diff --git "a/exp/log/log-train-2022-04-28-06-39-03-0" "b/exp/log/log-train-2022-04-28-06-39-03-0"
new file mode 100644--- /dev/null
+++ "b/exp/log/log-train-2022-04-28-06-39-03-0"
@@ -0,0 +1,3846 @@
+2022-04-28 06:39:03,114 INFO [train.py:827] (0/8) Training started
+2022-04-28 06:39:03,140 INFO [train.py:837] (0/8) Device: cuda:0
+2022-04-28 06:39:03,161 INFO [train.py:846] (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': '1.14', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '3b83183234d0f1d8391872630551c5af7c491ed2', 'k2-git-date': 'Tue Apr 12 08:26:41 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', 'icefall-git-sha1': 'd79f5fe-dirty', 'icefall-git-date': 'Mon Apr 25 17:26:43 2022', 'icefall-path': '/ceph-fj/fangjun/open-source-2/icefall-deeper-conformer', 'k2-path': '/ceph-fj/fangjun/open-source-2/k2-multi-2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-fj/fangjun/open-source-2/lhotse-multi-3/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0309102938-68688b4cbd-xhtcg', 'IP address': '10.48.32.137'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 0, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless4/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': 8000, 'keep_last_k': 20, '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}
+2022-04-28 06:39:03,161 INFO [train.py:848] (0/8) About to create model
+2022-04-28 06:39:03,686 INFO [train.py:852] (0/8) Number of model parameters: 118129516
+2022-04-28 06:39:09,557 INFO [train.py:858] (0/8) Using DDP
+2022-04-28 06:39:10,511 INFO [asr_datamodule.py:391] (0/8) About to get train-clean-100 cuts
+2022-04-28 06:39:16,562 INFO [asr_datamodule.py:398] (0/8) About to get train-clean-360 cuts
+2022-04-28 06:39:41,238 INFO [asr_datamodule.py:405] (0/8) About to get train-other-500 cuts
+2022-04-28 06:40:23,295 INFO [asr_datamodule.py:209] (0/8) Enable MUSAN
+2022-04-28 06:40:23,295 INFO [asr_datamodule.py:210] (0/8) About to get Musan cuts
+2022-04-28 06:40:24,564 INFO [asr_datamodule.py:238] (0/8) Enable SpecAugment
+2022-04-28 06:40:24,564 INFO [asr_datamodule.py:239] (0/8) Time warp factor: 80
+2022-04-28 06:40:24,564 INFO [asr_datamodule.py:251] (0/8) Num frame mask: 10
+2022-04-28 06:40:24,564 INFO [asr_datamodule.py:264] (0/8) About to create train dataset
+2022-04-28 06:40:24,564 INFO [asr_datamodule.py:292] (0/8) Using BucketingSampler.
+2022-04-28 06:40:29,135 INFO [asr_datamodule.py:308] (0/8) About to create train dataloader
+2022-04-28 06:40:29,136 INFO [asr_datamodule.py:412] (0/8) About to get dev-clean cuts
+2022-04-28 06:40:29,391 INFO [asr_datamodule.py:417] (0/8) About to get dev-other cuts
+2022-04-28 06:40:29,516 INFO [asr_datamodule.py:339] (0/8) About to create dev dataset
+2022-04-28 06:40:29,527 INFO [asr_datamodule.py:358] (0/8) About to create dev dataloader
+2022-04-28 06:40:29,527 INFO [train.py:987] (0/8) Sanity check -- see if any of the batches in epoch 0 would cause OOM.
+2022-04-28 06:40:42,726 INFO [distributed.py:874] (0/8) Reducer buckets have been rebuilt in this iteration.
+2022-04-28 06:41:17,076 INFO [train.py:763] (0/8) Epoch 0, batch 0, loss[loss=0.6419, simple_loss=1.284, pruned_loss=7.064, over 7290.00 frames.], tot_loss[loss=0.6419, simple_loss=1.284, pruned_loss=7.064, over 7290.00 frames.], batch size: 17, lr: 3.00e-03
+2022-04-28 06:42:23,567 INFO [train.py:763] (0/8) Epoch 0, batch 50, loss[loss=0.5289, simple_loss=1.058, pruned_loss=6.703, over 7154.00 frames.], tot_loss[loss=0.5646, simple_loss=1.129, pruned_loss=6.944, over 324226.35 frames.], batch size: 19, lr: 3.00e-03
+2022-04-28 06:43:30,304 INFO [train.py:763] (0/8) Epoch 0, batch 100, loss[loss=0.389, simple_loss=0.778, pruned_loss=6.515, over 6992.00 frames.], tot_loss[loss=0.509, simple_loss=1.018, pruned_loss=6.865, over 566699.90 frames.], batch size: 16, lr: 3.00e-03
+2022-04-28 06:44:37,541 INFO [train.py:763] (0/8) Epoch 0, batch 150, loss[loss=0.3853, simple_loss=0.7706, pruned_loss=6.674, over 6996.00 frames.], tot_loss[loss=0.4768, simple_loss=0.9536, pruned_loss=6.854, over 757952.98 frames.], batch size: 16, lr: 3.00e-03
+2022-04-28 06:45:44,962 INFO [train.py:763] (0/8) Epoch 0, batch 200, loss[loss=0.4312, simple_loss=0.8625, pruned_loss=6.852, over 7316.00 frames.], tot_loss[loss=0.4528, simple_loss=0.9055, pruned_loss=6.829, over 908488.44 frames.], batch size: 25, lr: 3.00e-03
+2022-04-28 06:46:50,984 INFO [train.py:763] (0/8) Epoch 0, batch 250, loss[loss=0.3858, simple_loss=0.7716, pruned_loss=6.663, over 7333.00 frames.], tot_loss[loss=0.4379, simple_loss=0.8759, pruned_loss=6.801, over 1016999.81 frames.], batch size: 21, lr: 3.00e-03
+2022-04-28 06:47:58,729 INFO [train.py:763] (0/8) Epoch 0, batch 300, loss[loss=0.3995, simple_loss=0.7991, pruned_loss=6.778, over 7291.00 frames.], tot_loss[loss=0.4257, simple_loss=0.8515, pruned_loss=6.77, over 1108811.87 frames.], batch size: 25, lr: 3.00e-03
+2022-04-28 06:49:06,202 INFO [train.py:763] (0/8) Epoch 0, batch 350, loss[loss=0.4039, simple_loss=0.8079, pruned_loss=6.771, over 7255.00 frames.], tot_loss[loss=0.4153, simple_loss=0.8306, pruned_loss=6.736, over 1178668.25 frames.], batch size: 19, lr: 3.00e-03
+2022-04-28 06:50:12,120 INFO [train.py:763] (0/8) Epoch 0, batch 400, loss[loss=0.3928, simple_loss=0.7857, pruned_loss=6.73, over 7409.00 frames.], tot_loss[loss=0.4048, simple_loss=0.8096, pruned_loss=6.706, over 1231926.34 frames.], batch size: 21, lr: 3.00e-03
+2022-04-28 06:51:17,807 INFO [train.py:763] (0/8) Epoch 0, batch 450, loss[loss=0.3544, simple_loss=0.7087, pruned_loss=6.634, over 7408.00 frames.], tot_loss[loss=0.3926, simple_loss=0.7851, pruned_loss=6.689, over 1268151.27 frames.], batch size: 21, lr: 2.99e-03
+2022-04-28 06:52:24,508 INFO [train.py:763] (0/8) Epoch 0, batch 500, loss[loss=0.3152, simple_loss=0.6304, pruned_loss=6.651, over 7204.00 frames.], tot_loss[loss=0.3762, simple_loss=0.7525, pruned_loss=6.679, over 1304139.11 frames.], batch size: 22, lr: 2.99e-03
+2022-04-28 06:53:30,000 INFO [train.py:763] (0/8) Epoch 0, batch 550, loss[loss=0.3049, simple_loss=0.6099, pruned_loss=6.665, over 7340.00 frames.], tot_loss[loss=0.3621, simple_loss=0.7242, pruned_loss=6.678, over 1329852.13 frames.], batch size: 22, lr: 2.99e-03
+2022-04-28 06:54:36,577 INFO [train.py:763] (0/8) Epoch 0, batch 600, loss[loss=0.3026, simple_loss=0.6052, pruned_loss=6.618, over 7111.00 frames.], tot_loss[loss=0.3471, simple_loss=0.6941, pruned_loss=6.67, over 1349991.24 frames.], batch size: 21, lr: 2.99e-03
+2022-04-28 06:55:42,134 INFO [train.py:763] (0/8) Epoch 0, batch 650, loss[loss=0.241, simple_loss=0.4821, pruned_loss=6.5, over 6990.00 frames.], tot_loss[loss=0.3322, simple_loss=0.6645, pruned_loss=6.659, over 1368558.64 frames.], batch size: 16, lr: 2.99e-03
+2022-04-28 06:56:47,778 INFO [train.py:763] (0/8) Epoch 0, batch 700, loss[loss=0.299, simple_loss=0.598, pruned_loss=6.786, over 7205.00 frames.], tot_loss[loss=0.3181, simple_loss=0.6361, pruned_loss=6.645, over 1380389.26 frames.], batch size: 23, lr: 2.99e-03
+2022-04-28 06:57:54,489 INFO [train.py:763] (0/8) Epoch 0, batch 750, loss[loss=0.2484, simple_loss=0.4968, pruned_loss=6.424, over 7286.00 frames.], tot_loss[loss=0.3049, simple_loss=0.6098, pruned_loss=6.627, over 1392227.11 frames.], batch size: 17, lr: 2.98e-03
+2022-04-28 06:59:01,277 INFO [train.py:763] (0/8) Epoch 0, batch 800, loss[loss=0.248, simple_loss=0.496, pruned_loss=6.574, over 7119.00 frames.], tot_loss[loss=0.2941, simple_loss=0.5881, pruned_loss=6.614, over 1397492.92 frames.], batch size: 21, lr: 2.98e-03
+2022-04-28 07:00:07,436 INFO [train.py:763] (0/8) Epoch 0, batch 850, loss[loss=0.25, simple_loss=0.5001, pruned_loss=6.563, over 7221.00 frames.], tot_loss[loss=0.2846, simple_loss=0.5693, pruned_loss=6.599, over 1402951.77 frames.], batch size: 21, lr: 2.98e-03
+2022-04-28 07:01:13,432 INFO [train.py:763] (0/8) Epoch 0, batch 900, loss[loss=0.2479, simple_loss=0.4959, pruned_loss=6.695, over 7304.00 frames.], tot_loss[loss=0.2753, simple_loss=0.5507, pruned_loss=6.588, over 1407271.55 frames.], batch size: 21, lr: 2.98e-03
+2022-04-28 07:02:19,015 INFO [train.py:763] (0/8) Epoch 0, batch 950, loss[loss=0.2353, simple_loss=0.4706, pruned_loss=6.478, over 6962.00 frames.], tot_loss[loss=0.2697, simple_loss=0.5394, pruned_loss=6.583, over 1403944.86 frames.], batch size: 16, lr: 2.97e-03
+2022-04-28 07:03:26,145 INFO [train.py:763] (0/8) Epoch 0, batch 1000, loss[loss=0.2038, simple_loss=0.4077, pruned_loss=6.493, over 6998.00 frames.], tot_loss[loss=0.2636, simple_loss=0.5272, pruned_loss=6.577, over 1404219.51 frames.], batch size: 16, lr: 2.97e-03
+2022-04-28 07:04:32,981 INFO [train.py:763] (0/8) Epoch 0, batch 1050, loss[loss=0.2022, simple_loss=0.4045, pruned_loss=6.435, over 7001.00 frames.], tot_loss[loss=0.2586, simple_loss=0.5173, pruned_loss=6.577, over 1406064.05 frames.], batch size: 16, lr: 2.97e-03
+2022-04-28 07:05:39,536 INFO [train.py:763] (0/8) Epoch 0, batch 1100, loss[loss=0.2233, simple_loss=0.4466, pruned_loss=6.538, over 7208.00 frames.], tot_loss[loss=0.2534, simple_loss=0.5068, pruned_loss=6.58, over 1410469.51 frames.], batch size: 22, lr: 2.96e-03
+2022-04-28 07:06:46,920 INFO [train.py:763] (0/8) Epoch 0, batch 1150, loss[loss=0.2601, simple_loss=0.5202, pruned_loss=6.656, over 6748.00 frames.], tot_loss[loss=0.2482, simple_loss=0.4964, pruned_loss=6.578, over 1412731.36 frames.], batch size: 31, lr: 2.96e-03
+2022-04-28 07:07:52,787 INFO [train.py:763] (0/8) Epoch 0, batch 1200, loss[loss=0.2454, simple_loss=0.4908, pruned_loss=6.701, over 7179.00 frames.], tot_loss[loss=0.2439, simple_loss=0.4878, pruned_loss=6.579, over 1420372.99 frames.], batch size: 26, lr: 2.96e-03
+2022-04-28 07:08:58,140 INFO [train.py:763] (0/8) Epoch 0, batch 1250, loss[loss=0.2247, simple_loss=0.4495, pruned_loss=6.615, over 7376.00 frames.], tot_loss[loss=0.2404, simple_loss=0.4808, pruned_loss=6.582, over 1414033.16 frames.], batch size: 23, lr: 2.95e-03
+2022-04-28 07:10:04,047 INFO [train.py:763] (0/8) Epoch 0, batch 1300, loss[loss=0.2241, simple_loss=0.4483, pruned_loss=6.671, over 7294.00 frames.], tot_loss[loss=0.2367, simple_loss=0.4735, pruned_loss=6.585, over 1421353.02 frames.], batch size: 24, lr: 2.95e-03
+2022-04-28 07:11:09,803 INFO [train.py:763] (0/8) Epoch 0, batch 1350, loss[loss=0.2293, simple_loss=0.4585, pruned_loss=6.6, over 7146.00 frames.], tot_loss[loss=0.2324, simple_loss=0.4649, pruned_loss=6.58, over 1422868.22 frames.], batch size: 20, lr: 2.95e-03
+2022-04-28 07:12:15,118 INFO [train.py:763] (0/8) Epoch 0, batch 1400, loss[loss=0.2156, simple_loss=0.4311, pruned_loss=6.544, over 7286.00 frames.], tot_loss[loss=0.2307, simple_loss=0.4614, pruned_loss=6.589, over 1418745.68 frames.], batch size: 24, lr: 2.94e-03
+2022-04-28 07:13:21,021 INFO [train.py:763] (0/8) Epoch 0, batch 1450, loss[loss=0.1989, simple_loss=0.3978, pruned_loss=6.499, over 7132.00 frames.], tot_loss[loss=0.2276, simple_loss=0.4552, pruned_loss=6.582, over 1419529.47 frames.], batch size: 17, lr: 2.94e-03
+2022-04-28 07:14:26,714 INFO [train.py:763] (0/8) Epoch 0, batch 1500, loss[loss=0.209, simple_loss=0.4181, pruned_loss=6.634, over 7270.00 frames.], tot_loss[loss=0.2251, simple_loss=0.4502, pruned_loss=6.577, over 1423078.74 frames.], batch size: 24, lr: 2.94e-03
+2022-04-28 07:15:32,251 INFO [train.py:763] (0/8) Epoch 0, batch 1550, loss[loss=0.2025, simple_loss=0.4051, pruned_loss=6.542, over 7117.00 frames.], tot_loss[loss=0.2228, simple_loss=0.4455, pruned_loss=6.573, over 1423255.85 frames.], batch size: 21, lr: 2.93e-03
+2022-04-28 07:16:38,331 INFO [train.py:763] (0/8) Epoch 0, batch 1600, loss[loss=0.1966, simple_loss=0.3931, pruned_loss=6.518, over 7319.00 frames.], tot_loss[loss=0.2203, simple_loss=0.4406, pruned_loss=6.567, over 1420576.14 frames.], batch size: 20, lr: 2.93e-03
+2022-04-28 07:17:45,347 INFO [train.py:763] (0/8) Epoch 0, batch 1650, loss[loss=0.1994, simple_loss=0.3988, pruned_loss=6.463, over 7156.00 frames.], tot_loss[loss=0.2187, simple_loss=0.4374, pruned_loss=6.566, over 1422457.41 frames.], batch size: 18, lr: 2.92e-03
+2022-04-28 07:18:52,001 INFO [train.py:763] (0/8) Epoch 0, batch 1700, loss[loss=0.2215, simple_loss=0.4429, pruned_loss=6.547, over 6419.00 frames.], tot_loss[loss=0.2172, simple_loss=0.4345, pruned_loss=6.564, over 1416495.48 frames.], batch size: 37, lr: 2.92e-03
+2022-04-28 07:19:58,700 INFO [train.py:763] (0/8) Epoch 0, batch 1750, loss[loss=0.2207, simple_loss=0.4414, pruned_loss=6.488, over 6560.00 frames.], tot_loss[loss=0.2151, simple_loss=0.4301, pruned_loss=6.563, over 1417000.61 frames.], batch size: 38, lr: 2.91e-03
+2022-04-28 07:21:06,374 INFO [train.py:763] (0/8) Epoch 0, batch 1800, loss[loss=0.2168, simple_loss=0.4336, pruned_loss=6.584, over 7018.00 frames.], tot_loss[loss=0.2144, simple_loss=0.4287, pruned_loss=6.566, over 1417420.93 frames.], batch size: 28, lr: 2.91e-03
+2022-04-28 07:22:12,427 INFO [train.py:763] (0/8) Epoch 0, batch 1850, loss[loss=0.2011, simple_loss=0.4021, pruned_loss=6.414, over 5097.00 frames.], tot_loss[loss=0.2125, simple_loss=0.4251, pruned_loss=6.563, over 1417902.09 frames.], batch size: 52, lr: 2.91e-03
+2022-04-28 07:23:18,922 INFO [train.py:763] (0/8) Epoch 0, batch 1900, loss[loss=0.1752, simple_loss=0.3503, pruned_loss=6.523, over 7262.00 frames.], tot_loss[loss=0.2111, simple_loss=0.4221, pruned_loss=6.568, over 1419689.33 frames.], batch size: 19, lr: 2.90e-03
+2022-04-28 07:24:26,531 INFO [train.py:763] (0/8) Epoch 0, batch 1950, loss[loss=0.2141, simple_loss=0.4281, pruned_loss=6.666, over 7330.00 frames.], tot_loss[loss=0.2095, simple_loss=0.4191, pruned_loss=6.57, over 1421898.91 frames.], batch size: 21, lr: 2.90e-03
+2022-04-28 07:25:34,076 INFO [train.py:763] (0/8) Epoch 0, batch 2000, loss[loss=0.1925, simple_loss=0.385, pruned_loss=6.475, over 6779.00 frames.], tot_loss[loss=0.2082, simple_loss=0.4163, pruned_loss=6.568, over 1422753.03 frames.], batch size: 15, lr: 2.89e-03
+2022-04-28 07:26:39,965 INFO [train.py:763] (0/8) Epoch 0, batch 2050, loss[loss=0.2231, simple_loss=0.4462, pruned_loss=6.699, over 7220.00 frames.], tot_loss[loss=0.2071, simple_loss=0.4143, pruned_loss=6.567, over 1420794.33 frames.], batch size: 26, lr: 2.89e-03
+2022-04-28 07:27:45,826 INFO [train.py:763] (0/8) Epoch 0, batch 2100, loss[loss=0.1758, simple_loss=0.3516, pruned_loss=6.419, over 7165.00 frames.], tot_loss[loss=0.206, simple_loss=0.4119, pruned_loss=6.571, over 1418406.34 frames.], batch size: 18, lr: 2.88e-03
+2022-04-28 07:28:51,554 INFO [train.py:763] (0/8) Epoch 0, batch 2150, loss[loss=0.2115, simple_loss=0.4231, pruned_loss=6.679, over 7343.00 frames.], tot_loss[loss=0.2042, simple_loss=0.4083, pruned_loss=6.575, over 1421402.40 frames.], batch size: 22, lr: 2.88e-03
+2022-04-28 07:29:57,481 INFO [train.py:763] (0/8) Epoch 0, batch 2200, loss[loss=0.2058, simple_loss=0.4116, pruned_loss=6.578, over 7287.00 frames.], tot_loss[loss=0.2037, simple_loss=0.4074, pruned_loss=6.582, over 1421184.50 frames.], batch size: 25, lr: 2.87e-03
+2022-04-28 07:31:03,292 INFO [train.py:763] (0/8) Epoch 0, batch 2250, loss[loss=0.2001, simple_loss=0.4002, pruned_loss=6.703, over 7229.00 frames.], tot_loss[loss=0.2026, simple_loss=0.4053, pruned_loss=6.582, over 1419686.93 frames.], batch size: 21, lr: 2.86e-03
+2022-04-28 07:32:08,993 INFO [train.py:763] (0/8) Epoch 0, batch 2300, loss[loss=0.1803, simple_loss=0.3606, pruned_loss=6.454, over 7259.00 frames.], tot_loss[loss=0.2019, simple_loss=0.4038, pruned_loss=6.581, over 1413953.57 frames.], batch size: 19, lr: 2.86e-03
+2022-04-28 07:33:14,419 INFO [train.py:763] (0/8) Epoch 0, batch 2350, loss[loss=0.2506, simple_loss=0.5011, pruned_loss=6.678, over 5026.00 frames.], tot_loss[loss=0.2017, simple_loss=0.4035, pruned_loss=6.587, over 1414196.41 frames.], batch size: 52, lr: 2.85e-03
+2022-04-28 07:34:20,291 INFO [train.py:763] (0/8) Epoch 0, batch 2400, loss[loss=0.1907, simple_loss=0.3814, pruned_loss=6.641, over 7428.00 frames.], tot_loss[loss=0.2014, simple_loss=0.4028, pruned_loss=6.587, over 1410121.97 frames.], batch size: 20, lr: 2.85e-03
+2022-04-28 07:35:25,720 INFO [train.py:763] (0/8) Epoch 0, batch 2450, loss[loss=0.2305, simple_loss=0.461, pruned_loss=6.648, over 5196.00 frames.], tot_loss[loss=0.2005, simple_loss=0.4009, pruned_loss=6.587, over 1411170.63 frames.], batch size: 53, lr: 2.84e-03
+2022-04-28 07:36:32,812 INFO [train.py:763] (0/8) Epoch 0, batch 2500, loss[loss=0.2044, simple_loss=0.4088, pruned_loss=6.675, over 7335.00 frames.], tot_loss[loss=0.1992, simple_loss=0.3985, pruned_loss=6.585, over 1417536.80 frames.], batch size: 20, lr: 2.84e-03
+2022-04-28 07:37:40,463 INFO [train.py:763] (0/8) Epoch 0, batch 2550, loss[loss=0.1891, simple_loss=0.3781, pruned_loss=6.487, over 7419.00 frames.], tot_loss[loss=0.1997, simple_loss=0.3995, pruned_loss=6.595, over 1417949.07 frames.], batch size: 18, lr: 2.83e-03
+2022-04-28 07:38:46,547 INFO [train.py:763] (0/8) Epoch 0, batch 2600, loss[loss=0.2043, simple_loss=0.4085, pruned_loss=6.698, over 7225.00 frames.], tot_loss[loss=0.1988, simple_loss=0.3975, pruned_loss=6.598, over 1420716.07 frames.], batch size: 20, lr: 2.83e-03
+2022-04-28 07:39:52,339 INFO [train.py:763] (0/8) Epoch 0, batch 2650, loss[loss=0.1945, simple_loss=0.3891, pruned_loss=6.504, over 7223.00 frames.], tot_loss[loss=0.1974, simple_loss=0.3948, pruned_loss=6.597, over 1421770.42 frames.], batch size: 20, lr: 2.82e-03
+2022-04-28 07:40:58,208 INFO [train.py:763] (0/8) Epoch 0, batch 2700, loss[loss=0.1986, simple_loss=0.3972, pruned_loss=6.647, over 7142.00 frames.], tot_loss[loss=0.197, simple_loss=0.394, pruned_loss=6.595, over 1421216.53 frames.], batch size: 20, lr: 2.81e-03
+2022-04-28 07:42:03,320 INFO [train.py:763] (0/8) Epoch 0, batch 2750, loss[loss=0.1894, simple_loss=0.3788, pruned_loss=6.556, over 7322.00 frames.], tot_loss[loss=0.1966, simple_loss=0.3932, pruned_loss=6.6, over 1421954.98 frames.], batch size: 20, lr: 2.81e-03
+2022-04-28 07:43:09,951 INFO [train.py:763] (0/8) Epoch 0, batch 2800, loss[loss=0.2004, simple_loss=0.4007, pruned_loss=6.671, over 7151.00 frames.], tot_loss[loss=0.1963, simple_loss=0.3926, pruned_loss=6.6, over 1421280.91 frames.], batch size: 20, lr: 2.80e-03
+2022-04-28 07:44:16,832 INFO [train.py:763] (0/8) Epoch 0, batch 2850, loss[loss=0.1753, simple_loss=0.3506, pruned_loss=6.481, over 7348.00 frames.], tot_loss[loss=0.1952, simple_loss=0.3904, pruned_loss=6.6, over 1424701.26 frames.], batch size: 19, lr: 2.80e-03
+2022-04-28 07:45:22,340 INFO [train.py:763] (0/8) Epoch 0, batch 2900, loss[loss=0.1805, simple_loss=0.361, pruned_loss=6.639, over 7331.00 frames.], tot_loss[loss=0.1954, simple_loss=0.3908, pruned_loss=6.605, over 1420572.24 frames.], batch size: 20, lr: 2.79e-03
+2022-04-28 07:46:27,658 INFO [train.py:763] (0/8) Epoch 0, batch 2950, loss[loss=0.2108, simple_loss=0.4217, pruned_loss=6.596, over 7107.00 frames.], tot_loss[loss=0.1948, simple_loss=0.3895, pruned_loss=6.605, over 1417015.68 frames.], batch size: 26, lr: 2.78e-03
+2022-04-28 07:47:32,892 INFO [train.py:763] (0/8) Epoch 0, batch 3000, loss[loss=0.3261, simple_loss=0.3761, pruned_loss=1.38, over 7290.00 frames.], tot_loss[loss=0.2266, simple_loss=0.388, pruned_loss=6.582, over 1421439.69 frames.], batch size: 17, lr: 2.78e-03
+2022-04-28 07:47:32,893 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-28 07:47:50,998 INFO [train.py:792] (0/8) Epoch 0, validation: loss=2.072, simple_loss=0.4419, pruned_loss=1.851, over 698248.00 frames.
+2022-04-28 07:48:57,718 INFO [train.py:763] (0/8) Epoch 0, batch 3050, loss[loss=0.3249, simple_loss=0.4476, pruned_loss=1.01, over 6288.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3962, pruned_loss=5.395, over 1420041.50 frames.], batch size: 37, lr: 2.77e-03
+2022-04-28 07:50:04,091 INFO [train.py:763] (0/8) Epoch 0, batch 3100, loss[loss=0.2598, simple_loss=0.4089, pruned_loss=0.5533, over 7415.00 frames.], tot_loss[loss=0.2516, simple_loss=0.392, pruned_loss=4.334, over 1425959.27 frames.], batch size: 21, lr: 2.77e-03
+2022-04-28 07:51:10,059 INFO [train.py:763] (0/8) Epoch 0, batch 3150, loss[loss=0.2475, simple_loss=0.4135, pruned_loss=0.4076, over 7418.00 frames.], tot_loss[loss=0.2465, simple_loss=0.3882, pruned_loss=3.462, over 1426877.58 frames.], batch size: 21, lr: 2.76e-03
+2022-04-28 07:52:16,822 INFO [train.py:763] (0/8) Epoch 0, batch 3200, loss[loss=0.2326, simple_loss=0.4066, pruned_loss=0.2931, over 7299.00 frames.], tot_loss[loss=0.241, simple_loss=0.3867, pruned_loss=2.771, over 1422699.73 frames.], batch size: 24, lr: 2.75e-03
+2022-04-28 07:53:24,325 INFO [train.py:763] (0/8) Epoch 0, batch 3250, loss[loss=0.2059, simple_loss=0.3687, pruned_loss=0.2159, over 7144.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3846, pruned_loss=2.213, over 1422688.52 frames.], batch size: 20, lr: 2.75e-03
+2022-04-28 07:54:30,951 INFO [train.py:763] (0/8) Epoch 0, batch 3300, loss[loss=0.2006, simple_loss=0.3617, pruned_loss=0.1975, over 7379.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3843, pruned_loss=1.781, over 1418034.22 frames.], batch size: 23, lr: 2.74e-03
+2022-04-28 07:55:37,623 INFO [train.py:763] (0/8) Epoch 0, batch 3350, loss[loss=0.2411, simple_loss=0.4285, pruned_loss=0.2687, over 7290.00 frames.], tot_loss[loss=0.227, simple_loss=0.3839, pruned_loss=1.432, over 1422980.14 frames.], batch size: 24, lr: 2.73e-03
+2022-04-28 07:56:43,239 INFO [train.py:763] (0/8) Epoch 0, batch 3400, loss[loss=0.2105, simple_loss=0.3785, pruned_loss=0.2131, over 7258.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3837, pruned_loss=1.161, over 1423439.90 frames.], batch size: 19, lr: 2.73e-03
+2022-04-28 07:57:49,115 INFO [train.py:763] (0/8) Epoch 0, batch 3450, loss[loss=0.2155, simple_loss=0.3906, pruned_loss=0.2017, over 7273.00 frames.], tot_loss[loss=0.221, simple_loss=0.3832, pruned_loss=0.9493, over 1422585.42 frames.], batch size: 25, lr: 2.72e-03
+2022-04-28 07:58:54,331 INFO [train.py:763] (0/8) Epoch 0, batch 3500, loss[loss=0.2158, simple_loss=0.3909, pruned_loss=0.2032, over 7173.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3815, pruned_loss=0.7818, over 1420848.78 frames.], batch size: 26, lr: 2.72e-03
+2022-04-28 08:00:00,013 INFO [train.py:763] (0/8) Epoch 0, batch 3550, loss[loss=0.2152, simple_loss=0.3934, pruned_loss=0.1847, over 7216.00 frames.], tot_loss[loss=0.2147, simple_loss=0.379, pruned_loss=0.6493, over 1422438.97 frames.], batch size: 21, lr: 2.71e-03
+2022-04-28 08:01:06,056 INFO [train.py:763] (0/8) Epoch 0, batch 3600, loss[loss=0.2077, simple_loss=0.3729, pruned_loss=0.2123, over 7008.00 frames.], tot_loss[loss=0.2125, simple_loss=0.3776, pruned_loss=0.5467, over 1421168.15 frames.], batch size: 16, lr: 2.70e-03
+2022-04-28 08:02:21,064 INFO [train.py:763] (0/8) Epoch 0, batch 3650, loss[loss=0.2128, simple_loss=0.39, pruned_loss=0.1778, over 7219.00 frames.], tot_loss[loss=0.2107, simple_loss=0.3765, pruned_loss=0.4653, over 1421704.12 frames.], batch size: 21, lr: 2.70e-03
+2022-04-28 08:04:03,469 INFO [train.py:763] (0/8) Epoch 0, batch 3700, loss[loss=0.2139, simple_loss=0.3889, pruned_loss=0.1947, over 6645.00 frames.], tot_loss[loss=0.2087, simple_loss=0.3748, pruned_loss=0.3997, over 1426308.93 frames.], batch size: 31, lr: 2.69e-03
+2022-04-28 08:05:34,892 INFO [train.py:763] (0/8) Epoch 0, batch 3750, loss[loss=0.21, simple_loss=0.3798, pruned_loss=0.2015, over 7285.00 frames.], tot_loss[loss=0.207, simple_loss=0.3731, pruned_loss=0.3508, over 1418925.19 frames.], batch size: 18, lr: 2.68e-03
+2022-04-28 08:06:40,599 INFO [train.py:763] (0/8) Epoch 0, batch 3800, loss[loss=0.1657, simple_loss=0.3093, pruned_loss=0.1099, over 7126.00 frames.], tot_loss[loss=0.2056, simple_loss=0.372, pruned_loss=0.31, over 1418792.80 frames.], batch size: 17, lr: 2.68e-03
+2022-04-28 08:07:46,194 INFO [train.py:763] (0/8) Epoch 0, batch 3850, loss[loss=0.1595, simple_loss=0.3, pruned_loss=0.09536, over 7157.00 frames.], tot_loss[loss=0.2048, simple_loss=0.3715, pruned_loss=0.2781, over 1423726.89 frames.], batch size: 17, lr: 2.67e-03
+2022-04-28 08:08:52,493 INFO [train.py:763] (0/8) Epoch 0, batch 3900, loss[loss=0.1909, simple_loss=0.3485, pruned_loss=0.166, over 6824.00 frames.], tot_loss[loss=0.2046, simple_loss=0.372, pruned_loss=0.2549, over 1419970.89 frames.], batch size: 15, lr: 2.66e-03
+2022-04-28 08:09:58,862 INFO [train.py:763] (0/8) Epoch 0, batch 3950, loss[loss=0.1915, simple_loss=0.3481, pruned_loss=0.1746, over 6786.00 frames.], tot_loss[loss=0.2034, simple_loss=0.3705, pruned_loss=0.2349, over 1418469.82 frames.], batch size: 15, lr: 2.66e-03
+2022-04-28 08:11:04,208 INFO [train.py:763] (0/8) Epoch 0, batch 4000, loss[loss=0.2082, simple_loss=0.3839, pruned_loss=0.1622, over 7312.00 frames.], tot_loss[loss=0.2031, simple_loss=0.3708, pruned_loss=0.2193, over 1420668.84 frames.], batch size: 21, lr: 2.65e-03
+2022-04-28 08:12:09,513 INFO [train.py:763] (0/8) Epoch 0, batch 4050, loss[loss=0.2118, simple_loss=0.3913, pruned_loss=0.1613, over 7081.00 frames.], tot_loss[loss=0.2028, simple_loss=0.3708, pruned_loss=0.2067, over 1421522.45 frames.], batch size: 28, lr: 2.64e-03
+2022-04-28 08:13:15,844 INFO [train.py:763] (0/8) Epoch 0, batch 4100, loss[loss=0.1894, simple_loss=0.3499, pruned_loss=0.1452, over 7257.00 frames.], tot_loss[loss=0.2011, simple_loss=0.3683, pruned_loss=0.1946, over 1421099.38 frames.], batch size: 19, lr: 2.64e-03
+2022-04-28 08:14:22,423 INFO [train.py:763] (0/8) Epoch 0, batch 4150, loss[loss=0.1823, simple_loss=0.3398, pruned_loss=0.1236, over 7070.00 frames.], tot_loss[loss=0.2009, simple_loss=0.3684, pruned_loss=0.1864, over 1425557.11 frames.], batch size: 18, lr: 2.63e-03
+2022-04-28 08:15:27,433 INFO [train.py:763] (0/8) Epoch 0, batch 4200, loss[loss=0.211, simple_loss=0.3863, pruned_loss=0.1787, over 7209.00 frames.], tot_loss[loss=0.2006, simple_loss=0.3683, pruned_loss=0.1796, over 1425015.78 frames.], batch size: 22, lr: 2.63e-03
+2022-04-28 08:16:32,487 INFO [train.py:763] (0/8) Epoch 0, batch 4250, loss[loss=0.1859, simple_loss=0.3463, pruned_loss=0.1276, over 7419.00 frames.], tot_loss[loss=0.2005, simple_loss=0.3683, pruned_loss=0.1753, over 1423487.14 frames.], batch size: 20, lr: 2.62e-03
+2022-04-28 08:17:38,269 INFO [train.py:763] (0/8) Epoch 0, batch 4300, loss[loss=0.1953, simple_loss=0.3632, pruned_loss=0.137, over 7060.00 frames.], tot_loss[loss=0.2011, simple_loss=0.3695, pruned_loss=0.1723, over 1422795.64 frames.], batch size: 28, lr: 2.61e-03
+2022-04-28 08:18:43,774 INFO [train.py:763] (0/8) Epoch 0, batch 4350, loss[loss=0.1964, simple_loss=0.362, pruned_loss=0.1542, over 7426.00 frames.], tot_loss[loss=0.2009, simple_loss=0.3694, pruned_loss=0.1687, over 1426345.13 frames.], batch size: 20, lr: 2.61e-03
+2022-04-28 08:19:48,920 INFO [train.py:763] (0/8) Epoch 0, batch 4400, loss[loss=0.1886, simple_loss=0.3485, pruned_loss=0.1429, over 7273.00 frames.], tot_loss[loss=0.2011, simple_loss=0.37, pruned_loss=0.1664, over 1424277.72 frames.], batch size: 18, lr: 2.60e-03
+2022-04-28 08:20:54,086 INFO [train.py:763] (0/8) Epoch 0, batch 4450, loss[loss=0.1947, simple_loss=0.3603, pruned_loss=0.1456, over 7421.00 frames.], tot_loss[loss=0.2007, simple_loss=0.3697, pruned_loss=0.1632, over 1423360.08 frames.], batch size: 20, lr: 2.59e-03
+2022-04-28 08:21:59,575 INFO [train.py:763] (0/8) Epoch 0, batch 4500, loss[loss=0.228, simple_loss=0.4187, pruned_loss=0.1859, over 6485.00 frames.], tot_loss[loss=0.2008, simple_loss=0.37, pruned_loss=0.1611, over 1414058.75 frames.], batch size: 38, lr: 2.59e-03
+2022-04-28 08:23:05,620 INFO [train.py:763] (0/8) Epoch 0, batch 4550, loss[loss=0.2239, simple_loss=0.4063, pruned_loss=0.2074, over 5215.00 frames.], tot_loss[loss=0.2017, simple_loss=0.3717, pruned_loss=0.1614, over 1394835.05 frames.], batch size: 52, lr: 2.58e-03
+2022-04-28 08:23:55,758 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-0.pt
+2022-04-28 08:24:44,869 INFO [train.py:763] (0/8) Epoch 1, batch 0, loss[loss=0.2035, simple_loss=0.3739, pruned_loss=0.1653, over 7160.00 frames.], tot_loss[loss=0.2035, simple_loss=0.3739, pruned_loss=0.1653, over 7160.00 frames.], batch size: 26, lr: 2.56e-03
+2022-04-28 08:25:50,522 INFO [train.py:763] (0/8) Epoch 1, batch 50, loss[loss=0.2068, simple_loss=0.3829, pruned_loss=0.153, over 7242.00 frames.], tot_loss[loss=0.2005, simple_loss=0.3693, pruned_loss=0.1585, over 311855.47 frames.], batch size: 20, lr: 2.55e-03
+2022-04-28 08:26:56,241 INFO [train.py:763] (0/8) Epoch 1, batch 100, loss[loss=0.1748, simple_loss=0.3275, pruned_loss=0.111, over 7425.00 frames.], tot_loss[loss=0.1961, simple_loss=0.3626, pruned_loss=0.1483, over 559745.45 frames.], batch size: 20, lr: 2.54e-03
+2022-04-28 08:28:01,400 INFO [train.py:763] (0/8) Epoch 1, batch 150, loss[loss=0.1846, simple_loss=0.3449, pruned_loss=0.1221, over 7342.00 frames.], tot_loss[loss=0.1949, simple_loss=0.3608, pruned_loss=0.1454, over 750552.75 frames.], batch size: 20, lr: 2.54e-03
+2022-04-28 08:29:06,948 INFO [train.py:763] (0/8) Epoch 1, batch 200, loss[loss=0.187, simple_loss=0.3452, pruned_loss=0.1442, over 7166.00 frames.], tot_loss[loss=0.1935, simple_loss=0.3585, pruned_loss=0.143, over 900226.90 frames.], batch size: 19, lr: 2.53e-03
+2022-04-28 08:30:12,408 INFO [train.py:763] (0/8) Epoch 1, batch 250, loss[loss=0.2062, simple_loss=0.3809, pruned_loss=0.1574, over 7379.00 frames.], tot_loss[loss=0.1946, simple_loss=0.3602, pruned_loss=0.1448, over 1015025.03 frames.], batch size: 23, lr: 2.53e-03
+2022-04-28 08:31:17,604 INFO [train.py:763] (0/8) Epoch 1, batch 300, loss[loss=0.1929, simple_loss=0.3579, pruned_loss=0.1393, over 7259.00 frames.], tot_loss[loss=0.1946, simple_loss=0.3604, pruned_loss=0.1437, over 1104885.98 frames.], batch size: 19, lr: 2.52e-03
+2022-04-28 08:32:23,182 INFO [train.py:763] (0/8) Epoch 1, batch 350, loss[loss=0.1977, simple_loss=0.368, pruned_loss=0.1373, over 7208.00 frames.], tot_loss[loss=0.1937, simple_loss=0.3588, pruned_loss=0.1428, over 1173402.46 frames.], batch size: 21, lr: 2.51e-03
+2022-04-28 08:33:29,299 INFO [train.py:763] (0/8) Epoch 1, batch 400, loss[loss=0.1951, simple_loss=0.3629, pruned_loss=0.1369, over 7145.00 frames.], tot_loss[loss=0.1931, simple_loss=0.3578, pruned_loss=0.1417, over 1230512.12 frames.], batch size: 20, lr: 2.51e-03
+2022-04-28 08:34:36,151 INFO [train.py:763] (0/8) Epoch 1, batch 450, loss[loss=0.1891, simple_loss=0.3526, pruned_loss=0.1286, over 7162.00 frames.], tot_loss[loss=0.1934, simple_loss=0.3585, pruned_loss=0.1413, over 1275815.00 frames.], batch size: 19, lr: 2.50e-03
+2022-04-28 08:35:42,356 INFO [train.py:763] (0/8) Epoch 1, batch 500, loss[loss=0.2055, simple_loss=0.3769, pruned_loss=0.1703, over 7165.00 frames.], tot_loss[loss=0.1938, simple_loss=0.3592, pruned_loss=0.1415, over 1307010.19 frames.], batch size: 18, lr: 2.49e-03
+2022-04-28 08:36:48,848 INFO [train.py:763] (0/8) Epoch 1, batch 550, loss[loss=0.1709, simple_loss=0.32, pruned_loss=0.1085, over 7364.00 frames.], tot_loss[loss=0.1938, simple_loss=0.3591, pruned_loss=0.1419, over 1331676.19 frames.], batch size: 19, lr: 2.49e-03
+2022-04-28 08:37:55,697 INFO [train.py:763] (0/8) Epoch 1, batch 600, loss[loss=0.2005, simple_loss=0.3726, pruned_loss=0.1421, over 7375.00 frames.], tot_loss[loss=0.1948, simple_loss=0.361, pruned_loss=0.143, over 1353597.05 frames.], batch size: 23, lr: 2.48e-03
+2022-04-28 08:39:01,288 INFO [train.py:763] (0/8) Epoch 1, batch 650, loss[loss=0.1747, simple_loss=0.3242, pruned_loss=0.1258, over 7288.00 frames.], tot_loss[loss=0.1938, simple_loss=0.3592, pruned_loss=0.1417, over 1367970.49 frames.], batch size: 18, lr: 2.48e-03
+2022-04-28 08:40:06,984 INFO [train.py:763] (0/8) Epoch 1, batch 700, loss[loss=0.2071, simple_loss=0.3778, pruned_loss=0.1819, over 4882.00 frames.], tot_loss[loss=0.1929, simple_loss=0.3577, pruned_loss=0.1404, over 1379447.40 frames.], batch size: 53, lr: 2.47e-03
+2022-04-28 08:41:12,400 INFO [train.py:763] (0/8) Epoch 1, batch 750, loss[loss=0.1885, simple_loss=0.3477, pruned_loss=0.1464, over 7245.00 frames.], tot_loss[loss=0.1926, simple_loss=0.3573, pruned_loss=0.1395, over 1390244.62 frames.], batch size: 19, lr: 2.46e-03
+2022-04-28 08:42:18,205 INFO [train.py:763] (0/8) Epoch 1, batch 800, loss[loss=0.189, simple_loss=0.3513, pruned_loss=0.1332, over 7064.00 frames.], tot_loss[loss=0.1914, simple_loss=0.3555, pruned_loss=0.1371, over 1399985.28 frames.], batch size: 18, lr: 2.46e-03
+2022-04-28 08:43:24,118 INFO [train.py:763] (0/8) Epoch 1, batch 850, loss[loss=0.1798, simple_loss=0.3343, pruned_loss=0.1264, over 7328.00 frames.], tot_loss[loss=0.191, simple_loss=0.3546, pruned_loss=0.1365, over 1408189.89 frames.], batch size: 20, lr: 2.45e-03
+2022-04-28 08:44:29,828 INFO [train.py:763] (0/8) Epoch 1, batch 900, loss[loss=0.2056, simple_loss=0.378, pruned_loss=0.1655, over 7435.00 frames.], tot_loss[loss=0.191, simple_loss=0.3547, pruned_loss=0.1365, over 1413131.24 frames.], batch size: 20, lr: 2.45e-03
+2022-04-28 08:45:35,253 INFO [train.py:763] (0/8) Epoch 1, batch 950, loss[loss=0.1596, simple_loss=0.2989, pruned_loss=0.1015, over 7258.00 frames.], tot_loss[loss=0.191, simple_loss=0.3548, pruned_loss=0.1363, over 1414747.54 frames.], batch size: 19, lr: 2.44e-03
+2022-04-28 08:46:40,821 INFO [train.py:763] (0/8) Epoch 1, batch 1000, loss[loss=0.2007, simple_loss=0.3697, pruned_loss=0.1584, over 6664.00 frames.], tot_loss[loss=0.1901, simple_loss=0.3532, pruned_loss=0.1345, over 1416177.82 frames.], batch size: 31, lr: 2.43e-03
+2022-04-28 08:47:46,482 INFO [train.py:763] (0/8) Epoch 1, batch 1050, loss[loss=0.1821, simple_loss=0.3391, pruned_loss=0.1256, over 7429.00 frames.], tot_loss[loss=0.19, simple_loss=0.3532, pruned_loss=0.1345, over 1418890.59 frames.], batch size: 20, lr: 2.43e-03
+2022-04-28 08:48:51,697 INFO [train.py:763] (0/8) Epoch 1, batch 1100, loss[loss=0.1901, simple_loss=0.3526, pruned_loss=0.1383, over 7162.00 frames.], tot_loss[loss=0.1897, simple_loss=0.3528, pruned_loss=0.1333, over 1420632.50 frames.], batch size: 18, lr: 2.42e-03
+2022-04-28 08:49:57,312 INFO [train.py:763] (0/8) Epoch 1, batch 1150, loss[loss=0.1926, simple_loss=0.3599, pruned_loss=0.126, over 7241.00 frames.], tot_loss[loss=0.1887, simple_loss=0.3511, pruned_loss=0.1315, over 1423816.84 frames.], batch size: 20, lr: 2.41e-03
+2022-04-28 08:51:02,494 INFO [train.py:763] (0/8) Epoch 1, batch 1200, loss[loss=0.192, simple_loss=0.3569, pruned_loss=0.1354, over 7091.00 frames.], tot_loss[loss=0.1896, simple_loss=0.3528, pruned_loss=0.1326, over 1423126.82 frames.], batch size: 28, lr: 2.41e-03
+2022-04-28 08:52:07,809 INFO [train.py:763] (0/8) Epoch 1, batch 1250, loss[loss=0.1771, simple_loss=0.331, pruned_loss=0.116, over 7285.00 frames.], tot_loss[loss=0.1901, simple_loss=0.3536, pruned_loss=0.133, over 1422568.38 frames.], batch size: 18, lr: 2.40e-03
+2022-04-28 08:53:12,962 INFO [train.py:763] (0/8) Epoch 1, batch 1300, loss[loss=0.2134, simple_loss=0.3956, pruned_loss=0.1555, over 7224.00 frames.], tot_loss[loss=0.1911, simple_loss=0.3552, pruned_loss=0.135, over 1416803.11 frames.], batch size: 21, lr: 2.40e-03
+2022-04-28 08:54:18,355 INFO [train.py:763] (0/8) Epoch 1, batch 1350, loss[loss=0.169, simple_loss=0.3153, pruned_loss=0.1137, over 7281.00 frames.], tot_loss[loss=0.1894, simple_loss=0.3523, pruned_loss=0.1323, over 1420152.50 frames.], batch size: 17, lr: 2.39e-03
+2022-04-28 08:55:23,451 INFO [train.py:763] (0/8) Epoch 1, batch 1400, loss[loss=0.1749, simple_loss=0.3295, pruned_loss=0.1019, over 7224.00 frames.], tot_loss[loss=0.1895, simple_loss=0.3526, pruned_loss=0.1323, over 1418397.34 frames.], batch size: 21, lr: 2.39e-03
+2022-04-28 08:56:28,952 INFO [train.py:763] (0/8) Epoch 1, batch 1450, loss[loss=0.3224, simple_loss=0.3595, pruned_loss=0.1426, over 7155.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3552, pruned_loss=0.1361, over 1422618.42 frames.], batch size: 26, lr: 2.38e-03
+2022-04-28 08:57:34,416 INFO [train.py:763] (0/8) Epoch 1, batch 1500, loss[loss=0.3258, simple_loss=0.3638, pruned_loss=0.1439, over 6514.00 frames.], tot_loss[loss=0.2388, simple_loss=0.3562, pruned_loss=0.1364, over 1422021.15 frames.], batch size: 38, lr: 2.37e-03
+2022-04-28 08:58:40,190 INFO [train.py:763] (0/8) Epoch 1, batch 1550, loss[loss=0.2667, simple_loss=0.3229, pruned_loss=0.1053, over 7437.00 frames.], tot_loss[loss=0.2556, simple_loss=0.3574, pruned_loss=0.1358, over 1425968.91 frames.], batch size: 20, lr: 2.37e-03
+2022-04-28 08:59:47,371 INFO [train.py:763] (0/8) Epoch 1, batch 1600, loss[loss=0.2664, simple_loss=0.3261, pruned_loss=0.1034, over 7159.00 frames.], tot_loss[loss=0.267, simple_loss=0.3571, pruned_loss=0.1343, over 1425285.39 frames.], batch size: 18, lr: 2.36e-03
+2022-04-28 09:00:52,897 INFO [train.py:763] (0/8) Epoch 1, batch 1650, loss[loss=0.3424, simple_loss=0.3729, pruned_loss=0.156, over 7432.00 frames.], tot_loss[loss=0.275, simple_loss=0.356, pruned_loss=0.1326, over 1425417.30 frames.], batch size: 20, lr: 2.36e-03
+2022-04-28 09:01:59,257 INFO [train.py:763] (0/8) Epoch 1, batch 1700, loss[loss=0.3303, simple_loss=0.3831, pruned_loss=0.1388, over 7404.00 frames.], tot_loss[loss=0.282, simple_loss=0.3563, pruned_loss=0.1316, over 1424434.93 frames.], batch size: 21, lr: 2.35e-03
+2022-04-28 09:03:06,155 INFO [train.py:763] (0/8) Epoch 1, batch 1750, loss[loss=0.275, simple_loss=0.3313, pruned_loss=0.1093, over 7275.00 frames.], tot_loss[loss=0.2887, simple_loss=0.3579, pruned_loss=0.1314, over 1423760.49 frames.], batch size: 18, lr: 2.34e-03
+2022-04-28 09:04:13,437 INFO [train.py:763] (0/8) Epoch 1, batch 1800, loss[loss=0.2522, simple_loss=0.318, pruned_loss=0.09317, over 7364.00 frames.], tot_loss[loss=0.2927, simple_loss=0.3577, pruned_loss=0.1307, over 1424964.15 frames.], batch size: 19, lr: 2.34e-03
+2022-04-28 09:05:20,685 INFO [train.py:763] (0/8) Epoch 1, batch 1850, loss[loss=0.2647, simple_loss=0.3326, pruned_loss=0.09842, over 7332.00 frames.], tot_loss[loss=0.2938, simple_loss=0.356, pruned_loss=0.1289, over 1425525.59 frames.], batch size: 20, lr: 2.33e-03
+2022-04-28 09:06:26,268 INFO [train.py:763] (0/8) Epoch 1, batch 1900, loss[loss=0.2924, simple_loss=0.334, pruned_loss=0.1254, over 7006.00 frames.], tot_loss[loss=0.2971, simple_loss=0.3569, pruned_loss=0.1288, over 1428836.39 frames.], batch size: 16, lr: 2.33e-03
+2022-04-28 09:07:32,762 INFO [train.py:763] (0/8) Epoch 1, batch 1950, loss[loss=0.2423, simple_loss=0.3006, pruned_loss=0.09205, over 7272.00 frames.], tot_loss[loss=0.2993, simple_loss=0.3574, pruned_loss=0.1285, over 1428895.54 frames.], batch size: 18, lr: 2.32e-03
+2022-04-28 09:08:38,164 INFO [train.py:763] (0/8) Epoch 1, batch 2000, loss[loss=0.3381, simple_loss=0.3767, pruned_loss=0.1498, over 7118.00 frames.], tot_loss[loss=0.3038, simple_loss=0.3601, pruned_loss=0.1299, over 1423621.53 frames.], batch size: 21, lr: 2.32e-03
+2022-04-28 09:09:44,444 INFO [train.py:763] (0/8) Epoch 1, batch 2050, loss[loss=0.3635, simple_loss=0.4084, pruned_loss=0.1593, over 7090.00 frames.], tot_loss[loss=0.3033, simple_loss=0.359, pruned_loss=0.1285, over 1425250.68 frames.], batch size: 28, lr: 2.31e-03
+2022-04-28 09:10:49,772 INFO [train.py:763] (0/8) Epoch 1, batch 2100, loss[loss=0.2881, simple_loss=0.3358, pruned_loss=0.1202, over 7414.00 frames.], tot_loss[loss=0.3, simple_loss=0.3562, pruned_loss=0.1257, over 1425737.50 frames.], batch size: 18, lr: 2.31e-03
+2022-04-28 09:11:55,368 INFO [train.py:763] (0/8) Epoch 1, batch 2150, loss[loss=0.2645, simple_loss=0.3336, pruned_loss=0.09767, over 7424.00 frames.], tot_loss[loss=0.2997, simple_loss=0.3555, pruned_loss=0.1249, over 1424421.00 frames.], batch size: 21, lr: 2.30e-03
+2022-04-28 09:13:01,260 INFO [train.py:763] (0/8) Epoch 1, batch 2200, loss[loss=0.3608, simple_loss=0.3974, pruned_loss=0.1621, over 7118.00 frames.], tot_loss[loss=0.3, simple_loss=0.3552, pruned_loss=0.1246, over 1422530.91 frames.], batch size: 21, lr: 2.29e-03
+2022-04-28 09:14:06,912 INFO [train.py:763] (0/8) Epoch 1, batch 2250, loss[loss=0.3371, simple_loss=0.3936, pruned_loss=0.1403, over 7219.00 frames.], tot_loss[loss=0.2989, simple_loss=0.3545, pruned_loss=0.1234, over 1423813.01 frames.], batch size: 21, lr: 2.29e-03
+2022-04-28 09:15:14,153 INFO [train.py:763] (0/8) Epoch 1, batch 2300, loss[loss=0.3027, simple_loss=0.3689, pruned_loss=0.1183, over 7201.00 frames.], tot_loss[loss=0.2991, simple_loss=0.3546, pruned_loss=0.1232, over 1424964.24 frames.], batch size: 22, lr: 2.28e-03
+2022-04-28 09:16:21,360 INFO [train.py:763] (0/8) Epoch 1, batch 2350, loss[loss=0.2704, simple_loss=0.3433, pruned_loss=0.0987, over 7226.00 frames.], tot_loss[loss=0.2993, simple_loss=0.3548, pruned_loss=0.123, over 1423344.59 frames.], batch size: 20, lr: 2.28e-03
+2022-04-28 09:17:26,503 INFO [train.py:763] (0/8) Epoch 1, batch 2400, loss[loss=0.3251, simple_loss=0.3842, pruned_loss=0.133, over 7317.00 frames.], tot_loss[loss=0.2994, simple_loss=0.3552, pruned_loss=0.1226, over 1422714.65 frames.], batch size: 21, lr: 2.27e-03
+2022-04-28 09:18:31,938 INFO [train.py:763] (0/8) Epoch 1, batch 2450, loss[loss=0.283, simple_loss=0.3567, pruned_loss=0.1046, over 7314.00 frames.], tot_loss[loss=0.2997, simple_loss=0.3558, pruned_loss=0.1225, over 1426108.71 frames.], batch size: 21, lr: 2.27e-03
+2022-04-28 09:19:37,107 INFO [train.py:763] (0/8) Epoch 1, batch 2500, loss[loss=0.3217, simple_loss=0.3766, pruned_loss=0.1334, over 7191.00 frames.], tot_loss[loss=0.2993, simple_loss=0.3556, pruned_loss=0.122, over 1426394.07 frames.], batch size: 26, lr: 2.26e-03
+2022-04-28 09:20:43,303 INFO [train.py:763] (0/8) Epoch 1, batch 2550, loss[loss=0.2783, simple_loss=0.3269, pruned_loss=0.1148, over 6999.00 frames.], tot_loss[loss=0.2971, simple_loss=0.3539, pruned_loss=0.1206, over 1426427.10 frames.], batch size: 16, lr: 2.26e-03
+2022-04-28 09:21:48,830 INFO [train.py:763] (0/8) Epoch 1, batch 2600, loss[loss=0.3558, simple_loss=0.399, pruned_loss=0.1562, over 7194.00 frames.], tot_loss[loss=0.2944, simple_loss=0.352, pruned_loss=0.1187, over 1428811.52 frames.], batch size: 26, lr: 2.25e-03
+2022-04-28 09:22:54,019 INFO [train.py:763] (0/8) Epoch 1, batch 2650, loss[loss=0.3848, simple_loss=0.416, pruned_loss=0.1768, over 6291.00 frames.], tot_loss[loss=0.2946, simple_loss=0.3526, pruned_loss=0.1185, over 1427162.76 frames.], batch size: 37, lr: 2.25e-03
+2022-04-28 09:24:00,444 INFO [train.py:763] (0/8) Epoch 1, batch 2700, loss[loss=0.3402, simple_loss=0.4012, pruned_loss=0.1396, over 6716.00 frames.], tot_loss[loss=0.2928, simple_loss=0.3512, pruned_loss=0.1173, over 1426406.18 frames.], batch size: 31, lr: 2.24e-03
+2022-04-28 09:25:06,560 INFO [train.py:763] (0/8) Epoch 1, batch 2750, loss[loss=0.2743, simple_loss=0.3405, pruned_loss=0.1041, over 7260.00 frames.], tot_loss[loss=0.2929, simple_loss=0.3512, pruned_loss=0.1175, over 1423410.66 frames.], batch size: 24, lr: 2.24e-03
+2022-04-28 09:26:12,254 INFO [train.py:763] (0/8) Epoch 1, batch 2800, loss[loss=0.3032, simple_loss=0.3739, pruned_loss=0.1163, over 7197.00 frames.], tot_loss[loss=0.2926, simple_loss=0.3512, pruned_loss=0.1171, over 1426925.71 frames.], batch size: 23, lr: 2.23e-03
+2022-04-28 09:27:17,549 INFO [train.py:763] (0/8) Epoch 1, batch 2850, loss[loss=0.2896, simple_loss=0.3612, pruned_loss=0.1091, over 7277.00 frames.], tot_loss[loss=0.293, simple_loss=0.3513, pruned_loss=0.1175, over 1426440.59 frames.], batch size: 24, lr: 2.23e-03
+2022-04-28 09:28:22,525 INFO [train.py:763] (0/8) Epoch 1, batch 2900, loss[loss=0.2866, simple_loss=0.3549, pruned_loss=0.1091, over 7220.00 frames.], tot_loss[loss=0.2932, simple_loss=0.3519, pruned_loss=0.1173, over 1422919.77 frames.], batch size: 20, lr: 2.22e-03
+2022-04-28 09:29:27,939 INFO [train.py:763] (0/8) Epoch 1, batch 2950, loss[loss=0.2819, simple_loss=0.3543, pruned_loss=0.1048, over 7239.00 frames.], tot_loss[loss=0.2929, simple_loss=0.3515, pruned_loss=0.1172, over 1424016.81 frames.], batch size: 20, lr: 2.22e-03
+2022-04-28 09:30:33,557 INFO [train.py:763] (0/8) Epoch 1, batch 3000, loss[loss=0.2623, simple_loss=0.3193, pruned_loss=0.1026, over 7290.00 frames.], tot_loss[loss=0.292, simple_loss=0.3512, pruned_loss=0.1165, over 1426619.93 frames.], batch size: 17, lr: 2.21e-03
+2022-04-28 09:30:33,558 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-28 09:30:49,514 INFO [train.py:792] (0/8) Epoch 1, validation: loss=0.217, simple_loss=0.3099, pruned_loss=0.06207, over 698248.00 frames.
+2022-04-28 09:31:55,887 INFO [train.py:763] (0/8) Epoch 1, batch 3050, loss[loss=0.2329, simple_loss=0.309, pruned_loss=0.07846, over 7289.00 frames.], tot_loss[loss=0.2917, simple_loss=0.351, pruned_loss=0.1162, over 1421759.65 frames.], batch size: 18, lr: 2.20e-03
+2022-04-28 09:33:01,972 INFO [train.py:763] (0/8) Epoch 1, batch 3100, loss[loss=0.3505, simple_loss=0.3846, pruned_loss=0.1582, over 5086.00 frames.], tot_loss[loss=0.2938, simple_loss=0.3526, pruned_loss=0.1176, over 1422107.05 frames.], batch size: 52, lr: 2.20e-03
+2022-04-28 09:34:07,388 INFO [train.py:763] (0/8) Epoch 1, batch 3150, loss[loss=0.2437, simple_loss=0.3003, pruned_loss=0.09353, over 6771.00 frames.], tot_loss[loss=0.2927, simple_loss=0.3519, pruned_loss=0.1168, over 1423869.33 frames.], batch size: 15, lr: 2.19e-03
+2022-04-28 09:35:13,551 INFO [train.py:763] (0/8) Epoch 1, batch 3200, loss[loss=0.3373, simple_loss=0.387, pruned_loss=0.1438, over 4936.00 frames.], tot_loss[loss=0.2937, simple_loss=0.3528, pruned_loss=0.1173, over 1413273.66 frames.], batch size: 52, lr: 2.19e-03
+2022-04-28 09:36:19,400 INFO [train.py:763] (0/8) Epoch 1, batch 3250, loss[loss=0.2974, simple_loss=0.3535, pruned_loss=0.1206, over 7196.00 frames.], tot_loss[loss=0.2932, simple_loss=0.3525, pruned_loss=0.117, over 1415630.59 frames.], batch size: 23, lr: 2.18e-03
+2022-04-28 09:37:26,025 INFO [train.py:763] (0/8) Epoch 1, batch 3300, loss[loss=0.3206, simple_loss=0.3715, pruned_loss=0.1348, over 7195.00 frames.], tot_loss[loss=0.2931, simple_loss=0.3525, pruned_loss=0.1168, over 1420034.29 frames.], batch size: 22, lr: 2.18e-03
+2022-04-28 09:38:31,148 INFO [train.py:763] (0/8) Epoch 1, batch 3350, loss[loss=0.3675, simple_loss=0.4257, pruned_loss=0.1546, over 7141.00 frames.], tot_loss[loss=0.2934, simple_loss=0.3533, pruned_loss=0.1167, over 1423457.43 frames.], batch size: 26, lr: 2.18e-03
+2022-04-28 09:39:36,463 INFO [train.py:763] (0/8) Epoch 1, batch 3400, loss[loss=0.2334, simple_loss=0.2976, pruned_loss=0.08461, over 7127.00 frames.], tot_loss[loss=0.2918, simple_loss=0.3516, pruned_loss=0.1159, over 1424925.33 frames.], batch size: 17, lr: 2.17e-03
+2022-04-28 09:39:50,754 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-8000.pt
+2022-04-28 09:40:52,296 INFO [train.py:763] (0/8) Epoch 1, batch 3450, loss[loss=0.2799, simple_loss=0.3466, pruned_loss=0.1067, over 7295.00 frames.], tot_loss[loss=0.2893, simple_loss=0.3504, pruned_loss=0.1141, over 1427035.29 frames.], batch size: 24, lr: 2.17e-03
+2022-04-28 09:41:59,119 INFO [train.py:763] (0/8) Epoch 1, batch 3500, loss[loss=0.3223, simple_loss=0.3851, pruned_loss=0.1298, over 6425.00 frames.], tot_loss[loss=0.2903, simple_loss=0.3513, pruned_loss=0.1147, over 1424956.32 frames.], batch size: 38, lr: 2.16e-03
+2022-04-28 09:43:05,806 INFO [train.py:763] (0/8) Epoch 1, batch 3550, loss[loss=0.2787, simple_loss=0.3462, pruned_loss=0.1056, over 7314.00 frames.], tot_loss[loss=0.2893, simple_loss=0.3505, pruned_loss=0.1141, over 1424396.73 frames.], batch size: 25, lr: 2.16e-03
+2022-04-28 09:44:12,977 INFO [train.py:763] (0/8) Epoch 1, batch 3600, loss[loss=0.2662, simple_loss=0.3388, pruned_loss=0.09679, over 7234.00 frames.], tot_loss[loss=0.2899, simple_loss=0.3509, pruned_loss=0.1145, over 1425811.43 frames.], batch size: 20, lr: 2.15e-03
+2022-04-28 09:45:20,596 INFO [train.py:763] (0/8) Epoch 1, batch 3650, loss[loss=0.2617, simple_loss=0.3234, pruned_loss=0.09999, over 6830.00 frames.], tot_loss[loss=0.2903, simple_loss=0.3515, pruned_loss=0.1145, over 1426907.80 frames.], batch size: 15, lr: 2.15e-03
+2022-04-28 09:46:27,943 INFO [train.py:763] (0/8) Epoch 1, batch 3700, loss[loss=0.2661, simple_loss=0.3259, pruned_loss=0.1031, over 7167.00 frames.], tot_loss[loss=0.2907, simple_loss=0.3522, pruned_loss=0.1145, over 1428723.53 frames.], batch size: 19, lr: 2.14e-03
+2022-04-28 09:47:33,415 INFO [train.py:763] (0/8) Epoch 1, batch 3750, loss[loss=0.3159, simple_loss=0.3874, pruned_loss=0.1222, over 7281.00 frames.], tot_loss[loss=0.2903, simple_loss=0.3522, pruned_loss=0.1141, over 1429652.86 frames.], batch size: 24, lr: 2.14e-03
+2022-04-28 09:48:38,890 INFO [train.py:763] (0/8) Epoch 1, batch 3800, loss[loss=0.2176, simple_loss=0.2909, pruned_loss=0.07218, over 6783.00 frames.], tot_loss[loss=0.2888, simple_loss=0.3513, pruned_loss=0.1132, over 1428776.73 frames.], batch size: 15, lr: 2.13e-03
+2022-04-28 09:49:44,150 INFO [train.py:763] (0/8) Epoch 1, batch 3850, loss[loss=0.3995, simple_loss=0.4302, pruned_loss=0.1844, over 7168.00 frames.], tot_loss[loss=0.2894, simple_loss=0.3521, pruned_loss=0.1134, over 1431082.28 frames.], batch size: 26, lr: 2.13e-03
+2022-04-28 09:50:49,549 INFO [train.py:763] (0/8) Epoch 1, batch 3900, loss[loss=0.3228, simple_loss=0.3806, pruned_loss=0.1325, over 7318.00 frames.], tot_loss[loss=0.2877, simple_loss=0.3507, pruned_loss=0.1123, over 1430219.86 frames.], batch size: 24, lr: 2.12e-03
+2022-04-28 09:51:55,503 INFO [train.py:763] (0/8) Epoch 1, batch 3950, loss[loss=0.2994, simple_loss=0.3614, pruned_loss=0.1187, over 7114.00 frames.], tot_loss[loss=0.287, simple_loss=0.3499, pruned_loss=0.112, over 1427912.46 frames.], batch size: 21, lr: 2.12e-03
+2022-04-28 09:53:01,246 INFO [train.py:763] (0/8) Epoch 1, batch 4000, loss[loss=0.2971, simple_loss=0.3616, pruned_loss=0.1164, over 7211.00 frames.], tot_loss[loss=0.2863, simple_loss=0.3492, pruned_loss=0.1117, over 1428151.45 frames.], batch size: 22, lr: 2.11e-03
+2022-04-28 09:54:07,054 INFO [train.py:763] (0/8) Epoch 1, batch 4050, loss[loss=0.3497, simple_loss=0.3972, pruned_loss=0.1511, over 6773.00 frames.], tot_loss[loss=0.288, simple_loss=0.3503, pruned_loss=0.1128, over 1426121.28 frames.], batch size: 31, lr: 2.11e-03
+2022-04-28 09:55:12,320 INFO [train.py:763] (0/8) Epoch 1, batch 4100, loss[loss=0.2651, simple_loss=0.344, pruned_loss=0.09312, over 7220.00 frames.], tot_loss[loss=0.2876, simple_loss=0.3503, pruned_loss=0.1124, over 1420460.72 frames.], batch size: 21, lr: 2.10e-03
+2022-04-28 09:56:17,397 INFO [train.py:763] (0/8) Epoch 1, batch 4150, loss[loss=0.3273, simple_loss=0.3785, pruned_loss=0.1381, over 6780.00 frames.], tot_loss[loss=0.2864, simple_loss=0.3494, pruned_loss=0.1117, over 1419972.99 frames.], batch size: 31, lr: 2.10e-03
+2022-04-28 09:57:22,849 INFO [train.py:763] (0/8) Epoch 1, batch 4200, loss[loss=0.2975, simple_loss=0.3494, pruned_loss=0.1229, over 7275.00 frames.], tot_loss[loss=0.2858, simple_loss=0.3487, pruned_loss=0.1114, over 1418669.90 frames.], batch size: 18, lr: 2.10e-03
+2022-04-28 09:58:27,895 INFO [train.py:763] (0/8) Epoch 1, batch 4250, loss[loss=0.2392, simple_loss=0.3015, pruned_loss=0.0885, over 7289.00 frames.], tot_loss[loss=0.2858, simple_loss=0.3487, pruned_loss=0.1115, over 1413637.46 frames.], batch size: 18, lr: 2.09e-03
+2022-04-28 09:59:34,317 INFO [train.py:763] (0/8) Epoch 1, batch 4300, loss[loss=0.2787, simple_loss=0.3551, pruned_loss=0.1012, over 7287.00 frames.], tot_loss[loss=0.2859, simple_loss=0.3485, pruned_loss=0.1117, over 1413282.85 frames.], batch size: 25, lr: 2.09e-03
+2022-04-28 10:00:39,975 INFO [train.py:763] (0/8) Epoch 1, batch 4350, loss[loss=0.1986, simple_loss=0.2818, pruned_loss=0.05771, over 7007.00 frames.], tot_loss[loss=0.2859, simple_loss=0.3488, pruned_loss=0.1115, over 1413448.77 frames.], batch size: 16, lr: 2.08e-03
+2022-04-28 10:01:45,341 INFO [train.py:763] (0/8) Epoch 1, batch 4400, loss[loss=0.3039, simple_loss=0.3805, pruned_loss=0.1136, over 7323.00 frames.], tot_loss[loss=0.285, simple_loss=0.3482, pruned_loss=0.1109, over 1408617.83 frames.], batch size: 21, lr: 2.08e-03
+2022-04-28 10:02:50,271 INFO [train.py:763] (0/8) Epoch 1, batch 4450, loss[loss=0.3479, simple_loss=0.3836, pruned_loss=0.1561, over 6462.00 frames.], tot_loss[loss=0.2855, simple_loss=0.3484, pruned_loss=0.1113, over 1401496.50 frames.], batch size: 37, lr: 2.07e-03
+2022-04-28 10:03:55,339 INFO [train.py:763] (0/8) Epoch 1, batch 4500, loss[loss=0.3088, simple_loss=0.3726, pruned_loss=0.1225, over 6537.00 frames.], tot_loss[loss=0.2851, simple_loss=0.3478, pruned_loss=0.1112, over 1386978.24 frames.], batch size: 38, lr: 2.07e-03
+2022-04-28 10:04:59,446 INFO [train.py:763] (0/8) Epoch 1, batch 4550, loss[loss=0.3379, simple_loss=0.381, pruned_loss=0.1474, over 5629.00 frames.], tot_loss[loss=0.2895, simple_loss=0.351, pruned_loss=0.114, over 1357489.48 frames.], batch size: 52, lr: 2.06e-03
+2022-04-28 10:05:48,602 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-1.pt
+2022-04-28 10:06:27,052 INFO [train.py:763] (0/8) Epoch 2, batch 0, loss[loss=0.2478, simple_loss=0.304, pruned_loss=0.09584, over 7278.00 frames.], tot_loss[loss=0.2478, simple_loss=0.304, pruned_loss=0.09584, over 7278.00 frames.], batch size: 17, lr: 2.02e-03
+2022-04-28 10:07:33,528 INFO [train.py:763] (0/8) Epoch 2, batch 50, loss[loss=0.3192, simple_loss=0.3743, pruned_loss=0.132, over 7292.00 frames.], tot_loss[loss=0.28, simple_loss=0.3422, pruned_loss=0.1089, over 321427.60 frames.], batch size: 25, lr: 2.02e-03
+2022-04-28 10:08:39,174 INFO [train.py:763] (0/8) Epoch 2, batch 100, loss[loss=0.2365, simple_loss=0.3066, pruned_loss=0.0832, over 7006.00 frames.], tot_loss[loss=0.2768, simple_loss=0.3428, pruned_loss=0.1054, over 568376.61 frames.], batch size: 16, lr: 2.01e-03
+2022-04-28 10:09:45,133 INFO [train.py:763] (0/8) Epoch 2, batch 150, loss[loss=0.3399, simple_loss=0.3875, pruned_loss=0.1462, over 6869.00 frames.], tot_loss[loss=0.2729, simple_loss=0.3397, pruned_loss=0.103, over 761124.08 frames.], batch size: 31, lr: 2.01e-03
+2022-04-28 10:10:50,704 INFO [train.py:763] (0/8) Epoch 2, batch 200, loss[loss=0.2436, simple_loss=0.3021, pruned_loss=0.09252, over 7225.00 frames.], tot_loss[loss=0.2759, simple_loss=0.342, pruned_loss=0.1049, over 899581.72 frames.], batch size: 16, lr: 2.00e-03
+2022-04-28 10:11:56,046 INFO [train.py:763] (0/8) Epoch 2, batch 250, loss[loss=0.271, simple_loss=0.3329, pruned_loss=0.1046, over 7356.00 frames.], tot_loss[loss=0.2794, simple_loss=0.3448, pruned_loss=0.1069, over 1009971.06 frames.], batch size: 19, lr: 2.00e-03
+2022-04-28 10:13:01,587 INFO [train.py:763] (0/8) Epoch 2, batch 300, loss[loss=0.2846, simple_loss=0.3433, pruned_loss=0.113, over 6671.00 frames.], tot_loss[loss=0.2803, simple_loss=0.3465, pruned_loss=0.107, over 1100054.34 frames.], batch size: 31, lr: 2.00e-03
+2022-04-28 10:14:07,031 INFO [train.py:763] (0/8) Epoch 2, batch 350, loss[loss=0.249, simple_loss=0.3356, pruned_loss=0.0812, over 7321.00 frames.], tot_loss[loss=0.2802, simple_loss=0.3465, pruned_loss=0.1069, over 1170440.02 frames.], batch size: 21, lr: 1.99e-03
+2022-04-28 10:15:12,741 INFO [train.py:763] (0/8) Epoch 2, batch 400, loss[loss=0.3133, simple_loss=0.38, pruned_loss=0.1232, over 7265.00 frames.], tot_loss[loss=0.2791, simple_loss=0.3457, pruned_loss=0.1063, over 1221694.92 frames.], batch size: 24, lr: 1.99e-03
+2022-04-28 10:16:17,714 INFO [train.py:763] (0/8) Epoch 2, batch 450, loss[loss=0.2799, simple_loss=0.357, pruned_loss=0.1014, over 7206.00 frames.], tot_loss[loss=0.2798, simple_loss=0.3464, pruned_loss=0.1066, over 1263692.57 frames.], batch size: 22, lr: 1.98e-03
+2022-04-28 10:17:41,025 INFO [train.py:763] (0/8) Epoch 2, batch 500, loss[loss=0.2304, simple_loss=0.3023, pruned_loss=0.07927, over 6991.00 frames.], tot_loss[loss=0.2786, simple_loss=0.3457, pruned_loss=0.1058, over 1302207.80 frames.], batch size: 16, lr: 1.98e-03
+2022-04-28 10:19:24,499 INFO [train.py:763] (0/8) Epoch 2, batch 550, loss[loss=0.2288, simple_loss=0.3173, pruned_loss=0.0701, over 7225.00 frames.], tot_loss[loss=0.2759, simple_loss=0.3438, pruned_loss=0.104, over 1332015.14 frames.], batch size: 21, lr: 1.98e-03
+2022-04-28 10:20:31,152 INFO [train.py:763] (0/8) Epoch 2, batch 600, loss[loss=0.3336, simple_loss=0.3996, pruned_loss=0.1338, over 7304.00 frames.], tot_loss[loss=0.2739, simple_loss=0.342, pruned_loss=0.1028, over 1353396.38 frames.], batch size: 25, lr: 1.97e-03
+2022-04-28 10:21:56,823 INFO [train.py:763] (0/8) Epoch 2, batch 650, loss[loss=0.2836, simple_loss=0.3384, pruned_loss=0.1144, over 7368.00 frames.], tot_loss[loss=0.2721, simple_loss=0.3404, pruned_loss=0.1019, over 1367542.24 frames.], batch size: 19, lr: 1.97e-03
+2022-04-28 10:23:03,996 INFO [train.py:763] (0/8) Epoch 2, batch 700, loss[loss=0.2803, simple_loss=0.3537, pruned_loss=0.1035, over 7218.00 frames.], tot_loss[loss=0.2729, simple_loss=0.3413, pruned_loss=0.1022, over 1378368.59 frames.], batch size: 21, lr: 1.96e-03
+2022-04-28 10:24:09,358 INFO [train.py:763] (0/8) Epoch 2, batch 750, loss[loss=0.2237, simple_loss=0.3065, pruned_loss=0.07042, over 7214.00 frames.], tot_loss[loss=0.2728, simple_loss=0.3413, pruned_loss=0.1021, over 1391788.55 frames.], batch size: 23, lr: 1.96e-03
+2022-04-28 10:25:14,627 INFO [train.py:763] (0/8) Epoch 2, batch 800, loss[loss=0.2809, simple_loss=0.3502, pruned_loss=0.1058, over 7196.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3419, pruned_loss=0.1025, over 1402272.07 frames.], batch size: 23, lr: 1.96e-03
+2022-04-28 10:26:20,186 INFO [train.py:763] (0/8) Epoch 2, batch 850, loss[loss=0.3242, simple_loss=0.3749, pruned_loss=0.1368, over 7286.00 frames.], tot_loss[loss=0.2713, simple_loss=0.34, pruned_loss=0.1013, over 1410174.78 frames.], batch size: 25, lr: 1.95e-03
+2022-04-28 10:27:26,281 INFO [train.py:763] (0/8) Epoch 2, batch 900, loss[loss=0.2002, simple_loss=0.2849, pruned_loss=0.05777, over 7056.00 frames.], tot_loss[loss=0.2741, simple_loss=0.3422, pruned_loss=0.103, over 1412364.58 frames.], batch size: 18, lr: 1.95e-03
+2022-04-28 10:28:31,604 INFO [train.py:763] (0/8) Epoch 2, batch 950, loss[loss=0.272, simple_loss=0.3535, pruned_loss=0.09523, over 7144.00 frames.], tot_loss[loss=0.2733, simple_loss=0.3418, pruned_loss=0.1025, over 1417483.63 frames.], batch size: 20, lr: 1.94e-03
+2022-04-28 10:29:36,675 INFO [train.py:763] (0/8) Epoch 2, batch 1000, loss[loss=0.357, simple_loss=0.4048, pruned_loss=0.1545, over 6691.00 frames.], tot_loss[loss=0.2745, simple_loss=0.3428, pruned_loss=0.103, over 1417390.79 frames.], batch size: 31, lr: 1.94e-03
+2022-04-28 10:30:41,956 INFO [train.py:763] (0/8) Epoch 2, batch 1050, loss[loss=0.219, simple_loss=0.2923, pruned_loss=0.07285, over 7272.00 frames.], tot_loss[loss=0.2734, simple_loss=0.342, pruned_loss=0.1024, over 1415379.57 frames.], batch size: 18, lr: 1.94e-03
+2022-04-28 10:31:48,325 INFO [train.py:763] (0/8) Epoch 2, batch 1100, loss[loss=0.2958, simple_loss=0.3678, pruned_loss=0.1119, over 7201.00 frames.], tot_loss[loss=0.275, simple_loss=0.3435, pruned_loss=0.1032, over 1420602.78 frames.], batch size: 21, lr: 1.93e-03
+2022-04-28 10:32:55,828 INFO [train.py:763] (0/8) Epoch 2, batch 1150, loss[loss=0.3079, simple_loss=0.3738, pruned_loss=0.121, over 7237.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3429, pruned_loss=0.1029, over 1421134.56 frames.], batch size: 20, lr: 1.93e-03
+2022-04-28 10:34:03,567 INFO [train.py:763] (0/8) Epoch 2, batch 1200, loss[loss=0.2685, simple_loss=0.3246, pruned_loss=0.1062, over 7436.00 frames.], tot_loss[loss=0.2741, simple_loss=0.3423, pruned_loss=0.1029, over 1424169.88 frames.], batch size: 20, lr: 1.93e-03
+2022-04-28 10:35:11,230 INFO [train.py:763] (0/8) Epoch 2, batch 1250, loss[loss=0.2722, simple_loss=0.3416, pruned_loss=0.1014, over 7409.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3418, pruned_loss=0.1026, over 1424804.05 frames.], batch size: 21, lr: 1.92e-03
+2022-04-28 10:36:17,281 INFO [train.py:763] (0/8) Epoch 2, batch 1300, loss[loss=0.2748, simple_loss=0.349, pruned_loss=0.1003, over 7330.00 frames.], tot_loss[loss=0.2733, simple_loss=0.3414, pruned_loss=0.1026, over 1426791.66 frames.], batch size: 21, lr: 1.92e-03
+2022-04-28 10:37:22,337 INFO [train.py:763] (0/8) Epoch 2, batch 1350, loss[loss=0.2678, simple_loss=0.334, pruned_loss=0.1009, over 7427.00 frames.], tot_loss[loss=0.2738, simple_loss=0.3425, pruned_loss=0.1026, over 1425927.91 frames.], batch size: 20, lr: 1.91e-03
+2022-04-28 10:38:27,407 INFO [train.py:763] (0/8) Epoch 2, batch 1400, loss[loss=0.2303, simple_loss=0.3163, pruned_loss=0.0721, over 7163.00 frames.], tot_loss[loss=0.2734, simple_loss=0.3425, pruned_loss=0.1021, over 1423603.50 frames.], batch size: 19, lr: 1.91e-03
+2022-04-28 10:39:32,828 INFO [train.py:763] (0/8) Epoch 2, batch 1450, loss[loss=0.2463, simple_loss=0.3059, pruned_loss=0.09332, over 7125.00 frames.], tot_loss[loss=0.2714, simple_loss=0.3409, pruned_loss=0.101, over 1420296.04 frames.], batch size: 17, lr: 1.91e-03
+2022-04-28 10:40:38,394 INFO [train.py:763] (0/8) Epoch 2, batch 1500, loss[loss=0.2959, simple_loss=0.3631, pruned_loss=0.1143, over 7317.00 frames.], tot_loss[loss=0.2717, simple_loss=0.3411, pruned_loss=0.1012, over 1418718.46 frames.], batch size: 21, lr: 1.90e-03
+2022-04-28 10:41:43,977 INFO [train.py:763] (0/8) Epoch 2, batch 1550, loss[loss=0.2559, simple_loss=0.3319, pruned_loss=0.08994, over 7156.00 frames.], tot_loss[loss=0.2697, simple_loss=0.34, pruned_loss=0.09972, over 1422668.05 frames.], batch size: 19, lr: 1.90e-03
+2022-04-28 10:42:49,552 INFO [train.py:763] (0/8) Epoch 2, batch 1600, loss[loss=0.2172, simple_loss=0.3004, pruned_loss=0.06696, over 7178.00 frames.], tot_loss[loss=0.2701, simple_loss=0.3405, pruned_loss=0.09991, over 1424882.16 frames.], batch size: 19, lr: 1.90e-03
+2022-04-28 10:43:56,347 INFO [train.py:763] (0/8) Epoch 2, batch 1650, loss[loss=0.2312, simple_loss=0.309, pruned_loss=0.07673, over 7433.00 frames.], tot_loss[loss=0.2688, simple_loss=0.3393, pruned_loss=0.0992, over 1428047.62 frames.], batch size: 20, lr: 1.89e-03
+2022-04-28 10:45:02,826 INFO [train.py:763] (0/8) Epoch 2, batch 1700, loss[loss=0.2605, simple_loss=0.3443, pruned_loss=0.08833, over 7152.00 frames.], tot_loss[loss=0.2696, simple_loss=0.3395, pruned_loss=0.09986, over 1417442.34 frames.], batch size: 20, lr: 1.89e-03
+2022-04-28 10:46:08,600 INFO [train.py:763] (0/8) Epoch 2, batch 1750, loss[loss=0.2795, simple_loss=0.3502, pruned_loss=0.1044, over 7237.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3379, pruned_loss=0.09824, over 1424852.33 frames.], batch size: 20, lr: 1.88e-03
+2022-04-28 10:47:13,956 INFO [train.py:763] (0/8) Epoch 2, batch 1800, loss[loss=0.3192, simple_loss=0.3835, pruned_loss=0.1274, over 7108.00 frames.], tot_loss[loss=0.2682, simple_loss=0.3383, pruned_loss=0.09911, over 1417379.74 frames.], batch size: 21, lr: 1.88e-03
+2022-04-28 10:48:20,973 INFO [train.py:763] (0/8) Epoch 2, batch 1850, loss[loss=0.2897, simple_loss=0.3585, pruned_loss=0.1104, over 7409.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3378, pruned_loss=0.09877, over 1419418.08 frames.], batch size: 21, lr: 1.88e-03
+2022-04-28 10:49:26,586 INFO [train.py:763] (0/8) Epoch 2, batch 1900, loss[loss=0.2543, simple_loss=0.3234, pruned_loss=0.09254, over 7173.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3376, pruned_loss=0.09866, over 1417187.67 frames.], batch size: 18, lr: 1.87e-03
+2022-04-28 10:50:31,927 INFO [train.py:763] (0/8) Epoch 2, batch 1950, loss[loss=0.341, simple_loss=0.3935, pruned_loss=0.1442, over 6732.00 frames.], tot_loss[loss=0.2671, simple_loss=0.3374, pruned_loss=0.09843, over 1418686.73 frames.], batch size: 31, lr: 1.87e-03
+2022-04-28 10:51:37,337 INFO [train.py:763] (0/8) Epoch 2, batch 2000, loss[loss=0.2608, simple_loss=0.3374, pruned_loss=0.09207, over 7157.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3369, pruned_loss=0.09846, over 1423116.33 frames.], batch size: 19, lr: 1.87e-03
+2022-04-28 10:52:43,643 INFO [train.py:763] (0/8) Epoch 2, batch 2050, loss[loss=0.3502, simple_loss=0.3872, pruned_loss=0.1566, over 4995.00 frames.], tot_loss[loss=0.2704, simple_loss=0.3397, pruned_loss=0.1006, over 1422527.94 frames.], batch size: 52, lr: 1.86e-03
+2022-04-28 10:53:49,755 INFO [train.py:763] (0/8) Epoch 2, batch 2100, loss[loss=0.2486, simple_loss=0.3382, pruned_loss=0.07949, over 7324.00 frames.], tot_loss[loss=0.2692, simple_loss=0.3394, pruned_loss=0.09945, over 1425566.82 frames.], batch size: 21, lr: 1.86e-03
+2022-04-28 10:54:55,194 INFO [train.py:763] (0/8) Epoch 2, batch 2150, loss[loss=0.2585, simple_loss=0.3376, pruned_loss=0.08971, over 7231.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3382, pruned_loss=0.09839, over 1426807.72 frames.], batch size: 20, lr: 1.86e-03
+2022-04-28 10:56:00,725 INFO [train.py:763] (0/8) Epoch 2, batch 2200, loss[loss=0.3383, simple_loss=0.3976, pruned_loss=0.1396, over 7153.00 frames.], tot_loss[loss=0.2679, simple_loss=0.3386, pruned_loss=0.09863, over 1426286.21 frames.], batch size: 20, lr: 1.85e-03
+2022-04-28 10:57:05,943 INFO [train.py:763] (0/8) Epoch 2, batch 2250, loss[loss=0.2704, simple_loss=0.3466, pruned_loss=0.0971, over 7332.00 frames.], tot_loss[loss=0.2683, simple_loss=0.3388, pruned_loss=0.09887, over 1425643.00 frames.], batch size: 20, lr: 1.85e-03
+2022-04-28 10:58:11,394 INFO [train.py:763] (0/8) Epoch 2, batch 2300, loss[loss=0.2566, simple_loss=0.3179, pruned_loss=0.09759, over 7360.00 frames.], tot_loss[loss=0.2685, simple_loss=0.3385, pruned_loss=0.09922, over 1413083.61 frames.], batch size: 19, lr: 1.85e-03
+2022-04-28 10:59:16,576 INFO [train.py:763] (0/8) Epoch 2, batch 2350, loss[loss=0.2313, simple_loss=0.3104, pruned_loss=0.07612, over 7254.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3384, pruned_loss=0.0997, over 1414938.38 frames.], batch size: 19, lr: 1.84e-03
+2022-04-28 11:00:21,744 INFO [train.py:763] (0/8) Epoch 2, batch 2400, loss[loss=0.2731, simple_loss=0.3536, pruned_loss=0.09632, over 7259.00 frames.], tot_loss[loss=0.2684, simple_loss=0.3388, pruned_loss=0.09898, over 1418679.69 frames.], batch size: 19, lr: 1.84e-03
+2022-04-28 11:01:26,808 INFO [train.py:763] (0/8) Epoch 2, batch 2450, loss[loss=0.2775, simple_loss=0.3489, pruned_loss=0.1031, over 7237.00 frames.], tot_loss[loss=0.2691, simple_loss=0.3393, pruned_loss=0.09941, over 1415653.95 frames.], batch size: 20, lr: 1.84e-03
+2022-04-28 11:02:32,501 INFO [train.py:763] (0/8) Epoch 2, batch 2500, loss[loss=0.2461, simple_loss=0.3157, pruned_loss=0.08823, over 7166.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3381, pruned_loss=0.09871, over 1414449.12 frames.], batch size: 19, lr: 1.83e-03
+2022-04-28 11:03:38,318 INFO [train.py:763] (0/8) Epoch 2, batch 2550, loss[loss=0.2713, simple_loss=0.3382, pruned_loss=0.1022, over 7209.00 frames.], tot_loss[loss=0.2668, simple_loss=0.3369, pruned_loss=0.09839, over 1413051.18 frames.], batch size: 21, lr: 1.83e-03
+2022-04-28 11:04:44,226 INFO [train.py:763] (0/8) Epoch 2, batch 2600, loss[loss=0.2267, simple_loss=0.3044, pruned_loss=0.0745, over 7282.00 frames.], tot_loss[loss=0.2657, simple_loss=0.336, pruned_loss=0.0977, over 1418828.31 frames.], batch size: 18, lr: 1.83e-03
+2022-04-28 11:05:50,138 INFO [train.py:763] (0/8) Epoch 2, batch 2650, loss[loss=0.2592, simple_loss=0.3284, pruned_loss=0.09495, over 7330.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3346, pruned_loss=0.09629, over 1418692.85 frames.], batch size: 20, lr: 1.82e-03
+2022-04-28 11:06:55,497 INFO [train.py:763] (0/8) Epoch 2, batch 2700, loss[loss=0.2623, simple_loss=0.3312, pruned_loss=0.09665, over 7071.00 frames.], tot_loss[loss=0.2658, simple_loss=0.337, pruned_loss=0.09727, over 1419898.21 frames.], batch size: 18, lr: 1.82e-03
+2022-04-28 11:08:01,961 INFO [train.py:763] (0/8) Epoch 2, batch 2750, loss[loss=0.2738, simple_loss=0.3601, pruned_loss=0.09381, over 7170.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3354, pruned_loss=0.09606, over 1418921.04 frames.], batch size: 26, lr: 1.82e-03
+2022-04-28 11:09:07,555 INFO [train.py:763] (0/8) Epoch 2, batch 2800, loss[loss=0.3683, simple_loss=0.3988, pruned_loss=0.1689, over 4582.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3353, pruned_loss=0.09619, over 1418367.30 frames.], batch size: 52, lr: 1.81e-03
+2022-04-28 11:10:13,395 INFO [train.py:763] (0/8) Epoch 2, batch 2850, loss[loss=0.3031, simple_loss=0.3836, pruned_loss=0.1112, over 7219.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3346, pruned_loss=0.09587, over 1420528.94 frames.], batch size: 21, lr: 1.81e-03
+2022-04-28 11:11:19,194 INFO [train.py:763] (0/8) Epoch 2, batch 2900, loss[loss=0.2966, simple_loss=0.3477, pruned_loss=0.1228, over 6585.00 frames.], tot_loss[loss=0.2627, simple_loss=0.334, pruned_loss=0.09566, over 1418437.26 frames.], batch size: 38, lr: 1.81e-03
+2022-04-28 11:12:24,874 INFO [train.py:763] (0/8) Epoch 2, batch 2950, loss[loss=0.2415, simple_loss=0.319, pruned_loss=0.08205, over 7104.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3341, pruned_loss=0.0955, over 1417658.93 frames.], batch size: 26, lr: 1.80e-03
+2022-04-28 11:13:30,382 INFO [train.py:763] (0/8) Epoch 2, batch 3000, loss[loss=0.2823, simple_loss=0.3523, pruned_loss=0.1062, over 7333.00 frames.], tot_loss[loss=0.262, simple_loss=0.334, pruned_loss=0.095, over 1420822.82 frames.], batch size: 22, lr: 1.80e-03
+2022-04-28 11:13:30,383 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-28 11:13:45,774 INFO [train.py:792] (0/8) Epoch 2, validation: loss=0.2017, simple_loss=0.3052, pruned_loss=0.04915, over 698248.00 frames.
+2022-04-28 11:14:51,568 INFO [train.py:763] (0/8) Epoch 2, batch 3050, loss[loss=0.2821, simple_loss=0.3598, pruned_loss=0.1022, over 7408.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3357, pruned_loss=0.0958, over 1425582.97 frames.], batch size: 21, lr: 1.80e-03
+2022-04-28 11:15:57,119 INFO [train.py:763] (0/8) Epoch 2, batch 3100, loss[loss=0.2643, simple_loss=0.3425, pruned_loss=0.09302, over 7271.00 frames.], tot_loss[loss=0.2624, simple_loss=0.3346, pruned_loss=0.09508, over 1428270.58 frames.], batch size: 18, lr: 1.79e-03
+2022-04-28 11:17:02,804 INFO [train.py:763] (0/8) Epoch 2, batch 3150, loss[loss=0.2904, simple_loss=0.368, pruned_loss=0.1064, over 7215.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3344, pruned_loss=0.09549, over 1422188.97 frames.], batch size: 21, lr: 1.79e-03
+2022-04-28 11:18:08,974 INFO [train.py:763] (0/8) Epoch 2, batch 3200, loss[loss=0.2711, simple_loss=0.3491, pruned_loss=0.09649, over 7385.00 frames.], tot_loss[loss=0.2633, simple_loss=0.3357, pruned_loss=0.0955, over 1425202.49 frames.], batch size: 23, lr: 1.79e-03
+2022-04-28 11:19:14,940 INFO [train.py:763] (0/8) Epoch 2, batch 3250, loss[loss=0.244, simple_loss=0.3223, pruned_loss=0.08288, over 7145.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3357, pruned_loss=0.09499, over 1426390.46 frames.], batch size: 19, lr: 1.79e-03
+2022-04-28 11:20:20,957 INFO [train.py:763] (0/8) Epoch 2, batch 3300, loss[loss=0.242, simple_loss=0.3297, pruned_loss=0.07717, over 7237.00 frames.], tot_loss[loss=0.2604, simple_loss=0.3335, pruned_loss=0.09365, over 1428836.49 frames.], batch size: 26, lr: 1.78e-03
+2022-04-28 11:21:25,813 INFO [train.py:763] (0/8) Epoch 2, batch 3350, loss[loss=0.2384, simple_loss=0.3157, pruned_loss=0.08055, over 7297.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3353, pruned_loss=0.09518, over 1425416.78 frames.], batch size: 18, lr: 1.78e-03
+2022-04-28 11:22:30,856 INFO [train.py:763] (0/8) Epoch 2, batch 3400, loss[loss=0.2107, simple_loss=0.2834, pruned_loss=0.06899, over 7430.00 frames.], tot_loss[loss=0.264, simple_loss=0.3361, pruned_loss=0.09592, over 1423627.02 frames.], batch size: 18, lr: 1.78e-03
+2022-04-28 11:23:36,231 INFO [train.py:763] (0/8) Epoch 2, batch 3450, loss[loss=0.2315, simple_loss=0.3001, pruned_loss=0.08145, over 7258.00 frames.], tot_loss[loss=0.2639, simple_loss=0.336, pruned_loss=0.09589, over 1420865.36 frames.], batch size: 19, lr: 1.77e-03
+2022-04-28 11:24:41,589 INFO [train.py:763] (0/8) Epoch 2, batch 3500, loss[loss=0.2492, simple_loss=0.3281, pruned_loss=0.08515, over 7343.00 frames.], tot_loss[loss=0.2629, simple_loss=0.3352, pruned_loss=0.0953, over 1421651.24 frames.], batch size: 25, lr: 1.77e-03
+2022-04-28 11:25:47,029 INFO [train.py:763] (0/8) Epoch 2, batch 3550, loss[loss=0.2625, simple_loss=0.3319, pruned_loss=0.09659, over 7217.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3359, pruned_loss=0.09584, over 1420275.64 frames.], batch size: 21, lr: 1.77e-03
+2022-04-28 11:26:52,374 INFO [train.py:763] (0/8) Epoch 2, batch 3600, loss[loss=0.2501, simple_loss=0.3399, pruned_loss=0.08014, over 7285.00 frames.], tot_loss[loss=0.2629, simple_loss=0.3349, pruned_loss=0.09546, over 1421657.07 frames.], batch size: 24, lr: 1.76e-03
+2022-04-28 11:27:57,959 INFO [train.py:763] (0/8) Epoch 2, batch 3650, loss[loss=0.3046, simple_loss=0.3573, pruned_loss=0.1259, over 7383.00 frames.], tot_loss[loss=0.2612, simple_loss=0.3331, pruned_loss=0.09462, over 1421691.33 frames.], batch size: 23, lr: 1.76e-03
+2022-04-28 11:29:03,184 INFO [train.py:763] (0/8) Epoch 2, batch 3700, loss[loss=0.2479, simple_loss=0.3128, pruned_loss=0.0915, over 7398.00 frames.], tot_loss[loss=0.2597, simple_loss=0.3323, pruned_loss=0.09361, over 1417105.25 frames.], batch size: 18, lr: 1.76e-03
+2022-04-28 11:30:08,704 INFO [train.py:763] (0/8) Epoch 2, batch 3750, loss[loss=0.1981, simple_loss=0.2825, pruned_loss=0.0568, over 7273.00 frames.], tot_loss[loss=0.2588, simple_loss=0.332, pruned_loss=0.09279, over 1423283.58 frames.], batch size: 18, lr: 1.76e-03
+2022-04-28 11:31:14,668 INFO [train.py:763] (0/8) Epoch 2, batch 3800, loss[loss=0.2139, simple_loss=0.3023, pruned_loss=0.06274, over 7161.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3313, pruned_loss=0.09245, over 1423296.35 frames.], batch size: 18, lr: 1.75e-03
+2022-04-28 11:32:20,652 INFO [train.py:763] (0/8) Epoch 2, batch 3850, loss[loss=0.2529, simple_loss=0.3381, pruned_loss=0.08383, over 7325.00 frames.], tot_loss[loss=0.2597, simple_loss=0.3324, pruned_loss=0.09347, over 1421513.96 frames.], batch size: 22, lr: 1.75e-03
+2022-04-28 11:33:26,625 INFO [train.py:763] (0/8) Epoch 2, batch 3900, loss[loss=0.231, simple_loss=0.3067, pruned_loss=0.07764, over 7321.00 frames.], tot_loss[loss=0.258, simple_loss=0.3311, pruned_loss=0.09245, over 1423294.93 frames.], batch size: 20, lr: 1.75e-03
+2022-04-28 11:34:31,999 INFO [train.py:763] (0/8) Epoch 2, batch 3950, loss[loss=0.2316, simple_loss=0.3042, pruned_loss=0.07956, over 7320.00 frames.], tot_loss[loss=0.2573, simple_loss=0.3306, pruned_loss=0.09201, over 1420332.38 frames.], batch size: 21, lr: 1.74e-03
+2022-04-28 11:35:37,605 INFO [train.py:763] (0/8) Epoch 2, batch 4000, loss[loss=0.2933, simple_loss=0.3694, pruned_loss=0.1086, over 7329.00 frames.], tot_loss[loss=0.2582, simple_loss=0.3316, pruned_loss=0.09236, over 1425248.68 frames.], batch size: 22, lr: 1.74e-03
+2022-04-28 11:36:44,083 INFO [train.py:763] (0/8) Epoch 2, batch 4050, loss[loss=0.2619, simple_loss=0.3368, pruned_loss=0.09352, over 7434.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3313, pruned_loss=0.09249, over 1425537.04 frames.], batch size: 20, lr: 1.74e-03
+2022-04-28 11:37:49,247 INFO [train.py:763] (0/8) Epoch 2, batch 4100, loss[loss=0.2306, simple_loss=0.3023, pruned_loss=0.07942, over 7081.00 frames.], tot_loss[loss=0.2588, simple_loss=0.3316, pruned_loss=0.09302, over 1417394.85 frames.], batch size: 18, lr: 1.73e-03
+2022-04-28 11:38:54,193 INFO [train.py:763] (0/8) Epoch 2, batch 4150, loss[loss=0.2527, simple_loss=0.3332, pruned_loss=0.08607, over 7118.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3315, pruned_loss=0.09234, over 1421990.28 frames.], batch size: 21, lr: 1.73e-03
+2022-04-28 11:40:00,869 INFO [train.py:763] (0/8) Epoch 2, batch 4200, loss[loss=0.2834, simple_loss=0.3752, pruned_loss=0.09582, over 7112.00 frames.], tot_loss[loss=0.2583, simple_loss=0.3316, pruned_loss=0.0925, over 1420808.67 frames.], batch size: 28, lr: 1.73e-03
+2022-04-28 11:41:07,995 INFO [train.py:763] (0/8) Epoch 2, batch 4250, loss[loss=0.2758, simple_loss=0.3348, pruned_loss=0.1084, over 7216.00 frames.], tot_loss[loss=0.2573, simple_loss=0.331, pruned_loss=0.09178, over 1421069.74 frames.], batch size: 22, lr: 1.73e-03
+2022-04-28 11:42:14,764 INFO [train.py:763] (0/8) Epoch 2, batch 4300, loss[loss=0.2412, simple_loss=0.3195, pruned_loss=0.08142, over 7066.00 frames.], tot_loss[loss=0.2574, simple_loss=0.3314, pruned_loss=0.0917, over 1423018.16 frames.], batch size: 18, lr: 1.72e-03
+2022-04-28 11:43:21,949 INFO [train.py:763] (0/8) Epoch 2, batch 4350, loss[loss=0.3172, simple_loss=0.3841, pruned_loss=0.1251, over 7151.00 frames.], tot_loss[loss=0.2577, simple_loss=0.3315, pruned_loss=0.09194, over 1424399.23 frames.], batch size: 20, lr: 1.72e-03
+2022-04-28 11:44:27,749 INFO [train.py:763] (0/8) Epoch 2, batch 4400, loss[loss=0.2989, simple_loss=0.3651, pruned_loss=0.1164, over 7303.00 frames.], tot_loss[loss=0.2579, simple_loss=0.3312, pruned_loss=0.09236, over 1419196.31 frames.], batch size: 25, lr: 1.72e-03
+2022-04-28 11:45:33,255 INFO [train.py:763] (0/8) Epoch 2, batch 4450, loss[loss=0.267, simple_loss=0.3465, pruned_loss=0.09373, over 7338.00 frames.], tot_loss[loss=0.2595, simple_loss=0.333, pruned_loss=0.09299, over 1412201.36 frames.], batch size: 22, lr: 1.71e-03
+2022-04-28 11:46:38,407 INFO [train.py:763] (0/8) Epoch 2, batch 4500, loss[loss=0.2603, simple_loss=0.3453, pruned_loss=0.08762, over 7116.00 frames.], tot_loss[loss=0.2609, simple_loss=0.3346, pruned_loss=0.09366, over 1405838.51 frames.], batch size: 21, lr: 1.71e-03
+2022-04-28 11:47:42,637 INFO [train.py:763] (0/8) Epoch 2, batch 4550, loss[loss=0.286, simple_loss=0.3625, pruned_loss=0.1048, over 6246.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3367, pruned_loss=0.09543, over 1377435.41 frames.], batch size: 37, lr: 1.71e-03
+2022-04-28 11:48:32,094 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-2.pt
+2022-04-28 11:49:10,907 INFO [train.py:763] (0/8) Epoch 3, batch 0, loss[loss=0.2667, simple_loss=0.3473, pruned_loss=0.0931, over 7190.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3473, pruned_loss=0.0931, over 7190.00 frames.], batch size: 23, lr: 1.66e-03
+2022-04-28 11:50:17,453 INFO [train.py:763] (0/8) Epoch 3, batch 50, loss[loss=0.2024, simple_loss=0.2763, pruned_loss=0.06428, over 7300.00 frames.], tot_loss[loss=0.2529, simple_loss=0.3279, pruned_loss=0.08895, over 317196.41 frames.], batch size: 17, lr: 1.66e-03
+2022-04-28 11:51:23,925 INFO [train.py:763] (0/8) Epoch 3, batch 100, loss[loss=0.197, simple_loss=0.2815, pruned_loss=0.05625, over 7279.00 frames.], tot_loss[loss=0.252, simple_loss=0.3266, pruned_loss=0.08867, over 564328.15 frames.], batch size: 17, lr: 1.65e-03
+2022-04-28 11:52:29,500 INFO [train.py:763] (0/8) Epoch 3, batch 150, loss[loss=0.2313, simple_loss=0.3274, pruned_loss=0.06764, over 7337.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3273, pruned_loss=0.08823, over 755205.07 frames.], batch size: 22, lr: 1.65e-03
+2022-04-28 11:53:34,979 INFO [train.py:763] (0/8) Epoch 3, batch 200, loss[loss=0.2605, simple_loss=0.3462, pruned_loss=0.08737, over 7210.00 frames.], tot_loss[loss=0.2529, simple_loss=0.3286, pruned_loss=0.0886, over 903901.05 frames.], batch size: 23, lr: 1.65e-03
+2022-04-28 11:54:40,987 INFO [train.py:763] (0/8) Epoch 3, batch 250, loss[loss=0.2211, simple_loss=0.3149, pruned_loss=0.06364, over 7332.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3289, pruned_loss=0.08882, over 1015791.98 frames.], batch size: 22, lr: 1.64e-03
+2022-04-28 11:55:46,613 INFO [train.py:763] (0/8) Epoch 3, batch 300, loss[loss=0.2425, simple_loss=0.3334, pruned_loss=0.0758, over 7386.00 frames.], tot_loss[loss=0.2521, simple_loss=0.3279, pruned_loss=0.08813, over 1110407.77 frames.], batch size: 23, lr: 1.64e-03
+2022-04-28 11:56:52,032 INFO [train.py:763] (0/8) Epoch 3, batch 350, loss[loss=0.2374, simple_loss=0.3194, pruned_loss=0.07773, over 7316.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3269, pruned_loss=0.08714, over 1182298.99 frames.], batch size: 21, lr: 1.64e-03
+2022-04-28 11:57:57,849 INFO [train.py:763] (0/8) Epoch 3, batch 400, loss[loss=0.2487, simple_loss=0.3172, pruned_loss=0.09008, over 7240.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3266, pruned_loss=0.08727, over 1233662.27 frames.], batch size: 20, lr: 1.64e-03
+2022-04-28 11:59:03,275 INFO [train.py:763] (0/8) Epoch 3, batch 450, loss[loss=0.2406, simple_loss=0.3287, pruned_loss=0.07628, over 7135.00 frames.], tot_loss[loss=0.25, simple_loss=0.3262, pruned_loss=0.08692, over 1275559.81 frames.], batch size: 20, lr: 1.63e-03
+2022-04-28 12:00:09,069 INFO [train.py:763] (0/8) Epoch 3, batch 500, loss[loss=0.2457, simple_loss=0.3144, pruned_loss=0.08856, over 7154.00 frames.], tot_loss[loss=0.2521, simple_loss=0.3279, pruned_loss=0.08811, over 1304620.24 frames.], batch size: 19, lr: 1.63e-03
+2022-04-28 12:01:14,930 INFO [train.py:763] (0/8) Epoch 3, batch 550, loss[loss=0.2659, simple_loss=0.3419, pruned_loss=0.0949, over 7166.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3281, pruned_loss=0.0884, over 1329918.33 frames.], batch size: 18, lr: 1.63e-03
+2022-04-28 12:02:20,847 INFO [train.py:763] (0/8) Epoch 3, batch 600, loss[loss=0.2801, simple_loss=0.3527, pruned_loss=0.1038, over 6486.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3276, pruned_loss=0.08808, over 1347544.63 frames.], batch size: 38, lr: 1.63e-03
+2022-04-28 12:03:27,789 INFO [train.py:763] (0/8) Epoch 3, batch 650, loss[loss=0.2424, simple_loss=0.3281, pruned_loss=0.07833, over 7429.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3272, pruned_loss=0.08757, over 1367933.01 frames.], batch size: 20, lr: 1.62e-03
+2022-04-28 12:04:35,121 INFO [train.py:763] (0/8) Epoch 3, batch 700, loss[loss=0.2479, simple_loss=0.3274, pruned_loss=0.08421, over 7246.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3254, pruned_loss=0.08617, over 1385365.45 frames.], batch size: 24, lr: 1.62e-03
+2022-04-28 12:05:41,314 INFO [train.py:763] (0/8) Epoch 3, batch 750, loss[loss=0.2827, simple_loss=0.3642, pruned_loss=0.1006, over 7297.00 frames.], tot_loss[loss=0.2503, simple_loss=0.326, pruned_loss=0.08733, over 1393015.03 frames.], batch size: 24, lr: 1.62e-03
+2022-04-28 12:06:46,996 INFO [train.py:763] (0/8) Epoch 3, batch 800, loss[loss=0.2203, simple_loss=0.3016, pruned_loss=0.06948, over 7256.00 frames.], tot_loss[loss=0.2517, simple_loss=0.3273, pruned_loss=0.08806, over 1396748.02 frames.], batch size: 19, lr: 1.62e-03
+2022-04-28 12:07:53,502 INFO [train.py:763] (0/8) Epoch 3, batch 850, loss[loss=0.2449, simple_loss=0.3095, pruned_loss=0.09019, over 7070.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3268, pruned_loss=0.08712, over 1407212.07 frames.], batch size: 18, lr: 1.61e-03
+2022-04-28 12:09:00,270 INFO [train.py:763] (0/8) Epoch 3, batch 900, loss[loss=0.2426, simple_loss=0.3301, pruned_loss=0.07762, over 7112.00 frames.], tot_loss[loss=0.2501, simple_loss=0.3265, pruned_loss=0.08684, over 1414624.73 frames.], batch size: 21, lr: 1.61e-03
+2022-04-28 12:10:06,509 INFO [train.py:763] (0/8) Epoch 3, batch 950, loss[loss=0.2555, simple_loss=0.3425, pruned_loss=0.08427, over 7142.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3258, pruned_loss=0.08623, over 1420082.76 frames.], batch size: 26, lr: 1.61e-03
+2022-04-28 12:11:12,752 INFO [train.py:763] (0/8) Epoch 3, batch 1000, loss[loss=0.2458, simple_loss=0.329, pruned_loss=0.08129, over 7270.00 frames.], tot_loss[loss=0.2494, simple_loss=0.3257, pruned_loss=0.08651, over 1420113.08 frames.], batch size: 18, lr: 1.61e-03
+2022-04-28 12:12:18,777 INFO [train.py:763] (0/8) Epoch 3, batch 1050, loss[loss=0.3327, simple_loss=0.3852, pruned_loss=0.1401, over 6764.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3271, pruned_loss=0.08763, over 1418697.78 frames.], batch size: 31, lr: 1.60e-03
+2022-04-28 12:13:24,406 INFO [train.py:763] (0/8) Epoch 3, batch 1100, loss[loss=0.262, simple_loss=0.3454, pruned_loss=0.08932, over 7413.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3266, pruned_loss=0.08719, over 1420146.94 frames.], batch size: 21, lr: 1.60e-03
+2022-04-28 12:14:28,885 INFO [train.py:763] (0/8) Epoch 3, batch 1150, loss[loss=0.2725, simple_loss=0.3626, pruned_loss=0.09125, over 7323.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3288, pruned_loss=0.08824, over 1417986.17 frames.], batch size: 21, lr: 1.60e-03
+2022-04-28 12:15:35,092 INFO [train.py:763] (0/8) Epoch 3, batch 1200, loss[loss=0.2806, simple_loss=0.3484, pruned_loss=0.1064, over 7316.00 frames.], tot_loss[loss=0.2534, simple_loss=0.3294, pruned_loss=0.08871, over 1416233.50 frames.], batch size: 21, lr: 1.60e-03
+2022-04-28 12:16:40,636 INFO [train.py:763] (0/8) Epoch 3, batch 1250, loss[loss=0.209, simple_loss=0.2821, pruned_loss=0.06798, over 7230.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3286, pruned_loss=0.0882, over 1414594.47 frames.], batch size: 16, lr: 1.59e-03
+2022-04-28 12:17:46,149 INFO [train.py:763] (0/8) Epoch 3, batch 1300, loss[loss=0.2529, simple_loss=0.3391, pruned_loss=0.08331, over 7217.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3275, pruned_loss=0.08786, over 1417609.81 frames.], batch size: 23, lr: 1.59e-03
+2022-04-28 12:18:51,894 INFO [train.py:763] (0/8) Epoch 3, batch 1350, loss[loss=0.2457, simple_loss=0.3373, pruned_loss=0.07708, over 7232.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3278, pruned_loss=0.08791, over 1416748.33 frames.], batch size: 20, lr: 1.59e-03
+2022-04-28 12:19:57,906 INFO [train.py:763] (0/8) Epoch 3, batch 1400, loss[loss=0.252, simple_loss=0.3316, pruned_loss=0.08618, over 7214.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3261, pruned_loss=0.08676, over 1419424.67 frames.], batch size: 22, lr: 1.59e-03
+2022-04-28 12:21:03,061 INFO [train.py:763] (0/8) Epoch 3, batch 1450, loss[loss=0.2416, simple_loss=0.3348, pruned_loss=0.07414, over 7289.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3275, pruned_loss=0.08683, over 1421665.18 frames.], batch size: 24, lr: 1.59e-03
+2022-04-28 12:22:08,506 INFO [train.py:763] (0/8) Epoch 3, batch 1500, loss[loss=0.2308, simple_loss=0.3083, pruned_loss=0.07664, over 7294.00 frames.], tot_loss[loss=0.2496, simple_loss=0.3267, pruned_loss=0.08629, over 1419716.46 frames.], batch size: 24, lr: 1.58e-03
+2022-04-28 12:23:14,008 INFO [train.py:763] (0/8) Epoch 3, batch 1550, loss[loss=0.2959, simple_loss=0.3511, pruned_loss=0.1203, over 5032.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3271, pruned_loss=0.08695, over 1418378.13 frames.], batch size: 52, lr: 1.58e-03
+2022-04-28 12:24:20,153 INFO [train.py:763] (0/8) Epoch 3, batch 1600, loss[loss=0.266, simple_loss=0.3482, pruned_loss=0.09192, over 7280.00 frames.], tot_loss[loss=0.2521, simple_loss=0.3282, pruned_loss=0.08796, over 1415463.74 frames.], batch size: 25, lr: 1.58e-03
+2022-04-28 12:25:26,912 INFO [train.py:763] (0/8) Epoch 3, batch 1650, loss[loss=0.2443, simple_loss=0.3271, pruned_loss=0.08072, over 7332.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3261, pruned_loss=0.08688, over 1416308.61 frames.], batch size: 20, lr: 1.58e-03
+2022-04-28 12:26:34,086 INFO [train.py:763] (0/8) Epoch 3, batch 1700, loss[loss=0.2473, simple_loss=0.3347, pruned_loss=0.07998, over 7151.00 frames.], tot_loss[loss=0.2492, simple_loss=0.3259, pruned_loss=0.08621, over 1419923.54 frames.], batch size: 20, lr: 1.57e-03
+2022-04-28 12:27:40,156 INFO [train.py:763] (0/8) Epoch 3, batch 1750, loss[loss=0.2357, simple_loss=0.3201, pruned_loss=0.07562, over 7213.00 frames.], tot_loss[loss=0.2495, simple_loss=0.3264, pruned_loss=0.08632, over 1419599.45 frames.], batch size: 22, lr: 1.57e-03
+2022-04-28 12:28:45,192 INFO [train.py:763] (0/8) Epoch 3, batch 1800, loss[loss=0.2836, simple_loss=0.3582, pruned_loss=0.1045, over 7222.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3283, pruned_loss=0.08768, over 1421875.53 frames.], batch size: 21, lr: 1.57e-03
+2022-04-28 12:29:50,464 INFO [train.py:763] (0/8) Epoch 3, batch 1850, loss[loss=0.2553, simple_loss=0.3179, pruned_loss=0.09637, over 7117.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3282, pruned_loss=0.08748, over 1420862.07 frames.], batch size: 17, lr: 1.57e-03
+2022-04-28 12:30:57,299 INFO [train.py:763] (0/8) Epoch 3, batch 1900, loss[loss=0.2551, simple_loss=0.3264, pruned_loss=0.09187, over 7158.00 frames.], tot_loss[loss=0.25, simple_loss=0.327, pruned_loss=0.08648, over 1423719.97 frames.], batch size: 19, lr: 1.56e-03
+2022-04-28 12:32:03,229 INFO [train.py:763] (0/8) Epoch 3, batch 1950, loss[loss=0.3238, simple_loss=0.3771, pruned_loss=0.1352, over 6431.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3262, pruned_loss=0.08521, over 1428599.79 frames.], batch size: 38, lr: 1.56e-03
+2022-04-28 12:33:17,828 INFO [train.py:763] (0/8) Epoch 3, batch 2000, loss[loss=0.2457, simple_loss=0.329, pruned_loss=0.08121, over 7115.00 frames.], tot_loss[loss=0.249, simple_loss=0.327, pruned_loss=0.08549, over 1425955.91 frames.], batch size: 21, lr: 1.56e-03
+2022-04-28 12:35:10,054 INFO [train.py:763] (0/8) Epoch 3, batch 2050, loss[loss=0.2647, simple_loss=0.3479, pruned_loss=0.09071, over 6777.00 frames.], tot_loss[loss=0.2495, simple_loss=0.3272, pruned_loss=0.08586, over 1422042.54 frames.], batch size: 31, lr: 1.56e-03
+2022-04-28 12:36:15,509 INFO [train.py:763] (0/8) Epoch 3, batch 2100, loss[loss=0.2341, simple_loss=0.3104, pruned_loss=0.07889, over 7322.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3263, pruned_loss=0.0854, over 1420198.03 frames.], batch size: 21, lr: 1.56e-03
+2022-04-28 12:37:29,645 INFO [train.py:763] (0/8) Epoch 3, batch 2150, loss[loss=0.256, simple_loss=0.3356, pruned_loss=0.08815, over 7327.00 frames.], tot_loss[loss=0.2481, simple_loss=0.3257, pruned_loss=0.0852, over 1422683.28 frames.], batch size: 22, lr: 1.55e-03
+2022-04-28 12:38:44,723 INFO [train.py:763] (0/8) Epoch 3, batch 2200, loss[loss=0.2745, simple_loss=0.3563, pruned_loss=0.09634, over 7212.00 frames.], tot_loss[loss=0.247, simple_loss=0.3248, pruned_loss=0.08459, over 1425350.73 frames.], batch size: 21, lr: 1.55e-03
+2022-04-28 12:39:31,441 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-16000.pt
+2022-04-28 12:40:02,467 INFO [train.py:763] (0/8) Epoch 3, batch 2250, loss[loss=0.3502, simple_loss=0.3839, pruned_loss=0.1582, over 4997.00 frames.], tot_loss[loss=0.2486, simple_loss=0.3262, pruned_loss=0.08551, over 1426768.16 frames.], batch size: 52, lr: 1.55e-03
+2022-04-28 12:41:07,757 INFO [train.py:763] (0/8) Epoch 3, batch 2300, loss[loss=0.2497, simple_loss=0.3295, pruned_loss=0.0849, over 7147.00 frames.], tot_loss[loss=0.2472, simple_loss=0.3251, pruned_loss=0.08465, over 1429779.60 frames.], batch size: 19, lr: 1.55e-03
+2022-04-28 12:42:14,645 INFO [train.py:763] (0/8) Epoch 3, batch 2350, loss[loss=0.2431, simple_loss=0.3193, pruned_loss=0.08347, over 7328.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3243, pruned_loss=0.08376, over 1430843.98 frames.], batch size: 20, lr: 1.54e-03
+2022-04-28 12:43:19,983 INFO [train.py:763] (0/8) Epoch 3, batch 2400, loss[loss=0.2994, simple_loss=0.3771, pruned_loss=0.1108, over 7242.00 frames.], tot_loss[loss=0.2474, simple_loss=0.326, pruned_loss=0.08435, over 1433170.35 frames.], batch size: 25, lr: 1.54e-03
+2022-04-28 12:44:25,923 INFO [train.py:763] (0/8) Epoch 3, batch 2450, loss[loss=0.2345, simple_loss=0.3282, pruned_loss=0.07035, over 7382.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3272, pruned_loss=0.08471, over 1436045.97 frames.], batch size: 23, lr: 1.54e-03
+2022-04-28 12:45:31,565 INFO [train.py:763] (0/8) Epoch 3, batch 2500, loss[loss=0.2369, simple_loss=0.3134, pruned_loss=0.08019, over 7144.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3264, pruned_loss=0.0844, over 1433981.31 frames.], batch size: 19, lr: 1.54e-03
+2022-04-28 12:46:36,898 INFO [train.py:763] (0/8) Epoch 3, batch 2550, loss[loss=0.221, simple_loss=0.3, pruned_loss=0.07104, over 7406.00 frames.], tot_loss[loss=0.248, simple_loss=0.3262, pruned_loss=0.08487, over 1426440.40 frames.], batch size: 18, lr: 1.54e-03
+2022-04-28 12:47:42,415 INFO [train.py:763] (0/8) Epoch 3, batch 2600, loss[loss=0.2669, simple_loss=0.3421, pruned_loss=0.09583, over 7237.00 frames.], tot_loss[loss=0.2496, simple_loss=0.3277, pruned_loss=0.08576, over 1425893.66 frames.], batch size: 20, lr: 1.53e-03
+2022-04-28 12:48:47,825 INFO [train.py:763] (0/8) Epoch 3, batch 2650, loss[loss=0.1868, simple_loss=0.2594, pruned_loss=0.05716, over 6973.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3281, pruned_loss=0.08582, over 1419358.80 frames.], batch size: 16, lr: 1.53e-03
+2022-04-28 12:49:52,905 INFO [train.py:763] (0/8) Epoch 3, batch 2700, loss[loss=0.2155, simple_loss=0.2919, pruned_loss=0.06959, over 7206.00 frames.], tot_loss[loss=0.2503, simple_loss=0.3281, pruned_loss=0.08623, over 1418121.41 frames.], batch size: 16, lr: 1.53e-03
+2022-04-28 12:50:58,286 INFO [train.py:763] (0/8) Epoch 3, batch 2750, loss[loss=0.2093, simple_loss=0.303, pruned_loss=0.05783, over 7248.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3274, pruned_loss=0.08518, over 1421584.57 frames.], batch size: 19, lr: 1.53e-03
+2022-04-28 12:52:03,631 INFO [train.py:763] (0/8) Epoch 3, batch 2800, loss[loss=0.2116, simple_loss=0.3015, pruned_loss=0.06083, over 7157.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3263, pruned_loss=0.08463, over 1424365.01 frames.], batch size: 19, lr: 1.53e-03
+2022-04-28 12:53:09,251 INFO [train.py:763] (0/8) Epoch 3, batch 2850, loss[loss=0.3137, simple_loss=0.3665, pruned_loss=0.1304, over 5264.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3255, pruned_loss=0.08483, over 1424015.61 frames.], batch size: 54, lr: 1.52e-03
+2022-04-28 12:54:14,540 INFO [train.py:763] (0/8) Epoch 3, batch 2900, loss[loss=0.2618, simple_loss=0.345, pruned_loss=0.08934, over 6761.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3258, pruned_loss=0.08493, over 1424230.61 frames.], batch size: 31, lr: 1.52e-03
+2022-04-28 12:55:20,291 INFO [train.py:763] (0/8) Epoch 3, batch 2950, loss[loss=0.2685, simple_loss=0.3452, pruned_loss=0.09586, over 7158.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3244, pruned_loss=0.08394, over 1428571.29 frames.], batch size: 28, lr: 1.52e-03
+2022-04-28 12:56:25,615 INFO [train.py:763] (0/8) Epoch 3, batch 3000, loss[loss=0.2738, simple_loss=0.349, pruned_loss=0.09928, over 7154.00 frames.], tot_loss[loss=0.2464, simple_loss=0.325, pruned_loss=0.08394, over 1426256.56 frames.], batch size: 20, lr: 1.52e-03
+2022-04-28 12:56:25,616 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-28 12:56:40,878 INFO [train.py:792] (0/8) Epoch 3, validation: loss=0.1917, simple_loss=0.2967, pruned_loss=0.04336, over 698248.00 frames.
+2022-04-28 12:57:46,585 INFO [train.py:763] (0/8) Epoch 3, batch 3050, loss[loss=0.2325, simple_loss=0.3204, pruned_loss=0.07231, over 7112.00 frames.], tot_loss[loss=0.2469, simple_loss=0.3252, pruned_loss=0.08431, over 1421133.75 frames.], batch size: 21, lr: 1.51e-03
+2022-04-28 12:58:52,516 INFO [train.py:763] (0/8) Epoch 3, batch 3100, loss[loss=0.2623, simple_loss=0.3411, pruned_loss=0.09176, over 7275.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3244, pruned_loss=0.08369, over 1417441.33 frames.], batch size: 24, lr: 1.51e-03
+2022-04-28 12:59:58,119 INFO [train.py:763] (0/8) Epoch 3, batch 3150, loss[loss=0.2475, simple_loss=0.3326, pruned_loss=0.08118, over 7275.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3235, pruned_loss=0.08317, over 1422454.04 frames.], batch size: 25, lr: 1.51e-03
+2022-04-28 13:01:03,466 INFO [train.py:763] (0/8) Epoch 3, batch 3200, loss[loss=0.2048, simple_loss=0.2916, pruned_loss=0.05901, over 7058.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3226, pruned_loss=0.08219, over 1423024.03 frames.], batch size: 18, lr: 1.51e-03
+2022-04-28 13:02:09,456 INFO [train.py:763] (0/8) Epoch 3, batch 3250, loss[loss=0.2251, simple_loss=0.2985, pruned_loss=0.07581, over 7251.00 frames.], tot_loss[loss=0.2438, simple_loss=0.3226, pruned_loss=0.08246, over 1423880.75 frames.], batch size: 19, lr: 1.51e-03
+2022-04-28 13:03:16,236 INFO [train.py:763] (0/8) Epoch 3, batch 3300, loss[loss=0.272, simple_loss=0.3443, pruned_loss=0.09983, over 7177.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3234, pruned_loss=0.08219, over 1421959.82 frames.], batch size: 23, lr: 1.50e-03
+2022-04-28 13:04:22,930 INFO [train.py:763] (0/8) Epoch 3, batch 3350, loss[loss=0.2981, simple_loss=0.3611, pruned_loss=0.1175, over 6248.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3226, pruned_loss=0.08197, over 1419691.77 frames.], batch size: 37, lr: 1.50e-03
+2022-04-28 13:05:28,647 INFO [train.py:763] (0/8) Epoch 3, batch 3400, loss[loss=0.2193, simple_loss=0.2873, pruned_loss=0.07561, over 7016.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3216, pruned_loss=0.08194, over 1420418.01 frames.], batch size: 16, lr: 1.50e-03
+2022-04-28 13:06:35,010 INFO [train.py:763] (0/8) Epoch 3, batch 3450, loss[loss=0.2092, simple_loss=0.2874, pruned_loss=0.06553, over 7167.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3209, pruned_loss=0.08171, over 1425634.72 frames.], batch size: 18, lr: 1.50e-03
+2022-04-28 13:07:42,202 INFO [train.py:763] (0/8) Epoch 3, batch 3500, loss[loss=0.23, simple_loss=0.3112, pruned_loss=0.07443, over 7366.00 frames.], tot_loss[loss=0.2428, simple_loss=0.321, pruned_loss=0.08233, over 1427263.56 frames.], batch size: 23, lr: 1.50e-03
+2022-04-28 13:08:48,568 INFO [train.py:763] (0/8) Epoch 3, batch 3550, loss[loss=0.2503, simple_loss=0.3305, pruned_loss=0.08503, over 7288.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3195, pruned_loss=0.08148, over 1427782.35 frames.], batch size: 24, lr: 1.49e-03
+2022-04-28 13:09:55,530 INFO [train.py:763] (0/8) Epoch 3, batch 3600, loss[loss=0.2228, simple_loss=0.292, pruned_loss=0.07676, over 7006.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3207, pruned_loss=0.08183, over 1426524.48 frames.], batch size: 16, lr: 1.49e-03
+2022-04-28 13:11:02,092 INFO [train.py:763] (0/8) Epoch 3, batch 3650, loss[loss=0.2632, simple_loss=0.3262, pruned_loss=0.1001, over 7142.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3221, pruned_loss=0.08267, over 1426906.47 frames.], batch size: 17, lr: 1.49e-03
+2022-04-28 13:12:07,908 INFO [train.py:763] (0/8) Epoch 3, batch 3700, loss[loss=0.2156, simple_loss=0.2844, pruned_loss=0.07339, over 7007.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3214, pruned_loss=0.08241, over 1426165.43 frames.], batch size: 16, lr: 1.49e-03
+2022-04-28 13:13:15,363 INFO [train.py:763] (0/8) Epoch 3, batch 3750, loss[loss=0.2409, simple_loss=0.3198, pruned_loss=0.08095, over 7429.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3189, pruned_loss=0.08092, over 1425011.67 frames.], batch size: 20, lr: 1.49e-03
+2022-04-28 13:14:22,363 INFO [train.py:763] (0/8) Epoch 3, batch 3800, loss[loss=0.2348, simple_loss=0.3008, pruned_loss=0.08435, over 7066.00 frames.], tot_loss[loss=0.2416, simple_loss=0.32, pruned_loss=0.08154, over 1421130.81 frames.], batch size: 18, lr: 1.48e-03
+2022-04-28 13:15:29,715 INFO [train.py:763] (0/8) Epoch 3, batch 3850, loss[loss=0.226, simple_loss=0.3061, pruned_loss=0.07299, over 7408.00 frames.], tot_loss[loss=0.2418, simple_loss=0.3204, pruned_loss=0.08161, over 1425275.55 frames.], batch size: 18, lr: 1.48e-03
+2022-04-28 13:16:35,241 INFO [train.py:763] (0/8) Epoch 3, batch 3900, loss[loss=0.3013, simple_loss=0.3709, pruned_loss=0.1158, over 4955.00 frames.], tot_loss[loss=0.2411, simple_loss=0.3203, pruned_loss=0.08101, over 1426044.47 frames.], batch size: 52, lr: 1.48e-03
+2022-04-28 13:17:41,256 INFO [train.py:763] (0/8) Epoch 3, batch 3950, loss[loss=0.2067, simple_loss=0.278, pruned_loss=0.06767, over 7241.00 frames.], tot_loss[loss=0.2428, simple_loss=0.321, pruned_loss=0.08231, over 1424831.02 frames.], batch size: 16, lr: 1.48e-03
+2022-04-28 13:18:46,798 INFO [train.py:763] (0/8) Epoch 3, batch 4000, loss[loss=0.2325, simple_loss=0.3158, pruned_loss=0.07464, over 7226.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3207, pruned_loss=0.0818, over 1417686.31 frames.], batch size: 21, lr: 1.48e-03
+2022-04-28 13:19:52,134 INFO [train.py:763] (0/8) Epoch 3, batch 4050, loss[loss=0.2786, simple_loss=0.3484, pruned_loss=0.1044, over 7418.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3215, pruned_loss=0.08257, over 1419727.17 frames.], batch size: 21, lr: 1.47e-03
+2022-04-28 13:20:58,246 INFO [train.py:763] (0/8) Epoch 3, batch 4100, loss[loss=0.2801, simple_loss=0.3467, pruned_loss=0.1068, over 6388.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3222, pruned_loss=0.08261, over 1421399.10 frames.], batch size: 38, lr: 1.47e-03
+2022-04-28 13:22:04,074 INFO [train.py:763] (0/8) Epoch 3, batch 4150, loss[loss=0.1932, simple_loss=0.272, pruned_loss=0.0572, over 7001.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3207, pruned_loss=0.08154, over 1423213.01 frames.], batch size: 16, lr: 1.47e-03
+2022-04-28 13:23:11,047 INFO [train.py:763] (0/8) Epoch 3, batch 4200, loss[loss=0.242, simple_loss=0.3166, pruned_loss=0.08367, over 7160.00 frames.], tot_loss[loss=0.2411, simple_loss=0.3203, pruned_loss=0.08096, over 1422072.00 frames.], batch size: 19, lr: 1.47e-03
+2022-04-28 13:24:18,329 INFO [train.py:763] (0/8) Epoch 3, batch 4250, loss[loss=0.2129, simple_loss=0.2942, pruned_loss=0.06581, over 7359.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3194, pruned_loss=0.08073, over 1414770.53 frames.], batch size: 19, lr: 1.47e-03
+2022-04-28 13:25:24,091 INFO [train.py:763] (0/8) Epoch 3, batch 4300, loss[loss=0.2265, simple_loss=0.3046, pruned_loss=0.07423, over 7363.00 frames.], tot_loss[loss=0.2384, simple_loss=0.3174, pruned_loss=0.07964, over 1413389.27 frames.], batch size: 19, lr: 1.47e-03
+2022-04-28 13:26:29,901 INFO [train.py:763] (0/8) Epoch 3, batch 4350, loss[loss=0.2275, simple_loss=0.3156, pruned_loss=0.06973, over 6392.00 frames.], tot_loss[loss=0.2383, simple_loss=0.3167, pruned_loss=0.08001, over 1410823.52 frames.], batch size: 37, lr: 1.46e-03
+2022-04-28 13:27:35,723 INFO [train.py:763] (0/8) Epoch 3, batch 4400, loss[loss=0.1859, simple_loss=0.274, pruned_loss=0.04893, over 7069.00 frames.], tot_loss[loss=0.237, simple_loss=0.3154, pruned_loss=0.07935, over 1409828.20 frames.], batch size: 18, lr: 1.46e-03
+2022-04-28 13:28:41,567 INFO [train.py:763] (0/8) Epoch 3, batch 4450, loss[loss=0.2264, simple_loss=0.3095, pruned_loss=0.07164, over 7357.00 frames.], tot_loss[loss=0.2381, simple_loss=0.316, pruned_loss=0.08015, over 1400682.89 frames.], batch size: 23, lr: 1.46e-03
+2022-04-28 13:29:46,954 INFO [train.py:763] (0/8) Epoch 3, batch 4500, loss[loss=0.2496, simple_loss=0.3243, pruned_loss=0.08744, over 6380.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3177, pruned_loss=0.08104, over 1395209.88 frames.], batch size: 37, lr: 1.46e-03
+2022-04-28 13:30:51,043 INFO [train.py:763] (0/8) Epoch 3, batch 4550, loss[loss=0.2657, simple_loss=0.3325, pruned_loss=0.09946, over 5216.00 frames.], tot_loss[loss=0.2437, simple_loss=0.3207, pruned_loss=0.08332, over 1361290.03 frames.], batch size: 52, lr: 1.46e-03
+2022-04-28 13:31:40,543 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-3.pt
+2022-04-28 13:32:20,227 INFO [train.py:763] (0/8) Epoch 4, batch 0, loss[loss=0.2592, simple_loss=0.345, pruned_loss=0.08671, over 7200.00 frames.], tot_loss[loss=0.2592, simple_loss=0.345, pruned_loss=0.08671, over 7200.00 frames.], batch size: 23, lr: 1.40e-03
+2022-04-28 13:33:26,507 INFO [train.py:763] (0/8) Epoch 4, batch 50, loss[loss=0.2602, simple_loss=0.3425, pruned_loss=0.08894, over 7337.00 frames.], tot_loss[loss=0.2425, simple_loss=0.321, pruned_loss=0.08195, over 320386.75 frames.], batch size: 22, lr: 1.40e-03
+2022-04-28 13:34:31,943 INFO [train.py:763] (0/8) Epoch 4, batch 100, loss[loss=0.2525, simple_loss=0.3383, pruned_loss=0.08337, over 7325.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3202, pruned_loss=0.08028, over 566165.30 frames.], batch size: 22, lr: 1.40e-03
+2022-04-28 13:35:37,385 INFO [train.py:763] (0/8) Epoch 4, batch 150, loss[loss=0.2894, simple_loss=0.3518, pruned_loss=0.1134, over 5449.00 frames.], tot_loss[loss=0.2395, simple_loss=0.3202, pruned_loss=0.07941, over 755937.25 frames.], batch size: 52, lr: 1.40e-03
+2022-04-28 13:36:43,017 INFO [train.py:763] (0/8) Epoch 4, batch 200, loss[loss=0.2724, simple_loss=0.3407, pruned_loss=0.1021, over 7165.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3224, pruned_loss=0.08206, over 903921.48 frames.], batch size: 19, lr: 1.40e-03
+2022-04-28 13:37:48,983 INFO [train.py:763] (0/8) Epoch 4, batch 250, loss[loss=0.2754, simple_loss=0.3389, pruned_loss=0.1059, over 7325.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3233, pruned_loss=0.08102, over 1021748.35 frames.], batch size: 22, lr: 1.39e-03
+2022-04-28 13:38:55,656 INFO [train.py:763] (0/8) Epoch 4, batch 300, loss[loss=0.2179, simple_loss=0.2972, pruned_loss=0.0693, over 7264.00 frames.], tot_loss[loss=0.239, simple_loss=0.3196, pruned_loss=0.07917, over 1113876.38 frames.], batch size: 17, lr: 1.39e-03
+2022-04-28 13:40:02,797 INFO [train.py:763] (0/8) Epoch 4, batch 350, loss[loss=0.2006, simple_loss=0.2955, pruned_loss=0.0528, over 7165.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3182, pruned_loss=0.07869, over 1181043.06 frames.], batch size: 19, lr: 1.39e-03
+2022-04-28 13:41:09,486 INFO [train.py:763] (0/8) Epoch 4, batch 400, loss[loss=0.2473, simple_loss=0.3246, pruned_loss=0.08503, over 7058.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3173, pruned_loss=0.07829, over 1232315.34 frames.], batch size: 28, lr: 1.39e-03
+2022-04-28 13:42:15,469 INFO [train.py:763] (0/8) Epoch 4, batch 450, loss[loss=0.276, simple_loss=0.343, pruned_loss=0.1045, over 7102.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3171, pruned_loss=0.07791, over 1274555.24 frames.], batch size: 28, lr: 1.39e-03
+2022-04-28 13:43:21,315 INFO [train.py:763] (0/8) Epoch 4, batch 500, loss[loss=0.2792, simple_loss=0.3449, pruned_loss=0.1068, over 7319.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3159, pruned_loss=0.07728, over 1310791.41 frames.], batch size: 21, lr: 1.39e-03
+2022-04-28 13:44:28,340 INFO [train.py:763] (0/8) Epoch 4, batch 550, loss[loss=0.2673, simple_loss=0.3379, pruned_loss=0.09838, over 6746.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3154, pruned_loss=0.07684, over 1335237.37 frames.], batch size: 31, lr: 1.38e-03
+2022-04-28 13:45:33,795 INFO [train.py:763] (0/8) Epoch 4, batch 600, loss[loss=0.2258, simple_loss=0.2916, pruned_loss=0.08004, over 6992.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3152, pruned_loss=0.07718, over 1356798.70 frames.], batch size: 16, lr: 1.38e-03
+2022-04-28 13:46:39,061 INFO [train.py:763] (0/8) Epoch 4, batch 650, loss[loss=0.2144, simple_loss=0.2964, pruned_loss=0.06617, over 7333.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3144, pruned_loss=0.0767, over 1371524.91 frames.], batch size: 20, lr: 1.38e-03
+2022-04-28 13:47:44,010 INFO [train.py:763] (0/8) Epoch 4, batch 700, loss[loss=0.2597, simple_loss=0.3457, pruned_loss=0.08686, over 7300.00 frames.], tot_loss[loss=0.2362, simple_loss=0.3168, pruned_loss=0.07787, over 1380659.80 frames.], batch size: 25, lr: 1.38e-03
+2022-04-28 13:48:49,483 INFO [train.py:763] (0/8) Epoch 4, batch 750, loss[loss=0.2192, simple_loss=0.3035, pruned_loss=0.0675, over 7063.00 frames.], tot_loss[loss=0.2361, simple_loss=0.3162, pruned_loss=0.07799, over 1384841.80 frames.], batch size: 18, lr: 1.38e-03
+2022-04-28 13:49:55,007 INFO [train.py:763] (0/8) Epoch 4, batch 800, loss[loss=0.2223, simple_loss=0.3057, pruned_loss=0.06943, over 7062.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3143, pruned_loss=0.07646, over 1396885.73 frames.], batch size: 18, lr: 1.38e-03
+2022-04-28 13:50:59,970 INFO [train.py:763] (0/8) Epoch 4, batch 850, loss[loss=0.2038, simple_loss=0.2914, pruned_loss=0.05807, over 7064.00 frames.], tot_loss[loss=0.2345, simple_loss=0.315, pruned_loss=0.07706, over 1394627.83 frames.], batch size: 18, lr: 1.37e-03
+2022-04-28 13:52:05,760 INFO [train.py:763] (0/8) Epoch 4, batch 900, loss[loss=0.2614, simple_loss=0.3387, pruned_loss=0.09198, over 7322.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3149, pruned_loss=0.07668, over 1401747.92 frames.], batch size: 21, lr: 1.37e-03
+2022-04-28 13:53:12,235 INFO [train.py:763] (0/8) Epoch 4, batch 950, loss[loss=0.23, simple_loss=0.3219, pruned_loss=0.06905, over 7109.00 frames.], tot_loss[loss=0.235, simple_loss=0.3159, pruned_loss=0.07706, over 1405407.12 frames.], batch size: 28, lr: 1.37e-03
+2022-04-28 13:54:19,386 INFO [train.py:763] (0/8) Epoch 4, batch 1000, loss[loss=0.2524, simple_loss=0.3203, pruned_loss=0.09227, over 7075.00 frames.], tot_loss[loss=0.2342, simple_loss=0.315, pruned_loss=0.0767, over 1411386.54 frames.], batch size: 18, lr: 1.37e-03
+2022-04-28 13:55:24,906 INFO [train.py:763] (0/8) Epoch 4, batch 1050, loss[loss=0.2822, simple_loss=0.362, pruned_loss=0.1012, over 7302.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3153, pruned_loss=0.07658, over 1416671.39 frames.], batch size: 24, lr: 1.37e-03
+2022-04-28 13:56:29,985 INFO [train.py:763] (0/8) Epoch 4, batch 1100, loss[loss=0.251, simple_loss=0.3257, pruned_loss=0.08815, over 6404.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3169, pruned_loss=0.07788, over 1412998.89 frames.], batch size: 38, lr: 1.37e-03
+2022-04-28 13:57:36,090 INFO [train.py:763] (0/8) Epoch 4, batch 1150, loss[loss=0.2742, simple_loss=0.3461, pruned_loss=0.1012, over 7425.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3178, pruned_loss=0.07847, over 1415449.79 frames.], batch size: 20, lr: 1.36e-03
+2022-04-28 13:58:41,151 INFO [train.py:763] (0/8) Epoch 4, batch 1200, loss[loss=0.2526, simple_loss=0.3315, pruned_loss=0.08685, over 6446.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3163, pruned_loss=0.07755, over 1417549.14 frames.], batch size: 38, lr: 1.36e-03
+2022-04-28 13:59:46,363 INFO [train.py:763] (0/8) Epoch 4, batch 1250, loss[loss=0.2178, simple_loss=0.302, pruned_loss=0.06676, over 7267.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3168, pruned_loss=0.07805, over 1413668.10 frames.], batch size: 19, lr: 1.36e-03
+2022-04-28 14:00:51,534 INFO [train.py:763] (0/8) Epoch 4, batch 1300, loss[loss=0.2235, simple_loss=0.3135, pruned_loss=0.06676, over 7328.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3169, pruned_loss=0.0775, over 1416918.25 frames.], batch size: 20, lr: 1.36e-03
+2022-04-28 14:01:57,426 INFO [train.py:763] (0/8) Epoch 4, batch 1350, loss[loss=0.2061, simple_loss=0.2835, pruned_loss=0.0644, over 7138.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3164, pruned_loss=0.07659, over 1423745.75 frames.], batch size: 17, lr: 1.36e-03
+2022-04-28 14:03:02,793 INFO [train.py:763] (0/8) Epoch 4, batch 1400, loss[loss=0.2201, simple_loss=0.3141, pruned_loss=0.063, over 7246.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3177, pruned_loss=0.07697, over 1419203.26 frames.], batch size: 20, lr: 1.36e-03
+2022-04-28 14:04:07,967 INFO [train.py:763] (0/8) Epoch 4, batch 1450, loss[loss=0.2194, simple_loss=0.2897, pruned_loss=0.07457, over 7014.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3181, pruned_loss=0.07731, over 1419869.47 frames.], batch size: 16, lr: 1.35e-03
+2022-04-28 14:05:14,095 INFO [train.py:763] (0/8) Epoch 4, batch 1500, loss[loss=0.204, simple_loss=0.2944, pruned_loss=0.05676, over 7321.00 frames.], tot_loss[loss=0.2354, simple_loss=0.317, pruned_loss=0.07691, over 1423441.68 frames.], batch size: 20, lr: 1.35e-03
+2022-04-28 14:06:19,710 INFO [train.py:763] (0/8) Epoch 4, batch 1550, loss[loss=0.2963, simple_loss=0.3502, pruned_loss=0.1212, over 7378.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3158, pruned_loss=0.07657, over 1425591.80 frames.], batch size: 23, lr: 1.35e-03
+2022-04-28 14:07:24,982 INFO [train.py:763] (0/8) Epoch 4, batch 1600, loss[loss=0.2132, simple_loss=0.3046, pruned_loss=0.06091, over 7312.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3158, pruned_loss=0.07646, over 1424199.42 frames.], batch size: 25, lr: 1.35e-03
+2022-04-28 14:08:30,209 INFO [train.py:763] (0/8) Epoch 4, batch 1650, loss[loss=0.2481, simple_loss=0.3357, pruned_loss=0.08024, over 7106.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3163, pruned_loss=0.07665, over 1422349.65 frames.], batch size: 21, lr: 1.35e-03
+2022-04-28 14:09:35,804 INFO [train.py:763] (0/8) Epoch 4, batch 1700, loss[loss=0.2466, simple_loss=0.3241, pruned_loss=0.08455, over 7334.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3152, pruned_loss=0.07632, over 1424314.65 frames.], batch size: 22, lr: 1.35e-03
+2022-04-28 14:10:42,774 INFO [train.py:763] (0/8) Epoch 4, batch 1750, loss[loss=0.2685, simple_loss=0.3451, pruned_loss=0.09597, over 7256.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3152, pruned_loss=0.07684, over 1423623.27 frames.], batch size: 24, lr: 1.34e-03
+2022-04-28 14:11:49,096 INFO [train.py:763] (0/8) Epoch 4, batch 1800, loss[loss=0.2509, simple_loss=0.3489, pruned_loss=0.07645, over 7328.00 frames.], tot_loss[loss=0.2351, simple_loss=0.316, pruned_loss=0.07709, over 1426170.22 frames.], batch size: 21, lr: 1.34e-03
+2022-04-28 14:12:54,653 INFO [train.py:763] (0/8) Epoch 4, batch 1850, loss[loss=0.2936, simple_loss=0.3684, pruned_loss=0.1094, over 6530.00 frames.], tot_loss[loss=0.2355, simple_loss=0.3165, pruned_loss=0.07731, over 1426584.62 frames.], batch size: 39, lr: 1.34e-03
+2022-04-28 14:13:59,954 INFO [train.py:763] (0/8) Epoch 4, batch 1900, loss[loss=0.2743, simple_loss=0.3582, pruned_loss=0.09522, over 7111.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3164, pruned_loss=0.07694, over 1427642.25 frames.], batch size: 21, lr: 1.34e-03
+2022-04-28 14:15:05,366 INFO [train.py:763] (0/8) Epoch 4, batch 1950, loss[loss=0.2359, simple_loss=0.3143, pruned_loss=0.07877, over 7167.00 frames.], tot_loss[loss=0.2347, simple_loss=0.3161, pruned_loss=0.07665, over 1428129.89 frames.], batch size: 18, lr: 1.34e-03
+2022-04-28 14:16:10,987 INFO [train.py:763] (0/8) Epoch 4, batch 2000, loss[loss=0.2638, simple_loss=0.3372, pruned_loss=0.09518, over 7312.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3151, pruned_loss=0.07654, over 1425976.07 frames.], batch size: 25, lr: 1.34e-03
+2022-04-28 14:17:16,774 INFO [train.py:763] (0/8) Epoch 4, batch 2050, loss[loss=0.251, simple_loss=0.3222, pruned_loss=0.08989, over 7294.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3145, pruned_loss=0.07582, over 1430689.38 frames.], batch size: 24, lr: 1.34e-03
+2022-04-28 14:18:22,263 INFO [train.py:763] (0/8) Epoch 4, batch 2100, loss[loss=0.2131, simple_loss=0.2864, pruned_loss=0.06994, over 7414.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3141, pruned_loss=0.07481, over 1433427.88 frames.], batch size: 18, lr: 1.33e-03
+2022-04-28 14:19:27,840 INFO [train.py:763] (0/8) Epoch 4, batch 2150, loss[loss=0.2179, simple_loss=0.2965, pruned_loss=0.06968, over 7061.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3159, pruned_loss=0.07544, over 1432056.26 frames.], batch size: 18, lr: 1.33e-03
+2022-04-28 14:20:34,211 INFO [train.py:763] (0/8) Epoch 4, batch 2200, loss[loss=0.2501, simple_loss=0.3206, pruned_loss=0.08977, over 7342.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3143, pruned_loss=0.07468, over 1434018.10 frames.], batch size: 22, lr: 1.33e-03
+2022-04-28 14:21:39,763 INFO [train.py:763] (0/8) Epoch 4, batch 2250, loss[loss=0.2296, simple_loss=0.3224, pruned_loss=0.06837, over 7388.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3142, pruned_loss=0.07463, over 1432263.38 frames.], batch size: 23, lr: 1.33e-03
+2022-04-28 14:22:45,307 INFO [train.py:763] (0/8) Epoch 4, batch 2300, loss[loss=0.1978, simple_loss=0.2772, pruned_loss=0.05914, over 7303.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3151, pruned_loss=0.07492, over 1429813.47 frames.], batch size: 17, lr: 1.33e-03
+2022-04-28 14:23:50,805 INFO [train.py:763] (0/8) Epoch 4, batch 2350, loss[loss=0.2374, simple_loss=0.3054, pruned_loss=0.08475, over 7415.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3154, pruned_loss=0.07501, over 1433011.43 frames.], batch size: 18, lr: 1.33e-03
+2022-04-28 14:24:56,458 INFO [train.py:763] (0/8) Epoch 4, batch 2400, loss[loss=0.2633, simple_loss=0.3408, pruned_loss=0.0929, over 7225.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3147, pruned_loss=0.0748, over 1434142.39 frames.], batch size: 21, lr: 1.32e-03
+2022-04-28 14:26:01,990 INFO [train.py:763] (0/8) Epoch 4, batch 2450, loss[loss=0.2044, simple_loss=0.2861, pruned_loss=0.06132, over 7268.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3158, pruned_loss=0.07552, over 1434151.56 frames.], batch size: 18, lr: 1.32e-03
+2022-04-28 14:27:09,111 INFO [train.py:763] (0/8) Epoch 4, batch 2500, loss[loss=0.2221, simple_loss=0.314, pruned_loss=0.06507, over 7219.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3151, pruned_loss=0.07567, over 1431562.31 frames.], batch size: 22, lr: 1.32e-03
+2022-04-28 14:28:15,000 INFO [train.py:763] (0/8) Epoch 4, batch 2550, loss[loss=0.262, simple_loss=0.3506, pruned_loss=0.08667, over 7144.00 frames.], tot_loss[loss=0.233, simple_loss=0.3153, pruned_loss=0.07541, over 1432159.35 frames.], batch size: 20, lr: 1.32e-03
+2022-04-28 14:29:20,321 INFO [train.py:763] (0/8) Epoch 4, batch 2600, loss[loss=0.2133, simple_loss=0.3083, pruned_loss=0.0591, over 7325.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3158, pruned_loss=0.07545, over 1430468.47 frames.], batch size: 21, lr: 1.32e-03
+2022-04-28 14:30:26,100 INFO [train.py:763] (0/8) Epoch 4, batch 2650, loss[loss=0.2054, simple_loss=0.2859, pruned_loss=0.06248, over 7438.00 frames.], tot_loss[loss=0.233, simple_loss=0.3153, pruned_loss=0.07534, over 1429676.63 frames.], batch size: 17, lr: 1.32e-03
+2022-04-28 14:31:31,710 INFO [train.py:763] (0/8) Epoch 4, batch 2700, loss[loss=0.2135, simple_loss=0.2851, pruned_loss=0.07095, over 7284.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3139, pruned_loss=0.07432, over 1432224.36 frames.], batch size: 18, lr: 1.32e-03
+2022-04-28 14:32:38,240 INFO [train.py:763] (0/8) Epoch 4, batch 2750, loss[loss=0.2926, simple_loss=0.3568, pruned_loss=0.1142, over 7352.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3139, pruned_loss=0.07439, over 1433112.52 frames.], batch size: 19, lr: 1.31e-03
+2022-04-28 14:33:43,927 INFO [train.py:763] (0/8) Epoch 4, batch 2800, loss[loss=0.2034, simple_loss=0.2833, pruned_loss=0.06169, over 7137.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3129, pruned_loss=0.07377, over 1434381.09 frames.], batch size: 17, lr: 1.31e-03
+2022-04-28 14:34:49,332 INFO [train.py:763] (0/8) Epoch 4, batch 2850, loss[loss=0.2368, simple_loss=0.3287, pruned_loss=0.07246, over 6693.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3135, pruned_loss=0.07442, over 1431261.77 frames.], batch size: 31, lr: 1.31e-03
+2022-04-28 14:35:55,990 INFO [train.py:763] (0/8) Epoch 4, batch 2900, loss[loss=0.2639, simple_loss=0.3407, pruned_loss=0.09353, over 7282.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3145, pruned_loss=0.07519, over 1429140.93 frames.], batch size: 24, lr: 1.31e-03
+2022-04-28 14:37:01,949 INFO [train.py:763] (0/8) Epoch 4, batch 2950, loss[loss=0.2198, simple_loss=0.3026, pruned_loss=0.06846, over 7342.00 frames.], tot_loss[loss=0.2299, simple_loss=0.3121, pruned_loss=0.07389, over 1429092.12 frames.], batch size: 22, lr: 1.31e-03
+2022-04-28 14:38:07,797 INFO [train.py:763] (0/8) Epoch 4, batch 3000, loss[loss=0.2134, simple_loss=0.3092, pruned_loss=0.0588, over 7200.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3127, pruned_loss=0.07458, over 1425036.34 frames.], batch size: 26, lr: 1.31e-03
+2022-04-28 14:38:07,799 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-28 14:38:23,245 INFO [train.py:792] (0/8) Epoch 4, validation: loss=0.1809, simple_loss=0.2865, pruned_loss=0.03766, over 698248.00 frames.
+2022-04-28 14:39:28,680 INFO [train.py:763] (0/8) Epoch 4, batch 3050, loss[loss=0.2779, simple_loss=0.3633, pruned_loss=0.09621, over 7200.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3138, pruned_loss=0.07453, over 1428630.93 frames.], batch size: 22, lr: 1.31e-03
+2022-04-28 14:40:34,114 INFO [train.py:763] (0/8) Epoch 4, batch 3100, loss[loss=0.2479, simple_loss=0.3341, pruned_loss=0.08087, over 7234.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3141, pruned_loss=0.07449, over 1427308.09 frames.], batch size: 20, lr: 1.30e-03
+2022-04-28 14:41:39,923 INFO [train.py:763] (0/8) Epoch 4, batch 3150, loss[loss=0.2624, simple_loss=0.3432, pruned_loss=0.09081, over 7277.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3136, pruned_loss=0.07389, over 1428074.72 frames.], batch size: 25, lr: 1.30e-03
+2022-04-28 14:42:46,510 INFO [train.py:763] (0/8) Epoch 4, batch 3200, loss[loss=0.2096, simple_loss=0.2916, pruned_loss=0.06376, over 7361.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3125, pruned_loss=0.07336, over 1429338.23 frames.], batch size: 19, lr: 1.30e-03
+2022-04-28 14:43:52,381 INFO [train.py:763] (0/8) Epoch 4, batch 3250, loss[loss=0.2189, simple_loss=0.2903, pruned_loss=0.07375, over 7170.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3131, pruned_loss=0.07431, over 1427967.71 frames.], batch size: 18, lr: 1.30e-03
+2022-04-28 14:44:57,975 INFO [train.py:763] (0/8) Epoch 4, batch 3300, loss[loss=0.2216, simple_loss=0.3091, pruned_loss=0.06708, over 7146.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3147, pruned_loss=0.07501, over 1422187.49 frames.], batch size: 26, lr: 1.30e-03
+2022-04-28 14:46:03,558 INFO [train.py:763] (0/8) Epoch 4, batch 3350, loss[loss=0.303, simple_loss=0.3661, pruned_loss=0.12, over 7116.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3144, pruned_loss=0.07452, over 1425085.82 frames.], batch size: 21, lr: 1.30e-03
+2022-04-28 14:47:08,819 INFO [train.py:763] (0/8) Epoch 4, batch 3400, loss[loss=0.2323, simple_loss=0.3208, pruned_loss=0.07186, over 7237.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3153, pruned_loss=0.0749, over 1426760.32 frames.], batch size: 20, lr: 1.30e-03
+2022-04-28 14:48:14,161 INFO [train.py:763] (0/8) Epoch 4, batch 3450, loss[loss=0.2378, simple_loss=0.3267, pruned_loss=0.07445, over 7194.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3138, pruned_loss=0.07424, over 1427596.53 frames.], batch size: 23, lr: 1.29e-03
+2022-04-28 14:49:37,449 INFO [train.py:763] (0/8) Epoch 4, batch 3500, loss[loss=0.2173, simple_loss=0.3066, pruned_loss=0.06397, over 7327.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3137, pruned_loss=0.07403, over 1429796.95 frames.], batch size: 20, lr: 1.29e-03
+2022-04-28 14:50:52,149 INFO [train.py:763] (0/8) Epoch 4, batch 3550, loss[loss=0.2245, simple_loss=0.3096, pruned_loss=0.06975, over 7412.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3146, pruned_loss=0.07462, over 1424273.36 frames.], batch size: 21, lr: 1.29e-03
+2022-04-28 14:51:57,884 INFO [train.py:763] (0/8) Epoch 4, batch 3600, loss[loss=0.2325, simple_loss=0.3244, pruned_loss=0.07033, over 7263.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3137, pruned_loss=0.07449, over 1421212.23 frames.], batch size: 19, lr: 1.29e-03
+2022-04-28 14:53:23,274 INFO [train.py:763] (0/8) Epoch 4, batch 3650, loss[loss=0.254, simple_loss=0.3398, pruned_loss=0.08413, over 6717.00 frames.], tot_loss[loss=0.2305, simple_loss=0.3135, pruned_loss=0.0738, over 1415498.80 frames.], batch size: 31, lr: 1.29e-03
+2022-04-28 14:54:39,018 INFO [train.py:763] (0/8) Epoch 4, batch 3700, loss[loss=0.2152, simple_loss=0.2934, pruned_loss=0.06847, over 7166.00 frames.], tot_loss[loss=0.2288, simple_loss=0.3114, pruned_loss=0.07311, over 1419678.16 frames.], batch size: 18, lr: 1.29e-03
+2022-04-28 14:55:53,486 INFO [train.py:763] (0/8) Epoch 4, batch 3750, loss[loss=0.208, simple_loss=0.2854, pruned_loss=0.06529, over 6750.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3122, pruned_loss=0.07347, over 1419658.09 frames.], batch size: 15, lr: 1.29e-03
+2022-04-28 14:56:59,181 INFO [train.py:763] (0/8) Epoch 4, batch 3800, loss[loss=0.2147, simple_loss=0.2925, pruned_loss=0.06842, over 7287.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3127, pruned_loss=0.07351, over 1420693.06 frames.], batch size: 18, lr: 1.28e-03
+2022-04-28 14:58:05,508 INFO [train.py:763] (0/8) Epoch 4, batch 3850, loss[loss=0.2502, simple_loss=0.3395, pruned_loss=0.08044, over 7410.00 frames.], tot_loss[loss=0.2305, simple_loss=0.313, pruned_loss=0.074, over 1419217.70 frames.], batch size: 21, lr: 1.28e-03
+2022-04-28 14:59:11,128 INFO [train.py:763] (0/8) Epoch 4, batch 3900, loss[loss=0.218, simple_loss=0.2983, pruned_loss=0.06881, over 7157.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3124, pruned_loss=0.07367, over 1416102.58 frames.], batch size: 18, lr: 1.28e-03
+2022-04-28 15:00:16,497 INFO [train.py:763] (0/8) Epoch 4, batch 3950, loss[loss=0.2394, simple_loss=0.3243, pruned_loss=0.07726, over 7416.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3122, pruned_loss=0.07328, over 1413239.55 frames.], batch size: 21, lr: 1.28e-03
+2022-04-28 15:01:21,852 INFO [train.py:763] (0/8) Epoch 4, batch 4000, loss[loss=0.2213, simple_loss=0.3096, pruned_loss=0.06649, over 7426.00 frames.], tot_loss[loss=0.229, simple_loss=0.3124, pruned_loss=0.07282, over 1416297.71 frames.], batch size: 20, lr: 1.28e-03
+2022-04-28 15:02:27,499 INFO [train.py:763] (0/8) Epoch 4, batch 4050, loss[loss=0.2267, simple_loss=0.3284, pruned_loss=0.06247, over 7212.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3116, pruned_loss=0.07242, over 1419169.33 frames.], batch size: 21, lr: 1.28e-03
+2022-04-28 15:03:34,146 INFO [train.py:763] (0/8) Epoch 4, batch 4100, loss[loss=0.2134, simple_loss=0.2922, pruned_loss=0.06733, over 7299.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3147, pruned_loss=0.07409, over 1415803.25 frames.], batch size: 18, lr: 1.28e-03
+2022-04-28 15:04:40,990 INFO [train.py:763] (0/8) Epoch 4, batch 4150, loss[loss=0.245, simple_loss=0.3332, pruned_loss=0.07841, over 7192.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3145, pruned_loss=0.07382, over 1415007.46 frames.], batch size: 22, lr: 1.27e-03
+2022-04-28 15:05:47,258 INFO [train.py:763] (0/8) Epoch 4, batch 4200, loss[loss=0.2388, simple_loss=0.3053, pruned_loss=0.08618, over 7150.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3151, pruned_loss=0.07449, over 1413898.09 frames.], batch size: 17, lr: 1.27e-03
+2022-04-28 15:06:53,145 INFO [train.py:763] (0/8) Epoch 4, batch 4250, loss[loss=0.2101, simple_loss=0.286, pruned_loss=0.06711, over 7064.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3154, pruned_loss=0.07522, over 1414393.84 frames.], batch size: 18, lr: 1.27e-03
+2022-04-28 15:07:59,473 INFO [train.py:763] (0/8) Epoch 4, batch 4300, loss[loss=0.2324, simple_loss=0.3187, pruned_loss=0.07304, over 7146.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3156, pruned_loss=0.07501, over 1414554.06 frames.], batch size: 20, lr: 1.27e-03
+2022-04-28 15:09:04,577 INFO [train.py:763] (0/8) Epoch 4, batch 4350, loss[loss=0.2314, simple_loss=0.3188, pruned_loss=0.072, over 7421.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3165, pruned_loss=0.07504, over 1413267.93 frames.], batch size: 21, lr: 1.27e-03
+2022-04-28 15:10:09,738 INFO [train.py:763] (0/8) Epoch 4, batch 4400, loss[loss=0.2031, simple_loss=0.2849, pruned_loss=0.0607, over 7265.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3152, pruned_loss=0.0745, over 1410126.95 frames.], batch size: 19, lr: 1.27e-03
+2022-04-28 15:11:14,754 INFO [train.py:763] (0/8) Epoch 4, batch 4450, loss[loss=0.2644, simple_loss=0.349, pruned_loss=0.08986, over 6744.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3155, pruned_loss=0.07475, over 1403887.95 frames.], batch size: 31, lr: 1.27e-03
+2022-04-28 15:12:19,767 INFO [train.py:763] (0/8) Epoch 4, batch 4500, loss[loss=0.2901, simple_loss=0.3542, pruned_loss=0.113, over 4830.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3171, pruned_loss=0.07574, over 1394431.43 frames.], batch size: 52, lr: 1.27e-03
+2022-04-28 15:13:25,336 INFO [train.py:763] (0/8) Epoch 4, batch 4550, loss[loss=0.2683, simple_loss=0.3315, pruned_loss=0.1025, over 5008.00 frames.], tot_loss[loss=0.2396, simple_loss=0.3204, pruned_loss=0.0794, over 1339023.25 frames.], batch size: 52, lr: 1.26e-03
+2022-04-28 15:14:14,414 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-4.pt
+2022-04-28 15:14:53,616 INFO [train.py:763] (0/8) Epoch 5, batch 0, loss[loss=0.2421, simple_loss=0.3149, pruned_loss=0.08468, over 7158.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3149, pruned_loss=0.08468, over 7158.00 frames.], batch size: 19, lr: 1.21e-03
+2022-04-28 15:15:59,882 INFO [train.py:763] (0/8) Epoch 5, batch 50, loss[loss=0.2669, simple_loss=0.332, pruned_loss=0.101, over 4900.00 frames.], tot_loss[loss=0.231, simple_loss=0.314, pruned_loss=0.07399, over 318034.48 frames.], batch size: 52, lr: 1.21e-03
+2022-04-28 15:17:05,488 INFO [train.py:763] (0/8) Epoch 5, batch 100, loss[loss=0.2243, simple_loss=0.3232, pruned_loss=0.06275, over 7143.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3133, pruned_loss=0.07219, over 561737.03 frames.], batch size: 20, lr: 1.21e-03
+2022-04-28 15:18:11,246 INFO [train.py:763] (0/8) Epoch 5, batch 150, loss[loss=0.2463, simple_loss=0.3358, pruned_loss=0.0784, over 6767.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3115, pruned_loss=0.0711, over 749438.81 frames.], batch size: 31, lr: 1.21e-03
+2022-04-28 15:19:17,542 INFO [train.py:763] (0/8) Epoch 5, batch 200, loss[loss=0.2079, simple_loss=0.2933, pruned_loss=0.06123, over 7421.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3126, pruned_loss=0.07263, over 898913.59 frames.], batch size: 18, lr: 1.21e-03
+2022-04-28 15:20:23,017 INFO [train.py:763] (0/8) Epoch 5, batch 250, loss[loss=0.2342, simple_loss=0.3188, pruned_loss=0.07483, over 7336.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3108, pruned_loss=0.07149, over 1018815.97 frames.], batch size: 22, lr: 1.21e-03
+2022-04-28 15:21:29,021 INFO [train.py:763] (0/8) Epoch 5, batch 300, loss[loss=0.2076, simple_loss=0.3108, pruned_loss=0.05217, over 7236.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3106, pruned_loss=0.07052, over 1111577.88 frames.], batch size: 20, lr: 1.21e-03
+2022-04-28 15:22:35,206 INFO [train.py:763] (0/8) Epoch 5, batch 350, loss[loss=0.23, simple_loss=0.317, pruned_loss=0.07151, over 7315.00 frames.], tot_loss[loss=0.225, simple_loss=0.3099, pruned_loss=0.07006, over 1184333.22 frames.], batch size: 20, lr: 1.20e-03
+2022-04-28 15:23:40,938 INFO [train.py:763] (0/8) Epoch 5, batch 400, loss[loss=0.2504, simple_loss=0.3357, pruned_loss=0.08255, over 7379.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3117, pruned_loss=0.07139, over 1235842.96 frames.], batch size: 23, lr: 1.20e-03
+2022-04-28 15:24:46,900 INFO [train.py:763] (0/8) Epoch 5, batch 450, loss[loss=0.1917, simple_loss=0.2827, pruned_loss=0.05034, over 7232.00 frames.], tot_loss[loss=0.2271, simple_loss=0.3117, pruned_loss=0.07122, over 1279428.50 frames.], batch size: 16, lr: 1.20e-03
+2022-04-28 15:25:52,442 INFO [train.py:763] (0/8) Epoch 5, batch 500, loss[loss=0.2523, simple_loss=0.3278, pruned_loss=0.08839, over 4797.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3123, pruned_loss=0.0713, over 1308005.27 frames.], batch size: 52, lr: 1.20e-03
+2022-04-28 15:26:57,647 INFO [train.py:763] (0/8) Epoch 5, batch 550, loss[loss=0.2836, simple_loss=0.359, pruned_loss=0.1042, over 6481.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3128, pruned_loss=0.07118, over 1332036.55 frames.], batch size: 38, lr: 1.20e-03
+2022-04-28 15:28:04,523 INFO [train.py:763] (0/8) Epoch 5, batch 600, loss[loss=0.2391, simple_loss=0.3241, pruned_loss=0.07705, over 7141.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3101, pruned_loss=0.07008, over 1350590.90 frames.], batch size: 20, lr: 1.20e-03
+2022-04-28 15:29:09,669 INFO [train.py:763] (0/8) Epoch 5, batch 650, loss[loss=0.2469, simple_loss=0.3398, pruned_loss=0.077, over 7406.00 frames.], tot_loss[loss=0.225, simple_loss=0.3099, pruned_loss=0.07012, over 1365801.23 frames.], batch size: 21, lr: 1.20e-03
+2022-04-28 15:30:15,014 INFO [train.py:763] (0/8) Epoch 5, batch 700, loss[loss=0.2153, simple_loss=0.2935, pruned_loss=0.0685, over 6816.00 frames.], tot_loss[loss=0.225, simple_loss=0.31, pruned_loss=0.06997, over 1377775.54 frames.], batch size: 15, lr: 1.20e-03
+2022-04-28 15:31:20,343 INFO [train.py:763] (0/8) Epoch 5, batch 750, loss[loss=0.2512, simple_loss=0.3413, pruned_loss=0.08052, over 7218.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3113, pruned_loss=0.0706, over 1388272.27 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:32:25,898 INFO [train.py:763] (0/8) Epoch 5, batch 800, loss[loss=0.2349, simple_loss=0.3289, pruned_loss=0.07044, over 7216.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3108, pruned_loss=0.07018, over 1399167.42 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:33:31,218 INFO [train.py:763] (0/8) Epoch 5, batch 850, loss[loss=0.2154, simple_loss=0.312, pruned_loss=0.05937, over 7194.00 frames.], tot_loss[loss=0.2249, simple_loss=0.31, pruned_loss=0.06991, over 1404114.88 frames.], batch size: 23, lr: 1.19e-03
+2022-04-28 15:34:36,551 INFO [train.py:763] (0/8) Epoch 5, batch 900, loss[loss=0.2422, simple_loss=0.3329, pruned_loss=0.07578, over 7413.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3104, pruned_loss=0.07045, over 1405894.66 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:35:42,337 INFO [train.py:763] (0/8) Epoch 5, batch 950, loss[loss=0.2367, simple_loss=0.3084, pruned_loss=0.08255, over 7143.00 frames.], tot_loss[loss=0.2262, simple_loss=0.3108, pruned_loss=0.07077, over 1406949.38 frames.], batch size: 17, lr: 1.19e-03
+2022-04-28 15:36:47,766 INFO [train.py:763] (0/8) Epoch 5, batch 1000, loss[loss=0.2326, simple_loss=0.3267, pruned_loss=0.06923, over 7412.00 frames.], tot_loss[loss=0.226, simple_loss=0.3106, pruned_loss=0.07071, over 1408401.69 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:37:53,895 INFO [train.py:763] (0/8) Epoch 5, batch 1050, loss[loss=0.2379, simple_loss=0.32, pruned_loss=0.07786, over 7326.00 frames.], tot_loss[loss=0.2269, simple_loss=0.3108, pruned_loss=0.07151, over 1413161.95 frames.], batch size: 20, lr: 1.19e-03
+2022-04-28 15:38:05,714 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-24000.pt
+2022-04-28 15:39:10,241 INFO [train.py:763] (0/8) Epoch 5, batch 1100, loss[loss=0.2131, simple_loss=0.3086, pruned_loss=0.0588, over 7318.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3123, pruned_loss=0.07209, over 1408539.71 frames.], batch size: 21, lr: 1.19e-03
+2022-04-28 15:40:16,767 INFO [train.py:763] (0/8) Epoch 5, batch 1150, loss[loss=0.2225, simple_loss=0.3038, pruned_loss=0.07063, over 7144.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3116, pruned_loss=0.07101, over 1412591.63 frames.], batch size: 20, lr: 1.19e-03
+2022-04-28 15:41:22,505 INFO [train.py:763] (0/8) Epoch 5, batch 1200, loss[loss=0.2314, simple_loss=0.3284, pruned_loss=0.06723, over 7148.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3114, pruned_loss=0.07094, over 1413384.98 frames.], batch size: 26, lr: 1.18e-03
+2022-04-28 15:42:28,998 INFO [train.py:763] (0/8) Epoch 5, batch 1250, loss[loss=0.2035, simple_loss=0.298, pruned_loss=0.05453, over 7145.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3122, pruned_loss=0.07127, over 1413211.51 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:43:35,962 INFO [train.py:763] (0/8) Epoch 5, batch 1300, loss[loss=0.1735, simple_loss=0.2698, pruned_loss=0.0386, over 7356.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3114, pruned_loss=0.07114, over 1411602.02 frames.], batch size: 19, lr: 1.18e-03
+2022-04-28 15:44:42,298 INFO [train.py:763] (0/8) Epoch 5, batch 1350, loss[loss=0.2652, simple_loss=0.343, pruned_loss=0.09373, over 7061.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3101, pruned_loss=0.07053, over 1415006.67 frames.], batch size: 28, lr: 1.18e-03
+2022-04-28 15:45:48,509 INFO [train.py:763] (0/8) Epoch 5, batch 1400, loss[loss=0.2194, simple_loss=0.3218, pruned_loss=0.0585, over 7321.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3085, pruned_loss=0.06908, over 1419112.47 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:46:53,769 INFO [train.py:763] (0/8) Epoch 5, batch 1450, loss[loss=0.254, simple_loss=0.339, pruned_loss=0.0845, over 7435.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3087, pruned_loss=0.06909, over 1420124.69 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:47:59,052 INFO [train.py:763] (0/8) Epoch 5, batch 1500, loss[loss=0.2245, simple_loss=0.3196, pruned_loss=0.06467, over 7148.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3086, pruned_loss=0.06921, over 1419974.05 frames.], batch size: 20, lr: 1.18e-03
+2022-04-28 15:49:04,612 INFO [train.py:763] (0/8) Epoch 5, batch 1550, loss[loss=0.1924, simple_loss=0.2697, pruned_loss=0.05754, over 7293.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3086, pruned_loss=0.06889, over 1421908.99 frames.], batch size: 17, lr: 1.18e-03
+2022-04-28 15:50:09,909 INFO [train.py:763] (0/8) Epoch 5, batch 1600, loss[loss=0.2179, simple_loss=0.306, pruned_loss=0.06484, over 7429.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3094, pruned_loss=0.06973, over 1415462.35 frames.], batch size: 20, lr: 1.17e-03
+2022-04-28 15:51:15,391 INFO [train.py:763] (0/8) Epoch 5, batch 1650, loss[loss=0.2516, simple_loss=0.3406, pruned_loss=0.08128, over 7288.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3087, pruned_loss=0.06951, over 1415158.85 frames.], batch size: 25, lr: 1.17e-03
+2022-04-28 15:52:21,479 INFO [train.py:763] (0/8) Epoch 5, batch 1700, loss[loss=0.2223, simple_loss=0.3143, pruned_loss=0.06511, over 7201.00 frames.], tot_loss[loss=0.2241, simple_loss=0.309, pruned_loss=0.06961, over 1413881.79 frames.], batch size: 22, lr: 1.17e-03
+2022-04-28 15:53:26,983 INFO [train.py:763] (0/8) Epoch 5, batch 1750, loss[loss=0.2217, simple_loss=0.2992, pruned_loss=0.07213, over 7283.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3107, pruned_loss=0.07077, over 1411530.67 frames.], batch size: 18, lr: 1.17e-03
+2022-04-28 15:54:32,251 INFO [train.py:763] (0/8) Epoch 5, batch 1800, loss[loss=0.2845, simple_loss=0.3407, pruned_loss=0.1142, over 5206.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3107, pruned_loss=0.07093, over 1413643.79 frames.], batch size: 52, lr: 1.17e-03
+2022-04-28 15:55:37,882 INFO [train.py:763] (0/8) Epoch 5, batch 1850, loss[loss=0.2339, simple_loss=0.2986, pruned_loss=0.08456, over 7161.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3107, pruned_loss=0.07103, over 1416530.98 frames.], batch size: 18, lr: 1.17e-03
+2022-04-28 15:56:43,242 INFO [train.py:763] (0/8) Epoch 5, batch 1900, loss[loss=0.1794, simple_loss=0.2687, pruned_loss=0.04503, over 7122.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3104, pruned_loss=0.07087, over 1415065.87 frames.], batch size: 17, lr: 1.17e-03
+2022-04-28 15:57:48,608 INFO [train.py:763] (0/8) Epoch 5, batch 1950, loss[loss=0.1872, simple_loss=0.2821, pruned_loss=0.04612, over 7120.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3108, pruned_loss=0.0705, over 1420700.68 frames.], batch size: 21, lr: 1.17e-03
+2022-04-28 15:58:54,747 INFO [train.py:763] (0/8) Epoch 5, batch 2000, loss[loss=0.1813, simple_loss=0.2729, pruned_loss=0.04483, over 7260.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3108, pruned_loss=0.0707, over 1424095.15 frames.], batch size: 18, lr: 1.17e-03
+2022-04-28 15:59:59,997 INFO [train.py:763] (0/8) Epoch 5, batch 2050, loss[loss=0.2271, simple_loss=0.3275, pruned_loss=0.06336, over 7124.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3109, pruned_loss=0.07023, over 1424184.23 frames.], batch size: 28, lr: 1.16e-03
+2022-04-28 16:01:06,588 INFO [train.py:763] (0/8) Epoch 5, batch 2100, loss[loss=0.2171, simple_loss=0.2978, pruned_loss=0.06819, over 6460.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3104, pruned_loss=0.06998, over 1426312.59 frames.], batch size: 38, lr: 1.16e-03
+2022-04-28 16:02:12,122 INFO [train.py:763] (0/8) Epoch 5, batch 2150, loss[loss=0.2032, simple_loss=0.2986, pruned_loss=0.05392, over 7144.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3093, pruned_loss=0.06927, over 1431075.78 frames.], batch size: 20, lr: 1.16e-03
+2022-04-28 16:03:17,462 INFO [train.py:763] (0/8) Epoch 5, batch 2200, loss[loss=0.2395, simple_loss=0.3121, pruned_loss=0.08345, over 7144.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3085, pruned_loss=0.069, over 1427715.35 frames.], batch size: 20, lr: 1.16e-03
+2022-04-28 16:04:22,918 INFO [train.py:763] (0/8) Epoch 5, batch 2250, loss[loss=0.191, simple_loss=0.2861, pruned_loss=0.04794, over 7357.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3082, pruned_loss=0.06908, over 1425901.66 frames.], batch size: 19, lr: 1.16e-03
+2022-04-28 16:05:29,104 INFO [train.py:763] (0/8) Epoch 5, batch 2300, loss[loss=0.2293, simple_loss=0.3065, pruned_loss=0.07608, over 7290.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3081, pruned_loss=0.06906, over 1423307.06 frames.], batch size: 24, lr: 1.16e-03
+2022-04-28 16:06:35,247 INFO [train.py:763] (0/8) Epoch 5, batch 2350, loss[loss=0.1962, simple_loss=0.2853, pruned_loss=0.05358, over 7210.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3074, pruned_loss=0.06881, over 1422643.41 frames.], batch size: 21, lr: 1.16e-03
+2022-04-28 16:07:41,484 INFO [train.py:763] (0/8) Epoch 5, batch 2400, loss[loss=0.1997, simple_loss=0.2897, pruned_loss=0.05483, over 7328.00 frames.], tot_loss[loss=0.2209, simple_loss=0.306, pruned_loss=0.06794, over 1422525.64 frames.], batch size: 20, lr: 1.16e-03
+2022-04-28 16:08:47,669 INFO [train.py:763] (0/8) Epoch 5, batch 2450, loss[loss=0.1923, simple_loss=0.2757, pruned_loss=0.05442, over 6803.00 frames.], tot_loss[loss=0.221, simple_loss=0.3057, pruned_loss=0.06814, over 1421023.29 frames.], batch size: 15, lr: 1.16e-03
+2022-04-28 16:09:52,918 INFO [train.py:763] (0/8) Epoch 5, batch 2500, loss[loss=0.2492, simple_loss=0.3255, pruned_loss=0.08646, over 7327.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3062, pruned_loss=0.06837, over 1420493.45 frames.], batch size: 22, lr: 1.15e-03
+2022-04-28 16:10:59,317 INFO [train.py:763] (0/8) Epoch 5, batch 2550, loss[loss=0.1855, simple_loss=0.2741, pruned_loss=0.04849, over 6868.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3062, pruned_loss=0.06844, over 1422562.49 frames.], batch size: 15, lr: 1.15e-03
+2022-04-28 16:12:05,360 INFO [train.py:763] (0/8) Epoch 5, batch 2600, loss[loss=0.2328, simple_loss=0.3185, pruned_loss=0.0735, over 7319.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3074, pruned_loss=0.06886, over 1425133.98 frames.], batch size: 21, lr: 1.15e-03
+2022-04-28 16:13:10,882 INFO [train.py:763] (0/8) Epoch 5, batch 2650, loss[loss=0.2015, simple_loss=0.3017, pruned_loss=0.05064, over 7314.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3073, pruned_loss=0.06805, over 1423616.05 frames.], batch size: 25, lr: 1.15e-03
+2022-04-28 16:14:16,442 INFO [train.py:763] (0/8) Epoch 5, batch 2700, loss[loss=0.1779, simple_loss=0.2636, pruned_loss=0.04608, over 6790.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3075, pruned_loss=0.06789, over 1425398.60 frames.], batch size: 15, lr: 1.15e-03
+2022-04-28 16:15:15,071 INFO [train.py:763] (0/8) Epoch 5, batch 2750, loss[loss=0.2334, simple_loss=0.3137, pruned_loss=0.07649, over 7239.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3073, pruned_loss=0.06756, over 1423431.32 frames.], batch size: 20, lr: 1.15e-03
+2022-04-28 16:16:11,921 INFO [train.py:763] (0/8) Epoch 5, batch 2800, loss[loss=0.1969, simple_loss=0.2749, pruned_loss=0.05946, over 7272.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3075, pruned_loss=0.06778, over 1421135.27 frames.], batch size: 18, lr: 1.15e-03
+2022-04-28 16:17:08,602 INFO [train.py:763] (0/8) Epoch 5, batch 2850, loss[loss=0.198, simple_loss=0.2862, pruned_loss=0.05487, over 7261.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3081, pruned_loss=0.06833, over 1417979.10 frames.], batch size: 17, lr: 1.15e-03
+2022-04-28 16:18:06,402 INFO [train.py:763] (0/8) Epoch 5, batch 2900, loss[loss=0.2569, simple_loss=0.3294, pruned_loss=0.09217, over 6725.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3081, pruned_loss=0.06829, over 1419851.28 frames.], batch size: 31, lr: 1.15e-03
+2022-04-28 16:19:04,273 INFO [train.py:763] (0/8) Epoch 5, batch 2950, loss[loss=0.2137, simple_loss=0.3012, pruned_loss=0.06309, over 7142.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3074, pruned_loss=0.06818, over 1420996.19 frames.], batch size: 20, lr: 1.14e-03
+2022-04-28 16:19:58,118 INFO [train.py:763] (0/8) Epoch 5, batch 3000, loss[loss=0.2204, simple_loss=0.3028, pruned_loss=0.06902, over 7245.00 frames.], tot_loss[loss=0.222, simple_loss=0.3075, pruned_loss=0.06829, over 1420668.07 frames.], batch size: 20, lr: 1.14e-03
+2022-04-28 16:19:58,120 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-28 16:20:13,356 INFO [train.py:792] (0/8) Epoch 5, validation: loss=0.1791, simple_loss=0.2847, pruned_loss=0.03677, over 698248.00 frames.
+2022-04-28 16:21:19,348 INFO [train.py:763] (0/8) Epoch 5, batch 3050, loss[loss=0.255, simple_loss=0.3387, pruned_loss=0.08564, over 7215.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3067, pruned_loss=0.06792, over 1426048.37 frames.], batch size: 23, lr: 1.14e-03
+2022-04-28 16:22:24,942 INFO [train.py:763] (0/8) Epoch 5, batch 3100, loss[loss=0.2144, simple_loss=0.3072, pruned_loss=0.0608, over 7342.00 frames.], tot_loss[loss=0.22, simple_loss=0.3056, pruned_loss=0.06719, over 1423364.73 frames.], batch size: 22, lr: 1.14e-03
+2022-04-28 16:23:30,175 INFO [train.py:763] (0/8) Epoch 5, batch 3150, loss[loss=0.2506, simple_loss=0.3331, pruned_loss=0.0841, over 7175.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3063, pruned_loss=0.067, over 1423358.54 frames.], batch size: 23, lr: 1.14e-03
+2022-04-28 16:24:36,693 INFO [train.py:763] (0/8) Epoch 5, batch 3200, loss[loss=0.2355, simple_loss=0.3212, pruned_loss=0.07496, over 7222.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3078, pruned_loss=0.06795, over 1424827.76 frames.], batch size: 21, lr: 1.14e-03
+2022-04-28 16:25:42,638 INFO [train.py:763] (0/8) Epoch 5, batch 3250, loss[loss=0.2133, simple_loss=0.305, pruned_loss=0.0608, over 7361.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3078, pruned_loss=0.06787, over 1424755.72 frames.], batch size: 19, lr: 1.14e-03
+2022-04-28 16:26:48,958 INFO [train.py:763] (0/8) Epoch 5, batch 3300, loss[loss=0.219, simple_loss=0.2991, pruned_loss=0.06946, over 7192.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3078, pruned_loss=0.06796, over 1420842.30 frames.], batch size: 23, lr: 1.14e-03
+2022-04-28 16:27:54,270 INFO [train.py:763] (0/8) Epoch 5, batch 3350, loss[loss=0.2183, simple_loss=0.3023, pruned_loss=0.06718, over 7258.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3065, pruned_loss=0.0673, over 1425583.94 frames.], batch size: 19, lr: 1.14e-03
+2022-04-28 16:28:59,517 INFO [train.py:763] (0/8) Epoch 5, batch 3400, loss[loss=0.2333, simple_loss=0.3291, pruned_loss=0.06879, over 7302.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3055, pruned_loss=0.0668, over 1426202.05 frames.], batch size: 24, lr: 1.14e-03
+2022-04-28 16:30:05,198 INFO [train.py:763] (0/8) Epoch 5, batch 3450, loss[loss=0.2416, simple_loss=0.3411, pruned_loss=0.07111, over 7416.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3077, pruned_loss=0.06809, over 1427561.34 frames.], batch size: 21, lr: 1.13e-03
+2022-04-28 16:31:11,009 INFO [train.py:763] (0/8) Epoch 5, batch 3500, loss[loss=0.2263, simple_loss=0.3178, pruned_loss=0.06741, over 7190.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3066, pruned_loss=0.06744, over 1424649.88 frames.], batch size: 22, lr: 1.13e-03
+2022-04-28 16:32:16,135 INFO [train.py:763] (0/8) Epoch 5, batch 3550, loss[loss=0.2203, simple_loss=0.3166, pruned_loss=0.06199, over 7310.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3065, pruned_loss=0.0671, over 1427539.27 frames.], batch size: 21, lr: 1.13e-03
+2022-04-28 16:33:21,412 INFO [train.py:763] (0/8) Epoch 5, batch 3600, loss[loss=0.2072, simple_loss=0.2812, pruned_loss=0.06661, over 7177.00 frames.], tot_loss[loss=0.2208, simple_loss=0.3066, pruned_loss=0.06753, over 1428564.42 frames.], batch size: 18, lr: 1.13e-03
+2022-04-28 16:34:27,116 INFO [train.py:763] (0/8) Epoch 5, batch 3650, loss[loss=0.2474, simple_loss=0.3279, pruned_loss=0.08348, over 7413.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3067, pruned_loss=0.06773, over 1427951.59 frames.], batch size: 21, lr: 1.13e-03
+2022-04-28 16:35:34,076 INFO [train.py:763] (0/8) Epoch 5, batch 3700, loss[loss=0.2408, simple_loss=0.3221, pruned_loss=0.07977, over 7243.00 frames.], tot_loss[loss=0.2217, simple_loss=0.307, pruned_loss=0.06818, over 1426285.15 frames.], batch size: 20, lr: 1.13e-03
+2022-04-28 16:36:39,376 INFO [train.py:763] (0/8) Epoch 5, batch 3750, loss[loss=0.2121, simple_loss=0.2958, pruned_loss=0.0642, over 7381.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3067, pruned_loss=0.06815, over 1424206.49 frames.], batch size: 23, lr: 1.13e-03
+2022-04-28 16:37:46,342 INFO [train.py:763] (0/8) Epoch 5, batch 3800, loss[loss=0.1955, simple_loss=0.2761, pruned_loss=0.05743, over 7234.00 frames.], tot_loss[loss=0.221, simple_loss=0.3059, pruned_loss=0.06803, over 1421653.35 frames.], batch size: 20, lr: 1.13e-03
+2022-04-28 16:38:51,774 INFO [train.py:763] (0/8) Epoch 5, batch 3850, loss[loss=0.1875, simple_loss=0.2759, pruned_loss=0.04949, over 7443.00 frames.], tot_loss[loss=0.2218, simple_loss=0.307, pruned_loss=0.06829, over 1421972.13 frames.], batch size: 20, lr: 1.13e-03
+2022-04-28 16:39:57,104 INFO [train.py:763] (0/8) Epoch 5, batch 3900, loss[loss=0.1817, simple_loss=0.2739, pruned_loss=0.04479, over 7398.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3074, pruned_loss=0.06853, over 1426699.31 frames.], batch size: 18, lr: 1.13e-03
+2022-04-28 16:41:04,090 INFO [train.py:763] (0/8) Epoch 5, batch 3950, loss[loss=0.2365, simple_loss=0.3228, pruned_loss=0.0751, over 7308.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3062, pruned_loss=0.06796, over 1425589.12 frames.], batch size: 24, lr: 1.12e-03
+2022-04-28 16:42:10,961 INFO [train.py:763] (0/8) Epoch 5, batch 4000, loss[loss=0.2636, simple_loss=0.3462, pruned_loss=0.09052, over 7205.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3064, pruned_loss=0.06769, over 1427331.74 frames.], batch size: 23, lr: 1.12e-03
+2022-04-28 16:43:18,294 INFO [train.py:763] (0/8) Epoch 5, batch 4050, loss[loss=0.2608, simple_loss=0.3483, pruned_loss=0.08665, over 7321.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3057, pruned_loss=0.06709, over 1427745.03 frames.], batch size: 24, lr: 1.12e-03
+2022-04-28 16:44:25,539 INFO [train.py:763] (0/8) Epoch 5, batch 4100, loss[loss=0.198, simple_loss=0.2889, pruned_loss=0.05362, over 7395.00 frames.], tot_loss[loss=0.2195, simple_loss=0.305, pruned_loss=0.06705, over 1428048.50 frames.], batch size: 18, lr: 1.12e-03
+2022-04-28 16:45:32,420 INFO [train.py:763] (0/8) Epoch 5, batch 4150, loss[loss=0.2472, simple_loss=0.3295, pruned_loss=0.08248, over 6673.00 frames.], tot_loss[loss=0.2189, simple_loss=0.3039, pruned_loss=0.06693, over 1427316.45 frames.], batch size: 31, lr: 1.12e-03
+2022-04-28 16:46:39,137 INFO [train.py:763] (0/8) Epoch 5, batch 4200, loss[loss=0.2376, simple_loss=0.3311, pruned_loss=0.07206, over 7119.00 frames.], tot_loss[loss=0.2177, simple_loss=0.303, pruned_loss=0.06619, over 1428946.38 frames.], batch size: 21, lr: 1.12e-03
+2022-04-28 16:47:45,476 INFO [train.py:763] (0/8) Epoch 5, batch 4250, loss[loss=0.2178, simple_loss=0.3089, pruned_loss=0.06334, over 7379.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3028, pruned_loss=0.06572, over 1429843.68 frames.], batch size: 23, lr: 1.12e-03
+2022-04-28 16:48:52,200 INFO [train.py:763] (0/8) Epoch 5, batch 4300, loss[loss=0.2167, simple_loss=0.301, pruned_loss=0.06626, over 7065.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3035, pruned_loss=0.06669, over 1424751.01 frames.], batch size: 18, lr: 1.12e-03
+2022-04-28 16:49:59,892 INFO [train.py:763] (0/8) Epoch 5, batch 4350, loss[loss=0.2458, simple_loss=0.3299, pruned_loss=0.08088, over 7239.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3031, pruned_loss=0.06663, over 1424513.78 frames.], batch size: 21, lr: 1.12e-03
+2022-04-28 16:51:07,559 INFO [train.py:763] (0/8) Epoch 5, batch 4400, loss[loss=0.2108, simple_loss=0.3046, pruned_loss=0.05844, over 7431.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3029, pruned_loss=0.06674, over 1423475.60 frames.], batch size: 20, lr: 1.12e-03
+2022-04-28 16:52:13,254 INFO [train.py:763] (0/8) Epoch 5, batch 4450, loss[loss=0.2059, simple_loss=0.2701, pruned_loss=0.07086, over 7275.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3039, pruned_loss=0.06768, over 1409547.82 frames.], batch size: 17, lr: 1.11e-03
+2022-04-28 16:53:19,254 INFO [train.py:763] (0/8) Epoch 5, batch 4500, loss[loss=0.2238, simple_loss=0.3026, pruned_loss=0.07252, over 7231.00 frames.], tot_loss[loss=0.2182, simple_loss=0.302, pruned_loss=0.06715, over 1408710.88 frames.], batch size: 20, lr: 1.11e-03
+2022-04-28 16:54:23,907 INFO [train.py:763] (0/8) Epoch 5, batch 4550, loss[loss=0.2877, simple_loss=0.3677, pruned_loss=0.1039, over 5076.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3051, pruned_loss=0.07018, over 1358931.15 frames.], batch size: 52, lr: 1.11e-03
+2022-04-28 16:55:12,698 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-5.pt
+2022-04-28 16:55:51,900 INFO [train.py:763] (0/8) Epoch 6, batch 0, loss[loss=0.2296, simple_loss=0.3064, pruned_loss=0.07645, over 7407.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3064, pruned_loss=0.07645, over 7407.00 frames.], batch size: 18, lr: 1.07e-03
+2022-04-28 16:56:58,098 INFO [train.py:763] (0/8) Epoch 6, batch 50, loss[loss=0.1848, simple_loss=0.2727, pruned_loss=0.04847, over 7406.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3017, pruned_loss=0.06445, over 322011.22 frames.], batch size: 18, lr: 1.07e-03
+2022-04-28 16:58:04,031 INFO [train.py:763] (0/8) Epoch 6, batch 100, loss[loss=0.219, simple_loss=0.3024, pruned_loss=0.06779, over 7153.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3005, pruned_loss=0.0632, over 565640.50 frames.], batch size: 19, lr: 1.06e-03
+2022-04-28 16:59:09,773 INFO [train.py:763] (0/8) Epoch 6, batch 150, loss[loss=0.2188, simple_loss=0.3102, pruned_loss=0.06368, over 7158.00 frames.], tot_loss[loss=0.217, simple_loss=0.3036, pruned_loss=0.06519, over 755063.52 frames.], batch size: 19, lr: 1.06e-03
+2022-04-28 17:00:15,503 INFO [train.py:763] (0/8) Epoch 6, batch 200, loss[loss=0.1942, simple_loss=0.284, pruned_loss=0.05219, over 7386.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3031, pruned_loss=0.06452, over 905418.96 frames.], batch size: 23, lr: 1.06e-03
+2022-04-28 17:01:29,837 INFO [train.py:763] (0/8) Epoch 6, batch 250, loss[loss=0.2565, simple_loss=0.3362, pruned_loss=0.08839, over 7149.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3035, pruned_loss=0.06449, over 1020114.07 frames.], batch size: 20, lr: 1.06e-03
+2022-04-28 17:02:45,518 INFO [train.py:763] (0/8) Epoch 6, batch 300, loss[loss=0.1976, simple_loss=0.2774, pruned_loss=0.05892, over 6829.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3044, pruned_loss=0.06511, over 1106611.16 frames.], batch size: 15, lr: 1.06e-03
+2022-04-28 17:03:59,809 INFO [train.py:763] (0/8) Epoch 6, batch 350, loss[loss=0.2154, simple_loss=0.3084, pruned_loss=0.0612, over 7118.00 frames.], tot_loss[loss=0.2165, simple_loss=0.304, pruned_loss=0.06446, over 1177548.92 frames.], batch size: 21, lr: 1.06e-03
+2022-04-28 17:05:05,102 INFO [train.py:763] (0/8) Epoch 6, batch 400, loss[loss=0.1884, simple_loss=0.2764, pruned_loss=0.05016, over 7156.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3048, pruned_loss=0.06489, over 1230399.02 frames.], batch size: 18, lr: 1.06e-03
+2022-04-28 17:06:20,543 INFO [train.py:763] (0/8) Epoch 6, batch 450, loss[loss=0.1561, simple_loss=0.2491, pruned_loss=0.03156, over 7357.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3043, pruned_loss=0.06454, over 1275737.21 frames.], batch size: 19, lr: 1.06e-03
+2022-04-28 17:07:44,120 INFO [train.py:763] (0/8) Epoch 6, batch 500, loss[loss=0.2457, simple_loss=0.3272, pruned_loss=0.08204, over 6476.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3041, pruned_loss=0.06472, over 1305814.25 frames.], batch size: 38, lr: 1.06e-03
+2022-04-28 17:08:59,117 INFO [train.py:763] (0/8) Epoch 6, batch 550, loss[loss=0.2294, simple_loss=0.3165, pruned_loss=0.07117, over 7116.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3038, pruned_loss=0.0649, over 1330668.92 frames.], batch size: 21, lr: 1.06e-03
+2022-04-28 17:10:13,650 INFO [train.py:763] (0/8) Epoch 6, batch 600, loss[loss=0.2012, simple_loss=0.2976, pruned_loss=0.05244, over 7134.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3054, pruned_loss=0.06541, over 1349425.56 frames.], batch size: 28, lr: 1.06e-03
+2022-04-28 17:11:19,533 INFO [train.py:763] (0/8) Epoch 6, batch 650, loss[loss=0.2379, simple_loss=0.3259, pruned_loss=0.07494, over 5157.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3046, pruned_loss=0.06498, over 1364577.37 frames.], batch size: 52, lr: 1.05e-03
+2022-04-28 17:12:25,181 INFO [train.py:763] (0/8) Epoch 6, batch 700, loss[loss=0.1987, simple_loss=0.2896, pruned_loss=0.05388, over 7155.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3028, pruned_loss=0.06424, over 1378558.71 frames.], batch size: 18, lr: 1.05e-03
+2022-04-28 17:13:31,502 INFO [train.py:763] (0/8) Epoch 6, batch 750, loss[loss=0.2214, simple_loss=0.3082, pruned_loss=0.06729, over 6792.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3024, pruned_loss=0.06407, over 1391900.98 frames.], batch size: 31, lr: 1.05e-03
+2022-04-28 17:14:37,101 INFO [train.py:763] (0/8) Epoch 6, batch 800, loss[loss=0.2034, simple_loss=0.2952, pruned_loss=0.05585, over 7316.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3023, pruned_loss=0.06453, over 1391981.75 frames.], batch size: 20, lr: 1.05e-03
+2022-04-28 17:15:43,536 INFO [train.py:763] (0/8) Epoch 6, batch 850, loss[loss=0.2313, simple_loss=0.3192, pruned_loss=0.07172, over 7290.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3017, pruned_loss=0.06375, over 1398310.21 frames.], batch size: 24, lr: 1.05e-03
+2022-04-28 17:16:48,960 INFO [train.py:763] (0/8) Epoch 6, batch 900, loss[loss=0.2677, simple_loss=0.3556, pruned_loss=0.08986, over 7378.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3022, pruned_loss=0.06411, over 1404159.82 frames.], batch size: 23, lr: 1.05e-03
+2022-04-28 17:17:54,054 INFO [train.py:763] (0/8) Epoch 6, batch 950, loss[loss=0.2853, simple_loss=0.3685, pruned_loss=0.1011, over 7378.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3041, pruned_loss=0.06532, over 1408256.82 frames.], batch size: 23, lr: 1.05e-03
+2022-04-28 17:18:59,566 INFO [train.py:763] (0/8) Epoch 6, batch 1000, loss[loss=0.2044, simple_loss=0.2964, pruned_loss=0.05622, over 7371.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3034, pruned_loss=0.06506, over 1408893.69 frames.], batch size: 23, lr: 1.05e-03
+2022-04-28 17:20:06,065 INFO [train.py:763] (0/8) Epoch 6, batch 1050, loss[loss=0.2439, simple_loss=0.3228, pruned_loss=0.08253, over 7157.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3029, pruned_loss=0.06449, over 1415855.76 frames.], batch size: 19, lr: 1.05e-03
+2022-04-28 17:21:12,161 INFO [train.py:763] (0/8) Epoch 6, batch 1100, loss[loss=0.2306, simple_loss=0.3219, pruned_loss=0.06959, over 7301.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3028, pruned_loss=0.06451, over 1419512.31 frames.], batch size: 25, lr: 1.05e-03
+2022-04-28 17:22:18,730 INFO [train.py:763] (0/8) Epoch 6, batch 1150, loss[loss=0.1867, simple_loss=0.2813, pruned_loss=0.04607, over 7140.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3028, pruned_loss=0.06423, over 1417617.72 frames.], batch size: 17, lr: 1.05e-03
+2022-04-28 17:23:26,119 INFO [train.py:763] (0/8) Epoch 6, batch 1200, loss[loss=0.1812, simple_loss=0.2808, pruned_loss=0.04079, over 6844.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3032, pruned_loss=0.06448, over 1412480.54 frames.], batch size: 15, lr: 1.04e-03
+2022-04-28 17:24:33,319 INFO [train.py:763] (0/8) Epoch 6, batch 1250, loss[loss=0.1971, simple_loss=0.2906, pruned_loss=0.0518, over 7230.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3032, pruned_loss=0.06465, over 1413915.14 frames.], batch size: 20, lr: 1.04e-03
+2022-04-28 17:25:39,232 INFO [train.py:763] (0/8) Epoch 6, batch 1300, loss[loss=0.2252, simple_loss=0.3016, pruned_loss=0.07441, over 7274.00 frames.], tot_loss[loss=0.2161, simple_loss=0.303, pruned_loss=0.06459, over 1415265.68 frames.], batch size: 17, lr: 1.04e-03
+2022-04-28 17:26:44,447 INFO [train.py:763] (0/8) Epoch 6, batch 1350, loss[loss=0.2096, simple_loss=0.3099, pruned_loss=0.05467, over 7431.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3032, pruned_loss=0.06411, over 1420904.05 frames.], batch size: 21, lr: 1.04e-03
+2022-04-28 17:27:49,622 INFO [train.py:763] (0/8) Epoch 6, batch 1400, loss[loss=0.1884, simple_loss=0.2818, pruned_loss=0.04753, over 7168.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3039, pruned_loss=0.06427, over 1419321.92 frames.], batch size: 19, lr: 1.04e-03
+2022-04-28 17:28:55,367 INFO [train.py:763] (0/8) Epoch 6, batch 1450, loss[loss=0.2301, simple_loss=0.3182, pruned_loss=0.07096, over 6818.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3034, pruned_loss=0.06407, over 1418630.83 frames.], batch size: 31, lr: 1.04e-03
+2022-04-28 17:30:00,752 INFO [train.py:763] (0/8) Epoch 6, batch 1500, loss[loss=0.1878, simple_loss=0.2774, pruned_loss=0.04913, over 7413.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3023, pruned_loss=0.06304, over 1422605.27 frames.], batch size: 21, lr: 1.04e-03
+2022-04-28 17:31:05,973 INFO [train.py:763] (0/8) Epoch 6, batch 1550, loss[loss=0.2248, simple_loss=0.3062, pruned_loss=0.07171, over 7156.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3023, pruned_loss=0.06356, over 1416614.61 frames.], batch size: 26, lr: 1.04e-03
+2022-04-28 17:32:11,543 INFO [train.py:763] (0/8) Epoch 6, batch 1600, loss[loss=0.2033, simple_loss=0.3023, pruned_loss=0.0522, over 7117.00 frames.], tot_loss[loss=0.2154, simple_loss=0.303, pruned_loss=0.0639, over 1422922.81 frames.], batch size: 21, lr: 1.04e-03
+2022-04-28 17:33:16,941 INFO [train.py:763] (0/8) Epoch 6, batch 1650, loss[loss=0.2052, simple_loss=0.2927, pruned_loss=0.05887, over 7066.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3021, pruned_loss=0.06427, over 1417649.83 frames.], batch size: 18, lr: 1.04e-03
+2022-04-28 17:34:24,088 INFO [train.py:763] (0/8) Epoch 6, batch 1700, loss[loss=0.2176, simple_loss=0.3064, pruned_loss=0.06437, over 7216.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3017, pruned_loss=0.06428, over 1416613.31 frames.], batch size: 22, lr: 1.04e-03
+2022-04-28 17:35:30,124 INFO [train.py:763] (0/8) Epoch 6, batch 1750, loss[loss=0.2015, simple_loss=0.2989, pruned_loss=0.05206, over 7340.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3016, pruned_loss=0.06409, over 1411891.85 frames.], batch size: 22, lr: 1.04e-03
+2022-04-28 17:36:35,268 INFO [train.py:763] (0/8) Epoch 6, batch 1800, loss[loss=0.2363, simple_loss=0.3264, pruned_loss=0.0731, over 7282.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3037, pruned_loss=0.06479, over 1414498.95 frames.], batch size: 25, lr: 1.03e-03
+2022-04-28 17:37:41,015 INFO [train.py:763] (0/8) Epoch 6, batch 1850, loss[loss=0.2082, simple_loss=0.2882, pruned_loss=0.06412, over 7015.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3035, pruned_loss=0.06496, over 1416256.81 frames.], batch size: 16, lr: 1.03e-03
+2022-04-28 17:38:46,207 INFO [train.py:763] (0/8) Epoch 6, batch 1900, loss[loss=0.1955, simple_loss=0.2821, pruned_loss=0.05449, over 7064.00 frames.], tot_loss[loss=0.2161, simple_loss=0.303, pruned_loss=0.06456, over 1413326.70 frames.], batch size: 18, lr: 1.03e-03
+2022-04-28 17:39:52,671 INFO [train.py:763] (0/8) Epoch 6, batch 1950, loss[loss=0.2332, simple_loss=0.3144, pruned_loss=0.07603, over 7268.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3024, pruned_loss=0.06435, over 1417746.95 frames.], batch size: 18, lr: 1.03e-03
+2022-04-28 17:40:59,224 INFO [train.py:763] (0/8) Epoch 6, batch 2000, loss[loss=0.2438, simple_loss=0.3372, pruned_loss=0.07525, over 7282.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3021, pruned_loss=0.06424, over 1418173.57 frames.], batch size: 25, lr: 1.03e-03
+2022-04-28 17:42:06,059 INFO [train.py:763] (0/8) Epoch 6, batch 2050, loss[loss=0.2031, simple_loss=0.3004, pruned_loss=0.05287, over 7323.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3031, pruned_loss=0.065, over 1414445.09 frames.], batch size: 24, lr: 1.03e-03
+2022-04-28 17:43:12,596 INFO [train.py:763] (0/8) Epoch 6, batch 2100, loss[loss=0.163, simple_loss=0.2462, pruned_loss=0.03994, over 6994.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3021, pruned_loss=0.06437, over 1418088.97 frames.], batch size: 16, lr: 1.03e-03
+2022-04-28 17:44:19,364 INFO [train.py:763] (0/8) Epoch 6, batch 2150, loss[loss=0.235, simple_loss=0.3235, pruned_loss=0.07322, over 7418.00 frames.], tot_loss[loss=0.214, simple_loss=0.3013, pruned_loss=0.0634, over 1424091.21 frames.], batch size: 21, lr: 1.03e-03
+2022-04-28 17:45:25,700 INFO [train.py:763] (0/8) Epoch 6, batch 2200, loss[loss=0.1819, simple_loss=0.2724, pruned_loss=0.04572, over 7124.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3016, pruned_loss=0.06414, over 1422055.84 frames.], batch size: 17, lr: 1.03e-03
+2022-04-28 17:46:32,102 INFO [train.py:763] (0/8) Epoch 6, batch 2250, loss[loss=0.2145, simple_loss=0.2959, pruned_loss=0.0666, over 7294.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3021, pruned_loss=0.06456, over 1416802.19 frames.], batch size: 17, lr: 1.03e-03
+2022-04-28 17:47:38,690 INFO [train.py:763] (0/8) Epoch 6, batch 2300, loss[loss=0.2168, simple_loss=0.3101, pruned_loss=0.0618, over 7211.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3028, pruned_loss=0.06494, over 1420114.14 frames.], batch size: 23, lr: 1.03e-03
+2022-04-28 17:48:44,947 INFO [train.py:763] (0/8) Epoch 6, batch 2350, loss[loss=0.2103, simple_loss=0.3037, pruned_loss=0.05848, over 7414.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3025, pruned_loss=0.06461, over 1417742.20 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 17:49:50,892 INFO [train.py:763] (0/8) Epoch 6, batch 2400, loss[loss=0.1669, simple_loss=0.2514, pruned_loss=0.04119, over 7289.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3022, pruned_loss=0.0643, over 1421444.98 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:50:56,973 INFO [train.py:763] (0/8) Epoch 6, batch 2450, loss[loss=0.2342, simple_loss=0.3198, pruned_loss=0.07427, over 7421.00 frames.], tot_loss[loss=0.217, simple_loss=0.3036, pruned_loss=0.06517, over 1416745.16 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 17:52:02,805 INFO [train.py:763] (0/8) Epoch 6, batch 2500, loss[loss=0.2228, simple_loss=0.3047, pruned_loss=0.07046, over 7318.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3039, pruned_loss=0.0653, over 1416301.05 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 17:53:08,646 INFO [train.py:763] (0/8) Epoch 6, batch 2550, loss[loss=0.2435, simple_loss=0.3242, pruned_loss=0.0814, over 7427.00 frames.], tot_loss[loss=0.217, simple_loss=0.304, pruned_loss=0.06498, over 1422885.73 frames.], batch size: 20, lr: 1.02e-03
+2022-04-28 17:54:14,772 INFO [train.py:763] (0/8) Epoch 6, batch 2600, loss[loss=0.1845, simple_loss=0.2739, pruned_loss=0.04755, over 7171.00 frames.], tot_loss[loss=0.2168, simple_loss=0.3035, pruned_loss=0.06509, over 1417142.78 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:55:21,049 INFO [train.py:763] (0/8) Epoch 6, batch 2650, loss[loss=0.1886, simple_loss=0.2813, pruned_loss=0.04794, over 7154.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3028, pruned_loss=0.0648, over 1416844.69 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:56:26,535 INFO [train.py:763] (0/8) Epoch 6, batch 2700, loss[loss=0.2027, simple_loss=0.2704, pruned_loss=0.06755, over 7202.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3025, pruned_loss=0.06434, over 1418783.90 frames.], batch size: 16, lr: 1.02e-03
+2022-04-28 17:57:32,632 INFO [train.py:763] (0/8) Epoch 6, batch 2750, loss[loss=0.1674, simple_loss=0.2511, pruned_loss=0.0418, over 7417.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3029, pruned_loss=0.06428, over 1419425.40 frames.], batch size: 18, lr: 1.02e-03
+2022-04-28 17:58:39,125 INFO [train.py:763] (0/8) Epoch 6, batch 2800, loss[loss=0.1898, simple_loss=0.2694, pruned_loss=0.05509, over 7013.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3029, pruned_loss=0.06494, over 1417308.38 frames.], batch size: 16, lr: 1.02e-03
+2022-04-28 17:59:46,052 INFO [train.py:763] (0/8) Epoch 6, batch 2850, loss[loss=0.1874, simple_loss=0.278, pruned_loss=0.04837, over 7323.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3006, pruned_loss=0.06355, over 1422106.58 frames.], batch size: 21, lr: 1.02e-03
+2022-04-28 18:00:52,217 INFO [train.py:763] (0/8) Epoch 6, batch 2900, loss[loss=0.248, simple_loss=0.3242, pruned_loss=0.08593, over 5558.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3004, pruned_loss=0.06348, over 1424008.98 frames.], batch size: 53, lr: 1.02e-03
+2022-04-28 18:01:57,566 INFO [train.py:763] (0/8) Epoch 6, batch 2950, loss[loss=0.2239, simple_loss=0.3123, pruned_loss=0.06778, over 7297.00 frames.], tot_loss[loss=0.2138, simple_loss=0.301, pruned_loss=0.06334, over 1424060.73 frames.], batch size: 25, lr: 1.01e-03
+2022-04-28 18:03:03,525 INFO [train.py:763] (0/8) Epoch 6, batch 3000, loss[loss=0.231, simple_loss=0.3113, pruned_loss=0.0753, over 7186.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3011, pruned_loss=0.06303, over 1425529.71 frames.], batch size: 26, lr: 1.01e-03
+2022-04-28 18:03:03,527 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-28 18:03:18,818 INFO [train.py:792] (0/8) Epoch 6, validation: loss=0.1749, simple_loss=0.2793, pruned_loss=0.03525, over 698248.00 frames.
+2022-04-28 18:04:24,352 INFO [train.py:763] (0/8) Epoch 6, batch 3050, loss[loss=0.2224, simple_loss=0.3108, pruned_loss=0.06701, over 7182.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3017, pruned_loss=0.06343, over 1425915.72 frames.], batch size: 26, lr: 1.01e-03
+2022-04-28 18:05:30,262 INFO [train.py:763] (0/8) Epoch 6, batch 3100, loss[loss=0.222, simple_loss=0.3029, pruned_loss=0.07049, over 7122.00 frames.], tot_loss[loss=0.2151, simple_loss=0.302, pruned_loss=0.06408, over 1423573.41 frames.], batch size: 26, lr: 1.01e-03
+2022-04-28 18:06:36,921 INFO [train.py:763] (0/8) Epoch 6, batch 3150, loss[loss=0.2556, simple_loss=0.3498, pruned_loss=0.08073, over 7101.00 frames.], tot_loss[loss=0.2144, simple_loss=0.302, pruned_loss=0.06339, over 1427182.36 frames.], batch size: 28, lr: 1.01e-03
+2022-04-28 18:07:42,783 INFO [train.py:763] (0/8) Epoch 6, batch 3200, loss[loss=0.2249, simple_loss=0.3071, pruned_loss=0.07133, over 7329.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3026, pruned_loss=0.06413, over 1423710.52 frames.], batch size: 22, lr: 1.01e-03
+2022-04-28 18:08:48,612 INFO [train.py:763] (0/8) Epoch 6, batch 3250, loss[loss=0.2307, simple_loss=0.3364, pruned_loss=0.06253, over 7056.00 frames.], tot_loss[loss=0.2147, simple_loss=0.302, pruned_loss=0.06374, over 1422693.63 frames.], batch size: 28, lr: 1.01e-03
+2022-04-28 18:09:54,866 INFO [train.py:763] (0/8) Epoch 6, batch 3300, loss[loss=0.2385, simple_loss=0.3348, pruned_loss=0.07113, over 7144.00 frames.], tot_loss[loss=0.215, simple_loss=0.3024, pruned_loss=0.06381, over 1417943.91 frames.], batch size: 20, lr: 1.01e-03
+2022-04-28 18:11:00,645 INFO [train.py:763] (0/8) Epoch 6, batch 3350, loss[loss=0.1804, simple_loss=0.2817, pruned_loss=0.03957, over 7162.00 frames.], tot_loss[loss=0.2141, simple_loss=0.3017, pruned_loss=0.0633, over 1418623.25 frames.], batch size: 19, lr: 1.01e-03
+2022-04-28 18:12:05,978 INFO [train.py:763] (0/8) Epoch 6, batch 3400, loss[loss=0.2347, simple_loss=0.3216, pruned_loss=0.07389, over 7115.00 frames.], tot_loss[loss=0.2141, simple_loss=0.302, pruned_loss=0.06315, over 1421607.69 frames.], batch size: 21, lr: 1.01e-03
+2022-04-28 18:13:11,474 INFO [train.py:763] (0/8) Epoch 6, batch 3450, loss[loss=0.2469, simple_loss=0.3341, pruned_loss=0.07979, over 7297.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3024, pruned_loss=0.06307, over 1420031.87 frames.], batch size: 24, lr: 1.01e-03
+2022-04-28 18:14:16,751 INFO [train.py:763] (0/8) Epoch 6, batch 3500, loss[loss=0.2267, simple_loss=0.3218, pruned_loss=0.06578, over 7208.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3027, pruned_loss=0.06294, over 1422619.02 frames.], batch size: 21, lr: 1.01e-03
+2022-04-28 18:15:22,311 INFO [train.py:763] (0/8) Epoch 6, batch 3550, loss[loss=0.2482, simple_loss=0.3332, pruned_loss=0.08156, over 7379.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3019, pruned_loss=0.06283, over 1424959.25 frames.], batch size: 23, lr: 1.01e-03
+2022-04-28 18:16:27,539 INFO [train.py:763] (0/8) Epoch 6, batch 3600, loss[loss=0.1946, simple_loss=0.2866, pruned_loss=0.0513, over 7228.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3021, pruned_loss=0.06271, over 1426464.22 frames.], batch size: 21, lr: 1.00e-03
+2022-04-28 18:17:32,795 INFO [train.py:763] (0/8) Epoch 6, batch 3650, loss[loss=0.2284, simple_loss=0.3175, pruned_loss=0.06963, over 7030.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3013, pruned_loss=0.06227, over 1423844.14 frames.], batch size: 28, lr: 1.00e-03
+2022-04-28 18:18:39,447 INFO [train.py:763] (0/8) Epoch 6, batch 3700, loss[loss=0.1926, simple_loss=0.2818, pruned_loss=0.05169, over 7438.00 frames.], tot_loss[loss=0.2126, simple_loss=0.3006, pruned_loss=0.0623, over 1424532.86 frames.], batch size: 20, lr: 1.00e-03
+2022-04-28 18:19:44,878 INFO [train.py:763] (0/8) Epoch 6, batch 3750, loss[loss=0.2834, simple_loss=0.3495, pruned_loss=0.1087, over 4880.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3015, pruned_loss=0.0631, over 1424399.06 frames.], batch size: 52, lr: 1.00e-03
+2022-04-28 18:20:50,231 INFO [train.py:763] (0/8) Epoch 6, batch 3800, loss[loss=0.2279, simple_loss=0.3085, pruned_loss=0.07361, over 7360.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3017, pruned_loss=0.06281, over 1421839.33 frames.], batch size: 19, lr: 1.00e-03
+2022-04-28 18:21:56,441 INFO [train.py:763] (0/8) Epoch 6, batch 3850, loss[loss=0.1715, simple_loss=0.2574, pruned_loss=0.04278, over 7144.00 frames.], tot_loss[loss=0.2132, simple_loss=0.301, pruned_loss=0.06276, over 1424559.25 frames.], batch size: 17, lr: 1.00e-03
+2022-04-28 18:23:02,747 INFO [train.py:763] (0/8) Epoch 6, batch 3900, loss[loss=0.2005, simple_loss=0.2935, pruned_loss=0.05373, over 7164.00 frames.], tot_loss[loss=0.2126, simple_loss=0.3004, pruned_loss=0.06242, over 1424957.78 frames.], batch size: 18, lr: 1.00e-03
+2022-04-28 18:24:08,629 INFO [train.py:763] (0/8) Epoch 6, batch 3950, loss[loss=0.2555, simple_loss=0.3441, pruned_loss=0.08339, over 7350.00 frames.], tot_loss[loss=0.2127, simple_loss=0.3006, pruned_loss=0.06242, over 1426569.98 frames.], batch size: 22, lr: 9.99e-04
+2022-04-28 18:25:14,080 INFO [train.py:763] (0/8) Epoch 6, batch 4000, loss[loss=0.2509, simple_loss=0.3283, pruned_loss=0.08672, over 6739.00 frames.], tot_loss[loss=0.2123, simple_loss=0.3003, pruned_loss=0.06217, over 1430961.43 frames.], batch size: 31, lr: 9.98e-04
+2022-04-28 18:26:19,666 INFO [train.py:763] (0/8) Epoch 6, batch 4050, loss[loss=0.179, simple_loss=0.27, pruned_loss=0.04404, over 7159.00 frames.], tot_loss[loss=0.2112, simple_loss=0.299, pruned_loss=0.0617, over 1428657.79 frames.], batch size: 18, lr: 9.98e-04
+2022-04-28 18:27:25,502 INFO [train.py:763] (0/8) Epoch 6, batch 4100, loss[loss=0.2354, simple_loss=0.3261, pruned_loss=0.07237, over 7443.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2997, pruned_loss=0.06264, over 1424476.39 frames.], batch size: 22, lr: 9.97e-04
+2022-04-28 18:28:32,072 INFO [train.py:763] (0/8) Epoch 6, batch 4150, loss[loss=0.2518, simple_loss=0.3468, pruned_loss=0.07844, over 7202.00 frames.], tot_loss[loss=0.2119, simple_loss=0.2995, pruned_loss=0.0622, over 1425611.96 frames.], batch size: 23, lr: 9.96e-04
+2022-04-28 18:29:37,834 INFO [train.py:763] (0/8) Epoch 6, batch 4200, loss[loss=0.171, simple_loss=0.2574, pruned_loss=0.04232, over 7285.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2986, pruned_loss=0.0618, over 1427828.43 frames.], batch size: 17, lr: 9.95e-04
+2022-04-28 18:30:43,254 INFO [train.py:763] (0/8) Epoch 6, batch 4250, loss[loss=0.2069, simple_loss=0.2959, pruned_loss=0.05896, over 7430.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2999, pruned_loss=0.06252, over 1422086.00 frames.], batch size: 20, lr: 9.95e-04
+2022-04-28 18:31:48,736 INFO [train.py:763] (0/8) Epoch 6, batch 4300, loss[loss=0.2088, simple_loss=0.3116, pruned_loss=0.05297, over 7229.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3014, pruned_loss=0.06268, over 1416247.33 frames.], batch size: 20, lr: 9.94e-04
+2022-04-28 18:32:54,889 INFO [train.py:763] (0/8) Epoch 6, batch 4350, loss[loss=0.2289, simple_loss=0.314, pruned_loss=0.07187, over 6516.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3016, pruned_loss=0.06246, over 1410386.88 frames.], batch size: 38, lr: 9.93e-04
+2022-04-28 18:34:00,601 INFO [train.py:763] (0/8) Epoch 6, batch 4400, loss[loss=0.2415, simple_loss=0.338, pruned_loss=0.07249, over 6826.00 frames.], tot_loss[loss=0.2131, simple_loss=0.3013, pruned_loss=0.0624, over 1411374.76 frames.], batch size: 31, lr: 9.92e-04
+2022-04-28 18:35:07,316 INFO [train.py:763] (0/8) Epoch 6, batch 4450, loss[loss=0.2473, simple_loss=0.341, pruned_loss=0.07676, over 7204.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3019, pruned_loss=0.06296, over 1406743.87 frames.], batch size: 22, lr: 9.92e-04
+2022-04-28 18:35:34,873 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-32000.pt
+2022-04-28 18:36:23,324 INFO [train.py:763] (0/8) Epoch 6, batch 4500, loss[loss=0.2588, simple_loss=0.3406, pruned_loss=0.08846, over 7202.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3032, pruned_loss=0.06408, over 1404259.15 frames.], batch size: 22, lr: 9.91e-04
+2022-04-28 18:37:28,295 INFO [train.py:763] (0/8) Epoch 6, batch 4550, loss[loss=0.3041, simple_loss=0.3753, pruned_loss=0.1164, over 4717.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3054, pruned_loss=0.06505, over 1389573.89 frames.], batch size: 53, lr: 9.90e-04
+2022-04-28 18:38:18,548 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-6.pt
+2022-04-28 18:38:57,449 INFO [train.py:763] (0/8) Epoch 7, batch 0, loss[loss=0.2065, simple_loss=0.2997, pruned_loss=0.05666, over 7331.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2997, pruned_loss=0.05666, over 7331.00 frames.], batch size: 22, lr: 9.49e-04
+2022-04-28 18:40:02,645 INFO [train.py:763] (0/8) Epoch 7, batch 50, loss[loss=0.1771, simple_loss=0.2672, pruned_loss=0.04349, over 7147.00 frames.], tot_loss[loss=0.2118, simple_loss=0.3016, pruned_loss=0.06102, over 320774.19 frames.], batch size: 17, lr: 9.48e-04
+2022-04-28 18:41:07,855 INFO [train.py:763] (0/8) Epoch 7, batch 100, loss[loss=0.2432, simple_loss=0.3233, pruned_loss=0.08151, over 7278.00 frames.], tot_loss[loss=0.2087, simple_loss=0.299, pruned_loss=0.05921, over 568866.91 frames.], batch size: 25, lr: 9.48e-04
+2022-04-28 18:42:13,316 INFO [train.py:763] (0/8) Epoch 7, batch 150, loss[loss=0.196, simple_loss=0.2794, pruned_loss=0.05633, over 7116.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2976, pruned_loss=0.05888, over 758204.88 frames.], batch size: 21, lr: 9.47e-04
+2022-04-28 18:43:19,115 INFO [train.py:763] (0/8) Epoch 7, batch 200, loss[loss=0.2294, simple_loss=0.3121, pruned_loss=0.07332, over 7198.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2993, pruned_loss=0.0599, over 907247.38 frames.], batch size: 22, lr: 9.46e-04
+2022-04-28 18:44:24,618 INFO [train.py:763] (0/8) Epoch 7, batch 250, loss[loss=0.2158, simple_loss=0.3118, pruned_loss=0.0599, over 7114.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2999, pruned_loss=0.05992, over 1020715.68 frames.], batch size: 21, lr: 9.46e-04
+2022-04-28 18:45:29,828 INFO [train.py:763] (0/8) Epoch 7, batch 300, loss[loss=0.1999, simple_loss=0.2837, pruned_loss=0.05808, over 7071.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3001, pruned_loss=0.06009, over 1106000.92 frames.], batch size: 18, lr: 9.45e-04
+2022-04-28 18:46:35,552 INFO [train.py:763] (0/8) Epoch 7, batch 350, loss[loss=0.2346, simple_loss=0.3299, pruned_loss=0.06967, over 7115.00 frames.], tot_loss[loss=0.21, simple_loss=0.2997, pruned_loss=0.06013, over 1177735.17 frames.], batch size: 21, lr: 9.44e-04
+2022-04-28 18:47:40,828 INFO [train.py:763] (0/8) Epoch 7, batch 400, loss[loss=0.2626, simple_loss=0.3317, pruned_loss=0.09669, over 4949.00 frames.], tot_loss[loss=0.211, simple_loss=0.3003, pruned_loss=0.06088, over 1231673.76 frames.], batch size: 52, lr: 9.43e-04
+2022-04-28 18:48:46,401 INFO [train.py:763] (0/8) Epoch 7, batch 450, loss[loss=0.2128, simple_loss=0.2918, pruned_loss=0.06688, over 6803.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2994, pruned_loss=0.06062, over 1272379.34 frames.], batch size: 15, lr: 9.43e-04
+2022-04-28 18:49:51,808 INFO [train.py:763] (0/8) Epoch 7, batch 500, loss[loss=0.2048, simple_loss=0.3003, pruned_loss=0.05461, over 7188.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2984, pruned_loss=0.0607, over 1305553.83 frames.], batch size: 23, lr: 9.42e-04
+2022-04-28 18:50:57,365 INFO [train.py:763] (0/8) Epoch 7, batch 550, loss[loss=0.2158, simple_loss=0.3057, pruned_loss=0.06295, over 7206.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2983, pruned_loss=0.06048, over 1333607.38 frames.], batch size: 23, lr: 9.41e-04
+2022-04-28 18:52:02,636 INFO [train.py:763] (0/8) Epoch 7, batch 600, loss[loss=0.2161, simple_loss=0.3028, pruned_loss=0.06466, over 7213.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2988, pruned_loss=0.06032, over 1353275.37 frames.], batch size: 21, lr: 9.41e-04
+2022-04-28 18:53:08,467 INFO [train.py:763] (0/8) Epoch 7, batch 650, loss[loss=0.2071, simple_loss=0.3002, pruned_loss=0.05695, over 7262.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2985, pruned_loss=0.06019, over 1368517.46 frames.], batch size: 19, lr: 9.40e-04
+2022-04-28 18:54:13,822 INFO [train.py:763] (0/8) Epoch 7, batch 700, loss[loss=0.2158, simple_loss=0.2975, pruned_loss=0.06702, over 5140.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2998, pruned_loss=0.06081, over 1376366.56 frames.], batch size: 52, lr: 9.39e-04
+2022-04-28 18:55:19,484 INFO [train.py:763] (0/8) Epoch 7, batch 750, loss[loss=0.1916, simple_loss=0.2806, pruned_loss=0.05133, over 7361.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2988, pruned_loss=0.06044, over 1384515.42 frames.], batch size: 19, lr: 9.39e-04
+2022-04-28 18:56:26,114 INFO [train.py:763] (0/8) Epoch 7, batch 800, loss[loss=0.2007, simple_loss=0.2963, pruned_loss=0.0525, over 6552.00 frames.], tot_loss[loss=0.2113, simple_loss=0.3005, pruned_loss=0.06104, over 1389570.35 frames.], batch size: 38, lr: 9.38e-04
+2022-04-28 18:57:33,288 INFO [train.py:763] (0/8) Epoch 7, batch 850, loss[loss=0.1701, simple_loss=0.2575, pruned_loss=0.04134, over 7412.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2986, pruned_loss=0.06015, over 1398543.40 frames.], batch size: 18, lr: 9.37e-04
+2022-04-28 18:58:40,235 INFO [train.py:763] (0/8) Epoch 7, batch 900, loss[loss=0.1979, simple_loss=0.3025, pruned_loss=0.04664, over 6739.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2987, pruned_loss=0.06035, over 1398178.40 frames.], batch size: 31, lr: 9.36e-04
+2022-04-28 18:59:46,950 INFO [train.py:763] (0/8) Epoch 7, batch 950, loss[loss=0.1916, simple_loss=0.2887, pruned_loss=0.04729, over 7239.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2993, pruned_loss=0.06051, over 1404323.51 frames.], batch size: 20, lr: 9.36e-04
+2022-04-28 19:00:52,056 INFO [train.py:763] (0/8) Epoch 7, batch 1000, loss[loss=0.1783, simple_loss=0.2813, pruned_loss=0.03769, over 7229.00 frames.], tot_loss[loss=0.2114, simple_loss=0.3006, pruned_loss=0.06109, over 1408652.09 frames.], batch size: 21, lr: 9.35e-04
+2022-04-28 19:01:58,582 INFO [train.py:763] (0/8) Epoch 7, batch 1050, loss[loss=0.1673, simple_loss=0.2535, pruned_loss=0.04057, over 7144.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3015, pruned_loss=0.06141, over 1406094.45 frames.], batch size: 17, lr: 9.34e-04
+2022-04-28 19:03:05,271 INFO [train.py:763] (0/8) Epoch 7, batch 1100, loss[loss=0.2407, simple_loss=0.327, pruned_loss=0.0772, over 7202.00 frames.], tot_loss[loss=0.2118, simple_loss=0.3004, pruned_loss=0.06156, over 1409613.65 frames.], batch size: 22, lr: 9.34e-04
+2022-04-28 19:04:11,973 INFO [train.py:763] (0/8) Epoch 7, batch 1150, loss[loss=0.2406, simple_loss=0.3094, pruned_loss=0.08588, over 5152.00 frames.], tot_loss[loss=0.2126, simple_loss=0.3013, pruned_loss=0.06199, over 1415700.06 frames.], batch size: 52, lr: 9.33e-04
+2022-04-28 19:05:18,443 INFO [train.py:763] (0/8) Epoch 7, batch 1200, loss[loss=0.1912, simple_loss=0.2998, pruned_loss=0.04131, over 7156.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3005, pruned_loss=0.06133, over 1419766.65 frames.], batch size: 20, lr: 9.32e-04
+2022-04-28 19:06:24,037 INFO [train.py:763] (0/8) Epoch 7, batch 1250, loss[loss=0.1817, simple_loss=0.2791, pruned_loss=0.04214, over 7282.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2994, pruned_loss=0.06113, over 1418991.71 frames.], batch size: 18, lr: 9.32e-04
+2022-04-28 19:07:30,161 INFO [train.py:763] (0/8) Epoch 7, batch 1300, loss[loss=0.1879, simple_loss=0.2841, pruned_loss=0.0459, over 7150.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2994, pruned_loss=0.06104, over 1415802.77 frames.], batch size: 20, lr: 9.31e-04
+2022-04-28 19:08:35,485 INFO [train.py:763] (0/8) Epoch 7, batch 1350, loss[loss=0.1884, simple_loss=0.284, pruned_loss=0.04646, over 7155.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2999, pruned_loss=0.06167, over 1414777.20 frames.], batch size: 19, lr: 9.30e-04
+2022-04-28 19:09:41,366 INFO [train.py:763] (0/8) Epoch 7, batch 1400, loss[loss=0.1833, simple_loss=0.2721, pruned_loss=0.0472, over 7286.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2993, pruned_loss=0.0608, over 1416523.83 frames.], batch size: 18, lr: 9.30e-04
+2022-04-28 19:10:48,195 INFO [train.py:763] (0/8) Epoch 7, batch 1450, loss[loss=0.2033, simple_loss=0.2851, pruned_loss=0.0607, over 7182.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2985, pruned_loss=0.06023, over 1416293.82 frames.], batch size: 18, lr: 9.29e-04
+2022-04-28 19:11:54,403 INFO [train.py:763] (0/8) Epoch 7, batch 1500, loss[loss=0.1888, simple_loss=0.2806, pruned_loss=0.04854, over 7433.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2972, pruned_loss=0.05981, over 1415460.99 frames.], batch size: 18, lr: 9.28e-04
+2022-04-28 19:12:59,482 INFO [train.py:763] (0/8) Epoch 7, batch 1550, loss[loss=0.2045, simple_loss=0.2901, pruned_loss=0.05945, over 7215.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2968, pruned_loss=0.05923, over 1420516.03 frames.], batch size: 22, lr: 9.28e-04
+2022-04-28 19:14:04,518 INFO [train.py:763] (0/8) Epoch 7, batch 1600, loss[loss=0.2333, simple_loss=0.3235, pruned_loss=0.07154, over 6300.00 frames.], tot_loss[loss=0.209, simple_loss=0.2983, pruned_loss=0.0599, over 1421078.89 frames.], batch size: 37, lr: 9.27e-04
+2022-04-28 19:15:09,648 INFO [train.py:763] (0/8) Epoch 7, batch 1650, loss[loss=0.1934, simple_loss=0.2929, pruned_loss=0.04694, over 7286.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2981, pruned_loss=0.05946, over 1419747.46 frames.], batch size: 24, lr: 9.26e-04
+2022-04-28 19:16:15,830 INFO [train.py:763] (0/8) Epoch 7, batch 1700, loss[loss=0.2144, simple_loss=0.3085, pruned_loss=0.06014, over 7323.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2986, pruned_loss=0.0595, over 1419575.93 frames.], batch size: 21, lr: 9.26e-04
+2022-04-28 19:17:22,178 INFO [train.py:763] (0/8) Epoch 7, batch 1750, loss[loss=0.1985, simple_loss=0.2987, pruned_loss=0.04913, over 7340.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2989, pruned_loss=0.06039, over 1420497.62 frames.], batch size: 22, lr: 9.25e-04
+2022-04-28 19:18:45,867 INFO [train.py:763] (0/8) Epoch 7, batch 1800, loss[loss=0.229, simple_loss=0.3176, pruned_loss=0.07021, over 7331.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2979, pruned_loss=0.06035, over 1421744.65 frames.], batch size: 22, lr: 9.24e-04
+2022-04-28 19:19:59,995 INFO [train.py:763] (0/8) Epoch 7, batch 1850, loss[loss=0.2168, simple_loss=0.3117, pruned_loss=0.06097, over 7235.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2991, pruned_loss=0.06074, over 1423215.76 frames.], batch size: 20, lr: 9.24e-04
+2022-04-28 19:21:23,374 INFO [train.py:763] (0/8) Epoch 7, batch 1900, loss[loss=0.2239, simple_loss=0.3094, pruned_loss=0.06926, over 7331.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2984, pruned_loss=0.06056, over 1421488.60 frames.], batch size: 25, lr: 9.23e-04
+2022-04-28 19:22:40,072 INFO [train.py:763] (0/8) Epoch 7, batch 1950, loss[loss=0.194, simple_loss=0.2787, pruned_loss=0.05471, over 7011.00 frames.], tot_loss[loss=0.2092, simple_loss=0.298, pruned_loss=0.06026, over 1426338.43 frames.], batch size: 16, lr: 9.22e-04
+2022-04-28 19:23:47,457 INFO [train.py:763] (0/8) Epoch 7, batch 2000, loss[loss=0.2335, simple_loss=0.325, pruned_loss=0.07099, over 7117.00 frames.], tot_loss[loss=0.21, simple_loss=0.2983, pruned_loss=0.06089, over 1427218.11 frames.], batch size: 21, lr: 9.22e-04
+2022-04-28 19:25:02,873 INFO [train.py:763] (0/8) Epoch 7, batch 2050, loss[loss=0.2187, simple_loss=0.2967, pruned_loss=0.07029, over 4960.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2992, pruned_loss=0.06113, over 1421068.68 frames.], batch size: 52, lr: 9.21e-04
+2022-04-28 19:26:07,942 INFO [train.py:763] (0/8) Epoch 7, batch 2100, loss[loss=0.1839, simple_loss=0.2813, pruned_loss=0.04329, over 7232.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2999, pruned_loss=0.06146, over 1417750.09 frames.], batch size: 20, lr: 9.20e-04
+2022-04-28 19:27:22,252 INFO [train.py:763] (0/8) Epoch 7, batch 2150, loss[loss=0.2383, simple_loss=0.3221, pruned_loss=0.0772, over 7191.00 frames.], tot_loss[loss=0.211, simple_loss=0.2994, pruned_loss=0.06131, over 1419444.56 frames.], batch size: 22, lr: 9.20e-04
+2022-04-28 19:28:27,693 INFO [train.py:763] (0/8) Epoch 7, batch 2200, loss[loss=0.2803, simple_loss=0.3707, pruned_loss=0.09494, over 7296.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2984, pruned_loss=0.0611, over 1417416.95 frames.], batch size: 24, lr: 9.19e-04
+2022-04-28 19:29:32,847 INFO [train.py:763] (0/8) Epoch 7, batch 2250, loss[loss=0.2107, simple_loss=0.3009, pruned_loss=0.06019, over 7184.00 frames.], tot_loss[loss=0.2098, simple_loss=0.298, pruned_loss=0.06079, over 1411893.66 frames.], batch size: 23, lr: 9.18e-04
+2022-04-28 19:30:38,174 INFO [train.py:763] (0/8) Epoch 7, batch 2300, loss[loss=0.1823, simple_loss=0.2699, pruned_loss=0.04732, over 7401.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2975, pruned_loss=0.0601, over 1412147.78 frames.], batch size: 18, lr: 9.18e-04
+2022-04-28 19:31:43,917 INFO [train.py:763] (0/8) Epoch 7, batch 2350, loss[loss=0.1908, simple_loss=0.2684, pruned_loss=0.05662, over 7071.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2976, pruned_loss=0.0596, over 1412095.32 frames.], batch size: 18, lr: 9.17e-04
+2022-04-28 19:32:50,596 INFO [train.py:763] (0/8) Epoch 7, batch 2400, loss[loss=0.1733, simple_loss=0.2724, pruned_loss=0.03709, over 7262.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2978, pruned_loss=0.05987, over 1415836.47 frames.], batch size: 19, lr: 9.16e-04
+2022-04-28 19:33:55,914 INFO [train.py:763] (0/8) Epoch 7, batch 2450, loss[loss=0.2309, simple_loss=0.3197, pruned_loss=0.07103, over 7317.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2979, pruned_loss=0.0599, over 1422472.55 frames.], batch size: 24, lr: 9.16e-04
+2022-04-28 19:35:01,306 INFO [train.py:763] (0/8) Epoch 7, batch 2500, loss[loss=0.2104, simple_loss=0.3111, pruned_loss=0.05484, over 7317.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2983, pruned_loss=0.06041, over 1420222.50 frames.], batch size: 21, lr: 9.15e-04
+2022-04-28 19:36:06,930 INFO [train.py:763] (0/8) Epoch 7, batch 2550, loss[loss=0.2202, simple_loss=0.2985, pruned_loss=0.07099, over 7360.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2984, pruned_loss=0.06052, over 1424592.50 frames.], batch size: 19, lr: 9.14e-04
+2022-04-28 19:37:12,487 INFO [train.py:763] (0/8) Epoch 7, batch 2600, loss[loss=0.1843, simple_loss=0.2662, pruned_loss=0.0512, over 6789.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2977, pruned_loss=0.05989, over 1424921.81 frames.], batch size: 15, lr: 9.14e-04
+2022-04-28 19:38:17,717 INFO [train.py:763] (0/8) Epoch 7, batch 2650, loss[loss=0.1965, simple_loss=0.3007, pruned_loss=0.04616, over 7120.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2975, pruned_loss=0.05948, over 1426161.01 frames.], batch size: 21, lr: 9.13e-04
+2022-04-28 19:39:23,655 INFO [train.py:763] (0/8) Epoch 7, batch 2700, loss[loss=0.1806, simple_loss=0.2646, pruned_loss=0.04831, over 6835.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2968, pruned_loss=0.05897, over 1428413.94 frames.], batch size: 15, lr: 9.12e-04
+2022-04-28 19:40:30,723 INFO [train.py:763] (0/8) Epoch 7, batch 2750, loss[loss=0.1999, simple_loss=0.2862, pruned_loss=0.05682, over 6995.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2962, pruned_loss=0.05869, over 1427693.70 frames.], batch size: 16, lr: 9.12e-04
+2022-04-28 19:41:36,694 INFO [train.py:763] (0/8) Epoch 7, batch 2800, loss[loss=0.2154, simple_loss=0.302, pruned_loss=0.06444, over 7155.00 frames.], tot_loss[loss=0.207, simple_loss=0.2965, pruned_loss=0.05873, over 1428183.49 frames.], batch size: 20, lr: 9.11e-04
+2022-04-28 19:42:43,490 INFO [train.py:763] (0/8) Epoch 7, batch 2850, loss[loss=0.2795, simple_loss=0.37, pruned_loss=0.0945, over 7216.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2969, pruned_loss=0.05873, over 1426401.73 frames.], batch size: 22, lr: 9.11e-04
+2022-04-28 19:43:49,297 INFO [train.py:763] (0/8) Epoch 7, batch 2900, loss[loss=0.1969, simple_loss=0.2768, pruned_loss=0.05853, over 7126.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2985, pruned_loss=0.05903, over 1425811.93 frames.], batch size: 17, lr: 9.10e-04
+2022-04-28 19:44:55,759 INFO [train.py:763] (0/8) Epoch 7, batch 2950, loss[loss=0.201, simple_loss=0.2955, pruned_loss=0.05326, over 7067.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2967, pruned_loss=0.0583, over 1424748.76 frames.], batch size: 18, lr: 9.09e-04
+2022-04-28 19:46:01,163 INFO [train.py:763] (0/8) Epoch 7, batch 3000, loss[loss=0.2896, simple_loss=0.3534, pruned_loss=0.1129, over 5237.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2967, pruned_loss=0.05845, over 1421481.52 frames.], batch size: 52, lr: 9.09e-04
+2022-04-28 19:46:01,165 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-28 19:46:16,423 INFO [train.py:792] (0/8) Epoch 7, validation: loss=0.1713, simple_loss=0.2754, pruned_loss=0.03361, over 698248.00 frames.
+2022-04-28 19:47:23,042 INFO [train.py:763] (0/8) Epoch 7, batch 3050, loss[loss=0.2488, simple_loss=0.3349, pruned_loss=0.0814, over 6687.00 frames.], tot_loss[loss=0.2078, simple_loss=0.297, pruned_loss=0.05934, over 1414031.27 frames.], batch size: 38, lr: 9.08e-04
+2022-04-28 19:48:28,739 INFO [train.py:763] (0/8) Epoch 7, batch 3100, loss[loss=0.2388, simple_loss=0.3067, pruned_loss=0.08548, over 7266.00 frames.], tot_loss[loss=0.208, simple_loss=0.2972, pruned_loss=0.05939, over 1418748.63 frames.], batch size: 19, lr: 9.07e-04
+2022-04-28 19:49:34,318 INFO [train.py:763] (0/8) Epoch 7, batch 3150, loss[loss=0.1718, simple_loss=0.2687, pruned_loss=0.03749, over 7427.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2958, pruned_loss=0.0588, over 1420467.79 frames.], batch size: 20, lr: 9.07e-04
+2022-04-28 19:50:39,923 INFO [train.py:763] (0/8) Epoch 7, batch 3200, loss[loss=0.1693, simple_loss=0.2655, pruned_loss=0.03657, over 7433.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2952, pruned_loss=0.05805, over 1423997.87 frames.], batch size: 20, lr: 9.06e-04
+2022-04-28 19:51:45,171 INFO [train.py:763] (0/8) Epoch 7, batch 3250, loss[loss=0.2147, simple_loss=0.3163, pruned_loss=0.05653, over 7034.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2965, pruned_loss=0.05858, over 1422539.13 frames.], batch size: 28, lr: 9.05e-04
+2022-04-28 19:52:50,679 INFO [train.py:763] (0/8) Epoch 7, batch 3300, loss[loss=0.2181, simple_loss=0.3134, pruned_loss=0.06136, over 6727.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2956, pruned_loss=0.05788, over 1422641.55 frames.], batch size: 31, lr: 9.05e-04
+2022-04-28 19:53:56,162 INFO [train.py:763] (0/8) Epoch 7, batch 3350, loss[loss=0.2215, simple_loss=0.3106, pruned_loss=0.06618, over 7426.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2959, pruned_loss=0.05845, over 1420371.19 frames.], batch size: 20, lr: 9.04e-04
+2022-04-28 19:55:01,746 INFO [train.py:763] (0/8) Epoch 7, batch 3400, loss[loss=0.1746, simple_loss=0.2706, pruned_loss=0.03932, over 6740.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2954, pruned_loss=0.05856, over 1419446.26 frames.], batch size: 31, lr: 9.04e-04
+2022-04-28 19:56:08,389 INFO [train.py:763] (0/8) Epoch 7, batch 3450, loss[loss=0.1661, simple_loss=0.257, pruned_loss=0.03761, over 7405.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2971, pruned_loss=0.05929, over 1422368.91 frames.], batch size: 18, lr: 9.03e-04
+2022-04-28 19:57:15,792 INFO [train.py:763] (0/8) Epoch 7, batch 3500, loss[loss=0.2006, simple_loss=0.2941, pruned_loss=0.05357, over 7381.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2978, pruned_loss=0.05946, over 1422619.59 frames.], batch size: 23, lr: 9.02e-04
+2022-04-28 19:58:22,791 INFO [train.py:763] (0/8) Epoch 7, batch 3550, loss[loss=0.1957, simple_loss=0.2968, pruned_loss=0.04726, over 7259.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2978, pruned_loss=0.05962, over 1423741.32 frames.], batch size: 19, lr: 9.02e-04
+2022-04-28 19:59:30,000 INFO [train.py:763] (0/8) Epoch 7, batch 3600, loss[loss=0.1895, simple_loss=0.2749, pruned_loss=0.05206, over 7272.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2967, pruned_loss=0.05898, over 1420983.25 frames.], batch size: 17, lr: 9.01e-04
+2022-04-28 20:00:37,041 INFO [train.py:763] (0/8) Epoch 7, batch 3650, loss[loss=0.2126, simple_loss=0.3066, pruned_loss=0.05926, over 7408.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2972, pruned_loss=0.05907, over 1415437.87 frames.], batch size: 21, lr: 9.01e-04
+2022-04-28 20:01:42,545 INFO [train.py:763] (0/8) Epoch 7, batch 3700, loss[loss=0.2244, simple_loss=0.3053, pruned_loss=0.07168, over 7224.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2967, pruned_loss=0.05872, over 1419175.16 frames.], batch size: 21, lr: 9.00e-04
+2022-04-28 20:02:49,235 INFO [train.py:763] (0/8) Epoch 7, batch 3750, loss[loss=0.2191, simple_loss=0.3095, pruned_loss=0.06437, over 7162.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2966, pruned_loss=0.05908, over 1416024.02 frames.], batch size: 19, lr: 8.99e-04
+2022-04-28 20:03:54,765 INFO [train.py:763] (0/8) Epoch 7, batch 3800, loss[loss=0.24, simple_loss=0.3254, pruned_loss=0.07731, over 7289.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2981, pruned_loss=0.05986, over 1419714.45 frames.], batch size: 24, lr: 8.99e-04
+2022-04-28 20:05:00,555 INFO [train.py:763] (0/8) Epoch 7, batch 3850, loss[loss=0.2252, simple_loss=0.3241, pruned_loss=0.06311, over 7205.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2993, pruned_loss=0.06011, over 1417696.72 frames.], batch size: 21, lr: 8.98e-04
+2022-04-28 20:06:06,744 INFO [train.py:763] (0/8) Epoch 7, batch 3900, loss[loss=0.1841, simple_loss=0.2785, pruned_loss=0.04488, over 7417.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2974, pruned_loss=0.05947, over 1421985.56 frames.], batch size: 20, lr: 8.97e-04
+2022-04-28 20:07:13,252 INFO [train.py:763] (0/8) Epoch 7, batch 3950, loss[loss=0.1894, simple_loss=0.2687, pruned_loss=0.05499, over 7420.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2958, pruned_loss=0.05818, over 1424899.01 frames.], batch size: 17, lr: 8.97e-04
+2022-04-28 20:08:18,740 INFO [train.py:763] (0/8) Epoch 7, batch 4000, loss[loss=0.2152, simple_loss=0.3093, pruned_loss=0.06052, over 7145.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2969, pruned_loss=0.05876, over 1424036.23 frames.], batch size: 20, lr: 8.96e-04
+2022-04-28 20:09:23,874 INFO [train.py:763] (0/8) Epoch 7, batch 4050, loss[loss=0.2081, simple_loss=0.304, pruned_loss=0.05615, over 7407.00 frames.], tot_loss[loss=0.207, simple_loss=0.2967, pruned_loss=0.05862, over 1426831.64 frames.], batch size: 21, lr: 8.96e-04
+2022-04-28 20:10:29,416 INFO [train.py:763] (0/8) Epoch 7, batch 4100, loss[loss=0.1862, simple_loss=0.2764, pruned_loss=0.04803, over 7277.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2973, pruned_loss=0.05887, over 1419948.92 frames.], batch size: 17, lr: 8.95e-04
+2022-04-28 20:11:34,147 INFO [train.py:763] (0/8) Epoch 7, batch 4150, loss[loss=0.1939, simple_loss=0.2956, pruned_loss=0.04613, over 7340.00 frames.], tot_loss[loss=0.208, simple_loss=0.2978, pruned_loss=0.05909, over 1414365.46 frames.], batch size: 22, lr: 8.94e-04
+2022-04-28 20:12:39,369 INFO [train.py:763] (0/8) Epoch 7, batch 4200, loss[loss=0.2092, simple_loss=0.3029, pruned_loss=0.05771, over 7142.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2976, pruned_loss=0.05861, over 1417133.37 frames.], batch size: 20, lr: 8.94e-04
+2022-04-28 20:13:44,893 INFO [train.py:763] (0/8) Epoch 7, batch 4250, loss[loss=0.2212, simple_loss=0.312, pruned_loss=0.0652, over 7201.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2969, pruned_loss=0.05827, over 1420615.05 frames.], batch size: 22, lr: 8.93e-04
+2022-04-28 20:14:50,392 INFO [train.py:763] (0/8) Epoch 7, batch 4300, loss[loss=0.2083, simple_loss=0.2977, pruned_loss=0.05947, over 7323.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2956, pruned_loss=0.05808, over 1419015.87 frames.], batch size: 21, lr: 8.93e-04
+2022-04-28 20:15:55,694 INFO [train.py:763] (0/8) Epoch 7, batch 4350, loss[loss=0.2326, simple_loss=0.3089, pruned_loss=0.07814, over 7121.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2948, pruned_loss=0.0579, over 1414431.18 frames.], batch size: 21, lr: 8.92e-04
+2022-04-28 20:17:01,784 INFO [train.py:763] (0/8) Epoch 7, batch 4400, loss[loss=0.2271, simple_loss=0.3218, pruned_loss=0.06625, over 7015.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2945, pruned_loss=0.05805, over 1417531.60 frames.], batch size: 28, lr: 8.91e-04
+2022-04-28 20:18:08,985 INFO [train.py:763] (0/8) Epoch 7, batch 4450, loss[loss=0.2271, simple_loss=0.3101, pruned_loss=0.07204, over 7333.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2945, pruned_loss=0.05807, over 1416638.00 frames.], batch size: 20, lr: 8.91e-04
+2022-04-28 20:19:16,365 INFO [train.py:763] (0/8) Epoch 7, batch 4500, loss[loss=0.2104, simple_loss=0.3002, pruned_loss=0.0603, over 7169.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2938, pruned_loss=0.0579, over 1414884.95 frames.], batch size: 18, lr: 8.90e-04
+2022-04-28 20:20:24,294 INFO [train.py:763] (0/8) Epoch 7, batch 4550, loss[loss=0.1856, simple_loss=0.2689, pruned_loss=0.05112, over 7274.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2928, pruned_loss=0.05866, over 1397950.53 frames.], batch size: 17, lr: 8.90e-04
+2022-04-28 20:21:14,990 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-7.pt
+2022-04-28 20:21:52,809 INFO [train.py:763] (0/8) Epoch 8, batch 0, loss[loss=0.2199, simple_loss=0.3148, pruned_loss=0.06246, over 7190.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3148, pruned_loss=0.06246, over 7190.00 frames.], batch size: 23, lr: 8.54e-04
+2022-04-28 20:22:58,565 INFO [train.py:763] (0/8) Epoch 8, batch 50, loss[loss=0.2075, simple_loss=0.3137, pruned_loss=0.05065, over 7044.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2973, pruned_loss=0.05915, over 318982.26 frames.], batch size: 28, lr: 8.53e-04
+2022-04-28 20:24:03,948 INFO [train.py:763] (0/8) Epoch 8, batch 100, loss[loss=0.2103, simple_loss=0.2972, pruned_loss=0.06167, over 7241.00 frames.], tot_loss[loss=0.2026, simple_loss=0.293, pruned_loss=0.05609, over 566750.51 frames.], batch size: 20, lr: 8.53e-04
+2022-04-28 20:25:10,094 INFO [train.py:763] (0/8) Epoch 8, batch 150, loss[loss=0.2606, simple_loss=0.3424, pruned_loss=0.08936, over 4991.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2943, pruned_loss=0.0564, over 754668.79 frames.], batch size: 52, lr: 8.52e-04
+2022-04-28 20:26:16,009 INFO [train.py:763] (0/8) Epoch 8, batch 200, loss[loss=0.2136, simple_loss=0.3075, pruned_loss=0.05983, over 7215.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2939, pruned_loss=0.05537, over 903026.48 frames.], batch size: 22, lr: 8.51e-04
+2022-04-28 20:27:21,277 INFO [train.py:763] (0/8) Epoch 8, batch 250, loss[loss=0.2003, simple_loss=0.2817, pruned_loss=0.05948, over 7438.00 frames.], tot_loss[loss=0.2028, simple_loss=0.294, pruned_loss=0.05584, over 1018923.74 frames.], batch size: 20, lr: 8.51e-04
+2022-04-28 20:28:27,039 INFO [train.py:763] (0/8) Epoch 8, batch 300, loss[loss=0.2062, simple_loss=0.298, pruned_loss=0.05715, over 7337.00 frames.], tot_loss[loss=0.204, simple_loss=0.2947, pruned_loss=0.05667, over 1104921.08 frames.], batch size: 22, lr: 8.50e-04
+2022-04-28 20:29:32,800 INFO [train.py:763] (0/8) Epoch 8, batch 350, loss[loss=0.2004, simple_loss=0.2951, pruned_loss=0.05288, over 7167.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2926, pruned_loss=0.05582, over 1178485.42 frames.], batch size: 19, lr: 8.50e-04
+2022-04-28 20:30:38,289 INFO [train.py:763] (0/8) Epoch 8, batch 400, loss[loss=0.179, simple_loss=0.2738, pruned_loss=0.04207, over 7130.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2934, pruned_loss=0.05638, over 1237548.71 frames.], batch size: 17, lr: 8.49e-04
+2022-04-28 20:31:43,760 INFO [train.py:763] (0/8) Epoch 8, batch 450, loss[loss=0.2094, simple_loss=0.2867, pruned_loss=0.066, over 7248.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2936, pruned_loss=0.05663, over 1278439.98 frames.], batch size: 19, lr: 8.49e-04
+2022-04-28 20:32:50,604 INFO [train.py:763] (0/8) Epoch 8, batch 500, loss[loss=0.1593, simple_loss=0.2556, pruned_loss=0.03153, over 7413.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2948, pruned_loss=0.05724, over 1310632.45 frames.], batch size: 18, lr: 8.48e-04
+2022-04-28 20:33:57,754 INFO [train.py:763] (0/8) Epoch 8, batch 550, loss[loss=0.188, simple_loss=0.2657, pruned_loss=0.0552, over 7054.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2937, pruned_loss=0.0567, over 1338812.45 frames.], batch size: 18, lr: 8.48e-04
+2022-04-28 20:35:03,802 INFO [train.py:763] (0/8) Epoch 8, batch 600, loss[loss=0.1933, simple_loss=0.2809, pruned_loss=0.05286, over 7070.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2934, pruned_loss=0.05604, over 1360396.84 frames.], batch size: 18, lr: 8.47e-04
+2022-04-28 20:36:09,112 INFO [train.py:763] (0/8) Epoch 8, batch 650, loss[loss=0.1955, simple_loss=0.2878, pruned_loss=0.05159, over 7360.00 frames.], tot_loss[loss=0.203, simple_loss=0.2934, pruned_loss=0.0563, over 1373653.11 frames.], batch size: 19, lr: 8.46e-04
+2022-04-28 20:37:14,556 INFO [train.py:763] (0/8) Epoch 8, batch 700, loss[loss=0.2336, simple_loss=0.3122, pruned_loss=0.07751, over 7435.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2937, pruned_loss=0.05647, over 1386418.96 frames.], batch size: 20, lr: 8.46e-04
+2022-04-28 20:38:20,317 INFO [train.py:763] (0/8) Epoch 8, batch 750, loss[loss=0.198, simple_loss=0.2851, pruned_loss=0.05542, over 7166.00 frames.], tot_loss[loss=0.204, simple_loss=0.2948, pruned_loss=0.05663, over 1389385.99 frames.], batch size: 18, lr: 8.45e-04
+2022-04-28 20:39:25,916 INFO [train.py:763] (0/8) Epoch 8, batch 800, loss[loss=0.2413, simple_loss=0.3315, pruned_loss=0.07553, over 7382.00 frames.], tot_loss[loss=0.204, simple_loss=0.2945, pruned_loss=0.05676, over 1396095.42 frames.], batch size: 23, lr: 8.45e-04
+2022-04-28 20:40:32,572 INFO [train.py:763] (0/8) Epoch 8, batch 850, loss[loss=0.1869, simple_loss=0.2752, pruned_loss=0.04929, over 7310.00 frames.], tot_loss[loss=0.2047, simple_loss=0.295, pruned_loss=0.05721, over 1401291.18 frames.], batch size: 21, lr: 8.44e-04
+2022-04-28 20:41:39,569 INFO [train.py:763] (0/8) Epoch 8, batch 900, loss[loss=0.2152, simple_loss=0.3129, pruned_loss=0.05874, over 7215.00 frames.], tot_loss[loss=0.2043, simple_loss=0.295, pruned_loss=0.05684, over 1410842.01 frames.], batch size: 21, lr: 8.44e-04
+2022-04-28 20:42:46,716 INFO [train.py:763] (0/8) Epoch 8, batch 950, loss[loss=0.2, simple_loss=0.302, pruned_loss=0.04904, over 7327.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2948, pruned_loss=0.05675, over 1409086.09 frames.], batch size: 20, lr: 8.43e-04
+2022-04-28 20:43:53,835 INFO [train.py:763] (0/8) Epoch 8, batch 1000, loss[loss=0.1979, simple_loss=0.2827, pruned_loss=0.0565, over 7432.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2942, pruned_loss=0.05633, over 1412626.32 frames.], batch size: 20, lr: 8.43e-04
+2022-04-28 20:45:00,980 INFO [train.py:763] (0/8) Epoch 8, batch 1050, loss[loss=0.1834, simple_loss=0.2796, pruned_loss=0.0436, over 7271.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2945, pruned_loss=0.05646, over 1417670.64 frames.], batch size: 19, lr: 8.42e-04
+2022-04-28 20:46:07,164 INFO [train.py:763] (0/8) Epoch 8, batch 1100, loss[loss=0.1803, simple_loss=0.264, pruned_loss=0.04827, over 7284.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2964, pruned_loss=0.05739, over 1420314.59 frames.], batch size: 17, lr: 8.41e-04
+2022-04-28 20:47:12,903 INFO [train.py:763] (0/8) Epoch 8, batch 1150, loss[loss=0.2222, simple_loss=0.3203, pruned_loss=0.06205, over 7322.00 frames.], tot_loss[loss=0.205, simple_loss=0.2954, pruned_loss=0.05728, over 1420725.65 frames.], batch size: 25, lr: 8.41e-04
+2022-04-28 20:48:18,245 INFO [train.py:763] (0/8) Epoch 8, batch 1200, loss[loss=0.2075, simple_loss=0.2975, pruned_loss=0.05875, over 7446.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2962, pruned_loss=0.05784, over 1420806.74 frames.], batch size: 20, lr: 8.40e-04
+2022-04-28 20:49:23,432 INFO [train.py:763] (0/8) Epoch 8, batch 1250, loss[loss=0.1633, simple_loss=0.2494, pruned_loss=0.03866, over 6845.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2961, pruned_loss=0.05804, over 1416696.98 frames.], batch size: 15, lr: 8.40e-04
+2022-04-28 20:50:29,925 INFO [train.py:763] (0/8) Epoch 8, batch 1300, loss[loss=0.2544, simple_loss=0.3407, pruned_loss=0.08404, over 7151.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2964, pruned_loss=0.05817, over 1413236.54 frames.], batch size: 19, lr: 8.39e-04
+2022-04-28 20:51:37,157 INFO [train.py:763] (0/8) Epoch 8, batch 1350, loss[loss=0.235, simple_loss=0.3131, pruned_loss=0.07847, over 7438.00 frames.], tot_loss[loss=0.206, simple_loss=0.296, pruned_loss=0.05797, over 1417741.87 frames.], batch size: 20, lr: 8.39e-04
+2022-04-28 20:52:43,215 INFO [train.py:763] (0/8) Epoch 8, batch 1400, loss[loss=0.1804, simple_loss=0.2817, pruned_loss=0.03953, over 7207.00 frames.], tot_loss[loss=0.205, simple_loss=0.2952, pruned_loss=0.05742, over 1414879.05 frames.], batch size: 21, lr: 8.38e-04
+2022-04-28 20:53:48,901 INFO [train.py:763] (0/8) Epoch 8, batch 1450, loss[loss=0.2006, simple_loss=0.2984, pruned_loss=0.05137, over 7314.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2937, pruned_loss=0.05634, over 1420079.54 frames.], batch size: 21, lr: 8.38e-04
+2022-04-28 20:54:55,526 INFO [train.py:763] (0/8) Epoch 8, batch 1500, loss[loss=0.2164, simple_loss=0.3202, pruned_loss=0.05632, over 7238.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2943, pruned_loss=0.05651, over 1422759.60 frames.], batch size: 20, lr: 8.37e-04
+2022-04-28 20:56:02,364 INFO [train.py:763] (0/8) Epoch 8, batch 1550, loss[loss=0.226, simple_loss=0.3219, pruned_loss=0.06503, over 7212.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2941, pruned_loss=0.05654, over 1422281.91 frames.], batch size: 22, lr: 8.37e-04
+2022-04-28 20:57:08,593 INFO [train.py:763] (0/8) Epoch 8, batch 1600, loss[loss=0.1835, simple_loss=0.2815, pruned_loss=0.04278, over 7061.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2941, pruned_loss=0.05625, over 1419612.84 frames.], batch size: 18, lr: 8.36e-04
+2022-04-28 20:58:15,584 INFO [train.py:763] (0/8) Epoch 8, batch 1650, loss[loss=0.2093, simple_loss=0.3006, pruned_loss=0.05899, over 7118.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2942, pruned_loss=0.05634, over 1420459.13 frames.], batch size: 21, lr: 8.35e-04
+2022-04-28 20:59:22,340 INFO [train.py:763] (0/8) Epoch 8, batch 1700, loss[loss=0.198, simple_loss=0.2936, pruned_loss=0.05124, over 7145.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2943, pruned_loss=0.05625, over 1419177.42 frames.], batch size: 20, lr: 8.35e-04
+2022-04-28 21:00:28,782 INFO [train.py:763] (0/8) Epoch 8, batch 1750, loss[loss=0.1985, simple_loss=0.3046, pruned_loss=0.04621, over 7314.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2935, pruned_loss=0.0557, over 1420531.03 frames.], batch size: 21, lr: 8.34e-04
+2022-04-28 21:01:33,983 INFO [train.py:763] (0/8) Epoch 8, batch 1800, loss[loss=0.1835, simple_loss=0.2792, pruned_loss=0.04386, over 7242.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2937, pruned_loss=0.05596, over 1417283.33 frames.], batch size: 20, lr: 8.34e-04
+2022-04-28 21:02:39,286 INFO [train.py:763] (0/8) Epoch 8, batch 1850, loss[loss=0.2174, simple_loss=0.3029, pruned_loss=0.06591, over 7239.00 frames.], tot_loss[loss=0.2029, simple_loss=0.294, pruned_loss=0.05583, over 1420761.28 frames.], batch size: 20, lr: 8.33e-04
+2022-04-28 21:03:44,678 INFO [train.py:763] (0/8) Epoch 8, batch 1900, loss[loss=0.1999, simple_loss=0.2949, pruned_loss=0.05248, over 7159.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2944, pruned_loss=0.05618, over 1419246.03 frames.], batch size: 19, lr: 8.33e-04
+2022-04-28 21:04:50,209 INFO [train.py:763] (0/8) Epoch 8, batch 1950, loss[loss=0.1821, simple_loss=0.2777, pruned_loss=0.0433, over 7106.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2949, pruned_loss=0.05627, over 1420511.70 frames.], batch size: 21, lr: 8.32e-04
+2022-04-28 21:05:55,502 INFO [train.py:763] (0/8) Epoch 8, batch 2000, loss[loss=0.1975, simple_loss=0.2898, pruned_loss=0.05263, over 7279.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2937, pruned_loss=0.05594, over 1422360.68 frames.], batch size: 24, lr: 8.32e-04
+2022-04-28 21:07:00,734 INFO [train.py:763] (0/8) Epoch 8, batch 2050, loss[loss=0.1684, simple_loss=0.2471, pruned_loss=0.04483, over 7269.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2938, pruned_loss=0.05667, over 1421764.51 frames.], batch size: 17, lr: 8.31e-04
+2022-04-28 21:08:05,940 INFO [train.py:763] (0/8) Epoch 8, batch 2100, loss[loss=0.1889, simple_loss=0.2738, pruned_loss=0.05201, over 7265.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2935, pruned_loss=0.05614, over 1424105.48 frames.], batch size: 19, lr: 8.31e-04
+2022-04-28 21:09:08,028 INFO [train.py:763] (0/8) Epoch 8, batch 2150, loss[loss=0.2025, simple_loss=0.2869, pruned_loss=0.05902, over 7071.00 frames.], tot_loss[loss=0.203, simple_loss=0.2938, pruned_loss=0.0561, over 1426060.28 frames.], batch size: 18, lr: 8.30e-04
+2022-04-28 21:10:14,561 INFO [train.py:763] (0/8) Epoch 8, batch 2200, loss[loss=0.2017, simple_loss=0.2723, pruned_loss=0.06556, over 7285.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2928, pruned_loss=0.05563, over 1423419.06 frames.], batch size: 17, lr: 8.30e-04
+2022-04-28 21:11:21,401 INFO [train.py:763] (0/8) Epoch 8, batch 2250, loss[loss=0.2211, simple_loss=0.3041, pruned_loss=0.06911, over 7159.00 frames.], tot_loss[loss=0.2024, simple_loss=0.293, pruned_loss=0.05585, over 1424133.66 frames.], batch size: 18, lr: 8.29e-04
+2022-04-28 21:12:26,812 INFO [train.py:763] (0/8) Epoch 8, batch 2300, loss[loss=0.1794, simple_loss=0.2742, pruned_loss=0.04224, over 7150.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2936, pruned_loss=0.05643, over 1425409.05 frames.], batch size: 20, lr: 8.29e-04
+2022-04-28 21:13:32,129 INFO [train.py:763] (0/8) Epoch 8, batch 2350, loss[loss=0.2373, simple_loss=0.325, pruned_loss=0.07474, over 6737.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2935, pruned_loss=0.05659, over 1424097.02 frames.], batch size: 31, lr: 8.28e-04
+2022-04-28 21:14:37,454 INFO [train.py:763] (0/8) Epoch 8, batch 2400, loss[loss=0.184, simple_loss=0.2686, pruned_loss=0.0497, over 7277.00 frames.], tot_loss[loss=0.2026, simple_loss=0.293, pruned_loss=0.05606, over 1424746.24 frames.], batch size: 18, lr: 8.28e-04
+2022-04-28 21:15:42,881 INFO [train.py:763] (0/8) Epoch 8, batch 2450, loss[loss=0.1686, simple_loss=0.2614, pruned_loss=0.03796, over 7404.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2934, pruned_loss=0.05588, over 1425899.66 frames.], batch size: 18, lr: 8.27e-04
+2022-04-28 21:16:48,168 INFO [train.py:763] (0/8) Epoch 8, batch 2500, loss[loss=0.1829, simple_loss=0.2818, pruned_loss=0.04202, over 7214.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2931, pruned_loss=0.0556, over 1423647.30 frames.], batch size: 22, lr: 8.27e-04
+2022-04-28 21:17:53,466 INFO [train.py:763] (0/8) Epoch 8, batch 2550, loss[loss=0.1989, simple_loss=0.287, pruned_loss=0.05537, over 7132.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2922, pruned_loss=0.0551, over 1419987.73 frames.], batch size: 17, lr: 8.26e-04
+2022-04-28 21:18:58,787 INFO [train.py:763] (0/8) Epoch 8, batch 2600, loss[loss=0.2545, simple_loss=0.3207, pruned_loss=0.09415, over 7392.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2938, pruned_loss=0.05638, over 1416989.21 frames.], batch size: 23, lr: 8.25e-04
+2022-04-28 21:20:03,882 INFO [train.py:763] (0/8) Epoch 8, batch 2650, loss[loss=0.2476, simple_loss=0.3204, pruned_loss=0.08738, over 4824.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2938, pruned_loss=0.05631, over 1415831.01 frames.], batch size: 52, lr: 8.25e-04
+2022-04-28 21:21:09,318 INFO [train.py:763] (0/8) Epoch 8, batch 2700, loss[loss=0.1827, simple_loss=0.2831, pruned_loss=0.04118, over 7327.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2936, pruned_loss=0.05577, over 1417541.50 frames.], batch size: 22, lr: 8.24e-04
+2022-04-28 21:22:14,619 INFO [train.py:763] (0/8) Epoch 8, batch 2750, loss[loss=0.1717, simple_loss=0.2607, pruned_loss=0.04138, over 7332.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2922, pruned_loss=0.0548, over 1422057.58 frames.], batch size: 20, lr: 8.24e-04
+2022-04-28 21:23:20,659 INFO [train.py:763] (0/8) Epoch 8, batch 2800, loss[loss=0.2317, simple_loss=0.3297, pruned_loss=0.06683, over 7198.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2924, pruned_loss=0.05524, over 1425686.88 frames.], batch size: 22, lr: 8.23e-04
+2022-04-28 21:24:26,776 INFO [train.py:763] (0/8) Epoch 8, batch 2850, loss[loss=0.1662, simple_loss=0.2521, pruned_loss=0.04012, over 7169.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2926, pruned_loss=0.05538, over 1427612.51 frames.], batch size: 19, lr: 8.23e-04
+2022-04-28 21:25:32,047 INFO [train.py:763] (0/8) Epoch 8, batch 2900, loss[loss=0.1873, simple_loss=0.2861, pruned_loss=0.04424, over 7330.00 frames.], tot_loss[loss=0.201, simple_loss=0.2923, pruned_loss=0.05486, over 1426721.98 frames.], batch size: 21, lr: 8.22e-04
+2022-04-28 21:26:37,473 INFO [train.py:763] (0/8) Epoch 8, batch 2950, loss[loss=0.2031, simple_loss=0.2823, pruned_loss=0.06197, over 7285.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2934, pruned_loss=0.05593, over 1422211.86 frames.], batch size: 18, lr: 8.22e-04
+2022-04-28 21:27:43,090 INFO [train.py:763] (0/8) Epoch 8, batch 3000, loss[loss=0.2107, simple_loss=0.3075, pruned_loss=0.05691, over 7290.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2931, pruned_loss=0.05586, over 1420755.70 frames.], batch size: 24, lr: 8.21e-04
+2022-04-28 21:27:43,091 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-28 21:27:58,489 INFO [train.py:792] (0/8) Epoch 8, validation: loss=0.1715, simple_loss=0.2766, pruned_loss=0.03324, over 698248.00 frames.
+2022-04-28 21:29:04,155 INFO [train.py:763] (0/8) Epoch 8, batch 3050, loss[loss=0.1737, simple_loss=0.2651, pruned_loss=0.04109, over 7316.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2927, pruned_loss=0.05584, over 1417912.20 frames.], batch size: 20, lr: 8.21e-04
+2022-04-28 21:30:09,335 INFO [train.py:763] (0/8) Epoch 8, batch 3100, loss[loss=0.2625, simple_loss=0.3401, pruned_loss=0.09246, over 6729.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2951, pruned_loss=0.05696, over 1413742.37 frames.], batch size: 31, lr: 8.20e-04
+2022-04-28 21:31:14,881 INFO [train.py:763] (0/8) Epoch 8, batch 3150, loss[loss=0.1731, simple_loss=0.2673, pruned_loss=0.03942, over 7162.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2942, pruned_loss=0.05645, over 1417542.36 frames.], batch size: 19, lr: 8.20e-04
+2022-04-28 21:32:20,537 INFO [train.py:763] (0/8) Epoch 8, batch 3200, loss[loss=0.1683, simple_loss=0.2656, pruned_loss=0.03551, over 7149.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2941, pruned_loss=0.05623, over 1422271.72 frames.], batch size: 20, lr: 8.19e-04
+2022-04-28 21:33:34,634 INFO [train.py:763] (0/8) Epoch 8, batch 3250, loss[loss=0.2115, simple_loss=0.3086, pruned_loss=0.0572, over 5066.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2944, pruned_loss=0.05647, over 1420367.47 frames.], batch size: 52, lr: 8.19e-04
+2022-04-28 21:34:33,648 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-40000.pt
+2022-04-28 21:34:51,675 INFO [train.py:763] (0/8) Epoch 8, batch 3300, loss[loss=0.2224, simple_loss=0.3133, pruned_loss=0.06577, over 7200.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2934, pruned_loss=0.05598, over 1420462.63 frames.], batch size: 22, lr: 8.18e-04
+2022-04-28 21:36:05,892 INFO [train.py:763] (0/8) Epoch 8, batch 3350, loss[loss=0.1762, simple_loss=0.2722, pruned_loss=0.04015, over 7264.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2932, pruned_loss=0.05562, over 1423966.16 frames.], batch size: 19, lr: 8.18e-04
+2022-04-28 21:37:39,121 INFO [train.py:763] (0/8) Epoch 8, batch 3400, loss[loss=0.2212, simple_loss=0.3118, pruned_loss=0.06534, over 6766.00 frames.], tot_loss[loss=0.2029, simple_loss=0.294, pruned_loss=0.05591, over 1421424.93 frames.], batch size: 31, lr: 8.17e-04
+2022-04-28 21:38:45,189 INFO [train.py:763] (0/8) Epoch 8, batch 3450, loss[loss=0.1972, simple_loss=0.264, pruned_loss=0.06521, over 7420.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2935, pruned_loss=0.05585, over 1424005.16 frames.], batch size: 18, lr: 8.17e-04
+2022-04-28 21:40:00,478 INFO [train.py:763] (0/8) Epoch 8, batch 3500, loss[loss=0.1935, simple_loss=0.293, pruned_loss=0.04698, over 7153.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2932, pruned_loss=0.05563, over 1425010.78 frames.], batch size: 19, lr: 8.16e-04
+2022-04-28 21:41:15,121 INFO [train.py:763] (0/8) Epoch 8, batch 3550, loss[loss=0.1639, simple_loss=0.2543, pruned_loss=0.03681, over 7168.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2927, pruned_loss=0.05572, over 1426258.76 frames.], batch size: 18, lr: 8.16e-04
+2022-04-28 21:42:20,510 INFO [train.py:763] (0/8) Epoch 8, batch 3600, loss[loss=0.1701, simple_loss=0.2591, pruned_loss=0.04059, over 7288.00 frames.], tot_loss[loss=0.2025, simple_loss=0.293, pruned_loss=0.05599, over 1424509.36 frames.], batch size: 18, lr: 8.15e-04
+2022-04-28 21:43:26,016 INFO [train.py:763] (0/8) Epoch 8, batch 3650, loss[loss=0.1811, simple_loss=0.2536, pruned_loss=0.05429, over 7134.00 frames.], tot_loss[loss=0.2023, simple_loss=0.293, pruned_loss=0.05579, over 1425448.96 frames.], batch size: 17, lr: 8.15e-04
+2022-04-28 21:44:39,934 INFO [train.py:763] (0/8) Epoch 8, batch 3700, loss[loss=0.2476, simple_loss=0.3372, pruned_loss=0.07896, over 7295.00 frames.], tot_loss[loss=0.203, simple_loss=0.2938, pruned_loss=0.05604, over 1425920.36 frames.], batch size: 25, lr: 8.14e-04
+2022-04-28 21:45:45,263 INFO [train.py:763] (0/8) Epoch 8, batch 3750, loss[loss=0.1683, simple_loss=0.2644, pruned_loss=0.03604, over 7437.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2944, pruned_loss=0.05593, over 1424925.26 frames.], batch size: 20, lr: 8.14e-04
+2022-04-28 21:46:51,554 INFO [train.py:763] (0/8) Epoch 8, batch 3800, loss[loss=0.1967, simple_loss=0.2869, pruned_loss=0.05322, over 7411.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2941, pruned_loss=0.05582, over 1426693.43 frames.], batch size: 18, lr: 8.13e-04
+2022-04-28 21:47:57,466 INFO [train.py:763] (0/8) Epoch 8, batch 3850, loss[loss=0.1938, simple_loss=0.2832, pruned_loss=0.0522, over 7279.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2936, pruned_loss=0.05545, over 1428707.52 frames.], batch size: 17, lr: 8.13e-04
+2022-04-28 21:49:03,321 INFO [train.py:763] (0/8) Epoch 8, batch 3900, loss[loss=0.2509, simple_loss=0.334, pruned_loss=0.08392, over 4912.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2944, pruned_loss=0.05551, over 1425856.74 frames.], batch size: 54, lr: 8.12e-04
+2022-04-28 21:50:08,725 INFO [train.py:763] (0/8) Epoch 8, batch 3950, loss[loss=0.2091, simple_loss=0.3061, pruned_loss=0.05606, over 6772.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2931, pruned_loss=0.05521, over 1426406.69 frames.], batch size: 31, lr: 8.12e-04
+2022-04-28 21:51:14,800 INFO [train.py:763] (0/8) Epoch 8, batch 4000, loss[loss=0.1854, simple_loss=0.284, pruned_loss=0.04336, over 7223.00 frames.], tot_loss[loss=0.202, simple_loss=0.294, pruned_loss=0.055, over 1425939.14 frames.], batch size: 21, lr: 8.11e-04
+2022-04-28 21:52:21,956 INFO [train.py:763] (0/8) Epoch 8, batch 4050, loss[loss=0.1681, simple_loss=0.259, pruned_loss=0.03859, over 7419.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2927, pruned_loss=0.05478, over 1425491.88 frames.], batch size: 18, lr: 8.11e-04
+2022-04-28 21:53:28,738 INFO [train.py:763] (0/8) Epoch 8, batch 4100, loss[loss=0.2113, simple_loss=0.2883, pruned_loss=0.06715, over 7140.00 frames.], tot_loss[loss=0.2001, simple_loss=0.292, pruned_loss=0.05412, over 1426616.10 frames.], batch size: 17, lr: 8.10e-04
+2022-04-28 21:54:34,094 INFO [train.py:763] (0/8) Epoch 8, batch 4150, loss[loss=0.2072, simple_loss=0.2945, pruned_loss=0.05998, over 7071.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2915, pruned_loss=0.05441, over 1422086.98 frames.], batch size: 28, lr: 8.10e-04
+2022-04-28 21:55:39,793 INFO [train.py:763] (0/8) Epoch 8, batch 4200, loss[loss=0.1799, simple_loss=0.2666, pruned_loss=0.04662, over 7319.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2901, pruned_loss=0.05419, over 1423466.75 frames.], batch size: 20, lr: 8.09e-04
+2022-04-28 21:56:45,200 INFO [train.py:763] (0/8) Epoch 8, batch 4250, loss[loss=0.1775, simple_loss=0.2712, pruned_loss=0.04194, over 7135.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2898, pruned_loss=0.05447, over 1419527.55 frames.], batch size: 17, lr: 8.09e-04
+2022-04-28 21:57:50,935 INFO [train.py:763] (0/8) Epoch 8, batch 4300, loss[loss=0.2134, simple_loss=0.3079, pruned_loss=0.05944, over 7413.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2903, pruned_loss=0.05459, over 1414057.96 frames.], batch size: 21, lr: 8.08e-04
+2022-04-28 21:58:56,625 INFO [train.py:763] (0/8) Epoch 8, batch 4350, loss[loss=0.1804, simple_loss=0.2529, pruned_loss=0.05391, over 7282.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2901, pruned_loss=0.05453, over 1420284.10 frames.], batch size: 17, lr: 8.08e-04
+2022-04-28 22:00:02,325 INFO [train.py:763] (0/8) Epoch 8, batch 4400, loss[loss=0.1925, simple_loss=0.2766, pruned_loss=0.05424, over 7042.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2899, pruned_loss=0.05443, over 1416675.36 frames.], batch size: 28, lr: 8.07e-04
+2022-04-28 22:01:09,623 INFO [train.py:763] (0/8) Epoch 8, batch 4450, loss[loss=0.2129, simple_loss=0.3036, pruned_loss=0.06112, over 6981.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2882, pruned_loss=0.05408, over 1411177.64 frames.], batch size: 28, lr: 8.07e-04
+2022-04-28 22:02:15,958 INFO [train.py:763] (0/8) Epoch 8, batch 4500, loss[loss=0.1965, simple_loss=0.301, pruned_loss=0.046, over 7059.00 frames.], tot_loss[loss=0.2002, simple_loss=0.29, pruned_loss=0.05526, over 1393241.81 frames.], batch size: 28, lr: 8.07e-04
+2022-04-28 22:03:19,883 INFO [train.py:763] (0/8) Epoch 8, batch 4550, loss[loss=0.2097, simple_loss=0.2946, pruned_loss=0.06239, over 6454.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2944, pruned_loss=0.05836, over 1353052.46 frames.], batch size: 38, lr: 8.06e-04
+2022-04-28 22:04:09,795 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-8.pt
+2022-04-28 22:04:39,798 INFO [train.py:763] (0/8) Epoch 9, batch 0, loss[loss=0.1955, simple_loss=0.2929, pruned_loss=0.0491, over 7421.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2929, pruned_loss=0.0491, over 7421.00 frames.], batch size: 21, lr: 7.75e-04
+2022-04-28 22:05:45,920 INFO [train.py:763] (0/8) Epoch 9, batch 50, loss[loss=0.2039, simple_loss=0.3124, pruned_loss=0.04774, over 7207.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2914, pruned_loss=0.05413, over 321892.53 frames.], batch size: 23, lr: 7.74e-04
+2022-04-28 22:06:51,607 INFO [train.py:763] (0/8) Epoch 9, batch 100, loss[loss=0.2259, simple_loss=0.3119, pruned_loss=0.06998, over 4942.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2896, pruned_loss=0.05396, over 557450.22 frames.], batch size: 52, lr: 7.74e-04
+2022-04-28 22:07:57,288 INFO [train.py:763] (0/8) Epoch 9, batch 150, loss[loss=0.1794, simple_loss=0.2704, pruned_loss=0.04421, over 7424.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2899, pruned_loss=0.05378, over 750879.81 frames.], batch size: 20, lr: 7.73e-04
+2022-04-28 22:09:03,764 INFO [train.py:763] (0/8) Epoch 9, batch 200, loss[loss=0.1931, simple_loss=0.2963, pruned_loss=0.04495, over 7432.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2914, pruned_loss=0.05411, over 898060.74 frames.], batch size: 20, lr: 7.73e-04
+2022-04-28 22:10:10,441 INFO [train.py:763] (0/8) Epoch 9, batch 250, loss[loss=0.1986, simple_loss=0.2871, pruned_loss=0.05504, over 7154.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2914, pruned_loss=0.05387, over 1010484.15 frames.], batch size: 18, lr: 7.72e-04
+2022-04-28 22:11:16,233 INFO [train.py:763] (0/8) Epoch 9, batch 300, loss[loss=0.2086, simple_loss=0.3043, pruned_loss=0.05648, over 7337.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2903, pruned_loss=0.05377, over 1103861.34 frames.], batch size: 20, lr: 7.72e-04
+2022-04-28 22:12:21,607 INFO [train.py:763] (0/8) Epoch 9, batch 350, loss[loss=0.217, simple_loss=0.3016, pruned_loss=0.06626, over 7210.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2906, pruned_loss=0.05358, over 1171976.74 frames.], batch size: 23, lr: 7.71e-04
+2022-04-28 22:13:26,953 INFO [train.py:763] (0/8) Epoch 9, batch 400, loss[loss=0.2468, simple_loss=0.3412, pruned_loss=0.07622, over 7213.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2923, pruned_loss=0.05435, over 1222546.13 frames.], batch size: 26, lr: 7.71e-04
+2022-04-28 22:14:32,173 INFO [train.py:763] (0/8) Epoch 9, batch 450, loss[loss=0.2148, simple_loss=0.3125, pruned_loss=0.05855, over 6360.00 frames.], tot_loss[loss=0.2, simple_loss=0.2918, pruned_loss=0.05406, over 1261656.20 frames.], batch size: 38, lr: 7.71e-04
+2022-04-28 22:15:37,760 INFO [train.py:763] (0/8) Epoch 9, batch 500, loss[loss=0.1996, simple_loss=0.296, pruned_loss=0.05158, over 7173.00 frames.], tot_loss[loss=0.2, simple_loss=0.2919, pruned_loss=0.05409, over 1297186.38 frames.], batch size: 19, lr: 7.70e-04
+2022-04-28 22:16:43,400 INFO [train.py:763] (0/8) Epoch 9, batch 550, loss[loss=0.1671, simple_loss=0.2539, pruned_loss=0.04013, over 7131.00 frames.], tot_loss[loss=0.199, simple_loss=0.2908, pruned_loss=0.05358, over 1324997.84 frames.], batch size: 17, lr: 7.70e-04
+2022-04-28 22:17:49,466 INFO [train.py:763] (0/8) Epoch 9, batch 600, loss[loss=0.1977, simple_loss=0.283, pruned_loss=0.05619, over 7274.00 frames.], tot_loss[loss=0.199, simple_loss=0.2906, pruned_loss=0.05367, over 1345965.78 frames.], batch size: 18, lr: 7.69e-04
+2022-04-28 22:18:54,917 INFO [train.py:763] (0/8) Epoch 9, batch 650, loss[loss=0.229, simple_loss=0.3229, pruned_loss=0.06753, over 7175.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2901, pruned_loss=0.05318, over 1361916.56 frames.], batch size: 26, lr: 7.69e-04
+2022-04-28 22:20:00,489 INFO [train.py:763] (0/8) Epoch 9, batch 700, loss[loss=0.1966, simple_loss=0.2914, pruned_loss=0.05089, over 7283.00 frames.], tot_loss[loss=0.1968, simple_loss=0.289, pruned_loss=0.05229, over 1377133.46 frames.], batch size: 25, lr: 7.68e-04
+2022-04-28 22:21:06,851 INFO [train.py:763] (0/8) Epoch 9, batch 750, loss[loss=0.176, simple_loss=0.2604, pruned_loss=0.04576, over 7429.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2892, pruned_loss=0.05254, over 1387016.75 frames.], batch size: 20, lr: 7.68e-04
+2022-04-28 22:22:12,205 INFO [train.py:763] (0/8) Epoch 9, batch 800, loss[loss=0.1997, simple_loss=0.2967, pruned_loss=0.05136, over 7287.00 frames.], tot_loss[loss=0.198, simple_loss=0.2894, pruned_loss=0.05327, over 1394615.24 frames.], batch size: 24, lr: 7.67e-04
+2022-04-28 22:23:17,417 INFO [train.py:763] (0/8) Epoch 9, batch 850, loss[loss=0.1776, simple_loss=0.2812, pruned_loss=0.03696, over 6380.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2905, pruned_loss=0.05385, over 1397601.33 frames.], batch size: 38, lr: 7.67e-04
+2022-04-28 22:24:22,765 INFO [train.py:763] (0/8) Epoch 9, batch 900, loss[loss=0.1858, simple_loss=0.2779, pruned_loss=0.04688, over 7330.00 frames.], tot_loss[loss=0.1996, simple_loss=0.291, pruned_loss=0.05403, over 1407863.49 frames.], batch size: 21, lr: 7.66e-04
+2022-04-28 22:25:27,958 INFO [train.py:763] (0/8) Epoch 9, batch 950, loss[loss=0.1938, simple_loss=0.297, pruned_loss=0.04531, over 7141.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2913, pruned_loss=0.05383, over 1406463.80 frames.], batch size: 26, lr: 7.66e-04
+2022-04-28 22:26:34,002 INFO [train.py:763] (0/8) Epoch 9, batch 1000, loss[loss=0.1857, simple_loss=0.2881, pruned_loss=0.04162, over 7331.00 frames.], tot_loss[loss=0.1979, simple_loss=0.29, pruned_loss=0.05286, over 1413786.54 frames.], batch size: 20, lr: 7.66e-04
+2022-04-28 22:27:40,367 INFO [train.py:763] (0/8) Epoch 9, batch 1050, loss[loss=0.2448, simple_loss=0.3337, pruned_loss=0.07798, over 7039.00 frames.], tot_loss[loss=0.198, simple_loss=0.29, pruned_loss=0.05299, over 1416217.09 frames.], batch size: 28, lr: 7.65e-04
+2022-04-28 22:28:46,006 INFO [train.py:763] (0/8) Epoch 9, batch 1100, loss[loss=0.1813, simple_loss=0.2812, pruned_loss=0.04069, over 7097.00 frames.], tot_loss[loss=0.199, simple_loss=0.2908, pruned_loss=0.05355, over 1417899.63 frames.], batch size: 28, lr: 7.65e-04
+2022-04-28 22:29:52,334 INFO [train.py:763] (0/8) Epoch 9, batch 1150, loss[loss=0.2128, simple_loss=0.3077, pruned_loss=0.05896, over 7321.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2918, pruned_loss=0.0537, over 1422296.82 frames.], batch size: 20, lr: 7.64e-04
+2022-04-28 22:30:57,649 INFO [train.py:763] (0/8) Epoch 9, batch 1200, loss[loss=0.2096, simple_loss=0.3186, pruned_loss=0.0503, over 7196.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2919, pruned_loss=0.05364, over 1421260.94 frames.], batch size: 23, lr: 7.64e-04
+2022-04-28 22:32:04,412 INFO [train.py:763] (0/8) Epoch 9, batch 1250, loss[loss=0.1672, simple_loss=0.2553, pruned_loss=0.03961, over 7286.00 frames.], tot_loss[loss=0.1996, simple_loss=0.292, pruned_loss=0.05362, over 1419045.71 frames.], batch size: 17, lr: 7.63e-04
+2022-04-28 22:33:11,159 INFO [train.py:763] (0/8) Epoch 9, batch 1300, loss[loss=0.1638, simple_loss=0.2512, pruned_loss=0.03817, over 7026.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2906, pruned_loss=0.05297, over 1416997.85 frames.], batch size: 16, lr: 7.63e-04
+2022-04-28 22:34:16,575 INFO [train.py:763] (0/8) Epoch 9, batch 1350, loss[loss=0.2121, simple_loss=0.31, pruned_loss=0.05708, over 7309.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2906, pruned_loss=0.05317, over 1416691.23 frames.], batch size: 21, lr: 7.62e-04
+2022-04-28 22:35:21,685 INFO [train.py:763] (0/8) Epoch 9, batch 1400, loss[loss=0.203, simple_loss=0.3038, pruned_loss=0.05111, over 7118.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2918, pruned_loss=0.05377, over 1419896.26 frames.], batch size: 21, lr: 7.62e-04
+2022-04-28 22:36:27,464 INFO [train.py:763] (0/8) Epoch 9, batch 1450, loss[loss=0.2125, simple_loss=0.2946, pruned_loss=0.06517, over 7301.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2905, pruned_loss=0.05316, over 1420570.41 frames.], batch size: 25, lr: 7.62e-04
+2022-04-28 22:37:33,370 INFO [train.py:763] (0/8) Epoch 9, batch 1500, loss[loss=0.2458, simple_loss=0.3264, pruned_loss=0.08266, over 5169.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2906, pruned_loss=0.05285, over 1416099.55 frames.], batch size: 52, lr: 7.61e-04
+2022-04-28 22:38:38,711 INFO [train.py:763] (0/8) Epoch 9, batch 1550, loss[loss=0.2117, simple_loss=0.2948, pruned_loss=0.0643, over 7367.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2903, pruned_loss=0.05273, over 1419065.72 frames.], batch size: 19, lr: 7.61e-04
+2022-04-28 22:39:43,993 INFO [train.py:763] (0/8) Epoch 9, batch 1600, loss[loss=0.2322, simple_loss=0.313, pruned_loss=0.07566, over 7260.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2899, pruned_loss=0.05287, over 1417669.04 frames.], batch size: 19, lr: 7.60e-04
+2022-04-28 22:40:50,105 INFO [train.py:763] (0/8) Epoch 9, batch 1650, loss[loss=0.202, simple_loss=0.3055, pruned_loss=0.04925, over 7414.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2905, pruned_loss=0.05333, over 1415678.78 frames.], batch size: 21, lr: 7.60e-04
+2022-04-28 22:41:56,351 INFO [train.py:763] (0/8) Epoch 9, batch 1700, loss[loss=0.1969, simple_loss=0.2893, pruned_loss=0.05222, over 7301.00 frames.], tot_loss[loss=0.1972, simple_loss=0.289, pruned_loss=0.0527, over 1413265.32 frames.], batch size: 24, lr: 7.59e-04
+2022-04-28 22:43:01,522 INFO [train.py:763] (0/8) Epoch 9, batch 1750, loss[loss=0.1758, simple_loss=0.2538, pruned_loss=0.04896, over 7247.00 frames.], tot_loss[loss=0.198, simple_loss=0.2897, pruned_loss=0.05319, over 1405870.73 frames.], batch size: 16, lr: 7.59e-04
+2022-04-28 22:44:07,090 INFO [train.py:763] (0/8) Epoch 9, batch 1800, loss[loss=0.195, simple_loss=0.2901, pruned_loss=0.04993, over 7346.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2894, pruned_loss=0.05302, over 1410310.48 frames.], batch size: 19, lr: 7.59e-04
+2022-04-28 22:45:14,113 INFO [train.py:763] (0/8) Epoch 9, batch 1850, loss[loss=0.2098, simple_loss=0.2912, pruned_loss=0.06418, over 7371.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2907, pruned_loss=0.05394, over 1410725.89 frames.], batch size: 19, lr: 7.58e-04
+2022-04-28 22:46:21,658 INFO [train.py:763] (0/8) Epoch 9, batch 1900, loss[loss=0.185, simple_loss=0.2707, pruned_loss=0.04968, over 7271.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2895, pruned_loss=0.05296, over 1414442.63 frames.], batch size: 18, lr: 7.58e-04
+2022-04-28 22:47:28,659 INFO [train.py:763] (0/8) Epoch 9, batch 1950, loss[loss=0.2498, simple_loss=0.3348, pruned_loss=0.0824, over 7203.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2902, pruned_loss=0.05367, over 1413450.71 frames.], batch size: 23, lr: 7.57e-04
+2022-04-28 22:48:34,059 INFO [train.py:763] (0/8) Epoch 9, batch 2000, loss[loss=0.1988, simple_loss=0.2936, pruned_loss=0.05195, over 7227.00 frames.], tot_loss[loss=0.1983, simple_loss=0.29, pruned_loss=0.05336, over 1416698.54 frames.], batch size: 20, lr: 7.57e-04
+2022-04-28 22:49:39,704 INFO [train.py:763] (0/8) Epoch 9, batch 2050, loss[loss=0.1727, simple_loss=0.2717, pruned_loss=0.03691, over 7194.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2903, pruned_loss=0.05317, over 1419504.78 frames.], batch size: 23, lr: 7.56e-04
+2022-04-28 22:50:45,169 INFO [train.py:763] (0/8) Epoch 9, batch 2100, loss[loss=0.1989, simple_loss=0.2925, pruned_loss=0.05264, over 7140.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2902, pruned_loss=0.05312, over 1424322.27 frames.], batch size: 20, lr: 7.56e-04
+2022-04-28 22:51:50,840 INFO [train.py:763] (0/8) Epoch 9, batch 2150, loss[loss=0.1572, simple_loss=0.2448, pruned_loss=0.03483, over 7424.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2887, pruned_loss=0.05243, over 1425723.66 frames.], batch size: 18, lr: 7.56e-04
+2022-04-28 22:52:56,062 INFO [train.py:763] (0/8) Epoch 9, batch 2200, loss[loss=0.2102, simple_loss=0.3029, pruned_loss=0.05877, over 6480.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2894, pruned_loss=0.05257, over 1426103.23 frames.], batch size: 38, lr: 7.55e-04
+2022-04-28 22:54:01,591 INFO [train.py:763] (0/8) Epoch 9, batch 2250, loss[loss=0.1967, simple_loss=0.3011, pruned_loss=0.04618, over 7321.00 frames.], tot_loss[loss=0.197, simple_loss=0.2892, pruned_loss=0.05243, over 1428458.27 frames.], batch size: 21, lr: 7.55e-04
+2022-04-28 22:55:07,229 INFO [train.py:763] (0/8) Epoch 9, batch 2300, loss[loss=0.2223, simple_loss=0.3137, pruned_loss=0.06546, over 7147.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2896, pruned_loss=0.05256, over 1426151.78 frames.], batch size: 20, lr: 7.54e-04
+2022-04-28 22:56:13,155 INFO [train.py:763] (0/8) Epoch 9, batch 2350, loss[loss=0.2215, simple_loss=0.3083, pruned_loss=0.06733, over 7182.00 frames.], tot_loss[loss=0.197, simple_loss=0.289, pruned_loss=0.05254, over 1424837.18 frames.], batch size: 22, lr: 7.54e-04
+2022-04-28 22:57:18,364 INFO [train.py:763] (0/8) Epoch 9, batch 2400, loss[loss=0.2044, simple_loss=0.2804, pruned_loss=0.06421, over 7269.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2889, pruned_loss=0.0523, over 1427032.79 frames.], batch size: 18, lr: 7.53e-04
+2022-04-28 22:58:24,898 INFO [train.py:763] (0/8) Epoch 9, batch 2450, loss[loss=0.1586, simple_loss=0.2483, pruned_loss=0.03446, over 7068.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2886, pruned_loss=0.05241, over 1430162.09 frames.], batch size: 18, lr: 7.53e-04
+2022-04-28 22:59:30,596 INFO [train.py:763] (0/8) Epoch 9, batch 2500, loss[loss=0.1748, simple_loss=0.2782, pruned_loss=0.03566, over 7322.00 frames.], tot_loss[loss=0.1963, simple_loss=0.288, pruned_loss=0.05231, over 1428172.16 frames.], batch size: 21, lr: 7.53e-04
+2022-04-28 23:00:35,857 INFO [train.py:763] (0/8) Epoch 9, batch 2550, loss[loss=0.2414, simple_loss=0.3323, pruned_loss=0.07523, over 7213.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2887, pruned_loss=0.05298, over 1426922.53 frames.], batch size: 21, lr: 7.52e-04
+2022-04-28 23:01:42,065 INFO [train.py:763] (0/8) Epoch 9, batch 2600, loss[loss=0.2355, simple_loss=0.3285, pruned_loss=0.07127, over 7119.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2888, pruned_loss=0.05279, over 1429913.57 frames.], batch size: 26, lr: 7.52e-04
+2022-04-28 23:02:47,169 INFO [train.py:763] (0/8) Epoch 9, batch 2650, loss[loss=0.2151, simple_loss=0.3074, pruned_loss=0.06142, over 7338.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2903, pruned_loss=0.05322, over 1426578.72 frames.], batch size: 22, lr: 7.51e-04
+2022-04-28 23:03:53,448 INFO [train.py:763] (0/8) Epoch 9, batch 2700, loss[loss=0.1868, simple_loss=0.2843, pruned_loss=0.04464, over 6730.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2893, pruned_loss=0.0526, over 1426871.92 frames.], batch size: 31, lr: 7.51e-04
+2022-04-28 23:04:58,887 INFO [train.py:763] (0/8) Epoch 9, batch 2750, loss[loss=0.2098, simple_loss=0.3017, pruned_loss=0.05891, over 6764.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2882, pruned_loss=0.05264, over 1424379.79 frames.], batch size: 31, lr: 7.50e-04
+2022-04-28 23:06:04,508 INFO [train.py:763] (0/8) Epoch 9, batch 2800, loss[loss=0.2327, simple_loss=0.323, pruned_loss=0.07123, over 7364.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2882, pruned_loss=0.05245, over 1429000.13 frames.], batch size: 23, lr: 7.50e-04
+2022-04-28 23:07:09,875 INFO [train.py:763] (0/8) Epoch 9, batch 2850, loss[loss=0.1948, simple_loss=0.2989, pruned_loss=0.04538, over 7359.00 frames.], tot_loss[loss=0.1965, simple_loss=0.288, pruned_loss=0.05252, over 1426801.56 frames.], batch size: 22, lr: 7.50e-04
+2022-04-28 23:08:15,558 INFO [train.py:763] (0/8) Epoch 9, batch 2900, loss[loss=0.2061, simple_loss=0.3033, pruned_loss=0.05447, over 7111.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2879, pruned_loss=0.05198, over 1425382.00 frames.], batch size: 21, lr: 7.49e-04
+2022-04-28 23:09:22,020 INFO [train.py:763] (0/8) Epoch 9, batch 2950, loss[loss=0.172, simple_loss=0.2586, pruned_loss=0.04267, over 7275.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2875, pruned_loss=0.05188, over 1425578.14 frames.], batch size: 18, lr: 7.49e-04
+2022-04-28 23:10:28,999 INFO [train.py:763] (0/8) Epoch 9, batch 3000, loss[loss=0.1812, simple_loss=0.2679, pruned_loss=0.0473, over 7278.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2879, pruned_loss=0.05231, over 1425453.27 frames.], batch size: 17, lr: 7.48e-04
+2022-04-28 23:10:29,001 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-28 23:10:44,551 INFO [train.py:792] (0/8) Epoch 9, validation: loss=0.1713, simple_loss=0.276, pruned_loss=0.03324, over 698248.00 frames.
+2022-04-28 23:11:50,382 INFO [train.py:763] (0/8) Epoch 9, batch 3050, loss[loss=0.2046, simple_loss=0.2955, pruned_loss=0.05687, over 7160.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2882, pruned_loss=0.0525, over 1425515.29 frames.], batch size: 19, lr: 7.48e-04
+2022-04-28 23:12:55,859 INFO [train.py:763] (0/8) Epoch 9, batch 3100, loss[loss=0.2033, simple_loss=0.3051, pruned_loss=0.05081, over 7114.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2882, pruned_loss=0.05196, over 1428170.47 frames.], batch size: 21, lr: 7.47e-04
+2022-04-28 23:14:01,349 INFO [train.py:763] (0/8) Epoch 9, batch 3150, loss[loss=0.2455, simple_loss=0.3275, pruned_loss=0.08174, over 7328.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2884, pruned_loss=0.05226, over 1424536.33 frames.], batch size: 21, lr: 7.47e-04
+2022-04-28 23:15:07,619 INFO [train.py:763] (0/8) Epoch 9, batch 3200, loss[loss=0.1947, simple_loss=0.2947, pruned_loss=0.04741, over 7234.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2871, pruned_loss=0.05167, over 1424890.04 frames.], batch size: 20, lr: 7.47e-04
+2022-04-28 23:16:13,889 INFO [train.py:763] (0/8) Epoch 9, batch 3250, loss[loss=0.1828, simple_loss=0.2917, pruned_loss=0.03702, over 7411.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2889, pruned_loss=0.05227, over 1426228.13 frames.], batch size: 21, lr: 7.46e-04
+2022-04-28 23:17:19,394 INFO [train.py:763] (0/8) Epoch 9, batch 3300, loss[loss=0.2, simple_loss=0.2962, pruned_loss=0.05187, over 7199.00 frames.], tot_loss[loss=0.1967, simple_loss=0.289, pruned_loss=0.05225, over 1427639.01 frames.], batch size: 22, lr: 7.46e-04
+2022-04-28 23:18:25,157 INFO [train.py:763] (0/8) Epoch 9, batch 3350, loss[loss=0.2207, simple_loss=0.3099, pruned_loss=0.06581, over 7202.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2889, pruned_loss=0.05204, over 1429044.02 frames.], batch size: 23, lr: 7.45e-04
+2022-04-28 23:19:31,234 INFO [train.py:763] (0/8) Epoch 9, batch 3400, loss[loss=0.1568, simple_loss=0.2401, pruned_loss=0.03679, over 7295.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2888, pruned_loss=0.05234, over 1425150.42 frames.], batch size: 17, lr: 7.45e-04
+2022-04-28 23:20:36,548 INFO [train.py:763] (0/8) Epoch 9, batch 3450, loss[loss=0.2018, simple_loss=0.299, pruned_loss=0.05229, over 7297.00 frames.], tot_loss[loss=0.1959, simple_loss=0.288, pruned_loss=0.05189, over 1424410.29 frames.], batch size: 24, lr: 7.45e-04
+2022-04-28 23:21:42,135 INFO [train.py:763] (0/8) Epoch 9, batch 3500, loss[loss=0.2344, simple_loss=0.3272, pruned_loss=0.07083, over 7422.00 frames.], tot_loss[loss=0.1957, simple_loss=0.288, pruned_loss=0.05169, over 1424841.56 frames.], batch size: 21, lr: 7.44e-04
+2022-04-28 23:22:49,861 INFO [train.py:763] (0/8) Epoch 9, batch 3550, loss[loss=0.195, simple_loss=0.2939, pruned_loss=0.04803, over 7029.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2872, pruned_loss=0.05148, over 1427609.04 frames.], batch size: 28, lr: 7.44e-04
+2022-04-28 23:23:55,519 INFO [train.py:763] (0/8) Epoch 9, batch 3600, loss[loss=0.1951, simple_loss=0.2901, pruned_loss=0.05002, over 7075.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2874, pruned_loss=0.05167, over 1427213.27 frames.], batch size: 28, lr: 7.43e-04
+2022-04-28 23:25:02,076 INFO [train.py:763] (0/8) Epoch 9, batch 3650, loss[loss=0.2026, simple_loss=0.286, pruned_loss=0.05957, over 7066.00 frames.], tot_loss[loss=0.1954, simple_loss=0.287, pruned_loss=0.0519, over 1422782.29 frames.], batch size: 18, lr: 7.43e-04
+2022-04-28 23:26:07,311 INFO [train.py:763] (0/8) Epoch 9, batch 3700, loss[loss=0.1913, simple_loss=0.2821, pruned_loss=0.05028, over 7276.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2886, pruned_loss=0.05296, over 1425650.31 frames.], batch size: 17, lr: 7.43e-04
+2022-04-28 23:27:12,611 INFO [train.py:763] (0/8) Epoch 9, batch 3750, loss[loss=0.19, simple_loss=0.2903, pruned_loss=0.04486, over 7155.00 frames.], tot_loss[loss=0.198, simple_loss=0.2896, pruned_loss=0.05323, over 1428205.23 frames.], batch size: 19, lr: 7.42e-04
+2022-04-28 23:28:17,828 INFO [train.py:763] (0/8) Epoch 9, batch 3800, loss[loss=0.1807, simple_loss=0.2694, pruned_loss=0.046, over 7429.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2898, pruned_loss=0.05327, over 1426118.72 frames.], batch size: 20, lr: 7.42e-04
+2022-04-28 23:29:23,014 INFO [train.py:763] (0/8) Epoch 9, batch 3850, loss[loss=0.1953, simple_loss=0.2779, pruned_loss=0.05635, over 7454.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2902, pruned_loss=0.05327, over 1425940.40 frames.], batch size: 19, lr: 7.41e-04
+2022-04-28 23:30:28,557 INFO [train.py:763] (0/8) Epoch 9, batch 3900, loss[loss=0.1904, simple_loss=0.2771, pruned_loss=0.0518, over 7150.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2888, pruned_loss=0.0527, over 1427709.74 frames.], batch size: 19, lr: 7.41e-04
+2022-04-28 23:31:35,180 INFO [train.py:763] (0/8) Epoch 9, batch 3950, loss[loss=0.2356, simple_loss=0.3058, pruned_loss=0.08275, over 5134.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2887, pruned_loss=0.05272, over 1422405.05 frames.], batch size: 54, lr: 7.41e-04
+2022-04-28 23:32:42,036 INFO [train.py:763] (0/8) Epoch 9, batch 4000, loss[loss=0.1909, simple_loss=0.2893, pruned_loss=0.04623, over 7266.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2903, pruned_loss=0.05368, over 1423563.24 frames.], batch size: 19, lr: 7.40e-04
+2022-04-28 23:33:47,291 INFO [train.py:763] (0/8) Epoch 9, batch 4050, loss[loss=0.1716, simple_loss=0.2623, pruned_loss=0.04046, over 7144.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2891, pruned_loss=0.05297, over 1423274.78 frames.], batch size: 17, lr: 7.40e-04
+2022-04-28 23:34:53,574 INFO [train.py:763] (0/8) Epoch 9, batch 4100, loss[loss=0.2037, simple_loss=0.3047, pruned_loss=0.05137, over 7312.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2891, pruned_loss=0.05229, over 1425533.39 frames.], batch size: 21, lr: 7.39e-04
+2022-04-28 23:35:59,484 INFO [train.py:763] (0/8) Epoch 9, batch 4150, loss[loss=0.1574, simple_loss=0.2479, pruned_loss=0.03349, over 7405.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2882, pruned_loss=0.0517, over 1425565.43 frames.], batch size: 18, lr: 7.39e-04
+2022-04-28 23:37:04,703 INFO [train.py:763] (0/8) Epoch 9, batch 4200, loss[loss=0.1941, simple_loss=0.2849, pruned_loss=0.05165, over 7274.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2891, pruned_loss=0.05213, over 1427135.31 frames.], batch size: 24, lr: 7.39e-04
+2022-04-28 23:38:10,559 INFO [train.py:763] (0/8) Epoch 9, batch 4250, loss[loss=0.1859, simple_loss=0.2671, pruned_loss=0.05236, over 7258.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2894, pruned_loss=0.05216, over 1422855.58 frames.], batch size: 17, lr: 7.38e-04
+2022-04-28 23:39:16,468 INFO [train.py:763] (0/8) Epoch 9, batch 4300, loss[loss=0.1809, simple_loss=0.2859, pruned_loss=0.03796, over 7295.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2893, pruned_loss=0.05224, over 1418125.99 frames.], batch size: 24, lr: 7.38e-04
+2022-04-28 23:40:22,459 INFO [train.py:763] (0/8) Epoch 9, batch 4350, loss[loss=0.2238, simple_loss=0.2979, pruned_loss=0.07488, over 5079.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2909, pruned_loss=0.05286, over 1408028.83 frames.], batch size: 53, lr: 7.37e-04
+2022-04-28 23:41:28,481 INFO [train.py:763] (0/8) Epoch 9, batch 4400, loss[loss=0.1968, simple_loss=0.2922, pruned_loss=0.05069, over 7220.00 frames.], tot_loss[loss=0.199, simple_loss=0.2916, pruned_loss=0.05316, over 1410840.23 frames.], batch size: 22, lr: 7.37e-04
+2022-04-28 23:42:35,225 INFO [train.py:763] (0/8) Epoch 9, batch 4450, loss[loss=0.2768, simple_loss=0.3424, pruned_loss=0.1055, over 4821.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2921, pruned_loss=0.05357, over 1395904.35 frames.], batch size: 52, lr: 7.37e-04
+2022-04-28 23:43:41,396 INFO [train.py:763] (0/8) Epoch 9, batch 4500, loss[loss=0.2609, simple_loss=0.3286, pruned_loss=0.09657, over 7143.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2911, pruned_loss=0.05372, over 1391778.99 frames.], batch size: 20, lr: 7.36e-04
+2022-04-28 23:44:47,999 INFO [train.py:763] (0/8) Epoch 9, batch 4550, loss[loss=0.1879, simple_loss=0.2926, pruned_loss=0.04157, over 7117.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2909, pruned_loss=0.05405, over 1373898.48 frames.], batch size: 26, lr: 7.36e-04
+2022-04-28 23:45:38,418 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-9.pt
+2022-04-28 23:46:26,283 INFO [train.py:763] (0/8) Epoch 10, batch 0, loss[loss=0.2283, simple_loss=0.3154, pruned_loss=0.0706, over 7440.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3154, pruned_loss=0.0706, over 7440.00 frames.], batch size: 20, lr: 7.08e-04
+2022-04-28 23:47:32,330 INFO [train.py:763] (0/8) Epoch 10, batch 50, loss[loss=0.1671, simple_loss=0.2558, pruned_loss=0.03921, over 7433.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2882, pruned_loss=0.04944, over 322475.31 frames.], batch size: 20, lr: 7.08e-04
+2022-04-28 23:48:38,934 INFO [train.py:763] (0/8) Epoch 10, batch 100, loss[loss=0.1855, simple_loss=0.2734, pruned_loss=0.04875, over 7289.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2882, pruned_loss=0.05063, over 566858.02 frames.], batch size: 18, lr: 7.08e-04
+2022-04-28 23:49:55,138 INFO [train.py:763] (0/8) Epoch 10, batch 150, loss[loss=0.1564, simple_loss=0.2511, pruned_loss=0.03083, over 6791.00 frames.], tot_loss[loss=0.1962, simple_loss=0.29, pruned_loss=0.0512, over 759661.63 frames.], batch size: 15, lr: 7.07e-04
+2022-04-28 23:51:18,550 INFO [train.py:763] (0/8) Epoch 10, batch 200, loss[loss=0.1663, simple_loss=0.2569, pruned_loss=0.03781, over 7410.00 frames.], tot_loss[loss=0.195, simple_loss=0.2892, pruned_loss=0.05041, over 907534.29 frames.], batch size: 18, lr: 7.07e-04
+2022-04-28 23:52:32,867 INFO [train.py:763] (0/8) Epoch 10, batch 250, loss[loss=0.1926, simple_loss=0.2794, pruned_loss=0.0529, over 6465.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2872, pruned_loss=0.04966, over 1023533.26 frames.], batch size: 38, lr: 7.06e-04
+2022-04-28 23:53:48,230 INFO [train.py:763] (0/8) Epoch 10, batch 300, loss[loss=0.2242, simple_loss=0.3103, pruned_loss=0.06907, over 4992.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2865, pruned_loss=0.04918, over 1114490.14 frames.], batch size: 52, lr: 7.06e-04
+2022-04-28 23:54:53,621 INFO [train.py:763] (0/8) Epoch 10, batch 350, loss[loss=0.2331, simple_loss=0.3244, pruned_loss=0.07091, over 6762.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2869, pruned_loss=0.04932, over 1186860.54 frames.], batch size: 31, lr: 7.06e-04
+2022-04-28 23:56:17,504 INFO [train.py:763] (0/8) Epoch 10, batch 400, loss[loss=0.1958, simple_loss=0.2825, pruned_loss=0.0546, over 7420.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2876, pruned_loss=0.05006, over 1241069.72 frames.], batch size: 20, lr: 7.05e-04
+2022-04-28 23:57:23,263 INFO [train.py:763] (0/8) Epoch 10, batch 450, loss[loss=0.2237, simple_loss=0.3048, pruned_loss=0.07136, over 7235.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2859, pruned_loss=0.04939, over 1280930.50 frames.], batch size: 20, lr: 7.05e-04
+2022-04-28 23:58:37,644 INFO [train.py:763] (0/8) Epoch 10, batch 500, loss[loss=0.2079, simple_loss=0.2925, pruned_loss=0.0616, over 7333.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2852, pruned_loss=0.04897, over 1315415.49 frames.], batch size: 20, lr: 7.04e-04
+2022-04-28 23:59:42,735 INFO [train.py:763] (0/8) Epoch 10, batch 550, loss[loss=0.2056, simple_loss=0.288, pruned_loss=0.06159, over 7072.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2856, pruned_loss=0.04958, over 1340521.52 frames.], batch size: 18, lr: 7.04e-04
+2022-04-29 00:00:47,816 INFO [train.py:763] (0/8) Epoch 10, batch 600, loss[loss=0.1892, simple_loss=0.2678, pruned_loss=0.05531, over 6998.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2854, pruned_loss=0.04954, over 1359663.32 frames.], batch size: 16, lr: 7.04e-04
+2022-04-29 00:01:53,011 INFO [train.py:763] (0/8) Epoch 10, batch 650, loss[loss=0.1563, simple_loss=0.2483, pruned_loss=0.0322, over 7122.00 frames.], tot_loss[loss=0.193, simple_loss=0.2858, pruned_loss=0.0501, over 1366014.91 frames.], batch size: 17, lr: 7.03e-04
+2022-04-29 00:02:58,041 INFO [train.py:763] (0/8) Epoch 10, batch 700, loss[loss=0.1595, simple_loss=0.2467, pruned_loss=0.0361, over 6754.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2871, pruned_loss=0.05049, over 1376094.32 frames.], batch size: 15, lr: 7.03e-04
+2022-04-29 00:04:03,198 INFO [train.py:763] (0/8) Epoch 10, batch 750, loss[loss=0.2032, simple_loss=0.302, pruned_loss=0.0522, over 7147.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2876, pruned_loss=0.05084, over 1382448.38 frames.], batch size: 20, lr: 7.03e-04
+2022-04-29 00:05:08,477 INFO [train.py:763] (0/8) Epoch 10, batch 800, loss[loss=0.2257, simple_loss=0.3224, pruned_loss=0.06456, over 7167.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2863, pruned_loss=0.04951, over 1394159.37 frames.], batch size: 26, lr: 7.02e-04
+2022-04-29 00:06:13,829 INFO [train.py:763] (0/8) Epoch 10, batch 850, loss[loss=0.2163, simple_loss=0.31, pruned_loss=0.06129, over 7326.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2863, pruned_loss=0.04956, over 1398376.29 frames.], batch size: 20, lr: 7.02e-04
+2022-04-29 00:07:19,246 INFO [train.py:763] (0/8) Epoch 10, batch 900, loss[loss=0.1781, simple_loss=0.2682, pruned_loss=0.04397, over 7423.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2859, pruned_loss=0.04972, over 1406891.60 frames.], batch size: 20, lr: 7.02e-04
+2022-04-29 00:08:24,544 INFO [train.py:763] (0/8) Epoch 10, batch 950, loss[loss=0.1667, simple_loss=0.2532, pruned_loss=0.04008, over 6981.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2862, pruned_loss=0.0501, over 1408575.85 frames.], batch size: 16, lr: 7.01e-04
+2022-04-29 00:09:29,924 INFO [train.py:763] (0/8) Epoch 10, batch 1000, loss[loss=0.1994, simple_loss=0.2973, pruned_loss=0.05077, over 7309.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2854, pruned_loss=0.04981, over 1413543.60 frames.], batch size: 25, lr: 7.01e-04
+2022-04-29 00:10:35,521 INFO [train.py:763] (0/8) Epoch 10, batch 1050, loss[loss=0.1731, simple_loss=0.2651, pruned_loss=0.04058, over 7258.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2868, pruned_loss=0.05026, over 1408141.84 frames.], batch size: 19, lr: 7.00e-04
+2022-04-29 00:11:41,114 INFO [train.py:763] (0/8) Epoch 10, batch 1100, loss[loss=0.1674, simple_loss=0.2642, pruned_loss=0.03528, over 7161.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2866, pruned_loss=0.04991, over 1413079.13 frames.], batch size: 18, lr: 7.00e-04
+2022-04-29 00:12:46,595 INFO [train.py:763] (0/8) Epoch 10, batch 1150, loss[loss=0.1845, simple_loss=0.2759, pruned_loss=0.04651, over 7068.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2859, pruned_loss=0.04971, over 1416632.23 frames.], batch size: 18, lr: 7.00e-04
+2022-04-29 00:13:53,264 INFO [train.py:763] (0/8) Epoch 10, batch 1200, loss[loss=0.1645, simple_loss=0.2531, pruned_loss=0.03798, over 6769.00 frames.], tot_loss[loss=0.1921, simple_loss=0.285, pruned_loss=0.04966, over 1419289.51 frames.], batch size: 15, lr: 6.99e-04
+2022-04-29 00:14:58,988 INFO [train.py:763] (0/8) Epoch 10, batch 1250, loss[loss=0.1871, simple_loss=0.2775, pruned_loss=0.04837, over 7123.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2853, pruned_loss=0.04992, over 1423333.47 frames.], batch size: 17, lr: 6.99e-04
+2022-04-29 00:16:04,767 INFO [train.py:763] (0/8) Epoch 10, batch 1300, loss[loss=0.1929, simple_loss=0.2865, pruned_loss=0.04965, over 7314.00 frames.], tot_loss[loss=0.192, simple_loss=0.285, pruned_loss=0.04949, over 1419701.60 frames.], batch size: 21, lr: 6.99e-04
+2022-04-29 00:17:11,810 INFO [train.py:763] (0/8) Epoch 10, batch 1350, loss[loss=0.2074, simple_loss=0.3065, pruned_loss=0.05421, over 7327.00 frames.], tot_loss[loss=0.193, simple_loss=0.286, pruned_loss=0.05001, over 1423902.26 frames.], batch size: 21, lr: 6.98e-04
+2022-04-29 00:18:18,363 INFO [train.py:763] (0/8) Epoch 10, batch 1400, loss[loss=0.2039, simple_loss=0.2936, pruned_loss=0.05712, over 7157.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2864, pruned_loss=0.05062, over 1426937.83 frames.], batch size: 19, lr: 6.98e-04
+2022-04-29 00:19:25,283 INFO [train.py:763] (0/8) Epoch 10, batch 1450, loss[loss=0.1833, simple_loss=0.2645, pruned_loss=0.05099, over 7290.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2867, pruned_loss=0.05076, over 1427418.62 frames.], batch size: 17, lr: 6.97e-04
+2022-04-29 00:20:30,755 INFO [train.py:763] (0/8) Epoch 10, batch 1500, loss[loss=0.2028, simple_loss=0.3026, pruned_loss=0.05147, over 7035.00 frames.], tot_loss[loss=0.194, simple_loss=0.2868, pruned_loss=0.05063, over 1425660.27 frames.], batch size: 28, lr: 6.97e-04
+2022-04-29 00:21:36,433 INFO [train.py:763] (0/8) Epoch 10, batch 1550, loss[loss=0.1875, simple_loss=0.2807, pruned_loss=0.04716, over 7427.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2866, pruned_loss=0.05051, over 1424103.98 frames.], batch size: 20, lr: 6.97e-04
+2022-04-29 00:22:41,651 INFO [train.py:763] (0/8) Epoch 10, batch 1600, loss[loss=0.2164, simple_loss=0.3023, pruned_loss=0.06522, over 6736.00 frames.], tot_loss[loss=0.194, simple_loss=0.2865, pruned_loss=0.05078, over 1418526.83 frames.], batch size: 31, lr: 6.96e-04
+2022-04-29 00:23:47,732 INFO [train.py:763] (0/8) Epoch 10, batch 1650, loss[loss=0.178, simple_loss=0.2648, pruned_loss=0.04559, over 6759.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2876, pruned_loss=0.05135, over 1418154.02 frames.], batch size: 15, lr: 6.96e-04
+2022-04-29 00:24:52,740 INFO [train.py:763] (0/8) Epoch 10, batch 1700, loss[loss=0.1764, simple_loss=0.262, pruned_loss=0.04537, over 6785.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2876, pruned_loss=0.05079, over 1417796.59 frames.], batch size: 15, lr: 6.96e-04
+2022-04-29 00:25:58,401 INFO [train.py:763] (0/8) Epoch 10, batch 1750, loss[loss=0.2002, simple_loss=0.2953, pruned_loss=0.05256, over 7103.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2864, pruned_loss=0.05042, over 1414512.33 frames.], batch size: 21, lr: 6.95e-04
+2022-04-29 00:27:03,857 INFO [train.py:763] (0/8) Epoch 10, batch 1800, loss[loss=0.231, simple_loss=0.3086, pruned_loss=0.07667, over 4836.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2863, pruned_loss=0.05017, over 1414899.15 frames.], batch size: 53, lr: 6.95e-04
+2022-04-29 00:28:10,769 INFO [train.py:763] (0/8) Epoch 10, batch 1850, loss[loss=0.2119, simple_loss=0.3048, pruned_loss=0.05945, over 6569.00 frames.], tot_loss[loss=0.193, simple_loss=0.2861, pruned_loss=0.04991, over 1418855.16 frames.], batch size: 38, lr: 6.95e-04
+2022-04-29 00:29:17,826 INFO [train.py:763] (0/8) Epoch 10, batch 1900, loss[loss=0.1882, simple_loss=0.296, pruned_loss=0.04022, over 7320.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2863, pruned_loss=0.0498, over 1423070.42 frames.], batch size: 21, lr: 6.94e-04
+2022-04-29 00:30:24,817 INFO [train.py:763] (0/8) Epoch 10, batch 1950, loss[loss=0.1902, simple_loss=0.2853, pruned_loss=0.04755, over 7364.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2865, pruned_loss=0.05036, over 1422125.92 frames.], batch size: 19, lr: 6.94e-04
+2022-04-29 00:31:31,798 INFO [train.py:763] (0/8) Epoch 10, batch 2000, loss[loss=0.1943, simple_loss=0.286, pruned_loss=0.05131, over 7166.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2873, pruned_loss=0.05062, over 1423030.41 frames.], batch size: 18, lr: 6.93e-04
+2022-04-29 00:32:38,670 INFO [train.py:763] (0/8) Epoch 10, batch 2050, loss[loss=0.1573, simple_loss=0.2436, pruned_loss=0.03551, over 7290.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2868, pruned_loss=0.05021, over 1424577.31 frames.], batch size: 17, lr: 6.93e-04
+2022-04-29 00:33:45,459 INFO [train.py:763] (0/8) Epoch 10, batch 2100, loss[loss=0.2158, simple_loss=0.3067, pruned_loss=0.06242, over 7382.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2861, pruned_loss=0.05004, over 1425088.36 frames.], batch size: 23, lr: 6.93e-04
+2022-04-29 00:34:10,192 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-48000.pt
+2022-04-29 00:35:01,081 INFO [train.py:763] (0/8) Epoch 10, batch 2150, loss[loss=0.1823, simple_loss=0.2834, pruned_loss=0.04064, over 7175.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2863, pruned_loss=0.05017, over 1425356.96 frames.], batch size: 18, lr: 6.92e-04
+2022-04-29 00:36:06,569 INFO [train.py:763] (0/8) Epoch 10, batch 2200, loss[loss=0.1997, simple_loss=0.2969, pruned_loss=0.05129, over 7232.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2867, pruned_loss=0.0505, over 1422673.48 frames.], batch size: 20, lr: 6.92e-04
+2022-04-29 00:37:11,930 INFO [train.py:763] (0/8) Epoch 10, batch 2250, loss[loss=0.1942, simple_loss=0.2928, pruned_loss=0.0478, over 7325.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2884, pruned_loss=0.05089, over 1425762.11 frames.], batch size: 22, lr: 6.92e-04
+2022-04-29 00:38:17,414 INFO [train.py:763] (0/8) Epoch 10, batch 2300, loss[loss=0.2289, simple_loss=0.3294, pruned_loss=0.06421, over 7155.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2882, pruned_loss=0.05084, over 1426329.76 frames.], batch size: 26, lr: 6.91e-04
+2022-04-29 00:39:22,713 INFO [train.py:763] (0/8) Epoch 10, batch 2350, loss[loss=0.199, simple_loss=0.2971, pruned_loss=0.05045, over 6781.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2867, pruned_loss=0.05023, over 1428576.31 frames.], batch size: 31, lr: 6.91e-04
+2022-04-29 00:40:27,870 INFO [train.py:763] (0/8) Epoch 10, batch 2400, loss[loss=0.1961, simple_loss=0.2978, pruned_loss=0.04721, over 7323.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2861, pruned_loss=0.05012, over 1423568.37 frames.], batch size: 21, lr: 6.91e-04
+2022-04-29 00:41:33,302 INFO [train.py:763] (0/8) Epoch 10, batch 2450, loss[loss=0.2055, simple_loss=0.2881, pruned_loss=0.06145, over 6992.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2861, pruned_loss=0.05015, over 1424787.59 frames.], batch size: 16, lr: 6.90e-04
+2022-04-29 00:42:38,517 INFO [train.py:763] (0/8) Epoch 10, batch 2500, loss[loss=0.1754, simple_loss=0.2681, pruned_loss=0.04133, over 7165.00 frames.], tot_loss[loss=0.194, simple_loss=0.2871, pruned_loss=0.05043, over 1423065.10 frames.], batch size: 19, lr: 6.90e-04
+2022-04-29 00:43:44,255 INFO [train.py:763] (0/8) Epoch 10, batch 2550, loss[loss=0.1607, simple_loss=0.2566, pruned_loss=0.03237, over 6791.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2866, pruned_loss=0.05017, over 1426579.98 frames.], batch size: 15, lr: 6.90e-04
+2022-04-29 00:44:51,071 INFO [train.py:763] (0/8) Epoch 10, batch 2600, loss[loss=0.2125, simple_loss=0.3117, pruned_loss=0.05666, over 7372.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2864, pruned_loss=0.05017, over 1427613.22 frames.], batch size: 23, lr: 6.89e-04
+2022-04-29 00:45:56,187 INFO [train.py:763] (0/8) Epoch 10, batch 2650, loss[loss=0.1678, simple_loss=0.2503, pruned_loss=0.04268, over 6995.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2869, pruned_loss=0.05045, over 1423258.61 frames.], batch size: 16, lr: 6.89e-04
+2022-04-29 00:47:01,661 INFO [train.py:763] (0/8) Epoch 10, batch 2700, loss[loss=0.2019, simple_loss=0.2963, pruned_loss=0.05372, over 7420.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2868, pruned_loss=0.05005, over 1426064.44 frames.], batch size: 21, lr: 6.89e-04
+2022-04-29 00:48:08,169 INFO [train.py:763] (0/8) Epoch 10, batch 2750, loss[loss=0.204, simple_loss=0.289, pruned_loss=0.05946, over 7307.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2869, pruned_loss=0.05063, over 1424925.31 frames.], batch size: 18, lr: 6.88e-04
+2022-04-29 00:49:13,517 INFO [train.py:763] (0/8) Epoch 10, batch 2800, loss[loss=0.181, simple_loss=0.2789, pruned_loss=0.04158, over 7161.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2873, pruned_loss=0.05084, over 1423783.52 frames.], batch size: 19, lr: 6.88e-04
+2022-04-29 00:50:19,056 INFO [train.py:763] (0/8) Epoch 10, batch 2850, loss[loss=0.1746, simple_loss=0.2712, pruned_loss=0.039, over 7317.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2863, pruned_loss=0.05037, over 1424885.36 frames.], batch size: 21, lr: 6.87e-04
+2022-04-29 00:51:24,561 INFO [train.py:763] (0/8) Epoch 10, batch 2900, loss[loss=0.2014, simple_loss=0.2913, pruned_loss=0.05574, over 7206.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2858, pruned_loss=0.05005, over 1427735.29 frames.], batch size: 23, lr: 6.87e-04
+2022-04-29 00:52:30,310 INFO [train.py:763] (0/8) Epoch 10, batch 2950, loss[loss=0.2358, simple_loss=0.334, pruned_loss=0.06883, over 7195.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2869, pruned_loss=0.05038, over 1424803.70 frames.], batch size: 22, lr: 6.87e-04
+2022-04-29 00:53:36,015 INFO [train.py:763] (0/8) Epoch 10, batch 3000, loss[loss=0.169, simple_loss=0.2613, pruned_loss=0.03832, over 7160.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2869, pruned_loss=0.05005, over 1423667.30 frames.], batch size: 18, lr: 6.86e-04
+2022-04-29 00:53:36,017 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 00:53:51,272 INFO [train.py:792] (0/8) Epoch 10, validation: loss=0.1689, simple_loss=0.2722, pruned_loss=0.03283, over 698248.00 frames.
+2022-04-29 00:54:57,778 INFO [train.py:763] (0/8) Epoch 10, batch 3050, loss[loss=0.2108, simple_loss=0.3127, pruned_loss=0.0545, over 7158.00 frames.], tot_loss[loss=0.1918, simple_loss=0.285, pruned_loss=0.04927, over 1428098.31 frames.], batch size: 26, lr: 6.86e-04
+2022-04-29 00:56:03,590 INFO [train.py:763] (0/8) Epoch 10, batch 3100, loss[loss=0.1632, simple_loss=0.2638, pruned_loss=0.03133, over 7426.00 frames.], tot_loss[loss=0.193, simple_loss=0.286, pruned_loss=0.05002, over 1426267.82 frames.], batch size: 18, lr: 6.86e-04
+2022-04-29 00:57:10,799 INFO [train.py:763] (0/8) Epoch 10, batch 3150, loss[loss=0.187, simple_loss=0.2771, pruned_loss=0.04846, over 7268.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2843, pruned_loss=0.04865, over 1428246.18 frames.], batch size: 18, lr: 6.85e-04
+2022-04-29 00:58:16,975 INFO [train.py:763] (0/8) Epoch 10, batch 3200, loss[loss=0.1677, simple_loss=0.2678, pruned_loss=0.03382, over 7167.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2841, pruned_loss=0.04907, over 1429476.94 frames.], batch size: 18, lr: 6.85e-04
+2022-04-29 00:59:22,571 INFO [train.py:763] (0/8) Epoch 10, batch 3250, loss[loss=0.1862, simple_loss=0.2878, pruned_loss=0.04234, over 7074.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2843, pruned_loss=0.04904, over 1430891.70 frames.], batch size: 18, lr: 6.85e-04
+2022-04-29 01:00:29,419 INFO [train.py:763] (0/8) Epoch 10, batch 3300, loss[loss=0.2322, simple_loss=0.3199, pruned_loss=0.07223, over 6384.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2842, pruned_loss=0.04903, over 1430357.54 frames.], batch size: 37, lr: 6.84e-04
+2022-04-29 01:01:36,490 INFO [train.py:763] (0/8) Epoch 10, batch 3350, loss[loss=0.1964, simple_loss=0.3047, pruned_loss=0.04399, over 7106.00 frames.], tot_loss[loss=0.1921, simple_loss=0.285, pruned_loss=0.04961, over 1423855.11 frames.], batch size: 21, lr: 6.84e-04
+2022-04-29 01:02:41,926 INFO [train.py:763] (0/8) Epoch 10, batch 3400, loss[loss=0.1633, simple_loss=0.2496, pruned_loss=0.03845, over 6990.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2854, pruned_loss=0.04969, over 1422003.34 frames.], batch size: 16, lr: 6.84e-04
+2022-04-29 01:03:47,415 INFO [train.py:763] (0/8) Epoch 10, batch 3450, loss[loss=0.213, simple_loss=0.3109, pruned_loss=0.05751, over 7106.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2855, pruned_loss=0.04942, over 1425052.44 frames.], batch size: 21, lr: 6.83e-04
+2022-04-29 01:04:52,725 INFO [train.py:763] (0/8) Epoch 10, batch 3500, loss[loss=0.1784, simple_loss=0.26, pruned_loss=0.04839, over 7419.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2853, pruned_loss=0.04975, over 1425703.80 frames.], batch size: 18, lr: 6.83e-04
+2022-04-29 01:05:58,216 INFO [train.py:763] (0/8) Epoch 10, batch 3550, loss[loss=0.1757, simple_loss=0.2774, pruned_loss=0.03704, over 6436.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2856, pruned_loss=0.04989, over 1424054.46 frames.], batch size: 38, lr: 6.83e-04
+2022-04-29 01:07:03,436 INFO [train.py:763] (0/8) Epoch 10, batch 3600, loss[loss=0.2019, simple_loss=0.2939, pruned_loss=0.05499, over 6418.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2864, pruned_loss=0.0503, over 1419899.56 frames.], batch size: 38, lr: 6.82e-04
+2022-04-29 01:08:09,039 INFO [train.py:763] (0/8) Epoch 10, batch 3650, loss[loss=0.2007, simple_loss=0.3046, pruned_loss=0.04844, over 7127.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2863, pruned_loss=0.05019, over 1422356.39 frames.], batch size: 21, lr: 6.82e-04
+2022-04-29 01:09:14,322 INFO [train.py:763] (0/8) Epoch 10, batch 3700, loss[loss=0.1889, simple_loss=0.2863, pruned_loss=0.04573, over 7116.00 frames.], tot_loss[loss=0.194, simple_loss=0.2868, pruned_loss=0.05059, over 1418461.51 frames.], batch size: 21, lr: 6.82e-04
+2022-04-29 01:10:20,246 INFO [train.py:763] (0/8) Epoch 10, batch 3750, loss[loss=0.1916, simple_loss=0.2849, pruned_loss=0.04913, over 7431.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2867, pruned_loss=0.05017, over 1424016.92 frames.], batch size: 20, lr: 6.81e-04
+2022-04-29 01:11:26,041 INFO [train.py:763] (0/8) Epoch 10, batch 3800, loss[loss=0.2089, simple_loss=0.2995, pruned_loss=0.05912, over 7279.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2861, pruned_loss=0.04979, over 1422294.08 frames.], batch size: 24, lr: 6.81e-04
+2022-04-29 01:12:32,921 INFO [train.py:763] (0/8) Epoch 10, batch 3850, loss[loss=0.2199, simple_loss=0.3204, pruned_loss=0.0597, over 7213.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2861, pruned_loss=0.04983, over 1426467.93 frames.], batch size: 22, lr: 6.81e-04
+2022-04-29 01:13:40,391 INFO [train.py:763] (0/8) Epoch 10, batch 3900, loss[loss=0.1988, simple_loss=0.2884, pruned_loss=0.05464, over 7376.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2855, pruned_loss=0.04949, over 1427294.10 frames.], batch size: 23, lr: 6.80e-04
+2022-04-29 01:14:47,760 INFO [train.py:763] (0/8) Epoch 10, batch 3950, loss[loss=0.1899, simple_loss=0.288, pruned_loss=0.04592, over 7430.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2852, pruned_loss=0.04913, over 1426676.38 frames.], batch size: 20, lr: 6.80e-04
+2022-04-29 01:15:53,617 INFO [train.py:763] (0/8) Epoch 10, batch 4000, loss[loss=0.1809, simple_loss=0.2776, pruned_loss=0.04209, over 7218.00 frames.], tot_loss[loss=0.192, simple_loss=0.2852, pruned_loss=0.04943, over 1417055.03 frames.], batch size: 21, lr: 6.80e-04
+2022-04-29 01:17:00,545 INFO [train.py:763] (0/8) Epoch 10, batch 4050, loss[loss=0.2069, simple_loss=0.2948, pruned_loss=0.05945, over 7214.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2854, pruned_loss=0.04992, over 1416945.37 frames.], batch size: 22, lr: 6.79e-04
+2022-04-29 01:18:07,367 INFO [train.py:763] (0/8) Epoch 10, batch 4100, loss[loss=0.2009, simple_loss=0.2814, pruned_loss=0.06024, over 7199.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2854, pruned_loss=0.04979, over 1417574.98 frames.], batch size: 22, lr: 6.79e-04
+2022-04-29 01:19:14,034 INFO [train.py:763] (0/8) Epoch 10, batch 4150, loss[loss=0.2132, simple_loss=0.314, pruned_loss=0.05616, over 6721.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2867, pruned_loss=0.05022, over 1414992.90 frames.], batch size: 31, lr: 6.79e-04
+2022-04-29 01:20:19,805 INFO [train.py:763] (0/8) Epoch 10, batch 4200, loss[loss=0.2048, simple_loss=0.2924, pruned_loss=0.05856, over 7082.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2867, pruned_loss=0.05013, over 1416116.13 frames.], batch size: 28, lr: 6.78e-04
+2022-04-29 01:21:26,034 INFO [train.py:763] (0/8) Epoch 10, batch 4250, loss[loss=0.2403, simple_loss=0.3134, pruned_loss=0.08362, over 4977.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2855, pruned_loss=0.04972, over 1415244.25 frames.], batch size: 52, lr: 6.78e-04
+2022-04-29 01:22:31,079 INFO [train.py:763] (0/8) Epoch 10, batch 4300, loss[loss=0.2237, simple_loss=0.3035, pruned_loss=0.07196, over 4861.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2864, pruned_loss=0.05088, over 1410682.26 frames.], batch size: 55, lr: 6.78e-04
+2022-04-29 01:23:36,201 INFO [train.py:763] (0/8) Epoch 10, batch 4350, loss[loss=0.2008, simple_loss=0.2913, pruned_loss=0.0551, over 7232.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2872, pruned_loss=0.05129, over 1409233.39 frames.], batch size: 20, lr: 6.77e-04
+2022-04-29 01:24:41,270 INFO [train.py:763] (0/8) Epoch 10, batch 4400, loss[loss=0.1831, simple_loss=0.2823, pruned_loss=0.04194, over 7188.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2873, pruned_loss=0.05107, over 1414755.54 frames.], batch size: 22, lr: 6.77e-04
+2022-04-29 01:25:46,580 INFO [train.py:763] (0/8) Epoch 10, batch 4450, loss[loss=0.2164, simple_loss=0.3134, pruned_loss=0.05971, over 7236.00 frames.], tot_loss[loss=0.196, simple_loss=0.2888, pruned_loss=0.05159, over 1417657.54 frames.], batch size: 20, lr: 6.77e-04
+2022-04-29 01:26:52,306 INFO [train.py:763] (0/8) Epoch 10, batch 4500, loss[loss=0.2287, simple_loss=0.3186, pruned_loss=0.06933, over 5371.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2903, pruned_loss=0.05233, over 1410156.40 frames.], batch size: 54, lr: 6.76e-04
+2022-04-29 01:27:57,106 INFO [train.py:763] (0/8) Epoch 10, batch 4550, loss[loss=0.213, simple_loss=0.2991, pruned_loss=0.06338, over 4961.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2924, pruned_loss=0.05461, over 1347080.60 frames.], batch size: 52, lr: 6.76e-04
+2022-04-29 01:28:46,435 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-10.pt
+2022-04-29 01:29:26,059 INFO [train.py:763] (0/8) Epoch 11, batch 0, loss[loss=0.2098, simple_loss=0.3105, pruned_loss=0.05459, over 7418.00 frames.], tot_loss[loss=0.2098, simple_loss=0.3105, pruned_loss=0.05459, over 7418.00 frames.], batch size: 21, lr: 6.52e-04
+2022-04-29 01:30:32,269 INFO [train.py:763] (0/8) Epoch 11, batch 50, loss[loss=0.2495, simple_loss=0.3337, pruned_loss=0.08264, over 5076.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2874, pruned_loss=0.05209, over 319225.36 frames.], batch size: 52, lr: 6.52e-04
+2022-04-29 01:31:38,381 INFO [train.py:763] (0/8) Epoch 11, batch 100, loss[loss=0.1646, simple_loss=0.2634, pruned_loss=0.03291, over 6271.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2884, pruned_loss=0.05097, over 558381.74 frames.], batch size: 37, lr: 6.51e-04
+2022-04-29 01:32:44,347 INFO [train.py:763] (0/8) Epoch 11, batch 150, loss[loss=0.1786, simple_loss=0.2686, pruned_loss=0.04427, over 7270.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2887, pruned_loss=0.05008, over 748147.53 frames.], batch size: 17, lr: 6.51e-04
+2022-04-29 01:33:50,260 INFO [train.py:763] (0/8) Epoch 11, batch 200, loss[loss=0.1953, simple_loss=0.3009, pruned_loss=0.04484, over 7199.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2887, pruned_loss=0.05033, over 895629.10 frames.], batch size: 22, lr: 6.51e-04
+2022-04-29 01:34:55,819 INFO [train.py:763] (0/8) Epoch 11, batch 250, loss[loss=0.1963, simple_loss=0.2974, pruned_loss=0.04754, over 6762.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2872, pruned_loss=0.04929, over 1013738.91 frames.], batch size: 31, lr: 6.50e-04
+2022-04-29 01:36:01,206 INFO [train.py:763] (0/8) Epoch 11, batch 300, loss[loss=0.1948, simple_loss=0.303, pruned_loss=0.04327, over 7197.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2878, pruned_loss=0.04982, over 1097870.99 frames.], batch size: 22, lr: 6.50e-04
+2022-04-29 01:37:06,948 INFO [train.py:763] (0/8) Epoch 11, batch 350, loss[loss=0.1784, simple_loss=0.2735, pruned_loss=0.04169, over 7332.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2864, pruned_loss=0.04964, over 1165411.71 frames.], batch size: 22, lr: 6.50e-04
+2022-04-29 01:38:12,679 INFO [train.py:763] (0/8) Epoch 11, batch 400, loss[loss=0.1612, simple_loss=0.2663, pruned_loss=0.02811, over 7349.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2863, pruned_loss=0.04949, over 1220739.45 frames.], batch size: 22, lr: 6.49e-04
+2022-04-29 01:39:18,306 INFO [train.py:763] (0/8) Epoch 11, batch 450, loss[loss=0.1861, simple_loss=0.2765, pruned_loss=0.04788, over 7153.00 frames.], tot_loss[loss=0.192, simple_loss=0.286, pruned_loss=0.04902, over 1268801.24 frames.], batch size: 19, lr: 6.49e-04
+2022-04-29 01:40:24,064 INFO [train.py:763] (0/8) Epoch 11, batch 500, loss[loss=0.2011, simple_loss=0.3108, pruned_loss=0.04571, over 7382.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2855, pruned_loss=0.04903, over 1302499.94 frames.], batch size: 23, lr: 6.49e-04
+2022-04-29 01:41:30,092 INFO [train.py:763] (0/8) Epoch 11, batch 550, loss[loss=0.2096, simple_loss=0.3096, pruned_loss=0.0548, over 7411.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2846, pruned_loss=0.04846, over 1328573.96 frames.], batch size: 21, lr: 6.48e-04
+2022-04-29 01:42:36,723 INFO [train.py:763] (0/8) Epoch 11, batch 600, loss[loss=0.1982, simple_loss=0.2988, pruned_loss=0.04876, over 7349.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2839, pruned_loss=0.04845, over 1349090.38 frames.], batch size: 22, lr: 6.48e-04
+2022-04-29 01:43:44,068 INFO [train.py:763] (0/8) Epoch 11, batch 650, loss[loss=0.2149, simple_loss=0.3083, pruned_loss=0.06079, over 7378.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2826, pruned_loss=0.04827, over 1370113.27 frames.], batch size: 23, lr: 6.48e-04
+2022-04-29 01:44:51,071 INFO [train.py:763] (0/8) Epoch 11, batch 700, loss[loss=0.2058, simple_loss=0.3094, pruned_loss=0.05106, over 7300.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2831, pruned_loss=0.04809, over 1380065.05 frames.], batch size: 24, lr: 6.47e-04
+2022-04-29 01:45:57,540 INFO [train.py:763] (0/8) Epoch 11, batch 750, loss[loss=0.2062, simple_loss=0.3022, pruned_loss=0.05508, over 7321.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2838, pruned_loss=0.04864, over 1385805.71 frames.], batch size: 20, lr: 6.47e-04
+2022-04-29 01:47:03,521 INFO [train.py:763] (0/8) Epoch 11, batch 800, loss[loss=0.1605, simple_loss=0.252, pruned_loss=0.03448, over 7414.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2836, pruned_loss=0.04848, over 1398002.24 frames.], batch size: 18, lr: 6.47e-04
+2022-04-29 01:48:08,967 INFO [train.py:763] (0/8) Epoch 11, batch 850, loss[loss=0.1953, simple_loss=0.2945, pruned_loss=0.04808, over 7003.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2835, pruned_loss=0.04804, over 1403870.01 frames.], batch size: 32, lr: 6.46e-04
+2022-04-29 01:49:14,794 INFO [train.py:763] (0/8) Epoch 11, batch 900, loss[loss=0.1912, simple_loss=0.3, pruned_loss=0.04118, over 7336.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2841, pruned_loss=0.04841, over 1407846.40 frames.], batch size: 22, lr: 6.46e-04
+2022-04-29 01:50:20,608 INFO [train.py:763] (0/8) Epoch 11, batch 950, loss[loss=0.1697, simple_loss=0.2594, pruned_loss=0.03997, over 7441.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2842, pruned_loss=0.04848, over 1412705.96 frames.], batch size: 20, lr: 6.46e-04
+2022-04-29 01:51:27,141 INFO [train.py:763] (0/8) Epoch 11, batch 1000, loss[loss=0.1786, simple_loss=0.2715, pruned_loss=0.04282, over 7148.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2847, pruned_loss=0.04852, over 1415593.69 frames.], batch size: 19, lr: 6.46e-04
+2022-04-29 01:52:32,493 INFO [train.py:763] (0/8) Epoch 11, batch 1050, loss[loss=0.1602, simple_loss=0.247, pruned_loss=0.03672, over 7000.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2851, pruned_loss=0.04865, over 1415008.20 frames.], batch size: 16, lr: 6.45e-04
+2022-04-29 01:53:38,740 INFO [train.py:763] (0/8) Epoch 11, batch 1100, loss[loss=0.1855, simple_loss=0.2769, pruned_loss=0.04703, over 7157.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2855, pruned_loss=0.04872, over 1417417.70 frames.], batch size: 19, lr: 6.45e-04
+2022-04-29 01:54:45,802 INFO [train.py:763] (0/8) Epoch 11, batch 1150, loss[loss=0.2513, simple_loss=0.3274, pruned_loss=0.08756, over 5331.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2853, pruned_loss=0.04888, over 1420930.72 frames.], batch size: 53, lr: 6.45e-04
+2022-04-29 01:55:51,961 INFO [train.py:763] (0/8) Epoch 11, batch 1200, loss[loss=0.1922, simple_loss=0.2902, pruned_loss=0.04708, over 7117.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2847, pruned_loss=0.04847, over 1423349.54 frames.], batch size: 21, lr: 6.44e-04
+2022-04-29 01:56:57,802 INFO [train.py:763] (0/8) Epoch 11, batch 1250, loss[loss=0.16, simple_loss=0.2553, pruned_loss=0.03236, over 6994.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2841, pruned_loss=0.04838, over 1424588.71 frames.], batch size: 16, lr: 6.44e-04
+2022-04-29 01:58:03,713 INFO [train.py:763] (0/8) Epoch 11, batch 1300, loss[loss=0.1617, simple_loss=0.2711, pruned_loss=0.02614, over 7321.00 frames.], tot_loss[loss=0.19, simple_loss=0.2838, pruned_loss=0.04807, over 1426483.67 frames.], batch size: 20, lr: 6.44e-04
+2022-04-29 01:59:10,175 INFO [train.py:763] (0/8) Epoch 11, batch 1350, loss[loss=0.1788, simple_loss=0.2751, pruned_loss=0.04119, over 7324.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2842, pruned_loss=0.04848, over 1423356.29 frames.], batch size: 21, lr: 6.43e-04
+2022-04-29 02:00:15,532 INFO [train.py:763] (0/8) Epoch 11, batch 1400, loss[loss=0.1967, simple_loss=0.2928, pruned_loss=0.05027, over 7325.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2839, pruned_loss=0.04877, over 1420465.13 frames.], batch size: 21, lr: 6.43e-04
+2022-04-29 02:01:21,170 INFO [train.py:763] (0/8) Epoch 11, batch 1450, loss[loss=0.1918, simple_loss=0.2875, pruned_loss=0.04801, over 7067.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2838, pruned_loss=0.04802, over 1420486.04 frames.], batch size: 18, lr: 6.43e-04
+2022-04-29 02:02:28,498 INFO [train.py:763] (0/8) Epoch 11, batch 1500, loss[loss=0.223, simple_loss=0.3099, pruned_loss=0.06801, over 7205.00 frames.], tot_loss[loss=0.1892, simple_loss=0.283, pruned_loss=0.04772, over 1424486.08 frames.], batch size: 23, lr: 6.42e-04
+2022-04-29 02:03:33,963 INFO [train.py:763] (0/8) Epoch 11, batch 1550, loss[loss=0.1911, simple_loss=0.2771, pruned_loss=0.05252, over 7236.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2832, pruned_loss=0.04801, over 1423899.74 frames.], batch size: 20, lr: 6.42e-04
+2022-04-29 02:04:39,641 INFO [train.py:763] (0/8) Epoch 11, batch 1600, loss[loss=0.167, simple_loss=0.2683, pruned_loss=0.03289, over 7354.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2843, pruned_loss=0.04866, over 1424987.23 frames.], batch size: 19, lr: 6.42e-04
+2022-04-29 02:06:04,020 INFO [train.py:763] (0/8) Epoch 11, batch 1650, loss[loss=0.1896, simple_loss=0.2906, pruned_loss=0.0443, over 7374.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2844, pruned_loss=0.0487, over 1425873.60 frames.], batch size: 23, lr: 6.42e-04
+2022-04-29 02:07:17,976 INFO [train.py:763] (0/8) Epoch 11, batch 1700, loss[loss=0.2266, simple_loss=0.3135, pruned_loss=0.06991, over 7227.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2848, pruned_loss=0.04844, over 1426784.00 frames.], batch size: 21, lr: 6.41e-04
+2022-04-29 02:08:33,283 INFO [train.py:763] (0/8) Epoch 11, batch 1750, loss[loss=0.2097, simple_loss=0.2924, pruned_loss=0.06345, over 7161.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2846, pruned_loss=0.04823, over 1427442.14 frames.], batch size: 26, lr: 6.41e-04
+2022-04-29 02:09:47,989 INFO [train.py:763] (0/8) Epoch 11, batch 1800, loss[loss=0.183, simple_loss=0.2705, pruned_loss=0.04778, over 6988.00 frames.], tot_loss[loss=0.1904, simple_loss=0.284, pruned_loss=0.04842, over 1427600.55 frames.], batch size: 16, lr: 6.41e-04
+2022-04-29 02:11:03,174 INFO [train.py:763] (0/8) Epoch 11, batch 1850, loss[loss=0.1951, simple_loss=0.291, pruned_loss=0.0496, over 7146.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2838, pruned_loss=0.04851, over 1426058.27 frames.], batch size: 26, lr: 6.40e-04
+2022-04-29 02:12:18,083 INFO [train.py:763] (0/8) Epoch 11, batch 1900, loss[loss=0.1891, simple_loss=0.2787, pruned_loss=0.04979, over 7439.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2827, pruned_loss=0.04782, over 1428587.03 frames.], batch size: 20, lr: 6.40e-04
+2022-04-29 02:13:32,353 INFO [train.py:763] (0/8) Epoch 11, batch 1950, loss[loss=0.177, simple_loss=0.2699, pruned_loss=0.0421, over 7012.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2836, pruned_loss=0.04846, over 1427351.09 frames.], batch size: 16, lr: 6.40e-04
+2022-04-29 02:14:38,130 INFO [train.py:763] (0/8) Epoch 11, batch 2000, loss[loss=0.2667, simple_loss=0.3332, pruned_loss=0.1001, over 6386.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2844, pruned_loss=0.04902, over 1425927.22 frames.], batch size: 38, lr: 6.39e-04
+2022-04-29 02:15:44,450 INFO [train.py:763] (0/8) Epoch 11, batch 2050, loss[loss=0.2227, simple_loss=0.3081, pruned_loss=0.06864, over 7382.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2842, pruned_loss=0.04904, over 1423712.53 frames.], batch size: 23, lr: 6.39e-04
+2022-04-29 02:16:50,755 INFO [train.py:763] (0/8) Epoch 11, batch 2100, loss[loss=0.2016, simple_loss=0.2937, pruned_loss=0.05472, over 6816.00 frames.], tot_loss[loss=0.192, simple_loss=0.285, pruned_loss=0.04952, over 1427558.88 frames.], batch size: 31, lr: 6.39e-04
+2022-04-29 02:17:57,130 INFO [train.py:763] (0/8) Epoch 11, batch 2150, loss[loss=0.173, simple_loss=0.2681, pruned_loss=0.03898, over 6814.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2851, pruned_loss=0.04961, over 1422447.65 frames.], batch size: 15, lr: 6.38e-04
+2022-04-29 02:19:03,275 INFO [train.py:763] (0/8) Epoch 11, batch 2200, loss[loss=0.1798, simple_loss=0.2673, pruned_loss=0.04616, over 7430.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2851, pruned_loss=0.04955, over 1426780.24 frames.], batch size: 20, lr: 6.38e-04
+2022-04-29 02:20:09,538 INFO [train.py:763] (0/8) Epoch 11, batch 2250, loss[loss=0.1837, simple_loss=0.2739, pruned_loss=0.04673, over 7139.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2841, pruned_loss=0.04909, over 1425539.17 frames.], batch size: 17, lr: 6.38e-04
+2022-04-29 02:21:16,311 INFO [train.py:763] (0/8) Epoch 11, batch 2300, loss[loss=0.1865, simple_loss=0.2731, pruned_loss=0.04996, over 7361.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2846, pruned_loss=0.04923, over 1424094.98 frames.], batch size: 19, lr: 6.38e-04
+2022-04-29 02:22:22,094 INFO [train.py:763] (0/8) Epoch 11, batch 2350, loss[loss=0.2072, simple_loss=0.3045, pruned_loss=0.05491, over 7285.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2848, pruned_loss=0.04877, over 1425801.00 frames.], batch size: 24, lr: 6.37e-04
+2022-04-29 02:23:28,147 INFO [train.py:763] (0/8) Epoch 11, batch 2400, loss[loss=0.166, simple_loss=0.2637, pruned_loss=0.0342, over 7111.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2847, pruned_loss=0.04849, over 1428128.25 frames.], batch size: 21, lr: 6.37e-04
+2022-04-29 02:24:33,625 INFO [train.py:763] (0/8) Epoch 11, batch 2450, loss[loss=0.2116, simple_loss=0.3041, pruned_loss=0.05952, over 7241.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2854, pruned_loss=0.04875, over 1426157.51 frames.], batch size: 20, lr: 6.37e-04
+2022-04-29 02:25:39,231 INFO [train.py:763] (0/8) Epoch 11, batch 2500, loss[loss=0.1504, simple_loss=0.243, pruned_loss=0.02889, over 7069.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2848, pruned_loss=0.04831, over 1425624.31 frames.], batch size: 18, lr: 6.36e-04
+2022-04-29 02:26:45,650 INFO [train.py:763] (0/8) Epoch 11, batch 2550, loss[loss=0.1798, simple_loss=0.2606, pruned_loss=0.04952, over 7265.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2851, pruned_loss=0.04866, over 1427970.36 frames.], batch size: 17, lr: 6.36e-04
+2022-04-29 02:27:50,871 INFO [train.py:763] (0/8) Epoch 11, batch 2600, loss[loss=0.213, simple_loss=0.3064, pruned_loss=0.05983, over 7288.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2853, pruned_loss=0.04905, over 1422766.53 frames.], batch size: 24, lr: 6.36e-04
+2022-04-29 02:28:56,438 INFO [train.py:763] (0/8) Epoch 11, batch 2650, loss[loss=0.1817, simple_loss=0.2751, pruned_loss=0.04415, over 7271.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2858, pruned_loss=0.04939, over 1419429.91 frames.], batch size: 19, lr: 6.36e-04
+2022-04-29 02:30:03,352 INFO [train.py:763] (0/8) Epoch 11, batch 2700, loss[loss=0.1947, simple_loss=0.2983, pruned_loss=0.04559, over 7305.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2855, pruned_loss=0.04873, over 1423600.31 frames.], batch size: 25, lr: 6.35e-04
+2022-04-29 02:31:08,824 INFO [train.py:763] (0/8) Epoch 11, batch 2750, loss[loss=0.1911, simple_loss=0.2807, pruned_loss=0.05075, over 7438.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2839, pruned_loss=0.04778, over 1426188.88 frames.], batch size: 20, lr: 6.35e-04
+2022-04-29 02:32:14,653 INFO [train.py:763] (0/8) Epoch 11, batch 2800, loss[loss=0.1989, simple_loss=0.2949, pruned_loss=0.05144, over 7113.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2846, pruned_loss=0.0481, over 1427234.15 frames.], batch size: 21, lr: 6.35e-04
+2022-04-29 02:33:21,121 INFO [train.py:763] (0/8) Epoch 11, batch 2850, loss[loss=0.1775, simple_loss=0.2858, pruned_loss=0.03458, over 7314.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2834, pruned_loss=0.04761, over 1428951.81 frames.], batch size: 21, lr: 6.34e-04
+2022-04-29 02:34:28,413 INFO [train.py:763] (0/8) Epoch 11, batch 2900, loss[loss=0.186, simple_loss=0.2921, pruned_loss=0.03996, over 7277.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2845, pruned_loss=0.04769, over 1425000.62 frames.], batch size: 24, lr: 6.34e-04
+2022-04-29 02:35:35,079 INFO [train.py:763] (0/8) Epoch 11, batch 2950, loss[loss=0.1806, simple_loss=0.2916, pruned_loss=0.03486, over 7206.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2846, pruned_loss=0.04787, over 1420880.56 frames.], batch size: 21, lr: 6.34e-04
+2022-04-29 02:36:40,648 INFO [train.py:763] (0/8) Epoch 11, batch 3000, loss[loss=0.1995, simple_loss=0.3031, pruned_loss=0.04799, over 7291.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2849, pruned_loss=0.04809, over 1422330.70 frames.], batch size: 25, lr: 6.33e-04
+2022-04-29 02:36:40,649 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 02:36:55,964 INFO [train.py:792] (0/8) Epoch 11, validation: loss=0.1677, simple_loss=0.2702, pruned_loss=0.03262, over 698248.00 frames.
+2022-04-29 02:38:01,334 INFO [train.py:763] (0/8) Epoch 11, batch 3050, loss[loss=0.2109, simple_loss=0.3049, pruned_loss=0.05846, over 7390.00 frames.], tot_loss[loss=0.192, simple_loss=0.2861, pruned_loss=0.04896, over 1419895.15 frames.], batch size: 23, lr: 6.33e-04
+2022-04-29 02:39:07,001 INFO [train.py:763] (0/8) Epoch 11, batch 3100, loss[loss=0.1962, simple_loss=0.2842, pruned_loss=0.0541, over 7320.00 frames.], tot_loss[loss=0.191, simple_loss=0.285, pruned_loss=0.04855, over 1423030.49 frames.], batch size: 20, lr: 6.33e-04
+2022-04-29 02:40:14,534 INFO [train.py:763] (0/8) Epoch 11, batch 3150, loss[loss=0.2081, simple_loss=0.3046, pruned_loss=0.0558, over 7393.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2845, pruned_loss=0.04818, over 1425854.04 frames.], batch size: 23, lr: 6.33e-04
+2022-04-29 02:41:19,860 INFO [train.py:763] (0/8) Epoch 11, batch 3200, loss[loss=0.1705, simple_loss=0.2724, pruned_loss=0.03432, over 7119.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2838, pruned_loss=0.04815, over 1425260.73 frames.], batch size: 21, lr: 6.32e-04
+2022-04-29 02:42:26,207 INFO [train.py:763] (0/8) Epoch 11, batch 3250, loss[loss=0.1891, simple_loss=0.2852, pruned_loss=0.04654, over 7407.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2831, pruned_loss=0.04762, over 1425894.41 frames.], batch size: 21, lr: 6.32e-04
+2022-04-29 02:43:31,321 INFO [train.py:763] (0/8) Epoch 11, batch 3300, loss[loss=0.1576, simple_loss=0.2478, pruned_loss=0.03372, over 7459.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2851, pruned_loss=0.0488, over 1425824.05 frames.], batch size: 17, lr: 6.32e-04
+2022-04-29 02:44:36,758 INFO [train.py:763] (0/8) Epoch 11, batch 3350, loss[loss=0.186, simple_loss=0.2718, pruned_loss=0.05016, over 7280.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2849, pruned_loss=0.04871, over 1426630.92 frames.], batch size: 18, lr: 6.31e-04
+2022-04-29 02:45:42,440 INFO [train.py:763] (0/8) Epoch 11, batch 3400, loss[loss=0.2117, simple_loss=0.3126, pruned_loss=0.05542, over 6427.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2851, pruned_loss=0.0491, over 1420843.86 frames.], batch size: 38, lr: 6.31e-04
+2022-04-29 02:46:49,535 INFO [train.py:763] (0/8) Epoch 11, batch 3450, loss[loss=0.1834, simple_loss=0.2841, pruned_loss=0.04131, over 7124.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2837, pruned_loss=0.04845, over 1419104.11 frames.], batch size: 21, lr: 6.31e-04
+2022-04-29 02:47:56,127 INFO [train.py:763] (0/8) Epoch 11, batch 3500, loss[loss=0.1861, simple_loss=0.2881, pruned_loss=0.04202, over 7325.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2838, pruned_loss=0.0484, over 1425024.92 frames.], batch size: 21, lr: 6.31e-04
+2022-04-29 02:49:02,215 INFO [train.py:763] (0/8) Epoch 11, batch 3550, loss[loss=0.1521, simple_loss=0.2426, pruned_loss=0.03077, over 6987.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2838, pruned_loss=0.0485, over 1423566.89 frames.], batch size: 16, lr: 6.30e-04
+2022-04-29 02:50:08,011 INFO [train.py:763] (0/8) Epoch 11, batch 3600, loss[loss=0.1728, simple_loss=0.2676, pruned_loss=0.03896, over 7242.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2844, pruned_loss=0.04829, over 1425236.98 frames.], batch size: 20, lr: 6.30e-04
+2022-04-29 02:51:13,364 INFO [train.py:763] (0/8) Epoch 11, batch 3650, loss[loss=0.1666, simple_loss=0.2647, pruned_loss=0.03425, over 7428.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2841, pruned_loss=0.04825, over 1424713.83 frames.], batch size: 20, lr: 6.30e-04
+2022-04-29 02:52:20,069 INFO [train.py:763] (0/8) Epoch 11, batch 3700, loss[loss=0.2022, simple_loss=0.3053, pruned_loss=0.04955, over 6787.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2842, pruned_loss=0.04804, over 1421584.43 frames.], batch size: 31, lr: 6.29e-04
+2022-04-29 02:53:25,484 INFO [train.py:763] (0/8) Epoch 11, batch 3750, loss[loss=0.1725, simple_loss=0.2742, pruned_loss=0.03539, over 7377.00 frames.], tot_loss[loss=0.1897, simple_loss=0.284, pruned_loss=0.04776, over 1425598.18 frames.], batch size: 23, lr: 6.29e-04
+2022-04-29 02:54:30,954 INFO [train.py:763] (0/8) Epoch 11, batch 3800, loss[loss=0.2414, simple_loss=0.3405, pruned_loss=0.0711, over 7138.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2831, pruned_loss=0.0473, over 1427400.08 frames.], batch size: 26, lr: 6.29e-04
+2022-04-29 02:55:36,109 INFO [train.py:763] (0/8) Epoch 11, batch 3850, loss[loss=0.1856, simple_loss=0.2831, pruned_loss=0.04406, over 7098.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2842, pruned_loss=0.04783, over 1428558.78 frames.], batch size: 21, lr: 6.29e-04
+2022-04-29 02:56:41,392 INFO [train.py:763] (0/8) Epoch 11, batch 3900, loss[loss=0.1623, simple_loss=0.2532, pruned_loss=0.03572, over 7433.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2836, pruned_loss=0.04748, over 1429900.86 frames.], batch size: 20, lr: 6.28e-04
+2022-04-29 02:57:46,962 INFO [train.py:763] (0/8) Epoch 11, batch 3950, loss[loss=0.2146, simple_loss=0.3028, pruned_loss=0.06324, over 7231.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2833, pruned_loss=0.04798, over 1431483.17 frames.], batch size: 20, lr: 6.28e-04
+2022-04-29 02:58:52,095 INFO [train.py:763] (0/8) Epoch 11, batch 4000, loss[loss=0.1758, simple_loss=0.2754, pruned_loss=0.0381, over 7408.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2829, pruned_loss=0.04773, over 1426180.85 frames.], batch size: 21, lr: 6.28e-04
+2022-04-29 02:59:57,360 INFO [train.py:763] (0/8) Epoch 11, batch 4050, loss[loss=0.1735, simple_loss=0.2745, pruned_loss=0.03623, over 7427.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2832, pruned_loss=0.0478, over 1424299.30 frames.], batch size: 20, lr: 6.27e-04
+2022-04-29 03:01:03,195 INFO [train.py:763] (0/8) Epoch 11, batch 4100, loss[loss=0.1801, simple_loss=0.2782, pruned_loss=0.04099, over 7326.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2827, pruned_loss=0.04785, over 1420676.25 frames.], batch size: 20, lr: 6.27e-04
+2022-04-29 03:02:08,247 INFO [train.py:763] (0/8) Epoch 11, batch 4150, loss[loss=0.1866, simple_loss=0.2768, pruned_loss=0.04817, over 7238.00 frames.], tot_loss[loss=0.19, simple_loss=0.2835, pruned_loss=0.04829, over 1421365.55 frames.], batch size: 20, lr: 6.27e-04
+2022-04-29 03:03:14,738 INFO [train.py:763] (0/8) Epoch 11, batch 4200, loss[loss=0.1833, simple_loss=0.2848, pruned_loss=0.0409, over 7335.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2842, pruned_loss=0.04829, over 1421859.34 frames.], batch size: 22, lr: 6.27e-04
+2022-04-29 03:04:21,497 INFO [train.py:763] (0/8) Epoch 11, batch 4250, loss[loss=0.1564, simple_loss=0.2353, pruned_loss=0.03868, over 7401.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2831, pruned_loss=0.04768, over 1424705.42 frames.], batch size: 18, lr: 6.26e-04
+2022-04-29 03:05:27,596 INFO [train.py:763] (0/8) Epoch 11, batch 4300, loss[loss=0.1647, simple_loss=0.2639, pruned_loss=0.03275, over 7237.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2831, pruned_loss=0.04776, over 1418570.95 frames.], batch size: 20, lr: 6.26e-04
+2022-04-29 03:06:35,265 INFO [train.py:763] (0/8) Epoch 11, batch 4350, loss[loss=0.2256, simple_loss=0.3094, pruned_loss=0.07095, over 7214.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2815, pruned_loss=0.04716, over 1420362.85 frames.], batch size: 22, lr: 6.26e-04
+2022-04-29 03:07:41,468 INFO [train.py:763] (0/8) Epoch 11, batch 4400, loss[loss=0.2092, simple_loss=0.3065, pruned_loss=0.05594, over 7319.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2819, pruned_loss=0.04763, over 1418719.45 frames.], batch size: 21, lr: 6.25e-04
+2022-04-29 03:08:47,767 INFO [train.py:763] (0/8) Epoch 11, batch 4450, loss[loss=0.1819, simple_loss=0.2784, pruned_loss=0.04265, over 6561.00 frames.], tot_loss[loss=0.188, simple_loss=0.2811, pruned_loss=0.04748, over 1407549.13 frames.], batch size: 38, lr: 6.25e-04
+2022-04-29 03:09:54,264 INFO [train.py:763] (0/8) Epoch 11, batch 4500, loss[loss=0.1891, simple_loss=0.2834, pruned_loss=0.04743, over 6279.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2816, pruned_loss=0.04859, over 1390102.57 frames.], batch size: 38, lr: 6.25e-04
+2022-04-29 03:10:59,845 INFO [train.py:763] (0/8) Epoch 11, batch 4550, loss[loss=0.2708, simple_loss=0.3469, pruned_loss=0.09736, over 5242.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2842, pruned_loss=0.05052, over 1349867.08 frames.], batch size: 52, lr: 6.25e-04
+2022-04-29 03:11:49,601 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-11.pt
+2022-04-29 03:12:38,233 INFO [train.py:763] (0/8) Epoch 12, batch 0, loss[loss=0.1927, simple_loss=0.2999, pruned_loss=0.04279, over 7144.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2999, pruned_loss=0.04279, over 7144.00 frames.], batch size: 20, lr: 6.03e-04
+2022-04-29 03:13:44,623 INFO [train.py:763] (0/8) Epoch 12, batch 50, loss[loss=0.1589, simple_loss=0.2579, pruned_loss=0.02996, over 7235.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2838, pruned_loss=0.04764, over 318101.29 frames.], batch size: 20, lr: 6.03e-04
+2022-04-29 03:14:50,361 INFO [train.py:763] (0/8) Epoch 12, batch 100, loss[loss=0.1942, simple_loss=0.2928, pruned_loss=0.0478, over 7205.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2837, pruned_loss=0.04788, over 564417.40 frames.], batch size: 23, lr: 6.03e-04
+2022-04-29 03:15:56,444 INFO [train.py:763] (0/8) Epoch 12, batch 150, loss[loss=0.1868, simple_loss=0.2864, pruned_loss=0.04366, over 7143.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2849, pruned_loss=0.04768, over 753385.41 frames.], batch size: 20, lr: 6.03e-04
+2022-04-29 03:17:02,806 INFO [train.py:763] (0/8) Epoch 12, batch 200, loss[loss=0.1799, simple_loss=0.2712, pruned_loss=0.04429, over 7145.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2835, pruned_loss=0.04743, over 900422.75 frames.], batch size: 20, lr: 6.02e-04
+2022-04-29 03:18:09,059 INFO [train.py:763] (0/8) Epoch 12, batch 250, loss[loss=0.1425, simple_loss=0.232, pruned_loss=0.02652, over 6771.00 frames.], tot_loss[loss=0.188, simple_loss=0.2823, pruned_loss=0.04681, over 1013403.34 frames.], batch size: 15, lr: 6.02e-04
+2022-04-29 03:19:15,285 INFO [train.py:763] (0/8) Epoch 12, batch 300, loss[loss=0.1952, simple_loss=0.293, pruned_loss=0.04874, over 7150.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2827, pruned_loss=0.04704, over 1102772.02 frames.], batch size: 20, lr: 6.02e-04
+2022-04-29 03:20:20,575 INFO [train.py:763] (0/8) Epoch 12, batch 350, loss[loss=0.1923, simple_loss=0.2842, pruned_loss=0.05014, over 7079.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2836, pruned_loss=0.04708, over 1175023.08 frames.], batch size: 28, lr: 6.01e-04
+2022-04-29 03:21:26,176 INFO [train.py:763] (0/8) Epoch 12, batch 400, loss[loss=0.163, simple_loss=0.2547, pruned_loss=0.03563, over 7353.00 frames.], tot_loss[loss=0.188, simple_loss=0.2827, pruned_loss=0.04661, over 1232317.36 frames.], batch size: 19, lr: 6.01e-04
+2022-04-29 03:22:31,841 INFO [train.py:763] (0/8) Epoch 12, batch 450, loss[loss=0.1668, simple_loss=0.2696, pruned_loss=0.03203, over 7300.00 frames.], tot_loss[loss=0.188, simple_loss=0.2827, pruned_loss=0.04667, over 1276482.84 frames.], batch size: 21, lr: 6.01e-04
+2022-04-29 03:23:38,045 INFO [train.py:763] (0/8) Epoch 12, batch 500, loss[loss=0.1969, simple_loss=0.296, pruned_loss=0.0489, over 6616.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2809, pruned_loss=0.046, over 1310378.24 frames.], batch size: 38, lr: 6.01e-04
+2022-04-29 03:24:43,951 INFO [train.py:763] (0/8) Epoch 12, batch 550, loss[loss=0.2181, simple_loss=0.3142, pruned_loss=0.06097, over 7372.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2812, pruned_loss=0.04603, over 1332844.19 frames.], batch size: 23, lr: 6.00e-04
+2022-04-29 03:25:49,972 INFO [train.py:763] (0/8) Epoch 12, batch 600, loss[loss=0.1503, simple_loss=0.2347, pruned_loss=0.03293, over 6769.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2807, pruned_loss=0.0458, over 1346536.57 frames.], batch size: 15, lr: 6.00e-04
+2022-04-29 03:26:55,896 INFO [train.py:763] (0/8) Epoch 12, batch 650, loss[loss=0.1871, simple_loss=0.2756, pruned_loss=0.04936, over 7279.00 frames.], tot_loss[loss=0.1863, simple_loss=0.281, pruned_loss=0.04576, over 1365807.10 frames.], batch size: 18, lr: 6.00e-04
+2022-04-29 03:28:02,307 INFO [train.py:763] (0/8) Epoch 12, batch 700, loss[loss=0.1635, simple_loss=0.2585, pruned_loss=0.03427, over 6776.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2814, pruned_loss=0.04558, over 1382661.43 frames.], batch size: 15, lr: 6.00e-04
+2022-04-29 03:29:07,997 INFO [train.py:763] (0/8) Epoch 12, batch 750, loss[loss=0.2208, simple_loss=0.3079, pruned_loss=0.06686, over 7199.00 frames.], tot_loss[loss=0.187, simple_loss=0.2821, pruned_loss=0.04596, over 1394830.84 frames.], batch size: 23, lr: 5.99e-04
+2022-04-29 03:30:14,231 INFO [train.py:763] (0/8) Epoch 12, batch 800, loss[loss=0.1814, simple_loss=0.2767, pruned_loss=0.04307, over 7207.00 frames.], tot_loss[loss=0.186, simple_loss=0.2813, pruned_loss=0.04531, over 1404180.38 frames.], batch size: 22, lr: 5.99e-04
+2022-04-29 03:31:20,695 INFO [train.py:763] (0/8) Epoch 12, batch 850, loss[loss=0.1563, simple_loss=0.2576, pruned_loss=0.02745, over 7128.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2819, pruned_loss=0.04555, over 1410243.05 frames.], batch size: 17, lr: 5.99e-04
+2022-04-29 03:32:27,847 INFO [train.py:763] (0/8) Epoch 12, batch 900, loss[loss=0.1741, simple_loss=0.2715, pruned_loss=0.03836, over 7325.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2817, pruned_loss=0.0459, over 1413236.03 frames.], batch size: 20, lr: 5.99e-04
+2022-04-29 03:33:24,379 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-56000.pt
+2022-04-29 03:33:44,140 INFO [train.py:763] (0/8) Epoch 12, batch 950, loss[loss=0.1995, simple_loss=0.3011, pruned_loss=0.04893, over 7184.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2816, pruned_loss=0.04583, over 1413912.97 frames.], batch size: 26, lr: 5.98e-04
+2022-04-29 03:34:49,713 INFO [train.py:763] (0/8) Epoch 12, batch 1000, loss[loss=0.1763, simple_loss=0.2719, pruned_loss=0.04036, over 6267.00 frames.], tot_loss[loss=0.1869, simple_loss=0.282, pruned_loss=0.04594, over 1414412.83 frames.], batch size: 38, lr: 5.98e-04
+2022-04-29 03:35:56,180 INFO [train.py:763] (0/8) Epoch 12, batch 1050, loss[loss=0.2327, simple_loss=0.3013, pruned_loss=0.08206, over 7265.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2815, pruned_loss=0.04599, over 1415203.49 frames.], batch size: 19, lr: 5.98e-04
+2022-04-29 03:37:02,302 INFO [train.py:763] (0/8) Epoch 12, batch 1100, loss[loss=0.1894, simple_loss=0.2894, pruned_loss=0.04472, over 7378.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2817, pruned_loss=0.04608, over 1421567.84 frames.], batch size: 23, lr: 5.97e-04
+2022-04-29 03:38:08,859 INFO [train.py:763] (0/8) Epoch 12, batch 1150, loss[loss=0.1891, simple_loss=0.2769, pruned_loss=0.05065, over 7323.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2817, pruned_loss=0.04625, over 1424045.73 frames.], batch size: 20, lr: 5.97e-04
+2022-04-29 03:39:15,123 INFO [train.py:763] (0/8) Epoch 12, batch 1200, loss[loss=0.2152, simple_loss=0.2992, pruned_loss=0.06563, over 5171.00 frames.], tot_loss[loss=0.188, simple_loss=0.282, pruned_loss=0.04703, over 1420538.63 frames.], batch size: 52, lr: 5.97e-04
+2022-04-29 03:40:21,674 INFO [train.py:763] (0/8) Epoch 12, batch 1250, loss[loss=0.1422, simple_loss=0.2427, pruned_loss=0.02088, over 7156.00 frames.], tot_loss[loss=0.188, simple_loss=0.2816, pruned_loss=0.04721, over 1417644.17 frames.], batch size: 19, lr: 5.97e-04
+2022-04-29 03:41:28,275 INFO [train.py:763] (0/8) Epoch 12, batch 1300, loss[loss=0.1733, simple_loss=0.2658, pruned_loss=0.04033, over 7073.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2809, pruned_loss=0.04695, over 1418388.43 frames.], batch size: 18, lr: 5.96e-04
+2022-04-29 03:42:33,930 INFO [train.py:763] (0/8) Epoch 12, batch 1350, loss[loss=0.206, simple_loss=0.2905, pruned_loss=0.06071, over 4879.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2819, pruned_loss=0.04696, over 1416410.07 frames.], batch size: 52, lr: 5.96e-04
+2022-04-29 03:43:39,832 INFO [train.py:763] (0/8) Epoch 12, batch 1400, loss[loss=0.1786, simple_loss=0.2731, pruned_loss=0.04203, over 7324.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2828, pruned_loss=0.04703, over 1415293.92 frames.], batch size: 25, lr: 5.96e-04
+2022-04-29 03:44:45,265 INFO [train.py:763] (0/8) Epoch 12, batch 1450, loss[loss=0.1755, simple_loss=0.2711, pruned_loss=0.03996, over 7323.00 frames.], tot_loss[loss=0.1883, simple_loss=0.283, pruned_loss=0.04677, over 1413693.32 frames.], batch size: 21, lr: 5.96e-04
+2022-04-29 03:45:51,890 INFO [train.py:763] (0/8) Epoch 12, batch 1500, loss[loss=0.208, simple_loss=0.3015, pruned_loss=0.05723, over 7200.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2829, pruned_loss=0.04669, over 1417157.25 frames.], batch size: 23, lr: 5.95e-04
+2022-04-29 03:46:59,263 INFO [train.py:763] (0/8) Epoch 12, batch 1550, loss[loss=0.2012, simple_loss=0.3094, pruned_loss=0.04652, over 7051.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2825, pruned_loss=0.04634, over 1419353.50 frames.], batch size: 28, lr: 5.95e-04
+2022-04-29 03:48:05,687 INFO [train.py:763] (0/8) Epoch 12, batch 1600, loss[loss=0.2085, simple_loss=0.3019, pruned_loss=0.05752, over 7266.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2821, pruned_loss=0.0461, over 1418840.61 frames.], batch size: 25, lr: 5.95e-04
+2022-04-29 03:49:11,832 INFO [train.py:763] (0/8) Epoch 12, batch 1650, loss[loss=0.2036, simple_loss=0.2969, pruned_loss=0.0551, over 7296.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2824, pruned_loss=0.04605, over 1422396.23 frames.], batch size: 24, lr: 5.95e-04
+2022-04-29 03:50:17,598 INFO [train.py:763] (0/8) Epoch 12, batch 1700, loss[loss=0.1787, simple_loss=0.2554, pruned_loss=0.05096, over 7138.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2818, pruned_loss=0.04587, over 1418861.20 frames.], batch size: 17, lr: 5.94e-04
+2022-04-29 03:51:23,279 INFO [train.py:763] (0/8) Epoch 12, batch 1750, loss[loss=0.1989, simple_loss=0.2997, pruned_loss=0.04902, over 7163.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2812, pruned_loss=0.04582, over 1422358.33 frames.], batch size: 26, lr: 5.94e-04
+2022-04-29 03:52:29,192 INFO [train.py:763] (0/8) Epoch 12, batch 1800, loss[loss=0.1884, simple_loss=0.266, pruned_loss=0.05543, over 7001.00 frames.], tot_loss[loss=0.1856, simple_loss=0.28, pruned_loss=0.0456, over 1427430.37 frames.], batch size: 16, lr: 5.94e-04
+2022-04-29 03:53:35,392 INFO [train.py:763] (0/8) Epoch 12, batch 1850, loss[loss=0.2149, simple_loss=0.3107, pruned_loss=0.05952, over 7342.00 frames.], tot_loss[loss=0.1856, simple_loss=0.28, pruned_loss=0.04558, over 1428044.54 frames.], batch size: 22, lr: 5.94e-04
+2022-04-29 03:54:41,520 INFO [train.py:763] (0/8) Epoch 12, batch 1900, loss[loss=0.1746, simple_loss=0.27, pruned_loss=0.03962, over 7231.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2811, pruned_loss=0.04625, over 1428543.01 frames.], batch size: 20, lr: 5.93e-04
+2022-04-29 03:55:47,356 INFO [train.py:763] (0/8) Epoch 12, batch 1950, loss[loss=0.1458, simple_loss=0.2394, pruned_loss=0.02612, over 7267.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2814, pruned_loss=0.04604, over 1428649.50 frames.], batch size: 17, lr: 5.93e-04
+2022-04-29 03:56:53,849 INFO [train.py:763] (0/8) Epoch 12, batch 2000, loss[loss=0.1814, simple_loss=0.2648, pruned_loss=0.04899, over 6999.00 frames.], tot_loss[loss=0.187, simple_loss=0.2813, pruned_loss=0.04631, over 1427667.42 frames.], batch size: 16, lr: 5.93e-04
+2022-04-29 03:57:59,762 INFO [train.py:763] (0/8) Epoch 12, batch 2050, loss[loss=0.1828, simple_loss=0.2811, pruned_loss=0.04228, over 7156.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2809, pruned_loss=0.04606, over 1420350.49 frames.], batch size: 19, lr: 5.93e-04
+2022-04-29 03:59:05,464 INFO [train.py:763] (0/8) Epoch 12, batch 2100, loss[loss=0.1885, simple_loss=0.2868, pruned_loss=0.04513, over 7155.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2808, pruned_loss=0.04598, over 1421492.44 frames.], batch size: 19, lr: 5.92e-04
+2022-04-29 04:00:11,341 INFO [train.py:763] (0/8) Epoch 12, batch 2150, loss[loss=0.1747, simple_loss=0.2547, pruned_loss=0.04732, over 7261.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2825, pruned_loss=0.04667, over 1422181.43 frames.], batch size: 18, lr: 5.92e-04
+2022-04-29 04:01:17,164 INFO [train.py:763] (0/8) Epoch 12, batch 2200, loss[loss=0.1813, simple_loss=0.2764, pruned_loss=0.04315, over 7320.00 frames.], tot_loss[loss=0.1876, simple_loss=0.282, pruned_loss=0.04656, over 1422659.14 frames.], batch size: 20, lr: 5.92e-04
+2022-04-29 04:02:23,237 INFO [train.py:763] (0/8) Epoch 12, batch 2250, loss[loss=0.2002, simple_loss=0.3068, pruned_loss=0.04677, over 6990.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2818, pruned_loss=0.0468, over 1420914.97 frames.], batch size: 28, lr: 5.91e-04
+2022-04-29 04:03:29,778 INFO [train.py:763] (0/8) Epoch 12, batch 2300, loss[loss=0.1966, simple_loss=0.3004, pruned_loss=0.04642, over 7114.00 frames.], tot_loss[loss=0.188, simple_loss=0.2826, pruned_loss=0.04676, over 1424685.44 frames.], batch size: 21, lr: 5.91e-04
+2022-04-29 04:04:36,294 INFO [train.py:763] (0/8) Epoch 12, batch 2350, loss[loss=0.1935, simple_loss=0.2898, pruned_loss=0.04858, over 7157.00 frames.], tot_loss[loss=0.1873, simple_loss=0.282, pruned_loss=0.04637, over 1425605.12 frames.], batch size: 19, lr: 5.91e-04
+2022-04-29 04:05:42,058 INFO [train.py:763] (0/8) Epoch 12, batch 2400, loss[loss=0.1941, simple_loss=0.2828, pruned_loss=0.05268, over 7156.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2816, pruned_loss=0.04608, over 1426036.72 frames.], batch size: 17, lr: 5.91e-04
+2022-04-29 04:06:47,903 INFO [train.py:763] (0/8) Epoch 12, batch 2450, loss[loss=0.2014, simple_loss=0.2915, pruned_loss=0.05569, over 7221.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2815, pruned_loss=0.04596, over 1425742.49 frames.], batch size: 21, lr: 5.90e-04
+2022-04-29 04:07:55,029 INFO [train.py:763] (0/8) Epoch 12, batch 2500, loss[loss=0.1619, simple_loss=0.2504, pruned_loss=0.03673, over 7280.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2828, pruned_loss=0.04647, over 1427034.88 frames.], batch size: 18, lr: 5.90e-04
+2022-04-29 04:09:01,290 INFO [train.py:763] (0/8) Epoch 12, batch 2550, loss[loss=0.1854, simple_loss=0.2844, pruned_loss=0.04324, over 7228.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2834, pruned_loss=0.04709, over 1429004.49 frames.], batch size: 16, lr: 5.90e-04
+2022-04-29 04:10:08,007 INFO [train.py:763] (0/8) Epoch 12, batch 2600, loss[loss=0.1629, simple_loss=0.2561, pruned_loss=0.0348, over 6776.00 frames.], tot_loss[loss=0.188, simple_loss=0.2822, pruned_loss=0.04692, over 1424752.56 frames.], batch size: 15, lr: 5.90e-04
+2022-04-29 04:11:13,664 INFO [train.py:763] (0/8) Epoch 12, batch 2650, loss[loss=0.1568, simple_loss=0.239, pruned_loss=0.03732, over 7018.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2817, pruned_loss=0.04693, over 1422866.63 frames.], batch size: 16, lr: 5.89e-04
+2022-04-29 04:12:19,562 INFO [train.py:763] (0/8) Epoch 12, batch 2700, loss[loss=0.1748, simple_loss=0.2582, pruned_loss=0.04575, over 7011.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2816, pruned_loss=0.04698, over 1423569.33 frames.], batch size: 16, lr: 5.89e-04
+2022-04-29 04:13:25,134 INFO [train.py:763] (0/8) Epoch 12, batch 2750, loss[loss=0.1832, simple_loss=0.2801, pruned_loss=0.04312, over 7116.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2813, pruned_loss=0.04655, over 1420875.79 frames.], batch size: 21, lr: 5.89e-04
+2022-04-29 04:14:30,850 INFO [train.py:763] (0/8) Epoch 12, batch 2800, loss[loss=0.1426, simple_loss=0.2404, pruned_loss=0.02245, over 7126.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2825, pruned_loss=0.04657, over 1421131.80 frames.], batch size: 17, lr: 5.89e-04
+2022-04-29 04:15:37,565 INFO [train.py:763] (0/8) Epoch 12, batch 2850, loss[loss=0.1992, simple_loss=0.2962, pruned_loss=0.05113, over 7380.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2828, pruned_loss=0.04633, over 1426659.46 frames.], batch size: 23, lr: 5.88e-04
+2022-04-29 04:16:43,207 INFO [train.py:763] (0/8) Epoch 12, batch 2900, loss[loss=0.1593, simple_loss=0.2522, pruned_loss=0.03317, over 7351.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2828, pruned_loss=0.04618, over 1424032.45 frames.], batch size: 19, lr: 5.88e-04
+2022-04-29 04:17:49,205 INFO [train.py:763] (0/8) Epoch 12, batch 2950, loss[loss=0.1741, simple_loss=0.2803, pruned_loss=0.03392, over 7113.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2813, pruned_loss=0.04526, over 1425568.83 frames.], batch size: 21, lr: 5.88e-04
+2022-04-29 04:18:54,876 INFO [train.py:763] (0/8) Epoch 12, batch 3000, loss[loss=0.1708, simple_loss=0.2572, pruned_loss=0.04221, over 7285.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2816, pruned_loss=0.04576, over 1426465.80 frames.], batch size: 17, lr: 5.88e-04
+2022-04-29 04:18:54,878 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 04:19:10,345 INFO [train.py:792] (0/8) Epoch 12, validation: loss=0.1673, simple_loss=0.27, pruned_loss=0.03225, over 698248.00 frames.
+2022-04-29 04:20:16,213 INFO [train.py:763] (0/8) Epoch 12, batch 3050, loss[loss=0.1764, simple_loss=0.259, pruned_loss=0.04692, over 7134.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2805, pruned_loss=0.0458, over 1427511.98 frames.], batch size: 17, lr: 5.87e-04
+2022-04-29 04:21:32,111 INFO [train.py:763] (0/8) Epoch 12, batch 3100, loss[loss=0.1991, simple_loss=0.2991, pruned_loss=0.04954, over 7119.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2803, pruned_loss=0.0455, over 1427251.71 frames.], batch size: 21, lr: 5.87e-04
+2022-04-29 04:22:37,472 INFO [train.py:763] (0/8) Epoch 12, batch 3150, loss[loss=0.2237, simple_loss=0.3019, pruned_loss=0.07271, over 7307.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2812, pruned_loss=0.04595, over 1424285.18 frames.], batch size: 25, lr: 5.87e-04
+2022-04-29 04:23:52,373 INFO [train.py:763] (0/8) Epoch 12, batch 3200, loss[loss=0.2378, simple_loss=0.3193, pruned_loss=0.07812, over 5194.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2816, pruned_loss=0.04595, over 1425465.54 frames.], batch size: 52, lr: 5.87e-04
+2022-04-29 04:25:17,148 INFO [train.py:763] (0/8) Epoch 12, batch 3250, loss[loss=0.1583, simple_loss=0.2494, pruned_loss=0.03361, over 7278.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2807, pruned_loss=0.04518, over 1427947.33 frames.], batch size: 17, lr: 5.86e-04
+2022-04-29 04:26:23,038 INFO [train.py:763] (0/8) Epoch 12, batch 3300, loss[loss=0.1988, simple_loss=0.2822, pruned_loss=0.05774, over 7321.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2806, pruned_loss=0.0455, over 1429027.57 frames.], batch size: 20, lr: 5.86e-04
+2022-04-29 04:27:37,939 INFO [train.py:763] (0/8) Epoch 12, batch 3350, loss[loss=0.1635, simple_loss=0.2616, pruned_loss=0.03272, over 7002.00 frames.], tot_loss[loss=0.186, simple_loss=0.2808, pruned_loss=0.04556, over 1421042.40 frames.], batch size: 16, lr: 5.86e-04
+2022-04-29 04:29:03,564 INFO [train.py:763] (0/8) Epoch 12, batch 3400, loss[loss=0.204, simple_loss=0.2971, pruned_loss=0.05541, over 7387.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2816, pruned_loss=0.04574, over 1425738.32 frames.], batch size: 23, lr: 5.86e-04
+2022-04-29 04:30:18,599 INFO [train.py:763] (0/8) Epoch 12, batch 3450, loss[loss=0.1876, simple_loss=0.2724, pruned_loss=0.05142, over 7393.00 frames.], tot_loss[loss=0.1871, simple_loss=0.282, pruned_loss=0.04614, over 1415223.96 frames.], batch size: 18, lr: 5.85e-04
+2022-04-29 04:31:24,863 INFO [train.py:763] (0/8) Epoch 12, batch 3500, loss[loss=0.1957, simple_loss=0.2921, pruned_loss=0.04968, over 6710.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2821, pruned_loss=0.04626, over 1416751.42 frames.], batch size: 31, lr: 5.85e-04
+2022-04-29 04:32:31,928 INFO [train.py:763] (0/8) Epoch 12, batch 3550, loss[loss=0.1622, simple_loss=0.2476, pruned_loss=0.03844, over 7001.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2824, pruned_loss=0.04646, over 1422131.63 frames.], batch size: 16, lr: 5.85e-04
+2022-04-29 04:33:38,546 INFO [train.py:763] (0/8) Epoch 12, batch 3600, loss[loss=0.1728, simple_loss=0.2594, pruned_loss=0.04305, over 7269.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2823, pruned_loss=0.04655, over 1421937.73 frames.], batch size: 18, lr: 5.85e-04
+2022-04-29 04:34:44,023 INFO [train.py:763] (0/8) Epoch 12, batch 3650, loss[loss=0.182, simple_loss=0.2869, pruned_loss=0.03851, over 7422.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2818, pruned_loss=0.04586, over 1424834.92 frames.], batch size: 21, lr: 5.84e-04
+2022-04-29 04:35:49,786 INFO [train.py:763] (0/8) Epoch 12, batch 3700, loss[loss=0.1699, simple_loss=0.2702, pruned_loss=0.03483, over 7266.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2806, pruned_loss=0.04582, over 1425387.88 frames.], batch size: 19, lr: 5.84e-04
+2022-04-29 04:36:55,384 INFO [train.py:763] (0/8) Epoch 12, batch 3750, loss[loss=0.183, simple_loss=0.2842, pruned_loss=0.04093, over 7411.00 frames.], tot_loss[loss=0.186, simple_loss=0.2808, pruned_loss=0.04554, over 1425133.29 frames.], batch size: 21, lr: 5.84e-04
+2022-04-29 04:38:01,440 INFO [train.py:763] (0/8) Epoch 12, batch 3800, loss[loss=0.1927, simple_loss=0.2963, pruned_loss=0.04455, over 7106.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2809, pruned_loss=0.04547, over 1429674.22 frames.], batch size: 28, lr: 5.84e-04
+2022-04-29 04:39:06,798 INFO [train.py:763] (0/8) Epoch 12, batch 3850, loss[loss=0.2153, simple_loss=0.3047, pruned_loss=0.06299, over 7189.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2822, pruned_loss=0.04575, over 1426785.89 frames.], batch size: 22, lr: 5.83e-04
+2022-04-29 04:40:13,133 INFO [train.py:763] (0/8) Epoch 12, batch 3900, loss[loss=0.2101, simple_loss=0.3026, pruned_loss=0.05877, over 7303.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2818, pruned_loss=0.04567, over 1425817.71 frames.], batch size: 24, lr: 5.83e-04
+2022-04-29 04:41:18,540 INFO [train.py:763] (0/8) Epoch 12, batch 3950, loss[loss=0.1725, simple_loss=0.2719, pruned_loss=0.03657, over 7204.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2817, pruned_loss=0.04565, over 1424134.00 frames.], batch size: 23, lr: 5.83e-04
+2022-04-29 04:42:24,205 INFO [train.py:763] (0/8) Epoch 12, batch 4000, loss[loss=0.1643, simple_loss=0.2601, pruned_loss=0.03427, over 7147.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2812, pruned_loss=0.04574, over 1424204.38 frames.], batch size: 17, lr: 5.83e-04
+2022-04-29 04:43:29,493 INFO [train.py:763] (0/8) Epoch 12, batch 4050, loss[loss=0.1891, simple_loss=0.2956, pruned_loss=0.04126, over 7233.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2814, pruned_loss=0.04575, over 1425858.33 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:44:35,692 INFO [train.py:763] (0/8) Epoch 12, batch 4100, loss[loss=0.1881, simple_loss=0.2957, pruned_loss=0.04026, over 7136.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2806, pruned_loss=0.04541, over 1425758.25 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:45:41,206 INFO [train.py:763] (0/8) Epoch 12, batch 4150, loss[loss=0.1796, simple_loss=0.2736, pruned_loss=0.04279, over 7423.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2827, pruned_loss=0.04629, over 1421036.33 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:46:48,398 INFO [train.py:763] (0/8) Epoch 12, batch 4200, loss[loss=0.1609, simple_loss=0.2735, pruned_loss=0.02414, over 7144.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2816, pruned_loss=0.04555, over 1422365.14 frames.], batch size: 20, lr: 5.82e-04
+2022-04-29 04:47:54,431 INFO [train.py:763] (0/8) Epoch 12, batch 4250, loss[loss=0.1797, simple_loss=0.2805, pruned_loss=0.03946, over 7171.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2811, pruned_loss=0.04568, over 1420051.71 frames.], batch size: 26, lr: 5.81e-04
+2022-04-29 04:49:00,812 INFO [train.py:763] (0/8) Epoch 12, batch 4300, loss[loss=0.1756, simple_loss=0.2722, pruned_loss=0.03946, over 7429.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2822, pruned_loss=0.04619, over 1416417.92 frames.], batch size: 20, lr: 5.81e-04
+2022-04-29 04:50:06,812 INFO [train.py:763] (0/8) Epoch 12, batch 4350, loss[loss=0.1484, simple_loss=0.2393, pruned_loss=0.02871, over 7006.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2819, pruned_loss=0.0466, over 1410900.62 frames.], batch size: 16, lr: 5.81e-04
+2022-04-29 04:51:13,418 INFO [train.py:763] (0/8) Epoch 12, batch 4400, loss[loss=0.2043, simple_loss=0.2911, pruned_loss=0.05879, over 5354.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2805, pruned_loss=0.04601, over 1410022.32 frames.], batch size: 53, lr: 5.81e-04
+2022-04-29 04:52:19,275 INFO [train.py:763] (0/8) Epoch 12, batch 4450, loss[loss=0.2082, simple_loss=0.3084, pruned_loss=0.05402, over 7302.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2792, pruned_loss=0.04549, over 1408859.77 frames.], batch size: 24, lr: 5.81e-04
+2022-04-29 04:53:25,220 INFO [train.py:763] (0/8) Epoch 12, batch 4500, loss[loss=0.1955, simple_loss=0.2915, pruned_loss=0.04972, over 7403.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2806, pruned_loss=0.04634, over 1389710.96 frames.], batch size: 21, lr: 5.80e-04
+2022-04-29 04:54:31,178 INFO [train.py:763] (0/8) Epoch 12, batch 4550, loss[loss=0.2372, simple_loss=0.3105, pruned_loss=0.08197, over 4796.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2829, pruned_loss=0.04738, over 1354973.79 frames.], batch size: 52, lr: 5.80e-04
+2022-04-29 04:55:21,462 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-12.pt
+2022-04-29 04:56:09,898 INFO [train.py:763] (0/8) Epoch 13, batch 0, loss[loss=0.1875, simple_loss=0.2862, pruned_loss=0.04439, over 7393.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2862, pruned_loss=0.04439, over 7393.00 frames.], batch size: 23, lr: 5.61e-04
+2022-04-29 04:57:15,975 INFO [train.py:763] (0/8) Epoch 13, batch 50, loss[loss=0.2231, simple_loss=0.3201, pruned_loss=0.06303, over 7110.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2782, pruned_loss=0.0438, over 321833.13 frames.], batch size: 21, lr: 5.61e-04
+2022-04-29 04:58:22,313 INFO [train.py:763] (0/8) Epoch 13, batch 100, loss[loss=0.2121, simple_loss=0.2999, pruned_loss=0.06219, over 7144.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2794, pruned_loss=0.04377, over 571819.45 frames.], batch size: 20, lr: 5.61e-04
+2022-04-29 04:59:28,145 INFO [train.py:763] (0/8) Epoch 13, batch 150, loss[loss=0.1675, simple_loss=0.2589, pruned_loss=0.03806, over 7006.00 frames.], tot_loss[loss=0.1812, simple_loss=0.277, pruned_loss=0.04271, over 762204.09 frames.], batch size: 16, lr: 5.61e-04
+2022-04-29 05:00:33,593 INFO [train.py:763] (0/8) Epoch 13, batch 200, loss[loss=0.1822, simple_loss=0.2915, pruned_loss=0.0364, over 7203.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2789, pruned_loss=0.04374, over 909695.10 frames.], batch size: 22, lr: 5.60e-04
+2022-04-29 05:01:39,411 INFO [train.py:763] (0/8) Epoch 13, batch 250, loss[loss=0.2208, simple_loss=0.3058, pruned_loss=0.06793, over 7198.00 frames.], tot_loss[loss=0.184, simple_loss=0.2793, pruned_loss=0.04434, over 1025694.42 frames.], batch size: 22, lr: 5.60e-04
+2022-04-29 05:02:44,826 INFO [train.py:763] (0/8) Epoch 13, batch 300, loss[loss=0.1776, simple_loss=0.2805, pruned_loss=0.03738, over 7408.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2803, pruned_loss=0.04461, over 1112486.84 frames.], batch size: 21, lr: 5.60e-04
+2022-04-29 05:03:50,341 INFO [train.py:763] (0/8) Epoch 13, batch 350, loss[loss=0.1701, simple_loss=0.275, pruned_loss=0.03262, over 7423.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2796, pruned_loss=0.04472, over 1181508.51 frames.], batch size: 20, lr: 5.60e-04
+2022-04-29 05:04:55,872 INFO [train.py:763] (0/8) Epoch 13, batch 400, loss[loss=0.2075, simple_loss=0.3001, pruned_loss=0.05739, over 7065.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2793, pruned_loss=0.04448, over 1231744.14 frames.], batch size: 28, lr: 5.59e-04
+2022-04-29 05:06:01,973 INFO [train.py:763] (0/8) Epoch 13, batch 450, loss[loss=0.1809, simple_loss=0.2833, pruned_loss=0.03928, over 6157.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2801, pruned_loss=0.04508, over 1273063.58 frames.], batch size: 37, lr: 5.59e-04
+2022-04-29 05:07:07,988 INFO [train.py:763] (0/8) Epoch 13, batch 500, loss[loss=0.2156, simple_loss=0.3207, pruned_loss=0.05524, over 7006.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2794, pruned_loss=0.04442, over 1300639.86 frames.], batch size: 28, lr: 5.59e-04
+2022-04-29 05:08:13,593 INFO [train.py:763] (0/8) Epoch 13, batch 550, loss[loss=0.1894, simple_loss=0.2841, pruned_loss=0.04734, over 6297.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2796, pruned_loss=0.04498, over 1325499.68 frames.], batch size: 37, lr: 5.59e-04
+2022-04-29 05:09:19,621 INFO [train.py:763] (0/8) Epoch 13, batch 600, loss[loss=0.188, simple_loss=0.2918, pruned_loss=0.04215, over 7317.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2797, pruned_loss=0.04505, over 1347369.57 frames.], batch size: 21, lr: 5.59e-04
+2022-04-29 05:10:25,807 INFO [train.py:763] (0/8) Epoch 13, batch 650, loss[loss=0.2007, simple_loss=0.2995, pruned_loss=0.0509, over 7065.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2807, pruned_loss=0.0457, over 1360200.22 frames.], batch size: 18, lr: 5.58e-04
+2022-04-29 05:11:32,554 INFO [train.py:763] (0/8) Epoch 13, batch 700, loss[loss=0.1609, simple_loss=0.2565, pruned_loss=0.03267, over 7278.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2797, pruned_loss=0.04509, over 1375730.75 frames.], batch size: 18, lr: 5.58e-04
+2022-04-29 05:12:37,749 INFO [train.py:763] (0/8) Epoch 13, batch 750, loss[loss=0.2065, simple_loss=0.3016, pruned_loss=0.05568, over 7175.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2792, pruned_loss=0.04502, over 1382423.85 frames.], batch size: 23, lr: 5.58e-04
+2022-04-29 05:13:44,419 INFO [train.py:763] (0/8) Epoch 13, batch 800, loss[loss=0.1838, simple_loss=0.2807, pruned_loss=0.04348, over 7279.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2798, pruned_loss=0.04457, over 1391920.90 frames.], batch size: 25, lr: 5.58e-04
+2022-04-29 05:14:50,902 INFO [train.py:763] (0/8) Epoch 13, batch 850, loss[loss=0.1977, simple_loss=0.3012, pruned_loss=0.04712, over 7211.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2801, pruned_loss=0.04477, over 1401019.20 frames.], batch size: 21, lr: 5.57e-04
+2022-04-29 05:15:57,591 INFO [train.py:763] (0/8) Epoch 13, batch 900, loss[loss=0.1688, simple_loss=0.267, pruned_loss=0.03527, over 7160.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2806, pruned_loss=0.0449, over 1403657.13 frames.], batch size: 18, lr: 5.57e-04
+2022-04-29 05:17:04,289 INFO [train.py:763] (0/8) Epoch 13, batch 950, loss[loss=0.1781, simple_loss=0.2761, pruned_loss=0.03999, over 7212.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2811, pruned_loss=0.04499, over 1404199.36 frames.], batch size: 21, lr: 5.57e-04
+2022-04-29 05:18:11,096 INFO [train.py:763] (0/8) Epoch 13, batch 1000, loss[loss=0.1855, simple_loss=0.2885, pruned_loss=0.04118, over 7208.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2813, pruned_loss=0.04547, over 1410907.07 frames.], batch size: 22, lr: 5.57e-04
+2022-04-29 05:19:17,018 INFO [train.py:763] (0/8) Epoch 13, batch 1050, loss[loss=0.2068, simple_loss=0.2979, pruned_loss=0.05786, over 7406.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2808, pruned_loss=0.04567, over 1411127.91 frames.], batch size: 21, lr: 5.56e-04
+2022-04-29 05:20:22,749 INFO [train.py:763] (0/8) Epoch 13, batch 1100, loss[loss=0.195, simple_loss=0.2919, pruned_loss=0.049, over 6832.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2795, pruned_loss=0.04509, over 1410814.56 frames.], batch size: 31, lr: 5.56e-04
+2022-04-29 05:21:28,699 INFO [train.py:763] (0/8) Epoch 13, batch 1150, loss[loss=0.1802, simple_loss=0.2809, pruned_loss=0.03971, over 7328.00 frames.], tot_loss[loss=0.1859, simple_loss=0.281, pruned_loss=0.04541, over 1410291.18 frames.], batch size: 22, lr: 5.56e-04
+2022-04-29 05:22:34,612 INFO [train.py:763] (0/8) Epoch 13, batch 1200, loss[loss=0.2033, simple_loss=0.2973, pruned_loss=0.05463, over 5046.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2808, pruned_loss=0.04519, over 1409920.86 frames.], batch size: 52, lr: 5.56e-04
+2022-04-29 05:23:40,304 INFO [train.py:763] (0/8) Epoch 13, batch 1250, loss[loss=0.1684, simple_loss=0.2644, pruned_loss=0.03625, over 7432.00 frames.], tot_loss[loss=0.187, simple_loss=0.282, pruned_loss=0.04595, over 1414408.76 frames.], batch size: 20, lr: 5.56e-04
+2022-04-29 05:24:45,579 INFO [train.py:763] (0/8) Epoch 13, batch 1300, loss[loss=0.2012, simple_loss=0.2877, pruned_loss=0.05735, over 7244.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2819, pruned_loss=0.04552, over 1418027.80 frames.], batch size: 19, lr: 5.55e-04
+2022-04-29 05:25:51,461 INFO [train.py:763] (0/8) Epoch 13, batch 1350, loss[loss=0.1641, simple_loss=0.2555, pruned_loss=0.03632, over 7279.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2813, pruned_loss=0.04558, over 1422412.19 frames.], batch size: 18, lr: 5.55e-04
+2022-04-29 05:26:57,111 INFO [train.py:763] (0/8) Epoch 13, batch 1400, loss[loss=0.1998, simple_loss=0.2829, pruned_loss=0.05839, over 7159.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2814, pruned_loss=0.04594, over 1418580.50 frames.], batch size: 18, lr: 5.55e-04
+2022-04-29 05:28:02,594 INFO [train.py:763] (0/8) Epoch 13, batch 1450, loss[loss=0.1532, simple_loss=0.2423, pruned_loss=0.03208, over 7284.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2809, pruned_loss=0.04541, over 1422140.30 frames.], batch size: 17, lr: 5.55e-04
+2022-04-29 05:29:08,111 INFO [train.py:763] (0/8) Epoch 13, batch 1500, loss[loss=0.1683, simple_loss=0.2595, pruned_loss=0.03855, over 7276.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2793, pruned_loss=0.04454, over 1423267.99 frames.], batch size: 17, lr: 5.54e-04
+2022-04-29 05:30:14,049 INFO [train.py:763] (0/8) Epoch 13, batch 1550, loss[loss=0.1714, simple_loss=0.2728, pruned_loss=0.03497, over 6328.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2795, pruned_loss=0.04463, over 1418415.41 frames.], batch size: 37, lr: 5.54e-04
+2022-04-29 05:31:19,485 INFO [train.py:763] (0/8) Epoch 13, batch 1600, loss[loss=0.2014, simple_loss=0.3089, pruned_loss=0.04694, over 7400.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2801, pruned_loss=0.04458, over 1417217.72 frames.], batch size: 21, lr: 5.54e-04
+2022-04-29 05:32:25,657 INFO [train.py:763] (0/8) Epoch 13, batch 1650, loss[loss=0.1678, simple_loss=0.27, pruned_loss=0.03282, over 7239.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2805, pruned_loss=0.04463, over 1418845.70 frames.], batch size: 20, lr: 5.54e-04
+2022-04-29 05:33:31,242 INFO [train.py:763] (0/8) Epoch 13, batch 1700, loss[loss=0.2034, simple_loss=0.3013, pruned_loss=0.05274, over 6344.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2803, pruned_loss=0.04454, over 1418300.26 frames.], batch size: 37, lr: 5.54e-04
+2022-04-29 05:34:36,771 INFO [train.py:763] (0/8) Epoch 13, batch 1750, loss[loss=0.1478, simple_loss=0.2428, pruned_loss=0.02639, over 7276.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2803, pruned_loss=0.04467, over 1420722.30 frames.], batch size: 17, lr: 5.53e-04
+2022-04-29 05:35:42,707 INFO [train.py:763] (0/8) Epoch 13, batch 1800, loss[loss=0.1988, simple_loss=0.2842, pruned_loss=0.05667, over 7150.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2797, pruned_loss=0.04436, over 1424994.84 frames.], batch size: 20, lr: 5.53e-04
+2022-04-29 05:36:48,189 INFO [train.py:763] (0/8) Epoch 13, batch 1850, loss[loss=0.2142, simple_loss=0.3035, pruned_loss=0.06241, over 7256.00 frames.], tot_loss[loss=0.185, simple_loss=0.2805, pruned_loss=0.04478, over 1424767.65 frames.], batch size: 25, lr: 5.53e-04
+2022-04-29 05:37:54,122 INFO [train.py:763] (0/8) Epoch 13, batch 1900, loss[loss=0.2231, simple_loss=0.3311, pruned_loss=0.05756, over 6410.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2817, pruned_loss=0.04565, over 1419691.37 frames.], batch size: 38, lr: 5.53e-04
+2022-04-29 05:39:00,693 INFO [train.py:763] (0/8) Epoch 13, batch 1950, loss[loss=0.1955, simple_loss=0.2895, pruned_loss=0.05073, over 7266.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2818, pruned_loss=0.04558, over 1421169.65 frames.], batch size: 19, lr: 5.52e-04
+2022-04-29 05:40:07,436 INFO [train.py:763] (0/8) Epoch 13, batch 2000, loss[loss=0.1839, simple_loss=0.2864, pruned_loss=0.04069, over 7352.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2812, pruned_loss=0.04524, over 1422250.25 frames.], batch size: 22, lr: 5.52e-04
+2022-04-29 05:41:13,028 INFO [train.py:763] (0/8) Epoch 13, batch 2050, loss[loss=0.2258, simple_loss=0.3112, pruned_loss=0.07015, over 7367.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2806, pruned_loss=0.04494, over 1424398.82 frames.], batch size: 23, lr: 5.52e-04
+2022-04-29 05:42:18,156 INFO [train.py:763] (0/8) Epoch 13, batch 2100, loss[loss=0.1611, simple_loss=0.2721, pruned_loss=0.02501, over 7220.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2809, pruned_loss=0.0449, over 1424389.14 frames.], batch size: 20, lr: 5.52e-04
+2022-04-29 05:43:24,246 INFO [train.py:763] (0/8) Epoch 13, batch 2150, loss[loss=0.1864, simple_loss=0.292, pruned_loss=0.04041, over 7134.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2798, pruned_loss=0.04424, over 1427192.77 frames.], batch size: 26, lr: 5.52e-04
+2022-04-29 05:44:29,765 INFO [train.py:763] (0/8) Epoch 13, batch 2200, loss[loss=0.1631, simple_loss=0.2658, pruned_loss=0.03015, over 7441.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2802, pruned_loss=0.04418, over 1425628.10 frames.], batch size: 20, lr: 5.51e-04
+2022-04-29 05:45:35,371 INFO [train.py:763] (0/8) Epoch 13, batch 2250, loss[loss=0.1879, simple_loss=0.2804, pruned_loss=0.04771, over 7229.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2801, pruned_loss=0.04436, over 1427137.34 frames.], batch size: 20, lr: 5.51e-04
+2022-04-29 05:46:41,463 INFO [train.py:763] (0/8) Epoch 13, batch 2300, loss[loss=0.1895, simple_loss=0.2914, pruned_loss=0.0438, over 7054.00 frames.], tot_loss[loss=0.1846, simple_loss=0.28, pruned_loss=0.04458, over 1427428.21 frames.], batch size: 28, lr: 5.51e-04
+2022-04-29 05:47:46,895 INFO [train.py:763] (0/8) Epoch 13, batch 2350, loss[loss=0.2229, simple_loss=0.3151, pruned_loss=0.0654, over 5426.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2805, pruned_loss=0.04485, over 1427282.15 frames.], batch size: 53, lr: 5.51e-04
+2022-04-29 05:48:52,773 INFO [train.py:763] (0/8) Epoch 13, batch 2400, loss[loss=0.1806, simple_loss=0.2668, pruned_loss=0.04724, over 7286.00 frames.], tot_loss[loss=0.184, simple_loss=0.2795, pruned_loss=0.0443, over 1428788.95 frames.], batch size: 17, lr: 5.50e-04
+2022-04-29 05:49:58,376 INFO [train.py:763] (0/8) Epoch 13, batch 2450, loss[loss=0.1786, simple_loss=0.2876, pruned_loss=0.03479, over 6822.00 frames.], tot_loss[loss=0.1856, simple_loss=0.281, pruned_loss=0.04508, over 1431180.07 frames.], batch size: 31, lr: 5.50e-04
+2022-04-29 05:51:03,654 INFO [train.py:763] (0/8) Epoch 13, batch 2500, loss[loss=0.1752, simple_loss=0.2599, pruned_loss=0.04524, over 7292.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2808, pruned_loss=0.04502, over 1426981.60 frames.], batch size: 17, lr: 5.50e-04
+2022-04-29 05:52:08,894 INFO [train.py:763] (0/8) Epoch 13, batch 2550, loss[loss=0.1654, simple_loss=0.2687, pruned_loss=0.031, over 7290.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2813, pruned_loss=0.04501, over 1423366.03 frames.], batch size: 25, lr: 5.50e-04
+2022-04-29 05:53:14,612 INFO [train.py:763] (0/8) Epoch 13, batch 2600, loss[loss=0.1992, simple_loss=0.3006, pruned_loss=0.04894, over 7410.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2804, pruned_loss=0.0446, over 1420412.76 frames.], batch size: 21, lr: 5.50e-04
+2022-04-29 05:54:20,024 INFO [train.py:763] (0/8) Epoch 13, batch 2650, loss[loss=0.1733, simple_loss=0.2736, pruned_loss=0.03652, over 7119.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2806, pruned_loss=0.045, over 1418946.06 frames.], batch size: 21, lr: 5.49e-04
+2022-04-29 05:55:25,832 INFO [train.py:763] (0/8) Epoch 13, batch 2700, loss[loss=0.1915, simple_loss=0.2655, pruned_loss=0.05876, over 6982.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2794, pruned_loss=0.04451, over 1422437.30 frames.], batch size: 16, lr: 5.49e-04
+2022-04-29 05:56:31,329 INFO [train.py:763] (0/8) Epoch 13, batch 2750, loss[loss=0.1789, simple_loss=0.2773, pruned_loss=0.04026, over 7308.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2791, pruned_loss=0.04416, over 1427196.16 frames.], batch size: 24, lr: 5.49e-04
+2022-04-29 05:57:36,858 INFO [train.py:763] (0/8) Epoch 13, batch 2800, loss[loss=0.1783, simple_loss=0.2644, pruned_loss=0.04612, over 7139.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2786, pruned_loss=0.04414, over 1426088.11 frames.], batch size: 17, lr: 5.49e-04
+2022-04-29 05:58:42,728 INFO [train.py:763] (0/8) Epoch 13, batch 2850, loss[loss=0.2067, simple_loss=0.3064, pruned_loss=0.05348, over 7417.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2783, pruned_loss=0.0442, over 1426997.12 frames.], batch size: 21, lr: 5.48e-04
+2022-04-29 05:59:48,440 INFO [train.py:763] (0/8) Epoch 13, batch 2900, loss[loss=0.1914, simple_loss=0.293, pruned_loss=0.04496, over 7106.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2795, pruned_loss=0.0446, over 1427851.98 frames.], batch size: 21, lr: 5.48e-04
+2022-04-29 06:00:53,893 INFO [train.py:763] (0/8) Epoch 13, batch 2950, loss[loss=0.2286, simple_loss=0.3198, pruned_loss=0.06866, over 7187.00 frames.], tot_loss[loss=0.185, simple_loss=0.2804, pruned_loss=0.04485, over 1429543.69 frames.], batch size: 23, lr: 5.48e-04
+2022-04-29 06:01:59,750 INFO [train.py:763] (0/8) Epoch 13, batch 3000, loss[loss=0.1978, simple_loss=0.3007, pruned_loss=0.0475, over 7287.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2795, pruned_loss=0.0448, over 1430550.34 frames.], batch size: 24, lr: 5.48e-04
+2022-04-29 06:01:59,752 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 06:02:15,158 INFO [train.py:792] (0/8) Epoch 13, validation: loss=0.1677, simple_loss=0.2714, pruned_loss=0.03198, over 698248.00 frames.
+2022-04-29 06:03:22,010 INFO [train.py:763] (0/8) Epoch 13, batch 3050, loss[loss=0.1668, simple_loss=0.2551, pruned_loss=0.03925, over 7278.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2799, pruned_loss=0.04496, over 1430206.84 frames.], batch size: 17, lr: 5.48e-04
+2022-04-29 06:04:29,225 INFO [train.py:763] (0/8) Epoch 13, batch 3100, loss[loss=0.2146, simple_loss=0.3221, pruned_loss=0.05354, over 7207.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2794, pruned_loss=0.04452, over 1431076.56 frames.], batch size: 23, lr: 5.47e-04
+2022-04-29 06:05:35,722 INFO [train.py:763] (0/8) Epoch 13, batch 3150, loss[loss=0.2667, simple_loss=0.3316, pruned_loss=0.1009, over 5017.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2786, pruned_loss=0.04428, over 1429709.50 frames.], batch size: 52, lr: 5.47e-04
+2022-04-29 06:06:41,348 INFO [train.py:763] (0/8) Epoch 13, batch 3200, loss[loss=0.2042, simple_loss=0.2971, pruned_loss=0.05565, over 7339.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2795, pruned_loss=0.04482, over 1430092.84 frames.], batch size: 22, lr: 5.47e-04
+2022-04-29 06:07:46,887 INFO [train.py:763] (0/8) Epoch 13, batch 3250, loss[loss=0.1842, simple_loss=0.2795, pruned_loss=0.04439, over 7138.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2795, pruned_loss=0.04485, over 1427265.70 frames.], batch size: 26, lr: 5.47e-04
+2022-04-29 06:08:52,450 INFO [train.py:763] (0/8) Epoch 13, batch 3300, loss[loss=0.1634, simple_loss=0.263, pruned_loss=0.03193, over 7166.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2793, pruned_loss=0.04488, over 1423873.96 frames.], batch size: 18, lr: 5.46e-04
+2022-04-29 06:09:57,832 INFO [train.py:763] (0/8) Epoch 13, batch 3350, loss[loss=0.1558, simple_loss=0.2512, pruned_loss=0.03016, over 7432.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2786, pruned_loss=0.04441, over 1425549.55 frames.], batch size: 18, lr: 5.46e-04
+2022-04-29 06:11:03,399 INFO [train.py:763] (0/8) Epoch 13, batch 3400, loss[loss=0.1734, simple_loss=0.2744, pruned_loss=0.03617, over 7173.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2792, pruned_loss=0.04479, over 1426143.09 frames.], batch size: 18, lr: 5.46e-04
+2022-04-29 06:12:10,296 INFO [train.py:763] (0/8) Epoch 13, batch 3450, loss[loss=0.1793, simple_loss=0.2866, pruned_loss=0.03593, over 7109.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2799, pruned_loss=0.04474, over 1425655.16 frames.], batch size: 21, lr: 5.46e-04
+2022-04-29 06:13:16,587 INFO [train.py:763] (0/8) Epoch 13, batch 3500, loss[loss=0.1843, simple_loss=0.2786, pruned_loss=0.04504, over 7344.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2788, pruned_loss=0.04427, over 1426952.63 frames.], batch size: 22, lr: 5.46e-04
+2022-04-29 06:14:22,084 INFO [train.py:763] (0/8) Epoch 13, batch 3550, loss[loss=0.1796, simple_loss=0.2879, pruned_loss=0.03561, over 7320.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2791, pruned_loss=0.0442, over 1426355.29 frames.], batch size: 21, lr: 5.45e-04
+2022-04-29 06:15:27,782 INFO [train.py:763] (0/8) Epoch 13, batch 3600, loss[loss=0.1665, simple_loss=0.2631, pruned_loss=0.03492, over 7354.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2779, pruned_loss=0.04376, over 1429366.25 frames.], batch size: 19, lr: 5.45e-04
+2022-04-29 06:16:33,710 INFO [train.py:763] (0/8) Epoch 13, batch 3650, loss[loss=0.1663, simple_loss=0.2655, pruned_loss=0.03357, over 7232.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2776, pruned_loss=0.04331, over 1428666.62 frames.], batch size: 20, lr: 5.45e-04
+2022-04-29 06:17:39,185 INFO [train.py:763] (0/8) Epoch 13, batch 3700, loss[loss=0.1961, simple_loss=0.2922, pruned_loss=0.04997, over 7304.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2783, pruned_loss=0.04347, over 1420603.72 frames.], batch size: 24, lr: 5.45e-04
+2022-04-29 06:18:44,840 INFO [train.py:763] (0/8) Epoch 13, batch 3750, loss[loss=0.2016, simple_loss=0.277, pruned_loss=0.06306, over 4837.00 frames.], tot_loss[loss=0.184, simple_loss=0.2794, pruned_loss=0.04433, over 1419025.75 frames.], batch size: 54, lr: 5.45e-04
+2022-04-29 06:19:51,478 INFO [train.py:763] (0/8) Epoch 13, batch 3800, loss[loss=0.1843, simple_loss=0.2641, pruned_loss=0.05227, over 6991.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2797, pruned_loss=0.04456, over 1418254.27 frames.], batch size: 16, lr: 5.44e-04
+2022-04-29 06:20:57,074 INFO [train.py:763] (0/8) Epoch 13, batch 3850, loss[loss=0.1825, simple_loss=0.2798, pruned_loss=0.04263, over 7216.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2798, pruned_loss=0.04462, over 1419903.84 frames.], batch size: 22, lr: 5.44e-04
+2022-04-29 06:22:02,337 INFO [train.py:763] (0/8) Epoch 13, batch 3900, loss[loss=0.1721, simple_loss=0.2736, pruned_loss=0.03536, over 7315.00 frames.], tot_loss[loss=0.184, simple_loss=0.2793, pruned_loss=0.04432, over 1422624.01 frames.], batch size: 21, lr: 5.44e-04
+2022-04-29 06:23:08,133 INFO [train.py:763] (0/8) Epoch 13, batch 3950, loss[loss=0.2608, simple_loss=0.3322, pruned_loss=0.09467, over 4775.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2784, pruned_loss=0.04396, over 1420450.63 frames.], batch size: 52, lr: 5.44e-04
+2022-04-29 06:24:13,274 INFO [train.py:763] (0/8) Epoch 13, batch 4000, loss[loss=0.2156, simple_loss=0.305, pruned_loss=0.06306, over 7340.00 frames.], tot_loss[loss=0.1839, simple_loss=0.279, pruned_loss=0.04444, over 1422635.29 frames.], batch size: 22, lr: 5.43e-04
+2022-04-29 06:25:19,016 INFO [train.py:763] (0/8) Epoch 13, batch 4050, loss[loss=0.1451, simple_loss=0.2371, pruned_loss=0.02658, over 6760.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2777, pruned_loss=0.04385, over 1423686.32 frames.], batch size: 15, lr: 5.43e-04
+2022-04-29 06:26:24,357 INFO [train.py:763] (0/8) Epoch 13, batch 4100, loss[loss=0.1997, simple_loss=0.3001, pruned_loss=0.04964, over 6825.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2785, pruned_loss=0.0443, over 1420373.33 frames.], batch size: 31, lr: 5.43e-04
+2022-04-29 06:27:29,941 INFO [train.py:763] (0/8) Epoch 13, batch 4150, loss[loss=0.1823, simple_loss=0.2825, pruned_loss=0.04111, over 7218.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2776, pruned_loss=0.04404, over 1419650.83 frames.], batch size: 21, lr: 5.43e-04
+2022-04-29 06:28:36,039 INFO [train.py:763] (0/8) Epoch 13, batch 4200, loss[loss=0.1745, simple_loss=0.2656, pruned_loss=0.04169, over 7260.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2761, pruned_loss=0.04354, over 1422029.16 frames.], batch size: 17, lr: 5.43e-04
+2022-04-29 06:29:41,280 INFO [train.py:763] (0/8) Epoch 13, batch 4250, loss[loss=0.2202, simple_loss=0.3149, pruned_loss=0.06272, over 6546.00 frames.], tot_loss[loss=0.1813, simple_loss=0.276, pruned_loss=0.04323, over 1415615.72 frames.], batch size: 38, lr: 5.42e-04
+2022-04-29 06:30:47,748 INFO [train.py:763] (0/8) Epoch 13, batch 4300, loss[loss=0.1631, simple_loss=0.2598, pruned_loss=0.03315, over 7220.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2767, pruned_loss=0.04341, over 1411877.20 frames.], batch size: 21, lr: 5.42e-04
+2022-04-29 06:31:53,168 INFO [train.py:763] (0/8) Epoch 13, batch 4350, loss[loss=0.2052, simple_loss=0.2755, pruned_loss=0.06747, over 6803.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2767, pruned_loss=0.04346, over 1408451.20 frames.], batch size: 15, lr: 5.42e-04
+2022-04-29 06:31:59,667 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-64000.pt
+2022-04-29 06:33:10,019 INFO [train.py:763] (0/8) Epoch 13, batch 4400, loss[loss=0.1982, simple_loss=0.2925, pruned_loss=0.05202, over 7147.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2763, pruned_loss=0.04369, over 1401960.73 frames.], batch size: 20, lr: 5.42e-04
+2022-04-29 06:34:14,934 INFO [train.py:763] (0/8) Epoch 13, batch 4450, loss[loss=0.2195, simple_loss=0.2976, pruned_loss=0.07073, over 5150.00 frames.], tot_loss[loss=0.183, simple_loss=0.278, pruned_loss=0.04402, over 1393230.48 frames.], batch size: 53, lr: 5.42e-04
+2022-04-29 06:35:30,497 INFO [train.py:763] (0/8) Epoch 13, batch 4500, loss[loss=0.2237, simple_loss=0.2997, pruned_loss=0.0739, over 5077.00 frames.], tot_loss[loss=0.185, simple_loss=0.2796, pruned_loss=0.04522, over 1379276.55 frames.], batch size: 52, lr: 5.41e-04
+2022-04-29 06:36:35,411 INFO [train.py:763] (0/8) Epoch 13, batch 4550, loss[loss=0.1998, simple_loss=0.2989, pruned_loss=0.05033, over 6763.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2796, pruned_loss=0.04536, over 1370260.68 frames.], batch size: 31, lr: 5.41e-04
+2022-04-29 06:37:34,966 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-13.pt
+2022-04-29 06:38:13,963 INFO [train.py:763] (0/8) Epoch 14, batch 0, loss[loss=0.1918, simple_loss=0.296, pruned_loss=0.04382, over 7004.00 frames.], tot_loss[loss=0.1918, simple_loss=0.296, pruned_loss=0.04382, over 7004.00 frames.], batch size: 28, lr: 5.25e-04
+2022-04-29 06:39:20,739 INFO [train.py:763] (0/8) Epoch 14, batch 50, loss[loss=0.2521, simple_loss=0.3274, pruned_loss=0.08847, over 5073.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2802, pruned_loss=0.04266, over 321760.44 frames.], batch size: 52, lr: 5.24e-04
+2022-04-29 06:40:45,788 INFO [train.py:763] (0/8) Epoch 14, batch 100, loss[loss=0.1815, simple_loss=0.2773, pruned_loss=0.04287, over 7160.00 frames.], tot_loss[loss=0.182, simple_loss=0.2786, pruned_loss=0.04269, over 569053.91 frames.], batch size: 18, lr: 5.24e-04
+2022-04-29 06:41:59,875 INFO [train.py:763] (0/8) Epoch 14, batch 150, loss[loss=0.1942, simple_loss=0.3022, pruned_loss=0.04304, over 7126.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2792, pruned_loss=0.04267, over 759299.89 frames.], batch size: 21, lr: 5.24e-04
+2022-04-29 06:43:06,518 INFO [train.py:763] (0/8) Epoch 14, batch 200, loss[loss=0.2012, simple_loss=0.2874, pruned_loss=0.05751, over 7328.00 frames.], tot_loss[loss=0.1836, simple_loss=0.28, pruned_loss=0.04362, over 902425.38 frames.], batch size: 20, lr: 5.24e-04
+2022-04-29 06:44:23,236 INFO [train.py:763] (0/8) Epoch 14, batch 250, loss[loss=0.2095, simple_loss=0.3133, pruned_loss=0.05288, over 6438.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2801, pruned_loss=0.04338, over 1019649.84 frames.], batch size: 37, lr: 5.24e-04
+2022-04-29 06:45:48,401 INFO [train.py:763] (0/8) Epoch 14, batch 300, loss[loss=0.1593, simple_loss=0.2491, pruned_loss=0.03472, over 7147.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2776, pruned_loss=0.04232, over 1109252.80 frames.], batch size: 17, lr: 5.23e-04
+2022-04-29 06:46:55,906 INFO [train.py:763] (0/8) Epoch 14, batch 350, loss[loss=0.1702, simple_loss=0.2531, pruned_loss=0.0436, over 6806.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2773, pruned_loss=0.04269, over 1172110.64 frames.], batch size: 15, lr: 5.23e-04
+2022-04-29 06:48:03,005 INFO [train.py:763] (0/8) Epoch 14, batch 400, loss[loss=0.1623, simple_loss=0.2644, pruned_loss=0.03012, over 7151.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2785, pruned_loss=0.04346, over 1226929.74 frames.], batch size: 20, lr: 5.23e-04
+2022-04-29 06:49:01,732 INFO [train.py:763] (0/8) Epoch 14, batch 450, loss[loss=0.1808, simple_loss=0.276, pruned_loss=0.04284, over 7154.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2785, pruned_loss=0.04349, over 1271194.30 frames.], batch size: 19, lr: 5.23e-04
+2022-04-29 06:50:05,443 INFO [train.py:763] (0/8) Epoch 14, batch 500, loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03047, over 7428.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2786, pruned_loss=0.04312, over 1303231.16 frames.], batch size: 20, lr: 5.23e-04
+2022-04-29 06:51:07,464 INFO [train.py:763] (0/8) Epoch 14, batch 550, loss[loss=0.1648, simple_loss=0.2521, pruned_loss=0.03869, over 7280.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2776, pruned_loss=0.04283, over 1332063.84 frames.], batch size: 18, lr: 5.22e-04
+2022-04-29 06:52:12,678 INFO [train.py:763] (0/8) Epoch 14, batch 600, loss[loss=0.1556, simple_loss=0.2568, pruned_loss=0.0272, over 7234.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2779, pruned_loss=0.04311, over 1354625.59 frames.], batch size: 20, lr: 5.22e-04
+2022-04-29 06:53:18,171 INFO [train.py:763] (0/8) Epoch 14, batch 650, loss[loss=0.164, simple_loss=0.2657, pruned_loss=0.03113, over 7333.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2776, pruned_loss=0.04271, over 1370039.79 frames.], batch size: 22, lr: 5.22e-04
+2022-04-29 06:54:23,440 INFO [train.py:763] (0/8) Epoch 14, batch 700, loss[loss=0.1892, simple_loss=0.288, pruned_loss=0.04514, over 7319.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2785, pruned_loss=0.04318, over 1383111.63 frames.], batch size: 20, lr: 5.22e-04
+2022-04-29 06:55:28,869 INFO [train.py:763] (0/8) Epoch 14, batch 750, loss[loss=0.159, simple_loss=0.263, pruned_loss=0.02746, over 7340.00 frames.], tot_loss[loss=0.1817, simple_loss=0.278, pruned_loss=0.0427, over 1391187.39 frames.], batch size: 22, lr: 5.22e-04
+2022-04-29 06:56:34,187 INFO [train.py:763] (0/8) Epoch 14, batch 800, loss[loss=0.2087, simple_loss=0.3132, pruned_loss=0.05213, over 7346.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2772, pruned_loss=0.04246, over 1399623.69 frames.], batch size: 22, lr: 5.21e-04
+2022-04-29 06:57:40,711 INFO [train.py:763] (0/8) Epoch 14, batch 850, loss[loss=0.1536, simple_loss=0.2355, pruned_loss=0.03579, over 7128.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2775, pruned_loss=0.04241, over 1402698.16 frames.], batch size: 17, lr: 5.21e-04
+2022-04-29 06:58:46,063 INFO [train.py:763] (0/8) Epoch 14, batch 900, loss[loss=0.1778, simple_loss=0.2764, pruned_loss=0.0396, over 7253.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2777, pruned_loss=0.04275, over 1396898.41 frames.], batch size: 19, lr: 5.21e-04
+2022-04-29 06:59:51,296 INFO [train.py:763] (0/8) Epoch 14, batch 950, loss[loss=0.1917, simple_loss=0.2892, pruned_loss=0.04709, over 7325.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2789, pruned_loss=0.04323, over 1405756.84 frames.], batch size: 22, lr: 5.21e-04
+2022-04-29 07:00:56,961 INFO [train.py:763] (0/8) Epoch 14, batch 1000, loss[loss=0.1744, simple_loss=0.2717, pruned_loss=0.03855, over 7017.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2787, pruned_loss=0.04294, over 1407219.67 frames.], batch size: 28, lr: 5.21e-04
+2022-04-29 07:02:02,206 INFO [train.py:763] (0/8) Epoch 14, batch 1050, loss[loss=0.1412, simple_loss=0.2302, pruned_loss=0.02614, over 7270.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2785, pruned_loss=0.04307, over 1412514.43 frames.], batch size: 18, lr: 5.20e-04
+2022-04-29 07:03:07,574 INFO [train.py:763] (0/8) Epoch 14, batch 1100, loss[loss=0.151, simple_loss=0.2448, pruned_loss=0.02862, over 7294.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2783, pruned_loss=0.043, over 1416842.60 frames.], batch size: 17, lr: 5.20e-04
+2022-04-29 07:04:13,192 INFO [train.py:763] (0/8) Epoch 14, batch 1150, loss[loss=0.1905, simple_loss=0.2874, pruned_loss=0.04685, over 7417.00 frames.], tot_loss[loss=0.182, simple_loss=0.2778, pruned_loss=0.04309, over 1421772.17 frames.], batch size: 21, lr: 5.20e-04
+2022-04-29 07:05:18,951 INFO [train.py:763] (0/8) Epoch 14, batch 1200, loss[loss=0.1864, simple_loss=0.2893, pruned_loss=0.04171, over 7427.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2765, pruned_loss=0.04247, over 1424070.53 frames.], batch size: 20, lr: 5.20e-04
+2022-04-29 07:06:24,256 INFO [train.py:763] (0/8) Epoch 14, batch 1250, loss[loss=0.1737, simple_loss=0.2697, pruned_loss=0.03884, over 7358.00 frames.], tot_loss[loss=0.181, simple_loss=0.2771, pruned_loss=0.04242, over 1427031.40 frames.], batch size: 19, lr: 5.20e-04
+2022-04-29 07:07:29,941 INFO [train.py:763] (0/8) Epoch 14, batch 1300, loss[loss=0.1781, simple_loss=0.2723, pruned_loss=0.04193, over 6376.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2772, pruned_loss=0.04266, over 1420409.79 frames.], batch size: 38, lr: 5.19e-04
+2022-04-29 07:08:35,859 INFO [train.py:763] (0/8) Epoch 14, batch 1350, loss[loss=0.159, simple_loss=0.2466, pruned_loss=0.03569, over 6994.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2775, pruned_loss=0.04271, over 1423003.53 frames.], batch size: 16, lr: 5.19e-04
+2022-04-29 07:09:40,891 INFO [train.py:763] (0/8) Epoch 14, batch 1400, loss[loss=0.1945, simple_loss=0.2927, pruned_loss=0.04821, over 7301.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2765, pruned_loss=0.04239, over 1422290.38 frames.], batch size: 24, lr: 5.19e-04
+2022-04-29 07:10:46,121 INFO [train.py:763] (0/8) Epoch 14, batch 1450, loss[loss=0.2222, simple_loss=0.3191, pruned_loss=0.06262, over 7380.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2768, pruned_loss=0.04266, over 1419080.16 frames.], batch size: 23, lr: 5.19e-04
+2022-04-29 07:11:52,465 INFO [train.py:763] (0/8) Epoch 14, batch 1500, loss[loss=0.1825, simple_loss=0.2768, pruned_loss=0.04414, over 7144.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2778, pruned_loss=0.04347, over 1413362.63 frames.], batch size: 20, lr: 5.19e-04
+2022-04-29 07:12:59,686 INFO [train.py:763] (0/8) Epoch 14, batch 1550, loss[loss=0.2075, simple_loss=0.3026, pruned_loss=0.05619, over 7110.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2766, pruned_loss=0.04313, over 1417177.48 frames.], batch size: 21, lr: 5.18e-04
+2022-04-29 07:14:06,940 INFO [train.py:763] (0/8) Epoch 14, batch 1600, loss[loss=0.1902, simple_loss=0.2911, pruned_loss=0.04467, over 7413.00 frames.], tot_loss[loss=0.181, simple_loss=0.2764, pruned_loss=0.04277, over 1419261.24 frames.], batch size: 21, lr: 5.18e-04
+2022-04-29 07:15:13,443 INFO [train.py:763] (0/8) Epoch 14, batch 1650, loss[loss=0.2042, simple_loss=0.3095, pruned_loss=0.0495, over 7199.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2762, pruned_loss=0.04214, over 1424484.46 frames.], batch size: 23, lr: 5.18e-04
+2022-04-29 07:16:19,633 INFO [train.py:763] (0/8) Epoch 14, batch 1700, loss[loss=0.2079, simple_loss=0.3034, pruned_loss=0.05616, over 7325.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2759, pruned_loss=0.0419, over 1428290.94 frames.], batch size: 25, lr: 5.18e-04
+2022-04-29 07:17:25,765 INFO [train.py:763] (0/8) Epoch 14, batch 1750, loss[loss=0.1932, simple_loss=0.2964, pruned_loss=0.04503, over 7115.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2754, pruned_loss=0.04159, over 1431167.44 frames.], batch size: 28, lr: 5.18e-04
+2022-04-29 07:18:31,000 INFO [train.py:763] (0/8) Epoch 14, batch 1800, loss[loss=0.17, simple_loss=0.2641, pruned_loss=0.03798, over 7273.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2758, pruned_loss=0.04186, over 1428431.32 frames.], batch size: 17, lr: 5.17e-04
+2022-04-29 07:19:36,656 INFO [train.py:763] (0/8) Epoch 14, batch 1850, loss[loss=0.1555, simple_loss=0.2509, pruned_loss=0.03006, over 7159.00 frames.], tot_loss[loss=0.18, simple_loss=0.2762, pruned_loss=0.04186, over 1432658.23 frames.], batch size: 18, lr: 5.17e-04
+2022-04-29 07:20:42,286 INFO [train.py:763] (0/8) Epoch 14, batch 1900, loss[loss=0.2005, simple_loss=0.2975, pruned_loss=0.05177, over 7117.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2763, pruned_loss=0.04201, over 1432477.63 frames.], batch size: 21, lr: 5.17e-04
+2022-04-29 07:21:47,871 INFO [train.py:763] (0/8) Epoch 14, batch 1950, loss[loss=0.1845, simple_loss=0.2825, pruned_loss=0.04331, over 7279.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2762, pruned_loss=0.04212, over 1432104.53 frames.], batch size: 18, lr: 5.17e-04
+2022-04-29 07:22:53,282 INFO [train.py:763] (0/8) Epoch 14, batch 2000, loss[loss=0.213, simple_loss=0.3165, pruned_loss=0.05473, over 6530.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2767, pruned_loss=0.04239, over 1427991.00 frames.], batch size: 38, lr: 5.17e-04
+2022-04-29 07:23:58,405 INFO [train.py:763] (0/8) Epoch 14, batch 2050, loss[loss=0.175, simple_loss=0.2837, pruned_loss=0.0332, over 7294.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2776, pruned_loss=0.04286, over 1429604.73 frames.], batch size: 25, lr: 5.16e-04
+2022-04-29 07:25:03,745 INFO [train.py:763] (0/8) Epoch 14, batch 2100, loss[loss=0.1727, simple_loss=0.2639, pruned_loss=0.04072, over 7412.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2773, pruned_loss=0.04313, over 1423080.48 frames.], batch size: 18, lr: 5.16e-04
+2022-04-29 07:26:09,027 INFO [train.py:763] (0/8) Epoch 14, batch 2150, loss[loss=0.1889, simple_loss=0.2922, pruned_loss=0.04274, over 7193.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2771, pruned_loss=0.04303, over 1420605.67 frames.], batch size: 22, lr: 5.16e-04
+2022-04-29 07:27:14,555 INFO [train.py:763] (0/8) Epoch 14, batch 2200, loss[loss=0.1843, simple_loss=0.2824, pruned_loss=0.0431, over 7421.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2774, pruned_loss=0.04327, over 1420564.45 frames.], batch size: 20, lr: 5.16e-04
+2022-04-29 07:28:19,754 INFO [train.py:763] (0/8) Epoch 14, batch 2250, loss[loss=0.1883, simple_loss=0.2884, pruned_loss=0.04415, over 7042.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2771, pruned_loss=0.04296, over 1421000.70 frames.], batch size: 28, lr: 5.16e-04
+2022-04-29 07:29:24,989 INFO [train.py:763] (0/8) Epoch 14, batch 2300, loss[loss=0.1565, simple_loss=0.2414, pruned_loss=0.03583, over 6775.00 frames.], tot_loss[loss=0.182, simple_loss=0.2776, pruned_loss=0.04314, over 1420114.35 frames.], batch size: 15, lr: 5.15e-04
+2022-04-29 07:30:30,171 INFO [train.py:763] (0/8) Epoch 14, batch 2350, loss[loss=0.1616, simple_loss=0.2434, pruned_loss=0.03988, over 7387.00 frames.], tot_loss[loss=0.182, simple_loss=0.2774, pruned_loss=0.04325, over 1423283.01 frames.], batch size: 18, lr: 5.15e-04
+2022-04-29 07:31:35,502 INFO [train.py:763] (0/8) Epoch 14, batch 2400, loss[loss=0.1521, simple_loss=0.2489, pruned_loss=0.02763, over 7417.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2786, pruned_loss=0.04388, over 1420936.70 frames.], batch size: 18, lr: 5.15e-04
+2022-04-29 07:32:40,934 INFO [train.py:763] (0/8) Epoch 14, batch 2450, loss[loss=0.1987, simple_loss=0.3013, pruned_loss=0.0481, over 7415.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2789, pruned_loss=0.04416, over 1422122.12 frames.], batch size: 21, lr: 5.15e-04
+2022-04-29 07:33:46,239 INFO [train.py:763] (0/8) Epoch 14, batch 2500, loss[loss=0.1994, simple_loss=0.2999, pruned_loss=0.04945, over 7315.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2797, pruned_loss=0.04439, over 1424461.07 frames.], batch size: 21, lr: 5.15e-04
+2022-04-29 07:34:51,435 INFO [train.py:763] (0/8) Epoch 14, batch 2550, loss[loss=0.1832, simple_loss=0.2762, pruned_loss=0.04515, over 7163.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2792, pruned_loss=0.04415, over 1427151.78 frames.], batch size: 18, lr: 5.14e-04
+2022-04-29 07:35:56,551 INFO [train.py:763] (0/8) Epoch 14, batch 2600, loss[loss=0.2021, simple_loss=0.3014, pruned_loss=0.05141, over 7200.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2799, pruned_loss=0.04476, over 1421337.02 frames.], batch size: 23, lr: 5.14e-04
+2022-04-29 07:37:01,623 INFO [train.py:763] (0/8) Epoch 14, batch 2650, loss[loss=0.1853, simple_loss=0.2868, pruned_loss=0.04188, over 7321.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2789, pruned_loss=0.04412, over 1421953.88 frames.], batch size: 25, lr: 5.14e-04
+2022-04-29 07:38:06,939 INFO [train.py:763] (0/8) Epoch 14, batch 2700, loss[loss=0.1962, simple_loss=0.3021, pruned_loss=0.0451, over 7314.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2786, pruned_loss=0.04359, over 1424190.28 frames.], batch size: 21, lr: 5.14e-04
+2022-04-29 07:39:12,141 INFO [train.py:763] (0/8) Epoch 14, batch 2750, loss[loss=0.2119, simple_loss=0.3017, pruned_loss=0.06104, over 7284.00 frames.], tot_loss[loss=0.1833, simple_loss=0.279, pruned_loss=0.04384, over 1425141.03 frames.], batch size: 24, lr: 5.14e-04
+2022-04-29 07:40:17,447 INFO [train.py:763] (0/8) Epoch 14, batch 2800, loss[loss=0.1748, simple_loss=0.2718, pruned_loss=0.03894, over 7150.00 frames.], tot_loss[loss=0.1823, simple_loss=0.278, pruned_loss=0.04328, over 1427951.03 frames.], batch size: 20, lr: 5.14e-04
+2022-04-29 07:41:22,763 INFO [train.py:763] (0/8) Epoch 14, batch 2850, loss[loss=0.1717, simple_loss=0.2683, pruned_loss=0.03759, over 7225.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2783, pruned_loss=0.04329, over 1428347.30 frames.], batch size: 16, lr: 5.13e-04
+2022-04-29 07:42:28,531 INFO [train.py:763] (0/8) Epoch 14, batch 2900, loss[loss=0.1798, simple_loss=0.2857, pruned_loss=0.03695, over 7388.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2778, pruned_loss=0.04287, over 1424238.83 frames.], batch size: 23, lr: 5.13e-04
+2022-04-29 07:43:34,059 INFO [train.py:763] (0/8) Epoch 14, batch 2950, loss[loss=0.1549, simple_loss=0.2584, pruned_loss=0.02575, over 7436.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2784, pruned_loss=0.0429, over 1425477.28 frames.], batch size: 20, lr: 5.13e-04
+2022-04-29 07:44:39,585 INFO [train.py:763] (0/8) Epoch 14, batch 3000, loss[loss=0.193, simple_loss=0.3036, pruned_loss=0.04118, over 7164.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2777, pruned_loss=0.04303, over 1423115.72 frames.], batch size: 19, lr: 5.13e-04
+2022-04-29 07:44:39,586 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 07:44:54,980 INFO [train.py:792] (0/8) Epoch 14, validation: loss=0.1687, simple_loss=0.2708, pruned_loss=0.03331, over 698248.00 frames.
+2022-04-29 07:46:00,334 INFO [train.py:763] (0/8) Epoch 14, batch 3050, loss[loss=0.1447, simple_loss=0.2411, pruned_loss=0.02414, over 7212.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2777, pruned_loss=0.04297, over 1426071.90 frames.], batch size: 16, lr: 5.13e-04
+2022-04-29 07:47:05,879 INFO [train.py:763] (0/8) Epoch 14, batch 3100, loss[loss=0.1541, simple_loss=0.2565, pruned_loss=0.02584, over 7329.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2783, pruned_loss=0.04378, over 1423203.20 frames.], batch size: 20, lr: 5.12e-04
+2022-04-29 07:48:12,217 INFO [train.py:763] (0/8) Epoch 14, batch 3150, loss[loss=0.1657, simple_loss=0.2531, pruned_loss=0.03909, over 7289.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2771, pruned_loss=0.04303, over 1427567.38 frames.], batch size: 17, lr: 5.12e-04
+2022-04-29 07:49:18,813 INFO [train.py:763] (0/8) Epoch 14, batch 3200, loss[loss=0.1927, simple_loss=0.2958, pruned_loss=0.04476, over 7115.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2766, pruned_loss=0.04285, over 1428227.49 frames.], batch size: 28, lr: 5.12e-04
+2022-04-29 07:50:24,265 INFO [train.py:763] (0/8) Epoch 14, batch 3250, loss[loss=0.1549, simple_loss=0.2553, pruned_loss=0.02724, over 7068.00 frames.], tot_loss[loss=0.1803, simple_loss=0.276, pruned_loss=0.04226, over 1428226.41 frames.], batch size: 18, lr: 5.12e-04
+2022-04-29 07:51:29,743 INFO [train.py:763] (0/8) Epoch 14, batch 3300, loss[loss=0.1741, simple_loss=0.2609, pruned_loss=0.04369, over 7305.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2748, pruned_loss=0.04179, over 1427772.49 frames.], batch size: 17, lr: 5.12e-04
+2022-04-29 07:52:35,067 INFO [train.py:763] (0/8) Epoch 14, batch 3350, loss[loss=0.1768, simple_loss=0.2844, pruned_loss=0.03462, over 7218.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2757, pruned_loss=0.04206, over 1427622.06 frames.], batch size: 23, lr: 5.11e-04
+2022-04-29 07:53:40,822 INFO [train.py:763] (0/8) Epoch 14, batch 3400, loss[loss=0.1849, simple_loss=0.2846, pruned_loss=0.04259, over 7228.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2769, pruned_loss=0.04243, over 1424753.16 frames.], batch size: 21, lr: 5.11e-04
+2022-04-29 07:54:45,995 INFO [train.py:763] (0/8) Epoch 14, batch 3450, loss[loss=0.1774, simple_loss=0.279, pruned_loss=0.03794, over 7058.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2779, pruned_loss=0.04291, over 1421885.18 frames.], batch size: 28, lr: 5.11e-04
+2022-04-29 07:55:51,605 INFO [train.py:763] (0/8) Epoch 14, batch 3500, loss[loss=0.1911, simple_loss=0.2811, pruned_loss=0.05057, over 7186.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2771, pruned_loss=0.04252, over 1426792.00 frames.], batch size: 26, lr: 5.11e-04
+2022-04-29 07:56:57,024 INFO [train.py:763] (0/8) Epoch 14, batch 3550, loss[loss=0.1841, simple_loss=0.2848, pruned_loss=0.0417, over 7236.00 frames.], tot_loss[loss=0.1811, simple_loss=0.277, pruned_loss=0.04261, over 1428404.28 frames.], batch size: 20, lr: 5.11e-04
+2022-04-29 07:58:03,511 INFO [train.py:763] (0/8) Epoch 14, batch 3600, loss[loss=0.1969, simple_loss=0.294, pruned_loss=0.0499, over 7322.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2772, pruned_loss=0.04284, over 1424169.80 frames.], batch size: 21, lr: 5.11e-04
+2022-04-29 07:59:08,921 INFO [train.py:763] (0/8) Epoch 14, batch 3650, loss[loss=0.1463, simple_loss=0.2394, pruned_loss=0.02663, over 7256.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2773, pruned_loss=0.0427, over 1425395.82 frames.], batch size: 19, lr: 5.10e-04
+2022-04-29 08:00:14,239 INFO [train.py:763] (0/8) Epoch 14, batch 3700, loss[loss=0.1714, simple_loss=0.265, pruned_loss=0.03894, over 7427.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2778, pruned_loss=0.04304, over 1421750.10 frames.], batch size: 20, lr: 5.10e-04
+2022-04-29 08:01:20,002 INFO [train.py:763] (0/8) Epoch 14, batch 3750, loss[loss=0.2164, simple_loss=0.3025, pruned_loss=0.06512, over 5330.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2774, pruned_loss=0.04313, over 1423475.52 frames.], batch size: 53, lr: 5.10e-04
+2022-04-29 08:02:27,030 INFO [train.py:763] (0/8) Epoch 14, batch 3800, loss[loss=0.1563, simple_loss=0.2528, pruned_loss=0.02996, over 7059.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2776, pruned_loss=0.04283, over 1425893.77 frames.], batch size: 18, lr: 5.10e-04
+2022-04-29 08:03:33,825 INFO [train.py:763] (0/8) Epoch 14, batch 3850, loss[loss=0.1779, simple_loss=0.2791, pruned_loss=0.03832, over 7240.00 frames.], tot_loss[loss=0.182, simple_loss=0.2781, pruned_loss=0.04291, over 1428634.78 frames.], batch size: 20, lr: 5.10e-04
+2022-04-29 08:04:40,273 INFO [train.py:763] (0/8) Epoch 14, batch 3900, loss[loss=0.1467, simple_loss=0.2525, pruned_loss=0.02049, over 7268.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2775, pruned_loss=0.04292, over 1426550.36 frames.], batch size: 19, lr: 5.09e-04
+2022-04-29 08:05:46,502 INFO [train.py:763] (0/8) Epoch 14, batch 3950, loss[loss=0.1767, simple_loss=0.269, pruned_loss=0.04221, over 7357.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2773, pruned_loss=0.04277, over 1423643.94 frames.], batch size: 19, lr: 5.09e-04
+2022-04-29 08:06:52,815 INFO [train.py:763] (0/8) Epoch 14, batch 4000, loss[loss=0.1559, simple_loss=0.2644, pruned_loss=0.02368, over 7219.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2765, pruned_loss=0.0419, over 1423380.22 frames.], batch size: 21, lr: 5.09e-04
+2022-04-29 08:07:57,997 INFO [train.py:763] (0/8) Epoch 14, batch 4050, loss[loss=0.1886, simple_loss=0.2798, pruned_loss=0.04866, over 7222.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2772, pruned_loss=0.04215, over 1427197.30 frames.], batch size: 21, lr: 5.09e-04
+2022-04-29 08:09:03,295 INFO [train.py:763] (0/8) Epoch 14, batch 4100, loss[loss=0.1778, simple_loss=0.2785, pruned_loss=0.03855, over 7213.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2776, pruned_loss=0.04244, over 1419228.16 frames.], batch size: 23, lr: 5.09e-04
+2022-04-29 08:10:08,501 INFO [train.py:763] (0/8) Epoch 14, batch 4150, loss[loss=0.2108, simple_loss=0.3036, pruned_loss=0.05906, over 4720.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2771, pruned_loss=0.04264, over 1412691.96 frames.], batch size: 52, lr: 5.08e-04
+2022-04-29 08:11:13,735 INFO [train.py:763] (0/8) Epoch 14, batch 4200, loss[loss=0.1887, simple_loss=0.2893, pruned_loss=0.04403, over 7230.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2756, pruned_loss=0.04212, over 1410280.95 frames.], batch size: 20, lr: 5.08e-04
+2022-04-29 08:12:19,799 INFO [train.py:763] (0/8) Epoch 14, batch 4250, loss[loss=0.1632, simple_loss=0.2635, pruned_loss=0.03148, over 7068.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2763, pruned_loss=0.04238, over 1408339.19 frames.], batch size: 18, lr: 5.08e-04
+2022-04-29 08:13:25,932 INFO [train.py:763] (0/8) Epoch 14, batch 4300, loss[loss=0.1476, simple_loss=0.2332, pruned_loss=0.031, over 6784.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2766, pruned_loss=0.0426, over 1403583.53 frames.], batch size: 15, lr: 5.08e-04
+2022-04-29 08:14:30,954 INFO [train.py:763] (0/8) Epoch 14, batch 4350, loss[loss=0.1642, simple_loss=0.2739, pruned_loss=0.02729, over 7330.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2774, pruned_loss=0.04272, over 1407609.60 frames.], batch size: 21, lr: 5.08e-04
+2022-04-29 08:15:37,054 INFO [train.py:763] (0/8) Epoch 14, batch 4400, loss[loss=0.1572, simple_loss=0.2549, pruned_loss=0.02974, over 7164.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2763, pruned_loss=0.0422, over 1409870.35 frames.], batch size: 19, lr: 5.08e-04
+2022-04-29 08:16:42,695 INFO [train.py:763] (0/8) Epoch 14, batch 4450, loss[loss=0.153, simple_loss=0.242, pruned_loss=0.03198, over 7154.00 frames.], tot_loss[loss=0.1795, simple_loss=0.275, pruned_loss=0.04205, over 1402435.77 frames.], batch size: 18, lr: 5.07e-04
+2022-04-29 08:17:47,615 INFO [train.py:763] (0/8) Epoch 14, batch 4500, loss[loss=0.1614, simple_loss=0.2541, pruned_loss=0.03435, over 7053.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2768, pruned_loss=0.04332, over 1393774.50 frames.], batch size: 18, lr: 5.07e-04
+2022-04-29 08:18:51,947 INFO [train.py:763] (0/8) Epoch 14, batch 4550, loss[loss=0.2217, simple_loss=0.3083, pruned_loss=0.06753, over 5117.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2781, pruned_loss=0.04426, over 1366263.63 frames.], batch size: 52, lr: 5.07e-04
+2022-04-29 08:19:42,461 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-14.pt
+2022-04-29 08:20:20,836 INFO [train.py:763] (0/8) Epoch 15, batch 0, loss[loss=0.1859, simple_loss=0.2886, pruned_loss=0.0416, over 7314.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2886, pruned_loss=0.0416, over 7314.00 frames.], batch size: 24, lr: 4.92e-04
+2022-04-29 08:21:27,549 INFO [train.py:763] (0/8) Epoch 15, batch 50, loss[loss=0.1673, simple_loss=0.2547, pruned_loss=0.04001, over 7409.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2791, pruned_loss=0.04231, over 320644.02 frames.], batch size: 18, lr: 4.92e-04
+2022-04-29 08:22:33,679 INFO [train.py:763] (0/8) Epoch 15, batch 100, loss[loss=0.1725, simple_loss=0.2719, pruned_loss=0.03653, over 7322.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2763, pruned_loss=0.04153, over 563906.91 frames.], batch size: 20, lr: 4.92e-04
+2022-04-29 08:23:40,364 INFO [train.py:763] (0/8) Epoch 15, batch 150, loss[loss=0.2002, simple_loss=0.2842, pruned_loss=0.05812, over 7147.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2766, pruned_loss=0.04192, over 754104.57 frames.], batch size: 20, lr: 4.92e-04
+2022-04-29 08:24:46,771 INFO [train.py:763] (0/8) Epoch 15, batch 200, loss[loss=0.1911, simple_loss=0.2948, pruned_loss=0.04369, over 7126.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2749, pruned_loss=0.04144, over 897916.16 frames.], batch size: 21, lr: 4.91e-04
+2022-04-29 08:25:52,230 INFO [train.py:763] (0/8) Epoch 15, batch 250, loss[loss=0.1695, simple_loss=0.265, pruned_loss=0.037, over 7165.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2742, pruned_loss=0.04115, over 1015025.77 frames.], batch size: 19, lr: 4.91e-04
+2022-04-29 08:26:57,842 INFO [train.py:763] (0/8) Epoch 15, batch 300, loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02917, over 7162.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2735, pruned_loss=0.04097, over 1109151.04 frames.], batch size: 19, lr: 4.91e-04
+2022-04-29 08:28:03,221 INFO [train.py:763] (0/8) Epoch 15, batch 350, loss[loss=0.171, simple_loss=0.2558, pruned_loss=0.04311, over 7264.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2735, pruned_loss=0.04066, over 1179861.55 frames.], batch size: 18, lr: 4.91e-04
+2022-04-29 08:29:08,694 INFO [train.py:763] (0/8) Epoch 15, batch 400, loss[loss=0.1747, simple_loss=0.2768, pruned_loss=0.03633, over 7250.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2742, pruned_loss=0.0403, over 1233585.30 frames.], batch size: 19, lr: 4.91e-04
+2022-04-29 08:30:14,243 INFO [train.py:763] (0/8) Epoch 15, batch 450, loss[loss=0.163, simple_loss=0.2635, pruned_loss=0.03123, over 7430.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2747, pruned_loss=0.04059, over 1281202.98 frames.], batch size: 20, lr: 4.91e-04
+2022-04-29 08:31:19,786 INFO [train.py:763] (0/8) Epoch 15, batch 500, loss[loss=0.1733, simple_loss=0.2706, pruned_loss=0.03801, over 7202.00 frames.], tot_loss[loss=0.178, simple_loss=0.2751, pruned_loss=0.04044, over 1317772.24 frames.], batch size: 23, lr: 4.90e-04
+2022-04-29 08:32:25,949 INFO [train.py:763] (0/8) Epoch 15, batch 550, loss[loss=0.1565, simple_loss=0.2451, pruned_loss=0.03399, over 7269.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2743, pruned_loss=0.04039, over 1344931.20 frames.], batch size: 18, lr: 4.90e-04
+2022-04-29 08:33:31,112 INFO [train.py:763] (0/8) Epoch 15, batch 600, loss[loss=0.1736, simple_loss=0.2637, pruned_loss=0.04172, over 7160.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2747, pruned_loss=0.04039, over 1360162.94 frames.], batch size: 19, lr: 4.90e-04
+2022-04-29 08:34:36,402 INFO [train.py:763] (0/8) Epoch 15, batch 650, loss[loss=0.2006, simple_loss=0.2964, pruned_loss=0.05237, over 6421.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2752, pruned_loss=0.0408, over 1373732.19 frames.], batch size: 38, lr: 4.90e-04
+2022-04-29 08:35:42,063 INFO [train.py:763] (0/8) Epoch 15, batch 700, loss[loss=0.1609, simple_loss=0.2638, pruned_loss=0.02903, over 7043.00 frames.], tot_loss[loss=0.179, simple_loss=0.2754, pruned_loss=0.04127, over 1386461.20 frames.], batch size: 28, lr: 4.90e-04
+2022-04-29 08:36:47,196 INFO [train.py:763] (0/8) Epoch 15, batch 750, loss[loss=0.1729, simple_loss=0.2628, pruned_loss=0.04153, over 7155.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2752, pruned_loss=0.04122, over 1395378.02 frames.], batch size: 19, lr: 4.89e-04
+2022-04-29 08:37:53,256 INFO [train.py:763] (0/8) Epoch 15, batch 800, loss[loss=0.1693, simple_loss=0.2677, pruned_loss=0.03549, over 7263.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2759, pruned_loss=0.04151, over 1402612.64 frames.], batch size: 19, lr: 4.89e-04
+2022-04-29 08:39:00,147 INFO [train.py:763] (0/8) Epoch 15, batch 850, loss[loss=0.1655, simple_loss=0.2722, pruned_loss=0.02944, over 7152.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2763, pruned_loss=0.0414, over 1404181.83 frames.], batch size: 20, lr: 4.89e-04
+2022-04-29 08:40:05,807 INFO [train.py:763] (0/8) Epoch 15, batch 900, loss[loss=0.1828, simple_loss=0.2894, pruned_loss=0.03811, over 7363.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2768, pruned_loss=0.0422, over 1403357.13 frames.], batch size: 19, lr: 4.89e-04
+2022-04-29 08:41:11,042 INFO [train.py:763] (0/8) Epoch 15, batch 950, loss[loss=0.1668, simple_loss=0.2698, pruned_loss=0.03188, over 7426.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2768, pruned_loss=0.04234, over 1406808.34 frames.], batch size: 20, lr: 4.89e-04
+2022-04-29 08:42:16,446 INFO [train.py:763] (0/8) Epoch 15, batch 1000, loss[loss=0.2023, simple_loss=0.3041, pruned_loss=0.05026, over 7310.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2759, pruned_loss=0.04189, over 1411962.31 frames.], batch size: 25, lr: 4.89e-04
+2022-04-29 08:43:21,673 INFO [train.py:763] (0/8) Epoch 15, batch 1050, loss[loss=0.1759, simple_loss=0.2677, pruned_loss=0.04207, over 7332.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2757, pruned_loss=0.0418, over 1417126.40 frames.], batch size: 20, lr: 4.88e-04
+2022-04-29 08:44:28,817 INFO [train.py:763] (0/8) Epoch 15, batch 1100, loss[loss=0.1977, simple_loss=0.2915, pruned_loss=0.05195, over 7362.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2756, pruned_loss=0.04127, over 1420857.68 frames.], batch size: 19, lr: 4.88e-04
+2022-04-29 08:45:35,104 INFO [train.py:763] (0/8) Epoch 15, batch 1150, loss[loss=0.2106, simple_loss=0.3006, pruned_loss=0.06028, over 5234.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2751, pruned_loss=0.04123, over 1421144.87 frames.], batch size: 52, lr: 4.88e-04
+2022-04-29 08:46:40,376 INFO [train.py:763] (0/8) Epoch 15, batch 1200, loss[loss=0.1788, simple_loss=0.2778, pruned_loss=0.03995, over 7109.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2752, pruned_loss=0.04169, over 1418633.28 frames.], batch size: 21, lr: 4.88e-04
+2022-04-29 08:47:45,863 INFO [train.py:763] (0/8) Epoch 15, batch 1250, loss[loss=0.1776, simple_loss=0.2557, pruned_loss=0.04976, over 6798.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2754, pruned_loss=0.04207, over 1418664.66 frames.], batch size: 15, lr: 4.88e-04
+2022-04-29 08:48:51,153 INFO [train.py:763] (0/8) Epoch 15, batch 1300, loss[loss=0.2049, simple_loss=0.2998, pruned_loss=0.05501, over 7211.00 frames.], tot_loss[loss=0.181, simple_loss=0.277, pruned_loss=0.04253, over 1424741.32 frames.], batch size: 22, lr: 4.88e-04
+2022-04-29 08:49:56,813 INFO [train.py:763] (0/8) Epoch 15, batch 1350, loss[loss=0.1602, simple_loss=0.2544, pruned_loss=0.03293, over 7173.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2772, pruned_loss=0.04274, over 1417897.02 frames.], batch size: 19, lr: 4.87e-04
+2022-04-29 08:51:13,243 INFO [train.py:763] (0/8) Epoch 15, batch 1400, loss[loss=0.1613, simple_loss=0.2673, pruned_loss=0.02768, over 7348.00 frames.], tot_loss[loss=0.182, simple_loss=0.2783, pruned_loss=0.04289, over 1416365.89 frames.], batch size: 22, lr: 4.87e-04
+2022-04-29 08:52:20,212 INFO [train.py:763] (0/8) Epoch 15, batch 1450, loss[loss=0.1792, simple_loss=0.2799, pruned_loss=0.03921, over 7420.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2779, pruned_loss=0.04214, over 1422554.12 frames.], batch size: 21, lr: 4.87e-04
+2022-04-29 08:53:25,688 INFO [train.py:763] (0/8) Epoch 15, batch 1500, loss[loss=0.2025, simple_loss=0.3181, pruned_loss=0.04346, over 7194.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2773, pruned_loss=0.04188, over 1421851.05 frames.], batch size: 23, lr: 4.87e-04
+2022-04-29 08:54:40,093 INFO [train.py:763] (0/8) Epoch 15, batch 1550, loss[loss=0.1571, simple_loss=0.2479, pruned_loss=0.03314, over 6824.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2768, pruned_loss=0.04208, over 1420207.77 frames.], batch size: 15, lr: 4.87e-04
+2022-04-29 08:56:03,999 INFO [train.py:763] (0/8) Epoch 15, batch 1600, loss[loss=0.197, simple_loss=0.2809, pruned_loss=0.05655, over 6774.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2768, pruned_loss=0.04172, over 1422264.73 frames.], batch size: 15, lr: 4.87e-04
+2022-04-29 08:57:19,959 INFO [train.py:763] (0/8) Epoch 15, batch 1650, loss[loss=0.179, simple_loss=0.2831, pruned_loss=0.03744, over 7140.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2774, pruned_loss=0.04178, over 1424019.53 frames.], batch size: 20, lr: 4.86e-04
+2022-04-29 08:58:25,685 INFO [train.py:763] (0/8) Epoch 15, batch 1700, loss[loss=0.1352, simple_loss=0.2327, pruned_loss=0.01885, over 7418.00 frames.], tot_loss[loss=0.18, simple_loss=0.2765, pruned_loss=0.04174, over 1424522.77 frames.], batch size: 18, lr: 4.86e-04
+2022-04-29 08:59:40,119 INFO [train.py:763] (0/8) Epoch 15, batch 1750, loss[loss=0.2136, simple_loss=0.3078, pruned_loss=0.05968, over 7376.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2777, pruned_loss=0.04258, over 1424206.30 frames.], batch size: 23, lr: 4.86e-04
+2022-04-29 09:00:47,100 INFO [train.py:763] (0/8) Epoch 15, batch 1800, loss[loss=0.1338, simple_loss=0.2335, pruned_loss=0.01703, over 7360.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2775, pruned_loss=0.04266, over 1422759.80 frames.], batch size: 19, lr: 4.86e-04
+2022-04-29 09:02:11,311 INFO [train.py:763] (0/8) Epoch 15, batch 1850, loss[loss=0.1811, simple_loss=0.2771, pruned_loss=0.04259, over 7146.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2763, pruned_loss=0.0423, over 1424820.45 frames.], batch size: 20, lr: 4.86e-04
+2022-04-29 09:03:16,752 INFO [train.py:763] (0/8) Epoch 15, batch 1900, loss[loss=0.2206, simple_loss=0.3246, pruned_loss=0.05827, over 7269.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2762, pruned_loss=0.04206, over 1428582.50 frames.], batch size: 25, lr: 4.86e-04
+2022-04-29 09:04:23,835 INFO [train.py:763] (0/8) Epoch 15, batch 1950, loss[loss=0.1748, simple_loss=0.28, pruned_loss=0.03484, over 7188.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2753, pruned_loss=0.04127, over 1429883.12 frames.], batch size: 23, lr: 4.85e-04
+2022-04-29 09:05:29,700 INFO [train.py:763] (0/8) Epoch 15, batch 2000, loss[loss=0.2198, simple_loss=0.3149, pruned_loss=0.06236, over 5053.00 frames.], tot_loss[loss=0.1797, simple_loss=0.276, pruned_loss=0.04167, over 1423870.58 frames.], batch size: 53, lr: 4.85e-04
+2022-04-29 09:06:36,321 INFO [train.py:763] (0/8) Epoch 15, batch 2050, loss[loss=0.2048, simple_loss=0.3069, pruned_loss=0.05134, over 6611.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2763, pruned_loss=0.04197, over 1422358.35 frames.], batch size: 38, lr: 4.85e-04
+2022-04-29 09:07:42,007 INFO [train.py:763] (0/8) Epoch 15, batch 2100, loss[loss=0.1748, simple_loss=0.275, pruned_loss=0.03728, over 7104.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2768, pruned_loss=0.04199, over 1422860.29 frames.], batch size: 21, lr: 4.85e-04
+2022-04-29 09:08:48,748 INFO [train.py:763] (0/8) Epoch 15, batch 2150, loss[loss=0.1481, simple_loss=0.2426, pruned_loss=0.02679, over 7255.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2772, pruned_loss=0.04213, over 1417881.31 frames.], batch size: 19, lr: 4.85e-04
+2022-04-29 09:09:53,842 INFO [train.py:763] (0/8) Epoch 15, batch 2200, loss[loss=0.1681, simple_loss=0.2704, pruned_loss=0.03294, over 7209.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2769, pruned_loss=0.04208, over 1416429.78 frames.], batch size: 22, lr: 4.84e-04
+2022-04-29 09:10:59,460 INFO [train.py:763] (0/8) Epoch 15, batch 2250, loss[loss=0.195, simple_loss=0.3035, pruned_loss=0.04325, over 7417.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2763, pruned_loss=0.04207, over 1417540.12 frames.], batch size: 21, lr: 4.84e-04
+2022-04-29 09:12:05,744 INFO [train.py:763] (0/8) Epoch 15, batch 2300, loss[loss=0.1944, simple_loss=0.297, pruned_loss=0.04589, over 7184.00 frames.], tot_loss[loss=0.18, simple_loss=0.2765, pruned_loss=0.04172, over 1419541.62 frames.], batch size: 23, lr: 4.84e-04
+2022-04-29 09:13:13,279 INFO [train.py:763] (0/8) Epoch 15, batch 2350, loss[loss=0.2038, simple_loss=0.3063, pruned_loss=0.05062, over 7275.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2768, pruned_loss=0.0422, over 1421554.65 frames.], batch size: 25, lr: 4.84e-04
+2022-04-29 09:14:19,344 INFO [train.py:763] (0/8) Epoch 15, batch 2400, loss[loss=0.1998, simple_loss=0.2909, pruned_loss=0.05436, over 7310.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2758, pruned_loss=0.04201, over 1425343.09 frames.], batch size: 25, lr: 4.84e-04
+2022-04-29 09:15:24,438 INFO [train.py:763] (0/8) Epoch 15, batch 2450, loss[loss=0.1872, simple_loss=0.2896, pruned_loss=0.04242, over 6658.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2754, pruned_loss=0.04189, over 1424342.46 frames.], batch size: 31, lr: 4.84e-04
+2022-04-29 09:16:31,168 INFO [train.py:763] (0/8) Epoch 15, batch 2500, loss[loss=0.1508, simple_loss=0.2514, pruned_loss=0.02512, over 7238.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2745, pruned_loss=0.04162, over 1426931.13 frames.], batch size: 21, lr: 4.83e-04
+2022-04-29 09:17:37,370 INFO [train.py:763] (0/8) Epoch 15, batch 2550, loss[loss=0.1864, simple_loss=0.2879, pruned_loss=0.04242, over 7153.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2737, pruned_loss=0.04146, over 1423647.46 frames.], batch size: 20, lr: 4.83e-04
+2022-04-29 09:18:44,504 INFO [train.py:763] (0/8) Epoch 15, batch 2600, loss[loss=0.1522, simple_loss=0.2539, pruned_loss=0.02521, over 7357.00 frames.], tot_loss[loss=0.1786, simple_loss=0.274, pruned_loss=0.04159, over 1421642.59 frames.], batch size: 19, lr: 4.83e-04
+2022-04-29 09:19:51,213 INFO [train.py:763] (0/8) Epoch 15, batch 2650, loss[loss=0.1726, simple_loss=0.2723, pruned_loss=0.03643, over 7375.00 frames.], tot_loss[loss=0.1796, simple_loss=0.275, pruned_loss=0.04207, over 1421980.51 frames.], batch size: 23, lr: 4.83e-04
+2022-04-29 09:20:56,497 INFO [train.py:763] (0/8) Epoch 15, batch 2700, loss[loss=0.2093, simple_loss=0.3043, pruned_loss=0.05714, over 7178.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2762, pruned_loss=0.04241, over 1419710.95 frames.], batch size: 26, lr: 4.83e-04
+2022-04-29 09:22:02,860 INFO [train.py:763] (0/8) Epoch 15, batch 2750, loss[loss=0.1649, simple_loss=0.2513, pruned_loss=0.03928, over 7266.00 frames.], tot_loss[loss=0.18, simple_loss=0.2759, pruned_loss=0.04208, over 1423878.62 frames.], batch size: 18, lr: 4.83e-04
+2022-04-29 09:23:10,128 INFO [train.py:763] (0/8) Epoch 15, batch 2800, loss[loss=0.1788, simple_loss=0.2816, pruned_loss=0.03806, over 7228.00 frames.], tot_loss[loss=0.1797, simple_loss=0.276, pruned_loss=0.0417, over 1426156.21 frames.], batch size: 21, lr: 4.82e-04
+2022-04-29 09:24:17,308 INFO [train.py:763] (0/8) Epoch 15, batch 2850, loss[loss=0.1744, simple_loss=0.278, pruned_loss=0.03535, over 7166.00 frames.], tot_loss[loss=0.18, simple_loss=0.2763, pruned_loss=0.04185, over 1425224.58 frames.], batch size: 18, lr: 4.82e-04
+2022-04-29 09:25:24,242 INFO [train.py:763] (0/8) Epoch 15, batch 2900, loss[loss=0.1648, simple_loss=0.2632, pruned_loss=0.03323, over 7166.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2759, pruned_loss=0.04159, over 1427419.37 frames.], batch size: 18, lr: 4.82e-04
+2022-04-29 09:26:29,785 INFO [train.py:763] (0/8) Epoch 15, batch 2950, loss[loss=0.1859, simple_loss=0.292, pruned_loss=0.03987, over 7342.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2766, pruned_loss=0.0421, over 1423768.94 frames.], batch size: 22, lr: 4.82e-04
+2022-04-29 09:27:35,047 INFO [train.py:763] (0/8) Epoch 15, batch 3000, loss[loss=0.1934, simple_loss=0.3, pruned_loss=0.04338, over 7412.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2766, pruned_loss=0.0421, over 1427828.87 frames.], batch size: 21, lr: 4.82e-04
+2022-04-29 09:27:35,049 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 09:27:50,493 INFO [train.py:792] (0/8) Epoch 15, validation: loss=0.1668, simple_loss=0.2684, pruned_loss=0.03254, over 698248.00 frames.
+2022-04-29 09:28:57,663 INFO [train.py:763] (0/8) Epoch 15, batch 3050, loss[loss=0.1746, simple_loss=0.2645, pruned_loss=0.04234, over 7413.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2759, pruned_loss=0.04196, over 1426814.81 frames.], batch size: 18, lr: 4.82e-04
+2022-04-29 09:30:04,582 INFO [train.py:763] (0/8) Epoch 15, batch 3100, loss[loss=0.1879, simple_loss=0.2792, pruned_loss=0.04827, over 7187.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2756, pruned_loss=0.04197, over 1426403.44 frames.], batch size: 23, lr: 4.81e-04
+2022-04-29 09:31:11,609 INFO [train.py:763] (0/8) Epoch 15, batch 3150, loss[loss=0.1768, simple_loss=0.2699, pruned_loss=0.04192, over 7172.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2755, pruned_loss=0.04165, over 1423427.81 frames.], batch size: 18, lr: 4.81e-04
+2022-04-29 09:31:50,212 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-72000.pt
+2022-04-29 09:32:29,199 INFO [train.py:763] (0/8) Epoch 15, batch 3200, loss[loss=0.176, simple_loss=0.2767, pruned_loss=0.0376, over 7291.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2761, pruned_loss=0.04159, over 1423831.87 frames.], batch size: 24, lr: 4.81e-04
+2022-04-29 09:33:36,707 INFO [train.py:763] (0/8) Epoch 15, batch 3250, loss[loss=0.1683, simple_loss=0.2715, pruned_loss=0.03262, over 7301.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2759, pruned_loss=0.04156, over 1425258.61 frames.], batch size: 21, lr: 4.81e-04
+2022-04-29 09:34:43,502 INFO [train.py:763] (0/8) Epoch 15, batch 3300, loss[loss=0.1808, simple_loss=0.2844, pruned_loss=0.03864, over 7253.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2761, pruned_loss=0.04131, over 1429193.99 frames.], batch size: 25, lr: 4.81e-04
+2022-04-29 09:35:50,332 INFO [train.py:763] (0/8) Epoch 15, batch 3350, loss[loss=0.1834, simple_loss=0.2876, pruned_loss=0.03965, over 7227.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2755, pruned_loss=0.04083, over 1431236.70 frames.], batch size: 20, lr: 4.81e-04
+2022-04-29 09:36:57,535 INFO [train.py:763] (0/8) Epoch 15, batch 3400, loss[loss=0.1851, simple_loss=0.2829, pruned_loss=0.04372, over 6987.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2767, pruned_loss=0.04118, over 1428297.70 frames.], batch size: 28, lr: 4.80e-04
+2022-04-29 09:38:05,027 INFO [train.py:763] (0/8) Epoch 15, batch 3450, loss[loss=0.1694, simple_loss=0.2651, pruned_loss=0.0368, over 7370.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2762, pruned_loss=0.04105, over 1429178.40 frames.], batch size: 19, lr: 4.80e-04
+2022-04-29 09:39:11,461 INFO [train.py:763] (0/8) Epoch 15, batch 3500, loss[loss=0.1658, simple_loss=0.2699, pruned_loss=0.03085, over 7308.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2762, pruned_loss=0.04071, over 1427719.08 frames.], batch size: 21, lr: 4.80e-04
+2022-04-29 09:40:16,438 INFO [train.py:763] (0/8) Epoch 15, batch 3550, loss[loss=0.2636, simple_loss=0.342, pruned_loss=0.09258, over 7158.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2772, pruned_loss=0.0413, over 1423279.00 frames.], batch size: 26, lr: 4.80e-04
+2022-04-29 09:41:21,624 INFO [train.py:763] (0/8) Epoch 15, batch 3600, loss[loss=0.1895, simple_loss=0.2937, pruned_loss=0.04266, over 7325.00 frames.], tot_loss[loss=0.1789, simple_loss=0.276, pruned_loss=0.04084, over 1424976.43 frames.], batch size: 21, lr: 4.80e-04
+2022-04-29 09:42:26,937 INFO [train.py:763] (0/8) Epoch 15, batch 3650, loss[loss=0.1993, simple_loss=0.2722, pruned_loss=0.06318, over 7282.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2762, pruned_loss=0.04134, over 1426024.24 frames.], batch size: 18, lr: 4.80e-04
+2022-04-29 09:43:33,159 INFO [train.py:763] (0/8) Epoch 15, batch 3700, loss[loss=0.1918, simple_loss=0.2798, pruned_loss=0.05186, over 7271.00 frames.], tot_loss[loss=0.179, simple_loss=0.2759, pruned_loss=0.04107, over 1423601.80 frames.], batch size: 16, lr: 4.79e-04
+2022-04-29 09:44:39,841 INFO [train.py:763] (0/8) Epoch 15, batch 3750, loss[loss=0.1879, simple_loss=0.2948, pruned_loss=0.04046, over 7290.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2761, pruned_loss=0.04134, over 1421224.02 frames.], batch size: 25, lr: 4.79e-04
+2022-04-29 09:45:46,804 INFO [train.py:763] (0/8) Epoch 15, batch 3800, loss[loss=0.1811, simple_loss=0.2658, pruned_loss=0.04819, over 7150.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2769, pruned_loss=0.04171, over 1424978.34 frames.], batch size: 17, lr: 4.79e-04
+2022-04-29 09:46:53,787 INFO [train.py:763] (0/8) Epoch 15, batch 3850, loss[loss=0.1506, simple_loss=0.2525, pruned_loss=0.02435, over 7273.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2774, pruned_loss=0.04195, over 1421952.47 frames.], batch size: 18, lr: 4.79e-04
+2022-04-29 09:48:00,488 INFO [train.py:763] (0/8) Epoch 15, batch 3900, loss[loss=0.204, simple_loss=0.3089, pruned_loss=0.04957, over 7224.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2768, pruned_loss=0.04171, over 1423226.99 frames.], batch size: 21, lr: 4.79e-04
+2022-04-29 09:49:06,621 INFO [train.py:763] (0/8) Epoch 15, batch 3950, loss[loss=0.1669, simple_loss=0.2715, pruned_loss=0.03122, over 7233.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2765, pruned_loss=0.04152, over 1421335.43 frames.], batch size: 20, lr: 4.79e-04
+2022-04-29 09:50:13,671 INFO [train.py:763] (0/8) Epoch 15, batch 4000, loss[loss=0.1977, simple_loss=0.2966, pruned_loss=0.04937, over 7318.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2759, pruned_loss=0.04122, over 1419156.29 frames.], batch size: 21, lr: 4.79e-04
+2022-04-29 09:51:19,319 INFO [train.py:763] (0/8) Epoch 15, batch 4050, loss[loss=0.1769, simple_loss=0.2731, pruned_loss=0.04031, over 7168.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2756, pruned_loss=0.04109, over 1418559.84 frames.], batch size: 18, lr: 4.78e-04
+2022-04-29 09:52:24,926 INFO [train.py:763] (0/8) Epoch 15, batch 4100, loss[loss=0.1491, simple_loss=0.2568, pruned_loss=0.02071, over 7163.00 frames.], tot_loss[loss=0.1785, simple_loss=0.275, pruned_loss=0.04101, over 1423713.59 frames.], batch size: 18, lr: 4.78e-04
+2022-04-29 09:53:30,120 INFO [train.py:763] (0/8) Epoch 15, batch 4150, loss[loss=0.1663, simple_loss=0.2602, pruned_loss=0.03615, over 7061.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2758, pruned_loss=0.04148, over 1417708.32 frames.], batch size: 28, lr: 4.78e-04
+2022-04-29 09:54:36,333 INFO [train.py:763] (0/8) Epoch 15, batch 4200, loss[loss=0.1583, simple_loss=0.2462, pruned_loss=0.03524, over 6990.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2747, pruned_loss=0.04077, over 1417059.50 frames.], batch size: 16, lr: 4.78e-04
+2022-04-29 09:55:43,469 INFO [train.py:763] (0/8) Epoch 15, batch 4250, loss[loss=0.1669, simple_loss=0.2675, pruned_loss=0.03316, over 7160.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2738, pruned_loss=0.04104, over 1416112.21 frames.], batch size: 18, lr: 4.78e-04
+2022-04-29 09:56:48,663 INFO [train.py:763] (0/8) Epoch 15, batch 4300, loss[loss=0.1709, simple_loss=0.2692, pruned_loss=0.03635, over 6850.00 frames.], tot_loss[loss=0.178, simple_loss=0.274, pruned_loss=0.04103, over 1411798.73 frames.], batch size: 31, lr: 4.78e-04
+2022-04-29 09:57:53,924 INFO [train.py:763] (0/8) Epoch 15, batch 4350, loss[loss=0.1645, simple_loss=0.2574, pruned_loss=0.03581, over 7170.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2742, pruned_loss=0.04077, over 1415288.38 frames.], batch size: 18, lr: 4.77e-04
+2022-04-29 09:59:00,574 INFO [train.py:763] (0/8) Epoch 15, batch 4400, loss[loss=0.1813, simple_loss=0.2755, pruned_loss=0.04353, over 7118.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2738, pruned_loss=0.04046, over 1415844.46 frames.], batch size: 21, lr: 4.77e-04
+2022-04-29 10:00:06,762 INFO [train.py:763] (0/8) Epoch 15, batch 4450, loss[loss=0.168, simple_loss=0.2729, pruned_loss=0.03154, over 7212.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2738, pruned_loss=0.04062, over 1411259.18 frames.], batch size: 22, lr: 4.77e-04
+2022-04-29 10:01:11,556 INFO [train.py:763] (0/8) Epoch 15, batch 4500, loss[loss=0.1557, simple_loss=0.2524, pruned_loss=0.02951, over 7111.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2736, pruned_loss=0.04046, over 1400946.44 frames.], batch size: 17, lr: 4.77e-04
+2022-04-29 10:02:15,687 INFO [train.py:763] (0/8) Epoch 15, batch 4550, loss[loss=0.2086, simple_loss=0.2995, pruned_loss=0.0589, over 4928.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2771, pruned_loss=0.04263, over 1350870.49 frames.], batch size: 52, lr: 4.77e-04
+2022-04-29 10:03:04,859 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-15.pt
+2022-04-29 10:03:53,501 INFO [train.py:763] (0/8) Epoch 16, batch 0, loss[loss=0.2044, simple_loss=0.2905, pruned_loss=0.0592, over 7104.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2905, pruned_loss=0.0592, over 7104.00 frames.], batch size: 21, lr: 4.63e-04
+2022-04-29 10:04:59,097 INFO [train.py:763] (0/8) Epoch 16, batch 50, loss[loss=0.1698, simple_loss=0.278, pruned_loss=0.03082, over 7314.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2803, pruned_loss=0.04465, over 317404.23 frames.], batch size: 21, lr: 4.63e-04
+2022-04-29 10:06:04,346 INFO [train.py:763] (0/8) Epoch 16, batch 100, loss[loss=0.1678, simple_loss=0.2647, pruned_loss=0.03542, over 7143.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2779, pruned_loss=0.04191, over 559345.24 frames.], batch size: 20, lr: 4.63e-04
+2022-04-29 10:07:09,686 INFO [train.py:763] (0/8) Epoch 16, batch 150, loss[loss=0.1414, simple_loss=0.2237, pruned_loss=0.02958, over 7430.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2757, pruned_loss=0.04166, over 747332.08 frames.], batch size: 17, lr: 4.63e-04
+2022-04-29 10:08:15,106 INFO [train.py:763] (0/8) Epoch 16, batch 200, loss[loss=0.1515, simple_loss=0.2461, pruned_loss=0.02851, over 7144.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2772, pruned_loss=0.04197, over 896400.85 frames.], batch size: 17, lr: 4.63e-04
+2022-04-29 10:09:20,563 INFO [train.py:763] (0/8) Epoch 16, batch 250, loss[loss=0.1839, simple_loss=0.2875, pruned_loss=0.0402, over 7268.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2769, pruned_loss=0.04075, over 1015422.63 frames.], batch size: 19, lr: 4.63e-04
+2022-04-29 10:10:25,851 INFO [train.py:763] (0/8) Epoch 16, batch 300, loss[loss=0.1637, simple_loss=0.2606, pruned_loss=0.03335, over 7077.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2776, pruned_loss=0.04146, over 1101092.16 frames.], batch size: 18, lr: 4.62e-04
+2022-04-29 10:11:32,024 INFO [train.py:763] (0/8) Epoch 16, batch 350, loss[loss=0.1484, simple_loss=0.2512, pruned_loss=0.02281, over 6890.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2761, pruned_loss=0.04116, over 1171416.98 frames.], batch size: 15, lr: 4.62e-04
+2022-04-29 10:12:38,029 INFO [train.py:763] (0/8) Epoch 16, batch 400, loss[loss=0.207, simple_loss=0.3003, pruned_loss=0.05688, over 4815.00 frames.], tot_loss[loss=0.178, simple_loss=0.2752, pruned_loss=0.04044, over 1227209.63 frames.], batch size: 52, lr: 4.62e-04
+2022-04-29 10:13:43,489 INFO [train.py:763] (0/8) Epoch 16, batch 450, loss[loss=0.1832, simple_loss=0.2812, pruned_loss=0.04255, over 7353.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2752, pruned_loss=0.04082, over 1267837.37 frames.], batch size: 19, lr: 4.62e-04
+2022-04-29 10:14:49,059 INFO [train.py:763] (0/8) Epoch 16, batch 500, loss[loss=0.1478, simple_loss=0.2453, pruned_loss=0.02518, over 7160.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2739, pruned_loss=0.04033, over 1301434.59 frames.], batch size: 18, lr: 4.62e-04
+2022-04-29 10:15:54,724 INFO [train.py:763] (0/8) Epoch 16, batch 550, loss[loss=0.1604, simple_loss=0.2535, pruned_loss=0.03366, over 7135.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2735, pruned_loss=0.04017, over 1327551.88 frames.], batch size: 17, lr: 4.62e-04
+2022-04-29 10:17:00,208 INFO [train.py:763] (0/8) Epoch 16, batch 600, loss[loss=0.1958, simple_loss=0.2829, pruned_loss=0.05438, over 7034.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2744, pruned_loss=0.04088, over 1342651.33 frames.], batch size: 28, lr: 4.62e-04
+2022-04-29 10:18:05,536 INFO [train.py:763] (0/8) Epoch 16, batch 650, loss[loss=0.1779, simple_loss=0.2775, pruned_loss=0.03914, over 7326.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2747, pruned_loss=0.04097, over 1360631.64 frames.], batch size: 20, lr: 4.61e-04
+2022-04-29 10:19:10,738 INFO [train.py:763] (0/8) Epoch 16, batch 700, loss[loss=0.1565, simple_loss=0.2517, pruned_loss=0.03071, over 7261.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2756, pruned_loss=0.04143, over 1367424.30 frames.], batch size: 19, lr: 4.61e-04
+2022-04-29 10:20:16,744 INFO [train.py:763] (0/8) Epoch 16, batch 750, loss[loss=0.1859, simple_loss=0.2921, pruned_loss=0.03987, over 7154.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2762, pruned_loss=0.04162, over 1376459.33 frames.], batch size: 20, lr: 4.61e-04
+2022-04-29 10:21:21,862 INFO [train.py:763] (0/8) Epoch 16, batch 800, loss[loss=0.1563, simple_loss=0.2502, pruned_loss=0.03124, over 7160.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2758, pruned_loss=0.04152, over 1387026.29 frames.], batch size: 19, lr: 4.61e-04
+2022-04-29 10:22:27,312 INFO [train.py:763] (0/8) Epoch 16, batch 850, loss[loss=0.1962, simple_loss=0.2915, pruned_loss=0.05048, over 6374.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2748, pruned_loss=0.04125, over 1395053.25 frames.], batch size: 38, lr: 4.61e-04
+2022-04-29 10:23:32,969 INFO [train.py:763] (0/8) Epoch 16, batch 900, loss[loss=0.1785, simple_loss=0.2848, pruned_loss=0.03605, over 7334.00 frames.], tot_loss[loss=0.1781, simple_loss=0.275, pruned_loss=0.04061, over 1406773.02 frames.], batch size: 20, lr: 4.61e-04
+2022-04-29 10:24:38,455 INFO [train.py:763] (0/8) Epoch 16, batch 950, loss[loss=0.1648, simple_loss=0.2601, pruned_loss=0.03477, over 7158.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2755, pruned_loss=0.04091, over 1411286.54 frames.], batch size: 17, lr: 4.60e-04
+2022-04-29 10:25:44,703 INFO [train.py:763] (0/8) Epoch 16, batch 1000, loss[loss=0.1874, simple_loss=0.2753, pruned_loss=0.04978, over 7112.00 frames.], tot_loss[loss=0.1779, simple_loss=0.275, pruned_loss=0.04042, over 1415187.38 frames.], batch size: 21, lr: 4.60e-04
+2022-04-29 10:26:51,223 INFO [train.py:763] (0/8) Epoch 16, batch 1050, loss[loss=0.1927, simple_loss=0.2876, pruned_loss=0.04892, over 7333.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2743, pruned_loss=0.04012, over 1419799.90 frames.], batch size: 22, lr: 4.60e-04
+2022-04-29 10:27:57,457 INFO [train.py:763] (0/8) Epoch 16, batch 1100, loss[loss=0.1781, simple_loss=0.2743, pruned_loss=0.04094, over 7285.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2737, pruned_loss=0.03987, over 1420746.23 frames.], batch size: 24, lr: 4.60e-04
+2022-04-29 10:29:02,476 INFO [train.py:763] (0/8) Epoch 16, batch 1150, loss[loss=0.1779, simple_loss=0.2823, pruned_loss=0.03674, over 7277.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2742, pruned_loss=0.0396, over 1422077.25 frames.], batch size: 24, lr: 4.60e-04
+2022-04-29 10:30:08,052 INFO [train.py:763] (0/8) Epoch 16, batch 1200, loss[loss=0.2531, simple_loss=0.3539, pruned_loss=0.07616, over 7295.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2753, pruned_loss=0.04021, over 1419753.25 frames.], batch size: 25, lr: 4.60e-04
+2022-04-29 10:31:13,270 INFO [train.py:763] (0/8) Epoch 16, batch 1250, loss[loss=0.1557, simple_loss=0.2555, pruned_loss=0.02792, over 7276.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2748, pruned_loss=0.04015, over 1415069.90 frames.], batch size: 18, lr: 4.60e-04
+2022-04-29 10:32:19,090 INFO [train.py:763] (0/8) Epoch 16, batch 1300, loss[loss=0.2062, simple_loss=0.3139, pruned_loss=0.04929, over 7341.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2749, pruned_loss=0.04015, over 1412684.01 frames.], batch size: 22, lr: 4.59e-04
+2022-04-29 10:33:25,813 INFO [train.py:763] (0/8) Epoch 16, batch 1350, loss[loss=0.1556, simple_loss=0.2454, pruned_loss=0.03285, over 7002.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2747, pruned_loss=0.03996, over 1418665.53 frames.], batch size: 16, lr: 4.59e-04
+2022-04-29 10:34:32,892 INFO [train.py:763] (0/8) Epoch 16, batch 1400, loss[loss=0.2149, simple_loss=0.3183, pruned_loss=0.05573, over 7140.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2733, pruned_loss=0.03996, over 1420192.42 frames.], batch size: 20, lr: 4.59e-04
+2022-04-29 10:35:38,356 INFO [train.py:763] (0/8) Epoch 16, batch 1450, loss[loss=0.2027, simple_loss=0.3038, pruned_loss=0.05085, over 7345.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2747, pruned_loss=0.04023, over 1418530.11 frames.], batch size: 22, lr: 4.59e-04
+2022-04-29 10:36:44,001 INFO [train.py:763] (0/8) Epoch 16, batch 1500, loss[loss=0.1951, simple_loss=0.2768, pruned_loss=0.05668, over 7264.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2738, pruned_loss=0.04036, over 1424649.06 frames.], batch size: 19, lr: 4.59e-04
+2022-04-29 10:37:49,282 INFO [train.py:763] (0/8) Epoch 16, batch 1550, loss[loss=0.1735, simple_loss=0.2801, pruned_loss=0.03348, over 7226.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2738, pruned_loss=0.04034, over 1422024.48 frames.], batch size: 21, lr: 4.59e-04
+2022-04-29 10:38:55,278 INFO [train.py:763] (0/8) Epoch 16, batch 1600, loss[loss=0.1817, simple_loss=0.2795, pruned_loss=0.04195, over 7425.00 frames.], tot_loss[loss=0.1775, simple_loss=0.274, pruned_loss=0.04047, over 1427050.57 frames.], batch size: 20, lr: 4.58e-04
+2022-04-29 10:40:00,458 INFO [train.py:763] (0/8) Epoch 16, batch 1650, loss[loss=0.1631, simple_loss=0.2669, pruned_loss=0.02964, over 7414.00 frames.], tot_loss[loss=0.1771, simple_loss=0.274, pruned_loss=0.04007, over 1428897.92 frames.], batch size: 21, lr: 4.58e-04
+2022-04-29 10:41:05,544 INFO [train.py:763] (0/8) Epoch 16, batch 1700, loss[loss=0.2232, simple_loss=0.3021, pruned_loss=0.07217, over 5071.00 frames.], tot_loss[loss=0.178, simple_loss=0.2747, pruned_loss=0.04072, over 1421985.63 frames.], batch size: 52, lr: 4.58e-04
+2022-04-29 10:42:10,604 INFO [train.py:763] (0/8) Epoch 16, batch 1750, loss[loss=0.2076, simple_loss=0.3048, pruned_loss=0.05519, over 7377.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2762, pruned_loss=0.04162, over 1413309.57 frames.], batch size: 23, lr: 4.58e-04
+2022-04-29 10:43:15,528 INFO [train.py:763] (0/8) Epoch 16, batch 1800, loss[loss=0.1815, simple_loss=0.2809, pruned_loss=0.04104, over 7195.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2761, pruned_loss=0.0409, over 1413627.99 frames.], batch size: 23, lr: 4.58e-04
+2022-04-29 10:44:20,688 INFO [train.py:763] (0/8) Epoch 16, batch 1850, loss[loss=0.1699, simple_loss=0.2592, pruned_loss=0.04025, over 6302.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2761, pruned_loss=0.04103, over 1414210.43 frames.], batch size: 37, lr: 4.58e-04
+2022-04-29 10:45:26,191 INFO [train.py:763] (0/8) Epoch 16, batch 1900, loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02887, over 7425.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2764, pruned_loss=0.04127, over 1419355.18 frames.], batch size: 20, lr: 4.58e-04
+2022-04-29 10:46:31,352 INFO [train.py:763] (0/8) Epoch 16, batch 1950, loss[loss=0.1703, simple_loss=0.2843, pruned_loss=0.02813, over 7320.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2761, pruned_loss=0.04127, over 1422283.16 frames.], batch size: 21, lr: 4.57e-04
+2022-04-29 10:47:36,632 INFO [train.py:763] (0/8) Epoch 16, batch 2000, loss[loss=0.1969, simple_loss=0.283, pruned_loss=0.05543, over 7256.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2764, pruned_loss=0.0412, over 1424546.24 frames.], batch size: 19, lr: 4.57e-04
+2022-04-29 10:48:44,161 INFO [train.py:763] (0/8) Epoch 16, batch 2050, loss[loss=0.1687, simple_loss=0.2627, pruned_loss=0.03735, over 7412.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2749, pruned_loss=0.0407, over 1428101.69 frames.], batch size: 18, lr: 4.57e-04
+2022-04-29 10:49:51,123 INFO [train.py:763] (0/8) Epoch 16, batch 2100, loss[loss=0.1831, simple_loss=0.2753, pruned_loss=0.0455, over 7416.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2749, pruned_loss=0.04085, over 1428530.92 frames.], batch size: 21, lr: 4.57e-04
+2022-04-29 10:50:57,998 INFO [train.py:763] (0/8) Epoch 16, batch 2150, loss[loss=0.1627, simple_loss=0.2542, pruned_loss=0.0356, over 7362.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2753, pruned_loss=0.04075, over 1423807.76 frames.], batch size: 19, lr: 4.57e-04
+2022-04-29 10:52:04,707 INFO [train.py:763] (0/8) Epoch 16, batch 2200, loss[loss=0.1638, simple_loss=0.2737, pruned_loss=0.02692, over 7339.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2756, pruned_loss=0.04053, over 1421058.58 frames.], batch size: 22, lr: 4.57e-04
+2022-04-29 10:53:10,679 INFO [train.py:763] (0/8) Epoch 16, batch 2250, loss[loss=0.1649, simple_loss=0.2713, pruned_loss=0.02928, over 7421.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2761, pruned_loss=0.04076, over 1423393.32 frames.], batch size: 21, lr: 4.56e-04
+2022-04-29 10:54:16,238 INFO [train.py:763] (0/8) Epoch 16, batch 2300, loss[loss=0.1909, simple_loss=0.2983, pruned_loss=0.04178, over 7292.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2751, pruned_loss=0.04012, over 1422534.96 frames.], batch size: 24, lr: 4.56e-04
+2022-04-29 10:55:22,592 INFO [train.py:763] (0/8) Epoch 16, batch 2350, loss[loss=0.1896, simple_loss=0.2919, pruned_loss=0.04366, over 7389.00 frames.], tot_loss[loss=0.177, simple_loss=0.2743, pruned_loss=0.03981, over 1426435.37 frames.], batch size: 23, lr: 4.56e-04
+2022-04-29 10:56:28,590 INFO [train.py:763] (0/8) Epoch 16, batch 2400, loss[loss=0.1417, simple_loss=0.2298, pruned_loss=0.02683, over 7010.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2735, pruned_loss=0.0391, over 1424133.03 frames.], batch size: 16, lr: 4.56e-04
+2022-04-29 10:57:34,912 INFO [train.py:763] (0/8) Epoch 16, batch 2450, loss[loss=0.1775, simple_loss=0.2838, pruned_loss=0.03564, over 7329.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2738, pruned_loss=0.03993, over 1422971.21 frames.], batch size: 22, lr: 4.56e-04
+2022-04-29 10:58:41,497 INFO [train.py:763] (0/8) Epoch 16, batch 2500, loss[loss=0.235, simple_loss=0.323, pruned_loss=0.07349, over 7222.00 frames.], tot_loss[loss=0.1765, simple_loss=0.273, pruned_loss=0.03999, over 1422759.13 frames.], batch size: 21, lr: 4.56e-04
+2022-04-29 10:59:48,430 INFO [train.py:763] (0/8) Epoch 16, batch 2550, loss[loss=0.1694, simple_loss=0.267, pruned_loss=0.03587, over 7222.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2732, pruned_loss=0.04056, over 1418058.21 frames.], batch size: 21, lr: 4.56e-04
+2022-04-29 11:00:54,067 INFO [train.py:763] (0/8) Epoch 16, batch 2600, loss[loss=0.2045, simple_loss=0.3034, pruned_loss=0.05279, over 7037.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2742, pruned_loss=0.04067, over 1421248.54 frames.], batch size: 28, lr: 4.55e-04
+2022-04-29 11:01:59,333 INFO [train.py:763] (0/8) Epoch 16, batch 2650, loss[loss=0.1643, simple_loss=0.2571, pruned_loss=0.03576, over 7357.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2748, pruned_loss=0.0409, over 1420160.77 frames.], batch size: 19, lr: 4.55e-04
+2022-04-29 11:03:04,686 INFO [train.py:763] (0/8) Epoch 16, batch 2700, loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03261, over 7337.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2737, pruned_loss=0.04048, over 1423854.20 frames.], batch size: 22, lr: 4.55e-04
+2022-04-29 11:04:10,098 INFO [train.py:763] (0/8) Epoch 16, batch 2750, loss[loss=0.1456, simple_loss=0.2478, pruned_loss=0.0217, over 7155.00 frames.], tot_loss[loss=0.177, simple_loss=0.2734, pruned_loss=0.04031, over 1423042.07 frames.], batch size: 19, lr: 4.55e-04
+2022-04-29 11:05:15,593 INFO [train.py:763] (0/8) Epoch 16, batch 2800, loss[loss=0.2143, simple_loss=0.2903, pruned_loss=0.06922, over 5030.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2729, pruned_loss=0.04017, over 1422067.31 frames.], batch size: 52, lr: 4.55e-04
+2022-04-29 11:06:20,614 INFO [train.py:763] (0/8) Epoch 16, batch 2850, loss[loss=0.1755, simple_loss=0.2736, pruned_loss=0.0387, over 7319.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2729, pruned_loss=0.04001, over 1421777.98 frames.], batch size: 21, lr: 4.55e-04
+2022-04-29 11:07:35,859 INFO [train.py:763] (0/8) Epoch 16, batch 2900, loss[loss=0.1876, simple_loss=0.2825, pruned_loss=0.04634, over 7227.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2735, pruned_loss=0.04042, over 1418062.23 frames.], batch size: 20, lr: 4.55e-04
+2022-04-29 11:08:42,374 INFO [train.py:763] (0/8) Epoch 16, batch 2950, loss[loss=0.1681, simple_loss=0.2643, pruned_loss=0.03596, over 7274.00 frames.], tot_loss[loss=0.178, simple_loss=0.2747, pruned_loss=0.0407, over 1418450.43 frames.], batch size: 18, lr: 4.54e-04
+2022-04-29 11:09:49,130 INFO [train.py:763] (0/8) Epoch 16, batch 3000, loss[loss=0.1852, simple_loss=0.2896, pruned_loss=0.04044, over 7144.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2747, pruned_loss=0.04084, over 1423206.20 frames.], batch size: 20, lr: 4.54e-04
+2022-04-29 11:09:49,131 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 11:10:05,042 INFO [train.py:792] (0/8) Epoch 16, validation: loss=0.1677, simple_loss=0.2693, pruned_loss=0.03309, over 698248.00 frames.
+2022-04-29 11:11:10,313 INFO [train.py:763] (0/8) Epoch 16, batch 3050, loss[loss=0.1828, simple_loss=0.2872, pruned_loss=0.03925, over 6568.00 frames.], tot_loss[loss=0.178, simple_loss=0.2745, pruned_loss=0.04078, over 1422712.14 frames.], batch size: 38, lr: 4.54e-04
+2022-04-29 11:12:42,604 INFO [train.py:763] (0/8) Epoch 16, batch 3100, loss[loss=0.2043, simple_loss=0.305, pruned_loss=0.05183, over 7262.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2756, pruned_loss=0.04128, over 1419624.27 frames.], batch size: 25, lr: 4.54e-04
+2022-04-29 11:13:48,024 INFO [train.py:763] (0/8) Epoch 16, batch 3150, loss[loss=0.1769, simple_loss=0.2799, pruned_loss=0.03692, over 7326.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2748, pruned_loss=0.04086, over 1419234.33 frames.], batch size: 20, lr: 4.54e-04
+2022-04-29 11:15:03,465 INFO [train.py:763] (0/8) Epoch 16, batch 3200, loss[loss=0.175, simple_loss=0.2718, pruned_loss=0.03912, over 7360.00 frames.], tot_loss[loss=0.178, simple_loss=0.2746, pruned_loss=0.04071, over 1419709.46 frames.], batch size: 19, lr: 4.54e-04
+2022-04-29 11:16:27,100 INFO [train.py:763] (0/8) Epoch 16, batch 3250, loss[loss=0.181, simple_loss=0.2806, pruned_loss=0.04064, over 7061.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2736, pruned_loss=0.04003, over 1424826.41 frames.], batch size: 18, lr: 4.54e-04
+2022-04-29 11:17:32,425 INFO [train.py:763] (0/8) Epoch 16, batch 3300, loss[loss=0.1927, simple_loss=0.2964, pruned_loss=0.0445, over 7166.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2745, pruned_loss=0.04041, over 1425526.11 frames.], batch size: 19, lr: 4.53e-04
+2022-04-29 11:18:47,357 INFO [train.py:763] (0/8) Epoch 16, batch 3350, loss[loss=0.1674, simple_loss=0.2679, pruned_loss=0.03346, over 7336.00 frames.], tot_loss[loss=0.178, simple_loss=0.2752, pruned_loss=0.04045, over 1426489.77 frames.], batch size: 22, lr: 4.53e-04
+2022-04-29 11:19:54,006 INFO [train.py:763] (0/8) Epoch 16, batch 3400, loss[loss=0.1501, simple_loss=0.2565, pruned_loss=0.02183, over 7155.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2747, pruned_loss=0.04017, over 1422621.89 frames.], batch size: 20, lr: 4.53e-04
+2022-04-29 11:21:00,500 INFO [train.py:763] (0/8) Epoch 16, batch 3450, loss[loss=0.18, simple_loss=0.2743, pruned_loss=0.04286, over 7327.00 frames.], tot_loss[loss=0.177, simple_loss=0.2735, pruned_loss=0.04024, over 1424009.06 frames.], batch size: 20, lr: 4.53e-04
+2022-04-29 11:22:05,840 INFO [train.py:763] (0/8) Epoch 16, batch 3500, loss[loss=0.2013, simple_loss=0.3068, pruned_loss=0.04795, over 7212.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2738, pruned_loss=0.04045, over 1423619.97 frames.], batch size: 22, lr: 4.53e-04
+2022-04-29 11:23:11,002 INFO [train.py:763] (0/8) Epoch 16, batch 3550, loss[loss=0.1903, simple_loss=0.2909, pruned_loss=0.04485, over 7127.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2744, pruned_loss=0.04045, over 1425981.08 frames.], batch size: 21, lr: 4.53e-04
+2022-04-29 11:24:16,269 INFO [train.py:763] (0/8) Epoch 16, batch 3600, loss[loss=0.1485, simple_loss=0.2414, pruned_loss=0.02785, over 7291.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2738, pruned_loss=0.03978, over 1427374.17 frames.], batch size: 18, lr: 4.52e-04
+2022-04-29 11:25:21,856 INFO [train.py:763] (0/8) Epoch 16, batch 3650, loss[loss=0.1828, simple_loss=0.2812, pruned_loss=0.04225, over 7325.00 frames.], tot_loss[loss=0.176, simple_loss=0.2732, pruned_loss=0.03936, over 1430658.99 frames.], batch size: 21, lr: 4.52e-04
+2022-04-29 11:26:27,139 INFO [train.py:763] (0/8) Epoch 16, batch 3700, loss[loss=0.1827, simple_loss=0.2823, pruned_loss=0.04155, over 7141.00 frames.], tot_loss[loss=0.1769, simple_loss=0.274, pruned_loss=0.03985, over 1430378.44 frames.], batch size: 20, lr: 4.52e-04
+2022-04-29 11:27:34,290 INFO [train.py:763] (0/8) Epoch 16, batch 3750, loss[loss=0.1701, simple_loss=0.2705, pruned_loss=0.03487, over 6293.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2738, pruned_loss=0.03979, over 1427689.21 frames.], batch size: 37, lr: 4.52e-04
+2022-04-29 11:28:40,556 INFO [train.py:763] (0/8) Epoch 16, batch 3800, loss[loss=0.1724, simple_loss=0.2643, pruned_loss=0.04025, over 6435.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2736, pruned_loss=0.03938, over 1426097.62 frames.], batch size: 38, lr: 4.52e-04
+2022-04-29 11:29:46,874 INFO [train.py:763] (0/8) Epoch 16, batch 3850, loss[loss=0.1637, simple_loss=0.2572, pruned_loss=0.0351, over 7014.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2735, pruned_loss=0.03909, over 1426034.25 frames.], batch size: 16, lr: 4.52e-04
+2022-04-29 11:30:53,565 INFO [train.py:763] (0/8) Epoch 16, batch 3900, loss[loss=0.2061, simple_loss=0.3023, pruned_loss=0.05492, over 7213.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2727, pruned_loss=0.03899, over 1428471.53 frames.], batch size: 22, lr: 4.52e-04
+2022-04-29 11:32:00,371 INFO [train.py:763] (0/8) Epoch 16, batch 3950, loss[loss=0.1851, simple_loss=0.2789, pruned_loss=0.04562, over 7193.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2734, pruned_loss=0.03924, over 1428768.37 frames.], batch size: 23, lr: 4.51e-04
+2022-04-29 11:33:05,773 INFO [train.py:763] (0/8) Epoch 16, batch 4000, loss[loss=0.1393, simple_loss=0.2356, pruned_loss=0.02151, over 7286.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2732, pruned_loss=0.0395, over 1428728.57 frames.], batch size: 18, lr: 4.51e-04
+2022-04-29 11:34:12,306 INFO [train.py:763] (0/8) Epoch 16, batch 4050, loss[loss=0.1923, simple_loss=0.3002, pruned_loss=0.0422, over 6881.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2734, pruned_loss=0.03964, over 1426263.88 frames.], batch size: 31, lr: 4.51e-04
+2022-04-29 11:35:18,255 INFO [train.py:763] (0/8) Epoch 16, batch 4100, loss[loss=0.1774, simple_loss=0.2712, pruned_loss=0.04183, over 6347.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2741, pruned_loss=0.03983, over 1425596.37 frames.], batch size: 37, lr: 4.51e-04
+2022-04-29 11:36:24,682 INFO [train.py:763] (0/8) Epoch 16, batch 4150, loss[loss=0.142, simple_loss=0.2308, pruned_loss=0.02661, over 7151.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2732, pruned_loss=0.03997, over 1424043.71 frames.], batch size: 17, lr: 4.51e-04
+2022-04-29 11:37:30,209 INFO [train.py:763] (0/8) Epoch 16, batch 4200, loss[loss=0.181, simple_loss=0.2811, pruned_loss=0.0404, over 7132.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2735, pruned_loss=0.04, over 1422486.20 frames.], batch size: 26, lr: 4.51e-04
+2022-04-29 11:38:36,630 INFO [train.py:763] (0/8) Epoch 16, batch 4250, loss[loss=0.1569, simple_loss=0.2594, pruned_loss=0.02723, over 7267.00 frames.], tot_loss[loss=0.1777, simple_loss=0.275, pruned_loss=0.04019, over 1423449.56 frames.], batch size: 18, lr: 4.51e-04
+2022-04-29 11:39:43,740 INFO [train.py:763] (0/8) Epoch 16, batch 4300, loss[loss=0.1785, simple_loss=0.281, pruned_loss=0.03801, over 7073.00 frames.], tot_loss[loss=0.1772, simple_loss=0.274, pruned_loss=0.04022, over 1422023.58 frames.], batch size: 18, lr: 4.50e-04
+2022-04-29 11:40:49,815 INFO [train.py:763] (0/8) Epoch 16, batch 4350, loss[loss=0.1524, simple_loss=0.238, pruned_loss=0.03338, over 7165.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2729, pruned_loss=0.03967, over 1420477.27 frames.], batch size: 18, lr: 4.50e-04
+2022-04-29 11:41:55,147 INFO [train.py:763] (0/8) Epoch 16, batch 4400, loss[loss=0.2074, simple_loss=0.3047, pruned_loss=0.05507, over 7221.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2732, pruned_loss=0.04003, over 1419558.16 frames.], batch size: 21, lr: 4.50e-04
+2022-04-29 11:43:00,293 INFO [train.py:763] (0/8) Epoch 16, batch 4450, loss[loss=0.1521, simple_loss=0.2532, pruned_loss=0.02552, over 7141.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2744, pruned_loss=0.04048, over 1415508.24 frames.], batch size: 17, lr: 4.50e-04
+2022-04-29 11:44:06,068 INFO [train.py:763] (0/8) Epoch 16, batch 4500, loss[loss=0.1849, simple_loss=0.2874, pruned_loss=0.04116, over 7243.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2732, pruned_loss=0.04012, over 1413971.36 frames.], batch size: 20, lr: 4.50e-04
+2022-04-29 11:45:13,693 INFO [train.py:763] (0/8) Epoch 16, batch 4550, loss[loss=0.1957, simple_loss=0.2877, pruned_loss=0.05188, over 4737.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2737, pruned_loss=0.04161, over 1380251.69 frames.], batch size: 52, lr: 4.50e-04
+2022-04-29 11:46:04,034 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-16.pt
+2022-04-29 11:46:42,229 INFO [train.py:763] (0/8) Epoch 17, batch 0, loss[loss=0.1842, simple_loss=0.2855, pruned_loss=0.04145, over 7231.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2855, pruned_loss=0.04145, over 7231.00 frames.], batch size: 20, lr: 4.38e-04
+2022-04-29 11:47:48,729 INFO [train.py:763] (0/8) Epoch 17, batch 50, loss[loss=0.1643, simple_loss=0.2513, pruned_loss=0.03863, over 6990.00 frames.], tot_loss[loss=0.175, simple_loss=0.2708, pruned_loss=0.03963, over 324444.89 frames.], batch size: 16, lr: 4.38e-04
+2022-04-29 11:48:54,581 INFO [train.py:763] (0/8) Epoch 17, batch 100, loss[loss=0.1617, simple_loss=0.2579, pruned_loss=0.03271, over 7161.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2715, pruned_loss=0.03852, over 565528.47 frames.], batch size: 18, lr: 4.37e-04
+2022-04-29 11:50:00,289 INFO [train.py:763] (0/8) Epoch 17, batch 150, loss[loss=0.1917, simple_loss=0.2972, pruned_loss=0.04313, over 7144.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2727, pruned_loss=0.03952, over 752956.63 frames.], batch size: 20, lr: 4.37e-04
+2022-04-29 11:51:07,239 INFO [train.py:763] (0/8) Epoch 17, batch 200, loss[loss=0.1575, simple_loss=0.2565, pruned_loss=0.02925, over 7155.00 frames.], tot_loss[loss=0.1769, simple_loss=0.274, pruned_loss=0.03987, over 903768.40 frames.], batch size: 18, lr: 4.37e-04
+2022-04-29 11:52:14,166 INFO [train.py:763] (0/8) Epoch 17, batch 250, loss[loss=0.1938, simple_loss=0.2884, pruned_loss=0.04957, over 6720.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2743, pruned_loss=0.0395, over 1021183.24 frames.], batch size: 31, lr: 4.37e-04
+2022-04-29 11:53:19,842 INFO [train.py:763] (0/8) Epoch 17, batch 300, loss[loss=0.1796, simple_loss=0.2732, pruned_loss=0.04306, over 7077.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2737, pruned_loss=0.03929, over 1104906.11 frames.], batch size: 28, lr: 4.37e-04
+2022-04-29 11:54:25,561 INFO [train.py:763] (0/8) Epoch 17, batch 350, loss[loss=0.1657, simple_loss=0.2731, pruned_loss=0.02911, over 7342.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2724, pruned_loss=0.03945, over 1173092.82 frames.], batch size: 22, lr: 4.37e-04
+2022-04-29 11:55:31,580 INFO [train.py:763] (0/8) Epoch 17, batch 400, loss[loss=0.1634, simple_loss=0.252, pruned_loss=0.03744, over 6829.00 frames.], tot_loss[loss=0.1766, simple_loss=0.274, pruned_loss=0.03961, over 1232909.04 frames.], batch size: 15, lr: 4.37e-04
+2022-04-29 11:56:37,257 INFO [train.py:763] (0/8) Epoch 17, batch 450, loss[loss=0.1675, simple_loss=0.2562, pruned_loss=0.03939, over 7208.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2747, pruned_loss=0.03986, over 1276807.70 frames.], batch size: 22, lr: 4.36e-04
+2022-04-29 11:57:42,950 INFO [train.py:763] (0/8) Epoch 17, batch 500, loss[loss=0.1995, simple_loss=0.2932, pruned_loss=0.05295, over 7336.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2742, pruned_loss=0.03969, over 1313573.99 frames.], batch size: 22, lr: 4.36e-04
+2022-04-29 11:58:48,669 INFO [train.py:763] (0/8) Epoch 17, batch 550, loss[loss=0.1597, simple_loss=0.2549, pruned_loss=0.03226, over 7130.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2732, pruned_loss=0.03953, over 1339617.35 frames.], batch size: 17, lr: 4.36e-04
+2022-04-29 11:59:54,500 INFO [train.py:763] (0/8) Epoch 17, batch 600, loss[loss=0.1825, simple_loss=0.2804, pruned_loss=0.04232, over 6577.00 frames.], tot_loss[loss=0.177, simple_loss=0.2742, pruned_loss=0.03993, over 1357253.44 frames.], batch size: 38, lr: 4.36e-04
+2022-04-29 12:01:00,150 INFO [train.py:763] (0/8) Epoch 17, batch 650, loss[loss=0.211, simple_loss=0.3002, pruned_loss=0.06091, over 5191.00 frames.], tot_loss[loss=0.177, simple_loss=0.2743, pruned_loss=0.03991, over 1370000.19 frames.], batch size: 52, lr: 4.36e-04
+2022-04-29 12:02:07,663 INFO [train.py:763] (0/8) Epoch 17, batch 700, loss[loss=0.1945, simple_loss=0.2997, pruned_loss=0.04468, over 7315.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2746, pruned_loss=0.03982, over 1381630.76 frames.], batch size: 21, lr: 4.36e-04
+2022-04-29 12:03:15,590 INFO [train.py:763] (0/8) Epoch 17, batch 750, loss[loss=0.15, simple_loss=0.2457, pruned_loss=0.02715, over 7413.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2728, pruned_loss=0.03908, over 1391294.70 frames.], batch size: 18, lr: 4.36e-04
+2022-04-29 12:04:22,607 INFO [train.py:763] (0/8) Epoch 17, batch 800, loss[loss=0.1933, simple_loss=0.2911, pruned_loss=0.04774, over 7320.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2722, pruned_loss=0.0385, over 1402988.98 frames.], batch size: 21, lr: 4.36e-04
+2022-04-29 12:05:28,624 INFO [train.py:763] (0/8) Epoch 17, batch 850, loss[loss=0.1923, simple_loss=0.285, pruned_loss=0.04983, over 7411.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2724, pruned_loss=0.03868, over 1406559.97 frames.], batch size: 21, lr: 4.35e-04
+2022-04-29 12:06:34,129 INFO [train.py:763] (0/8) Epoch 17, batch 900, loss[loss=0.1919, simple_loss=0.2869, pruned_loss=0.04841, over 7211.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2744, pruned_loss=0.03937, over 1406539.56 frames.], batch size: 22, lr: 4.35e-04
+2022-04-29 12:07:40,042 INFO [train.py:763] (0/8) Epoch 17, batch 950, loss[loss=0.1681, simple_loss=0.2646, pruned_loss=0.03575, over 7250.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2741, pruned_loss=0.03901, over 1408608.58 frames.], batch size: 19, lr: 4.35e-04
+2022-04-29 12:08:46,278 INFO [train.py:763] (0/8) Epoch 17, batch 1000, loss[loss=0.1773, simple_loss=0.2804, pruned_loss=0.03709, over 7283.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2734, pruned_loss=0.0391, over 1413272.07 frames.], batch size: 24, lr: 4.35e-04
+2022-04-29 12:09:52,071 INFO [train.py:763] (0/8) Epoch 17, batch 1050, loss[loss=0.152, simple_loss=0.2389, pruned_loss=0.03256, over 7276.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2726, pruned_loss=0.03878, over 1416005.08 frames.], batch size: 17, lr: 4.35e-04
+2022-04-29 12:10:57,973 INFO [train.py:763] (0/8) Epoch 17, batch 1100, loss[loss=0.1798, simple_loss=0.2843, pruned_loss=0.03767, over 7297.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2733, pruned_loss=0.03924, over 1419414.32 frames.], batch size: 25, lr: 4.35e-04
+2022-04-29 12:12:04,950 INFO [train.py:763] (0/8) Epoch 17, batch 1150, loss[loss=0.2071, simple_loss=0.3076, pruned_loss=0.05334, over 7390.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2723, pruned_loss=0.03895, over 1417429.85 frames.], batch size: 23, lr: 4.35e-04
+2022-04-29 12:13:12,224 INFO [train.py:763] (0/8) Epoch 17, batch 1200, loss[loss=0.2197, simple_loss=0.2991, pruned_loss=0.07011, over 7284.00 frames.], tot_loss[loss=0.176, simple_loss=0.2727, pruned_loss=0.03967, over 1414845.18 frames.], batch size: 18, lr: 4.34e-04
+2022-04-29 12:14:19,348 INFO [train.py:763] (0/8) Epoch 17, batch 1250, loss[loss=0.1568, simple_loss=0.2664, pruned_loss=0.02357, over 7424.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2721, pruned_loss=0.03945, over 1416778.39 frames.], batch size: 21, lr: 4.34e-04
+2022-04-29 12:15:25,183 INFO [train.py:763] (0/8) Epoch 17, batch 1300, loss[loss=0.1683, simple_loss=0.2682, pruned_loss=0.03426, over 7182.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2721, pruned_loss=0.03954, over 1417694.86 frames.], batch size: 26, lr: 4.34e-04
+2022-04-29 12:16:30,500 INFO [train.py:763] (0/8) Epoch 17, batch 1350, loss[loss=0.1751, simple_loss=0.26, pruned_loss=0.04513, over 6996.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2731, pruned_loss=0.03998, over 1420539.80 frames.], batch size: 16, lr: 4.34e-04
+2022-04-29 12:17:36,051 INFO [train.py:763] (0/8) Epoch 17, batch 1400, loss[loss=0.1858, simple_loss=0.2902, pruned_loss=0.04069, over 7121.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2741, pruned_loss=0.04022, over 1422822.86 frames.], batch size: 21, lr: 4.34e-04
+2022-04-29 12:18:41,497 INFO [train.py:763] (0/8) Epoch 17, batch 1450, loss[loss=0.1765, simple_loss=0.277, pruned_loss=0.03799, over 7139.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2744, pruned_loss=0.03997, over 1421233.35 frames.], batch size: 20, lr: 4.34e-04
+2022-04-29 12:19:47,549 INFO [train.py:763] (0/8) Epoch 17, batch 1500, loss[loss=0.1752, simple_loss=0.2809, pruned_loss=0.03473, over 7320.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2744, pruned_loss=0.0401, over 1412780.82 frames.], batch size: 25, lr: 4.34e-04
+2022-04-29 12:20:53,500 INFO [train.py:763] (0/8) Epoch 17, batch 1550, loss[loss=0.1634, simple_loss=0.2636, pruned_loss=0.03153, over 7149.00 frames.], tot_loss[loss=0.176, simple_loss=0.2734, pruned_loss=0.03932, over 1420130.23 frames.], batch size: 19, lr: 4.33e-04
+2022-04-29 12:21:59,206 INFO [train.py:763] (0/8) Epoch 17, batch 1600, loss[loss=0.1654, simple_loss=0.2583, pruned_loss=0.03627, over 7427.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2733, pruned_loss=0.03931, over 1421483.08 frames.], batch size: 20, lr: 4.33e-04
+2022-04-29 12:23:04,507 INFO [train.py:763] (0/8) Epoch 17, batch 1650, loss[loss=0.1386, simple_loss=0.2372, pruned_loss=0.01999, over 7287.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2727, pruned_loss=0.03925, over 1421033.54 frames.], batch size: 17, lr: 4.33e-04
+2022-04-29 12:24:09,903 INFO [train.py:763] (0/8) Epoch 17, batch 1700, loss[loss=0.1525, simple_loss=0.2439, pruned_loss=0.03054, over 7364.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2729, pruned_loss=0.03923, over 1423774.14 frames.], batch size: 19, lr: 4.33e-04
+2022-04-29 12:25:15,258 INFO [train.py:763] (0/8) Epoch 17, batch 1750, loss[loss=0.1939, simple_loss=0.3003, pruned_loss=0.0437, over 7322.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2719, pruned_loss=0.03875, over 1424516.73 frames.], batch size: 21, lr: 4.33e-04
+2022-04-29 12:26:20,546 INFO [train.py:763] (0/8) Epoch 17, batch 1800, loss[loss=0.1639, simple_loss=0.2644, pruned_loss=0.0317, over 7233.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2713, pruned_loss=0.03854, over 1428548.37 frames.], batch size: 20, lr: 4.33e-04
+2022-04-29 12:27:26,288 INFO [train.py:763] (0/8) Epoch 17, batch 1850, loss[loss=0.2068, simple_loss=0.3014, pruned_loss=0.05611, over 5268.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2713, pruned_loss=0.03909, over 1426857.18 frames.], batch size: 52, lr: 4.33e-04
+2022-04-29 12:28:31,344 INFO [train.py:763] (0/8) Epoch 17, batch 1900, loss[loss=0.1562, simple_loss=0.2625, pruned_loss=0.02497, over 7324.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2732, pruned_loss=0.03922, over 1426914.97 frames.], batch size: 21, lr: 4.33e-04
+2022-04-29 12:29:36,739 INFO [train.py:763] (0/8) Epoch 17, batch 1950, loss[loss=0.1704, simple_loss=0.2723, pruned_loss=0.03426, over 7314.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2738, pruned_loss=0.0393, over 1424354.84 frames.], batch size: 21, lr: 4.32e-04
+2022-04-29 12:30:42,666 INFO [train.py:763] (0/8) Epoch 17, batch 2000, loss[loss=0.2258, simple_loss=0.2957, pruned_loss=0.07794, over 5031.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2728, pruned_loss=0.03904, over 1425024.19 frames.], batch size: 52, lr: 4.32e-04
+2022-04-29 12:30:46,732 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-80000.pt
+2022-04-29 12:31:59,165 INFO [train.py:763] (0/8) Epoch 17, batch 2050, loss[loss=0.1827, simple_loss=0.2806, pruned_loss=0.04243, over 7116.00 frames.], tot_loss[loss=0.1758, simple_loss=0.273, pruned_loss=0.0393, over 1420660.70 frames.], batch size: 21, lr: 4.32e-04
+2022-04-29 12:33:04,646 INFO [train.py:763] (0/8) Epoch 17, batch 2100, loss[loss=0.1895, simple_loss=0.3001, pruned_loss=0.03947, over 6808.00 frames.], tot_loss[loss=0.1756, simple_loss=0.273, pruned_loss=0.03911, over 1415591.64 frames.], batch size: 31, lr: 4.32e-04
+2022-04-29 12:34:11,530 INFO [train.py:763] (0/8) Epoch 17, batch 2150, loss[loss=0.1826, simple_loss=0.293, pruned_loss=0.03611, over 7222.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2732, pruned_loss=0.03902, over 1417493.39 frames.], batch size: 21, lr: 4.32e-04
+2022-04-29 12:35:18,273 INFO [train.py:763] (0/8) Epoch 17, batch 2200, loss[loss=0.173, simple_loss=0.2605, pruned_loss=0.04273, over 6799.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2726, pruned_loss=0.03845, over 1419818.62 frames.], batch size: 15, lr: 4.32e-04
+2022-04-29 12:36:23,983 INFO [train.py:763] (0/8) Epoch 17, batch 2250, loss[loss=0.1495, simple_loss=0.2392, pruned_loss=0.02995, over 6991.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2716, pruned_loss=0.03864, over 1423293.22 frames.], batch size: 16, lr: 4.32e-04
+2022-04-29 12:37:31,408 INFO [train.py:763] (0/8) Epoch 17, batch 2300, loss[loss=0.1846, simple_loss=0.2823, pruned_loss=0.04341, over 7149.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2732, pruned_loss=0.03912, over 1425606.81 frames.], batch size: 20, lr: 4.31e-04
+2022-04-29 12:38:38,627 INFO [train.py:763] (0/8) Epoch 17, batch 2350, loss[loss=0.2015, simple_loss=0.3043, pruned_loss=0.04932, over 7190.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2724, pruned_loss=0.03896, over 1424735.69 frames.], batch size: 26, lr: 4.31e-04
+2022-04-29 12:39:44,067 INFO [train.py:763] (0/8) Epoch 17, batch 2400, loss[loss=0.1987, simple_loss=0.2805, pruned_loss=0.05844, over 6240.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2723, pruned_loss=0.039, over 1422406.31 frames.], batch size: 37, lr: 4.31e-04
+2022-04-29 12:40:49,293 INFO [train.py:763] (0/8) Epoch 17, batch 2450, loss[loss=0.172, simple_loss=0.2626, pruned_loss=0.04074, over 7150.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2723, pruned_loss=0.03898, over 1424194.94 frames.], batch size: 19, lr: 4.31e-04
+2022-04-29 12:41:54,337 INFO [train.py:763] (0/8) Epoch 17, batch 2500, loss[loss=0.1749, simple_loss=0.2621, pruned_loss=0.04383, over 7130.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2733, pruned_loss=0.03979, over 1416752.52 frames.], batch size: 21, lr: 4.31e-04
+2022-04-29 12:42:59,728 INFO [train.py:763] (0/8) Epoch 17, batch 2550, loss[loss=0.1835, simple_loss=0.2928, pruned_loss=0.03711, over 7322.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2728, pruned_loss=0.0397, over 1417859.04 frames.], batch size: 21, lr: 4.31e-04
+2022-04-29 12:44:04,854 INFO [train.py:763] (0/8) Epoch 17, batch 2600, loss[loss=0.1469, simple_loss=0.2353, pruned_loss=0.02927, over 6749.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2735, pruned_loss=0.04004, over 1417513.49 frames.], batch size: 15, lr: 4.31e-04
+2022-04-29 12:45:10,704 INFO [train.py:763] (0/8) Epoch 17, batch 2650, loss[loss=0.1536, simple_loss=0.2417, pruned_loss=0.03279, over 7361.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2735, pruned_loss=0.04037, over 1418177.73 frames.], batch size: 19, lr: 4.31e-04
+2022-04-29 12:46:17,011 INFO [train.py:763] (0/8) Epoch 17, batch 2700, loss[loss=0.1496, simple_loss=0.2353, pruned_loss=0.03197, over 7279.00 frames.], tot_loss[loss=0.176, simple_loss=0.2724, pruned_loss=0.03983, over 1417915.32 frames.], batch size: 18, lr: 4.30e-04
+2022-04-29 12:47:22,121 INFO [train.py:763] (0/8) Epoch 17, batch 2750, loss[loss=0.1871, simple_loss=0.2888, pruned_loss=0.04274, over 7143.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2727, pruned_loss=0.03987, over 1416210.59 frames.], batch size: 20, lr: 4.30e-04
+2022-04-29 12:48:28,862 INFO [train.py:763] (0/8) Epoch 17, batch 2800, loss[loss=0.1801, simple_loss=0.2749, pruned_loss=0.04264, over 7321.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2725, pruned_loss=0.03959, over 1417012.50 frames.], batch size: 21, lr: 4.30e-04
+2022-04-29 12:49:34,428 INFO [train.py:763] (0/8) Epoch 17, batch 2850, loss[loss=0.201, simple_loss=0.2935, pruned_loss=0.05421, over 7288.00 frames.], tot_loss[loss=0.176, simple_loss=0.273, pruned_loss=0.0395, over 1419997.84 frames.], batch size: 25, lr: 4.30e-04
+2022-04-29 12:50:39,891 INFO [train.py:763] (0/8) Epoch 17, batch 2900, loss[loss=0.1982, simple_loss=0.3077, pruned_loss=0.04438, over 7196.00 frames.], tot_loss[loss=0.1759, simple_loss=0.273, pruned_loss=0.03938, over 1422216.42 frames.], batch size: 22, lr: 4.30e-04
+2022-04-29 12:51:46,406 INFO [train.py:763] (0/8) Epoch 17, batch 2950, loss[loss=0.1892, simple_loss=0.2879, pruned_loss=0.04529, over 6403.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2729, pruned_loss=0.03939, over 1419698.34 frames.], batch size: 37, lr: 4.30e-04
+2022-04-29 12:52:52,641 INFO [train.py:763] (0/8) Epoch 17, batch 3000, loss[loss=0.1979, simple_loss=0.3061, pruned_loss=0.04482, over 7293.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2726, pruned_loss=0.03931, over 1418783.33 frames.], batch size: 25, lr: 4.30e-04
+2022-04-29 12:52:52,642 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 12:53:07,982 INFO [train.py:792] (0/8) Epoch 17, validation: loss=0.167, simple_loss=0.268, pruned_loss=0.03296, over 698248.00 frames.
+2022-04-29 12:54:13,319 INFO [train.py:763] (0/8) Epoch 17, batch 3050, loss[loss=0.1887, simple_loss=0.2969, pruned_loss=0.04029, over 7120.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2731, pruned_loss=0.03967, over 1417915.48 frames.], batch size: 21, lr: 4.29e-04
+2022-04-29 12:55:18,435 INFO [train.py:763] (0/8) Epoch 17, batch 3100, loss[loss=0.1625, simple_loss=0.2604, pruned_loss=0.03225, over 7226.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2734, pruned_loss=0.03958, over 1419253.61 frames.], batch size: 20, lr: 4.29e-04
+2022-04-29 12:56:23,984 INFO [train.py:763] (0/8) Epoch 17, batch 3150, loss[loss=0.1687, simple_loss=0.2698, pruned_loss=0.03377, over 7262.00 frames.], tot_loss[loss=0.176, simple_loss=0.2731, pruned_loss=0.0394, over 1421877.58 frames.], batch size: 19, lr: 4.29e-04
+2022-04-29 12:57:29,298 INFO [train.py:763] (0/8) Epoch 17, batch 3200, loss[loss=0.1874, simple_loss=0.2921, pruned_loss=0.04138, over 6787.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2729, pruned_loss=0.03942, over 1419675.87 frames.], batch size: 31, lr: 4.29e-04
+2022-04-29 12:58:34,635 INFO [train.py:763] (0/8) Epoch 17, batch 3250, loss[loss=0.1871, simple_loss=0.2793, pruned_loss=0.0475, over 7369.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2717, pruned_loss=0.03883, over 1422885.49 frames.], batch size: 23, lr: 4.29e-04
+2022-04-29 12:59:42,249 INFO [train.py:763] (0/8) Epoch 17, batch 3300, loss[loss=0.1659, simple_loss=0.252, pruned_loss=0.03991, over 7157.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2713, pruned_loss=0.03875, over 1427352.64 frames.], batch size: 18, lr: 4.29e-04
+2022-04-29 13:00:47,857 INFO [train.py:763] (0/8) Epoch 17, batch 3350, loss[loss=0.1582, simple_loss=0.2516, pruned_loss=0.03243, over 7390.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2719, pruned_loss=0.03893, over 1427534.86 frames.], batch size: 18, lr: 4.29e-04
+2022-04-29 13:01:54,348 INFO [train.py:763] (0/8) Epoch 17, batch 3400, loss[loss=0.1753, simple_loss=0.27, pruned_loss=0.04028, over 7371.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2724, pruned_loss=0.03935, over 1430463.50 frames.], batch size: 23, lr: 4.29e-04
+2022-04-29 13:02:59,888 INFO [train.py:763] (0/8) Epoch 17, batch 3450, loss[loss=0.163, simple_loss=0.2633, pruned_loss=0.03138, over 7408.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2737, pruned_loss=0.03952, over 1430768.51 frames.], batch size: 18, lr: 4.28e-04
+2022-04-29 13:04:05,576 INFO [train.py:763] (0/8) Epoch 17, batch 3500, loss[loss=0.1835, simple_loss=0.2885, pruned_loss=0.03922, over 6371.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2736, pruned_loss=0.03945, over 1433117.52 frames.], batch size: 38, lr: 4.28e-04
+2022-04-29 13:05:11,607 INFO [train.py:763] (0/8) Epoch 17, batch 3550, loss[loss=0.1734, simple_loss=0.2755, pruned_loss=0.03568, over 7199.00 frames.], tot_loss[loss=0.177, simple_loss=0.2744, pruned_loss=0.03977, over 1431561.23 frames.], batch size: 23, lr: 4.28e-04
+2022-04-29 13:06:17,360 INFO [train.py:763] (0/8) Epoch 17, batch 3600, loss[loss=0.2293, simple_loss=0.3243, pruned_loss=0.06715, over 7222.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2742, pruned_loss=0.03972, over 1432624.33 frames.], batch size: 21, lr: 4.28e-04
+2022-04-29 13:07:22,981 INFO [train.py:763] (0/8) Epoch 17, batch 3650, loss[loss=0.1851, simple_loss=0.2919, pruned_loss=0.03917, over 7333.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2738, pruned_loss=0.03951, over 1424301.93 frames.], batch size: 22, lr: 4.28e-04
+2022-04-29 13:08:28,137 INFO [train.py:763] (0/8) Epoch 17, batch 3700, loss[loss=0.1637, simple_loss=0.2453, pruned_loss=0.04105, over 7000.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2741, pruned_loss=0.03989, over 1425357.93 frames.], batch size: 16, lr: 4.28e-04
+2022-04-29 13:09:33,329 INFO [train.py:763] (0/8) Epoch 17, batch 3750, loss[loss=0.1749, simple_loss=0.2833, pruned_loss=0.03324, over 7290.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2742, pruned_loss=0.03956, over 1427107.68 frames.], batch size: 25, lr: 4.28e-04
+2022-04-29 13:10:39,697 INFO [train.py:763] (0/8) Epoch 17, batch 3800, loss[loss=0.1807, simple_loss=0.2786, pruned_loss=0.04137, over 7359.00 frames.], tot_loss[loss=0.1766, simple_loss=0.274, pruned_loss=0.03958, over 1427437.99 frames.], batch size: 19, lr: 4.28e-04
+2022-04-29 13:11:45,025 INFO [train.py:763] (0/8) Epoch 17, batch 3850, loss[loss=0.1577, simple_loss=0.2586, pruned_loss=0.02842, over 7402.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2739, pruned_loss=0.03989, over 1426253.77 frames.], batch size: 18, lr: 4.27e-04
+2022-04-29 13:12:50,428 INFO [train.py:763] (0/8) Epoch 17, batch 3900, loss[loss=0.1557, simple_loss=0.2545, pruned_loss=0.02852, over 7114.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2735, pruned_loss=0.03985, over 1421402.46 frames.], batch size: 21, lr: 4.27e-04
+2022-04-29 13:13:55,784 INFO [train.py:763] (0/8) Epoch 17, batch 3950, loss[loss=0.2001, simple_loss=0.2954, pruned_loss=0.05236, over 7054.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2734, pruned_loss=0.04006, over 1422547.36 frames.], batch size: 28, lr: 4.27e-04
+2022-04-29 13:15:01,129 INFO [train.py:763] (0/8) Epoch 17, batch 4000, loss[loss=0.1949, simple_loss=0.278, pruned_loss=0.05589, over 6818.00 frames.], tot_loss[loss=0.1773, simple_loss=0.274, pruned_loss=0.04027, over 1423676.96 frames.], batch size: 15, lr: 4.27e-04
+2022-04-29 13:16:06,985 INFO [train.py:763] (0/8) Epoch 17, batch 4050, loss[loss=0.1779, simple_loss=0.2905, pruned_loss=0.03264, over 7055.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2737, pruned_loss=0.03976, over 1427176.87 frames.], batch size: 28, lr: 4.27e-04
+2022-04-29 13:17:12,361 INFO [train.py:763] (0/8) Epoch 17, batch 4100, loss[loss=0.187, simple_loss=0.285, pruned_loss=0.04454, over 7147.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2732, pruned_loss=0.03955, over 1424034.33 frames.], batch size: 20, lr: 4.27e-04
+2022-04-29 13:18:18,027 INFO [train.py:763] (0/8) Epoch 17, batch 4150, loss[loss=0.1856, simple_loss=0.281, pruned_loss=0.04515, over 7329.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2734, pruned_loss=0.0398, over 1423577.37 frames.], batch size: 20, lr: 4.27e-04
+2022-04-29 13:19:24,067 INFO [train.py:763] (0/8) Epoch 17, batch 4200, loss[loss=0.1543, simple_loss=0.2374, pruned_loss=0.03562, over 6993.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2725, pruned_loss=0.03901, over 1423095.72 frames.], batch size: 16, lr: 4.26e-04
+2022-04-29 13:20:29,207 INFO [train.py:763] (0/8) Epoch 17, batch 4250, loss[loss=0.1852, simple_loss=0.2864, pruned_loss=0.04203, over 6756.00 frames.], tot_loss[loss=0.176, simple_loss=0.2729, pruned_loss=0.03956, over 1417798.39 frames.], batch size: 31, lr: 4.26e-04
+2022-04-29 13:21:35,204 INFO [train.py:763] (0/8) Epoch 17, batch 4300, loss[loss=0.1377, simple_loss=0.2324, pruned_loss=0.0215, over 7008.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2716, pruned_loss=0.03914, over 1418663.08 frames.], batch size: 16, lr: 4.26e-04
+2022-04-29 13:22:49,727 INFO [train.py:763] (0/8) Epoch 17, batch 4350, loss[loss=0.1878, simple_loss=0.2871, pruned_loss=0.04421, over 7227.00 frames.], tot_loss[loss=0.1754, simple_loss=0.272, pruned_loss=0.03943, over 1405952.33 frames.], batch size: 21, lr: 4.26e-04
+2022-04-29 13:23:54,555 INFO [train.py:763] (0/8) Epoch 17, batch 4400, loss[loss=0.1694, simple_loss=0.2689, pruned_loss=0.03495, over 7072.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2731, pruned_loss=0.03959, over 1399834.42 frames.], batch size: 18, lr: 4.26e-04
+2022-04-29 13:24:59,621 INFO [train.py:763] (0/8) Epoch 17, batch 4450, loss[loss=0.1975, simple_loss=0.2909, pruned_loss=0.05204, over 6518.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2742, pruned_loss=0.04019, over 1391693.50 frames.], batch size: 38, lr: 4.26e-04
+2022-04-29 13:26:04,078 INFO [train.py:763] (0/8) Epoch 17, batch 4500, loss[loss=0.1549, simple_loss=0.2391, pruned_loss=0.03537, over 7021.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2754, pruned_loss=0.04051, over 1379031.62 frames.], batch size: 16, lr: 4.26e-04
+2022-04-29 13:27:09,438 INFO [train.py:763] (0/8) Epoch 17, batch 4550, loss[loss=0.1744, simple_loss=0.2752, pruned_loss=0.03684, over 7167.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2747, pruned_loss=0.04039, over 1368128.36 frames.], batch size: 19, lr: 4.26e-04
+2022-04-29 13:28:27,328 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-17.pt
+2022-04-29 13:29:06,470 INFO [train.py:763] (0/8) Epoch 18, batch 0, loss[loss=0.177, simple_loss=0.2835, pruned_loss=0.03524, over 7337.00 frames.], tot_loss[loss=0.177, simple_loss=0.2835, pruned_loss=0.03524, over 7337.00 frames.], batch size: 25, lr: 4.15e-04
+2022-04-29 13:30:22,091 INFO [train.py:763] (0/8) Epoch 18, batch 50, loss[loss=0.2164, simple_loss=0.3162, pruned_loss=0.05833, over 7333.00 frames.], tot_loss[loss=0.176, simple_loss=0.2744, pruned_loss=0.03877, over 325386.02 frames.], batch size: 22, lr: 4.15e-04
+2022-04-29 13:31:37,254 INFO [train.py:763] (0/8) Epoch 18, batch 100, loss[loss=0.17, simple_loss=0.2746, pruned_loss=0.03272, over 7333.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2706, pruned_loss=0.03636, over 574894.93 frames.], batch size: 22, lr: 4.14e-04
+2022-04-29 13:32:51,555 INFO [train.py:763] (0/8) Epoch 18, batch 150, loss[loss=0.2022, simple_loss=0.302, pruned_loss=0.05123, over 7220.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2702, pruned_loss=0.03734, over 764449.21 frames.], batch size: 21, lr: 4.14e-04
+2022-04-29 13:33:57,532 INFO [train.py:763] (0/8) Epoch 18, batch 200, loss[loss=0.1545, simple_loss=0.25, pruned_loss=0.02956, over 7283.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2711, pruned_loss=0.03859, over 909618.18 frames.], batch size: 17, lr: 4.14e-04
+2022-04-29 13:35:11,773 INFO [train.py:763] (0/8) Epoch 18, batch 250, loss[loss=0.156, simple_loss=0.2611, pruned_loss=0.02546, over 6716.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2706, pruned_loss=0.03819, over 1024550.79 frames.], batch size: 31, lr: 4.14e-04
+2022-04-29 13:36:17,275 INFO [train.py:763] (0/8) Epoch 18, batch 300, loss[loss=0.1499, simple_loss=0.2567, pruned_loss=0.02157, over 7233.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2712, pruned_loss=0.03809, over 1115350.43 frames.], batch size: 20, lr: 4.14e-04
+2022-04-29 13:37:24,211 INFO [train.py:763] (0/8) Epoch 18, batch 350, loss[loss=0.1973, simple_loss=0.2892, pruned_loss=0.05269, over 6695.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2706, pruned_loss=0.03784, over 1181460.98 frames.], batch size: 31, lr: 4.14e-04
+2022-04-29 13:38:31,278 INFO [train.py:763] (0/8) Epoch 18, batch 400, loss[loss=0.1633, simple_loss=0.2668, pruned_loss=0.02993, over 7067.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2713, pruned_loss=0.03803, over 1232339.95 frames.], batch size: 18, lr: 4.14e-04
+2022-04-29 13:39:38,722 INFO [train.py:763] (0/8) Epoch 18, batch 450, loss[loss=0.1716, simple_loss=0.2806, pruned_loss=0.03126, over 7342.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2716, pruned_loss=0.03812, over 1274207.23 frames.], batch size: 22, lr: 4.14e-04
+2022-04-29 13:40:45,471 INFO [train.py:763] (0/8) Epoch 18, batch 500, loss[loss=0.137, simple_loss=0.2316, pruned_loss=0.02123, over 7147.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2722, pruned_loss=0.03837, over 1305202.53 frames.], batch size: 17, lr: 4.13e-04
+2022-04-29 13:41:52,283 INFO [train.py:763] (0/8) Epoch 18, batch 550, loss[loss=0.1824, simple_loss=0.2705, pruned_loss=0.04708, over 7288.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2715, pruned_loss=0.03819, over 1335817.32 frames.], batch size: 17, lr: 4.13e-04
+2022-04-29 13:42:57,771 INFO [train.py:763] (0/8) Epoch 18, batch 600, loss[loss=0.1678, simple_loss=0.2632, pruned_loss=0.03619, over 7267.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2711, pruned_loss=0.03829, over 1356411.57 frames.], batch size: 18, lr: 4.13e-04
+2022-04-29 13:44:04,381 INFO [train.py:763] (0/8) Epoch 18, batch 650, loss[loss=0.1937, simple_loss=0.302, pruned_loss=0.04269, over 7434.00 frames.], tot_loss[loss=0.173, simple_loss=0.2705, pruned_loss=0.03773, over 1375598.06 frames.], batch size: 22, lr: 4.13e-04
+2022-04-29 13:45:09,476 INFO [train.py:763] (0/8) Epoch 18, batch 700, loss[loss=0.2117, simple_loss=0.3098, pruned_loss=0.05686, over 5111.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2712, pruned_loss=0.038, over 1385835.50 frames.], batch size: 53, lr: 4.13e-04
+2022-04-29 13:46:15,219 INFO [train.py:763] (0/8) Epoch 18, batch 750, loss[loss=0.1816, simple_loss=0.2708, pruned_loss=0.04616, over 7163.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2712, pruned_loss=0.03828, over 1394331.34 frames.], batch size: 19, lr: 4.13e-04
+2022-04-29 13:47:20,152 INFO [train.py:763] (0/8) Epoch 18, batch 800, loss[loss=0.1735, simple_loss=0.2805, pruned_loss=0.03325, over 6739.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2719, pruned_loss=0.03846, over 1397139.86 frames.], batch size: 31, lr: 4.13e-04
+2022-04-29 13:48:26,406 INFO [train.py:763] (0/8) Epoch 18, batch 850, loss[loss=0.1666, simple_loss=0.2552, pruned_loss=0.03898, over 7060.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2721, pruned_loss=0.0384, over 1404658.41 frames.], batch size: 18, lr: 4.13e-04
+2022-04-29 13:49:33,110 INFO [train.py:763] (0/8) Epoch 18, batch 900, loss[loss=0.1608, simple_loss=0.2516, pruned_loss=0.03499, over 6828.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2727, pruned_loss=0.03814, over 1410225.77 frames.], batch size: 15, lr: 4.12e-04
+2022-04-29 13:50:38,408 INFO [train.py:763] (0/8) Epoch 18, batch 950, loss[loss=0.1684, simple_loss=0.2734, pruned_loss=0.03167, over 7385.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2725, pruned_loss=0.03805, over 1413659.48 frames.], batch size: 23, lr: 4.12e-04
+2022-04-29 13:51:45,517 INFO [train.py:763] (0/8) Epoch 18, batch 1000, loss[loss=0.1647, simple_loss=0.2663, pruned_loss=0.03154, over 7142.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2726, pruned_loss=0.03814, over 1420049.81 frames.], batch size: 20, lr: 4.12e-04
+2022-04-29 13:52:52,994 INFO [train.py:763] (0/8) Epoch 18, batch 1050, loss[loss=0.1906, simple_loss=0.2933, pruned_loss=0.04395, over 7302.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2722, pruned_loss=0.03833, over 1417353.64 frames.], batch size: 25, lr: 4.12e-04
+2022-04-29 13:53:58,534 INFO [train.py:763] (0/8) Epoch 18, batch 1100, loss[loss=0.181, simple_loss=0.2828, pruned_loss=0.03959, over 7326.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2714, pruned_loss=0.03793, over 1418122.20 frames.], batch size: 20, lr: 4.12e-04
+2022-04-29 13:55:03,941 INFO [train.py:763] (0/8) Epoch 18, batch 1150, loss[loss=0.1782, simple_loss=0.2778, pruned_loss=0.03935, over 7278.00 frames.], tot_loss[loss=0.174, simple_loss=0.2717, pruned_loss=0.03812, over 1419005.67 frames.], batch size: 24, lr: 4.12e-04
+2022-04-29 13:56:09,838 INFO [train.py:763] (0/8) Epoch 18, batch 1200, loss[loss=0.2034, simple_loss=0.2949, pruned_loss=0.05599, over 4968.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2719, pruned_loss=0.03844, over 1414075.47 frames.], batch size: 53, lr: 4.12e-04
+2022-04-29 13:57:15,054 INFO [train.py:763] (0/8) Epoch 18, batch 1250, loss[loss=0.1862, simple_loss=0.2921, pruned_loss=0.0402, over 7112.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2716, pruned_loss=0.03827, over 1414620.97 frames.], batch size: 21, lr: 4.12e-04
+2022-04-29 13:58:20,087 INFO [train.py:763] (0/8) Epoch 18, batch 1300, loss[loss=0.1676, simple_loss=0.2637, pruned_loss=0.03579, over 7161.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2725, pruned_loss=0.03857, over 1413101.67 frames.], batch size: 19, lr: 4.12e-04
+2022-04-29 13:59:25,441 INFO [train.py:763] (0/8) Epoch 18, batch 1350, loss[loss=0.1991, simple_loss=0.2887, pruned_loss=0.05473, over 7010.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2735, pruned_loss=0.03903, over 1411587.28 frames.], batch size: 28, lr: 4.11e-04
+2022-04-29 14:00:32,451 INFO [train.py:763] (0/8) Epoch 18, batch 1400, loss[loss=0.1981, simple_loss=0.2785, pruned_loss=0.05885, over 7064.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2725, pruned_loss=0.03907, over 1409858.17 frames.], batch size: 18, lr: 4.11e-04
+2022-04-29 14:01:39,699 INFO [train.py:763] (0/8) Epoch 18, batch 1450, loss[loss=0.1714, simple_loss=0.2723, pruned_loss=0.03524, over 7333.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2713, pruned_loss=0.03812, over 1417154.65 frames.], batch size: 21, lr: 4.11e-04
+2022-04-29 14:02:45,986 INFO [train.py:763] (0/8) Epoch 18, batch 1500, loss[loss=0.1819, simple_loss=0.2748, pruned_loss=0.04448, over 7268.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2725, pruned_loss=0.03862, over 1420653.02 frames.], batch size: 19, lr: 4.11e-04
+2022-04-29 14:03:53,123 INFO [train.py:763] (0/8) Epoch 18, batch 1550, loss[loss=0.1882, simple_loss=0.2852, pruned_loss=0.04564, over 7416.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2714, pruned_loss=0.03784, over 1424152.76 frames.], batch size: 21, lr: 4.11e-04
+2022-04-29 14:04:58,311 INFO [train.py:763] (0/8) Epoch 18, batch 1600, loss[loss=0.1787, simple_loss=0.2788, pruned_loss=0.03926, over 7216.00 frames.], tot_loss[loss=0.1731, simple_loss=0.271, pruned_loss=0.03762, over 1423376.28 frames.], batch size: 22, lr: 4.11e-04
+2022-04-29 14:06:03,952 INFO [train.py:763] (0/8) Epoch 18, batch 1650, loss[loss=0.1513, simple_loss=0.2472, pruned_loss=0.02767, over 7168.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2716, pruned_loss=0.03813, over 1422647.45 frames.], batch size: 18, lr: 4.11e-04
+2022-04-29 14:07:10,558 INFO [train.py:763] (0/8) Epoch 18, batch 1700, loss[loss=0.1635, simple_loss=0.256, pruned_loss=0.03552, over 7156.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2715, pruned_loss=0.03783, over 1423703.15 frames.], batch size: 18, lr: 4.11e-04
+2022-04-29 14:08:17,587 INFO [train.py:763] (0/8) Epoch 18, batch 1750, loss[loss=0.1821, simple_loss=0.2789, pruned_loss=0.04263, over 7142.00 frames.], tot_loss[loss=0.1752, simple_loss=0.273, pruned_loss=0.03873, over 1416592.89 frames.], batch size: 20, lr: 4.10e-04
+2022-04-29 14:09:24,698 INFO [train.py:763] (0/8) Epoch 18, batch 1800, loss[loss=0.1814, simple_loss=0.2822, pruned_loss=0.04027, over 7253.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2742, pruned_loss=0.03916, over 1417162.38 frames.], batch size: 19, lr: 4.10e-04
+2022-04-29 14:10:32,230 INFO [train.py:763] (0/8) Epoch 18, batch 1850, loss[loss=0.2005, simple_loss=0.3023, pruned_loss=0.04933, over 7325.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2739, pruned_loss=0.03864, over 1422953.34 frames.], batch size: 24, lr: 4.10e-04
+2022-04-29 14:11:39,565 INFO [train.py:763] (0/8) Epoch 18, batch 1900, loss[loss=0.1619, simple_loss=0.2669, pruned_loss=0.02845, over 7065.00 frames.], tot_loss[loss=0.176, simple_loss=0.274, pruned_loss=0.03899, over 1419820.43 frames.], batch size: 28, lr: 4.10e-04
+2022-04-29 14:12:46,676 INFO [train.py:763] (0/8) Epoch 18, batch 1950, loss[loss=0.1551, simple_loss=0.242, pruned_loss=0.03413, over 6995.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2741, pruned_loss=0.0388, over 1421047.43 frames.], batch size: 16, lr: 4.10e-04
+2022-04-29 14:13:51,993 INFO [train.py:763] (0/8) Epoch 18, batch 2000, loss[loss=0.1965, simple_loss=0.3068, pruned_loss=0.04309, over 7141.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2732, pruned_loss=0.03829, over 1424087.14 frames.], batch size: 20, lr: 4.10e-04
+2022-04-29 14:14:57,427 INFO [train.py:763] (0/8) Epoch 18, batch 2050, loss[loss=0.1917, simple_loss=0.2936, pruned_loss=0.04492, over 7315.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2722, pruned_loss=0.03818, over 1423608.88 frames.], batch size: 25, lr: 4.10e-04
+2022-04-29 14:16:02,573 INFO [train.py:763] (0/8) Epoch 18, batch 2100, loss[loss=0.1649, simple_loss=0.266, pruned_loss=0.03196, over 7150.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2715, pruned_loss=0.03772, over 1424720.24 frames.], batch size: 19, lr: 4.10e-04
+2022-04-29 14:17:08,138 INFO [train.py:763] (0/8) Epoch 18, batch 2150, loss[loss=0.1649, simple_loss=0.2662, pruned_loss=0.03175, over 7211.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2711, pruned_loss=0.03788, over 1421121.19 frames.], batch size: 21, lr: 4.09e-04
+2022-04-29 14:18:13,402 INFO [train.py:763] (0/8) Epoch 18, batch 2200, loss[loss=0.1782, simple_loss=0.2846, pruned_loss=0.03585, over 7105.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2708, pruned_loss=0.03751, over 1425052.34 frames.], batch size: 21, lr: 4.09e-04
+2022-04-29 14:19:18,573 INFO [train.py:763] (0/8) Epoch 18, batch 2250, loss[loss=0.1746, simple_loss=0.2806, pruned_loss=0.03431, over 6650.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2704, pruned_loss=0.03729, over 1424655.77 frames.], batch size: 38, lr: 4.09e-04
+2022-04-29 14:20:23,891 INFO [train.py:763] (0/8) Epoch 18, batch 2300, loss[loss=0.1859, simple_loss=0.276, pruned_loss=0.04792, over 7389.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2702, pruned_loss=0.0375, over 1425894.71 frames.], batch size: 23, lr: 4.09e-04
+2022-04-29 14:21:28,911 INFO [train.py:763] (0/8) Epoch 18, batch 2350, loss[loss=0.163, simple_loss=0.2508, pruned_loss=0.03758, over 7271.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2706, pruned_loss=0.03758, over 1422827.30 frames.], batch size: 17, lr: 4.09e-04
+2022-04-29 14:22:34,040 INFO [train.py:763] (0/8) Epoch 18, batch 2400, loss[loss=0.1698, simple_loss=0.2614, pruned_loss=0.03909, over 7140.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2707, pruned_loss=0.03798, over 1418929.98 frames.], batch size: 20, lr: 4.09e-04
+2022-04-29 14:23:41,081 INFO [train.py:763] (0/8) Epoch 18, batch 2450, loss[loss=0.2015, simple_loss=0.3015, pruned_loss=0.05081, over 7151.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2705, pruned_loss=0.038, over 1422572.70 frames.], batch size: 20, lr: 4.09e-04
+2022-04-29 14:24:46,859 INFO [train.py:763] (0/8) Epoch 18, batch 2500, loss[loss=0.1859, simple_loss=0.2979, pruned_loss=0.03693, over 7192.00 frames.], tot_loss[loss=0.1728, simple_loss=0.27, pruned_loss=0.03776, over 1421991.06 frames.], batch size: 26, lr: 4.09e-04
+2022-04-29 14:25:51,855 INFO [train.py:763] (0/8) Epoch 18, batch 2550, loss[loss=0.2335, simple_loss=0.328, pruned_loss=0.06952, over 7279.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2704, pruned_loss=0.03833, over 1422096.96 frames.], batch size: 24, lr: 4.08e-04
+2022-04-29 14:26:57,015 INFO [train.py:763] (0/8) Epoch 18, batch 2600, loss[loss=0.1424, simple_loss=0.231, pruned_loss=0.02684, over 6991.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2717, pruned_loss=0.03866, over 1425746.31 frames.], batch size: 16, lr: 4.08e-04
+2022-04-29 14:28:02,335 INFO [train.py:763] (0/8) Epoch 18, batch 2650, loss[loss=0.2045, simple_loss=0.3024, pruned_loss=0.05326, over 7283.00 frames.], tot_loss[loss=0.1747, simple_loss=0.272, pruned_loss=0.03866, over 1427266.20 frames.], batch size: 24, lr: 4.08e-04
+2022-04-29 14:29:08,100 INFO [train.py:763] (0/8) Epoch 18, batch 2700, loss[loss=0.1924, simple_loss=0.2892, pruned_loss=0.04777, over 7321.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2708, pruned_loss=0.03767, over 1431018.79 frames.], batch size: 25, lr: 4.08e-04
+2022-04-29 14:30:14,946 INFO [train.py:763] (0/8) Epoch 18, batch 2750, loss[loss=0.1704, simple_loss=0.2649, pruned_loss=0.03799, over 7412.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2711, pruned_loss=0.03771, over 1430084.86 frames.], batch size: 21, lr: 4.08e-04
+2022-04-29 14:31:21,341 INFO [train.py:763] (0/8) Epoch 18, batch 2800, loss[loss=0.1515, simple_loss=0.2452, pruned_loss=0.0289, over 7072.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2715, pruned_loss=0.03794, over 1430550.71 frames.], batch size: 18, lr: 4.08e-04
+2022-04-29 14:32:26,510 INFO [train.py:763] (0/8) Epoch 18, batch 2850, loss[loss=0.1709, simple_loss=0.2688, pruned_loss=0.03652, over 7157.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2719, pruned_loss=0.03819, over 1427448.42 frames.], batch size: 19, lr: 4.08e-04
+2022-04-29 14:33:31,784 INFO [train.py:763] (0/8) Epoch 18, batch 2900, loss[loss=0.1923, simple_loss=0.2837, pruned_loss=0.05045, over 7117.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2719, pruned_loss=0.03832, over 1424925.21 frames.], batch size: 26, lr: 4.08e-04
+2022-04-29 14:34:37,296 INFO [train.py:763] (0/8) Epoch 18, batch 2950, loss[loss=0.1533, simple_loss=0.2502, pruned_loss=0.02824, over 7274.00 frames.], tot_loss[loss=0.174, simple_loss=0.272, pruned_loss=0.03802, over 1430429.27 frames.], batch size: 17, lr: 4.08e-04
+2022-04-29 14:35:43,267 INFO [train.py:763] (0/8) Epoch 18, batch 3000, loss[loss=0.2132, simple_loss=0.3021, pruned_loss=0.0622, over 5090.00 frames.], tot_loss[loss=0.174, simple_loss=0.2716, pruned_loss=0.03817, over 1430184.30 frames.], batch size: 53, lr: 4.07e-04
+2022-04-29 14:35:43,268 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 14:35:58,559 INFO [train.py:792] (0/8) Epoch 18, validation: loss=0.1668, simple_loss=0.2671, pruned_loss=0.03324, over 698248.00 frames.
+2022-04-29 14:37:05,452 INFO [train.py:763] (0/8) Epoch 18, batch 3050, loss[loss=0.1838, simple_loss=0.2864, pruned_loss=0.04065, over 7176.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2723, pruned_loss=0.03833, over 1430557.81 frames.], batch size: 23, lr: 4.07e-04
+2022-04-29 14:38:12,649 INFO [train.py:763] (0/8) Epoch 18, batch 3100, loss[loss=0.1888, simple_loss=0.2928, pruned_loss=0.04244, over 6456.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2723, pruned_loss=0.03847, over 1432149.73 frames.], batch size: 38, lr: 4.07e-04
+2022-04-29 14:39:19,395 INFO [train.py:763] (0/8) Epoch 18, batch 3150, loss[loss=0.1818, simple_loss=0.2684, pruned_loss=0.04756, over 7274.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2725, pruned_loss=0.03826, over 1429105.61 frames.], batch size: 18, lr: 4.07e-04
+2022-04-29 14:40:26,381 INFO [train.py:763] (0/8) Epoch 18, batch 3200, loss[loss=0.1593, simple_loss=0.2565, pruned_loss=0.03104, over 7162.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2723, pruned_loss=0.0383, over 1427808.16 frames.], batch size: 19, lr: 4.07e-04
+2022-04-29 14:41:32,523 INFO [train.py:763] (0/8) Epoch 18, batch 3250, loss[loss=0.1479, simple_loss=0.2447, pruned_loss=0.02556, over 7355.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2735, pruned_loss=0.03881, over 1425465.38 frames.], batch size: 19, lr: 4.07e-04
+2022-04-29 14:42:37,745 INFO [train.py:763] (0/8) Epoch 18, batch 3300, loss[loss=0.1752, simple_loss=0.2737, pruned_loss=0.0383, over 6468.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2738, pruned_loss=0.03895, over 1425502.48 frames.], batch size: 38, lr: 4.07e-04
+2022-04-29 14:43:43,240 INFO [train.py:763] (0/8) Epoch 18, batch 3350, loss[loss=0.1751, simple_loss=0.2773, pruned_loss=0.03643, over 7121.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2726, pruned_loss=0.03821, over 1424294.04 frames.], batch size: 21, lr: 4.07e-04
+2022-04-29 14:44:48,486 INFO [train.py:763] (0/8) Epoch 18, batch 3400, loss[loss=0.1771, simple_loss=0.262, pruned_loss=0.04614, over 7282.00 frames.], tot_loss[loss=0.174, simple_loss=0.2723, pruned_loss=0.03786, over 1425099.39 frames.], batch size: 18, lr: 4.06e-04
+2022-04-29 14:45:53,985 INFO [train.py:763] (0/8) Epoch 18, batch 3450, loss[loss=0.173, simple_loss=0.2619, pruned_loss=0.04207, over 7356.00 frames.], tot_loss[loss=0.1733, simple_loss=0.271, pruned_loss=0.03774, over 1421444.02 frames.], batch size: 19, lr: 4.06e-04
+2022-04-29 14:46:59,200 INFO [train.py:763] (0/8) Epoch 18, batch 3500, loss[loss=0.1827, simple_loss=0.2689, pruned_loss=0.04824, over 7269.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2709, pruned_loss=0.03794, over 1423843.96 frames.], batch size: 18, lr: 4.06e-04
+2022-04-29 14:48:04,604 INFO [train.py:763] (0/8) Epoch 18, batch 3550, loss[loss=0.1573, simple_loss=0.2459, pruned_loss=0.03433, over 7158.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2712, pruned_loss=0.03814, over 1422972.93 frames.], batch size: 17, lr: 4.06e-04
+2022-04-29 14:49:09,820 INFO [train.py:763] (0/8) Epoch 18, batch 3600, loss[loss=0.2083, simple_loss=0.3054, pruned_loss=0.05563, over 7203.00 frames.], tot_loss[loss=0.1747, simple_loss=0.272, pruned_loss=0.03866, over 1421141.30 frames.], batch size: 23, lr: 4.06e-04
+2022-04-29 14:50:14,983 INFO [train.py:763] (0/8) Epoch 18, batch 3650, loss[loss=0.1931, simple_loss=0.2889, pruned_loss=0.04867, over 7327.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2717, pruned_loss=0.03846, over 1414834.48 frames.], batch size: 20, lr: 4.06e-04
+2022-04-29 14:51:20,204 INFO [train.py:763] (0/8) Epoch 18, batch 3700, loss[loss=0.1755, simple_loss=0.2857, pruned_loss=0.03267, over 7412.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2726, pruned_loss=0.03885, over 1417614.34 frames.], batch size: 21, lr: 4.06e-04
+2022-04-29 14:52:25,587 INFO [train.py:763] (0/8) Epoch 18, batch 3750, loss[loss=0.1753, simple_loss=0.279, pruned_loss=0.03576, over 7393.00 frames.], tot_loss[loss=0.1758, simple_loss=0.273, pruned_loss=0.03934, over 1414111.46 frames.], batch size: 23, lr: 4.06e-04
+2022-04-29 14:53:30,898 INFO [train.py:763] (0/8) Epoch 18, batch 3800, loss[loss=0.1778, simple_loss=0.2738, pruned_loss=0.04091, over 7356.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2731, pruned_loss=0.03896, over 1419435.24 frames.], batch size: 19, lr: 4.06e-04
+2022-04-29 14:54:36,411 INFO [train.py:763] (0/8) Epoch 18, batch 3850, loss[loss=0.1421, simple_loss=0.2312, pruned_loss=0.02647, over 7168.00 frames.], tot_loss[loss=0.1758, simple_loss=0.273, pruned_loss=0.03931, over 1416586.33 frames.], batch size: 18, lr: 4.05e-04
+2022-04-29 14:55:41,218 INFO [train.py:763] (0/8) Epoch 18, batch 3900, loss[loss=0.1572, simple_loss=0.2608, pruned_loss=0.02683, over 7115.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2728, pruned_loss=0.039, over 1414526.88 frames.], batch size: 21, lr: 4.05e-04
+2022-04-29 14:56:46,304 INFO [train.py:763] (0/8) Epoch 18, batch 3950, loss[loss=0.1857, simple_loss=0.2836, pruned_loss=0.04388, over 7162.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2733, pruned_loss=0.03917, over 1416449.38 frames.], batch size: 18, lr: 4.05e-04
+2022-04-29 14:57:51,530 INFO [train.py:763] (0/8) Epoch 18, batch 4000, loss[loss=0.229, simple_loss=0.3041, pruned_loss=0.07693, over 5372.00 frames.], tot_loss[loss=0.1757, simple_loss=0.273, pruned_loss=0.03919, over 1418121.84 frames.], batch size: 52, lr: 4.05e-04
+2022-04-29 14:58:57,196 INFO [train.py:763] (0/8) Epoch 18, batch 4050, loss[loss=0.155, simple_loss=0.2392, pruned_loss=0.03543, over 7229.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2721, pruned_loss=0.03899, over 1415758.59 frames.], batch size: 16, lr: 4.05e-04
+2022-04-29 15:00:03,354 INFO [train.py:763] (0/8) Epoch 18, batch 4100, loss[loss=0.1964, simple_loss=0.2888, pruned_loss=0.05205, over 5299.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2721, pruned_loss=0.03878, over 1416893.66 frames.], batch size: 52, lr: 4.05e-04
+2022-04-29 15:01:09,085 INFO [train.py:763] (0/8) Epoch 18, batch 4150, loss[loss=0.1901, simple_loss=0.2923, pruned_loss=0.04391, over 7385.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2717, pruned_loss=0.03879, over 1422263.37 frames.], batch size: 23, lr: 4.05e-04
+2022-04-29 15:02:16,184 INFO [train.py:763] (0/8) Epoch 18, batch 4200, loss[loss=0.1534, simple_loss=0.2621, pruned_loss=0.02237, over 7195.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2719, pruned_loss=0.03851, over 1420822.55 frames.], batch size: 23, lr: 4.05e-04
+2022-04-29 15:03:23,613 INFO [train.py:763] (0/8) Epoch 18, batch 4250, loss[loss=0.1549, simple_loss=0.2454, pruned_loss=0.03218, over 6768.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2712, pruned_loss=0.03813, over 1419995.32 frames.], batch size: 15, lr: 4.04e-04
+2022-04-29 15:04:28,934 INFO [train.py:763] (0/8) Epoch 18, batch 4300, loss[loss=0.1855, simple_loss=0.2715, pruned_loss=0.04976, over 7128.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2719, pruned_loss=0.03865, over 1419688.94 frames.], batch size: 26, lr: 4.04e-04
+2022-04-29 15:05:35,083 INFO [train.py:763] (0/8) Epoch 18, batch 4350, loss[loss=0.1795, simple_loss=0.2776, pruned_loss=0.04069, over 7158.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2718, pruned_loss=0.03864, over 1417858.70 frames.], batch size: 18, lr: 4.04e-04
+2022-04-29 15:06:42,528 INFO [train.py:763] (0/8) Epoch 18, batch 4400, loss[loss=0.1898, simple_loss=0.2846, pruned_loss=0.04744, over 6346.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2716, pruned_loss=0.03888, over 1413733.04 frames.], batch size: 37, lr: 4.04e-04
+2022-04-29 15:07:48,914 INFO [train.py:763] (0/8) Epoch 18, batch 4450, loss[loss=0.1608, simple_loss=0.2446, pruned_loss=0.03853, over 6797.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2704, pruned_loss=0.03852, over 1408414.93 frames.], batch size: 15, lr: 4.04e-04
+2022-04-29 15:08:55,428 INFO [train.py:763] (0/8) Epoch 18, batch 4500, loss[loss=0.1748, simple_loss=0.273, pruned_loss=0.03827, over 7143.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2719, pruned_loss=0.03974, over 1394442.86 frames.], batch size: 20, lr: 4.04e-04
+2022-04-29 15:10:01,685 INFO [train.py:763] (0/8) Epoch 18, batch 4550, loss[loss=0.1713, simple_loss=0.2737, pruned_loss=0.03448, over 6242.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2714, pruned_loss=0.04014, over 1368316.49 frames.], batch size: 38, lr: 4.04e-04
+2022-04-29 15:10:52,042 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-18.pt
+2022-04-29 15:11:30,597 INFO [train.py:763] (0/8) Epoch 19, batch 0, loss[loss=0.1456, simple_loss=0.2436, pruned_loss=0.02381, over 7351.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2436, pruned_loss=0.02381, over 7351.00 frames.], batch size: 19, lr: 3.94e-04
+2022-04-29 15:12:36,747 INFO [train.py:763] (0/8) Epoch 19, batch 50, loss[loss=0.1502, simple_loss=0.2481, pruned_loss=0.02617, over 7276.00 frames.], tot_loss[loss=0.173, simple_loss=0.2727, pruned_loss=0.03664, over 320199.41 frames.], batch size: 18, lr: 3.94e-04
+2022-04-29 15:13:42,683 INFO [train.py:763] (0/8) Epoch 19, batch 100, loss[loss=0.2254, simple_loss=0.304, pruned_loss=0.07335, over 4870.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2713, pruned_loss=0.03711, over 566190.12 frames.], batch size: 52, lr: 3.94e-04
+2022-04-29 15:14:48,879 INFO [train.py:763] (0/8) Epoch 19, batch 150, loss[loss=0.1739, simple_loss=0.2756, pruned_loss=0.03603, over 7322.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2735, pruned_loss=0.03793, over 756620.16 frames.], batch size: 21, lr: 3.94e-04
+2022-04-29 15:15:54,345 INFO [train.py:763] (0/8) Epoch 19, batch 200, loss[loss=0.1834, simple_loss=0.2853, pruned_loss=0.04077, over 7348.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2738, pruned_loss=0.03818, over 903963.09 frames.], batch size: 22, lr: 3.93e-04
+2022-04-29 15:17:00,303 INFO [train.py:763] (0/8) Epoch 19, batch 250, loss[loss=0.1918, simple_loss=0.2948, pruned_loss=0.04442, over 7325.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2719, pruned_loss=0.03757, over 1023128.49 frames.], batch size: 22, lr: 3.93e-04
+2022-04-29 15:18:06,653 INFO [train.py:763] (0/8) Epoch 19, batch 300, loss[loss=0.1847, simple_loss=0.2826, pruned_loss=0.04342, over 7200.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2721, pruned_loss=0.0374, over 1113363.74 frames.], batch size: 23, lr: 3.93e-04
+2022-04-29 15:19:12,796 INFO [train.py:763] (0/8) Epoch 19, batch 350, loss[loss=0.1721, simple_loss=0.2788, pruned_loss=0.03268, over 7142.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2725, pruned_loss=0.0372, over 1186005.61 frames.], batch size: 20, lr: 3.93e-04
+2022-04-29 15:20:18,131 INFO [train.py:763] (0/8) Epoch 19, batch 400, loss[loss=0.1857, simple_loss=0.2854, pruned_loss=0.04302, over 7143.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2731, pruned_loss=0.03766, over 1237966.12 frames.], batch size: 20, lr: 3.93e-04
+2022-04-29 15:21:23,460 INFO [train.py:763] (0/8) Epoch 19, batch 450, loss[loss=0.1804, simple_loss=0.2837, pruned_loss=0.03852, over 7369.00 frames.], tot_loss[loss=0.174, simple_loss=0.2729, pruned_loss=0.03754, over 1275789.04 frames.], batch size: 23, lr: 3.93e-04
+2022-04-29 15:22:28,669 INFO [train.py:763] (0/8) Epoch 19, batch 500, loss[loss=0.1827, simple_loss=0.2896, pruned_loss=0.03793, over 7222.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2729, pruned_loss=0.03747, over 1306879.79 frames.], batch size: 21, lr: 3.93e-04
+2022-04-29 15:23:34,291 INFO [train.py:763] (0/8) Epoch 19, batch 550, loss[loss=0.1805, simple_loss=0.2851, pruned_loss=0.0379, over 6824.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2716, pruned_loss=0.0366, over 1333457.25 frames.], batch size: 31, lr: 3.93e-04
+2022-04-29 15:24:40,471 INFO [train.py:763] (0/8) Epoch 19, batch 600, loss[loss=0.159, simple_loss=0.2565, pruned_loss=0.03077, over 7160.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2699, pruned_loss=0.03637, over 1356087.40 frames.], batch size: 18, lr: 3.93e-04
+2022-04-29 15:25:45,946 INFO [train.py:763] (0/8) Epoch 19, batch 650, loss[loss=0.162, simple_loss=0.2617, pruned_loss=0.03114, over 7161.00 frames.], tot_loss[loss=0.172, simple_loss=0.2706, pruned_loss=0.03676, over 1370573.01 frames.], batch size: 18, lr: 3.92e-04
+2022-04-29 15:26:51,174 INFO [train.py:763] (0/8) Epoch 19, batch 700, loss[loss=0.1664, simple_loss=0.2734, pruned_loss=0.02965, over 7246.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2715, pruned_loss=0.0365, over 1384022.21 frames.], batch size: 20, lr: 3.92e-04
+2022-04-29 15:27:56,826 INFO [train.py:763] (0/8) Epoch 19, batch 750, loss[loss=0.1734, simple_loss=0.2653, pruned_loss=0.04076, over 7294.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2702, pruned_loss=0.03632, over 1394618.19 frames.], batch size: 25, lr: 3.92e-04
+2022-04-29 15:29:03,500 INFO [train.py:763] (0/8) Epoch 19, batch 800, loss[loss=0.1462, simple_loss=0.2357, pruned_loss=0.02833, over 7419.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2697, pruned_loss=0.03636, over 1403989.42 frames.], batch size: 18, lr: 3.92e-04
+2022-04-29 15:29:39,191 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-88000.pt
+2022-04-29 15:30:19,531 INFO [train.py:763] (0/8) Epoch 19, batch 850, loss[loss=0.1921, simple_loss=0.2891, pruned_loss=0.04756, over 7028.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2701, pruned_loss=0.03645, over 1411653.35 frames.], batch size: 28, lr: 3.92e-04
+2022-04-29 15:31:25,293 INFO [train.py:763] (0/8) Epoch 19, batch 900, loss[loss=0.1415, simple_loss=0.2319, pruned_loss=0.02555, over 7352.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2697, pruned_loss=0.03671, over 1417148.46 frames.], batch size: 19, lr: 3.92e-04
+2022-04-29 15:32:30,756 INFO [train.py:763] (0/8) Epoch 19, batch 950, loss[loss=0.1978, simple_loss=0.2855, pruned_loss=0.05503, over 7240.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2699, pruned_loss=0.03683, over 1420598.80 frames.], batch size: 20, lr: 3.92e-04
+2022-04-29 15:33:36,042 INFO [train.py:763] (0/8) Epoch 19, batch 1000, loss[loss=0.1783, simple_loss=0.2764, pruned_loss=0.04013, over 7285.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2705, pruned_loss=0.03718, over 1421124.01 frames.], batch size: 24, lr: 3.92e-04
+2022-04-29 15:34:41,373 INFO [train.py:763] (0/8) Epoch 19, batch 1050, loss[loss=0.1828, simple_loss=0.2747, pruned_loss=0.04539, over 7219.00 frames.], tot_loss[loss=0.172, simple_loss=0.2702, pruned_loss=0.03688, over 1420881.10 frames.], batch size: 22, lr: 3.92e-04
+2022-04-29 15:35:47,015 INFO [train.py:763] (0/8) Epoch 19, batch 1100, loss[loss=0.1828, simple_loss=0.2905, pruned_loss=0.0376, over 7211.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2707, pruned_loss=0.03743, over 1416362.90 frames.], batch size: 22, lr: 3.91e-04
+2022-04-29 15:36:52,335 INFO [train.py:763] (0/8) Epoch 19, batch 1150, loss[loss=0.2178, simple_loss=0.3051, pruned_loss=0.06523, over 7280.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2716, pruned_loss=0.03789, over 1420361.73 frames.], batch size: 24, lr: 3.91e-04
+2022-04-29 15:38:08,762 INFO [train.py:763] (0/8) Epoch 19, batch 1200, loss[loss=0.1898, simple_loss=0.2973, pruned_loss=0.04117, over 7329.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2708, pruned_loss=0.03773, over 1425440.04 frames.], batch size: 22, lr: 3.91e-04
+2022-04-29 15:39:14,199 INFO [train.py:763] (0/8) Epoch 19, batch 1250, loss[loss=0.1601, simple_loss=0.2512, pruned_loss=0.03451, over 7146.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2697, pruned_loss=0.03703, over 1426085.83 frames.], batch size: 17, lr: 3.91e-04
+2022-04-29 15:40:19,883 INFO [train.py:763] (0/8) Epoch 19, batch 1300, loss[loss=0.1616, simple_loss=0.2628, pruned_loss=0.03026, over 7124.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2696, pruned_loss=0.03706, over 1427682.27 frames.], batch size: 21, lr: 3.91e-04
+2022-04-29 15:41:25,083 INFO [train.py:763] (0/8) Epoch 19, batch 1350, loss[loss=0.17, simple_loss=0.2758, pruned_loss=0.03214, over 7202.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2706, pruned_loss=0.03748, over 1429902.31 frames.], batch size: 22, lr: 3.91e-04
+2022-04-29 15:42:30,866 INFO [train.py:763] (0/8) Epoch 19, batch 1400, loss[loss=0.1785, simple_loss=0.274, pruned_loss=0.04151, over 7195.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2703, pruned_loss=0.03762, over 1431274.45 frames.], batch size: 26, lr: 3.91e-04
+2022-04-29 15:43:46,288 INFO [train.py:763] (0/8) Epoch 19, batch 1450, loss[loss=0.1962, simple_loss=0.2855, pruned_loss=0.05345, over 7207.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2723, pruned_loss=0.03878, over 1429453.91 frames.], batch size: 26, lr: 3.91e-04
+2022-04-29 15:45:09,724 INFO [train.py:763] (0/8) Epoch 19, batch 1500, loss[loss=0.1765, simple_loss=0.2767, pruned_loss=0.03817, over 7401.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2723, pruned_loss=0.03855, over 1426301.17 frames.], batch size: 23, lr: 3.91e-04
+2022-04-29 15:46:15,430 INFO [train.py:763] (0/8) Epoch 19, batch 1550, loss[loss=0.1652, simple_loss=0.2597, pruned_loss=0.03539, over 7440.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2718, pruned_loss=0.03862, over 1428766.20 frames.], batch size: 20, lr: 3.91e-04
+2022-04-29 15:47:30,080 INFO [train.py:763] (0/8) Epoch 19, batch 1600, loss[loss=0.1802, simple_loss=0.295, pruned_loss=0.03274, over 7344.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2713, pruned_loss=0.03794, over 1423885.02 frames.], batch size: 22, lr: 3.90e-04
+2022-04-29 15:48:53,938 INFO [train.py:763] (0/8) Epoch 19, batch 1650, loss[loss=0.1922, simple_loss=0.2921, pruned_loss=0.0461, over 7209.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2715, pruned_loss=0.0379, over 1420777.84 frames.], batch size: 23, lr: 3.90e-04
+2022-04-29 15:50:08,831 INFO [train.py:763] (0/8) Epoch 19, batch 1700, loss[loss=0.1436, simple_loss=0.2406, pruned_loss=0.02331, over 7158.00 frames.], tot_loss[loss=0.173, simple_loss=0.2708, pruned_loss=0.03762, over 1420400.74 frames.], batch size: 19, lr: 3.90e-04
+2022-04-29 15:51:14,404 INFO [train.py:763] (0/8) Epoch 19, batch 1750, loss[loss=0.1677, simple_loss=0.2759, pruned_loss=0.02975, over 7321.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2711, pruned_loss=0.03794, over 1425694.92 frames.], batch size: 22, lr: 3.90e-04
+2022-04-29 15:52:20,003 INFO [train.py:763] (0/8) Epoch 19, batch 1800, loss[loss=0.2103, simple_loss=0.307, pruned_loss=0.0568, over 7280.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2713, pruned_loss=0.03776, over 1425589.80 frames.], batch size: 25, lr: 3.90e-04
+2022-04-29 15:53:25,561 INFO [train.py:763] (0/8) Epoch 19, batch 1850, loss[loss=0.1499, simple_loss=0.25, pruned_loss=0.02485, over 7065.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2713, pruned_loss=0.03779, over 1428672.87 frames.], batch size: 18, lr: 3.90e-04
+2022-04-29 15:54:30,918 INFO [train.py:763] (0/8) Epoch 19, batch 1900, loss[loss=0.1674, simple_loss=0.2713, pruned_loss=0.03172, over 7229.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2717, pruned_loss=0.03768, over 1429041.29 frames.], batch size: 20, lr: 3.90e-04
+2022-04-29 15:55:38,254 INFO [train.py:763] (0/8) Epoch 19, batch 1950, loss[loss=0.1913, simple_loss=0.293, pruned_loss=0.04482, over 6266.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2703, pruned_loss=0.03717, over 1429497.41 frames.], batch size: 37, lr: 3.90e-04
+2022-04-29 15:56:45,562 INFO [train.py:763] (0/8) Epoch 19, batch 2000, loss[loss=0.1632, simple_loss=0.2656, pruned_loss=0.03043, over 7234.00 frames.], tot_loss[loss=0.172, simple_loss=0.2699, pruned_loss=0.03707, over 1430354.92 frames.], batch size: 20, lr: 3.90e-04
+2022-04-29 15:57:52,841 INFO [train.py:763] (0/8) Epoch 19, batch 2050, loss[loss=0.1725, simple_loss=0.2765, pruned_loss=0.03427, over 7214.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2696, pruned_loss=0.03735, over 1429547.39 frames.], batch size: 21, lr: 3.89e-04
+2022-04-29 15:58:58,696 INFO [train.py:763] (0/8) Epoch 19, batch 2100, loss[loss=0.1654, simple_loss=0.2677, pruned_loss=0.03158, over 7419.00 frames.], tot_loss[loss=0.172, simple_loss=0.2696, pruned_loss=0.03724, over 1431644.38 frames.], batch size: 20, lr: 3.89e-04
+2022-04-29 16:00:05,514 INFO [train.py:763] (0/8) Epoch 19, batch 2150, loss[loss=0.2006, simple_loss=0.2973, pruned_loss=0.05195, over 7205.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2691, pruned_loss=0.03708, over 1425280.19 frames.], batch size: 22, lr: 3.89e-04
+2022-04-29 16:01:11,346 INFO [train.py:763] (0/8) Epoch 19, batch 2200, loss[loss=0.137, simple_loss=0.2291, pruned_loss=0.02246, over 6796.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2688, pruned_loss=0.03715, over 1420086.71 frames.], batch size: 15, lr: 3.89e-04
+2022-04-29 16:02:17,300 INFO [train.py:763] (0/8) Epoch 19, batch 2250, loss[loss=0.18, simple_loss=0.2785, pruned_loss=0.04076, over 7156.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2684, pruned_loss=0.0372, over 1422856.01 frames.], batch size: 20, lr: 3.89e-04
+2022-04-29 16:03:23,079 INFO [train.py:763] (0/8) Epoch 19, batch 2300, loss[loss=0.193, simple_loss=0.2941, pruned_loss=0.04596, over 7387.00 frames.], tot_loss[loss=0.172, simple_loss=0.2688, pruned_loss=0.03763, over 1422942.18 frames.], batch size: 23, lr: 3.89e-04
+2022-04-29 16:04:28,772 INFO [train.py:763] (0/8) Epoch 19, batch 2350, loss[loss=0.1772, simple_loss=0.2788, pruned_loss=0.03783, over 7313.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2696, pruned_loss=0.03773, over 1421578.22 frames.], batch size: 21, lr: 3.89e-04
+2022-04-29 16:05:34,134 INFO [train.py:763] (0/8) Epoch 19, batch 2400, loss[loss=0.1622, simple_loss=0.2658, pruned_loss=0.02926, over 7419.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2696, pruned_loss=0.03764, over 1424025.95 frames.], batch size: 20, lr: 3.89e-04
+2022-04-29 16:06:39,737 INFO [train.py:763] (0/8) Epoch 19, batch 2450, loss[loss=0.1721, simple_loss=0.2798, pruned_loss=0.03223, over 7121.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2685, pruned_loss=0.03696, over 1427200.58 frames.], batch size: 28, lr: 3.89e-04
+2022-04-29 16:07:45,467 INFO [train.py:763] (0/8) Epoch 19, batch 2500, loss[loss=0.1616, simple_loss=0.2679, pruned_loss=0.02767, over 7118.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2688, pruned_loss=0.03697, over 1426830.32 frames.], batch size: 26, lr: 3.88e-04
+2022-04-29 16:08:51,038 INFO [train.py:763] (0/8) Epoch 19, batch 2550, loss[loss=0.1835, simple_loss=0.2857, pruned_loss=0.04063, over 7332.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2691, pruned_loss=0.03715, over 1425602.88 frames.], batch size: 20, lr: 3.88e-04
+2022-04-29 16:09:56,812 INFO [train.py:763] (0/8) Epoch 19, batch 2600, loss[loss=0.2139, simple_loss=0.311, pruned_loss=0.05836, over 6810.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2701, pruned_loss=0.03738, over 1426712.13 frames.], batch size: 31, lr: 3.88e-04
+2022-04-29 16:11:03,368 INFO [train.py:763] (0/8) Epoch 19, batch 2650, loss[loss=0.1258, simple_loss=0.2134, pruned_loss=0.01908, over 7024.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2694, pruned_loss=0.03719, over 1427390.17 frames.], batch size: 16, lr: 3.88e-04
+2022-04-29 16:12:10,015 INFO [train.py:763] (0/8) Epoch 19, batch 2700, loss[loss=0.1733, simple_loss=0.2713, pruned_loss=0.03767, over 7389.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2693, pruned_loss=0.03742, over 1428493.63 frames.], batch size: 23, lr: 3.88e-04
+2022-04-29 16:13:17,142 INFO [train.py:763] (0/8) Epoch 19, batch 2750, loss[loss=0.1908, simple_loss=0.2956, pruned_loss=0.04298, over 7200.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2704, pruned_loss=0.03775, over 1426731.38 frames.], batch size: 23, lr: 3.88e-04
+2022-04-29 16:14:22,709 INFO [train.py:763] (0/8) Epoch 19, batch 2800, loss[loss=0.1649, simple_loss=0.2549, pruned_loss=0.03746, over 7165.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2706, pruned_loss=0.03781, over 1430744.99 frames.], batch size: 18, lr: 3.88e-04
+2022-04-29 16:15:28,804 INFO [train.py:763] (0/8) Epoch 19, batch 2850, loss[loss=0.1858, simple_loss=0.2835, pruned_loss=0.04408, over 7415.00 frames.], tot_loss[loss=0.1723, simple_loss=0.27, pruned_loss=0.03728, over 1432490.15 frames.], batch size: 21, lr: 3.88e-04
+2022-04-29 16:16:34,850 INFO [train.py:763] (0/8) Epoch 19, batch 2900, loss[loss=0.1894, simple_loss=0.2864, pruned_loss=0.04625, over 7120.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2695, pruned_loss=0.03713, over 1428299.85 frames.], batch size: 26, lr: 3.88e-04
+2022-04-29 16:17:40,414 INFO [train.py:763] (0/8) Epoch 19, batch 2950, loss[loss=0.1762, simple_loss=0.2764, pruned_loss=0.038, over 7228.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2703, pruned_loss=0.03729, over 1432209.51 frames.], batch size: 20, lr: 3.87e-04
+2022-04-29 16:18:45,960 INFO [train.py:763] (0/8) Epoch 19, batch 3000, loss[loss=0.2135, simple_loss=0.3142, pruned_loss=0.05636, over 7380.00 frames.], tot_loss[loss=0.174, simple_loss=0.2721, pruned_loss=0.03797, over 1431645.75 frames.], batch size: 23, lr: 3.87e-04
+2022-04-29 16:18:45,962 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 16:19:01,554 INFO [train.py:792] (0/8) Epoch 19, validation: loss=0.1668, simple_loss=0.2663, pruned_loss=0.03363, over 698248.00 frames.
+2022-04-29 16:20:06,924 INFO [train.py:763] (0/8) Epoch 19, batch 3050, loss[loss=0.1888, simple_loss=0.2901, pruned_loss=0.04377, over 7159.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2724, pruned_loss=0.03801, over 1433327.87 frames.], batch size: 19, lr: 3.87e-04
+2022-04-29 16:21:12,184 INFO [train.py:763] (0/8) Epoch 19, batch 3100, loss[loss=0.1822, simple_loss=0.2801, pruned_loss=0.04214, over 7117.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2727, pruned_loss=0.03799, over 1431960.42 frames.], batch size: 21, lr: 3.87e-04
+2022-04-29 16:22:17,542 INFO [train.py:763] (0/8) Epoch 19, batch 3150, loss[loss=0.1719, simple_loss=0.2656, pruned_loss=0.03914, over 7291.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2719, pruned_loss=0.03785, over 1432939.81 frames.], batch size: 18, lr: 3.87e-04
+2022-04-29 16:23:23,024 INFO [train.py:763] (0/8) Epoch 19, batch 3200, loss[loss=0.1797, simple_loss=0.2763, pruned_loss=0.04156, over 6727.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2711, pruned_loss=0.03778, over 1431981.42 frames.], batch size: 31, lr: 3.87e-04
+2022-04-29 16:24:28,070 INFO [train.py:763] (0/8) Epoch 19, batch 3250, loss[loss=0.1623, simple_loss=0.2711, pruned_loss=0.02671, over 7071.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2715, pruned_loss=0.03769, over 1429033.30 frames.], batch size: 18, lr: 3.87e-04
+2022-04-29 16:25:34,728 INFO [train.py:763] (0/8) Epoch 19, batch 3300, loss[loss=0.1471, simple_loss=0.2427, pruned_loss=0.02574, over 7127.00 frames.], tot_loss[loss=0.1735, simple_loss=0.271, pruned_loss=0.03798, over 1427477.21 frames.], batch size: 17, lr: 3.87e-04
+2022-04-29 16:26:41,787 INFO [train.py:763] (0/8) Epoch 19, batch 3350, loss[loss=0.2002, simple_loss=0.3005, pruned_loss=0.04996, over 7148.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2711, pruned_loss=0.03794, over 1427488.38 frames.], batch size: 20, lr: 3.87e-04
+2022-04-29 16:27:47,545 INFO [train.py:763] (0/8) Epoch 19, batch 3400, loss[loss=0.1419, simple_loss=0.2363, pruned_loss=0.02374, over 7268.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2713, pruned_loss=0.03804, over 1426832.61 frames.], batch size: 17, lr: 3.87e-04
+2022-04-29 16:28:53,019 INFO [train.py:763] (0/8) Epoch 19, batch 3450, loss[loss=0.1815, simple_loss=0.2741, pruned_loss=0.04444, over 7239.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2719, pruned_loss=0.03836, over 1425688.70 frames.], batch size: 20, lr: 3.86e-04
+2022-04-29 16:29:58,525 INFO [train.py:763] (0/8) Epoch 19, batch 3500, loss[loss=0.1295, simple_loss=0.2219, pruned_loss=0.01857, over 7261.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2709, pruned_loss=0.03788, over 1424204.14 frames.], batch size: 19, lr: 3.86e-04
+2022-04-29 16:31:03,663 INFO [train.py:763] (0/8) Epoch 19, batch 3550, loss[loss=0.1513, simple_loss=0.2571, pruned_loss=0.02279, over 7106.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2716, pruned_loss=0.03782, over 1427085.34 frames.], batch size: 21, lr: 3.86e-04
+2022-04-29 16:32:09,195 INFO [train.py:763] (0/8) Epoch 19, batch 3600, loss[loss=0.1683, simple_loss=0.2724, pruned_loss=0.03211, over 7214.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2716, pruned_loss=0.03803, over 1429670.61 frames.], batch size: 23, lr: 3.86e-04
+2022-04-29 16:33:15,441 INFO [train.py:763] (0/8) Epoch 19, batch 3650, loss[loss=0.1791, simple_loss=0.2916, pruned_loss=0.03334, over 7325.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2711, pruned_loss=0.03748, over 1430193.44 frames.], batch size: 21, lr: 3.86e-04
+2022-04-29 16:34:21,096 INFO [train.py:763] (0/8) Epoch 19, batch 3700, loss[loss=0.1721, simple_loss=0.2698, pruned_loss=0.03722, over 7156.00 frames.], tot_loss[loss=0.1728, simple_loss=0.271, pruned_loss=0.0373, over 1432200.76 frames.], batch size: 18, lr: 3.86e-04
+2022-04-29 16:35:26,774 INFO [train.py:763] (0/8) Epoch 19, batch 3750, loss[loss=0.1681, simple_loss=0.2697, pruned_loss=0.0333, over 7104.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2703, pruned_loss=0.03717, over 1426536.48 frames.], batch size: 28, lr: 3.86e-04
+2022-04-29 16:36:32,310 INFO [train.py:763] (0/8) Epoch 19, batch 3800, loss[loss=0.1582, simple_loss=0.2618, pruned_loss=0.02728, over 7323.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2699, pruned_loss=0.0375, over 1422077.50 frames.], batch size: 20, lr: 3.86e-04
+2022-04-29 16:37:37,910 INFO [train.py:763] (0/8) Epoch 19, batch 3850, loss[loss=0.1437, simple_loss=0.2394, pruned_loss=0.02398, over 7283.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2684, pruned_loss=0.03691, over 1420543.55 frames.], batch size: 17, lr: 3.86e-04
+2022-04-29 16:38:44,212 INFO [train.py:763] (0/8) Epoch 19, batch 3900, loss[loss=0.211, simple_loss=0.3182, pruned_loss=0.05189, over 7129.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2695, pruned_loss=0.03692, over 1417592.85 frames.], batch size: 21, lr: 3.85e-04
+2022-04-29 16:39:50,797 INFO [train.py:763] (0/8) Epoch 19, batch 3950, loss[loss=0.1613, simple_loss=0.2681, pruned_loss=0.02728, over 7345.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2698, pruned_loss=0.03735, over 1412193.18 frames.], batch size: 20, lr: 3.85e-04
+2022-04-29 16:40:57,156 INFO [train.py:763] (0/8) Epoch 19, batch 4000, loss[loss=0.1548, simple_loss=0.2515, pruned_loss=0.02902, over 7160.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2698, pruned_loss=0.03736, over 1409794.45 frames.], batch size: 18, lr: 3.85e-04
+2022-04-29 16:42:03,330 INFO [train.py:763] (0/8) Epoch 19, batch 4050, loss[loss=0.1643, simple_loss=0.2749, pruned_loss=0.02683, over 7331.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2697, pruned_loss=0.03736, over 1406632.91 frames.], batch size: 20, lr: 3.85e-04
+2022-04-29 16:43:09,193 INFO [train.py:763] (0/8) Epoch 19, batch 4100, loss[loss=0.1497, simple_loss=0.2335, pruned_loss=0.03297, over 7277.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2686, pruned_loss=0.03684, over 1406559.56 frames.], batch size: 18, lr: 3.85e-04
+2022-04-29 16:44:14,864 INFO [train.py:763] (0/8) Epoch 19, batch 4150, loss[loss=0.15, simple_loss=0.2543, pruned_loss=0.02283, over 7074.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2683, pruned_loss=0.03658, over 1410681.58 frames.], batch size: 18, lr: 3.85e-04
+2022-04-29 16:45:20,207 INFO [train.py:763] (0/8) Epoch 19, batch 4200, loss[loss=0.1343, simple_loss=0.2276, pruned_loss=0.02051, over 6722.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2689, pruned_loss=0.03677, over 1405060.94 frames.], batch size: 15, lr: 3.85e-04
+2022-04-29 16:46:26,006 INFO [train.py:763] (0/8) Epoch 19, batch 4250, loss[loss=0.1973, simple_loss=0.2946, pruned_loss=0.04997, over 7199.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2676, pruned_loss=0.03662, over 1403671.28 frames.], batch size: 23, lr: 3.85e-04
+2022-04-29 16:47:31,538 INFO [train.py:763] (0/8) Epoch 19, batch 4300, loss[loss=0.1831, simple_loss=0.2823, pruned_loss=0.04199, over 7219.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2686, pruned_loss=0.03681, over 1402144.33 frames.], batch size: 21, lr: 3.85e-04
+2022-04-29 16:48:37,212 INFO [train.py:763] (0/8) Epoch 19, batch 4350, loss[loss=0.227, simple_loss=0.3132, pruned_loss=0.07039, over 5170.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2672, pruned_loss=0.03634, over 1404629.75 frames.], batch size: 55, lr: 3.84e-04
+2022-04-29 16:49:42,596 INFO [train.py:763] (0/8) Epoch 19, batch 4400, loss[loss=0.1806, simple_loss=0.2758, pruned_loss=0.0427, over 7162.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2674, pruned_loss=0.03647, over 1398291.76 frames.], batch size: 19, lr: 3.84e-04
+2022-04-29 16:50:47,792 INFO [train.py:763] (0/8) Epoch 19, batch 4450, loss[loss=0.1577, simple_loss=0.2446, pruned_loss=0.03538, over 6770.00 frames.], tot_loss[loss=0.1699, simple_loss=0.267, pruned_loss=0.0364, over 1389396.14 frames.], batch size: 15, lr: 3.84e-04
+2022-04-29 16:51:52,277 INFO [train.py:763] (0/8) Epoch 19, batch 4500, loss[loss=0.2035, simple_loss=0.2985, pruned_loss=0.05426, over 7198.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2688, pruned_loss=0.03696, over 1382631.02 frames.], batch size: 23, lr: 3.84e-04
+2022-04-29 16:52:57,057 INFO [train.py:763] (0/8) Epoch 19, batch 4550, loss[loss=0.1743, simple_loss=0.2625, pruned_loss=0.04309, over 6466.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2717, pruned_loss=0.03854, over 1335229.22 frames.], batch size: 38, lr: 3.84e-04
+2022-04-29 16:53:46,451 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-19.pt
+2022-04-29 16:54:25,843 INFO [train.py:763] (0/8) Epoch 20, batch 0, loss[loss=0.1798, simple_loss=0.259, pruned_loss=0.05033, over 7008.00 frames.], tot_loss[loss=0.1798, simple_loss=0.259, pruned_loss=0.05033, over 7008.00 frames.], batch size: 16, lr: 3.75e-04
+2022-04-29 16:55:32,597 INFO [train.py:763] (0/8) Epoch 20, batch 50, loss[loss=0.1659, simple_loss=0.2652, pruned_loss=0.03327, over 6388.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2703, pruned_loss=0.03769, over 322612.21 frames.], batch size: 37, lr: 3.75e-04
+2022-04-29 16:56:38,006 INFO [train.py:763] (0/8) Epoch 20, batch 100, loss[loss=0.187, simple_loss=0.2732, pruned_loss=0.05037, over 7236.00 frames.], tot_loss[loss=0.1736, simple_loss=0.271, pruned_loss=0.03809, over 566679.29 frames.], batch size: 16, lr: 3.75e-04
+2022-04-29 16:57:44,567 INFO [train.py:763] (0/8) Epoch 20, batch 150, loss[loss=0.1658, simple_loss=0.2632, pruned_loss=0.03415, over 7148.00 frames.], tot_loss[loss=0.1727, simple_loss=0.27, pruned_loss=0.03767, over 755748.65 frames.], batch size: 18, lr: 3.75e-04
+2022-04-29 16:58:49,755 INFO [train.py:763] (0/8) Epoch 20, batch 200, loss[loss=0.1791, simple_loss=0.2874, pruned_loss=0.03544, over 6763.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2711, pruned_loss=0.03755, over 900773.30 frames.], batch size: 31, lr: 3.75e-04
+2022-04-29 16:59:55,583 INFO [train.py:763] (0/8) Epoch 20, batch 250, loss[loss=0.1612, simple_loss=0.2574, pruned_loss=0.03245, over 7152.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2694, pruned_loss=0.03696, over 1013737.18 frames.], batch size: 19, lr: 3.75e-04
+2022-04-29 17:01:00,767 INFO [train.py:763] (0/8) Epoch 20, batch 300, loss[loss=0.1623, simple_loss=0.2597, pruned_loss=0.03242, over 7272.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2706, pruned_loss=0.03741, over 1102783.16 frames.], batch size: 18, lr: 3.75e-04
+2022-04-29 17:02:05,619 INFO [train.py:763] (0/8) Epoch 20, batch 350, loss[loss=0.1654, simple_loss=0.2625, pruned_loss=0.03413, over 7264.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2712, pruned_loss=0.03783, over 1171748.39 frames.], batch size: 19, lr: 3.74e-04
+2022-04-29 17:03:10,961 INFO [train.py:763] (0/8) Epoch 20, batch 400, loss[loss=0.1607, simple_loss=0.2565, pruned_loss=0.03247, over 7056.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2699, pruned_loss=0.03716, over 1230208.96 frames.], batch size: 18, lr: 3.74e-04
+2022-04-29 17:04:16,937 INFO [train.py:763] (0/8) Epoch 20, batch 450, loss[loss=0.1481, simple_loss=0.2482, pruned_loss=0.02398, over 7075.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2698, pruned_loss=0.03679, over 1272124.75 frames.], batch size: 18, lr: 3.74e-04
+2022-04-29 17:05:22,379 INFO [train.py:763] (0/8) Epoch 20, batch 500, loss[loss=0.2048, simple_loss=0.296, pruned_loss=0.0568, over 7094.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2696, pruned_loss=0.03671, over 1310784.47 frames.], batch size: 28, lr: 3.74e-04
+2022-04-29 17:06:27,720 INFO [train.py:763] (0/8) Epoch 20, batch 550, loss[loss=0.1647, simple_loss=0.2501, pruned_loss=0.03967, over 6814.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2694, pruned_loss=0.0365, over 1336446.23 frames.], batch size: 15, lr: 3.74e-04
+2022-04-29 17:07:34,460 INFO [train.py:763] (0/8) Epoch 20, batch 600, loss[loss=0.195, simple_loss=0.2897, pruned_loss=0.05018, over 7219.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2698, pruned_loss=0.03666, over 1354414.01 frames.], batch size: 22, lr: 3.74e-04
+2022-04-29 17:08:41,623 INFO [train.py:763] (0/8) Epoch 20, batch 650, loss[loss=0.144, simple_loss=0.238, pruned_loss=0.02506, over 7136.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2675, pruned_loss=0.03604, over 1369241.62 frames.], batch size: 17, lr: 3.74e-04
+2022-04-29 17:09:47,536 INFO [train.py:763] (0/8) Epoch 20, batch 700, loss[loss=0.1687, simple_loss=0.279, pruned_loss=0.02923, over 7234.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2683, pruned_loss=0.03602, over 1380278.29 frames.], batch size: 20, lr: 3.74e-04
+2022-04-29 17:10:53,621 INFO [train.py:763] (0/8) Epoch 20, batch 750, loss[loss=0.1427, simple_loss=0.2483, pruned_loss=0.01855, over 7403.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2693, pruned_loss=0.0362, over 1385871.93 frames.], batch size: 18, lr: 3.74e-04
+2022-04-29 17:11:58,960 INFO [train.py:763] (0/8) Epoch 20, batch 800, loss[loss=0.1785, simple_loss=0.2811, pruned_loss=0.03798, over 7234.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2687, pruned_loss=0.03651, over 1384655.47 frames.], batch size: 20, lr: 3.73e-04
+2022-04-29 17:13:05,461 INFO [train.py:763] (0/8) Epoch 20, batch 850, loss[loss=0.1824, simple_loss=0.2903, pruned_loss=0.03727, over 7282.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2674, pruned_loss=0.0361, over 1390988.92 frames.], batch size: 25, lr: 3.73e-04
+2022-04-29 17:14:10,910 INFO [train.py:763] (0/8) Epoch 20, batch 900, loss[loss=0.1981, simple_loss=0.3023, pruned_loss=0.04701, over 7232.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2676, pruned_loss=0.0366, over 1399409.13 frames.], batch size: 20, lr: 3.73e-04
+2022-04-29 17:15:15,951 INFO [train.py:763] (0/8) Epoch 20, batch 950, loss[loss=0.1625, simple_loss=0.2722, pruned_loss=0.02634, over 7336.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2677, pruned_loss=0.03633, over 1406148.92 frames.], batch size: 22, lr: 3.73e-04
+2022-04-29 17:16:21,954 INFO [train.py:763] (0/8) Epoch 20, batch 1000, loss[loss=0.1995, simple_loss=0.3011, pruned_loss=0.04894, over 7203.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2687, pruned_loss=0.03671, over 1405416.10 frames.], batch size: 23, lr: 3.73e-04
+2022-04-29 17:17:26,880 INFO [train.py:763] (0/8) Epoch 20, batch 1050, loss[loss=0.1548, simple_loss=0.2567, pruned_loss=0.02641, over 7424.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2698, pruned_loss=0.03639, over 1406975.82 frames.], batch size: 21, lr: 3.73e-04
+2022-04-29 17:18:32,324 INFO [train.py:763] (0/8) Epoch 20, batch 1100, loss[loss=0.1651, simple_loss=0.2486, pruned_loss=0.0408, over 6783.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2684, pruned_loss=0.03625, over 1408214.69 frames.], batch size: 15, lr: 3.73e-04
+2022-04-29 17:19:37,618 INFO [train.py:763] (0/8) Epoch 20, batch 1150, loss[loss=0.1931, simple_loss=0.2955, pruned_loss=0.04538, over 7306.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2682, pruned_loss=0.03582, over 1413362.93 frames.], batch size: 24, lr: 3.73e-04
+2022-04-29 17:20:42,602 INFO [train.py:763] (0/8) Epoch 20, batch 1200, loss[loss=0.1601, simple_loss=0.2543, pruned_loss=0.03294, over 7286.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2692, pruned_loss=0.03625, over 1415664.82 frames.], batch size: 18, lr: 3.73e-04
+2022-04-29 17:21:47,935 INFO [train.py:763] (0/8) Epoch 20, batch 1250, loss[loss=0.198, simple_loss=0.2892, pruned_loss=0.05343, over 7311.00 frames.], tot_loss[loss=0.1707, simple_loss=0.269, pruned_loss=0.03621, over 1417797.38 frames.], batch size: 24, lr: 3.73e-04
+2022-04-29 17:22:53,229 INFO [train.py:763] (0/8) Epoch 20, batch 1300, loss[loss=0.1534, simple_loss=0.2451, pruned_loss=0.0309, over 7070.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2686, pruned_loss=0.03618, over 1417087.41 frames.], batch size: 18, lr: 3.72e-04
+2022-04-29 17:23:59,022 INFO [train.py:763] (0/8) Epoch 20, batch 1350, loss[loss=0.1906, simple_loss=0.2934, pruned_loss=0.04383, over 7343.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2694, pruned_loss=0.03669, over 1423789.15 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:25:04,576 INFO [train.py:763] (0/8) Epoch 20, batch 1400, loss[loss=0.1864, simple_loss=0.2776, pruned_loss=0.04754, over 7380.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2691, pruned_loss=0.03681, over 1426160.32 frames.], batch size: 23, lr: 3.72e-04
+2022-04-29 17:26:11,041 INFO [train.py:763] (0/8) Epoch 20, batch 1450, loss[loss=0.2178, simple_loss=0.2984, pruned_loss=0.06861, over 4866.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2687, pruned_loss=0.03679, over 1420361.55 frames.], batch size: 52, lr: 3.72e-04
+2022-04-29 17:27:17,687 INFO [train.py:763] (0/8) Epoch 20, batch 1500, loss[loss=0.1625, simple_loss=0.2669, pruned_loss=0.02904, over 7328.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2683, pruned_loss=0.03658, over 1418367.66 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:28:24,725 INFO [train.py:763] (0/8) Epoch 20, batch 1550, loss[loss=0.17, simple_loss=0.2798, pruned_loss=0.0301, over 6694.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2682, pruned_loss=0.03654, over 1420716.72 frames.], batch size: 31, lr: 3.72e-04
+2022-04-29 17:29:31,835 INFO [train.py:763] (0/8) Epoch 20, batch 1600, loss[loss=0.1812, simple_loss=0.2825, pruned_loss=0.04, over 7340.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2685, pruned_loss=0.03644, over 1421953.35 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:30:38,904 INFO [train.py:763] (0/8) Epoch 20, batch 1650, loss[loss=0.1432, simple_loss=0.2457, pruned_loss=0.02036, over 7332.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2683, pruned_loss=0.03645, over 1422628.01 frames.], batch size: 20, lr: 3.72e-04
+2022-04-29 17:31:46,180 INFO [train.py:763] (0/8) Epoch 20, batch 1700, loss[loss=0.1941, simple_loss=0.2926, pruned_loss=0.04775, over 7332.00 frames.], tot_loss[loss=0.17, simple_loss=0.2679, pruned_loss=0.03603, over 1422410.16 frames.], batch size: 22, lr: 3.72e-04
+2022-04-29 17:32:52,734 INFO [train.py:763] (0/8) Epoch 20, batch 1750, loss[loss=0.1403, simple_loss=0.2374, pruned_loss=0.02164, over 7406.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2684, pruned_loss=0.0363, over 1423700.06 frames.], batch size: 18, lr: 3.72e-04
+2022-04-29 17:33:59,660 INFO [train.py:763] (0/8) Epoch 20, batch 1800, loss[loss=0.1809, simple_loss=0.2817, pruned_loss=0.04004, over 7221.00 frames.], tot_loss[loss=0.17, simple_loss=0.268, pruned_loss=0.03598, over 1424806.74 frames.], batch size: 23, lr: 3.71e-04
+2022-04-29 17:35:06,947 INFO [train.py:763] (0/8) Epoch 20, batch 1850, loss[loss=0.1612, simple_loss=0.2727, pruned_loss=0.02486, over 7414.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2687, pruned_loss=0.03643, over 1424411.40 frames.], batch size: 18, lr: 3.71e-04
+2022-04-29 17:36:12,562 INFO [train.py:763] (0/8) Epoch 20, batch 1900, loss[loss=0.1453, simple_loss=0.2397, pruned_loss=0.02544, over 7170.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2686, pruned_loss=0.0362, over 1425733.34 frames.], batch size: 19, lr: 3.71e-04
+2022-04-29 17:37:18,021 INFO [train.py:763] (0/8) Epoch 20, batch 1950, loss[loss=0.1672, simple_loss=0.2624, pruned_loss=0.03597, over 7254.00 frames.], tot_loss[loss=0.1707, simple_loss=0.269, pruned_loss=0.03619, over 1429412.48 frames.], batch size: 19, lr: 3.71e-04
+2022-04-29 17:38:24,306 INFO [train.py:763] (0/8) Epoch 20, batch 2000, loss[loss=0.1696, simple_loss=0.2758, pruned_loss=0.03174, over 6728.00 frames.], tot_loss[loss=0.17, simple_loss=0.2683, pruned_loss=0.0359, over 1426157.37 frames.], batch size: 31, lr: 3.71e-04
+2022-04-29 17:39:29,422 INFO [train.py:763] (0/8) Epoch 20, batch 2050, loss[loss=0.1679, simple_loss=0.271, pruned_loss=0.03244, over 7228.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2687, pruned_loss=0.03611, over 1425321.02 frames.], batch size: 21, lr: 3.71e-04
+2022-04-29 17:40:35,606 INFO [train.py:763] (0/8) Epoch 20, batch 2100, loss[loss=0.1641, simple_loss=0.2728, pruned_loss=0.02773, over 7073.00 frames.], tot_loss[loss=0.17, simple_loss=0.2682, pruned_loss=0.03586, over 1424603.89 frames.], batch size: 18, lr: 3.71e-04
+2022-04-29 17:41:42,820 INFO [train.py:763] (0/8) Epoch 20, batch 2150, loss[loss=0.1582, simple_loss=0.2453, pruned_loss=0.03555, over 6799.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2692, pruned_loss=0.0362, over 1422278.90 frames.], batch size: 15, lr: 3.71e-04
+2022-04-29 17:42:48,997 INFO [train.py:763] (0/8) Epoch 20, batch 2200, loss[loss=0.1604, simple_loss=0.2781, pruned_loss=0.02134, over 7217.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2689, pruned_loss=0.03609, over 1425072.72 frames.], batch size: 22, lr: 3.71e-04
+2022-04-29 17:43:54,369 INFO [train.py:763] (0/8) Epoch 20, batch 2250, loss[loss=0.1877, simple_loss=0.2848, pruned_loss=0.0453, over 7203.00 frames.], tot_loss[loss=0.171, simple_loss=0.2692, pruned_loss=0.03636, over 1425776.25 frames.], batch size: 22, lr: 3.71e-04
+2022-04-29 17:45:01,610 INFO [train.py:763] (0/8) Epoch 20, batch 2300, loss[loss=0.2035, simple_loss=0.2825, pruned_loss=0.06219, over 5083.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2686, pruned_loss=0.03654, over 1422344.74 frames.], batch size: 52, lr: 3.71e-04
+2022-04-29 17:46:08,272 INFO [train.py:763] (0/8) Epoch 20, batch 2350, loss[loss=0.1657, simple_loss=0.2664, pruned_loss=0.03256, over 7288.00 frames.], tot_loss[loss=0.171, simple_loss=0.269, pruned_loss=0.03651, over 1417238.38 frames.], batch size: 24, lr: 3.70e-04
+2022-04-29 17:47:15,540 INFO [train.py:763] (0/8) Epoch 20, batch 2400, loss[loss=0.1836, simple_loss=0.2776, pruned_loss=0.04479, over 7207.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2684, pruned_loss=0.03628, over 1420446.53 frames.], batch size: 23, lr: 3.70e-04
+2022-04-29 17:48:22,383 INFO [train.py:763] (0/8) Epoch 20, batch 2450, loss[loss=0.189, simple_loss=0.2935, pruned_loss=0.04226, over 7161.00 frames.], tot_loss[loss=0.17, simple_loss=0.2681, pruned_loss=0.03597, over 1421088.64 frames.], batch size: 19, lr: 3.70e-04
+2022-04-29 17:49:29,428 INFO [train.py:763] (0/8) Epoch 20, batch 2500, loss[loss=0.1801, simple_loss=0.2842, pruned_loss=0.03798, over 7418.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2685, pruned_loss=0.03639, over 1422519.16 frames.], batch size: 21, lr: 3.70e-04
+2022-04-29 17:50:36,104 INFO [train.py:763] (0/8) Epoch 20, batch 2550, loss[loss=0.1816, simple_loss=0.276, pruned_loss=0.0436, over 5231.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2691, pruned_loss=0.03667, over 1420414.27 frames.], batch size: 52, lr: 3.70e-04
+2022-04-29 17:51:41,492 INFO [train.py:763] (0/8) Epoch 20, batch 2600, loss[loss=0.1883, simple_loss=0.2757, pruned_loss=0.05042, over 7075.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2696, pruned_loss=0.03679, over 1421408.10 frames.], batch size: 18, lr: 3.70e-04
+2022-04-29 17:52:58,283 INFO [train.py:763] (0/8) Epoch 20, batch 2650, loss[loss=0.1525, simple_loss=0.2521, pruned_loss=0.02647, over 7331.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2699, pruned_loss=0.03701, over 1416791.49 frames.], batch size: 20, lr: 3.70e-04
+2022-04-29 17:54:04,104 INFO [train.py:763] (0/8) Epoch 20, batch 2700, loss[loss=0.1392, simple_loss=0.2306, pruned_loss=0.02387, over 7418.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2697, pruned_loss=0.03689, over 1420697.93 frames.], batch size: 18, lr: 3.70e-04
+2022-04-29 17:55:10,587 INFO [train.py:763] (0/8) Epoch 20, batch 2750, loss[loss=0.1646, simple_loss=0.2661, pruned_loss=0.03157, over 7165.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2691, pruned_loss=0.03674, over 1422479.95 frames.], batch size: 18, lr: 3.70e-04
+2022-04-29 17:56:15,905 INFO [train.py:763] (0/8) Epoch 20, batch 2800, loss[loss=0.1974, simple_loss=0.3029, pruned_loss=0.04593, over 7378.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2691, pruned_loss=0.03666, over 1426042.48 frames.], batch size: 23, lr: 3.70e-04
+2022-04-29 17:57:21,240 INFO [train.py:763] (0/8) Epoch 20, batch 2850, loss[loss=0.182, simple_loss=0.2793, pruned_loss=0.04236, over 7211.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2686, pruned_loss=0.03636, over 1420779.74 frames.], batch size: 23, lr: 3.69e-04
+2022-04-29 17:58:26,462 INFO [train.py:763] (0/8) Epoch 20, batch 2900, loss[loss=0.1928, simple_loss=0.2962, pruned_loss=0.04466, over 7077.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2689, pruned_loss=0.03635, over 1417118.60 frames.], batch size: 28, lr: 3.69e-04
+2022-04-29 17:59:31,732 INFO [train.py:763] (0/8) Epoch 20, batch 2950, loss[loss=0.1578, simple_loss=0.2488, pruned_loss=0.03346, over 7348.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2695, pruned_loss=0.03642, over 1415874.70 frames.], batch size: 19, lr: 3.69e-04
+2022-04-29 18:01:03,489 INFO [train.py:763] (0/8) Epoch 20, batch 3000, loss[loss=0.2173, simple_loss=0.3145, pruned_loss=0.06005, over 6781.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2693, pruned_loss=0.03685, over 1414508.35 frames.], batch size: 31, lr: 3.69e-04
+2022-04-29 18:01:03,490 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 18:01:18,757 INFO [train.py:792] (0/8) Epoch 20, validation: loss=0.1672, simple_loss=0.2663, pruned_loss=0.03407, over 698248.00 frames.
+2022-04-29 18:02:33,691 INFO [train.py:763] (0/8) Epoch 20, batch 3050, loss[loss=0.1639, simple_loss=0.2592, pruned_loss=0.03435, over 7284.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2692, pruned_loss=0.0367, over 1414947.17 frames.], batch size: 18, lr: 3.69e-04
+2022-04-29 18:03:49,777 INFO [train.py:763] (0/8) Epoch 20, batch 3100, loss[loss=0.1734, simple_loss=0.2707, pruned_loss=0.03805, over 7361.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2691, pruned_loss=0.03658, over 1413502.30 frames.], batch size: 23, lr: 3.69e-04
+2022-04-29 18:05:13,905 INFO [train.py:763] (0/8) Epoch 20, batch 3150, loss[loss=0.2058, simple_loss=0.2921, pruned_loss=0.05977, over 7276.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2695, pruned_loss=0.03677, over 1418755.13 frames.], batch size: 24, lr: 3.69e-04
+2022-04-29 18:06:18,933 INFO [train.py:763] (0/8) Epoch 20, batch 3200, loss[loss=0.1781, simple_loss=0.285, pruned_loss=0.03558, over 7311.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2708, pruned_loss=0.03708, over 1423464.43 frames.], batch size: 21, lr: 3.69e-04
+2022-04-29 18:07:24,054 INFO [train.py:763] (0/8) Epoch 20, batch 3250, loss[loss=0.1382, simple_loss=0.229, pruned_loss=0.02375, over 7075.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2706, pruned_loss=0.03734, over 1422850.56 frames.], batch size: 18, lr: 3.69e-04
+2022-04-29 18:08:29,715 INFO [train.py:763] (0/8) Epoch 20, batch 3300, loss[loss=0.1407, simple_loss=0.2316, pruned_loss=0.02492, over 7128.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2698, pruned_loss=0.03672, over 1423933.48 frames.], batch size: 17, lr: 3.69e-04
+2022-04-29 18:09:35,978 INFO [train.py:763] (0/8) Epoch 20, batch 3350, loss[loss=0.1631, simple_loss=0.2637, pruned_loss=0.03128, over 7238.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2694, pruned_loss=0.03668, over 1419593.76 frames.], batch size: 20, lr: 3.68e-04
+2022-04-29 18:10:42,814 INFO [train.py:763] (0/8) Epoch 20, batch 3400, loss[loss=0.1855, simple_loss=0.2866, pruned_loss=0.04225, over 6646.00 frames.], tot_loss[loss=0.1716, simple_loss=0.27, pruned_loss=0.03654, over 1416671.90 frames.], batch size: 38, lr: 3.68e-04
+2022-04-29 18:11:49,531 INFO [train.py:763] (0/8) Epoch 20, batch 3450, loss[loss=0.1821, simple_loss=0.2774, pruned_loss=0.04338, over 7324.00 frames.], tot_loss[loss=0.1717, simple_loss=0.27, pruned_loss=0.03668, over 1414497.55 frames.], batch size: 21, lr: 3.68e-04
+2022-04-29 18:12:54,741 INFO [train.py:763] (0/8) Epoch 20, batch 3500, loss[loss=0.1762, simple_loss=0.2702, pruned_loss=0.04112, over 7006.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2701, pruned_loss=0.03668, over 1410090.51 frames.], batch size: 28, lr: 3.68e-04
+2022-04-29 18:14:00,246 INFO [train.py:763] (0/8) Epoch 20, batch 3550, loss[loss=0.1419, simple_loss=0.2322, pruned_loss=0.02578, over 7267.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2689, pruned_loss=0.03614, over 1414481.96 frames.], batch size: 17, lr: 3.68e-04
+2022-04-29 18:15:05,504 INFO [train.py:763] (0/8) Epoch 20, batch 3600, loss[loss=0.1775, simple_loss=0.2749, pruned_loss=0.04006, over 7397.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2704, pruned_loss=0.03703, over 1412894.51 frames.], batch size: 23, lr: 3.68e-04
+2022-04-29 18:16:10,764 INFO [train.py:763] (0/8) Epoch 20, batch 3650, loss[loss=0.163, simple_loss=0.2591, pruned_loss=0.03348, over 7154.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2699, pruned_loss=0.03682, over 1414967.59 frames.], batch size: 26, lr: 3.68e-04
+2022-04-29 18:17:15,975 INFO [train.py:763] (0/8) Epoch 20, batch 3700, loss[loss=0.1786, simple_loss=0.2834, pruned_loss=0.03684, over 7320.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2701, pruned_loss=0.03655, over 1414525.77 frames.], batch size: 21, lr: 3.68e-04
+2022-04-29 18:18:22,134 INFO [train.py:763] (0/8) Epoch 20, batch 3750, loss[loss=0.2032, simple_loss=0.3039, pruned_loss=0.05126, over 7289.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2695, pruned_loss=0.03651, over 1418118.13 frames.], batch size: 25, lr: 3.68e-04
+2022-04-29 18:19:27,286 INFO [train.py:763] (0/8) Epoch 20, batch 3800, loss[loss=0.1847, simple_loss=0.279, pruned_loss=0.04521, over 7160.00 frames.], tot_loss[loss=0.171, simple_loss=0.269, pruned_loss=0.03645, over 1419016.22 frames.], batch size: 26, lr: 3.68e-04
+2022-04-29 18:20:33,284 INFO [train.py:763] (0/8) Epoch 20, batch 3850, loss[loss=0.1901, simple_loss=0.2867, pruned_loss=0.04671, over 7331.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2694, pruned_loss=0.03617, over 1419122.06 frames.], batch size: 20, lr: 3.68e-04
+2022-04-29 18:21:38,671 INFO [train.py:763] (0/8) Epoch 20, batch 3900, loss[loss=0.1913, simple_loss=0.2773, pruned_loss=0.05267, over 7264.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2692, pruned_loss=0.03618, over 1423751.43 frames.], batch size: 19, lr: 3.67e-04
+2022-04-29 18:22:44,415 INFO [train.py:763] (0/8) Epoch 20, batch 3950, loss[loss=0.1563, simple_loss=0.2558, pruned_loss=0.02841, over 7414.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2704, pruned_loss=0.03639, over 1419196.64 frames.], batch size: 18, lr: 3.67e-04
+2022-04-29 18:23:51,281 INFO [train.py:763] (0/8) Epoch 20, batch 4000, loss[loss=0.1743, simple_loss=0.278, pruned_loss=0.03529, over 7356.00 frames.], tot_loss[loss=0.171, simple_loss=0.2697, pruned_loss=0.03616, over 1422774.83 frames.], batch size: 19, lr: 3.67e-04
+2022-04-29 18:24:58,617 INFO [train.py:763] (0/8) Epoch 20, batch 4050, loss[loss=0.2465, simple_loss=0.3317, pruned_loss=0.08064, over 5123.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2688, pruned_loss=0.03621, over 1419550.01 frames.], batch size: 52, lr: 3.67e-04
+2022-04-29 18:26:05,426 INFO [train.py:763] (0/8) Epoch 20, batch 4100, loss[loss=0.1643, simple_loss=0.26, pruned_loss=0.03427, over 7223.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2693, pruned_loss=0.03676, over 1412116.53 frames.], batch size: 21, lr: 3.67e-04
+2022-04-29 18:27:11,035 INFO [train.py:763] (0/8) Epoch 20, batch 4150, loss[loss=0.1722, simple_loss=0.2756, pruned_loss=0.03439, over 7065.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2699, pruned_loss=0.03667, over 1413234.30 frames.], batch size: 18, lr: 3.67e-04
+2022-04-29 18:28:16,328 INFO [train.py:763] (0/8) Epoch 20, batch 4200, loss[loss=0.1752, simple_loss=0.2723, pruned_loss=0.03899, over 6773.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2699, pruned_loss=0.03655, over 1412435.73 frames.], batch size: 31, lr: 3.67e-04
+2022-04-29 18:29:07,221 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-96000.pt
+2022-04-29 18:29:32,313 INFO [train.py:763] (0/8) Epoch 20, batch 4250, loss[loss=0.168, simple_loss=0.2727, pruned_loss=0.03163, over 7225.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2688, pruned_loss=0.03615, over 1416782.50 frames.], batch size: 21, lr: 3.67e-04
+2022-04-29 18:30:38,993 INFO [train.py:763] (0/8) Epoch 20, batch 4300, loss[loss=0.174, simple_loss=0.2829, pruned_loss=0.03255, over 7289.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2679, pruned_loss=0.03584, over 1418196.72 frames.], batch size: 24, lr: 3.67e-04
+2022-04-29 18:31:45,011 INFO [train.py:763] (0/8) Epoch 20, batch 4350, loss[loss=0.1734, simple_loss=0.2734, pruned_loss=0.03673, over 7223.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2687, pruned_loss=0.03615, over 1417830.40 frames.], batch size: 21, lr: 3.67e-04
+2022-04-29 18:32:52,218 INFO [train.py:763] (0/8) Epoch 20, batch 4400, loss[loss=0.1516, simple_loss=0.2521, pruned_loss=0.02558, over 7162.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2691, pruned_loss=0.03616, over 1415575.94 frames.], batch size: 18, lr: 3.66e-04
+2022-04-29 18:33:58,497 INFO [train.py:763] (0/8) Epoch 20, batch 4450, loss[loss=0.1416, simple_loss=0.2371, pruned_loss=0.02302, over 6989.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2691, pruned_loss=0.03607, over 1407817.88 frames.], batch size: 16, lr: 3.66e-04
+2022-04-29 18:35:05,766 INFO [train.py:763] (0/8) Epoch 20, batch 4500, loss[loss=0.148, simple_loss=0.2354, pruned_loss=0.03032, over 7016.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2695, pruned_loss=0.0362, over 1410191.59 frames.], batch size: 16, lr: 3.66e-04
+2022-04-29 18:36:13,320 INFO [train.py:763] (0/8) Epoch 20, batch 4550, loss[loss=0.1802, simple_loss=0.2764, pruned_loss=0.04199, over 5090.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2684, pruned_loss=0.03596, over 1394283.07 frames.], batch size: 53, lr: 3.66e-04
+2022-04-29 18:37:03,095 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-20.pt
+2022-04-29 18:37:42,392 INFO [train.py:763] (0/8) Epoch 21, batch 0, loss[loss=0.1723, simple_loss=0.2797, pruned_loss=0.03238, over 7270.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2797, pruned_loss=0.03238, over 7270.00 frames.], batch size: 25, lr: 3.58e-04
+2022-04-29 18:38:48,211 INFO [train.py:763] (0/8) Epoch 21, batch 50, loss[loss=0.1524, simple_loss=0.2528, pruned_loss=0.02602, over 7158.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2731, pruned_loss=0.03871, over 318144.76 frames.], batch size: 18, lr: 3.58e-04
+2022-04-29 18:39:53,575 INFO [train.py:763] (0/8) Epoch 21, batch 100, loss[loss=0.17, simple_loss=0.2771, pruned_loss=0.03143, over 7118.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2702, pruned_loss=0.03681, over 564371.45 frames.], batch size: 21, lr: 3.58e-04
+2022-04-29 18:41:00,345 INFO [train.py:763] (0/8) Epoch 21, batch 150, loss[loss=0.1748, simple_loss=0.2808, pruned_loss=0.03437, over 7313.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2698, pruned_loss=0.03651, over 753791.24 frames.], batch size: 21, lr: 3.58e-04
+2022-04-29 18:42:07,761 INFO [train.py:763] (0/8) Epoch 21, batch 200, loss[loss=0.163, simple_loss=0.2679, pruned_loss=0.02907, over 7332.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2688, pruned_loss=0.03637, over 901565.87 frames.], batch size: 22, lr: 3.58e-04
+2022-04-29 18:43:14,306 INFO [train.py:763] (0/8) Epoch 21, batch 250, loss[loss=0.1433, simple_loss=0.2455, pruned_loss=0.02056, over 7259.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2685, pruned_loss=0.03588, over 1015242.33 frames.], batch size: 19, lr: 3.57e-04
+2022-04-29 18:44:19,577 INFO [train.py:763] (0/8) Epoch 21, batch 300, loss[loss=0.1799, simple_loss=0.2781, pruned_loss=0.04082, over 7232.00 frames.], tot_loss[loss=0.1706, simple_loss=0.269, pruned_loss=0.03615, over 1107851.42 frames.], batch size: 20, lr: 3.57e-04
+2022-04-29 18:45:25,086 INFO [train.py:763] (0/8) Epoch 21, batch 350, loss[loss=0.1559, simple_loss=0.2628, pruned_loss=0.0245, over 7169.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2676, pruned_loss=0.03542, over 1178682.68 frames.], batch size: 19, lr: 3.57e-04
+2022-04-29 18:46:30,622 INFO [train.py:763] (0/8) Epoch 21, batch 400, loss[loss=0.1963, simple_loss=0.2996, pruned_loss=0.04652, over 7219.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2679, pruned_loss=0.0357, over 1230699.90 frames.], batch size: 21, lr: 3.57e-04
+2022-04-29 18:47:36,045 INFO [train.py:763] (0/8) Epoch 21, batch 450, loss[loss=0.2066, simple_loss=0.3014, pruned_loss=0.05587, over 5165.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2668, pruned_loss=0.03499, over 1274005.11 frames.], batch size: 52, lr: 3.57e-04
+2022-04-29 18:48:41,857 INFO [train.py:763] (0/8) Epoch 21, batch 500, loss[loss=0.1741, simple_loss=0.2837, pruned_loss=0.03228, over 7299.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2679, pruned_loss=0.03523, over 1309812.64 frames.], batch size: 25, lr: 3.57e-04
+2022-04-29 18:49:47,440 INFO [train.py:763] (0/8) Epoch 21, batch 550, loss[loss=0.1527, simple_loss=0.2464, pruned_loss=0.02949, over 7422.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2682, pruned_loss=0.03507, over 1332493.03 frames.], batch size: 20, lr: 3.57e-04
+2022-04-29 18:50:53,644 INFO [train.py:763] (0/8) Epoch 21, batch 600, loss[loss=0.1749, simple_loss=0.277, pruned_loss=0.03639, over 7346.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2665, pruned_loss=0.03467, over 1354047.84 frames.], batch size: 22, lr: 3.57e-04
+2022-04-29 18:51:58,881 INFO [train.py:763] (0/8) Epoch 21, batch 650, loss[loss=0.1901, simple_loss=0.2938, pruned_loss=0.04318, over 7344.00 frames.], tot_loss[loss=0.169, simple_loss=0.2678, pruned_loss=0.03512, over 1370401.22 frames.], batch size: 22, lr: 3.57e-04
+2022-04-29 18:53:04,515 INFO [train.py:763] (0/8) Epoch 21, batch 700, loss[loss=0.1832, simple_loss=0.2945, pruned_loss=0.03598, over 7300.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2685, pruned_loss=0.03556, over 1379278.87 frames.], batch size: 25, lr: 3.57e-04
+2022-04-29 18:54:10,373 INFO [train.py:763] (0/8) Epoch 21, batch 750, loss[loss=0.1792, simple_loss=0.2663, pruned_loss=0.04607, over 7170.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2689, pruned_loss=0.03583, over 1387061.08 frames.], batch size: 18, lr: 3.57e-04
+2022-04-29 18:55:16,601 INFO [train.py:763] (0/8) Epoch 21, batch 800, loss[loss=0.1856, simple_loss=0.2863, pruned_loss=0.04252, over 7318.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2695, pruned_loss=0.03592, over 1399551.97 frames.], batch size: 25, lr: 3.56e-04
+2022-04-29 18:56:22,308 INFO [train.py:763] (0/8) Epoch 21, batch 850, loss[loss=0.1498, simple_loss=0.2403, pruned_loss=0.02967, over 7409.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2681, pruned_loss=0.03543, over 1404933.79 frames.], batch size: 18, lr: 3.56e-04
+2022-04-29 18:57:27,460 INFO [train.py:763] (0/8) Epoch 21, batch 900, loss[loss=0.1704, simple_loss=0.272, pruned_loss=0.03436, over 6104.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2682, pruned_loss=0.03551, over 1407838.55 frames.], batch size: 37, lr: 3.56e-04
+2022-04-29 18:58:32,839 INFO [train.py:763] (0/8) Epoch 21, batch 950, loss[loss=0.1344, simple_loss=0.2285, pruned_loss=0.02015, over 7277.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2681, pruned_loss=0.03533, over 1410275.44 frames.], batch size: 18, lr: 3.56e-04
+2022-04-29 18:59:38,153 INFO [train.py:763] (0/8) Epoch 21, batch 1000, loss[loss=0.155, simple_loss=0.2642, pruned_loss=0.02284, over 7162.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2696, pruned_loss=0.03589, over 1410997.28 frames.], batch size: 19, lr: 3.56e-04
+2022-04-29 19:00:44,814 INFO [train.py:763] (0/8) Epoch 21, batch 1050, loss[loss=0.1574, simple_loss=0.2604, pruned_loss=0.02724, over 7328.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2681, pruned_loss=0.03571, over 1414722.78 frames.], batch size: 22, lr: 3.56e-04
+2022-04-29 19:01:50,758 INFO [train.py:763] (0/8) Epoch 21, batch 1100, loss[loss=0.1755, simple_loss=0.2845, pruned_loss=0.03324, over 6389.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2682, pruned_loss=0.03564, over 1418522.43 frames.], batch size: 38, lr: 3.56e-04
+2022-04-29 19:02:56,405 INFO [train.py:763] (0/8) Epoch 21, batch 1150, loss[loss=0.1626, simple_loss=0.2549, pruned_loss=0.03515, over 7257.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2687, pruned_loss=0.03573, over 1419511.17 frames.], batch size: 19, lr: 3.56e-04
+2022-04-29 19:04:02,101 INFO [train.py:763] (0/8) Epoch 21, batch 1200, loss[loss=0.1603, simple_loss=0.2545, pruned_loss=0.0331, over 7319.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2681, pruned_loss=0.03602, over 1420926.20 frames.], batch size: 25, lr: 3.56e-04
+2022-04-29 19:05:07,723 INFO [train.py:763] (0/8) Epoch 21, batch 1250, loss[loss=0.1384, simple_loss=0.231, pruned_loss=0.02287, over 7009.00 frames.], tot_loss[loss=0.1697, simple_loss=0.268, pruned_loss=0.03573, over 1419442.43 frames.], batch size: 16, lr: 3.56e-04
+2022-04-29 19:06:13,274 INFO [train.py:763] (0/8) Epoch 21, batch 1300, loss[loss=0.1588, simple_loss=0.2597, pruned_loss=0.02897, over 7150.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2679, pruned_loss=0.03576, over 1418956.51 frames.], batch size: 19, lr: 3.56e-04
+2022-04-29 19:07:19,457 INFO [train.py:763] (0/8) Epoch 21, batch 1350, loss[loss=0.1876, simple_loss=0.2883, pruned_loss=0.04349, over 7411.00 frames.], tot_loss[loss=0.1691, simple_loss=0.267, pruned_loss=0.03562, over 1423440.23 frames.], batch size: 21, lr: 3.55e-04
+2022-04-29 19:08:24,897 INFO [train.py:763] (0/8) Epoch 21, batch 1400, loss[loss=0.194, simple_loss=0.298, pruned_loss=0.04496, over 7211.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2667, pruned_loss=0.0354, over 1419770.30 frames.], batch size: 22, lr: 3.55e-04
+2022-04-29 19:09:30,412 INFO [train.py:763] (0/8) Epoch 21, batch 1450, loss[loss=0.1678, simple_loss=0.2643, pruned_loss=0.0357, over 7439.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2669, pruned_loss=0.03529, over 1424245.30 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:10:36,221 INFO [train.py:763] (0/8) Epoch 21, batch 1500, loss[loss=0.1553, simple_loss=0.2493, pruned_loss=0.03065, over 7238.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2661, pruned_loss=0.03485, over 1427365.93 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:11:42,026 INFO [train.py:763] (0/8) Epoch 21, batch 1550, loss[loss=0.1577, simple_loss=0.2685, pruned_loss=0.0235, over 7230.00 frames.], tot_loss[loss=0.168, simple_loss=0.266, pruned_loss=0.03499, over 1429555.65 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:12:47,991 INFO [train.py:763] (0/8) Epoch 21, batch 1600, loss[loss=0.1407, simple_loss=0.2312, pruned_loss=0.02504, over 6777.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2664, pruned_loss=0.0351, over 1430407.77 frames.], batch size: 15, lr: 3.55e-04
+2022-04-29 19:13:54,887 INFO [train.py:763] (0/8) Epoch 21, batch 1650, loss[loss=0.1789, simple_loss=0.2835, pruned_loss=0.03717, over 6715.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2669, pruned_loss=0.03501, over 1432272.34 frames.], batch size: 31, lr: 3.55e-04
+2022-04-29 19:15:01,841 INFO [train.py:763] (0/8) Epoch 21, batch 1700, loss[loss=0.1653, simple_loss=0.2706, pruned_loss=0.02994, over 7344.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2659, pruned_loss=0.03451, over 1434627.54 frames.], batch size: 22, lr: 3.55e-04
+2022-04-29 19:16:08,180 INFO [train.py:763] (0/8) Epoch 21, batch 1750, loss[loss=0.1886, simple_loss=0.289, pruned_loss=0.04412, over 7235.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2666, pruned_loss=0.03489, over 1433535.44 frames.], batch size: 20, lr: 3.55e-04
+2022-04-29 19:17:14,201 INFO [train.py:763] (0/8) Epoch 21, batch 1800, loss[loss=0.1317, simple_loss=0.2176, pruned_loss=0.02287, over 7289.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2655, pruned_loss=0.03488, over 1430937.87 frames.], batch size: 17, lr: 3.55e-04
+2022-04-29 19:18:19,482 INFO [train.py:763] (0/8) Epoch 21, batch 1850, loss[loss=0.1737, simple_loss=0.2759, pruned_loss=0.03578, over 6280.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2661, pruned_loss=0.03478, over 1426459.59 frames.], batch size: 37, lr: 3.55e-04
+2022-04-29 19:19:25,209 INFO [train.py:763] (0/8) Epoch 21, batch 1900, loss[loss=0.1874, simple_loss=0.2805, pruned_loss=0.0471, over 4890.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2665, pruned_loss=0.03509, over 1424590.42 frames.], batch size: 52, lr: 3.54e-04
+2022-04-29 19:20:31,953 INFO [train.py:763] (0/8) Epoch 21, batch 1950, loss[loss=0.1605, simple_loss=0.2412, pruned_loss=0.03992, over 7289.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2668, pruned_loss=0.03527, over 1425204.47 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:21:37,706 INFO [train.py:763] (0/8) Epoch 21, batch 2000, loss[loss=0.1873, simple_loss=0.294, pruned_loss=0.04027, over 7329.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2673, pruned_loss=0.03549, over 1427730.47 frames.], batch size: 20, lr: 3.54e-04
+2022-04-29 19:22:44,084 INFO [train.py:763] (0/8) Epoch 21, batch 2050, loss[loss=0.1588, simple_loss=0.2526, pruned_loss=0.03248, over 7264.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2681, pruned_loss=0.03563, over 1429067.72 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:23:50,546 INFO [train.py:763] (0/8) Epoch 21, batch 2100, loss[loss=0.158, simple_loss=0.2494, pruned_loss=0.03323, over 7427.00 frames.], tot_loss[loss=0.1703, simple_loss=0.269, pruned_loss=0.03575, over 1428230.82 frames.], batch size: 18, lr: 3.54e-04
+2022-04-29 19:24:56,277 INFO [train.py:763] (0/8) Epoch 21, batch 2150, loss[loss=0.1535, simple_loss=0.2515, pruned_loss=0.02776, over 7181.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2682, pruned_loss=0.03536, over 1424338.45 frames.], batch size: 18, lr: 3.54e-04
+2022-04-29 19:26:02,256 INFO [train.py:763] (0/8) Epoch 21, batch 2200, loss[loss=0.1848, simple_loss=0.285, pruned_loss=0.04234, over 7115.00 frames.], tot_loss[loss=0.1694, simple_loss=0.268, pruned_loss=0.03537, over 1426337.98 frames.], batch size: 21, lr: 3.54e-04
+2022-04-29 19:27:08,633 INFO [train.py:763] (0/8) Epoch 21, batch 2250, loss[loss=0.1508, simple_loss=0.2495, pruned_loss=0.02603, over 6842.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2688, pruned_loss=0.03615, over 1423704.79 frames.], batch size: 15, lr: 3.54e-04
+2022-04-29 19:28:14,985 INFO [train.py:763] (0/8) Epoch 21, batch 2300, loss[loss=0.2175, simple_loss=0.3092, pruned_loss=0.06293, over 4962.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2689, pruned_loss=0.03637, over 1425022.43 frames.], batch size: 53, lr: 3.54e-04
+2022-04-29 19:29:21,499 INFO [train.py:763] (0/8) Epoch 21, batch 2350, loss[loss=0.164, simple_loss=0.2705, pruned_loss=0.02872, over 6347.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2677, pruned_loss=0.03571, over 1426685.64 frames.], batch size: 38, lr: 3.54e-04
+2022-04-29 19:30:28,265 INFO [train.py:763] (0/8) Epoch 21, batch 2400, loss[loss=0.163, simple_loss=0.2597, pruned_loss=0.03312, over 7134.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2675, pruned_loss=0.03576, over 1426372.92 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:31:33,885 INFO [train.py:763] (0/8) Epoch 21, batch 2450, loss[loss=0.1551, simple_loss=0.2476, pruned_loss=0.03127, over 7263.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2673, pruned_loss=0.03552, over 1425068.84 frames.], batch size: 17, lr: 3.54e-04
+2022-04-29 19:32:39,522 INFO [train.py:763] (0/8) Epoch 21, batch 2500, loss[loss=0.1652, simple_loss=0.2627, pruned_loss=0.0338, over 7406.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2676, pruned_loss=0.03552, over 1423964.00 frames.], batch size: 21, lr: 3.53e-04
+2022-04-29 19:33:46,169 INFO [train.py:763] (0/8) Epoch 21, batch 2550, loss[loss=0.1921, simple_loss=0.2816, pruned_loss=0.05137, over 7064.00 frames.], tot_loss[loss=0.1699, simple_loss=0.268, pruned_loss=0.03587, over 1421901.34 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:34:52,134 INFO [train.py:763] (0/8) Epoch 21, batch 2600, loss[loss=0.152, simple_loss=0.25, pruned_loss=0.02698, over 7159.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2688, pruned_loss=0.03584, over 1417912.01 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:35:58,119 INFO [train.py:763] (0/8) Epoch 21, batch 2650, loss[loss=0.1789, simple_loss=0.2784, pruned_loss=0.03967, over 7250.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2675, pruned_loss=0.03548, over 1421390.10 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:37:03,420 INFO [train.py:763] (0/8) Epoch 21, batch 2700, loss[loss=0.1779, simple_loss=0.2615, pruned_loss=0.04718, over 7149.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2664, pruned_loss=0.03507, over 1420282.30 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:38:08,441 INFO [train.py:763] (0/8) Epoch 21, batch 2750, loss[loss=0.1671, simple_loss=0.2659, pruned_loss=0.03416, over 7065.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2669, pruned_loss=0.03509, over 1420318.54 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:39:13,889 INFO [train.py:763] (0/8) Epoch 21, batch 2800, loss[loss=0.1463, simple_loss=0.2399, pruned_loss=0.02637, over 7277.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2667, pruned_loss=0.03522, over 1420383.54 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:40:19,370 INFO [train.py:763] (0/8) Epoch 21, batch 2850, loss[loss=0.1715, simple_loss=0.2823, pruned_loss=0.03033, over 7153.00 frames.], tot_loss[loss=0.169, simple_loss=0.2669, pruned_loss=0.03554, over 1418873.03 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:41:24,562 INFO [train.py:763] (0/8) Epoch 21, batch 2900, loss[loss=0.1534, simple_loss=0.254, pruned_loss=0.02645, over 7171.00 frames.], tot_loss[loss=0.1688, simple_loss=0.267, pruned_loss=0.03532, over 1421080.44 frames.], batch size: 19, lr: 3.53e-04
+2022-04-29 19:42:30,259 INFO [train.py:763] (0/8) Epoch 21, batch 2950, loss[loss=0.1693, simple_loss=0.27, pruned_loss=0.03429, over 7424.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2669, pruned_loss=0.03585, over 1421234.05 frames.], batch size: 21, lr: 3.53e-04
+2022-04-29 19:43:36,686 INFO [train.py:763] (0/8) Epoch 21, batch 3000, loss[loss=0.1687, simple_loss=0.2514, pruned_loss=0.04302, over 7161.00 frames.], tot_loss[loss=0.1691, simple_loss=0.267, pruned_loss=0.03558, over 1424997.17 frames.], batch size: 18, lr: 3.53e-04
+2022-04-29 19:43:36,688 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 19:43:52,055 INFO [train.py:792] (0/8) Epoch 21, validation: loss=0.1676, simple_loss=0.2672, pruned_loss=0.03398, over 698248.00 frames.
+2022-04-29 19:44:57,942 INFO [train.py:763] (0/8) Epoch 21, batch 3050, loss[loss=0.2022, simple_loss=0.2917, pruned_loss=0.0564, over 7079.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2669, pruned_loss=0.03565, over 1426839.57 frames.], batch size: 28, lr: 3.52e-04
+2022-04-29 19:46:03,961 INFO [train.py:763] (0/8) Epoch 21, batch 3100, loss[loss=0.2286, simple_loss=0.3106, pruned_loss=0.07332, over 5060.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2673, pruned_loss=0.03594, over 1427349.75 frames.], batch size: 52, lr: 3.52e-04
+2022-04-29 19:47:10,171 INFO [train.py:763] (0/8) Epoch 21, batch 3150, loss[loss=0.1905, simple_loss=0.2867, pruned_loss=0.04709, over 7422.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2664, pruned_loss=0.03531, over 1424964.38 frames.], batch size: 21, lr: 3.52e-04
+2022-04-29 19:48:15,888 INFO [train.py:763] (0/8) Epoch 21, batch 3200, loss[loss=0.1648, simple_loss=0.2592, pruned_loss=0.03519, over 7068.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2664, pruned_loss=0.03505, over 1426489.42 frames.], batch size: 18, lr: 3.52e-04
+2022-04-29 19:49:21,870 INFO [train.py:763] (0/8) Epoch 21, batch 3250, loss[loss=0.1469, simple_loss=0.2366, pruned_loss=0.02861, over 7009.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2678, pruned_loss=0.03546, over 1427445.49 frames.], batch size: 16, lr: 3.52e-04
+2022-04-29 19:50:27,768 INFO [train.py:763] (0/8) Epoch 21, batch 3300, loss[loss=0.1699, simple_loss=0.2629, pruned_loss=0.03847, over 7427.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2686, pruned_loss=0.03596, over 1429396.68 frames.], batch size: 20, lr: 3.52e-04
+2022-04-29 19:51:34,104 INFO [train.py:763] (0/8) Epoch 21, batch 3350, loss[loss=0.1724, simple_loss=0.2632, pruned_loss=0.04077, over 7362.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2691, pruned_loss=0.03597, over 1428446.15 frames.], batch size: 19, lr: 3.52e-04
+2022-04-29 19:52:40,203 INFO [train.py:763] (0/8) Epoch 21, batch 3400, loss[loss=0.1619, simple_loss=0.2507, pruned_loss=0.03654, over 7143.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2686, pruned_loss=0.03599, over 1425472.47 frames.], batch size: 17, lr: 3.52e-04
+2022-04-29 19:53:45,696 INFO [train.py:763] (0/8) Epoch 21, batch 3450, loss[loss=0.203, simple_loss=0.3082, pruned_loss=0.04888, over 7333.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2695, pruned_loss=0.03618, over 1426624.71 frames.], batch size: 22, lr: 3.52e-04
+2022-04-29 19:54:51,963 INFO [train.py:763] (0/8) Epoch 21, batch 3500, loss[loss=0.1682, simple_loss=0.2744, pruned_loss=0.031, over 7332.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2688, pruned_loss=0.03583, over 1429660.53 frames.], batch size: 22, lr: 3.52e-04
+2022-04-29 19:55:58,081 INFO [train.py:763] (0/8) Epoch 21, batch 3550, loss[loss=0.1893, simple_loss=0.2943, pruned_loss=0.04214, over 6779.00 frames.], tot_loss[loss=0.1711, simple_loss=0.27, pruned_loss=0.03615, over 1427684.15 frames.], batch size: 31, lr: 3.52e-04
+2022-04-29 19:57:04,818 INFO [train.py:763] (0/8) Epoch 21, batch 3600, loss[loss=0.1565, simple_loss=0.2473, pruned_loss=0.03282, over 7298.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2698, pruned_loss=0.03655, over 1422156.55 frames.], batch size: 17, lr: 3.51e-04
+2022-04-29 19:58:10,366 INFO [train.py:763] (0/8) Epoch 21, batch 3650, loss[loss=0.1978, simple_loss=0.2979, pruned_loss=0.04887, over 7397.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2697, pruned_loss=0.03637, over 1424324.31 frames.], batch size: 23, lr: 3.51e-04
+2022-04-29 19:59:15,687 INFO [train.py:763] (0/8) Epoch 21, batch 3700, loss[loss=0.1677, simple_loss=0.2821, pruned_loss=0.02671, over 7222.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2692, pruned_loss=0.03598, over 1426279.99 frames.], batch size: 21, lr: 3.51e-04
+2022-04-29 20:00:21,235 INFO [train.py:763] (0/8) Epoch 21, batch 3750, loss[loss=0.1512, simple_loss=0.2416, pruned_loss=0.03043, over 6998.00 frames.], tot_loss[loss=0.17, simple_loss=0.2684, pruned_loss=0.03578, over 1430742.17 frames.], batch size: 16, lr: 3.51e-04
+2022-04-29 20:01:26,924 INFO [train.py:763] (0/8) Epoch 21, batch 3800, loss[loss=0.2062, simple_loss=0.291, pruned_loss=0.06067, over 4820.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2678, pruned_loss=0.03576, over 1424706.90 frames.], batch size: 52, lr: 3.51e-04
+2022-04-29 20:02:32,215 INFO [train.py:763] (0/8) Epoch 21, batch 3850, loss[loss=0.1861, simple_loss=0.284, pruned_loss=0.04414, over 7224.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2681, pruned_loss=0.03559, over 1427519.22 frames.], batch size: 20, lr: 3.51e-04
+2022-04-29 20:03:37,835 INFO [train.py:763] (0/8) Epoch 21, batch 3900, loss[loss=0.1643, simple_loss=0.2691, pruned_loss=0.02979, over 6296.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2678, pruned_loss=0.03544, over 1427660.22 frames.], batch size: 37, lr: 3.51e-04
+2022-04-29 20:04:43,334 INFO [train.py:763] (0/8) Epoch 21, batch 3950, loss[loss=0.1304, simple_loss=0.2269, pruned_loss=0.01698, over 7273.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2668, pruned_loss=0.03502, over 1425637.83 frames.], batch size: 17, lr: 3.51e-04
+2022-04-29 20:05:50,735 INFO [train.py:763] (0/8) Epoch 21, batch 4000, loss[loss=0.153, simple_loss=0.2623, pruned_loss=0.02187, over 7318.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2681, pruned_loss=0.03537, over 1425230.95 frames.], batch size: 21, lr: 3.51e-04
+2022-04-29 20:06:57,093 INFO [train.py:763] (0/8) Epoch 21, batch 4050, loss[loss=0.1564, simple_loss=0.2564, pruned_loss=0.02823, over 7347.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2675, pruned_loss=0.03506, over 1423339.48 frames.], batch size: 19, lr: 3.51e-04
+2022-04-29 20:08:02,550 INFO [train.py:763] (0/8) Epoch 21, batch 4100, loss[loss=0.1389, simple_loss=0.2444, pruned_loss=0.01667, over 7318.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2686, pruned_loss=0.03555, over 1425126.73 frames.], batch size: 20, lr: 3.51e-04
+2022-04-29 20:09:08,420 INFO [train.py:763] (0/8) Epoch 21, batch 4150, loss[loss=0.1642, simple_loss=0.2649, pruned_loss=0.03177, over 7070.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2674, pruned_loss=0.03539, over 1419445.19 frames.], batch size: 18, lr: 3.51e-04
+2022-04-29 20:10:23,433 INFO [train.py:763] (0/8) Epoch 21, batch 4200, loss[loss=0.1688, simple_loss=0.2736, pruned_loss=0.03199, over 7148.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2679, pruned_loss=0.03549, over 1414960.84 frames.], batch size: 20, lr: 3.50e-04
+2022-04-29 20:11:28,560 INFO [train.py:763] (0/8) Epoch 21, batch 4250, loss[loss=0.1594, simple_loss=0.2654, pruned_loss=0.02669, over 6786.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2692, pruned_loss=0.03611, over 1408503.89 frames.], batch size: 31, lr: 3.50e-04
+2022-04-29 20:12:34,561 INFO [train.py:763] (0/8) Epoch 21, batch 4300, loss[loss=0.1764, simple_loss=0.2823, pruned_loss=0.03526, over 7289.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2693, pruned_loss=0.03593, over 1410659.12 frames.], batch size: 24, lr: 3.50e-04
+2022-04-29 20:13:40,103 INFO [train.py:763] (0/8) Epoch 21, batch 4350, loss[loss=0.1767, simple_loss=0.277, pruned_loss=0.03817, over 7336.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2695, pruned_loss=0.03604, over 1407820.43 frames.], batch size: 22, lr: 3.50e-04
+2022-04-29 20:14:45,328 INFO [train.py:763] (0/8) Epoch 21, batch 4400, loss[loss=0.1645, simple_loss=0.2595, pruned_loss=0.03477, over 7113.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2693, pruned_loss=0.03569, over 1403059.59 frames.], batch size: 21, lr: 3.50e-04
+2022-04-29 20:15:50,791 INFO [train.py:763] (0/8) Epoch 21, batch 4450, loss[loss=0.1768, simple_loss=0.2863, pruned_loss=0.03369, over 7347.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2699, pruned_loss=0.03632, over 1398735.89 frames.], batch size: 22, lr: 3.50e-04
+2022-04-29 20:17:22,862 INFO [train.py:763] (0/8) Epoch 21, batch 4500, loss[loss=0.184, simple_loss=0.2835, pruned_loss=0.04222, over 7076.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2718, pruned_loss=0.03759, over 1388719.78 frames.], batch size: 28, lr: 3.50e-04
+2022-04-29 20:18:27,313 INFO [train.py:763] (0/8) Epoch 21, batch 4550, loss[loss=0.2039, simple_loss=0.2828, pruned_loss=0.06254, over 4891.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2738, pruned_loss=0.03882, over 1349490.90 frames.], batch size: 53, lr: 3.50e-04
+2022-04-29 20:19:44,642 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-21.pt
+2022-04-29 20:20:15,522 INFO [train.py:763] (0/8) Epoch 22, batch 0, loss[loss=0.1807, simple_loss=0.2543, pruned_loss=0.0535, over 6831.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2543, pruned_loss=0.0535, over 6831.00 frames.], batch size: 15, lr: 3.42e-04
+2022-04-29 20:21:30,529 INFO [train.py:763] (0/8) Epoch 22, batch 50, loss[loss=0.1845, simple_loss=0.2806, pruned_loss=0.04422, over 7153.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2694, pruned_loss=0.03754, over 319144.94 frames.], batch size: 19, lr: 3.42e-04
+2022-04-29 20:22:35,945 INFO [train.py:763] (0/8) Epoch 22, batch 100, loss[loss=0.1468, simple_loss=0.2432, pruned_loss=0.02521, over 7280.00 frames.], tot_loss[loss=0.171, simple_loss=0.2696, pruned_loss=0.03623, over 566358.21 frames.], batch size: 18, lr: 3.42e-04
+2022-04-29 20:23:41,424 INFO [train.py:763] (0/8) Epoch 22, batch 150, loss[loss=0.1803, simple_loss=0.2855, pruned_loss=0.03757, over 7281.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2704, pruned_loss=0.03619, over 753487.48 frames.], batch size: 24, lr: 3.42e-04
+2022-04-29 20:24:46,886 INFO [train.py:763] (0/8) Epoch 22, batch 200, loss[loss=0.1718, simple_loss=0.2794, pruned_loss=0.03214, over 6492.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2698, pruned_loss=0.03543, over 901800.17 frames.], batch size: 38, lr: 3.42e-04
+2022-04-29 20:25:52,445 INFO [train.py:763] (0/8) Epoch 22, batch 250, loss[loss=0.1981, simple_loss=0.3011, pruned_loss=0.04761, over 7189.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2698, pruned_loss=0.03536, over 1017299.80 frames.], batch size: 23, lr: 3.42e-04
+2022-04-29 20:26:58,037 INFO [train.py:763] (0/8) Epoch 22, batch 300, loss[loss=0.1491, simple_loss=0.2434, pruned_loss=0.02738, over 7162.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2696, pruned_loss=0.03585, over 1103117.33 frames.], batch size: 19, lr: 3.42e-04
+2022-04-29 20:28:05,357 INFO [train.py:763] (0/8) Epoch 22, batch 350, loss[loss=0.1491, simple_loss=0.249, pruned_loss=0.02464, over 7330.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2687, pruned_loss=0.03519, over 1178305.47 frames.], batch size: 22, lr: 3.42e-04
+2022-04-29 20:29:12,809 INFO [train.py:763] (0/8) Epoch 22, batch 400, loss[loss=0.1669, simple_loss=0.2584, pruned_loss=0.03768, over 7205.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2681, pruned_loss=0.03524, over 1232074.92 frames.], batch size: 23, lr: 3.42e-04
+2022-04-29 20:30:18,206 INFO [train.py:763] (0/8) Epoch 22, batch 450, loss[loss=0.1742, simple_loss=0.2776, pruned_loss=0.03543, over 7292.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2686, pruned_loss=0.03538, over 1273365.67 frames.], batch size: 24, lr: 3.42e-04
+2022-04-29 20:31:24,307 INFO [train.py:763] (0/8) Epoch 22, batch 500, loss[loss=0.156, simple_loss=0.2473, pruned_loss=0.03239, over 6812.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2681, pruned_loss=0.03513, over 1308037.04 frames.], batch size: 15, lr: 3.41e-04
+2022-04-29 20:32:31,789 INFO [train.py:763] (0/8) Epoch 22, batch 550, loss[loss=0.1856, simple_loss=0.2917, pruned_loss=0.03975, over 7296.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2669, pruned_loss=0.03492, over 1337363.80 frames.], batch size: 24, lr: 3.41e-04
+2022-04-29 20:33:39,043 INFO [train.py:763] (0/8) Epoch 22, batch 600, loss[loss=0.1961, simple_loss=0.3012, pruned_loss=0.04552, over 7127.00 frames.], tot_loss[loss=0.169, simple_loss=0.2677, pruned_loss=0.03515, over 1359853.02 frames.], batch size: 21, lr: 3.41e-04
+2022-04-29 20:34:44,746 INFO [train.py:763] (0/8) Epoch 22, batch 650, loss[loss=0.1678, simple_loss=0.2699, pruned_loss=0.03284, over 6769.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2687, pruned_loss=0.03541, over 1374797.18 frames.], batch size: 31, lr: 3.41e-04
+2022-04-29 20:35:51,887 INFO [train.py:763] (0/8) Epoch 22, batch 700, loss[loss=0.2171, simple_loss=0.3159, pruned_loss=0.0591, over 5221.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2681, pruned_loss=0.03516, over 1380539.73 frames.], batch size: 53, lr: 3.41e-04
+2022-04-29 20:36:59,165 INFO [train.py:763] (0/8) Epoch 22, batch 750, loss[loss=0.171, simple_loss=0.2755, pruned_loss=0.03326, over 7195.00 frames.], tot_loss[loss=0.17, simple_loss=0.2689, pruned_loss=0.03549, over 1391784.03 frames.], batch size: 23, lr: 3.41e-04
+2022-04-29 20:38:05,937 INFO [train.py:763] (0/8) Epoch 22, batch 800, loss[loss=0.1583, simple_loss=0.2558, pruned_loss=0.0304, over 7366.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2691, pruned_loss=0.03582, over 1395946.46 frames.], batch size: 19, lr: 3.41e-04
+2022-04-29 20:39:11,699 INFO [train.py:763] (0/8) Epoch 22, batch 850, loss[loss=0.1788, simple_loss=0.2746, pruned_loss=0.04148, over 7442.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2692, pruned_loss=0.03597, over 1404552.63 frames.], batch size: 20, lr: 3.41e-04
+2022-04-29 20:40:16,918 INFO [train.py:763] (0/8) Epoch 22, batch 900, loss[loss=0.1553, simple_loss=0.2512, pruned_loss=0.02968, over 7153.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2693, pruned_loss=0.03586, over 1408397.25 frames.], batch size: 19, lr: 3.41e-04
+2022-04-29 20:41:22,125 INFO [train.py:763] (0/8) Epoch 22, batch 950, loss[loss=0.1833, simple_loss=0.2885, pruned_loss=0.03903, over 6969.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2692, pruned_loss=0.03572, over 1410585.17 frames.], batch size: 28, lr: 3.41e-04
+2022-04-29 20:42:27,348 INFO [train.py:763] (0/8) Epoch 22, batch 1000, loss[loss=0.1753, simple_loss=0.2732, pruned_loss=0.03868, over 7350.00 frames.], tot_loss[loss=0.169, simple_loss=0.2682, pruned_loss=0.03486, over 1417766.14 frames.], batch size: 19, lr: 3.41e-04
+2022-04-29 20:43:32,809 INFO [train.py:763] (0/8) Epoch 22, batch 1050, loss[loss=0.1761, simple_loss=0.2737, pruned_loss=0.03927, over 5226.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2676, pruned_loss=0.03485, over 1419003.19 frames.], batch size: 52, lr: 3.41e-04
+2022-04-29 20:44:37,792 INFO [train.py:763] (0/8) Epoch 22, batch 1100, loss[loss=0.164, simple_loss=0.252, pruned_loss=0.03799, over 7282.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2687, pruned_loss=0.03523, over 1418438.58 frames.], batch size: 17, lr: 3.40e-04
+2022-04-29 20:45:43,164 INFO [train.py:763] (0/8) Epoch 22, batch 1150, loss[loss=0.1806, simple_loss=0.2843, pruned_loss=0.03845, over 7417.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2693, pruned_loss=0.03544, over 1421882.88 frames.], batch size: 20, lr: 3.40e-04
+2022-04-29 20:46:49,115 INFO [train.py:763] (0/8) Epoch 22, batch 1200, loss[loss=0.1504, simple_loss=0.2419, pruned_loss=0.02945, over 7283.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2691, pruned_loss=0.03529, over 1420311.36 frames.], batch size: 18, lr: 3.40e-04
+2022-04-29 20:47:55,639 INFO [train.py:763] (0/8) Epoch 22, batch 1250, loss[loss=0.1374, simple_loss=0.2286, pruned_loss=0.02314, over 6797.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2676, pruned_loss=0.03484, over 1423288.92 frames.], batch size: 15, lr: 3.40e-04
+2022-04-29 20:49:00,853 INFO [train.py:763] (0/8) Epoch 22, batch 1300, loss[loss=0.1672, simple_loss=0.2692, pruned_loss=0.03256, over 7192.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2666, pruned_loss=0.03448, over 1426270.77 frames.], batch size: 23, lr: 3.40e-04
+2022-04-29 20:50:07,496 INFO [train.py:763] (0/8) Epoch 22, batch 1350, loss[loss=0.1748, simple_loss=0.2623, pruned_loss=0.04368, over 7279.00 frames.], tot_loss[loss=0.168, simple_loss=0.2665, pruned_loss=0.03479, over 1426847.86 frames.], batch size: 18, lr: 3.40e-04
+2022-04-29 20:51:13,808 INFO [train.py:763] (0/8) Epoch 22, batch 1400, loss[loss=0.1695, simple_loss=0.2848, pruned_loss=0.02712, over 7124.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2669, pruned_loss=0.03516, over 1426596.17 frames.], batch size: 21, lr: 3.40e-04
+2022-04-29 20:52:19,588 INFO [train.py:763] (0/8) Epoch 22, batch 1450, loss[loss=0.1642, simple_loss=0.254, pruned_loss=0.03717, over 7419.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2672, pruned_loss=0.03548, over 1421239.71 frames.], batch size: 18, lr: 3.40e-04
+2022-04-29 20:53:25,454 INFO [train.py:763] (0/8) Epoch 22, batch 1500, loss[loss=0.1809, simple_loss=0.2816, pruned_loss=0.04011, over 7128.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2664, pruned_loss=0.03526, over 1423140.51 frames.], batch size: 28, lr: 3.40e-04
+2022-04-29 20:54:31,431 INFO [train.py:763] (0/8) Epoch 22, batch 1550, loss[loss=0.1456, simple_loss=0.2416, pruned_loss=0.02482, over 7365.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2668, pruned_loss=0.03568, over 1412712.99 frames.], batch size: 19, lr: 3.40e-04
+2022-04-29 20:55:37,835 INFO [train.py:763] (0/8) Epoch 22, batch 1600, loss[loss=0.1714, simple_loss=0.2812, pruned_loss=0.03083, over 7225.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2677, pruned_loss=0.03628, over 1411266.82 frames.], batch size: 21, lr: 3.40e-04
+2022-04-29 20:56:43,438 INFO [train.py:763] (0/8) Epoch 22, batch 1650, loss[loss=0.2225, simple_loss=0.3157, pruned_loss=0.06467, over 7393.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2668, pruned_loss=0.03568, over 1414624.78 frames.], batch size: 23, lr: 3.40e-04
+2022-04-29 20:57:48,944 INFO [train.py:763] (0/8) Epoch 22, batch 1700, loss[loss=0.1341, simple_loss=0.2311, pruned_loss=0.01859, over 7422.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2671, pruned_loss=0.03535, over 1415528.43 frames.], batch size: 18, lr: 3.39e-04
+2022-04-29 20:58:54,074 INFO [train.py:763] (0/8) Epoch 22, batch 1750, loss[loss=0.1906, simple_loss=0.2817, pruned_loss=0.04975, over 7203.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2678, pruned_loss=0.03578, over 1414458.33 frames.], batch size: 26, lr: 3.39e-04
+2022-04-29 20:59:59,912 INFO [train.py:763] (0/8) Epoch 22, batch 1800, loss[loss=0.2163, simple_loss=0.3086, pruned_loss=0.06199, over 5003.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2679, pruned_loss=0.03565, over 1412433.99 frames.], batch size: 52, lr: 3.39e-04
+2022-04-29 21:01:05,544 INFO [train.py:763] (0/8) Epoch 22, batch 1850, loss[loss=0.1441, simple_loss=0.2494, pruned_loss=0.01937, over 7426.00 frames.], tot_loss[loss=0.169, simple_loss=0.2673, pruned_loss=0.03531, over 1417407.50 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:02:10,919 INFO [train.py:763] (0/8) Epoch 22, batch 1900, loss[loss=0.1943, simple_loss=0.3055, pruned_loss=0.0416, over 7141.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2669, pruned_loss=0.03513, over 1420728.23 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:03:17,157 INFO [train.py:763] (0/8) Epoch 22, batch 1950, loss[loss=0.1663, simple_loss=0.2805, pruned_loss=0.02605, over 7135.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2668, pruned_loss=0.03508, over 1417996.39 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:04:22,507 INFO [train.py:763] (0/8) Epoch 22, batch 2000, loss[loss=0.1877, simple_loss=0.2788, pruned_loss=0.04826, over 7255.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2683, pruned_loss=0.0355, over 1421440.52 frames.], batch size: 19, lr: 3.39e-04
+2022-04-29 21:05:28,511 INFO [train.py:763] (0/8) Epoch 22, batch 2050, loss[loss=0.1611, simple_loss=0.2662, pruned_loss=0.02802, over 7231.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2672, pruned_loss=0.03476, over 1425718.46 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:06:35,655 INFO [train.py:763] (0/8) Epoch 22, batch 2100, loss[loss=0.2021, simple_loss=0.3085, pruned_loss=0.04784, over 7185.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2666, pruned_loss=0.0344, over 1420599.49 frames.], batch size: 23, lr: 3.39e-04
+2022-04-29 21:07:42,151 INFO [train.py:763] (0/8) Epoch 22, batch 2150, loss[loss=0.1649, simple_loss=0.2648, pruned_loss=0.03252, over 7154.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2668, pruned_loss=0.03443, over 1422038.72 frames.], batch size: 19, lr: 3.39e-04
+2022-04-29 21:08:47,300 INFO [train.py:763] (0/8) Epoch 22, batch 2200, loss[loss=0.1831, simple_loss=0.2824, pruned_loss=0.04191, over 7151.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2665, pruned_loss=0.03448, over 1417740.25 frames.], batch size: 20, lr: 3.39e-04
+2022-04-29 21:09:53,564 INFO [train.py:763] (0/8) Epoch 22, batch 2250, loss[loss=0.2066, simple_loss=0.2953, pruned_loss=0.05896, over 7164.00 frames.], tot_loss[loss=0.1685, simple_loss=0.267, pruned_loss=0.03501, over 1413438.38 frames.], batch size: 19, lr: 3.39e-04
+2022-04-29 21:11:00,718 INFO [train.py:763] (0/8) Epoch 22, batch 2300, loss[loss=0.1715, simple_loss=0.2786, pruned_loss=0.03218, over 7320.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2661, pruned_loss=0.03503, over 1414710.13 frames.], batch size: 21, lr: 3.38e-04
+2022-04-29 21:12:07,642 INFO [train.py:763] (0/8) Epoch 22, batch 2350, loss[loss=0.16, simple_loss=0.2659, pruned_loss=0.027, over 7333.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2666, pruned_loss=0.03504, over 1416387.23 frames.], batch size: 22, lr: 3.38e-04
+2022-04-29 21:13:14,357 INFO [train.py:763] (0/8) Epoch 22, batch 2400, loss[loss=0.173, simple_loss=0.2757, pruned_loss=0.03515, over 7294.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2674, pruned_loss=0.03492, over 1419328.75 frames.], batch size: 24, lr: 3.38e-04
+2022-04-29 21:14:19,607 INFO [train.py:763] (0/8) Epoch 22, batch 2450, loss[loss=0.2106, simple_loss=0.2967, pruned_loss=0.06228, over 7195.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2682, pruned_loss=0.03539, over 1423216.19 frames.], batch size: 22, lr: 3.38e-04
+2022-04-29 21:15:24,886 INFO [train.py:763] (0/8) Epoch 22, batch 2500, loss[loss=0.153, simple_loss=0.2565, pruned_loss=0.02474, over 6631.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2673, pruned_loss=0.03521, over 1421043.91 frames.], batch size: 38, lr: 3.38e-04
+2022-04-29 21:16:30,049 INFO [train.py:763] (0/8) Epoch 22, batch 2550, loss[loss=0.1587, simple_loss=0.2636, pruned_loss=0.02689, over 7387.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2674, pruned_loss=0.03543, over 1422011.48 frames.], batch size: 23, lr: 3.38e-04
+2022-04-29 21:17:35,662 INFO [train.py:763] (0/8) Epoch 22, batch 2600, loss[loss=0.1627, simple_loss=0.2692, pruned_loss=0.02805, over 7327.00 frames.], tot_loss[loss=0.1686, simple_loss=0.267, pruned_loss=0.03504, over 1426186.46 frames.], batch size: 22, lr: 3.38e-04
+2022-04-29 21:18:41,160 INFO [train.py:763] (0/8) Epoch 22, batch 2650, loss[loss=0.1823, simple_loss=0.2819, pruned_loss=0.04142, over 7292.00 frames.], tot_loss[loss=0.1668, simple_loss=0.265, pruned_loss=0.0343, over 1423481.88 frames.], batch size: 25, lr: 3.38e-04
+2022-04-29 21:19:46,689 INFO [train.py:763] (0/8) Epoch 22, batch 2700, loss[loss=0.1509, simple_loss=0.2623, pruned_loss=0.01972, over 7163.00 frames.], tot_loss[loss=0.1675, simple_loss=0.266, pruned_loss=0.03447, over 1422724.69 frames.], batch size: 19, lr: 3.38e-04
+2022-04-29 21:20:54,050 INFO [train.py:763] (0/8) Epoch 22, batch 2750, loss[loss=0.1812, simple_loss=0.2657, pruned_loss=0.04839, over 7156.00 frames.], tot_loss[loss=0.1679, simple_loss=0.266, pruned_loss=0.0349, over 1421110.76 frames.], batch size: 18, lr: 3.38e-04
+2022-04-29 21:22:00,033 INFO [train.py:763] (0/8) Epoch 22, batch 2800, loss[loss=0.1436, simple_loss=0.2373, pruned_loss=0.02489, over 7160.00 frames.], tot_loss[loss=0.168, simple_loss=0.2659, pruned_loss=0.03506, over 1420433.44 frames.], batch size: 18, lr: 3.38e-04
+2022-04-29 21:23:05,441 INFO [train.py:763] (0/8) Epoch 22, batch 2850, loss[loss=0.1778, simple_loss=0.2921, pruned_loss=0.03179, over 7089.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2657, pruned_loss=0.03502, over 1421667.61 frames.], batch size: 28, lr: 3.38e-04
+2022-04-29 21:24:10,667 INFO [train.py:763] (0/8) Epoch 22, batch 2900, loss[loss=0.1773, simple_loss=0.2907, pruned_loss=0.03195, over 7339.00 frames.], tot_loss[loss=0.1689, simple_loss=0.267, pruned_loss=0.03538, over 1423706.22 frames.], batch size: 25, lr: 3.37e-04
+2022-04-29 21:25:15,972 INFO [train.py:763] (0/8) Epoch 22, batch 2950, loss[loss=0.1838, simple_loss=0.2907, pruned_loss=0.03841, over 7217.00 frames.], tot_loss[loss=0.169, simple_loss=0.2674, pruned_loss=0.0353, over 1424099.84 frames.], batch size: 22, lr: 3.37e-04
+2022-04-29 21:26:20,977 INFO [train.py:763] (0/8) Epoch 22, batch 3000, loss[loss=0.1336, simple_loss=0.224, pruned_loss=0.02163, over 7007.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2671, pruned_loss=0.03509, over 1424288.99 frames.], batch size: 16, lr: 3.37e-04
+2022-04-29 21:26:20,979 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 21:26:36,379 INFO [train.py:792] (0/8) Epoch 22, validation: loss=0.1681, simple_loss=0.2667, pruned_loss=0.03474, over 698248.00 frames.
+2022-04-29 21:27:41,679 INFO [train.py:763] (0/8) Epoch 22, batch 3050, loss[loss=0.1657, simple_loss=0.2714, pruned_loss=0.03004, over 7160.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2672, pruned_loss=0.03505, over 1426825.46 frames.], batch size: 19, lr: 3.37e-04
+2022-04-29 21:27:58,677 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-104000.pt
+2022-04-29 21:28:58,465 INFO [train.py:763] (0/8) Epoch 22, batch 3100, loss[loss=0.175, simple_loss=0.278, pruned_loss=0.03604, over 7234.00 frames.], tot_loss[loss=0.168, simple_loss=0.2664, pruned_loss=0.03477, over 1426052.01 frames.], batch size: 20, lr: 3.37e-04
+2022-04-29 21:30:03,951 INFO [train.py:763] (0/8) Epoch 22, batch 3150, loss[loss=0.1709, simple_loss=0.2785, pruned_loss=0.03164, over 7324.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2663, pruned_loss=0.03462, over 1427570.22 frames.], batch size: 20, lr: 3.37e-04
+2022-04-29 21:31:09,279 INFO [train.py:763] (0/8) Epoch 22, batch 3200, loss[loss=0.1867, simple_loss=0.2902, pruned_loss=0.04159, over 7115.00 frames.], tot_loss[loss=0.1686, simple_loss=0.267, pruned_loss=0.03507, over 1427908.72 frames.], batch size: 21, lr: 3.37e-04
+2022-04-29 21:32:14,553 INFO [train.py:763] (0/8) Epoch 22, batch 3250, loss[loss=0.1819, simple_loss=0.2805, pruned_loss=0.04168, over 6367.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2671, pruned_loss=0.03538, over 1422452.36 frames.], batch size: 37, lr: 3.37e-04
+2022-04-29 21:33:19,832 INFO [train.py:763] (0/8) Epoch 22, batch 3300, loss[loss=0.1943, simple_loss=0.2826, pruned_loss=0.05301, over 7311.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2681, pruned_loss=0.03541, over 1422797.82 frames.], batch size: 24, lr: 3.37e-04
+2022-04-29 21:34:25,359 INFO [train.py:763] (0/8) Epoch 22, batch 3350, loss[loss=0.2007, simple_loss=0.3018, pruned_loss=0.04983, over 7239.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2671, pruned_loss=0.03521, over 1427288.01 frames.], batch size: 26, lr: 3.37e-04
+2022-04-29 21:35:30,554 INFO [train.py:763] (0/8) Epoch 22, batch 3400, loss[loss=0.1518, simple_loss=0.2537, pruned_loss=0.02489, over 7159.00 frames.], tot_loss[loss=0.1684, simple_loss=0.267, pruned_loss=0.03493, over 1428367.65 frames.], batch size: 19, lr: 3.37e-04
+2022-04-29 21:36:36,040 INFO [train.py:763] (0/8) Epoch 22, batch 3450, loss[loss=0.1367, simple_loss=0.2318, pruned_loss=0.02078, over 6876.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2656, pruned_loss=0.03454, over 1429829.15 frames.], batch size: 15, lr: 3.37e-04
+2022-04-29 21:37:41,471 INFO [train.py:763] (0/8) Epoch 22, batch 3500, loss[loss=0.1482, simple_loss=0.2335, pruned_loss=0.03144, over 6838.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2656, pruned_loss=0.03447, over 1430769.79 frames.], batch size: 15, lr: 3.37e-04
+2022-04-29 21:38:46,766 INFO [train.py:763] (0/8) Epoch 22, batch 3550, loss[loss=0.1699, simple_loss=0.257, pruned_loss=0.04136, over 7429.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2657, pruned_loss=0.03472, over 1430882.78 frames.], batch size: 18, lr: 3.36e-04
+2022-04-29 21:39:52,009 INFO [train.py:763] (0/8) Epoch 22, batch 3600, loss[loss=0.1345, simple_loss=0.2231, pruned_loss=0.02299, over 7284.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2677, pruned_loss=0.03525, over 1431961.95 frames.], batch size: 17, lr: 3.36e-04
+2022-04-29 21:40:57,420 INFO [train.py:763] (0/8) Epoch 22, batch 3650, loss[loss=0.1724, simple_loss=0.2696, pruned_loss=0.03764, over 6416.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2683, pruned_loss=0.03539, over 1431868.00 frames.], batch size: 37, lr: 3.36e-04
+2022-04-29 21:42:03,794 INFO [train.py:763] (0/8) Epoch 22, batch 3700, loss[loss=0.1578, simple_loss=0.2527, pruned_loss=0.03141, over 7157.00 frames.], tot_loss[loss=0.1692, simple_loss=0.268, pruned_loss=0.03521, over 1430208.91 frames.], batch size: 19, lr: 3.36e-04
+2022-04-29 21:43:09,200 INFO [train.py:763] (0/8) Epoch 22, batch 3750, loss[loss=0.1266, simple_loss=0.2263, pruned_loss=0.01343, over 7295.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2679, pruned_loss=0.03486, over 1427791.24 frames.], batch size: 17, lr: 3.36e-04
+2022-04-29 21:44:14,443 INFO [train.py:763] (0/8) Epoch 22, batch 3800, loss[loss=0.1473, simple_loss=0.2473, pruned_loss=0.02359, over 7377.00 frames.], tot_loss[loss=0.169, simple_loss=0.2679, pruned_loss=0.03503, over 1428926.03 frames.], batch size: 23, lr: 3.36e-04
+2022-04-29 21:45:19,948 INFO [train.py:763] (0/8) Epoch 22, batch 3850, loss[loss=0.1934, simple_loss=0.2919, pruned_loss=0.04746, over 6987.00 frames.], tot_loss[loss=0.169, simple_loss=0.2676, pruned_loss=0.03514, over 1429675.08 frames.], batch size: 28, lr: 3.36e-04
+2022-04-29 21:46:26,376 INFO [train.py:763] (0/8) Epoch 22, batch 3900, loss[loss=0.2026, simple_loss=0.3008, pruned_loss=0.0522, over 7441.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2679, pruned_loss=0.03541, over 1430184.95 frames.], batch size: 22, lr: 3.36e-04
+2022-04-29 21:47:31,496 INFO [train.py:763] (0/8) Epoch 22, batch 3950, loss[loss=0.1604, simple_loss=0.2512, pruned_loss=0.0348, over 7171.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2677, pruned_loss=0.03522, over 1429810.98 frames.], batch size: 19, lr: 3.36e-04
+2022-04-29 21:48:36,601 INFO [train.py:763] (0/8) Epoch 22, batch 4000, loss[loss=0.1604, simple_loss=0.2502, pruned_loss=0.03533, over 7253.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2677, pruned_loss=0.03546, over 1426185.15 frames.], batch size: 17, lr: 3.36e-04
+2022-04-29 21:49:42,514 INFO [train.py:763] (0/8) Epoch 22, batch 4050, loss[loss=0.1505, simple_loss=0.2358, pruned_loss=0.03259, over 7171.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2684, pruned_loss=0.03595, over 1421318.61 frames.], batch size: 16, lr: 3.36e-04
+2022-04-29 21:50:49,123 INFO [train.py:763] (0/8) Epoch 22, batch 4100, loss[loss=0.1438, simple_loss=0.2327, pruned_loss=0.02744, over 7247.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2682, pruned_loss=0.03634, over 1417674.42 frames.], batch size: 16, lr: 3.36e-04
+2022-04-29 21:51:54,122 INFO [train.py:763] (0/8) Epoch 22, batch 4150, loss[loss=0.1876, simple_loss=0.2898, pruned_loss=0.04269, over 7324.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2684, pruned_loss=0.03591, over 1416288.77 frames.], batch size: 21, lr: 3.35e-04
+2022-04-29 21:52:59,310 INFO [train.py:763] (0/8) Epoch 22, batch 4200, loss[loss=0.1358, simple_loss=0.232, pruned_loss=0.01981, over 7008.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2681, pruned_loss=0.03554, over 1420829.92 frames.], batch size: 16, lr: 3.35e-04
+2022-04-29 21:54:05,494 INFO [train.py:763] (0/8) Epoch 22, batch 4250, loss[loss=0.1725, simple_loss=0.278, pruned_loss=0.03344, over 7233.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2679, pruned_loss=0.03545, over 1422424.20 frames.], batch size: 20, lr: 3.35e-04
+2022-04-29 21:55:12,491 INFO [train.py:763] (0/8) Epoch 22, batch 4300, loss[loss=0.1429, simple_loss=0.2414, pruned_loss=0.02218, over 7149.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2659, pruned_loss=0.03512, over 1419424.74 frames.], batch size: 18, lr: 3.35e-04
+2022-04-29 21:56:19,743 INFO [train.py:763] (0/8) Epoch 22, batch 4350, loss[loss=0.1496, simple_loss=0.2432, pruned_loss=0.028, over 7260.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2657, pruned_loss=0.03504, over 1421305.70 frames.], batch size: 16, lr: 3.35e-04
+2022-04-29 21:57:26,794 INFO [train.py:763] (0/8) Epoch 22, batch 4400, loss[loss=0.1563, simple_loss=0.2545, pruned_loss=0.02907, over 7069.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2653, pruned_loss=0.03486, over 1419064.73 frames.], batch size: 18, lr: 3.35e-04
+2022-04-29 21:58:31,948 INFO [train.py:763] (0/8) Epoch 22, batch 4450, loss[loss=0.2282, simple_loss=0.3174, pruned_loss=0.0695, over 5269.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2661, pruned_loss=0.03509, over 1413310.72 frames.], batch size: 52, lr: 3.35e-04
+2022-04-29 21:59:36,922 INFO [train.py:763] (0/8) Epoch 22, batch 4500, loss[loss=0.1466, simple_loss=0.2425, pruned_loss=0.02539, over 7063.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2663, pruned_loss=0.03527, over 1412686.54 frames.], batch size: 18, lr: 3.35e-04
+2022-04-29 22:00:41,215 INFO [train.py:763] (0/8) Epoch 22, batch 4550, loss[loss=0.1923, simple_loss=0.286, pruned_loss=0.0493, over 5257.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2697, pruned_loss=0.03744, over 1356591.00 frames.], batch size: 52, lr: 3.35e-04
+2022-04-29 22:01:30,621 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-22.pt
+2022-04-29 22:02:00,636 INFO [train.py:763] (0/8) Epoch 23, batch 0, loss[loss=0.1525, simple_loss=0.244, pruned_loss=0.03048, over 6826.00 frames.], tot_loss[loss=0.1525, simple_loss=0.244, pruned_loss=0.03048, over 6826.00 frames.], batch size: 15, lr: 3.28e-04
+2022-04-29 22:03:02,946 INFO [train.py:763] (0/8) Epoch 23, batch 50, loss[loss=0.1331, simple_loss=0.2282, pruned_loss=0.01896, over 7280.00 frames.], tot_loss[loss=0.168, simple_loss=0.2665, pruned_loss=0.03475, over 316699.52 frames.], batch size: 17, lr: 3.28e-04
+2022-04-29 22:04:05,012 INFO [train.py:763] (0/8) Epoch 23, batch 100, loss[loss=0.1771, simple_loss=0.2746, pruned_loss=0.03974, over 7335.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2662, pruned_loss=0.03339, over 567132.79 frames.], batch size: 20, lr: 3.28e-04
+2022-04-29 22:05:10,559 INFO [train.py:763] (0/8) Epoch 23, batch 150, loss[loss=0.1812, simple_loss=0.2799, pruned_loss=0.04124, over 7383.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2676, pruned_loss=0.03411, over 752744.06 frames.], batch size: 23, lr: 3.28e-04
+2022-04-29 22:06:15,914 INFO [train.py:763] (0/8) Epoch 23, batch 200, loss[loss=0.1687, simple_loss=0.2717, pruned_loss=0.03287, over 7204.00 frames.], tot_loss[loss=0.1678, simple_loss=0.267, pruned_loss=0.03431, over 903516.07 frames.], batch size: 22, lr: 3.28e-04
+2022-04-29 22:07:21,273 INFO [train.py:763] (0/8) Epoch 23, batch 250, loss[loss=0.1515, simple_loss=0.2605, pruned_loss=0.02122, over 7415.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2665, pruned_loss=0.03397, over 1015321.43 frames.], batch size: 21, lr: 3.28e-04
+2022-04-29 22:08:27,028 INFO [train.py:763] (0/8) Epoch 23, batch 300, loss[loss=0.1663, simple_loss=0.264, pruned_loss=0.03428, over 7148.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2656, pruned_loss=0.03359, over 1107314.49 frames.], batch size: 20, lr: 3.27e-04
+2022-04-29 22:09:32,883 INFO [train.py:763] (0/8) Epoch 23, batch 350, loss[loss=0.1681, simple_loss=0.2728, pruned_loss=0.03167, over 7283.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2652, pruned_loss=0.03358, over 1179085.43 frames.], batch size: 25, lr: 3.27e-04
+2022-04-29 22:10:38,049 INFO [train.py:763] (0/8) Epoch 23, batch 400, loss[loss=0.1661, simple_loss=0.2679, pruned_loss=0.0321, over 7267.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2652, pruned_loss=0.03363, over 1230556.03 frames.], batch size: 24, lr: 3.27e-04
+2022-04-29 22:11:43,829 INFO [train.py:763] (0/8) Epoch 23, batch 450, loss[loss=0.1721, simple_loss=0.2684, pruned_loss=0.03785, over 7151.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2657, pruned_loss=0.03386, over 1276565.50 frames.], batch size: 20, lr: 3.27e-04
+2022-04-29 22:12:49,139 INFO [train.py:763] (0/8) Epoch 23, batch 500, loss[loss=0.1672, simple_loss=0.2685, pruned_loss=0.03298, over 7349.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2658, pruned_loss=0.03395, over 1308047.80 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:13:54,756 INFO [train.py:763] (0/8) Epoch 23, batch 550, loss[loss=0.1914, simple_loss=0.2914, pruned_loss=0.04565, over 7205.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2656, pruned_loss=0.03377, over 1337236.11 frames.], batch size: 22, lr: 3.27e-04
+2022-04-29 22:15:00,609 INFO [train.py:763] (0/8) Epoch 23, batch 600, loss[loss=0.1504, simple_loss=0.2374, pruned_loss=0.03171, over 7359.00 frames.], tot_loss[loss=0.1666, simple_loss=0.265, pruned_loss=0.03408, over 1354641.98 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:16:06,058 INFO [train.py:763] (0/8) Epoch 23, batch 650, loss[loss=0.1524, simple_loss=0.2448, pruned_loss=0.03001, over 7361.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2651, pruned_loss=0.03422, over 1365285.08 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:17:12,014 INFO [train.py:763] (0/8) Epoch 23, batch 700, loss[loss=0.1965, simple_loss=0.3007, pruned_loss=0.04611, over 7200.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2638, pruned_loss=0.03382, over 1382867.42 frames.], batch size: 26, lr: 3.27e-04
+2022-04-29 22:18:17,845 INFO [train.py:763] (0/8) Epoch 23, batch 750, loss[loss=0.1453, simple_loss=0.2292, pruned_loss=0.03071, over 6990.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2643, pruned_loss=0.03346, over 1393470.31 frames.], batch size: 16, lr: 3.27e-04
+2022-04-29 22:19:23,436 INFO [train.py:763] (0/8) Epoch 23, batch 800, loss[loss=0.168, simple_loss=0.2673, pruned_loss=0.03436, over 7258.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2642, pruned_loss=0.03357, over 1400477.51 frames.], batch size: 19, lr: 3.27e-04
+2022-04-29 22:20:28,947 INFO [train.py:763] (0/8) Epoch 23, batch 850, loss[loss=0.1794, simple_loss=0.2771, pruned_loss=0.04085, over 6729.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2648, pruned_loss=0.03401, over 1407243.97 frames.], batch size: 31, lr: 3.27e-04
+2022-04-29 22:21:34,335 INFO [train.py:763] (0/8) Epoch 23, batch 900, loss[loss=0.1563, simple_loss=0.2554, pruned_loss=0.02867, over 7425.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2646, pruned_loss=0.03394, over 1413073.99 frames.], batch size: 20, lr: 3.27e-04
+2022-04-29 22:22:49,578 INFO [train.py:763] (0/8) Epoch 23, batch 950, loss[loss=0.1859, simple_loss=0.2893, pruned_loss=0.04123, over 6491.00 frames.], tot_loss[loss=0.1659, simple_loss=0.264, pruned_loss=0.03389, over 1418280.53 frames.], batch size: 38, lr: 3.26e-04
+2022-04-29 22:23:55,242 INFO [train.py:763] (0/8) Epoch 23, batch 1000, loss[loss=0.1774, simple_loss=0.2781, pruned_loss=0.0384, over 7323.00 frames.], tot_loss[loss=0.166, simple_loss=0.2641, pruned_loss=0.03391, over 1419835.87 frames.], batch size: 21, lr: 3.26e-04
+2022-04-29 22:25:00,706 INFO [train.py:763] (0/8) Epoch 23, batch 1050, loss[loss=0.1583, simple_loss=0.2588, pruned_loss=0.02893, over 7228.00 frames.], tot_loss[loss=0.167, simple_loss=0.265, pruned_loss=0.03447, over 1413265.37 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:26:07,031 INFO [train.py:763] (0/8) Epoch 23, batch 1100, loss[loss=0.1467, simple_loss=0.2466, pruned_loss=0.02343, over 7147.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2652, pruned_loss=0.03459, over 1412384.98 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:27:12,608 INFO [train.py:763] (0/8) Epoch 23, batch 1150, loss[loss=0.1802, simple_loss=0.2781, pruned_loss=0.04116, over 6266.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2644, pruned_loss=0.03418, over 1415494.80 frames.], batch size: 37, lr: 3.26e-04
+2022-04-29 22:28:17,837 INFO [train.py:763] (0/8) Epoch 23, batch 1200, loss[loss=0.1582, simple_loss=0.2507, pruned_loss=0.03286, over 7164.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2649, pruned_loss=0.03439, over 1417935.89 frames.], batch size: 18, lr: 3.26e-04
+2022-04-29 22:29:23,312 INFO [train.py:763] (0/8) Epoch 23, batch 1250, loss[loss=0.1325, simple_loss=0.2308, pruned_loss=0.01707, over 7319.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2653, pruned_loss=0.03483, over 1419011.35 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:30:28,897 INFO [train.py:763] (0/8) Epoch 23, batch 1300, loss[loss=0.1891, simple_loss=0.2842, pruned_loss=0.04702, over 6863.00 frames.], tot_loss[loss=0.168, simple_loss=0.2658, pruned_loss=0.03513, over 1420356.64 frames.], batch size: 31, lr: 3.26e-04
+2022-04-29 22:31:51,698 INFO [train.py:763] (0/8) Epoch 23, batch 1350, loss[loss=0.1397, simple_loss=0.2375, pruned_loss=0.02097, over 7418.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2659, pruned_loss=0.0346, over 1425758.40 frames.], batch size: 18, lr: 3.26e-04
+2022-04-29 22:32:57,247 INFO [train.py:763] (0/8) Epoch 23, batch 1400, loss[loss=0.1677, simple_loss=0.2717, pruned_loss=0.03183, over 7167.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2651, pruned_loss=0.03415, over 1423716.07 frames.], batch size: 26, lr: 3.26e-04
+2022-04-29 22:34:20,491 INFO [train.py:763] (0/8) Epoch 23, batch 1450, loss[loss=0.1483, simple_loss=0.2466, pruned_loss=0.02501, over 7154.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2659, pruned_loss=0.03458, over 1421398.86 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:35:53,266 INFO [train.py:763] (0/8) Epoch 23, batch 1500, loss[loss=0.1672, simple_loss=0.2661, pruned_loss=0.03417, over 7141.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2658, pruned_loss=0.03463, over 1419699.67 frames.], batch size: 20, lr: 3.26e-04
+2022-04-29 22:36:59,424 INFO [train.py:763] (0/8) Epoch 23, batch 1550, loss[loss=0.1871, simple_loss=0.2927, pruned_loss=0.04075, over 6834.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2651, pruned_loss=0.03425, over 1420442.61 frames.], batch size: 31, lr: 3.26e-04
+2022-04-29 22:38:04,563 INFO [train.py:763] (0/8) Epoch 23, batch 1600, loss[loss=0.1716, simple_loss=0.2787, pruned_loss=0.03229, over 7325.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2661, pruned_loss=0.03448, over 1422116.73 frames.], batch size: 20, lr: 3.25e-04
+2022-04-29 22:39:10,557 INFO [train.py:763] (0/8) Epoch 23, batch 1650, loss[loss=0.1496, simple_loss=0.2393, pruned_loss=0.02997, over 6855.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2664, pruned_loss=0.0344, over 1413670.19 frames.], batch size: 15, lr: 3.25e-04
+2022-04-29 22:40:17,831 INFO [train.py:763] (0/8) Epoch 23, batch 1700, loss[loss=0.171, simple_loss=0.2815, pruned_loss=0.03021, over 7309.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2662, pruned_loss=0.03412, over 1417385.45 frames.], batch size: 21, lr: 3.25e-04
+2022-04-29 22:41:24,858 INFO [train.py:763] (0/8) Epoch 23, batch 1750, loss[loss=0.1412, simple_loss=0.231, pruned_loss=0.02571, over 7068.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2658, pruned_loss=0.03386, over 1419024.67 frames.], batch size: 18, lr: 3.25e-04
+2022-04-29 22:42:30,375 INFO [train.py:763] (0/8) Epoch 23, batch 1800, loss[loss=0.1782, simple_loss=0.2872, pruned_loss=0.03464, over 7323.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2663, pruned_loss=0.0341, over 1418997.71 frames.], batch size: 22, lr: 3.25e-04
+2022-04-29 22:43:35,690 INFO [train.py:763] (0/8) Epoch 23, batch 1850, loss[loss=0.1966, simple_loss=0.2875, pruned_loss=0.05285, over 7293.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2673, pruned_loss=0.03466, over 1422979.55 frames.], batch size: 24, lr: 3.25e-04
+2022-04-29 22:44:41,112 INFO [train.py:763] (0/8) Epoch 23, batch 1900, loss[loss=0.1628, simple_loss=0.2728, pruned_loss=0.02644, over 7071.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2674, pruned_loss=0.03475, over 1422121.99 frames.], batch size: 28, lr: 3.25e-04
+2022-04-29 22:45:46,554 INFO [train.py:763] (0/8) Epoch 23, batch 1950, loss[loss=0.1541, simple_loss=0.255, pruned_loss=0.02659, over 7103.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2681, pruned_loss=0.03506, over 1423652.28 frames.], batch size: 21, lr: 3.25e-04
+2022-04-29 22:46:52,062 INFO [train.py:763] (0/8) Epoch 23, batch 2000, loss[loss=0.1781, simple_loss=0.2873, pruned_loss=0.03446, over 4822.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2686, pruned_loss=0.03531, over 1421551.90 frames.], batch size: 52, lr: 3.25e-04
+2022-04-29 22:47:58,961 INFO [train.py:763] (0/8) Epoch 23, batch 2050, loss[loss=0.1677, simple_loss=0.2662, pruned_loss=0.03463, over 7438.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2684, pruned_loss=0.03521, over 1421451.41 frames.], batch size: 20, lr: 3.25e-04
+2022-04-29 22:49:05,153 INFO [train.py:763] (0/8) Epoch 23, batch 2100, loss[loss=0.169, simple_loss=0.2555, pruned_loss=0.04122, over 6996.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2682, pruned_loss=0.0353, over 1422632.27 frames.], batch size: 16, lr: 3.25e-04
+2022-04-29 22:50:10,661 INFO [train.py:763] (0/8) Epoch 23, batch 2150, loss[loss=0.2062, simple_loss=0.2898, pruned_loss=0.06126, over 4972.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2675, pruned_loss=0.03505, over 1420235.83 frames.], batch size: 52, lr: 3.25e-04
+2022-04-29 22:51:16,168 INFO [train.py:763] (0/8) Epoch 23, batch 2200, loss[loss=0.1434, simple_loss=0.2407, pruned_loss=0.02307, over 7125.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2663, pruned_loss=0.03459, over 1419877.61 frames.], batch size: 17, lr: 3.25e-04
+2022-04-29 22:52:21,344 INFO [train.py:763] (0/8) Epoch 23, batch 2250, loss[loss=0.2106, simple_loss=0.3131, pruned_loss=0.0541, over 7311.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2674, pruned_loss=0.03489, over 1410233.83 frames.], batch size: 25, lr: 3.24e-04
+2022-04-29 22:53:28,275 INFO [train.py:763] (0/8) Epoch 23, batch 2300, loss[loss=0.1525, simple_loss=0.2395, pruned_loss=0.03275, over 7274.00 frames.], tot_loss[loss=0.1672, simple_loss=0.266, pruned_loss=0.03422, over 1417316.50 frames.], batch size: 17, lr: 3.24e-04
+2022-04-29 22:54:34,468 INFO [train.py:763] (0/8) Epoch 23, batch 2350, loss[loss=0.1868, simple_loss=0.2969, pruned_loss=0.03833, over 7343.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2673, pruned_loss=0.03477, over 1418692.61 frames.], batch size: 22, lr: 3.24e-04
+2022-04-29 22:55:39,715 INFO [train.py:763] (0/8) Epoch 23, batch 2400, loss[loss=0.16, simple_loss=0.2563, pruned_loss=0.03184, over 7240.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2672, pruned_loss=0.03447, over 1421759.30 frames.], batch size: 16, lr: 3.24e-04
+2022-04-29 22:56:45,977 INFO [train.py:763] (0/8) Epoch 23, batch 2450, loss[loss=0.1644, simple_loss=0.2575, pruned_loss=0.0356, over 7233.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2673, pruned_loss=0.03457, over 1418186.08 frames.], batch size: 20, lr: 3.24e-04
+2022-04-29 22:57:51,402 INFO [train.py:763] (0/8) Epoch 23, batch 2500, loss[loss=0.1739, simple_loss=0.2804, pruned_loss=0.03371, over 7311.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2671, pruned_loss=0.0345, over 1418954.18 frames.], batch size: 21, lr: 3.24e-04
+2022-04-29 22:58:56,889 INFO [train.py:763] (0/8) Epoch 23, batch 2550, loss[loss=0.1761, simple_loss=0.281, pruned_loss=0.03556, over 5254.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2671, pruned_loss=0.03474, over 1415231.70 frames.], batch size: 52, lr: 3.24e-04
+2022-04-29 23:00:02,924 INFO [train.py:763] (0/8) Epoch 23, batch 2600, loss[loss=0.1507, simple_loss=0.2462, pruned_loss=0.02758, over 7270.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2681, pruned_loss=0.03464, over 1419396.13 frames.], batch size: 18, lr: 3.24e-04
+2022-04-29 23:01:08,578 INFO [train.py:763] (0/8) Epoch 23, batch 2650, loss[loss=0.1413, simple_loss=0.2477, pruned_loss=0.0174, over 7323.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2668, pruned_loss=0.03427, over 1418578.00 frames.], batch size: 21, lr: 3.24e-04
+2022-04-29 23:02:14,027 INFO [train.py:763] (0/8) Epoch 23, batch 2700, loss[loss=0.1715, simple_loss=0.2818, pruned_loss=0.03056, over 7341.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2668, pruned_loss=0.0342, over 1423035.99 frames.], batch size: 22, lr: 3.24e-04
+2022-04-29 23:03:19,907 INFO [train.py:763] (0/8) Epoch 23, batch 2750, loss[loss=0.1604, simple_loss=0.2631, pruned_loss=0.02885, over 7416.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2665, pruned_loss=0.0341, over 1425788.79 frames.], batch size: 21, lr: 3.24e-04
+2022-04-29 23:04:25,100 INFO [train.py:763] (0/8) Epoch 23, batch 2800, loss[loss=0.1606, simple_loss=0.2631, pruned_loss=0.029, over 7237.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2672, pruned_loss=0.03461, over 1422340.86 frames.], batch size: 20, lr: 3.24e-04
+2022-04-29 23:05:30,277 INFO [train.py:763] (0/8) Epoch 23, batch 2850, loss[loss=0.1611, simple_loss=0.2584, pruned_loss=0.0319, over 7353.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2689, pruned_loss=0.03502, over 1422315.60 frames.], batch size: 19, lr: 3.24e-04
+2022-04-29 23:06:35,477 INFO [train.py:763] (0/8) Epoch 23, batch 2900, loss[loss=0.1803, simple_loss=0.2802, pruned_loss=0.04026, over 7299.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2691, pruned_loss=0.03515, over 1421613.57 frames.], batch size: 25, lr: 3.24e-04
+2022-04-29 23:07:40,688 INFO [train.py:763] (0/8) Epoch 23, batch 2950, loss[loss=0.1604, simple_loss=0.2454, pruned_loss=0.03766, over 7277.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2687, pruned_loss=0.03496, over 1425758.53 frames.], batch size: 17, lr: 3.23e-04
+2022-04-29 23:08:45,896 INFO [train.py:763] (0/8) Epoch 23, batch 3000, loss[loss=0.1756, simple_loss=0.2786, pruned_loss=0.03628, over 7115.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2683, pruned_loss=0.03478, over 1421201.66 frames.], batch size: 21, lr: 3.23e-04
+2022-04-29 23:08:45,897 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-29 23:09:01,228 INFO [train.py:792] (0/8) Epoch 23, validation: loss=0.1683, simple_loss=0.2665, pruned_loss=0.03509, over 698248.00 frames.
+2022-04-29 23:10:07,041 INFO [train.py:763] (0/8) Epoch 23, batch 3050, loss[loss=0.1489, simple_loss=0.2458, pruned_loss=0.02601, over 7277.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2681, pruned_loss=0.03485, over 1416659.17 frames.], batch size: 18, lr: 3.23e-04
+2022-04-29 23:11:12,532 INFO [train.py:763] (0/8) Epoch 23, batch 3100, loss[loss=0.1755, simple_loss=0.268, pruned_loss=0.04153, over 6841.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2674, pruned_loss=0.0349, over 1419887.20 frames.], batch size: 31, lr: 3.23e-04
+2022-04-29 23:12:19,067 INFO [train.py:763] (0/8) Epoch 23, batch 3150, loss[loss=0.1397, simple_loss=0.2301, pruned_loss=0.02468, over 6993.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2671, pruned_loss=0.03479, over 1421744.39 frames.], batch size: 16, lr: 3.23e-04
+2022-04-29 23:13:26,796 INFO [train.py:763] (0/8) Epoch 23, batch 3200, loss[loss=0.1883, simple_loss=0.2929, pruned_loss=0.04191, over 7313.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2663, pruned_loss=0.03415, over 1425965.68 frames.], batch size: 21, lr: 3.23e-04
+2022-04-29 23:14:33,558 INFO [train.py:763] (0/8) Epoch 23, batch 3250, loss[loss=0.1555, simple_loss=0.2592, pruned_loss=0.02588, over 7154.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2665, pruned_loss=0.034, over 1427684.70 frames.], batch size: 18, lr: 3.23e-04
+2022-04-29 23:15:38,822 INFO [train.py:763] (0/8) Epoch 23, batch 3300, loss[loss=0.1909, simple_loss=0.2943, pruned_loss=0.04371, over 7299.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2666, pruned_loss=0.03409, over 1427140.90 frames.], batch size: 24, lr: 3.23e-04
+2022-04-29 23:16:45,591 INFO [train.py:763] (0/8) Epoch 23, batch 3350, loss[loss=0.1705, simple_loss=0.2642, pruned_loss=0.0384, over 7310.00 frames.], tot_loss[loss=0.168, simple_loss=0.267, pruned_loss=0.03453, over 1423171.94 frames.], batch size: 24, lr: 3.23e-04
+2022-04-29 23:17:51,567 INFO [train.py:763] (0/8) Epoch 23, batch 3400, loss[loss=0.1575, simple_loss=0.2472, pruned_loss=0.03391, over 7363.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2668, pruned_loss=0.03456, over 1427258.07 frames.], batch size: 19, lr: 3.23e-04
+2022-04-29 23:18:56,730 INFO [train.py:763] (0/8) Epoch 23, batch 3450, loss[loss=0.1623, simple_loss=0.2742, pruned_loss=0.02526, over 7320.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2665, pruned_loss=0.03389, over 1422831.48 frames.], batch size: 22, lr: 3.23e-04
+2022-04-29 23:20:02,255 INFO [train.py:763] (0/8) Epoch 23, batch 3500, loss[loss=0.1412, simple_loss=0.2375, pruned_loss=0.0224, over 6801.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2657, pruned_loss=0.03388, over 1422154.72 frames.], batch size: 15, lr: 3.23e-04
+2022-04-29 23:21:08,258 INFO [train.py:763] (0/8) Epoch 23, batch 3550, loss[loss=0.1746, simple_loss=0.2769, pruned_loss=0.03613, over 7120.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2664, pruned_loss=0.0343, over 1423702.74 frames.], batch size: 21, lr: 3.23e-04
+2022-04-29 23:22:13,624 INFO [train.py:763] (0/8) Epoch 23, batch 3600, loss[loss=0.1443, simple_loss=0.2474, pruned_loss=0.02058, over 7448.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2666, pruned_loss=0.03417, over 1423313.38 frames.], batch size: 19, lr: 3.22e-04
+2022-04-29 23:23:18,845 INFO [train.py:763] (0/8) Epoch 23, batch 3650, loss[loss=0.1523, simple_loss=0.2455, pruned_loss=0.02956, over 7347.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2668, pruned_loss=0.03425, over 1424261.39 frames.], batch size: 19, lr: 3.22e-04
+2022-04-29 23:24:24,046 INFO [train.py:763] (0/8) Epoch 23, batch 3700, loss[loss=0.1741, simple_loss=0.2802, pruned_loss=0.03401, over 6431.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2674, pruned_loss=0.03457, over 1421256.80 frames.], batch size: 38, lr: 3.22e-04
+2022-04-29 23:25:30,847 INFO [train.py:763] (0/8) Epoch 23, batch 3750, loss[loss=0.153, simple_loss=0.2493, pruned_loss=0.02837, over 7279.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2677, pruned_loss=0.0344, over 1422646.69 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:26:37,760 INFO [train.py:763] (0/8) Epoch 23, batch 3800, loss[loss=0.1538, simple_loss=0.2516, pruned_loss=0.02798, over 7440.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2665, pruned_loss=0.03392, over 1424546.65 frames.], batch size: 20, lr: 3.22e-04
+2022-04-29 23:27:43,268 INFO [train.py:763] (0/8) Epoch 23, batch 3850, loss[loss=0.1975, simple_loss=0.2933, pruned_loss=0.05083, over 4975.00 frames.], tot_loss[loss=0.1669, simple_loss=0.266, pruned_loss=0.03388, over 1421026.30 frames.], batch size: 52, lr: 3.22e-04
+2022-04-29 23:28:48,638 INFO [train.py:763] (0/8) Epoch 23, batch 3900, loss[loss=0.2069, simple_loss=0.3056, pruned_loss=0.05408, over 6704.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2672, pruned_loss=0.03461, over 1416489.51 frames.], batch size: 31, lr: 3.22e-04
+2022-04-29 23:29:53,690 INFO [train.py:763] (0/8) Epoch 23, batch 3950, loss[loss=0.1441, simple_loss=0.2418, pruned_loss=0.02316, over 7133.00 frames.], tot_loss[loss=0.169, simple_loss=0.2682, pruned_loss=0.03488, over 1416677.25 frames.], batch size: 17, lr: 3.22e-04
+2022-04-29 23:30:59,590 INFO [train.py:763] (0/8) Epoch 23, batch 4000, loss[loss=0.1933, simple_loss=0.2985, pruned_loss=0.04402, over 7203.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2684, pruned_loss=0.03464, over 1415153.26 frames.], batch size: 22, lr: 3.22e-04
+2022-04-29 23:32:05,451 INFO [train.py:763] (0/8) Epoch 23, batch 4050, loss[loss=0.2008, simple_loss=0.2939, pruned_loss=0.05382, over 5281.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2675, pruned_loss=0.03432, over 1416521.02 frames.], batch size: 52, lr: 3.22e-04
+2022-04-29 23:33:10,721 INFO [train.py:763] (0/8) Epoch 23, batch 4100, loss[loss=0.1443, simple_loss=0.2425, pruned_loss=0.02306, over 7270.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2671, pruned_loss=0.03399, over 1415973.44 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:34:16,157 INFO [train.py:763] (0/8) Epoch 23, batch 4150, loss[loss=0.1571, simple_loss=0.2484, pruned_loss=0.03295, over 6996.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2671, pruned_loss=0.03415, over 1417946.99 frames.], batch size: 16, lr: 3.22e-04
+2022-04-29 23:35:21,259 INFO [train.py:763] (0/8) Epoch 23, batch 4200, loss[loss=0.1559, simple_loss=0.2477, pruned_loss=0.03202, over 7284.00 frames.], tot_loss[loss=0.1686, simple_loss=0.268, pruned_loss=0.03463, over 1418578.34 frames.], batch size: 18, lr: 3.22e-04
+2022-04-29 23:36:26,923 INFO [train.py:763] (0/8) Epoch 23, batch 4250, loss[loss=0.2005, simple_loss=0.3108, pruned_loss=0.04508, over 7390.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2681, pruned_loss=0.03513, over 1416904.91 frames.], batch size: 23, lr: 3.22e-04
+2022-04-29 23:37:32,238 INFO [train.py:763] (0/8) Epoch 23, batch 4300, loss[loss=0.1527, simple_loss=0.2321, pruned_loss=0.03665, over 6745.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2667, pruned_loss=0.03504, over 1415644.56 frames.], batch size: 15, lr: 3.21e-04
+2022-04-29 23:38:37,634 INFO [train.py:763] (0/8) Epoch 23, batch 4350, loss[loss=0.1746, simple_loss=0.2769, pruned_loss=0.03613, over 6904.00 frames.], tot_loss[loss=0.169, simple_loss=0.2676, pruned_loss=0.03519, over 1413260.55 frames.], batch size: 32, lr: 3.21e-04
+2022-04-29 23:39:43,235 INFO [train.py:763] (0/8) Epoch 23, batch 4400, loss[loss=0.1739, simple_loss=0.2745, pruned_loss=0.03672, over 6311.00 frames.], tot_loss[loss=0.1688, simple_loss=0.267, pruned_loss=0.03528, over 1406157.46 frames.], batch size: 37, lr: 3.21e-04
+2022-04-29 23:40:48,378 INFO [train.py:763] (0/8) Epoch 23, batch 4450, loss[loss=0.1776, simple_loss=0.2811, pruned_loss=0.03702, over 6199.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2666, pruned_loss=0.03491, over 1409269.69 frames.], batch size: 37, lr: 3.21e-04
+2022-04-29 23:41:53,047 INFO [train.py:763] (0/8) Epoch 23, batch 4500, loss[loss=0.1735, simple_loss=0.2757, pruned_loss=0.03566, over 6343.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2668, pruned_loss=0.03519, over 1396018.81 frames.], batch size: 37, lr: 3.21e-04
+2022-04-29 23:42:58,315 INFO [train.py:763] (0/8) Epoch 23, batch 4550, loss[loss=0.1831, simple_loss=0.287, pruned_loss=0.03961, over 7301.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2677, pruned_loss=0.0359, over 1384803.15 frames.], batch size: 24, lr: 3.21e-04
+2022-04-29 23:43:48,006 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-23.pt
+2022-04-29 23:44:17,939 INFO [train.py:763] (0/8) Epoch 24, batch 0, loss[loss=0.1708, simple_loss=0.2739, pruned_loss=0.0338, over 7077.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2739, pruned_loss=0.0338, over 7077.00 frames.], batch size: 18, lr: 3.15e-04
+2022-04-29 23:45:23,863 INFO [train.py:763] (0/8) Epoch 24, batch 50, loss[loss=0.1633, simple_loss=0.2566, pruned_loss=0.035, over 7234.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2684, pruned_loss=0.03493, over 321318.33 frames.], batch size: 19, lr: 3.15e-04
+2022-04-29 23:46:30,373 INFO [train.py:763] (0/8) Epoch 24, batch 100, loss[loss=0.1967, simple_loss=0.2983, pruned_loss=0.04752, over 7320.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2681, pruned_loss=0.03514, over 569742.11 frames.], batch size: 20, lr: 3.15e-04
+2022-04-29 23:47:36,018 INFO [train.py:763] (0/8) Epoch 24, batch 150, loss[loss=0.1711, simple_loss=0.2756, pruned_loss=0.03326, over 7319.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2668, pruned_loss=0.03422, over 761133.33 frames.], batch size: 21, lr: 3.14e-04
+2022-04-29 23:48:41,598 INFO [train.py:763] (0/8) Epoch 24, batch 200, loss[loss=0.1575, simple_loss=0.2518, pruned_loss=0.03157, over 6785.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2661, pruned_loss=0.03416, over 906101.16 frames.], batch size: 15, lr: 3.14e-04
+2022-04-29 23:49:46,887 INFO [train.py:763] (0/8) Epoch 24, batch 250, loss[loss=0.1791, simple_loss=0.2786, pruned_loss=0.03978, over 7240.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2662, pruned_loss=0.03411, over 1018670.77 frames.], batch size: 20, lr: 3.14e-04
+2022-04-29 23:50:52,239 INFO [train.py:763] (0/8) Epoch 24, batch 300, loss[loss=0.1635, simple_loss=0.2556, pruned_loss=0.03571, over 7158.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2664, pruned_loss=0.03403, over 1112303.19 frames.], batch size: 19, lr: 3.14e-04
+2022-04-29 23:51:57,524 INFO [train.py:763] (0/8) Epoch 24, batch 350, loss[loss=0.1827, simple_loss=0.2762, pruned_loss=0.04456, over 7226.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2667, pruned_loss=0.03438, over 1182480.41 frames.], batch size: 23, lr: 3.14e-04
+2022-04-29 23:53:03,351 INFO [train.py:763] (0/8) Epoch 24, batch 400, loss[loss=0.1837, simple_loss=0.2844, pruned_loss=0.04153, over 7235.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2657, pruned_loss=0.03388, over 1237159.02 frames.], batch size: 20, lr: 3.14e-04
+2022-04-29 23:54:08,676 INFO [train.py:763] (0/8) Epoch 24, batch 450, loss[loss=0.1698, simple_loss=0.2666, pruned_loss=0.03656, over 7181.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2648, pruned_loss=0.03395, over 1277527.21 frames.], batch size: 28, lr: 3.14e-04
+2022-04-29 23:55:14,218 INFO [train.py:763] (0/8) Epoch 24, batch 500, loss[loss=0.1727, simple_loss=0.2672, pruned_loss=0.03913, over 7182.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2646, pruned_loss=0.03376, over 1312372.92 frames.], batch size: 18, lr: 3.14e-04
+2022-04-29 23:56:20,431 INFO [train.py:763] (0/8) Epoch 24, batch 550, loss[loss=0.1645, simple_loss=0.2606, pruned_loss=0.03416, over 7168.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2646, pruned_loss=0.03344, over 1339506.32 frames.], batch size: 18, lr: 3.14e-04
+2022-04-29 23:57:26,724 INFO [train.py:763] (0/8) Epoch 24, batch 600, loss[loss=0.1743, simple_loss=0.2716, pruned_loss=0.0385, over 7203.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2646, pruned_loss=0.03364, over 1359301.51 frames.], batch size: 23, lr: 3.14e-04
+2022-04-29 23:58:32,104 INFO [train.py:763] (0/8) Epoch 24, batch 650, loss[loss=0.1588, simple_loss=0.2411, pruned_loss=0.03824, over 7291.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2644, pruned_loss=0.03391, over 1371535.42 frames.], batch size: 17, lr: 3.14e-04
+2022-04-29 23:59:38,751 INFO [train.py:763] (0/8) Epoch 24, batch 700, loss[loss=0.1468, simple_loss=0.2335, pruned_loss=0.03004, over 6761.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2646, pruned_loss=0.03391, over 1387474.68 frames.], batch size: 15, lr: 3.14e-04
+2022-04-30 00:00:44,930 INFO [train.py:763] (0/8) Epoch 24, batch 750, loss[loss=0.1592, simple_loss=0.2619, pruned_loss=0.02821, over 7234.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2655, pruned_loss=0.03397, over 1397880.25 frames.], batch size: 20, lr: 3.14e-04
+2022-04-30 00:01:50,613 INFO [train.py:763] (0/8) Epoch 24, batch 800, loss[loss=0.1838, simple_loss=0.2854, pruned_loss=0.04114, over 7415.00 frames.], tot_loss[loss=0.168, simple_loss=0.267, pruned_loss=0.03451, over 1405275.48 frames.], batch size: 21, lr: 3.14e-04
+2022-04-30 00:02:56,134 INFO [train.py:763] (0/8) Epoch 24, batch 850, loss[loss=0.1458, simple_loss=0.2572, pruned_loss=0.01719, over 7314.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2672, pruned_loss=0.03455, over 1407320.23 frames.], batch size: 21, lr: 3.13e-04
+2022-04-30 00:04:01,374 INFO [train.py:763] (0/8) Epoch 24, batch 900, loss[loss=0.1925, simple_loss=0.2989, pruned_loss=0.04305, over 7332.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2678, pruned_loss=0.03496, over 1410757.31 frames.], batch size: 25, lr: 3.13e-04
+2022-04-30 00:05:07,036 INFO [train.py:763] (0/8) Epoch 24, batch 950, loss[loss=0.2006, simple_loss=0.2939, pruned_loss=0.05365, over 5037.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2676, pruned_loss=0.03499, over 1405475.30 frames.], batch size: 52, lr: 3.13e-04
+2022-04-30 00:06:12,852 INFO [train.py:763] (0/8) Epoch 24, batch 1000, loss[loss=0.1776, simple_loss=0.274, pruned_loss=0.04057, over 7411.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2683, pruned_loss=0.03522, over 1412132.56 frames.], batch size: 21, lr: 3.13e-04
+2022-04-30 00:07:18,490 INFO [train.py:763] (0/8) Epoch 24, batch 1050, loss[loss=0.1585, simple_loss=0.2632, pruned_loss=0.02688, over 7335.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2677, pruned_loss=0.03453, over 1418897.37 frames.], batch size: 20, lr: 3.13e-04
+2022-04-30 00:08:24,029 INFO [train.py:763] (0/8) Epoch 24, batch 1100, loss[loss=0.1647, simple_loss=0.2708, pruned_loss=0.02928, over 7338.00 frames.], tot_loss[loss=0.168, simple_loss=0.2674, pruned_loss=0.03437, over 1421015.23 frames.], batch size: 22, lr: 3.13e-04
+2022-04-30 00:09:29,781 INFO [train.py:763] (0/8) Epoch 24, batch 1150, loss[loss=0.1919, simple_loss=0.2962, pruned_loss=0.04383, over 7221.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2667, pruned_loss=0.03455, over 1423288.62 frames.], batch size: 23, lr: 3.13e-04
+2022-04-30 00:10:35,407 INFO [train.py:763] (0/8) Epoch 24, batch 1200, loss[loss=0.1694, simple_loss=0.2736, pruned_loss=0.0326, over 7377.00 frames.], tot_loss[loss=0.168, simple_loss=0.2668, pruned_loss=0.03455, over 1422987.72 frames.], batch size: 23, lr: 3.13e-04
+2022-04-30 00:11:41,677 INFO [train.py:763] (0/8) Epoch 24, batch 1250, loss[loss=0.176, simple_loss=0.2724, pruned_loss=0.0398, over 7139.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2668, pruned_loss=0.03468, over 1421744.70 frames.], batch size: 20, lr: 3.13e-04
+2022-04-30 00:12:47,625 INFO [train.py:763] (0/8) Epoch 24, batch 1300, loss[loss=0.1377, simple_loss=0.2263, pruned_loss=0.02456, over 6767.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2659, pruned_loss=0.03435, over 1420306.26 frames.], batch size: 15, lr: 3.13e-04
+2022-04-30 00:13:53,408 INFO [train.py:763] (0/8) Epoch 24, batch 1350, loss[loss=0.1662, simple_loss=0.2694, pruned_loss=0.03147, over 6471.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2656, pruned_loss=0.03406, over 1420737.63 frames.], batch size: 38, lr: 3.13e-04
+2022-04-30 00:14:58,838 INFO [train.py:763] (0/8) Epoch 24, batch 1400, loss[loss=0.1411, simple_loss=0.2377, pruned_loss=0.02228, over 7271.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2656, pruned_loss=0.03389, over 1425703.64 frames.], batch size: 17, lr: 3.13e-04
+2022-04-30 00:16:04,293 INFO [train.py:763] (0/8) Epoch 24, batch 1450, loss[loss=0.1632, simple_loss=0.2718, pruned_loss=0.0273, over 7140.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2651, pruned_loss=0.03373, over 1421938.65 frames.], batch size: 20, lr: 3.13e-04
+2022-04-30 00:17:11,229 INFO [train.py:763] (0/8) Epoch 24, batch 1500, loss[loss=0.1804, simple_loss=0.2811, pruned_loss=0.03983, over 6770.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2653, pruned_loss=0.03343, over 1420315.45 frames.], batch size: 31, lr: 3.13e-04
+2022-04-30 00:18:17,541 INFO [train.py:763] (0/8) Epoch 24, batch 1550, loss[loss=0.166, simple_loss=0.2558, pruned_loss=0.03813, over 7272.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2667, pruned_loss=0.03407, over 1421646.91 frames.], batch size: 18, lr: 3.12e-04
+2022-04-30 00:19:23,715 INFO [train.py:763] (0/8) Epoch 24, batch 1600, loss[loss=0.1494, simple_loss=0.251, pruned_loss=0.02389, over 7196.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2667, pruned_loss=0.03379, over 1419979.92 frames.], batch size: 16, lr: 3.12e-04
+2022-04-30 00:20:29,917 INFO [train.py:763] (0/8) Epoch 24, batch 1650, loss[loss=0.173, simple_loss=0.2825, pruned_loss=0.03178, over 7225.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2666, pruned_loss=0.03374, over 1421203.90 frames.], batch size: 21, lr: 3.12e-04
+2022-04-30 00:21:35,728 INFO [train.py:763] (0/8) Epoch 24, batch 1700, loss[loss=0.1753, simple_loss=0.276, pruned_loss=0.03734, over 7381.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2672, pruned_loss=0.03427, over 1419583.42 frames.], batch size: 23, lr: 3.12e-04
+2022-04-30 00:22:40,925 INFO [train.py:763] (0/8) Epoch 24, batch 1750, loss[loss=0.1546, simple_loss=0.2465, pruned_loss=0.03129, over 7125.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2668, pruned_loss=0.03423, over 1422784.39 frames.], batch size: 17, lr: 3.12e-04
+2022-04-30 00:23:47,089 INFO [train.py:763] (0/8) Epoch 24, batch 1800, loss[loss=0.1464, simple_loss=0.2284, pruned_loss=0.03218, over 6985.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2667, pruned_loss=0.03412, over 1422660.90 frames.], batch size: 16, lr: 3.12e-04
+2022-04-30 00:24:52,833 INFO [train.py:763] (0/8) Epoch 24, batch 1850, loss[loss=0.1466, simple_loss=0.2399, pruned_loss=0.02666, over 6796.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2657, pruned_loss=0.03425, over 1419937.91 frames.], batch size: 15, lr: 3.12e-04
+2022-04-30 00:25:41,273 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-112000.pt
+2022-04-30 00:26:09,449 INFO [train.py:763] (0/8) Epoch 24, batch 1900, loss[loss=0.1887, simple_loss=0.2966, pruned_loss=0.0404, over 7299.00 frames.], tot_loss[loss=0.167, simple_loss=0.2655, pruned_loss=0.03422, over 1421909.75 frames.], batch size: 25, lr: 3.12e-04
+2022-04-30 00:27:15,227 INFO [train.py:763] (0/8) Epoch 24, batch 1950, loss[loss=0.1445, simple_loss=0.2427, pruned_loss=0.02311, over 7267.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2659, pruned_loss=0.03425, over 1423751.32 frames.], batch size: 19, lr: 3.12e-04
+2022-04-30 00:28:21,032 INFO [train.py:763] (0/8) Epoch 24, batch 2000, loss[loss=0.1665, simple_loss=0.2651, pruned_loss=0.03398, over 7165.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2661, pruned_loss=0.03424, over 1424307.05 frames.], batch size: 18, lr: 3.12e-04
+2022-04-30 00:29:27,113 INFO [train.py:763] (0/8) Epoch 24, batch 2050, loss[loss=0.1975, simple_loss=0.3006, pruned_loss=0.04721, over 7330.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2648, pruned_loss=0.03388, over 1427336.39 frames.], batch size: 21, lr: 3.12e-04
+2022-04-30 00:30:32,487 INFO [train.py:763] (0/8) Epoch 24, batch 2100, loss[loss=0.1923, simple_loss=0.2802, pruned_loss=0.05224, over 7265.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2646, pruned_loss=0.0335, over 1423807.09 frames.], batch size: 19, lr: 3.12e-04
+2022-04-30 00:31:37,977 INFO [train.py:763] (0/8) Epoch 24, batch 2150, loss[loss=0.1694, simple_loss=0.2666, pruned_loss=0.03613, over 7438.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2653, pruned_loss=0.03368, over 1422502.35 frames.], batch size: 20, lr: 3.12e-04
+2022-04-30 00:32:43,336 INFO [train.py:763] (0/8) Epoch 24, batch 2200, loss[loss=0.1489, simple_loss=0.2371, pruned_loss=0.03033, over 6826.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03358, over 1421153.45 frames.], batch size: 15, lr: 3.12e-04
+2022-04-30 00:33:49,452 INFO [train.py:763] (0/8) Epoch 24, batch 2250, loss[loss=0.1633, simple_loss=0.2628, pruned_loss=0.03196, over 7073.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2655, pruned_loss=0.03361, over 1417279.34 frames.], batch size: 18, lr: 3.12e-04
+2022-04-30 00:34:55,316 INFO [train.py:763] (0/8) Epoch 24, batch 2300, loss[loss=0.146, simple_loss=0.2363, pruned_loss=0.02789, over 6780.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2652, pruned_loss=0.0336, over 1418376.94 frames.], batch size: 15, lr: 3.11e-04
+2022-04-30 00:36:01,139 INFO [train.py:763] (0/8) Epoch 24, batch 2350, loss[loss=0.1574, simple_loss=0.2634, pruned_loss=0.02568, over 7311.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2648, pruned_loss=0.03335, over 1419551.97 frames.], batch size: 21, lr: 3.11e-04
+2022-04-30 00:37:06,717 INFO [train.py:763] (0/8) Epoch 24, batch 2400, loss[loss=0.1442, simple_loss=0.2406, pruned_loss=0.02394, over 7360.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2657, pruned_loss=0.03344, over 1424701.05 frames.], batch size: 19, lr: 3.11e-04
+2022-04-30 00:38:21,822 INFO [train.py:763] (0/8) Epoch 24, batch 2450, loss[loss=0.1653, simple_loss=0.2552, pruned_loss=0.03773, over 7154.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2656, pruned_loss=0.03374, over 1423717.09 frames.], batch size: 17, lr: 3.11e-04
+2022-04-30 00:39:27,189 INFO [train.py:763] (0/8) Epoch 24, batch 2500, loss[loss=0.1861, simple_loss=0.2926, pruned_loss=0.03977, over 7414.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2658, pruned_loss=0.03388, over 1424379.97 frames.], batch size: 21, lr: 3.11e-04
+2022-04-30 00:40:32,707 INFO [train.py:763] (0/8) Epoch 24, batch 2550, loss[loss=0.1618, simple_loss=0.2632, pruned_loss=0.03018, over 7433.00 frames.], tot_loss[loss=0.167, simple_loss=0.2664, pruned_loss=0.03382, over 1425584.83 frames.], batch size: 20, lr: 3.11e-04
+2022-04-30 00:41:38,109 INFO [train.py:763] (0/8) Epoch 24, batch 2600, loss[loss=0.1268, simple_loss=0.2196, pruned_loss=0.01701, over 7134.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2668, pruned_loss=0.0342, over 1422452.17 frames.], batch size: 17, lr: 3.11e-04
+2022-04-30 00:42:43,683 INFO [train.py:763] (0/8) Epoch 24, batch 2650, loss[loss=0.1615, simple_loss=0.263, pruned_loss=0.03003, over 7207.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2672, pruned_loss=0.0343, over 1424155.11 frames.], batch size: 22, lr: 3.11e-04
+2022-04-30 00:43:49,279 INFO [train.py:763] (0/8) Epoch 24, batch 2700, loss[loss=0.1481, simple_loss=0.2394, pruned_loss=0.0284, over 7075.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2663, pruned_loss=0.03409, over 1426737.70 frames.], batch size: 18, lr: 3.11e-04
+2022-04-30 00:44:54,693 INFO [train.py:763] (0/8) Epoch 24, batch 2750, loss[loss=0.1543, simple_loss=0.2674, pruned_loss=0.02058, over 7141.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2656, pruned_loss=0.03404, over 1421106.84 frames.], batch size: 20, lr: 3.11e-04
+2022-04-30 00:46:00,213 INFO [train.py:763] (0/8) Epoch 24, batch 2800, loss[loss=0.1609, simple_loss=0.2587, pruned_loss=0.03155, over 7256.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2659, pruned_loss=0.03427, over 1421310.18 frames.], batch size: 19, lr: 3.11e-04
+2022-04-30 00:47:22,979 INFO [train.py:763] (0/8) Epoch 24, batch 2850, loss[loss=0.1829, simple_loss=0.2782, pruned_loss=0.04384, over 7422.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2661, pruned_loss=0.03432, over 1419021.19 frames.], batch size: 20, lr: 3.11e-04
+2022-04-30 00:48:28,457 INFO [train.py:763] (0/8) Epoch 24, batch 2900, loss[loss=0.1652, simple_loss=0.2772, pruned_loss=0.02654, over 7207.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2664, pruned_loss=0.0342, over 1420232.11 frames.], batch size: 23, lr: 3.11e-04
+2022-04-30 00:49:52,266 INFO [train.py:763] (0/8) Epoch 24, batch 2950, loss[loss=0.1591, simple_loss=0.2564, pruned_loss=0.03085, over 7124.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2663, pruned_loss=0.03371, over 1426069.39 frames.], batch size: 21, lr: 3.11e-04
+2022-04-30 00:51:06,868 INFO [train.py:763] (0/8) Epoch 24, batch 3000, loss[loss=0.1642, simple_loss=0.2717, pruned_loss=0.02839, over 6908.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2647, pruned_loss=0.03338, over 1428824.06 frames.], batch size: 32, lr: 3.10e-04
+2022-04-30 00:51:06,869 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 00:51:22,143 INFO [train.py:792] (0/8) Epoch 24, validation: loss=0.1679, simple_loss=0.2653, pruned_loss=0.03523, over 698248.00 frames.
+2022-04-30 00:52:37,066 INFO [train.py:763] (0/8) Epoch 24, batch 3050, loss[loss=0.1891, simple_loss=0.2886, pruned_loss=0.04476, over 7119.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2649, pruned_loss=0.03362, over 1428734.37 frames.], batch size: 21, lr: 3.10e-04
+2022-04-30 00:53:42,766 INFO [train.py:763] (0/8) Epoch 24, batch 3100, loss[loss=0.1258, simple_loss=0.2197, pruned_loss=0.01592, over 6790.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2641, pruned_loss=0.03359, over 1428577.57 frames.], batch size: 15, lr: 3.10e-04
+2022-04-30 00:54:48,074 INFO [train.py:763] (0/8) Epoch 24, batch 3150, loss[loss=0.1632, simple_loss=0.2608, pruned_loss=0.0328, over 7251.00 frames.], tot_loss[loss=0.1654, simple_loss=0.264, pruned_loss=0.03339, over 1430116.59 frames.], batch size: 19, lr: 3.10e-04
+2022-04-30 00:55:53,506 INFO [train.py:763] (0/8) Epoch 24, batch 3200, loss[loss=0.2002, simple_loss=0.2832, pruned_loss=0.05863, over 5167.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2635, pruned_loss=0.03307, over 1428621.37 frames.], batch size: 54, lr: 3.10e-04
+2022-04-30 00:56:59,208 INFO [train.py:763] (0/8) Epoch 24, batch 3250, loss[loss=0.2181, simple_loss=0.3153, pruned_loss=0.06045, over 7235.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2638, pruned_loss=0.0333, over 1426259.24 frames.], batch size: 20, lr: 3.10e-04
+2022-04-30 00:58:05,424 INFO [train.py:763] (0/8) Epoch 24, batch 3300, loss[loss=0.1471, simple_loss=0.2456, pruned_loss=0.02432, over 7166.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2641, pruned_loss=0.03327, over 1426105.49 frames.], batch size: 19, lr: 3.10e-04
+2022-04-30 00:59:11,087 INFO [train.py:763] (0/8) Epoch 24, batch 3350, loss[loss=0.1701, simple_loss=0.268, pruned_loss=0.03615, over 7262.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2647, pruned_loss=0.03337, over 1422762.90 frames.], batch size: 19, lr: 3.10e-04
+2022-04-30 01:00:16,808 INFO [train.py:763] (0/8) Epoch 24, batch 3400, loss[loss=0.1652, simple_loss=0.2553, pruned_loss=0.03754, over 7276.00 frames.], tot_loss[loss=0.1652, simple_loss=0.264, pruned_loss=0.0332, over 1424156.98 frames.], batch size: 17, lr: 3.10e-04
+2022-04-30 01:01:22,338 INFO [train.py:763] (0/8) Epoch 24, batch 3450, loss[loss=0.1512, simple_loss=0.2578, pruned_loss=0.02236, over 7220.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2647, pruned_loss=0.0338, over 1420867.55 frames.], batch size: 21, lr: 3.10e-04
+2022-04-30 01:02:27,614 INFO [train.py:763] (0/8) Epoch 24, batch 3500, loss[loss=0.1473, simple_loss=0.2408, pruned_loss=0.0269, over 7137.00 frames.], tot_loss[loss=0.167, simple_loss=0.2657, pruned_loss=0.03417, over 1422322.30 frames.], batch size: 17, lr: 3.10e-04
+2022-04-30 01:03:33,201 INFO [train.py:763] (0/8) Epoch 24, batch 3550, loss[loss=0.1736, simple_loss=0.2814, pruned_loss=0.03284, over 7320.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2664, pruned_loss=0.03408, over 1423349.13 frames.], batch size: 20, lr: 3.10e-04
+2022-04-30 01:04:38,439 INFO [train.py:763] (0/8) Epoch 24, batch 3600, loss[loss=0.1624, simple_loss=0.2703, pruned_loss=0.02727, over 7201.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2664, pruned_loss=0.03397, over 1421668.10 frames.], batch size: 23, lr: 3.10e-04
+2022-04-30 01:05:45,319 INFO [train.py:763] (0/8) Epoch 24, batch 3650, loss[loss=0.187, simple_loss=0.2905, pruned_loss=0.04179, over 6657.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2669, pruned_loss=0.03414, over 1418210.01 frames.], batch size: 38, lr: 3.10e-04
+2022-04-30 01:06:51,864 INFO [train.py:763] (0/8) Epoch 24, batch 3700, loss[loss=0.1397, simple_loss=0.2401, pruned_loss=0.01968, over 7431.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2659, pruned_loss=0.03382, over 1421575.38 frames.], batch size: 20, lr: 3.10e-04
+2022-04-30 01:07:57,547 INFO [train.py:763] (0/8) Epoch 24, batch 3750, loss[loss=0.1771, simple_loss=0.2812, pruned_loss=0.03655, over 7384.00 frames.], tot_loss[loss=0.1668, simple_loss=0.266, pruned_loss=0.03381, over 1424397.70 frames.], batch size: 23, lr: 3.09e-04
+2022-04-30 01:09:02,955 INFO [train.py:763] (0/8) Epoch 24, batch 3800, loss[loss=0.1695, simple_loss=0.2585, pruned_loss=0.04025, over 4922.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2656, pruned_loss=0.03379, over 1421571.55 frames.], batch size: 52, lr: 3.09e-04
+2022-04-30 01:10:08,037 INFO [train.py:763] (0/8) Epoch 24, batch 3850, loss[loss=0.1482, simple_loss=0.2376, pruned_loss=0.02938, over 7272.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2663, pruned_loss=0.03432, over 1421087.05 frames.], batch size: 18, lr: 3.09e-04
+2022-04-30 01:11:13,751 INFO [train.py:763] (0/8) Epoch 24, batch 3900, loss[loss=0.1829, simple_loss=0.2762, pruned_loss=0.04476, over 7265.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2664, pruned_loss=0.03427, over 1420221.94 frames.], batch size: 19, lr: 3.09e-04
+2022-04-30 01:12:19,232 INFO [train.py:763] (0/8) Epoch 24, batch 3950, loss[loss=0.1434, simple_loss=0.2387, pruned_loss=0.02402, over 7394.00 frames.], tot_loss[loss=0.1669, simple_loss=0.266, pruned_loss=0.03386, over 1422822.86 frames.], batch size: 18, lr: 3.09e-04
+2022-04-30 01:13:24,354 INFO [train.py:763] (0/8) Epoch 24, batch 4000, loss[loss=0.166, simple_loss=0.2841, pruned_loss=0.02398, over 7319.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.03361, over 1422907.68 frames.], batch size: 21, lr: 3.09e-04
+2022-04-30 01:14:29,876 INFO [train.py:763] (0/8) Epoch 24, batch 4050, loss[loss=0.154, simple_loss=0.2485, pruned_loss=0.02969, over 7421.00 frames.], tot_loss[loss=0.1659, simple_loss=0.265, pruned_loss=0.0334, over 1421319.75 frames.], batch size: 20, lr: 3.09e-04
+2022-04-30 01:15:36,740 INFO [train.py:763] (0/8) Epoch 24, batch 4100, loss[loss=0.1752, simple_loss=0.2773, pruned_loss=0.03652, over 6370.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.03364, over 1421625.79 frames.], batch size: 37, lr: 3.09e-04
+2022-04-30 01:16:43,487 INFO [train.py:763] (0/8) Epoch 24, batch 4150, loss[loss=0.1839, simple_loss=0.2856, pruned_loss=0.04114, over 7214.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03351, over 1417913.38 frames.], batch size: 21, lr: 3.09e-04
+2022-04-30 01:17:50,211 INFO [train.py:763] (0/8) Epoch 24, batch 4200, loss[loss=0.1826, simple_loss=0.2893, pruned_loss=0.03799, over 7201.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2668, pruned_loss=0.03396, over 1419515.15 frames.], batch size: 23, lr: 3.09e-04
+2022-04-30 01:18:56,570 INFO [train.py:763] (0/8) Epoch 24, batch 4250, loss[loss=0.1709, simple_loss=0.2801, pruned_loss=0.03083, over 6367.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2659, pruned_loss=0.03358, over 1414501.74 frames.], batch size: 38, lr: 3.09e-04
+2022-04-30 01:20:02,375 INFO [train.py:763] (0/8) Epoch 24, batch 4300, loss[loss=0.1564, simple_loss=0.2638, pruned_loss=0.02449, over 7164.00 frames.], tot_loss[loss=0.166, simple_loss=0.2649, pruned_loss=0.03354, over 1414825.56 frames.], batch size: 19, lr: 3.09e-04
+2022-04-30 01:21:09,455 INFO [train.py:763] (0/8) Epoch 24, batch 4350, loss[loss=0.1732, simple_loss=0.2736, pruned_loss=0.03636, over 7326.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2641, pruned_loss=0.03348, over 1414616.53 frames.], batch size: 25, lr: 3.09e-04
+2022-04-30 01:22:16,145 INFO [train.py:763] (0/8) Epoch 24, batch 4400, loss[loss=0.1881, simple_loss=0.2822, pruned_loss=0.04701, over 7286.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03352, over 1413542.81 frames.], batch size: 24, lr: 3.09e-04
+2022-04-30 01:23:21,766 INFO [train.py:763] (0/8) Epoch 24, batch 4450, loss[loss=0.1881, simple_loss=0.2887, pruned_loss=0.04376, over 7265.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2668, pruned_loss=0.03372, over 1405280.68 frames.], batch size: 25, lr: 3.09e-04
+2022-04-30 01:24:28,248 INFO [train.py:763] (0/8) Epoch 24, batch 4500, loss[loss=0.1794, simple_loss=0.2681, pruned_loss=0.04537, over 5160.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2696, pruned_loss=0.03514, over 1390368.19 frames.], batch size: 52, lr: 3.08e-04
+2022-04-30 01:25:32,954 INFO [train.py:763] (0/8) Epoch 24, batch 4550, loss[loss=0.1993, simple_loss=0.2954, pruned_loss=0.05164, over 4888.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2711, pruned_loss=0.03559, over 1352626.16 frames.], batch size: 53, lr: 3.08e-04
+2022-04-30 01:26:22,274 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-24.pt
+2022-04-30 01:26:52,288 INFO [train.py:763] (0/8) Epoch 25, batch 0, loss[loss=0.1639, simple_loss=0.2691, pruned_loss=0.02931, over 7221.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2691, pruned_loss=0.02931, over 7221.00 frames.], batch size: 21, lr: 3.02e-04
+2022-04-30 01:27:58,475 INFO [train.py:763] (0/8) Epoch 25, batch 50, loss[loss=0.179, simple_loss=0.2746, pruned_loss=0.0417, over 7323.00 frames.], tot_loss[loss=0.162, simple_loss=0.2615, pruned_loss=0.03121, over 322727.58 frames.], batch size: 21, lr: 3.02e-04
+2022-04-30 01:29:03,634 INFO [train.py:763] (0/8) Epoch 25, batch 100, loss[loss=0.1837, simple_loss=0.2818, pruned_loss=0.04277, over 4935.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2639, pruned_loss=0.03141, over 566465.17 frames.], batch size: 53, lr: 3.02e-04
+2022-04-30 01:30:08,886 INFO [train.py:763] (0/8) Epoch 25, batch 150, loss[loss=0.1777, simple_loss=0.2651, pruned_loss=0.04508, over 7273.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2647, pruned_loss=0.03257, over 759810.14 frames.], batch size: 17, lr: 3.02e-04
+2022-04-30 01:31:14,541 INFO [train.py:763] (0/8) Epoch 25, batch 200, loss[loss=0.1747, simple_loss=0.2881, pruned_loss=0.03062, over 7359.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2641, pruned_loss=0.03237, over 907383.74 frames.], batch size: 23, lr: 3.02e-04
+2022-04-30 01:32:20,364 INFO [train.py:763] (0/8) Epoch 25, batch 250, loss[loss=0.1832, simple_loss=0.2831, pruned_loss=0.04166, over 7218.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2652, pruned_loss=0.03331, over 1020820.22 frames.], batch size: 22, lr: 3.02e-04
+2022-04-30 01:33:26,241 INFO [train.py:763] (0/8) Epoch 25, batch 300, loss[loss=0.1745, simple_loss=0.2787, pruned_loss=0.03512, over 7320.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.03342, over 1106930.31 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:34:31,520 INFO [train.py:763] (0/8) Epoch 25, batch 350, loss[loss=0.1709, simple_loss=0.2686, pruned_loss=0.03657, over 7165.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2643, pruned_loss=0.03293, over 1176034.47 frames.], batch size: 18, lr: 3.02e-04
+2022-04-30 01:35:36,793 INFO [train.py:763] (0/8) Epoch 25, batch 400, loss[loss=0.1387, simple_loss=0.2283, pruned_loss=0.02457, over 7391.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2645, pruned_loss=0.03305, over 1233814.84 frames.], batch size: 18, lr: 3.02e-04
+2022-04-30 01:36:42,362 INFO [train.py:763] (0/8) Epoch 25, batch 450, loss[loss=0.1925, simple_loss=0.2907, pruned_loss=0.04713, over 7421.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2636, pruned_loss=0.03258, over 1274826.20 frames.], batch size: 21, lr: 3.02e-04
+2022-04-30 01:37:47,505 INFO [train.py:763] (0/8) Epoch 25, batch 500, loss[loss=0.1552, simple_loss=0.2564, pruned_loss=0.02701, over 7378.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2639, pruned_loss=0.03272, over 1302495.68 frames.], batch size: 23, lr: 3.02e-04
+2022-04-30 01:38:52,812 INFO [train.py:763] (0/8) Epoch 25, batch 550, loss[loss=0.16, simple_loss=0.2735, pruned_loss=0.02331, over 7237.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2632, pruned_loss=0.03212, over 1328296.08 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:39:58,989 INFO [train.py:763] (0/8) Epoch 25, batch 600, loss[loss=0.1538, simple_loss=0.2594, pruned_loss=0.02413, over 7099.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2632, pruned_loss=0.03199, over 1346557.43 frames.], batch size: 28, lr: 3.02e-04
+2022-04-30 01:41:04,684 INFO [train.py:763] (0/8) Epoch 25, batch 650, loss[loss=0.1604, simple_loss=0.2618, pruned_loss=0.02953, over 7332.00 frames.], tot_loss[loss=0.164, simple_loss=0.2632, pruned_loss=0.0324, over 1360613.98 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:42:10,711 INFO [train.py:763] (0/8) Epoch 25, batch 700, loss[loss=0.1672, simple_loss=0.2703, pruned_loss=0.03208, over 7146.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2629, pruned_loss=0.03227, over 1373810.17 frames.], batch size: 20, lr: 3.02e-04
+2022-04-30 01:43:16,100 INFO [train.py:763] (0/8) Epoch 25, batch 750, loss[loss=0.1653, simple_loss=0.2726, pruned_loss=0.02897, over 7436.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2635, pruned_loss=0.03252, over 1389838.73 frames.], batch size: 20, lr: 3.01e-04
+2022-04-30 01:44:20,967 INFO [train.py:763] (0/8) Epoch 25, batch 800, loss[loss=0.1647, simple_loss=0.2699, pruned_loss=0.02977, over 6806.00 frames.], tot_loss[loss=0.165, simple_loss=0.2644, pruned_loss=0.03284, over 1395117.45 frames.], batch size: 31, lr: 3.01e-04
+2022-04-30 01:45:26,285 INFO [train.py:763] (0/8) Epoch 25, batch 850, loss[loss=0.1795, simple_loss=0.2806, pruned_loss=0.03916, over 7121.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2655, pruned_loss=0.0329, over 1405702.54 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:46:33,103 INFO [train.py:763] (0/8) Epoch 25, batch 900, loss[loss=0.1409, simple_loss=0.2368, pruned_loss=0.0225, over 7214.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2652, pruned_loss=0.033, over 1405967.27 frames.], batch size: 16, lr: 3.01e-04
+2022-04-30 01:47:40,158 INFO [train.py:763] (0/8) Epoch 25, batch 950, loss[loss=0.1345, simple_loss=0.2305, pruned_loss=0.01927, over 7276.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2653, pruned_loss=0.03285, over 1412214.71 frames.], batch size: 17, lr: 3.01e-04
+2022-04-30 01:48:46,811 INFO [train.py:763] (0/8) Epoch 25, batch 1000, loss[loss=0.1611, simple_loss=0.2611, pruned_loss=0.03057, over 7119.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2652, pruned_loss=0.03294, over 1410857.69 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:49:52,617 INFO [train.py:763] (0/8) Epoch 25, batch 1050, loss[loss=0.1638, simple_loss=0.2696, pruned_loss=0.02901, over 4932.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2654, pruned_loss=0.03298, over 1411927.79 frames.], batch size: 53, lr: 3.01e-04
+2022-04-30 01:50:59,153 INFO [train.py:763] (0/8) Epoch 25, batch 1100, loss[loss=0.1609, simple_loss=0.2698, pruned_loss=0.02601, over 7113.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2651, pruned_loss=0.03285, over 1413209.16 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:52:04,516 INFO [train.py:763] (0/8) Epoch 25, batch 1150, loss[loss=0.171, simple_loss=0.2731, pruned_loss=0.0344, over 7379.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2652, pruned_loss=0.03309, over 1417786.91 frames.], batch size: 23, lr: 3.01e-04
+2022-04-30 01:53:10,912 INFO [train.py:763] (0/8) Epoch 25, batch 1200, loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.02847, over 7119.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2647, pruned_loss=0.03357, over 1421593.88 frames.], batch size: 17, lr: 3.01e-04
+2022-04-30 01:54:16,909 INFO [train.py:763] (0/8) Epoch 25, batch 1250, loss[loss=0.1768, simple_loss=0.2707, pruned_loss=0.04141, over 7321.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2652, pruned_loss=0.03374, over 1423368.14 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:55:23,803 INFO [train.py:763] (0/8) Epoch 25, batch 1300, loss[loss=0.1463, simple_loss=0.243, pruned_loss=0.02476, over 7431.00 frames.], tot_loss[loss=0.1657, simple_loss=0.265, pruned_loss=0.03324, over 1426674.34 frames.], batch size: 20, lr: 3.01e-04
+2022-04-30 01:56:30,379 INFO [train.py:763] (0/8) Epoch 25, batch 1350, loss[loss=0.1535, simple_loss=0.2583, pruned_loss=0.02437, over 7332.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2657, pruned_loss=0.03321, over 1426719.17 frames.], batch size: 21, lr: 3.01e-04
+2022-04-30 01:57:36,868 INFO [train.py:763] (0/8) Epoch 25, batch 1400, loss[loss=0.1703, simple_loss=0.2738, pruned_loss=0.03342, over 7343.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2659, pruned_loss=0.0335, over 1427105.04 frames.], batch size: 22, lr: 3.01e-04
+2022-04-30 01:58:42,273 INFO [train.py:763] (0/8) Epoch 25, batch 1450, loss[loss=0.1544, simple_loss=0.2416, pruned_loss=0.03364, over 6994.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2649, pruned_loss=0.03324, over 1428697.25 frames.], batch size: 16, lr: 3.01e-04
+2022-04-30 01:59:49,364 INFO [train.py:763] (0/8) Epoch 25, batch 1500, loss[loss=0.1566, simple_loss=0.2614, pruned_loss=0.02593, over 7215.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2645, pruned_loss=0.03345, over 1428047.86 frames.], batch size: 21, lr: 3.00e-04
+2022-04-30 02:00:55,050 INFO [train.py:763] (0/8) Epoch 25, batch 1550, loss[loss=0.1388, simple_loss=0.2296, pruned_loss=0.02402, over 7139.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2646, pruned_loss=0.03361, over 1427361.92 frames.], batch size: 17, lr: 3.00e-04
+2022-04-30 02:02:00,077 INFO [train.py:763] (0/8) Epoch 25, batch 1600, loss[loss=0.1793, simple_loss=0.2796, pruned_loss=0.03952, over 7152.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2662, pruned_loss=0.03414, over 1424739.54 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:03:05,637 INFO [train.py:763] (0/8) Epoch 25, batch 1650, loss[loss=0.2122, simple_loss=0.3211, pruned_loss=0.05161, over 7098.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2647, pruned_loss=0.03385, over 1426111.02 frames.], batch size: 28, lr: 3.00e-04
+2022-04-30 02:04:10,614 INFO [train.py:763] (0/8) Epoch 25, batch 1700, loss[loss=0.1613, simple_loss=0.2653, pruned_loss=0.02872, over 7324.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2649, pruned_loss=0.03371, over 1425791.41 frames.], batch size: 21, lr: 3.00e-04
+2022-04-30 02:05:15,844 INFO [train.py:763] (0/8) Epoch 25, batch 1750, loss[loss=0.1486, simple_loss=0.2466, pruned_loss=0.02526, over 7132.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2642, pruned_loss=0.03305, over 1425329.92 frames.], batch size: 17, lr: 3.00e-04
+2022-04-30 02:06:21,043 INFO [train.py:763] (0/8) Epoch 25, batch 1800, loss[loss=0.1666, simple_loss=0.2666, pruned_loss=0.03331, over 7148.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2642, pruned_loss=0.03323, over 1422430.91 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:07:26,301 INFO [train.py:763] (0/8) Epoch 25, batch 1850, loss[loss=0.1572, simple_loss=0.2564, pruned_loss=0.02902, over 7435.00 frames.], tot_loss[loss=0.165, simple_loss=0.264, pruned_loss=0.03302, over 1422984.77 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:08:31,450 INFO [train.py:763] (0/8) Epoch 25, batch 1900, loss[loss=0.1413, simple_loss=0.2379, pruned_loss=0.02232, over 7126.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2644, pruned_loss=0.03299, over 1424975.14 frames.], batch size: 17, lr: 3.00e-04
+2022-04-30 02:09:36,781 INFO [train.py:763] (0/8) Epoch 25, batch 1950, loss[loss=0.2078, simple_loss=0.2958, pruned_loss=0.05989, over 5200.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2639, pruned_loss=0.03299, over 1422058.89 frames.], batch size: 52, lr: 3.00e-04
+2022-04-30 02:10:42,032 INFO [train.py:763] (0/8) Epoch 25, batch 2000, loss[loss=0.1571, simple_loss=0.25, pruned_loss=0.03205, over 7156.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2647, pruned_loss=0.03358, over 1418375.60 frames.], batch size: 19, lr: 3.00e-04
+2022-04-30 02:11:47,912 INFO [train.py:763] (0/8) Epoch 25, batch 2050, loss[loss=0.1514, simple_loss=0.2548, pruned_loss=0.02405, over 7333.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2642, pruned_loss=0.03357, over 1419612.32 frames.], batch size: 20, lr: 3.00e-04
+2022-04-30 02:12:54,277 INFO [train.py:763] (0/8) Epoch 25, batch 2100, loss[loss=0.1814, simple_loss=0.2867, pruned_loss=0.03805, over 7196.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03385, over 1418237.32 frames.], batch size: 22, lr: 3.00e-04
+2022-04-30 02:13:59,526 INFO [train.py:763] (0/8) Epoch 25, batch 2150, loss[loss=0.1419, simple_loss=0.2364, pruned_loss=0.02374, over 7173.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2656, pruned_loss=0.03396, over 1419703.27 frames.], batch size: 18, lr: 3.00e-04
+2022-04-30 02:15:05,487 INFO [train.py:763] (0/8) Epoch 25, batch 2200, loss[loss=0.1849, simple_loss=0.2821, pruned_loss=0.04387, over 7074.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2655, pruned_loss=0.03344, over 1422035.22 frames.], batch size: 28, lr: 3.00e-04
+2022-04-30 02:16:11,389 INFO [train.py:763] (0/8) Epoch 25, batch 2250, loss[loss=0.1706, simple_loss=0.275, pruned_loss=0.0331, over 7370.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2645, pruned_loss=0.03307, over 1424661.07 frames.], batch size: 23, lr: 3.00e-04
+2022-04-30 02:17:16,597 INFO [train.py:763] (0/8) Epoch 25, batch 2300, loss[loss=0.1654, simple_loss=0.2661, pruned_loss=0.03228, over 7064.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2659, pruned_loss=0.03336, over 1424696.42 frames.], batch size: 18, lr: 2.99e-04
+2022-04-30 02:18:23,424 INFO [train.py:763] (0/8) Epoch 25, batch 2350, loss[loss=0.1588, simple_loss=0.2555, pruned_loss=0.03104, over 7267.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2653, pruned_loss=0.03325, over 1424530.30 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:19:30,578 INFO [train.py:763] (0/8) Epoch 25, batch 2400, loss[loss=0.2141, simple_loss=0.3076, pruned_loss=0.06031, over 7380.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2648, pruned_loss=0.03327, over 1422541.33 frames.], batch size: 23, lr: 2.99e-04
+2022-04-30 02:20:35,966 INFO [train.py:763] (0/8) Epoch 25, batch 2450, loss[loss=0.1482, simple_loss=0.2528, pruned_loss=0.02183, over 6712.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03348, over 1421283.02 frames.], batch size: 31, lr: 2.99e-04
+2022-04-30 02:21:42,832 INFO [train.py:763] (0/8) Epoch 25, batch 2500, loss[loss=0.1521, simple_loss=0.2484, pruned_loss=0.02792, over 7367.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03357, over 1423353.62 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:22:48,790 INFO [train.py:763] (0/8) Epoch 25, batch 2550, loss[loss=0.1445, simple_loss=0.24, pruned_loss=0.02453, over 7411.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.0336, over 1426641.48 frames.], batch size: 18, lr: 2.99e-04
+2022-04-30 02:23:56,381 INFO [train.py:763] (0/8) Epoch 25, batch 2600, loss[loss=0.1633, simple_loss=0.2648, pruned_loss=0.03091, over 7168.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2654, pruned_loss=0.03358, over 1424665.95 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:25:02,543 INFO [train.py:763] (0/8) Epoch 25, batch 2650, loss[loss=0.1799, simple_loss=0.2896, pruned_loss=0.03508, over 7008.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2654, pruned_loss=0.03339, over 1419770.55 frames.], batch size: 28, lr: 2.99e-04
+2022-04-30 02:26:07,760 INFO [train.py:763] (0/8) Epoch 25, batch 2700, loss[loss=0.1516, simple_loss=0.2495, pruned_loss=0.02684, over 7258.00 frames.], tot_loss[loss=0.1655, simple_loss=0.265, pruned_loss=0.03296, over 1420438.96 frames.], batch size: 19, lr: 2.99e-04
+2022-04-30 02:27:12,943 INFO [train.py:763] (0/8) Epoch 25, batch 2750, loss[loss=0.1938, simple_loss=0.2912, pruned_loss=0.04821, over 7277.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2657, pruned_loss=0.03349, over 1413498.47 frames.], batch size: 25, lr: 2.99e-04
+2022-04-30 02:28:19,373 INFO [train.py:763] (0/8) Epoch 25, batch 2800, loss[loss=0.1641, simple_loss=0.2549, pruned_loss=0.03662, over 7265.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2649, pruned_loss=0.03317, over 1415409.96 frames.], batch size: 18, lr: 2.99e-04
+2022-04-30 02:29:24,934 INFO [train.py:763] (0/8) Epoch 25, batch 2850, loss[loss=0.1572, simple_loss=0.2593, pruned_loss=0.02752, over 7412.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2642, pruned_loss=0.03282, over 1411190.57 frames.], batch size: 21, lr: 2.99e-04
+2022-04-30 02:30:30,624 INFO [train.py:763] (0/8) Epoch 25, batch 2900, loss[loss=0.1661, simple_loss=0.2727, pruned_loss=0.02973, over 7144.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2644, pruned_loss=0.03298, over 1417491.11 frames.], batch size: 20, lr: 2.99e-04
+2022-04-30 02:31:35,887 INFO [train.py:763] (0/8) Epoch 25, batch 2950, loss[loss=0.1692, simple_loss=0.2753, pruned_loss=0.03159, over 7323.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2647, pruned_loss=0.03298, over 1418288.24 frames.], batch size: 20, lr: 2.99e-04
+2022-04-30 02:32:41,165 INFO [train.py:763] (0/8) Epoch 25, batch 3000, loss[loss=0.1649, simple_loss=0.2678, pruned_loss=0.031, over 6322.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2649, pruned_loss=0.03331, over 1422281.64 frames.], batch size: 37, lr: 2.99e-04
+2022-04-30 02:32:41,166 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 02:32:56,273 INFO [train.py:792] (0/8) Epoch 25, validation: loss=0.1697, simple_loss=0.2684, pruned_loss=0.03548, over 698248.00 frames.
+2022-04-30 02:34:02,077 INFO [train.py:763] (0/8) Epoch 25, batch 3050, loss[loss=0.1537, simple_loss=0.2568, pruned_loss=0.02534, over 7348.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2661, pruned_loss=0.03368, over 1422000.80 frames.], batch size: 22, lr: 2.99e-04
+2022-04-30 02:35:09,275 INFO [train.py:763] (0/8) Epoch 25, batch 3100, loss[loss=0.1737, simple_loss=0.2697, pruned_loss=0.03879, over 7254.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2658, pruned_loss=0.0335, over 1420011.71 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:36:16,365 INFO [train.py:763] (0/8) Epoch 25, batch 3150, loss[loss=0.1665, simple_loss=0.2563, pruned_loss=0.03837, over 7120.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2651, pruned_loss=0.03333, over 1419197.83 frames.], batch size: 17, lr: 2.98e-04
+2022-04-30 02:37:22,261 INFO [train.py:763] (0/8) Epoch 25, batch 3200, loss[loss=0.154, simple_loss=0.2496, pruned_loss=0.02921, over 7167.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2653, pruned_loss=0.03339, over 1421523.14 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:38:29,216 INFO [train.py:763] (0/8) Epoch 25, batch 3250, loss[loss=0.1729, simple_loss=0.2568, pruned_loss=0.04445, over 7268.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2636, pruned_loss=0.03344, over 1424616.47 frames.], batch size: 18, lr: 2.98e-04
+2022-04-30 02:39:35,761 INFO [train.py:763] (0/8) Epoch 25, batch 3300, loss[loss=0.1534, simple_loss=0.2588, pruned_loss=0.02396, over 7205.00 frames.], tot_loss[loss=0.166, simple_loss=0.2645, pruned_loss=0.03378, over 1416767.62 frames.], batch size: 26, lr: 2.98e-04
+2022-04-30 02:40:42,710 INFO [train.py:763] (0/8) Epoch 25, batch 3350, loss[loss=0.1883, simple_loss=0.2957, pruned_loss=0.04049, over 7326.00 frames.], tot_loss[loss=0.166, simple_loss=0.2646, pruned_loss=0.03376, over 1412954.53 frames.], batch size: 21, lr: 2.98e-04
+2022-04-30 02:41:49,875 INFO [train.py:763] (0/8) Epoch 25, batch 3400, loss[loss=0.1715, simple_loss=0.281, pruned_loss=0.03101, over 6339.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2632, pruned_loss=0.03345, over 1418336.06 frames.], batch size: 38, lr: 2.98e-04
+2022-04-30 02:42:55,397 INFO [train.py:763] (0/8) Epoch 25, batch 3450, loss[loss=0.1586, simple_loss=0.2621, pruned_loss=0.02753, over 7162.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2635, pruned_loss=0.03357, over 1418387.48 frames.], batch size: 18, lr: 2.98e-04
+2022-04-30 02:44:00,607 INFO [train.py:763] (0/8) Epoch 25, batch 3500, loss[loss=0.184, simple_loss=0.2885, pruned_loss=0.0398, over 7385.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2641, pruned_loss=0.03344, over 1417786.05 frames.], batch size: 23, lr: 2.98e-04
+2022-04-30 02:45:06,560 INFO [train.py:763] (0/8) Epoch 25, batch 3550, loss[loss=0.1627, simple_loss=0.2679, pruned_loss=0.02879, over 7415.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2639, pruned_loss=0.03287, over 1420269.58 frames.], batch size: 21, lr: 2.98e-04
+2022-04-30 02:46:12,320 INFO [train.py:763] (0/8) Epoch 25, batch 3600, loss[loss=0.1745, simple_loss=0.2775, pruned_loss=0.03573, over 7203.00 frames.], tot_loss[loss=0.164, simple_loss=0.2627, pruned_loss=0.03266, over 1425413.18 frames.], batch size: 23, lr: 2.98e-04
+2022-04-30 02:47:18,091 INFO [train.py:763] (0/8) Epoch 25, batch 3650, loss[loss=0.1547, simple_loss=0.2525, pruned_loss=0.02849, over 7257.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2633, pruned_loss=0.03258, over 1427619.72 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:48:25,758 INFO [train.py:763] (0/8) Epoch 25, batch 3700, loss[loss=0.1525, simple_loss=0.2457, pruned_loss=0.02967, over 7067.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2635, pruned_loss=0.033, over 1424804.40 frames.], batch size: 18, lr: 2.98e-04
+2022-04-30 02:49:32,867 INFO [train.py:763] (0/8) Epoch 25, batch 3750, loss[loss=0.1621, simple_loss=0.263, pruned_loss=0.03063, over 7155.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2639, pruned_loss=0.0333, over 1423751.80 frames.], batch size: 19, lr: 2.98e-04
+2022-04-30 02:50:38,250 INFO [train.py:763] (0/8) Epoch 25, batch 3800, loss[loss=0.1732, simple_loss=0.2736, pruned_loss=0.03636, over 6231.00 frames.], tot_loss[loss=0.1653, simple_loss=0.264, pruned_loss=0.03329, over 1421225.53 frames.], batch size: 37, lr: 2.98e-04
+2022-04-30 02:51:43,569 INFO [train.py:763] (0/8) Epoch 25, batch 3850, loss[loss=0.1578, simple_loss=0.2689, pruned_loss=0.0233, over 7149.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2649, pruned_loss=0.03364, over 1418770.30 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 02:52:57,815 INFO [train.py:763] (0/8) Epoch 25, batch 3900, loss[loss=0.1617, simple_loss=0.2582, pruned_loss=0.03256, over 7396.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2648, pruned_loss=0.03355, over 1421088.41 frames.], batch size: 18, lr: 2.97e-04
+2022-04-30 02:54:03,718 INFO [train.py:763] (0/8) Epoch 25, batch 3950, loss[loss=0.1853, simple_loss=0.2907, pruned_loss=0.03995, over 7238.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2646, pruned_loss=0.03356, over 1425570.82 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 02:55:09,641 INFO [train.py:763] (0/8) Epoch 25, batch 4000, loss[loss=0.1615, simple_loss=0.2595, pruned_loss=0.03175, over 7431.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2648, pruned_loss=0.03373, over 1419503.45 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 02:56:14,890 INFO [train.py:763] (0/8) Epoch 25, batch 4050, loss[loss=0.19, simple_loss=0.2861, pruned_loss=0.04694, over 7416.00 frames.], tot_loss[loss=0.166, simple_loss=0.2651, pruned_loss=0.03347, over 1421480.49 frames.], batch size: 21, lr: 2.97e-04
+2022-04-30 02:57:21,072 INFO [train.py:763] (0/8) Epoch 25, batch 4100, loss[loss=0.1839, simple_loss=0.279, pruned_loss=0.04444, over 7412.00 frames.], tot_loss[loss=0.167, simple_loss=0.2665, pruned_loss=0.03381, over 1419775.08 frames.], batch size: 21, lr: 2.97e-04
+2022-04-30 02:58:26,420 INFO [train.py:763] (0/8) Epoch 25, batch 4150, loss[loss=0.1606, simple_loss=0.2612, pruned_loss=0.03, over 7250.00 frames.], tot_loss[loss=0.1665, simple_loss=0.266, pruned_loss=0.03346, over 1424539.81 frames.], batch size: 19, lr: 2.97e-04
+2022-04-30 02:59:32,223 INFO [train.py:763] (0/8) Epoch 25, batch 4200, loss[loss=0.1997, simple_loss=0.294, pruned_loss=0.05267, over 7018.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2665, pruned_loss=0.0338, over 1420403.96 frames.], batch size: 28, lr: 2.97e-04
+2022-04-30 03:00:37,744 INFO [train.py:763] (0/8) Epoch 25, batch 4250, loss[loss=0.1592, simple_loss=0.2595, pruned_loss=0.02947, over 7173.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2657, pruned_loss=0.03355, over 1419966.93 frames.], batch size: 18, lr: 2.97e-04
+2022-04-30 03:01:43,178 INFO [train.py:763] (0/8) Epoch 25, batch 4300, loss[loss=0.1789, simple_loss=0.2876, pruned_loss=0.03513, over 7165.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.03338, over 1422903.00 frames.], batch size: 26, lr: 2.97e-04
+2022-04-30 03:03:06,203 INFO [train.py:763] (0/8) Epoch 25, batch 4350, loss[loss=0.163, simple_loss=0.2733, pruned_loss=0.02634, over 7231.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2658, pruned_loss=0.03369, over 1416146.85 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 03:04:20,104 INFO [train.py:763] (0/8) Epoch 25, batch 4400, loss[loss=0.1488, simple_loss=0.2491, pruned_loss=0.02429, over 7070.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2669, pruned_loss=0.03379, over 1415243.01 frames.], batch size: 18, lr: 2.97e-04
+2022-04-30 03:05:34,213 INFO [train.py:763] (0/8) Epoch 25, batch 4450, loss[loss=0.1536, simple_loss=0.2603, pruned_loss=0.02347, over 7287.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2664, pruned_loss=0.03376, over 1414125.74 frames.], batch size: 24, lr: 2.97e-04
+2022-04-30 03:06:39,196 INFO [train.py:763] (0/8) Epoch 25, batch 4500, loss[loss=0.1654, simple_loss=0.2671, pruned_loss=0.03184, over 7332.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2666, pruned_loss=0.03416, over 1398675.71 frames.], batch size: 20, lr: 2.97e-04
+2022-04-30 03:08:11,353 INFO [train.py:763] (0/8) Epoch 25, batch 4550, loss[loss=0.1811, simple_loss=0.2782, pruned_loss=0.04204, over 5393.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2666, pruned_loss=0.03436, over 1389667.99 frames.], batch size: 53, lr: 2.97e-04
+2022-04-30 03:09:01,316 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-25.pt
+2022-04-30 03:09:39,544 INFO [train.py:763] (0/8) Epoch 26, batch 0, loss[loss=0.139, simple_loss=0.2317, pruned_loss=0.0232, over 7161.00 frames.], tot_loss[loss=0.139, simple_loss=0.2317, pruned_loss=0.0232, over 7161.00 frames.], batch size: 18, lr: 2.91e-04
+2022-04-30 03:10:45,452 INFO [train.py:763] (0/8) Epoch 26, batch 50, loss[loss=0.1445, simple_loss=0.2416, pruned_loss=0.0237, over 7268.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2604, pruned_loss=0.03235, over 318683.69 frames.], batch size: 17, lr: 2.91e-04
+2022-04-30 03:11:50,714 INFO [train.py:763] (0/8) Epoch 26, batch 100, loss[loss=0.144, simple_loss=0.2342, pruned_loss=0.02692, over 7270.00 frames.], tot_loss[loss=0.163, simple_loss=0.262, pruned_loss=0.03199, over 562659.31 frames.], batch size: 17, lr: 2.91e-04
+2022-04-30 03:12:56,053 INFO [train.py:763] (0/8) Epoch 26, batch 150, loss[loss=0.1716, simple_loss=0.2734, pruned_loss=0.03488, over 6309.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2635, pruned_loss=0.03264, over 751176.56 frames.], batch size: 37, lr: 2.91e-04
+2022-04-30 03:14:01,251 INFO [train.py:763] (0/8) Epoch 26, batch 200, loss[loss=0.1841, simple_loss=0.2889, pruned_loss=0.03959, over 7161.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2646, pruned_loss=0.03292, over 894486.09 frames.], batch size: 26, lr: 2.91e-04
+2022-04-30 03:15:07,044 INFO [train.py:763] (0/8) Epoch 26, batch 250, loss[loss=0.1593, simple_loss=0.2666, pruned_loss=0.02602, over 6173.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2656, pruned_loss=0.0335, over 1006397.62 frames.], batch size: 37, lr: 2.91e-04
+2022-04-30 03:16:13,164 INFO [train.py:763] (0/8) Epoch 26, batch 300, loss[loss=0.1683, simple_loss=0.2818, pruned_loss=0.02742, over 6385.00 frames.], tot_loss[loss=0.1656, simple_loss=0.265, pruned_loss=0.03308, over 1100207.58 frames.], batch size: 37, lr: 2.91e-04
+2022-04-30 03:17:18,450 INFO [train.py:763] (0/8) Epoch 26, batch 350, loss[loss=0.1661, simple_loss=0.2685, pruned_loss=0.0319, over 6802.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2643, pruned_loss=0.0331, over 1167973.78 frames.], batch size: 31, lr: 2.91e-04
+2022-04-30 03:18:23,755 INFO [train.py:763] (0/8) Epoch 26, batch 400, loss[loss=0.1507, simple_loss=0.2518, pruned_loss=0.02482, over 7153.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2634, pruned_loss=0.03265, over 1228108.85 frames.], batch size: 20, lr: 2.91e-04
+2022-04-30 03:19:29,473 INFO [train.py:763] (0/8) Epoch 26, batch 450, loss[loss=0.1567, simple_loss=0.2596, pruned_loss=0.02685, over 7236.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2628, pruned_loss=0.03198, over 1275600.31 frames.], batch size: 20, lr: 2.91e-04
+2022-04-30 03:20:34,849 INFO [train.py:763] (0/8) Epoch 26, batch 500, loss[loss=0.2004, simple_loss=0.2877, pruned_loss=0.0566, over 4904.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2625, pruned_loss=0.03185, over 1307284.81 frames.], batch size: 52, lr: 2.91e-04
+2022-04-30 03:21:40,172 INFO [train.py:763] (0/8) Epoch 26, batch 550, loss[loss=0.1726, simple_loss=0.2724, pruned_loss=0.03642, over 7202.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2634, pruned_loss=0.03206, over 1332638.13 frames.], batch size: 22, lr: 2.90e-04
+2022-04-30 03:22:45,581 INFO [train.py:763] (0/8) Epoch 26, batch 600, loss[loss=0.1748, simple_loss=0.2703, pruned_loss=0.03965, over 7268.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2637, pruned_loss=0.03232, over 1355752.78 frames.], batch size: 19, lr: 2.90e-04
+2022-04-30 03:23:51,107 INFO [train.py:763] (0/8) Epoch 26, batch 650, loss[loss=0.151, simple_loss=0.2463, pruned_loss=0.02781, over 7286.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2626, pruned_loss=0.03207, over 1372070.36 frames.], batch size: 18, lr: 2.90e-04
+2022-04-30 03:24:56,239 INFO [train.py:763] (0/8) Epoch 26, batch 700, loss[loss=0.1392, simple_loss=0.2485, pruned_loss=0.0149, over 7124.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2635, pruned_loss=0.03195, over 1382151.38 frames.], batch size: 21, lr: 2.90e-04
+2022-04-30 03:25:10,848 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-120000.pt
+2022-04-30 03:26:12,129 INFO [train.py:763] (0/8) Epoch 26, batch 750, loss[loss=0.1542, simple_loss=0.2545, pruned_loss=0.02693, over 7139.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2631, pruned_loss=0.03194, over 1390188.76 frames.], batch size: 20, lr: 2.90e-04
+2022-04-30 03:27:17,955 INFO [train.py:763] (0/8) Epoch 26, batch 800, loss[loss=0.1666, simple_loss=0.264, pruned_loss=0.0346, over 7233.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2633, pruned_loss=0.03222, over 1395707.44 frames.], batch size: 20, lr: 2.90e-04
+2022-04-30 03:28:23,827 INFO [train.py:763] (0/8) Epoch 26, batch 850, loss[loss=0.2104, simple_loss=0.2912, pruned_loss=0.06486, over 4971.00 frames.], tot_loss[loss=0.1653, simple_loss=0.265, pruned_loss=0.03282, over 1398517.03 frames.], batch size: 52, lr: 2.90e-04
+2022-04-30 03:29:29,382 INFO [train.py:763] (0/8) Epoch 26, batch 900, loss[loss=0.129, simple_loss=0.2216, pruned_loss=0.01823, over 7416.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2639, pruned_loss=0.03234, over 1407258.18 frames.], batch size: 18, lr: 2.90e-04
+2022-04-30 03:30:35,254 INFO [train.py:763] (0/8) Epoch 26, batch 950, loss[loss=0.1402, simple_loss=0.2305, pruned_loss=0.02493, over 6754.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2641, pruned_loss=0.03216, over 1408063.43 frames.], batch size: 15, lr: 2.90e-04
+2022-04-30 03:31:40,718 INFO [train.py:763] (0/8) Epoch 26, batch 1000, loss[loss=0.1909, simple_loss=0.299, pruned_loss=0.04139, over 7295.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2652, pruned_loss=0.03263, over 1411402.02 frames.], batch size: 24, lr: 2.90e-04
+2022-04-30 03:32:46,143 INFO [train.py:763] (0/8) Epoch 26, batch 1050, loss[loss=0.1613, simple_loss=0.2659, pruned_loss=0.02834, over 7193.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2651, pruned_loss=0.0326, over 1416533.20 frames.], batch size: 23, lr: 2.90e-04
+2022-04-30 03:33:51,500 INFO [train.py:763] (0/8) Epoch 26, batch 1100, loss[loss=0.1959, simple_loss=0.2934, pruned_loss=0.04923, over 7200.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2637, pruned_loss=0.03226, over 1421564.10 frames.], batch size: 22, lr: 2.90e-04
+2022-04-30 03:34:56,897 INFO [train.py:763] (0/8) Epoch 26, batch 1150, loss[loss=0.1595, simple_loss=0.2601, pruned_loss=0.02943, over 7163.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2646, pruned_loss=0.03244, over 1423282.29 frames.], batch size: 19, lr: 2.90e-04
+2022-04-30 03:36:02,475 INFO [train.py:763] (0/8) Epoch 26, batch 1200, loss[loss=0.1879, simple_loss=0.2828, pruned_loss=0.04647, over 7299.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2647, pruned_loss=0.03255, over 1427357.40 frames.], batch size: 24, lr: 2.90e-04
+2022-04-30 03:37:08,334 INFO [train.py:763] (0/8) Epoch 26, batch 1250, loss[loss=0.2015, simple_loss=0.3062, pruned_loss=0.0484, over 6609.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2643, pruned_loss=0.03235, over 1426794.29 frames.], batch size: 39, lr: 2.90e-04
+2022-04-30 03:38:14,068 INFO [train.py:763] (0/8) Epoch 26, batch 1300, loss[loss=0.1489, simple_loss=0.2396, pruned_loss=0.02908, over 7277.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2643, pruned_loss=0.03263, over 1422661.55 frames.], batch size: 18, lr: 2.90e-04
+2022-04-30 03:39:20,370 INFO [train.py:763] (0/8) Epoch 26, batch 1350, loss[loss=0.1623, simple_loss=0.2489, pruned_loss=0.03788, over 7418.00 frames.], tot_loss[loss=0.1643, simple_loss=0.263, pruned_loss=0.03281, over 1426024.12 frames.], batch size: 18, lr: 2.89e-04
+2022-04-30 03:40:25,493 INFO [train.py:763] (0/8) Epoch 26, batch 1400, loss[loss=0.1956, simple_loss=0.3035, pruned_loss=0.04383, over 7212.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2628, pruned_loss=0.03243, over 1418261.51 frames.], batch size: 23, lr: 2.89e-04
+2022-04-30 03:41:30,978 INFO [train.py:763] (0/8) Epoch 26, batch 1450, loss[loss=0.1455, simple_loss=0.245, pruned_loss=0.02303, over 7279.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2635, pruned_loss=0.03257, over 1420623.83 frames.], batch size: 18, lr: 2.89e-04
+2022-04-30 03:42:36,436 INFO [train.py:763] (0/8) Epoch 26, batch 1500, loss[loss=0.1791, simple_loss=0.2673, pruned_loss=0.04549, over 4679.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2638, pruned_loss=0.03297, over 1416240.33 frames.], batch size: 52, lr: 2.89e-04
+2022-04-30 03:43:42,614 INFO [train.py:763] (0/8) Epoch 26, batch 1550, loss[loss=0.1656, simple_loss=0.2763, pruned_loss=0.0274, over 7123.00 frames.], tot_loss[loss=0.1649, simple_loss=0.264, pruned_loss=0.0329, over 1420495.75 frames.], batch size: 21, lr: 2.89e-04
+2022-04-30 03:44:49,283 INFO [train.py:763] (0/8) Epoch 26, batch 1600, loss[loss=0.1691, simple_loss=0.2696, pruned_loss=0.03435, over 7253.00 frames.], tot_loss[loss=0.164, simple_loss=0.2629, pruned_loss=0.03253, over 1424218.31 frames.], batch size: 19, lr: 2.89e-04
+2022-04-30 03:45:54,884 INFO [train.py:763] (0/8) Epoch 26, batch 1650, loss[loss=0.1899, simple_loss=0.3011, pruned_loss=0.03934, over 7171.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2628, pruned_loss=0.03267, over 1428012.18 frames.], batch size: 26, lr: 2.89e-04
+2022-04-30 03:47:00,417 INFO [train.py:763] (0/8) Epoch 26, batch 1700, loss[loss=0.1516, simple_loss=0.2634, pruned_loss=0.01985, over 7335.00 frames.], tot_loss[loss=0.164, simple_loss=0.2629, pruned_loss=0.03255, over 1429913.49 frames.], batch size: 22, lr: 2.89e-04
+2022-04-30 03:48:06,061 INFO [train.py:763] (0/8) Epoch 26, batch 1750, loss[loss=0.1908, simple_loss=0.2904, pruned_loss=0.0456, over 7179.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2645, pruned_loss=0.03307, over 1431037.02 frames.], batch size: 26, lr: 2.89e-04
+2022-04-30 03:49:13,315 INFO [train.py:763] (0/8) Epoch 26, batch 1800, loss[loss=0.1649, simple_loss=0.2582, pruned_loss=0.03584, over 7118.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2643, pruned_loss=0.03276, over 1428957.91 frames.], batch size: 21, lr: 2.89e-04
+2022-04-30 03:50:19,938 INFO [train.py:763] (0/8) Epoch 26, batch 1850, loss[loss=0.1896, simple_loss=0.2916, pruned_loss=0.04384, over 4831.00 frames.], tot_loss[loss=0.165, simple_loss=0.2644, pruned_loss=0.03281, over 1428443.49 frames.], batch size: 52, lr: 2.89e-04
+2022-04-30 03:51:25,631 INFO [train.py:763] (0/8) Epoch 26, batch 1900, loss[loss=0.1691, simple_loss=0.2621, pruned_loss=0.03804, over 7361.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2636, pruned_loss=0.0327, over 1427443.16 frames.], batch size: 19, lr: 2.89e-04
+2022-04-30 03:52:30,904 INFO [train.py:763] (0/8) Epoch 26, batch 1950, loss[loss=0.149, simple_loss=0.2521, pruned_loss=0.02295, over 6435.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2634, pruned_loss=0.0327, over 1424328.00 frames.], batch size: 38, lr: 2.89e-04
+2022-04-30 03:53:36,223 INFO [train.py:763] (0/8) Epoch 26, batch 2000, loss[loss=0.1882, simple_loss=0.2901, pruned_loss=0.04316, over 6816.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2624, pruned_loss=0.0322, over 1423709.74 frames.], batch size: 31, lr: 2.89e-04
+2022-04-30 03:54:41,496 INFO [train.py:763] (0/8) Epoch 26, batch 2050, loss[loss=0.1657, simple_loss=0.2613, pruned_loss=0.035, over 7207.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2634, pruned_loss=0.03249, over 1427149.97 frames.], batch size: 26, lr: 2.89e-04
+2022-04-30 03:55:48,155 INFO [train.py:763] (0/8) Epoch 26, batch 2100, loss[loss=0.1946, simple_loss=0.2857, pruned_loss=0.05173, over 7217.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2629, pruned_loss=0.03228, over 1424475.37 frames.], batch size: 22, lr: 2.89e-04
+2022-04-30 03:56:54,318 INFO [train.py:763] (0/8) Epoch 26, batch 2150, loss[loss=0.1883, simple_loss=0.2892, pruned_loss=0.04368, over 7278.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2638, pruned_loss=0.03241, over 1427725.49 frames.], batch size: 25, lr: 2.89e-04
+2022-04-30 03:57:59,849 INFO [train.py:763] (0/8) Epoch 26, batch 2200, loss[loss=0.1751, simple_loss=0.2685, pruned_loss=0.04086, over 7249.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2636, pruned_loss=0.03254, over 1426389.88 frames.], batch size: 20, lr: 2.88e-04
+2022-04-30 03:59:06,006 INFO [train.py:763] (0/8) Epoch 26, batch 2250, loss[loss=0.1523, simple_loss=0.2439, pruned_loss=0.03036, over 7001.00 frames.], tot_loss[loss=0.1646, simple_loss=0.264, pruned_loss=0.0326, over 1431381.31 frames.], batch size: 16, lr: 2.88e-04
+2022-04-30 04:00:11,175 INFO [train.py:763] (0/8) Epoch 26, batch 2300, loss[loss=0.1293, simple_loss=0.2264, pruned_loss=0.01606, over 7131.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2636, pruned_loss=0.03225, over 1432814.98 frames.], batch size: 17, lr: 2.88e-04
+2022-04-30 04:01:17,209 INFO [train.py:763] (0/8) Epoch 26, batch 2350, loss[loss=0.1699, simple_loss=0.2848, pruned_loss=0.02751, over 7144.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2647, pruned_loss=0.03259, over 1431210.68 frames.], batch size: 20, lr: 2.88e-04
+2022-04-30 04:02:24,611 INFO [train.py:763] (0/8) Epoch 26, batch 2400, loss[loss=0.1638, simple_loss=0.2645, pruned_loss=0.03155, over 7278.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2651, pruned_loss=0.03266, over 1433016.37 frames.], batch size: 24, lr: 2.88e-04
+2022-04-30 04:03:31,278 INFO [train.py:763] (0/8) Epoch 26, batch 2450, loss[loss=0.1607, simple_loss=0.2592, pruned_loss=0.03109, over 7226.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2645, pruned_loss=0.03223, over 1436019.32 frames.], batch size: 20, lr: 2.88e-04
+2022-04-30 04:04:36,621 INFO [train.py:763] (0/8) Epoch 26, batch 2500, loss[loss=0.1723, simple_loss=0.2758, pruned_loss=0.03436, over 7222.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2642, pruned_loss=0.03239, over 1437407.35 frames.], batch size: 21, lr: 2.88e-04
+2022-04-30 04:05:41,766 INFO [train.py:763] (0/8) Epoch 26, batch 2550, loss[loss=0.1605, simple_loss=0.2668, pruned_loss=0.02715, over 6700.00 frames.], tot_loss[loss=0.1642, simple_loss=0.264, pruned_loss=0.03223, over 1434672.14 frames.], batch size: 31, lr: 2.88e-04
+2022-04-30 04:06:47,205 INFO [train.py:763] (0/8) Epoch 26, batch 2600, loss[loss=0.1578, simple_loss=0.2454, pruned_loss=0.03504, over 7213.00 frames.], tot_loss[loss=0.164, simple_loss=0.2636, pruned_loss=0.0322, over 1434950.06 frames.], batch size: 16, lr: 2.88e-04
+2022-04-30 04:07:52,619 INFO [train.py:763] (0/8) Epoch 26, batch 2650, loss[loss=0.1996, simple_loss=0.3032, pruned_loss=0.04799, over 7278.00 frames.], tot_loss[loss=0.1644, simple_loss=0.264, pruned_loss=0.03239, over 1430733.56 frames.], batch size: 24, lr: 2.88e-04
+2022-04-30 04:08:58,044 INFO [train.py:763] (0/8) Epoch 26, batch 2700, loss[loss=0.1683, simple_loss=0.2704, pruned_loss=0.03313, over 7332.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2642, pruned_loss=0.03243, over 1428807.15 frames.], batch size: 22, lr: 2.88e-04
+2022-04-30 04:10:03,967 INFO [train.py:763] (0/8) Epoch 26, batch 2750, loss[loss=0.1497, simple_loss=0.2555, pruned_loss=0.0219, over 7154.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2635, pruned_loss=0.03213, over 1428094.33 frames.], batch size: 19, lr: 2.88e-04
+2022-04-30 04:11:09,749 INFO [train.py:763] (0/8) Epoch 26, batch 2800, loss[loss=0.1783, simple_loss=0.2824, pruned_loss=0.03714, over 7308.00 frames.], tot_loss[loss=0.164, simple_loss=0.2639, pruned_loss=0.03207, over 1426657.52 frames.], batch size: 25, lr: 2.88e-04
+2022-04-30 04:12:16,490 INFO [train.py:763] (0/8) Epoch 26, batch 2850, loss[loss=0.1609, simple_loss=0.2478, pruned_loss=0.037, over 7259.00 frames.], tot_loss[loss=0.165, simple_loss=0.265, pruned_loss=0.03247, over 1425863.83 frames.], batch size: 19, lr: 2.88e-04
+2022-04-30 04:13:21,772 INFO [train.py:763] (0/8) Epoch 26, batch 2900, loss[loss=0.1514, simple_loss=0.2517, pruned_loss=0.02554, over 7173.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2649, pruned_loss=0.03263, over 1425318.31 frames.], batch size: 19, lr: 2.88e-04
+2022-04-30 04:14:26,930 INFO [train.py:763] (0/8) Epoch 26, batch 2950, loss[loss=0.185, simple_loss=0.2886, pruned_loss=0.0407, over 7120.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2653, pruned_loss=0.03301, over 1420125.37 frames.], batch size: 21, lr: 2.88e-04
+2022-04-30 04:15:32,487 INFO [train.py:763] (0/8) Epoch 26, batch 3000, loss[loss=0.1597, simple_loss=0.2617, pruned_loss=0.02886, over 7411.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2649, pruned_loss=0.03267, over 1419564.25 frames.], batch size: 21, lr: 2.88e-04
+2022-04-30 04:15:32,488 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 04:15:47,843 INFO [train.py:792] (0/8) Epoch 26, validation: loss=0.1682, simple_loss=0.2653, pruned_loss=0.03549, over 698248.00 frames.
+2022-04-30 04:16:54,063 INFO [train.py:763] (0/8) Epoch 26, batch 3050, loss[loss=0.1872, simple_loss=0.2947, pruned_loss=0.03984, over 7118.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2641, pruned_loss=0.03239, over 1410144.66 frames.], batch size: 21, lr: 2.87e-04
+2022-04-30 04:17:59,873 INFO [train.py:763] (0/8) Epoch 26, batch 3100, loss[loss=0.1782, simple_loss=0.2791, pruned_loss=0.03861, over 7322.00 frames.], tot_loss[loss=0.165, simple_loss=0.2646, pruned_loss=0.03272, over 1416536.87 frames.], batch size: 21, lr: 2.87e-04
+2022-04-30 04:19:05,976 INFO [train.py:763] (0/8) Epoch 26, batch 3150, loss[loss=0.1788, simple_loss=0.2727, pruned_loss=0.04243, over 7212.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2647, pruned_loss=0.03279, over 1417205.14 frames.], batch size: 22, lr: 2.87e-04
+2022-04-30 04:20:11,643 INFO [train.py:763] (0/8) Epoch 26, batch 3200, loss[loss=0.1828, simple_loss=0.2878, pruned_loss=0.03885, over 7209.00 frames.], tot_loss[loss=0.1654, simple_loss=0.265, pruned_loss=0.03291, over 1419361.58 frames.], batch size: 23, lr: 2.87e-04
+2022-04-30 04:21:17,161 INFO [train.py:763] (0/8) Epoch 26, batch 3250, loss[loss=0.1726, simple_loss=0.2846, pruned_loss=0.03025, over 6574.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2648, pruned_loss=0.03287, over 1419864.38 frames.], batch size: 38, lr: 2.87e-04
+2022-04-30 04:22:22,724 INFO [train.py:763] (0/8) Epoch 26, batch 3300, loss[loss=0.1609, simple_loss=0.2617, pruned_loss=0.03006, over 6823.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2652, pruned_loss=0.03305, over 1418973.11 frames.], batch size: 31, lr: 2.87e-04
+2022-04-30 04:23:27,756 INFO [train.py:763] (0/8) Epoch 26, batch 3350, loss[loss=0.1565, simple_loss=0.2643, pruned_loss=0.02437, over 7325.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2664, pruned_loss=0.0334, over 1419321.29 frames.], batch size: 22, lr: 2.87e-04
+2022-04-30 04:24:33,270 INFO [train.py:763] (0/8) Epoch 26, batch 3400, loss[loss=0.1783, simple_loss=0.2725, pruned_loss=0.04209, over 7153.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2663, pruned_loss=0.03324, over 1416887.74 frames.], batch size: 20, lr: 2.87e-04
+2022-04-30 04:25:38,630 INFO [train.py:763] (0/8) Epoch 26, batch 3450, loss[loss=0.1801, simple_loss=0.2867, pruned_loss=0.03671, over 7338.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2662, pruned_loss=0.03298, over 1420481.24 frames.], batch size: 22, lr: 2.87e-04
+2022-04-30 04:26:44,107 INFO [train.py:763] (0/8) Epoch 26, batch 3500, loss[loss=0.1468, simple_loss=0.233, pruned_loss=0.03029, over 7235.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2653, pruned_loss=0.0328, over 1423286.83 frames.], batch size: 16, lr: 2.87e-04
+2022-04-30 04:27:49,690 INFO [train.py:763] (0/8) Epoch 26, batch 3550, loss[loss=0.1755, simple_loss=0.2661, pruned_loss=0.04245, over 4904.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.03255, over 1415944.26 frames.], batch size: 52, lr: 2.87e-04
+2022-04-30 04:28:54,787 INFO [train.py:763] (0/8) Epoch 26, batch 3600, loss[loss=0.164, simple_loss=0.2756, pruned_loss=0.02615, over 7169.00 frames.], tot_loss[loss=0.165, simple_loss=0.2648, pruned_loss=0.03263, over 1413435.39 frames.], batch size: 19, lr: 2.87e-04
+2022-04-30 04:30:00,889 INFO [train.py:763] (0/8) Epoch 26, batch 3650, loss[loss=0.1359, simple_loss=0.228, pruned_loss=0.02194, over 7063.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2645, pruned_loss=0.03236, over 1413149.09 frames.], batch size: 18, lr: 2.87e-04
+2022-04-30 04:31:07,248 INFO [train.py:763] (0/8) Epoch 26, batch 3700, loss[loss=0.143, simple_loss=0.2304, pruned_loss=0.02775, over 7271.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2648, pruned_loss=0.03287, over 1412269.27 frames.], batch size: 18, lr: 2.87e-04
+2022-04-30 04:32:12,935 INFO [train.py:763] (0/8) Epoch 26, batch 3750, loss[loss=0.1593, simple_loss=0.2691, pruned_loss=0.0248, over 7227.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2635, pruned_loss=0.03258, over 1416728.47 frames.], batch size: 21, lr: 2.87e-04
+2022-04-30 04:33:19,999 INFO [train.py:763] (0/8) Epoch 26, batch 3800, loss[loss=0.1687, simple_loss=0.2613, pruned_loss=0.03804, over 7343.00 frames.], tot_loss[loss=0.1632, simple_loss=0.262, pruned_loss=0.03221, over 1420642.06 frames.], batch size: 20, lr: 2.87e-04
+2022-04-30 04:34:26,379 INFO [train.py:763] (0/8) Epoch 26, batch 3850, loss[loss=0.1308, simple_loss=0.2173, pruned_loss=0.02217, over 7414.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2632, pruned_loss=0.03288, over 1414351.31 frames.], batch size: 18, lr: 2.87e-04
+2022-04-30 04:35:31,746 INFO [train.py:763] (0/8) Epoch 26, batch 3900, loss[loss=0.1542, simple_loss=0.2513, pruned_loss=0.0286, over 7004.00 frames.], tot_loss[loss=0.165, simple_loss=0.2639, pruned_loss=0.03305, over 1415551.25 frames.], batch size: 28, lr: 2.86e-04
+2022-04-30 04:36:37,012 INFO [train.py:763] (0/8) Epoch 26, batch 3950, loss[loss=0.1753, simple_loss=0.2693, pruned_loss=0.04069, over 7364.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2644, pruned_loss=0.03297, over 1419890.48 frames.], batch size: 19, lr: 2.86e-04
+2022-04-30 04:37:42,776 INFO [train.py:763] (0/8) Epoch 26, batch 4000, loss[loss=0.1778, simple_loss=0.2803, pruned_loss=0.03769, over 7150.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2634, pruned_loss=0.03265, over 1425307.57 frames.], batch size: 28, lr: 2.86e-04
+2022-04-30 04:38:48,123 INFO [train.py:763] (0/8) Epoch 26, batch 4050, loss[loss=0.1579, simple_loss=0.2628, pruned_loss=0.02649, over 7323.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2635, pruned_loss=0.03271, over 1426139.68 frames.], batch size: 20, lr: 2.86e-04
+2022-04-30 04:39:53,367 INFO [train.py:763] (0/8) Epoch 26, batch 4100, loss[loss=0.1603, simple_loss=0.2541, pruned_loss=0.03324, over 7327.00 frames.], tot_loss[loss=0.164, simple_loss=0.2632, pruned_loss=0.03234, over 1424109.87 frames.], batch size: 20, lr: 2.86e-04
+2022-04-30 04:40:58,515 INFO [train.py:763] (0/8) Epoch 26, batch 4150, loss[loss=0.1774, simple_loss=0.2851, pruned_loss=0.03486, over 7112.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2641, pruned_loss=0.03246, over 1421337.44 frames.], batch size: 21, lr: 2.86e-04
+2022-04-30 04:42:03,904 INFO [train.py:763] (0/8) Epoch 26, batch 4200, loss[loss=0.1584, simple_loss=0.2653, pruned_loss=0.02576, over 7339.00 frames.], tot_loss[loss=0.164, simple_loss=0.2638, pruned_loss=0.03213, over 1422825.45 frames.], batch size: 22, lr: 2.86e-04
+2022-04-30 04:43:08,782 INFO [train.py:763] (0/8) Epoch 26, batch 4250, loss[loss=0.1535, simple_loss=0.2572, pruned_loss=0.02495, over 7411.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2653, pruned_loss=0.03285, over 1415701.32 frames.], batch size: 21, lr: 2.86e-04
+2022-04-30 04:44:14,527 INFO [train.py:763] (0/8) Epoch 26, batch 4300, loss[loss=0.1666, simple_loss=0.2795, pruned_loss=0.02684, over 6836.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2653, pruned_loss=0.03268, over 1413874.06 frames.], batch size: 31, lr: 2.86e-04
+2022-04-30 04:45:19,679 INFO [train.py:763] (0/8) Epoch 26, batch 4350, loss[loss=0.1627, simple_loss=0.2589, pruned_loss=0.03327, over 6982.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2654, pruned_loss=0.03281, over 1413916.30 frames.], batch size: 16, lr: 2.86e-04
+2022-04-30 04:46:24,708 INFO [train.py:763] (0/8) Epoch 26, batch 4400, loss[loss=0.1681, simple_loss=0.2725, pruned_loss=0.03191, over 6351.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2666, pruned_loss=0.0335, over 1400820.87 frames.], batch size: 37, lr: 2.86e-04
+2022-04-30 04:47:29,338 INFO [train.py:763] (0/8) Epoch 26, batch 4450, loss[loss=0.1868, simple_loss=0.2951, pruned_loss=0.03919, over 7333.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2655, pruned_loss=0.03345, over 1395644.25 frames.], batch size: 22, lr: 2.86e-04
+2022-04-30 04:48:34,536 INFO [train.py:763] (0/8) Epoch 26, batch 4500, loss[loss=0.1684, simple_loss=0.2677, pruned_loss=0.03459, over 7155.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2654, pruned_loss=0.03338, over 1387344.62 frames.], batch size: 18, lr: 2.86e-04
+2022-04-30 04:49:39,411 INFO [train.py:763] (0/8) Epoch 26, batch 4550, loss[loss=0.1889, simple_loss=0.2823, pruned_loss=0.04769, over 4806.00 frames.], tot_loss[loss=0.1652, simple_loss=0.264, pruned_loss=0.03318, over 1371546.61 frames.], batch size: 52, lr: 2.86e-04
+2022-04-30 04:50:28,669 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-26.pt
+2022-04-30 04:51:07,360 INFO [train.py:763] (0/8) Epoch 27, batch 0, loss[loss=0.1537, simple_loss=0.2574, pruned_loss=0.02503, over 7259.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2574, pruned_loss=0.02503, over 7259.00 frames.], batch size: 19, lr: 2.81e-04
+2022-04-30 04:52:13,087 INFO [train.py:763] (0/8) Epoch 27, batch 50, loss[loss=0.1499, simple_loss=0.2539, pruned_loss=0.02291, over 7258.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03126, over 321373.27 frames.], batch size: 19, lr: 2.81e-04
+2022-04-30 04:53:19,219 INFO [train.py:763] (0/8) Epoch 27, batch 100, loss[loss=0.1847, simple_loss=0.2864, pruned_loss=0.04152, over 7152.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2644, pruned_loss=0.03229, over 565354.89 frames.], batch size: 20, lr: 2.80e-04
+2022-04-30 04:54:25,262 INFO [train.py:763] (0/8) Epoch 27, batch 150, loss[loss=0.1526, simple_loss=0.264, pruned_loss=0.02055, over 6642.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2645, pruned_loss=0.03122, over 753432.25 frames.], batch size: 38, lr: 2.80e-04
+2022-04-30 04:55:31,378 INFO [train.py:763] (0/8) Epoch 27, batch 200, loss[loss=0.2097, simple_loss=0.3076, pruned_loss=0.0559, over 7182.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2642, pruned_loss=0.03149, over 899174.35 frames.], batch size: 23, lr: 2.80e-04
+2022-04-30 04:56:38,013 INFO [train.py:763] (0/8) Epoch 27, batch 250, loss[loss=0.1682, simple_loss=0.2709, pruned_loss=0.03268, over 7293.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2645, pruned_loss=0.03205, over 1015423.68 frames.], batch size: 24, lr: 2.80e-04
+2022-04-30 04:57:44,222 INFO [train.py:763] (0/8) Epoch 27, batch 300, loss[loss=0.1672, simple_loss=0.2688, pruned_loss=0.0328, over 6642.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2646, pruned_loss=0.03233, over 1104764.46 frames.], batch size: 31, lr: 2.80e-04
+2022-04-30 04:58:50,100 INFO [train.py:763] (0/8) Epoch 27, batch 350, loss[loss=0.1388, simple_loss=0.2447, pruned_loss=0.01644, over 7169.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2638, pruned_loss=0.03222, over 1177213.70 frames.], batch size: 19, lr: 2.80e-04
+2022-04-30 04:59:56,411 INFO [train.py:763] (0/8) Epoch 27, batch 400, loss[loss=0.1404, simple_loss=0.2336, pruned_loss=0.02356, over 7127.00 frames.], tot_loss[loss=0.1645, simple_loss=0.264, pruned_loss=0.03252, over 1233498.47 frames.], batch size: 17, lr: 2.80e-04
+2022-04-30 05:01:02,264 INFO [train.py:763] (0/8) Epoch 27, batch 450, loss[loss=0.1741, simple_loss=0.2805, pruned_loss=0.03382, over 7278.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03262, over 1269907.00 frames.], batch size: 25, lr: 2.80e-04
+2022-04-30 05:02:08,170 INFO [train.py:763] (0/8) Epoch 27, batch 500, loss[loss=0.1682, simple_loss=0.2704, pruned_loss=0.03298, over 7311.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2642, pruned_loss=0.03255, over 1307564.62 frames.], batch size: 21, lr: 2.80e-04
+2022-04-30 05:03:14,026 INFO [train.py:763] (0/8) Epoch 27, batch 550, loss[loss=0.1721, simple_loss=0.2634, pruned_loss=0.04043, over 7066.00 frames.], tot_loss[loss=0.165, simple_loss=0.2641, pruned_loss=0.03293, over 1329635.37 frames.], batch size: 18, lr: 2.80e-04
+2022-04-30 05:04:19,660 INFO [train.py:763] (0/8) Epoch 27, batch 600, loss[loss=0.1575, simple_loss=0.2507, pruned_loss=0.0322, over 7329.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.0323, over 1348484.70 frames.], batch size: 20, lr: 2.80e-04
+2022-04-30 05:05:24,804 INFO [train.py:763] (0/8) Epoch 27, batch 650, loss[loss=0.1818, simple_loss=0.2891, pruned_loss=0.03727, over 7088.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2641, pruned_loss=0.03274, over 1366453.52 frames.], batch size: 28, lr: 2.80e-04
+2022-04-30 05:06:40,263 INFO [train.py:763] (0/8) Epoch 27, batch 700, loss[loss=0.1655, simple_loss=0.2598, pruned_loss=0.03566, over 7070.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2636, pruned_loss=0.03246, over 1380879.42 frames.], batch size: 18, lr: 2.80e-04
+2022-04-30 05:07:46,097 INFO [train.py:763] (0/8) Epoch 27, batch 750, loss[loss=0.1621, simple_loss=0.2755, pruned_loss=0.02431, over 7218.00 frames.], tot_loss[loss=0.1637, simple_loss=0.263, pruned_loss=0.03222, over 1391983.36 frames.], batch size: 21, lr: 2.80e-04
+2022-04-30 05:08:51,499 INFO [train.py:763] (0/8) Epoch 27, batch 800, loss[loss=0.1719, simple_loss=0.2767, pruned_loss=0.03359, over 7071.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2632, pruned_loss=0.032, over 1398521.47 frames.], batch size: 28, lr: 2.80e-04
+2022-04-30 05:09:56,922 INFO [train.py:763] (0/8) Epoch 27, batch 850, loss[loss=0.1538, simple_loss=0.2618, pruned_loss=0.02295, over 7326.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2637, pruned_loss=0.03235, over 1406096.75 frames.], batch size: 25, lr: 2.80e-04
+2022-04-30 05:11:02,109 INFO [train.py:763] (0/8) Epoch 27, batch 900, loss[loss=0.146, simple_loss=0.2346, pruned_loss=0.02869, over 6992.00 frames.], tot_loss[loss=0.1645, simple_loss=0.264, pruned_loss=0.03246, over 1407961.42 frames.], batch size: 16, lr: 2.80e-04
+2022-04-30 05:12:07,295 INFO [train.py:763] (0/8) Epoch 27, batch 950, loss[loss=0.1699, simple_loss=0.258, pruned_loss=0.04088, over 7168.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2642, pruned_loss=0.03277, over 1410163.49 frames.], batch size: 18, lr: 2.80e-04
+2022-04-30 05:13:12,794 INFO [train.py:763] (0/8) Epoch 27, batch 1000, loss[loss=0.1443, simple_loss=0.2496, pruned_loss=0.01948, over 7429.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2641, pruned_loss=0.03275, over 1415552.57 frames.], batch size: 20, lr: 2.79e-04
+2022-04-30 05:14:18,860 INFO [train.py:763] (0/8) Epoch 27, batch 1050, loss[loss=0.1747, simple_loss=0.2813, pruned_loss=0.03407, over 7408.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2644, pruned_loss=0.03289, over 1415491.09 frames.], batch size: 21, lr: 2.79e-04
+2022-04-30 05:15:25,049 INFO [train.py:763] (0/8) Epoch 27, batch 1100, loss[loss=0.1437, simple_loss=0.2378, pruned_loss=0.02479, over 7444.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2647, pruned_loss=0.03298, over 1416731.28 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:16:31,285 INFO [train.py:763] (0/8) Epoch 27, batch 1150, loss[loss=0.1896, simple_loss=0.2899, pruned_loss=0.04469, over 7206.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2631, pruned_loss=0.03257, over 1421502.29 frames.], batch size: 23, lr: 2.79e-04
+2022-04-30 05:17:47,513 INFO [train.py:763] (0/8) Epoch 27, batch 1200, loss[loss=0.1381, simple_loss=0.2386, pruned_loss=0.01879, over 7150.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2617, pruned_loss=0.03176, over 1425616.39 frames.], batch size: 17, lr: 2.79e-04
+2022-04-30 05:19:01,892 INFO [train.py:763] (0/8) Epoch 27, batch 1250, loss[loss=0.1619, simple_loss=0.2574, pruned_loss=0.03326, over 7127.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2625, pruned_loss=0.0318, over 1423209.61 frames.], batch size: 17, lr: 2.79e-04
+2022-04-30 05:20:26,024 INFO [train.py:763] (0/8) Epoch 27, batch 1300, loss[loss=0.1739, simple_loss=0.2701, pruned_loss=0.0389, over 7289.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2626, pruned_loss=0.03176, over 1419558.68 frames.], batch size: 18, lr: 2.79e-04
+2022-04-30 05:21:31,878 INFO [train.py:763] (0/8) Epoch 27, batch 1350, loss[loss=0.176, simple_loss=0.2775, pruned_loss=0.0372, over 7344.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2631, pruned_loss=0.03232, over 1419150.69 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:22:37,306 INFO [train.py:763] (0/8) Epoch 27, batch 1400, loss[loss=0.1435, simple_loss=0.2408, pruned_loss=0.02307, over 7064.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2635, pruned_loss=0.03264, over 1419745.06 frames.], batch size: 18, lr: 2.79e-04
+2022-04-30 05:24:10,246 INFO [train.py:763] (0/8) Epoch 27, batch 1450, loss[loss=0.164, simple_loss=0.2662, pruned_loss=0.03086, over 7324.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2612, pruned_loss=0.03203, over 1421909.15 frames.], batch size: 20, lr: 2.79e-04
+2022-04-30 05:25:16,098 INFO [train.py:763] (0/8) Epoch 27, batch 1500, loss[loss=0.1769, simple_loss=0.277, pruned_loss=0.03837, over 7118.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2626, pruned_loss=0.03206, over 1423460.57 frames.], batch size: 21, lr: 2.79e-04
+2022-04-30 05:26:22,002 INFO [train.py:763] (0/8) Epoch 27, batch 1550, loss[loss=0.1349, simple_loss=0.2132, pruned_loss=0.02825, over 6841.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03231, over 1421039.57 frames.], batch size: 15, lr: 2.79e-04
+2022-04-30 05:27:29,038 INFO [train.py:763] (0/8) Epoch 27, batch 1600, loss[loss=0.1692, simple_loss=0.2719, pruned_loss=0.03327, over 7425.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2636, pruned_loss=0.03244, over 1424669.66 frames.], batch size: 21, lr: 2.79e-04
+2022-04-30 05:28:35,023 INFO [train.py:763] (0/8) Epoch 27, batch 1650, loss[loss=0.1462, simple_loss=0.2467, pruned_loss=0.02284, over 7072.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2628, pruned_loss=0.03215, over 1425676.57 frames.], batch size: 18, lr: 2.79e-04
+2022-04-30 05:29:41,345 INFO [train.py:763] (0/8) Epoch 27, batch 1700, loss[loss=0.1539, simple_loss=0.2557, pruned_loss=0.02607, over 7352.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2633, pruned_loss=0.03223, over 1427116.78 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:30:48,494 INFO [train.py:763] (0/8) Epoch 27, batch 1750, loss[loss=0.165, simple_loss=0.2663, pruned_loss=0.03184, over 6839.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2634, pruned_loss=0.03267, over 1428888.47 frames.], batch size: 31, lr: 2.79e-04
+2022-04-30 05:31:54,574 INFO [train.py:763] (0/8) Epoch 27, batch 1800, loss[loss=0.1732, simple_loss=0.2777, pruned_loss=0.03434, over 7236.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2637, pruned_loss=0.03296, over 1428501.70 frames.], batch size: 20, lr: 2.79e-04
+2022-04-30 05:33:00,695 INFO [train.py:763] (0/8) Epoch 27, batch 1850, loss[loss=0.1749, simple_loss=0.2652, pruned_loss=0.04229, over 7157.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2637, pruned_loss=0.03285, over 1431329.36 frames.], batch size: 19, lr: 2.79e-04
+2022-04-30 05:34:06,844 INFO [train.py:763] (0/8) Epoch 27, batch 1900, loss[loss=0.1603, simple_loss=0.2555, pruned_loss=0.03255, over 7293.00 frames.], tot_loss[loss=0.1649, simple_loss=0.264, pruned_loss=0.03293, over 1431862.89 frames.], batch size: 17, lr: 2.78e-04
+2022-04-30 05:35:13,653 INFO [train.py:763] (0/8) Epoch 27, batch 1950, loss[loss=0.1842, simple_loss=0.2885, pruned_loss=0.03989, over 6148.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2643, pruned_loss=0.03316, over 1425856.19 frames.], batch size: 37, lr: 2.78e-04
+2022-04-30 05:36:20,339 INFO [train.py:763] (0/8) Epoch 27, batch 2000, loss[loss=0.1555, simple_loss=0.2657, pruned_loss=0.02263, over 7222.00 frames.], tot_loss[loss=0.165, simple_loss=0.2639, pruned_loss=0.03312, over 1424965.62 frames.], batch size: 21, lr: 2.78e-04
+2022-04-30 05:37:26,475 INFO [train.py:763] (0/8) Epoch 27, batch 2050, loss[loss=0.1923, simple_loss=0.2977, pruned_loss=0.04349, over 7195.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2652, pruned_loss=0.03377, over 1423330.88 frames.], batch size: 23, lr: 2.78e-04
+2022-04-30 05:38:32,953 INFO [train.py:763] (0/8) Epoch 27, batch 2100, loss[loss=0.1853, simple_loss=0.2842, pruned_loss=0.04316, over 7324.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2649, pruned_loss=0.03345, over 1423414.97 frames.], batch size: 25, lr: 2.78e-04
+2022-04-30 05:39:38,777 INFO [train.py:763] (0/8) Epoch 27, batch 2150, loss[loss=0.1449, simple_loss=0.2405, pruned_loss=0.02467, over 7137.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2651, pruned_loss=0.03324, over 1422967.04 frames.], batch size: 17, lr: 2.78e-04
+2022-04-30 05:40:44,418 INFO [train.py:763] (0/8) Epoch 27, batch 2200, loss[loss=0.169, simple_loss=0.2665, pruned_loss=0.0358, over 7314.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2649, pruned_loss=0.03314, over 1421463.04 frames.], batch size: 24, lr: 2.78e-04
+2022-04-30 05:41:50,166 INFO [train.py:763] (0/8) Epoch 27, batch 2250, loss[loss=0.1709, simple_loss=0.265, pruned_loss=0.03836, over 7319.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2647, pruned_loss=0.03324, over 1424882.29 frames.], batch size: 22, lr: 2.78e-04
+2022-04-30 05:42:56,037 INFO [train.py:763] (0/8) Epoch 27, batch 2300, loss[loss=0.1746, simple_loss=0.2774, pruned_loss=0.03595, over 7148.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2658, pruned_loss=0.03391, over 1421229.82 frames.], batch size: 20, lr: 2.78e-04
+2022-04-30 05:44:01,809 INFO [train.py:763] (0/8) Epoch 27, batch 2350, loss[loss=0.1538, simple_loss=0.2551, pruned_loss=0.0263, over 7150.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03357, over 1419352.88 frames.], batch size: 19, lr: 2.78e-04
+2022-04-30 05:45:08,048 INFO [train.py:763] (0/8) Epoch 27, batch 2400, loss[loss=0.1779, simple_loss=0.2699, pruned_loss=0.043, over 7179.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03354, over 1422566.51 frames.], batch size: 23, lr: 2.78e-04
+2022-04-30 05:46:14,168 INFO [train.py:763] (0/8) Epoch 27, batch 2450, loss[loss=0.1861, simple_loss=0.2846, pruned_loss=0.04376, over 6558.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2632, pruned_loss=0.03281, over 1424395.90 frames.], batch size: 38, lr: 2.78e-04
+2022-04-30 05:47:19,846 INFO [train.py:763] (0/8) Epoch 27, batch 2500, loss[loss=0.1591, simple_loss=0.2564, pruned_loss=0.03092, over 7221.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2637, pruned_loss=0.03366, over 1421437.54 frames.], batch size: 16, lr: 2.78e-04
+2022-04-30 05:48:25,935 INFO [train.py:763] (0/8) Epoch 27, batch 2550, loss[loss=0.1384, simple_loss=0.2334, pruned_loss=0.02172, over 7259.00 frames.], tot_loss[loss=0.1647, simple_loss=0.263, pruned_loss=0.03321, over 1422480.01 frames.], batch size: 19, lr: 2.78e-04
+2022-04-30 05:49:31,729 INFO [train.py:763] (0/8) Epoch 27, batch 2600, loss[loss=0.1443, simple_loss=0.2555, pruned_loss=0.01656, over 7231.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2628, pruned_loss=0.03279, over 1422205.32 frames.], batch size: 20, lr: 2.78e-04
+2022-04-30 05:50:37,401 INFO [train.py:763] (0/8) Epoch 27, batch 2650, loss[loss=0.1556, simple_loss=0.2425, pruned_loss=0.03437, over 7008.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2625, pruned_loss=0.03233, over 1419906.13 frames.], batch size: 16, lr: 2.78e-04
+2022-04-30 05:51:42,954 INFO [train.py:763] (0/8) Epoch 27, batch 2700, loss[loss=0.1766, simple_loss=0.2769, pruned_loss=0.03819, over 7329.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2624, pruned_loss=0.03212, over 1422495.56 frames.], batch size: 21, lr: 2.78e-04
+2022-04-30 05:52:49,040 INFO [train.py:763] (0/8) Epoch 27, batch 2750, loss[loss=0.145, simple_loss=0.2421, pruned_loss=0.02398, over 7262.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2624, pruned_loss=0.03203, over 1420972.17 frames.], batch size: 19, lr: 2.78e-04
+2022-04-30 05:53:54,763 INFO [train.py:763] (0/8) Epoch 27, batch 2800, loss[loss=0.1552, simple_loss=0.2588, pruned_loss=0.02577, over 7238.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2631, pruned_loss=0.03234, over 1416699.69 frames.], batch size: 20, lr: 2.77e-04
+2022-04-30 05:55:00,523 INFO [train.py:763] (0/8) Epoch 27, batch 2850, loss[loss=0.1482, simple_loss=0.2469, pruned_loss=0.02472, over 7131.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2627, pruned_loss=0.0319, over 1421149.47 frames.], batch size: 17, lr: 2.77e-04
+2022-04-30 05:56:06,161 INFO [train.py:763] (0/8) Epoch 27, batch 2900, loss[loss=0.1636, simple_loss=0.2674, pruned_loss=0.02986, over 7291.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2628, pruned_loss=0.0317, over 1420532.64 frames.], batch size: 25, lr: 2.77e-04
+2022-04-30 05:57:11,752 INFO [train.py:763] (0/8) Epoch 27, batch 2950, loss[loss=0.197, simple_loss=0.3036, pruned_loss=0.04518, over 7208.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2633, pruned_loss=0.03176, over 1423104.43 frames.], batch size: 23, lr: 2.77e-04
+2022-04-30 05:58:18,067 INFO [train.py:763] (0/8) Epoch 27, batch 3000, loss[loss=0.1635, simple_loss=0.2721, pruned_loss=0.02752, over 7058.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2639, pruned_loss=0.03184, over 1425127.90 frames.], batch size: 28, lr: 2.77e-04
+2022-04-30 05:58:18,068 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 05:58:33,165 INFO [train.py:792] (0/8) Epoch 27, validation: loss=0.1686, simple_loss=0.2648, pruned_loss=0.03621, over 698248.00 frames.
+2022-04-30 05:59:40,078 INFO [train.py:763] (0/8) Epoch 27, batch 3050, loss[loss=0.1514, simple_loss=0.2473, pruned_loss=0.02773, over 7138.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2636, pruned_loss=0.03204, over 1427252.64 frames.], batch size: 17, lr: 2.77e-04
+2022-04-30 06:00:45,838 INFO [train.py:763] (0/8) Epoch 27, batch 3100, loss[loss=0.1699, simple_loss=0.2642, pruned_loss=0.03777, over 7366.00 frames.], tot_loss[loss=0.163, simple_loss=0.2622, pruned_loss=0.03193, over 1426433.51 frames.], batch size: 23, lr: 2.77e-04
+2022-04-30 06:01:51,945 INFO [train.py:763] (0/8) Epoch 27, batch 3150, loss[loss=0.1328, simple_loss=0.2275, pruned_loss=0.01902, over 7386.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2621, pruned_loss=0.03203, over 1423943.12 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:02:58,135 INFO [train.py:763] (0/8) Epoch 27, batch 3200, loss[loss=0.182, simple_loss=0.2906, pruned_loss=0.03667, over 7330.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2627, pruned_loss=0.03174, over 1424470.83 frames.], batch size: 21, lr: 2.77e-04
+2022-04-30 06:04:04,085 INFO [train.py:763] (0/8) Epoch 27, batch 3250, loss[loss=0.1557, simple_loss=0.2574, pruned_loss=0.02696, over 7173.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2618, pruned_loss=0.03178, over 1424106.56 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:05:10,055 INFO [train.py:763] (0/8) Epoch 27, batch 3300, loss[loss=0.1543, simple_loss=0.2484, pruned_loss=0.03007, over 6997.00 frames.], tot_loss[loss=0.1628, simple_loss=0.262, pruned_loss=0.03176, over 1423549.93 frames.], batch size: 16, lr: 2.77e-04
+2022-04-30 06:06:16,455 INFO [train.py:763] (0/8) Epoch 27, batch 3350, loss[loss=0.1851, simple_loss=0.2858, pruned_loss=0.0422, over 7375.00 frames.], tot_loss[loss=0.163, simple_loss=0.2623, pruned_loss=0.03181, over 1420847.08 frames.], batch size: 23, lr: 2.77e-04
+2022-04-30 06:07:23,078 INFO [train.py:763] (0/8) Epoch 27, batch 3400, loss[loss=0.1858, simple_loss=0.2815, pruned_loss=0.04502, over 7329.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2628, pruned_loss=0.03205, over 1422740.58 frames.], batch size: 20, lr: 2.77e-04
+2022-04-30 06:08:29,077 INFO [train.py:763] (0/8) Epoch 27, batch 3450, loss[loss=0.1804, simple_loss=0.2866, pruned_loss=0.0371, over 7203.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2627, pruned_loss=0.03194, over 1424213.32 frames.], batch size: 22, lr: 2.77e-04
+2022-04-30 06:09:34,970 INFO [train.py:763] (0/8) Epoch 27, batch 3500, loss[loss=0.1518, simple_loss=0.2522, pruned_loss=0.02572, over 7063.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2628, pruned_loss=0.03181, over 1423012.29 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:10:40,830 INFO [train.py:763] (0/8) Epoch 27, batch 3550, loss[loss=0.1496, simple_loss=0.2535, pruned_loss=0.02289, over 7334.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2634, pruned_loss=0.0321, over 1423821.05 frames.], batch size: 22, lr: 2.77e-04
+2022-04-30 06:11:46,450 INFO [train.py:763] (0/8) Epoch 27, batch 3600, loss[loss=0.1768, simple_loss=0.287, pruned_loss=0.03331, over 7064.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2641, pruned_loss=0.0323, over 1423770.74 frames.], batch size: 18, lr: 2.77e-04
+2022-04-30 06:12:52,073 INFO [train.py:763] (0/8) Epoch 27, batch 3650, loss[loss=0.1902, simple_loss=0.2871, pruned_loss=0.04662, over 7415.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2628, pruned_loss=0.03211, over 1424464.16 frames.], batch size: 21, lr: 2.77e-04
+2022-04-30 06:13:58,385 INFO [train.py:763] (0/8) Epoch 27, batch 3700, loss[loss=0.1719, simple_loss=0.2771, pruned_loss=0.03333, over 7425.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2634, pruned_loss=0.03224, over 1424757.85 frames.], batch size: 20, lr: 2.77e-04
+2022-04-30 06:15:04,067 INFO [train.py:763] (0/8) Epoch 27, batch 3750, loss[loss=0.1821, simple_loss=0.2751, pruned_loss=0.04462, over 5416.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2639, pruned_loss=0.03229, over 1420423.41 frames.], batch size: 52, lr: 2.76e-04
+2022-04-30 06:16:10,315 INFO [train.py:763] (0/8) Epoch 27, batch 3800, loss[loss=0.173, simple_loss=0.2577, pruned_loss=0.0441, over 7287.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2645, pruned_loss=0.0326, over 1422350.67 frames.], batch size: 17, lr: 2.76e-04
+2022-04-30 06:17:16,534 INFO [train.py:763] (0/8) Epoch 27, batch 3850, loss[loss=0.1724, simple_loss=0.2741, pruned_loss=0.0353, over 7153.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2638, pruned_loss=0.03231, over 1426922.22 frames.], batch size: 19, lr: 2.76e-04
+2022-04-30 06:18:22,913 INFO [train.py:763] (0/8) Epoch 27, batch 3900, loss[loss=0.1609, simple_loss=0.2654, pruned_loss=0.02814, over 7205.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2638, pruned_loss=0.03239, over 1425221.33 frames.], batch size: 22, lr: 2.76e-04
+2022-04-30 06:19:28,549 INFO [train.py:763] (0/8) Epoch 27, batch 3950, loss[loss=0.1656, simple_loss=0.2663, pruned_loss=0.03251, over 7197.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2637, pruned_loss=0.03241, over 1426259.61 frames.], batch size: 22, lr: 2.76e-04
+2022-04-30 06:20:34,801 INFO [train.py:763] (0/8) Epoch 27, batch 4000, loss[loss=0.1701, simple_loss=0.272, pruned_loss=0.03414, over 6837.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2625, pruned_loss=0.0322, over 1423202.89 frames.], batch size: 31, lr: 2.76e-04
+2022-04-30 06:21:40,921 INFO [train.py:763] (0/8) Epoch 27, batch 4050, loss[loss=0.2095, simple_loss=0.2938, pruned_loss=0.06256, over 4725.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2628, pruned_loss=0.03218, over 1416138.37 frames.], batch size: 52, lr: 2.76e-04
+2022-04-30 06:22:47,112 INFO [train.py:763] (0/8) Epoch 27, batch 4100, loss[loss=0.1501, simple_loss=0.2406, pruned_loss=0.0298, over 7125.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2622, pruned_loss=0.03198, over 1418618.05 frames.], batch size: 17, lr: 2.76e-04
+2022-04-30 06:23:17,537 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-128000.pt
+2022-04-30 06:24:03,949 INFO [train.py:763] (0/8) Epoch 27, batch 4150, loss[loss=0.146, simple_loss=0.2394, pruned_loss=0.02634, over 7153.00 frames.], tot_loss[loss=0.164, simple_loss=0.2632, pruned_loss=0.03239, over 1423179.88 frames.], batch size: 19, lr: 2.76e-04
+2022-04-30 06:25:09,379 INFO [train.py:763] (0/8) Epoch 27, batch 4200, loss[loss=0.1869, simple_loss=0.276, pruned_loss=0.04896, over 5069.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2636, pruned_loss=0.03269, over 1416777.54 frames.], batch size: 52, lr: 2.76e-04
+2022-04-30 06:26:15,110 INFO [train.py:763] (0/8) Epoch 27, batch 4250, loss[loss=0.1593, simple_loss=0.2521, pruned_loss=0.03328, over 7457.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2636, pruned_loss=0.03241, over 1415218.77 frames.], batch size: 19, lr: 2.76e-04
+2022-04-30 06:27:21,148 INFO [train.py:763] (0/8) Epoch 27, batch 4300, loss[loss=0.1606, simple_loss=0.2518, pruned_loss=0.03472, over 7144.00 frames.], tot_loss[loss=0.164, simple_loss=0.2637, pruned_loss=0.03219, over 1416363.67 frames.], batch size: 17, lr: 2.76e-04
+2022-04-30 06:28:27,405 INFO [train.py:763] (0/8) Epoch 27, batch 4350, loss[loss=0.1692, simple_loss=0.2758, pruned_loss=0.03125, over 7219.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2641, pruned_loss=0.03252, over 1416950.56 frames.], batch size: 21, lr: 2.76e-04
+2022-04-30 06:29:33,360 INFO [train.py:763] (0/8) Epoch 27, batch 4400, loss[loss=0.15, simple_loss=0.2486, pruned_loss=0.02571, over 6436.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03224, over 1408731.23 frames.], batch size: 38, lr: 2.76e-04
+2022-04-30 06:30:39,371 INFO [train.py:763] (0/8) Epoch 27, batch 4450, loss[loss=0.1441, simple_loss=0.2337, pruned_loss=0.02728, over 7174.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2633, pruned_loss=0.03222, over 1402873.92 frames.], batch size: 16, lr: 2.76e-04
+2022-04-30 06:31:44,906 INFO [train.py:763] (0/8) Epoch 27, batch 4500, loss[loss=0.1596, simple_loss=0.256, pruned_loss=0.03164, over 7232.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2639, pruned_loss=0.03241, over 1393355.29 frames.], batch size: 21, lr: 2.76e-04
+2022-04-30 06:32:50,078 INFO [train.py:763] (0/8) Epoch 27, batch 4550, loss[loss=0.157, simple_loss=0.2671, pruned_loss=0.02345, over 6432.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2647, pruned_loss=0.03324, over 1361666.34 frames.], batch size: 38, lr: 2.76e-04
+2022-04-30 06:33:39,309 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-27.pt
+2022-04-30 06:34:19,195 INFO [train.py:763] (0/8) Epoch 28, batch 0, loss[loss=0.1595, simple_loss=0.2679, pruned_loss=0.02561, over 7067.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2679, pruned_loss=0.02561, over 7067.00 frames.], batch size: 28, lr: 2.71e-04
+2022-04-30 06:35:24,837 INFO [train.py:763] (0/8) Epoch 28, batch 50, loss[loss=0.1962, simple_loss=0.3002, pruned_loss=0.04611, over 7305.00 frames.], tot_loss[loss=0.164, simple_loss=0.2644, pruned_loss=0.03179, over 323244.22 frames.], batch size: 24, lr: 2.71e-04
+2022-04-30 06:36:31,690 INFO [train.py:763] (0/8) Epoch 28, batch 100, loss[loss=0.1516, simple_loss=0.2504, pruned_loss=0.02637, over 7318.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2629, pruned_loss=0.03172, over 569344.83 frames.], batch size: 21, lr: 2.71e-04
+2022-04-30 06:37:37,380 INFO [train.py:763] (0/8) Epoch 28, batch 150, loss[loss=0.1442, simple_loss=0.2393, pruned_loss=0.02453, over 7232.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2626, pruned_loss=0.03199, over 759957.17 frames.], batch size: 20, lr: 2.71e-04
+2022-04-30 06:38:43,644 INFO [train.py:763] (0/8) Epoch 28, batch 200, loss[loss=0.1365, simple_loss=0.2373, pruned_loss=0.01784, over 7072.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2628, pruned_loss=0.03181, over 908913.15 frames.], batch size: 18, lr: 2.71e-04
+2022-04-30 06:39:49,243 INFO [train.py:763] (0/8) Epoch 28, batch 250, loss[loss=0.1919, simple_loss=0.2871, pruned_loss=0.0484, over 4932.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2629, pruned_loss=0.03168, over 1019761.54 frames.], batch size: 52, lr: 2.71e-04
+2022-04-30 06:40:54,491 INFO [train.py:763] (0/8) Epoch 28, batch 300, loss[loss=0.1662, simple_loss=0.2615, pruned_loss=0.03541, over 7172.00 frames.], tot_loss[loss=0.1634, simple_loss=0.263, pruned_loss=0.03194, over 1109253.74 frames.], batch size: 18, lr: 2.70e-04
+2022-04-30 06:41:59,627 INFO [train.py:763] (0/8) Epoch 28, batch 350, loss[loss=0.1654, simple_loss=0.268, pruned_loss=0.03141, over 7061.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2634, pruned_loss=0.03168, over 1180500.82 frames.], batch size: 18, lr: 2.70e-04
+2022-04-30 06:43:05,895 INFO [train.py:763] (0/8) Epoch 28, batch 400, loss[loss=0.1713, simple_loss=0.2742, pruned_loss=0.03418, over 7142.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03259, over 1236136.99 frames.], batch size: 20, lr: 2.70e-04
+2022-04-30 06:44:12,424 INFO [train.py:763] (0/8) Epoch 28, batch 450, loss[loss=0.1835, simple_loss=0.2764, pruned_loss=0.04535, over 7118.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2652, pruned_loss=0.03276, over 1281853.15 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:45:17,941 INFO [train.py:763] (0/8) Epoch 28, batch 500, loss[loss=0.1807, simple_loss=0.279, pruned_loss=0.04123, over 5196.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2652, pruned_loss=0.03278, over 1308896.85 frames.], batch size: 53, lr: 2.70e-04
+2022-04-30 06:46:23,651 INFO [train.py:763] (0/8) Epoch 28, batch 550, loss[loss=0.1742, simple_loss=0.2786, pruned_loss=0.03494, over 7216.00 frames.], tot_loss[loss=0.166, simple_loss=0.2657, pruned_loss=0.03312, over 1331472.77 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:47:29,782 INFO [train.py:763] (0/8) Epoch 28, batch 600, loss[loss=0.1538, simple_loss=0.2477, pruned_loss=0.02993, over 7264.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2637, pruned_loss=0.03246, over 1348669.66 frames.], batch size: 19, lr: 2.70e-04
+2022-04-30 06:48:35,464 INFO [train.py:763] (0/8) Epoch 28, batch 650, loss[loss=0.1673, simple_loss=0.2597, pruned_loss=0.0374, over 7070.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2623, pruned_loss=0.03223, over 1367087.21 frames.], batch size: 18, lr: 2.70e-04
+2022-04-30 06:49:42,654 INFO [train.py:763] (0/8) Epoch 28, batch 700, loss[loss=0.1881, simple_loss=0.2828, pruned_loss=0.04665, over 5087.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2634, pruned_loss=0.03257, over 1376389.51 frames.], batch size: 52, lr: 2.70e-04
+2022-04-30 06:50:48,232 INFO [train.py:763] (0/8) Epoch 28, batch 750, loss[loss=0.1682, simple_loss=0.2767, pruned_loss=0.0299, over 7434.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2631, pruned_loss=0.03232, over 1383361.67 frames.], batch size: 20, lr: 2.70e-04
+2022-04-30 06:51:53,713 INFO [train.py:763] (0/8) Epoch 28, batch 800, loss[loss=0.1637, simple_loss=0.2748, pruned_loss=0.02628, over 7111.00 frames.], tot_loss[loss=0.164, simple_loss=0.2635, pruned_loss=0.03221, over 1388468.52 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:52:59,920 INFO [train.py:763] (0/8) Epoch 28, batch 850, loss[loss=0.1496, simple_loss=0.2491, pruned_loss=0.02506, over 6348.00 frames.], tot_loss[loss=0.165, simple_loss=0.2643, pruned_loss=0.03282, over 1392738.92 frames.], batch size: 37, lr: 2.70e-04
+2022-04-30 06:54:06,454 INFO [train.py:763] (0/8) Epoch 28, batch 900, loss[loss=0.1643, simple_loss=0.2694, pruned_loss=0.02958, over 6724.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03263, over 1399135.91 frames.], batch size: 31, lr: 2.70e-04
+2022-04-30 06:55:12,067 INFO [train.py:763] (0/8) Epoch 28, batch 950, loss[loss=0.164, simple_loss=0.2703, pruned_loss=0.02888, over 7208.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2636, pruned_loss=0.03228, over 1408107.73 frames.], batch size: 22, lr: 2.70e-04
+2022-04-30 06:56:17,985 INFO [train.py:763] (0/8) Epoch 28, batch 1000, loss[loss=0.1374, simple_loss=0.2256, pruned_loss=0.02458, over 6826.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2622, pruned_loss=0.03177, over 1414494.69 frames.], batch size: 15, lr: 2.70e-04
+2022-04-30 06:57:23,500 INFO [train.py:763] (0/8) Epoch 28, batch 1050, loss[loss=0.1579, simple_loss=0.2694, pruned_loss=0.02324, over 7406.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2621, pruned_loss=0.03116, over 1419910.29 frames.], batch size: 21, lr: 2.70e-04
+2022-04-30 06:58:29,252 INFO [train.py:763] (0/8) Epoch 28, batch 1100, loss[loss=0.1474, simple_loss=0.2418, pruned_loss=0.02649, over 7278.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03112, over 1423705.56 frames.], batch size: 17, lr: 2.70e-04
+2022-04-30 06:59:35,662 INFO [train.py:763] (0/8) Epoch 28, batch 1150, loss[loss=0.1862, simple_loss=0.2799, pruned_loss=0.04629, over 7081.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2621, pruned_loss=0.03139, over 1421699.95 frames.], batch size: 28, lr: 2.70e-04
+2022-04-30 07:00:40,816 INFO [train.py:763] (0/8) Epoch 28, batch 1200, loss[loss=0.1972, simple_loss=0.2871, pruned_loss=0.05365, over 7137.00 frames.], tot_loss[loss=0.164, simple_loss=0.264, pruned_loss=0.032, over 1423742.90 frames.], batch size: 28, lr: 2.70e-04
+2022-04-30 07:01:47,030 INFO [train.py:763] (0/8) Epoch 28, batch 1250, loss[loss=0.1748, simple_loss=0.2757, pruned_loss=0.03699, over 7196.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2638, pruned_loss=0.03233, over 1417842.43 frames.], batch size: 22, lr: 2.70e-04
+2022-04-30 07:02:52,933 INFO [train.py:763] (0/8) Epoch 28, batch 1300, loss[loss=0.1668, simple_loss=0.2736, pruned_loss=0.03002, over 7162.00 frames.], tot_loss[loss=0.164, simple_loss=0.2637, pruned_loss=0.03217, over 1421072.48 frames.], batch size: 20, lr: 2.69e-04
+2022-04-30 07:03:58,478 INFO [train.py:763] (0/8) Epoch 28, batch 1350, loss[loss=0.1571, simple_loss=0.2633, pruned_loss=0.02541, over 7108.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2634, pruned_loss=0.03198, over 1425986.71 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:05:04,530 INFO [train.py:763] (0/8) Epoch 28, batch 1400, loss[loss=0.1476, simple_loss=0.2376, pruned_loss=0.02884, over 7275.00 frames.], tot_loss[loss=0.1636, simple_loss=0.263, pruned_loss=0.03207, over 1427557.81 frames.], batch size: 17, lr: 2.69e-04
+2022-04-30 07:06:10,011 INFO [train.py:763] (0/8) Epoch 28, batch 1450, loss[loss=0.1586, simple_loss=0.266, pruned_loss=0.02561, over 7308.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2632, pruned_loss=0.03229, over 1431387.14 frames.], batch size: 24, lr: 2.69e-04
+2022-04-30 07:07:16,033 INFO [train.py:763] (0/8) Epoch 28, batch 1500, loss[loss=0.1538, simple_loss=0.2529, pruned_loss=0.0273, over 7339.00 frames.], tot_loss[loss=0.164, simple_loss=0.2632, pruned_loss=0.03239, over 1428140.62 frames.], batch size: 20, lr: 2.69e-04
+2022-04-30 07:08:21,697 INFO [train.py:763] (0/8) Epoch 28, batch 1550, loss[loss=0.1543, simple_loss=0.2565, pruned_loss=0.02606, over 7211.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2633, pruned_loss=0.03229, over 1429670.58 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:09:26,979 INFO [train.py:763] (0/8) Epoch 28, batch 1600, loss[loss=0.1443, simple_loss=0.241, pruned_loss=0.02378, over 6806.00 frames.], tot_loss[loss=0.1644, simple_loss=0.264, pruned_loss=0.03238, over 1426265.24 frames.], batch size: 15, lr: 2.69e-04
+2022-04-30 07:10:32,963 INFO [train.py:763] (0/8) Epoch 28, batch 1650, loss[loss=0.1347, simple_loss=0.233, pruned_loss=0.01819, over 7227.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2629, pruned_loss=0.03189, over 1428027.61 frames.], batch size: 16, lr: 2.69e-04
+2022-04-30 07:11:39,865 INFO [train.py:763] (0/8) Epoch 28, batch 1700, loss[loss=0.1465, simple_loss=0.2475, pruned_loss=0.02278, over 7251.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2627, pruned_loss=0.03199, over 1430623.81 frames.], batch size: 19, lr: 2.69e-04
+2022-04-30 07:12:45,215 INFO [train.py:763] (0/8) Epoch 28, batch 1750, loss[loss=0.1496, simple_loss=0.2493, pruned_loss=0.02498, over 7115.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2619, pruned_loss=0.03166, over 1432646.91 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:13:50,841 INFO [train.py:763] (0/8) Epoch 28, batch 1800, loss[loss=0.1514, simple_loss=0.2522, pruned_loss=0.02529, over 6991.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2617, pruned_loss=0.03158, over 1422818.55 frames.], batch size: 16, lr: 2.69e-04
+2022-04-30 07:14:56,961 INFO [train.py:763] (0/8) Epoch 28, batch 1850, loss[loss=0.1417, simple_loss=0.2263, pruned_loss=0.02852, over 7403.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2623, pruned_loss=0.03171, over 1425606.67 frames.], batch size: 18, lr: 2.69e-04
+2022-04-30 07:16:02,993 INFO [train.py:763] (0/8) Epoch 28, batch 1900, loss[loss=0.1759, simple_loss=0.2752, pruned_loss=0.03833, over 7152.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2622, pruned_loss=0.03154, over 1425904.17 frames.], batch size: 26, lr: 2.69e-04
+2022-04-30 07:17:09,720 INFO [train.py:763] (0/8) Epoch 28, batch 1950, loss[loss=0.1802, simple_loss=0.2787, pruned_loss=0.04083, over 7296.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2624, pruned_loss=0.03156, over 1428058.24 frames.], batch size: 25, lr: 2.69e-04
+2022-04-30 07:18:15,514 INFO [train.py:763] (0/8) Epoch 28, batch 2000, loss[loss=0.1964, simple_loss=0.3044, pruned_loss=0.04419, over 7207.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.03165, over 1431044.98 frames.], batch size: 23, lr: 2.69e-04
+2022-04-30 07:19:21,146 INFO [train.py:763] (0/8) Epoch 28, batch 2050, loss[loss=0.1603, simple_loss=0.2762, pruned_loss=0.02221, over 7314.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2629, pruned_loss=0.03195, over 1424160.77 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:20:26,747 INFO [train.py:763] (0/8) Epoch 28, batch 2100, loss[loss=0.1823, simple_loss=0.281, pruned_loss=0.04184, over 7329.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2621, pruned_loss=0.03168, over 1426207.82 frames.], batch size: 25, lr: 2.69e-04
+2022-04-30 07:21:33,846 INFO [train.py:763] (0/8) Epoch 28, batch 2150, loss[loss=0.1439, simple_loss=0.2555, pruned_loss=0.01614, over 7212.00 frames.], tot_loss[loss=0.162, simple_loss=0.2618, pruned_loss=0.03113, over 1427697.11 frames.], batch size: 21, lr: 2.69e-04
+2022-04-30 07:22:48,763 INFO [train.py:763] (0/8) Epoch 28, batch 2200, loss[loss=0.1791, simple_loss=0.2887, pruned_loss=0.03478, over 7301.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03131, over 1423043.00 frames.], batch size: 25, lr: 2.69e-04
+2022-04-30 07:23:56,118 INFO [train.py:763] (0/8) Epoch 28, batch 2250, loss[loss=0.1564, simple_loss=0.2578, pruned_loss=0.02748, over 7115.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.0316, over 1426622.85 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:25:01,844 INFO [train.py:763] (0/8) Epoch 28, batch 2300, loss[loss=0.1864, simple_loss=0.2992, pruned_loss=0.03675, over 7305.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2631, pruned_loss=0.03177, over 1427552.70 frames.], batch size: 24, lr: 2.68e-04
+2022-04-30 07:26:07,591 INFO [train.py:763] (0/8) Epoch 28, batch 2350, loss[loss=0.1509, simple_loss=0.2502, pruned_loss=0.02579, over 7076.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2632, pruned_loss=0.03189, over 1424690.32 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:27:14,919 INFO [train.py:763] (0/8) Epoch 28, batch 2400, loss[loss=0.1447, simple_loss=0.2464, pruned_loss=0.02145, over 7351.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2623, pruned_loss=0.03162, over 1425906.36 frames.], batch size: 19, lr: 2.68e-04
+2022-04-30 07:28:20,440 INFO [train.py:763] (0/8) Epoch 28, batch 2450, loss[loss=0.1469, simple_loss=0.2485, pruned_loss=0.02271, over 7122.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2634, pruned_loss=0.03221, over 1416315.57 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:29:26,097 INFO [train.py:763] (0/8) Epoch 28, batch 2500, loss[loss=0.1271, simple_loss=0.2161, pruned_loss=0.01911, over 7417.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2623, pruned_loss=0.03164, over 1419925.33 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:30:32,244 INFO [train.py:763] (0/8) Epoch 28, batch 2550, loss[loss=0.161, simple_loss=0.2483, pruned_loss=0.03686, over 7167.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2624, pruned_loss=0.03203, over 1417484.59 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:31:37,903 INFO [train.py:763] (0/8) Epoch 28, batch 2600, loss[loss=0.1668, simple_loss=0.2715, pruned_loss=0.03103, over 7214.00 frames.], tot_loss[loss=0.163, simple_loss=0.2622, pruned_loss=0.03193, over 1416975.34 frames.], batch size: 23, lr: 2.68e-04
+2022-04-30 07:32:43,498 INFO [train.py:763] (0/8) Epoch 28, batch 2650, loss[loss=0.1577, simple_loss=0.2559, pruned_loss=0.02969, over 7416.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2622, pruned_loss=0.03178, over 1420256.20 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:33:59,648 INFO [train.py:763] (0/8) Epoch 28, batch 2700, loss[loss=0.1748, simple_loss=0.2691, pruned_loss=0.04027, over 5295.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2616, pruned_loss=0.03186, over 1420761.00 frames.], batch size: 52, lr: 2.68e-04
+2022-04-30 07:35:13,953 INFO [train.py:763] (0/8) Epoch 28, batch 2750, loss[loss=0.1744, simple_loss=0.2761, pruned_loss=0.03629, over 7323.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2625, pruned_loss=0.03223, over 1416763.16 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:36:28,358 INFO [train.py:763] (0/8) Epoch 28, batch 2800, loss[loss=0.1621, simple_loss=0.2651, pruned_loss=0.02954, over 7345.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2626, pruned_loss=0.03195, over 1419775.42 frames.], batch size: 22, lr: 2.68e-04
+2022-04-30 07:37:44,246 INFO [train.py:763] (0/8) Epoch 28, batch 2850, loss[loss=0.1591, simple_loss=0.2647, pruned_loss=0.02675, over 7268.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2633, pruned_loss=0.0325, over 1420008.23 frames.], batch size: 19, lr: 2.68e-04
+2022-04-30 07:38:58,501 INFO [train.py:763] (0/8) Epoch 28, batch 2900, loss[loss=0.1517, simple_loss=0.2422, pruned_loss=0.03058, over 7273.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2626, pruned_loss=0.03217, over 1418522.43 frames.], batch size: 17, lr: 2.68e-04
+2022-04-30 07:40:13,617 INFO [train.py:763] (0/8) Epoch 28, batch 2950, loss[loss=0.1386, simple_loss=0.2344, pruned_loss=0.02142, over 7148.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2612, pruned_loss=0.03215, over 1418123.09 frames.], batch size: 17, lr: 2.68e-04
+2022-04-30 07:41:27,537 INFO [train.py:763] (0/8) Epoch 28, batch 3000, loss[loss=0.1719, simple_loss=0.2817, pruned_loss=0.03106, over 7236.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2624, pruned_loss=0.03209, over 1418517.49 frames.], batch size: 20, lr: 2.68e-04
+2022-04-30 07:41:27,539 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 07:41:44,122 INFO [train.py:792] (0/8) Epoch 28, validation: loss=0.1685, simple_loss=0.2656, pruned_loss=0.03573, over 698248.00 frames.
+2022-04-30 07:42:49,826 INFO [train.py:763] (0/8) Epoch 28, batch 3050, loss[loss=0.1434, simple_loss=0.2373, pruned_loss=0.02473, over 7164.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2617, pruned_loss=0.03181, over 1421912.56 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:43:55,531 INFO [train.py:763] (0/8) Epoch 28, batch 3100, loss[loss=0.1418, simple_loss=0.242, pruned_loss=0.02076, over 7268.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2612, pruned_loss=0.03155, over 1418595.50 frames.], batch size: 18, lr: 2.68e-04
+2022-04-30 07:45:01,635 INFO [train.py:763] (0/8) Epoch 28, batch 3150, loss[loss=0.1814, simple_loss=0.2819, pruned_loss=0.04051, over 7212.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2622, pruned_loss=0.03148, over 1422340.68 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:46:07,728 INFO [train.py:763] (0/8) Epoch 28, batch 3200, loss[loss=0.1554, simple_loss=0.2645, pruned_loss=0.0231, over 7128.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2623, pruned_loss=0.03121, over 1422266.79 frames.], batch size: 21, lr: 2.68e-04
+2022-04-30 07:47:14,371 INFO [train.py:763] (0/8) Epoch 28, batch 3250, loss[loss=0.1427, simple_loss=0.2288, pruned_loss=0.02828, over 6804.00 frames.], tot_loss[loss=0.162, simple_loss=0.2616, pruned_loss=0.03114, over 1421560.68 frames.], batch size: 15, lr: 2.67e-04
+2022-04-30 07:48:20,831 INFO [train.py:763] (0/8) Epoch 28, batch 3300, loss[loss=0.1599, simple_loss=0.2645, pruned_loss=0.02764, over 7231.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2629, pruned_loss=0.03146, over 1421634.05 frames.], batch size: 21, lr: 2.67e-04
+2022-04-30 07:49:26,933 INFO [train.py:763] (0/8) Epoch 28, batch 3350, loss[loss=0.15, simple_loss=0.2523, pruned_loss=0.02388, over 7070.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2625, pruned_loss=0.03152, over 1418959.42 frames.], batch size: 28, lr: 2.67e-04
+2022-04-30 07:50:33,836 INFO [train.py:763] (0/8) Epoch 28, batch 3400, loss[loss=0.1568, simple_loss=0.2503, pruned_loss=0.03172, over 7066.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2624, pruned_loss=0.03174, over 1418048.30 frames.], batch size: 18, lr: 2.67e-04
+2022-04-30 07:51:39,854 INFO [train.py:763] (0/8) Epoch 28, batch 3450, loss[loss=0.1442, simple_loss=0.2364, pruned_loss=0.02601, over 7272.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2618, pruned_loss=0.03156, over 1420091.76 frames.], batch size: 17, lr: 2.67e-04
+2022-04-30 07:52:45,409 INFO [train.py:763] (0/8) Epoch 28, batch 3500, loss[loss=0.156, simple_loss=0.2632, pruned_loss=0.0244, over 6976.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03143, over 1420046.99 frames.], batch size: 32, lr: 2.67e-04
+2022-04-30 07:53:50,885 INFO [train.py:763] (0/8) Epoch 28, batch 3550, loss[loss=0.1606, simple_loss=0.2499, pruned_loss=0.03567, over 7262.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2623, pruned_loss=0.03166, over 1423268.24 frames.], batch size: 18, lr: 2.67e-04
+2022-04-30 07:54:56,704 INFO [train.py:763] (0/8) Epoch 28, batch 3600, loss[loss=0.1556, simple_loss=0.2444, pruned_loss=0.03337, over 7205.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2625, pruned_loss=0.0318, over 1423819.07 frames.], batch size: 16, lr: 2.67e-04
+2022-04-30 07:56:02,363 INFO [train.py:763] (0/8) Epoch 28, batch 3650, loss[loss=0.1713, simple_loss=0.2775, pruned_loss=0.03249, over 7344.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2623, pruned_loss=0.03177, over 1426914.23 frames.], batch size: 22, lr: 2.67e-04
+2022-04-30 07:57:08,121 INFO [train.py:763] (0/8) Epoch 28, batch 3700, loss[loss=0.2075, simple_loss=0.3007, pruned_loss=0.05713, over 7202.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2621, pruned_loss=0.03176, over 1426533.57 frames.], batch size: 23, lr: 2.67e-04
+2022-04-30 07:58:13,564 INFO [train.py:763] (0/8) Epoch 28, batch 3750, loss[loss=0.1963, simple_loss=0.2896, pruned_loss=0.0515, over 5120.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2621, pruned_loss=0.03177, over 1426101.74 frames.], batch size: 52, lr: 2.67e-04
+2022-04-30 07:59:19,066 INFO [train.py:763] (0/8) Epoch 28, batch 3800, loss[loss=0.1496, simple_loss=0.2488, pruned_loss=0.02517, over 7428.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.03181, over 1426097.49 frames.], batch size: 20, lr: 2.67e-04
+2022-04-30 08:00:24,652 INFO [train.py:763] (0/8) Epoch 28, batch 3850, loss[loss=0.1682, simple_loss=0.2637, pruned_loss=0.03638, over 7384.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03197, over 1426646.51 frames.], batch size: 23, lr: 2.67e-04
+2022-04-30 08:01:31,047 INFO [train.py:763] (0/8) Epoch 28, batch 3900, loss[loss=0.1569, simple_loss=0.2645, pruned_loss=0.02466, over 7268.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2632, pruned_loss=0.0319, over 1429235.92 frames.], batch size: 24, lr: 2.67e-04
+2022-04-30 08:02:37,689 INFO [train.py:763] (0/8) Epoch 28, batch 3950, loss[loss=0.1417, simple_loss=0.2337, pruned_loss=0.02483, over 7412.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2641, pruned_loss=0.0321, over 1430478.13 frames.], batch size: 18, lr: 2.67e-04
+2022-04-30 08:03:44,067 INFO [train.py:763] (0/8) Epoch 28, batch 4000, loss[loss=0.1671, simple_loss=0.2642, pruned_loss=0.03499, over 7317.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2644, pruned_loss=0.03244, over 1430277.53 frames.], batch size: 22, lr: 2.67e-04
+2022-04-30 08:04:50,787 INFO [train.py:763] (0/8) Epoch 28, batch 4050, loss[loss=0.1522, simple_loss=0.2354, pruned_loss=0.03449, over 7273.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2639, pruned_loss=0.03214, over 1429425.63 frames.], batch size: 17, lr: 2.67e-04
+2022-04-30 08:05:55,982 INFO [train.py:763] (0/8) Epoch 28, batch 4100, loss[loss=0.1707, simple_loss=0.2823, pruned_loss=0.02952, over 7322.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2636, pruned_loss=0.03169, over 1430776.47 frames.], batch size: 22, lr: 2.67e-04
+2022-04-30 08:07:02,633 INFO [train.py:763] (0/8) Epoch 28, batch 4150, loss[loss=0.1714, simple_loss=0.2705, pruned_loss=0.03611, over 7321.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2628, pruned_loss=0.03141, over 1423898.95 frames.], batch size: 21, lr: 2.67e-04
+2022-04-30 08:08:09,145 INFO [train.py:763] (0/8) Epoch 28, batch 4200, loss[loss=0.163, simple_loss=0.2625, pruned_loss=0.03175, over 7261.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2637, pruned_loss=0.03164, over 1420784.63 frames.], batch size: 19, lr: 2.66e-04
+2022-04-30 08:09:14,670 INFO [train.py:763] (0/8) Epoch 28, batch 4250, loss[loss=0.18, simple_loss=0.2899, pruned_loss=0.03504, over 6712.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2634, pruned_loss=0.03163, over 1421499.08 frames.], batch size: 31, lr: 2.66e-04
+2022-04-30 08:10:19,667 INFO [train.py:763] (0/8) Epoch 28, batch 4300, loss[loss=0.1557, simple_loss=0.2483, pruned_loss=0.03158, over 7168.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2631, pruned_loss=0.03134, over 1416845.75 frames.], batch size: 18, lr: 2.66e-04
+2022-04-30 08:11:24,970 INFO [train.py:763] (0/8) Epoch 28, batch 4350, loss[loss=0.1746, simple_loss=0.2872, pruned_loss=0.031, over 7324.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2626, pruned_loss=0.03135, over 1417591.57 frames.], batch size: 21, lr: 2.66e-04
+2022-04-30 08:12:30,147 INFO [train.py:763] (0/8) Epoch 28, batch 4400, loss[loss=0.1925, simple_loss=0.2942, pruned_loss=0.04542, over 7274.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2636, pruned_loss=0.03202, over 1409569.11 frames.], batch size: 24, lr: 2.66e-04
+2022-04-30 08:13:35,277 INFO [train.py:763] (0/8) Epoch 28, batch 4450, loss[loss=0.1431, simple_loss=0.2484, pruned_loss=0.01893, over 6341.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2629, pruned_loss=0.032, over 1400530.07 frames.], batch size: 38, lr: 2.66e-04
+2022-04-30 08:14:40,132 INFO [train.py:763] (0/8) Epoch 28, batch 4500, loss[loss=0.1698, simple_loss=0.2763, pruned_loss=0.03159, over 7201.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2643, pruned_loss=0.03262, over 1378013.24 frames.], batch size: 22, lr: 2.66e-04
+2022-04-30 08:15:45,365 INFO [train.py:763] (0/8) Epoch 28, batch 4550, loss[loss=0.1752, simple_loss=0.2713, pruned_loss=0.03953, over 5125.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2654, pruned_loss=0.03289, over 1359059.75 frames.], batch size: 52, lr: 2.66e-04
+2022-04-30 08:16:35,582 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-28.pt
+2022-04-30 08:17:05,898 INFO [train.py:763] (0/8) Epoch 29, batch 0, loss[loss=0.1496, simple_loss=0.2486, pruned_loss=0.02527, over 7317.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2486, pruned_loss=0.02527, over 7317.00 frames.], batch size: 20, lr: 2.62e-04
+2022-04-30 08:18:11,693 INFO [train.py:763] (0/8) Epoch 29, batch 50, loss[loss=0.1604, simple_loss=0.2572, pruned_loss=0.03178, over 7294.00 frames.], tot_loss[loss=0.166, simple_loss=0.2666, pruned_loss=0.0327, over 324712.85 frames.], batch size: 18, lr: 2.62e-04
+2022-04-30 08:19:17,263 INFO [train.py:763] (0/8) Epoch 29, batch 100, loss[loss=0.1372, simple_loss=0.2284, pruned_loss=0.02302, over 7289.00 frames.], tot_loss[loss=0.1632, simple_loss=0.262, pruned_loss=0.03217, over 572534.15 frames.], batch size: 17, lr: 2.62e-04
+2022-04-30 08:20:22,574 INFO [train.py:763] (0/8) Epoch 29, batch 150, loss[loss=0.2018, simple_loss=0.3036, pruned_loss=0.04998, over 7290.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2625, pruned_loss=0.0326, over 749807.85 frames.], batch size: 24, lr: 2.62e-04
+2022-04-30 08:21:28,007 INFO [train.py:763] (0/8) Epoch 29, batch 200, loss[loss=0.1452, simple_loss=0.2442, pruned_loss=0.02313, over 7362.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2619, pruned_loss=0.03156, over 899776.74 frames.], batch size: 19, lr: 2.61e-04
+2022-04-30 08:22:33,082 INFO [train.py:763] (0/8) Epoch 29, batch 250, loss[loss=0.1322, simple_loss=0.2261, pruned_loss=0.0192, over 6808.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2618, pruned_loss=0.03093, over 1015464.03 frames.], batch size: 15, lr: 2.61e-04
+2022-04-30 08:23:39,500 INFO [train.py:763] (0/8) Epoch 29, batch 300, loss[loss=0.164, simple_loss=0.2457, pruned_loss=0.04119, over 7275.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2634, pruned_loss=0.03166, over 1107724.48 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:24:46,643 INFO [train.py:763] (0/8) Epoch 29, batch 350, loss[loss=0.1529, simple_loss=0.2555, pruned_loss=0.02516, over 7333.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2618, pruned_loss=0.03138, over 1180543.31 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:25:52,375 INFO [train.py:763] (0/8) Epoch 29, batch 400, loss[loss=0.189, simple_loss=0.2969, pruned_loss=0.04054, over 7318.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.0311, over 1236771.70 frames.], batch size: 24, lr: 2.61e-04
+2022-04-30 08:26:57,832 INFO [train.py:763] (0/8) Epoch 29, batch 450, loss[loss=0.1582, simple_loss=0.262, pruned_loss=0.02716, over 7411.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03113, over 1279561.91 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:28:03,217 INFO [train.py:763] (0/8) Epoch 29, batch 500, loss[loss=0.1522, simple_loss=0.2537, pruned_loss=0.02532, over 7327.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2623, pruned_loss=0.03144, over 1307634.82 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:29:08,675 INFO [train.py:763] (0/8) Epoch 29, batch 550, loss[loss=0.1673, simple_loss=0.2775, pruned_loss=0.02856, over 7325.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2631, pruned_loss=0.03161, over 1335687.41 frames.], batch size: 24, lr: 2.61e-04
+2022-04-30 08:30:14,689 INFO [train.py:763] (0/8) Epoch 29, batch 600, loss[loss=0.1595, simple_loss=0.267, pruned_loss=0.02596, over 7210.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2629, pruned_loss=0.03164, over 1351612.98 frames.], batch size: 22, lr: 2.61e-04
+2022-04-30 08:31:20,915 INFO [train.py:763] (0/8) Epoch 29, batch 650, loss[loss=0.1371, simple_loss=0.2345, pruned_loss=0.01986, over 7455.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2621, pruned_loss=0.03148, over 1366467.26 frames.], batch size: 19, lr: 2.61e-04
+2022-04-30 08:32:27,049 INFO [train.py:763] (0/8) Epoch 29, batch 700, loss[loss=0.1589, simple_loss=0.2616, pruned_loss=0.0281, over 7310.00 frames.], tot_loss[loss=0.1632, simple_loss=0.263, pruned_loss=0.03168, over 1375585.84 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:33:32,286 INFO [train.py:763] (0/8) Epoch 29, batch 750, loss[loss=0.1791, simple_loss=0.2813, pruned_loss=0.03842, over 7229.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2637, pruned_loss=0.03211, over 1382253.18 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:34:37,543 INFO [train.py:763] (0/8) Epoch 29, batch 800, loss[loss=0.1648, simple_loss=0.2657, pruned_loss=0.03202, over 7342.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2628, pruned_loss=0.0317, over 1387798.01 frames.], batch size: 22, lr: 2.61e-04
+2022-04-30 08:35:43,025 INFO [train.py:763] (0/8) Epoch 29, batch 850, loss[loss=0.1512, simple_loss=0.253, pruned_loss=0.02467, over 7066.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2616, pruned_loss=0.03133, over 1396493.53 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:36:48,532 INFO [train.py:763] (0/8) Epoch 29, batch 900, loss[loss=0.1516, simple_loss=0.2525, pruned_loss=0.02535, over 7215.00 frames.], tot_loss[loss=0.162, simple_loss=0.2618, pruned_loss=0.03107, over 1400193.14 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:37:53,912 INFO [train.py:763] (0/8) Epoch 29, batch 950, loss[loss=0.1637, simple_loss=0.2735, pruned_loss=0.02696, over 7117.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03105, over 1406395.20 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:38:59,978 INFO [train.py:763] (0/8) Epoch 29, batch 1000, loss[loss=0.1558, simple_loss=0.2461, pruned_loss=0.03275, over 7139.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2624, pruned_loss=0.03125, over 1410584.84 frames.], batch size: 20, lr: 2.61e-04
+2022-04-30 08:40:06,273 INFO [train.py:763] (0/8) Epoch 29, batch 1050, loss[loss=0.1687, simple_loss=0.2678, pruned_loss=0.03479, over 7275.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2626, pruned_loss=0.03151, over 1407512.04 frames.], batch size: 18, lr: 2.61e-04
+2022-04-30 08:41:11,509 INFO [train.py:763] (0/8) Epoch 29, batch 1100, loss[loss=0.1667, simple_loss=0.276, pruned_loss=0.0287, over 7317.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2644, pruned_loss=0.03204, over 1416942.31 frames.], batch size: 21, lr: 2.61e-04
+2022-04-30 08:42:16,631 INFO [train.py:763] (0/8) Epoch 29, batch 1150, loss[loss=0.1342, simple_loss=0.2317, pruned_loss=0.01836, over 6981.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2648, pruned_loss=0.03227, over 1418015.36 frames.], batch size: 16, lr: 2.61e-04
+2022-04-30 08:43:21,914 INFO [train.py:763] (0/8) Epoch 29, batch 1200, loss[loss=0.1607, simple_loss=0.2664, pruned_loss=0.02749, over 7166.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2638, pruned_loss=0.03193, over 1422798.20 frames.], batch size: 19, lr: 2.61e-04
+2022-04-30 08:44:27,481 INFO [train.py:763] (0/8) Epoch 29, batch 1250, loss[loss=0.1763, simple_loss=0.2703, pruned_loss=0.04111, over 5354.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2624, pruned_loss=0.03151, over 1418201.34 frames.], batch size: 53, lr: 2.60e-04
+2022-04-30 08:45:34,627 INFO [train.py:763] (0/8) Epoch 29, batch 1300, loss[loss=0.15, simple_loss=0.2639, pruned_loss=0.01804, over 7342.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2624, pruned_loss=0.03128, over 1418585.38 frames.], batch size: 22, lr: 2.60e-04
+2022-04-30 08:46:42,217 INFO [train.py:763] (0/8) Epoch 29, batch 1350, loss[loss=0.185, simple_loss=0.2782, pruned_loss=0.04589, over 6125.00 frames.], tot_loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03149, over 1418694.86 frames.], batch size: 37, lr: 2.60e-04
+2022-04-30 08:47:48,991 INFO [train.py:763] (0/8) Epoch 29, batch 1400, loss[loss=0.1526, simple_loss=0.2364, pruned_loss=0.03441, over 6842.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2627, pruned_loss=0.03198, over 1418934.32 frames.], batch size: 15, lr: 2.60e-04
+2022-04-30 08:48:56,277 INFO [train.py:763] (0/8) Epoch 29, batch 1450, loss[loss=0.1679, simple_loss=0.2683, pruned_loss=0.03373, over 7119.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2628, pruned_loss=0.03201, over 1417165.82 frames.], batch size: 21, lr: 2.60e-04
+2022-04-30 08:50:03,380 INFO [train.py:763] (0/8) Epoch 29, batch 1500, loss[loss=0.151, simple_loss=0.2519, pruned_loss=0.02504, over 7257.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2626, pruned_loss=0.03213, over 1417256.63 frames.], batch size: 19, lr: 2.60e-04
+2022-04-30 08:51:09,980 INFO [train.py:763] (0/8) Epoch 29, batch 1550, loss[loss=0.1642, simple_loss=0.2659, pruned_loss=0.03131, over 7156.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2624, pruned_loss=0.03167, over 1418018.87 frames.], batch size: 23, lr: 2.60e-04
+2022-04-30 08:52:16,975 INFO [train.py:763] (0/8) Epoch 29, batch 1600, loss[loss=0.167, simple_loss=0.2867, pruned_loss=0.02366, over 7320.00 frames.], tot_loss[loss=0.164, simple_loss=0.2635, pruned_loss=0.0322, over 1419379.51 frames.], batch size: 21, lr: 2.60e-04
+2022-04-30 08:53:22,977 INFO [train.py:763] (0/8) Epoch 29, batch 1650, loss[loss=0.1772, simple_loss=0.2849, pruned_loss=0.03477, over 7208.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2631, pruned_loss=0.03213, over 1423424.59 frames.], batch size: 26, lr: 2.60e-04
+2022-04-30 08:54:28,295 INFO [train.py:763] (0/8) Epoch 29, batch 1700, loss[loss=0.1481, simple_loss=0.2432, pruned_loss=0.0265, over 7128.00 frames.], tot_loss[loss=0.164, simple_loss=0.2636, pruned_loss=0.03217, over 1426080.08 frames.], batch size: 17, lr: 2.60e-04
+2022-04-30 08:55:35,259 INFO [train.py:763] (0/8) Epoch 29, batch 1750, loss[loss=0.1557, simple_loss=0.2619, pruned_loss=0.02472, over 7140.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03226, over 1423215.00 frames.], batch size: 20, lr: 2.60e-04
+2022-04-30 08:56:42,199 INFO [train.py:763] (0/8) Epoch 29, batch 1800, loss[loss=0.1772, simple_loss=0.2791, pruned_loss=0.03768, over 5218.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2636, pruned_loss=0.03246, over 1420051.18 frames.], batch size: 53, lr: 2.60e-04
+2022-04-30 08:57:49,266 INFO [train.py:763] (0/8) Epoch 29, batch 1850, loss[loss=0.1943, simple_loss=0.2872, pruned_loss=0.05068, over 7110.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2626, pruned_loss=0.03227, over 1424327.98 frames.], batch size: 21, lr: 2.60e-04
+2022-04-30 08:58:55,869 INFO [train.py:763] (0/8) Epoch 29, batch 1900, loss[loss=0.1451, simple_loss=0.2387, pruned_loss=0.02576, over 6820.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2631, pruned_loss=0.03219, over 1426169.68 frames.], batch size: 15, lr: 2.60e-04
+2022-04-30 09:00:01,483 INFO [train.py:763] (0/8) Epoch 29, batch 1950, loss[loss=0.1381, simple_loss=0.2252, pruned_loss=0.02549, over 7268.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2632, pruned_loss=0.03235, over 1427372.71 frames.], batch size: 17, lr: 2.60e-04
+2022-04-30 09:01:06,703 INFO [train.py:763] (0/8) Epoch 29, batch 2000, loss[loss=0.1668, simple_loss=0.2759, pruned_loss=0.02884, over 7334.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2631, pruned_loss=0.03207, over 1429964.78 frames.], batch size: 22, lr: 2.60e-04
+2022-04-30 09:02:12,110 INFO [train.py:763] (0/8) Epoch 29, batch 2050, loss[loss=0.2292, simple_loss=0.326, pruned_loss=0.06626, over 7205.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2634, pruned_loss=0.03242, over 1430168.31 frames.], batch size: 23, lr: 2.60e-04
+2022-04-30 09:03:17,250 INFO [train.py:763] (0/8) Epoch 29, batch 2100, loss[loss=0.1617, simple_loss=0.2694, pruned_loss=0.02694, over 7148.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2634, pruned_loss=0.03211, over 1429697.89 frames.], batch size: 20, lr: 2.60e-04
+2022-04-30 09:04:22,320 INFO [train.py:763] (0/8) Epoch 29, batch 2150, loss[loss=0.1515, simple_loss=0.24, pruned_loss=0.03151, over 7133.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2626, pruned_loss=0.03179, over 1428585.59 frames.], batch size: 17, lr: 2.60e-04
+2022-04-30 09:05:27,763 INFO [train.py:763] (0/8) Epoch 29, batch 2200, loss[loss=0.1808, simple_loss=0.2724, pruned_loss=0.04463, over 7289.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2618, pruned_loss=0.0317, over 1423837.45 frames.], batch size: 24, lr: 2.60e-04
+2022-04-30 09:06:32,913 INFO [train.py:763] (0/8) Epoch 29, batch 2250, loss[loss=0.1787, simple_loss=0.2766, pruned_loss=0.04044, over 7168.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2619, pruned_loss=0.03173, over 1422464.91 frames.], batch size: 26, lr: 2.59e-04
+2022-04-30 09:07:38,521 INFO [train.py:763] (0/8) Epoch 29, batch 2300, loss[loss=0.1321, simple_loss=0.2289, pruned_loss=0.01766, over 7350.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2619, pruned_loss=0.0315, over 1419619.93 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:08:43,791 INFO [train.py:763] (0/8) Epoch 29, batch 2350, loss[loss=0.1622, simple_loss=0.2763, pruned_loss=0.02402, over 7331.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2615, pruned_loss=0.03136, over 1420811.70 frames.], batch size: 22, lr: 2.59e-04
+2022-04-30 09:09:49,531 INFO [train.py:763] (0/8) Epoch 29, batch 2400, loss[loss=0.1915, simple_loss=0.2899, pruned_loss=0.04652, over 7271.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2621, pruned_loss=0.03154, over 1422503.82 frames.], batch size: 25, lr: 2.59e-04
+2022-04-30 09:10:55,178 INFO [train.py:763] (0/8) Epoch 29, batch 2450, loss[loss=0.1598, simple_loss=0.2657, pruned_loss=0.02692, over 7148.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03106, over 1426588.53 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:12:00,715 INFO [train.py:763] (0/8) Epoch 29, batch 2500, loss[loss=0.1318, simple_loss=0.2227, pruned_loss=0.02042, over 7167.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2614, pruned_loss=0.03139, over 1430415.91 frames.], batch size: 16, lr: 2.59e-04
+2022-04-30 09:13:06,083 INFO [train.py:763] (0/8) Epoch 29, batch 2550, loss[loss=0.1575, simple_loss=0.2516, pruned_loss=0.03164, over 7409.00 frames.], tot_loss[loss=0.162, simple_loss=0.2609, pruned_loss=0.03154, over 1427024.16 frames.], batch size: 18, lr: 2.59e-04
+2022-04-30 09:14:11,177 INFO [train.py:763] (0/8) Epoch 29, batch 2600, loss[loss=0.1566, simple_loss=0.2519, pruned_loss=0.0306, over 7447.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2613, pruned_loss=0.03126, over 1426773.84 frames.], batch size: 22, lr: 2.59e-04
+2022-04-30 09:15:16,457 INFO [train.py:763] (0/8) Epoch 29, batch 2650, loss[loss=0.1357, simple_loss=0.2239, pruned_loss=0.02379, over 7141.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.03099, over 1429526.10 frames.], batch size: 17, lr: 2.59e-04
+2022-04-30 09:16:21,504 INFO [train.py:763] (0/8) Epoch 29, batch 2700, loss[loss=0.1574, simple_loss=0.2631, pruned_loss=0.02582, over 7116.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2623, pruned_loss=0.03103, over 1429455.57 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:17:27,769 INFO [train.py:763] (0/8) Epoch 29, batch 2750, loss[loss=0.1497, simple_loss=0.2557, pruned_loss=0.02183, over 7233.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2626, pruned_loss=0.03122, over 1425580.18 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:18:33,547 INFO [train.py:763] (0/8) Epoch 29, batch 2800, loss[loss=0.1653, simple_loss=0.2676, pruned_loss=0.03154, over 7329.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2627, pruned_loss=0.0316, over 1424964.33 frames.], batch size: 22, lr: 2.59e-04
+2022-04-30 09:19:39,948 INFO [train.py:763] (0/8) Epoch 29, batch 2850, loss[loss=0.1904, simple_loss=0.2956, pruned_loss=0.04262, over 7219.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2622, pruned_loss=0.03162, over 1419147.31 frames.], batch size: 20, lr: 2.59e-04
+2022-04-30 09:20:45,394 INFO [train.py:763] (0/8) Epoch 29, batch 2900, loss[loss=0.132, simple_loss=0.2195, pruned_loss=0.02224, over 6978.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2616, pruned_loss=0.03158, over 1421608.17 frames.], batch size: 16, lr: 2.59e-04
+2022-04-30 09:21:47,040 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-136000.pt
+2022-04-30 09:22:01,687 INFO [train.py:763] (0/8) Epoch 29, batch 2950, loss[loss=0.1524, simple_loss=0.2685, pruned_loss=0.01817, over 6424.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2607, pruned_loss=0.03104, over 1422657.37 frames.], batch size: 39, lr: 2.59e-04
+2022-04-30 09:23:07,154 INFO [train.py:763] (0/8) Epoch 29, batch 3000, loss[loss=0.1519, simple_loss=0.255, pruned_loss=0.02441, over 7105.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2609, pruned_loss=0.03132, over 1425421.70 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:23:07,155 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 09:23:22,371 INFO [train.py:792] (0/8) Epoch 29, validation: loss=0.1693, simple_loss=0.2664, pruned_loss=0.03606, over 698248.00 frames.
+2022-04-30 09:24:27,453 INFO [train.py:763] (0/8) Epoch 29, batch 3050, loss[loss=0.1595, simple_loss=0.2655, pruned_loss=0.02676, over 7109.00 frames.], tot_loss[loss=0.162, simple_loss=0.2615, pruned_loss=0.03124, over 1427238.86 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:25:32,597 INFO [train.py:763] (0/8) Epoch 29, batch 3100, loss[loss=0.1473, simple_loss=0.2469, pruned_loss=0.02389, over 7419.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2617, pruned_loss=0.0312, over 1427394.20 frames.], batch size: 21, lr: 2.59e-04
+2022-04-30 09:26:38,425 INFO [train.py:763] (0/8) Epoch 29, batch 3150, loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.02834, over 7170.00 frames.], tot_loss[loss=0.162, simple_loss=0.2616, pruned_loss=0.03123, over 1422912.40 frames.], batch size: 18, lr: 2.59e-04
+2022-04-30 09:27:44,875 INFO [train.py:763] (0/8) Epoch 29, batch 3200, loss[loss=0.153, simple_loss=0.2466, pruned_loss=0.02973, over 7256.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2601, pruned_loss=0.03115, over 1425768.78 frames.], batch size: 19, lr: 2.59e-04
+2022-04-30 09:28:51,945 INFO [train.py:763] (0/8) Epoch 29, batch 3250, loss[loss=0.1771, simple_loss=0.2775, pruned_loss=0.0383, over 7033.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2598, pruned_loss=0.03122, over 1421129.63 frames.], batch size: 28, lr: 2.59e-04
+2022-04-30 09:29:57,734 INFO [train.py:763] (0/8) Epoch 29, batch 3300, loss[loss=0.1474, simple_loss=0.2564, pruned_loss=0.01922, over 7325.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2605, pruned_loss=0.03114, over 1423908.19 frames.], batch size: 20, lr: 2.58e-04
+2022-04-30 09:31:03,714 INFO [train.py:763] (0/8) Epoch 29, batch 3350, loss[loss=0.1554, simple_loss=0.2427, pruned_loss=0.03402, over 7282.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2601, pruned_loss=0.03113, over 1427686.73 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:32:09,343 INFO [train.py:763] (0/8) Epoch 29, batch 3400, loss[loss=0.1929, simple_loss=0.2943, pruned_loss=0.04572, over 4990.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2603, pruned_loss=0.03131, over 1424178.60 frames.], batch size: 52, lr: 2.58e-04
+2022-04-30 09:33:15,122 INFO [train.py:763] (0/8) Epoch 29, batch 3450, loss[loss=0.175, simple_loss=0.2691, pruned_loss=0.04044, over 7299.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2606, pruned_loss=0.03128, over 1420675.24 frames.], batch size: 24, lr: 2.58e-04
+2022-04-30 09:34:21,152 INFO [train.py:763] (0/8) Epoch 29, batch 3500, loss[loss=0.2026, simple_loss=0.3126, pruned_loss=0.04624, over 7153.00 frames.], tot_loss[loss=0.1628, simple_loss=0.262, pruned_loss=0.03178, over 1422749.90 frames.], batch size: 26, lr: 2.58e-04
+2022-04-30 09:35:26,539 INFO [train.py:763] (0/8) Epoch 29, batch 3550, loss[loss=0.1479, simple_loss=0.25, pruned_loss=0.02286, over 7173.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2619, pruned_loss=0.03159, over 1421477.12 frames.], batch size: 18, lr: 2.58e-04
+2022-04-30 09:36:32,242 INFO [train.py:763] (0/8) Epoch 29, batch 3600, loss[loss=0.1588, simple_loss=0.2536, pruned_loss=0.03203, over 7252.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2617, pruned_loss=0.03165, over 1425932.12 frames.], batch size: 19, lr: 2.58e-04
+2022-04-30 09:37:46,881 INFO [train.py:763] (0/8) Epoch 29, batch 3650, loss[loss=0.1612, simple_loss=0.2699, pruned_loss=0.02627, over 6766.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2617, pruned_loss=0.03162, over 1428015.77 frames.], batch size: 31, lr: 2.58e-04
+2022-04-30 09:38:52,215 INFO [train.py:763] (0/8) Epoch 29, batch 3700, loss[loss=0.132, simple_loss=0.2182, pruned_loss=0.02295, over 7291.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2616, pruned_loss=0.03143, over 1429211.21 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:39:59,123 INFO [train.py:763] (0/8) Epoch 29, batch 3750, loss[loss=0.1628, simple_loss=0.2662, pruned_loss=0.02972, over 7082.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03134, over 1432039.96 frames.], batch size: 28, lr: 2.58e-04
+2022-04-30 09:41:05,837 INFO [train.py:763] (0/8) Epoch 29, batch 3800, loss[loss=0.1913, simple_loss=0.2967, pruned_loss=0.04294, over 7199.00 frames.], tot_loss[loss=0.163, simple_loss=0.263, pruned_loss=0.03154, over 1425884.87 frames.], batch size: 22, lr: 2.58e-04
+2022-04-30 09:42:11,181 INFO [train.py:763] (0/8) Epoch 29, batch 3850, loss[loss=0.1379, simple_loss=0.2277, pruned_loss=0.024, over 6795.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2622, pruned_loss=0.03134, over 1426521.55 frames.], batch size: 15, lr: 2.58e-04
+2022-04-30 09:43:16,819 INFO [train.py:763] (0/8) Epoch 29, batch 3900, loss[loss=0.1361, simple_loss=0.2252, pruned_loss=0.02354, over 7119.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03155, over 1426345.71 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:44:22,552 INFO [train.py:763] (0/8) Epoch 29, batch 3950, loss[loss=0.1798, simple_loss=0.2789, pruned_loss=0.04032, over 7352.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2634, pruned_loss=0.03167, over 1420927.94 frames.], batch size: 23, lr: 2.58e-04
+2022-04-30 09:45:27,976 INFO [train.py:763] (0/8) Epoch 29, batch 4000, loss[loss=0.1619, simple_loss=0.268, pruned_loss=0.02788, over 7301.00 frames.], tot_loss[loss=0.1627, simple_loss=0.263, pruned_loss=0.03122, over 1419186.73 frames.], batch size: 25, lr: 2.58e-04
+2022-04-30 09:46:33,253 INFO [train.py:763] (0/8) Epoch 29, batch 4050, loss[loss=0.1732, simple_loss=0.2791, pruned_loss=0.03365, over 7039.00 frames.], tot_loss[loss=0.163, simple_loss=0.263, pruned_loss=0.03152, over 1418205.35 frames.], batch size: 28, lr: 2.58e-04
+2022-04-30 09:47:39,267 INFO [train.py:763] (0/8) Epoch 29, batch 4100, loss[loss=0.1661, simple_loss=0.263, pruned_loss=0.0346, over 7313.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2628, pruned_loss=0.03154, over 1420167.33 frames.], batch size: 21, lr: 2.58e-04
+2022-04-30 09:48:45,605 INFO [train.py:763] (0/8) Epoch 29, batch 4150, loss[loss=0.1771, simple_loss=0.2823, pruned_loss=0.03596, over 7220.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03102, over 1420963.51 frames.], batch size: 21, lr: 2.58e-04
+2022-04-30 09:50:00,126 INFO [train.py:763] (0/8) Epoch 29, batch 4200, loss[loss=0.1536, simple_loss=0.2506, pruned_loss=0.0283, over 7420.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.03079, over 1420982.99 frames.], batch size: 20, lr: 2.58e-04
+2022-04-30 09:51:13,967 INFO [train.py:763] (0/8) Epoch 29, batch 4250, loss[loss=0.1446, simple_loss=0.2492, pruned_loss=0.02002, over 7378.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2635, pruned_loss=0.03118, over 1415767.35 frames.], batch size: 23, lr: 2.58e-04
+2022-04-30 09:52:28,887 INFO [train.py:763] (0/8) Epoch 29, batch 4300, loss[loss=0.1331, simple_loss=0.2222, pruned_loss=0.02203, over 7294.00 frames.], tot_loss[loss=0.163, simple_loss=0.2633, pruned_loss=0.03132, over 1419573.72 frames.], batch size: 17, lr: 2.58e-04
+2022-04-30 09:53:43,992 INFO [train.py:763] (0/8) Epoch 29, batch 4350, loss[loss=0.1541, simple_loss=0.2548, pruned_loss=0.02672, over 7241.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03119, over 1422024.49 frames.], batch size: 20, lr: 2.58e-04
+2022-04-30 09:54:58,500 INFO [train.py:763] (0/8) Epoch 29, batch 4400, loss[loss=0.1546, simple_loss=0.261, pruned_loss=0.02407, over 7230.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03057, over 1418907.70 frames.], batch size: 20, lr: 2.57e-04
+2022-04-30 09:56:12,790 INFO [train.py:763] (0/8) Epoch 29, batch 4450, loss[loss=0.1523, simple_loss=0.2575, pruned_loss=0.02356, over 6546.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03063, over 1413752.98 frames.], batch size: 38, lr: 2.57e-04
+2022-04-30 09:57:17,986 INFO [train.py:763] (0/8) Epoch 29, batch 4500, loss[loss=0.1981, simple_loss=0.2917, pruned_loss=0.05226, over 5040.00 frames.], tot_loss[loss=0.163, simple_loss=0.2632, pruned_loss=0.03142, over 1398903.20 frames.], batch size: 52, lr: 2.57e-04
+2022-04-30 09:58:32,308 INFO [train.py:763] (0/8) Epoch 29, batch 4550, loss[loss=0.1644, simple_loss=0.2591, pruned_loss=0.03491, over 5025.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2656, pruned_loss=0.03242, over 1358818.15 frames.], batch size: 52, lr: 2.57e-04
+2022-04-30 09:59:21,601 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-29.pt
+2022-04-30 10:00:01,329 INFO [train.py:763] (0/8) Epoch 30, batch 0, loss[loss=0.156, simple_loss=0.258, pruned_loss=0.02694, over 7336.00 frames.], tot_loss[loss=0.156, simple_loss=0.258, pruned_loss=0.02694, over 7336.00 frames.], batch size: 20, lr: 2.53e-04
+2022-04-30 10:01:06,994 INFO [train.py:763] (0/8) Epoch 30, batch 50, loss[loss=0.1584, simple_loss=0.263, pruned_loss=0.02692, over 7259.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2611, pruned_loss=0.0313, over 316705.30 frames.], batch size: 19, lr: 2.53e-04
+2022-04-30 10:02:12,188 INFO [train.py:763] (0/8) Epoch 30, batch 100, loss[loss=0.1678, simple_loss=0.2735, pruned_loss=0.031, over 7377.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2644, pruned_loss=0.03214, over 560838.75 frames.], batch size: 23, lr: 2.53e-04
+2022-04-30 10:03:17,815 INFO [train.py:763] (0/8) Epoch 30, batch 150, loss[loss=0.1802, simple_loss=0.2833, pruned_loss=0.03852, over 7201.00 frames.], tot_loss[loss=0.163, simple_loss=0.263, pruned_loss=0.03155, over 755618.21 frames.], batch size: 22, lr: 2.53e-04
+2022-04-30 10:04:23,874 INFO [train.py:763] (0/8) Epoch 30, batch 200, loss[loss=0.185, simple_loss=0.2832, pruned_loss=0.0434, over 5348.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2624, pruned_loss=0.03157, over 901112.47 frames.], batch size: 52, lr: 2.53e-04
+2022-04-30 10:05:30,000 INFO [train.py:763] (0/8) Epoch 30, batch 250, loss[loss=0.1535, simple_loss=0.2497, pruned_loss=0.02862, over 7280.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2642, pruned_loss=0.03245, over 1015586.91 frames.], batch size: 25, lr: 2.53e-04
+2022-04-30 10:06:35,958 INFO [train.py:763] (0/8) Epoch 30, batch 300, loss[loss=0.1505, simple_loss=0.2526, pruned_loss=0.02416, over 7314.00 frames.], tot_loss[loss=0.163, simple_loss=0.2628, pruned_loss=0.03161, over 1107140.65 frames.], batch size: 21, lr: 2.53e-04
+2022-04-30 10:07:41,455 INFO [train.py:763] (0/8) Epoch 30, batch 350, loss[loss=0.1328, simple_loss=0.228, pruned_loss=0.01882, over 7154.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2622, pruned_loss=0.0312, over 1174214.21 frames.], batch size: 18, lr: 2.53e-04
+2022-04-30 10:08:46,859 INFO [train.py:763] (0/8) Epoch 30, batch 400, loss[loss=0.1611, simple_loss=0.2708, pruned_loss=0.02568, over 7219.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2625, pruned_loss=0.03138, over 1225232.58 frames.], batch size: 21, lr: 2.53e-04
+2022-04-30 10:09:52,324 INFO [train.py:763] (0/8) Epoch 30, batch 450, loss[loss=0.1797, simple_loss=0.2935, pruned_loss=0.03293, over 7163.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2632, pruned_loss=0.03116, over 1265525.92 frames.], batch size: 26, lr: 2.53e-04
+2022-04-30 10:10:57,899 INFO [train.py:763] (0/8) Epoch 30, batch 500, loss[loss=0.1581, simple_loss=0.2447, pruned_loss=0.03576, over 7279.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2622, pruned_loss=0.03079, over 1301067.29 frames.], batch size: 17, lr: 2.53e-04
+2022-04-30 10:12:03,595 INFO [train.py:763] (0/8) Epoch 30, batch 550, loss[loss=0.1868, simple_loss=0.2853, pruned_loss=0.04416, over 7403.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2634, pruned_loss=0.03158, over 1327924.30 frames.], batch size: 21, lr: 2.53e-04
+2022-04-30 10:13:09,443 INFO [train.py:763] (0/8) Epoch 30, batch 600, loss[loss=0.162, simple_loss=0.2503, pruned_loss=0.03687, over 7059.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2637, pruned_loss=0.03182, over 1347175.18 frames.], batch size: 18, lr: 2.53e-04
+2022-04-30 10:14:15,866 INFO [train.py:763] (0/8) Epoch 30, batch 650, loss[loss=0.1408, simple_loss=0.252, pruned_loss=0.01483, over 7148.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2629, pruned_loss=0.03139, over 1368963.86 frames.], batch size: 20, lr: 2.53e-04
+2022-04-30 10:15:21,897 INFO [train.py:763] (0/8) Epoch 30, batch 700, loss[loss=0.1597, simple_loss=0.2481, pruned_loss=0.03567, over 6797.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2623, pruned_loss=0.03148, over 1378826.84 frames.], batch size: 15, lr: 2.52e-04
+2022-04-30 10:16:28,673 INFO [train.py:763] (0/8) Epoch 30, batch 750, loss[loss=0.1561, simple_loss=0.2554, pruned_loss=0.0284, over 7229.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2614, pruned_loss=0.03107, over 1387217.58 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:17:34,229 INFO [train.py:763] (0/8) Epoch 30, batch 800, loss[loss=0.1569, simple_loss=0.2619, pruned_loss=0.02598, over 7328.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03149, over 1395258.81 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:18:39,963 INFO [train.py:763] (0/8) Epoch 30, batch 850, loss[loss=0.1659, simple_loss=0.2737, pruned_loss=0.02905, over 7423.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2617, pruned_loss=0.03133, over 1399571.03 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:19:45,743 INFO [train.py:763] (0/8) Epoch 30, batch 900, loss[loss=0.1295, simple_loss=0.2143, pruned_loss=0.02239, over 6755.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2617, pruned_loss=0.03143, over 1404311.09 frames.], batch size: 15, lr: 2.52e-04
+2022-04-30 10:20:52,500 INFO [train.py:763] (0/8) Epoch 30, batch 950, loss[loss=0.1477, simple_loss=0.2578, pruned_loss=0.01883, over 7056.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2611, pruned_loss=0.03118, over 1405540.35 frames.], batch size: 28, lr: 2.52e-04
+2022-04-30 10:21:58,503 INFO [train.py:763] (0/8) Epoch 30, batch 1000, loss[loss=0.155, simple_loss=0.2585, pruned_loss=0.02571, over 7337.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2619, pruned_loss=0.03158, over 1408724.70 frames.], batch size: 22, lr: 2.52e-04
+2022-04-30 10:23:03,977 INFO [train.py:763] (0/8) Epoch 30, batch 1050, loss[loss=0.1635, simple_loss=0.2655, pruned_loss=0.03073, over 7060.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2621, pruned_loss=0.03137, over 1410554.15 frames.], batch size: 28, lr: 2.52e-04
+2022-04-30 10:24:09,741 INFO [train.py:763] (0/8) Epoch 30, batch 1100, loss[loss=0.1391, simple_loss=0.2418, pruned_loss=0.01823, over 7070.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2619, pruned_loss=0.03127, over 1415488.02 frames.], batch size: 18, lr: 2.52e-04
+2022-04-30 10:25:15,763 INFO [train.py:763] (0/8) Epoch 30, batch 1150, loss[loss=0.1408, simple_loss=0.2405, pruned_loss=0.02058, over 7060.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2616, pruned_loss=0.03137, over 1416636.56 frames.], batch size: 18, lr: 2.52e-04
+2022-04-30 10:26:21,667 INFO [train.py:763] (0/8) Epoch 30, batch 1200, loss[loss=0.1627, simple_loss=0.2665, pruned_loss=0.02946, over 7207.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2614, pruned_loss=0.03136, over 1418660.76 frames.], batch size: 22, lr: 2.52e-04
+2022-04-30 10:27:27,471 INFO [train.py:763] (0/8) Epoch 30, batch 1250, loss[loss=0.1747, simple_loss=0.2665, pruned_loss=0.04143, over 7404.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2619, pruned_loss=0.03168, over 1418228.35 frames.], batch size: 18, lr: 2.52e-04
+2022-04-30 10:28:33,939 INFO [train.py:763] (0/8) Epoch 30, batch 1300, loss[loss=0.199, simple_loss=0.3009, pruned_loss=0.04853, over 7145.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2624, pruned_loss=0.03158, over 1417636.48 frames.], batch size: 26, lr: 2.52e-04
+2022-04-30 10:29:40,220 INFO [train.py:763] (0/8) Epoch 30, batch 1350, loss[loss=0.1399, simple_loss=0.242, pruned_loss=0.01884, over 7151.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03195, over 1414956.93 frames.], batch size: 17, lr: 2.52e-04
+2022-04-30 10:30:45,748 INFO [train.py:763] (0/8) Epoch 30, batch 1400, loss[loss=0.1954, simple_loss=0.2955, pruned_loss=0.0477, over 7314.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2633, pruned_loss=0.03157, over 1418529.17 frames.], batch size: 22, lr: 2.52e-04
+2022-04-30 10:31:51,071 INFO [train.py:763] (0/8) Epoch 30, batch 1450, loss[loss=0.1529, simple_loss=0.2535, pruned_loss=0.02616, over 7143.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2629, pruned_loss=0.03092, over 1420388.22 frames.], batch size: 20, lr: 2.52e-04
+2022-04-30 10:32:56,520 INFO [train.py:763] (0/8) Epoch 30, batch 1500, loss[loss=0.2011, simple_loss=0.2984, pruned_loss=0.05191, over 7295.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2635, pruned_loss=0.03105, over 1426054.90 frames.], batch size: 25, lr: 2.52e-04
+2022-04-30 10:34:02,185 INFO [train.py:763] (0/8) Epoch 30, batch 1550, loss[loss=0.1897, simple_loss=0.2943, pruned_loss=0.04257, over 7304.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2619, pruned_loss=0.03096, over 1427692.08 frames.], batch size: 25, lr: 2.52e-04
+2022-04-30 10:35:07,687 INFO [train.py:763] (0/8) Epoch 30, batch 1600, loss[loss=0.1783, simple_loss=0.2707, pruned_loss=0.04294, over 7257.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2606, pruned_loss=0.03056, over 1428499.10 frames.], batch size: 19, lr: 2.52e-04
+2022-04-30 10:36:13,954 INFO [train.py:763] (0/8) Epoch 30, batch 1650, loss[loss=0.1695, simple_loss=0.2807, pruned_loss=0.02917, over 7107.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2621, pruned_loss=0.03076, over 1428032.48 frames.], batch size: 21, lr: 2.52e-04
+2022-04-30 10:37:20,425 INFO [train.py:763] (0/8) Epoch 30, batch 1700, loss[loss=0.179, simple_loss=0.2846, pruned_loss=0.0367, over 7291.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.0307, over 1424408.50 frames.], batch size: 24, lr: 2.52e-04
+2022-04-30 10:38:27,159 INFO [train.py:763] (0/8) Epoch 30, batch 1750, loss[loss=0.1974, simple_loss=0.2904, pruned_loss=0.05217, over 7378.00 frames.], tot_loss[loss=0.162, simple_loss=0.2615, pruned_loss=0.03121, over 1427160.84 frames.], batch size: 23, lr: 2.52e-04
+2022-04-30 10:39:33,035 INFO [train.py:763] (0/8) Epoch 30, batch 1800, loss[loss=0.1624, simple_loss=0.2612, pruned_loss=0.03175, over 7422.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2606, pruned_loss=0.03101, over 1423689.50 frames.], batch size: 20, lr: 2.51e-04
+2022-04-30 10:40:39,000 INFO [train.py:763] (0/8) Epoch 30, batch 1850, loss[loss=0.1448, simple_loss=0.237, pruned_loss=0.02631, over 7134.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2605, pruned_loss=0.0312, over 1421442.13 frames.], batch size: 17, lr: 2.51e-04
+2022-04-30 10:41:45,830 INFO [train.py:763] (0/8) Epoch 30, batch 1900, loss[loss=0.1557, simple_loss=0.2653, pruned_loss=0.02301, over 7325.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2605, pruned_loss=0.03107, over 1424529.22 frames.], batch size: 20, lr: 2.51e-04
+2022-04-30 10:42:51,813 INFO [train.py:763] (0/8) Epoch 30, batch 1950, loss[loss=0.1608, simple_loss=0.2569, pruned_loss=0.03239, over 7381.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2608, pruned_loss=0.0312, over 1424946.69 frames.], batch size: 23, lr: 2.51e-04
+2022-04-30 10:43:59,482 INFO [train.py:763] (0/8) Epoch 30, batch 2000, loss[loss=0.1735, simple_loss=0.2577, pruned_loss=0.04464, over 7162.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2599, pruned_loss=0.03097, over 1426309.20 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:45:05,774 INFO [train.py:763] (0/8) Epoch 30, batch 2050, loss[loss=0.1884, simple_loss=0.2877, pruned_loss=0.04457, over 7202.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2596, pruned_loss=0.03088, over 1423702.31 frames.], batch size: 22, lr: 2.51e-04
+2022-04-30 10:46:11,296 INFO [train.py:763] (0/8) Epoch 30, batch 2100, loss[loss=0.1666, simple_loss=0.2548, pruned_loss=0.0392, over 7161.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2605, pruned_loss=0.03088, over 1422366.22 frames.], batch size: 19, lr: 2.51e-04
+2022-04-30 10:47:17,306 INFO [train.py:763] (0/8) Epoch 30, batch 2150, loss[loss=0.1528, simple_loss=0.2456, pruned_loss=0.02995, over 7165.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2599, pruned_loss=0.03066, over 1426470.46 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:48:22,855 INFO [train.py:763] (0/8) Epoch 30, batch 2200, loss[loss=0.1482, simple_loss=0.2381, pruned_loss=0.02915, over 7072.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.0311, over 1428402.23 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:49:28,463 INFO [train.py:763] (0/8) Epoch 30, batch 2250, loss[loss=0.2162, simple_loss=0.3204, pruned_loss=0.05604, over 7185.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03141, over 1427523.31 frames.], batch size: 23, lr: 2.51e-04
+2022-04-30 10:50:34,519 INFO [train.py:763] (0/8) Epoch 30, batch 2300, loss[loss=0.148, simple_loss=0.2475, pruned_loss=0.02421, over 7263.00 frames.], tot_loss[loss=0.1622, simple_loss=0.262, pruned_loss=0.03122, over 1430094.54 frames.], batch size: 19, lr: 2.51e-04
+2022-04-30 10:51:40,507 INFO [train.py:763] (0/8) Epoch 30, batch 2350, loss[loss=0.1425, simple_loss=0.2386, pruned_loss=0.0232, over 7071.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03128, over 1430828.96 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:52:46,208 INFO [train.py:763] (0/8) Epoch 30, batch 2400, loss[loss=0.1517, simple_loss=0.2604, pruned_loss=0.02147, over 7224.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2626, pruned_loss=0.03146, over 1428798.43 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 10:53:51,756 INFO [train.py:763] (0/8) Epoch 30, batch 2450, loss[loss=0.1732, simple_loss=0.2706, pruned_loss=0.03786, over 7234.00 frames.], tot_loss[loss=0.1631, simple_loss=0.263, pruned_loss=0.03158, over 1425321.77 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 10:54:57,036 INFO [train.py:763] (0/8) Epoch 30, batch 2500, loss[loss=0.1579, simple_loss=0.2612, pruned_loss=0.02734, over 7331.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.0312, over 1428059.98 frames.], batch size: 22, lr: 2.51e-04
+2022-04-30 10:56:03,606 INFO [train.py:763] (0/8) Epoch 30, batch 2550, loss[loss=0.1846, simple_loss=0.285, pruned_loss=0.04213, over 7177.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.03087, over 1429657.83 frames.], batch size: 23, lr: 2.51e-04
+2022-04-30 10:57:09,410 INFO [train.py:763] (0/8) Epoch 30, batch 2600, loss[loss=0.1496, simple_loss=0.2471, pruned_loss=0.02605, over 7409.00 frames.], tot_loss[loss=0.1623, simple_loss=0.262, pruned_loss=0.03128, over 1429086.59 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 10:58:15,107 INFO [train.py:763] (0/8) Epoch 30, batch 2650, loss[loss=0.1577, simple_loss=0.2679, pruned_loss=0.02374, over 7408.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2622, pruned_loss=0.03118, over 1426143.63 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 10:59:20,434 INFO [train.py:763] (0/8) Epoch 30, batch 2700, loss[loss=0.1909, simple_loss=0.3028, pruned_loss=0.03954, over 7260.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2623, pruned_loss=0.03093, over 1419908.12 frames.], batch size: 25, lr: 2.51e-04
+2022-04-30 11:00:26,180 INFO [train.py:763] (0/8) Epoch 30, batch 2750, loss[loss=0.1798, simple_loss=0.2801, pruned_loss=0.0397, over 7142.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2626, pruned_loss=0.03113, over 1420180.89 frames.], batch size: 20, lr: 2.51e-04
+2022-04-30 11:01:31,738 INFO [train.py:763] (0/8) Epoch 30, batch 2800, loss[loss=0.1783, simple_loss=0.2692, pruned_loss=0.04366, over 7164.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2626, pruned_loss=0.03122, over 1422082.23 frames.], batch size: 18, lr: 2.51e-04
+2022-04-30 11:02:36,841 INFO [train.py:763] (0/8) Epoch 30, batch 2850, loss[loss=0.1804, simple_loss=0.2764, pruned_loss=0.0422, over 7220.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2628, pruned_loss=0.03124, over 1420125.36 frames.], batch size: 22, lr: 2.51e-04
+2022-04-30 11:03:42,115 INFO [train.py:763] (0/8) Epoch 30, batch 2900, loss[loss=0.1583, simple_loss=0.2677, pruned_loss=0.02442, over 7123.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2632, pruned_loss=0.03135, over 1424293.28 frames.], batch size: 21, lr: 2.51e-04
+2022-04-30 11:04:47,462 INFO [train.py:763] (0/8) Epoch 30, batch 2950, loss[loss=0.1751, simple_loss=0.2834, pruned_loss=0.03343, over 7263.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2632, pruned_loss=0.03129, over 1423703.87 frames.], batch size: 19, lr: 2.50e-04
+2022-04-30 11:05:53,069 INFO [train.py:763] (0/8) Epoch 30, batch 3000, loss[loss=0.1559, simple_loss=0.2598, pruned_loss=0.02602, over 7334.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03116, over 1423607.59 frames.], batch size: 20, lr: 2.50e-04
+2022-04-30 11:05:53,070 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 11:06:08,154 INFO [train.py:792] (0/8) Epoch 30, validation: loss=0.1701, simple_loss=0.2661, pruned_loss=0.03704, over 698248.00 frames.
+2022-04-30 11:07:13,677 INFO [train.py:763] (0/8) Epoch 30, batch 3050, loss[loss=0.1421, simple_loss=0.2343, pruned_loss=0.02494, over 7427.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2626, pruned_loss=0.03134, over 1423540.15 frames.], batch size: 17, lr: 2.50e-04
+2022-04-30 11:08:19,236 INFO [train.py:763] (0/8) Epoch 30, batch 3100, loss[loss=0.1799, simple_loss=0.2824, pruned_loss=0.03873, over 7324.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03107, over 1426548.10 frames.], batch size: 25, lr: 2.50e-04
+2022-04-30 11:09:24,930 INFO [train.py:763] (0/8) Epoch 30, batch 3150, loss[loss=0.1485, simple_loss=0.247, pruned_loss=0.02498, over 6993.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2607, pruned_loss=0.03074, over 1426132.96 frames.], batch size: 16, lr: 2.50e-04
+2022-04-30 11:10:31,244 INFO [train.py:763] (0/8) Epoch 30, batch 3200, loss[loss=0.1767, simple_loss=0.2764, pruned_loss=0.03848, over 7203.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03054, over 1417055.69 frames.], batch size: 23, lr: 2.50e-04
+2022-04-30 11:11:37,984 INFO [train.py:763] (0/8) Epoch 30, batch 3250, loss[loss=0.1649, simple_loss=0.2712, pruned_loss=0.02932, over 7151.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2617, pruned_loss=0.03087, over 1416677.78 frames.], batch size: 20, lr: 2.50e-04
+2022-04-30 11:12:45,430 INFO [train.py:763] (0/8) Epoch 30, batch 3300, loss[loss=0.1414, simple_loss=0.2286, pruned_loss=0.0271, over 7284.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.0304, over 1422809.29 frames.], batch size: 17, lr: 2.50e-04
+2022-04-30 11:13:51,994 INFO [train.py:763] (0/8) Epoch 30, batch 3350, loss[loss=0.1578, simple_loss=0.2523, pruned_loss=0.03166, over 7233.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.03059, over 1422150.93 frames.], batch size: 21, lr: 2.50e-04
+2022-04-30 11:14:57,145 INFO [train.py:763] (0/8) Epoch 30, batch 3400, loss[loss=0.1518, simple_loss=0.2651, pruned_loss=0.0192, over 7296.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.03045, over 1421876.10 frames.], batch size: 25, lr: 2.50e-04
+2022-04-30 11:16:02,384 INFO [train.py:763] (0/8) Epoch 30, batch 3450, loss[loss=0.1765, simple_loss=0.2822, pruned_loss=0.03534, over 6491.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.03045, over 1425945.44 frames.], batch size: 38, lr: 2.50e-04
+2022-04-30 11:17:08,657 INFO [train.py:763] (0/8) Epoch 30, batch 3500, loss[loss=0.1737, simple_loss=0.2726, pruned_loss=0.03744, over 7387.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2603, pruned_loss=0.03027, over 1427105.78 frames.], batch size: 23, lr: 2.50e-04
+2022-04-30 11:18:14,708 INFO [train.py:763] (0/8) Epoch 30, batch 3550, loss[loss=0.1491, simple_loss=0.2443, pruned_loss=0.02696, over 7422.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.03063, over 1428391.84 frames.], batch size: 20, lr: 2.50e-04
+2022-04-30 11:19:20,440 INFO [train.py:763] (0/8) Epoch 30, batch 3600, loss[loss=0.1705, simple_loss=0.2629, pruned_loss=0.03905, over 7314.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2621, pruned_loss=0.03115, over 1423511.75 frames.], batch size: 24, lr: 2.50e-04
+2022-04-30 11:20:25,895 INFO [train.py:763] (0/8) Epoch 30, batch 3650, loss[loss=0.1483, simple_loss=0.2464, pruned_loss=0.02505, over 7125.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2619, pruned_loss=0.03091, over 1422403.48 frames.], batch size: 17, lr: 2.50e-04
+2022-04-30 11:21:32,104 INFO [train.py:763] (0/8) Epoch 30, batch 3700, loss[loss=0.1275, simple_loss=0.2193, pruned_loss=0.01783, over 7289.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2609, pruned_loss=0.03082, over 1424876.12 frames.], batch size: 17, lr: 2.50e-04
+2022-04-30 11:22:38,029 INFO [train.py:763] (0/8) Epoch 30, batch 3750, loss[loss=0.1405, simple_loss=0.2395, pruned_loss=0.02073, over 7263.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2613, pruned_loss=0.03112, over 1423324.45 frames.], batch size: 19, lr: 2.50e-04
+2022-04-30 11:23:45,248 INFO [train.py:763] (0/8) Epoch 30, batch 3800, loss[loss=0.148, simple_loss=0.2446, pruned_loss=0.02568, over 7258.00 frames.], tot_loss[loss=0.162, simple_loss=0.2616, pruned_loss=0.03121, over 1425516.27 frames.], batch size: 18, lr: 2.50e-04
+2022-04-30 11:24:50,563 INFO [train.py:763] (0/8) Epoch 30, batch 3850, loss[loss=0.1567, simple_loss=0.2636, pruned_loss=0.02484, over 7070.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2622, pruned_loss=0.03145, over 1425102.58 frames.], batch size: 18, lr: 2.50e-04
+2022-04-30 11:25:56,100 INFO [train.py:763] (0/8) Epoch 30, batch 3900, loss[loss=0.1715, simple_loss=0.2775, pruned_loss=0.03277, over 7287.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03086, over 1428804.56 frames.], batch size: 24, lr: 2.50e-04
+2022-04-30 11:27:01,588 INFO [train.py:763] (0/8) Epoch 30, batch 3950, loss[loss=0.1429, simple_loss=0.2405, pruned_loss=0.02262, over 7358.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.03098, over 1429165.97 frames.], batch size: 19, lr: 2.50e-04
+2022-04-30 11:28:06,975 INFO [train.py:763] (0/8) Epoch 30, batch 4000, loss[loss=0.146, simple_loss=0.2372, pruned_loss=0.02736, over 7161.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2624, pruned_loss=0.03132, over 1426824.63 frames.], batch size: 18, lr: 2.50e-04
+2022-04-30 11:29:11,965 INFO [train.py:763] (0/8) Epoch 30, batch 4050, loss[loss=0.1619, simple_loss=0.2609, pruned_loss=0.03146, over 7317.00 frames.], tot_loss[loss=0.1628, simple_loss=0.263, pruned_loss=0.03126, over 1426086.10 frames.], batch size: 24, lr: 2.49e-04
+2022-04-30 11:30:18,176 INFO [train.py:763] (0/8) Epoch 30, batch 4100, loss[loss=0.1668, simple_loss=0.2666, pruned_loss=0.03355, over 7172.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2631, pruned_loss=0.03127, over 1427610.86 frames.], batch size: 19, lr: 2.49e-04
+2022-04-30 11:31:24,163 INFO [train.py:763] (0/8) Epoch 30, batch 4150, loss[loss=0.153, simple_loss=0.2746, pruned_loss=0.01568, over 7121.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2618, pruned_loss=0.03046, over 1429514.14 frames.], batch size: 21, lr: 2.49e-04
+2022-04-30 11:32:29,734 INFO [train.py:763] (0/8) Epoch 30, batch 4200, loss[loss=0.1216, simple_loss=0.2072, pruned_loss=0.01794, over 6800.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2612, pruned_loss=0.03035, over 1430304.41 frames.], batch size: 15, lr: 2.49e-04
+2022-04-30 11:33:35,049 INFO [train.py:763] (0/8) Epoch 30, batch 4250, loss[loss=0.1774, simple_loss=0.2733, pruned_loss=0.04079, over 7159.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2613, pruned_loss=0.03049, over 1427397.03 frames.], batch size: 26, lr: 2.49e-04
+2022-04-30 11:34:41,238 INFO [train.py:763] (0/8) Epoch 30, batch 4300, loss[loss=0.1768, simple_loss=0.2833, pruned_loss=0.03511, over 7299.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03044, over 1430244.26 frames.], batch size: 24, lr: 2.49e-04
+2022-04-30 11:35:46,151 INFO [train.py:763] (0/8) Epoch 30, batch 4350, loss[loss=0.161, simple_loss=0.2752, pruned_loss=0.0234, over 7101.00 frames.], tot_loss[loss=0.161, simple_loss=0.2613, pruned_loss=0.03035, over 1421595.43 frames.], batch size: 21, lr: 2.49e-04
+2022-04-30 11:36:51,033 INFO [train.py:763] (0/8) Epoch 30, batch 4400, loss[loss=0.1836, simple_loss=0.2856, pruned_loss=0.04082, over 7108.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2616, pruned_loss=0.03064, over 1411606.20 frames.], batch size: 21, lr: 2.49e-04
+2022-04-30 11:37:56,350 INFO [train.py:763] (0/8) Epoch 30, batch 4450, loss[loss=0.1904, simple_loss=0.2869, pruned_loss=0.04691, over 6275.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03052, over 1410293.19 frames.], batch size: 37, lr: 2.49e-04
+2022-04-30 11:39:02,214 INFO [train.py:763] (0/8) Epoch 30, batch 4500, loss[loss=0.1644, simple_loss=0.264, pruned_loss=0.03234, over 6292.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2626, pruned_loss=0.03104, over 1387066.70 frames.], batch size: 37, lr: 2.49e-04
+2022-04-30 11:40:07,227 INFO [train.py:763] (0/8) Epoch 30, batch 4550, loss[loss=0.1872, simple_loss=0.2861, pruned_loss=0.04417, over 4962.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2646, pruned_loss=0.03208, over 1357738.12 frames.], batch size: 53, lr: 2.49e-04
+2022-04-30 11:40:57,490 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-30.pt
+2022-04-30 11:41:35,703 INFO [train.py:763] (0/8) Epoch 31, batch 0, loss[loss=0.1995, simple_loss=0.2994, pruned_loss=0.04973, over 5112.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2994, pruned_loss=0.04973, over 5112.00 frames.], batch size: 52, lr: 2.45e-04
+2022-04-30 11:42:41,166 INFO [train.py:763] (0/8) Epoch 31, batch 50, loss[loss=0.1669, simple_loss=0.2612, pruned_loss=0.03628, over 6522.00 frames.], tot_loss[loss=0.1661, simple_loss=0.267, pruned_loss=0.03256, over 319908.04 frames.], batch size: 38, lr: 2.45e-04
+2022-04-30 11:43:46,473 INFO [train.py:763] (0/8) Epoch 31, batch 100, loss[loss=0.1552, simple_loss=0.2578, pruned_loss=0.02633, over 7303.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2641, pruned_loss=0.03172, over 566265.88 frames.], batch size: 25, lr: 2.45e-04
+2022-04-30 11:44:52,613 INFO [train.py:763] (0/8) Epoch 31, batch 150, loss[loss=0.1772, simple_loss=0.2701, pruned_loss=0.0421, over 7156.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2625, pruned_loss=0.03096, over 757687.06 frames.], batch size: 26, lr: 2.45e-04
+2022-04-30 11:45:58,818 INFO [train.py:763] (0/8) Epoch 31, batch 200, loss[loss=0.1389, simple_loss=0.236, pruned_loss=0.02088, over 6981.00 frames.], tot_loss[loss=0.161, simple_loss=0.2613, pruned_loss=0.03039, over 902588.09 frames.], batch size: 16, lr: 2.45e-04
+2022-04-30 11:47:04,085 INFO [train.py:763] (0/8) Epoch 31, batch 250, loss[loss=0.1628, simple_loss=0.2692, pruned_loss=0.02821, over 7290.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2625, pruned_loss=0.0311, over 1022537.45 frames.], batch size: 24, lr: 2.45e-04
+2022-04-30 11:48:09,437 INFO [train.py:763] (0/8) Epoch 31, batch 300, loss[loss=0.1691, simple_loss=0.2656, pruned_loss=0.03632, over 7288.00 frames.], tot_loss[loss=0.163, simple_loss=0.2625, pruned_loss=0.03168, over 1113242.89 frames.], batch size: 24, lr: 2.45e-04
+2022-04-30 11:49:14,699 INFO [train.py:763] (0/8) Epoch 31, batch 350, loss[loss=0.1666, simple_loss=0.2671, pruned_loss=0.03301, over 7039.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03135, over 1181086.07 frames.], batch size: 28, lr: 2.45e-04
+2022-04-30 11:50:20,239 INFO [train.py:763] (0/8) Epoch 31, batch 400, loss[loss=0.1502, simple_loss=0.2603, pruned_loss=0.02002, over 7209.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2619, pruned_loss=0.03128, over 1237155.15 frames.], batch size: 26, lr: 2.45e-04
+2022-04-30 11:51:25,630 INFO [train.py:763] (0/8) Epoch 31, batch 450, loss[loss=0.1669, simple_loss=0.2783, pruned_loss=0.02769, over 7313.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2618, pruned_loss=0.03131, over 1277938.95 frames.], batch size: 21, lr: 2.45e-04
+2022-04-30 11:52:41,066 INFO [train.py:763] (0/8) Epoch 31, batch 500, loss[loss=0.1588, simple_loss=0.2623, pruned_loss=0.02764, over 7322.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2616, pruned_loss=0.03139, over 1313639.61 frames.], batch size: 22, lr: 2.45e-04
+2022-04-30 11:53:47,805 INFO [train.py:763] (0/8) Epoch 31, batch 550, loss[loss=0.1501, simple_loss=0.2544, pruned_loss=0.02292, over 7331.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2622, pruned_loss=0.03155, over 1341519.68 frames.], batch size: 22, lr: 2.45e-04
+2022-04-30 11:54:53,979 INFO [train.py:763] (0/8) Epoch 31, batch 600, loss[loss=0.1283, simple_loss=0.2162, pruned_loss=0.02023, over 7150.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2617, pruned_loss=0.03129, over 1364200.87 frames.], batch size: 17, lr: 2.45e-04
+2022-04-30 11:55:59,918 INFO [train.py:763] (0/8) Epoch 31, batch 650, loss[loss=0.1447, simple_loss=0.2263, pruned_loss=0.03157, over 6998.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2612, pruned_loss=0.03147, over 1380085.74 frames.], batch size: 16, lr: 2.45e-04
+2022-04-30 11:57:06,465 INFO [train.py:763] (0/8) Epoch 31, batch 700, loss[loss=0.158, simple_loss=0.2571, pruned_loss=0.02944, over 7202.00 frames.], tot_loss[loss=0.162, simple_loss=0.2615, pruned_loss=0.0313, over 1387803.98 frames.], batch size: 23, lr: 2.45e-04
+2022-04-30 11:58:13,277 INFO [train.py:763] (0/8) Epoch 31, batch 750, loss[loss=0.1639, simple_loss=0.2714, pruned_loss=0.02826, over 7116.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2611, pruned_loss=0.03078, over 1395602.64 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 11:59:18,736 INFO [train.py:763] (0/8) Epoch 31, batch 800, loss[loss=0.1423, simple_loss=0.2431, pruned_loss=0.02077, over 7281.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03106, over 1401134.01 frames.], batch size: 18, lr: 2.44e-04
+2022-04-30 12:00:24,043 INFO [train.py:763] (0/8) Epoch 31, batch 850, loss[loss=0.1871, simple_loss=0.2887, pruned_loss=0.0428, over 7305.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03126, over 1407917.56 frames.], batch size: 25, lr: 2.44e-04
+2022-04-30 12:01:28,738 INFO [train.py:763] (0/8) Epoch 31, batch 900, loss[loss=0.1679, simple_loss=0.2712, pruned_loss=0.03234, over 7344.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2636, pruned_loss=0.03112, over 1410214.55 frames.], batch size: 22, lr: 2.44e-04
+2022-04-30 12:02:34,066 INFO [train.py:763] (0/8) Epoch 31, batch 950, loss[loss=0.1402, simple_loss=0.2351, pruned_loss=0.02264, over 6842.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2619, pruned_loss=0.03098, over 1411595.38 frames.], batch size: 15, lr: 2.44e-04
+2022-04-30 12:03:39,308 INFO [train.py:763] (0/8) Epoch 31, batch 1000, loss[loss=0.1326, simple_loss=0.2319, pruned_loss=0.01666, over 7423.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03056, over 1416069.83 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:04:53,742 INFO [train.py:763] (0/8) Epoch 31, batch 1050, loss[loss=0.175, simple_loss=0.2746, pruned_loss=0.03775, over 7244.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2613, pruned_loss=0.03048, over 1419780.77 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:05:59,159 INFO [train.py:763] (0/8) Epoch 31, batch 1100, loss[loss=0.1864, simple_loss=0.282, pruned_loss=0.04538, over 7193.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2611, pruned_loss=0.03051, over 1417930.11 frames.], batch size: 22, lr: 2.44e-04
+2022-04-30 12:07:23,565 INFO [train.py:763] (0/8) Epoch 31, batch 1150, loss[loss=0.1453, simple_loss=0.2323, pruned_loss=0.02918, over 7149.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2617, pruned_loss=0.03073, over 1421598.20 frames.], batch size: 17, lr: 2.44e-04
+2022-04-30 12:08:30,102 INFO [train.py:763] (0/8) Epoch 31, batch 1200, loss[loss=0.1616, simple_loss=0.2782, pruned_loss=0.0225, over 7407.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2612, pruned_loss=0.03026, over 1424317.51 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 12:09:54,558 INFO [train.py:763] (0/8) Epoch 31, batch 1250, loss[loss=0.1569, simple_loss=0.2672, pruned_loss=0.02332, over 7197.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03082, over 1417497.79 frames.], batch size: 23, lr: 2.44e-04
+2022-04-30 12:11:00,229 INFO [train.py:763] (0/8) Epoch 31, batch 1300, loss[loss=0.1458, simple_loss=0.2471, pruned_loss=0.0223, over 7143.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2612, pruned_loss=0.03081, over 1422964.77 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:12:14,871 INFO [train.py:763] (0/8) Epoch 31, batch 1350, loss[loss=0.1642, simple_loss=0.2581, pruned_loss=0.03511, over 7336.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2605, pruned_loss=0.03082, over 1421833.20 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:13:22,481 INFO [train.py:763] (0/8) Epoch 31, batch 1400, loss[loss=0.1417, simple_loss=0.2439, pruned_loss=0.01978, over 7229.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2593, pruned_loss=0.03018, over 1422362.13 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:14:38,789 INFO [train.py:763] (0/8) Epoch 31, batch 1450, loss[loss=0.1318, simple_loss=0.2366, pruned_loss=0.01351, over 7333.00 frames.], tot_loss[loss=0.1601, simple_loss=0.26, pruned_loss=0.03014, over 1423944.91 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:15:46,116 INFO [train.py:763] (0/8) Epoch 31, batch 1500, loss[loss=0.1676, simple_loss=0.2656, pruned_loss=0.03477, over 5263.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2591, pruned_loss=0.02996, over 1422767.29 frames.], batch size: 52, lr: 2.44e-04
+2022-04-30 12:16:51,632 INFO [train.py:763] (0/8) Epoch 31, batch 1550, loss[loss=0.136, simple_loss=0.2334, pruned_loss=0.01924, over 7416.00 frames.], tot_loss[loss=0.159, simple_loss=0.2588, pruned_loss=0.02962, over 1422460.46 frames.], batch size: 18, lr: 2.44e-04
+2022-04-30 12:17:56,942 INFO [train.py:763] (0/8) Epoch 31, batch 1600, loss[loss=0.191, simple_loss=0.2923, pruned_loss=0.04488, over 7212.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02984, over 1418850.87 frames.], batch size: 23, lr: 2.44e-04
+2022-04-30 12:19:02,307 INFO [train.py:763] (0/8) Epoch 31, batch 1650, loss[loss=0.1521, simple_loss=0.2626, pruned_loss=0.02085, over 7404.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03056, over 1417806.10 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 12:20:07,993 INFO [train.py:763] (0/8) Epoch 31, batch 1700, loss[loss=0.1724, simple_loss=0.2804, pruned_loss=0.03214, over 7101.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.03041, over 1413662.17 frames.], batch size: 21, lr: 2.44e-04
+2022-04-30 12:21:14,755 INFO [train.py:763] (0/8) Epoch 31, batch 1750, loss[loss=0.1791, simple_loss=0.2689, pruned_loss=0.04462, over 4664.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03059, over 1410524.59 frames.], batch size: 52, lr: 2.44e-04
+2022-04-30 12:21:42,858 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-144000.pt
+2022-04-30 12:22:33,263 INFO [train.py:763] (0/8) Epoch 31, batch 1800, loss[loss=0.1751, simple_loss=0.2792, pruned_loss=0.03553, over 7230.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2617, pruned_loss=0.03039, over 1411812.88 frames.], batch size: 20, lr: 2.44e-04
+2022-04-30 12:23:40,155 INFO [train.py:763] (0/8) Epoch 31, batch 1850, loss[loss=0.1554, simple_loss=0.2446, pruned_loss=0.03309, over 7004.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2617, pruned_loss=0.03066, over 1405913.84 frames.], batch size: 16, lr: 2.44e-04
+2022-04-30 12:24:46,007 INFO [train.py:763] (0/8) Epoch 31, batch 1900, loss[loss=0.1675, simple_loss=0.2617, pruned_loss=0.03665, over 7362.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2611, pruned_loss=0.03066, over 1412932.99 frames.], batch size: 19, lr: 2.44e-04
+2022-04-30 12:25:51,353 INFO [train.py:763] (0/8) Epoch 31, batch 1950, loss[loss=0.1516, simple_loss=0.2488, pruned_loss=0.0272, over 7348.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.0306, over 1418975.93 frames.], batch size: 19, lr: 2.43e-04
+2022-04-30 12:26:56,760 INFO [train.py:763] (0/8) Epoch 31, batch 2000, loss[loss=0.1489, simple_loss=0.247, pruned_loss=0.02536, over 7284.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2612, pruned_loss=0.03085, over 1419786.03 frames.], batch size: 18, lr: 2.43e-04
+2022-04-30 12:28:01,922 INFO [train.py:763] (0/8) Epoch 31, batch 2050, loss[loss=0.1966, simple_loss=0.3104, pruned_loss=0.04142, over 7139.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2625, pruned_loss=0.03101, over 1416130.87 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:29:07,877 INFO [train.py:763] (0/8) Epoch 31, batch 2100, loss[loss=0.1471, simple_loss=0.2381, pruned_loss=0.02809, over 7232.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2635, pruned_loss=0.03118, over 1416394.37 frames.], batch size: 16, lr: 2.43e-04
+2022-04-30 12:30:13,155 INFO [train.py:763] (0/8) Epoch 31, batch 2150, loss[loss=0.153, simple_loss=0.2613, pruned_loss=0.02234, over 7220.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2634, pruned_loss=0.03082, over 1420745.76 frames.], batch size: 21, lr: 2.43e-04
+2022-04-30 12:31:18,654 INFO [train.py:763] (0/8) Epoch 31, batch 2200, loss[loss=0.1619, simple_loss=0.2692, pruned_loss=0.02727, over 7134.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2622, pruned_loss=0.03046, over 1423498.81 frames.], batch size: 26, lr: 2.43e-04
+2022-04-30 12:32:23,993 INFO [train.py:763] (0/8) Epoch 31, batch 2250, loss[loss=0.1408, simple_loss=0.2375, pruned_loss=0.0221, over 7071.00 frames.], tot_loss[loss=0.161, simple_loss=0.2616, pruned_loss=0.0302, over 1424209.14 frames.], batch size: 18, lr: 2.43e-04
+2022-04-30 12:33:30,786 INFO [train.py:763] (0/8) Epoch 31, batch 2300, loss[loss=0.1616, simple_loss=0.2631, pruned_loss=0.03007, over 7347.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.03034, over 1421348.06 frames.], batch size: 22, lr: 2.43e-04
+2022-04-30 12:34:36,639 INFO [train.py:763] (0/8) Epoch 31, batch 2350, loss[loss=0.1264, simple_loss=0.2169, pruned_loss=0.01802, over 7299.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2617, pruned_loss=0.03037, over 1424938.42 frames.], batch size: 17, lr: 2.43e-04
+2022-04-30 12:35:41,759 INFO [train.py:763] (0/8) Epoch 31, batch 2400, loss[loss=0.1575, simple_loss=0.2653, pruned_loss=0.02488, over 7326.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2613, pruned_loss=0.03024, over 1420395.53 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:36:47,285 INFO [train.py:763] (0/8) Epoch 31, batch 2450, loss[loss=0.2001, simple_loss=0.299, pruned_loss=0.05065, over 7176.00 frames.], tot_loss[loss=0.161, simple_loss=0.261, pruned_loss=0.03046, over 1421453.17 frames.], batch size: 26, lr: 2.43e-04
+2022-04-30 12:37:52,784 INFO [train.py:763] (0/8) Epoch 31, batch 2500, loss[loss=0.1351, simple_loss=0.2324, pruned_loss=0.01892, over 7283.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03074, over 1424304.29 frames.], batch size: 17, lr: 2.43e-04
+2022-04-30 12:38:58,020 INFO [train.py:763] (0/8) Epoch 31, batch 2550, loss[loss=0.1586, simple_loss=0.2519, pruned_loss=0.03267, over 7314.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.031, over 1422176.93 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:40:03,282 INFO [train.py:763] (0/8) Epoch 31, batch 2600, loss[loss=0.1345, simple_loss=0.2279, pruned_loss=0.02052, over 7144.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.03065, over 1421383.78 frames.], batch size: 17, lr: 2.43e-04
+2022-04-30 12:41:08,496 INFO [train.py:763] (0/8) Epoch 31, batch 2650, loss[loss=0.1893, simple_loss=0.2926, pruned_loss=0.04302, over 7147.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03029, over 1423765.58 frames.], batch size: 26, lr: 2.43e-04
+2022-04-30 12:42:15,315 INFO [train.py:763] (0/8) Epoch 31, batch 2700, loss[loss=0.1496, simple_loss=0.2551, pruned_loss=0.02202, over 7329.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.03, over 1422516.28 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:43:20,592 INFO [train.py:763] (0/8) Epoch 31, batch 2750, loss[loss=0.1711, simple_loss=0.2788, pruned_loss=0.03169, over 7159.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2608, pruned_loss=0.03011, over 1425153.39 frames.], batch size: 28, lr: 2.43e-04
+2022-04-30 12:44:27,121 INFO [train.py:763] (0/8) Epoch 31, batch 2800, loss[loss=0.1402, simple_loss=0.2257, pruned_loss=0.02735, over 7425.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2605, pruned_loss=0.03054, over 1424098.97 frames.], batch size: 18, lr: 2.43e-04
+2022-04-30 12:45:34,100 INFO [train.py:763] (0/8) Epoch 31, batch 2850, loss[loss=0.1703, simple_loss=0.2746, pruned_loss=0.03297, over 6372.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2609, pruned_loss=0.03108, over 1421294.58 frames.], batch size: 38, lr: 2.43e-04
+2022-04-30 12:46:39,730 INFO [train.py:763] (0/8) Epoch 31, batch 2900, loss[loss=0.1664, simple_loss=0.2623, pruned_loss=0.03527, over 7222.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2618, pruned_loss=0.03092, over 1425759.51 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:47:44,748 INFO [train.py:763] (0/8) Epoch 31, batch 2950, loss[loss=0.167, simple_loss=0.2734, pruned_loss=0.03033, over 7198.00 frames.], tot_loss[loss=0.162, simple_loss=0.2622, pruned_loss=0.03089, over 1419463.34 frames.], batch size: 23, lr: 2.43e-04
+2022-04-30 12:48:50,669 INFO [train.py:763] (0/8) Epoch 31, batch 3000, loss[loss=0.1664, simple_loss=0.2684, pruned_loss=0.03222, over 7424.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2622, pruned_loss=0.03112, over 1420081.76 frames.], batch size: 20, lr: 2.43e-04
+2022-04-30 12:48:50,670 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 12:49:05,872 INFO [train.py:792] (0/8) Epoch 31, validation: loss=0.1686, simple_loss=0.2652, pruned_loss=0.03603, over 698248.00 frames.
+2022-04-30 12:50:12,210 INFO [train.py:763] (0/8) Epoch 31, batch 3050, loss[loss=0.1938, simple_loss=0.3014, pruned_loss=0.04309, over 7263.00 frames.], tot_loss[loss=0.1622, simple_loss=0.262, pruned_loss=0.0312, over 1423802.53 frames.], batch size: 25, lr: 2.43e-04
+2022-04-30 12:51:18,208 INFO [train.py:763] (0/8) Epoch 31, batch 3100, loss[loss=0.1781, simple_loss=0.2926, pruned_loss=0.0318, over 7005.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03101, over 1426747.56 frames.], batch size: 28, lr: 2.42e-04
+2022-04-30 12:52:23,643 INFO [train.py:763] (0/8) Epoch 31, batch 3150, loss[loss=0.1568, simple_loss=0.2457, pruned_loss=0.034, over 7282.00 frames.], tot_loss[loss=0.162, simple_loss=0.2615, pruned_loss=0.03129, over 1423851.34 frames.], batch size: 17, lr: 2.42e-04
+2022-04-30 12:53:29,128 INFO [train.py:763] (0/8) Epoch 31, batch 3200, loss[loss=0.1449, simple_loss=0.2518, pruned_loss=0.01899, over 7110.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2622, pruned_loss=0.03103, over 1426620.01 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 12:54:36,156 INFO [train.py:763] (0/8) Epoch 31, batch 3250, loss[loss=0.1582, simple_loss=0.2571, pruned_loss=0.02967, over 7339.00 frames.], tot_loss[loss=0.162, simple_loss=0.2622, pruned_loss=0.03089, over 1427079.74 frames.], batch size: 22, lr: 2.42e-04
+2022-04-30 12:55:42,947 INFO [train.py:763] (0/8) Epoch 31, batch 3300, loss[loss=0.1541, simple_loss=0.2593, pruned_loss=0.02449, over 7435.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03077, over 1423190.74 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 12:56:50,147 INFO [train.py:763] (0/8) Epoch 31, batch 3350, loss[loss=0.1667, simple_loss=0.2673, pruned_loss=0.0331, over 7322.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2603, pruned_loss=0.03019, over 1424293.09 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 12:57:56,879 INFO [train.py:763] (0/8) Epoch 31, batch 3400, loss[loss=0.1552, simple_loss=0.2478, pruned_loss=0.03128, over 7326.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2621, pruned_loss=0.0311, over 1421604.93 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 12:59:03,245 INFO [train.py:763] (0/8) Epoch 31, batch 3450, loss[loss=0.1507, simple_loss=0.2653, pruned_loss=0.01807, over 7206.00 frames.], tot_loss[loss=0.162, simple_loss=0.2622, pruned_loss=0.0309, over 1424225.39 frames.], batch size: 22, lr: 2.42e-04
+2022-04-30 13:00:08,966 INFO [train.py:763] (0/8) Epoch 31, batch 3500, loss[loss=0.1759, simple_loss=0.2787, pruned_loss=0.03651, over 7285.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2623, pruned_loss=0.03074, over 1427833.89 frames.], batch size: 24, lr: 2.42e-04
+2022-04-30 13:01:14,845 INFO [train.py:763] (0/8) Epoch 31, batch 3550, loss[loss=0.1937, simple_loss=0.2808, pruned_loss=0.05331, over 7391.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03074, over 1430682.29 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:02:21,339 INFO [train.py:763] (0/8) Epoch 31, batch 3600, loss[loss=0.1649, simple_loss=0.2658, pruned_loss=0.03197, over 6382.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03032, over 1427928.50 frames.], batch size: 38, lr: 2.42e-04
+2022-04-30 13:03:26,541 INFO [train.py:763] (0/8) Epoch 31, batch 3650, loss[loss=0.1539, simple_loss=0.261, pruned_loss=0.02345, over 7234.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2618, pruned_loss=0.03069, over 1428243.15 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 13:04:32,090 INFO [train.py:763] (0/8) Epoch 31, batch 3700, loss[loss=0.1337, simple_loss=0.2254, pruned_loss=0.02106, over 7133.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03061, over 1430354.72 frames.], batch size: 17, lr: 2.42e-04
+2022-04-30 13:05:36,818 INFO [train.py:763] (0/8) Epoch 31, batch 3750, loss[loss=0.1652, simple_loss=0.2644, pruned_loss=0.03298, over 7223.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03053, over 1423965.26 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:06:42,590 INFO [train.py:763] (0/8) Epoch 31, batch 3800, loss[loss=0.1732, simple_loss=0.2814, pruned_loss=0.03255, over 7376.00 frames.], tot_loss[loss=0.1617, simple_loss=0.262, pruned_loss=0.03067, over 1425866.13 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:07:47,980 INFO [train.py:763] (0/8) Epoch 31, batch 3850, loss[loss=0.1586, simple_loss=0.2641, pruned_loss=0.02655, over 7424.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2621, pruned_loss=0.03075, over 1428092.54 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 13:08:53,261 INFO [train.py:763] (0/8) Epoch 31, batch 3900, loss[loss=0.1628, simple_loss=0.2543, pruned_loss=0.03562, over 7173.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2615, pruned_loss=0.03043, over 1429338.17 frames.], batch size: 18, lr: 2.42e-04
+2022-04-30 13:09:58,653 INFO [train.py:763] (0/8) Epoch 31, batch 3950, loss[loss=0.1658, simple_loss=0.2736, pruned_loss=0.02901, over 7219.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2618, pruned_loss=0.0309, over 1424316.23 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 13:11:04,251 INFO [train.py:763] (0/8) Epoch 31, batch 4000, loss[loss=0.1479, simple_loss=0.2429, pruned_loss=0.02642, over 7409.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2611, pruned_loss=0.03083, over 1422138.74 frames.], batch size: 18, lr: 2.42e-04
+2022-04-30 13:12:09,635 INFO [train.py:763] (0/8) Epoch 31, batch 4050, loss[loss=0.1868, simple_loss=0.2965, pruned_loss=0.03853, over 7388.00 frames.], tot_loss[loss=0.1614, simple_loss=0.261, pruned_loss=0.03096, over 1419835.07 frames.], batch size: 23, lr: 2.42e-04
+2022-04-30 13:13:15,808 INFO [train.py:763] (0/8) Epoch 31, batch 4100, loss[loss=0.1753, simple_loss=0.2742, pruned_loss=0.03818, over 7218.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2611, pruned_loss=0.0308, over 1417715.94 frames.], batch size: 22, lr: 2.42e-04
+2022-04-30 13:14:21,778 INFO [train.py:763] (0/8) Epoch 31, batch 4150, loss[loss=0.1626, simple_loss=0.2728, pruned_loss=0.02625, over 7223.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03088, over 1421471.65 frames.], batch size: 21, lr: 2.42e-04
+2022-04-30 13:15:28,736 INFO [train.py:763] (0/8) Epoch 31, batch 4200, loss[loss=0.1577, simple_loss=0.254, pruned_loss=0.03067, over 7324.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2602, pruned_loss=0.03062, over 1421177.52 frames.], batch size: 20, lr: 2.42e-04
+2022-04-30 13:16:35,577 INFO [train.py:763] (0/8) Epoch 31, batch 4250, loss[loss=0.1527, simple_loss=0.2491, pruned_loss=0.02817, over 7250.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2603, pruned_loss=0.03052, over 1419381.53 frames.], batch size: 19, lr: 2.42e-04
+2022-04-30 13:17:40,855 INFO [train.py:763] (0/8) Epoch 31, batch 4300, loss[loss=0.1628, simple_loss=0.2559, pruned_loss=0.03484, over 7416.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2601, pruned_loss=0.03057, over 1418818.87 frames.], batch size: 18, lr: 2.42e-04
+2022-04-30 13:18:46,146 INFO [train.py:763] (0/8) Epoch 31, batch 4350, loss[loss=0.1392, simple_loss=0.2335, pruned_loss=0.02239, over 7182.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2608, pruned_loss=0.03084, over 1419161.71 frames.], batch size: 18, lr: 2.41e-04
+2022-04-30 13:19:51,346 INFO [train.py:763] (0/8) Epoch 31, batch 4400, loss[loss=0.1832, simple_loss=0.2892, pruned_loss=0.03862, over 7264.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2618, pruned_loss=0.03143, over 1405462.31 frames.], batch size: 25, lr: 2.41e-04
+2022-04-30 13:20:56,970 INFO [train.py:763] (0/8) Epoch 31, batch 4450, loss[loss=0.1299, simple_loss=0.2256, pruned_loss=0.01707, over 7206.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.03171, over 1402893.66 frames.], batch size: 16, lr: 2.41e-04
+2022-04-30 13:22:02,218 INFO [train.py:763] (0/8) Epoch 31, batch 4500, loss[loss=0.1804, simple_loss=0.2811, pruned_loss=0.03983, over 6675.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2626, pruned_loss=0.03178, over 1395961.88 frames.], batch size: 31, lr: 2.41e-04
+2022-04-30 13:23:07,085 INFO [train.py:763] (0/8) Epoch 31, batch 4550, loss[loss=0.1804, simple_loss=0.2787, pruned_loss=0.0411, over 5220.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2628, pruned_loss=0.03228, over 1358016.40 frames.], batch size: 52, lr: 2.41e-04
+2022-04-30 13:23:56,193 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-31.pt
+2022-04-30 13:24:35,152 INFO [train.py:763] (0/8) Epoch 32, batch 0, loss[loss=0.183, simple_loss=0.282, pruned_loss=0.04206, over 6741.00 frames.], tot_loss[loss=0.183, simple_loss=0.282, pruned_loss=0.04206, over 6741.00 frames.], batch size: 31, lr: 2.38e-04
+2022-04-30 13:25:38,926 INFO [train.py:763] (0/8) Epoch 32, batch 50, loss[loss=0.1519, simple_loss=0.2565, pruned_loss=0.02365, over 5098.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2621, pruned_loss=0.03137, over 313831.21 frames.], batch size: 52, lr: 2.38e-04
+2022-04-30 13:26:41,329 INFO [train.py:763] (0/8) Epoch 32, batch 100, loss[loss=0.1586, simple_loss=0.2587, pruned_loss=0.02926, over 6285.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2623, pruned_loss=0.03163, over 558728.88 frames.], batch size: 37, lr: 2.38e-04
+2022-04-30 13:27:47,094 INFO [train.py:763] (0/8) Epoch 32, batch 150, loss[loss=0.1626, simple_loss=0.2652, pruned_loss=0.02997, over 7197.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2626, pruned_loss=0.03094, over 750791.88 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:28:52,462 INFO [train.py:763] (0/8) Epoch 32, batch 200, loss[loss=0.1287, simple_loss=0.2206, pruned_loss=0.01838, over 7000.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2612, pruned_loss=0.03071, over 894134.69 frames.], batch size: 16, lr: 2.37e-04
+2022-04-30 13:29:57,602 INFO [train.py:763] (0/8) Epoch 32, batch 250, loss[loss=0.1548, simple_loss=0.2584, pruned_loss=0.02559, over 7247.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2615, pruned_loss=0.0306, over 1009508.31 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:31:03,090 INFO [train.py:763] (0/8) Epoch 32, batch 300, loss[loss=0.1865, simple_loss=0.2983, pruned_loss=0.03732, over 6751.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2624, pruned_loss=0.03102, over 1092255.37 frames.], batch size: 31, lr: 2.37e-04
+2022-04-30 13:32:10,110 INFO [train.py:763] (0/8) Epoch 32, batch 350, loss[loss=0.1477, simple_loss=0.2381, pruned_loss=0.02863, over 7417.00 frames.], tot_loss[loss=0.163, simple_loss=0.2631, pruned_loss=0.03143, over 1163190.95 frames.], batch size: 18, lr: 2.37e-04
+2022-04-30 13:33:15,981 INFO [train.py:763] (0/8) Epoch 32, batch 400, loss[loss=0.1618, simple_loss=0.2523, pruned_loss=0.03572, over 7431.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2615, pruned_loss=0.03086, over 1219744.68 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:34:21,568 INFO [train.py:763] (0/8) Epoch 32, batch 450, loss[loss=0.1562, simple_loss=0.2608, pruned_loss=0.02577, over 6815.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03041, over 1261878.63 frames.], batch size: 31, lr: 2.37e-04
+2022-04-30 13:35:26,882 INFO [train.py:763] (0/8) Epoch 32, batch 500, loss[loss=0.1787, simple_loss=0.2702, pruned_loss=0.04366, over 7207.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2613, pruned_loss=0.03043, over 1300162.90 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:36:32,868 INFO [train.py:763] (0/8) Epoch 32, batch 550, loss[loss=0.1554, simple_loss=0.2655, pruned_loss=0.0226, over 7324.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2627, pruned_loss=0.03057, over 1328877.61 frames.], batch size: 21, lr: 2.37e-04
+2022-04-30 13:37:38,147 INFO [train.py:763] (0/8) Epoch 32, batch 600, loss[loss=0.1833, simple_loss=0.2873, pruned_loss=0.03961, over 7269.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2628, pruned_loss=0.031, over 1346452.33 frames.], batch size: 24, lr: 2.37e-04
+2022-04-30 13:38:43,405 INFO [train.py:763] (0/8) Epoch 32, batch 650, loss[loss=0.1854, simple_loss=0.284, pruned_loss=0.04341, over 7171.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2624, pruned_loss=0.03051, over 1363733.24 frames.], batch size: 26, lr: 2.37e-04
+2022-04-30 13:39:48,623 INFO [train.py:763] (0/8) Epoch 32, batch 700, loss[loss=0.1703, simple_loss=0.2534, pruned_loss=0.04363, over 7143.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2619, pruned_loss=0.03055, over 1374294.95 frames.], batch size: 17, lr: 2.37e-04
+2022-04-30 13:40:55,077 INFO [train.py:763] (0/8) Epoch 32, batch 750, loss[loss=0.1642, simple_loss=0.277, pruned_loss=0.02572, over 7231.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2619, pruned_loss=0.03048, over 1380426.75 frames.], batch size: 21, lr: 2.37e-04
+2022-04-30 13:42:02,253 INFO [train.py:763] (0/8) Epoch 32, batch 800, loss[loss=0.1514, simple_loss=0.247, pruned_loss=0.02783, over 7435.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.03042, over 1391823.55 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:43:08,541 INFO [train.py:763] (0/8) Epoch 32, batch 850, loss[loss=0.1686, simple_loss=0.2728, pruned_loss=0.03219, over 7378.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03057, over 1399469.90 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:44:14,308 INFO [train.py:763] (0/8) Epoch 32, batch 900, loss[loss=0.1749, simple_loss=0.2816, pruned_loss=0.03415, over 7212.00 frames.], tot_loss[loss=0.16, simple_loss=0.2597, pruned_loss=0.03018, over 1409522.73 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:45:21,142 INFO [train.py:763] (0/8) Epoch 32, batch 950, loss[loss=0.1565, simple_loss=0.2572, pruned_loss=0.02792, over 7433.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.03006, over 1414494.86 frames.], batch size: 20, lr: 2.37e-04
+2022-04-30 13:46:27,366 INFO [train.py:763] (0/8) Epoch 32, batch 1000, loss[loss=0.1774, simple_loss=0.2831, pruned_loss=0.03584, over 7210.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.0298, over 1414583.81 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:47:33,319 INFO [train.py:763] (0/8) Epoch 32, batch 1050, loss[loss=0.1621, simple_loss=0.2652, pruned_loss=0.02953, over 7032.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02993, over 1414077.95 frames.], batch size: 28, lr: 2.37e-04
+2022-04-30 13:48:38,623 INFO [train.py:763] (0/8) Epoch 32, batch 1100, loss[loss=0.1774, simple_loss=0.2832, pruned_loss=0.03576, over 7260.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.02984, over 1419000.92 frames.], batch size: 24, lr: 2.37e-04
+2022-04-30 13:49:45,284 INFO [train.py:763] (0/8) Epoch 32, batch 1150, loss[loss=0.1594, simple_loss=0.264, pruned_loss=0.02737, over 7197.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02941, over 1420549.89 frames.], batch size: 23, lr: 2.37e-04
+2022-04-30 13:50:50,724 INFO [train.py:763] (0/8) Epoch 32, batch 1200, loss[loss=0.1475, simple_loss=0.2549, pruned_loss=0.02002, over 7181.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2607, pruned_loss=0.02998, over 1423082.35 frames.], batch size: 26, lr: 2.37e-04
+2022-04-30 13:51:56,751 INFO [train.py:763] (0/8) Epoch 32, batch 1250, loss[loss=0.1496, simple_loss=0.2619, pruned_loss=0.01864, over 6583.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2619, pruned_loss=0.03065, over 1422535.26 frames.], batch size: 38, lr: 2.37e-04
+2022-04-30 13:53:02,504 INFO [train.py:763] (0/8) Epoch 32, batch 1300, loss[loss=0.1497, simple_loss=0.262, pruned_loss=0.01871, over 7207.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2606, pruned_loss=0.0309, over 1422606.00 frames.], batch size: 21, lr: 2.37e-04
+2022-04-30 13:54:10,203 INFO [train.py:763] (0/8) Epoch 32, batch 1350, loss[loss=0.1809, simple_loss=0.2726, pruned_loss=0.04462, over 7259.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2611, pruned_loss=0.0311, over 1421530.84 frames.], batch size: 17, lr: 2.37e-04
+2022-04-30 13:55:17,154 INFO [train.py:763] (0/8) Epoch 32, batch 1400, loss[loss=0.1706, simple_loss=0.2756, pruned_loss=0.0328, over 7140.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2612, pruned_loss=0.03089, over 1423281.01 frames.], batch size: 20, lr: 2.36e-04
+2022-04-30 13:56:22,424 INFO [train.py:763] (0/8) Epoch 32, batch 1450, loss[loss=0.1644, simple_loss=0.2674, pruned_loss=0.03073, over 6834.00 frames.], tot_loss[loss=0.1612, simple_loss=0.261, pruned_loss=0.0307, over 1425879.27 frames.], batch size: 31, lr: 2.36e-04
+2022-04-30 13:57:27,829 INFO [train.py:763] (0/8) Epoch 32, batch 1500, loss[loss=0.188, simple_loss=0.2813, pruned_loss=0.04736, over 5112.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2613, pruned_loss=0.03114, over 1423126.82 frames.], batch size: 52, lr: 2.36e-04
+2022-04-30 13:58:33,082 INFO [train.py:763] (0/8) Epoch 32, batch 1550, loss[loss=0.1762, simple_loss=0.2779, pruned_loss=0.03721, over 7224.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03103, over 1418848.02 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 13:59:38,330 INFO [train.py:763] (0/8) Epoch 32, batch 1600, loss[loss=0.1922, simple_loss=0.2882, pruned_loss=0.04807, over 7419.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2614, pruned_loss=0.03114, over 1420656.56 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:00:43,697 INFO [train.py:763] (0/8) Epoch 32, batch 1650, loss[loss=0.1472, simple_loss=0.2579, pruned_loss=0.01827, over 7226.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2611, pruned_loss=0.03076, over 1421547.25 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:01:48,797 INFO [train.py:763] (0/8) Epoch 32, batch 1700, loss[loss=0.1786, simple_loss=0.2799, pruned_loss=0.03862, over 7293.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2616, pruned_loss=0.03094, over 1423535.39 frames.], batch size: 24, lr: 2.36e-04
+2022-04-30 14:02:54,188 INFO [train.py:763] (0/8) Epoch 32, batch 1750, loss[loss=0.2032, simple_loss=0.3037, pruned_loss=0.05135, over 7111.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2622, pruned_loss=0.03114, over 1417331.70 frames.], batch size: 28, lr: 2.36e-04
+2022-04-30 14:03:59,684 INFO [train.py:763] (0/8) Epoch 32, batch 1800, loss[loss=0.1524, simple_loss=0.2538, pruned_loss=0.02551, over 7257.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03078, over 1420660.93 frames.], batch size: 19, lr: 2.36e-04
+2022-04-30 14:05:06,120 INFO [train.py:763] (0/8) Epoch 32, batch 1850, loss[loss=0.1516, simple_loss=0.2583, pruned_loss=0.02252, over 7314.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2611, pruned_loss=0.03063, over 1423534.14 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:06:21,252 INFO [train.py:763] (0/8) Epoch 32, batch 1900, loss[loss=0.1732, simple_loss=0.2783, pruned_loss=0.03401, over 7380.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2618, pruned_loss=0.03063, over 1425797.30 frames.], batch size: 23, lr: 2.36e-04
+2022-04-30 14:07:26,674 INFO [train.py:763] (0/8) Epoch 32, batch 1950, loss[loss=0.1587, simple_loss=0.2584, pruned_loss=0.02954, over 7308.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2622, pruned_loss=0.03082, over 1423951.11 frames.], batch size: 24, lr: 2.36e-04
+2022-04-30 14:08:33,682 INFO [train.py:763] (0/8) Epoch 32, batch 2000, loss[loss=0.1611, simple_loss=0.2687, pruned_loss=0.02677, over 6460.00 frames.], tot_loss[loss=0.1621, simple_loss=0.262, pruned_loss=0.03112, over 1425405.70 frames.], batch size: 38, lr: 2.36e-04
+2022-04-30 14:09:39,832 INFO [train.py:763] (0/8) Epoch 32, batch 2050, loss[loss=0.1741, simple_loss=0.2643, pruned_loss=0.04192, over 7159.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.03084, over 1425809.57 frames.], batch size: 18, lr: 2.36e-04
+2022-04-30 14:10:45,574 INFO [train.py:763] (0/8) Epoch 32, batch 2100, loss[loss=0.1606, simple_loss=0.2563, pruned_loss=0.03248, over 7158.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03074, over 1426507.40 frames.], batch size: 19, lr: 2.36e-04
+2022-04-30 14:11:52,597 INFO [train.py:763] (0/8) Epoch 32, batch 2150, loss[loss=0.1307, simple_loss=0.231, pruned_loss=0.01518, over 7422.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.03066, over 1427548.67 frames.], batch size: 18, lr: 2.36e-04
+2022-04-30 14:12:58,737 INFO [train.py:763] (0/8) Epoch 32, batch 2200, loss[loss=0.2329, simple_loss=0.3139, pruned_loss=0.07595, over 4828.00 frames.], tot_loss[loss=0.161, simple_loss=0.2604, pruned_loss=0.03085, over 1421143.81 frames.], batch size: 52, lr: 2.36e-04
+2022-04-30 14:14:05,743 INFO [train.py:763] (0/8) Epoch 32, batch 2250, loss[loss=0.1688, simple_loss=0.2778, pruned_loss=0.02991, over 7184.00 frames.], tot_loss[loss=0.1615, simple_loss=0.261, pruned_loss=0.03102, over 1419883.62 frames.], batch size: 26, lr: 2.36e-04
+2022-04-30 14:15:12,728 INFO [train.py:763] (0/8) Epoch 32, batch 2300, loss[loss=0.1746, simple_loss=0.2802, pruned_loss=0.03453, over 7210.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2605, pruned_loss=0.03095, over 1418613.60 frames.], batch size: 22, lr: 2.36e-04
+2022-04-30 14:16:18,593 INFO [train.py:763] (0/8) Epoch 32, batch 2350, loss[loss=0.1349, simple_loss=0.2247, pruned_loss=0.02258, over 7152.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2593, pruned_loss=0.03042, over 1422149.34 frames.], batch size: 16, lr: 2.36e-04
+2022-04-30 14:17:26,040 INFO [train.py:763] (0/8) Epoch 32, batch 2400, loss[loss=0.1579, simple_loss=0.2605, pruned_loss=0.02767, over 7428.00 frames.], tot_loss[loss=0.16, simple_loss=0.259, pruned_loss=0.03043, over 1424729.06 frames.], batch size: 20, lr: 2.36e-04
+2022-04-30 14:18:32,881 INFO [train.py:763] (0/8) Epoch 32, batch 2450, loss[loss=0.147, simple_loss=0.2427, pruned_loss=0.0256, over 7260.00 frames.], tot_loss[loss=0.16, simple_loss=0.2594, pruned_loss=0.03035, over 1426233.00 frames.], batch size: 19, lr: 2.36e-04
+2022-04-30 14:19:38,458 INFO [train.py:763] (0/8) Epoch 32, batch 2500, loss[loss=0.1793, simple_loss=0.286, pruned_loss=0.03631, over 7315.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2593, pruned_loss=0.03053, over 1427980.40 frames.], batch size: 21, lr: 2.36e-04
+2022-04-30 14:20:45,111 INFO [train.py:763] (0/8) Epoch 32, batch 2550, loss[loss=0.1863, simple_loss=0.2906, pruned_loss=0.04102, over 7386.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2592, pruned_loss=0.03048, over 1427869.79 frames.], batch size: 23, lr: 2.36e-04
+2022-04-30 14:21:59,930 INFO [train.py:763] (0/8) Epoch 32, batch 2600, loss[loss=0.1538, simple_loss=0.2655, pruned_loss=0.02106, over 7168.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2591, pruned_loss=0.0306, over 1427656.18 frames.], batch size: 23, lr: 2.36e-04
+2022-04-30 14:23:23,014 INFO [train.py:763] (0/8) Epoch 32, batch 2650, loss[loss=0.182, simple_loss=0.2696, pruned_loss=0.04714, over 7173.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2597, pruned_loss=0.03066, over 1423194.94 frames.], batch size: 16, lr: 2.35e-04
+2022-04-30 14:24:36,945 INFO [train.py:763] (0/8) Epoch 32, batch 2700, loss[loss=0.1573, simple_loss=0.2624, pruned_loss=0.02613, over 7438.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2599, pruned_loss=0.03044, over 1424484.75 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:25:51,361 INFO [train.py:763] (0/8) Epoch 32, batch 2750, loss[loss=0.1627, simple_loss=0.2598, pruned_loss=0.03281, over 7294.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03073, over 1425574.89 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:26:57,708 INFO [train.py:763] (0/8) Epoch 32, batch 2800, loss[loss=0.1764, simple_loss=0.2712, pruned_loss=0.04074, over 7214.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2611, pruned_loss=0.03065, over 1425334.87 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:28:12,051 INFO [train.py:763] (0/8) Epoch 32, batch 2850, loss[loss=0.1603, simple_loss=0.2635, pruned_loss=0.02853, over 7309.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03048, over 1426505.20 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:29:27,086 INFO [train.py:763] (0/8) Epoch 32, batch 2900, loss[loss=0.1741, simple_loss=0.2875, pruned_loss=0.03036, over 7306.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2617, pruned_loss=0.0307, over 1426006.17 frames.], batch size: 25, lr: 2.35e-04
+2022-04-30 14:30:33,977 INFO [train.py:763] (0/8) Epoch 32, batch 2950, loss[loss=0.1509, simple_loss=0.2617, pruned_loss=0.02008, over 7427.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2623, pruned_loss=0.03073, over 1428008.87 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:31:40,161 INFO [train.py:763] (0/8) Epoch 32, batch 3000, loss[loss=0.1501, simple_loss=0.2413, pruned_loss=0.02944, over 7081.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2616, pruned_loss=0.0306, over 1426876.95 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:31:40,163 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 14:31:55,319 INFO [train.py:792] (0/8) Epoch 32, validation: loss=0.1696, simple_loss=0.2645, pruned_loss=0.0374, over 698248.00 frames.
+2022-04-30 14:33:01,768 INFO [train.py:763] (0/8) Epoch 32, batch 3050, loss[loss=0.1618, simple_loss=0.2586, pruned_loss=0.03244, over 6418.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03042, over 1423251.64 frames.], batch size: 38, lr: 2.35e-04
+2022-04-30 14:34:07,509 INFO [train.py:763] (0/8) Epoch 32, batch 3100, loss[loss=0.1816, simple_loss=0.2897, pruned_loss=0.03673, over 7366.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03016, over 1423313.03 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:35:13,894 INFO [train.py:763] (0/8) Epoch 32, batch 3150, loss[loss=0.1441, simple_loss=0.2409, pruned_loss=0.02367, over 7075.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2598, pruned_loss=0.03017, over 1420689.33 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:36:20,359 INFO [train.py:763] (0/8) Epoch 32, batch 3200, loss[loss=0.1472, simple_loss=0.2275, pruned_loss=0.03344, over 6781.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2601, pruned_loss=0.03048, over 1421081.67 frames.], batch size: 15, lr: 2.35e-04
+2022-04-30 14:37:25,789 INFO [train.py:763] (0/8) Epoch 32, batch 3250, loss[loss=0.1243, simple_loss=0.2262, pruned_loss=0.01123, over 7282.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2604, pruned_loss=0.03102, over 1419097.32 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:38:31,360 INFO [train.py:763] (0/8) Epoch 32, batch 3300, loss[loss=0.1493, simple_loss=0.2528, pruned_loss=0.0229, over 7230.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03024, over 1424168.65 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:39:37,093 INFO [train.py:763] (0/8) Epoch 32, batch 3350, loss[loss=0.1859, simple_loss=0.2808, pruned_loss=0.04546, over 7319.00 frames.], tot_loss[loss=0.16, simple_loss=0.26, pruned_loss=0.03005, over 1427513.25 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:40:43,454 INFO [train.py:763] (0/8) Epoch 32, batch 3400, loss[loss=0.1563, simple_loss=0.2541, pruned_loss=0.0292, over 7288.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03006, over 1428195.95 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:41:50,120 INFO [train.py:763] (0/8) Epoch 32, batch 3450, loss[loss=0.1601, simple_loss=0.2617, pruned_loss=0.02923, over 7343.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03022, over 1432598.40 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:42:56,327 INFO [train.py:763] (0/8) Epoch 32, batch 3500, loss[loss=0.1751, simple_loss=0.2766, pruned_loss=0.03679, over 7371.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03059, over 1429727.81 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:44:01,650 INFO [train.py:763] (0/8) Epoch 32, batch 3550, loss[loss=0.1771, simple_loss=0.2679, pruned_loss=0.04318, over 7404.00 frames.], tot_loss[loss=0.162, simple_loss=0.2617, pruned_loss=0.0312, over 1427824.78 frames.], batch size: 18, lr: 2.35e-04
+2022-04-30 14:45:06,997 INFO [train.py:763] (0/8) Epoch 32, batch 3600, loss[loss=0.1282, simple_loss=0.2284, pruned_loss=0.01398, over 7334.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03093, over 1423924.35 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:46:12,718 INFO [train.py:763] (0/8) Epoch 32, batch 3650, loss[loss=0.1697, simple_loss=0.2733, pruned_loss=0.03308, over 7324.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03062, over 1423625.64 frames.], batch size: 20, lr: 2.35e-04
+2022-04-30 14:47:18,445 INFO [train.py:763] (0/8) Epoch 32, batch 3700, loss[loss=0.1382, simple_loss=0.2303, pruned_loss=0.02308, over 7277.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2621, pruned_loss=0.03115, over 1427099.30 frames.], batch size: 17, lr: 2.35e-04
+2022-04-30 14:48:25,081 INFO [train.py:763] (0/8) Epoch 32, batch 3750, loss[loss=0.1582, simple_loss=0.2624, pruned_loss=0.02697, over 7225.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03069, over 1427074.36 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:49:30,594 INFO [train.py:763] (0/8) Epoch 32, batch 3800, loss[loss=0.183, simple_loss=0.2901, pruned_loss=0.03795, over 7212.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03076, over 1428189.10 frames.], batch size: 23, lr: 2.35e-04
+2022-04-30 14:50:35,847 INFO [train.py:763] (0/8) Epoch 32, batch 3850, loss[loss=0.159, simple_loss=0.2604, pruned_loss=0.02878, over 7313.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.03058, over 1428267.52 frames.], batch size: 21, lr: 2.35e-04
+2022-04-30 14:51:41,201 INFO [train.py:763] (0/8) Epoch 32, batch 3900, loss[loss=0.1666, simple_loss=0.2575, pruned_loss=0.03786, over 7210.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2627, pruned_loss=0.03126, over 1428624.57 frames.], batch size: 16, lr: 2.35e-04
+2022-04-30 14:52:46,614 INFO [train.py:763] (0/8) Epoch 32, batch 3950, loss[loss=0.1299, simple_loss=0.2199, pruned_loss=0.01997, over 7407.00 frames.], tot_loss[loss=0.163, simple_loss=0.2633, pruned_loss=0.0314, over 1431214.19 frames.], batch size: 18, lr: 2.34e-04
+2022-04-30 14:53:52,269 INFO [train.py:763] (0/8) Epoch 32, batch 4000, loss[loss=0.1835, simple_loss=0.2882, pruned_loss=0.03938, over 6367.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2618, pruned_loss=0.03074, over 1431475.34 frames.], batch size: 37, lr: 2.34e-04
+2022-04-30 14:54:57,663 INFO [train.py:763] (0/8) Epoch 32, batch 4050, loss[loss=0.1493, simple_loss=0.235, pruned_loss=0.03177, over 7292.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03081, over 1428730.72 frames.], batch size: 18, lr: 2.34e-04
+2022-04-30 14:56:02,800 INFO [train.py:763] (0/8) Epoch 32, batch 4100, loss[loss=0.1921, simple_loss=0.2935, pruned_loss=0.04531, over 7174.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2612, pruned_loss=0.03087, over 1422591.19 frames.], batch size: 26, lr: 2.34e-04
+2022-04-30 14:57:08,512 INFO [train.py:763] (0/8) Epoch 32, batch 4150, loss[loss=0.1289, simple_loss=0.2181, pruned_loss=0.01987, over 6840.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2616, pruned_loss=0.0306, over 1421911.88 frames.], batch size: 15, lr: 2.34e-04
+2022-04-30 14:58:14,272 INFO [train.py:763] (0/8) Epoch 32, batch 4200, loss[loss=0.1536, simple_loss=0.2454, pruned_loss=0.03086, over 7256.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.03, over 1419377.67 frames.], batch size: 19, lr: 2.34e-04
+2022-04-30 14:59:19,684 INFO [train.py:763] (0/8) Epoch 32, batch 4250, loss[loss=0.16, simple_loss=0.2736, pruned_loss=0.02316, over 7424.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02936, over 1420274.19 frames.], batch size: 20, lr: 2.34e-04
+2022-04-30 15:00:26,355 INFO [train.py:763] (0/8) Epoch 32, batch 4300, loss[loss=0.1593, simple_loss=0.257, pruned_loss=0.03083, over 6693.00 frames.], tot_loss[loss=0.1595, simple_loss=0.26, pruned_loss=0.02947, over 1419051.56 frames.], batch size: 31, lr: 2.34e-04
+2022-04-30 15:01:32,997 INFO [train.py:763] (0/8) Epoch 32, batch 4350, loss[loss=0.1539, simple_loss=0.2587, pruned_loss=0.02453, over 7223.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.02964, over 1414716.67 frames.], batch size: 21, lr: 2.34e-04
+2022-04-30 15:02:38,281 INFO [train.py:763] (0/8) Epoch 32, batch 4400, loss[loss=0.164, simple_loss=0.269, pruned_loss=0.02954, over 7143.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2588, pruned_loss=0.02937, over 1414170.37 frames.], batch size: 20, lr: 2.34e-04
+2022-04-30 15:03:43,371 INFO [train.py:763] (0/8) Epoch 32, batch 4450, loss[loss=0.1662, simple_loss=0.2737, pruned_loss=0.02931, over 7349.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02958, over 1405947.18 frames.], batch size: 22, lr: 2.34e-04
+2022-04-30 15:04:48,250 INFO [train.py:763] (0/8) Epoch 32, batch 4500, loss[loss=0.1701, simple_loss=0.2779, pruned_loss=0.03115, over 7146.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2612, pruned_loss=0.02997, over 1396286.27 frames.], batch size: 20, lr: 2.34e-04
+2022-04-30 15:05:53,076 INFO [train.py:763] (0/8) Epoch 32, batch 4550, loss[loss=0.1766, simple_loss=0.2787, pruned_loss=0.0372, over 5086.00 frames.], tot_loss[loss=0.162, simple_loss=0.2626, pruned_loss=0.03072, over 1375574.37 frames.], batch size: 52, lr: 2.34e-04
+2022-04-30 15:06:42,385 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-32.pt
+2022-04-30 15:07:21,090 INFO [train.py:763] (0/8) Epoch 33, batch 0, loss[loss=0.1689, simple_loss=0.2736, pruned_loss=0.03207, over 7430.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2736, pruned_loss=0.03207, over 7430.00 frames.], batch size: 20, lr: 2.31e-04
+2022-04-30 15:08:26,676 INFO [train.py:763] (0/8) Epoch 33, batch 50, loss[loss=0.1933, simple_loss=0.3026, pruned_loss=0.04198, over 7119.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2575, pruned_loss=0.02989, over 324863.72 frames.], batch size: 28, lr: 2.30e-04
+2022-04-30 15:09:31,886 INFO [train.py:763] (0/8) Epoch 33, batch 100, loss[loss=0.1731, simple_loss=0.2761, pruned_loss=0.03502, over 7120.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2602, pruned_loss=0.0305, over 566011.08 frames.], batch size: 21, lr: 2.30e-04
+2022-04-30 15:10:37,384 INFO [train.py:763] (0/8) Epoch 33, batch 150, loss[loss=0.1644, simple_loss=0.2599, pruned_loss=0.03449, over 7068.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2588, pruned_loss=0.02991, over 755934.43 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:11:42,901 INFO [train.py:763] (0/8) Epoch 33, batch 200, loss[loss=0.1325, simple_loss=0.2195, pruned_loss=0.02275, over 7286.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2585, pruned_loss=0.02964, over 905040.26 frames.], batch size: 17, lr: 2.30e-04
+2022-04-30 15:12:48,617 INFO [train.py:763] (0/8) Epoch 33, batch 250, loss[loss=0.1969, simple_loss=0.2852, pruned_loss=0.0543, over 4488.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2581, pruned_loss=0.02971, over 1011083.62 frames.], batch size: 53, lr: 2.30e-04
+2022-04-30 15:13:55,861 INFO [train.py:763] (0/8) Epoch 33, batch 300, loss[loss=0.1724, simple_loss=0.2801, pruned_loss=0.03236, over 7389.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2583, pruned_loss=0.02941, over 1101713.54 frames.], batch size: 23, lr: 2.30e-04
+2022-04-30 15:15:01,951 INFO [train.py:763] (0/8) Epoch 33, batch 350, loss[loss=0.1412, simple_loss=0.2445, pruned_loss=0.01892, over 7140.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2601, pruned_loss=0.02991, over 1166801.05 frames.], batch size: 17, lr: 2.30e-04
+2022-04-30 15:16:08,897 INFO [train.py:763] (0/8) Epoch 33, batch 400, loss[loss=0.1639, simple_loss=0.2621, pruned_loss=0.03287, over 7419.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2587, pruned_loss=0.02984, over 1227692.58 frames.], batch size: 21, lr: 2.30e-04
+2022-04-30 15:17:14,702 INFO [train.py:763] (0/8) Epoch 33, batch 450, loss[loss=0.1398, simple_loss=0.2345, pruned_loss=0.02252, over 7405.00 frames.], tot_loss[loss=0.1602, simple_loss=0.26, pruned_loss=0.03015, over 1272509.05 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:18:21,055 INFO [train.py:763] (0/8) Epoch 33, batch 500, loss[loss=0.1686, simple_loss=0.2588, pruned_loss=0.03916, over 7261.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03061, over 1305057.53 frames.], batch size: 24, lr: 2.30e-04
+2022-04-30 15:19:26,292 INFO [train.py:763] (0/8) Epoch 33, batch 550, loss[loss=0.1801, simple_loss=0.2819, pruned_loss=0.03912, over 6384.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.0307, over 1329705.66 frames.], batch size: 37, lr: 2.30e-04
+2022-04-30 15:20:25,014 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-152000.pt
+2022-04-30 15:20:43,089 INFO [train.py:763] (0/8) Epoch 33, batch 600, loss[loss=0.2021, simple_loss=0.2926, pruned_loss=0.05582, over 7308.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2615, pruned_loss=0.03082, over 1351754.58 frames.], batch size: 25, lr: 2.30e-04
+2022-04-30 15:21:48,334 INFO [train.py:763] (0/8) Epoch 33, batch 650, loss[loss=0.1381, simple_loss=0.2306, pruned_loss=0.02283, over 7156.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2616, pruned_loss=0.03068, over 1370302.49 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:22:53,616 INFO [train.py:763] (0/8) Epoch 33, batch 700, loss[loss=0.137, simple_loss=0.2264, pruned_loss=0.02384, over 7120.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2606, pruned_loss=0.03053, over 1377628.00 frames.], batch size: 17, lr: 2.30e-04
+2022-04-30 15:23:58,788 INFO [train.py:763] (0/8) Epoch 33, batch 750, loss[loss=0.1787, simple_loss=0.2823, pruned_loss=0.03759, over 7199.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03059, over 1389588.36 frames.], batch size: 23, lr: 2.30e-04
+2022-04-30 15:25:05,625 INFO [train.py:763] (0/8) Epoch 33, batch 800, loss[loss=0.162, simple_loss=0.2641, pruned_loss=0.02998, over 7270.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2616, pruned_loss=0.03098, over 1394816.26 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:26:11,929 INFO [train.py:763] (0/8) Epoch 33, batch 850, loss[loss=0.137, simple_loss=0.244, pruned_loss=0.01506, over 6417.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2612, pruned_loss=0.03078, over 1404911.42 frames.], batch size: 37, lr: 2.30e-04
+2022-04-30 15:27:17,424 INFO [train.py:763] (0/8) Epoch 33, batch 900, loss[loss=0.1637, simple_loss=0.2603, pruned_loss=0.03352, over 4862.00 frames.], tot_loss[loss=0.1601, simple_loss=0.26, pruned_loss=0.0301, over 1409492.60 frames.], batch size: 52, lr: 2.30e-04
+2022-04-30 15:28:22,827 INFO [train.py:763] (0/8) Epoch 33, batch 950, loss[loss=0.1862, simple_loss=0.28, pruned_loss=0.04619, over 7281.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2605, pruned_loss=0.03031, over 1407757.64 frames.], batch size: 18, lr: 2.30e-04
+2022-04-30 15:29:28,257 INFO [train.py:763] (0/8) Epoch 33, batch 1000, loss[loss=0.1452, simple_loss=0.2471, pruned_loss=0.0217, over 7428.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2599, pruned_loss=0.03013, over 1408839.31 frames.], batch size: 20, lr: 2.30e-04
+2022-04-30 15:30:33,674 INFO [train.py:763] (0/8) Epoch 33, batch 1050, loss[loss=0.1417, simple_loss=0.2501, pruned_loss=0.01662, over 7157.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2601, pruned_loss=0.02988, over 1415192.81 frames.], batch size: 19, lr: 2.30e-04
+2022-04-30 15:31:40,477 INFO [train.py:763] (0/8) Epoch 33, batch 1100, loss[loss=0.1621, simple_loss=0.2681, pruned_loss=0.02802, over 6545.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2608, pruned_loss=0.02998, over 1413632.39 frames.], batch size: 38, lr: 2.30e-04
+2022-04-30 15:32:45,931 INFO [train.py:763] (0/8) Epoch 33, batch 1150, loss[loss=0.1507, simple_loss=0.242, pruned_loss=0.02963, over 7423.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2596, pruned_loss=0.02981, over 1415787.15 frames.], batch size: 20, lr: 2.30e-04
+2022-04-30 15:33:51,346 INFO [train.py:763] (0/8) Epoch 33, batch 1200, loss[loss=0.1837, simple_loss=0.2883, pruned_loss=0.03954, over 7198.00 frames.], tot_loss[loss=0.16, simple_loss=0.2598, pruned_loss=0.03009, over 1420152.65 frames.], batch size: 23, lr: 2.30e-04
+2022-04-30 15:34:56,637 INFO [train.py:763] (0/8) Epoch 33, batch 1250, loss[loss=0.1584, simple_loss=0.2633, pruned_loss=0.02669, over 7330.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2603, pruned_loss=0.03022, over 1417438.48 frames.], batch size: 22, lr: 2.30e-04
+2022-04-30 15:36:02,620 INFO [train.py:763] (0/8) Epoch 33, batch 1300, loss[loss=0.1658, simple_loss=0.2721, pruned_loss=0.02977, over 7128.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03022, over 1417694.05 frames.], batch size: 26, lr: 2.30e-04
+2022-04-30 15:37:09,767 INFO [train.py:763] (0/8) Epoch 33, batch 1350, loss[loss=0.1666, simple_loss=0.2719, pruned_loss=0.0307, over 7216.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03023, over 1418564.07 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:38:16,830 INFO [train.py:763] (0/8) Epoch 33, batch 1400, loss[loss=0.1802, simple_loss=0.2704, pruned_loss=0.04504, over 7259.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2597, pruned_loss=0.0304, over 1421419.79 frames.], batch size: 19, lr: 2.29e-04
+2022-04-30 15:39:22,846 INFO [train.py:763] (0/8) Epoch 33, batch 1450, loss[loss=0.1585, simple_loss=0.2628, pruned_loss=0.02705, over 7415.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2598, pruned_loss=0.03035, over 1424855.65 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:40:28,342 INFO [train.py:763] (0/8) Epoch 33, batch 1500, loss[loss=0.1673, simple_loss=0.2689, pruned_loss=0.03281, over 7370.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.0302, over 1423298.84 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 15:41:33,829 INFO [train.py:763] (0/8) Epoch 33, batch 1550, loss[loss=0.1734, simple_loss=0.2776, pruned_loss=0.03458, over 7271.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03058, over 1421483.46 frames.], batch size: 24, lr: 2.29e-04
+2022-04-30 15:42:39,071 INFO [train.py:763] (0/8) Epoch 33, batch 1600, loss[loss=0.1729, simple_loss=0.2753, pruned_loss=0.03523, over 7331.00 frames.], tot_loss[loss=0.161, simple_loss=0.2611, pruned_loss=0.03044, over 1422561.62 frames.], batch size: 20, lr: 2.29e-04
+2022-04-30 15:43:46,173 INFO [train.py:763] (0/8) Epoch 33, batch 1650, loss[loss=0.1854, simple_loss=0.2905, pruned_loss=0.0401, over 7184.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2625, pruned_loss=0.03095, over 1422103.16 frames.], batch size: 22, lr: 2.29e-04
+2022-04-30 15:44:53,522 INFO [train.py:763] (0/8) Epoch 33, batch 1700, loss[loss=0.1739, simple_loss=0.2752, pruned_loss=0.03634, over 7376.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2627, pruned_loss=0.03106, over 1426087.64 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 15:46:00,135 INFO [train.py:763] (0/8) Epoch 33, batch 1750, loss[loss=0.1459, simple_loss=0.2504, pruned_loss=0.02071, over 7113.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2629, pruned_loss=0.03084, over 1420870.81 frames.], batch size: 28, lr: 2.29e-04
+2022-04-30 15:47:05,297 INFO [train.py:763] (0/8) Epoch 33, batch 1800, loss[loss=0.1378, simple_loss=0.2278, pruned_loss=0.02388, over 7263.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2624, pruned_loss=0.03066, over 1422241.59 frames.], batch size: 17, lr: 2.29e-04
+2022-04-30 15:48:11,901 INFO [train.py:763] (0/8) Epoch 33, batch 1850, loss[loss=0.189, simple_loss=0.2801, pruned_loss=0.04898, over 7320.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2614, pruned_loss=0.03043, over 1414781.82 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:49:17,345 INFO [train.py:763] (0/8) Epoch 33, batch 1900, loss[loss=0.1639, simple_loss=0.268, pruned_loss=0.02987, over 6797.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2615, pruned_loss=0.03046, over 1410305.46 frames.], batch size: 31, lr: 2.29e-04
+2022-04-30 15:50:23,870 INFO [train.py:763] (0/8) Epoch 33, batch 1950, loss[loss=0.1619, simple_loss=0.2392, pruned_loss=0.04235, over 7010.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2613, pruned_loss=0.03055, over 1416305.05 frames.], batch size: 16, lr: 2.29e-04
+2022-04-30 15:51:31,117 INFO [train.py:763] (0/8) Epoch 33, batch 2000, loss[loss=0.1308, simple_loss=0.2271, pruned_loss=0.01723, over 7395.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03014, over 1421631.52 frames.], batch size: 18, lr: 2.29e-04
+2022-04-30 15:52:37,446 INFO [train.py:763] (0/8) Epoch 33, batch 2050, loss[loss=0.1636, simple_loss=0.2607, pruned_loss=0.03323, over 7126.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2598, pruned_loss=0.02972, over 1421796.37 frames.], batch size: 26, lr: 2.29e-04
+2022-04-30 15:53:42,713 INFO [train.py:763] (0/8) Epoch 33, batch 2100, loss[loss=0.1716, simple_loss=0.2666, pruned_loss=0.03833, over 7210.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2602, pruned_loss=0.02976, over 1424850.76 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 15:54:47,945 INFO [train.py:763] (0/8) Epoch 33, batch 2150, loss[loss=0.1616, simple_loss=0.2637, pruned_loss=0.02969, over 7295.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.02984, over 1424312.37 frames.], batch size: 24, lr: 2.29e-04
+2022-04-30 15:55:53,183 INFO [train.py:763] (0/8) Epoch 33, batch 2200, loss[loss=0.1774, simple_loss=0.284, pruned_loss=0.03537, over 7319.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2623, pruned_loss=0.03051, over 1427373.73 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 15:56:58,877 INFO [train.py:763] (0/8) Epoch 33, batch 2250, loss[loss=0.1362, simple_loss=0.2359, pruned_loss=0.01823, over 7257.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2616, pruned_loss=0.0306, over 1423587.52 frames.], batch size: 18, lr: 2.29e-04
+2022-04-30 15:58:05,275 INFO [train.py:763] (0/8) Epoch 33, batch 2300, loss[loss=0.1465, simple_loss=0.2437, pruned_loss=0.02466, over 7156.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2622, pruned_loss=0.03069, over 1424143.08 frames.], batch size: 19, lr: 2.29e-04
+2022-04-30 15:59:10,711 INFO [train.py:763] (0/8) Epoch 33, batch 2350, loss[loss=0.1429, simple_loss=0.2349, pruned_loss=0.0255, over 7170.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.03047, over 1425073.72 frames.], batch size: 19, lr: 2.29e-04
+2022-04-30 16:00:16,792 INFO [train.py:763] (0/8) Epoch 33, batch 2400, loss[loss=0.1699, simple_loss=0.2749, pruned_loss=0.03244, over 7386.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03023, over 1425199.75 frames.], batch size: 23, lr: 2.29e-04
+2022-04-30 16:01:22,895 INFO [train.py:763] (0/8) Epoch 33, batch 2450, loss[loss=0.1508, simple_loss=0.2592, pruned_loss=0.02117, over 7214.00 frames.], tot_loss[loss=0.161, simple_loss=0.2613, pruned_loss=0.03037, over 1419567.81 frames.], batch size: 21, lr: 2.29e-04
+2022-04-30 16:02:28,049 INFO [train.py:763] (0/8) Epoch 33, batch 2500, loss[loss=0.1474, simple_loss=0.2401, pruned_loss=0.02737, over 6997.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2618, pruned_loss=0.03055, over 1418731.02 frames.], batch size: 16, lr: 2.29e-04
+2022-04-30 16:03:33,226 INFO [train.py:763] (0/8) Epoch 33, batch 2550, loss[loss=0.1548, simple_loss=0.2702, pruned_loss=0.01975, over 7344.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2615, pruned_loss=0.03038, over 1420437.20 frames.], batch size: 22, lr: 2.29e-04
+2022-04-30 16:04:38,855 INFO [train.py:763] (0/8) Epoch 33, batch 2600, loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02825, over 7070.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2612, pruned_loss=0.03067, over 1420387.37 frames.], batch size: 18, lr: 2.29e-04
+2022-04-30 16:05:45,692 INFO [train.py:763] (0/8) Epoch 33, batch 2650, loss[loss=0.1676, simple_loss=0.2742, pruned_loss=0.03046, over 7342.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2604, pruned_loss=0.03042, over 1420804.38 frames.], batch size: 22, lr: 2.29e-04
+2022-04-30 16:06:52,537 INFO [train.py:763] (0/8) Epoch 33, batch 2700, loss[loss=0.1485, simple_loss=0.243, pruned_loss=0.02699, over 7278.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03033, over 1425397.13 frames.], batch size: 18, lr: 2.28e-04
+2022-04-30 16:07:59,671 INFO [train.py:763] (0/8) Epoch 33, batch 2750, loss[loss=0.1711, simple_loss=0.2719, pruned_loss=0.03511, over 7320.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.03015, over 1423441.50 frames.], batch size: 21, lr: 2.28e-04
+2022-04-30 16:09:06,757 INFO [train.py:763] (0/8) Epoch 33, batch 2800, loss[loss=0.1351, simple_loss=0.2394, pruned_loss=0.01545, over 7420.00 frames.], tot_loss[loss=0.1606, simple_loss=0.261, pruned_loss=0.03013, over 1429106.30 frames.], batch size: 18, lr: 2.28e-04
+2022-04-30 16:10:13,299 INFO [train.py:763] (0/8) Epoch 33, batch 2850, loss[loss=0.1753, simple_loss=0.2773, pruned_loss=0.03659, over 7183.00 frames.], tot_loss[loss=0.16, simple_loss=0.2608, pruned_loss=0.02957, over 1430576.10 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:11:18,333 INFO [train.py:763] (0/8) Epoch 33, batch 2900, loss[loss=0.1539, simple_loss=0.2578, pruned_loss=0.02494, over 7146.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2604, pruned_loss=0.02963, over 1426845.59 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:12:24,378 INFO [train.py:763] (0/8) Epoch 33, batch 2950, loss[loss=0.1491, simple_loss=0.2599, pruned_loss=0.01916, over 7138.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2602, pruned_loss=0.02955, over 1427499.19 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:13:31,414 INFO [train.py:763] (0/8) Epoch 33, batch 3000, loss[loss=0.1562, simple_loss=0.2633, pruned_loss=0.0246, over 7358.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2603, pruned_loss=0.0294, over 1427682.82 frames.], batch size: 19, lr: 2.28e-04
+2022-04-30 16:13:31,415 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 16:13:46,765 INFO [train.py:792] (0/8) Epoch 33, validation: loss=0.1701, simple_loss=0.2653, pruned_loss=0.03746, over 698248.00 frames.
+2022-04-30 16:14:51,752 INFO [train.py:763] (0/8) Epoch 33, batch 3050, loss[loss=0.1553, simple_loss=0.239, pruned_loss=0.03577, over 7350.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2606, pruned_loss=0.0293, over 1427861.16 frames.], batch size: 19, lr: 2.28e-04
+2022-04-30 16:15:58,106 INFO [train.py:763] (0/8) Epoch 33, batch 3100, loss[loss=0.1543, simple_loss=0.2457, pruned_loss=0.03147, over 6766.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2615, pruned_loss=0.02977, over 1429127.43 frames.], batch size: 15, lr: 2.28e-04
+2022-04-30 16:17:04,955 INFO [train.py:763] (0/8) Epoch 33, batch 3150, loss[loss=0.1454, simple_loss=0.2385, pruned_loss=0.0261, over 7301.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2605, pruned_loss=0.02936, over 1429420.97 frames.], batch size: 17, lr: 2.28e-04
+2022-04-30 16:18:11,847 INFO [train.py:763] (0/8) Epoch 33, batch 3200, loss[loss=0.1566, simple_loss=0.2571, pruned_loss=0.02808, over 5162.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2605, pruned_loss=0.02955, over 1425294.57 frames.], batch size: 52, lr: 2.28e-04
+2022-04-30 16:19:17,476 INFO [train.py:763] (0/8) Epoch 33, batch 3250, loss[loss=0.15, simple_loss=0.2465, pruned_loss=0.02677, over 7124.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2605, pruned_loss=0.02959, over 1422832.18 frames.], batch size: 17, lr: 2.28e-04
+2022-04-30 16:20:22,902 INFO [train.py:763] (0/8) Epoch 33, batch 3300, loss[loss=0.1806, simple_loss=0.2901, pruned_loss=0.03554, over 7096.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.03035, over 1419474.02 frames.], batch size: 28, lr: 2.28e-04
+2022-04-30 16:21:28,694 INFO [train.py:763] (0/8) Epoch 33, batch 3350, loss[loss=0.151, simple_loss=0.2536, pruned_loss=0.02421, over 7147.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2605, pruned_loss=0.03037, over 1421786.13 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:22:44,385 INFO [train.py:763] (0/8) Epoch 33, batch 3400, loss[loss=0.1538, simple_loss=0.246, pruned_loss=0.0308, over 7204.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2609, pruned_loss=0.03025, over 1422135.05 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:23:50,293 INFO [train.py:763] (0/8) Epoch 33, batch 3450, loss[loss=0.1474, simple_loss=0.2451, pruned_loss=0.02479, over 6990.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.03045, over 1427566.66 frames.], batch size: 16, lr: 2.28e-04
+2022-04-30 16:24:55,496 INFO [train.py:763] (0/8) Epoch 33, batch 3500, loss[loss=0.1667, simple_loss=0.2796, pruned_loss=0.02686, over 7203.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2618, pruned_loss=0.03042, over 1429353.61 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:26:01,147 INFO [train.py:763] (0/8) Epoch 33, batch 3550, loss[loss=0.1272, simple_loss=0.2249, pruned_loss=0.01477, over 7300.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.03019, over 1431934.92 frames.], batch size: 17, lr: 2.28e-04
+2022-04-30 16:27:06,630 INFO [train.py:763] (0/8) Epoch 33, batch 3600, loss[loss=0.1456, simple_loss=0.2453, pruned_loss=0.02294, over 7320.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2596, pruned_loss=0.02985, over 1433327.51 frames.], batch size: 21, lr: 2.28e-04
+2022-04-30 16:28:13,484 INFO [train.py:763] (0/8) Epoch 33, batch 3650, loss[loss=0.1566, simple_loss=0.2641, pruned_loss=0.02461, over 6167.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2599, pruned_loss=0.0298, over 1428551.67 frames.], batch size: 37, lr: 2.28e-04
+2022-04-30 16:29:20,527 INFO [train.py:763] (0/8) Epoch 33, batch 3700, loss[loss=0.1628, simple_loss=0.2665, pruned_loss=0.0295, over 7242.00 frames.], tot_loss[loss=0.1593, simple_loss=0.259, pruned_loss=0.02985, over 1424345.79 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:30:26,042 INFO [train.py:763] (0/8) Epoch 33, batch 3750, loss[loss=0.167, simple_loss=0.2681, pruned_loss=0.03291, over 7269.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2587, pruned_loss=0.03006, over 1421192.71 frames.], batch size: 24, lr: 2.28e-04
+2022-04-30 16:31:31,703 INFO [train.py:763] (0/8) Epoch 33, batch 3800, loss[loss=0.1591, simple_loss=0.2753, pruned_loss=0.02141, over 7137.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.02971, over 1425519.45 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:32:38,584 INFO [train.py:763] (0/8) Epoch 33, batch 3850, loss[loss=0.1809, simple_loss=0.2766, pruned_loss=0.04262, over 7216.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2593, pruned_loss=0.03005, over 1427188.13 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:33:45,464 INFO [train.py:763] (0/8) Epoch 33, batch 3900, loss[loss=0.1751, simple_loss=0.2829, pruned_loss=0.03369, over 7205.00 frames.], tot_loss[loss=0.16, simple_loss=0.2596, pruned_loss=0.03018, over 1426302.37 frames.], batch size: 23, lr: 2.28e-04
+2022-04-30 16:34:52,424 INFO [train.py:763] (0/8) Epoch 33, batch 3950, loss[loss=0.1831, simple_loss=0.2738, pruned_loss=0.04618, over 7327.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2591, pruned_loss=0.02995, over 1424210.08 frames.], batch size: 20, lr: 2.28e-04
+2022-04-30 16:35:59,194 INFO [train.py:763] (0/8) Epoch 33, batch 4000, loss[loss=0.1545, simple_loss=0.2558, pruned_loss=0.02654, over 7066.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03024, over 1424041.09 frames.], batch size: 18, lr: 2.28e-04
+2022-04-30 16:37:13,146 INFO [train.py:763] (0/8) Epoch 33, batch 4050, loss[loss=0.1811, simple_loss=0.2872, pruned_loss=0.03752, over 7160.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2604, pruned_loss=0.03058, over 1419452.29 frames.], batch size: 26, lr: 2.27e-04
+2022-04-30 16:38:27,104 INFO [train.py:763] (0/8) Epoch 33, batch 4100, loss[loss=0.1855, simple_loss=0.283, pruned_loss=0.04394, over 6321.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03039, over 1419807.81 frames.], batch size: 38, lr: 2.27e-04
+2022-04-30 16:39:41,396 INFO [train.py:763] (0/8) Epoch 33, batch 4150, loss[loss=0.1444, simple_loss=0.2407, pruned_loss=0.02403, over 7414.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2604, pruned_loss=0.03024, over 1418911.17 frames.], batch size: 18, lr: 2.27e-04
+2022-04-30 16:40:55,333 INFO [train.py:763] (0/8) Epoch 33, batch 4200, loss[loss=0.1691, simple_loss=0.2736, pruned_loss=0.03232, over 7229.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.0304, over 1421477.78 frames.], batch size: 20, lr: 2.27e-04
+2022-04-30 16:42:02,091 INFO [train.py:763] (0/8) Epoch 33, batch 4250, loss[loss=0.1403, simple_loss=0.231, pruned_loss=0.02483, over 7133.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.0304, over 1420705.48 frames.], batch size: 17, lr: 2.27e-04
+2022-04-30 16:43:17,960 INFO [train.py:763] (0/8) Epoch 33, batch 4300, loss[loss=0.1394, simple_loss=0.2339, pruned_loss=0.02247, over 7002.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2608, pruned_loss=0.03016, over 1420559.74 frames.], batch size: 16, lr: 2.27e-04
+2022-04-30 16:44:24,674 INFO [train.py:763] (0/8) Epoch 33, batch 4350, loss[loss=0.1707, simple_loss=0.2608, pruned_loss=0.04032, over 7228.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.03065, over 1417094.39 frames.], batch size: 16, lr: 2.27e-04
+2022-04-30 16:45:48,497 INFO [train.py:763] (0/8) Epoch 33, batch 4400, loss[loss=0.1387, simple_loss=0.2346, pruned_loss=0.0214, over 7176.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.03065, over 1417267.81 frames.], batch size: 18, lr: 2.27e-04
+2022-04-30 16:46:53,557 INFO [train.py:763] (0/8) Epoch 33, batch 4450, loss[loss=0.1862, simple_loss=0.2836, pruned_loss=0.04436, over 7221.00 frames.], tot_loss[loss=0.1615, simple_loss=0.261, pruned_loss=0.03097, over 1402344.72 frames.], batch size: 23, lr: 2.27e-04
+2022-04-30 16:48:00,205 INFO [train.py:763] (0/8) Epoch 33, batch 4500, loss[loss=0.1822, simple_loss=0.2849, pruned_loss=0.03976, over 5336.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2614, pruned_loss=0.03122, over 1392057.73 frames.], batch size: 52, lr: 2.27e-04
+2022-04-30 16:49:05,832 INFO [train.py:763] (0/8) Epoch 33, batch 4550, loss[loss=0.196, simple_loss=0.289, pruned_loss=0.05152, over 5130.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2634, pruned_loss=0.03196, over 1351652.72 frames.], batch size: 52, lr: 2.27e-04
+2022-04-30 16:49:55,107 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-33.pt
+2022-04-30 16:50:25,381 INFO [train.py:763] (0/8) Epoch 34, batch 0, loss[loss=0.1663, simple_loss=0.2695, pruned_loss=0.03148, over 7231.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2695, pruned_loss=0.03148, over 7231.00 frames.], batch size: 20, lr: 2.24e-04
+2022-04-30 16:51:31,607 INFO [train.py:763] (0/8) Epoch 34, batch 50, loss[loss=0.1592, simple_loss=0.2716, pruned_loss=0.02342, over 7290.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2632, pruned_loss=0.03057, over 317887.21 frames.], batch size: 24, lr: 2.24e-04
+2022-04-30 16:52:37,607 INFO [train.py:763] (0/8) Epoch 34, batch 100, loss[loss=0.1794, simple_loss=0.275, pruned_loss=0.04185, over 7166.00 frames.], tot_loss[loss=0.1593, simple_loss=0.26, pruned_loss=0.02934, over 567971.10 frames.], batch size: 26, lr: 2.24e-04
+2022-04-30 16:53:43,314 INFO [train.py:763] (0/8) Epoch 34, batch 150, loss[loss=0.1718, simple_loss=0.2683, pruned_loss=0.03763, over 7377.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2604, pruned_loss=0.02939, over 761208.65 frames.], batch size: 23, lr: 2.24e-04
+2022-04-30 16:54:49,445 INFO [train.py:763] (0/8) Epoch 34, batch 200, loss[loss=0.1503, simple_loss=0.2475, pruned_loss=0.0266, over 7067.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2604, pruned_loss=0.02992, over 910156.31 frames.], batch size: 18, lr: 2.24e-04
+2022-04-30 16:55:56,601 INFO [train.py:763] (0/8) Epoch 34, batch 250, loss[loss=0.1528, simple_loss=0.2592, pruned_loss=0.0232, over 7229.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.02977, over 1027584.31 frames.], batch size: 20, lr: 2.24e-04
+2022-04-30 16:57:03,058 INFO [train.py:763] (0/8) Epoch 34, batch 300, loss[loss=0.1486, simple_loss=0.2522, pruned_loss=0.02243, over 7158.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02949, over 1113837.17 frames.], batch size: 19, lr: 2.24e-04
+2022-04-30 16:58:08,941 INFO [train.py:763] (0/8) Epoch 34, batch 350, loss[loss=0.1699, simple_loss=0.2659, pruned_loss=0.03693, over 7193.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2591, pruned_loss=0.02926, over 1185976.24 frames.], batch size: 23, lr: 2.24e-04
+2022-04-30 16:59:14,462 INFO [train.py:763] (0/8) Epoch 34, batch 400, loss[loss=0.1528, simple_loss=0.2532, pruned_loss=0.02623, over 7328.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2596, pruned_loss=0.02945, over 1240289.54 frames.], batch size: 20, lr: 2.24e-04
+2022-04-30 17:00:20,021 INFO [train.py:763] (0/8) Epoch 34, batch 450, loss[loss=0.1525, simple_loss=0.2528, pruned_loss=0.02612, over 6876.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2591, pruned_loss=0.02913, over 1285425.42 frames.], batch size: 31, lr: 2.24e-04
+2022-04-30 17:01:27,004 INFO [train.py:763] (0/8) Epoch 34, batch 500, loss[loss=0.1465, simple_loss=0.2485, pruned_loss=0.02222, over 7326.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2587, pruned_loss=0.02916, over 1314898.43 frames.], batch size: 20, lr: 2.23e-04
+2022-04-30 17:02:32,707 INFO [train.py:763] (0/8) Epoch 34, batch 550, loss[loss=0.1538, simple_loss=0.2532, pruned_loss=0.02716, over 7060.00 frames.], tot_loss[loss=0.158, simple_loss=0.2579, pruned_loss=0.02906, over 1335430.66 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:03:38,804 INFO [train.py:763] (0/8) Epoch 34, batch 600, loss[loss=0.1578, simple_loss=0.2682, pruned_loss=0.0237, over 7342.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2585, pruned_loss=0.02938, over 1354320.06 frames.], batch size: 22, lr: 2.23e-04
+2022-04-30 17:04:44,667 INFO [train.py:763] (0/8) Epoch 34, batch 650, loss[loss=0.1255, simple_loss=0.2191, pruned_loss=0.01598, over 7169.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2589, pruned_loss=0.02941, over 1372822.96 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:05:50,790 INFO [train.py:763] (0/8) Epoch 34, batch 700, loss[loss=0.1538, simple_loss=0.2405, pruned_loss=0.03353, over 7267.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2587, pruned_loss=0.02958, over 1386668.49 frames.], batch size: 17, lr: 2.23e-04
+2022-04-30 17:06:58,065 INFO [train.py:763] (0/8) Epoch 34, batch 750, loss[loss=0.1324, simple_loss=0.2335, pruned_loss=0.01563, over 7263.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2573, pruned_loss=0.02919, over 1394113.18 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:08:04,373 INFO [train.py:763] (0/8) Epoch 34, batch 800, loss[loss=0.1738, simple_loss=0.2853, pruned_loss=0.03114, over 7222.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2582, pruned_loss=0.02949, over 1403122.15 frames.], batch size: 21, lr: 2.23e-04
+2022-04-30 17:09:09,698 INFO [train.py:763] (0/8) Epoch 34, batch 850, loss[loss=0.2085, simple_loss=0.3142, pruned_loss=0.0514, over 7290.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2591, pruned_loss=0.02986, over 1402520.57 frames.], batch size: 24, lr: 2.23e-04
+2022-04-30 17:10:15,226 INFO [train.py:763] (0/8) Epoch 34, batch 900, loss[loss=0.1819, simple_loss=0.2724, pruned_loss=0.04565, over 5349.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2593, pruned_loss=0.02984, over 1405899.94 frames.], batch size: 52, lr: 2.23e-04
+2022-04-30 17:11:21,169 INFO [train.py:763] (0/8) Epoch 34, batch 950, loss[loss=0.1583, simple_loss=0.2574, pruned_loss=0.02956, over 7248.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2589, pruned_loss=0.0297, over 1409685.15 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:12:27,415 INFO [train.py:763] (0/8) Epoch 34, batch 1000, loss[loss=0.174, simple_loss=0.278, pruned_loss=0.03502, over 6783.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2589, pruned_loss=0.02989, over 1411710.34 frames.], batch size: 31, lr: 2.23e-04
+2022-04-30 17:13:34,604 INFO [train.py:763] (0/8) Epoch 34, batch 1050, loss[loss=0.1582, simple_loss=0.2628, pruned_loss=0.02682, over 7409.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2588, pruned_loss=0.02955, over 1416823.04 frames.], batch size: 21, lr: 2.23e-04
+2022-04-30 17:14:40,039 INFO [train.py:763] (0/8) Epoch 34, batch 1100, loss[loss=0.1354, simple_loss=0.2309, pruned_loss=0.01999, over 7359.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2584, pruned_loss=0.02934, over 1420769.05 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:15:45,153 INFO [train.py:763] (0/8) Epoch 34, batch 1150, loss[loss=0.1751, simple_loss=0.2785, pruned_loss=0.03587, over 7214.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2586, pruned_loss=0.02918, over 1422556.95 frames.], batch size: 23, lr: 2.23e-04
+2022-04-30 17:16:50,475 INFO [train.py:763] (0/8) Epoch 34, batch 1200, loss[loss=0.151, simple_loss=0.2533, pruned_loss=0.02436, over 7294.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02916, over 1425866.63 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:17:56,124 INFO [train.py:763] (0/8) Epoch 34, batch 1250, loss[loss=0.1662, simple_loss=0.2772, pruned_loss=0.02764, over 7330.00 frames.], tot_loss[loss=0.1589, simple_loss=0.259, pruned_loss=0.0294, over 1424786.17 frames.], batch size: 22, lr: 2.23e-04
+2022-04-30 17:19:02,076 INFO [train.py:763] (0/8) Epoch 34, batch 1300, loss[loss=0.1627, simple_loss=0.2697, pruned_loss=0.02785, over 7075.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2597, pruned_loss=0.02994, over 1420649.60 frames.], batch size: 28, lr: 2.23e-04
+2022-04-30 17:20:07,323 INFO [train.py:763] (0/8) Epoch 34, batch 1350, loss[loss=0.1673, simple_loss=0.2648, pruned_loss=0.03493, over 7141.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03024, over 1423156.04 frames.], batch size: 28, lr: 2.23e-04
+2022-04-30 17:21:12,467 INFO [train.py:763] (0/8) Epoch 34, batch 1400, loss[loss=0.1817, simple_loss=0.2798, pruned_loss=0.04183, over 7322.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2611, pruned_loss=0.03052, over 1420334.14 frames.], batch size: 20, lr: 2.23e-04
+2022-04-30 17:22:17,959 INFO [train.py:763] (0/8) Epoch 34, batch 1450, loss[loss=0.1641, simple_loss=0.2835, pruned_loss=0.02232, over 7257.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2602, pruned_loss=0.03029, over 1419108.59 frames.], batch size: 19, lr: 2.23e-04
+2022-04-30 17:23:24,438 INFO [train.py:763] (0/8) Epoch 34, batch 1500, loss[loss=0.1422, simple_loss=0.2348, pruned_loss=0.02481, over 7147.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.03011, over 1419426.06 frames.], batch size: 17, lr: 2.23e-04
+2022-04-30 17:24:29,702 INFO [train.py:763] (0/8) Epoch 34, batch 1550, loss[loss=0.2016, simple_loss=0.306, pruned_loss=0.04858, over 7212.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03023, over 1419762.08 frames.], batch size: 21, lr: 2.23e-04
+2022-04-30 17:25:36,476 INFO [train.py:763] (0/8) Epoch 34, batch 1600, loss[loss=0.1757, simple_loss=0.2823, pruned_loss=0.03455, over 7048.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2607, pruned_loss=0.03016, over 1421123.78 frames.], batch size: 28, lr: 2.23e-04
+2022-04-30 17:26:43,362 INFO [train.py:763] (0/8) Epoch 34, batch 1650, loss[loss=0.1186, simple_loss=0.2167, pruned_loss=0.01024, over 7418.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2605, pruned_loss=0.02992, over 1426449.34 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:27:48,838 INFO [train.py:763] (0/8) Epoch 34, batch 1700, loss[loss=0.1724, simple_loss=0.2692, pruned_loss=0.0378, over 5050.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2605, pruned_loss=0.02996, over 1425546.74 frames.], batch size: 52, lr: 2.23e-04
+2022-04-30 17:28:54,325 INFO [train.py:763] (0/8) Epoch 34, batch 1750, loss[loss=0.1534, simple_loss=0.2543, pruned_loss=0.02618, over 7164.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2589, pruned_loss=0.02993, over 1427102.33 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:29:59,727 INFO [train.py:763] (0/8) Epoch 34, batch 1800, loss[loss=0.162, simple_loss=0.2686, pruned_loss=0.0277, over 7326.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2584, pruned_loss=0.02956, over 1430935.66 frames.], batch size: 25, lr: 2.23e-04
+2022-04-30 17:31:04,985 INFO [train.py:763] (0/8) Epoch 34, batch 1850, loss[loss=0.1495, simple_loss=0.2502, pruned_loss=0.02443, over 7068.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2584, pruned_loss=0.0295, over 1426857.22 frames.], batch size: 18, lr: 2.23e-04
+2022-04-30 17:32:10,322 INFO [train.py:763] (0/8) Epoch 34, batch 1900, loss[loss=0.1815, simple_loss=0.2922, pruned_loss=0.03534, over 7376.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2583, pruned_loss=0.02955, over 1425540.92 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:33:15,845 INFO [train.py:763] (0/8) Epoch 34, batch 1950, loss[loss=0.1351, simple_loss=0.2308, pruned_loss=0.01965, over 7156.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2582, pruned_loss=0.02941, over 1424370.41 frames.], batch size: 18, lr: 2.22e-04
+2022-04-30 17:34:22,084 INFO [train.py:763] (0/8) Epoch 34, batch 2000, loss[loss=0.163, simple_loss=0.2715, pruned_loss=0.02729, over 6365.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2589, pruned_loss=0.02982, over 1419871.75 frames.], batch size: 38, lr: 2.22e-04
+2022-04-30 17:35:27,878 INFO [train.py:763] (0/8) Epoch 34, batch 2050, loss[loss=0.1387, simple_loss=0.2414, pruned_loss=0.018, over 7121.00 frames.], tot_loss[loss=0.1589, simple_loss=0.259, pruned_loss=0.02941, over 1421613.54 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:36:33,097 INFO [train.py:763] (0/8) Epoch 34, batch 2100, loss[loss=0.1463, simple_loss=0.2539, pruned_loss=0.01939, over 7413.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.0293, over 1423991.45 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:37:40,129 INFO [train.py:763] (0/8) Epoch 34, batch 2150, loss[loss=0.1496, simple_loss=0.256, pruned_loss=0.02165, over 6235.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02903, over 1427222.73 frames.], batch size: 37, lr: 2.22e-04
+2022-04-30 17:38:46,199 INFO [train.py:763] (0/8) Epoch 34, batch 2200, loss[loss=0.1757, simple_loss=0.2849, pruned_loss=0.0332, over 7428.00 frames.], tot_loss[loss=0.159, simple_loss=0.2593, pruned_loss=0.02931, over 1423813.60 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:39:51,388 INFO [train.py:763] (0/8) Epoch 34, batch 2250, loss[loss=0.1528, simple_loss=0.2466, pruned_loss=0.02953, over 7283.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02942, over 1421899.84 frames.], batch size: 18, lr: 2.22e-04
+2022-04-30 17:40:56,561 INFO [train.py:763] (0/8) Epoch 34, batch 2300, loss[loss=0.1867, simple_loss=0.3, pruned_loss=0.03677, over 7192.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.02979, over 1418668.55 frames.], batch size: 26, lr: 2.22e-04
+2022-04-30 17:42:01,783 INFO [train.py:763] (0/8) Epoch 34, batch 2350, loss[loss=0.141, simple_loss=0.249, pruned_loss=0.01649, over 7176.00 frames.], tot_loss[loss=0.1591, simple_loss=0.259, pruned_loss=0.02958, over 1416690.62 frames.], batch size: 28, lr: 2.22e-04
+2022-04-30 17:43:08,057 INFO [train.py:763] (0/8) Epoch 34, batch 2400, loss[loss=0.1287, simple_loss=0.2282, pruned_loss=0.01457, over 6998.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.02979, over 1421652.22 frames.], batch size: 16, lr: 2.22e-04
+2022-04-30 17:44:15,106 INFO [train.py:763] (0/8) Epoch 34, batch 2450, loss[loss=0.1482, simple_loss=0.2461, pruned_loss=0.0252, over 7429.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2586, pruned_loss=0.02942, over 1422184.60 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:45:22,384 INFO [train.py:763] (0/8) Epoch 34, batch 2500, loss[loss=0.1934, simple_loss=0.2929, pruned_loss=0.04689, over 6436.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2584, pruned_loss=0.02967, over 1423830.44 frames.], batch size: 38, lr: 2.22e-04
+2022-04-30 17:46:28,757 INFO [train.py:763] (0/8) Epoch 34, batch 2550, loss[loss=0.1774, simple_loss=0.2842, pruned_loss=0.03537, over 7116.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2587, pruned_loss=0.02986, over 1423910.60 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:47:35,801 INFO [train.py:763] (0/8) Epoch 34, batch 2600, loss[loss=0.2019, simple_loss=0.2911, pruned_loss=0.0564, over 7199.00 frames.], tot_loss[loss=0.159, simple_loss=0.2583, pruned_loss=0.0298, over 1423545.52 frames.], batch size: 22, lr: 2.22e-04
+2022-04-30 17:48:40,942 INFO [train.py:763] (0/8) Epoch 34, batch 2650, loss[loss=0.179, simple_loss=0.2798, pruned_loss=0.03911, over 7205.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2586, pruned_loss=0.02979, over 1421586.17 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:49:46,282 INFO [train.py:763] (0/8) Epoch 34, batch 2700, loss[loss=0.1519, simple_loss=0.2617, pruned_loss=0.02101, over 7106.00 frames.], tot_loss[loss=0.159, simple_loss=0.2588, pruned_loss=0.02962, over 1423713.96 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:50:51,547 INFO [train.py:763] (0/8) Epoch 34, batch 2750, loss[loss=0.1693, simple_loss=0.2808, pruned_loss=0.02883, over 7316.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03035, over 1423118.01 frames.], batch size: 21, lr: 2.22e-04
+2022-04-30 17:51:57,732 INFO [train.py:763] (0/8) Epoch 34, batch 2800, loss[loss=0.1536, simple_loss=0.2448, pruned_loss=0.03117, over 7327.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2605, pruned_loss=0.03043, over 1423881.13 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:53:04,502 INFO [train.py:763] (0/8) Epoch 34, batch 2850, loss[loss=0.1531, simple_loss=0.2567, pruned_loss=0.0248, over 7158.00 frames.], tot_loss[loss=0.161, simple_loss=0.2611, pruned_loss=0.03043, over 1421692.22 frames.], batch size: 19, lr: 2.22e-04
+2022-04-30 17:54:11,628 INFO [train.py:763] (0/8) Epoch 34, batch 2900, loss[loss=0.163, simple_loss=0.2675, pruned_loss=0.02926, over 6615.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03064, over 1421901.73 frames.], batch size: 37, lr: 2.22e-04
+2022-04-30 17:55:17,496 INFO [train.py:763] (0/8) Epoch 34, batch 2950, loss[loss=0.1617, simple_loss=0.2566, pruned_loss=0.03341, over 6811.00 frames.], tot_loss[loss=0.162, simple_loss=0.2623, pruned_loss=0.0309, over 1415090.86 frames.], batch size: 15, lr: 2.22e-04
+2022-04-30 17:56:22,959 INFO [train.py:763] (0/8) Epoch 34, batch 3000, loss[loss=0.1697, simple_loss=0.2698, pruned_loss=0.03486, over 7375.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.03017, over 1419392.06 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:56:22,960 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 17:56:38,270 INFO [train.py:792] (0/8) Epoch 34, validation: loss=0.1686, simple_loss=0.2638, pruned_loss=0.03669, over 698248.00 frames.
+2022-04-30 17:57:44,336 INFO [train.py:763] (0/8) Epoch 34, batch 3050, loss[loss=0.1658, simple_loss=0.2703, pruned_loss=0.03062, over 7228.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2619, pruned_loss=0.03036, over 1422811.72 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 17:58:51,173 INFO [train.py:763] (0/8) Epoch 34, batch 3100, loss[loss=0.1595, simple_loss=0.2662, pruned_loss=0.0264, over 7363.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2609, pruned_loss=0.03016, over 1419953.76 frames.], batch size: 23, lr: 2.22e-04
+2022-04-30 17:59:56,672 INFO [train.py:763] (0/8) Epoch 34, batch 3150, loss[loss=0.189, simple_loss=0.2823, pruned_loss=0.04781, over 7211.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2599, pruned_loss=0.02973, over 1422465.30 frames.], batch size: 22, lr: 2.22e-04
+2022-04-30 18:01:02,302 INFO [train.py:763] (0/8) Epoch 34, batch 3200, loss[loss=0.1528, simple_loss=0.2625, pruned_loss=0.02153, over 7200.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2607, pruned_loss=0.02979, over 1427122.62 frames.], batch size: 22, lr: 2.22e-04
+2022-04-30 18:02:09,421 INFO [train.py:763] (0/8) Epoch 34, batch 3250, loss[loss=0.1873, simple_loss=0.2728, pruned_loss=0.05089, over 7433.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.02981, over 1425217.67 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 18:03:15,763 INFO [train.py:763] (0/8) Epoch 34, batch 3300, loss[loss=0.1468, simple_loss=0.2537, pruned_loss=0.01998, over 7422.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.02977, over 1426495.64 frames.], batch size: 20, lr: 2.22e-04
+2022-04-30 18:04:21,129 INFO [train.py:763] (0/8) Epoch 34, batch 3350, loss[loss=0.1508, simple_loss=0.2446, pruned_loss=0.02845, over 7423.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2605, pruned_loss=0.02955, over 1429574.88 frames.], batch size: 20, lr: 2.21e-04
+2022-04-30 18:05:26,511 INFO [train.py:763] (0/8) Epoch 34, batch 3400, loss[loss=0.1485, simple_loss=0.2484, pruned_loss=0.02427, over 7281.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2601, pruned_loss=0.02935, over 1425909.22 frames.], batch size: 18, lr: 2.21e-04
+2022-04-30 18:06:31,939 INFO [train.py:763] (0/8) Epoch 34, batch 3450, loss[loss=0.1419, simple_loss=0.2415, pruned_loss=0.02114, over 7001.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2603, pruned_loss=0.02947, over 1429161.59 frames.], batch size: 16, lr: 2.21e-04
+2022-04-30 18:07:37,453 INFO [train.py:763] (0/8) Epoch 34, batch 3500, loss[loss=0.1534, simple_loss=0.2629, pruned_loss=0.02194, over 7334.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2604, pruned_loss=0.02945, over 1428349.40 frames.], batch size: 22, lr: 2.21e-04
+2022-04-30 18:08:42,513 INFO [train.py:763] (0/8) Epoch 34, batch 3550, loss[loss=0.1701, simple_loss=0.2708, pruned_loss=0.03469, over 6796.00 frames.], tot_loss[loss=0.16, simple_loss=0.2606, pruned_loss=0.02965, over 1421077.96 frames.], batch size: 31, lr: 2.21e-04
+2022-04-30 18:09:48,234 INFO [train.py:763] (0/8) Epoch 34, batch 3600, loss[loss=0.206, simple_loss=0.3116, pruned_loss=0.05021, over 7199.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2612, pruned_loss=0.03016, over 1420250.57 frames.], batch size: 22, lr: 2.21e-04
+2022-04-30 18:10:55,331 INFO [train.py:763] (0/8) Epoch 34, batch 3650, loss[loss=0.1499, simple_loss=0.2585, pruned_loss=0.02062, over 7310.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2617, pruned_loss=0.03034, over 1421634.69 frames.], batch size: 25, lr: 2.21e-04
+2022-04-30 18:12:01,497 INFO [train.py:763] (0/8) Epoch 34, batch 3700, loss[loss=0.1602, simple_loss=0.26, pruned_loss=0.03021, over 6389.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2613, pruned_loss=0.02999, over 1421505.47 frames.], batch size: 37, lr: 2.21e-04
+2022-04-30 18:13:06,706 INFO [train.py:763] (0/8) Epoch 34, batch 3750, loss[loss=0.2059, simple_loss=0.3005, pruned_loss=0.05564, over 4843.00 frames.], tot_loss[loss=0.161, simple_loss=0.2617, pruned_loss=0.03012, over 1419027.27 frames.], batch size: 52, lr: 2.21e-04
+2022-04-30 18:14:11,988 INFO [train.py:763] (0/8) Epoch 34, batch 3800, loss[loss=0.1605, simple_loss=0.2652, pruned_loss=0.02795, over 6717.00 frames.], tot_loss[loss=0.161, simple_loss=0.2618, pruned_loss=0.03013, over 1419169.06 frames.], batch size: 31, lr: 2.21e-04
+2022-04-30 18:15:17,338 INFO [train.py:763] (0/8) Epoch 34, batch 3850, loss[loss=0.188, simple_loss=0.2827, pruned_loss=0.04666, over 7305.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2612, pruned_loss=0.0298, over 1421267.09 frames.], batch size: 24, lr: 2.21e-04
+2022-04-30 18:16:23,853 INFO [train.py:763] (0/8) Epoch 34, batch 3900, loss[loss=0.1554, simple_loss=0.2414, pruned_loss=0.03464, over 6755.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2616, pruned_loss=0.03006, over 1416902.56 frames.], batch size: 15, lr: 2.21e-04
+2022-04-30 18:17:31,010 INFO [train.py:763] (0/8) Epoch 34, batch 3950, loss[loss=0.1303, simple_loss=0.2313, pruned_loss=0.01463, over 7130.00 frames.], tot_loss[loss=0.1601, simple_loss=0.261, pruned_loss=0.02965, over 1418169.32 frames.], batch size: 17, lr: 2.21e-04
+2022-04-30 18:18:37,996 INFO [train.py:763] (0/8) Epoch 34, batch 4000, loss[loss=0.1605, simple_loss=0.2532, pruned_loss=0.03395, over 6990.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2605, pruned_loss=0.02961, over 1418198.19 frames.], batch size: 16, lr: 2.21e-04
+2022-04-30 18:18:47,284 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-160000.pt
+2022-04-30 18:19:54,716 INFO [train.py:763] (0/8) Epoch 34, batch 4050, loss[loss=0.1705, simple_loss=0.2778, pruned_loss=0.03158, over 6348.00 frames.], tot_loss[loss=0.16, simple_loss=0.261, pruned_loss=0.02944, over 1420729.81 frames.], batch size: 37, lr: 2.21e-04
+2022-04-30 18:21:01,775 INFO [train.py:763] (0/8) Epoch 34, batch 4100, loss[loss=0.1475, simple_loss=0.2554, pruned_loss=0.01976, over 7223.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2611, pruned_loss=0.02957, over 1425905.04 frames.], batch size: 21, lr: 2.21e-04
+2022-04-30 18:22:08,653 INFO [train.py:763] (0/8) Epoch 34, batch 4150, loss[loss=0.1546, simple_loss=0.2675, pruned_loss=0.02086, over 7315.00 frames.], tot_loss[loss=0.1593, simple_loss=0.26, pruned_loss=0.02931, over 1425347.09 frames.], batch size: 21, lr: 2.21e-04
+2022-04-30 18:23:15,044 INFO [train.py:763] (0/8) Epoch 34, batch 4200, loss[loss=0.1824, simple_loss=0.2909, pruned_loss=0.03694, over 7316.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2602, pruned_loss=0.02955, over 1423016.85 frames.], batch size: 21, lr: 2.21e-04
+2022-04-30 18:24:20,542 INFO [train.py:763] (0/8) Epoch 34, batch 4250, loss[loss=0.129, simple_loss=0.2226, pruned_loss=0.01769, over 7280.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2594, pruned_loss=0.02914, over 1427911.21 frames.], batch size: 17, lr: 2.21e-04
+2022-04-30 18:25:25,966 INFO [train.py:763] (0/8) Epoch 34, batch 4300, loss[loss=0.1495, simple_loss=0.2493, pruned_loss=0.02486, over 7179.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.0292, over 1418911.30 frames.], batch size: 26, lr: 2.21e-04
+2022-04-30 18:26:32,713 INFO [train.py:763] (0/8) Epoch 34, batch 4350, loss[loss=0.1862, simple_loss=0.2905, pruned_loss=0.04095, over 7289.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2605, pruned_loss=0.0301, over 1415157.31 frames.], batch size: 24, lr: 2.21e-04
+2022-04-30 18:27:38,209 INFO [train.py:763] (0/8) Epoch 34, batch 4400, loss[loss=0.1347, simple_loss=0.2341, pruned_loss=0.01762, over 7159.00 frames.], tot_loss[loss=0.1595, simple_loss=0.26, pruned_loss=0.02953, over 1409422.15 frames.], batch size: 19, lr: 2.21e-04
+2022-04-30 18:28:42,660 INFO [train.py:763] (0/8) Epoch 34, batch 4450, loss[loss=0.1644, simple_loss=0.2635, pruned_loss=0.03262, over 6736.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2607, pruned_loss=0.02992, over 1394073.30 frames.], batch size: 31, lr: 2.21e-04
+2022-04-30 18:29:47,248 INFO [train.py:763] (0/8) Epoch 34, batch 4500, loss[loss=0.1791, simple_loss=0.2831, pruned_loss=0.03759, over 7173.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03037, over 1380972.44 frames.], batch size: 26, lr: 2.21e-04
+2022-04-30 18:30:51,778 INFO [train.py:763] (0/8) Epoch 34, batch 4550, loss[loss=0.1918, simple_loss=0.2836, pruned_loss=0.04997, over 5369.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2635, pruned_loss=0.03166, over 1354862.25 frames.], batch size: 53, lr: 2.21e-04
+2022-04-30 18:31:40,905 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-34.pt
+2022-04-30 18:32:11,390 INFO [train.py:763] (0/8) Epoch 35, batch 0, loss[loss=0.1476, simple_loss=0.2479, pruned_loss=0.02363, over 7329.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2479, pruned_loss=0.02363, over 7329.00 frames.], batch size: 20, lr: 2.18e-04
+2022-04-30 18:33:17,377 INFO [train.py:763] (0/8) Epoch 35, batch 50, loss[loss=0.1573, simple_loss=0.2566, pruned_loss=0.029, over 7432.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2605, pruned_loss=0.03008, over 317314.58 frames.], batch size: 20, lr: 2.18e-04
+2022-04-30 18:34:22,747 INFO [train.py:763] (0/8) Epoch 35, batch 100, loss[loss=0.1798, simple_loss=0.274, pruned_loss=0.0428, over 4800.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2604, pruned_loss=0.02956, over 562296.69 frames.], batch size: 52, lr: 2.17e-04
+2022-04-30 18:35:28,406 INFO [train.py:763] (0/8) Epoch 35, batch 150, loss[loss=0.1629, simple_loss=0.2735, pruned_loss=0.02618, over 7231.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2591, pruned_loss=0.02954, over 751033.84 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 18:36:34,089 INFO [train.py:763] (0/8) Epoch 35, batch 200, loss[loss=0.1599, simple_loss=0.2627, pruned_loss=0.02852, over 7328.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.0297, over 902092.01 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 18:37:50,845 INFO [train.py:763] (0/8) Epoch 35, batch 250, loss[loss=0.1449, simple_loss=0.25, pruned_loss=0.01989, over 7169.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2592, pruned_loss=0.02953, over 1021255.41 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:38:58,244 INFO [train.py:763] (0/8) Epoch 35, batch 300, loss[loss=0.1979, simple_loss=0.3037, pruned_loss=0.04604, over 7178.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.02953, over 1106124.01 frames.], batch size: 26, lr: 2.17e-04
+2022-04-30 18:40:05,548 INFO [train.py:763] (0/8) Epoch 35, batch 350, loss[loss=0.1677, simple_loss=0.2792, pruned_loss=0.02813, over 6728.00 frames.], tot_loss[loss=0.1594, simple_loss=0.26, pruned_loss=0.02944, over 1175286.64 frames.], batch size: 31, lr: 2.17e-04
+2022-04-30 18:41:12,764 INFO [train.py:763] (0/8) Epoch 35, batch 400, loss[loss=0.1721, simple_loss=0.272, pruned_loss=0.03607, over 7207.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2611, pruned_loss=0.02981, over 1231157.36 frames.], batch size: 22, lr: 2.17e-04
+2022-04-30 18:42:19,853 INFO [train.py:763] (0/8) Epoch 35, batch 450, loss[loss=0.1896, simple_loss=0.2984, pruned_loss=0.04043, over 7190.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2613, pruned_loss=0.03027, over 1278737.46 frames.], batch size: 26, lr: 2.17e-04
+2022-04-30 18:43:25,157 INFO [train.py:763] (0/8) Epoch 35, batch 500, loss[loss=0.1561, simple_loss=0.2515, pruned_loss=0.03035, over 7192.00 frames.], tot_loss[loss=0.1606, simple_loss=0.261, pruned_loss=0.03006, over 1310152.24 frames.], batch size: 23, lr: 2.17e-04
+2022-04-30 18:44:30,971 INFO [train.py:763] (0/8) Epoch 35, batch 550, loss[loss=0.1678, simple_loss=0.2648, pruned_loss=0.03542, over 7435.00 frames.], tot_loss[loss=0.1611, simple_loss=0.262, pruned_loss=0.03007, over 1336537.98 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 18:45:37,231 INFO [train.py:763] (0/8) Epoch 35, batch 600, loss[loss=0.1613, simple_loss=0.2727, pruned_loss=0.02491, over 7199.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2609, pruned_loss=0.02977, over 1358843.26 frames.], batch size: 23, lr: 2.17e-04
+2022-04-30 18:46:44,902 INFO [train.py:763] (0/8) Epoch 35, batch 650, loss[loss=0.1582, simple_loss=0.2604, pruned_loss=0.02803, over 7151.00 frames.], tot_loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.02961, over 1373963.79 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:47:52,738 INFO [train.py:763] (0/8) Epoch 35, batch 700, loss[loss=0.1339, simple_loss=0.2369, pruned_loss=0.01549, over 7263.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2598, pruned_loss=0.02963, over 1384980.31 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:48:58,274 INFO [train.py:763] (0/8) Epoch 35, batch 750, loss[loss=0.1806, simple_loss=0.2884, pruned_loss=0.03643, over 7324.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02964, over 1384876.40 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 18:50:03,737 INFO [train.py:763] (0/8) Epoch 35, batch 800, loss[loss=0.1918, simple_loss=0.289, pruned_loss=0.04731, over 7408.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2606, pruned_loss=0.02963, over 1393650.62 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 18:51:09,204 INFO [train.py:763] (0/8) Epoch 35, batch 850, loss[loss=0.148, simple_loss=0.2546, pruned_loss=0.02071, over 7225.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02971, over 1395005.93 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 18:52:23,433 INFO [train.py:763] (0/8) Epoch 35, batch 900, loss[loss=0.1522, simple_loss=0.2532, pruned_loss=0.02561, over 6915.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2606, pruned_loss=0.02993, over 1402162.92 frames.], batch size: 31, lr: 2.17e-04
+2022-04-30 18:53:37,769 INFO [train.py:763] (0/8) Epoch 35, batch 950, loss[loss=0.1343, simple_loss=0.2391, pruned_loss=0.01476, over 6987.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03048, over 1406471.51 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 18:54:42,880 INFO [train.py:763] (0/8) Epoch 35, batch 1000, loss[loss=0.1419, simple_loss=0.2367, pruned_loss=0.02351, over 7276.00 frames.], tot_loss[loss=0.16, simple_loss=0.2603, pruned_loss=0.0299, over 1408242.76 frames.], batch size: 17, lr: 2.17e-04
+2022-04-30 18:55:57,245 INFO [train.py:763] (0/8) Epoch 35, batch 1050, loss[loss=0.1506, simple_loss=0.2507, pruned_loss=0.02526, over 7365.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02988, over 1408696.44 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 18:57:20,302 INFO [train.py:763] (0/8) Epoch 35, batch 1100, loss[loss=0.1803, simple_loss=0.2723, pruned_loss=0.04419, over 7196.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03024, over 1408378.69 frames.], batch size: 22, lr: 2.17e-04
+2022-04-30 18:58:25,989 INFO [train.py:763] (0/8) Epoch 35, batch 1150, loss[loss=0.1781, simple_loss=0.2832, pruned_loss=0.03647, over 7288.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2604, pruned_loss=0.03048, over 1413600.91 frames.], batch size: 24, lr: 2.17e-04
+2022-04-30 18:59:32,079 INFO [train.py:763] (0/8) Epoch 35, batch 1200, loss[loss=0.1493, simple_loss=0.2361, pruned_loss=0.03129, over 7286.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03077, over 1409510.88 frames.], batch size: 17, lr: 2.17e-04
+2022-04-30 19:00:55,259 INFO [train.py:763] (0/8) Epoch 35, batch 1250, loss[loss=0.1498, simple_loss=0.2458, pruned_loss=0.02688, over 7001.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2599, pruned_loss=0.0302, over 1410971.55 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 19:02:00,727 INFO [train.py:763] (0/8) Epoch 35, batch 1300, loss[loss=0.1465, simple_loss=0.2483, pruned_loss=0.02236, over 7140.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03022, over 1415321.59 frames.], batch size: 17, lr: 2.17e-04
+2022-04-30 19:03:07,809 INFO [train.py:763] (0/8) Epoch 35, batch 1350, loss[loss=0.1649, simple_loss=0.2596, pruned_loss=0.03508, over 7259.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2585, pruned_loss=0.02956, over 1420311.15 frames.], batch size: 19, lr: 2.17e-04
+2022-04-30 19:04:12,917 INFO [train.py:763] (0/8) Epoch 35, batch 1400, loss[loss=0.1353, simple_loss=0.2266, pruned_loss=0.022, over 7007.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2591, pruned_loss=0.02985, over 1419122.97 frames.], batch size: 16, lr: 2.17e-04
+2022-04-30 19:05:18,838 INFO [train.py:763] (0/8) Epoch 35, batch 1450, loss[loss=0.125, simple_loss=0.2218, pruned_loss=0.0141, over 6857.00 frames.], tot_loss[loss=0.159, simple_loss=0.2587, pruned_loss=0.02963, over 1415645.33 frames.], batch size: 15, lr: 2.17e-04
+2022-04-30 19:06:24,730 INFO [train.py:763] (0/8) Epoch 35, batch 1500, loss[loss=0.1475, simple_loss=0.2535, pruned_loss=0.02071, over 7308.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02936, over 1419464.40 frames.], batch size: 21, lr: 2.17e-04
+2022-04-30 19:07:30,583 INFO [train.py:763] (0/8) Epoch 35, batch 1550, loss[loss=0.13, simple_loss=0.2371, pruned_loss=0.0115, over 7226.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2592, pruned_loss=0.02898, over 1421198.55 frames.], batch size: 20, lr: 2.17e-04
+2022-04-30 19:08:36,021 INFO [train.py:763] (0/8) Epoch 35, batch 1600, loss[loss=0.1717, simple_loss=0.2716, pruned_loss=0.03583, over 7393.00 frames.], tot_loss[loss=0.1586, simple_loss=0.259, pruned_loss=0.02908, over 1420920.28 frames.], batch size: 23, lr: 2.16e-04
+2022-04-30 19:09:42,667 INFO [train.py:763] (0/8) Epoch 35, batch 1650, loss[loss=0.1554, simple_loss=0.2542, pruned_loss=0.02836, over 7163.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02938, over 1421927.12 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:10:49,608 INFO [train.py:763] (0/8) Epoch 35, batch 1700, loss[loss=0.1715, simple_loss=0.2754, pruned_loss=0.03382, over 7293.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2599, pruned_loss=0.02922, over 1424255.16 frames.], batch size: 25, lr: 2.16e-04
+2022-04-30 19:11:56,546 INFO [train.py:763] (0/8) Epoch 35, batch 1750, loss[loss=0.1735, simple_loss=0.256, pruned_loss=0.04549, over 7280.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2601, pruned_loss=0.0295, over 1420463.89 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:13:03,591 INFO [train.py:763] (0/8) Epoch 35, batch 1800, loss[loss=0.1667, simple_loss=0.2669, pruned_loss=0.03327, over 7188.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2606, pruned_loss=0.02944, over 1422754.81 frames.], batch size: 23, lr: 2.16e-04
+2022-04-30 19:14:09,383 INFO [train.py:763] (0/8) Epoch 35, batch 1850, loss[loss=0.1896, simple_loss=0.2833, pruned_loss=0.04799, over 7120.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2603, pruned_loss=0.02966, over 1425219.28 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:15:15,155 INFO [train.py:763] (0/8) Epoch 35, batch 1900, loss[loss=0.1783, simple_loss=0.2682, pruned_loss=0.04419, over 6869.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2596, pruned_loss=0.02954, over 1426351.59 frames.], batch size: 31, lr: 2.16e-04
+2022-04-30 19:16:21,444 INFO [train.py:763] (0/8) Epoch 35, batch 1950, loss[loss=0.1451, simple_loss=0.2558, pruned_loss=0.01718, over 7235.00 frames.], tot_loss[loss=0.16, simple_loss=0.2597, pruned_loss=0.03014, over 1423710.64 frames.], batch size: 20, lr: 2.16e-04
+2022-04-30 19:17:27,465 INFO [train.py:763] (0/8) Epoch 35, batch 2000, loss[loss=0.1709, simple_loss=0.2693, pruned_loss=0.03622, over 7004.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.03042, over 1420746.62 frames.], batch size: 16, lr: 2.16e-04
+2022-04-30 19:18:34,501 INFO [train.py:763] (0/8) Epoch 35, batch 2050, loss[loss=0.1976, simple_loss=0.3087, pruned_loss=0.04322, over 7315.00 frames.], tot_loss[loss=0.1607, simple_loss=0.261, pruned_loss=0.0302, over 1425061.90 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:19:40,356 INFO [train.py:763] (0/8) Epoch 35, batch 2100, loss[loss=0.1536, simple_loss=0.2629, pruned_loss=0.02212, over 7420.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2598, pruned_loss=0.03004, over 1424116.52 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:20:47,329 INFO [train.py:763] (0/8) Epoch 35, batch 2150, loss[loss=0.1652, simple_loss=0.2669, pruned_loss=0.03177, over 7255.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2588, pruned_loss=0.02967, over 1426961.13 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:21:54,061 INFO [train.py:763] (0/8) Epoch 35, batch 2200, loss[loss=0.1424, simple_loss=0.2352, pruned_loss=0.02484, over 7401.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2587, pruned_loss=0.02923, over 1425895.68 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:23:01,265 INFO [train.py:763] (0/8) Epoch 35, batch 2250, loss[loss=0.1689, simple_loss=0.2723, pruned_loss=0.03276, over 7350.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2602, pruned_loss=0.02972, over 1422459.46 frames.], batch size: 22, lr: 2.16e-04
+2022-04-30 19:24:07,990 INFO [train.py:763] (0/8) Epoch 35, batch 2300, loss[loss=0.1504, simple_loss=0.2486, pruned_loss=0.02612, over 7130.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2592, pruned_loss=0.02928, over 1425166.14 frames.], batch size: 17, lr: 2.16e-04
+2022-04-30 19:25:12,953 INFO [train.py:763] (0/8) Epoch 35, batch 2350, loss[loss=0.184, simple_loss=0.2749, pruned_loss=0.04654, over 5251.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.02978, over 1424122.66 frames.], batch size: 52, lr: 2.16e-04
+2022-04-30 19:26:18,893 INFO [train.py:763] (0/8) Epoch 35, batch 2400, loss[loss=0.147, simple_loss=0.245, pruned_loss=0.02454, over 7415.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2594, pruned_loss=0.02944, over 1427863.52 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:27:24,051 INFO [train.py:763] (0/8) Epoch 35, batch 2450, loss[loss=0.1769, simple_loss=0.26, pruned_loss=0.04691, over 7167.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02938, over 1423626.25 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:28:30,202 INFO [train.py:763] (0/8) Epoch 35, batch 2500, loss[loss=0.1679, simple_loss=0.2728, pruned_loss=0.03146, over 7149.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.0291, over 1427449.76 frames.], batch size: 20, lr: 2.16e-04
+2022-04-30 19:29:36,786 INFO [train.py:763] (0/8) Epoch 35, batch 2550, loss[loss=0.152, simple_loss=0.2472, pruned_loss=0.02843, over 7364.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2594, pruned_loss=0.02963, over 1424101.78 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:30:41,925 INFO [train.py:763] (0/8) Epoch 35, batch 2600, loss[loss=0.1478, simple_loss=0.251, pruned_loss=0.02231, over 7143.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02941, over 1424262.97 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:31:47,698 INFO [train.py:763] (0/8) Epoch 35, batch 2650, loss[loss=0.2165, simple_loss=0.3129, pruned_loss=0.0601, over 4844.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2589, pruned_loss=0.02968, over 1422932.39 frames.], batch size: 52, lr: 2.16e-04
+2022-04-30 19:32:53,217 INFO [train.py:763] (0/8) Epoch 35, batch 2700, loss[loss=0.1666, simple_loss=0.2734, pruned_loss=0.02992, over 7319.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2586, pruned_loss=0.02944, over 1424188.82 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:33:59,272 INFO [train.py:763] (0/8) Epoch 35, batch 2750, loss[loss=0.1482, simple_loss=0.2599, pruned_loss=0.01826, over 7115.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2582, pruned_loss=0.02905, over 1426936.29 frames.], batch size: 21, lr: 2.16e-04
+2022-04-30 19:35:05,460 INFO [train.py:763] (0/8) Epoch 35, batch 2800, loss[loss=0.1718, simple_loss=0.2759, pruned_loss=0.03382, over 7208.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2574, pruned_loss=0.02891, over 1428308.85 frames.], batch size: 22, lr: 2.16e-04
+2022-04-30 19:36:12,182 INFO [train.py:763] (0/8) Epoch 35, batch 2850, loss[loss=0.1304, simple_loss=0.2274, pruned_loss=0.0167, over 7288.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2566, pruned_loss=0.02853, over 1428898.87 frames.], batch size: 17, lr: 2.16e-04
+2022-04-30 19:37:18,079 INFO [train.py:763] (0/8) Epoch 35, batch 2900, loss[loss=0.1397, simple_loss=0.2435, pruned_loss=0.01792, over 7261.00 frames.], tot_loss[loss=0.1564, simple_loss=0.256, pruned_loss=0.0284, over 1427803.67 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:38:23,364 INFO [train.py:763] (0/8) Epoch 35, batch 2950, loss[loss=0.1381, simple_loss=0.2367, pruned_loss=0.01974, over 7156.00 frames.], tot_loss[loss=0.158, simple_loss=0.2576, pruned_loss=0.02922, over 1425636.05 frames.], batch size: 18, lr: 2.16e-04
+2022-04-30 19:39:28,875 INFO [train.py:763] (0/8) Epoch 35, batch 3000, loss[loss=0.1535, simple_loss=0.2581, pruned_loss=0.02446, over 7167.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2595, pruned_loss=0.02993, over 1421760.15 frames.], batch size: 19, lr: 2.16e-04
+2022-04-30 19:39:28,876 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 19:39:43,929 INFO [train.py:792] (0/8) Epoch 35, validation: loss=0.1681, simple_loss=0.2634, pruned_loss=0.03644, over 698248.00 frames.
+2022-04-30 19:40:49,420 INFO [train.py:763] (0/8) Epoch 35, batch 3050, loss[loss=0.1959, simple_loss=0.291, pruned_loss=0.05036, over 7295.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2597, pruned_loss=0.03003, over 1423989.31 frames.], batch size: 24, lr: 2.16e-04
+2022-04-30 19:41:55,516 INFO [train.py:763] (0/8) Epoch 35, batch 3100, loss[loss=0.1721, simple_loss=0.2779, pruned_loss=0.03311, over 7308.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2598, pruned_loss=0.02971, over 1428422.38 frames.], batch size: 25, lr: 2.15e-04
+2022-04-30 19:43:02,619 INFO [train.py:763] (0/8) Epoch 35, batch 3150, loss[loss=0.1743, simple_loss=0.2803, pruned_loss=0.03412, over 7368.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02966, over 1427057.96 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 19:44:09,430 INFO [train.py:763] (0/8) Epoch 35, batch 3200, loss[loss=0.1265, simple_loss=0.2187, pruned_loss=0.01719, over 7124.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.02966, over 1420728.43 frames.], batch size: 17, lr: 2.15e-04
+2022-04-30 19:45:15,570 INFO [train.py:763] (0/8) Epoch 35, batch 3250, loss[loss=0.1757, simple_loss=0.2671, pruned_loss=0.04212, over 4880.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2601, pruned_loss=0.02978, over 1417617.56 frames.], batch size: 52, lr: 2.15e-04
+2022-04-30 19:46:21,016 INFO [train.py:763] (0/8) Epoch 35, batch 3300, loss[loss=0.2025, simple_loss=0.3108, pruned_loss=0.04706, over 7216.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2605, pruned_loss=0.0299, over 1421576.61 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 19:47:26,303 INFO [train.py:763] (0/8) Epoch 35, batch 3350, loss[loss=0.1486, simple_loss=0.2552, pruned_loss=0.02097, over 7192.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2594, pruned_loss=0.02949, over 1426186.37 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 19:48:32,225 INFO [train.py:763] (0/8) Epoch 35, batch 3400, loss[loss=0.1426, simple_loss=0.2381, pruned_loss=0.02353, over 7262.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2588, pruned_loss=0.02932, over 1424687.89 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 19:49:37,621 INFO [train.py:763] (0/8) Epoch 35, batch 3450, loss[loss=0.1603, simple_loss=0.2454, pruned_loss=0.03763, over 7278.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2585, pruned_loss=0.02924, over 1421792.00 frames.], batch size: 17, lr: 2.15e-04
+2022-04-30 19:50:43,220 INFO [train.py:763] (0/8) Epoch 35, batch 3500, loss[loss=0.1856, simple_loss=0.2886, pruned_loss=0.0413, over 7410.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2585, pruned_loss=0.02938, over 1419146.85 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 19:51:48,960 INFO [train.py:763] (0/8) Epoch 35, batch 3550, loss[loss=0.1577, simple_loss=0.2566, pruned_loss=0.02937, over 7092.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2588, pruned_loss=0.02923, over 1422876.88 frames.], batch size: 28, lr: 2.15e-04
+2022-04-30 19:52:54,521 INFO [train.py:763] (0/8) Epoch 35, batch 3600, loss[loss=0.1787, simple_loss=0.2918, pruned_loss=0.03278, over 7285.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2603, pruned_loss=0.02973, over 1421328.91 frames.], batch size: 25, lr: 2.15e-04
+2022-04-30 19:54:00,486 INFO [train.py:763] (0/8) Epoch 35, batch 3650, loss[loss=0.1735, simple_loss=0.2799, pruned_loss=0.03351, over 7291.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02942, over 1423051.66 frames.], batch size: 24, lr: 2.15e-04
+2022-04-30 19:55:05,858 INFO [train.py:763] (0/8) Epoch 35, batch 3700, loss[loss=0.1619, simple_loss=0.2597, pruned_loss=0.03202, over 7113.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2596, pruned_loss=0.0296, over 1426573.01 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 19:56:11,432 INFO [train.py:763] (0/8) Epoch 35, batch 3750, loss[loss=0.1781, simple_loss=0.285, pruned_loss=0.0356, over 7329.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2595, pruned_loss=0.0296, over 1426131.61 frames.], batch size: 22, lr: 2.15e-04
+2022-04-30 19:57:16,649 INFO [train.py:763] (0/8) Epoch 35, batch 3800, loss[loss=0.1587, simple_loss=0.2596, pruned_loss=0.02892, over 7357.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2605, pruned_loss=0.03, over 1428067.14 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 19:58:21,849 INFO [train.py:763] (0/8) Epoch 35, batch 3850, loss[loss=0.1348, simple_loss=0.2244, pruned_loss=0.02258, over 7013.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2605, pruned_loss=0.02999, over 1423796.40 frames.], batch size: 16, lr: 2.15e-04
+2022-04-30 19:59:27,370 INFO [train.py:763] (0/8) Epoch 35, batch 3900, loss[loss=0.1669, simple_loss=0.263, pruned_loss=0.03545, over 7211.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03041, over 1425708.69 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 20:00:33,653 INFO [train.py:763] (0/8) Epoch 35, batch 3950, loss[loss=0.1821, simple_loss=0.2891, pruned_loss=0.0375, over 6741.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2614, pruned_loss=0.0307, over 1423932.91 frames.], batch size: 31, lr: 2.15e-04
+2022-04-30 20:01:41,046 INFO [train.py:763] (0/8) Epoch 35, batch 4000, loss[loss=0.1594, simple_loss=0.2628, pruned_loss=0.02801, over 7097.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2615, pruned_loss=0.03053, over 1423697.36 frames.], batch size: 28, lr: 2.15e-04
+2022-04-30 20:02:46,175 INFO [train.py:763] (0/8) Epoch 35, batch 4050, loss[loss=0.181, simple_loss=0.2799, pruned_loss=0.04106, over 7215.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2617, pruned_loss=0.03034, over 1425832.43 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 20:03:51,649 INFO [train.py:763] (0/8) Epoch 35, batch 4100, loss[loss=0.15, simple_loss=0.2333, pruned_loss=0.03336, over 7151.00 frames.], tot_loss[loss=0.1607, simple_loss=0.261, pruned_loss=0.03015, over 1426812.20 frames.], batch size: 17, lr: 2.15e-04
+2022-04-30 20:04:57,468 INFO [train.py:763] (0/8) Epoch 35, batch 4150, loss[loss=0.1793, simple_loss=0.2767, pruned_loss=0.04095, over 7209.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2598, pruned_loss=0.02992, over 1418802.82 frames.], batch size: 23, lr: 2.15e-04
+2022-04-30 20:06:03,154 INFO [train.py:763] (0/8) Epoch 35, batch 4200, loss[loss=0.1685, simple_loss=0.263, pruned_loss=0.03699, over 7235.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02982, over 1417067.63 frames.], batch size: 20, lr: 2.15e-04
+2022-04-30 20:07:09,104 INFO [train.py:763] (0/8) Epoch 35, batch 4250, loss[loss=0.1876, simple_loss=0.2905, pruned_loss=0.04233, over 7198.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03032, over 1415848.93 frames.], batch size: 22, lr: 2.15e-04
+2022-04-30 20:08:14,300 INFO [train.py:763] (0/8) Epoch 35, batch 4300, loss[loss=0.1682, simple_loss=0.2646, pruned_loss=0.03589, over 7200.00 frames.], tot_loss[loss=0.1594, simple_loss=0.259, pruned_loss=0.02992, over 1412218.87 frames.], batch size: 22, lr: 2.15e-04
+2022-04-30 20:09:20,410 INFO [train.py:763] (0/8) Epoch 35, batch 4350, loss[loss=0.1526, simple_loss=0.2546, pruned_loss=0.02535, over 7427.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2591, pruned_loss=0.02987, over 1411356.38 frames.], batch size: 20, lr: 2.15e-04
+2022-04-30 20:10:26,460 INFO [train.py:763] (0/8) Epoch 35, batch 4400, loss[loss=0.164, simple_loss=0.26, pruned_loss=0.03397, over 7347.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2584, pruned_loss=0.02988, over 1415494.92 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 20:11:33,107 INFO [train.py:763] (0/8) Epoch 35, batch 4450, loss[loss=0.1467, simple_loss=0.2393, pruned_loss=0.02706, over 7218.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2578, pruned_loss=0.02968, over 1406610.45 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 20:12:39,701 INFO [train.py:763] (0/8) Epoch 35, batch 4500, loss[loss=0.1761, simple_loss=0.278, pruned_loss=0.03714, over 7210.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2578, pruned_loss=0.0297, over 1393862.21 frames.], batch size: 21, lr: 2.15e-04
+2022-04-30 20:13:46,218 INFO [train.py:763] (0/8) Epoch 35, batch 4550, loss[loss=0.1523, simple_loss=0.2479, pruned_loss=0.02832, over 7239.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2589, pruned_loss=0.03048, over 1355037.65 frames.], batch size: 19, lr: 2.15e-04
+2022-04-30 20:14:35,168 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-35.pt
+2022-04-30 20:15:13,850 INFO [train.py:763] (0/8) Epoch 36, batch 0, loss[loss=0.1644, simple_loss=0.2864, pruned_loss=0.02123, over 7342.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2864, pruned_loss=0.02123, over 7342.00 frames.], batch size: 22, lr: 2.12e-04
+2022-04-30 20:16:19,183 INFO [train.py:763] (0/8) Epoch 36, batch 50, loss[loss=0.1587, simple_loss=0.2541, pruned_loss=0.0316, over 7076.00 frames.], tot_loss[loss=0.1581, simple_loss=0.26, pruned_loss=0.02811, over 321286.46 frames.], batch size: 18, lr: 2.12e-04
+2022-04-30 20:17:24,383 INFO [train.py:763] (0/8) Epoch 36, batch 100, loss[loss=0.1582, simple_loss=0.264, pruned_loss=0.02621, over 7326.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2596, pruned_loss=0.02787, over 567291.28 frames.], batch size: 20, lr: 2.12e-04
+2022-04-30 20:18:29,500 INFO [train.py:763] (0/8) Epoch 36, batch 150, loss[loss=0.1644, simple_loss=0.2774, pruned_loss=0.0257, over 7096.00 frames.], tot_loss[loss=0.1581, simple_loss=0.26, pruned_loss=0.0281, over 755075.58 frames.], batch size: 28, lr: 2.11e-04
+2022-04-30 20:19:34,478 INFO [train.py:763] (0/8) Epoch 36, batch 200, loss[loss=0.1457, simple_loss=0.2431, pruned_loss=0.02415, over 7313.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2619, pruned_loss=0.02886, over 906566.93 frames.], batch size: 21, lr: 2.11e-04
+2022-04-30 20:20:39,734 INFO [train.py:763] (0/8) Epoch 36, batch 250, loss[loss=0.1383, simple_loss=0.2422, pruned_loss=0.01721, over 7263.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2594, pruned_loss=0.02853, over 1018195.24 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:21:45,229 INFO [train.py:763] (0/8) Epoch 36, batch 300, loss[loss=0.1589, simple_loss=0.255, pruned_loss=0.03136, over 7343.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2587, pruned_loss=0.02857, over 1104381.77 frames.], batch size: 22, lr: 2.11e-04
+2022-04-30 20:22:50,520 INFO [train.py:763] (0/8) Epoch 36, batch 350, loss[loss=0.1257, simple_loss=0.219, pruned_loss=0.01615, over 7168.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02906, over 1172743.85 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:23:55,937 INFO [train.py:763] (0/8) Epoch 36, batch 400, loss[loss=0.1552, simple_loss=0.2561, pruned_loss=0.02713, over 7237.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02914, over 1232272.71 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:25:01,051 INFO [train.py:763] (0/8) Epoch 36, batch 450, loss[loss=0.1571, simple_loss=0.2537, pruned_loss=0.03023, over 7135.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02926, over 1277248.37 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:26:07,080 INFO [train.py:763] (0/8) Epoch 36, batch 500, loss[loss=0.1633, simple_loss=0.2647, pruned_loss=0.03099, over 7236.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2596, pruned_loss=0.02949, over 1307044.43 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:27:14,411 INFO [train.py:763] (0/8) Epoch 36, batch 550, loss[loss=0.1384, simple_loss=0.229, pruned_loss=0.02387, over 7064.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02929, over 1323342.19 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:28:22,081 INFO [train.py:763] (0/8) Epoch 36, batch 600, loss[loss=0.158, simple_loss=0.2475, pruned_loss=0.03427, over 7422.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02875, over 1348679.68 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:29:29,901 INFO [train.py:763] (0/8) Epoch 36, batch 650, loss[loss=0.1422, simple_loss=0.2314, pruned_loss=0.02655, over 7148.00 frames.], tot_loss[loss=0.1569, simple_loss=0.257, pruned_loss=0.02844, over 1367626.69 frames.], batch size: 17, lr: 2.11e-04
+2022-04-30 20:30:35,973 INFO [train.py:763] (0/8) Epoch 36, batch 700, loss[loss=0.1653, simple_loss=0.269, pruned_loss=0.03078, over 7235.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2572, pruned_loss=0.02855, over 1380410.52 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:31:41,366 INFO [train.py:763] (0/8) Epoch 36, batch 750, loss[loss=0.1651, simple_loss=0.2592, pruned_loss=0.03548, over 7162.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2571, pruned_loss=0.02887, over 1389318.27 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:32:47,561 INFO [train.py:763] (0/8) Epoch 36, batch 800, loss[loss=0.1505, simple_loss=0.2367, pruned_loss=0.0321, over 7407.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2568, pruned_loss=0.02915, over 1398851.89 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:33:53,520 INFO [train.py:763] (0/8) Epoch 36, batch 850, loss[loss=0.1649, simple_loss=0.2549, pruned_loss=0.03739, over 7263.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2578, pruned_loss=0.02945, over 1397642.80 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:34:59,129 INFO [train.py:763] (0/8) Epoch 36, batch 900, loss[loss=0.1601, simple_loss=0.256, pruned_loss=0.03208, over 7454.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2588, pruned_loss=0.02946, over 1406586.88 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:36:04,441 INFO [train.py:763] (0/8) Epoch 36, batch 950, loss[loss=0.1661, simple_loss=0.2555, pruned_loss=0.03836, over 7284.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.02965, over 1410080.35 frames.], batch size: 17, lr: 2.11e-04
+2022-04-30 20:37:09,733 INFO [train.py:763] (0/8) Epoch 36, batch 1000, loss[loss=0.1729, simple_loss=0.2655, pruned_loss=0.04016, over 6708.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.02914, over 1412718.03 frames.], batch size: 31, lr: 2.11e-04
+2022-04-30 20:38:15,276 INFO [train.py:763] (0/8) Epoch 36, batch 1050, loss[loss=0.17, simple_loss=0.2782, pruned_loss=0.0309, over 7360.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2584, pruned_loss=0.02891, over 1417748.80 frames.], batch size: 23, lr: 2.11e-04
+2022-04-30 20:39:20,508 INFO [train.py:763] (0/8) Epoch 36, batch 1100, loss[loss=0.1624, simple_loss=0.2654, pruned_loss=0.02971, over 7220.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2586, pruned_loss=0.02905, over 1418561.15 frames.], batch size: 21, lr: 2.11e-04
+2022-04-30 20:40:26,427 INFO [train.py:763] (0/8) Epoch 36, batch 1150, loss[loss=0.1721, simple_loss=0.2672, pruned_loss=0.03846, over 4825.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2584, pruned_loss=0.02926, over 1416903.75 frames.], batch size: 52, lr: 2.11e-04
+2022-04-30 20:41:32,757 INFO [train.py:763] (0/8) Epoch 36, batch 1200, loss[loss=0.1602, simple_loss=0.2672, pruned_loss=0.02657, over 7150.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2593, pruned_loss=0.02957, over 1419554.64 frames.], batch size: 20, lr: 2.11e-04
+2022-04-30 20:42:37,811 INFO [train.py:763] (0/8) Epoch 36, batch 1250, loss[loss=0.1872, simple_loss=0.2862, pruned_loss=0.04411, over 7209.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02933, over 1419854.73 frames.], batch size: 22, lr: 2.11e-04
+2022-04-30 20:43:42,986 INFO [train.py:763] (0/8) Epoch 36, batch 1300, loss[loss=0.1425, simple_loss=0.2359, pruned_loss=0.02461, over 7144.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2599, pruned_loss=0.02949, over 1422432.28 frames.], batch size: 17, lr: 2.11e-04
+2022-04-30 20:44:48,213 INFO [train.py:763] (0/8) Epoch 36, batch 1350, loss[loss=0.1547, simple_loss=0.2506, pruned_loss=0.0294, over 7063.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2601, pruned_loss=0.02981, over 1418329.31 frames.], batch size: 18, lr: 2.11e-04
+2022-04-30 20:45:54,985 INFO [train.py:763] (0/8) Epoch 36, batch 1400, loss[loss=0.1267, simple_loss=0.2178, pruned_loss=0.01779, over 6991.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2593, pruned_loss=0.02971, over 1417777.81 frames.], batch size: 16, lr: 2.11e-04
+2022-04-30 20:47:00,120 INFO [train.py:763] (0/8) Epoch 36, batch 1450, loss[loss=0.1578, simple_loss=0.2562, pruned_loss=0.02968, over 7289.00 frames.], tot_loss[loss=0.1588, simple_loss=0.259, pruned_loss=0.02933, over 1419170.39 frames.], batch size: 24, lr: 2.11e-04
+2022-04-30 20:48:05,227 INFO [train.py:763] (0/8) Epoch 36, batch 1500, loss[loss=0.1832, simple_loss=0.2874, pruned_loss=0.03947, over 7289.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2602, pruned_loss=0.02948, over 1416612.17 frames.], batch size: 24, lr: 2.11e-04
+2022-04-30 20:49:10,953 INFO [train.py:763] (0/8) Epoch 36, batch 1550, loss[loss=0.1751, simple_loss=0.2826, pruned_loss=0.03383, over 6704.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2602, pruned_loss=0.0295, over 1411158.12 frames.], batch size: 31, lr: 2.11e-04
+2022-04-30 20:50:16,851 INFO [train.py:763] (0/8) Epoch 36, batch 1600, loss[loss=0.1798, simple_loss=0.2808, pruned_loss=0.03941, over 7390.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2592, pruned_loss=0.02949, over 1411538.97 frames.], batch size: 23, lr: 2.11e-04
+2022-04-30 20:51:24,015 INFO [train.py:763] (0/8) Epoch 36, batch 1650, loss[loss=0.172, simple_loss=0.2742, pruned_loss=0.0349, over 7201.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.0295, over 1414421.79 frames.], batch size: 22, lr: 2.11e-04
+2022-04-30 20:52:38,233 INFO [train.py:763] (0/8) Epoch 36, batch 1700, loss[loss=0.1387, simple_loss=0.2366, pruned_loss=0.02037, over 7157.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02983, over 1413133.42 frames.], batch size: 19, lr: 2.11e-04
+2022-04-30 20:53:43,586 INFO [train.py:763] (0/8) Epoch 36, batch 1750, loss[loss=0.1731, simple_loss=0.274, pruned_loss=0.03613, over 7358.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2594, pruned_loss=0.02963, over 1406804.74 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 20:54:48,734 INFO [train.py:763] (0/8) Epoch 36, batch 1800, loss[loss=0.176, simple_loss=0.2731, pruned_loss=0.03947, over 7289.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2608, pruned_loss=0.02995, over 1409410.87 frames.], batch size: 24, lr: 2.10e-04
+2022-04-30 20:55:54,039 INFO [train.py:763] (0/8) Epoch 36, batch 1850, loss[loss=0.1393, simple_loss=0.2376, pruned_loss=0.02045, over 7271.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2596, pruned_loss=0.02971, over 1410589.41 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 20:56:59,662 INFO [train.py:763] (0/8) Epoch 36, batch 1900, loss[loss=0.1875, simple_loss=0.2911, pruned_loss=0.04192, over 6798.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2611, pruned_loss=0.02967, over 1416571.02 frames.], batch size: 31, lr: 2.10e-04
+2022-04-30 20:58:07,237 INFO [train.py:763] (0/8) Epoch 36, batch 1950, loss[loss=0.1584, simple_loss=0.2635, pruned_loss=0.02664, over 7222.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2602, pruned_loss=0.02932, over 1419681.11 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 20:59:14,634 INFO [train.py:763] (0/8) Epoch 36, batch 2000, loss[loss=0.1738, simple_loss=0.2728, pruned_loss=0.03738, over 7413.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2601, pruned_loss=0.02917, over 1416927.38 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:00:22,197 INFO [train.py:763] (0/8) Epoch 36, batch 2050, loss[loss=0.1867, simple_loss=0.284, pruned_loss=0.04474, over 7238.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2592, pruned_loss=0.02901, over 1419542.52 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:01:28,534 INFO [train.py:763] (0/8) Epoch 36, batch 2100, loss[loss=0.1658, simple_loss=0.2602, pruned_loss=0.03566, over 7140.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02903, over 1420002.71 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:02:35,093 INFO [train.py:763] (0/8) Epoch 36, batch 2150, loss[loss=0.1544, simple_loss=0.2592, pruned_loss=0.02479, over 7416.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2596, pruned_loss=0.02931, over 1417865.24 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:03:42,387 INFO [train.py:763] (0/8) Epoch 36, batch 2200, loss[loss=0.1546, simple_loss=0.2456, pruned_loss=0.03179, over 7263.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02941, over 1419734.60 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 21:04:49,056 INFO [train.py:763] (0/8) Epoch 36, batch 2250, loss[loss=0.1684, simple_loss=0.2762, pruned_loss=0.03034, over 7150.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2598, pruned_loss=0.0296, over 1420211.43 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:05:54,016 INFO [train.py:763] (0/8) Epoch 36, batch 2300, loss[loss=0.1838, simple_loss=0.2933, pruned_loss=0.03719, over 7199.00 frames.], tot_loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.02958, over 1420006.31 frames.], batch size: 23, lr: 2.10e-04
+2022-04-30 21:06:59,156 INFO [train.py:763] (0/8) Epoch 36, batch 2350, loss[loss=0.1233, simple_loss=0.215, pruned_loss=0.01577, over 7274.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03007, over 1413266.69 frames.], batch size: 17, lr: 2.10e-04
+2022-04-30 21:08:06,524 INFO [train.py:763] (0/8) Epoch 36, batch 2400, loss[loss=0.1752, simple_loss=0.2842, pruned_loss=0.03307, over 7316.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2586, pruned_loss=0.02949, over 1419406.82 frames.], batch size: 25, lr: 2.10e-04
+2022-04-30 21:09:12,594 INFO [train.py:763] (0/8) Epoch 36, batch 2450, loss[loss=0.1848, simple_loss=0.2877, pruned_loss=0.04095, over 7163.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2583, pruned_loss=0.02954, over 1424507.90 frames.], batch size: 26, lr: 2.10e-04
+2022-04-30 21:10:36,033 INFO [train.py:763] (0/8) Epoch 36, batch 2500, loss[loss=0.1459, simple_loss=0.2503, pruned_loss=0.02069, over 7155.00 frames.], tot_loss[loss=0.158, simple_loss=0.2579, pruned_loss=0.02902, over 1427116.57 frames.], batch size: 19, lr: 2.10e-04
+2022-04-30 21:11:41,256 INFO [train.py:763] (0/8) Epoch 36, batch 2550, loss[loss=0.181, simple_loss=0.2718, pruned_loss=0.04507, over 7287.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.02886, over 1427747.67 frames.], batch size: 24, lr: 2.10e-04
+2022-04-30 21:12:55,227 INFO [train.py:763] (0/8) Epoch 36, batch 2600, loss[loss=0.1341, simple_loss=0.2227, pruned_loss=0.02282, over 6788.00 frames.], tot_loss[loss=0.1584, simple_loss=0.259, pruned_loss=0.02893, over 1424832.88 frames.], batch size: 15, lr: 2.10e-04
+2022-04-30 21:14:18,388 INFO [train.py:763] (0/8) Epoch 36, batch 2650, loss[loss=0.1798, simple_loss=0.2864, pruned_loss=0.03661, over 7188.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2592, pruned_loss=0.02922, over 1427892.42 frames.], batch size: 22, lr: 2.10e-04
+2022-04-30 21:15:32,425 INFO [train.py:763] (0/8) Epoch 36, batch 2700, loss[loss=0.1635, simple_loss=0.2699, pruned_loss=0.02854, over 6338.00 frames.], tot_loss[loss=0.158, simple_loss=0.2585, pruned_loss=0.02879, over 1425177.59 frames.], batch size: 37, lr: 2.10e-04
+2022-04-30 21:16:46,243 INFO [train.py:763] (0/8) Epoch 36, batch 2750, loss[loss=0.221, simple_loss=0.3037, pruned_loss=0.06911, over 5009.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2596, pruned_loss=0.02904, over 1425245.41 frames.], batch size: 52, lr: 2.10e-04
+2022-04-30 21:17:52,040 INFO [train.py:763] (0/8) Epoch 36, batch 2800, loss[loss=0.1232, simple_loss=0.2149, pruned_loss=0.01573, over 7274.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2587, pruned_loss=0.02888, over 1429421.10 frames.], batch size: 18, lr: 2.10e-04
+2022-04-30 21:18:32,716 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-168000.pt
+2022-04-30 21:19:07,518 INFO [train.py:763] (0/8) Epoch 36, batch 2850, loss[loss=0.1589, simple_loss=0.2689, pruned_loss=0.02445, over 6390.00 frames.], tot_loss[loss=0.158, simple_loss=0.2588, pruned_loss=0.02861, over 1427675.75 frames.], batch size: 37, lr: 2.10e-04
+2022-04-30 21:20:12,997 INFO [train.py:763] (0/8) Epoch 36, batch 2900, loss[loss=0.1342, simple_loss=0.229, pruned_loss=0.01974, over 6985.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2586, pruned_loss=0.02826, over 1429099.62 frames.], batch size: 16, lr: 2.10e-04
+2022-04-30 21:21:20,755 INFO [train.py:763] (0/8) Epoch 36, batch 2950, loss[loss=0.1375, simple_loss=0.2384, pruned_loss=0.01828, over 7424.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2581, pruned_loss=0.02837, over 1424579.19 frames.], batch size: 20, lr: 2.10e-04
+2022-04-30 21:22:27,941 INFO [train.py:763] (0/8) Epoch 36, batch 3000, loss[loss=0.1654, simple_loss=0.2763, pruned_loss=0.02722, over 7226.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02893, over 1421775.84 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:22:27,942 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 21:22:43,065 INFO [train.py:792] (0/8) Epoch 36, validation: loss=0.1683, simple_loss=0.2628, pruned_loss=0.03692, over 698248.00 frames.
+2022-04-30 21:23:48,283 INFO [train.py:763] (0/8) Epoch 36, batch 3050, loss[loss=0.1315, simple_loss=0.2235, pruned_loss=0.01976, over 6831.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02943, over 1420770.64 frames.], batch size: 15, lr: 2.10e-04
+2022-04-30 21:24:54,044 INFO [train.py:763] (0/8) Epoch 36, batch 3100, loss[loss=0.1719, simple_loss=0.2714, pruned_loss=0.03619, over 7059.00 frames.], tot_loss[loss=0.159, simple_loss=0.2594, pruned_loss=0.02925, over 1419569.34 frames.], batch size: 18, lr: 2.10e-04
+2022-04-30 21:26:01,271 INFO [train.py:763] (0/8) Epoch 36, batch 3150, loss[loss=0.1429, simple_loss=0.2296, pruned_loss=0.02809, over 7003.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2591, pruned_loss=0.02918, over 1418834.90 frames.], batch size: 16, lr: 2.10e-04
+2022-04-30 21:27:07,751 INFO [train.py:763] (0/8) Epoch 36, batch 3200, loss[loss=0.1602, simple_loss=0.2515, pruned_loss=0.03444, over 4808.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02892, over 1418725.04 frames.], batch size: 52, lr: 2.10e-04
+2022-04-30 21:28:14,791 INFO [train.py:763] (0/8) Epoch 36, batch 3250, loss[loss=0.1912, simple_loss=0.2927, pruned_loss=0.04485, over 7194.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2578, pruned_loss=0.02858, over 1418752.34 frames.], batch size: 22, lr: 2.10e-04
+2022-04-30 21:29:20,189 INFO [train.py:763] (0/8) Epoch 36, batch 3300, loss[loss=0.1536, simple_loss=0.2607, pruned_loss=0.02327, over 7414.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02892, over 1415635.70 frames.], batch size: 21, lr: 2.10e-04
+2022-04-30 21:30:25,148 INFO [train.py:763] (0/8) Epoch 36, batch 3350, loss[loss=0.1779, simple_loss=0.2859, pruned_loss=0.03498, over 7376.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2599, pruned_loss=0.02936, over 1411772.19 frames.], batch size: 23, lr: 2.09e-04
+2022-04-30 21:31:31,788 INFO [train.py:763] (0/8) Epoch 36, batch 3400, loss[loss=0.1614, simple_loss=0.2569, pruned_loss=0.03293, over 7132.00 frames.], tot_loss[loss=0.1586, simple_loss=0.259, pruned_loss=0.02907, over 1416426.10 frames.], batch size: 17, lr: 2.09e-04
+2022-04-30 21:32:37,223 INFO [train.py:763] (0/8) Epoch 36, batch 3450, loss[loss=0.1441, simple_loss=0.2395, pruned_loss=0.02437, over 7298.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02927, over 1419088.31 frames.], batch size: 17, lr: 2.09e-04
+2022-04-30 21:33:42,453 INFO [train.py:763] (0/8) Epoch 36, batch 3500, loss[loss=0.1449, simple_loss=0.2492, pruned_loss=0.0203, over 7352.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2597, pruned_loss=0.02925, over 1417076.40 frames.], batch size: 19, lr: 2.09e-04
+2022-04-30 21:34:47,632 INFO [train.py:763] (0/8) Epoch 36, batch 3550, loss[loss=0.142, simple_loss=0.2316, pruned_loss=0.02623, over 6812.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02938, over 1414617.10 frames.], batch size: 15, lr: 2.09e-04
+2022-04-30 21:35:54,821 INFO [train.py:763] (0/8) Epoch 36, batch 3600, loss[loss=0.1456, simple_loss=0.2325, pruned_loss=0.02933, over 7004.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2581, pruned_loss=0.02909, over 1420957.87 frames.], batch size: 16, lr: 2.09e-04
+2022-04-30 21:37:01,777 INFO [train.py:763] (0/8) Epoch 36, batch 3650, loss[loss=0.1566, simple_loss=0.2561, pruned_loss=0.0286, over 7166.00 frames.], tot_loss[loss=0.1579, simple_loss=0.258, pruned_loss=0.02888, over 1422951.56 frames.], batch size: 19, lr: 2.09e-04
+2022-04-30 21:38:08,987 INFO [train.py:763] (0/8) Epoch 36, batch 3700, loss[loss=0.1727, simple_loss=0.2774, pruned_loss=0.03398, over 7225.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2585, pruned_loss=0.02913, over 1426534.17 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:39:14,214 INFO [train.py:763] (0/8) Epoch 36, batch 3750, loss[loss=0.1625, simple_loss=0.2594, pruned_loss=0.03281, over 7282.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02909, over 1423344.64 frames.], batch size: 24, lr: 2.09e-04
+2022-04-30 21:40:19,607 INFO [train.py:763] (0/8) Epoch 36, batch 3800, loss[loss=0.16, simple_loss=0.2491, pruned_loss=0.03542, over 7264.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2585, pruned_loss=0.02906, over 1424921.86 frames.], batch size: 17, lr: 2.09e-04
+2022-04-30 21:41:25,007 INFO [train.py:763] (0/8) Epoch 36, batch 3850, loss[loss=0.1829, simple_loss=0.2771, pruned_loss=0.04437, over 4902.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2587, pruned_loss=0.02921, over 1423487.48 frames.], batch size: 53, lr: 2.09e-04
+2022-04-30 21:42:30,260 INFO [train.py:763] (0/8) Epoch 36, batch 3900, loss[loss=0.1542, simple_loss=0.2555, pruned_loss=0.02642, over 7323.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2579, pruned_loss=0.02911, over 1425113.80 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:43:35,824 INFO [train.py:763] (0/8) Epoch 36, batch 3950, loss[loss=0.1623, simple_loss=0.246, pruned_loss=0.03929, over 7286.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2581, pruned_loss=0.02922, over 1426565.63 frames.], batch size: 18, lr: 2.09e-04
+2022-04-30 21:44:41,523 INFO [train.py:763] (0/8) Epoch 36, batch 4000, loss[loss=0.1686, simple_loss=0.2759, pruned_loss=0.03069, over 7144.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2584, pruned_loss=0.02908, over 1426912.97 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:45:48,404 INFO [train.py:763] (0/8) Epoch 36, batch 4050, loss[loss=0.1623, simple_loss=0.2767, pruned_loss=0.02392, over 7154.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2579, pruned_loss=0.0288, over 1425213.04 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:46:54,634 INFO [train.py:763] (0/8) Epoch 36, batch 4100, loss[loss=0.1483, simple_loss=0.2516, pruned_loss=0.02248, over 7325.00 frames.], tot_loss[loss=0.1583, simple_loss=0.259, pruned_loss=0.02879, over 1422492.22 frames.], batch size: 25, lr: 2.09e-04
+2022-04-30 21:48:00,285 INFO [train.py:763] (0/8) Epoch 36, batch 4150, loss[loss=0.1533, simple_loss=0.2541, pruned_loss=0.0263, over 7216.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2584, pruned_loss=0.02861, over 1424992.49 frames.], batch size: 21, lr: 2.09e-04
+2022-04-30 21:49:06,729 INFO [train.py:763] (0/8) Epoch 36, batch 4200, loss[loss=0.1631, simple_loss=0.2762, pruned_loss=0.02502, over 7337.00 frames.], tot_loss[loss=0.1574, simple_loss=0.258, pruned_loss=0.02843, over 1427431.94 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:50:13,182 INFO [train.py:763] (0/8) Epoch 36, batch 4250, loss[loss=0.1792, simple_loss=0.2772, pruned_loss=0.04056, over 7205.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2575, pruned_loss=0.02861, over 1430482.84 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:51:18,751 INFO [train.py:763] (0/8) Epoch 36, batch 4300, loss[loss=0.1637, simple_loss=0.2686, pruned_loss=0.02937, over 7322.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.02923, over 1423658.50 frames.], batch size: 20, lr: 2.09e-04
+2022-04-30 21:52:24,309 INFO [train.py:763] (0/8) Epoch 36, batch 4350, loss[loss=0.1737, simple_loss=0.2854, pruned_loss=0.03101, over 7324.00 frames.], tot_loss[loss=0.158, simple_loss=0.258, pruned_loss=0.02899, over 1428525.12 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:53:30,990 INFO [train.py:763] (0/8) Epoch 36, batch 4400, loss[loss=0.145, simple_loss=0.2581, pruned_loss=0.01599, over 7336.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2579, pruned_loss=0.02875, over 1420122.77 frames.], batch size: 22, lr: 2.09e-04
+2022-04-30 21:54:38,271 INFO [train.py:763] (0/8) Epoch 36, batch 4450, loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03173, over 7428.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2587, pruned_loss=0.02932, over 1419496.38 frames.], batch size: 18, lr: 2.09e-04
+2022-04-30 21:55:43,449 INFO [train.py:763] (0/8) Epoch 36, batch 4500, loss[loss=0.1409, simple_loss=0.2351, pruned_loss=0.02337, over 7273.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2587, pruned_loss=0.02935, over 1415076.69 frames.], batch size: 18, lr: 2.09e-04
+2022-04-30 21:56:47,994 INFO [train.py:763] (0/8) Epoch 36, batch 4550, loss[loss=0.161, simple_loss=0.2567, pruned_loss=0.03266, over 6254.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2593, pruned_loss=0.02977, over 1390358.79 frames.], batch size: 37, lr: 2.09e-04
+2022-04-30 21:57:37,281 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-36.pt
+2022-04-30 21:58:07,232 INFO [train.py:763] (0/8) Epoch 37, batch 0, loss[loss=0.1525, simple_loss=0.2546, pruned_loss=0.02523, over 7360.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2546, pruned_loss=0.02523, over 7360.00 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 21:59:13,883 INFO [train.py:763] (0/8) Epoch 37, batch 50, loss[loss=0.1684, simple_loss=0.2762, pruned_loss=0.03029, over 6390.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2529, pruned_loss=0.02685, over 322703.19 frames.], batch size: 37, lr: 2.06e-04
+2022-04-30 22:00:20,507 INFO [train.py:763] (0/8) Epoch 37, batch 100, loss[loss=0.142, simple_loss=0.246, pruned_loss=0.01902, over 7252.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2569, pruned_loss=0.02794, over 559985.05 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 22:01:27,284 INFO [train.py:763] (0/8) Epoch 37, batch 150, loss[loss=0.1827, simple_loss=0.2775, pruned_loss=0.04398, over 7385.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2589, pruned_loss=0.02849, over 747832.33 frames.], batch size: 23, lr: 2.06e-04
+2022-04-30 22:02:34,178 INFO [train.py:763] (0/8) Epoch 37, batch 200, loss[loss=0.1455, simple_loss=0.2492, pruned_loss=0.02092, over 7405.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2582, pruned_loss=0.02849, over 897274.56 frames.], batch size: 21, lr: 2.06e-04
+2022-04-30 22:03:39,634 INFO [train.py:763] (0/8) Epoch 37, batch 250, loss[loss=0.1509, simple_loss=0.2465, pruned_loss=0.02771, over 7361.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02846, over 1015983.74 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 22:04:45,211 INFO [train.py:763] (0/8) Epoch 37, batch 300, loss[loss=0.1626, simple_loss=0.2685, pruned_loss=0.02839, over 7245.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2588, pruned_loss=0.0289, over 1105513.88 frames.], batch size: 20, lr: 2.06e-04
+2022-04-30 22:05:51,659 INFO [train.py:763] (0/8) Epoch 37, batch 350, loss[loss=0.131, simple_loss=0.2227, pruned_loss=0.01961, over 7257.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.0283, over 1173744.75 frames.], batch size: 19, lr: 2.06e-04
+2022-04-30 22:06:57,564 INFO [train.py:763] (0/8) Epoch 37, batch 400, loss[loss=0.1223, simple_loss=0.2138, pruned_loss=0.01541, over 7281.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02874, over 1233582.42 frames.], batch size: 17, lr: 2.06e-04
+2022-04-30 22:08:03,018 INFO [train.py:763] (0/8) Epoch 37, batch 450, loss[loss=0.1555, simple_loss=0.2591, pruned_loss=0.0259, over 7111.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2581, pruned_loss=0.02858, over 1276570.49 frames.], batch size: 21, lr: 2.06e-04
+2022-04-30 22:09:09,223 INFO [train.py:763] (0/8) Epoch 37, batch 500, loss[loss=0.1452, simple_loss=0.2297, pruned_loss=0.03033, over 7263.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2572, pruned_loss=0.02855, over 1312545.90 frames.], batch size: 18, lr: 2.06e-04
+2022-04-30 22:10:16,147 INFO [train.py:763] (0/8) Epoch 37, batch 550, loss[loss=0.1441, simple_loss=0.2495, pruned_loss=0.01936, over 7331.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2574, pruned_loss=0.02851, over 1336243.96 frames.], batch size: 20, lr: 2.06e-04
+2022-04-30 22:11:22,965 INFO [train.py:763] (0/8) Epoch 37, batch 600, loss[loss=0.18, simple_loss=0.2877, pruned_loss=0.03611, over 7363.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02855, over 1358118.05 frames.], batch size: 23, lr: 2.06e-04
+2022-04-30 22:12:30,636 INFO [train.py:763] (0/8) Epoch 37, batch 650, loss[loss=0.1726, simple_loss=0.2805, pruned_loss=0.03229, over 7334.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2591, pruned_loss=0.02862, over 1373938.27 frames.], batch size: 22, lr: 2.06e-04
+2022-04-30 22:13:38,158 INFO [train.py:763] (0/8) Epoch 37, batch 700, loss[loss=0.1537, simple_loss=0.2578, pruned_loss=0.02482, over 7148.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2587, pruned_loss=0.02846, over 1386615.45 frames.], batch size: 18, lr: 2.06e-04
+2022-04-30 22:14:45,732 INFO [train.py:763] (0/8) Epoch 37, batch 750, loss[loss=0.1711, simple_loss=0.2713, pruned_loss=0.03543, over 7380.00 frames.], tot_loss[loss=0.158, simple_loss=0.2592, pruned_loss=0.02841, over 1401273.06 frames.], batch size: 23, lr: 2.05e-04
+2022-04-30 22:15:51,458 INFO [train.py:763] (0/8) Epoch 37, batch 800, loss[loss=0.1344, simple_loss=0.2226, pruned_loss=0.02304, over 7391.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2586, pruned_loss=0.02805, over 1408925.14 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:16:56,742 INFO [train.py:763] (0/8) Epoch 37, batch 850, loss[loss=0.1437, simple_loss=0.2433, pruned_loss=0.02207, over 7361.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2586, pruned_loss=0.02803, over 1411246.02 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:18:02,422 INFO [train.py:763] (0/8) Epoch 37, batch 900, loss[loss=0.2003, simple_loss=0.303, pruned_loss=0.04881, over 7292.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2583, pruned_loss=0.02823, over 1413442.92 frames.], batch size: 24, lr: 2.05e-04
+2022-04-30 22:19:07,699 INFO [train.py:763] (0/8) Epoch 37, batch 950, loss[loss=0.1326, simple_loss=0.2324, pruned_loss=0.0164, over 7260.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2592, pruned_loss=0.02866, over 1418590.23 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:20:12,879 INFO [train.py:763] (0/8) Epoch 37, batch 1000, loss[loss=0.1648, simple_loss=0.2691, pruned_loss=0.03025, over 7213.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2596, pruned_loss=0.02892, over 1421467.12 frames.], batch size: 22, lr: 2.05e-04
+2022-04-30 22:21:18,162 INFO [train.py:763] (0/8) Epoch 37, batch 1050, loss[loss=0.1414, simple_loss=0.2519, pruned_loss=0.01543, over 7341.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2597, pruned_loss=0.02882, over 1422271.22 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:22:25,737 INFO [train.py:763] (0/8) Epoch 37, batch 1100, loss[loss=0.1424, simple_loss=0.2412, pruned_loss=0.02176, over 6780.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2597, pruned_loss=0.02895, over 1425514.96 frames.], batch size: 15, lr: 2.05e-04
+2022-04-30 22:23:31,646 INFO [train.py:763] (0/8) Epoch 37, batch 1150, loss[loss=0.1492, simple_loss=0.2443, pruned_loss=0.02706, over 7264.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2599, pruned_loss=0.02895, over 1422327.60 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:24:36,970 INFO [train.py:763] (0/8) Epoch 37, batch 1200, loss[loss=0.1665, simple_loss=0.2714, pruned_loss=0.03082, over 7230.00 frames.], tot_loss[loss=0.1589, simple_loss=0.26, pruned_loss=0.02891, over 1423655.69 frames.], batch size: 26, lr: 2.05e-04
+2022-04-30 22:25:43,869 INFO [train.py:763] (0/8) Epoch 37, batch 1250, loss[loss=0.1826, simple_loss=0.2773, pruned_loss=0.04394, over 6403.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2597, pruned_loss=0.02874, over 1426760.38 frames.], batch size: 37, lr: 2.05e-04
+2022-04-30 22:26:50,674 INFO [train.py:763] (0/8) Epoch 37, batch 1300, loss[loss=0.1384, simple_loss=0.2359, pruned_loss=0.02049, over 7297.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2606, pruned_loss=0.02937, over 1426025.39 frames.], batch size: 17, lr: 2.05e-04
+2022-04-30 22:27:56,063 INFO [train.py:763] (0/8) Epoch 37, batch 1350, loss[loss=0.1592, simple_loss=0.2598, pruned_loss=0.02928, over 7112.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2598, pruned_loss=0.02941, over 1419607.21 frames.], batch size: 21, lr: 2.05e-04
+2022-04-30 22:29:02,061 INFO [train.py:763] (0/8) Epoch 37, batch 1400, loss[loss=0.1762, simple_loss=0.2754, pruned_loss=0.03851, over 7278.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2595, pruned_loss=0.02947, over 1419543.55 frames.], batch size: 24, lr: 2.05e-04
+2022-04-30 22:30:07,332 INFO [train.py:763] (0/8) Epoch 37, batch 1450, loss[loss=0.1676, simple_loss=0.2806, pruned_loss=0.02732, over 7207.00 frames.], tot_loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.02961, over 1424706.30 frames.], batch size: 22, lr: 2.05e-04
+2022-04-30 22:31:13,186 INFO [train.py:763] (0/8) Epoch 37, batch 1500, loss[loss=0.1774, simple_loss=0.2858, pruned_loss=0.03452, over 7275.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2597, pruned_loss=0.02923, over 1425181.02 frames.], batch size: 25, lr: 2.05e-04
+2022-04-30 22:32:18,525 INFO [train.py:763] (0/8) Epoch 37, batch 1550, loss[loss=0.1732, simple_loss=0.2761, pruned_loss=0.03519, over 7233.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2601, pruned_loss=0.02941, over 1422938.69 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:33:23,886 INFO [train.py:763] (0/8) Epoch 37, batch 1600, loss[loss=0.1504, simple_loss=0.2504, pruned_loss=0.02519, over 7267.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2598, pruned_loss=0.02917, over 1425788.98 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:34:29,223 INFO [train.py:763] (0/8) Epoch 37, batch 1650, loss[loss=0.1755, simple_loss=0.2833, pruned_loss=0.03381, over 6965.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2592, pruned_loss=0.02883, over 1424515.16 frames.], batch size: 28, lr: 2.05e-04
+2022-04-30 22:35:34,595 INFO [train.py:763] (0/8) Epoch 37, batch 1700, loss[loss=0.1612, simple_loss=0.2662, pruned_loss=0.02807, over 7156.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2582, pruned_loss=0.02882, over 1422449.75 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:36:40,249 INFO [train.py:763] (0/8) Epoch 37, batch 1750, loss[loss=0.1845, simple_loss=0.2801, pruned_loss=0.0445, over 5350.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02884, over 1422028.98 frames.], batch size: 52, lr: 2.05e-04
+2022-04-30 22:37:45,573 INFO [train.py:763] (0/8) Epoch 37, batch 1800, loss[loss=0.1498, simple_loss=0.2533, pruned_loss=0.02316, over 7328.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2576, pruned_loss=0.02849, over 1420075.29 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:38:50,832 INFO [train.py:763] (0/8) Epoch 37, batch 1850, loss[loss=0.1409, simple_loss=0.2357, pruned_loss=0.02307, over 7286.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02842, over 1421355.99 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:39:57,183 INFO [train.py:763] (0/8) Epoch 37, batch 1900, loss[loss=0.1646, simple_loss=0.2603, pruned_loss=0.03438, over 6796.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2588, pruned_loss=0.02893, over 1424173.60 frames.], batch size: 15, lr: 2.05e-04
+2022-04-30 22:41:04,602 INFO [train.py:763] (0/8) Epoch 37, batch 1950, loss[loss=0.1484, simple_loss=0.253, pruned_loss=0.02191, over 7257.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2595, pruned_loss=0.0292, over 1427086.22 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:42:12,277 INFO [train.py:763] (0/8) Epoch 37, batch 2000, loss[loss=0.1592, simple_loss=0.2553, pruned_loss=0.03154, over 7423.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2585, pruned_loss=0.0293, over 1426927.25 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:43:17,405 INFO [train.py:763] (0/8) Epoch 37, batch 2050, loss[loss=0.1785, simple_loss=0.2647, pruned_loss=0.04616, over 7254.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2595, pruned_loss=0.02947, over 1424023.43 frames.], batch size: 19, lr: 2.05e-04
+2022-04-30 22:44:22,377 INFO [train.py:763] (0/8) Epoch 37, batch 2100, loss[loss=0.1595, simple_loss=0.261, pruned_loss=0.02901, over 7152.00 frames.], tot_loss[loss=0.1595, simple_loss=0.26, pruned_loss=0.02954, over 1417944.58 frames.], batch size: 26, lr: 2.05e-04
+2022-04-30 22:45:27,591 INFO [train.py:763] (0/8) Epoch 37, batch 2150, loss[loss=0.1422, simple_loss=0.2391, pruned_loss=0.02264, over 7079.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2598, pruned_loss=0.02934, over 1418396.76 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:46:32,468 INFO [train.py:763] (0/8) Epoch 37, batch 2200, loss[loss=0.1345, simple_loss=0.231, pruned_loss=0.01901, over 7078.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2603, pruned_loss=0.02918, over 1418866.32 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:47:37,568 INFO [train.py:763] (0/8) Epoch 37, batch 2250, loss[loss=0.176, simple_loss=0.2773, pruned_loss=0.03739, over 6279.00 frames.], tot_loss[loss=0.1591, simple_loss=0.26, pruned_loss=0.02913, over 1418590.22 frames.], batch size: 37, lr: 2.05e-04
+2022-04-30 22:48:44,668 INFO [train.py:763] (0/8) Epoch 37, batch 2300, loss[loss=0.1583, simple_loss=0.251, pruned_loss=0.03282, over 7074.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2597, pruned_loss=0.02879, over 1422231.64 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:49:50,012 INFO [train.py:763] (0/8) Epoch 37, batch 2350, loss[loss=0.1481, simple_loss=0.2479, pruned_loss=0.02409, over 7321.00 frames.], tot_loss[loss=0.158, simple_loss=0.2591, pruned_loss=0.02847, over 1419352.49 frames.], batch size: 20, lr: 2.05e-04
+2022-04-30 22:50:55,504 INFO [train.py:763] (0/8) Epoch 37, batch 2400, loss[loss=0.1381, simple_loss=0.2292, pruned_loss=0.02349, over 7413.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02867, over 1424402.57 frames.], batch size: 18, lr: 2.05e-04
+2022-04-30 22:52:02,209 INFO [train.py:763] (0/8) Epoch 37, batch 2450, loss[loss=0.1809, simple_loss=0.2865, pruned_loss=0.03765, over 7314.00 frames.], tot_loss[loss=0.158, simple_loss=0.2591, pruned_loss=0.02845, over 1427101.64 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 22:53:07,504 INFO [train.py:763] (0/8) Epoch 37, batch 2500, loss[loss=0.1629, simple_loss=0.2555, pruned_loss=0.03511, over 7164.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.02879, over 1427339.42 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 22:54:13,279 INFO [train.py:763] (0/8) Epoch 37, batch 2550, loss[loss=0.1464, simple_loss=0.2432, pruned_loss=0.02481, over 7159.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.0288, over 1425275.47 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 22:55:19,543 INFO [train.py:763] (0/8) Epoch 37, batch 2600, loss[loss=0.1318, simple_loss=0.2341, pruned_loss=0.01474, over 7426.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2584, pruned_loss=0.02867, over 1424645.55 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 22:56:24,708 INFO [train.py:763] (0/8) Epoch 37, batch 2650, loss[loss=0.1661, simple_loss=0.2707, pruned_loss=0.03073, over 7194.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2587, pruned_loss=0.0288, over 1425334.40 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 22:57:30,431 INFO [train.py:763] (0/8) Epoch 37, batch 2700, loss[loss=0.1694, simple_loss=0.2777, pruned_loss=0.03054, over 7230.00 frames.], tot_loss[loss=0.158, simple_loss=0.2585, pruned_loss=0.02871, over 1423781.52 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 22:58:35,700 INFO [train.py:763] (0/8) Epoch 37, batch 2750, loss[loss=0.1644, simple_loss=0.2648, pruned_loss=0.03194, over 7360.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02852, over 1424975.84 frames.], batch size: 19, lr: 2.04e-04
+2022-04-30 22:59:42,061 INFO [train.py:763] (0/8) Epoch 37, batch 2800, loss[loss=0.1596, simple_loss=0.259, pruned_loss=0.03006, over 7278.00 frames.], tot_loss[loss=0.1577, simple_loss=0.258, pruned_loss=0.02865, over 1423172.92 frames.], batch size: 24, lr: 2.04e-04
+2022-04-30 23:00:49,141 INFO [train.py:763] (0/8) Epoch 37, batch 2850, loss[loss=0.1611, simple_loss=0.2606, pruned_loss=0.03076, over 7415.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2578, pruned_loss=0.02854, over 1423227.71 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:01:56,139 INFO [train.py:763] (0/8) Epoch 37, batch 2900, loss[loss=0.1456, simple_loss=0.2378, pruned_loss=0.02667, over 7137.00 frames.], tot_loss[loss=0.1576, simple_loss=0.258, pruned_loss=0.02861, over 1423608.72 frames.], batch size: 17, lr: 2.04e-04
+2022-04-30 23:03:03,262 INFO [train.py:763] (0/8) Epoch 37, batch 2950, loss[loss=0.1258, simple_loss=0.2178, pruned_loss=0.01693, over 7411.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2581, pruned_loss=0.02869, over 1428658.78 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 23:04:10,181 INFO [train.py:763] (0/8) Epoch 37, batch 3000, loss[loss=0.1708, simple_loss=0.2718, pruned_loss=0.03488, over 7197.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2579, pruned_loss=0.02869, over 1428058.98 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 23:04:10,182 INFO [train.py:783] (0/8) Computing validation loss
+2022-04-30 23:04:25,434 INFO [train.py:792] (0/8) Epoch 37, validation: loss=0.1692, simple_loss=0.2632, pruned_loss=0.03757, over 698248.00 frames.
+2022-04-30 23:05:32,519 INFO [train.py:763] (0/8) Epoch 37, batch 3050, loss[loss=0.1601, simple_loss=0.2525, pruned_loss=0.03384, over 7165.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2586, pruned_loss=0.02896, over 1427980.97 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 23:06:38,296 INFO [train.py:763] (0/8) Epoch 37, batch 3100, loss[loss=0.1686, simple_loss=0.2726, pruned_loss=0.03229, over 7208.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.0285, over 1421301.77 frames.], batch size: 22, lr: 2.04e-04
+2022-04-30 23:07:53,071 INFO [train.py:763] (0/8) Epoch 37, batch 3150, loss[loss=0.1781, simple_loss=0.2856, pruned_loss=0.03529, over 7375.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2584, pruned_loss=0.02845, over 1419957.48 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 23:08:58,938 INFO [train.py:763] (0/8) Epoch 37, batch 3200, loss[loss=0.1583, simple_loss=0.2687, pruned_loss=0.02401, over 7115.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2578, pruned_loss=0.02861, over 1425060.81 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:10:06,291 INFO [train.py:763] (0/8) Epoch 37, batch 3250, loss[loss=0.1379, simple_loss=0.2253, pruned_loss=0.02525, over 7274.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2577, pruned_loss=0.02875, over 1425771.98 frames.], batch size: 18, lr: 2.04e-04
+2022-04-30 23:11:13,126 INFO [train.py:763] (0/8) Epoch 37, batch 3300, loss[loss=0.1612, simple_loss=0.266, pruned_loss=0.02819, over 7226.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2577, pruned_loss=0.02874, over 1425358.74 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:12:18,277 INFO [train.py:763] (0/8) Epoch 37, batch 3350, loss[loss=0.1827, simple_loss=0.2853, pruned_loss=0.04007, over 7207.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2602, pruned_loss=0.02957, over 1426385.74 frames.], batch size: 22, lr: 2.04e-04
+2022-04-30 23:13:23,569 INFO [train.py:763] (0/8) Epoch 37, batch 3400, loss[loss=0.1538, simple_loss=0.2595, pruned_loss=0.02404, over 6667.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02941, over 1430059.05 frames.], batch size: 31, lr: 2.04e-04
+2022-04-30 23:14:28,973 INFO [train.py:763] (0/8) Epoch 37, batch 3450, loss[loss=0.1325, simple_loss=0.2318, pruned_loss=0.01658, over 7431.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.0297, over 1432074.98 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:15:34,300 INFO [train.py:763] (0/8) Epoch 37, batch 3500, loss[loss=0.157, simple_loss=0.2569, pruned_loss=0.02856, over 7232.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2598, pruned_loss=0.02917, over 1430479.47 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:16:39,550 INFO [train.py:763] (0/8) Epoch 37, batch 3550, loss[loss=0.1672, simple_loss=0.2702, pruned_loss=0.03206, over 7150.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2609, pruned_loss=0.02958, over 1431084.04 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:17:44,643 INFO [train.py:763] (0/8) Epoch 37, batch 3600, loss[loss=0.1865, simple_loss=0.2816, pruned_loss=0.04565, over 6801.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2612, pruned_loss=0.02992, over 1429003.14 frames.], batch size: 31, lr: 2.04e-04
+2022-04-30 23:18:50,221 INFO [train.py:763] (0/8) Epoch 37, batch 3650, loss[loss=0.1596, simple_loss=0.2646, pruned_loss=0.02731, over 7066.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2601, pruned_loss=0.02926, over 1431267.54 frames.], batch size: 28, lr: 2.04e-04
+2022-04-30 23:19:55,916 INFO [train.py:763] (0/8) Epoch 37, batch 3700, loss[loss=0.1658, simple_loss=0.268, pruned_loss=0.03181, over 7251.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2598, pruned_loss=0.02933, over 1422837.37 frames.], batch size: 24, lr: 2.04e-04
+2022-04-30 23:21:00,950 INFO [train.py:763] (0/8) Epoch 37, batch 3750, loss[loss=0.1527, simple_loss=0.2614, pruned_loss=0.02202, over 7160.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2599, pruned_loss=0.0292, over 1417966.15 frames.], batch size: 19, lr: 2.04e-04
+2022-04-30 23:22:07,065 INFO [train.py:763] (0/8) Epoch 37, batch 3800, loss[loss=0.1701, simple_loss=0.2712, pruned_loss=0.03446, over 7355.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2592, pruned_loss=0.02913, over 1417963.29 frames.], batch size: 23, lr: 2.04e-04
+2022-04-30 23:23:12,321 INFO [train.py:763] (0/8) Epoch 37, batch 3850, loss[loss=0.1554, simple_loss=0.253, pruned_loss=0.02891, over 7104.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02858, over 1420341.79 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:24:18,026 INFO [train.py:763] (0/8) Epoch 37, batch 3900, loss[loss=0.1627, simple_loss=0.2603, pruned_loss=0.03259, over 7330.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2582, pruned_loss=0.02907, over 1421911.08 frames.], batch size: 20, lr: 2.04e-04
+2022-04-30 23:25:32,662 INFO [train.py:763] (0/8) Epoch 37, batch 3950, loss[loss=0.1854, simple_loss=0.2839, pruned_loss=0.0434, over 7208.00 frames.], tot_loss[loss=0.158, simple_loss=0.258, pruned_loss=0.02899, over 1416442.25 frames.], batch size: 22, lr: 2.04e-04
+2022-04-30 23:26:37,880 INFO [train.py:763] (0/8) Epoch 37, batch 4000, loss[loss=0.1406, simple_loss=0.2403, pruned_loss=0.02046, over 7155.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2577, pruned_loss=0.02882, over 1417071.58 frames.], batch size: 19, lr: 2.04e-04
+2022-04-30 23:28:01,973 INFO [train.py:763] (0/8) Epoch 37, batch 4050, loss[loss=0.1469, simple_loss=0.2365, pruned_loss=0.02864, over 7293.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2573, pruned_loss=0.0287, over 1411953.87 frames.], batch size: 17, lr: 2.04e-04
+2022-04-30 23:29:07,118 INFO [train.py:763] (0/8) Epoch 37, batch 4100, loss[loss=0.1633, simple_loss=0.2656, pruned_loss=0.03047, over 7221.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2581, pruned_loss=0.02862, over 1413467.72 frames.], batch size: 21, lr: 2.04e-04
+2022-04-30 23:30:21,710 INFO [train.py:763] (0/8) Epoch 37, batch 4150, loss[loss=0.1481, simple_loss=0.2486, pruned_loss=0.02373, over 7258.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2568, pruned_loss=0.0284, over 1413227.47 frames.], batch size: 19, lr: 2.03e-04
+2022-04-30 23:31:36,373 INFO [train.py:763] (0/8) Epoch 37, batch 4200, loss[loss=0.1598, simple_loss=0.2674, pruned_loss=0.02614, over 7295.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2571, pruned_loss=0.02817, over 1413993.49 frames.], batch size: 24, lr: 2.03e-04
+2022-04-30 23:32:51,955 INFO [train.py:763] (0/8) Epoch 37, batch 4250, loss[loss=0.1533, simple_loss=0.2536, pruned_loss=0.02654, over 7234.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2574, pruned_loss=0.0285, over 1413776.99 frames.], batch size: 20, lr: 2.03e-04
+2022-04-30 23:33:58,670 INFO [train.py:763] (0/8) Epoch 37, batch 4300, loss[loss=0.1987, simple_loss=0.2879, pruned_loss=0.05481, over 5199.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2562, pruned_loss=0.02841, over 1411660.84 frames.], batch size: 54, lr: 2.03e-04
+2022-04-30 23:35:04,838 INFO [train.py:763] (0/8) Epoch 37, batch 4350, loss[loss=0.1386, simple_loss=0.2284, pruned_loss=0.02444, over 6993.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2556, pruned_loss=0.02841, over 1413736.09 frames.], batch size: 16, lr: 2.03e-04
+2022-04-30 23:36:10,341 INFO [train.py:763] (0/8) Epoch 37, batch 4400, loss[loss=0.1482, simple_loss=0.241, pruned_loss=0.02773, over 7171.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2554, pruned_loss=0.02819, over 1414665.68 frames.], batch size: 16, lr: 2.03e-04
+2022-04-30 23:37:17,180 INFO [train.py:763] (0/8) Epoch 37, batch 4450, loss[loss=0.1394, simple_loss=0.2329, pruned_loss=0.02294, over 6858.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2553, pruned_loss=0.02851, over 1406997.30 frames.], batch size: 15, lr: 2.03e-04
+2022-04-30 23:38:22,789 INFO [train.py:763] (0/8) Epoch 37, batch 4500, loss[loss=0.1686, simple_loss=0.2697, pruned_loss=0.03377, over 6437.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2559, pruned_loss=0.02881, over 1383396.28 frames.], batch size: 38, lr: 2.03e-04
+2022-04-30 23:39:28,702 INFO [train.py:763] (0/8) Epoch 37, batch 4550, loss[loss=0.1748, simple_loss=0.2647, pruned_loss=0.04247, over 5045.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2559, pruned_loss=0.02931, over 1356003.04 frames.], batch size: 52, lr: 2.03e-04
+2022-04-30 23:40:19,344 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-37.pt
+2022-04-30 23:40:56,598 INFO [train.py:763] (0/8) Epoch 38, batch 0, loss[loss=0.1736, simple_loss=0.2788, pruned_loss=0.03419, over 7266.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2788, pruned_loss=0.03419, over 7266.00 frames.], batch size: 19, lr: 2.01e-04
+2022-04-30 23:42:03,208 INFO [train.py:763] (0/8) Epoch 38, batch 50, loss[loss=0.1587, simple_loss=0.2664, pruned_loss=0.02554, over 7154.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2603, pruned_loss=0.02927, over 320385.83 frames.], batch size: 20, lr: 2.01e-04
+2022-04-30 23:43:10,054 INFO [train.py:763] (0/8) Epoch 38, batch 100, loss[loss=0.1572, simple_loss=0.2623, pruned_loss=0.02609, over 6817.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03043, over 565509.94 frames.], batch size: 31, lr: 2.01e-04
+2022-04-30 23:44:16,794 INFO [train.py:763] (0/8) Epoch 38, batch 150, loss[loss=0.1593, simple_loss=0.2662, pruned_loss=0.02621, over 7158.00 frames.], tot_loss[loss=0.158, simple_loss=0.2572, pruned_loss=0.02944, over 754640.63 frames.], batch size: 18, lr: 2.01e-04
+2022-04-30 23:45:22,777 INFO [train.py:763] (0/8) Epoch 38, batch 200, loss[loss=0.1562, simple_loss=0.2475, pruned_loss=0.03243, over 7427.00 frames.], tot_loss[loss=0.159, simple_loss=0.2589, pruned_loss=0.0296, over 902197.90 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:46:29,139 INFO [train.py:763] (0/8) Epoch 38, batch 250, loss[loss=0.1659, simple_loss=0.2666, pruned_loss=0.03255, over 6413.00 frames.], tot_loss[loss=0.1591, simple_loss=0.259, pruned_loss=0.02963, over 1017706.64 frames.], batch size: 38, lr: 2.00e-04
+2022-04-30 23:47:35,369 INFO [train.py:763] (0/8) Epoch 38, batch 300, loss[loss=0.1565, simple_loss=0.2656, pruned_loss=0.02369, over 7421.00 frames.], tot_loss[loss=0.158, simple_loss=0.2581, pruned_loss=0.02896, over 1113005.79 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:48:41,450 INFO [train.py:763] (0/8) Epoch 38, batch 350, loss[loss=0.1806, simple_loss=0.2871, pruned_loss=0.03706, over 7265.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2582, pruned_loss=0.02885, over 1180429.17 frames.], batch size: 24, lr: 2.00e-04
+2022-04-30 23:49:47,448 INFO [train.py:763] (0/8) Epoch 38, batch 400, loss[loss=0.1609, simple_loss=0.2633, pruned_loss=0.02928, over 7221.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2584, pruned_loss=0.02907, over 1230374.08 frames.], batch size: 21, lr: 2.00e-04
+2022-04-30 23:50:53,878 INFO [train.py:763] (0/8) Epoch 38, batch 450, loss[loss=0.1613, simple_loss=0.2624, pruned_loss=0.0301, over 7192.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2581, pruned_loss=0.02922, over 1274852.69 frames.], batch size: 23, lr: 2.00e-04
+2022-04-30 23:52:00,166 INFO [train.py:763] (0/8) Epoch 38, batch 500, loss[loss=0.1561, simple_loss=0.2673, pruned_loss=0.02247, over 7141.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2579, pruned_loss=0.02923, over 1302134.81 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:53:06,417 INFO [train.py:763] (0/8) Epoch 38, batch 550, loss[loss=0.1526, simple_loss=0.2518, pruned_loss=0.02666, over 7432.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2574, pruned_loss=0.02893, over 1327051.78 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:54:12,149 INFO [train.py:763] (0/8) Epoch 38, batch 600, loss[loss=0.1396, simple_loss=0.2443, pruned_loss=0.01745, over 7163.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2575, pruned_loss=0.02852, over 1345771.94 frames.], batch size: 18, lr: 2.00e-04
+2022-04-30 23:55:17,891 INFO [train.py:763] (0/8) Epoch 38, batch 650, loss[loss=0.1453, simple_loss=0.2301, pruned_loss=0.0303, over 7296.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2573, pruned_loss=0.02845, over 1365067.20 frames.], batch size: 17, lr: 2.00e-04
+2022-04-30 23:56:23,415 INFO [train.py:763] (0/8) Epoch 38, batch 700, loss[loss=0.1301, simple_loss=0.2148, pruned_loss=0.02271, over 7239.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2566, pruned_loss=0.02835, over 1378852.97 frames.], batch size: 16, lr: 2.00e-04
+2022-04-30 23:57:28,965 INFO [train.py:763] (0/8) Epoch 38, batch 750, loss[loss=0.1561, simple_loss=0.2636, pruned_loss=0.02428, over 6345.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2561, pruned_loss=0.02773, over 1387586.31 frames.], batch size: 37, lr: 2.00e-04
+2022-04-30 23:58:35,121 INFO [train.py:763] (0/8) Epoch 38, batch 800, loss[loss=0.1558, simple_loss=0.2598, pruned_loss=0.02593, over 7234.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2565, pruned_loss=0.02784, over 1399886.82 frames.], batch size: 20, lr: 2.00e-04
+2022-04-30 23:59:41,186 INFO [train.py:763] (0/8) Epoch 38, batch 850, loss[loss=0.1969, simple_loss=0.3005, pruned_loss=0.04667, over 7077.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2562, pruned_loss=0.02775, over 1405965.05 frames.], batch size: 28, lr: 2.00e-04
+2022-05-01 00:00:47,053 INFO [train.py:763] (0/8) Epoch 38, batch 900, loss[loss=0.1505, simple_loss=0.259, pruned_loss=0.02098, over 7408.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2564, pruned_loss=0.02769, over 1404677.67 frames.], batch size: 21, lr: 2.00e-04
+2022-05-01 00:01:52,979 INFO [train.py:763] (0/8) Epoch 38, batch 950, loss[loss=0.1343, simple_loss=0.22, pruned_loss=0.02431, over 7149.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2573, pruned_loss=0.0282, over 1406076.20 frames.], batch size: 17, lr: 2.00e-04
+2022-05-01 00:02:58,572 INFO [train.py:763] (0/8) Epoch 38, batch 1000, loss[loss=0.1594, simple_loss=0.2553, pruned_loss=0.03173, over 7362.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02846, over 1409501.25 frames.], batch size: 19, lr: 2.00e-04
+2022-05-01 00:04:04,005 INFO [train.py:763] (0/8) Epoch 38, batch 1050, loss[loss=0.1794, simple_loss=0.2834, pruned_loss=0.03772, over 6777.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2576, pruned_loss=0.02848, over 1412006.25 frames.], batch size: 31, lr: 2.00e-04
+2022-05-01 00:05:09,987 INFO [train.py:763] (0/8) Epoch 38, batch 1100, loss[loss=0.189, simple_loss=0.292, pruned_loss=0.04297, over 7400.00 frames.], tot_loss[loss=0.1569, simple_loss=0.257, pruned_loss=0.02841, over 1416412.97 frames.], batch size: 23, lr: 2.00e-04
+2022-05-01 00:06:15,682 INFO [train.py:763] (0/8) Epoch 38, batch 1150, loss[loss=0.1467, simple_loss=0.2324, pruned_loss=0.03055, over 7269.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2563, pruned_loss=0.02828, over 1419932.09 frames.], batch size: 18, lr: 2.00e-04
+2022-05-01 00:07:21,228 INFO [train.py:763] (0/8) Epoch 38, batch 1200, loss[loss=0.1637, simple_loss=0.2683, pruned_loss=0.02955, over 6726.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2566, pruned_loss=0.0286, over 1420952.58 frames.], batch size: 31, lr: 2.00e-04
+2022-05-01 00:08:27,135 INFO [train.py:763] (0/8) Epoch 38, batch 1250, loss[loss=0.1495, simple_loss=0.2402, pruned_loss=0.02943, over 7432.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2571, pruned_loss=0.02855, over 1422179.23 frames.], batch size: 20, lr: 2.00e-04
+2022-05-01 00:09:34,227 INFO [train.py:763] (0/8) Epoch 38, batch 1300, loss[loss=0.1407, simple_loss=0.2295, pruned_loss=0.02589, over 7264.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2565, pruned_loss=0.02855, over 1425539.28 frames.], batch size: 17, lr: 2.00e-04
+2022-05-01 00:10:39,855 INFO [train.py:763] (0/8) Epoch 38, batch 1350, loss[loss=0.1514, simple_loss=0.2559, pruned_loss=0.02347, over 7327.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02843, over 1425708.67 frames.], batch size: 20, lr: 2.00e-04
+2022-05-01 00:11:45,179 INFO [train.py:763] (0/8) Epoch 38, batch 1400, loss[loss=0.1457, simple_loss=0.2459, pruned_loss=0.02277, over 7173.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2572, pruned_loss=0.02822, over 1425031.30 frames.], batch size: 19, lr: 2.00e-04
+2022-05-01 00:12:50,406 INFO [train.py:763] (0/8) Epoch 38, batch 1450, loss[loss=0.1778, simple_loss=0.2795, pruned_loss=0.03801, over 7311.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02859, over 1424866.86 frames.], batch size: 25, lr: 2.00e-04
+2022-05-01 00:13:55,960 INFO [train.py:763] (0/8) Epoch 38, batch 1500, loss[loss=0.1606, simple_loss=0.2762, pruned_loss=0.02252, over 7113.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2586, pruned_loss=0.02831, over 1424326.84 frames.], batch size: 21, lr: 2.00e-04
+2022-05-01 00:15:03,020 INFO [train.py:763] (0/8) Epoch 38, batch 1550, loss[loss=0.1588, simple_loss=0.2619, pruned_loss=0.02784, over 7201.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.02825, over 1424185.28 frames.], batch size: 22, lr: 2.00e-04
+2022-05-01 00:16:09,302 INFO [train.py:763] (0/8) Epoch 38, batch 1600, loss[loss=0.191, simple_loss=0.3083, pruned_loss=0.03683, over 6760.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2577, pruned_loss=0.02827, over 1425665.64 frames.], batch size: 31, lr: 2.00e-04
+2022-05-01 00:17:15,075 INFO [train.py:763] (0/8) Epoch 38, batch 1650, loss[loss=0.1468, simple_loss=0.2512, pruned_loss=0.02115, over 7226.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2564, pruned_loss=0.02803, over 1425279.59 frames.], batch size: 21, lr: 2.00e-04
+2022-05-01 00:17:21,613 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/checkpoint-176000.pt
+2022-05-01 00:18:31,387 INFO [train.py:763] (0/8) Epoch 38, batch 1700, loss[loss=0.1559, simple_loss=0.2564, pruned_loss=0.02769, over 7092.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2572, pruned_loss=0.02828, over 1427109.70 frames.], batch size: 28, lr: 2.00e-04
+2022-05-01 00:19:36,543 INFO [train.py:763] (0/8) Epoch 38, batch 1750, loss[loss=0.1514, simple_loss=0.2487, pruned_loss=0.02703, over 7428.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.02834, over 1426827.48 frames.], batch size: 20, lr: 2.00e-04
+2022-05-01 00:20:42,267 INFO [train.py:763] (0/8) Epoch 38, batch 1800, loss[loss=0.1772, simple_loss=0.2852, pruned_loss=0.03454, over 7193.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2583, pruned_loss=0.02852, over 1424188.91 frames.], batch size: 23, lr: 2.00e-04
+2022-05-01 00:21:47,724 INFO [train.py:763] (0/8) Epoch 38, batch 1850, loss[loss=0.1394, simple_loss=0.2371, pruned_loss=0.02087, over 7165.00 frames.], tot_loss[loss=0.1574, simple_loss=0.258, pruned_loss=0.02838, over 1421914.19 frames.], batch size: 19, lr: 2.00e-04
+2022-05-01 00:22:54,689 INFO [train.py:763] (0/8) Epoch 38, batch 1900, loss[loss=0.1467, simple_loss=0.2392, pruned_loss=0.02712, over 7287.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2576, pruned_loss=0.02849, over 1424851.63 frames.], batch size: 18, lr: 2.00e-04
+2022-05-01 00:24:00,344 INFO [train.py:763] (0/8) Epoch 38, batch 1950, loss[loss=0.1709, simple_loss=0.276, pruned_loss=0.03293, over 7344.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2581, pruned_loss=0.02858, over 1424776.65 frames.], batch size: 21, lr: 1.99e-04
+2022-05-01 00:25:06,443 INFO [train.py:763] (0/8) Epoch 38, batch 2000, loss[loss=0.1464, simple_loss=0.2419, pruned_loss=0.02541, over 7252.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2582, pruned_loss=0.02836, over 1424056.07 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:26:13,058 INFO [train.py:763] (0/8) Epoch 38, batch 2050, loss[loss=0.1517, simple_loss=0.2586, pruned_loss=0.02244, over 7325.00 frames.], tot_loss[loss=0.1581, simple_loss=0.259, pruned_loss=0.02866, over 1422497.40 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:27:18,302 INFO [train.py:763] (0/8) Epoch 38, batch 2100, loss[loss=0.1522, simple_loss=0.2363, pruned_loss=0.0341, over 6764.00 frames.], tot_loss[loss=0.1572, simple_loss=0.258, pruned_loss=0.02816, over 1423372.80 frames.], batch size: 15, lr: 1.99e-04
+2022-05-01 00:28:25,367 INFO [train.py:763] (0/8) Epoch 38, batch 2150, loss[loss=0.1601, simple_loss=0.2613, pruned_loss=0.02948, over 7260.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2581, pruned_loss=0.02814, over 1420671.79 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:29:31,363 INFO [train.py:763] (0/8) Epoch 38, batch 2200, loss[loss=0.1828, simple_loss=0.282, pruned_loss=0.04181, over 7197.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2592, pruned_loss=0.0286, over 1421408.50 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 00:30:38,853 INFO [train.py:763] (0/8) Epoch 38, batch 2250, loss[loss=0.1436, simple_loss=0.2484, pruned_loss=0.01938, over 7154.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2586, pruned_loss=0.02882, over 1424052.83 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:31:44,026 INFO [train.py:763] (0/8) Epoch 38, batch 2300, loss[loss=0.1494, simple_loss=0.2507, pruned_loss=0.02407, over 7156.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02865, over 1422964.83 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:32:50,162 INFO [train.py:763] (0/8) Epoch 38, batch 2350, loss[loss=0.1706, simple_loss=0.2629, pruned_loss=0.03914, over 7240.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2587, pruned_loss=0.02889, over 1424450.78 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:33:55,527 INFO [train.py:763] (0/8) Epoch 38, batch 2400, loss[loss=0.1559, simple_loss=0.2595, pruned_loss=0.0262, over 7152.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2587, pruned_loss=0.02885, over 1427562.06 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:35:01,023 INFO [train.py:763] (0/8) Epoch 38, batch 2450, loss[loss=0.1432, simple_loss=0.2314, pruned_loss=0.02754, over 7413.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02876, over 1427962.13 frames.], batch size: 18, lr: 1.99e-04
+2022-05-01 00:36:06,998 INFO [train.py:763] (0/8) Epoch 38, batch 2500, loss[loss=0.1268, simple_loss=0.2255, pruned_loss=0.01401, over 7431.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.02833, over 1425951.84 frames.], batch size: 18, lr: 1.99e-04
+2022-05-01 00:37:12,689 INFO [train.py:763] (0/8) Epoch 38, batch 2550, loss[loss=0.1607, simple_loss=0.2593, pruned_loss=0.0311, over 7438.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2572, pruned_loss=0.02802, over 1430867.84 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:38:18,039 INFO [train.py:763] (0/8) Epoch 38, batch 2600, loss[loss=0.2039, simple_loss=0.3135, pruned_loss=0.04714, over 7131.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2579, pruned_loss=0.02831, over 1428514.20 frames.], batch size: 26, lr: 1.99e-04
+2022-05-01 00:39:23,365 INFO [train.py:763] (0/8) Epoch 38, batch 2650, loss[loss=0.1698, simple_loss=0.2713, pruned_loss=0.03418, over 7135.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02887, over 1429493.15 frames.], batch size: 28, lr: 1.99e-04
+2022-05-01 00:40:27,515 INFO [train.py:763] (0/8) Epoch 38, batch 2700, loss[loss=0.1781, simple_loss=0.2725, pruned_loss=0.04181, over 7317.00 frames.], tot_loss[loss=0.158, simple_loss=0.2586, pruned_loss=0.02871, over 1427726.99 frames.], batch size: 25, lr: 1.99e-04
+2022-05-01 00:41:33,245 INFO [train.py:763] (0/8) Epoch 38, batch 2750, loss[loss=0.1604, simple_loss=0.2647, pruned_loss=0.02809, over 7155.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2586, pruned_loss=0.02882, over 1428395.45 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:42:38,769 INFO [train.py:763] (0/8) Epoch 38, batch 2800, loss[loss=0.1568, simple_loss=0.261, pruned_loss=0.02624, over 7336.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02889, over 1425487.39 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 00:43:44,131 INFO [train.py:763] (0/8) Epoch 38, batch 2850, loss[loss=0.1376, simple_loss=0.2401, pruned_loss=0.01754, over 6463.00 frames.], tot_loss[loss=0.1583, simple_loss=0.259, pruned_loss=0.02882, over 1425953.76 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 00:44:49,677 INFO [train.py:763] (0/8) Epoch 38, batch 2900, loss[loss=0.1802, simple_loss=0.2877, pruned_loss=0.03628, over 7314.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02909, over 1425178.73 frames.], batch size: 21, lr: 1.99e-04
+2022-05-01 00:45:55,144 INFO [train.py:763] (0/8) Epoch 38, batch 2950, loss[loss=0.1481, simple_loss=0.2531, pruned_loss=0.02155, over 7330.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2584, pruned_loss=0.02903, over 1428860.07 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 00:47:00,418 INFO [train.py:763] (0/8) Epoch 38, batch 3000, loss[loss=0.1571, simple_loss=0.2693, pruned_loss=0.02239, over 7226.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02882, over 1429629.08 frames.], batch size: 20, lr: 1.99e-04
+2022-05-01 00:47:00,420 INFO [train.py:783] (0/8) Computing validation loss
+2022-05-01 00:47:15,873 INFO [train.py:792] (0/8) Epoch 38, validation: loss=0.1707, simple_loss=0.2648, pruned_loss=0.03834, over 698248.00 frames.
+2022-05-01 00:48:21,033 INFO [train.py:763] (0/8) Epoch 38, batch 3050, loss[loss=0.1544, simple_loss=0.2463, pruned_loss=0.03124, over 7119.00 frames.], tot_loss[loss=0.1583, simple_loss=0.259, pruned_loss=0.02882, over 1426566.40 frames.], batch size: 17, lr: 1.99e-04
+2022-05-01 00:49:26,207 INFO [train.py:763] (0/8) Epoch 38, batch 3100, loss[loss=0.1554, simple_loss=0.2624, pruned_loss=0.02422, over 6456.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2595, pruned_loss=0.02913, over 1418660.05 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 00:50:31,509 INFO [train.py:763] (0/8) Epoch 38, batch 3150, loss[loss=0.1801, simple_loss=0.2772, pruned_loss=0.04151, over 7397.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2597, pruned_loss=0.02887, over 1423802.21 frames.], batch size: 21, lr: 1.99e-04
+2022-05-01 00:51:36,878 INFO [train.py:763] (0/8) Epoch 38, batch 3200, loss[loss=0.1825, simple_loss=0.2907, pruned_loss=0.03716, over 6586.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2588, pruned_loss=0.02845, over 1424761.86 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 00:52:42,224 INFO [train.py:763] (0/8) Epoch 38, batch 3250, loss[loss=0.1553, simple_loss=0.2581, pruned_loss=0.02624, over 6533.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2592, pruned_loss=0.0286, over 1425314.76 frames.], batch size: 38, lr: 1.99e-04
+2022-05-01 00:53:47,533 INFO [train.py:763] (0/8) Epoch 38, batch 3300, loss[loss=0.1719, simple_loss=0.2741, pruned_loss=0.03487, over 7153.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2594, pruned_loss=0.02859, over 1424437.95 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:54:52,917 INFO [train.py:763] (0/8) Epoch 38, batch 3350, loss[loss=0.1407, simple_loss=0.2339, pruned_loss=0.02372, over 7129.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2587, pruned_loss=0.02844, over 1426083.12 frames.], batch size: 17, lr: 1.99e-04
+2022-05-01 00:55:59,024 INFO [train.py:763] (0/8) Epoch 38, batch 3400, loss[loss=0.1569, simple_loss=0.2471, pruned_loss=0.03329, over 7361.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2584, pruned_loss=0.02815, over 1427564.32 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:57:06,510 INFO [train.py:763] (0/8) Epoch 38, batch 3450, loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03117, over 7219.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2579, pruned_loss=0.02835, over 1419913.85 frames.], batch size: 23, lr: 1.99e-04
+2022-05-01 00:58:13,611 INFO [train.py:763] (0/8) Epoch 38, batch 3500, loss[loss=0.1351, simple_loss=0.2344, pruned_loss=0.01792, over 7160.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2581, pruned_loss=0.02833, over 1420610.32 frames.], batch size: 19, lr: 1.99e-04
+2022-05-01 00:59:19,220 INFO [train.py:763] (0/8) Epoch 38, batch 3550, loss[loss=0.1614, simple_loss=0.2764, pruned_loss=0.02319, over 7337.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2574, pruned_loss=0.02854, over 1423141.74 frames.], batch size: 22, lr: 1.99e-04
+2022-05-01 01:00:25,366 INFO [train.py:763] (0/8) Epoch 38, batch 3600, loss[loss=0.1429, simple_loss=0.2276, pruned_loss=0.02904, over 7263.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2583, pruned_loss=0.02902, over 1424861.62 frames.], batch size: 18, lr: 1.99e-04
+2022-05-01 01:01:30,576 INFO [train.py:763] (0/8) Epoch 38, batch 3650, loss[loss=0.1698, simple_loss=0.2772, pruned_loss=0.03123, over 7057.00 frames.], tot_loss[loss=0.159, simple_loss=0.2594, pruned_loss=0.02935, over 1426274.72 frames.], batch size: 28, lr: 1.99e-04
+2022-05-01 01:02:35,706 INFO [train.py:763] (0/8) Epoch 38, batch 3700, loss[loss=0.1514, simple_loss=0.2558, pruned_loss=0.02351, over 6238.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2591, pruned_loss=0.02887, over 1423851.79 frames.], batch size: 37, lr: 1.99e-04
+2022-05-01 01:03:41,350 INFO [train.py:763] (0/8) Epoch 38, batch 3750, loss[loss=0.1584, simple_loss=0.2571, pruned_loss=0.02986, over 7221.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2583, pruned_loss=0.02889, over 1417800.82 frames.], batch size: 23, lr: 1.98e-04
+2022-05-01 01:04:46,831 INFO [train.py:763] (0/8) Epoch 38, batch 3800, loss[loss=0.1497, simple_loss=0.254, pruned_loss=0.0227, over 7355.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02881, over 1423982.37 frames.], batch size: 19, lr: 1.98e-04
+2022-05-01 01:05:52,028 INFO [train.py:763] (0/8) Epoch 38, batch 3850, loss[loss=0.1984, simple_loss=0.2894, pruned_loss=0.0537, over 5227.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.02888, over 1420993.49 frames.], batch size: 52, lr: 1.98e-04
+2022-05-01 01:06:57,236 INFO [train.py:763] (0/8) Epoch 38, batch 3900, loss[loss=0.1549, simple_loss=0.2542, pruned_loss=0.02785, over 7073.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2585, pruned_loss=0.02868, over 1421324.22 frames.], batch size: 28, lr: 1.98e-04
+2022-05-01 01:08:02,836 INFO [train.py:763] (0/8) Epoch 38, batch 3950, loss[loss=0.1844, simple_loss=0.2861, pruned_loss=0.0413, over 7284.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02839, over 1423210.71 frames.], batch size: 25, lr: 1.98e-04
+2022-05-01 01:09:08,088 INFO [train.py:763] (0/8) Epoch 38, batch 4000, loss[loss=0.1698, simple_loss=0.2715, pruned_loss=0.03404, over 6681.00 frames.], tot_loss[loss=0.158, simple_loss=0.2582, pruned_loss=0.02892, over 1424640.32 frames.], batch size: 31, lr: 1.98e-04
+2022-05-01 01:10:13,455 INFO [train.py:763] (0/8) Epoch 38, batch 4050, loss[loss=0.1792, simple_loss=0.2899, pruned_loss=0.03429, over 6675.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.02835, over 1423319.64 frames.], batch size: 31, lr: 1.98e-04
+2022-05-01 01:11:18,891 INFO [train.py:763] (0/8) Epoch 38, batch 4100, loss[loss=0.1609, simple_loss=0.2678, pruned_loss=0.02704, over 7211.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2573, pruned_loss=0.0286, over 1421968.25 frames.], batch size: 21, lr: 1.98e-04
+2022-05-01 01:12:24,232 INFO [train.py:763] (0/8) Epoch 38, batch 4150, loss[loss=0.1551, simple_loss=0.2574, pruned_loss=0.02633, over 7214.00 frames.], tot_loss[loss=0.157, simple_loss=0.2571, pruned_loss=0.02851, over 1419774.45 frames.], batch size: 21, lr: 1.98e-04
+2022-05-01 01:13:30,539 INFO [train.py:763] (0/8) Epoch 38, batch 4200, loss[loss=0.165, simple_loss=0.2695, pruned_loss=0.03025, over 6705.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2576, pruned_loss=0.02862, over 1419564.57 frames.], batch size: 31, lr: 1.98e-04
+2022-05-01 01:14:35,839 INFO [train.py:763] (0/8) Epoch 38, batch 4250, loss[loss=0.1546, simple_loss=0.2435, pruned_loss=0.03286, over 7161.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2579, pruned_loss=0.02866, over 1416602.47 frames.], batch size: 17, lr: 1.98e-04
+2022-05-01 01:15:41,262 INFO [train.py:763] (0/8) Epoch 38, batch 4300, loss[loss=0.177, simple_loss=0.2686, pruned_loss=0.0427, over 7285.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02873, over 1417520.65 frames.], batch size: 25, lr: 1.98e-04
+2022-05-01 01:16:46,659 INFO [train.py:763] (0/8) Epoch 38, batch 4350, loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.02958, over 7424.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2587, pruned_loss=0.02881, over 1413418.37 frames.], batch size: 20, lr: 1.98e-04
+2022-05-01 01:17:51,731 INFO [train.py:763] (0/8) Epoch 38, batch 4400, loss[loss=0.1779, simple_loss=0.2925, pruned_loss=0.03165, over 7329.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2601, pruned_loss=0.02911, over 1410470.45 frames.], batch size: 22, lr: 1.98e-04
+2022-05-01 01:18:57,808 INFO [train.py:763] (0/8) Epoch 38, batch 4450, loss[loss=0.1337, simple_loss=0.2276, pruned_loss=0.01997, over 7019.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2605, pruned_loss=0.02935, over 1398570.93 frames.], batch size: 16, lr: 1.98e-04
+2022-05-01 01:20:03,891 INFO [train.py:763] (0/8) Epoch 38, batch 4500, loss[loss=0.146, simple_loss=0.2418, pruned_loss=0.02507, over 7163.00 frames.], tot_loss[loss=0.1603, simple_loss=0.261, pruned_loss=0.02976, over 1387621.22 frames.], batch size: 18, lr: 1.98e-04
+2022-05-01 01:21:09,325 INFO [train.py:763] (0/8) Epoch 38, batch 4550, loss[loss=0.2008, simple_loss=0.298, pruned_loss=0.05178, over 5115.00 frames.], tot_loss[loss=0.1624, simple_loss=0.263, pruned_loss=0.03086, over 1348291.21 frames.], batch size: 52, lr: 1.98e-04
+2022-05-01 01:21:58,494 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-38.pt
+2022-05-01 01:22:39,309 INFO [train.py:763] (0/8) Epoch 39, batch 0, loss[loss=0.1909, simple_loss=0.2982, pruned_loss=0.04176, over 7282.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2982, pruned_loss=0.04176, over 7282.00 frames.], batch size: 24, lr: 1.96e-04
+2022-05-01 01:23:45,005 INFO [train.py:763] (0/8) Epoch 39, batch 50, loss[loss=0.1164, simple_loss=0.2135, pruned_loss=0.009648, over 7268.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03028, over 317097.43 frames.], batch size: 17, lr: 1.95e-04
+2022-05-01 01:24:50,358 INFO [train.py:763] (0/8) Epoch 39, batch 100, loss[loss=0.1432, simple_loss=0.2409, pruned_loss=0.02278, over 7354.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2572, pruned_loss=0.02852, over 562102.10 frames.], batch size: 19, lr: 1.95e-04
+2022-05-01 01:25:56,221 INFO [train.py:763] (0/8) Epoch 39, batch 150, loss[loss=0.1464, simple_loss=0.2617, pruned_loss=0.01552, over 7238.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2545, pruned_loss=0.02802, over 755094.27 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:27:01,298 INFO [train.py:763] (0/8) Epoch 39, batch 200, loss[loss=0.1291, simple_loss=0.2262, pruned_loss=0.01601, over 7426.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2563, pruned_loss=0.02803, over 903343.16 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 01:28:06,663 INFO [train.py:763] (0/8) Epoch 39, batch 250, loss[loss=0.1473, simple_loss=0.2457, pruned_loss=0.0245, over 7113.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2563, pruned_loss=0.02794, over 1016302.44 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:29:11,532 INFO [train.py:763] (0/8) Epoch 39, batch 300, loss[loss=0.1839, simple_loss=0.2851, pruned_loss=0.04131, over 7286.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2574, pruned_loss=0.02811, over 1107365.71 frames.], batch size: 24, lr: 1.95e-04
+2022-05-01 01:30:16,879 INFO [train.py:763] (0/8) Epoch 39, batch 350, loss[loss=0.1612, simple_loss=0.2741, pruned_loss=0.02409, over 7141.00 frames.], tot_loss[loss=0.157, simple_loss=0.2572, pruned_loss=0.02841, over 1171412.25 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:31:22,263 INFO [train.py:763] (0/8) Epoch 39, batch 400, loss[loss=0.1762, simple_loss=0.2843, pruned_loss=0.034, over 7183.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2577, pruned_loss=0.02828, over 1229168.01 frames.], batch size: 26, lr: 1.95e-04
+2022-05-01 01:32:27,457 INFO [train.py:763] (0/8) Epoch 39, batch 450, loss[loss=0.1697, simple_loss=0.2807, pruned_loss=0.02933, over 7276.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2574, pruned_loss=0.02795, over 1272510.15 frames.], batch size: 25, lr: 1.95e-04
+2022-05-01 01:33:32,870 INFO [train.py:763] (0/8) Epoch 39, batch 500, loss[loss=0.1509, simple_loss=0.2564, pruned_loss=0.02273, over 7307.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2565, pruned_loss=0.02765, over 1305386.90 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:34:38,283 INFO [train.py:763] (0/8) Epoch 39, batch 550, loss[loss=0.1613, simple_loss=0.2637, pruned_loss=0.02946, over 7234.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2562, pruned_loss=0.0278, over 1327314.47 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:35:43,501 INFO [train.py:763] (0/8) Epoch 39, batch 600, loss[loss=0.1495, simple_loss=0.2484, pruned_loss=0.0253, over 7256.00 frames.], tot_loss[loss=0.156, simple_loss=0.2563, pruned_loss=0.02787, over 1349193.56 frames.], batch size: 19, lr: 1.95e-04
+2022-05-01 01:36:48,740 INFO [train.py:763] (0/8) Epoch 39, batch 650, loss[loss=0.1602, simple_loss=0.2614, pruned_loss=0.02951, over 7238.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2564, pruned_loss=0.02794, over 1367723.59 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:37:53,925 INFO [train.py:763] (0/8) Epoch 39, batch 700, loss[loss=0.1274, simple_loss=0.2159, pruned_loss=0.01948, over 7285.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2562, pruned_loss=0.02779, over 1381632.77 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 01:38:59,267 INFO [train.py:763] (0/8) Epoch 39, batch 750, loss[loss=0.1416, simple_loss=0.2431, pruned_loss=0.02009, over 7358.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2562, pruned_loss=0.02773, over 1386867.44 frames.], batch size: 19, lr: 1.95e-04
+2022-05-01 01:40:04,496 INFO [train.py:763] (0/8) Epoch 39, batch 800, loss[loss=0.1718, simple_loss=0.2846, pruned_loss=0.02947, over 7113.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2559, pruned_loss=0.02746, over 1396097.34 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:41:18,505 INFO [train.py:763] (0/8) Epoch 39, batch 850, loss[loss=0.1367, simple_loss=0.2288, pruned_loss=0.02233, over 7129.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2568, pruned_loss=0.02791, over 1403587.24 frames.], batch size: 17, lr: 1.95e-04
+2022-05-01 01:42:32,267 INFO [train.py:763] (0/8) Epoch 39, batch 900, loss[loss=0.1615, simple_loss=0.2627, pruned_loss=0.03012, over 7210.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2582, pruned_loss=0.02821, over 1409716.64 frames.], batch size: 23, lr: 1.95e-04
+2022-05-01 01:43:55,214 INFO [train.py:763] (0/8) Epoch 39, batch 950, loss[loss=0.1786, simple_loss=0.2698, pruned_loss=0.04373, over 4703.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2584, pruned_loss=0.02835, over 1412328.37 frames.], batch size: 52, lr: 1.95e-04
+2022-05-01 01:45:01,225 INFO [train.py:763] (0/8) Epoch 39, batch 1000, loss[loss=0.1673, simple_loss=0.2769, pruned_loss=0.02885, over 7108.00 frames.], tot_loss[loss=0.1582, simple_loss=0.259, pruned_loss=0.02867, over 1411108.08 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:46:06,275 INFO [train.py:763] (0/8) Epoch 39, batch 1050, loss[loss=0.1529, simple_loss=0.2557, pruned_loss=0.025, over 7224.00 frames.], tot_loss[loss=0.158, simple_loss=0.2588, pruned_loss=0.02857, over 1410030.40 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 01:47:29,497 INFO [train.py:763] (0/8) Epoch 39, batch 1100, loss[loss=0.1478, simple_loss=0.2442, pruned_loss=0.02576, over 7153.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2578, pruned_loss=0.02846, over 1408097.09 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 01:48:43,947 INFO [train.py:763] (0/8) Epoch 39, batch 1150, loss[loss=0.154, simple_loss=0.2662, pruned_loss=0.02096, over 6726.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.02834, over 1415544.55 frames.], batch size: 31, lr: 1.95e-04
+2022-05-01 01:49:48,906 INFO [train.py:763] (0/8) Epoch 39, batch 1200, loss[loss=0.1731, simple_loss=0.2676, pruned_loss=0.03927, over 6450.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2587, pruned_loss=0.02846, over 1417654.90 frames.], batch size: 38, lr: 1.95e-04
+2022-05-01 01:50:54,372 INFO [train.py:763] (0/8) Epoch 39, batch 1250, loss[loss=0.1505, simple_loss=0.2604, pruned_loss=0.02031, over 7285.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2586, pruned_loss=0.02842, over 1421595.91 frames.], batch size: 25, lr: 1.95e-04
+2022-05-01 01:51:59,443 INFO [train.py:763] (0/8) Epoch 39, batch 1300, loss[loss=0.1594, simple_loss=0.2659, pruned_loss=0.02649, over 7431.00 frames.], tot_loss[loss=0.158, simple_loss=0.2587, pruned_loss=0.02867, over 1422432.65 frames.], batch size: 20, lr: 1.95e-04
+2022-05-01 01:53:04,859 INFO [train.py:763] (0/8) Epoch 39, batch 1350, loss[loss=0.1583, simple_loss=0.2638, pruned_loss=0.02646, over 6308.00 frames.], tot_loss[loss=0.1584, simple_loss=0.259, pruned_loss=0.02896, over 1421625.87 frames.], batch size: 37, lr: 1.95e-04
+2022-05-01 01:54:11,092 INFO [train.py:763] (0/8) Epoch 39, batch 1400, loss[loss=0.1703, simple_loss=0.2771, pruned_loss=0.03181, over 6365.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2594, pruned_loss=0.02874, over 1422903.56 frames.], batch size: 37, lr: 1.95e-04
+2022-05-01 01:55:16,356 INFO [train.py:763] (0/8) Epoch 39, batch 1450, loss[loss=0.1892, simple_loss=0.2838, pruned_loss=0.04729, over 7206.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2593, pruned_loss=0.02857, over 1424550.55 frames.], batch size: 23, lr: 1.95e-04
+2022-05-01 01:56:21,448 INFO [train.py:763] (0/8) Epoch 39, batch 1500, loss[loss=0.1676, simple_loss=0.2589, pruned_loss=0.03819, over 7143.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2602, pruned_loss=0.02901, over 1425484.12 frames.], batch size: 17, lr: 1.95e-04
+2022-05-01 01:57:28,669 INFO [train.py:763] (0/8) Epoch 39, batch 1550, loss[loss=0.1723, simple_loss=0.2836, pruned_loss=0.0305, over 7219.00 frames.], tot_loss[loss=0.158, simple_loss=0.2589, pruned_loss=0.02862, over 1423444.84 frames.], batch size: 23, lr: 1.95e-04
+2022-05-01 01:58:35,233 INFO [train.py:763] (0/8) Epoch 39, batch 1600, loss[loss=0.1778, simple_loss=0.2809, pruned_loss=0.03734, over 7043.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2591, pruned_loss=0.02828, over 1426048.80 frames.], batch size: 28, lr: 1.95e-04
+2022-05-01 01:59:41,359 INFO [train.py:763] (0/8) Epoch 39, batch 1650, loss[loss=0.1489, simple_loss=0.2425, pruned_loss=0.02768, over 5041.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2592, pruned_loss=0.0286, over 1419273.41 frames.], batch size: 52, lr: 1.95e-04
+2022-05-01 02:00:47,166 INFO [train.py:763] (0/8) Epoch 39, batch 1700, loss[loss=0.1384, simple_loss=0.2289, pruned_loss=0.02397, over 6992.00 frames.], tot_loss[loss=0.1582, simple_loss=0.259, pruned_loss=0.02865, over 1413332.18 frames.], batch size: 16, lr: 1.95e-04
+2022-05-01 02:01:53,364 INFO [train.py:763] (0/8) Epoch 39, batch 1750, loss[loss=0.1613, simple_loss=0.2648, pruned_loss=0.02888, over 7318.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2582, pruned_loss=0.02844, over 1415137.72 frames.], batch size: 21, lr: 1.95e-04
+2022-05-01 02:02:58,284 INFO [train.py:763] (0/8) Epoch 39, batch 1800, loss[loss=0.1577, simple_loss=0.2633, pruned_loss=0.026, over 7347.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2592, pruned_loss=0.02882, over 1417760.51 frames.], batch size: 22, lr: 1.95e-04
+2022-05-01 02:04:03,604 INFO [train.py:763] (0/8) Epoch 39, batch 1850, loss[loss=0.1751, simple_loss=0.2732, pruned_loss=0.03851, over 7061.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2596, pruned_loss=0.02899, over 1421310.79 frames.], batch size: 18, lr: 1.95e-04
+2022-05-01 02:05:08,887 INFO [train.py:763] (0/8) Epoch 39, batch 1900, loss[loss=0.1442, simple_loss=0.2513, pruned_loss=0.01849, over 7157.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2595, pruned_loss=0.02892, over 1424471.24 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:06:14,313 INFO [train.py:763] (0/8) Epoch 39, batch 1950, loss[loss=0.1972, simple_loss=0.2914, pruned_loss=0.0515, over 5110.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2593, pruned_loss=0.02929, over 1418371.23 frames.], batch size: 53, lr: 1.94e-04
+2022-05-01 02:07:19,650 INFO [train.py:763] (0/8) Epoch 39, batch 2000, loss[loss=0.1588, simple_loss=0.2568, pruned_loss=0.0304, over 7067.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.02888, over 1422255.83 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:08:24,813 INFO [train.py:763] (0/8) Epoch 39, batch 2050, loss[loss=0.1581, simple_loss=0.2621, pruned_loss=0.02707, over 7435.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02898, over 1426053.11 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:09:30,533 INFO [train.py:763] (0/8) Epoch 39, batch 2100, loss[loss=0.1318, simple_loss=0.2157, pruned_loss=0.02394, over 7410.00 frames.], tot_loss[loss=0.158, simple_loss=0.2583, pruned_loss=0.02884, over 1425158.85 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:10:35,932 INFO [train.py:763] (0/8) Epoch 39, batch 2150, loss[loss=0.156, simple_loss=0.2601, pruned_loss=0.02595, over 7139.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2587, pruned_loss=0.02902, over 1428918.57 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:11:43,131 INFO [train.py:763] (0/8) Epoch 39, batch 2200, loss[loss=0.143, simple_loss=0.2497, pruned_loss=0.01819, over 7233.00 frames.], tot_loss[loss=0.1576, simple_loss=0.258, pruned_loss=0.0286, over 1431549.36 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:12:48,273 INFO [train.py:763] (0/8) Epoch 39, batch 2250, loss[loss=0.1835, simple_loss=0.278, pruned_loss=0.0445, over 7212.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2584, pruned_loss=0.02872, over 1429312.48 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:13:53,531 INFO [train.py:763] (0/8) Epoch 39, batch 2300, loss[loss=0.1417, simple_loss=0.2458, pruned_loss=0.01883, over 7438.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2574, pruned_loss=0.02866, over 1426791.32 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:15:00,688 INFO [train.py:763] (0/8) Epoch 39, batch 2350, loss[loss=0.1565, simple_loss=0.2639, pruned_loss=0.02456, over 7328.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2567, pruned_loss=0.0287, over 1425809.81 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:16:07,737 INFO [train.py:763] (0/8) Epoch 39, batch 2400, loss[loss=0.1456, simple_loss=0.2559, pruned_loss=0.01766, over 7206.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2564, pruned_loss=0.02861, over 1426408.15 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:17:13,331 INFO [train.py:763] (0/8) Epoch 39, batch 2450, loss[loss=0.1705, simple_loss=0.2681, pruned_loss=0.03639, over 7010.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2571, pruned_loss=0.02858, over 1421471.54 frames.], batch size: 28, lr: 1.94e-04
+2022-05-01 02:18:19,525 INFO [train.py:763] (0/8) Epoch 39, batch 2500, loss[loss=0.1483, simple_loss=0.2577, pruned_loss=0.01951, over 7415.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2577, pruned_loss=0.02887, over 1418210.31 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:19:24,729 INFO [train.py:763] (0/8) Epoch 39, batch 2550, loss[loss=0.1692, simple_loss=0.277, pruned_loss=0.03074, over 7023.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2582, pruned_loss=0.02901, over 1418134.66 frames.], batch size: 28, lr: 1.94e-04
+2022-05-01 02:20:31,566 INFO [train.py:763] (0/8) Epoch 39, batch 2600, loss[loss=0.1585, simple_loss=0.27, pruned_loss=0.02353, over 7331.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2568, pruned_loss=0.02846, over 1418119.95 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:21:37,537 INFO [train.py:763] (0/8) Epoch 39, batch 2650, loss[loss=0.1453, simple_loss=0.2465, pruned_loss=0.02209, over 7167.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2576, pruned_loss=0.02858, over 1420745.68 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:22:43,390 INFO [train.py:763] (0/8) Epoch 39, batch 2700, loss[loss=0.1761, simple_loss=0.274, pruned_loss=0.03908, over 7167.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2586, pruned_loss=0.02883, over 1422442.87 frames.], batch size: 26, lr: 1.94e-04
+2022-05-01 02:23:48,614 INFO [train.py:763] (0/8) Epoch 39, batch 2750, loss[loss=0.173, simple_loss=0.2831, pruned_loss=0.03143, over 7307.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.02829, over 1425555.03 frames.], batch size: 24, lr: 1.94e-04
+2022-05-01 02:24:53,692 INFO [train.py:763] (0/8) Epoch 39, batch 2800, loss[loss=0.1359, simple_loss=0.2381, pruned_loss=0.01682, over 7064.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02863, over 1422206.76 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:25:58,658 INFO [train.py:763] (0/8) Epoch 39, batch 2850, loss[loss=0.1561, simple_loss=0.262, pruned_loss=0.02509, over 6249.00 frames.], tot_loss[loss=0.1583, simple_loss=0.259, pruned_loss=0.02878, over 1418387.90 frames.], batch size: 37, lr: 1.94e-04
+2022-05-01 02:27:03,584 INFO [train.py:763] (0/8) Epoch 39, batch 2900, loss[loss=0.1723, simple_loss=0.2669, pruned_loss=0.0388, over 7077.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02864, over 1418513.67 frames.], batch size: 18, lr: 1.94e-04
+2022-05-01 02:28:08,503 INFO [train.py:763] (0/8) Epoch 39, batch 2950, loss[loss=0.1786, simple_loss=0.2829, pruned_loss=0.03709, over 7276.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2605, pruned_loss=0.0292, over 1418690.89 frames.], batch size: 24, lr: 1.94e-04
+2022-05-01 02:29:13,392 INFO [train.py:763] (0/8) Epoch 39, batch 3000, loss[loss=0.1751, simple_loss=0.2842, pruned_loss=0.03299, over 7346.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2604, pruned_loss=0.02935, over 1412242.11 frames.], batch size: 22, lr: 1.94e-04
+2022-05-01 02:29:13,393 INFO [train.py:783] (0/8) Computing validation loss
+2022-05-01 02:29:28,415 INFO [train.py:792] (0/8) Epoch 39, validation: loss=0.1688, simple_loss=0.2638, pruned_loss=0.03694, over 698248.00 frames.
+2022-05-01 02:30:33,960 INFO [train.py:763] (0/8) Epoch 39, batch 3050, loss[loss=0.1503, simple_loss=0.2403, pruned_loss=0.03016, over 7358.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2602, pruned_loss=0.02958, over 1414543.19 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:31:41,157 INFO [train.py:763] (0/8) Epoch 39, batch 3100, loss[loss=0.1588, simple_loss=0.2627, pruned_loss=0.02741, over 7198.00 frames.], tot_loss[loss=0.16, simple_loss=0.2606, pruned_loss=0.02965, over 1416989.01 frames.], batch size: 26, lr: 1.94e-04
+2022-05-01 02:32:47,806 INFO [train.py:763] (0/8) Epoch 39, batch 3150, loss[loss=0.1576, simple_loss=0.2547, pruned_loss=0.03027, over 7151.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2598, pruned_loss=0.02941, over 1420835.63 frames.], batch size: 20, lr: 1.94e-04
+2022-05-01 02:33:53,389 INFO [train.py:763] (0/8) Epoch 39, batch 3200, loss[loss=0.1787, simple_loss=0.2715, pruned_loss=0.04298, over 5051.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2602, pruned_loss=0.02931, over 1421059.79 frames.], batch size: 53, lr: 1.94e-04
+2022-05-01 02:34:58,491 INFO [train.py:763] (0/8) Epoch 39, batch 3250, loss[loss=0.1698, simple_loss=0.275, pruned_loss=0.03229, over 7378.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2603, pruned_loss=0.02907, over 1420744.30 frames.], batch size: 23, lr: 1.94e-04
+2022-05-01 02:36:03,622 INFO [train.py:763] (0/8) Epoch 39, batch 3300, loss[loss=0.1583, simple_loss=0.2654, pruned_loss=0.0256, over 7114.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2584, pruned_loss=0.02834, over 1419727.61 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:37:08,803 INFO [train.py:763] (0/8) Epoch 39, batch 3350, loss[loss=0.1472, simple_loss=0.251, pruned_loss=0.02174, over 7113.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.02826, over 1417467.41 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:38:14,841 INFO [train.py:763] (0/8) Epoch 39, batch 3400, loss[loss=0.1514, simple_loss=0.2519, pruned_loss=0.02543, over 7161.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2571, pruned_loss=0.02801, over 1417762.09 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:39:20,474 INFO [train.py:763] (0/8) Epoch 39, batch 3450, loss[loss=0.1456, simple_loss=0.23, pruned_loss=0.03061, over 7290.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2576, pruned_loss=0.02805, over 1416421.08 frames.], batch size: 17, lr: 1.94e-04
+2022-05-01 02:40:25,654 INFO [train.py:763] (0/8) Epoch 39, batch 3500, loss[loss=0.164, simple_loss=0.2763, pruned_loss=0.0258, over 7318.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2587, pruned_loss=0.02834, over 1418344.12 frames.], batch size: 21, lr: 1.94e-04
+2022-05-01 02:41:31,491 INFO [train.py:763] (0/8) Epoch 39, batch 3550, loss[loss=0.1518, simple_loss=0.2411, pruned_loss=0.03128, over 7447.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2571, pruned_loss=0.02821, over 1419295.21 frames.], batch size: 19, lr: 1.94e-04
+2022-05-01 02:42:37,770 INFO [train.py:763] (0/8) Epoch 39, batch 3600, loss[loss=0.1683, simple_loss=0.2759, pruned_loss=0.03038, over 4830.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2575, pruned_loss=0.02847, over 1416512.62 frames.], batch size: 52, lr: 1.94e-04
+2022-05-01 02:43:44,826 INFO [train.py:763] (0/8) Epoch 39, batch 3650, loss[loss=0.1852, simple_loss=0.2859, pruned_loss=0.04226, over 6349.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2571, pruned_loss=0.02809, over 1418534.18 frames.], batch size: 37, lr: 1.94e-04
+2022-05-01 02:44:50,057 INFO [train.py:763] (0/8) Epoch 39, batch 3700, loss[loss=0.1507, simple_loss=0.2376, pruned_loss=0.03194, over 7139.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2571, pruned_loss=0.02818, over 1422686.50 frames.], batch size: 17, lr: 1.94e-04
+2022-05-01 02:45:55,099 INFO [train.py:763] (0/8) Epoch 39, batch 3750, loss[loss=0.1442, simple_loss=0.2449, pruned_loss=0.02179, over 7348.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2578, pruned_loss=0.02823, over 1419623.97 frames.], batch size: 19, lr: 1.93e-04
+2022-05-01 02:47:00,748 INFO [train.py:763] (0/8) Epoch 39, batch 3800, loss[loss=0.1353, simple_loss=0.2254, pruned_loss=0.02255, over 7429.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2581, pruned_loss=0.02834, over 1423880.13 frames.], batch size: 17, lr: 1.93e-04
+2022-05-01 02:48:07,772 INFO [train.py:763] (0/8) Epoch 39, batch 3850, loss[loss=0.1646, simple_loss=0.2662, pruned_loss=0.0315, over 7425.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2578, pruned_loss=0.02818, over 1420277.94 frames.], batch size: 21, lr: 1.93e-04
+2022-05-01 02:49:13,634 INFO [train.py:763] (0/8) Epoch 39, batch 3900, loss[loss=0.1603, simple_loss=0.2635, pruned_loss=0.02854, over 7214.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2577, pruned_loss=0.02793, over 1420990.46 frames.], batch size: 23, lr: 1.93e-04
+2022-05-01 02:50:20,010 INFO [train.py:763] (0/8) Epoch 39, batch 3950, loss[loss=0.1448, simple_loss=0.2394, pruned_loss=0.02508, over 7085.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2572, pruned_loss=0.02806, over 1416593.87 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:51:25,351 INFO [train.py:763] (0/8) Epoch 39, batch 4000, loss[loss=0.1359, simple_loss=0.2309, pruned_loss=0.02047, over 7114.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2573, pruned_loss=0.02817, over 1415105.96 frames.], batch size: 17, lr: 1.93e-04
+2022-05-01 02:52:30,798 INFO [train.py:763] (0/8) Epoch 39, batch 4050, loss[loss=0.1571, simple_loss=0.2555, pruned_loss=0.02938, over 7199.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2573, pruned_loss=0.02822, over 1420090.48 frames.], batch size: 22, lr: 1.93e-04
+2022-05-01 02:53:35,948 INFO [train.py:763] (0/8) Epoch 39, batch 4100, loss[loss=0.1502, simple_loss=0.2533, pruned_loss=0.0236, over 7236.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2569, pruned_loss=0.02826, over 1419901.90 frames.], batch size: 20, lr: 1.93e-04
+2022-05-01 02:54:41,373 INFO [train.py:763] (0/8) Epoch 39, batch 4150, loss[loss=0.1716, simple_loss=0.2597, pruned_loss=0.04178, over 7282.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2579, pruned_loss=0.02853, over 1421308.97 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:55:46,812 INFO [train.py:763] (0/8) Epoch 39, batch 4200, loss[loss=0.1345, simple_loss=0.2345, pruned_loss=0.01728, over 7162.00 frames.], tot_loss[loss=0.157, simple_loss=0.2577, pruned_loss=0.0282, over 1423489.28 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:56:52,119 INFO [train.py:763] (0/8) Epoch 39, batch 4250, loss[loss=0.169, simple_loss=0.2755, pruned_loss=0.03124, over 7312.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2582, pruned_loss=0.0285, over 1419519.78 frames.], batch size: 21, lr: 1.93e-04
+2022-05-01 02:57:57,426 INFO [train.py:763] (0/8) Epoch 39, batch 4300, loss[loss=0.1336, simple_loss=0.2335, pruned_loss=0.01688, over 7160.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2573, pruned_loss=0.02848, over 1420191.50 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 02:59:02,815 INFO [train.py:763] (0/8) Epoch 39, batch 4350, loss[loss=0.1652, simple_loss=0.255, pruned_loss=0.0377, over 7337.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2574, pruned_loss=0.02844, over 1421164.45 frames.], batch size: 20, lr: 1.93e-04
+2022-05-01 03:00:09,031 INFO [train.py:763] (0/8) Epoch 39, batch 4400, loss[loss=0.169, simple_loss=0.2717, pruned_loss=0.03315, over 6749.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2572, pruned_loss=0.02821, over 1421574.59 frames.], batch size: 31, lr: 1.93e-04
+2022-05-01 03:01:14,009 INFO [train.py:763] (0/8) Epoch 39, batch 4450, loss[loss=0.1397, simple_loss=0.2365, pruned_loss=0.02146, over 7166.00 frames.], tot_loss[loss=0.157, simple_loss=0.2572, pruned_loss=0.02839, over 1408931.18 frames.], batch size: 18, lr: 1.93e-04
+2022-05-01 03:02:19,224 INFO [train.py:763] (0/8) Epoch 39, batch 4500, loss[loss=0.1475, simple_loss=0.2563, pruned_loss=0.01933, over 7218.00 frames.], tot_loss[loss=0.158, simple_loss=0.2583, pruned_loss=0.02887, over 1401654.74 frames.], batch size: 21, lr: 1.93e-04
+2022-05-01 03:03:25,873 INFO [train.py:763] (0/8) Epoch 39, batch 4550, loss[loss=0.1569, simple_loss=0.2457, pruned_loss=0.03406, over 7176.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2555, pruned_loss=0.02854, over 1393041.39 frames.], batch size: 16, lr: 1.93e-04
+2022-05-01 03:04:15,401 INFO [checkpoint.py:70] (0/8) Saving checkpoint to pruned_transducer_stateless4/exp-L/epoch-39.pt
+2022-05-01 03:04:37,768 INFO [train.py:971] (0/8) Done!