/8) Epoch 33, batch 100, loss[loss=0.1608, simple_loss=0.2462, pruned_loss=0.03772, over 6285.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2448, pruned_loss=0.03076, over 558728.88 frames.], batch size: 37, lr: 2.38e-04
+2022-05-15 20:12:13,237 INFO [train.py:812] (0/8) Epoch 33, batch 150, loss[loss=0.1556, simple_loss=0.248, pruned_loss=0.03162, over 7197.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2458, pruned_loss=0.03036, over 750791.88 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:13:12,819 INFO [train.py:812] (0/8) Epoch 33, batch 200, loss[loss=0.134, simple_loss=0.2134, pruned_loss=0.0273, over 7000.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.03018, over 894134.69 frames.], batch size: 16, lr: 2.37e-04
+2022-05-15 20:14:10,197 INFO [train.py:812] (0/8) Epoch 33, batch 250, loss[loss=0.1481, simple_loss=0.242, pruned_loss=0.02705, over 7247.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03033, over 1009508.31 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:15:08,980 INFO [train.py:812] (0/8) Epoch 33, batch 300, loss[loss=0.1762, simple_loss=0.2887, pruned_loss=0.03187, over 6751.00 frames.], tot_loss[loss=0.154, simple_loss=0.2462, pruned_loss=0.03089, over 1092255.37 frames.], batch size: 31, lr: 2.37e-04
+2022-05-15 20:16:07,546 INFO [train.py:812] (0/8) Epoch 33, batch 350, loss[loss=0.1254, simple_loss=0.2114, pruned_loss=0.01964, over 7417.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2465, pruned_loss=0.03131, over 1163190.95 frames.], batch size: 18, lr: 2.37e-04
+2022-05-15 20:17:07,049 INFO [train.py:812] (0/8) Epoch 33, batch 400, loss[loss=0.1471, simple_loss=0.2329, pruned_loss=0.03067, over 7431.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2452, pruned_loss=0.03119, over 1219744.68 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:18:06,463 INFO [train.py:812] (0/8) Epoch 33, batch 450, loss[loss=0.1622, simple_loss=0.2537, pruned_loss=0.03536, over 6815.00 frames.], tot_loss[loss=0.153, simple_loss=0.2443, pruned_loss=0.03081, over 1261878.63 frames.], batch size: 31, lr: 2.37e-04
+2022-05-15 20:19:06,074 INFO [train.py:812] (0/8) Epoch 33, batch 500, loss[loss=0.1706, simple_loss=0.2523, pruned_loss=0.04444, over 7207.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2448, pruned_loss=0.03081, over 1300162.90 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:20:04,283 INFO [train.py:812] (0/8) Epoch 33, batch 550, loss[loss=0.1698, simple_loss=0.2627, pruned_loss=0.03847, over 7324.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2461, pruned_loss=0.03087, over 1328877.61 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:21:03,109 INFO [train.py:812] (0/8) Epoch 33, batch 600, loss[loss=0.1751, simple_loss=0.2666, pruned_loss=0.04183, over 7269.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2458, pruned_loss=0.03092, over 1346452.33 frames.], batch size: 24, lr: 2.37e-04
+2022-05-15 20:22:00,739 INFO [train.py:812] (0/8) Epoch 33, batch 650, loss[loss=0.1768, simple_loss=0.2692, pruned_loss=0.04221, over 7171.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2459, pruned_loss=0.03098, over 1363733.24 frames.], batch size: 26, lr: 2.37e-04
+2022-05-15 20:23:00,265 INFO [train.py:812] (0/8) Epoch 33, batch 700, loss[loss=0.1542, simple_loss=0.2355, pruned_loss=0.03648, over 7143.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2456, pruned_loss=0.0309, over 1374294.95 frames.], batch size: 17, lr: 2.37e-04
+2022-05-15 20:23:58,663 INFO [train.py:812] (0/8) Epoch 33, batch 750, loss[loss=0.147, simple_loss=0.2542, pruned_loss=0.01991, over 7231.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03077, over 1380426.75 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:24:57,996 INFO [train.py:812] (0/8) Epoch 33, batch 800, loss[loss=0.1453, simple_loss=0.233, pruned_loss=0.02877, over 7435.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2444, pruned_loss=0.03054, over 1391823.55 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:25:55,964 INFO [train.py:812] (0/8) Epoch 33, batch 850, loss[loss=0.1529, simple_loss=0.2497, pruned_loss=0.02809, over 7378.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03014, over 1399469.90 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:26:54,544 INFO [train.py:812] (0/8) Epoch 33, batch 900, loss[loss=0.1575, simple_loss=0.2585, pruned_loss=0.02829, over 7212.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2429, pruned_loss=0.02985, over 1409522.73 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:27:51,780 INFO [train.py:812] (0/8) Epoch 33, batch 950, loss[loss=0.1569, simple_loss=0.244, pruned_loss=0.03489, over 7433.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.02989, over 1414494.86 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:28:51,356 INFO [train.py:812] (0/8) Epoch 33, batch 1000, loss[loss=0.1757, simple_loss=0.2681, pruned_loss=0.04159, over 7210.00 frames.], tot_loss[loss=0.151, simple_loss=0.2426, pruned_loss=0.02967, over 1414583.81 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:29:49,464 INFO [train.py:812] (0/8) Epoch 33, batch 1050, loss[loss=0.1665, simple_loss=0.2545, pruned_loss=0.03927, over 7032.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02964, over 1414077.95 frames.], batch size: 28, lr: 2.37e-04
+2022-05-15 20:30:48,556 INFO [train.py:812] (0/8) Epoch 33, batch 1100, loss[loss=0.1707, simple_loss=0.2679, pruned_loss=0.03677, over 7260.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02965, over 1419000.92 frames.], batch size: 24, lr: 2.37e-04
+2022-05-15 20:31:47,035 INFO [train.py:812] (0/8) Epoch 33, batch 1150, loss[loss=0.1612, simple_loss=0.253, pruned_loss=0.03466, over 7197.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.0298, over 1420549.89 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:32:25,766 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-148000.pt
+2022-05-15 20:32:51,449 INFO [train.py:812] (0/8) Epoch 33, batch 1200, loss[loss=0.1541, simple_loss=0.2558, pruned_loss=0.02615, over 7181.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02991, over 1423082.35 frames.], batch size: 26, lr: 2.37e-04
+2022-05-15 20:33:50,441 INFO [train.py:812] (0/8) Epoch 33, batch 1250, loss[loss=0.1592, simple_loss=0.2542, pruned_loss=0.03206, over 6583.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2444, pruned_loss=0.0299, over 1422535.26 frames.], batch size: 38, lr: 2.37e-04
+2022-05-15 20:34:50,209 INFO [train.py:812] (0/8) Epoch 33, batch 1300, loss[loss=0.1345, simple_loss=0.2409, pruned_loss=0.01406, over 7207.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2426, pruned_loss=0.02959, over 1422606.00 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:35:49,519 INFO [train.py:812] (0/8) Epoch 33, batch 1350, loss[loss=0.1484, simple_loss=0.2396, pruned_loss=0.0286, over 7259.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2433, pruned_loss=0.02985, over 1421530.84 frames.], batch size: 17, lr: 2.37e-04
+2022-05-15 20:36:48,981 INFO [train.py:812] (0/8) Epoch 33, batch 1400, loss[loss=0.1533, simple_loss=0.2522, pruned_loss=0.02718, over 7140.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.0299, over 1423281.01 frames.], batch size: 20, lr: 2.36e-04
+2022-05-15 20:37:47,490 INFO [train.py:812] (0/8) Epoch 33, batch 1450, loss[loss=0.1489, simple_loss=0.2444, pruned_loss=0.02674, over 6834.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2434, pruned_loss=0.02985, over 1425879.27 frames.], batch size: 31, lr: 2.36e-04
+2022-05-15 20:38:46,324 INFO [train.py:812] (0/8) Epoch 33, batch 1500, loss[loss=0.1768, simple_loss=0.2612, pruned_loss=0.04619, over 5112.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.0302, over 1423126.82 frames.], batch size: 52, lr: 2.36e-04
+2022-05-15 20:39:44,929 INFO [train.py:812] (0/8) Epoch 33, batch 1550, loss[loss=0.1673, simple_loss=0.2594, pruned_loss=0.03762, over 7224.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2442, pruned_loss=0.03023, over 1418848.02 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:40:43,835 INFO [train.py:812] (0/8) Epoch 33, batch 1600, loss[loss=0.1623, simple_loss=0.257, pruned_loss=0.03381, over 7419.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2441, pruned_loss=0.03024, over 1420656.56 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:41:42,725 INFO [train.py:812] (0/8) Epoch 33, batch 1650, loss[loss=0.1637, simple_loss=0.252, pruned_loss=0.03769, over 7226.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2437, pruned_loss=0.03007, over 1421547.25 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:42:41,749 INFO [train.py:812] (0/8) Epoch 33, batch 1700, loss[loss=0.1724, simple_loss=0.2628, pruned_loss=0.04099, over 7293.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2442, pruned_loss=0.03019, over 1423535.39 frames.], batch size: 24, lr: 2.36e-04
+2022-05-15 20:43:40,830 INFO [train.py:812] (0/8) Epoch 33, batch 1750, loss[loss=0.1685, simple_loss=0.2646, pruned_loss=0.03619, over 7111.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2446, pruned_loss=0.03044, over 1417331.70 frames.], batch size: 28, lr: 2.36e-04
+2022-05-15 20:44:40,059 INFO [train.py:812] (0/8) Epoch 33, batch 1800, loss[loss=0.1496, simple_loss=0.2384, pruned_loss=0.03043, over 7257.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.03002, over 1420660.93 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:45:38,937 INFO [train.py:812] (0/8) Epoch 33, batch 1850, loss[loss=0.1552, simple_loss=0.2476, pruned_loss=0.03138, over 7314.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03018, over 1423534.14 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:46:37,341 INFO [train.py:812] (0/8) Epoch 33, batch 1900, loss[loss=0.163, simple_loss=0.2596, pruned_loss=0.03321, over 7380.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.0301, over 1425797.30 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 20:47:35,890 INFO [train.py:812] (0/8) Epoch 33, batch 1950, loss[loss=0.1526, simple_loss=0.245, pruned_loss=0.03005, over 7308.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.02997, over 1423951.11 frames.], batch size: 24, lr: 2.36e-04
+2022-05-15 20:48:34,905 INFO [train.py:812] (0/8) Epoch 33, batch 2000, loss[loss=0.1479, simple_loss=0.2484, pruned_loss=0.02371, over 6460.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2444, pruned_loss=0.03034, over 1425405.70 frames.], batch size: 38, lr: 2.36e-04
+2022-05-15 20:49:32,708 INFO [train.py:812] (0/8) Epoch 33, batch 2050, loss[loss=0.1495, simple_loss=0.2358, pruned_loss=0.03166, over 7159.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2442, pruned_loss=0.03015, over 1425809.57 frames.], batch size: 18, lr: 2.36e-04
+2022-05-15 20:50:32,328 INFO [train.py:812] (0/8) Epoch 33, batch 2100, loss[loss=0.1405, simple_loss=0.2322, pruned_loss=0.02437, over 7158.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2436, pruned_loss=0.03026, over 1426507.40 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:51:30,239 INFO [train.py:812] (0/8) Epoch 33, batch 2150, loss[loss=0.1339, simple_loss=0.2207, pruned_loss=0.02353, over 7422.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.03005, over 1427548.67 frames.], batch size: 18, lr: 2.36e-04
+2022-05-15 20:52:28,377 INFO [train.py:812] (0/8) Epoch 33, batch 2200, loss[loss=0.2166, simple_loss=0.2988, pruned_loss=0.06715, over 4828.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2435, pruned_loss=0.03045, over 1421143.81 frames.], batch size: 52, lr: 2.36e-04
+2022-05-15 20:53:26,617 INFO [train.py:812] (0/8) Epoch 33, batch 2250, loss[loss=0.1628, simple_loss=0.2594, pruned_loss=0.03312, over 7184.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2439, pruned_loss=0.03059, over 1419883.62 frames.], batch size: 26, lr: 2.36e-04
+2022-05-15 20:54:25,575 INFO [train.py:812] (0/8) Epoch 33, batch 2300, loss[loss=0.166, simple_loss=0.2619, pruned_loss=0.03506, over 7210.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2438, pruned_loss=0.03068, over 1418613.60 frames.], batch size: 22, lr: 2.36e-04
+2022-05-15 20:55:24,372 INFO [train.py:812] (0/8) Epoch 33, batch 2350, loss[loss=0.1272, simple_loss=0.2094, pruned_loss=0.02244, over 7152.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2425, pruned_loss=0.03005, over 1422149.34 frames.], batch size: 16, lr: 2.36e-04
+2022-05-15 20:56:22,960 INFO [train.py:812] (0/8) Epoch 33, batch 2400, loss[loss=0.1497, simple_loss=0.2473, pruned_loss=0.02604, over 7428.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2424, pruned_loss=0.03003, over 1424729.06 frames.], batch size: 20, lr: 2.36e-04
+2022-05-15 20:57:40,436 INFO [train.py:812] (0/8) Epoch 33, batch 2450, loss[loss=0.1488, simple_loss=0.2323, pruned_loss=0.03263, over 7260.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2424, pruned_loss=0.02967, over 1426233.00 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:58:40,009 INFO [train.py:812] (0/8) Epoch 33, batch 2500, loss[loss=0.1459, simple_loss=0.2519, pruned_loss=0.01994, over 7315.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2421, pruned_loss=0.02939, over 1427980.40 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:59:48,291 INFO [train.py:812] (0/8) Epoch 33, batch 2550, loss[loss=0.1684, simple_loss=0.265, pruned_loss=0.03587, over 7386.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2418, pruned_loss=0.02934, over 1427869.79 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 21:00:46,740 INFO [train.py:812] (0/8) Epoch 33, batch 2600, loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03077, over 7168.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2415, pruned_loss=0.02944, over 1427656.18 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 21:01:44,968 INFO [train.py:812] (0/8) Epoch 33, batch 2650, loss[loss=0.1585, simple_loss=0.2458, pruned_loss=0.03563, over 7173.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2423, pruned_loss=0.02976, over 1423194.94 frames.], batch size: 16, lr: 2.35e-04
+2022-05-15 21:02:52,792 INFO [train.py:812] (0/8) Epoch 33, batch 2700, loss[loss=0.1457, simple_loss=0.2411, pruned_loss=0.02511, over 7438.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2429, pruned_loss=0.02996, over 1424484.75 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:04:10,601 INFO [train.py:812] (0/8) Epoch 33, batch 2750, loss[loss=0.1481, simple_loss=0.241, pruned_loss=0.02765, over 7294.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2443, pruned_loss=0.03041, over 1425574.89 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:05:09,525 INFO [train.py:812] (0/8) Epoch 33, batch 2800, loss[loss=0.1587, simple_loss=0.2448, pruned_loss=0.03624, over 7214.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03014, over 1425334.87 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:06:07,272 INFO [train.py:812] (0/8) Epoch 33, batch 2850, loss[loss=0.1406, simple_loss=0.2383, pruned_loss=0.02139, over 7309.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2434, pruned_loss=0.0299, over 1426505.20 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:07:06,353 INFO [train.py:812] (0/8) Epoch 33, batch 2900, loss[loss=0.1727, simple_loss=0.273, pruned_loss=0.03621, over 7306.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2444, pruned_loss=0.02994, over 1426006.17 frames.], batch size: 25, lr: 2.35e-04
+2022-05-15 21:08:04,493 INFO [train.py:812] (0/8) Epoch 33, batch 2950, loss[loss=0.1488, simple_loss=0.2463, pruned_loss=0.0256, over 7427.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2449, pruned_loss=0.03014, over 1428008.87 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:09:12,260 INFO [train.py:812] (0/8) Epoch 33, batch 3000, loss[loss=0.128, simple_loss=0.2163, pruned_loss=0.01986, over 7081.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2447, pruned_loss=0.03036, over 1426876.95 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:09:12,262 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 21:09:19,691 INFO [train.py:841] (0/8) Epoch 33, validation: loss=0.1535, simple_loss=0.2493, pruned_loss=0.02886, over 698248.00 frames.
+2022-05-15 21:10:18,071 INFO [train.py:812] (0/8) Epoch 33, batch 3050, loss[loss=0.1426, simple_loss=0.2384, pruned_loss=0.02345, over 6418.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02966, over 1423251.64 frames.], batch size: 38, lr: 2.35e-04
+2022-05-15 21:11:15,956 INFO [train.py:812] (0/8) Epoch 33, batch 3100, loss[loss=0.1629, simple_loss=0.266, pruned_loss=0.02992, over 7366.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2433, pruned_loss=0.02971, over 1423313.03 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:12:14,884 INFO [train.py:812] (0/8) Epoch 33, batch 3150, loss[loss=0.1351, simple_loss=0.2247, pruned_loss=0.02276, over 7075.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2423, pruned_loss=0.02946, over 1420689.33 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:13:13,022 INFO [train.py:812] (0/8) Epoch 33, batch 3200, loss[loss=0.1245, simple_loss=0.2059, pruned_loss=0.02157, over 6781.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2424, pruned_loss=0.02951, over 1421081.67 frames.], batch size: 15, lr: 2.35e-04
+2022-05-15 21:14:11,707 INFO [train.py:812] (0/8) Epoch 33, batch 3250, loss[loss=0.141, simple_loss=0.2253, pruned_loss=0.02837, over 7282.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2423, pruned_loss=0.02958, over 1419097.32 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:15:11,742 INFO [train.py:812] (0/8) Epoch 33, batch 3300, loss[loss=0.1439, simple_loss=0.2381, pruned_loss=0.02485, over 7230.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2422, pruned_loss=0.02945, over 1424168.65 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:16:10,449 INFO [train.py:812] (0/8) Epoch 33, batch 3350, loss[loss=0.1535, simple_loss=0.2514, pruned_loss=0.02781, over 7319.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02958, over 1427513.25 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:17:09,948 INFO [train.py:812] (0/8) Epoch 33, batch 3400, loss[loss=0.145, simple_loss=0.2337, pruned_loss=0.02812, over 7288.00 frames.], tot_loss[loss=0.151, simple_loss=0.2427, pruned_loss=0.02969, over 1428195.95 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:18:09,757 INFO [train.py:812] (0/8) Epoch 33, batch 3450, loss[loss=0.1563, simple_loss=0.2479, pruned_loss=0.03238, over 7343.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2436, pruned_loss=0.03005, over 1432598.40 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:19:07,583 INFO [train.py:812] (0/8) Epoch 33, batch 3500, loss[loss=0.1564, simple_loss=0.2524, pruned_loss=0.03024, over 7371.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03018, over 1429727.81 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:20:05,726 INFO [train.py:812] (0/8) Epoch 33, batch 3550, loss[loss=0.1457, simple_loss=0.2375, pruned_loss=0.02694, over 7404.00 frames.], tot_loss[loss=0.152, simple_loss=0.2439, pruned_loss=0.0301, over 1427824.78 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:21:04,471 INFO [train.py:812] (0/8) Epoch 33, batch 3600, loss[loss=0.134, simple_loss=0.2205, pruned_loss=0.02369, over 7334.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.0299, over 1423924.35 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:22:03,597 INFO [train.py:812] (0/8) Epoch 33, batch 3650, loss[loss=0.1613, simple_loss=0.2577, pruned_loss=0.03249, over 7324.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02966, over 1423625.64 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:23:02,536 INFO [train.py:812] (0/8) Epoch 33, batch 3700, loss[loss=0.1314, simple_loss=0.2165, pruned_loss=0.02315, over 7277.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2447, pruned_loss=0.03009, over 1427099.30 frames.], batch size: 17, lr: 2.35e-04
+2022-05-15 21:24:01,168 INFO [train.py:812] (0/8) Epoch 33, batch 3750, loss[loss=0.1426, simple_loss=0.241, pruned_loss=0.02212, over 7225.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.03004, over 1427074.36 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:25:00,787 INFO [train.py:812] (0/8) Epoch 33, batch 3800, loss[loss=0.2142, simple_loss=0.2963, pruned_loss=0.06608, over 7212.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.03023, over 1428189.10 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:25:58,575 INFO [train.py:812] (0/8) Epoch 33, batch 3850, loss[loss=0.1634, simple_loss=0.2584, pruned_loss=0.03418, over 7313.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2437, pruned_loss=0.02969, over 1428267.52 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:26:57,071 INFO [train.py:812] (0/8) Epoch 33, batch 3900, loss[loss=0.1359, simple_loss=0.2237, pruned_loss=0.02406, over 7210.00 frames.], tot_loss[loss=0.1524, simple_loss=0.245, pruned_loss=0.02993, over 1428624.57 frames.], batch size: 16, lr: 2.35e-04
+2022-05-15 21:27:55,700 INFO [train.py:812] (0/8) Epoch 33, batch 3950, loss[loss=0.1237, simple_loss=0.206, pruned_loss=0.02073, over 7407.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2455, pruned_loss=0.03037, over 1431214.19 frames.], batch size: 18, lr: 2.34e-04
+2022-05-15 21:28:55,478 INFO [train.py:812] (0/8) Epoch 33, batch 4000, loss[loss=0.1519, simple_loss=0.2541, pruned_loss=0.02483, over 6367.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2443, pruned_loss=0.02972, over 1431475.34 frames.], batch size: 37, lr: 2.34e-04
+2022-05-15 21:29:54,328 INFO [train.py:812] (0/8) Epoch 33, batch 4050, loss[loss=0.1365, simple_loss=0.2202, pruned_loss=0.02645, over 7292.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02997, over 1428730.72 frames.], batch size: 18, lr: 2.34e-04
+2022-05-15 21:30:52,665 INFO [train.py:812] (0/8) Epoch 33, batch 4100, loss[loss=0.1596, simple_loss=0.2635, pruned_loss=0.02781, over 7174.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2436, pruned_loss=0.02974, over 1422591.19 frames.], batch size: 26, lr: 2.34e-04
+2022-05-15 21:31:50,545 INFO [train.py:812] (0/8) Epoch 33, batch 4150, loss[loss=0.1339, simple_loss=0.211, pruned_loss=0.02838, over 6840.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03012, over 1421911.88 frames.], batch size: 15, lr: 2.34e-04
+2022-05-15 21:32:49,159 INFO [train.py:812] (0/8) Epoch 33, batch 4200, loss[loss=0.1462, simple_loss=0.2362, pruned_loss=0.02814, over 7256.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02981, over 1419377.67 frames.], batch size: 19, lr: 2.34e-04
+2022-05-15 21:33:48,264 INFO [train.py:812] (0/8) Epoch 33, batch 4250, loss[loss=0.1532, simple_loss=0.2587, pruned_loss=0.02379, over 7424.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.0295, over 1420274.19 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:34:46,558 INFO [train.py:812] (0/8) Epoch 33, batch 4300, loss[loss=0.1347, simple_loss=0.2299, pruned_loss=0.01974, over 6693.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.0295, over 1419051.56 frames.], batch size: 31, lr: 2.34e-04
+2022-05-15 21:35:44,866 INFO [train.py:812] (0/8) Epoch 33, batch 4350, loss[loss=0.1588, simple_loss=0.2507, pruned_loss=0.03351, over 7223.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02906, over 1414716.67 frames.], batch size: 21, lr: 2.34e-04
+2022-05-15 21:36:43,639 INFO [train.py:812] (0/8) Epoch 33, batch 4400, loss[loss=0.1358, simple_loss=0.2398, pruned_loss=0.01589, over 7143.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2416, pruned_loss=0.02889, over 1414170.37 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:37:42,032 INFO [train.py:812] (0/8) Epoch 33, batch 4450, loss[loss=0.1469, simple_loss=0.2507, pruned_loss=0.0216, over 7349.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.02881, over 1405947.18 frames.], batch size: 22, lr: 2.34e-04
+2022-05-15 21:38:41,149 INFO [train.py:812] (0/8) Epoch 33, batch 4500, loss[loss=0.1569, simple_loss=0.2595, pruned_loss=0.02712, over 7146.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2437, pruned_loss=0.02907, over 1396286.27 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:39:39,847 INFO [train.py:812] (0/8) Epoch 33, batch 4550, loss[loss=0.1642, simple_loss=0.2583, pruned_loss=0.0351, over 5086.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2452, pruned_loss=0.03011, over 1375574.37 frames.], batch size: 52, lr: 2.34e-04
+2022-05-15 21:40:24,647 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-33.pt
+2022-05-15 21:40:52,140 INFO [train.py:812] (0/8) Epoch 34, batch 0, loss[loss=0.1589, simple_loss=0.2561, pruned_loss=0.03086, over 7430.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2561, pruned_loss=0.03086, over 7430.00 frames.], batch size: 20, lr: 2.31e-04
+2022-05-15 21:41:51,337 INFO [train.py:812] (0/8) Epoch 34, batch 50, loss[loss=0.1682, simple_loss=0.2715, pruned_loss=0.03242, over 7119.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2395, pruned_loss=0.028, over 324863.72 frames.], batch size: 28, lr: 2.30e-04
+2022-05-15 21:42:51,123 INFO [train.py:812] (0/8) Epoch 34, batch 100, loss[loss=0.1567, simple_loss=0.26, pruned_loss=0.02671, over 7120.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2423, pruned_loss=0.02855, over 566011.08 frames.], batch size: 21, lr: 2.30e-04
+2022-05-15 21:43:50,298 INFO [train.py:812] (0/8) Epoch 34, batch 150, loss[loss=0.1461, simple_loss=0.2347, pruned_loss=0.0287, over 7068.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.0289, over 755934.43 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:44:49,630 INFO [train.py:812] (0/8) Epoch 34, batch 200, loss[loss=0.1192, simple_loss=0.2019, pruned_loss=0.01827, over 7286.00 frames.], tot_loss[loss=0.1505, simple_loss=0.242, pruned_loss=0.02951, over 905040.26 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:45:48,775 INFO [train.py:812] (0/8) Epoch 34, batch 250, loss[loss=0.1868, simple_loss=0.2665, pruned_loss=0.0536, over 4488.00 frames.], tot_loss[loss=0.151, simple_loss=0.242, pruned_loss=0.02999, over 1011083.62 frames.], batch size: 53, lr: 2.30e-04
+2022-05-15 21:46:48,759 INFO [train.py:812] (0/8) Epoch 34, batch 300, loss[loss=0.1686, simple_loss=0.2643, pruned_loss=0.03645, over 7389.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2427, pruned_loss=0.03016, over 1101713.54 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 21:47:46,236 INFO [train.py:812] (0/8) Epoch 34, batch 350, loss[loss=0.1403, simple_loss=0.2339, pruned_loss=0.02338, over 7140.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2441, pruned_loss=0.03053, over 1166801.05 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:48:46,227 INFO [train.py:812] (0/8) Epoch 34, batch 400, loss[loss=0.1486, simple_loss=0.2414, pruned_loss=0.02792, over 7419.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2429, pruned_loss=0.03018, over 1227692.58 frames.], batch size: 21, lr: 2.30e-04
+2022-05-15 21:49:44,749 INFO [train.py:812] (0/8) Epoch 34, batch 450, loss[loss=0.1426, simple_loss=0.2235, pruned_loss=0.03083, over 7405.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2437, pruned_loss=0.0303, over 1272509.05 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:50:44,142 INFO [train.py:812] (0/8) Epoch 34, batch 500, loss[loss=0.138, simple_loss=0.2294, pruned_loss=0.02325, over 7261.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2445, pruned_loss=0.03065, over 1305057.53 frames.], batch size: 24, lr: 2.30e-04
+2022-05-15 21:51:42,497 INFO [train.py:812] (0/8) Epoch 34, batch 550, loss[loss=0.1512, simple_loss=0.2516, pruned_loss=0.02546, over 6384.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03026, over 1329705.66 frames.], batch size: 37, lr: 2.30e-04
+2022-05-15 21:52:45,703 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-152000.pt
+2022-05-15 21:52:57,373 INFO [train.py:812] (0/8) Epoch 34, batch 600, loss[loss=0.183, simple_loss=0.2701, pruned_loss=0.04792, over 7308.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.03007, over 1351754.58 frames.], batch size: 25, lr: 2.30e-04
+2022-05-15 21:53:55,923 INFO [train.py:812] (0/8) Epoch 34, batch 650, loss[loss=0.1245, simple_loss=0.2119, pruned_loss=0.01858, over 7156.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2446, pruned_loss=0.02994, over 1370302.49 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:54:54,865 INFO [train.py:812] (0/8) Epoch 34, batch 700, loss[loss=0.1253, simple_loss=0.208, pruned_loss=0.02134, over 7120.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02958, over 1377628.00 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:55:51,398 INFO [train.py:812] (0/8) Epoch 34, batch 750, loss[loss=0.1637, simple_loss=0.2616, pruned_loss=0.03294, over 7199.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02953, over 1389588.36 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 21:56:50,462 INFO [train.py:812] (0/8) Epoch 34, batch 800, loss[loss=0.1404, simple_loss=0.2371, pruned_loss=0.02186, over 7270.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2442, pruned_loss=0.02969, over 1394816.26 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:57:49,904 INFO [train.py:812] (0/8) Epoch 34, batch 850, loss[loss=0.135, simple_loss=0.23, pruned_loss=0.02, over 6417.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02961, over 1404911.42 frames.], batch size: 37, lr: 2.30e-04
+2022-05-15 21:58:48,167 INFO [train.py:812] (0/8) Epoch 34, batch 900, loss[loss=0.1539, simple_loss=0.2408, pruned_loss=0.03348, over 4862.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02962, over 1409492.60 frames.], batch size: 52, lr: 2.30e-04
+2022-05-15 21:59:45,346 INFO [train.py:812] (0/8) Epoch 34, batch 950, loss[loss=0.1594, simple_loss=0.2518, pruned_loss=0.03348, over 7281.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2436, pruned_loss=0.02993, over 1407757.64 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 22:00:43,776 INFO [train.py:812] (0/8) Epoch 34, batch 1000, loss[loss=0.1434, simple_loss=0.2339, pruned_loss=0.02645, over 7428.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2429, pruned_loss=0.02977, over 1408839.31 frames.], batch size: 20, lr: 2.30e-04
+2022-05-15 22:01:41,760 INFO [train.py:812] (0/8) Epoch 34, batch 1050, loss[loss=0.1369, simple_loss=0.2362, pruned_loss=0.01878, over 7157.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2431, pruned_loss=0.02958, over 1415192.81 frames.], batch size: 19, lr: 2.30e-04
+2022-05-15 22:02:40,864 INFO [train.py:812] (0/8) Epoch 34, batch 1100, loss[loss=0.1627, simple_loss=0.2555, pruned_loss=0.03493, over 6545.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02955, over 1413632.39 frames.], batch size: 38, lr: 2.30e-04
+2022-05-15 22:03:39,417 INFO [train.py:812] (0/8) Epoch 34, batch 1150, loss[loss=0.1348, simple_loss=0.2217, pruned_loss=0.02393, over 7423.00 frames.], tot_loss[loss=0.151, simple_loss=0.2426, pruned_loss=0.02965, over 1415787.15 frames.], batch size: 20, lr: 2.30e-04
+2022-05-15 22:04:38,211 INFO [train.py:812] (0/8) Epoch 34, batch 1200, loss[loss=0.1834, simple_loss=0.2718, pruned_loss=0.04753, over 7198.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2428, pruned_loss=0.02966, over 1420152.65 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 22:05:35,693 INFO [train.py:812] (0/8) Epoch 34, batch 1250, loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02939, over 7330.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.03025, over 1417438.48 frames.], batch size: 22, lr: 2.30e-04
+2022-05-15 22:06:34,733 INFO [train.py:812] (0/8) Epoch 34, batch 1300, loss[loss=0.1668, simple_loss=0.2592, pruned_loss=0.03717, over 7128.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2437, pruned_loss=0.03044, over 1417694.05 frames.], batch size: 26, lr: 2.30e-04
+2022-05-15 22:07:33,172 INFO [train.py:812] (0/8) Epoch 34, batch 1350, loss[loss=0.1416, simple_loss=0.2443, pruned_loss=0.01941, over 7216.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2428, pruned_loss=0.02981, over 1418564.07 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:08:32,136 INFO [train.py:812] (0/8) Epoch 34, batch 1400, loss[loss=0.1498, simple_loss=0.2398, pruned_loss=0.02987, over 7259.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2427, pruned_loss=0.02971, over 1421419.79 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:09:31,083 INFO [train.py:812] (0/8) Epoch 34, batch 1450, loss[loss=0.1446, simple_loss=0.2456, pruned_loss=0.02177, over 7415.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2429, pruned_loss=0.02989, over 1424855.65 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:10:29,314 INFO [train.py:812] (0/8) Epoch 34, batch 1500, loss[loss=0.1675, simple_loss=0.2548, pruned_loss=0.04006, over 7370.00 frames.], tot_loss[loss=0.152, simple_loss=0.2435, pruned_loss=0.03025, over 1423298.84 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:11:28,512 INFO [train.py:812] (0/8) Epoch 34, batch 1550, loss[loss=0.1638, simple_loss=0.2605, pruned_loss=0.0335, over 7271.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.03003, over 1421483.46 frames.], batch size: 24, lr: 2.29e-04
+2022-05-15 22:12:27,923 INFO [train.py:812] (0/8) Epoch 34, batch 1600, loss[loss=0.152, simple_loss=0.2497, pruned_loss=0.02718, over 7331.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02983, over 1422561.62 frames.], batch size: 20, lr: 2.29e-04
+2022-05-15 22:13:26,005 INFO [train.py:812] (0/8) Epoch 34, batch 1650, loss[loss=0.1797, simple_loss=0.2729, pruned_loss=0.04322, over 7184.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2454, pruned_loss=0.03042, over 1422103.16 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:14:25,164 INFO [train.py:812] (0/8) Epoch 34, batch 1700, loss[loss=0.1637, simple_loss=0.2558, pruned_loss=0.03583, over 7376.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2456, pruned_loss=0.03033, over 1426087.64 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:15:24,022 INFO [train.py:812] (0/8) Epoch 34, batch 1750, loss[loss=0.1521, simple_loss=0.2417, pruned_loss=0.03128, over 7113.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2459, pruned_loss=0.03061, over 1420870.81 frames.], batch size: 28, lr: 2.29e-04
+2022-05-15 22:16:22,622 INFO [train.py:812] (0/8) Epoch 34, batch 1800, loss[loss=0.1226, simple_loss=0.2081, pruned_loss=0.01854, over 7263.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2454, pruned_loss=0.03047, over 1422241.59 frames.], batch size: 17, lr: 2.29e-04
+2022-05-15 22:17:21,598 INFO [train.py:812] (0/8) Epoch 34, batch 1850, loss[loss=0.1563, simple_loss=0.2529, pruned_loss=0.02981, over 7320.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.03002, over 1414781.82 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:18:20,805 INFO [train.py:812] (0/8) Epoch 34, batch 1900, loss[loss=0.1449, simple_loss=0.2433, pruned_loss=0.02327, over 6797.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2442, pruned_loss=0.02964, over 1410305.46 frames.], batch size: 31, lr: 2.29e-04
+2022-05-15 22:19:17,930 INFO [train.py:812] (0/8) Epoch 34, batch 1950, loss[loss=0.1353, simple_loss=0.2115, pruned_loss=0.0296, over 7010.00 frames.], tot_loss[loss=0.1517, simple_loss=0.244, pruned_loss=0.02976, over 1416305.05 frames.], batch size: 16, lr: 2.29e-04
+2022-05-15 22:20:16,776 INFO [train.py:812] (0/8) Epoch 34, batch 2000, loss[loss=0.1318, simple_loss=0.2163, pruned_loss=0.02365, over 7395.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02944, over 1421631.52 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:21:15,725 INFO [train.py:812] (0/8) Epoch 34, batch 2050, loss[loss=0.1429, simple_loss=0.236, pruned_loss=0.02484, over 7126.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02962, over 1421796.37 frames.], batch size: 26, lr: 2.29e-04
+2022-05-15 22:22:14,732 INFO [train.py:812] (0/8) Epoch 34, batch 2100, loss[loss=0.1561, simple_loss=0.2464, pruned_loss=0.03294, over 7210.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02933, over 1424850.76 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:23:12,300 INFO [train.py:812] (0/8) Epoch 34, batch 2150, loss[loss=0.1704, simple_loss=0.2561, pruned_loss=0.04234, over 7295.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02913, over 1424312.37 frames.], batch size: 24, lr: 2.29e-04
+2022-05-15 22:24:11,612 INFO [train.py:812] (0/8) Epoch 34, batch 2200, loss[loss=0.1611, simple_loss=0.2593, pruned_loss=0.03147, over 7319.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2447, pruned_loss=0.02946, over 1427373.73 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:25:10,941 INFO [train.py:812] (0/8) Epoch 34, batch 2250, loss[loss=0.1304, simple_loss=0.2198, pruned_loss=0.02051, over 7257.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2442, pruned_loss=0.02942, over 1423587.52 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:26:09,641 INFO [train.py:812] (0/8) Epoch 34, batch 2300, loss[loss=0.1489, simple_loss=0.2354, pruned_loss=0.03118, over 7156.00 frames.], tot_loss[loss=0.152, simple_loss=0.2447, pruned_loss=0.02967, over 1424143.08 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:27:08,006 INFO [train.py:812] (0/8) Epoch 34, batch 2350, loss[loss=0.1232, simple_loss=0.2115, pruned_loss=0.01743, over 7170.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02941, over 1425073.72 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:28:06,470 INFO [train.py:812] (0/8) Epoch 34, batch 2400, loss[loss=0.1686, simple_loss=0.2609, pruned_loss=0.0381, over 7386.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2432, pruned_loss=0.02918, over 1425199.75 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:29:04,644 INFO [train.py:812] (0/8) Epoch 34, batch 2450, loss[loss=0.1457, simple_loss=0.2438, pruned_loss=0.02379, over 7214.00 frames.], tot_loss[loss=0.151, simple_loss=0.2435, pruned_loss=0.02923, over 1419567.81 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:30:04,441 INFO [train.py:812] (0/8) Epoch 34, batch 2500, loss[loss=0.1312, simple_loss=0.2193, pruned_loss=0.02156, over 6997.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2438, pruned_loss=0.029, over 1418731.02 frames.], batch size: 16, lr: 2.29e-04
+2022-05-15 22:31:02,268 INFO [train.py:812] (0/8) Epoch 34, batch 2550, loss[loss=0.155, simple_loss=0.2586, pruned_loss=0.02575, over 7344.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2436, pruned_loss=0.02882, over 1420437.20 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:32:00,046 INFO [train.py:812] (0/8) Epoch 34, batch 2600, loss[loss=0.13, simple_loss=0.2177, pruned_loss=0.02121, over 7070.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2432, pruned_loss=0.02892, over 1420387.37 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:32:58,092 INFO [train.py:812] (0/8) Epoch 34, batch 2650, loss[loss=0.1485, simple_loss=0.2505, pruned_loss=0.02327, over 7342.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2429, pruned_loss=0.02925, over 1420804.38 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:33:56,977 INFO [train.py:812] (0/8) Epoch 34, batch 2700, loss[loss=0.1297, simple_loss=0.22, pruned_loss=0.01967, over 7278.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02882, over 1425397.13 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 22:34:55,301 INFO [train.py:812] (0/8) Epoch 34, batch 2750, loss[loss=0.1738, simple_loss=0.2606, pruned_loss=0.04348, over 7320.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.02908, over 1423441.50 frames.], batch size: 21, lr: 2.28e-04
+2022-05-15 22:35:54,061 INFO [train.py:812] (0/8) Epoch 34, batch 2800, loss[loss=0.1402, simple_loss=0.2314, pruned_loss=0.02446, over 7420.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2437, pruned_loss=0.02934, over 1429106.30 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 22:36:52,771 INFO [train.py:812] (0/8) Epoch 34, batch 2850, loss[loss=0.1514, simple_loss=0.2501, pruned_loss=0.02636, over 7183.00 frames.], tot_loss[loss=0.151, simple_loss=0.2439, pruned_loss=0.02907, over 1430576.10 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:37:50,505 INFO [train.py:812] (0/8) Epoch 34, batch 2900, loss[loss=0.1498, simple_loss=0.2429, pruned_loss=0.02841, over 7146.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2437, pruned_loss=0.02935, over 1426845.59 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:38:49,626 INFO [train.py:812] (0/8) Epoch 34, batch 2950, loss[loss=0.1419, simple_loss=0.2428, pruned_loss=0.02054, over 7138.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2434, pruned_loss=0.0291, over 1427499.19 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:39:49,392 INFO [train.py:812] (0/8) Epoch 34, batch 3000, loss[loss=0.1606, simple_loss=0.2522, pruned_loss=0.03445, over 7358.00 frames.], tot_loss[loss=0.151, simple_loss=0.2437, pruned_loss=0.02919, over 1427682.82 frames.], batch size: 19, lr: 2.28e-04
+2022-05-15 22:39:49,393 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-15 22:39:56,836 INFO [train.py:841] (0/8) Epoch 34, validation: loss=0.1534, simple_loss=0.2492, pruned_loss=0.02878, over 698248.00 frames.
+2022-05-15 22:40:55,236 INFO [train.py:812] (0/8) Epoch 34, batch 3050, loss[loss=0.1378, simple_loss=0.2262, pruned_loss=0.02473, over 7350.00 frames.], tot_loss[loss=0.151, simple_loss=0.244, pruned_loss=0.02905, over 1427861.16 frames.], batch size: 19, lr: 2.28e-04
+2022-05-15 22:41:53,724 INFO [train.py:812] (0/8) Epoch 34, batch 3100, loss[loss=0.1285, simple_loss=0.2203, pruned_loss=0.01834, over 6766.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2449, pruned_loss=0.02965, over 1429127.43 frames.], batch size: 15, lr: 2.28e-04
+2022-05-15 22:42:52,703 INFO [train.py:812] (0/8) Epoch 34, batch 3150, loss[loss=0.1354, simple_loss=0.2226, pruned_loss=0.0241, over 7301.00 frames.], tot_loss[loss=0.1516, simple_loss=0.244, pruned_loss=0.02957, over 1429420.97 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:43:51,457 INFO [train.py:812] (0/8) Epoch 34, batch 3200, loss[loss=0.1681, simple_loss=0.2528, pruned_loss=0.04163, over 5162.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.03017, over 1425294.57 frames.], batch size: 52, lr: 2.28e-04
+2022-05-15 22:44:49,454 INFO [train.py:812] (0/8) Epoch 34, batch 3250, loss[loss=0.1491, simple_loss=0.2394, pruned_loss=0.02941, over 7124.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03046, over 1422832.18 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:45:48,018 INFO [train.py:812] (0/8) Epoch 34, batch 3300, loss[loss=0.1768, simple_loss=0.2755, pruned_loss=0.03905, over 7096.00 frames.], tot_loss[loss=0.153, simple_loss=0.2447, pruned_loss=0.03064, over 1419474.02 frames.], batch size: 28, lr: 2.28e-04
+2022-05-15 22:46:47,344 INFO [train.py:812] (0/8) Epoch 34, batch 3350, loss[loss=0.1377, simple_loss=0.2335, pruned_loss=0.0209, over 7147.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2433, pruned_loss=0.02988, over 1421786.13 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:47:45,299 INFO [train.py:812] (0/8) Epoch 34, batch 3400, loss[loss=0.1419, simple_loss=0.2259, pruned_loss=0.02898, over 7204.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2435, pruned_loss=0.02969, over 1422135.05 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:48:43,913 INFO [train.py:812] (0/8) Epoch 34, batch 3450, loss[loss=0.1603, simple_loss=0.2479, pruned_loss=0.0364, over 6990.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.02949, over 1427566.66 frames.], batch size: 16, lr: 2.28e-04
+2022-05-15 22:49:41,428 INFO [train.py:812] (0/8) Epoch 34, batch 3500, loss[loss=0.1529, simple_loss=0.2572, pruned_loss=0.02434, over 7203.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2447, pruned_loss=0.02989, over 1429353.61 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:50:38,737 INFO [train.py:812] (0/8) Epoch 34, batch 3550, loss[loss=0.125, simple_loss=0.2109, pruned_loss=0.01958, over 7300.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2433, pruned_loss=0.02902, over 1431934.92 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:51:37,798 INFO [train.py:812] (0/8) Epoch 34, batch 3600, loss[loss=0.1411, simple_loss=0.2331, pruned_loss=0.02452, over 7320.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2419, pruned_loss=0.02864, over 1433327.51 frames.], batch size: 21, lr: 2.28e-04
+2022-05-15 22:52:35,092 INFO [train.py:812] (0/8) Epoch 34, batch 3650, loss[loss=0.1628, simple_loss=0.2561, pruned_loss=0.03473, over 6167.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2427, pruned_loss=0.02898, over 1428551.67 frames.], batch size: 37, lr: 2.28e-04
+2022-05-15 22:53:34,866 INFO [train.py:812] (0/8) Epoch 34, batch 3700, loss[loss=0.1502, simple_loss=0.2469, pruned_loss=0.02676, over 7242.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2415, pruned_loss=0.02878, over 1424345.79 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:54:33,430 INFO [train.py:812] (0/8) Epoch 34, batch 3750, loss[loss=0.1594, simple_loss=0.2522, pruned_loss=0.03332, over 7269.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2407, pruned_loss=0.02851, over 1421192.71 frames.], batch size: 24, lr: 2.28e-04
+2022-05-15 22:55:32,406 INFO [train.py:812] (0/8) Epoch 34, batch 3800, loss[loss=0.1526, simple_loss=0.2579, pruned_loss=0.02367, over 7137.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02888, over 1425519.45 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:56:31,629 INFO [train.py:812] (0/8) Epoch 34, batch 3850, loss[loss=0.1407, simple_loss=0.2413, pruned_loss=0.02007, over 7216.00 frames.], tot_loss[loss=0.15, simple_loss=0.2417, pruned_loss=0.02917, over 1427188.13 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:57:28,722 INFO [train.py:812] (0/8) Epoch 34, batch 3900, loss[loss=0.157, simple_loss=0.2617, pruned_loss=0.02616, over 7205.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2424, pruned_loss=0.02937, over 1426302.37 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:58:46,514 INFO [train.py:812] (0/8) Epoch 34, batch 3950, loss[loss=0.1313, simple_loss=0.2309, pruned_loss=0.01581, over 7327.00 frames.], tot_loss[loss=0.1504, simple_loss=0.242, pruned_loss=0.02942, over 1424210.08 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:59:45,587 INFO [train.py:812] (0/8) Epoch 34, batch 4000, loss[loss=0.1337, simple_loss=0.2318, pruned_loss=0.01775, over 7066.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2425, pruned_loss=0.02956, over 1424041.09 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 23:00:53,090 INFO [train.py:812] (0/8) Epoch 34, batch 4050, loss[loss=0.1732, simple_loss=0.2673, pruned_loss=0.03956, over 7160.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2431, pruned_loss=0.02993, over 1419452.29 frames.], batch size: 26, lr: 2.27e-04
+2022-05-15 23:01:51,477 INFO [train.py:812] (0/8) Epoch 34, batch 4100, loss[loss=0.1515, simple_loss=0.2539, pruned_loss=0.02461, over 6321.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2435, pruned_loss=0.03003, over 1419807.81 frames.], batch size: 38, lr: 2.27e-04
+2022-05-15 23:02:49,334 INFO [train.py:812] (0/8) Epoch 34, batch 4150, loss[loss=0.1333, simple_loss=0.2208, pruned_loss=0.02287, over 7414.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2439, pruned_loss=0.03036, over 1418911.17 frames.], batch size: 18, lr: 2.27e-04
+2022-05-15 23:03:57,831 INFO [train.py:812] (0/8) Epoch 34, batch 4200, loss[loss=0.1594, simple_loss=0.2571, pruned_loss=0.03086, over 7229.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03011, over 1421477.78 frames.], batch size: 20, lr: 2.27e-04
+2022-05-15 23:05:06,365 INFO [train.py:812] (0/8) Epoch 34, batch 4250, loss[loss=0.1386, simple_loss=0.2193, pruned_loss=0.02889, over 7133.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2438, pruned_loss=0.02971, over 1420705.48 frames.], batch size: 17, lr: 2.27e-04
+2022-05-15 23:06:05,060 INFO [train.py:812] (0/8) Epoch 34, batch 4300, loss[loss=0.1404, simple_loss=0.2217, pruned_loss=0.02958, over 7002.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02987, over 1420559.74 frames.], batch size: 16, lr: 2.27e-04
+2022-05-15 23:07:13,197 INFO [train.py:812] (0/8) Epoch 34, batch 4350, loss[loss=0.1404, simple_loss=0.2335, pruned_loss=0.02364, over 7228.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03024, over 1417094.39 frames.], batch size: 16, lr: 2.27e-04
+2022-05-15 23:08:12,762 INFO [train.py:812] (0/8) Epoch 34, batch 4400, loss[loss=0.1553, simple_loss=0.2328, pruned_loss=0.03891, over 7176.00 frames.], tot_loss[loss=0.152, simple_loss=0.2436, pruned_loss=0.03022, over 1417267.81 frames.], batch size: 18, lr: 2.27e-04
+2022-05-15 23:09:11,146 INFO [train.py:812] (0/8) Epoch 34, batch 4450, loss[loss=0.1774, simple_loss=0.2639, pruned_loss=0.04546, over 7221.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2436, pruned_loss=0.03029, over 1402344.72 frames.], batch size: 23, lr: 2.27e-04
+2022-05-15 23:10:19,462 INFO [train.py:812] (0/8) Epoch 34, batch 4500, loss[loss=0.1973, simple_loss=0.2871, pruned_loss=0.05375, over 5336.00 frames.], tot_loss[loss=0.1525, simple_loss=0.244, pruned_loss=0.03048, over 1392057.73 frames.], batch size: 52, lr: 2.27e-04
+2022-05-15 23:11:16,022 INFO [train.py:812] (0/8) Epoch 34, batch 4550, loss[loss=0.1962, simple_loss=0.2761, pruned_loss=0.0582, over 5130.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2461, pruned_loss=0.03117, over 1351652.72 frames.], batch size: 52, lr: 2.27e-04
+2022-05-15 23:11:59,894 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-34.pt
+2022-05-15 23:12:20,556 INFO [train.py:812] (0/8) Epoch 35, batch 0, loss[loss=0.1619, simple_loss=0.2549, pruned_loss=0.03444, over 7231.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2549, pruned_loss=0.03444, over 7231.00 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:12:29,409 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-156000.pt
+2022-05-15 23:13:24,535 INFO [train.py:812] (0/8) Epoch 35, batch 50, loss[loss=0.1782, simple_loss=0.2699, pruned_loss=0.04323, over 7290.00 frames.], tot_loss[loss=0.157, simple_loss=0.2483, pruned_loss=0.03282, over 317887.21 frames.], batch size: 24, lr: 2.24e-04
+2022-05-15 23:14:23,038 INFO [train.py:812] (0/8) Epoch 35, batch 100, loss[loss=0.1703, simple_loss=0.257, pruned_loss=0.04184, over 7166.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.03075, over 567971.10 frames.], batch size: 26, lr: 2.24e-04
+2022-05-15 23:15:22,490 INFO [train.py:812] (0/8) Epoch 35, batch 150, loss[loss=0.1457, simple_loss=0.2406, pruned_loss=0.02543, over 7377.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.03015, over 761208.65 frames.], batch size: 23, lr: 2.24e-04
+2022-05-15 23:16:21,257 INFO [train.py:812] (0/8) Epoch 35, batch 200, loss[loss=0.1495, simple_loss=0.2379, pruned_loss=0.03054, over 7067.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02958, over 910156.31 frames.], batch size: 18, lr: 2.24e-04
+2022-05-15 23:17:21,137 INFO [train.py:812] (0/8) Epoch 35, batch 250, loss[loss=0.1436, simple_loss=0.2399, pruned_loss=0.02363, over 7229.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02958, over 1027584.31 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:18:18,901 INFO [train.py:812] (0/8) Epoch 35, batch 300, loss[loss=0.132, simple_loss=0.2284, pruned_loss=0.01779, over 7158.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02971, over 1113837.17 frames.], batch size: 19, lr: 2.24e-04
+2022-05-15 23:19:18,444 INFO [train.py:812] (0/8) Epoch 35, batch 350, loss[loss=0.1712, simple_loss=0.2543, pruned_loss=0.04401, over 7193.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02951, over 1185976.24 frames.], batch size: 23, lr: 2.24e-04
+2022-05-15 23:20:16,875 INFO [train.py:812] (0/8) Epoch 35, batch 400, loss[loss=0.1519, simple_loss=0.2374, pruned_loss=0.03321, over 7328.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02975, over 1240289.54 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:21:15,056 INFO [train.py:812] (0/8) Epoch 35, batch 450, loss[loss=0.1524, simple_loss=0.2478, pruned_loss=0.02847, over 6876.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02955, over 1285425.42 frames.], batch size: 31, lr: 2.24e-04
+2022-05-15 23:22:13,175 INFO [train.py:812] (0/8) Epoch 35, batch 500, loss[loss=0.1311, simple_loss=0.2257, pruned_loss=0.01826, over 7326.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2423, pruned_loss=0.02962, over 1314898.43 frames.], batch size: 20, lr: 2.23e-04
+2022-05-15 23:23:12,758 INFO [train.py:812] (0/8) Epoch 35, batch 550, loss[loss=0.1406, simple_loss=0.2345, pruned_loss=0.02331, over 7060.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2414, pruned_loss=0.02939, over 1335430.66 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:24:10,892 INFO [train.py:812] (0/8) Epoch 35, batch 600, loss[loss=0.148, simple_loss=0.2503, pruned_loss=0.02286, over 7342.00 frames.], tot_loss[loss=0.1506, simple_loss=0.242, pruned_loss=0.02961, over 1354320.06 frames.], batch size: 22, lr: 2.23e-04
+2022-05-15 23:25:10,086 INFO [train.py:812] (0/8) Epoch 35, batch 650, loss[loss=0.1365, simple_loss=0.2158, pruned_loss=0.02856, over 7169.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2424, pruned_loss=0.02959, over 1372822.96 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:26:08,921 INFO [train.py:812] (0/8) Epoch 35, batch 700, loss[loss=0.1332, simple_loss=0.2273, pruned_loss=0.01955, over 7267.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2422, pruned_loss=0.02965, over 1386668.49 frames.], batch size: 17, lr: 2.23e-04
+2022-05-15 23:27:08,864 INFO [train.py:812] (0/8) Epoch 35, batch 750, loss[loss=0.1363, simple_loss=0.2238, pruned_loss=0.02437, over 7263.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2405, pruned_loss=0.02906, over 1394113.18 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:28:07,151 INFO [train.py:812] (0/8) Epoch 35, batch 800, loss[loss=0.1728, simple_loss=0.2716, pruned_loss=0.03694, over 7222.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2412, pruned_loss=0.02908, over 1403122.15 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:29:06,803 INFO [train.py:812] (0/8) Epoch 35, batch 850, loss[loss=0.1887, simple_loss=0.2953, pruned_loss=0.04107, over 7290.00 frames.], tot_loss[loss=0.1502, simple_loss=0.242, pruned_loss=0.02918, over 1402520.57 frames.], batch size: 24, lr: 2.23e-04
+2022-05-15 23:30:05,680 INFO [train.py:812] (0/8) Epoch 35, batch 900, loss[loss=0.1505, simple_loss=0.2434, pruned_loss=0.0288, over 5349.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2425, pruned_loss=0.02918, over 1405899.94 frames.], batch size: 52, lr: 2.23e-04
+2022-05-15 23:31:04,511 INFO [train.py:812] (0/8) Epoch 35, batch 950, loss[loss=0.1522, simple_loss=0.2445, pruned_loss=0.03, over 7248.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02908, over 1409685.15 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:32:02,580 INFO [train.py:812] (0/8) Epoch 35, batch 1000, loss[loss=0.1428, simple_loss=0.2438, pruned_loss=0.02086, over 6783.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02917, over 1411710.34 frames.], batch size: 31, lr: 2.23e-04
+2022-05-15 23:33:01,153 INFO [train.py:812] (0/8) Epoch 35, batch 1050, loss[loss=0.1517, simple_loss=0.2493, pruned_loss=0.0271, over 7409.00 frames.], tot_loss[loss=0.1499, simple_loss=0.242, pruned_loss=0.02894, over 1416823.04 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:33:59,756 INFO [train.py:812] (0/8) Epoch 35, batch 1100, loss[loss=0.1336, simple_loss=0.2165, pruned_loss=0.02532, over 7359.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2416, pruned_loss=0.02896, over 1420769.05 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:34:58,671 INFO [train.py:812] (0/8) Epoch 35, batch 1150, loss[loss=0.1808, simple_loss=0.2673, pruned_loss=0.0472, over 7214.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.02889, over 1422556.95 frames.], batch size: 23, lr: 2.23e-04
+2022-05-15 23:35:56,638 INFO [train.py:812] (0/8) Epoch 35, batch 1200, loss[loss=0.1537, simple_loss=0.2407, pruned_loss=0.03334, over 7294.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02893, over 1425866.63 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:36:54,992 INFO [train.py:812] (0/8) Epoch 35, batch 1250, loss[loss=0.1777, simple_loss=0.2768, pruned_loss=0.03933, over 7330.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.02926, over 1424786.17 frames.], batch size: 22, lr: 2.23e-04
+2022-05-15 23:37:53,435 INFO [train.py:812] (0/8) Epoch 35, batch 1300, loss[loss=0.1468, simple_loss=0.247, pruned_loss=0.02331, over 7075.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02943, over 1420649.60 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:38:52,774 INFO [train.py:812] (0/8) Epoch 35, batch 1350, loss[loss=0.1474, simple_loss=0.2394, pruned_loss=0.02772, over 7141.00 frames.], tot_loss[loss=0.1507, simple_loss=0.243, pruned_loss=0.02917, over 1423156.04 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:39:51,325 INFO [train.py:812] (0/8) Epoch 35, batch 1400, loss[loss=0.1294, simple_loss=0.2335, pruned_loss=0.01261, over 7322.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2433, pruned_loss=0.02925, over 1420334.14 frames.], batch size: 20, lr: 2.23e-04
+2022-05-15 23:40:50,633 INFO [train.py:812] (0/8) Epoch 35, batch 1450, loss[loss=0.1757, simple_loss=0.2743, pruned_loss=0.03857, over 7257.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02961, over 1419108.59 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:41:50,031 INFO [train.py:812] (0/8) Epoch 35, batch 1500, loss[loss=0.1253, simple_loss=0.2129, pruned_loss=0.01883, over 7147.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.02941, over 1419426.06 frames.], batch size: 17, lr: 2.23e-04
+2022-05-15 23:42:48,947 INFO [train.py:812] (0/8) Epoch 35, batch 1550, loss[loss=0.1871, simple_loss=0.2942, pruned_loss=0.03997, over 7212.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.02924, over 1419762.08 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:43:47,278 INFO [train.py:812] (0/8) Epoch 35, batch 1600, loss[loss=0.1553, simple_loss=0.2546, pruned_loss=0.02804, over 7048.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02936, over 1421123.78 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:44:46,440 INFO [train.py:812] (0/8) Epoch 35, batch 1650, loss[loss=0.1286, simple_loss=0.2108, pruned_loss=0.02318, over 7418.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.02933, over 1426449.34 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:45:45,358 INFO [train.py:812] (0/8) Epoch 35, batch 1700, loss[loss=0.1614, simple_loss=0.2509, pruned_loss=0.03593, over 5050.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.0293, over 1425546.74 frames.], batch size: 52, lr: 2.23e-04
+2022-05-15 23:46:45,275 INFO [train.py:812] (0/8) Epoch 35, batch 1750, loss[loss=0.1294, simple_loss=0.2259, pruned_loss=0.01644, over 7164.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2415, pruned_loss=0.0289, over 1427102.33 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:47:44,607 INFO [train.py:812] (0/8) Epoch 35, batch 1800, loss[loss=0.1519, simple_loss=0.2502, pruned_loss=0.0268, over 7326.00 frames.], tot_loss[loss=0.1493, simple_loss=0.241, pruned_loss=0.02878, over 1430935.66 frames.], batch size: 25, lr: 2.23e-04
+2022-05-15 23:48:43,672 INFO [train.py:812] (0/8) Epoch 35, batch 1850, loss[loss=0.1468, simple_loss=0.2364, pruned_loss=0.02864, over 7068.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2405, pruned_loss=0.0284, over 1426857.22 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:49:42,139 INFO [train.py:812] (0/8) Epoch 35, batch 1900, loss[loss=0.1879, simple_loss=0.2839, pruned_loss=0.0459, over 7376.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2406, pruned_loss=0.02861, over 1425540.92 frames.], batch size: 23, lr: 2.22e-04
+2022-05-15 23:50:51,019 INFO [train.py:812] (0/8) Epoch 35, batch 1950, loss[loss=0.141, simple_loss=0.2215, pruned_loss=0.03023, over 7156.00 frames.], tot_loss[loss=0.1495, simple_loss=0.241, pruned_loss=0.02901, over 1424370.41 frames.], batch size: 18, lr: 2.22e-04
+2022-05-15 23:51:48,111 INFO [train.py:812] (0/8) Epoch 35, batch 2000, loss[loss=0.1543, simple_loss=0.253, pruned_loss=0.02774, over 6365.00 frames.], tot_loss[loss=0.15, simple_loss=0.2417, pruned_loss=0.02917, over 1419871.75 frames.], batch size: 38, lr: 2.22e-04
+2022-05-15 23:52:46,837 INFO [train.py:812] (0/8) Epoch 35, batch 2050, loss[loss=0.1459, simple_loss=0.235, pruned_loss=0.02841, over 7121.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.02923, over 1421613.54 frames.], batch size: 21, lr: 2.22e-04
+2022-05-15 23:53:45,609 INFO [train.py:812] (0/8) Epoch 35, batch 2100, loss[loss=0.1507, simple_loss=0.2472, pruned_loss=0.02714, over 7413.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02947, over 1423991.45 frames.], batch size: 21, lr: 2.22e-04
+2022-05-15 23:54:43,304 INFO [train.py:812] (0/8) Epoch 35, batch 2150, loss[loss=0.1438, simple_loss=0.2389, pruned_loss=0.02434, over 6235.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.02937, over 1427222.73 frames.], batch size: 37, lr: 2.22e-04
+2022-05-15 23:55:40,407 INFO [train.py:812] (0/8) Epoch 35, batch 2200, loss[loss=0.1585, simple_loss=0.2617, pruned_loss=0.02762, over 7428.00 frames.], tot_loss[loss=0.1512, simple_loss=0.243, pruned_loss=0.02967, over 1423813.60 frames.], batch size: 20, lr: 2.22e-04
+2022-05-15 23:56:39,644 INFO [train.py:812] (0/8) Epoch 35, batch 2250, loss[loss=0.1277, simple_loss=0.2189, pruned_loss=0.01829, over 7283.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.02945, over 1421899.84 frames.], batch size: 18, lr: 2.22e-04
+2022-05-15 23:57:38,199 INFO [train.py:812] (0/8) Epoch 35, batch 2300, loss[loss=0.1758, simple_loss=0.281, pruned_loss=0.03532, over 7192.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.02965, over 1418668.55 frames.], batch size: 26, lr: 2.22e-04
+2022-05-15 23:58:36,587 INFO [train.py:812] (0/8) Epoch 35, batch 2350, loss[loss=0.1523, simple_loss=0.2408, pruned_loss=0.03187, over 7176.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2422, pruned_loss=0.02934, over 1416690.62 frames.], batch size: 28, lr: 2.22e-04
+2022-05-15 23:59:34,360 INFO [train.py:812] (0/8) Epoch 35, batch 2400, loss[loss=0.1519, simple_loss=0.231, pruned_loss=0.03646, over 6998.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.02934, over 1421652.22 frames.], batch size: 16, lr: 2.22e-04
+2022-05-16 00:00:32,002 INFO [train.py:812] (0/8) Epoch 35, batch 2450, loss[loss=0.1476, simple_loss=0.2324, pruned_loss=0.03144, over 7429.00 frames.], tot_loss[loss=0.1502, simple_loss=0.242, pruned_loss=0.02917, over 1422184.60 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:01:31,500 INFO [train.py:812] (0/8) Epoch 35, batch 2500, loss[loss=0.1925, simple_loss=0.2889, pruned_loss=0.04806, over 6436.00 frames.], tot_loss[loss=0.15, simple_loss=0.2416, pruned_loss=0.02921, over 1423830.44 frames.], batch size: 38, lr: 2.22e-04
+2022-05-16 00:02:30,460 INFO [train.py:812] (0/8) Epoch 35, batch 2550, loss[loss=0.1566, simple_loss=0.2575, pruned_loss=0.02781, over 7116.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2414, pruned_loss=0.02893, over 1423910.60 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:03:28,735 INFO [train.py:812] (0/8) Epoch 35, batch 2600, loss[loss=0.1631, simple_loss=0.2531, pruned_loss=0.03661, over 7199.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2413, pruned_loss=0.02919, over 1423545.52 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:04:26,540 INFO [train.py:812] (0/8) Epoch 35, batch 2650, loss[loss=0.1502, simple_loss=0.2496, pruned_loss=0.02538, over 7205.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2417, pruned_loss=0.02962, over 1421586.17 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:05:25,223 INFO [train.py:812] (0/8) Epoch 35, batch 2700, loss[loss=0.1504, simple_loss=0.2457, pruned_loss=0.02755, over 7106.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2419, pruned_loss=0.0293, over 1423713.96 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:06:24,234 INFO [train.py:812] (0/8) Epoch 35, batch 2750, loss[loss=0.1717, simple_loss=0.2697, pruned_loss=0.03688, over 7316.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2436, pruned_loss=0.02976, over 1423118.01 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:07:23,047 INFO [train.py:812] (0/8) Epoch 35, batch 2800, loss[loss=0.1206, simple_loss=0.2129, pruned_loss=0.01412, over 7327.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02984, over 1423881.13 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:08:20,795 INFO [train.py:812] (0/8) Epoch 35, batch 2850, loss[loss=0.1419, simple_loss=0.2456, pruned_loss=0.01904, over 7158.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02953, over 1421692.22 frames.], batch size: 19, lr: 2.22e-04
+2022-05-16 00:09:20,169 INFO [train.py:812] (0/8) Epoch 35, batch 2900, loss[loss=0.1391, simple_loss=0.2379, pruned_loss=0.02018, over 6615.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02915, over 1421901.73 frames.], batch size: 37, lr: 2.22e-04
+2022-05-16 00:10:18,381 INFO [train.py:812] (0/8) Epoch 35, batch 2950, loss[loss=0.1437, simple_loss=0.2344, pruned_loss=0.02651, over 6811.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2446, pruned_loss=0.02963, over 1415090.86 frames.], batch size: 15, lr: 2.22e-04
+2022-05-16 00:11:17,551 INFO [train.py:812] (0/8) Epoch 35, batch 3000, loss[loss=0.1617, simple_loss=0.2514, pruned_loss=0.03601, over 7375.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2437, pruned_loss=0.02935, over 1419392.06 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:11:17,552 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-16 00:11:25,086 INFO [train.py:841] (0/8) Epoch 35, validation: loss=0.1528, simple_loss=0.2485, pruned_loss=0.02851, over 698248.00 frames.
+2022-05-16 00:12:24,395 INFO [train.py:812] (0/8) Epoch 35, batch 3050, loss[loss=0.1542, simple_loss=0.2514, pruned_loss=0.02854, over 7228.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2441, pruned_loss=0.02926, over 1422811.72 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:13:22,720 INFO [train.py:812] (0/8) Epoch 35, batch 3100, loss[loss=0.163, simple_loss=0.253, pruned_loss=0.03655, over 7363.00 frames.], tot_loss[loss=0.1505, simple_loss=0.243, pruned_loss=0.02893, over 1419953.76 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:14:22,652 INFO [train.py:812] (0/8) Epoch 35, batch 3150, loss[loss=0.1627, simple_loss=0.2548, pruned_loss=0.0353, over 7211.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2424, pruned_loss=0.02893, over 1422465.30 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:15:21,753 INFO [train.py:812] (0/8) Epoch 35, batch 3200, loss[loss=0.1642, simple_loss=0.2561, pruned_loss=0.03619, over 7200.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2433, pruned_loss=0.02916, over 1427122.62 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:16:21,594 INFO [train.py:812] (0/8) Epoch 35, batch 3250, loss[loss=0.1603, simple_loss=0.2416, pruned_loss=0.03954, over 7433.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2433, pruned_loss=0.02922, over 1425217.67 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:17:21,157 INFO [train.py:812] (0/8) Epoch 35, batch 3300, loss[loss=0.1425, simple_loss=0.2393, pruned_loss=0.02282, over 7422.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2437, pruned_loss=0.02937, over 1426495.64 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:18:19,932 INFO [train.py:812] (0/8) Epoch 35, batch 3350, loss[loss=0.1336, simple_loss=0.2239, pruned_loss=0.02171, over 7423.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2437, pruned_loss=0.02896, over 1429574.88 frames.], batch size: 20, lr: 2.21e-04
+2022-05-16 00:19:17,056 INFO [train.py:812] (0/8) Epoch 35, batch 3400, loss[loss=0.1491, simple_loss=0.2389, pruned_loss=0.02967, over 7281.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2433, pruned_loss=0.02906, over 1425909.22 frames.], batch size: 18, lr: 2.21e-04
+2022-05-16 00:20:15,911 INFO [train.py:812] (0/8) Epoch 35, batch 3450, loss[loss=0.1399, simple_loss=0.2268, pruned_loss=0.02648, over 7001.00 frames.], tot_loss[loss=0.151, simple_loss=0.2434, pruned_loss=0.02926, over 1429161.59 frames.], batch size: 16, lr: 2.21e-04
+2022-05-16 00:21:14,788 INFO [train.py:812] (0/8) Epoch 35, batch 3500, loss[loss=0.1569, simple_loss=0.2517, pruned_loss=0.03103, over 7334.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2437, pruned_loss=0.02933, over 1428349.40 frames.], batch size: 22, lr: 2.21e-04
+2022-05-16 00:22:12,826 INFO [train.py:812] (0/8) Epoch 35, batch 3550, loss[loss=0.1562, simple_loss=0.248, pruned_loss=0.03223, over 6796.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2438, pruned_loss=0.02955, over 1421077.96 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:23:10,735 INFO [train.py:812] (0/8) Epoch 35, batch 3600, loss[loss=0.1893, simple_loss=0.2856, pruned_loss=0.04656, over 7199.00 frames.], tot_loss[loss=0.1516, simple_loss=0.244, pruned_loss=0.02958, over 1420250.57 frames.], batch size: 22, lr: 2.21e-04
+2022-05-16 00:24:08,688 INFO [train.py:812] (0/8) Epoch 35, batch 3650, loss[loss=0.1529, simple_loss=0.2489, pruned_loss=0.0285, over 7310.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2448, pruned_loss=0.02991, over 1421634.69 frames.], batch size: 25, lr: 2.21e-04
+2022-05-16 00:25:06,921 INFO [train.py:812] (0/8) Epoch 35, batch 3700, loss[loss=0.1409, simple_loss=0.2354, pruned_loss=0.02315, over 6389.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2443, pruned_loss=0.02942, over 1421505.47 frames.], batch size: 37, lr: 2.21e-04
+2022-05-16 00:26:05,695 INFO [train.py:812] (0/8) Epoch 35, batch 3750, loss[loss=0.1738, simple_loss=0.2648, pruned_loss=0.0414, over 4843.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2446, pruned_loss=0.02939, over 1419027.27 frames.], batch size: 52, lr: 2.21e-04
+2022-05-16 00:27:04,275 INFO [train.py:812] (0/8) Epoch 35, batch 3800, loss[loss=0.1584, simple_loss=0.2561, pruned_loss=0.03038, over 6717.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2451, pruned_loss=0.02985, over 1419169.06 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:28:02,102 INFO [train.py:812] (0/8) Epoch 35, batch 3850, loss[loss=0.1834, simple_loss=0.2694, pruned_loss=0.04867, over 7305.00 frames.], tot_loss[loss=0.152, simple_loss=0.2446, pruned_loss=0.02971, over 1421267.09 frames.], batch size: 24, lr: 2.21e-04
+2022-05-16 00:29:00,965 INFO [train.py:812] (0/8) Epoch 35, batch 3900, loss[loss=0.1629, simple_loss=0.2372, pruned_loss=0.04428, over 6755.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2448, pruned_loss=0.02974, over 1416902.56 frames.], batch size: 15, lr: 2.21e-04
+2022-05-16 00:30:00,069 INFO [train.py:812] (0/8) Epoch 35, batch 3950, loss[loss=0.1504, simple_loss=0.2319, pruned_loss=0.03441, over 7130.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2445, pruned_loss=0.0298, over 1418169.32 frames.], batch size: 17, lr: 2.21e-04
+2022-05-16 00:30:58,305 INFO [train.py:812] (0/8) Epoch 35, batch 4000, loss[loss=0.149, simple_loss=0.2318, pruned_loss=0.03311, over 6990.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2438, pruned_loss=0.02977, over 1418198.19 frames.], batch size: 16, lr: 2.21e-04
+2022-05-16 00:31:07,021 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-160000.pt
+2022-05-16 00:32:02,089 INFO [train.py:812] (0/8) Epoch 35, batch 4050, loss[loss=0.1564, simple_loss=0.2559, pruned_loss=0.02842, over 6348.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2443, pruned_loss=0.02956, over 1420729.81 frames.], batch size: 37, lr: 2.21e-04
+2022-05-16 00:33:00,885 INFO [train.py:812] (0/8) Epoch 35, batch 4100, loss[loss=0.1481, simple_loss=0.2443, pruned_loss=0.02597, over 7223.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2444, pruned_loss=0.0297, over 1425905.04 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:33:59,525 INFO [train.py:812] (0/8) Epoch 35, batch 4150, loss[loss=0.1566, simple_loss=0.2548, pruned_loss=0.02919, over 7315.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.0296, over 1425347.09 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:34:58,344 INFO [train.py:812] (0/8) Epoch 35, batch 4200, loss[loss=0.163, simple_loss=0.2641, pruned_loss=0.03093, over 7316.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02971, over 1423016.85 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:35:57,142 INFO [train.py:812] (0/8) Epoch 35, batch 4250, loss[loss=0.1196, simple_loss=0.2064, pruned_loss=0.01636, over 7280.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2426, pruned_loss=0.02903, over 1427911.21 frames.], batch size: 17, lr: 2.21e-04
+2022-05-16 00:36:55,253 INFO [train.py:812] (0/8) Epoch 35, batch 4300, loss[loss=0.1364, simple_loss=0.2295, pruned_loss=0.02161, over 7179.00 frames.], tot_loss[loss=0.15, simple_loss=0.2421, pruned_loss=0.02901, over 1418911.30 frames.], batch size: 26, lr: 2.21e-04
+2022-05-16 00:37:53,240 INFO [train.py:812] (0/8) Epoch 35, batch 4350, loss[loss=0.1781, simple_loss=0.2719, pruned_loss=0.04218, over 7289.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2436, pruned_loss=0.0295, over 1415157.31 frames.], batch size: 24, lr: 2.21e-04
+2022-05-16 00:38:52,034 INFO [train.py:812] (0/8) Epoch 35, batch 4400, loss[loss=0.1259, simple_loss=0.215, pruned_loss=0.01838, over 7159.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2432, pruned_loss=0.02919, over 1409422.15 frames.], batch size: 19, lr: 2.21e-04
+2022-05-16 00:39:50,183 INFO [train.py:812] (0/8) Epoch 35, batch 4450, loss[loss=0.146, simple_loss=0.2423, pruned_loss=0.02487, over 6736.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2439, pruned_loss=0.02965, over 1394073.30 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:40:48,508 INFO [train.py:812] (0/8) Epoch 35, batch 4500, loss[loss=0.1745, simple_loss=0.2658, pruned_loss=0.04158, over 7173.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2443, pruned_loss=0.03001, over 1380972.44 frames.], batch size: 26, lr: 2.21e-04
+2022-05-16 00:41:45,652 INFO [train.py:812] (0/8) Epoch 35, batch 4550, loss[loss=0.1561, simple_loss=0.2476, pruned_loss=0.03231, over 5369.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2465, pruned_loss=0.03122, over 1354862.25 frames.], batch size: 53, lr: 2.21e-04
+2022-05-16 00:42:29,925 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-35.pt
+2022-05-16 00:42:50,915 INFO [train.py:812] (0/8) Epoch 36, batch 0, loss[loss=0.1465, simple_loss=0.2369, pruned_loss=0.02808, over 7329.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2369, pruned_loss=0.02808, over 7329.00 frames.], batch size: 20, lr: 2.18e-04
+2022-05-16 00:43:50,524 INFO [train.py:812] (0/8) Epoch 36, batch 50, loss[loss=0.13, simple_loss=0.2275, pruned_loss=0.01629, over 7432.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02969, over 317314.58 frames.], batch size: 20, lr: 2.18e-04
+2022-05-16 00:44:48,775 INFO [train.py:812] (0/8) Epoch 36, batch 100, loss[loss=0.1987, simple_loss=0.2736, pruned_loss=0.06192, over 4800.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.02942, over 562296.69 frames.], batch size: 52, lr: 2.17e-04
+2022-05-16 00:45:47,221 INFO [train.py:812] (0/8) Epoch 36, batch 150, loss[loss=0.1398, simple_loss=0.2476, pruned_loss=0.01603, over 7231.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2421, pruned_loss=0.0295, over 751033.84 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:46:46,269 INFO [train.py:812] (0/8) Epoch 36, batch 200, loss[loss=0.1463, simple_loss=0.2428, pruned_loss=0.02487, over 7328.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02926, over 902092.01 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 00:47:45,328 INFO [train.py:812] (0/8) Epoch 36, batch 250, loss[loss=0.1434, simple_loss=0.2358, pruned_loss=0.02556, over 7169.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02879, over 1021255.41 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:48:43,642 INFO [train.py:812] (0/8) Epoch 36, batch 300, loss[loss=0.1789, simple_loss=0.2788, pruned_loss=0.03945, over 7178.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02894, over 1106124.01 frames.], batch size: 26, lr: 2.17e-04
+2022-05-16 00:49:42,277 INFO [train.py:812] (0/8) Epoch 36, batch 350, loss[loss=0.1639, simple_loss=0.2633, pruned_loss=0.03227, over 6728.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.029, over 1175286.64 frames.], batch size: 31, lr: 2.17e-04
+2022-05-16 00:50:40,181 INFO [train.py:812] (0/8) Epoch 36, batch 400, loss[loss=0.1595, simple_loss=0.251, pruned_loss=0.03404, over 7207.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2439, pruned_loss=0.02913, over 1231157.36 frames.], batch size: 22, lr: 2.17e-04
+2022-05-16 00:51:39,797 INFO [train.py:812] (0/8) Epoch 36, batch 450, loss[loss=0.1955, simple_loss=0.2872, pruned_loss=0.0519, over 7190.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2438, pruned_loss=0.02919, over 1278737.46 frames.], batch size: 26, lr: 2.17e-04
+2022-05-16 00:52:38,603 INFO [train.py:812] (0/8) Epoch 36, batch 500, loss[loss=0.1484, simple_loss=0.2339, pruned_loss=0.03142, over 7192.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2439, pruned_loss=0.0295, over 1310152.24 frames.], batch size: 23, lr: 2.17e-04
+2022-05-16 00:53:37,429 INFO [train.py:812] (0/8) Epoch 36, batch 550, loss[loss=0.1532, simple_loss=0.2454, pruned_loss=0.03053, over 7435.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2449, pruned_loss=0.02962, over 1336537.98 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:54:35,747 INFO [train.py:812] (0/8) Epoch 36, batch 600, loss[loss=0.1651, simple_loss=0.2606, pruned_loss=0.0348, over 7199.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2438, pruned_loss=0.02948, over 1358843.26 frames.], batch size: 23, lr: 2.17e-04
+2022-05-16 00:55:34,845 INFO [train.py:812] (0/8) Epoch 36, batch 650, loss[loss=0.1497, simple_loss=0.2449, pruned_loss=0.02723, over 7151.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2429, pruned_loss=0.02946, over 1373963.79 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:56:33,800 INFO [train.py:812] (0/8) Epoch 36, batch 700, loss[loss=0.1445, simple_loss=0.2331, pruned_loss=0.02796, over 7263.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2428, pruned_loss=0.02967, over 1384980.31 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:57:42,558 INFO [train.py:812] (0/8) Epoch 36, batch 750, loss[loss=0.1746, simple_loss=0.2706, pruned_loss=0.03928, over 7324.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02949, over 1384876.40 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:58:59,872 INFO [train.py:812] (0/8) Epoch 36, batch 800, loss[loss=0.1557, simple_loss=0.2531, pruned_loss=0.02911, over 7408.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02946, over 1393650.62 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 00:59:58,233 INFO [train.py:812] (0/8) Epoch 36, batch 850, loss[loss=0.1345, simple_loss=0.2343, pruned_loss=0.01732, over 7225.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2429, pruned_loss=0.02947, over 1395005.93 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 01:00:57,351 INFO [train.py:812] (0/8) Epoch 36, batch 900, loss[loss=0.1441, simple_loss=0.2388, pruned_loss=0.02474, over 6915.00 frames.], tot_loss[loss=0.1507, simple_loss=0.243, pruned_loss=0.02916, over 1402162.92 frames.], batch size: 31, lr: 2.17e-04
+2022-05-16 01:01:55,269 INFO [train.py:812] (0/8) Epoch 36, batch 950, loss[loss=0.1491, simple_loss=0.2345, pruned_loss=0.03189, over 6987.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02952, over 1406471.51 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:03:03,215 INFO [train.py:812] (0/8) Epoch 36, batch 1000, loss[loss=0.1313, simple_loss=0.2197, pruned_loss=0.02144, over 7276.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2429, pruned_loss=0.02942, over 1408242.76 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:04:02,086 INFO [train.py:812] (0/8) Epoch 36, batch 1050, loss[loss=0.1258, simple_loss=0.2242, pruned_loss=0.01368, over 7365.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.02943, over 1408696.44 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 01:05:09,917 INFO [train.py:812] (0/8) Epoch 36, batch 1100, loss[loss=0.1711, simple_loss=0.2623, pruned_loss=0.03996, over 7196.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02955, over 1408378.69 frames.], batch size: 22, lr: 2.17e-04
+2022-05-16 01:06:19,082 INFO [train.py:812] (0/8) Epoch 36, batch 1150, loss[loss=0.1592, simple_loss=0.2584, pruned_loss=0.02997, over 7288.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02961, over 1413600.91 frames.], batch size: 24, lr: 2.17e-04
+2022-05-16 01:07:18,009 INFO [train.py:812] (0/8) Epoch 36, batch 1200, loss[loss=0.1215, simple_loss=0.2097, pruned_loss=0.01665, over 7286.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2439, pruned_loss=0.02996, over 1409510.88 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:08:16,990 INFO [train.py:812] (0/8) Epoch 36, batch 1250, loss[loss=0.1356, simple_loss=0.2262, pruned_loss=0.02252, over 7001.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02971, over 1410971.55 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:09:23,811 INFO [train.py:812] (0/8) Epoch 36, batch 1300, loss[loss=0.1476, simple_loss=0.2377, pruned_loss=0.02872, over 7140.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2427, pruned_loss=0.02928, over 1415321.59 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:10:23,380 INFO [train.py:812] (0/8) Epoch 36, batch 1350, loss[loss=0.1386, simple_loss=0.2301, pruned_loss=0.02349, over 7259.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2414, pruned_loss=0.02908, over 1420311.15 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 01:11:21,708 INFO [train.py:812] (0/8) Epoch 36, batch 1400, loss[loss=0.1393, simple_loss=0.2194, pruned_loss=0.02959, over 7007.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2419, pruned_loss=0.02923, over 1419122.97 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:12:20,389 INFO [train.py:812] (0/8) Epoch 36, batch 1450, loss[loss=0.1309, simple_loss=0.2139, pruned_loss=0.02399, over 6857.00 frames.], tot_loss[loss=0.15, simple_loss=0.2417, pruned_loss=0.02915, over 1415645.33 frames.], batch size: 15, lr: 2.17e-04
+2022-05-16 01:13:19,188 INFO [train.py:812] (0/8) Epoch 36, batch 1500, loss[loss=0.1541, simple_loss=0.2451, pruned_loss=0.03156, over 7308.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2424, pruned_loss=0.02911, over 1419464.40 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 01:14:17,131 INFO [train.py:812] (0/8) Epoch 36, batch 1550, loss[loss=0.1365, simple_loss=0.2291, pruned_loss=0.0219, over 7226.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2423, pruned_loss=0.02869, over 1421198.55 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 01:15:14,902 INFO [train.py:812] (0/8) Epoch 36, batch 1600, loss[loss=0.1686, simple_loss=0.256, pruned_loss=0.04055, over 7393.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02899, over 1420920.28 frames.], batch size: 23, lr: 2.16e-04
+2022-05-16 01:16:13,257 INFO [train.py:812] (0/8) Epoch 36, batch 1650, loss[loss=0.1403, simple_loss=0.2306, pruned_loss=0.02504, over 7163.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02887, over 1421927.12 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:17:10,674 INFO [train.py:812] (0/8) Epoch 36, batch 1700, loss[loss=0.1781, simple_loss=0.2648, pruned_loss=0.04576, over 7293.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02915, over 1424255.16 frames.], batch size: 25, lr: 2.16e-04
+2022-05-16 01:18:09,649 INFO [train.py:812] (0/8) Epoch 36, batch 1750, loss[loss=0.1334, simple_loss=0.2206, pruned_loss=0.02305, over 7280.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2429, pruned_loss=0.02929, over 1420463.89 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:19:07,100 INFO [train.py:812] (0/8) Epoch 36, batch 1800, loss[loss=0.1695, simple_loss=0.2585, pruned_loss=0.04027, over 7188.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2437, pruned_loss=0.0293, over 1422754.81 frames.], batch size: 23, lr: 2.16e-04
+2022-05-16 01:20:05,568 INFO [train.py:812] (0/8) Epoch 36, batch 1850, loss[loss=0.1576, simple_loss=0.2532, pruned_loss=0.03104, over 7120.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.02926, over 1425219.28 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:21:04,165 INFO [train.py:812] (0/8) Epoch 36, batch 1900, loss[loss=0.1477, simple_loss=0.2393, pruned_loss=0.02809, over 6869.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.02963, over 1426351.59 frames.], batch size: 31, lr: 2.16e-04
+2022-05-16 01:22:03,011 INFO [train.py:812] (0/8) Epoch 36, batch 1950, loss[loss=0.1436, simple_loss=0.2427, pruned_loss=0.02224, over 7235.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02936, over 1423710.64 frames.], batch size: 20, lr: 2.16e-04
+2022-05-16 01:23:01,527 INFO [train.py:812] (0/8) Epoch 36, batch 2000, loss[loss=0.1402, simple_loss=0.2363, pruned_loss=0.02208, over 7004.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.0297, over 1420746.62 frames.], batch size: 16, lr: 2.16e-04
+2022-05-16 01:24:00,327 INFO [train.py:812] (0/8) Epoch 36, batch 2050, loss[loss=0.1659, simple_loss=0.2713, pruned_loss=0.03026, over 7315.00 frames.], tot_loss[loss=0.1517, simple_loss=0.244, pruned_loss=0.02973, over 1425061.90 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:24:59,285 INFO [train.py:812] (0/8) Epoch 36, batch 2100, loss[loss=0.1479, simple_loss=0.2488, pruned_loss=0.02344, over 7420.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2427, pruned_loss=0.02933, over 1424116.52 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:25:59,146 INFO [train.py:812] (0/8) Epoch 36, batch 2150, loss[loss=0.1472, simple_loss=0.241, pruned_loss=0.02668, over 7255.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02907, over 1426961.13 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:26:58,702 INFO [train.py:812] (0/8) Epoch 36, batch 2200, loss[loss=0.1364, simple_loss=0.2202, pruned_loss=0.02627, over 7401.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02895, over 1425895.68 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:27:57,342 INFO [train.py:812] (0/8) Epoch 36, batch 2250, loss[loss=0.151, simple_loss=0.2465, pruned_loss=0.02777, over 7350.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2433, pruned_loss=0.02889, over 1422459.46 frames.], batch size: 22, lr: 2.16e-04
+2022-05-16 01:28:55,630 INFO [train.py:812] (0/8) Epoch 36, batch 2300, loss[loss=0.1367, simple_loss=0.2268, pruned_loss=0.02333, over 7130.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02878, over 1425166.14 frames.], batch size: 17, lr: 2.16e-04
+2022-05-16 01:29:55,173 INFO [train.py:812] (0/8) Epoch 36, batch 2350, loss[loss=0.1782, simple_loss=0.2637, pruned_loss=0.04638, over 5251.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02913, over 1424122.66 frames.], batch size: 52, lr: 2.16e-04
+2022-05-16 01:30:54,420 INFO [train.py:812] (0/8) Epoch 36, batch 2400, loss[loss=0.1557, simple_loss=0.2463, pruned_loss=0.03261, over 7415.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02918, over 1427863.52 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:31:54,041 INFO [train.py:812] (0/8) Epoch 36, batch 2450, loss[loss=0.1323, simple_loss=0.2216, pruned_loss=0.02148, over 7167.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02898, over 1423626.25 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:32:52,237 INFO [train.py:812] (0/8) Epoch 36, batch 2500, loss[loss=0.1537, simple_loss=0.2542, pruned_loss=0.02661, over 7149.00 frames.], tot_loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.02863, over 1427449.76 frames.], batch size: 20, lr: 2.16e-04
+2022-05-16 01:33:51,369 INFO [train.py:812] (0/8) Epoch 36, batch 2550, loss[loss=0.1306, simple_loss=0.2239, pruned_loss=0.01862, over 7364.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2426, pruned_loss=0.02904, over 1424101.78 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:34:50,031 INFO [train.py:812] (0/8) Epoch 36, batch 2600, loss[loss=0.1581, simple_loss=0.2455, pruned_loss=0.03533, over 7143.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2425, pruned_loss=0.02912, over 1424262.97 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:35:48,593 INFO [train.py:812] (0/8) Epoch 36, batch 2650, loss[loss=0.2397, simple_loss=0.3168, pruned_loss=0.08125, over 4844.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02906, over 1422932.39 frames.], batch size: 52, lr: 2.16e-04
+2022-05-16 01:36:46,989 INFO [train.py:812] (0/8) Epoch 36, batch 2700, loss[loss=0.1484, simple_loss=0.2499, pruned_loss=0.02352, over 7319.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02882, over 1424188.82 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:37:45,792 INFO [train.py:812] (0/8) Epoch 36, batch 2750, loss[loss=0.1551, simple_loss=0.2521, pruned_loss=0.02899, over 7115.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2414, pruned_loss=0.02869, over 1426936.29 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:38:45,026 INFO [train.py:812] (0/8) Epoch 36, batch 2800, loss[loss=0.1709, simple_loss=0.2722, pruned_loss=0.03484, over 7208.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2409, pruned_loss=0.02878, over 1428308.85 frames.], batch size: 22, lr: 2.16e-04
+2022-05-16 01:39:44,884 INFO [train.py:812] (0/8) Epoch 36, batch 2850, loss[loss=0.1302, simple_loss=0.2158, pruned_loss=0.02224, over 7288.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2403, pruned_loss=0.02877, over 1428898.87 frames.], batch size: 17, lr: 2.16e-04
+2022-05-16 01:40:43,962 INFO [train.py:812] (0/8) Epoch 36, batch 2900, loss[loss=0.1297, simple_loss=0.2267, pruned_loss=0.01636, over 7261.00 frames.], tot_loss[loss=0.149, simple_loss=0.24, pruned_loss=0.02905, over 1427803.67 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:41:42,649 INFO [train.py:812] (0/8) Epoch 36, batch 2950, loss[loss=0.1346, simple_loss=0.2224, pruned_loss=0.02337, over 7156.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2411, pruned_loss=0.02919, over 1425636.05 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:42:41,189 INFO [train.py:812] (0/8) Epoch 36, batch 3000, loss[loss=0.1391, simple_loss=0.237, pruned_loss=0.02061, over 7167.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.02949, over 1421760.15 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:42:41,190 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-16 01:42:48,527 INFO [train.py:841] (0/8) Epoch 36, validation: loss=0.1533, simple_loss=0.2487, pruned_loss=0.02893, over 698248.00 frames.
+2022-05-16 01:43:48,418 INFO [train.py:812] (0/8) Epoch 36, batch 3050, loss[loss=0.1601, simple_loss=0.2584, pruned_loss=0.03093, over 7295.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.02929, over 1423989.31 frames.], batch size: 24, lr: 2.16e-04
+2022-05-16 01:44:47,691 INFO [train.py:812] (0/8) Epoch 36, batch 3100, loss[loss=0.1718, simple_loss=0.2641, pruned_loss=0.03972, over 7308.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02916, over 1428422.38 frames.], batch size: 25, lr: 2.15e-04
+2022-05-16 01:45:47,582 INFO [train.py:812] (0/8) Epoch 36, batch 3150, loss[loss=0.1656, simple_loss=0.2625, pruned_loss=0.03434, over 7368.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02898, over 1427057.96 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:46:46,194 INFO [train.py:812] (0/8) Epoch 36, batch 3200, loss[loss=0.1254, simple_loss=0.2093, pruned_loss=0.02079, over 7124.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2425, pruned_loss=0.02955, over 1420728.43 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 01:47:45,912 INFO [train.py:812] (0/8) Epoch 36, batch 3250, loss[loss=0.1634, simple_loss=0.2493, pruned_loss=0.03881, over 4880.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02983, over 1417617.56 frames.], batch size: 52, lr: 2.15e-04
+2022-05-16 01:48:53,221 INFO [train.py:812] (0/8) Epoch 36, batch 3300, loss[loss=0.1578, simple_loss=0.2686, pruned_loss=0.02354, over 7216.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2439, pruned_loss=0.02963, over 1421576.61 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:49:52,249 INFO [train.py:812] (0/8) Epoch 36, batch 3350, loss[loss=0.1672, simple_loss=0.2513, pruned_loss=0.0416, over 7192.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.02939, over 1426186.37 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:50:50,249 INFO [train.py:812] (0/8) Epoch 36, batch 3400, loss[loss=0.1299, simple_loss=0.2208, pruned_loss=0.01949, over 7262.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02916, over 1424687.89 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 01:51:13,275 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-164000.pt
+2022-05-16 01:51:53,844 INFO [train.py:812] (0/8) Epoch 36, batch 3450, loss[loss=0.1333, simple_loss=0.219, pruned_loss=0.02383, over 7278.00 frames.], tot_loss[loss=0.15, simple_loss=0.2419, pruned_loss=0.02906, over 1421792.00 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 01:52:52,274 INFO [train.py:812] (0/8) Epoch 36, batch 3500, loss[loss=0.168, simple_loss=0.2771, pruned_loss=0.02944, over 7410.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2417, pruned_loss=0.02907, over 1419146.85 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 01:53:50,960 INFO [train.py:812] (0/8) Epoch 36, batch 3550, loss[loss=0.1348, simple_loss=0.2315, pruned_loss=0.01902, over 7092.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02899, over 1422876.88 frames.], batch size: 28, lr: 2.15e-04
+2022-05-16 01:54:49,011 INFO [train.py:812] (0/8) Epoch 36, batch 3600, loss[loss=0.1694, simple_loss=0.2716, pruned_loss=0.03357, over 7285.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02913, over 1421328.91 frames.], batch size: 25, lr: 2.15e-04
+2022-05-16 01:55:48,150 INFO [train.py:812] (0/8) Epoch 36, batch 3650, loss[loss=0.1677, simple_loss=0.2646, pruned_loss=0.03537, over 7291.00 frames.], tot_loss[loss=0.1499, simple_loss=0.242, pruned_loss=0.02886, over 1423051.66 frames.], batch size: 24, lr: 2.15e-04
+2022-05-16 01:56:46,026 INFO [train.py:812] (0/8) Epoch 36, batch 3700, loss[loss=0.1502, simple_loss=0.2414, pruned_loss=0.02956, over 7113.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02882, over 1426573.01 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 01:57:44,755 INFO [train.py:812] (0/8) Epoch 36, batch 3750, loss[loss=0.1678, simple_loss=0.2685, pruned_loss=0.03356, over 7329.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02891, over 1426131.61 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 01:58:43,594 INFO [train.py:812] (0/8) Epoch 36, batch 3800, loss[loss=0.1427, simple_loss=0.2392, pruned_loss=0.02307, over 7357.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2435, pruned_loss=0.0294, over 1428067.14 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 01:59:42,833 INFO [train.py:812] (0/8) Epoch 36, batch 3850, loss[loss=0.1237, simple_loss=0.2069, pruned_loss=0.02019, over 7013.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02964, over 1423796.40 frames.], batch size: 16, lr: 2.15e-04
+2022-05-16 02:00:41,784 INFO [train.py:812] (0/8) Epoch 36, batch 3900, loss[loss=0.151, simple_loss=0.2419, pruned_loss=0.03003, over 7211.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02971, over 1425708.69 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 02:01:40,054 INFO [train.py:812] (0/8) Epoch 36, batch 3950, loss[loss=0.172, simple_loss=0.269, pruned_loss=0.03755, over 6741.00 frames.], tot_loss[loss=0.152, simple_loss=0.2442, pruned_loss=0.02991, over 1423932.91 frames.], batch size: 31, lr: 2.15e-04
+2022-05-16 02:02:38,477 INFO [train.py:812] (0/8) Epoch 36, batch 4000, loss[loss=0.1572, simple_loss=0.2485, pruned_loss=0.03292, over 7097.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2443, pruned_loss=0.0298, over 1423697.36 frames.], batch size: 28, lr: 2.15e-04
+2022-05-16 02:03:36,279 INFO [train.py:812] (0/8) Epoch 36, batch 4050, loss[loss=0.1429, simple_loss=0.2444, pruned_loss=0.02076, over 7215.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2441, pruned_loss=0.02934, over 1425832.43 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:04:34,898 INFO [train.py:812] (0/8) Epoch 36, batch 4100, loss[loss=0.1226, simple_loss=0.2061, pruned_loss=0.01952, over 7151.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2433, pruned_loss=0.02909, over 1426812.20 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 02:05:34,470 INFO [train.py:812] (0/8) Epoch 36, batch 4150, loss[loss=0.1454, simple_loss=0.2425, pruned_loss=0.02415, over 7209.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02891, over 1418802.82 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 02:06:32,914 INFO [train.py:812] (0/8) Epoch 36, batch 4200, loss[loss=0.1443, simple_loss=0.2374, pruned_loss=0.02561, over 7235.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02897, over 1417067.63 frames.], batch size: 20, lr: 2.15e-04
+2022-05-16 02:07:31,844 INFO [train.py:812] (0/8) Epoch 36, batch 4250, loss[loss=0.1613, simple_loss=0.2621, pruned_loss=0.0302, over 7198.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02898, over 1415848.93 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 02:08:31,000 INFO [train.py:812] (0/8) Epoch 36, batch 4300, loss[loss=0.1493, simple_loss=0.239, pruned_loss=0.02981, over 7200.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2416, pruned_loss=0.02903, over 1412218.87 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 02:09:30,579 INFO [train.py:812] (0/8) Epoch 36, batch 4350, loss[loss=0.1546, simple_loss=0.2429, pruned_loss=0.03316, over 7427.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2415, pruned_loss=0.02885, over 1411356.38 frames.], batch size: 20, lr: 2.15e-04
+2022-05-16 02:10:29,636 INFO [train.py:812] (0/8) Epoch 36, batch 4400, loss[loss=0.1373, simple_loss=0.2329, pruned_loss=0.02083, over 7347.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2407, pruned_loss=0.0283, over 1415494.92 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 02:11:29,738 INFO [train.py:812] (0/8) Epoch 36, batch 4450, loss[loss=0.1345, simple_loss=0.2195, pruned_loss=0.0248, over 7218.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2403, pruned_loss=0.02831, over 1406610.45 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:12:28,147 INFO [train.py:812] (0/8) Epoch 36, batch 4500, loss[loss=0.1541, simple_loss=0.2512, pruned_loss=0.02844, over 7210.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2401, pruned_loss=0.0282, over 1393862.21 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:13:26,408 INFO [train.py:812] (0/8) Epoch 36, batch 4550, loss[loss=0.1416, simple_loss=0.2308, pruned_loss=0.02618, over 7239.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2412, pruned_loss=0.02895, over 1355037.65 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 02:14:11,518 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-36.pt
+2022-05-16 02:14:35,972 INFO [train.py:812] (0/8) Epoch 37, batch 0, loss[loss=0.1543, simple_loss=0.2625, pruned_loss=0.02305, over 7342.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2625, pruned_loss=0.02305, over 7342.00 frames.], batch size: 22, lr: 2.12e-04
+2022-05-16 02:15:34,995 INFO [train.py:812] (0/8) Epoch 37, batch 50, loss[loss=0.1488, simple_loss=0.2364, pruned_loss=0.03056, over 7076.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2435, pruned_loss=0.02899, over 321286.46 frames.], batch size: 18, lr: 2.12e-04
+2022-05-16 02:16:33,779 INFO [train.py:812] (0/8) Epoch 37, batch 100, loss[loss=0.1402, simple_loss=0.2399, pruned_loss=0.02026, over 7326.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2434, pruned_loss=0.02844, over 567291.28 frames.], batch size: 20, lr: 2.12e-04
+2022-05-16 02:17:32,747 INFO [train.py:812] (0/8) Epoch 37, batch 150, loss[loss=0.1543, simple_loss=0.2572, pruned_loss=0.02569, over 7096.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2439, pruned_loss=0.02874, over 755075.58 frames.], batch size: 28, lr: 2.11e-04
+2022-05-16 02:18:31,110 INFO [train.py:812] (0/8) Epoch 37, batch 200, loss[loss=0.1243, simple_loss=0.2206, pruned_loss=0.014, over 7313.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2456, pruned_loss=0.02913, over 906566.93 frames.], batch size: 21, lr: 2.11e-04
+2022-05-16 02:19:29,650 INFO [train.py:812] (0/8) Epoch 37, batch 250, loss[loss=0.1334, simple_loss=0.2269, pruned_loss=0.01993, over 7263.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2428, pruned_loss=0.02843, over 1018195.24 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:20:28,594 INFO [train.py:812] (0/8) Epoch 37, batch 300, loss[loss=0.1432, simple_loss=0.2322, pruned_loss=0.02712, over 7343.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2422, pruned_loss=0.02859, over 1104381.77 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:21:27,109 INFO [train.py:812] (0/8) Epoch 37, batch 350, loss[loss=0.1194, simple_loss=0.205, pruned_loss=0.01694, over 7168.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2422, pruned_loss=0.02845, over 1172743.85 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:22:25,666 INFO [train.py:812] (0/8) Epoch 37, batch 400, loss[loss=0.1645, simple_loss=0.2513, pruned_loss=0.03885, over 7237.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2419, pruned_loss=0.02862, over 1232272.71 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:23:24,540 INFO [train.py:812] (0/8) Epoch 37, batch 450, loss[loss=0.137, simple_loss=0.2283, pruned_loss=0.02283, over 7135.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2422, pruned_loss=0.02838, over 1277248.37 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:24:21,841 INFO [train.py:812] (0/8) Epoch 37, batch 500, loss[loss=0.1399, simple_loss=0.237, pruned_loss=0.02138, over 7236.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2421, pruned_loss=0.02846, over 1307044.43 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:25:21,110 INFO [train.py:812] (0/8) Epoch 37, batch 550, loss[loss=0.1247, simple_loss=0.209, pruned_loss=0.02021, over 7064.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2423, pruned_loss=0.02862, over 1323342.19 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:26:19,457 INFO [train.py:812] (0/8) Epoch 37, batch 600, loss[loss=0.1357, simple_loss=0.2228, pruned_loss=0.02424, over 7422.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02879, over 1348679.68 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:27:18,097 INFO [train.py:812] (0/8) Epoch 37, batch 650, loss[loss=0.1182, simple_loss=0.2072, pruned_loss=0.01459, over 7148.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2404, pruned_loss=0.0281, over 1367626.69 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:28:16,739 INFO [train.py:812] (0/8) Epoch 37, batch 700, loss[loss=0.14, simple_loss=0.2421, pruned_loss=0.01895, over 7235.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2404, pruned_loss=0.02803, over 1380410.52 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:29:16,751 INFO [train.py:812] (0/8) Epoch 37, batch 750, loss[loss=0.1388, simple_loss=0.2321, pruned_loss=0.02279, over 7162.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2401, pruned_loss=0.02804, over 1389318.27 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:30:15,257 INFO [train.py:812] (0/8) Epoch 37, batch 800, loss[loss=0.1237, simple_loss=0.2118, pruned_loss=0.01784, over 7407.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2399, pruned_loss=0.02833, over 1398851.89 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:31:14,041 INFO [train.py:812] (0/8) Epoch 37, batch 850, loss[loss=0.1317, simple_loss=0.2238, pruned_loss=0.0198, over 7263.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2408, pruned_loss=0.02869, over 1397642.80 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:32:12,857 INFO [train.py:812] (0/8) Epoch 37, batch 900, loss[loss=0.1454, simple_loss=0.2349, pruned_loss=0.02795, over 7454.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2415, pruned_loss=0.02863, over 1406586.88 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:33:11,830 INFO [train.py:812] (0/8) Epoch 37, batch 950, loss[loss=0.1457, simple_loss=0.2282, pruned_loss=0.03162, over 7284.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02878, over 1410080.35 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:34:09,790 INFO [train.py:812] (0/8) Epoch 37, batch 1000, loss[loss=0.1634, simple_loss=0.2524, pruned_loss=0.0372, over 6708.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02838, over 1412718.03 frames.], batch size: 31, lr: 2.11e-04
+2022-05-16 02:35:08,651 INFO [train.py:812] (0/8) Epoch 37, batch 1050, loss[loss=0.1865, simple_loss=0.2762, pruned_loss=0.04844, over 7360.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2414, pruned_loss=0.02852, over 1417748.80 frames.], batch size: 23, lr: 2.11e-04
+2022-05-16 02:36:07,923 INFO [train.py:812] (0/8) Epoch 37, batch 1100, loss[loss=0.1564, simple_loss=0.2563, pruned_loss=0.02826, over 7220.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2417, pruned_loss=0.02863, over 1418561.15 frames.], batch size: 21, lr: 2.11e-04
+2022-05-16 02:37:06,616 INFO [train.py:812] (0/8) Epoch 37, batch 1150, loss[loss=0.1429, simple_loss=0.2374, pruned_loss=0.02418, over 4825.00 frames.], tot_loss[loss=0.149, simple_loss=0.2412, pruned_loss=0.02843, over 1416903.75 frames.], batch size: 52, lr: 2.11e-04
+2022-05-16 02:38:04,298 INFO [train.py:812] (0/8) Epoch 37, batch 1200, loss[loss=0.1746, simple_loss=0.2632, pruned_loss=0.04306, over 7150.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2423, pruned_loss=0.02869, over 1419554.64 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:39:03,401 INFO [train.py:812] (0/8) Epoch 37, batch 1250, loss[loss=0.1462, simple_loss=0.2509, pruned_loss=0.02078, over 7209.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2429, pruned_loss=0.02876, over 1419854.73 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:40:01,885 INFO [train.py:812] (0/8) Epoch 37, batch 1300, loss[loss=0.1359, simple_loss=0.2216, pruned_loss=0.02507, over 7144.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2427, pruned_loss=0.02842, over 1422432.28 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:41:00,868 INFO [train.py:812] (0/8) Epoch 37, batch 1350, loss[loss=0.1462, simple_loss=0.2314, pruned_loss=0.03047, over 7063.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2432, pruned_loss=0.02894, over 1418329.31 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:41:59,961 INFO [train.py:812] (0/8) Epoch 37, batch 1400, loss[loss=0.1241, simple_loss=0.2066, pruned_loss=0.02079, over 6991.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2423, pruned_loss=0.02865, over 1417777.81 frames.], batch size: 16, lr: 2.11e-04
+2022-05-16 02:42:58,487 INFO [train.py:812] (0/8) Epoch 37, batch 1450, loss[loss=0.1639, simple_loss=0.249, pruned_loss=0.03944, over 7289.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02876, over 1419170.39 frames.], batch size: 24, lr: 2.11e-04
+2022-05-16 02:43:56,626 INFO [train.py:812] (0/8) Epoch 37, batch 1500, loss[loss=0.1755, simple_loss=0.2772, pruned_loss=0.0369, over 7289.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2439, pruned_loss=0.02945, over 1416612.17 frames.], batch size: 24, lr: 2.11e-04
+2022-05-16 02:44:55,805 INFO [train.py:812] (0/8) Epoch 37, batch 1550, loss[loss=0.1746, simple_loss=0.2729, pruned_loss=0.03818, over 6704.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2442, pruned_loss=0.03013, over 1411158.12 frames.], batch size: 31, lr: 2.11e-04
+2022-05-16 02:45:53,998 INFO [train.py:812] (0/8) Epoch 37, batch 1600, loss[loss=0.1675, simple_loss=0.2603, pruned_loss=0.03736, over 7390.00 frames.], tot_loss[loss=0.1515, simple_loss=0.243, pruned_loss=0.03001, over 1411538.97 frames.], batch size: 23, lr: 2.11e-04
+2022-05-16 02:46:52,088 INFO [train.py:812] (0/8) Epoch 37, batch 1650, loss[loss=0.1654, simple_loss=0.2672, pruned_loss=0.03179, over 7201.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.02961, over 1414421.79 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:47:50,654 INFO [train.py:812] (0/8) Epoch 37, batch 1700, loss[loss=0.1355, simple_loss=0.2241, pruned_loss=0.02343, over 7157.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2429, pruned_loss=0.02947, over 1413133.42 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:48:48,770 INFO [train.py:812] (0/8) Epoch 37, batch 1750, loss[loss=0.1547, simple_loss=0.2534, pruned_loss=0.02804, over 7358.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02957, over 1406804.74 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:49:47,207 INFO [train.py:812] (0/8) Epoch 37, batch 1800, loss[loss=0.1715, simple_loss=0.2606, pruned_loss=0.04117, over 7289.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02988, over 1409410.87 frames.], batch size: 24, lr: 2.10e-04
+2022-05-16 02:50:46,353 INFO [train.py:812] (0/8) Epoch 37, batch 1850, loss[loss=0.1297, simple_loss=0.2201, pruned_loss=0.0197, over 7271.00 frames.], tot_loss[loss=0.1512, simple_loss=0.243, pruned_loss=0.02969, over 1410589.41 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:51:45,049 INFO [train.py:812] (0/8) Epoch 37, batch 1900, loss[loss=0.1748, simple_loss=0.2718, pruned_loss=0.03887, over 6798.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2444, pruned_loss=0.02972, over 1416571.02 frames.], batch size: 31, lr: 2.10e-04
+2022-05-16 02:52:44,043 INFO [train.py:812] (0/8) Epoch 37, batch 1950, loss[loss=0.1428, simple_loss=0.2401, pruned_loss=0.02274, over 7222.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2438, pruned_loss=0.02958, over 1419681.11 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:53:42,402 INFO [train.py:812] (0/8) Epoch 37, batch 2000, loss[loss=0.1437, simple_loss=0.2455, pruned_loss=0.02089, over 7413.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2438, pruned_loss=0.02943, over 1416927.38 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:54:41,774 INFO [train.py:812] (0/8) Epoch 37, batch 2050, loss[loss=0.1557, simple_loss=0.2548, pruned_loss=0.02828, over 7238.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02924, over 1419542.52 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 02:55:38,571 INFO [train.py:812] (0/8) Epoch 37, batch 2100, loss[loss=0.1635, simple_loss=0.2486, pruned_loss=0.0392, over 7140.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2426, pruned_loss=0.02897, over 1420002.71 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 02:56:46,818 INFO [train.py:812] (0/8) Epoch 37, batch 2150, loss[loss=0.1464, simple_loss=0.2447, pruned_loss=0.0241, over 7416.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02902, over 1417865.24 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:57:45,134 INFO [train.py:812] (0/8) Epoch 37, batch 2200, loss[loss=0.1357, simple_loss=0.223, pruned_loss=0.02415, over 7263.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02874, over 1419734.60 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:58:53,433 INFO [train.py:812] (0/8) Epoch 37, batch 2250, loss[loss=0.1696, simple_loss=0.2708, pruned_loss=0.03421, over 7150.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02907, over 1420211.43 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 03:00:01,341 INFO [train.py:812] (0/8) Epoch 37, batch 2300, loss[loss=0.1767, simple_loss=0.2756, pruned_loss=0.03886, over 7199.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2432, pruned_loss=0.02915, over 1420006.31 frames.], batch size: 23, lr: 2.10e-04
+2022-05-16 03:01:01,059 INFO [train.py:812] (0/8) Epoch 37, batch 2350, loss[loss=0.1216, simple_loss=0.2043, pruned_loss=0.01941, over 7274.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02928, over 1413266.69 frames.], batch size: 17, lr: 2.10e-04
+2022-05-16 03:01:59,217 INFO [train.py:812] (0/8) Epoch 37, batch 2400, loss[loss=0.1693, simple_loss=0.2679, pruned_loss=0.03532, over 7316.00 frames.], tot_loss[loss=0.1502, simple_loss=0.242, pruned_loss=0.02916, over 1419406.82 frames.], batch size: 25, lr: 2.10e-04
+2022-05-16 03:02:57,099 INFO [train.py:812] (0/8) Epoch 37, batch 2450, loss[loss=0.1762, simple_loss=0.2682, pruned_loss=0.04208, over 7163.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2417, pruned_loss=0.02909, over 1424507.90 frames.], batch size: 26, lr: 2.10e-04
+2022-05-16 03:04:04,661 INFO [train.py:812] (0/8) Epoch 37, batch 2500, loss[loss=0.1481, simple_loss=0.239, pruned_loss=0.02863, over 7155.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2414, pruned_loss=0.02895, over 1427116.57 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 03:05:04,379 INFO [train.py:812] (0/8) Epoch 37, batch 2550, loss[loss=0.1473, simple_loss=0.2404, pruned_loss=0.02707, over 7287.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02895, over 1427747.67 frames.], batch size: 24, lr: 2.10e-04
+2022-05-16 03:06:02,695 INFO [train.py:812] (0/8) Epoch 37, batch 2600, loss[loss=0.1279, simple_loss=0.2104, pruned_loss=0.02269, over 6788.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02888, over 1424832.88 frames.], batch size: 15, lr: 2.10e-04
+2022-05-16 03:07:21,585 INFO [train.py:812] (0/8) Epoch 37, batch 2650, loss[loss=0.1809, simple_loss=0.2764, pruned_loss=0.04273, over 7188.00 frames.], tot_loss[loss=0.15, simple_loss=0.2426, pruned_loss=0.0287, over 1427892.42 frames.], batch size: 22, lr: 2.10e-04
+2022-05-16 03:08:19,691 INFO [train.py:812] (0/8) Epoch 37, batch 2700, loss[loss=0.1443, simple_loss=0.2476, pruned_loss=0.0205, over 6338.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2423, pruned_loss=0.02862, over 1425177.59 frames.], batch size: 37, lr: 2.10e-04
+2022-05-16 03:09:18,860 INFO [train.py:812] (0/8) Epoch 37, batch 2750, loss[loss=0.1739, simple_loss=0.2596, pruned_loss=0.0441, over 5009.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2429, pruned_loss=0.02862, over 1425245.41 frames.], batch size: 52, lr: 2.10e-04
+2022-05-16 03:10:16,997 INFO [train.py:812] (0/8) Epoch 37, batch 2800, loss[loss=0.1205, simple_loss=0.2032, pruned_loss=0.01889, over 7274.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02853, over 1429421.10 frames.], batch size: 18, lr: 2.10e-04
+2022-05-16 03:11:03,437 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-168000.pt
+2022-05-16 03:11:34,308 INFO [train.py:812] (0/8) Epoch 37, batch 2850, loss[loss=0.173, simple_loss=0.2627, pruned_loss=0.04165, over 6390.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.02882, over 1427675.75 frames.], batch size: 37, lr: 2.10e-04
+2022-05-16 03:12:32,636 INFO [train.py:812] (0/8) Epoch 37, batch 2900, loss[loss=0.1502, simple_loss=0.2287, pruned_loss=0.03584, over 6985.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2423, pruned_loss=0.02846, over 1429099.62 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:13:31,899 INFO [train.py:812] (0/8) Epoch 37, batch 2950, loss[loss=0.1412, simple_loss=0.2275, pruned_loss=0.02743, over 7424.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2418, pruned_loss=0.02838, over 1424579.19 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 03:14:30,563 INFO [train.py:812] (0/8) Epoch 37, batch 3000, loss[loss=0.1437, simple_loss=0.249, pruned_loss=0.01917, over 7226.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.0287, over 1421775.84 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 03:14:30,565 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-16 03:14:38,088 INFO [train.py:841] (0/8) Epoch 37, validation: loss=0.1539, simple_loss=0.2491, pruned_loss=0.02931, over 698248.00 frames.
+2022-05-16 03:15:37,670 INFO [train.py:812] (0/8) Epoch 37, batch 3050, loss[loss=0.1149, simple_loss=0.2031, pruned_loss=0.01339, over 6831.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.0289, over 1420770.64 frames.], batch size: 15, lr: 2.10e-04
+2022-05-16 03:16:36,460 INFO [train.py:812] (0/8) Epoch 37, batch 3100, loss[loss=0.1494, simple_loss=0.2453, pruned_loss=0.02678, over 7059.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02898, over 1419569.34 frames.], batch size: 18, lr: 2.10e-04
+2022-05-16 03:17:34,872 INFO [train.py:812] (0/8) Epoch 37, batch 3150, loss[loss=0.1391, simple_loss=0.2178, pruned_loss=0.03023, over 7003.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.0293, over 1418834.90 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:18:33,948 INFO [train.py:812] (0/8) Epoch 37, batch 3200, loss[loss=0.1445, simple_loss=0.2285, pruned_loss=0.03024, over 4808.00 frames.], tot_loss[loss=0.15, simple_loss=0.2418, pruned_loss=0.02911, over 1418725.04 frames.], batch size: 52, lr: 2.10e-04
+2022-05-16 03:19:33,504 INFO [train.py:812] (0/8) Epoch 37, batch 3250, loss[loss=0.1737, simple_loss=0.2687, pruned_loss=0.03932, over 7194.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2414, pruned_loss=0.02924, over 1418752.34 frames.], batch size: 22, lr: 2.10e-04
+2022-05-16 03:20:31,417 INFO [train.py:812] (0/8) Epoch 37, batch 3300, loss[loss=0.1558, simple_loss=0.2523, pruned_loss=0.0297, over 7414.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02965, over 1415635.70 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 03:21:29,305 INFO [train.py:812] (0/8) Epoch 37, batch 3350, loss[loss=0.1942, simple_loss=0.2829, pruned_loss=0.05277, over 7376.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2433, pruned_loss=0.02979, over 1411772.19 frames.], batch size: 23, lr: 2.09e-04
+2022-05-16 03:22:27,818 INFO [train.py:812] (0/8) Epoch 37, batch 3400, loss[loss=0.1518, simple_loss=0.2363, pruned_loss=0.03362, over 7132.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2425, pruned_loss=0.02963, over 1416426.10 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:23:27,254 INFO [train.py:812] (0/8) Epoch 37, batch 3450, loss[loss=0.1339, simple_loss=0.2212, pruned_loss=0.02332, over 7298.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02964, over 1419088.31 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:24:25,214 INFO [train.py:812] (0/8) Epoch 37, batch 3500, loss[loss=0.1553, simple_loss=0.2427, pruned_loss=0.03401, over 7352.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.0294, over 1417076.40 frames.], batch size: 19, lr: 2.09e-04
+2022-05-16 03:25:24,377 INFO [train.py:812] (0/8) Epoch 37, batch 3550, loss[loss=0.1309, simple_loss=0.2149, pruned_loss=0.02345, over 6812.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2423, pruned_loss=0.02916, over 1414617.10 frames.], batch size: 15, lr: 2.09e-04
+2022-05-16 03:26:23,184 INFO [train.py:812] (0/8) Epoch 37, batch 3600, loss[loss=0.1355, simple_loss=0.2146, pruned_loss=0.02819, over 7004.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2407, pruned_loss=0.02847, over 1420957.87 frames.], batch size: 16, lr: 2.09e-04
+2022-05-16 03:27:22,034 INFO [train.py:812] (0/8) Epoch 37, batch 3650, loss[loss=0.1517, simple_loss=0.2407, pruned_loss=0.03138, over 7166.00 frames.], tot_loss[loss=0.149, simple_loss=0.2408, pruned_loss=0.02859, over 1422951.56 frames.], batch size: 19, lr: 2.09e-04
+2022-05-16 03:28:20,564 INFO [train.py:812] (0/8) Epoch 37, batch 3700, loss[loss=0.1545, simple_loss=0.2574, pruned_loss=0.02575, over 7225.00 frames.], tot_loss[loss=0.149, simple_loss=0.2411, pruned_loss=0.02841, over 1426534.17 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:29:19,667 INFO [train.py:812] (0/8) Epoch 37, batch 3750, loss[loss=0.1511, simple_loss=0.2397, pruned_loss=0.03119, over 7282.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2417, pruned_loss=0.02836, over 1423344.64 frames.], batch size: 24, lr: 2.09e-04
+2022-05-16 03:30:17,091 INFO [train.py:812] (0/8) Epoch 37, batch 3800, loss[loss=0.1399, simple_loss=0.2201, pruned_loss=0.02985, over 7264.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2409, pruned_loss=0.02815, over 1424921.86 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:31:15,848 INFO [train.py:812] (0/8) Epoch 37, batch 3850, loss[loss=0.1776, simple_loss=0.2587, pruned_loss=0.04826, over 4902.00 frames.], tot_loss[loss=0.1488, simple_loss=0.241, pruned_loss=0.02826, over 1423487.48 frames.], batch size: 53, lr: 2.09e-04
+2022-05-16 03:32:12,581 INFO [train.py:812] (0/8) Epoch 37, batch 3900, loss[loss=0.1629, simple_loss=0.2497, pruned_loss=0.03805, over 7323.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2401, pruned_loss=0.02798, over 1425113.80 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:33:11,473 INFO [train.py:812] (0/8) Epoch 37, batch 3950, loss[loss=0.1231, simple_loss=0.2186, pruned_loss=0.01382, over 7286.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02856, over 1426565.63 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:34:09,837 INFO [train.py:812] (0/8) Epoch 37, batch 4000, loss[loss=0.1749, simple_loss=0.2668, pruned_loss=0.04146, over 7144.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2416, pruned_loss=0.02886, over 1426912.97 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:35:09,202 INFO [train.py:812] (0/8) Epoch 37, batch 4050, loss[loss=0.1648, simple_loss=0.265, pruned_loss=0.03233, over 7154.00 frames.], tot_loss[loss=0.1492, simple_loss=0.241, pruned_loss=0.02865, over 1425213.04 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:36:06,878 INFO [train.py:812] (0/8) Epoch 37, batch 4100, loss[loss=0.1374, simple_loss=0.2324, pruned_loss=0.02121, over 7325.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.0285, over 1422492.22 frames.], batch size: 25, lr: 2.09e-04
+2022-05-16 03:37:05,733 INFO [train.py:812] (0/8) Epoch 37, batch 4150, loss[loss=0.1345, simple_loss=0.233, pruned_loss=0.01798, over 7216.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02836, over 1424992.49 frames.], batch size: 21, lr: 2.09e-04
+2022-05-16 03:38:02,987 INFO [train.py:812] (0/8) Epoch 37, batch 4200, loss[loss=0.177, simple_loss=0.2735, pruned_loss=0.04026, over 7337.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02835, over 1427431.94 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:39:02,442 INFO [train.py:812] (0/8) Epoch 37, batch 4250, loss[loss=0.1495, simple_loss=0.2479, pruned_loss=0.02551, over 7205.00 frames.], tot_loss[loss=0.148, simple_loss=0.2403, pruned_loss=0.0279, over 1430482.84 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:40:00,847 INFO [train.py:812] (0/8) Epoch 37, batch 4300, loss[loss=0.1719, simple_loss=0.2617, pruned_loss=0.04108, over 7322.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2411, pruned_loss=0.02831, over 1423658.50 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:41:00,618 INFO [train.py:812] (0/8) Epoch 37, batch 4350, loss[loss=0.1784, simple_loss=0.2775, pruned_loss=0.03969, over 7324.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2408, pruned_loss=0.02813, over 1428525.12 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:41:59,219 INFO [train.py:812] (0/8) Epoch 37, batch 4400, loss[loss=0.1506, simple_loss=0.247, pruned_loss=0.02712, over 7336.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2409, pruned_loss=0.02819, over 1420122.77 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:42:59,127 INFO [train.py:812] (0/8) Epoch 37, batch 4450, loss[loss=0.1517, simple_loss=0.2327, pruned_loss=0.03536, over 7428.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2419, pruned_loss=0.02868, over 1419496.38 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:43:58,018 INFO [train.py:812] (0/8) Epoch 37, batch 4500, loss[loss=0.1496, simple_loss=0.2299, pruned_loss=0.03461, over 7273.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2422, pruned_loss=0.02901, over 1415076.69 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:44:56,291 INFO [train.py:812] (0/8) Epoch 37, batch 4550, loss[loss=0.1483, simple_loss=0.2368, pruned_loss=0.02984, over 6254.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2432, pruned_loss=0.0298, over 1390358.79 frames.], batch size: 37, lr: 2.09e-04
+2022-05-16 03:45:41,022 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-37.pt
+2022-05-16 03:46:01,493 INFO [train.py:812] (0/8) Epoch 38, batch 0, loss[loss=0.1438, simple_loss=0.2313, pruned_loss=0.02818, over 7360.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2313, pruned_loss=0.02818, over 7360.00 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:47:10,791 INFO [train.py:812] (0/8) Epoch 38, batch 50, loss[loss=0.1553, simple_loss=0.2576, pruned_loss=0.02649, over 6390.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2367, pruned_loss=0.0271, over 322703.19 frames.], batch size: 37, lr: 2.06e-04
+2022-05-16 03:48:09,427 INFO [train.py:812] (0/8) Epoch 38, batch 100, loss[loss=0.1524, simple_loss=0.2397, pruned_loss=0.0326, over 7252.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2425, pruned_loss=0.02982, over 559985.05 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:49:08,227 INFO [train.py:812] (0/8) Epoch 38, batch 150, loss[loss=0.1487, simple_loss=0.2444, pruned_loss=0.02649, over 7385.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02948, over 747832.33 frames.], batch size: 23, lr: 2.06e-04
+2022-05-16 03:50:07,472 INFO [train.py:812] (0/8) Epoch 38, batch 200, loss[loss=0.1451, simple_loss=0.2376, pruned_loss=0.02627, over 7405.00 frames.], tot_loss[loss=0.1502, simple_loss=0.242, pruned_loss=0.0292, over 897274.56 frames.], batch size: 21, lr: 2.06e-04
+2022-05-16 03:51:06,705 INFO [train.py:812] (0/8) Epoch 38, batch 250, loss[loss=0.1427, simple_loss=0.2305, pruned_loss=0.02745, over 7361.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2419, pruned_loss=0.02947, over 1015983.74 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:52:05,083 INFO [train.py:812] (0/8) Epoch 38, batch 300, loss[loss=0.158, simple_loss=0.2551, pruned_loss=0.03043, over 7245.00 frames.], tot_loss[loss=0.151, simple_loss=0.2427, pruned_loss=0.02958, over 1105513.88 frames.], batch size: 20, lr: 2.06e-04
+2022-05-16 03:53:04,628 INFO [train.py:812] (0/8) Epoch 38, batch 350, loss[loss=0.1345, simple_loss=0.2149, pruned_loss=0.02707, over 7257.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02911, over 1173744.75 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:54:02,507 INFO [train.py:812] (0/8) Epoch 38, batch 400, loss[loss=0.1214, simple_loss=0.1991, pruned_loss=0.02184, over 7281.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2412, pruned_loss=0.02855, over 1233582.42 frames.], batch size: 17, lr: 2.06e-04
+2022-05-16 03:55:02,005 INFO [train.py:812] (0/8) Epoch 38, batch 450, loss[loss=0.1347, simple_loss=0.236, pruned_loss=0.01675, over 7111.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2413, pruned_loss=0.02867, over 1276570.49 frames.], batch size: 21, lr: 2.06e-04
+2022-05-16 03:56:00,728 INFO [train.py:812] (0/8) Epoch 38, batch 500, loss[loss=0.1366, simple_loss=0.2171, pruned_loss=0.02803, over 7263.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2406, pruned_loss=0.02842, over 1312545.90 frames.], batch size: 18, lr: 2.06e-04
+2022-05-16 03:56:58,583 INFO [train.py:812] (0/8) Epoch 38, batch 550, loss[loss=0.1348, simple_loss=0.2303, pruned_loss=0.0197, over 7331.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2405, pruned_loss=0.02819, over 1336243.96 frames.], batch size: 20, lr: 2.06e-04
+2022-05-16 03:57:56,239 INFO [train.py:812] (0/8) Epoch 38, batch 600, loss[loss=0.1788, simple_loss=0.2723, pruned_loss=0.04258, over 7363.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02888, over 1358118.05 frames.], batch size: 23, lr: 2.06e-04
+2022-05-16 03:58:54,200 INFO [train.py:812] (0/8) Epoch 38, batch 650, loss[loss=0.1634, simple_loss=0.2622, pruned_loss=0.0323, over 7334.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2427, pruned_loss=0.02888, over 1373938.27 frames.], batch size: 22, lr: 2.06e-04
+2022-05-16 03:59:53,353 INFO [train.py:812] (0/8) Epoch 38, batch 700, loss[loss=0.179, simple_loss=0.2668, pruned_loss=0.04564, over 7148.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2425, pruned_loss=0.02865, over 1386615.45 frames.], batch size: 18, lr: 2.06e-04
+2022-05-16 04:00:52,142 INFO [train.py:812] (0/8) Epoch 38, batch 750, loss[loss=0.1565, simple_loss=0.2457, pruned_loss=0.0337, over 7380.00 frames.], tot_loss[loss=0.15, simple_loss=0.2429, pruned_loss=0.02857, over 1401273.06 frames.], batch size: 23, lr: 2.05e-04
+2022-05-16 04:01:50,299 INFO [train.py:812] (0/8) Epoch 38, batch 800, loss[loss=0.1284, simple_loss=0.2113, pruned_loss=0.02271, over 7391.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2426, pruned_loss=0.02848, over 1408925.14 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:02:49,123 INFO [train.py:812] (0/8) Epoch 38, batch 850, loss[loss=0.1582, simple_loss=0.2403, pruned_loss=0.03802, over 7361.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2428, pruned_loss=0.02864, over 1411246.02 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:03:47,715 INFO [train.py:812] (0/8) Epoch 38, batch 900, loss[loss=0.1512, simple_loss=0.2591, pruned_loss=0.02169, over 7292.00 frames.], tot_loss[loss=0.149, simple_loss=0.2418, pruned_loss=0.02807, over 1413442.92 frames.], batch size: 24, lr: 2.05e-04
+2022-05-16 04:04:46,241 INFO [train.py:812] (0/8) Epoch 38, batch 950, loss[loss=0.1263, simple_loss=0.217, pruned_loss=0.01778, over 7260.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2424, pruned_loss=0.02821, over 1418590.23 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:05:44,599 INFO [train.py:812] (0/8) Epoch 38, batch 1000, loss[loss=0.16, simple_loss=0.2538, pruned_loss=0.03311, over 7213.00 frames.], tot_loss[loss=0.15, simple_loss=0.2428, pruned_loss=0.02863, over 1421467.12 frames.], batch size: 22, lr: 2.05e-04
+2022-05-16 04:06:43,996 INFO [train.py:812] (0/8) Epoch 38, batch 1050, loss[loss=0.151, simple_loss=0.2438, pruned_loss=0.02904, over 7341.00 frames.], tot_loss[loss=0.15, simple_loss=0.2429, pruned_loss=0.02851, over 1422271.22 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:07:41,755 INFO [train.py:812] (0/8) Epoch 38, batch 1100, loss[loss=0.1249, simple_loss=0.2171, pruned_loss=0.01634, over 6780.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2427, pruned_loss=0.0284, over 1425514.96 frames.], batch size: 15, lr: 2.05e-04
+2022-05-16 04:08:41,049 INFO [train.py:812] (0/8) Epoch 38, batch 1150, loss[loss=0.1445, simple_loss=0.2306, pruned_loss=0.02918, over 7264.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2427, pruned_loss=0.02837, over 1422327.60 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:09:40,639 INFO [train.py:812] (0/8) Epoch 38, batch 1200, loss[loss=0.152, simple_loss=0.2488, pruned_loss=0.02755, over 7230.00 frames.], tot_loss[loss=0.1501, simple_loss=0.243, pruned_loss=0.02856, over 1423655.69 frames.], batch size: 26, lr: 2.05e-04
+2022-05-16 04:10:39,670 INFO [train.py:812] (0/8) Epoch 38, batch 1250, loss[loss=0.1564, simple_loss=0.247, pruned_loss=0.03292, over 6403.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2429, pruned_loss=0.02865, over 1426760.38 frames.], batch size: 37, lr: 2.05e-04
+2022-05-16 04:11:38,547 INFO [train.py:812] (0/8) Epoch 38, batch 1300, loss[loss=0.143, simple_loss=0.2299, pruned_loss=0.02804, over 7297.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2436, pruned_loss=0.0289, over 1426025.39 frames.], batch size: 17, lr: 2.05e-04
+2022-05-16 04:12:36,175 INFO [train.py:812] (0/8) Epoch 38, batch 1350, loss[loss=0.1389, simple_loss=0.2333, pruned_loss=0.02228, over 7112.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.02888, over 1419607.21 frames.], batch size: 21, lr: 2.05e-04
+2022-05-16 04:13:33,883 INFO [train.py:812] (0/8) Epoch 38, batch 1400, loss[loss=0.1567, simple_loss=0.2536, pruned_loss=0.02989, over 7278.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02922, over 1419543.55 frames.], batch size: 24, lr: 2.05e-04
+2022-05-16 04:14:32,884 INFO [train.py:812] (0/8) Epoch 38, batch 1450, loss[loss=0.1808, simple_loss=0.2746, pruned_loss=0.04348, over 7207.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02962, over 1424706.30 frames.], batch size: 22, lr: 2.05e-04
+2022-05-16 04:15:31,407 INFO [train.py:812] (0/8) Epoch 38, batch 1500, loss[loss=0.1661, simple_loss=0.2672, pruned_loss=0.03247, over 7275.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2435, pruned_loss=0.02938, over 1425181.02 frames.], batch size: 25, lr: 2.05e-04
+2022-05-16 04:16:30,118 INFO [train.py:812] (0/8) Epoch 38, batch 1550, loss[loss=0.1439, simple_loss=0.2473, pruned_loss=0.02026, over 7233.00 frames.], tot_loss[loss=0.151, simple_loss=0.2436, pruned_loss=0.02916, over 1422938.69 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:17:27,389 INFO [train.py:812] (0/8) Epoch 38, batch 1600, loss[loss=0.1505, simple_loss=0.239, pruned_loss=0.03102, over 7267.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2433, pruned_loss=0.02898, over 1425788.98 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:18:25,539 INFO [train.py:812] (0/8) Epoch 38, batch 1650, loss[loss=0.1644, simple_loss=0.274, pruned_loss=0.02739, over 6965.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2429, pruned_loss=0.02878, over 1424515.16 frames.], batch size: 28, lr: 2.05e-04
+2022-05-16 04:19:24,086 INFO [train.py:812] (0/8) Epoch 38, batch 1700, loss[loss=0.1605, simple_loss=0.2531, pruned_loss=0.0339, over 7156.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2418, pruned_loss=0.02863, over 1422449.75 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:20:24,601 INFO [train.py:812] (0/8) Epoch 38, batch 1750, loss[loss=0.1789, simple_loss=0.2651, pruned_loss=0.0463, over 5350.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2425, pruned_loss=0.02881, over 1422028.98 frames.], batch size: 52, lr: 2.05e-04
+2022-05-16 04:21:23,195 INFO [train.py:812] (0/8) Epoch 38, batch 1800, loss[loss=0.1581, simple_loss=0.2561, pruned_loss=0.03008, over 7328.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2415, pruned_loss=0.02865, over 1420075.29 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:22:21,146 INFO [train.py:812] (0/8) Epoch 38, batch 1850, loss[loss=0.1348, simple_loss=0.2197, pruned_loss=0.02488, over 7286.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2418, pruned_loss=0.02878, over 1421355.99 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:23:20,145 INFO [train.py:812] (0/8) Epoch 38, batch 1900, loss[loss=0.1398, simple_loss=0.2334, pruned_loss=0.02309, over 6796.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02895, over 1424173.60 frames.], batch size: 15, lr: 2.05e-04
+2022-05-16 04:24:18,764 INFO [train.py:812] (0/8) Epoch 38, batch 1950, loss[loss=0.155, simple_loss=0.2434, pruned_loss=0.03334, over 7257.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02913, over 1427086.22 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:25:17,616 INFO [train.py:812] (0/8) Epoch 38, batch 2000, loss[loss=0.1443, simple_loss=0.235, pruned_loss=0.02681, over 7423.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02901, over 1426927.25 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:26:16,444 INFO [train.py:812] (0/8) Epoch 38, batch 2050, loss[loss=0.1428, simple_loss=0.2341, pruned_loss=0.02573, over 7254.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.02945, over 1424023.43 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:27:14,051 INFO [train.py:812] (0/8) Epoch 38, batch 2100, loss[loss=0.1633, simple_loss=0.2539, pruned_loss=0.03631, over 7152.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.02948, over 1417944.58 frames.], batch size: 26, lr: 2.05e-04
+2022-05-16 04:28:12,413 INFO [train.py:812] (0/8) Epoch 38, batch 2150, loss[loss=0.1349, simple_loss=0.2227, pruned_loss=0.02352, over 7079.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02931, over 1418396.76 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:29:11,057 INFO [train.py:812] (0/8) Epoch 38, batch 2200, loss[loss=0.1281, simple_loss=0.2161, pruned_loss=0.02008, over 7078.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2438, pruned_loss=0.02922, over 1418866.32 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:30:01,721 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-172000.pt
+2022-05-16 04:30:15,080 INFO [train.py:812] (0/8) Epoch 38, batch 2250, loss[loss=0.1581, simple_loss=0.2533, pruned_loss=0.03142, over 6279.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2435, pruned_loss=0.02909, over 1418590.22 frames.], batch size: 37, lr: 2.05e-04
+2022-05-16 04:31:14,193 INFO [train.py:812] (0/8) Epoch 38, batch 2300, loss[loss=0.1376, simple_loss=0.2289, pruned_loss=0.02318, over 7074.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2435, pruned_loss=0.02914, over 1422231.64 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:32:13,368 INFO [train.py:812] (0/8) Epoch 38, batch 2350, loss[loss=0.1392, simple_loss=0.2302, pruned_loss=0.02412, over 7321.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2425, pruned_loss=0.02863, over 1419352.49 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:33:12,139 INFO [train.py:812] (0/8) Epoch 38, batch 2400, loss[loss=0.1416, simple_loss=0.2189, pruned_loss=0.03217, over 7413.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02888, over 1424402.57 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:34:10,718 INFO [train.py:812] (0/8) Epoch 38, batch 2450, loss[loss=0.1858, simple_loss=0.2733, pruned_loss=0.04915, over 7314.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.02884, over 1427101.64 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:35:08,791 INFO [train.py:812] (0/8) Epoch 38, batch 2500, loss[loss=0.1407, simple_loss=0.2315, pruned_loss=0.02499, over 7164.00 frames.], tot_loss[loss=0.15, simple_loss=0.2425, pruned_loss=0.02879, over 1427339.42 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:36:06,679 INFO [train.py:812] (0/8) Epoch 38, batch 2550, loss[loss=0.1514, simple_loss=0.2364, pruned_loss=0.03321, over 7159.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02892, over 1425275.47 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:37:05,337 INFO [train.py:812] (0/8) Epoch 38, batch 2600, loss[loss=0.1261, simple_loss=0.2188, pruned_loss=0.0167, over 7426.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2415, pruned_loss=0.02866, over 1424645.55 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:38:03,414 INFO [train.py:812] (0/8) Epoch 38, batch 2650, loss[loss=0.1692, simple_loss=0.2591, pruned_loss=0.03968, over 7194.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2417, pruned_loss=0.02861, over 1425334.40 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:39:01,017 INFO [train.py:812] (0/8) Epoch 38, batch 2700, loss[loss=0.1441, simple_loss=0.2503, pruned_loss=0.01899, over 7230.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2413, pruned_loss=0.02818, over 1423781.52 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:39:59,838 INFO [train.py:812] (0/8) Epoch 38, batch 2750, loss[loss=0.1512, simple_loss=0.2521, pruned_loss=0.02518, over 7360.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2414, pruned_loss=0.02822, over 1424975.84 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 04:40:57,550 INFO [train.py:812] (0/8) Epoch 38, batch 2800, loss[loss=0.1462, simple_loss=0.2387, pruned_loss=0.02683, over 7278.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02818, over 1423172.92 frames.], batch size: 24, lr: 2.04e-04
+2022-05-16 04:41:55,560 INFO [train.py:812] (0/8) Epoch 38, batch 2850, loss[loss=0.1373, simple_loss=0.2357, pruned_loss=0.01948, over 7415.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2404, pruned_loss=0.02794, over 1423227.71 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 04:42:54,177 INFO [train.py:812] (0/8) Epoch 38, batch 2900, loss[loss=0.1197, simple_loss=0.2097, pruned_loss=0.01487, over 7137.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02826, over 1423608.72 frames.], batch size: 17, lr: 2.04e-04
+2022-05-16 04:43:53,029 INFO [train.py:812] (0/8) Epoch 38, batch 2950, loss[loss=0.115, simple_loss=0.2002, pruned_loss=0.01489, over 7411.00 frames.], tot_loss[loss=0.1487, simple_loss=0.241, pruned_loss=0.02821, over 1428658.78 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:44:52,005 INFO [train.py:812] (0/8) Epoch 38, batch 3000, loss[loss=0.149, simple_loss=0.2472, pruned_loss=0.02539, over 7197.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2408, pruned_loss=0.02812, over 1428058.98 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:44:52,007 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-16 04:44:59,415 INFO [train.py:841] (0/8) Epoch 38, validation: loss=0.1532, simple_loss=0.2484, pruned_loss=0.02898, over 698248.00 frames.
+2022-05-16 04:45:58,533 INFO [train.py:812] (0/8) Epoch 38, batch 3050, loss[loss=0.1344, simple_loss=0.2261, pruned_loss=0.02142, over 7165.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2418, pruned_loss=0.0285, over 1427980.97 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:46:56,195 INFO [train.py:812] (0/8) Epoch 38, batch 3100, loss[loss=0.1569, simple_loss=0.2536, pruned_loss=0.03005, over 7208.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02876, over 1421301.77 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 04:47:54,519 INFO [train.py:812] (0/8) Epoch 38, batch 3150, loss[loss=0.1666, simple_loss=0.2622, pruned_loss=0.03551, over 7375.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2421, pruned_loss=0.02878, over 1419957.48 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:48:52,448 INFO [train.py:812] (0/8) Epoch 38, batch 3200, loss[loss=0.1563, simple_loss=0.2504, pruned_loss=0.03113, over 7115.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2408, pruned_loss=0.02816, over 1425060.81 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 04:49:51,391 INFO [train.py:812] (0/8) Epoch 38, batch 3250, loss[loss=0.1238, simple_loss=0.2066, pruned_loss=0.02051, over 7274.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2404, pruned_loss=0.02809, over 1425771.98 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:50:49,198 INFO [train.py:812] (0/8) Epoch 38, batch 3300, loss[loss=0.1388, simple_loss=0.2359, pruned_loss=0.02092, over 7226.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2405, pruned_loss=0.02817, over 1425358.74 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:51:47,396 INFO [train.py:812] (0/8) Epoch 38, batch 3350, loss[loss=0.176, simple_loss=0.266, pruned_loss=0.04307, over 7207.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02821, over 1426385.74 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 04:52:45,590 INFO [train.py:812] (0/8) Epoch 38, batch 3400, loss[loss=0.1386, simple_loss=0.2369, pruned_loss=0.02016, over 6667.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2415, pruned_loss=0.02805, over 1430059.05 frames.], batch size: 31, lr: 2.04e-04
+2022-05-16 04:53:45,197 INFO [train.py:812] (0/8) Epoch 38, batch 3450, loss[loss=0.143, simple_loss=0.2282, pruned_loss=0.0289, over 7431.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02825, over 1432074.98 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:54:43,556 INFO [train.py:812] (0/8) Epoch 38, batch 3500, loss[loss=0.1327, simple_loss=0.2289, pruned_loss=0.01826, over 7232.00 frames.], tot_loss[loss=0.1494, simple_loss=0.242, pruned_loss=0.02844, over 1430479.47 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:55:41,784 INFO [train.py:812] (0/8) Epoch 38, batch 3550, loss[loss=0.157, simple_loss=0.2495, pruned_loss=0.03221, over 7150.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2432, pruned_loss=0.02866, over 1431084.04 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:56:49,623 INFO [train.py:812] (0/8) Epoch 38, batch 3600, loss[loss=0.1723, simple_loss=0.2594, pruned_loss=0.04265, over 6801.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2434, pruned_loss=0.0289, over 1429003.14 frames.], batch size: 31, lr: 2.04e-04
+2022-05-16 04:57:48,342 INFO [train.py:812] (0/8) Epoch 38, batch 3650, loss[loss=0.1555, simple_loss=0.2492, pruned_loss=0.03091, over 7066.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2431, pruned_loss=0.0288, over 1431267.54 frames.], batch size: 28, lr: 2.04e-04
+2022-05-16 04:58:46,148 INFO [train.py:812] (0/8) Epoch 38, batch 3700, loss[loss=0.1503, simple_loss=0.2428, pruned_loss=0.02889, over 7251.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2427, pruned_loss=0.02876, over 1422837.37 frames.], batch size: 24, lr: 2.04e-04
+2022-05-16 05:00:03,396 INFO [train.py:812] (0/8) Epoch 38, batch 3750, loss[loss=0.1653, simple_loss=0.2572, pruned_loss=0.03677, over 7160.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2431, pruned_loss=0.02889, over 1417966.15 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 05:01:01,777 INFO [train.py:812] (0/8) Epoch 38, batch 3800, loss[loss=0.1606, simple_loss=0.2543, pruned_loss=0.03347, over 7355.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2424, pruned_loss=0.02891, over 1417963.29 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 05:02:01,297 INFO [train.py:812] (0/8) Epoch 38, batch 3850, loss[loss=0.1424, simple_loss=0.2345, pruned_loss=0.02518, over 7104.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2415, pruned_loss=0.02852, over 1420341.79 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 05:03:01,096 INFO [train.py:812] (0/8) Epoch 38, batch 3900, loss[loss=0.1591, simple_loss=0.2437, pruned_loss=0.03728, over 7330.00 frames.], tot_loss[loss=0.15, simple_loss=0.2416, pruned_loss=0.02915, over 1421911.08 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 05:03:59,287 INFO [train.py:812] (0/8) Epoch 38, batch 3950, loss[loss=0.1668, simple_loss=0.2598, pruned_loss=0.03691, over 7208.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2408, pruned_loss=0.02848, over 1416442.25 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 05:04:56,832 INFO [train.py:812] (0/8) Epoch 38, batch 4000, loss[loss=0.1322, simple_loss=0.2238, pruned_loss=0.0203, over 7155.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2406, pruned_loss=0.02848, over 1417071.58 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 05:06:06,107 INFO [train.py:812] (0/8) Epoch 38, batch 4050, loss[loss=0.1559, simple_loss=0.2335, pruned_loss=0.03921, over 7293.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2403, pruned_loss=0.0283, over 1411953.87 frames.], batch size: 17, lr: 2.04e-04
+2022-05-16 05:07:14,542 INFO [train.py:812] (0/8) Epoch 38, batch 4100, loss[loss=0.1491, simple_loss=0.2427, pruned_loss=0.02776, over 7221.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2415, pruned_loss=0.02845, over 1413467.72 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 05:08:13,923 INFO [train.py:812] (0/8) Epoch 38, batch 4150, loss[loss=0.1747, simple_loss=0.2545, pruned_loss=0.04743, over 7258.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2403, pruned_loss=0.02831, over 1413227.47 frames.], batch size: 19, lr: 2.03e-04
+2022-05-16 05:09:21,207 INFO [train.py:812] (0/8) Epoch 38, batch 4200, loss[loss=0.168, simple_loss=0.2586, pruned_loss=0.03875, over 7295.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2407, pruned_loss=0.02816, over 1413993.49 frames.], batch size: 24, lr: 2.03e-04
+2022-05-16 05:10:29,481 INFO [train.py:812] (0/8) Epoch 38, batch 4250, loss[loss=0.1337, simple_loss=0.2286, pruned_loss=0.01935, over 7234.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2408, pruned_loss=0.02793, over 1413776.99 frames.], batch size: 20, lr: 2.03e-04
+2022-05-16 05:11:27,990 INFO [train.py:812] (0/8) Epoch 38, batch 4300, loss[loss=0.1527, simple_loss=0.2533, pruned_loss=0.026, over 5199.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2397, pruned_loss=0.0278, over 1411660.84 frames.], batch size: 54, lr: 2.03e-04
+2022-05-16 05:12:26,579 INFO [train.py:812] (0/8) Epoch 38, batch 4350, loss[loss=0.1362, simple_loss=0.2149, pruned_loss=0.02875, over 6993.00 frames.], tot_loss[loss=0.1471, simple_loss=0.239, pruned_loss=0.02758, over 1413736.09 frames.], batch size: 16, lr: 2.03e-04
+2022-05-16 05:13:26,087 INFO [train.py:812] (0/8) Epoch 38, batch 4400, loss[loss=0.127, simple_loss=0.2174, pruned_loss=0.01831, over 7171.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2383, pruned_loss=0.02715, over 1414665.68 frames.], batch size: 16, lr: 2.03e-04
+2022-05-16 05:14:25,868 INFO [train.py:812] (0/8) Epoch 38, batch 4450, loss[loss=0.1422, simple_loss=0.2293, pruned_loss=0.02753, over 6858.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2385, pruned_loss=0.02767, over 1406997.30 frames.], batch size: 15, lr: 2.03e-04
+2022-05-16 05:15:24,198 INFO [train.py:812] (0/8) Epoch 38, batch 4500, loss[loss=0.1571, simple_loss=0.2482, pruned_loss=0.03299, over 6437.00 frames.], tot_loss[loss=0.1475, simple_loss=0.239, pruned_loss=0.02796, over 1383396.28 frames.], batch size: 38, lr: 2.03e-04
+2022-05-16 05:16:23,029 INFO [train.py:812] (0/8) Epoch 38, batch 4550, loss[loss=0.1713, simple_loss=0.2498, pruned_loss=0.04639, over 5045.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2388, pruned_loss=0.02845, over 1356003.04 frames.], batch size: 52, lr: 2.03e-04
+2022-05-16 05:17:07,585 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-38.pt
+2022-05-16 05:17:28,595 INFO [train.py:812] (0/8) Epoch 39, batch 0, loss[loss=0.1674, simple_loss=0.2716, pruned_loss=0.03165, over 7266.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2716, pruned_loss=0.03165, over 7266.00 frames.], batch size: 19, lr: 2.01e-04
+2022-05-16 05:18:26,910 INFO [train.py:812] (0/8) Epoch 39, batch 50, loss[loss=0.1592, simple_loss=0.254, pruned_loss=0.03221, over 7154.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2412, pruned_loss=0.02671, over 320385.83 frames.], batch size: 20, lr: 2.01e-04
+2022-05-16 05:19:25,862 INFO [train.py:812] (0/8) Epoch 39, batch 100, loss[loss=0.1496, simple_loss=0.2475, pruned_loss=0.02581, over 6817.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2419, pruned_loss=0.02753, over 565509.94 frames.], batch size: 31, lr: 2.01e-04
+2022-05-16 05:20:24,081 INFO [train.py:812] (0/8) Epoch 39, batch 150, loss[loss=0.151, simple_loss=0.2483, pruned_loss=0.02686, over 7158.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2397, pruned_loss=0.02766, over 754640.63 frames.], batch size: 18, lr: 2.01e-04
+2022-05-16 05:21:22,506 INFO [train.py:812] (0/8) Epoch 39, batch 200, loss[loss=0.1293, simple_loss=0.2197, pruned_loss=0.0194, over 7427.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2415, pruned_loss=0.02848, over 902197.90 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:22:20,438 INFO [train.py:812] (0/8) Epoch 39, batch 250, loss[loss=0.1465, simple_loss=0.2451, pruned_loss=0.02398, over 6413.00 frames.], tot_loss[loss=0.1499, simple_loss=0.242, pruned_loss=0.02891, over 1017706.64 frames.], batch size: 38, lr: 2.00e-04
+2022-05-16 05:23:19,071 INFO [train.py:812] (0/8) Epoch 39, batch 300, loss[loss=0.1645, simple_loss=0.26, pruned_loss=0.03447, over 7421.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2416, pruned_loss=0.02889, over 1113005.79 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:24:17,712 INFO [train.py:812] (0/8) Epoch 39, batch 350, loss[loss=0.1681, simple_loss=0.2683, pruned_loss=0.03391, over 7265.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2416, pruned_loss=0.02899, over 1180429.17 frames.], batch size: 24, lr: 2.00e-04
+2022-05-16 05:25:17,165 INFO [train.py:812] (0/8) Epoch 39, batch 400, loss[loss=0.1389, simple_loss=0.238, pruned_loss=0.0199, over 7221.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2413, pruned_loss=0.02864, over 1230374.08 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:26:16,270 INFO [train.py:812] (0/8) Epoch 39, batch 450, loss[loss=0.1689, simple_loss=0.2554, pruned_loss=0.04126, over 7192.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02856, over 1274852.69 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:27:15,047 INFO [train.py:812] (0/8) Epoch 39, batch 500, loss[loss=0.1469, simple_loss=0.2513, pruned_loss=0.02126, over 7141.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2409, pruned_loss=0.02859, over 1302134.81 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:28:14,643 INFO [train.py:812] (0/8) Epoch 39, batch 550, loss[loss=0.1639, simple_loss=0.2444, pruned_loss=0.0417, over 7432.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2406, pruned_loss=0.02856, over 1327051.78 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:29:14,823 INFO [train.py:812] (0/8) Epoch 39, batch 600, loss[loss=0.1449, simple_loss=0.2347, pruned_loss=0.02753, over 7163.00 frames.], tot_loss[loss=0.149, simple_loss=0.2409, pruned_loss=0.02852, over 1345771.94 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:30:14,643 INFO [train.py:812] (0/8) Epoch 39, batch 650, loss[loss=0.1416, simple_loss=0.2161, pruned_loss=0.03355, over 7296.00 frames.], tot_loss[loss=0.149, simple_loss=0.2407, pruned_loss=0.02858, over 1365067.20 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:31:13,689 INFO [train.py:812] (0/8) Epoch 39, batch 700, loss[loss=0.1218, simple_loss=0.1994, pruned_loss=0.0221, over 7239.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2401, pruned_loss=0.02858, over 1378852.97 frames.], batch size: 16, lr: 2.00e-04
+2022-05-16 05:32:12,711 INFO [train.py:812] (0/8) Epoch 39, batch 750, loss[loss=0.1698, simple_loss=0.2614, pruned_loss=0.03906, over 6345.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2403, pruned_loss=0.02859, over 1387586.31 frames.], batch size: 37, lr: 2.00e-04
+2022-05-16 05:33:12,253 INFO [train.py:812] (0/8) Epoch 39, batch 800, loss[loss=0.1628, simple_loss=0.2514, pruned_loss=0.03705, over 7234.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2406, pruned_loss=0.02862, over 1399886.82 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:34:10,577 INFO [train.py:812] (0/8) Epoch 39, batch 850, loss[loss=0.1703, simple_loss=0.2732, pruned_loss=0.03366, over 7077.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2399, pruned_loss=0.02817, over 1405965.05 frames.], batch size: 28, lr: 2.00e-04
+2022-05-16 05:35:08,792 INFO [train.py:812] (0/8) Epoch 39, batch 900, loss[loss=0.1629, simple_loss=0.2604, pruned_loss=0.0327, over 7408.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2406, pruned_loss=0.02861, over 1404677.67 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:36:07,906 INFO [train.py:812] (0/8) Epoch 39, batch 950, loss[loss=0.1116, simple_loss=0.1959, pruned_loss=0.01362, over 7149.00 frames.], tot_loss[loss=0.149, simple_loss=0.241, pruned_loss=0.02852, over 1406076.20 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:37:07,666 INFO [train.py:812] (0/8) Epoch 39, batch 1000, loss[loss=0.1622, simple_loss=0.2477, pruned_loss=0.03839, over 7362.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2417, pruned_loss=0.0287, over 1409501.25 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:38:06,535 INFO [train.py:812] (0/8) Epoch 39, batch 1050, loss[loss=0.1455, simple_loss=0.2499, pruned_loss=0.02054, over 6777.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02861, over 1412006.25 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:39:05,051 INFO [train.py:812] (0/8) Epoch 39, batch 1100, loss[loss=0.1834, simple_loss=0.2728, pruned_loss=0.04702, over 7400.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2408, pruned_loss=0.0285, over 1416412.97 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:40:03,841 INFO [train.py:812] (0/8) Epoch 39, batch 1150, loss[loss=0.1367, simple_loss=0.2159, pruned_loss=0.02874, over 7269.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2397, pruned_loss=0.02789, over 1419932.09 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:41:02,328 INFO [train.py:812] (0/8) Epoch 39, batch 1200, loss[loss=0.1574, simple_loss=0.2545, pruned_loss=0.03018, over 6726.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2398, pruned_loss=0.02801, over 1420952.58 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:42:00,509 INFO [train.py:812] (0/8) Epoch 39, batch 1250, loss[loss=0.1229, simple_loss=0.2148, pruned_loss=0.01548, over 7432.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2405, pruned_loss=0.028, over 1422179.23 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:42:59,404 INFO [train.py:812] (0/8) Epoch 39, batch 1300, loss[loss=0.1168, simple_loss=0.2042, pruned_loss=0.01468, over 7264.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2396, pruned_loss=0.02755, over 1425539.28 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:43:56,594 INFO [train.py:812] (0/8) Epoch 39, batch 1350, loss[loss=0.1635, simple_loss=0.2534, pruned_loss=0.03679, over 7327.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2408, pruned_loss=0.02774, over 1425708.67 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:45:05,759 INFO [train.py:812] (0/8) Epoch 39, batch 1400, loss[loss=0.1329, simple_loss=0.2259, pruned_loss=0.02001, over 7173.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2406, pruned_loss=0.02785, over 1425031.30 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:46:03,935 INFO [train.py:812] (0/8) Epoch 39, batch 1450, loss[loss=0.1669, simple_loss=0.2594, pruned_loss=0.03715, over 7311.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02825, over 1424866.86 frames.], batch size: 25, lr: 2.00e-04
+2022-05-16 05:47:01,538 INFO [train.py:812] (0/8) Epoch 39, batch 1500, loss[loss=0.1719, simple_loss=0.2785, pruned_loss=0.03263, over 7113.00 frames.], tot_loss[loss=0.1492, simple_loss=0.242, pruned_loss=0.02824, over 1424326.84 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:48:00,120 INFO [train.py:812] (0/8) Epoch 39, batch 1550, loss[loss=0.1675, simple_loss=0.2545, pruned_loss=0.04025, over 7201.00 frames.], tot_loss[loss=0.149, simple_loss=0.2415, pruned_loss=0.02823, over 1424185.28 frames.], batch size: 22, lr: 2.00e-04
+2022-05-16 05:48:59,842 INFO [train.py:812] (0/8) Epoch 39, batch 1600, loss[loss=0.172, simple_loss=0.2787, pruned_loss=0.03268, over 6760.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2411, pruned_loss=0.02815, over 1425665.64 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:49:57,797 INFO [train.py:812] (0/8) Epoch 39, batch 1650, loss[loss=0.143, simple_loss=0.2374, pruned_loss=0.02425, over 7226.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2404, pruned_loss=0.02815, over 1425279.59 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:50:03,973 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-176000.pt
+2022-05-16 05:51:01,155 INFO [train.py:812] (0/8) Epoch 39, batch 1700, loss[loss=0.1324, simple_loss=0.2302, pruned_loss=0.01733, over 7092.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2407, pruned_loss=0.02803, over 1427109.70 frames.], batch size: 28, lr: 2.00e-04
+2022-05-16 05:51:59,416 INFO [train.py:812] (0/8) Epoch 39, batch 1750, loss[loss=0.1357, simple_loss=0.2293, pruned_loss=0.02108, over 7428.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2412, pruned_loss=0.02803, over 1426827.48 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:52:58,519 INFO [train.py:812] (0/8) Epoch 39, batch 1800, loss[loss=0.1646, simple_loss=0.2642, pruned_loss=0.03255, over 7193.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2413, pruned_loss=0.02796, over 1424188.91 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:53:57,500 INFO [train.py:812] (0/8) Epoch 39, batch 1850, loss[loss=0.1245, simple_loss=0.2183, pruned_loss=0.01535, over 7165.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2411, pruned_loss=0.02812, over 1421914.19 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:54:55,917 INFO [train.py:812] (0/8) Epoch 39, batch 1900, loss[loss=0.1202, simple_loss=0.2127, pruned_loss=0.01386, over 7287.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2407, pruned_loss=0.02784, over 1424851.63 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:55:54,014 INFO [train.py:812] (0/8) Epoch 39, batch 1950, loss[loss=0.1531, simple_loss=0.2538, pruned_loss=0.02617, over 7344.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2411, pruned_loss=0.02785, over 1424776.65 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 05:56:52,304 INFO [train.py:812] (0/8) Epoch 39, batch 2000, loss[loss=0.1332, simple_loss=0.2253, pruned_loss=0.02054, over 7252.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2413, pruned_loss=0.02805, over 1424056.07 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 05:57:50,316 INFO [train.py:812] (0/8) Epoch 39, batch 2050, loss[loss=0.1515, simple_loss=0.2459, pruned_loss=0.02856, over 7325.00 frames.], tot_loss[loss=0.1493, simple_loss=0.242, pruned_loss=0.0283, over 1422497.40 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 05:58:49,538 INFO [train.py:812] (0/8) Epoch 39, batch 2100, loss[loss=0.1309, simple_loss=0.2147, pruned_loss=0.02352, over 6764.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2412, pruned_loss=0.02796, over 1423372.80 frames.], batch size: 15, lr: 1.99e-04
+2022-05-16 05:59:47,689 INFO [train.py:812] (0/8) Epoch 39, batch 2150, loss[loss=0.156, simple_loss=0.2486, pruned_loss=0.03171, over 7260.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2418, pruned_loss=0.02829, over 1420671.79 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:00:46,902 INFO [train.py:812] (0/8) Epoch 39, batch 2200, loss[loss=0.1585, simple_loss=0.2549, pruned_loss=0.03109, over 7197.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2424, pruned_loss=0.0284, over 1421408.50 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:01:45,952 INFO [train.py:812] (0/8) Epoch 39, batch 2250, loss[loss=0.1556, simple_loss=0.2451, pruned_loss=0.03303, over 7154.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2414, pruned_loss=0.02804, over 1424052.83 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:02:45,395 INFO [train.py:812] (0/8) Epoch 39, batch 2300, loss[loss=0.141, simple_loss=0.2337, pruned_loss=0.0242, over 7156.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2412, pruned_loss=0.02812, over 1422964.83 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:03:45,426 INFO [train.py:812] (0/8) Epoch 39, batch 2350, loss[loss=0.1353, simple_loss=0.2298, pruned_loss=0.02037, over 7240.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2411, pruned_loss=0.02779, over 1424450.78 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:04:43,840 INFO [train.py:812] (0/8) Epoch 39, batch 2400, loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02886, over 7152.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2413, pruned_loss=0.02813, over 1427562.06 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:05:41,781 INFO [train.py:812] (0/8) Epoch 39, batch 2450, loss[loss=0.122, simple_loss=0.2062, pruned_loss=0.01896, over 7413.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2408, pruned_loss=0.02792, over 1427962.13 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:06:40,888 INFO [train.py:812] (0/8) Epoch 39, batch 2500, loss[loss=0.1364, simple_loss=0.2197, pruned_loss=0.02659, over 7431.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2405, pruned_loss=0.02748, over 1425951.84 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:07:38,138 INFO [train.py:812] (0/8) Epoch 39, batch 2550, loss[loss=0.1421, simple_loss=0.2356, pruned_loss=0.0243, over 7438.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2397, pruned_loss=0.0273, over 1430867.84 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:08:37,415 INFO [train.py:812] (0/8) Epoch 39, batch 2600, loss[loss=0.1732, simple_loss=0.2811, pruned_loss=0.03265, over 7131.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2406, pruned_loss=0.02759, over 1428514.20 frames.], batch size: 26, lr: 1.99e-04
+2022-05-16 06:09:36,149 INFO [train.py:812] (0/8) Epoch 39, batch 2650, loss[loss=0.1505, simple_loss=0.2452, pruned_loss=0.02789, over 7135.00 frames.], tot_loss[loss=0.1482, simple_loss=0.241, pruned_loss=0.0277, over 1429493.15 frames.], batch size: 28, lr: 1.99e-04
+2022-05-16 06:10:34,092 INFO [train.py:812] (0/8) Epoch 39, batch 2700, loss[loss=0.1653, simple_loss=0.2519, pruned_loss=0.03934, over 7317.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2416, pruned_loss=0.02801, over 1427726.99 frames.], batch size: 25, lr: 1.99e-04
+2022-05-16 06:11:32,674 INFO [train.py:812] (0/8) Epoch 39, batch 2750, loss[loss=0.1456, simple_loss=0.2439, pruned_loss=0.02367, over 7155.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2418, pruned_loss=0.02833, over 1428395.45 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:12:31,327 INFO [train.py:812] (0/8) Epoch 39, batch 2800, loss[loss=0.1426, simple_loss=0.239, pruned_loss=0.02316, over 7336.00 frames.], tot_loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.0286, over 1425487.39 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:13:29,182 INFO [train.py:812] (0/8) Epoch 39, batch 2850, loss[loss=0.1295, simple_loss=0.2223, pruned_loss=0.0183, over 6463.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2423, pruned_loss=0.02837, over 1425953.76 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:14:28,567 INFO [train.py:812] (0/8) Epoch 39, batch 2900, loss[loss=0.1613, simple_loss=0.263, pruned_loss=0.02986, over 7314.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2422, pruned_loss=0.02839, over 1425178.73 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 06:15:27,558 INFO [train.py:812] (0/8) Epoch 39, batch 2950, loss[loss=0.1407, simple_loss=0.2361, pruned_loss=0.02267, over 7330.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2416, pruned_loss=0.02854, over 1428860.07 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:16:26,909 INFO [train.py:812] (0/8) Epoch 39, batch 3000, loss[loss=0.1516, simple_loss=0.2532, pruned_loss=0.02502, over 7226.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.02862, over 1429629.08 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:16:26,910 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-16 06:16:34,437 INFO [train.py:841] (0/8) Epoch 39, validation: loss=0.153, simple_loss=0.2484, pruned_loss=0.02885, over 698248.00 frames.
+2022-05-16 06:17:33,502 INFO [train.py:812] (0/8) Epoch 39, batch 3050, loss[loss=0.1566, simple_loss=0.2423, pruned_loss=0.03543, over 7119.00 frames.], tot_loss[loss=0.1507, simple_loss=0.243, pruned_loss=0.02923, over 1426566.40 frames.], batch size: 17, lr: 1.99e-04
+2022-05-16 06:18:32,169 INFO [train.py:812] (0/8) Epoch 39, batch 3100, loss[loss=0.1434, simple_loss=0.2413, pruned_loss=0.02276, over 6456.00 frames.], tot_loss[loss=0.1505, simple_loss=0.243, pruned_loss=0.02898, over 1418660.05 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:19:30,256 INFO [train.py:812] (0/8) Epoch 39, batch 3150, loss[loss=0.1723, simple_loss=0.2602, pruned_loss=0.04224, over 7397.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2435, pruned_loss=0.02919, over 1423802.21 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 06:20:28,866 INFO [train.py:812] (0/8) Epoch 39, batch 3200, loss[loss=0.1551, simple_loss=0.2621, pruned_loss=0.02399, over 6586.00 frames.], tot_loss[loss=0.15, simple_loss=0.2426, pruned_loss=0.02873, over 1424761.86 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:21:26,196 INFO [train.py:812] (0/8) Epoch 39, batch 3250, loss[loss=0.1558, simple_loss=0.2455, pruned_loss=0.03309, over 6533.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2427, pruned_loss=0.0286, over 1425314.76 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:22:25,450 INFO [train.py:812] (0/8) Epoch 39, batch 3300, loss[loss=0.1689, simple_loss=0.2579, pruned_loss=0.03998, over 7153.00 frames.], tot_loss[loss=0.1501, simple_loss=0.243, pruned_loss=0.02862, over 1424437.95 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:23:24,355 INFO [train.py:812] (0/8) Epoch 39, batch 3350, loss[loss=0.1387, simple_loss=0.224, pruned_loss=0.02674, over 7129.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2422, pruned_loss=0.02837, over 1426083.12 frames.], batch size: 17, lr: 1.99e-04
+2022-05-16 06:24:23,010 INFO [train.py:812] (0/8) Epoch 39, batch 3400, loss[loss=0.164, simple_loss=0.2451, pruned_loss=0.04142, over 7361.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2419, pruned_loss=0.02824, over 1427564.32 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:25:22,172 INFO [train.py:812] (0/8) Epoch 39, batch 3450, loss[loss=0.1507, simple_loss=0.241, pruned_loss=0.03021, over 7219.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2415, pruned_loss=0.02842, over 1419913.85 frames.], batch size: 23, lr: 1.99e-04
+2022-05-16 06:26:21,433 INFO [train.py:812] (0/8) Epoch 39, batch 3500, loss[loss=0.1369, simple_loss=0.226, pruned_loss=0.02395, over 7160.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2419, pruned_loss=0.02874, over 1420610.32 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:27:20,242 INFO [train.py:812] (0/8) Epoch 39, batch 3550, loss[loss=0.1547, simple_loss=0.2607, pruned_loss=0.02432, over 7337.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02854, over 1423141.74 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:28:19,534 INFO [train.py:812] (0/8) Epoch 39, batch 3600, loss[loss=0.1256, simple_loss=0.2079, pruned_loss=0.02165, over 7263.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02887, over 1424861.62 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:29:17,984 INFO [train.py:812] (0/8) Epoch 39, batch 3650, loss[loss=0.156, simple_loss=0.2548, pruned_loss=0.02859, over 7057.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2424, pruned_loss=0.02871, over 1426274.72 frames.], batch size: 28, lr: 1.99e-04
+2022-05-16 06:30:16,878 INFO [train.py:812] (0/8) Epoch 39, batch 3700, loss[loss=0.1408, simple_loss=0.2337, pruned_loss=0.02396, over 6238.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2423, pruned_loss=0.0285, over 1423851.79 frames.], batch size: 37, lr: 1.99e-04
+2022-05-16 06:31:16,255 INFO [train.py:812] (0/8) Epoch 39, batch 3750, loss[loss=0.1429, simple_loss=0.2354, pruned_loss=0.02521, over 7221.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02872, over 1417800.82 frames.], batch size: 23, lr: 1.98e-04
+2022-05-16 06:32:15,606 INFO [train.py:812] (0/8) Epoch 39, batch 3800, loss[loss=0.13, simple_loss=0.2275, pruned_loss=0.01625, over 7355.00 frames.], tot_loss[loss=0.1488, simple_loss=0.241, pruned_loss=0.02828, over 1423982.37 frames.], batch size: 19, lr: 1.98e-04
+2022-05-16 06:33:12,750 INFO [train.py:812] (0/8) Epoch 39, batch 3850, loss[loss=0.2074, simple_loss=0.279, pruned_loss=0.06784, over 5227.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2418, pruned_loss=0.02855, over 1420993.49 frames.], batch size: 52, lr: 1.98e-04
+2022-05-16 06:34:10,683 INFO [train.py:812] (0/8) Epoch 39, batch 3900, loss[loss=0.1434, simple_loss=0.2363, pruned_loss=0.02529, over 7073.00 frames.], tot_loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.02858, over 1421324.22 frames.], batch size: 28, lr: 1.98e-04
+2022-05-16 06:35:09,121 INFO [train.py:812] (0/8) Epoch 39, batch 3950, loss[loss=0.167, simple_loss=0.2608, pruned_loss=0.03657, over 7284.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02842, over 1423210.71 frames.], batch size: 25, lr: 1.98e-04
+2022-05-16 06:36:07,262 INFO [train.py:812] (0/8) Epoch 39, batch 4000, loss[loss=0.1465, simple_loss=0.2446, pruned_loss=0.0242, over 6681.00 frames.], tot_loss[loss=0.149, simple_loss=0.2412, pruned_loss=0.02839, over 1424640.32 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:37:03,580 INFO [train.py:812] (0/8) Epoch 39, batch 4050, loss[loss=0.1585, simple_loss=0.262, pruned_loss=0.02749, over 6675.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2415, pruned_loss=0.02846, over 1423319.64 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:38:02,731 INFO [train.py:812] (0/8) Epoch 39, batch 4100, loss[loss=0.1494, simple_loss=0.2475, pruned_loss=0.0257, over 7211.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2407, pruned_loss=0.02856, over 1421968.25 frames.], batch size: 21, lr: 1.98e-04
+2022-05-16 06:39:01,679 INFO [train.py:812] (0/8) Epoch 39, batch 4150, loss[loss=0.1432, simple_loss=0.2386, pruned_loss=0.0239, over 7214.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2406, pruned_loss=0.02845, over 1419774.45 frames.], batch size: 21, lr: 1.98e-04
+2022-05-16 06:40:00,313 INFO [train.py:812] (0/8) Epoch 39, batch 4200, loss[loss=0.1576, simple_loss=0.2541, pruned_loss=0.03049, over 6705.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2406, pruned_loss=0.0282, over 1419564.57 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:40:58,856 INFO [train.py:812] (0/8) Epoch 39, batch 4250, loss[loss=0.1385, simple_loss=0.2239, pruned_loss=0.02652, over 7161.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2409, pruned_loss=0.02808, over 1416602.47 frames.], batch size: 17, lr: 1.98e-04
+2022-05-16 06:41:58,210 INFO [train.py:812] (0/8) Epoch 39, batch 4300, loss[loss=0.1455, simple_loss=0.2403, pruned_loss=0.02532, over 7285.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2411, pruned_loss=0.02809, over 1417520.65 frames.], batch size: 25, lr: 1.98e-04
+2022-05-16 06:42:57,064 INFO [train.py:812] (0/8) Epoch 39, batch 4350, loss[loss=0.1421, simple_loss=0.2387, pruned_loss=0.02275, over 7424.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02854, over 1413418.37 frames.], batch size: 20, lr: 1.98e-04
+2022-05-16 06:43:56,261 INFO [train.py:812] (0/8) Epoch 39, batch 4400, loss[loss=0.1623, simple_loss=0.2685, pruned_loss=0.02806, over 7329.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2433, pruned_loss=0.02877, over 1410470.45 frames.], batch size: 22, lr: 1.98e-04
+2022-05-16 06:44:54,110 INFO [train.py:812] (0/8) Epoch 39, batch 4450, loss[loss=0.1297, simple_loss=0.2121, pruned_loss=0.02363, over 7019.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2431, pruned_loss=0.02864, over 1398570.93 frames.], batch size: 16, lr: 1.98e-04
+2022-05-16 06:45:52,376 INFO [train.py:812] (0/8) Epoch 39, batch 4500, loss[loss=0.1594, simple_loss=0.2399, pruned_loss=0.03948, over 7163.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2437, pruned_loss=0.02904, over 1387621.22 frames.], batch size: 18, lr: 1.98e-04
+2022-05-16 06:46:49,710 INFO [train.py:812] (0/8) Epoch 39, batch 4550, loss[loss=0.2069, simple_loss=0.2981, pruned_loss=0.05787, over 5115.00 frames.], tot_loss[loss=0.1536, simple_loss=0.246, pruned_loss=0.03066, over 1348291.21 frames.], batch size: 52, lr: 1.98e-04
+2022-05-16 06:47:34,595 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-39.pt
+2022-05-16 06:47:54,904 INFO [train.py:812] (0/8) Epoch 40, batch 0, loss[loss=0.2068, simple_loss=0.308, pruned_loss=0.0528, over 7282.00 frames.], tot_loss[loss=0.2068, simple_loss=0.308, pruned_loss=0.0528, over 7282.00 frames.], batch size: 24, lr: 1.96e-04
+2022-05-16 06:48:53,259 INFO [train.py:812] (0/8) Epoch 40, batch 50, loss[loss=0.116, simple_loss=0.2016, pruned_loss=0.01516, over 7268.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2423, pruned_loss=0.02805, over 317097.43 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 06:49:52,152 INFO [train.py:812] (0/8) Epoch 40, batch 100, loss[loss=0.1285, simple_loss=0.2253, pruned_loss=0.01582, over 7354.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2405, pruned_loss=0.02743, over 562102.10 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 06:50:51,506 INFO [train.py:812] (0/8) Epoch 40, batch 150, loss[loss=0.1492, simple_loss=0.25, pruned_loss=0.02419, over 7238.00 frames.], tot_loss[loss=0.1463, simple_loss=0.238, pruned_loss=0.02729, over 755094.27 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:51:50,272 INFO [train.py:812] (0/8) Epoch 40, batch 200, loss[loss=0.1399, simple_loss=0.2225, pruned_loss=0.02863, over 7426.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2404, pruned_loss=0.02825, over 903343.16 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 06:52:48,876 INFO [train.py:812] (0/8) Epoch 40, batch 250, loss[loss=0.1323, simple_loss=0.2251, pruned_loss=0.01977, over 7113.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2402, pruned_loss=0.02818, over 1016302.44 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 06:53:47,827 INFO [train.py:812] (0/8) Epoch 40, batch 300, loss[loss=0.1479, simple_loss=0.2505, pruned_loss=0.0226, over 7286.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2409, pruned_loss=0.02794, over 1107365.71 frames.], batch size: 24, lr: 1.95e-04
+2022-05-16 06:54:46,961 INFO [train.py:812] (0/8) Epoch 40, batch 350, loss[loss=0.1501, simple_loss=0.2539, pruned_loss=0.02322, over 7141.00 frames.], tot_loss[loss=0.148, simple_loss=0.2402, pruned_loss=0.02788, over 1171412.25 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:55:45,351 INFO [train.py:812] (0/8) Epoch 40, batch 400, loss[loss=0.1517, simple_loss=0.2574, pruned_loss=0.02302, over 7183.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2409, pruned_loss=0.02791, over 1229168.01 frames.], batch size: 26, lr: 1.95e-04
+2022-05-16 06:56:53,627 INFO [train.py:812] (0/8) Epoch 40, batch 450, loss[loss=0.171, simple_loss=0.2636, pruned_loss=0.03922, over 7276.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2409, pruned_loss=0.02804, over 1272510.15 frames.], batch size: 25, lr: 1.95e-04
+2022-05-16 06:57:52,466 INFO [train.py:812] (0/8) Epoch 40, batch 500, loss[loss=0.1434, simple_loss=0.239, pruned_loss=0.0239, over 7307.00 frames.], tot_loss[loss=0.148, simple_loss=0.2402, pruned_loss=0.02789, over 1305386.90 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 06:58:59,574 INFO [train.py:812] (0/8) Epoch 40, batch 550, loss[loss=0.1514, simple_loss=0.2447, pruned_loss=0.029, over 7234.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2403, pruned_loss=0.02799, over 1327314.47 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:59:58,519 INFO [train.py:812] (0/8) Epoch 40, batch 600, loss[loss=0.1337, simple_loss=0.2264, pruned_loss=0.02048, over 7256.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2403, pruned_loss=0.02826, over 1349193.56 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 07:01:07,483 INFO [train.py:812] (0/8) Epoch 40, batch 650, loss[loss=0.158, simple_loss=0.2488, pruned_loss=0.03358, over 7238.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2402, pruned_loss=0.02826, over 1367723.59 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 07:02:07,006 INFO [train.py:812] (0/8) Epoch 40, batch 700, loss[loss=0.1207, simple_loss=0.2018, pruned_loss=0.01986, over 7285.00 frames.], tot_loss[loss=0.149, simple_loss=0.2406, pruned_loss=0.02874, over 1381632.77 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:03:06,181 INFO [train.py:812] (0/8) Epoch 40, batch 750, loss[loss=0.1251, simple_loss=0.2216, pruned_loss=0.0143, over 7358.00 frames.], tot_loss[loss=0.1481, simple_loss=0.24, pruned_loss=0.02812, over 1386867.44 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 07:04:05,430 INFO [train.py:812] (0/8) Epoch 40, batch 800, loss[loss=0.1471, simple_loss=0.2547, pruned_loss=0.01973, over 7113.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2396, pruned_loss=0.02781, over 1396097.34 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:05:03,685 INFO [train.py:812] (0/8) Epoch 40, batch 850, loss[loss=0.1203, simple_loss=0.2104, pruned_loss=0.01508, over 7129.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2409, pruned_loss=0.02836, over 1403587.24 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 07:06:12,334 INFO [train.py:812] (0/8) Epoch 40, batch 900, loss[loss=0.1587, simple_loss=0.2504, pruned_loss=0.03349, over 7210.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2419, pruned_loss=0.02826, over 1409716.64 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:07:10,687 INFO [train.py:812] (0/8) Epoch 40, batch 950, loss[loss=0.1799, simple_loss=0.2577, pruned_loss=0.05101, over 4703.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2424, pruned_loss=0.02847, over 1412328.37 frames.], batch size: 52, lr: 1.95e-04
+2022-05-16 07:08:20,193 INFO [train.py:812] (0/8) Epoch 40, batch 1000, loss[loss=0.1705, simple_loss=0.2691, pruned_loss=0.03599, over 7108.00 frames.], tot_loss[loss=0.15, simple_loss=0.2428, pruned_loss=0.02856, over 1411108.08 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:09:19,209 INFO [train.py:812] (0/8) Epoch 40, batch 1050, loss[loss=0.1451, simple_loss=0.2399, pruned_loss=0.02517, over 7224.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2422, pruned_loss=0.02814, over 1410030.40 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:09:49,376 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/checkpoint-180000.pt
+2022-05-16 07:10:42,474 INFO [train.py:812] (0/8) Epoch 40, batch 1100, loss[loss=0.1422, simple_loss=0.2298, pruned_loss=0.02733, over 7153.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2413, pruned_loss=0.02814, over 1408097.09 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:11:40,908 INFO [train.py:812] (0/8) Epoch 40, batch 1150, loss[loss=0.1566, simple_loss=0.2511, pruned_loss=0.03107, over 6726.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2415, pruned_loss=0.02839, over 1415544.55 frames.], batch size: 31, lr: 1.95e-04
+2022-05-16 07:12:38,502 INFO [train.py:812] (0/8) Epoch 40, batch 1200, loss[loss=0.1515, simple_loss=0.2454, pruned_loss=0.02876, over 6450.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2422, pruned_loss=0.02827, over 1417654.90 frames.], batch size: 38, lr: 1.95e-04
+2022-05-16 07:13:37,105 INFO [train.py:812] (0/8) Epoch 40, batch 1250, loss[loss=0.1741, simple_loss=0.263, pruned_loss=0.04258, over 7285.00 frames.], tot_loss[loss=0.1494, simple_loss=0.242, pruned_loss=0.02841, over 1421595.91 frames.], batch size: 25, lr: 1.95e-04
+2022-05-16 07:14:35,223 INFO [train.py:812] (0/8) Epoch 40, batch 1300, loss[loss=0.1599, simple_loss=0.2656, pruned_loss=0.02716, over 7431.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2418, pruned_loss=0.02823, over 1422432.65 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 07:15:34,005 INFO [train.py:812] (0/8) Epoch 40, batch 1350, loss[loss=0.1417, simple_loss=0.2426, pruned_loss=0.02036, over 6308.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02852, over 1421625.87 frames.], batch size: 37, lr: 1.95e-04
+2022-05-16 07:16:32,405 INFO [train.py:812] (0/8) Epoch 40, batch 1400, loss[loss=0.1538, simple_loss=0.2558, pruned_loss=0.02594, over 6365.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2423, pruned_loss=0.02813, over 1422903.56 frames.], batch size: 37, lr: 1.95e-04
+2022-05-16 07:17:30,653 INFO [train.py:812] (0/8) Epoch 40, batch 1450, loss[loss=0.1484, simple_loss=0.2509, pruned_loss=0.0229, over 7206.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2422, pruned_loss=0.02809, over 1424550.55 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:18:29,879 INFO [train.py:812] (0/8) Epoch 40, batch 1500, loss[loss=0.1361, simple_loss=0.2252, pruned_loss=0.02353, over 7143.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2428, pruned_loss=0.02815, over 1425484.12 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 07:19:28,043 INFO [train.py:812] (0/8) Epoch 40, batch 1550, loss[loss=0.1769, simple_loss=0.2712, pruned_loss=0.04133, over 7219.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2416, pruned_loss=0.02795, over 1423444.84 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:20:27,050 INFO [train.py:812] (0/8) Epoch 40, batch 1600, loss[loss=0.165, simple_loss=0.2592, pruned_loss=0.03539, over 7043.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2423, pruned_loss=0.02799, over 1426048.80 frames.], batch size: 28, lr: 1.95e-04
+2022-05-16 07:21:25,474 INFO [train.py:812] (0/8) Epoch 40, batch 1650, loss[loss=0.1582, simple_loss=0.2358, pruned_loss=0.04031, over 5041.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2419, pruned_loss=0.02779, over 1419273.41 frames.], batch size: 52, lr: 1.95e-04
+2022-05-16 07:22:23,881 INFO [train.py:812] (0/8) Epoch 40, batch 1700, loss[loss=0.1263, simple_loss=0.2119, pruned_loss=0.02036, over 6992.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2418, pruned_loss=0.02788, over 1413332.18 frames.], batch size: 16, lr: 1.95e-04
+2022-05-16 07:23:23,266 INFO [train.py:812] (0/8) Epoch 40, batch 1750, loss[loss=0.1571, simple_loss=0.252, pruned_loss=0.03107, over 7318.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2411, pruned_loss=0.02772, over 1415137.72 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:24:22,409 INFO [train.py:812] (0/8) Epoch 40, batch 1800, loss[loss=0.1563, simple_loss=0.2499, pruned_loss=0.03136, over 7347.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2423, pruned_loss=0.02815, over 1417760.51 frames.], batch size: 22, lr: 1.95e-04
+2022-05-16 07:25:21,043 INFO [train.py:812] (0/8) Epoch 40, batch 1850, loss[loss=0.1692, simple_loss=0.2585, pruned_loss=0.03993, over 7061.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2422, pruned_loss=0.02803, over 1421310.79 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:26:20,294 INFO [train.py:812] (0/8) Epoch 40, batch 1900, loss[loss=0.1496, simple_loss=0.2409, pruned_loss=0.02918, over 7157.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2424, pruned_loss=0.02829, over 1424471.24 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:27:17,887 INFO [train.py:812] (0/8) Epoch 40, batch 1950, loss[loss=0.177, simple_loss=0.2637, pruned_loss=0.04522, over 5110.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2421, pruned_loss=0.02843, over 1418371.23 frames.], batch size: 53, lr: 1.94e-04
+2022-05-16 07:28:16,463 INFO [train.py:812] (0/8) Epoch 40, batch 2000, loss[loss=0.1495, simple_loss=0.238, pruned_loss=0.03053, over 7067.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02824, over 1422255.83 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:29:15,160 INFO [train.py:812] (0/8) Epoch 40, batch 2050, loss[loss=0.1535, simple_loss=0.2488, pruned_loss=0.02907, over 7435.00 frames.], tot_loss[loss=0.1493, simple_loss=0.242, pruned_loss=0.02829, over 1426053.11 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:30:14,383 INFO [train.py:812] (0/8) Epoch 40, batch 2100, loss[loss=0.1174, simple_loss=0.1982, pruned_loss=0.01829, over 7410.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2414, pruned_loss=0.02814, over 1425158.85 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:31:12,643 INFO [train.py:812] (0/8) Epoch 40, batch 2150, loss[loss=0.1533, simple_loss=0.2557, pruned_loss=0.02548, over 7139.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2412, pruned_loss=0.02761, over 1428918.57 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:32:11,437 INFO [train.py:812] (0/8) Epoch 40, batch 2200, loss[loss=0.1662, simple_loss=0.255, pruned_loss=0.0387, over 7233.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2407, pruned_loss=0.02741, over 1431549.36 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:33:10,377 INFO [train.py:812] (0/8) Epoch 40, batch 2250, loss[loss=0.1516, simple_loss=0.2473, pruned_loss=0.02793, over 7212.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2411, pruned_loss=0.02761, over 1429312.48 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:34:08,363 INFO [train.py:812] (0/8) Epoch 40, batch 2300, loss[loss=0.146, simple_loss=0.2366, pruned_loss=0.0277, over 7438.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2401, pruned_loss=0.02748, over 1426791.32 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:35:07,173 INFO [train.py:812] (0/8) Epoch 40, batch 2350, loss[loss=0.1499, simple_loss=0.2482, pruned_loss=0.02584, over 7328.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2393, pruned_loss=0.02745, over 1425809.81 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:36:06,633 INFO [train.py:812] (0/8) Epoch 40, batch 2400, loss[loss=0.1617, simple_loss=0.2523, pruned_loss=0.0355, over 7206.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2391, pruned_loss=0.02757, over 1426408.15 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:37:04,705 INFO [train.py:812] (0/8) Epoch 40, batch 2450, loss[loss=0.1483, simple_loss=0.2426, pruned_loss=0.027, over 7010.00 frames.], tot_loss[loss=0.1476, simple_loss=0.24, pruned_loss=0.02759, over 1421471.54 frames.], batch size: 28, lr: 1.94e-04
+2022-05-16 07:38:03,598 INFO [train.py:812] (0/8) Epoch 40, batch 2500, loss[loss=0.134, simple_loss=0.2362, pruned_loss=0.0159, over 7415.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2407, pruned_loss=0.02796, over 1418210.31 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:39:02,627 INFO [train.py:812] (0/8) Epoch 40, batch 2550, loss[loss=0.1485, simple_loss=0.2496, pruned_loss=0.02369, over 7023.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2408, pruned_loss=0.02781, over 1418134.66 frames.], batch size: 28, lr: 1.94e-04
+2022-05-16 07:40:02,265 INFO [train.py:812] (0/8) Epoch 40, batch 2600, loss[loss=0.172, simple_loss=0.2678, pruned_loss=0.03809, over 7331.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2398, pruned_loss=0.02757, over 1418119.95 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:40:59,591 INFO [train.py:812] (0/8) Epoch 40, batch 2650, loss[loss=0.1528, simple_loss=0.2405, pruned_loss=0.0326, over 7167.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2406, pruned_loss=0.02793, over 1420745.68 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:42:08,105 INFO [train.py:812] (0/8) Epoch 40, batch 2700, loss[loss=0.1385, simple_loss=0.2373, pruned_loss=0.01986, over 7167.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2415, pruned_loss=0.02816, over 1422442.87 frames.], batch size: 26, lr: 1.94e-04
+2022-05-16 07:43:06,242 INFO [train.py:812] (0/8) Epoch 40, batch 2750, loss[loss=0.1789, simple_loss=0.2797, pruned_loss=0.03901, over 7307.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2412, pruned_loss=0.02784, over 1425555.03 frames.], batch size: 24, lr: 1.94e-04
+2022-05-16 07:44:05,759 INFO [train.py:812] (0/8) Epoch 40, batch 2800, loss[loss=0.1379, simple_loss=0.2278, pruned_loss=0.024, over 7064.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2415, pruned_loss=0.02792, over 1422206.76 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:45:02,888 INFO [train.py:812] (0/8) Epoch 40, batch 2850, loss[loss=0.1454, simple_loss=0.2437, pruned_loss=0.02358, over 6249.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2414, pruned_loss=0.02772, over 1418387.90 frames.], batch size: 37, lr: 1.94e-04
+2022-05-16 07:46:01,096 INFO [train.py:812] (0/8) Epoch 40, batch 2900, loss[loss=0.1291, simple_loss=0.2289, pruned_loss=0.01468, over 7077.00 frames.], tot_loss[loss=0.149, simple_loss=0.2418, pruned_loss=0.02805, over 1418513.67 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:46:58,674 INFO [train.py:812] (0/8) Epoch 40, batch 2950, loss[loss=0.1859, simple_loss=0.2727, pruned_loss=0.04957, over 7276.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2428, pruned_loss=0.02821, over 1418690.89 frames.], batch size: 24, lr: 1.94e-04
+2022-05-16 07:47:56,493 INFO [train.py:812] (0/8) Epoch 40, batch 3000, loss[loss=0.1661, simple_loss=0.2645, pruned_loss=0.03381, over 7346.00 frames.], tot_loss[loss=0.15, simple_loss=0.243, pruned_loss=0.0285, over 1412242.11 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:47:56,495 INFO [train.py:832] (0/8) Computing validation loss
+2022-05-16 07:48:04,107 INFO [train.py:841] (0/8) Epoch 40, validation: loss=0.1534, simple_loss=0.2485, pruned_loss=0.02916, over 698248.00 frames.
+2022-05-16 07:49:02,576 INFO [train.py:812] (0/8) Epoch 40, batch 3050, loss[loss=0.1338, simple_loss=0.2201, pruned_loss=0.02373, over 7358.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2423, pruned_loss=0.02829, over 1414543.19 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:50:01,835 INFO [train.py:812] (0/8) Epoch 40, batch 3100, loss[loss=0.1418, simple_loss=0.2411, pruned_loss=0.02125, over 7198.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2429, pruned_loss=0.02845, over 1416989.01 frames.], batch size: 26, lr: 1.94e-04
+2022-05-16 07:51:00,381 INFO [train.py:812] (0/8) Epoch 40, batch 3150, loss[loss=0.1299, simple_loss=0.2236, pruned_loss=0.01809, over 7151.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2424, pruned_loss=0.02828, over 1420835.63 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:51:59,461 INFO [train.py:812] (0/8) Epoch 40, batch 3200, loss[loss=0.1488, simple_loss=0.2434, pruned_loss=0.02711, over 5051.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2428, pruned_loss=0.02814, over 1421059.79 frames.], batch size: 53, lr: 1.94e-04
+2022-05-16 07:52:57,276 INFO [train.py:812] (0/8) Epoch 40, batch 3250, loss[loss=0.1555, simple_loss=0.2525, pruned_loss=0.02923, over 7378.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2435, pruned_loss=0.02861, over 1420744.30 frames.], batch size: 23, lr: 1.94e-04
+2022-05-16 07:53:57,053 INFO [train.py:812] (0/8) Epoch 40, batch 3300, loss[loss=0.1547, simple_loss=0.2518, pruned_loss=0.02881, over 7114.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2415, pruned_loss=0.02792, over 1419727.61 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:54:55,914 INFO [train.py:812] (0/8) Epoch 40, batch 3350, loss[loss=0.1443, simple_loss=0.2355, pruned_loss=0.02649, over 7113.00 frames.], tot_loss[loss=0.1481, simple_loss=0.241, pruned_loss=0.02763, over 1417467.41 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:55:55,662 INFO [train.py:812] (0/8) Epoch 40, batch 3400, loss[loss=0.1366, simple_loss=0.237, pruned_loss=0.01808, over 7161.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2403, pruned_loss=0.02735, over 1417762.09 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:56:54,697 INFO [train.py:812] (0/8) Epoch 40, batch 3450, loss[loss=0.1356, simple_loss=0.2157, pruned_loss=0.02777, over 7290.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2411, pruned_loss=0.02786, over 1416421.08 frames.], batch size: 17, lr: 1.94e-04
+2022-05-16 07:57:54,492 INFO [train.py:812] (0/8) Epoch 40, batch 3500, loss[loss=0.1612, simple_loss=0.2626, pruned_loss=0.02992, over 7318.00 frames.], tot_loss[loss=0.149, simple_loss=0.2419, pruned_loss=0.02807, over 1418344.12 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:58:53,156 INFO [train.py:812] (0/8) Epoch 40, batch 3550, loss[loss=0.1303, simple_loss=0.2174, pruned_loss=0.02159, over 7447.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2405, pruned_loss=0.02795, over 1419295.21 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:59:51,353 INFO [train.py:812] (0/8) Epoch 40, batch 3600, loss[loss=0.2063, simple_loss=0.2855, pruned_loss=0.06352, over 4830.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2412, pruned_loss=0.02851, over 1416512.62 frames.], batch size: 52, lr: 1.94e-04
+2022-05-16 08:00:51,211 INFO [train.py:812] (0/8) Epoch 40, batch 3650, loss[loss=0.1647, simple_loss=0.2589, pruned_loss=0.03522, over 6349.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2406, pruned_loss=0.02792, over 1418534.18 frames.], batch size: 37, lr: 1.94e-04
+2022-05-16 08:01:49,907 INFO [train.py:812] (0/8) Epoch 40, batch 3700, loss[loss=0.1392, simple_loss=0.2195, pruned_loss=0.02946, over 7139.00 frames.], tot_loss[loss=0.148, simple_loss=0.2403, pruned_loss=0.02785, over 1422686.50 frames.], batch size: 17, lr: 1.94e-04
+2022-05-16 08:02:46,987 INFO [train.py:812] (0/8) Epoch 40, batch 3750, loss[loss=0.1404, simple_loss=0.2305, pruned_loss=0.02518, over 7348.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2411, pruned_loss=0.02798, over 1419623.97 frames.], batch size: 19, lr: 1.93e-04
+2022-05-16 08:03:45,489 INFO [train.py:812] (0/8) Epoch 40, batch 3800, loss[loss=0.1307, simple_loss=0.2118, pruned_loss=0.02478, over 7429.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2414, pruned_loss=0.02802, over 1423880.13 frames.], batch size: 17, lr: 1.93e-04
+2022-05-16 08:04:42,346 INFO [train.py:812] (0/8) Epoch 40, batch 3850, loss[loss=0.1608, simple_loss=0.2503, pruned_loss=0.03571, over 7425.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2411, pruned_loss=0.02789, over 1420277.94 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:05:41,369 INFO [train.py:812] (0/8) Epoch 40, batch 3900, loss[loss=0.1668, simple_loss=0.2617, pruned_loss=0.03593, over 7214.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2412, pruned_loss=0.02787, over 1420990.46 frames.], batch size: 23, lr: 1.93e-04
+2022-05-16 08:06:40,225 INFO [train.py:812] (0/8) Epoch 40, batch 3950, loss[loss=0.1321, simple_loss=0.2223, pruned_loss=0.02094, over 7085.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2407, pruned_loss=0.02799, over 1416593.87 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:07:38,729 INFO [train.py:812] (0/8) Epoch 40, batch 4000, loss[loss=0.1402, simple_loss=0.2213, pruned_loss=0.02956, over 7114.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2409, pruned_loss=0.02829, over 1415105.96 frames.], batch size: 17, lr: 1.93e-04
+2022-05-16 08:08:36,084 INFO [train.py:812] (0/8) Epoch 40, batch 4050, loss[loss=0.1631, simple_loss=0.2458, pruned_loss=0.04019, over 7199.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2409, pruned_loss=0.02811, over 1420090.48 frames.], batch size: 22, lr: 1.93e-04
+2022-05-16 08:09:35,652 INFO [train.py:812] (0/8) Epoch 40, batch 4100, loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.0291, over 7236.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2402, pruned_loss=0.02803, over 1419901.90 frames.], batch size: 20, lr: 1.93e-04
+2022-05-16 08:10:34,178 INFO [train.py:812] (0/8) Epoch 40, batch 4150, loss[loss=0.145, simple_loss=0.2343, pruned_loss=0.02785, over 7282.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2411, pruned_loss=0.02805, over 1421308.97 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:11:33,026 INFO [train.py:812] (0/8) Epoch 40, batch 4200, loss[loss=0.1311, simple_loss=0.2175, pruned_loss=0.02237, over 7162.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2411, pruned_loss=0.02824, over 1423489.28 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:12:31,935 INFO [train.py:812] (0/8) Epoch 40, batch 4250, loss[loss=0.1599, simple_loss=0.2544, pruned_loss=0.03272, over 7312.00 frames.], tot_loss[loss=0.1485, simple_loss=0.241, pruned_loss=0.02799, over 1419519.78 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:13:30,179 INFO [train.py:812] (0/8) Epoch 40, batch 4300, loss[loss=0.1349, simple_loss=0.2244, pruned_loss=0.02276, over 7160.00 frames.], tot_loss[loss=0.1476, simple_loss=0.24, pruned_loss=0.02761, over 1420191.50 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:14:29,467 INFO [train.py:812] (0/8) Epoch 40, batch 4350, loss[loss=0.1494, simple_loss=0.2373, pruned_loss=0.03075, over 7337.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2403, pruned_loss=0.02759, over 1421164.45 frames.], batch size: 20, lr: 1.93e-04
+2022-05-16 08:15:29,071 INFO [train.py:812] (0/8) Epoch 40, batch 4400, loss[loss=0.1656, simple_loss=0.2547, pruned_loss=0.03822, over 6749.00 frames.], tot_loss[loss=0.148, simple_loss=0.2406, pruned_loss=0.02769, over 1421574.59 frames.], batch size: 31, lr: 1.93e-04
+2022-05-16 08:16:26,679 INFO [train.py:812] (0/8) Epoch 40, batch 4450, loss[loss=0.1331, simple_loss=0.222, pruned_loss=0.02214, over 7166.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2405, pruned_loss=0.02795, over 1408931.18 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:17:25,846 INFO [train.py:812] (0/8) Epoch 40, batch 4500, loss[loss=0.1491, simple_loss=0.2464, pruned_loss=0.02593, over 7218.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2415, pruned_loss=0.02846, over 1401654.74 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:18:25,889 INFO [train.py:812] (0/8) Epoch 40, batch 4550, loss[loss=0.1255, simple_loss=0.2174, pruned_loss=0.01682, over 7176.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2387, pruned_loss=0.02816, over 1393041.39 frames.], batch size: 16, lr: 1.93e-04
+2022-05-16 08:19:10,406 INFO [checkpoint.py:75] (0/8) Saving checkpoint to pruned_transducer_stateless5/exp-L/epoch-40.pt
+2022-05-16 08:19:19,470 INFO [train.py:1030] (0/8) Done!