diff --git "a/exp/log/log-train-2022-05-13-19-15-59-2" "b/exp/log/log-train-2022-05-13-19-15-59-2"
new file mode 100644--- /dev/null
+++ "b/exp/log/log-train-2022-05-13-19-15-59-2"
@@ -0,0 +1,3784 @@
+2022-05-13 19:15:59,542 INFO [train.py:876] (2/8) Training started
+2022-05-13 19:15:59,542 INFO [train.py:886] (2/8) Device: cuda:2
+2022-05-13 19:15:59,546 INFO [train.py:895] (2/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.15.1', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': 'f8d2dba06c000ffee36aab5b66f24e7c9809f116', 'k2-git-date': 'Thu Apr 21 12:20:34 2022', 'lhotse-version': '1.1.0.dev+missing.version.file', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'deeper-conformer-without-random-combiner', 'icefall-git-sha1': '7b786ce-dirty', 'icefall-git-date': 'Fri May 13 18:53:22 2022', 'icefall-path': '/ceph-fj/fangjun/open-source-2/icefall-deeper-conformer-2', 'k2-path': '/ceph-fj/fangjun/open-source-2/k2-multi-22/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-fj/fangjun/open-source-2/lhotse-multi-3/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-6-0415002726-7dc5bf9fdc-w24k9', 'IP address': '10.177.28.71'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 1, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless5/exp-L'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'initial_lr': 0.003, 'lr_batches': 5000, 'lr_epochs': 6, 'context_size': 2, 'prune_range': 5, 'lm_scale': 0.25, 'am_scale': 0.0, 'simple_loss_scale': 0.5, 'seed': 42, 'print_diagnostics': False, 'save_every_n': 4000, 'keep_last_k': 30, 'average_period': 100, 'use_fp16': False, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'blank_id': 0, 'vocab_size': 500}
+2022-05-13 19:15:59,546 INFO [train.py:897] (2/8) About to create model
+2022-05-13 19:16:00,251 INFO [train.py:901] (2/8) Number of model parameters: 116553580
+2022-05-13 19:16:07,880 INFO [train.py:916] (2/8) Using DDP
+2022-05-13 19:16:09,395 INFO [asr_datamodule.py:391] (2/8) About to get train-clean-100 cuts
+2022-05-13 19:16:17,925 INFO [asr_datamodule.py:398] (2/8) About to get train-clean-360 cuts
+2022-05-13 19:16:51,723 INFO [asr_datamodule.py:405] (2/8) About to get train-other-500 cuts
+2022-05-13 19:17:46,832 INFO [asr_datamodule.py:209] (2/8) Enable MUSAN
+2022-05-13 19:17:46,832 INFO [asr_datamodule.py:210] (2/8) About to get Musan cuts
+2022-05-13 19:17:48,728 INFO [asr_datamodule.py:238] (2/8) Enable SpecAugment
+2022-05-13 19:17:48,728 INFO [asr_datamodule.py:239] (2/8) Time warp factor: 80
+2022-05-13 19:17:48,729 INFO [asr_datamodule.py:251] (2/8) Num frame mask: 10
+2022-05-13 19:17:48,729 INFO [asr_datamodule.py:264] (2/8) About to create train dataset
+2022-05-13 19:17:48,729 INFO [asr_datamodule.py:292] (2/8) Using BucketingSampler.
+2022-05-13 19:17:54,172 INFO [asr_datamodule.py:308] (2/8) About to create train dataloader
+2022-05-13 19:17:54,173 INFO [asr_datamodule.py:412] (2/8) About to get dev-clean cuts
+2022-05-13 19:17:54,520 INFO [asr_datamodule.py:417] (2/8) About to get dev-other cuts
+2022-05-13 19:17:54,721 INFO [asr_datamodule.py:339] (2/8) About to create dev dataset
+2022-05-13 19:17:54,733 INFO [asr_datamodule.py:358] (2/8) About to create dev dataloader
+2022-05-13 19:17:54,734 INFO [train.py:1078] (2/8) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
+2022-05-13 19:18:18,393 INFO [distributed.py:874] (2/8) Reducer buckets have been rebuilt in this iteration.
+2022-05-13 19:18:41,988 INFO [train.py:812] (2/8) Epoch 1, batch 0, loss[loss=0.7761, simple_loss=1.552, pruned_loss=6.595, over 7296.00 frames.], tot_loss[loss=0.7761, simple_loss=1.552, pruned_loss=6.595, over 7296.00 frames.], batch size: 17, lr: 3.00e-03
+2022-05-13 19:19:41,268 INFO [train.py:812] (2/8) Epoch 1, batch 50, loss[loss=0.4916, simple_loss=0.9832, pruned_loss=7.067, over 7163.00 frames.], tot_loss[loss=0.5554, simple_loss=1.111, pruned_loss=7.11, over 323641.55 frames.], batch size: 19, lr: 3.00e-03
+2022-05-13 19:20:39,815 INFO [train.py:812] (2/8) Epoch 1, batch 100, loss[loss=0.4088, simple_loss=0.8177, pruned_loss=6.638, over 7009.00 frames.], tot_loss[loss=0.4963, simple_loss=0.9925, pruned_loss=6.969, over 566898.99 frames.], batch size: 16, lr: 3.00e-03
+2022-05-13 19:21:38,700 INFO [train.py:812] (2/8) Epoch 1, batch 150, loss[loss=0.3548, simple_loss=0.7095, pruned_loss=6.743, over 6980.00 frames.], tot_loss[loss=0.4644, simple_loss=0.9288, pruned_loss=6.88, over 757960.79 frames.], batch size: 16, lr: 3.00e-03
+2022-05-13 19:22:37,013 INFO [train.py:812] (2/8) Epoch 1, batch 200, loss[loss=0.4448, simple_loss=0.8896, pruned_loss=6.806, over 7300.00 frames.], tot_loss[loss=0.4437, simple_loss=0.8874, pruned_loss=6.847, over 908055.36 frames.], batch size: 25, lr: 3.00e-03
+2022-05-13 19:23:35,740 INFO [train.py:812] (2/8) Epoch 1, batch 250, loss[loss=0.4319, simple_loss=0.8638, pruned_loss=7.011, over 7314.00 frames.], tot_loss[loss=0.4313, simple_loss=0.8625, pruned_loss=6.843, over 1016466.32 frames.], batch size: 21, lr: 3.00e-03
+2022-05-13 19:24:34,038 INFO [train.py:812] (2/8) Epoch 1, batch 300, loss[loss=0.4222, simple_loss=0.8445, pruned_loss=6.86, over 7299.00 frames.], tot_loss[loss=0.4201, simple_loss=0.8403, pruned_loss=6.835, over 1108793.90 frames.], batch size: 25, lr: 3.00e-03
+2022-05-13 19:25:33,445 INFO [train.py:812] (2/8) Epoch 1, batch 350, loss[loss=0.3794, simple_loss=0.7587, pruned_loss=6.817, over 7264.00 frames.], tot_loss[loss=0.4106, simple_loss=0.8213, pruned_loss=6.821, over 1178310.31 frames.], batch size: 19, lr: 3.00e-03
+2022-05-13 19:26:31,630 INFO [train.py:812] (2/8) Epoch 1, batch 400, loss[loss=0.3936, simple_loss=0.7872, pruned_loss=6.912, over 7422.00 frames.], tot_loss[loss=0.4019, simple_loss=0.8037, pruned_loss=6.802, over 1231527.53 frames.], batch size: 21, lr: 3.00e-03
+2022-05-13 19:27:30,029 INFO [train.py:812] (2/8) Epoch 1, batch 450, loss[loss=0.3384, simple_loss=0.6767, pruned_loss=6.747, over 7409.00 frames.], tot_loss[loss=0.3919, simple_loss=0.7839, pruned_loss=6.786, over 1266470.44 frames.], batch size: 21, lr: 2.99e-03
+2022-05-13 19:28:29,388 INFO [train.py:812] (2/8) Epoch 1, batch 500, loss[loss=0.3187, simple_loss=0.6373, pruned_loss=6.773, over 7223.00 frames.], tot_loss[loss=0.3774, simple_loss=0.7547, pruned_loss=6.775, over 1302545.74 frames.], batch size: 22, lr: 2.99e-03
+2022-05-13 19:29:27,219 INFO [train.py:812] (2/8) Epoch 1, batch 550, loss[loss=0.3332, simple_loss=0.6664, pruned_loss=6.867, over 7338.00 frames.], tot_loss[loss=0.3637, simple_loss=0.7274, pruned_loss=6.771, over 1328824.69 frames.], batch size: 22, lr: 2.99e-03
+2022-05-13 19:30:26,694 INFO [train.py:812] (2/8) Epoch 1, batch 600, loss[loss=0.2705, simple_loss=0.5411, pruned_loss=6.692, over 7119.00 frames.], tot_loss[loss=0.347, simple_loss=0.6939, pruned_loss=6.762, over 1350008.93 frames.], batch size: 21, lr: 2.99e-03
+2022-05-13 19:31:24,369 INFO [train.py:812] (2/8) Epoch 1, batch 650, loss[loss=0.2489, simple_loss=0.4977, pruned_loss=6.606, over 7013.00 frames.], tot_loss[loss=0.3312, simple_loss=0.6624, pruned_loss=6.754, over 1368533.50 frames.], batch size: 16, lr: 2.99e-03
+2022-05-13 19:32:22,731 INFO [train.py:812] (2/8) Epoch 1, batch 700, loss[loss=0.2928, simple_loss=0.5857, pruned_loss=6.82, over 7197.00 frames.], tot_loss[loss=0.3165, simple_loss=0.6331, pruned_loss=6.743, over 1379447.11 frames.], batch size: 23, lr: 2.99e-03
+2022-05-13 19:33:21,843 INFO [train.py:812] (2/8) Epoch 1, batch 750, loss[loss=0.2382, simple_loss=0.4763, pruned_loss=6.532, over 7297.00 frames.], tot_loss[loss=0.3025, simple_loss=0.605, pruned_loss=6.735, over 1391728.06 frames.], batch size: 17, lr: 2.98e-03
+2022-05-13 19:34:19,622 INFO [train.py:812] (2/8) Epoch 1, batch 800, loss[loss=0.252, simple_loss=0.504, pruned_loss=6.723, over 7100.00 frames.], tot_loss[loss=0.2916, simple_loss=0.5832, pruned_loss=6.734, over 1397287.60 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:35:17,951 INFO [train.py:812] (2/8) Epoch 1, batch 850, loss[loss=0.2597, simple_loss=0.5193, pruned_loss=6.81, over 7213.00 frames.], tot_loss[loss=0.2812, simple_loss=0.5623, pruned_loss=6.735, over 1403384.56 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:36:17,408 INFO [train.py:812] (2/8) Epoch 1, batch 900, loss[loss=0.2663, simple_loss=0.5325, pruned_loss=6.838, over 7308.00 frames.], tot_loss[loss=0.2717, simple_loss=0.5433, pruned_loss=6.733, over 1407651.70 frames.], batch size: 21, lr: 2.98e-03
+2022-05-13 19:37:15,467 INFO [train.py:812] (2/8) Epoch 1, batch 950, loss[loss=0.2147, simple_loss=0.4293, pruned_loss=6.622, over 7015.00 frames.], tot_loss[loss=0.2649, simple_loss=0.5298, pruned_loss=6.741, over 1405297.46 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:38:15,216 INFO [train.py:812] (2/8) Epoch 1, batch 1000, loss[loss=0.2285, simple_loss=0.4571, pruned_loss=6.654, over 6982.00 frames.], tot_loss[loss=0.2588, simple_loss=0.5177, pruned_loss=6.742, over 1406385.65 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:39:14,095 INFO [train.py:812] (2/8) Epoch 1, batch 1050, loss[loss=0.1984, simple_loss=0.3969, pruned_loss=6.633, over 6988.00 frames.], tot_loss[loss=0.252, simple_loss=0.504, pruned_loss=6.745, over 1408859.01 frames.], batch size: 16, lr: 2.97e-03
+2022-05-13 19:40:12,433 INFO [train.py:812] (2/8) Epoch 1, batch 1100, loss[loss=0.2427, simple_loss=0.4854, pruned_loss=6.809, over 7209.00 frames.], tot_loss[loss=0.2464, simple_loss=0.4928, pruned_loss=6.75, over 1412958.75 frames.], batch size: 22, lr: 2.96e-03
+2022-05-13 19:41:10,372 INFO [train.py:812] (2/8) Epoch 1, batch 1150, loss[loss=0.2279, simple_loss=0.4558, pruned_loss=6.859, over 6844.00 frames.], tot_loss[loss=0.2401, simple_loss=0.4803, pruned_loss=6.75, over 1413758.23 frames.], batch size: 31, lr: 2.96e-03
+2022-05-13 19:42:08,516 INFO [train.py:812] (2/8) Epoch 1, batch 1200, loss[loss=0.2338, simple_loss=0.4675, pruned_loss=6.899, over 7158.00 frames.], tot_loss[loss=0.2349, simple_loss=0.4699, pruned_loss=6.751, over 1422064.93 frames.], batch size: 26, lr: 2.96e-03
+2022-05-13 19:43:07,164 INFO [train.py:812] (2/8) Epoch 1, batch 1250, loss[loss=0.2423, simple_loss=0.4846, pruned_loss=6.899, over 7383.00 frames.], tot_loss[loss=0.2311, simple_loss=0.4622, pruned_loss=6.754, over 1414893.79 frames.], batch size: 23, lr: 2.95e-03
+2022-05-13 19:44:06,119 INFO [train.py:812] (2/8) Epoch 1, batch 1300, loss[loss=0.2301, simple_loss=0.4602, pruned_loss=6.868, over 7300.00 frames.], tot_loss[loss=0.2264, simple_loss=0.4528, pruned_loss=6.757, over 1422344.93 frames.], batch size: 24, lr: 2.95e-03
+2022-05-13 19:45:04,274 INFO [train.py:812] (2/8) Epoch 1, batch 1350, loss[loss=0.2, simple_loss=0.4, pruned_loss=6.745, over 7150.00 frames.], tot_loss[loss=0.2224, simple_loss=0.4448, pruned_loss=6.754, over 1423721.98 frames.], batch size: 20, lr: 2.95e-03
+2022-05-13 19:46:03,535 INFO [train.py:812] (2/8) Epoch 1, batch 1400, loss[loss=0.2135, simple_loss=0.427, pruned_loss=6.784, over 7304.00 frames.], tot_loss[loss=0.2206, simple_loss=0.4412, pruned_loss=6.76, over 1420255.88 frames.], batch size: 24, lr: 2.94e-03
+2022-05-13 19:47:02,122 INFO [train.py:812] (2/8) Epoch 1, batch 1450, loss[loss=0.1805, simple_loss=0.361, pruned_loss=6.766, over 7154.00 frames.], tot_loss[loss=0.2178, simple_loss=0.4355, pruned_loss=6.762, over 1420438.74 frames.], batch size: 17, lr: 2.94e-03
+2022-05-13 19:48:00,923 INFO [train.py:812] (2/8) Epoch 1, batch 1500, loss[loss=0.2103, simple_loss=0.4207, pruned_loss=6.88, over 7296.00 frames.], tot_loss[loss=0.2151, simple_loss=0.4302, pruned_loss=6.762, over 1423780.93 frames.], batch size: 24, lr: 2.94e-03
+2022-05-13 19:48:59,487 INFO [train.py:812] (2/8) Epoch 1, batch 1550, loss[loss=0.2225, simple_loss=0.4451, pruned_loss=6.843, over 7122.00 frames.], tot_loss[loss=0.213, simple_loss=0.426, pruned_loss=6.764, over 1423567.68 frames.], batch size: 21, lr: 2.93e-03
+2022-05-13 19:49:59,141 INFO [train.py:812] (2/8) Epoch 1, batch 1600, loss[loss=0.2221, simple_loss=0.4443, pruned_loss=6.799, over 7326.00 frames.], tot_loss[loss=0.2107, simple_loss=0.4214, pruned_loss=6.764, over 1420977.21 frames.], batch size: 20, lr: 2.93e-03
+2022-05-13 19:50:59,011 INFO [train.py:812] (2/8) Epoch 1, batch 1650, loss[loss=0.1676, simple_loss=0.3352, pruned_loss=6.609, over 7165.00 frames.], tot_loss[loss=0.2085, simple_loss=0.417, pruned_loss=6.759, over 1422693.39 frames.], batch size: 18, lr: 2.92e-03
+2022-05-13 19:51:59,056 INFO [train.py:812] (2/8) Epoch 1, batch 1700, loss[loss=0.2216, simple_loss=0.4432, pruned_loss=6.911, over 6197.00 frames.], tot_loss[loss=0.2069, simple_loss=0.4138, pruned_loss=6.763, over 1417327.27 frames.], batch size: 37, lr: 2.92e-03
+2022-05-13 19:52:58,951 INFO [train.py:812] (2/8) Epoch 1, batch 1750, loss[loss=0.2225, simple_loss=0.4449, pruned_loss=6.834, over 6495.00 frames.], tot_loss[loss=0.2041, simple_loss=0.4081, pruned_loss=6.759, over 1417354.97 frames.], batch size: 37, lr: 2.91e-03
+2022-05-13 19:54:00,187 INFO [train.py:812] (2/8) Epoch 1, batch 1800, loss[loss=0.2085, simple_loss=0.417, pruned_loss=6.882, over 7086.00 frames.], tot_loss[loss=0.2022, simple_loss=0.4044, pruned_loss=6.757, over 1417974.35 frames.], batch size: 28, lr: 2.91e-03
+2022-05-13 19:54:58,731 INFO [train.py:812] (2/8) Epoch 1, batch 1850, loss[loss=0.2236, simple_loss=0.4472, pruned_loss=6.869, over 5311.00 frames.], tot_loss[loss=0.2004, simple_loss=0.4009, pruned_loss=6.758, over 1419180.86 frames.], batch size: 52, lr: 2.91e-03
+2022-05-13 19:55:57,021 INFO [train.py:812] (2/8) Epoch 1, batch 1900, loss[loss=0.1989, simple_loss=0.3978, pruned_loss=6.704, over 7269.00 frames.], tot_loss[loss=0.1989, simple_loss=0.3978, pruned_loss=6.756, over 1420195.67 frames.], batch size: 19, lr: 2.90e-03
+2022-05-13 19:56:55,503 INFO [train.py:812] (2/8) Epoch 1, batch 1950, loss[loss=0.1918, simple_loss=0.3836, pruned_loss=6.773, over 7316.00 frames.], tot_loss[loss=0.1976, simple_loss=0.3952, pruned_loss=6.759, over 1423479.59 frames.], batch size: 21, lr: 2.90e-03
+2022-05-13 19:57:54,268 INFO [train.py:812] (2/8) Epoch 1, batch 2000, loss[loss=0.1554, simple_loss=0.3109, pruned_loss=6.603, over 6782.00 frames.], tot_loss[loss=0.196, simple_loss=0.392, pruned_loss=6.758, over 1424250.07 frames.], batch size: 15, lr: 2.89e-03
+2022-05-13 19:58:53,130 INFO [train.py:812] (2/8) Epoch 1, batch 2050, loss[loss=0.198, simple_loss=0.3959, pruned_loss=6.896, over 7168.00 frames.], tot_loss[loss=0.1946, simple_loss=0.3892, pruned_loss=6.761, over 1422693.60 frames.], batch size: 26, lr: 2.89e-03
+2022-05-13 19:59:51,421 INFO [train.py:812] (2/8) Epoch 1, batch 2100, loss[loss=0.1744, simple_loss=0.3489, pruned_loss=6.749, over 7163.00 frames.], tot_loss[loss=0.1941, simple_loss=0.3883, pruned_loss=6.759, over 1419075.32 frames.], batch size: 18, lr: 2.88e-03
+2022-05-13 20:00:49,532 INFO [train.py:812] (2/8) Epoch 1, batch 2150, loss[loss=0.1898, simple_loss=0.3796, pruned_loss=6.732, over 7341.00 frames.], tot_loss[loss=0.193, simple_loss=0.3859, pruned_loss=6.755, over 1423279.01 frames.], batch size: 22, lr: 2.88e-03
+2022-05-13 20:01:48,629 INFO [train.py:812] (2/8) Epoch 1, batch 2200, loss[loss=0.194, simple_loss=0.388, pruned_loss=6.631, over 7297.00 frames.], tot_loss[loss=0.1925, simple_loss=0.385, pruned_loss=6.754, over 1422516.49 frames.], batch size: 25, lr: 2.87e-03
+2022-05-13 20:02:47,463 INFO [train.py:812] (2/8) Epoch 1, batch 2250, loss[loss=0.1982, simple_loss=0.3965, pruned_loss=6.832, over 7209.00 frames.], tot_loss[loss=0.1913, simple_loss=0.3826, pruned_loss=6.749, over 1420823.96 frames.], batch size: 21, lr: 2.86e-03
+2022-05-13 20:03:45,867 INFO [train.py:812] (2/8) Epoch 1, batch 2300, loss[loss=0.1736, simple_loss=0.3472, pruned_loss=6.789, over 7249.00 frames.], tot_loss[loss=0.1915, simple_loss=0.3831, pruned_loss=6.753, over 1415019.26 frames.], batch size: 19, lr: 2.86e-03
+2022-05-13 20:04:43,217 INFO [train.py:812] (2/8) Epoch 1, batch 2350, loss[loss=0.2259, simple_loss=0.4518, pruned_loss=6.879, over 4769.00 frames.], tot_loss[loss=0.1915, simple_loss=0.3831, pruned_loss=6.76, over 1414409.16 frames.], batch size: 52, lr: 2.85e-03
+2022-05-13 20:05:42,782 INFO [train.py:812] (2/8) Epoch 1, batch 2400, loss[loss=0.1536, simple_loss=0.3071, pruned_loss=6.742, over 7437.00 frames.], tot_loss[loss=0.1903, simple_loss=0.3807, pruned_loss=6.758, over 1410521.62 frames.], batch size: 20, lr: 2.85e-03
+2022-05-13 20:06:41,465 INFO [train.py:812] (2/8) Epoch 1, batch 2450, loss[loss=0.2376, simple_loss=0.4751, pruned_loss=6.825, over 5134.00 frames.], tot_loss[loss=0.1894, simple_loss=0.3787, pruned_loss=6.757, over 1411129.36 frames.], batch size: 53, lr: 2.84e-03
+2022-05-13 20:07:40,731 INFO [train.py:812] (2/8) Epoch 1, batch 2500, loss[loss=0.1799, simple_loss=0.3599, pruned_loss=6.783, over 7325.00 frames.], tot_loss[loss=0.1883, simple_loss=0.3765, pruned_loss=6.753, over 1417635.61 frames.], batch size: 20, lr: 2.84e-03
+2022-05-13 20:08:39,344 INFO [train.py:812] (2/8) Epoch 1, batch 2550, loss[loss=0.1672, simple_loss=0.3344, pruned_loss=6.687, over 7405.00 frames.], tot_loss[loss=0.1883, simple_loss=0.3765, pruned_loss=6.753, over 1418500.35 frames.], batch size: 18, lr: 2.83e-03
+2022-05-13 20:09:37,899 INFO [train.py:812] (2/8) Epoch 1, batch 2600, loss[loss=0.2058, simple_loss=0.4115, pruned_loss=6.799, over 7232.00 frames.], tot_loss[loss=0.1867, simple_loss=0.3734, pruned_loss=6.745, over 1421362.11 frames.], batch size: 20, lr: 2.83e-03
+2022-05-13 20:10:35,868 INFO [train.py:812] (2/8) Epoch 1, batch 2650, loss[loss=0.1584, simple_loss=0.3169, pruned_loss=6.719, over 7234.00 frames.], tot_loss[loss=0.1855, simple_loss=0.3709, pruned_loss=6.744, over 1422850.41 frames.], batch size: 20, lr: 2.82e-03
+2022-05-13 20:11:35,630 INFO [train.py:812] (2/8) Epoch 1, batch 2700, loss[loss=0.1838, simple_loss=0.3677, pruned_loss=6.741, over 7132.00 frames.], tot_loss[loss=0.1855, simple_loss=0.371, pruned_loss=6.746, over 1422097.03 frames.], batch size: 20, lr: 2.81e-03
+2022-05-13 20:12:32,616 INFO [train.py:812] (2/8) Epoch 1, batch 2750, loss[loss=0.1853, simple_loss=0.3706, pruned_loss=6.773, over 7318.00 frames.], tot_loss[loss=0.1851, simple_loss=0.3702, pruned_loss=6.748, over 1423103.94 frames.], batch size: 20, lr: 2.81e-03
+2022-05-13 20:13:32,045 INFO [train.py:812] (2/8) Epoch 1, batch 2800, loss[loss=0.1719, simple_loss=0.3439, pruned_loss=6.761, over 7147.00 frames.], tot_loss[loss=0.1847, simple_loss=0.3694, pruned_loss=6.747, over 1421784.23 frames.], batch size: 20, lr: 2.80e-03
+2022-05-13 20:14:30,978 INFO [train.py:812] (2/8) Epoch 1, batch 2850, loss[loss=0.1822, simple_loss=0.3644, pruned_loss=6.712, over 7358.00 frames.], tot_loss[loss=0.1831, simple_loss=0.3662, pruned_loss=6.741, over 1425229.45 frames.], batch size: 19, lr: 2.80e-03
+2022-05-13 20:15:28,497 INFO [train.py:812] (2/8) Epoch 1, batch 2900, loss[loss=0.1814, simple_loss=0.3628, pruned_loss=6.733, over 7311.00 frames.], tot_loss[loss=0.1845, simple_loss=0.3689, pruned_loss=6.747, over 1421082.26 frames.], batch size: 20, lr: 2.79e-03
+2022-05-13 20:16:27,576 INFO [train.py:812] (2/8) Epoch 1, batch 2950, loss[loss=0.1878, simple_loss=0.3755, pruned_loss=6.763, over 7152.00 frames.], tot_loss[loss=0.1828, simple_loss=0.3657, pruned_loss=6.739, over 1417057.00 frames.], batch size: 26, lr: 2.78e-03
+2022-05-13 20:17:26,743 INFO [train.py:812] (2/8) Epoch 1, batch 3000, loss[loss=0.3192, simple_loss=0.3225, pruned_loss=1.58, over 7283.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3636, pruned_loss=6.712, over 1420556.07 frames.], batch size: 17, lr: 2.78e-03
+2022-05-13 20:17:26,743 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-13 20:17:34,933 INFO [train.py:841] (2/8) Epoch 1, validation: loss=2.094, simple_loss=0.4148, pruned_loss=1.887, over 698248.00 frames.
+2022-05-13 20:18:33,929 INFO [train.py:812] (2/8) Epoch 1, batch 3050, loss[loss=0.2933, simple_loss=0.3949, pruned_loss=0.9583, over 6373.00 frames.], tot_loss[loss=0.241, simple_loss=0.3733, pruned_loss=5.501, over 1420698.26 frames.], batch size: 38, lr: 2.77e-03
+2022-05-13 20:19:33,922 INFO [train.py:812] (2/8) Epoch 1, batch 3100, loss[loss=0.2366, simple_loss=0.3599, pruned_loss=0.5665, over 7411.00 frames.], tot_loss[loss=0.2428, simple_loss=0.369, pruned_loss=4.428, over 1426122.06 frames.], batch size: 21, lr: 2.77e-03
+2022-05-13 20:20:32,551 INFO [train.py:812] (2/8) Epoch 1, batch 3150, loss[loss=0.1883, simple_loss=0.3189, pruned_loss=0.2881, over 7415.00 frames.], tot_loss[loss=0.2375, simple_loss=0.3652, pruned_loss=3.539, over 1427075.09 frames.], batch size: 21, lr: 2.76e-03
+2022-05-13 20:21:30,559 INFO [train.py:812] (2/8) Epoch 1, batch 3200, loss[loss=0.2199, simple_loss=0.3824, pruned_loss=0.2871, over 7278.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3649, pruned_loss=2.83, over 1423136.62 frames.], batch size: 24, lr: 2.75e-03
+2022-05-13 20:22:29,481 INFO [train.py:812] (2/8) Epoch 1, batch 3250, loss[loss=0.216, simple_loss=0.3809, pruned_loss=0.2553, over 7149.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3646, pruned_loss=2.261, over 1423101.91 frames.], batch size: 20, lr: 2.75e-03
+2022-05-13 20:23:28,325 INFO [train.py:812] (2/8) Epoch 1, batch 3300, loss[loss=0.2114, simple_loss=0.3755, pruned_loss=0.2361, over 7405.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3646, pruned_loss=1.816, over 1418910.22 frames.], batch size: 23, lr: 2.74e-03
+2022-05-13 20:24:25,791 INFO [train.py:812] (2/8) Epoch 1, batch 3350, loss[loss=0.2157, simple_loss=0.384, pruned_loss=0.2367, over 7289.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3643, pruned_loss=1.457, over 1423414.83 frames.], batch size: 24, lr: 2.73e-03
+2022-05-13 20:25:24,227 INFO [train.py:812] (2/8) Epoch 1, batch 3400, loss[loss=0.1923, simple_loss=0.3474, pruned_loss=0.1863, over 7256.00 frames.], tot_loss[loss=0.214, simple_loss=0.3635, pruned_loss=1.178, over 1423849.53 frames.], batch size: 19, lr: 2.73e-03
+2022-05-13 20:26:22,126 INFO [train.py:812] (2/8) Epoch 1, batch 3450, loss[loss=0.1936, simple_loss=0.3515, pruned_loss=0.1779, over 7311.00 frames.], tot_loss[loss=0.2103, simple_loss=0.3619, pruned_loss=0.96, over 1423335.00 frames.], batch size: 25, lr: 2.72e-03
+2022-05-13 20:27:20,155 INFO [train.py:812] (2/8) Epoch 1, batch 3500, loss[loss=0.2061, simple_loss=0.3737, pruned_loss=0.192, over 7133.00 frames.], tot_loss[loss=0.2073, simple_loss=0.3607, pruned_loss=0.7885, over 1421812.44 frames.], batch size: 26, lr: 2.72e-03
+2022-05-13 20:28:19,218 INFO [train.py:812] (2/8) Epoch 1, batch 3550, loss[loss=0.2029, simple_loss=0.3712, pruned_loss=0.1725, over 7218.00 frames.], tot_loss[loss=0.2037, simple_loss=0.3579, pruned_loss=0.6514, over 1422843.50 frames.], batch size: 21, lr: 2.71e-03
+2022-05-13 20:29:18,097 INFO [train.py:812] (2/8) Epoch 1, batch 3600, loss[loss=0.1764, simple_loss=0.3221, pruned_loss=0.1529, over 7010.00 frames.], tot_loss[loss=0.201, simple_loss=0.356, pruned_loss=0.5452, over 1421309.00 frames.], batch size: 16, lr: 2.70e-03
+2022-05-13 20:30:25,600 INFO [train.py:812] (2/8) Epoch 1, batch 3650, loss[loss=0.1976, simple_loss=0.3608, pruned_loss=0.1726, over 7219.00 frames.], tot_loss[loss=0.1987, simple_loss=0.3543, pruned_loss=0.4607, over 1421824.87 frames.], batch size: 21, lr: 2.70e-03
+2022-05-13 20:32:10,011 INFO [train.py:812] (2/8) Epoch 1, batch 3700, loss[loss=0.1745, simple_loss=0.3228, pruned_loss=0.1316, over 6731.00 frames.], tot_loss[loss=0.1967, simple_loss=0.3525, pruned_loss=0.3939, over 1426528.30 frames.], batch size: 31, lr: 2.69e-03
+2022-05-13 20:33:27,102 INFO [train.py:812] (2/8) Epoch 1, batch 3750, loss[loss=0.1639, simple_loss=0.3025, pruned_loss=0.1265, over 7277.00 frames.], tot_loss[loss=0.1953, simple_loss=0.3516, pruned_loss=0.3438, over 1417750.19 frames.], batch size: 18, lr: 2.68e-03
+2022-05-13 20:34:26,667 INFO [train.py:812] (2/8) Epoch 1, batch 3800, loss[loss=0.1668, simple_loss=0.3078, pruned_loss=0.1288, over 7130.00 frames.], tot_loss[loss=0.1939, simple_loss=0.3504, pruned_loss=0.3025, over 1417544.90 frames.], batch size: 17, lr: 2.68e-03
+2022-05-13 20:35:25,744 INFO [train.py:812] (2/8) Epoch 1, batch 3850, loss[loss=0.1914, simple_loss=0.3506, pruned_loss=0.1611, over 7134.00 frames.], tot_loss[loss=0.193, simple_loss=0.35, pruned_loss=0.2696, over 1422952.39 frames.], batch size: 17, lr: 2.67e-03
+2022-05-13 20:36:24,057 INFO [train.py:812] (2/8) Epoch 1, batch 3900, loss[loss=0.1719, simple_loss=0.3175, pruned_loss=0.1316, over 6820.00 frames.], tot_loss[loss=0.192, simple_loss=0.3492, pruned_loss=0.2442, over 1419175.61 frames.], batch size: 15, lr: 2.66e-03
+2022-05-13 20:37:21,119 INFO [train.py:812] (2/8) Epoch 1, batch 3950, loss[loss=0.1667, simple_loss=0.3052, pruned_loss=0.1411, over 6765.00 frames.], tot_loss[loss=0.1909, simple_loss=0.3479, pruned_loss=0.2236, over 1417088.35 frames.], batch size: 15, lr: 2.66e-03
+2022-05-13 20:38:28,014 INFO [train.py:812] (2/8) Epoch 1, batch 4000, loss[loss=0.175, simple_loss=0.3277, pruned_loss=0.1112, over 7325.00 frames.], tot_loss[loss=0.1906, simple_loss=0.3481, pruned_loss=0.2076, over 1419860.70 frames.], batch size: 21, lr: 2.65e-03
+2022-05-13 20:39:26,727 INFO [train.py:812] (2/8) Epoch 1, batch 4050, loss[loss=0.1941, simple_loss=0.3592, pruned_loss=0.1451, over 7061.00 frames.], tot_loss[loss=0.1902, simple_loss=0.3479, pruned_loss=0.1949, over 1420906.73 frames.], batch size: 28, lr: 2.64e-03
+2022-05-13 20:40:25,262 INFO [train.py:812] (2/8) Epoch 1, batch 4100, loss[loss=0.1641, simple_loss=0.3057, pruned_loss=0.1124, over 7258.00 frames.], tot_loss[loss=0.1891, simple_loss=0.3466, pruned_loss=0.1839, over 1420867.23 frames.], batch size: 19, lr: 2.64e-03
+2022-05-13 20:41:23,925 INFO [train.py:812] (2/8) Epoch 1, batch 4150, loss[loss=0.1671, simple_loss=0.3088, pruned_loss=0.1266, over 7064.00 frames.], tot_loss[loss=0.1886, simple_loss=0.3462, pruned_loss=0.175, over 1425446.82 frames.], batch size: 18, lr: 2.63e-03
+2022-05-13 20:42:22,996 INFO [train.py:812] (2/8) Epoch 1, batch 4200, loss[loss=0.1978, simple_loss=0.3636, pruned_loss=0.1601, over 7210.00 frames.], tot_loss[loss=0.1877, simple_loss=0.3451, pruned_loss=0.1676, over 1424090.06 frames.], batch size: 22, lr: 2.63e-03
+2022-05-13 20:43:21,439 INFO [train.py:812] (2/8) Epoch 1, batch 4250, loss[loss=0.1906, simple_loss=0.3508, pruned_loss=0.1525, over 7425.00 frames.], tot_loss[loss=0.1887, simple_loss=0.3469, pruned_loss=0.1641, over 1422932.68 frames.], batch size: 20, lr: 2.62e-03
+2022-05-13 20:44:20,462 INFO [train.py:812] (2/8) Epoch 1, batch 4300, loss[loss=0.198, simple_loss=0.3659, pruned_loss=0.1505, over 7036.00 frames.], tot_loss[loss=0.1891, simple_loss=0.3479, pruned_loss=0.1607, over 1422530.15 frames.], batch size: 28, lr: 2.61e-03
+2022-05-13 20:45:18,959 INFO [train.py:812] (2/8) Epoch 1, batch 4350, loss[loss=0.2023, simple_loss=0.3705, pruned_loss=0.1708, over 7438.00 frames.], tot_loss[loss=0.1883, simple_loss=0.347, pruned_loss=0.1558, over 1426113.41 frames.], batch size: 20, lr: 2.61e-03
+2022-05-13 20:46:18,413 INFO [train.py:812] (2/8) Epoch 1, batch 4400, loss[loss=0.1813, simple_loss=0.3345, pruned_loss=0.1408, over 7281.00 frames.], tot_loss[loss=0.1888, simple_loss=0.3479, pruned_loss=0.1538, over 1424113.82 frames.], batch size: 18, lr: 2.60e-03
+2022-05-13 20:47:17,290 INFO [train.py:812] (2/8) Epoch 1, batch 4450, loss[loss=0.1711, simple_loss=0.3174, pruned_loss=0.124, over 7424.00 frames.], tot_loss[loss=0.1892, simple_loss=0.3488, pruned_loss=0.1524, over 1423735.15 frames.], batch size: 20, lr: 2.59e-03
+2022-05-13 20:48:16,734 INFO [train.py:812] (2/8) Epoch 1, batch 4500, loss[loss=0.2061, simple_loss=0.3771, pruned_loss=0.176, over 6274.00 frames.], tot_loss[loss=0.1893, simple_loss=0.349, pruned_loss=0.1516, over 1414567.11 frames.], batch size: 37, lr: 2.59e-03
+2022-05-13 20:49:13,801 INFO [train.py:812] (2/8) Epoch 1, batch 4550, loss[loss=0.2102, simple_loss=0.3848, pruned_loss=0.1786, over 5020.00 frames.], tot_loss[loss=0.19, simple_loss=0.3502, pruned_loss=0.1514, over 1395779.40 frames.], batch size: 52, lr: 2.58e-03
+2022-05-13 20:50:25,939 INFO [train.py:812] (2/8) Epoch 2, batch 0, loss[loss=0.2101, simple_loss=0.3848, pruned_loss=0.1766, over 7186.00 frames.], tot_loss[loss=0.2101, simple_loss=0.3848, pruned_loss=0.1766, over 7186.00 frames.], batch size: 26, lr: 2.56e-03
+2022-05-13 20:51:25,844 INFO [train.py:812] (2/8) Epoch 2, batch 50, loss[loss=0.1732, simple_loss=0.3253, pruned_loss=0.1053, over 7234.00 frames.], tot_loss[loss=0.188, simple_loss=0.347, pruned_loss=0.1448, over 312334.29 frames.], batch size: 20, lr: 2.55e-03
+2022-05-13 20:52:24,857 INFO [train.py:812] (2/8) Epoch 2, batch 100, loss[loss=0.19, simple_loss=0.3511, pruned_loss=0.1447, over 7429.00 frames.], tot_loss[loss=0.1844, simple_loss=0.341, pruned_loss=0.1391, over 560142.16 frames.], batch size: 20, lr: 2.54e-03
+2022-05-13 20:53:23,906 INFO [train.py:812] (2/8) Epoch 2, batch 150, loss[loss=0.1713, simple_loss=0.323, pruned_loss=0.09841, over 7334.00 frames.], tot_loss[loss=0.1833, simple_loss=0.3393, pruned_loss=0.1362, over 751010.46 frames.], batch size: 20, lr: 2.54e-03
+2022-05-13 20:54:21,307 INFO [train.py:812] (2/8) Epoch 2, batch 200, loss[loss=0.1624, simple_loss=0.303, pruned_loss=0.1095, over 7146.00 frames.], tot_loss[loss=0.1816, simple_loss=0.3366, pruned_loss=0.133, over 900925.62 frames.], batch size: 19, lr: 2.53e-03
+2022-05-13 20:55:19,836 INFO [train.py:812] (2/8) Epoch 2, batch 250, loss[loss=0.1935, simple_loss=0.3604, pruned_loss=0.1332, over 7371.00 frames.], tot_loss[loss=0.1818, simple_loss=0.3369, pruned_loss=0.1332, over 1015562.20 frames.], batch size: 23, lr: 2.53e-03
+2022-05-13 20:56:18,194 INFO [train.py:812] (2/8) Epoch 2, batch 300, loss[loss=0.184, simple_loss=0.342, pruned_loss=0.1298, over 7268.00 frames.], tot_loss[loss=0.1821, simple_loss=0.3377, pruned_loss=0.1327, over 1104697.28 frames.], batch size: 19, lr: 2.52e-03
+2022-05-13 20:57:16,219 INFO [train.py:812] (2/8) Epoch 2, batch 350, loss[loss=0.1647, simple_loss=0.3085, pruned_loss=0.1046, over 7224.00 frames.], tot_loss[loss=0.1819, simple_loss=0.3373, pruned_loss=0.1326, over 1173552.78 frames.], batch size: 21, lr: 2.51e-03
+2022-05-13 20:58:14,815 INFO [train.py:812] (2/8) Epoch 2, batch 400, loss[loss=0.211, simple_loss=0.3882, pruned_loss=0.1689, over 7151.00 frames.], tot_loss[loss=0.182, simple_loss=0.3376, pruned_loss=0.1324, over 1230362.31 frames.], batch size: 20, lr: 2.51e-03
+2022-05-13 20:59:13,974 INFO [train.py:812] (2/8) Epoch 2, batch 450, loss[loss=0.1575, simple_loss=0.2945, pruned_loss=0.103, over 7158.00 frames.], tot_loss[loss=0.1819, simple_loss=0.3374, pruned_loss=0.132, over 1276044.00 frames.], batch size: 19, lr: 2.50e-03
+2022-05-13 21:00:12,407 INFO [train.py:812] (2/8) Epoch 2, batch 500, loss[loss=0.1655, simple_loss=0.3122, pruned_loss=0.09377, over 7170.00 frames.], tot_loss[loss=0.1814, simple_loss=0.3368, pruned_loss=0.1304, over 1307596.84 frames.], batch size: 18, lr: 2.49e-03
+2022-05-13 21:01:12,170 INFO [train.py:812] (2/8) Epoch 2, batch 550, loss[loss=0.1751, simple_loss=0.3275, pruned_loss=0.1134, over 7356.00 frames.], tot_loss[loss=0.1804, simple_loss=0.335, pruned_loss=0.129, over 1332429.00 frames.], batch size: 19, lr: 2.49e-03
+2022-05-13 21:02:09,993 INFO [train.py:812] (2/8) Epoch 2, batch 600, loss[loss=0.1954, simple_loss=0.3584, pruned_loss=0.1623, over 7389.00 frames.], tot_loss[loss=0.1814, simple_loss=0.3369, pruned_loss=0.1292, over 1354069.71 frames.], batch size: 23, lr: 2.48e-03
+2022-05-13 21:03:09,000 INFO [train.py:812] (2/8) Epoch 2, batch 650, loss[loss=0.1604, simple_loss=0.2983, pruned_loss=0.1124, over 7276.00 frames.], tot_loss[loss=0.1818, simple_loss=0.3374, pruned_loss=0.1308, over 1368160.03 frames.], batch size: 18, lr: 2.48e-03
+2022-05-13 21:04:08,339 INFO [train.py:812] (2/8) Epoch 2, batch 700, loss[loss=0.2177, simple_loss=0.394, pruned_loss=0.2072, over 4988.00 frames.], tot_loss[loss=0.1813, simple_loss=0.3366, pruned_loss=0.1298, over 1379525.16 frames.], batch size: 52, lr: 2.47e-03
+2022-05-13 21:05:07,224 INFO [train.py:812] (2/8) Epoch 2, batch 750, loss[loss=0.178, simple_loss=0.3296, pruned_loss=0.1321, over 7271.00 frames.], tot_loss[loss=0.1814, simple_loss=0.3369, pruned_loss=0.1293, over 1391101.09 frames.], batch size: 19, lr: 2.46e-03
+2022-05-13 21:06:06,512 INFO [train.py:812] (2/8) Epoch 2, batch 800, loss[loss=0.1675, simple_loss=0.3117, pruned_loss=0.1166, over 7057.00 frames.], tot_loss[loss=0.1805, simple_loss=0.3355, pruned_loss=0.1281, over 1401022.22 frames.], batch size: 18, lr: 2.46e-03
+2022-05-13 21:07:06,154 INFO [train.py:812] (2/8) Epoch 2, batch 850, loss[loss=0.1906, simple_loss=0.3542, pruned_loss=0.1349, over 7309.00 frames.], tot_loss[loss=0.1796, simple_loss=0.3341, pruned_loss=0.1262, over 1408462.84 frames.], batch size: 20, lr: 2.45e-03
+2022-05-13 21:08:05,121 INFO [train.py:812] (2/8) Epoch 2, batch 900, loss[loss=0.1733, simple_loss=0.3222, pruned_loss=0.1216, over 7446.00 frames.], tot_loss[loss=0.1797, simple_loss=0.3341, pruned_loss=0.1266, over 1412895.97 frames.], batch size: 20, lr: 2.45e-03
+2022-05-13 21:09:04,125 INFO [train.py:812] (2/8) Epoch 2, batch 950, loss[loss=0.1666, simple_loss=0.3124, pruned_loss=0.1045, over 7243.00 frames.], tot_loss[loss=0.1802, simple_loss=0.3349, pruned_loss=0.1275, over 1415241.72 frames.], batch size: 19, lr: 2.44e-03
+2022-05-13 21:10:02,108 INFO [train.py:812] (2/8) Epoch 2, batch 1000, loss[loss=0.2135, simple_loss=0.3916, pruned_loss=0.1773, over 6655.00 frames.], tot_loss[loss=0.1795, simple_loss=0.3337, pruned_loss=0.1263, over 1417033.47 frames.], batch size: 31, lr: 2.43e-03
+2022-05-13 21:11:00,257 INFO [train.py:812] (2/8) Epoch 2, batch 1050, loss[loss=0.1586, simple_loss=0.2985, pruned_loss=0.09326, over 7428.00 frames.], tot_loss[loss=0.1788, simple_loss=0.3326, pruned_loss=0.1256, over 1418846.60 frames.], batch size: 20, lr: 2.43e-03
+2022-05-13 21:11:59,255 INFO [train.py:812] (2/8) Epoch 2, batch 1100, loss[loss=0.1642, simple_loss=0.3071, pruned_loss=0.1067, over 7164.00 frames.], tot_loss[loss=0.1784, simple_loss=0.332, pruned_loss=0.1241, over 1420415.72 frames.], batch size: 18, lr: 2.42e-03
+2022-05-13 21:12:57,639 INFO [train.py:812] (2/8) Epoch 2, batch 1150, loss[loss=0.1658, simple_loss=0.3117, pruned_loss=0.09986, over 7229.00 frames.], tot_loss[loss=0.1771, simple_loss=0.3298, pruned_loss=0.1222, over 1423262.55 frames.], batch size: 20, lr: 2.41e-03
+2022-05-13 21:13:56,173 INFO [train.py:812] (2/8) Epoch 2, batch 1200, loss[loss=0.1921, simple_loss=0.356, pruned_loss=0.1413, over 6983.00 frames.], tot_loss[loss=0.177, simple_loss=0.3296, pruned_loss=0.1221, over 1422587.24 frames.], batch size: 28, lr: 2.41e-03
+2022-05-13 21:14:54,773 INFO [train.py:812] (2/8) Epoch 2, batch 1250, loss[loss=0.1617, simple_loss=0.302, pruned_loss=0.1074, over 7268.00 frames.], tot_loss[loss=0.1775, simple_loss=0.3306, pruned_loss=0.1223, over 1421868.00 frames.], batch size: 18, lr: 2.40e-03
+2022-05-13 21:15:53,348 INFO [train.py:812] (2/8) Epoch 2, batch 1300, loss[loss=0.1818, simple_loss=0.3392, pruned_loss=0.1216, over 7225.00 frames.], tot_loss[loss=0.1782, simple_loss=0.3317, pruned_loss=0.1236, over 1416335.83 frames.], batch size: 21, lr: 2.40e-03
+2022-05-13 21:16:52,357 INFO [train.py:812] (2/8) Epoch 2, batch 1350, loss[loss=0.154, simple_loss=0.2886, pruned_loss=0.09733, over 7275.00 frames.], tot_loss[loss=0.1772, simple_loss=0.3299, pruned_loss=0.1222, over 1419773.76 frames.], batch size: 17, lr: 2.39e-03
+2022-05-13 21:17:49,937 INFO [train.py:812] (2/8) Epoch 2, batch 1400, loss[loss=0.1804, simple_loss=0.3378, pruned_loss=0.1151, over 7214.00 frames.], tot_loss[loss=0.1772, simple_loss=0.33, pruned_loss=0.1218, over 1418644.43 frames.], batch size: 21, lr: 2.39e-03
+2022-05-13 21:18:49,327 INFO [train.py:812] (2/8) Epoch 2, batch 1450, loss[loss=0.3116, simple_loss=0.3405, pruned_loss=0.1413, over 7134.00 frames.], tot_loss[loss=0.2009, simple_loss=0.3318, pruned_loss=0.1243, over 1423053.79 frames.], batch size: 26, lr: 2.38e-03
+2022-05-13 21:19:47,681 INFO [train.py:812] (2/8) Epoch 2, batch 1500, loss[loss=0.2916, simple_loss=0.3399, pruned_loss=0.1217, over 6417.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3338, pruned_loss=0.1259, over 1422477.54 frames.], batch size: 38, lr: 2.37e-03
+2022-05-13 21:20:45,894 INFO [train.py:812] (2/8) Epoch 2, batch 1550, loss[loss=0.2635, simple_loss=0.3239, pruned_loss=0.1016, over 7427.00 frames.], tot_loss[loss=0.2389, simple_loss=0.335, pruned_loss=0.1254, over 1425546.40 frames.], batch size: 20, lr: 2.37e-03
+2022-05-13 21:21:43,112 INFO [train.py:812] (2/8) Epoch 2, batch 1600, loss[loss=0.2399, simple_loss=0.2963, pruned_loss=0.09174, over 7165.00 frames.], tot_loss[loss=0.2473, simple_loss=0.333, pruned_loss=0.1228, over 1425172.75 frames.], batch size: 18, lr: 2.36e-03
+2022-05-13 21:22:41,983 INFO [train.py:812] (2/8) Epoch 2, batch 1650, loss[loss=0.2656, simple_loss=0.3221, pruned_loss=0.1045, over 7429.00 frames.], tot_loss[loss=0.2547, simple_loss=0.332, pruned_loss=0.1214, over 1425597.40 frames.], batch size: 20, lr: 2.36e-03
+2022-05-13 21:23:40,000 INFO [train.py:812] (2/8) Epoch 2, batch 1700, loss[loss=0.3469, simple_loss=0.3835, pruned_loss=0.1552, over 7428.00 frames.], tot_loss[loss=0.2624, simple_loss=0.3332, pruned_loss=0.1213, over 1424433.04 frames.], batch size: 21, lr: 2.35e-03
+2022-05-13 21:24:38,973 INFO [train.py:812] (2/8) Epoch 2, batch 1750, loss[loss=0.2586, simple_loss=0.3072, pruned_loss=0.105, over 7292.00 frames.], tot_loss[loss=0.2684, simple_loss=0.335, pruned_loss=0.1207, over 1423287.81 frames.], batch size: 18, lr: 2.34e-03
+2022-05-13 21:25:38,306 INFO [train.py:812] (2/8) Epoch 2, batch 1800, loss[loss=0.2837, simple_loss=0.3194, pruned_loss=0.124, over 7371.00 frames.], tot_loss[loss=0.2712, simple_loss=0.3344, pruned_loss=0.1194, over 1424156.95 frames.], batch size: 19, lr: 2.34e-03
+2022-05-13 21:26:37,481 INFO [train.py:812] (2/8) Epoch 2, batch 1850, loss[loss=0.275, simple_loss=0.3321, pruned_loss=0.1089, over 7329.00 frames.], tot_loss[loss=0.2719, simple_loss=0.3326, pruned_loss=0.1176, over 1424776.57 frames.], batch size: 20, lr: 2.33e-03
+2022-05-13 21:27:35,686 INFO [train.py:812] (2/8) Epoch 2, batch 1900, loss[loss=0.2345, simple_loss=0.2928, pruned_loss=0.08811, over 7010.00 frames.], tot_loss[loss=0.2746, simple_loss=0.3336, pruned_loss=0.1171, over 1428779.99 frames.], batch size: 16, lr: 2.33e-03
+2022-05-13 21:28:33,671 INFO [train.py:812] (2/8) Epoch 2, batch 1950, loss[loss=0.2331, simple_loss=0.2952, pruned_loss=0.08553, over 7295.00 frames.], tot_loss[loss=0.2763, simple_loss=0.3339, pruned_loss=0.1165, over 1429307.40 frames.], batch size: 18, lr: 2.32e-03
+2022-05-13 21:29:31,785 INFO [train.py:812] (2/8) Epoch 2, batch 2000, loss[loss=0.2508, simple_loss=0.3257, pruned_loss=0.08791, over 7117.00 frames.], tot_loss[loss=0.2776, simple_loss=0.3344, pruned_loss=0.1161, over 1423453.95 frames.], batch size: 21, lr: 2.32e-03
+2022-05-13 21:30:31,549 INFO [train.py:812] (2/8) Epoch 2, batch 2050, loss[loss=0.3132, simple_loss=0.364, pruned_loss=0.1312, over 7089.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3337, pruned_loss=0.1152, over 1424996.89 frames.], batch size: 28, lr: 2.31e-03
+2022-05-13 21:31:31,043 INFO [train.py:812] (2/8) Epoch 2, batch 2100, loss[loss=0.2547, simple_loss=0.3048, pruned_loss=0.1023, over 7408.00 frames.], tot_loss[loss=0.2773, simple_loss=0.3333, pruned_loss=0.1141, over 1425910.65 frames.], batch size: 18, lr: 2.31e-03
+2022-05-13 21:32:30,573 INFO [train.py:812] (2/8) Epoch 2, batch 2150, loss[loss=0.2721, simple_loss=0.3301, pruned_loss=0.107, over 7403.00 frames.], tot_loss[loss=0.2768, simple_loss=0.3328, pruned_loss=0.1131, over 1424080.95 frames.], batch size: 21, lr: 2.30e-03
+2022-05-13 21:33:29,449 INFO [train.py:812] (2/8) Epoch 2, batch 2200, loss[loss=0.2637, simple_loss=0.3263, pruned_loss=0.1006, over 7104.00 frames.], tot_loss[loss=0.2755, simple_loss=0.3313, pruned_loss=0.1119, over 1423074.97 frames.], batch size: 21, lr: 2.29e-03
+2022-05-13 21:34:29,303 INFO [train.py:812] (2/8) Epoch 2, batch 2250, loss[loss=0.269, simple_loss=0.3406, pruned_loss=0.09868, over 7209.00 frames.], tot_loss[loss=0.2738, simple_loss=0.3304, pruned_loss=0.1103, over 1424113.61 frames.], batch size: 21, lr: 2.29e-03
+2022-05-13 21:35:27,779 INFO [train.py:812] (2/8) Epoch 2, batch 2300, loss[loss=0.3429, simple_loss=0.3814, pruned_loss=0.1522, over 7202.00 frames.], tot_loss[loss=0.2745, simple_loss=0.3308, pruned_loss=0.1103, over 1424487.70 frames.], batch size: 22, lr: 2.28e-03
+2022-05-13 21:36:26,826 INFO [train.py:812] (2/8) Epoch 2, batch 2350, loss[loss=0.2827, simple_loss=0.3457, pruned_loss=0.1099, over 7225.00 frames.], tot_loss[loss=0.2752, simple_loss=0.3311, pruned_loss=0.1107, over 1423513.52 frames.], batch size: 20, lr: 2.28e-03
+2022-05-13 21:37:24,978 INFO [train.py:812] (2/8) Epoch 2, batch 2400, loss[loss=0.2889, simple_loss=0.3568, pruned_loss=0.1105, over 7313.00 frames.], tot_loss[loss=0.2761, simple_loss=0.3316, pruned_loss=0.1111, over 1423126.64 frames.], batch size: 21, lr: 2.27e-03
+2022-05-13 21:38:23,790 INFO [train.py:812] (2/8) Epoch 2, batch 2450, loss[loss=0.2687, simple_loss=0.3213, pruned_loss=0.108, over 7328.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3318, pruned_loss=0.1104, over 1425840.45 frames.], batch size: 21, lr: 2.27e-03
+2022-05-13 21:39:23,280 INFO [train.py:812] (2/8) Epoch 2, batch 2500, loss[loss=0.3169, simple_loss=0.3689, pruned_loss=0.1324, over 7197.00 frames.], tot_loss[loss=0.275, simple_loss=0.3315, pruned_loss=0.1097, over 1426489.64 frames.], batch size: 26, lr: 2.26e-03
+2022-05-13 21:40:21,931 INFO [train.py:812] (2/8) Epoch 2, batch 2550, loss[loss=0.2638, simple_loss=0.313, pruned_loss=0.1073, over 6969.00 frames.], tot_loss[loss=0.2751, simple_loss=0.3313, pruned_loss=0.1098, over 1426457.58 frames.], batch size: 16, lr: 2.26e-03
+2022-05-13 21:41:21,067 INFO [train.py:812] (2/8) Epoch 2, batch 2600, loss[loss=0.2746, simple_loss=0.3396, pruned_loss=0.1048, over 7166.00 frames.], tot_loss[loss=0.2736, simple_loss=0.3304, pruned_loss=0.1087, over 1428722.21 frames.], batch size: 26, lr: 2.25e-03
+2022-05-13 21:42:20,698 INFO [train.py:812] (2/8) Epoch 2, batch 2650, loss[loss=0.3167, simple_loss=0.3615, pruned_loss=0.1359, over 6628.00 frames.], tot_loss[loss=0.2728, simple_loss=0.3299, pruned_loss=0.1081, over 1427943.15 frames.], batch size: 38, lr: 2.25e-03
+2022-05-13 21:43:18,315 INFO [train.py:812] (2/8) Epoch 2, batch 2700, loss[loss=0.2981, simple_loss=0.3562, pruned_loss=0.12, over 6691.00 frames.], tot_loss[loss=0.2716, simple_loss=0.3289, pruned_loss=0.1074, over 1426880.15 frames.], batch size: 31, lr: 2.24e-03
+2022-05-13 21:44:17,958 INFO [train.py:812] (2/8) Epoch 2, batch 2750, loss[loss=0.2917, simple_loss=0.3452, pruned_loss=0.119, over 7292.00 frames.], tot_loss[loss=0.2707, simple_loss=0.328, pruned_loss=0.1068, over 1424259.78 frames.], batch size: 24, lr: 2.24e-03
+2022-05-13 21:45:15,692 INFO [train.py:812] (2/8) Epoch 2, batch 2800, loss[loss=0.3036, simple_loss=0.3571, pruned_loss=0.1251, over 7212.00 frames.], tot_loss[loss=0.2687, simple_loss=0.3269, pruned_loss=0.1054, over 1426702.66 frames.], batch size: 23, lr: 2.23e-03
+2022-05-13 21:46:14,910 INFO [train.py:812] (2/8) Epoch 2, batch 2850, loss[loss=0.3057, simple_loss=0.3692, pruned_loss=0.1211, over 7290.00 frames.], tot_loss[loss=0.2686, simple_loss=0.3269, pruned_loss=0.1053, over 1425979.71 frames.], batch size: 24, lr: 2.23e-03
+2022-05-13 21:47:13,485 INFO [train.py:812] (2/8) Epoch 2, batch 2900, loss[loss=0.2748, simple_loss=0.3298, pruned_loss=0.1098, over 7218.00 frames.], tot_loss[loss=0.2695, simple_loss=0.3278, pruned_loss=0.1057, over 1422016.21 frames.], batch size: 20, lr: 2.22e-03
+2022-05-13 21:48:11,746 INFO [train.py:812] (2/8) Epoch 2, batch 2950, loss[loss=0.2431, simple_loss=0.3159, pruned_loss=0.08511, over 7241.00 frames.], tot_loss[loss=0.2683, simple_loss=0.3268, pruned_loss=0.1049, over 1422305.56 frames.], batch size: 20, lr: 2.22e-03
+2022-05-13 21:49:10,837 INFO [train.py:812] (2/8) Epoch 2, batch 3000, loss[loss=0.21, simple_loss=0.2766, pruned_loss=0.07173, over 7282.00 frames.], tot_loss[loss=0.2665, simple_loss=0.3259, pruned_loss=0.1036, over 1425584.59 frames.], batch size: 17, lr: 2.21e-03
+2022-05-13 21:49:10,838 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-13 21:49:18,580 INFO [train.py:841] (2/8) Epoch 2, validation: loss=0.2016, simple_loss=0.2977, pruned_loss=0.0527, over 698248.00 frames.
+2022-05-13 21:50:17,419 INFO [train.py:812] (2/8) Epoch 2, batch 3050, loss[loss=0.3597, simple_loss=0.3697, pruned_loss=0.1748, over 7279.00 frames.], tot_loss[loss=0.2684, simple_loss=0.3271, pruned_loss=0.1049, over 1421121.78 frames.], batch size: 18, lr: 2.20e-03
+2022-05-13 21:51:15,126 INFO [train.py:812] (2/8) Epoch 2, batch 3100, loss[loss=0.3046, simple_loss=0.3535, pruned_loss=0.1278, over 4723.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3269, pruned_loss=0.1039, over 1420676.97 frames.], batch size: 53, lr: 2.20e-03
+2022-05-13 21:52:13,944 INFO [train.py:812] (2/8) Epoch 2, batch 3150, loss[loss=0.241, simple_loss=0.2974, pruned_loss=0.09234, over 7280.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3273, pruned_loss=0.104, over 1423237.44 frames.], batch size: 16, lr: 2.19e-03
+2022-05-13 21:53:13,039 INFO [train.py:812] (2/8) Epoch 2, batch 3200, loss[loss=0.2609, simple_loss=0.3262, pruned_loss=0.09782, over 4993.00 frames.], tot_loss[loss=0.2695, simple_loss=0.3286, pruned_loss=0.1052, over 1412379.83 frames.], batch size: 52, lr: 2.19e-03
+2022-05-13 21:54:12,613 INFO [train.py:812] (2/8) Epoch 2, batch 3250, loss[loss=0.2886, simple_loss=0.3513, pruned_loss=0.113, over 7198.00 frames.], tot_loss[loss=0.2695, simple_loss=0.3289, pruned_loss=0.1051, over 1415185.67 frames.], batch size: 23, lr: 2.18e-03
+2022-05-13 21:55:12,233 INFO [train.py:812] (2/8) Epoch 2, batch 3300, loss[loss=0.2887, simple_loss=0.3485, pruned_loss=0.1144, over 7210.00 frames.], tot_loss[loss=0.2678, simple_loss=0.3274, pruned_loss=0.1041, over 1420273.54 frames.], batch size: 22, lr: 2.18e-03
+2022-05-13 21:56:11,991 INFO [train.py:812] (2/8) Epoch 2, batch 3350, loss[loss=0.2418, simple_loss=0.3203, pruned_loss=0.08163, over 7176.00 frames.], tot_loss[loss=0.267, simple_loss=0.328, pruned_loss=0.103, over 1423183.73 frames.], batch size: 26, lr: 2.18e-03
+2022-05-13 21:57:11,189 INFO [train.py:812] (2/8) Epoch 2, batch 3400, loss[loss=0.1942, simple_loss=0.2635, pruned_loss=0.06245, over 7130.00 frames.], tot_loss[loss=0.2648, simple_loss=0.3262, pruned_loss=0.1018, over 1424027.20 frames.], batch size: 17, lr: 2.17e-03
+2022-05-13 21:58:14,552 INFO [train.py:812] (2/8) Epoch 2, batch 3450, loss[loss=0.2974, simple_loss=0.3629, pruned_loss=0.116, over 7303.00 frames.], tot_loss[loss=0.2644, simple_loss=0.3259, pruned_loss=0.1014, over 1426211.22 frames.], batch size: 24, lr: 2.17e-03
+2022-05-13 21:59:13,437 INFO [train.py:812] (2/8) Epoch 2, batch 3500, loss[loss=0.3486, simple_loss=0.3945, pruned_loss=0.1513, over 6440.00 frames.], tot_loss[loss=0.2643, simple_loss=0.326, pruned_loss=0.1013, over 1423706.31 frames.], batch size: 37, lr: 2.16e-03
+2022-05-13 22:00:12,761 INFO [train.py:812] (2/8) Epoch 2, batch 3550, loss[loss=0.2799, simple_loss=0.3457, pruned_loss=0.107, over 7298.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3264, pruned_loss=0.1017, over 1423834.32 frames.], batch size: 25, lr: 2.16e-03
+2022-05-13 22:01:11,658 INFO [train.py:812] (2/8) Epoch 2, batch 3600, loss[loss=0.3195, simple_loss=0.3567, pruned_loss=0.1412, over 7232.00 frames.], tot_loss[loss=0.2637, simple_loss=0.326, pruned_loss=0.1007, over 1425196.91 frames.], batch size: 20, lr: 2.15e-03
+2022-05-13 22:02:11,445 INFO [train.py:812] (2/8) Epoch 2, batch 3650, loss[loss=0.263, simple_loss=0.3106, pruned_loss=0.1077, over 6766.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3252, pruned_loss=0.1001, over 1426740.84 frames.], batch size: 15, lr: 2.15e-03
+2022-05-13 22:03:10,448 INFO [train.py:812] (2/8) Epoch 2, batch 3700, loss[loss=0.2578, simple_loss=0.315, pruned_loss=0.1003, over 7159.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3263, pruned_loss=0.1006, over 1428894.57 frames.], batch size: 19, lr: 2.14e-03
+2022-05-13 22:04:09,800 INFO [train.py:812] (2/8) Epoch 2, batch 3750, loss[loss=0.2737, simple_loss=0.3435, pruned_loss=0.102, over 7278.00 frames.], tot_loss[loss=0.2637, simple_loss=0.3265, pruned_loss=0.1005, over 1429876.54 frames.], batch size: 24, lr: 2.14e-03
+2022-05-13 22:05:09,270 INFO [train.py:812] (2/8) Epoch 2, batch 3800, loss[loss=0.226, simple_loss=0.2909, pruned_loss=0.08058, over 6775.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3251, pruned_loss=0.1002, over 1429495.42 frames.], batch size: 15, lr: 2.13e-03
+2022-05-13 22:06:07,966 INFO [train.py:812] (2/8) Epoch 2, batch 3850, loss[loss=0.2941, simple_loss=0.3506, pruned_loss=0.1188, over 7138.00 frames.], tot_loss[loss=0.2625, simple_loss=0.3252, pruned_loss=0.09986, over 1430897.46 frames.], batch size: 26, lr: 2.13e-03
+2022-05-13 22:07:06,194 INFO [train.py:812] (2/8) Epoch 2, batch 3900, loss[loss=0.3064, simple_loss=0.3571, pruned_loss=0.1278, over 7310.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3263, pruned_loss=0.1006, over 1429355.47 frames.], batch size: 24, lr: 2.12e-03
+2022-05-13 22:08:05,670 INFO [train.py:812] (2/8) Epoch 2, batch 3950, loss[loss=0.255, simple_loss=0.324, pruned_loss=0.09301, over 7111.00 frames.], tot_loss[loss=0.2634, simple_loss=0.326, pruned_loss=0.1004, over 1426537.94 frames.], batch size: 21, lr: 2.12e-03
+2022-05-13 22:09:04,770 INFO [train.py:812] (2/8) Epoch 2, batch 4000, loss[loss=0.2492, simple_loss=0.3272, pruned_loss=0.08557, over 7203.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3251, pruned_loss=0.09927, over 1427687.77 frames.], batch size: 22, lr: 2.11e-03
+2022-05-13 22:10:02,684 INFO [train.py:812] (2/8) Epoch 2, batch 4050, loss[loss=0.3165, simple_loss=0.3553, pruned_loss=0.1388, over 6679.00 frames.], tot_loss[loss=0.2619, simple_loss=0.325, pruned_loss=0.09936, over 1425426.47 frames.], batch size: 31, lr: 2.11e-03
+2022-05-13 22:11:01,219 INFO [train.py:812] (2/8) Epoch 2, batch 4100, loss[loss=0.2553, simple_loss=0.3195, pruned_loss=0.09553, over 7214.00 frames.], tot_loss[loss=0.2623, simple_loss=0.3255, pruned_loss=0.09953, over 1420209.56 frames.], batch size: 21, lr: 2.10e-03
+2022-05-13 22:11:59,869 INFO [train.py:812] (2/8) Epoch 2, batch 4150, loss[loss=0.2759, simple_loss=0.3337, pruned_loss=0.109, over 6743.00 frames.], tot_loss[loss=0.26, simple_loss=0.324, pruned_loss=0.09804, over 1419065.85 frames.], batch size: 31, lr: 2.10e-03
+2022-05-13 22:12:58,584 INFO [train.py:812] (2/8) Epoch 2, batch 4200, loss[loss=0.2233, simple_loss=0.2901, pruned_loss=0.07825, over 7281.00 frames.], tot_loss[loss=0.2604, simple_loss=0.3239, pruned_loss=0.09844, over 1417439.49 frames.], batch size: 18, lr: 2.10e-03
+2022-05-13 22:13:58,093 INFO [train.py:812] (2/8) Epoch 2, batch 4250, loss[loss=0.2078, simple_loss=0.2613, pruned_loss=0.07716, over 7274.00 frames.], tot_loss[loss=0.2607, simple_loss=0.324, pruned_loss=0.09876, over 1413051.76 frames.], batch size: 18, lr: 2.09e-03
+2022-05-13 22:14:56,712 INFO [train.py:812] (2/8) Epoch 2, batch 4300, loss[loss=0.2638, simple_loss=0.3394, pruned_loss=0.09412, over 7317.00 frames.], tot_loss[loss=0.2605, simple_loss=0.3237, pruned_loss=0.09862, over 1412360.45 frames.], batch size: 25, lr: 2.09e-03
+2022-05-13 22:15:55,429 INFO [train.py:812] (2/8) Epoch 2, batch 4350, loss[loss=0.2258, simple_loss=0.2853, pruned_loss=0.08319, over 6979.00 frames.], tot_loss[loss=0.2615, simple_loss=0.3246, pruned_loss=0.09922, over 1413126.81 frames.], batch size: 16, lr: 2.08e-03
+2022-05-13 22:16:54,206 INFO [train.py:812] (2/8) Epoch 2, batch 4400, loss[loss=0.2713, simple_loss=0.3303, pruned_loss=0.1061, over 7315.00 frames.], tot_loss[loss=0.2606, simple_loss=0.3237, pruned_loss=0.09873, over 1408013.45 frames.], batch size: 21, lr: 2.08e-03
+2022-05-13 22:17:52,728 INFO [train.py:812] (2/8) Epoch 2, batch 4450, loss[loss=0.2694, simple_loss=0.3189, pruned_loss=0.1099, over 6503.00 frames.], tot_loss[loss=0.2619, simple_loss=0.3246, pruned_loss=0.09957, over 1400608.63 frames.], batch size: 38, lr: 2.07e-03
+2022-05-13 22:18:50,559 INFO [train.py:812] (2/8) Epoch 2, batch 4500, loss[loss=0.2765, simple_loss=0.3328, pruned_loss=0.1101, over 6587.00 frames.], tot_loss[loss=0.2619, simple_loss=0.3239, pruned_loss=0.09995, over 1386099.60 frames.], batch size: 38, lr: 2.07e-03
+2022-05-13 22:19:49,227 INFO [train.py:812] (2/8) Epoch 2, batch 4550, loss[loss=0.2845, simple_loss=0.3278, pruned_loss=0.1206, over 4783.00 frames.], tot_loss[loss=0.2647, simple_loss=0.3261, pruned_loss=0.1016, over 1356053.02 frames.], batch size: 52, lr: 2.06e-03
+2022-05-13 22:20:58,923 INFO [train.py:812] (2/8) Epoch 3, batch 0, loss[loss=0.2204, simple_loss=0.2828, pruned_loss=0.07903, over 7269.00 frames.], tot_loss[loss=0.2204, simple_loss=0.2828, pruned_loss=0.07903, over 7269.00 frames.], batch size: 17, lr: 2.02e-03
+2022-05-13 22:21:58,061 INFO [train.py:812] (2/8) Epoch 3, batch 50, loss[loss=0.261, simple_loss=0.3257, pruned_loss=0.09818, over 7309.00 frames.], tot_loss[loss=0.2586, simple_loss=0.3218, pruned_loss=0.09772, over 321418.85 frames.], batch size: 25, lr: 2.02e-03
+2022-05-13 22:22:56,161 INFO [train.py:812] (2/8) Epoch 3, batch 100, loss[loss=0.2619, simple_loss=0.3179, pruned_loss=0.1029, over 6973.00 frames.], tot_loss[loss=0.2521, simple_loss=0.3168, pruned_loss=0.09366, over 568758.43 frames.], batch size: 16, lr: 2.01e-03
+2022-05-13 22:23:56,095 INFO [train.py:812] (2/8) Epoch 3, batch 150, loss[loss=0.2648, simple_loss=0.3221, pruned_loss=0.1038, over 6686.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3147, pruned_loss=0.09284, over 761535.48 frames.], batch size: 31, lr: 2.01e-03
+2022-05-13 22:24:53,587 INFO [train.py:812] (2/8) Epoch 3, batch 200, loss[loss=0.2152, simple_loss=0.2758, pruned_loss=0.07728, over 6774.00 frames.], tot_loss[loss=0.2528, simple_loss=0.3164, pruned_loss=0.09455, over 900395.65 frames.], batch size: 15, lr: 2.00e-03
+2022-05-13 22:25:53,019 INFO [train.py:812] (2/8) Epoch 3, batch 250, loss[loss=0.2483, simple_loss=0.3143, pruned_loss=0.09111, over 7361.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3174, pruned_loss=0.09461, over 1010756.21 frames.], batch size: 19, lr: 2.00e-03
+2022-05-13 22:26:52,124 INFO [train.py:812] (2/8) Epoch 3, batch 300, loss[loss=0.278, simple_loss=0.3397, pruned_loss=0.1081, over 6752.00 frames.], tot_loss[loss=0.2548, simple_loss=0.3192, pruned_loss=0.09518, over 1100315.56 frames.], batch size: 31, lr: 2.00e-03
+2022-05-13 22:27:52,043 INFO [train.py:812] (2/8) Epoch 3, batch 350, loss[loss=0.2648, simple_loss=0.3325, pruned_loss=0.09857, over 7318.00 frames.], tot_loss[loss=0.2553, simple_loss=0.32, pruned_loss=0.09528, over 1171513.78 frames.], batch size: 21, lr: 1.99e-03
+2022-05-13 22:29:00,803 INFO [train.py:812] (2/8) Epoch 3, batch 400, loss[loss=0.2777, simple_loss=0.3363, pruned_loss=0.1096, over 7290.00 frames.], tot_loss[loss=0.2569, simple_loss=0.3213, pruned_loss=0.09627, over 1221677.05 frames.], batch size: 24, lr: 1.99e-03
+2022-05-13 22:29:59,465 INFO [train.py:812] (2/8) Epoch 3, batch 450, loss[loss=0.2708, simple_loss=0.3445, pruned_loss=0.09854, over 7208.00 frames.], tot_loss[loss=0.2561, simple_loss=0.3211, pruned_loss=0.09556, over 1261587.05 frames.], batch size: 22, lr: 1.98e-03
+2022-05-13 22:31:07,454 INFO [train.py:812] (2/8) Epoch 3, batch 500, loss[loss=0.1992, simple_loss=0.2673, pruned_loss=0.06553, over 6992.00 frames.], tot_loss[loss=0.253, simple_loss=0.3186, pruned_loss=0.09368, over 1299744.30 frames.], batch size: 16, lr: 1.98e-03
+2022-05-13 22:32:54,336 INFO [train.py:812] (2/8) Epoch 3, batch 550, loss[loss=0.2684, simple_loss=0.3425, pruned_loss=0.09721, over 7220.00 frames.], tot_loss[loss=0.2536, simple_loss=0.3194, pruned_loss=0.09388, over 1330362.45 frames.], batch size: 21, lr: 1.98e-03
+2022-05-13 22:34:03,104 INFO [train.py:812] (2/8) Epoch 3, batch 600, loss[loss=0.3354, simple_loss=0.3928, pruned_loss=0.139, over 7246.00 frames.], tot_loss[loss=0.2529, simple_loss=0.3187, pruned_loss=0.09358, over 1351415.49 frames.], batch size: 25, lr: 1.97e-03
+2022-05-13 22:35:02,659 INFO [train.py:812] (2/8) Epoch 3, batch 650, loss[loss=0.1935, simple_loss=0.2662, pruned_loss=0.06034, over 7359.00 frames.], tot_loss[loss=0.2535, simple_loss=0.3188, pruned_loss=0.09414, over 1366764.56 frames.], batch size: 19, lr: 1.97e-03
+2022-05-13 22:36:02,056 INFO [train.py:812] (2/8) Epoch 3, batch 700, loss[loss=0.2528, simple_loss=0.3282, pruned_loss=0.08869, over 7209.00 frames.], tot_loss[loss=0.2535, simple_loss=0.319, pruned_loss=0.09405, over 1376830.20 frames.], batch size: 21, lr: 1.96e-03
+2022-05-13 22:37:01,823 INFO [train.py:812] (2/8) Epoch 3, batch 750, loss[loss=0.2715, simple_loss=0.3406, pruned_loss=0.1012, over 7176.00 frames.], tot_loss[loss=0.2539, simple_loss=0.3196, pruned_loss=0.09415, over 1390184.67 frames.], batch size: 23, lr: 1.96e-03
+2022-05-13 22:38:00,542 INFO [train.py:812] (2/8) Epoch 3, batch 800, loss[loss=0.2383, simple_loss=0.3128, pruned_loss=0.08194, over 7202.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3191, pruned_loss=0.09373, over 1400890.75 frames.], batch size: 23, lr: 1.96e-03
+2022-05-13 22:38:59,775 INFO [train.py:812] (2/8) Epoch 3, batch 850, loss[loss=0.2749, simple_loss=0.3421, pruned_loss=0.1039, over 7296.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3179, pruned_loss=0.09278, over 1408922.40 frames.], batch size: 25, lr: 1.95e-03
+2022-05-13 22:39:58,565 INFO [train.py:812] (2/8) Epoch 3, batch 900, loss[loss=0.2551, simple_loss=0.3161, pruned_loss=0.09703, over 7077.00 frames.], tot_loss[loss=0.2529, simple_loss=0.3193, pruned_loss=0.09322, over 1411340.05 frames.], batch size: 18, lr: 1.95e-03
+2022-05-13 22:40:58,628 INFO [train.py:812] (2/8) Epoch 3, batch 950, loss[loss=0.2601, simple_loss=0.3308, pruned_loss=0.09469, over 7144.00 frames.], tot_loss[loss=0.252, simple_loss=0.3188, pruned_loss=0.09265, over 1416879.97 frames.], batch size: 20, lr: 1.94e-03
+2022-05-13 22:41:58,404 INFO [train.py:812] (2/8) Epoch 3, batch 1000, loss[loss=0.262, simple_loss=0.328, pruned_loss=0.09798, over 6722.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3195, pruned_loss=0.09299, over 1416470.50 frames.], batch size: 31, lr: 1.94e-03
+2022-05-13 22:42:57,495 INFO [train.py:812] (2/8) Epoch 3, batch 1050, loss[loss=0.2399, simple_loss=0.2985, pruned_loss=0.09068, over 7297.00 frames.], tot_loss[loss=0.253, simple_loss=0.3195, pruned_loss=0.09324, over 1414604.54 frames.], batch size: 18, lr: 1.94e-03
+2022-05-13 22:43:56,791 INFO [train.py:812] (2/8) Epoch 3, batch 1100, loss[loss=0.2217, simple_loss=0.3044, pruned_loss=0.06955, over 7219.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3206, pruned_loss=0.09339, over 1419891.59 frames.], batch size: 21, lr: 1.93e-03
+2022-05-13 22:44:56,335 INFO [train.py:812] (2/8) Epoch 3, batch 1150, loss[loss=0.252, simple_loss=0.3186, pruned_loss=0.09265, over 7229.00 frames.], tot_loss[loss=0.2521, simple_loss=0.3185, pruned_loss=0.09283, over 1420633.58 frames.], batch size: 20, lr: 1.93e-03
+2022-05-13 22:45:54,824 INFO [train.py:812] (2/8) Epoch 3, batch 1200, loss[loss=0.2572, simple_loss=0.3182, pruned_loss=0.09809, over 7431.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3173, pruned_loss=0.09199, over 1424778.66 frames.], batch size: 20, lr: 1.93e-03
+2022-05-13 22:46:52,820 INFO [train.py:812] (2/8) Epoch 3, batch 1250, loss[loss=0.231, simple_loss=0.3094, pruned_loss=0.07631, over 7424.00 frames.], tot_loss[loss=0.249, simple_loss=0.3161, pruned_loss=0.09096, over 1424842.10 frames.], batch size: 21, lr: 1.92e-03
+2022-05-13 22:47:52,092 INFO [train.py:812] (2/8) Epoch 3, batch 1300, loss[loss=0.2467, simple_loss=0.3217, pruned_loss=0.08583, over 7311.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3156, pruned_loss=0.09069, over 1426158.96 frames.], batch size: 21, lr: 1.92e-03
+2022-05-13 22:48:50,082 INFO [train.py:812] (2/8) Epoch 3, batch 1350, loss[loss=0.2212, simple_loss=0.295, pruned_loss=0.07367, over 7430.00 frames.], tot_loss[loss=0.2493, simple_loss=0.3168, pruned_loss=0.09092, over 1426116.00 frames.], batch size: 20, lr: 1.91e-03
+2022-05-13 22:49:48,130 INFO [train.py:812] (2/8) Epoch 3, batch 1400, loss[loss=0.2462, simple_loss=0.3057, pruned_loss=0.09339, over 7158.00 frames.], tot_loss[loss=0.2495, simple_loss=0.3173, pruned_loss=0.09089, over 1422489.12 frames.], batch size: 19, lr: 1.91e-03
+2022-05-13 22:50:48,079 INFO [train.py:812] (2/8) Epoch 3, batch 1450, loss[loss=0.2639, simple_loss=0.3202, pruned_loss=0.1038, over 7130.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3178, pruned_loss=0.09174, over 1419985.32 frames.], batch size: 17, lr: 1.91e-03
+2022-05-13 22:51:46,936 INFO [train.py:812] (2/8) Epoch 3, batch 1500, loss[loss=0.2717, simple_loss=0.3444, pruned_loss=0.09948, over 7311.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3183, pruned_loss=0.09203, over 1418474.66 frames.], batch size: 21, lr: 1.90e-03
+2022-05-13 22:52:47,272 INFO [train.py:812] (2/8) Epoch 3, batch 1550, loss[loss=0.2272, simple_loss=0.3105, pruned_loss=0.07195, over 7170.00 frames.], tot_loss[loss=0.2493, simple_loss=0.3171, pruned_loss=0.09073, over 1422685.87 frames.], batch size: 19, lr: 1.90e-03
+2022-05-13 22:53:45,770 INFO [train.py:812] (2/8) Epoch 3, batch 1600, loss[loss=0.2203, simple_loss=0.297, pruned_loss=0.07176, over 7160.00 frames.], tot_loss[loss=0.2479, simple_loss=0.3162, pruned_loss=0.08979, over 1424331.27 frames.], batch size: 19, lr: 1.90e-03
+2022-05-13 22:54:44,638 INFO [train.py:812] (2/8) Epoch 3, batch 1650, loss[loss=0.2561, simple_loss=0.3254, pruned_loss=0.09341, over 7436.00 frames.], tot_loss[loss=0.249, simple_loss=0.3167, pruned_loss=0.09063, over 1426682.49 frames.], batch size: 20, lr: 1.89e-03
+2022-05-13 22:55:42,298 INFO [train.py:812] (2/8) Epoch 3, batch 1700, loss[loss=0.2079, simple_loss=0.2924, pruned_loss=0.06167, over 7140.00 frames.], tot_loss[loss=0.25, simple_loss=0.3176, pruned_loss=0.09123, over 1417354.34 frames.], batch size: 20, lr: 1.89e-03
+2022-05-13 22:56:41,863 INFO [train.py:812] (2/8) Epoch 3, batch 1750, loss[loss=0.2269, simple_loss=0.3031, pruned_loss=0.07538, over 7241.00 frames.], tot_loss[loss=0.2487, simple_loss=0.3169, pruned_loss=0.09031, over 1424418.29 frames.], batch size: 20, lr: 1.88e-03
+2022-05-13 22:57:40,291 INFO [train.py:812] (2/8) Epoch 3, batch 1800, loss[loss=0.2484, simple_loss=0.3241, pruned_loss=0.08641, over 7123.00 frames.], tot_loss[loss=0.2486, simple_loss=0.3166, pruned_loss=0.09025, over 1416700.46 frames.], batch size: 21, lr: 1.88e-03
+2022-05-13 22:58:39,766 INFO [train.py:812] (2/8) Epoch 3, batch 1850, loss[loss=0.2705, simple_loss=0.3296, pruned_loss=0.1057, over 7404.00 frames.], tot_loss[loss=0.2471, simple_loss=0.3151, pruned_loss=0.08954, over 1418974.27 frames.], batch size: 21, lr: 1.88e-03
+2022-05-13 22:59:38,878 INFO [train.py:812] (2/8) Epoch 3, batch 1900, loss[loss=0.2704, simple_loss=0.3348, pruned_loss=0.1029, over 7166.00 frames.], tot_loss[loss=0.2465, simple_loss=0.3146, pruned_loss=0.08915, over 1416268.53 frames.], batch size: 18, lr: 1.87e-03
+2022-05-13 23:00:38,436 INFO [train.py:812] (2/8) Epoch 3, batch 1950, loss[loss=0.2996, simple_loss=0.3588, pruned_loss=0.1203, over 6842.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3144, pruned_loss=0.0894, over 1417600.74 frames.], batch size: 31, lr: 1.87e-03
+2022-05-13 23:01:37,608 INFO [train.py:812] (2/8) Epoch 3, batch 2000, loss[loss=0.2057, simple_loss=0.2859, pruned_loss=0.0627, over 7163.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3133, pruned_loss=0.08866, over 1421225.30 frames.], batch size: 19, lr: 1.87e-03
+2022-05-13 23:02:36,935 INFO [train.py:812] (2/8) Epoch 3, batch 2050, loss[loss=0.3253, simple_loss=0.361, pruned_loss=0.1448, over 5280.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3156, pruned_loss=0.08982, over 1421070.59 frames.], batch size: 52, lr: 1.86e-03
+2022-05-13 23:03:35,452 INFO [train.py:812] (2/8) Epoch 3, batch 2100, loss[loss=0.2978, simple_loss=0.3598, pruned_loss=0.118, over 7310.00 frames.], tot_loss[loss=0.2487, simple_loss=0.3168, pruned_loss=0.09033, over 1424333.59 frames.], batch size: 21, lr: 1.86e-03
+2022-05-13 23:04:34,073 INFO [train.py:812] (2/8) Epoch 3, batch 2150, loss[loss=0.2572, simple_loss=0.3359, pruned_loss=0.08927, over 7224.00 frames.], tot_loss[loss=0.2465, simple_loss=0.3153, pruned_loss=0.08888, over 1425986.59 frames.], batch size: 20, lr: 1.86e-03
+2022-05-13 23:05:32,768 INFO [train.py:812] (2/8) Epoch 3, batch 2200, loss[loss=0.2907, simple_loss=0.3553, pruned_loss=0.113, over 7142.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3155, pruned_loss=0.08905, over 1424397.30 frames.], batch size: 20, lr: 1.85e-03
+2022-05-13 23:06:32,202 INFO [train.py:812] (2/8) Epoch 3, batch 2250, loss[loss=0.2628, simple_loss=0.3268, pruned_loss=0.09938, over 7317.00 frames.], tot_loss[loss=0.248, simple_loss=0.3167, pruned_loss=0.08962, over 1424544.21 frames.], batch size: 20, lr: 1.85e-03
+2022-05-13 23:07:31,565 INFO [train.py:812] (2/8) Epoch 3, batch 2300, loss[loss=0.2148, simple_loss=0.2937, pruned_loss=0.06791, over 7363.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3162, pruned_loss=0.08968, over 1413418.66 frames.], batch size: 19, lr: 1.85e-03
+2022-05-13 23:08:31,267 INFO [train.py:812] (2/8) Epoch 3, batch 2350, loss[loss=0.2039, simple_loss=0.274, pruned_loss=0.06694, over 7253.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3145, pruned_loss=0.0883, over 1414575.39 frames.], batch size: 19, lr: 1.84e-03
+2022-05-13 23:09:29,604 INFO [train.py:812] (2/8) Epoch 3, batch 2400, loss[loss=0.2513, simple_loss=0.3202, pruned_loss=0.09122, over 7254.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3146, pruned_loss=0.08789, over 1417641.96 frames.], batch size: 19, lr: 1.84e-03
+2022-05-13 23:10:29,108 INFO [train.py:812] (2/8) Epoch 3, batch 2450, loss[loss=0.2183, simple_loss=0.2944, pruned_loss=0.0711, over 7250.00 frames.], tot_loss[loss=0.2446, simple_loss=0.3142, pruned_loss=0.08752, over 1415552.17 frames.], batch size: 20, lr: 1.84e-03
+2022-05-13 23:11:28,078 INFO [train.py:812] (2/8) Epoch 3, batch 2500, loss[loss=0.2603, simple_loss=0.3229, pruned_loss=0.09889, over 7158.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3134, pruned_loss=0.08723, over 1414903.24 frames.], batch size: 19, lr: 1.83e-03
+2022-05-13 23:12:27,806 INFO [train.py:812] (2/8) Epoch 3, batch 2550, loss[loss=0.2721, simple_loss=0.3322, pruned_loss=0.106, over 7223.00 frames.], tot_loss[loss=0.2438, simple_loss=0.3128, pruned_loss=0.08739, over 1414267.38 frames.], batch size: 21, lr: 1.83e-03
+2022-05-13 23:13:27,135 INFO [train.py:812] (2/8) Epoch 3, batch 2600, loss[loss=0.2611, simple_loss=0.3199, pruned_loss=0.1012, over 7280.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3119, pruned_loss=0.08668, over 1420635.02 frames.], batch size: 18, lr: 1.83e-03
+2022-05-13 23:14:26,424 INFO [train.py:812] (2/8) Epoch 3, batch 2650, loss[loss=0.2345, simple_loss=0.3073, pruned_loss=0.08085, over 7323.00 frames.], tot_loss[loss=0.242, simple_loss=0.3113, pruned_loss=0.08635, over 1420076.52 frames.], batch size: 20, lr: 1.82e-03
+2022-05-13 23:15:24,413 INFO [train.py:812] (2/8) Epoch 3, batch 2700, loss[loss=0.1907, simple_loss=0.2622, pruned_loss=0.05957, over 7452.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3113, pruned_loss=0.08642, over 1422016.56 frames.], batch size: 19, lr: 1.82e-03
+2022-05-13 23:16:23,936 INFO [train.py:812] (2/8) Epoch 3, batch 2750, loss[loss=0.3319, simple_loss=0.3955, pruned_loss=0.1342, over 7148.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3117, pruned_loss=0.08646, over 1420966.26 frames.], batch size: 26, lr: 1.82e-03
+2022-05-13 23:17:22,908 INFO [train.py:812] (2/8) Epoch 3, batch 2800, loss[loss=0.2744, simple_loss=0.3322, pruned_loss=0.1083, over 4915.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3122, pruned_loss=0.08651, over 1419837.86 frames.], batch size: 55, lr: 1.81e-03
+2022-05-13 23:18:30,782 INFO [train.py:812] (2/8) Epoch 3, batch 2850, loss[loss=0.2401, simple_loss=0.3124, pruned_loss=0.08394, over 7220.00 frames.], tot_loss[loss=0.243, simple_loss=0.3124, pruned_loss=0.08677, over 1422532.08 frames.], batch size: 21, lr: 1.81e-03
+2022-05-13 23:19:29,908 INFO [train.py:812] (2/8) Epoch 3, batch 2900, loss[loss=0.2614, simple_loss=0.3269, pruned_loss=0.0979, over 6461.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3121, pruned_loss=0.08661, over 1418013.42 frames.], batch size: 38, lr: 1.81e-03
+2022-05-13 23:20:29,369 INFO [train.py:812] (2/8) Epoch 3, batch 2950, loss[loss=0.232, simple_loss=0.3071, pruned_loss=0.07847, over 7240.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3135, pruned_loss=0.08793, over 1417085.01 frames.], batch size: 26, lr: 1.80e-03
+2022-05-13 23:21:28,605 INFO [train.py:812] (2/8) Epoch 3, batch 3000, loss[loss=0.2741, simple_loss=0.3302, pruned_loss=0.109, over 7340.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3131, pruned_loss=0.08761, over 1420342.18 frames.], batch size: 22, lr: 1.80e-03
+2022-05-13 23:21:28,607 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-13 23:21:36,069 INFO [train.py:841] (2/8) Epoch 3, validation: loss=0.1862, simple_loss=0.2867, pruned_loss=0.04278, over 698248.00 frames.
+2022-05-13 23:22:33,840 INFO [train.py:812] (2/8) Epoch 3, batch 3050, loss[loss=0.2447, simple_loss=0.3099, pruned_loss=0.08975, over 7416.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3134, pruned_loss=0.08799, over 1425330.03 frames.], batch size: 21, lr: 1.80e-03
+2022-05-13 23:23:30,788 INFO [train.py:812] (2/8) Epoch 3, batch 3100, loss[loss=0.2118, simple_loss=0.2783, pruned_loss=0.07265, over 7288.00 frames.], tot_loss[loss=0.2438, simple_loss=0.3128, pruned_loss=0.08739, over 1427933.27 frames.], batch size: 18, lr: 1.79e-03
+2022-05-13 23:24:30,034 INFO [train.py:812] (2/8) Epoch 3, batch 3150, loss[loss=0.2225, simple_loss=0.305, pruned_loss=0.06999, over 7215.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3121, pruned_loss=0.08705, over 1422476.31 frames.], batch size: 21, lr: 1.79e-03
+2022-05-13 23:25:29,453 INFO [train.py:812] (2/8) Epoch 3, batch 3200, loss[loss=0.2286, simple_loss=0.3004, pruned_loss=0.07836, over 7368.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3128, pruned_loss=0.08745, over 1425928.68 frames.], batch size: 23, lr: 1.79e-03
+2022-05-13 23:26:29,121 INFO [train.py:812] (2/8) Epoch 3, batch 3250, loss[loss=0.2631, simple_loss=0.3282, pruned_loss=0.09901, over 7159.00 frames.], tot_loss[loss=0.245, simple_loss=0.3144, pruned_loss=0.08782, over 1426729.61 frames.], batch size: 19, lr: 1.79e-03
+2022-05-13 23:27:27,265 INFO [train.py:812] (2/8) Epoch 3, batch 3300, loss[loss=0.2514, simple_loss=0.3202, pruned_loss=0.09127, over 7142.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3128, pruned_loss=0.08675, over 1429061.07 frames.], batch size: 26, lr: 1.78e-03
+2022-05-13 23:28:26,178 INFO [train.py:812] (2/8) Epoch 3, batch 3350, loss[loss=0.2209, simple_loss=0.2876, pruned_loss=0.07707, over 7283.00 frames.], tot_loss[loss=0.244, simple_loss=0.3136, pruned_loss=0.08716, over 1425820.67 frames.], batch size: 18, lr: 1.78e-03
+2022-05-13 23:29:23,910 INFO [train.py:812] (2/8) Epoch 3, batch 3400, loss[loss=0.1978, simple_loss=0.2789, pruned_loss=0.05833, over 7416.00 frames.], tot_loss[loss=0.2438, simple_loss=0.3139, pruned_loss=0.08686, over 1423829.14 frames.], batch size: 18, lr: 1.78e-03
+2022-05-13 23:30:22,280 INFO [train.py:812] (2/8) Epoch 3, batch 3450, loss[loss=0.224, simple_loss=0.3094, pruned_loss=0.06932, over 7258.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3129, pruned_loss=0.08649, over 1420166.41 frames.], batch size: 19, lr: 1.77e-03
+2022-05-13 23:31:20,981 INFO [train.py:812] (2/8) Epoch 3, batch 3500, loss[loss=0.2907, simple_loss=0.3453, pruned_loss=0.1181, over 7289.00 frames.], tot_loss[loss=0.2416, simple_loss=0.3115, pruned_loss=0.08589, over 1420568.64 frames.], batch size: 25, lr: 1.77e-03
+2022-05-13 23:32:20,612 INFO [train.py:812] (2/8) Epoch 3, batch 3550, loss[loss=0.2323, simple_loss=0.3197, pruned_loss=0.07243, over 7213.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3121, pruned_loss=0.08635, over 1419409.72 frames.], batch size: 21, lr: 1.77e-03
+2022-05-13 23:33:19,898 INFO [train.py:812] (2/8) Epoch 3, batch 3600, loss[loss=0.2474, simple_loss=0.3246, pruned_loss=0.08508, over 7282.00 frames.], tot_loss[loss=0.2403, simple_loss=0.3102, pruned_loss=0.08517, over 1421137.48 frames.], batch size: 24, lr: 1.76e-03
+2022-05-13 23:34:19,533 INFO [train.py:812] (2/8) Epoch 3, batch 3650, loss[loss=0.2579, simple_loss=0.3315, pruned_loss=0.09215, over 7366.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3101, pruned_loss=0.08514, over 1420898.13 frames.], batch size: 23, lr: 1.76e-03
+2022-05-13 23:35:18,611 INFO [train.py:812] (2/8) Epoch 3, batch 3700, loss[loss=0.2079, simple_loss=0.2777, pruned_loss=0.06901, over 7408.00 frames.], tot_loss[loss=0.2406, simple_loss=0.3108, pruned_loss=0.08518, over 1416553.06 frames.], batch size: 18, lr: 1.76e-03
+2022-05-13 23:36:18,211 INFO [train.py:812] (2/8) Epoch 3, batch 3750, loss[loss=0.2589, simple_loss=0.3123, pruned_loss=0.1028, over 7283.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3106, pruned_loss=0.08464, over 1422875.43 frames.], batch size: 18, lr: 1.76e-03
+2022-05-13 23:37:16,796 INFO [train.py:812] (2/8) Epoch 3, batch 3800, loss[loss=0.2401, simple_loss=0.3133, pruned_loss=0.08346, over 7156.00 frames.], tot_loss[loss=0.239, simple_loss=0.3096, pruned_loss=0.08418, over 1423110.45 frames.], batch size: 18, lr: 1.75e-03
+2022-05-13 23:38:16,202 INFO [train.py:812] (2/8) Epoch 3, batch 3850, loss[loss=0.1993, simple_loss=0.2871, pruned_loss=0.05578, over 7340.00 frames.], tot_loss[loss=0.2397, simple_loss=0.31, pruned_loss=0.08467, over 1422676.99 frames.], batch size: 22, lr: 1.75e-03
+2022-05-13 23:39:15,483 INFO [train.py:812] (2/8) Epoch 3, batch 3900, loss[loss=0.237, simple_loss=0.3129, pruned_loss=0.08048, over 7325.00 frames.], tot_loss[loss=0.2389, simple_loss=0.3097, pruned_loss=0.08405, over 1424703.44 frames.], batch size: 20, lr: 1.75e-03
+2022-05-13 23:40:14,818 INFO [train.py:812] (2/8) Epoch 3, batch 3950, loss[loss=0.2393, simple_loss=0.3167, pruned_loss=0.08095, over 7335.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3106, pruned_loss=0.0851, over 1421375.22 frames.], batch size: 21, lr: 1.74e-03
+2022-05-13 23:41:14,031 INFO [train.py:812] (2/8) Epoch 3, batch 4000, loss[loss=0.2529, simple_loss=0.3263, pruned_loss=0.08978, over 7328.00 frames.], tot_loss[loss=0.2396, simple_loss=0.3101, pruned_loss=0.08453, over 1425817.47 frames.], batch size: 22, lr: 1.74e-03
+2022-05-13 23:42:13,750 INFO [train.py:812] (2/8) Epoch 3, batch 4050, loss[loss=0.2276, simple_loss=0.3053, pruned_loss=0.07493, over 7441.00 frames.], tot_loss[loss=0.2387, simple_loss=0.3093, pruned_loss=0.08403, over 1426505.65 frames.], batch size: 20, lr: 1.74e-03
+2022-05-13 23:43:12,783 INFO [train.py:812] (2/8) Epoch 3, batch 4100, loss[loss=0.2221, simple_loss=0.3021, pruned_loss=0.07109, over 7065.00 frames.], tot_loss[loss=0.2395, simple_loss=0.3101, pruned_loss=0.08442, over 1417027.05 frames.], batch size: 18, lr: 1.73e-03
+2022-05-13 23:44:12,465 INFO [train.py:812] (2/8) Epoch 3, batch 4150, loss[loss=0.2517, simple_loss=0.3359, pruned_loss=0.08375, over 7121.00 frames.], tot_loss[loss=0.2406, simple_loss=0.3113, pruned_loss=0.08491, over 1421842.19 frames.], batch size: 21, lr: 1.73e-03
+2022-05-13 23:45:10,715 INFO [train.py:812] (2/8) Epoch 3, batch 4200, loss[loss=0.2526, simple_loss=0.3193, pruned_loss=0.09298, over 7110.00 frames.], tot_loss[loss=0.2417, simple_loss=0.312, pruned_loss=0.08573, over 1420998.30 frames.], batch size: 28, lr: 1.73e-03
+2022-05-13 23:46:09,999 INFO [train.py:812] (2/8) Epoch 3, batch 4250, loss[loss=0.2799, simple_loss=0.3372, pruned_loss=0.1112, over 7217.00 frames.], tot_loss[loss=0.241, simple_loss=0.3113, pruned_loss=0.08541, over 1422111.69 frames.], batch size: 22, lr: 1.73e-03
+2022-05-13 23:47:09,080 INFO [train.py:812] (2/8) Epoch 3, batch 4300, loss[loss=0.2288, simple_loss=0.3031, pruned_loss=0.07728, over 7067.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3121, pruned_loss=0.08585, over 1423903.48 frames.], batch size: 18, lr: 1.72e-03
+2022-05-13 23:48:08,221 INFO [train.py:812] (2/8) Epoch 3, batch 4350, loss[loss=0.2405, simple_loss=0.3141, pruned_loss=0.08345, over 7140.00 frames.], tot_loss[loss=0.24, simple_loss=0.3106, pruned_loss=0.08472, over 1424842.01 frames.], batch size: 20, lr: 1.72e-03
+2022-05-13 23:49:06,722 INFO [train.py:812] (2/8) Epoch 3, batch 4400, loss[loss=0.2748, simple_loss=0.3454, pruned_loss=0.1021, over 7284.00 frames.], tot_loss[loss=0.2395, simple_loss=0.3097, pruned_loss=0.0846, over 1419551.29 frames.], batch size: 25, lr: 1.72e-03
+2022-05-13 23:50:05,671 INFO [train.py:812] (2/8) Epoch 3, batch 4450, loss[loss=0.2463, simple_loss=0.3255, pruned_loss=0.08359, over 7333.00 frames.], tot_loss[loss=0.2405, simple_loss=0.3109, pruned_loss=0.08506, over 1411983.93 frames.], batch size: 22, lr: 1.71e-03
+2022-05-13 23:51:04,262 INFO [train.py:812] (2/8) Epoch 3, batch 4500, loss[loss=0.2201, simple_loss=0.3083, pruned_loss=0.06593, over 7113.00 frames.], tot_loss[loss=0.2414, simple_loss=0.312, pruned_loss=0.0854, over 1406359.10 frames.], batch size: 21, lr: 1.71e-03
+2022-05-13 23:52:01,825 INFO [train.py:812] (2/8) Epoch 3, batch 4550, loss[loss=0.3072, simple_loss=0.3658, pruned_loss=0.1242, over 6241.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3152, pruned_loss=0.08799, over 1378441.33 frames.], batch size: 37, lr: 1.71e-03
+2022-05-13 23:53:11,479 INFO [train.py:812] (2/8) Epoch 4, batch 0, loss[loss=0.2425, simple_loss=0.3255, pruned_loss=0.07976, over 7196.00 frames.], tot_loss[loss=0.2425, simple_loss=0.3255, pruned_loss=0.07976, over 7196.00 frames.], batch size: 23, lr: 1.66e-03
+2022-05-13 23:54:10,765 INFO [train.py:812] (2/8) Epoch 4, batch 50, loss[loss=0.2312, simple_loss=0.2995, pruned_loss=0.0814, over 7276.00 frames.], tot_loss[loss=0.2317, simple_loss=0.303, pruned_loss=0.08016, over 317912.16 frames.], batch size: 17, lr: 1.66e-03
+2022-05-13 23:55:09,413 INFO [train.py:812] (2/8) Epoch 4, batch 100, loss[loss=0.2314, simple_loss=0.2836, pruned_loss=0.08963, over 7284.00 frames.], tot_loss[loss=0.2299, simple_loss=0.3013, pruned_loss=0.07927, over 564468.20 frames.], batch size: 17, lr: 1.65e-03
+2022-05-13 23:56:09,341 INFO [train.py:812] (2/8) Epoch 4, batch 150, loss[loss=0.2026, simple_loss=0.2933, pruned_loss=0.05593, over 7344.00 frames.], tot_loss[loss=0.2299, simple_loss=0.3024, pruned_loss=0.07872, over 754980.53 frames.], batch size: 22, lr: 1.65e-03
+2022-05-13 23:57:08,450 INFO [train.py:812] (2/8) Epoch 4, batch 200, loss[loss=0.299, simple_loss=0.3575, pruned_loss=0.1203, over 7187.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3048, pruned_loss=0.08015, over 904086.73 frames.], batch size: 23, lr: 1.65e-03
+2022-05-13 23:58:07,160 INFO [train.py:812] (2/8) Epoch 4, batch 250, loss[loss=0.238, simple_loss=0.3269, pruned_loss=0.07457, over 7320.00 frames.], tot_loss[loss=0.234, simple_loss=0.3071, pruned_loss=0.08041, over 1016736.27 frames.], batch size: 22, lr: 1.64e-03
+2022-05-13 23:59:06,606 INFO [train.py:812] (2/8) Epoch 4, batch 300, loss[loss=0.2609, simple_loss=0.3339, pruned_loss=0.09393, over 7378.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3062, pruned_loss=0.0804, over 1111219.70 frames.], batch size: 23, lr: 1.64e-03
+2022-05-14 00:00:06,134 INFO [train.py:812] (2/8) Epoch 4, batch 350, loss[loss=0.2108, simple_loss=0.3032, pruned_loss=0.05918, over 7320.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3062, pruned_loss=0.07982, over 1183253.42 frames.], batch size: 21, lr: 1.64e-03
+2022-05-14 00:01:05,123 INFO [train.py:812] (2/8) Epoch 4, batch 400, loss[loss=0.195, simple_loss=0.2811, pruned_loss=0.05442, over 7232.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3049, pruned_loss=0.07949, over 1232299.00 frames.], batch size: 20, lr: 1.64e-03
+2022-05-14 00:02:04,542 INFO [train.py:812] (2/8) Epoch 4, batch 450, loss[loss=0.222, simple_loss=0.302, pruned_loss=0.07098, over 7144.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3043, pruned_loss=0.0793, over 1273859.35 frames.], batch size: 20, lr: 1.63e-03
+2022-05-14 00:03:03,241 INFO [train.py:812] (2/8) Epoch 4, batch 500, loss[loss=0.2038, simple_loss=0.2832, pruned_loss=0.06222, over 7159.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3062, pruned_loss=0.08009, over 1302856.90 frames.], batch size: 19, lr: 1.63e-03
+2022-05-14 00:04:02,751 INFO [train.py:812] (2/8) Epoch 4, batch 550, loss[loss=0.2439, simple_loss=0.3102, pruned_loss=0.08876, over 7174.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3061, pruned_loss=0.08, over 1329055.80 frames.], batch size: 18, lr: 1.63e-03
+2022-05-14 00:05:01,441 INFO [train.py:812] (2/8) Epoch 4, batch 600, loss[loss=0.2635, simple_loss=0.3373, pruned_loss=0.09486, over 6383.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3051, pruned_loss=0.07974, over 1347049.38 frames.], batch size: 37, lr: 1.63e-03
+2022-05-14 00:06:00,905 INFO [train.py:812] (2/8) Epoch 4, batch 650, loss[loss=0.2357, simple_loss=0.313, pruned_loss=0.07925, over 7429.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3045, pruned_loss=0.07884, over 1367502.35 frames.], batch size: 20, lr: 1.62e-03
+2022-05-14 00:07:00,242 INFO [train.py:812] (2/8) Epoch 4, batch 700, loss[loss=0.2579, simple_loss=0.3225, pruned_loss=0.09662, over 7249.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3031, pruned_loss=0.07797, over 1385223.66 frames.], batch size: 24, lr: 1.62e-03
+2022-05-14 00:07:59,209 INFO [train.py:812] (2/8) Epoch 4, batch 750, loss[loss=0.248, simple_loss=0.321, pruned_loss=0.08753, over 7311.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3032, pruned_loss=0.07859, over 1393056.17 frames.], batch size: 24, lr: 1.62e-03
+2022-05-14 00:08:58,467 INFO [train.py:812] (2/8) Epoch 4, batch 800, loss[loss=0.224, simple_loss=0.295, pruned_loss=0.07649, over 7253.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3035, pruned_loss=0.0785, over 1397080.37 frames.], batch size: 19, lr: 1.62e-03
+2022-05-14 00:09:58,459 INFO [train.py:812] (2/8) Epoch 4, batch 850, loss[loss=0.1949, simple_loss=0.2821, pruned_loss=0.05388, over 7066.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3043, pruned_loss=0.07913, over 1407542.85 frames.], batch size: 18, lr: 1.61e-03
+2022-05-14 00:10:57,737 INFO [train.py:812] (2/8) Epoch 4, batch 900, loss[loss=0.2397, simple_loss=0.3248, pruned_loss=0.07726, over 7107.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3034, pruned_loss=0.07857, over 1414744.99 frames.], batch size: 21, lr: 1.61e-03
+2022-05-14 00:11:56,762 INFO [train.py:812] (2/8) Epoch 4, batch 950, loss[loss=0.2429, simple_loss=0.3228, pruned_loss=0.08149, over 7196.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3046, pruned_loss=0.07905, over 1419890.49 frames.], batch size: 26, lr: 1.61e-03
+2022-05-14 00:12:55,423 INFO [train.py:812] (2/8) Epoch 4, batch 1000, loss[loss=0.2092, simple_loss=0.2821, pruned_loss=0.06816, over 7293.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3043, pruned_loss=0.07948, over 1419739.01 frames.], batch size: 18, lr: 1.61e-03
+2022-05-14 00:13:54,564 INFO [train.py:812] (2/8) Epoch 4, batch 1050, loss[loss=0.269, simple_loss=0.3304, pruned_loss=0.1038, over 6841.00 frames.], tot_loss[loss=0.232, simple_loss=0.3049, pruned_loss=0.07954, over 1419066.24 frames.], batch size: 31, lr: 1.60e-03
+2022-05-14 00:14:53,557 INFO [train.py:812] (2/8) Epoch 4, batch 1100, loss[loss=0.2304, simple_loss=0.3134, pruned_loss=0.07371, over 7415.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3044, pruned_loss=0.07903, over 1420305.23 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:15:52,721 INFO [train.py:812] (2/8) Epoch 4, batch 1150, loss[loss=0.2425, simple_loss=0.324, pruned_loss=0.08049, over 7322.00 frames.], tot_loss[loss=0.232, simple_loss=0.3054, pruned_loss=0.07927, over 1417849.47 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:16:51,392 INFO [train.py:812] (2/8) Epoch 4, batch 1200, loss[loss=0.2063, simple_loss=0.2922, pruned_loss=0.06017, over 7313.00 frames.], tot_loss[loss=0.2324, simple_loss=0.306, pruned_loss=0.07945, over 1415560.00 frames.], batch size: 21, lr: 1.60e-03
+2022-05-14 00:17:50,409 INFO [train.py:812] (2/8) Epoch 4, batch 1250, loss[loss=0.17, simple_loss=0.2432, pruned_loss=0.04838, over 7212.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3056, pruned_loss=0.07903, over 1413789.01 frames.], batch size: 16, lr: 1.59e-03
+2022-05-14 00:18:48,729 INFO [train.py:812] (2/8) Epoch 4, batch 1300, loss[loss=0.2204, simple_loss=0.309, pruned_loss=0.06584, over 7195.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3043, pruned_loss=0.07825, over 1417332.05 frames.], batch size: 23, lr: 1.59e-03
+2022-05-14 00:19:47,559 INFO [train.py:812] (2/8) Epoch 4, batch 1350, loss[loss=0.2271, simple_loss=0.2981, pruned_loss=0.078, over 7241.00 frames.], tot_loss[loss=0.232, simple_loss=0.3054, pruned_loss=0.07925, over 1416906.18 frames.], batch size: 20, lr: 1.59e-03
+2022-05-14 00:20:44,855 INFO [train.py:812] (2/8) Epoch 4, batch 1400, loss[loss=0.2767, simple_loss=0.3441, pruned_loss=0.1046, over 7197.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3051, pruned_loss=0.07908, over 1419843.80 frames.], batch size: 22, lr: 1.59e-03
+2022-05-14 00:21:44,655 INFO [train.py:812] (2/8) Epoch 4, batch 1450, loss[loss=0.2444, simple_loss=0.3273, pruned_loss=0.08074, over 7310.00 frames.], tot_loss[loss=0.2322, simple_loss=0.306, pruned_loss=0.0792, over 1421875.83 frames.], batch size: 24, lr: 1.59e-03
+2022-05-14 00:22:43,709 INFO [train.py:812] (2/8) Epoch 4, batch 1500, loss[loss=0.2525, simple_loss=0.3217, pruned_loss=0.09168, over 7312.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3052, pruned_loss=0.07879, over 1419239.51 frames.], batch size: 24, lr: 1.58e-03
+2022-05-14 00:23:43,449 INFO [train.py:812] (2/8) Epoch 4, batch 1550, loss[loss=0.267, simple_loss=0.3297, pruned_loss=0.1021, over 5167.00 frames.], tot_loss[loss=0.231, simple_loss=0.3047, pruned_loss=0.07861, over 1417507.00 frames.], batch size: 52, lr: 1.58e-03
+2022-05-14 00:24:41,370 INFO [train.py:812] (2/8) Epoch 4, batch 1600, loss[loss=0.2194, simple_loss=0.3028, pruned_loss=0.06801, over 7335.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3058, pruned_loss=0.07918, over 1413920.78 frames.], batch size: 25, lr: 1.58e-03
+2022-05-14 00:25:40,740 INFO [train.py:812] (2/8) Epoch 4, batch 1650, loss[loss=0.2199, simple_loss=0.3079, pruned_loss=0.066, over 7329.00 frames.], tot_loss[loss=0.23, simple_loss=0.3037, pruned_loss=0.07811, over 1415120.96 frames.], batch size: 20, lr: 1.58e-03
+2022-05-14 00:26:39,532 INFO [train.py:812] (2/8) Epoch 4, batch 1700, loss[loss=0.2331, simple_loss=0.303, pruned_loss=0.08165, over 7146.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3035, pruned_loss=0.07745, over 1419057.94 frames.], batch size: 20, lr: 1.57e-03
+2022-05-14 00:27:38,786 INFO [train.py:812] (2/8) Epoch 4, batch 1750, loss[loss=0.2463, simple_loss=0.3277, pruned_loss=0.08239, over 7215.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3042, pruned_loss=0.07768, over 1418295.18 frames.], batch size: 22, lr: 1.57e-03
+2022-05-14 00:28:45,524 INFO [train.py:812] (2/8) Epoch 4, batch 1800, loss[loss=0.1965, simple_loss=0.2775, pruned_loss=0.0577, over 7220.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3064, pruned_loss=0.07925, over 1420086.12 frames.], batch size: 21, lr: 1.57e-03
+2022-05-14 00:29:45,164 INFO [train.py:812] (2/8) Epoch 4, batch 1850, loss[loss=0.2123, simple_loss=0.2855, pruned_loss=0.06955, over 7145.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3059, pruned_loss=0.07863, over 1419594.14 frames.], batch size: 17, lr: 1.57e-03
+2022-05-14 00:30:44,404 INFO [train.py:812] (2/8) Epoch 4, batch 1900, loss[loss=0.2035, simple_loss=0.2801, pruned_loss=0.06351, over 7160.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3058, pruned_loss=0.07856, over 1423001.19 frames.], batch size: 19, lr: 1.56e-03
+2022-05-14 00:31:43,797 INFO [train.py:812] (2/8) Epoch 4, batch 1950, loss[loss=0.2565, simple_loss=0.3232, pruned_loss=0.09491, over 6276.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3052, pruned_loss=0.0778, over 1427956.32 frames.], batch size: 37, lr: 1.56e-03
+2022-05-14 00:32:40,427 INFO [train.py:812] (2/8) Epoch 4, batch 2000, loss[loss=0.2547, simple_loss=0.3252, pruned_loss=0.09213, over 7103.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3057, pruned_loss=0.07832, over 1425252.30 frames.], batch size: 21, lr: 1.56e-03
+2022-05-14 00:34:15,587 INFO [train.py:812] (2/8) Epoch 4, batch 2050, loss[loss=0.237, simple_loss=0.309, pruned_loss=0.08255, over 6822.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3057, pruned_loss=0.07874, over 1422631.41 frames.], batch size: 31, lr: 1.56e-03
+2022-05-14 00:35:41,818 INFO [train.py:812] (2/8) Epoch 4, batch 2100, loss[loss=0.2341, simple_loss=0.3108, pruned_loss=0.07867, over 7320.00 frames.], tot_loss[loss=0.2308, simple_loss=0.305, pruned_loss=0.07829, over 1421261.16 frames.], batch size: 21, lr: 1.56e-03
+2022-05-14 00:36:41,407 INFO [train.py:812] (2/8) Epoch 4, batch 2150, loss[loss=0.1954, simple_loss=0.279, pruned_loss=0.05588, over 7339.00 frames.], tot_loss[loss=0.23, simple_loss=0.3039, pruned_loss=0.07806, over 1423301.18 frames.], batch size: 22, lr: 1.55e-03
+2022-05-14 00:37:40,432 INFO [train.py:812] (2/8) Epoch 4, batch 2200, loss[loss=0.2067, simple_loss=0.2984, pruned_loss=0.05755, over 7210.00 frames.], tot_loss[loss=0.2288, simple_loss=0.3028, pruned_loss=0.07739, over 1425604.10 frames.], batch size: 21, lr: 1.55e-03
+2022-05-14 00:38:47,586 INFO [train.py:812] (2/8) Epoch 4, batch 2250, loss[loss=0.3394, simple_loss=0.3679, pruned_loss=0.1554, over 4991.00 frames.], tot_loss[loss=0.2286, simple_loss=0.303, pruned_loss=0.07712, over 1427866.90 frames.], batch size: 52, lr: 1.55e-03
+2022-05-14 00:39:45,547 INFO [train.py:812] (2/8) Epoch 4, batch 2300, loss[loss=0.216, simple_loss=0.289, pruned_loss=0.07154, over 7167.00 frames.], tot_loss[loss=0.2289, simple_loss=0.3034, pruned_loss=0.07721, over 1430361.58 frames.], batch size: 19, lr: 1.55e-03
+2022-05-14 00:40:45,380 INFO [train.py:812] (2/8) Epoch 4, batch 2350, loss[loss=0.2252, simple_loss=0.3067, pruned_loss=0.0718, over 7328.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3021, pruned_loss=0.07638, over 1431516.92 frames.], batch size: 20, lr: 1.54e-03
+2022-05-14 00:41:44,198 INFO [train.py:812] (2/8) Epoch 4, batch 2400, loss[loss=0.2475, simple_loss=0.3243, pruned_loss=0.08529, over 7302.00 frames.], tot_loss[loss=0.2287, simple_loss=0.3035, pruned_loss=0.07695, over 1433353.29 frames.], batch size: 25, lr: 1.54e-03
+2022-05-14 00:42:43,279 INFO [train.py:812] (2/8) Epoch 4, batch 2450, loss[loss=0.2583, simple_loss=0.3337, pruned_loss=0.09142, over 7354.00 frames.], tot_loss[loss=0.2292, simple_loss=0.3038, pruned_loss=0.07727, over 1436305.20 frames.], batch size: 23, lr: 1.54e-03
+2022-05-14 00:43:42,439 INFO [train.py:812] (2/8) Epoch 4, batch 2500, loss[loss=0.2002, simple_loss=0.2746, pruned_loss=0.0629, over 7155.00 frames.], tot_loss[loss=0.2293, simple_loss=0.304, pruned_loss=0.07726, over 1433662.36 frames.], batch size: 19, lr: 1.54e-03
+2022-05-14 00:44:40,437 INFO [train.py:812] (2/8) Epoch 4, batch 2550, loss[loss=0.2006, simple_loss=0.2757, pruned_loss=0.06268, over 7404.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3038, pruned_loss=0.07769, over 1425972.15 frames.], batch size: 18, lr: 1.54e-03
+2022-05-14 00:45:38,428 INFO [train.py:812] (2/8) Epoch 4, batch 2600, loss[loss=0.2086, simple_loss=0.2954, pruned_loss=0.06095, over 7238.00 frames.], tot_loss[loss=0.231, simple_loss=0.3053, pruned_loss=0.07839, over 1425934.53 frames.], batch size: 20, lr: 1.53e-03
+2022-05-14 00:46:37,705 INFO [train.py:812] (2/8) Epoch 4, batch 2650, loss[loss=0.199, simple_loss=0.2713, pruned_loss=0.06332, over 6999.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3058, pruned_loss=0.07869, over 1419318.21 frames.], batch size: 16, lr: 1.53e-03
+2022-05-14 00:47:36,752 INFO [train.py:812] (2/8) Epoch 4, batch 2700, loss[loss=0.1712, simple_loss=0.2507, pruned_loss=0.04588, over 6765.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3053, pruned_loss=0.0782, over 1417681.12 frames.], batch size: 15, lr: 1.53e-03
+2022-05-14 00:48:35,547 INFO [train.py:812] (2/8) Epoch 4, batch 2750, loss[loss=0.2168, simple_loss=0.29, pruned_loss=0.07173, over 7260.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3054, pruned_loss=0.07797, over 1421233.08 frames.], batch size: 19, lr: 1.53e-03
+2022-05-14 00:49:34,107 INFO [train.py:812] (2/8) Epoch 4, batch 2800, loss[loss=0.1789, simple_loss=0.2543, pruned_loss=0.05175, over 7156.00 frames.], tot_loss[loss=0.2287, simple_loss=0.3037, pruned_loss=0.07692, over 1424346.64 frames.], batch size: 19, lr: 1.53e-03
+2022-05-14 00:50:32,970 INFO [train.py:812] (2/8) Epoch 4, batch 2850, loss[loss=0.3088, simple_loss=0.3594, pruned_loss=0.129, over 5110.00 frames.], tot_loss[loss=0.228, simple_loss=0.3027, pruned_loss=0.07667, over 1423905.28 frames.], batch size: 52, lr: 1.52e-03
+2022-05-14 00:51:31,212 INFO [train.py:812] (2/8) Epoch 4, batch 2900, loss[loss=0.2529, simple_loss=0.3317, pruned_loss=0.08704, over 6801.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3024, pruned_loss=0.07645, over 1424245.23 frames.], batch size: 31, lr: 1.52e-03
+2022-05-14 00:52:31,096 INFO [train.py:812] (2/8) Epoch 4, batch 2950, loss[loss=0.209, simple_loss=0.2952, pruned_loss=0.06141, over 7023.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3015, pruned_loss=0.0757, over 1428153.79 frames.], batch size: 28, lr: 1.52e-03
+2022-05-14 00:53:30,062 INFO [train.py:812] (2/8) Epoch 4, batch 3000, loss[loss=0.2264, simple_loss=0.3037, pruned_loss=0.07456, over 7151.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3033, pruned_loss=0.07675, over 1426603.14 frames.], batch size: 20, lr: 1.52e-03
+2022-05-14 00:53:30,063 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 00:53:37,753 INFO [train.py:841] (2/8) Epoch 4, validation: loss=0.1771, simple_loss=0.279, pruned_loss=0.03761, over 698248.00 frames.
+2022-05-14 00:54:36,382 INFO [train.py:812] (2/8) Epoch 4, batch 3050, loss[loss=0.2586, simple_loss=0.3353, pruned_loss=0.09097, over 7116.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3026, pruned_loss=0.07633, over 1421965.77 frames.], batch size: 21, lr: 1.51e-03
+2022-05-14 00:55:35,281 INFO [train.py:812] (2/8) Epoch 4, batch 3100, loss[loss=0.2358, simple_loss=0.3232, pruned_loss=0.0742, over 7306.00 frames.], tot_loss[loss=0.2272, simple_loss=0.302, pruned_loss=0.07624, over 1419010.48 frames.], batch size: 24, lr: 1.51e-03
+2022-05-14 00:56:35,204 INFO [train.py:812] (2/8) Epoch 4, batch 3150, loss[loss=0.2174, simple_loss=0.3029, pruned_loss=0.0659, over 7289.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3014, pruned_loss=0.07592, over 1423875.69 frames.], batch size: 25, lr: 1.51e-03
+2022-05-14 00:57:33,590 INFO [train.py:812] (2/8) Epoch 4, batch 3200, loss[loss=0.2293, simple_loss=0.2986, pruned_loss=0.08003, over 7060.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3012, pruned_loss=0.07584, over 1424636.96 frames.], batch size: 18, lr: 1.51e-03
+2022-05-14 00:58:32,692 INFO [train.py:812] (2/8) Epoch 4, batch 3250, loss[loss=0.1896, simple_loss=0.269, pruned_loss=0.05507, over 7256.00 frames.], tot_loss[loss=0.2284, simple_loss=0.3025, pruned_loss=0.07713, over 1424795.40 frames.], batch size: 19, lr: 1.51e-03
+2022-05-14 00:59:30,506 INFO [train.py:812] (2/8) Epoch 4, batch 3300, loss[loss=0.2527, simple_loss=0.3234, pruned_loss=0.09105, over 7215.00 frames.], tot_loss[loss=0.2276, simple_loss=0.3022, pruned_loss=0.0765, over 1423468.06 frames.], batch size: 23, lr: 1.50e-03
+2022-05-14 01:00:29,643 INFO [train.py:812] (2/8) Epoch 4, batch 3350, loss[loss=0.2853, simple_loss=0.3584, pruned_loss=0.1061, over 6324.00 frames.], tot_loss[loss=0.227, simple_loss=0.3014, pruned_loss=0.0763, over 1421669.91 frames.], batch size: 37, lr: 1.50e-03
+2022-05-14 01:01:28,321 INFO [train.py:812] (2/8) Epoch 4, batch 3400, loss[loss=0.1659, simple_loss=0.2427, pruned_loss=0.04458, over 6997.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3009, pruned_loss=0.07584, over 1422221.55 frames.], batch size: 16, lr: 1.50e-03
+2022-05-14 01:02:28,067 INFO [train.py:812] (2/8) Epoch 4, batch 3450, loss[loss=0.2055, simple_loss=0.2773, pruned_loss=0.06684, over 7165.00 frames.], tot_loss[loss=0.225, simple_loss=0.2998, pruned_loss=0.07514, over 1426899.90 frames.], batch size: 18, lr: 1.50e-03
+2022-05-14 01:03:26,382 INFO [train.py:812] (2/8) Epoch 4, batch 3500, loss[loss=0.2173, simple_loss=0.3007, pruned_loss=0.06697, over 7389.00 frames.], tot_loss[loss=0.2239, simple_loss=0.2989, pruned_loss=0.07448, over 1428600.46 frames.], batch size: 23, lr: 1.50e-03
+2022-05-14 01:04:26,017 INFO [train.py:812] (2/8) Epoch 4, batch 3550, loss[loss=0.2609, simple_loss=0.3212, pruned_loss=0.1003, over 7286.00 frames.], tot_loss[loss=0.2225, simple_loss=0.2973, pruned_loss=0.07385, over 1429264.51 frames.], batch size: 24, lr: 1.49e-03
+2022-05-14 01:05:25,248 INFO [train.py:812] (2/8) Epoch 4, batch 3600, loss[loss=0.2352, simple_loss=0.2875, pruned_loss=0.09147, over 6985.00 frames.], tot_loss[loss=0.2235, simple_loss=0.2984, pruned_loss=0.07429, over 1428010.33 frames.], batch size: 16, lr: 1.49e-03
+2022-05-14 01:06:24,746 INFO [train.py:812] (2/8) Epoch 4, batch 3650, loss[loss=0.199, simple_loss=0.272, pruned_loss=0.06299, over 7130.00 frames.], tot_loss[loss=0.223, simple_loss=0.298, pruned_loss=0.07398, over 1427775.43 frames.], batch size: 17, lr: 1.49e-03
+2022-05-14 01:07:24,235 INFO [train.py:812] (2/8) Epoch 4, batch 3700, loss[loss=0.1824, simple_loss=0.2542, pruned_loss=0.05528, over 7010.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2977, pruned_loss=0.07381, over 1427057.72 frames.], batch size: 16, lr: 1.49e-03
+2022-05-14 01:08:24,372 INFO [train.py:812] (2/8) Epoch 4, batch 3750, loss[loss=0.2493, simple_loss=0.3135, pruned_loss=0.09255, over 7437.00 frames.], tot_loss[loss=0.2223, simple_loss=0.2971, pruned_loss=0.07377, over 1425101.10 frames.], batch size: 20, lr: 1.49e-03
+2022-05-14 01:09:22,779 INFO [train.py:812] (2/8) Epoch 4, batch 3800, loss[loss=0.2234, simple_loss=0.3012, pruned_loss=0.07276, over 7457.00 frames.], tot_loss[loss=0.2237, simple_loss=0.2985, pruned_loss=0.0744, over 1421809.80 frames.], batch size: 19, lr: 1.48e-03
+2022-05-14 01:10:22,616 INFO [train.py:812] (2/8) Epoch 4, batch 3850, loss[loss=0.2119, simple_loss=0.2831, pruned_loss=0.07036, over 7421.00 frames.], tot_loss[loss=0.2221, simple_loss=0.2972, pruned_loss=0.07345, over 1425124.62 frames.], batch size: 18, lr: 1.48e-03
+2022-05-14 01:11:21,496 INFO [train.py:812] (2/8) Epoch 4, batch 3900, loss[loss=0.2946, simple_loss=0.343, pruned_loss=0.1231, over 5182.00 frames.], tot_loss[loss=0.2241, simple_loss=0.2987, pruned_loss=0.07472, over 1426332.44 frames.], batch size: 52, lr: 1.48e-03
+2022-05-14 01:12:20,483 INFO [train.py:812] (2/8) Epoch 4, batch 3950, loss[loss=0.1995, simple_loss=0.2625, pruned_loss=0.06823, over 6755.00 frames.], tot_loss[loss=0.2231, simple_loss=0.298, pruned_loss=0.07413, over 1424509.48 frames.], batch size: 15, lr: 1.48e-03
+2022-05-14 01:13:19,410 INFO [train.py:812] (2/8) Epoch 4, batch 4000, loss[loss=0.1976, simple_loss=0.2918, pruned_loss=0.05168, over 7211.00 frames.], tot_loss[loss=0.224, simple_loss=0.2987, pruned_loss=0.07468, over 1416605.40 frames.], batch size: 21, lr: 1.48e-03
+2022-05-14 01:14:18,991 INFO [train.py:812] (2/8) Epoch 4, batch 4050, loss[loss=0.2371, simple_loss=0.3162, pruned_loss=0.079, over 7413.00 frames.], tot_loss[loss=0.2247, simple_loss=0.2993, pruned_loss=0.07506, over 1419011.15 frames.], batch size: 21, lr: 1.47e-03
+2022-05-14 01:15:18,247 INFO [train.py:812] (2/8) Epoch 4, batch 4100, loss[loss=0.2598, simple_loss=0.3174, pruned_loss=0.1011, over 6191.00 frames.], tot_loss[loss=0.2255, simple_loss=0.2999, pruned_loss=0.07554, over 1421141.26 frames.], batch size: 37, lr: 1.47e-03
+2022-05-14 01:16:17,163 INFO [train.py:812] (2/8) Epoch 4, batch 4150, loss[loss=0.212, simple_loss=0.2836, pruned_loss=0.07017, over 7004.00 frames.], tot_loss[loss=0.2243, simple_loss=0.299, pruned_loss=0.07486, over 1422919.55 frames.], batch size: 16, lr: 1.47e-03
+2022-05-14 01:17:15,915 INFO [train.py:812] (2/8) Epoch 4, batch 4200, loss[loss=0.2086, simple_loss=0.2987, pruned_loss=0.05923, over 7151.00 frames.], tot_loss[loss=0.2238, simple_loss=0.2989, pruned_loss=0.07433, over 1421499.12 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:18:15,905 INFO [train.py:812] (2/8) Epoch 4, batch 4250, loss[loss=0.1944, simple_loss=0.2736, pruned_loss=0.05759, over 7370.00 frames.], tot_loss[loss=0.2225, simple_loss=0.2977, pruned_loss=0.07365, over 1412765.48 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:19:14,765 INFO [train.py:812] (2/8) Epoch 4, batch 4300, loss[loss=0.2188, simple_loss=0.2915, pruned_loss=0.07302, over 7351.00 frames.], tot_loss[loss=0.222, simple_loss=0.2967, pruned_loss=0.07362, over 1411177.58 frames.], batch size: 19, lr: 1.47e-03
+2022-05-14 01:20:14,300 INFO [train.py:812] (2/8) Epoch 4, batch 4350, loss[loss=0.2807, simple_loss=0.3492, pruned_loss=0.1061, over 6569.00 frames.], tot_loss[loss=0.2208, simple_loss=0.2951, pruned_loss=0.07323, over 1409226.30 frames.], batch size: 38, lr: 1.46e-03
+2022-05-14 01:21:13,825 INFO [train.py:812] (2/8) Epoch 4, batch 4400, loss[loss=0.2129, simple_loss=0.2828, pruned_loss=0.07149, over 7070.00 frames.], tot_loss[loss=0.22, simple_loss=0.2942, pruned_loss=0.07287, over 1409398.45 frames.], batch size: 18, lr: 1.46e-03
+2022-05-14 01:22:13,500 INFO [train.py:812] (2/8) Epoch 4, batch 4450, loss[loss=0.2067, simple_loss=0.2986, pruned_loss=0.05742, over 7382.00 frames.], tot_loss[loss=0.221, simple_loss=0.2945, pruned_loss=0.07373, over 1399989.35 frames.], batch size: 23, lr: 1.46e-03
+2022-05-14 01:23:11,881 INFO [train.py:812] (2/8) Epoch 4, batch 4500, loss[loss=0.2463, simple_loss=0.32, pruned_loss=0.08635, over 6542.00 frames.], tot_loss[loss=0.2214, simple_loss=0.2952, pruned_loss=0.07379, over 1395494.44 frames.], batch size: 38, lr: 1.46e-03
+2022-05-14 01:24:10,627 INFO [train.py:812] (2/8) Epoch 4, batch 4550, loss[loss=0.2543, simple_loss=0.3207, pruned_loss=0.09395, over 5590.00 frames.], tot_loss[loss=0.2251, simple_loss=0.2985, pruned_loss=0.07592, over 1361142.35 frames.], batch size: 53, lr: 1.46e-03
+2022-05-14 01:25:17,917 INFO [train.py:812] (2/8) Epoch 5, batch 0, loss[loss=0.2505, simple_loss=0.3282, pruned_loss=0.08636, over 7179.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3282, pruned_loss=0.08636, over 7179.00 frames.], batch size: 23, lr: 1.40e-03
+2022-05-14 01:26:16,020 INFO [train.py:812] (2/8) Epoch 5, batch 50, loss[loss=0.2348, simple_loss=0.3152, pruned_loss=0.07725, over 7339.00 frames.], tot_loss[loss=0.2199, simple_loss=0.2965, pruned_loss=0.07165, over 320738.81 frames.], batch size: 22, lr: 1.40e-03
+2022-05-14 01:27:13,781 INFO [train.py:812] (2/8) Epoch 5, batch 100, loss[loss=0.2302, simple_loss=0.3166, pruned_loss=0.07193, over 7336.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2995, pruned_loss=0.07358, over 566959.81 frames.], batch size: 22, lr: 1.40e-03
+2022-05-14 01:28:13,019 INFO [train.py:812] (2/8) Epoch 5, batch 150, loss[loss=0.2533, simple_loss=0.3209, pruned_loss=0.09283, over 5146.00 frames.], tot_loss[loss=0.2259, simple_loss=0.301, pruned_loss=0.07543, over 755725.04 frames.], batch size: 52, lr: 1.40e-03
+2022-05-14 01:29:12,392 INFO [train.py:812] (2/8) Epoch 5, batch 200, loss[loss=0.2309, simple_loss=0.2948, pruned_loss=0.08351, over 7165.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3002, pruned_loss=0.07521, over 904276.41 frames.], batch size: 19, lr: 1.40e-03
+2022-05-14 01:30:11,974 INFO [train.py:812] (2/8) Epoch 5, batch 250, loss[loss=0.2191, simple_loss=0.2977, pruned_loss=0.07023, over 7336.00 frames.], tot_loss[loss=0.2257, simple_loss=0.302, pruned_loss=0.07473, over 1022231.81 frames.], batch size: 22, lr: 1.39e-03
+2022-05-14 01:31:10,335 INFO [train.py:812] (2/8) Epoch 5, batch 300, loss[loss=0.1938, simple_loss=0.2691, pruned_loss=0.05928, over 7279.00 frames.], tot_loss[loss=0.2228, simple_loss=0.2991, pruned_loss=0.07324, over 1114231.73 frames.], batch size: 17, lr: 1.39e-03
+2022-05-14 01:32:09,253 INFO [train.py:812] (2/8) Epoch 5, batch 350, loss[loss=0.2277, simple_loss=0.2922, pruned_loss=0.08158, over 7159.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2984, pruned_loss=0.07347, over 1181301.29 frames.], batch size: 19, lr: 1.39e-03
+2022-05-14 01:33:06,930 INFO [train.py:812] (2/8) Epoch 5, batch 400, loss[loss=0.2088, simple_loss=0.2864, pruned_loss=0.0656, over 7097.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2972, pruned_loss=0.07287, over 1232691.44 frames.], batch size: 28, lr: 1.39e-03
+2022-05-14 01:34:05,734 INFO [train.py:812] (2/8) Epoch 5, batch 450, loss[loss=0.2191, simple_loss=0.3007, pruned_loss=0.06878, over 6997.00 frames.], tot_loss[loss=0.2208, simple_loss=0.2968, pruned_loss=0.07239, over 1273699.65 frames.], batch size: 28, lr: 1.39e-03
+2022-05-14 01:35:05,238 INFO [train.py:812] (2/8) Epoch 5, batch 500, loss[loss=0.2061, simple_loss=0.2929, pruned_loss=0.05968, over 7315.00 frames.], tot_loss[loss=0.2194, simple_loss=0.2955, pruned_loss=0.07164, over 1308771.54 frames.], batch size: 21, lr: 1.39e-03
+2022-05-14 01:36:04,824 INFO [train.py:812] (2/8) Epoch 5, batch 550, loss[loss=0.2361, simple_loss=0.3141, pruned_loss=0.07911, over 6942.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2953, pruned_loss=0.0715, over 1333783.92 frames.], batch size: 31, lr: 1.38e-03
+2022-05-14 01:37:04,123 INFO [train.py:812] (2/8) Epoch 5, batch 600, loss[loss=0.2035, simple_loss=0.2811, pruned_loss=0.06289, over 7434.00 frames.], tot_loss[loss=0.219, simple_loss=0.295, pruned_loss=0.07153, over 1356285.15 frames.], batch size: 17, lr: 1.38e-03
+2022-05-14 01:38:03,179 INFO [train.py:812] (2/8) Epoch 5, batch 650, loss[loss=0.2319, simple_loss=0.3028, pruned_loss=0.08051, over 7332.00 frames.], tot_loss[loss=0.2194, simple_loss=0.2955, pruned_loss=0.07165, over 1370971.25 frames.], batch size: 20, lr: 1.38e-03
+2022-05-14 01:39:02,107 INFO [train.py:812] (2/8) Epoch 5, batch 700, loss[loss=0.2895, simple_loss=0.3652, pruned_loss=0.1069, over 7285.00 frames.], tot_loss[loss=0.2203, simple_loss=0.2966, pruned_loss=0.07199, over 1380797.84 frames.], batch size: 25, lr: 1.38e-03
+2022-05-14 01:40:02,037 INFO [train.py:812] (2/8) Epoch 5, batch 750, loss[loss=0.2112, simple_loss=0.2795, pruned_loss=0.07143, over 7071.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2949, pruned_loss=0.07127, over 1385197.82 frames.], batch size: 18, lr: 1.38e-03
+2022-05-14 01:40:59,759 INFO [train.py:812] (2/8) Epoch 5, batch 800, loss[loss=0.1983, simple_loss=0.2816, pruned_loss=0.0575, over 7065.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2923, pruned_loss=0.07013, over 1396095.67 frames.], batch size: 18, lr: 1.38e-03
+2022-05-14 01:41:57,356 INFO [train.py:812] (2/8) Epoch 5, batch 850, loss[loss=0.1893, simple_loss=0.2684, pruned_loss=0.05506, over 7071.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2922, pruned_loss=0.07012, over 1394802.77 frames.], batch size: 18, lr: 1.37e-03
+2022-05-14 01:42:55,897 INFO [train.py:812] (2/8) Epoch 5, batch 900, loss[loss=0.2083, simple_loss=0.2788, pruned_loss=0.0689, over 7321.00 frames.], tot_loss[loss=0.2167, simple_loss=0.2929, pruned_loss=0.07024, over 1402062.99 frames.], batch size: 21, lr: 1.37e-03
+2022-05-14 01:43:53,341 INFO [train.py:812] (2/8) Epoch 5, batch 950, loss[loss=0.2451, simple_loss=0.3212, pruned_loss=0.08445, over 7073.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2937, pruned_loss=0.07038, over 1405542.19 frames.], batch size: 28, lr: 1.37e-03
+2022-05-14 01:44:52,022 INFO [train.py:812] (2/8) Epoch 5, batch 1000, loss[loss=0.1916, simple_loss=0.2636, pruned_loss=0.05977, over 7072.00 frames.], tot_loss[loss=0.2166, simple_loss=0.293, pruned_loss=0.07017, over 1410378.10 frames.], batch size: 18, lr: 1.37e-03
+2022-05-14 01:45:49,419 INFO [train.py:812] (2/8) Epoch 5, batch 1050, loss[loss=0.2252, simple_loss=0.3094, pruned_loss=0.0705, over 7296.00 frames.], tot_loss[loss=0.2167, simple_loss=0.2936, pruned_loss=0.06992, over 1416242.96 frames.], batch size: 24, lr: 1.37e-03
+2022-05-14 01:46:47,348 INFO [train.py:812] (2/8) Epoch 5, batch 1100, loss[loss=0.2732, simple_loss=0.3388, pruned_loss=0.1038, over 6490.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2945, pruned_loss=0.07043, over 1412015.80 frames.], batch size: 38, lr: 1.37e-03
+2022-05-14 01:47:47,039 INFO [train.py:812] (2/8) Epoch 5, batch 1150, loss[loss=0.269, simple_loss=0.3296, pruned_loss=0.1042, over 7442.00 frames.], tot_loss[loss=0.2182, simple_loss=0.2953, pruned_loss=0.07054, over 1414606.69 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:48:45,957 INFO [train.py:812] (2/8) Epoch 5, batch 1200, loss[loss=0.2074, simple_loss=0.2894, pruned_loss=0.06267, over 6338.00 frames.], tot_loss[loss=0.218, simple_loss=0.2948, pruned_loss=0.07056, over 1416901.27 frames.], batch size: 37, lr: 1.36e-03
+2022-05-14 01:49:45,448 INFO [train.py:812] (2/8) Epoch 5, batch 1250, loss[loss=0.2081, simple_loss=0.2951, pruned_loss=0.06056, over 7255.00 frames.], tot_loss[loss=0.2186, simple_loss=0.2951, pruned_loss=0.07106, over 1412775.15 frames.], batch size: 19, lr: 1.36e-03
+2022-05-14 01:50:43,727 INFO [train.py:812] (2/8) Epoch 5, batch 1300, loss[loss=0.1873, simple_loss=0.2723, pruned_loss=0.05114, over 7334.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2957, pruned_loss=0.071, over 1415996.61 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:51:42,399 INFO [train.py:812] (2/8) Epoch 5, batch 1350, loss[loss=0.1938, simple_loss=0.2691, pruned_loss=0.05923, over 7136.00 frames.], tot_loss[loss=0.219, simple_loss=0.2959, pruned_loss=0.0711, over 1422822.05 frames.], batch size: 17, lr: 1.36e-03
+2022-05-14 01:52:39,818 INFO [train.py:812] (2/8) Epoch 5, batch 1400, loss[loss=0.1817, simple_loss=0.2762, pruned_loss=0.0436, over 7219.00 frames.], tot_loss[loss=0.22, simple_loss=0.2973, pruned_loss=0.07137, over 1418945.58 frames.], batch size: 20, lr: 1.36e-03
+2022-05-14 01:53:37,455 INFO [train.py:812] (2/8) Epoch 5, batch 1450, loss[loss=0.2057, simple_loss=0.2792, pruned_loss=0.06605, over 6999.00 frames.], tot_loss[loss=0.2203, simple_loss=0.2976, pruned_loss=0.07151, over 1419557.20 frames.], batch size: 16, lr: 1.35e-03
+2022-05-14 01:54:35,092 INFO [train.py:812] (2/8) Epoch 5, batch 1500, loss[loss=0.213, simple_loss=0.2943, pruned_loss=0.06582, over 7337.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2958, pruned_loss=0.07075, over 1423106.62 frames.], batch size: 20, lr: 1.35e-03
+2022-05-14 01:55:34,746 INFO [train.py:812] (2/8) Epoch 5, batch 1550, loss[loss=0.2204, simple_loss=0.3135, pruned_loss=0.06365, over 7384.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2943, pruned_loss=0.07003, over 1425489.09 frames.], batch size: 23, lr: 1.35e-03
+2022-05-14 01:56:33,045 INFO [train.py:812] (2/8) Epoch 5, batch 1600, loss[loss=0.2378, simple_loss=0.3123, pruned_loss=0.08165, over 7280.00 frames.], tot_loss[loss=0.2167, simple_loss=0.2938, pruned_loss=0.06974, over 1424686.26 frames.], batch size: 25, lr: 1.35e-03
+2022-05-14 01:57:37,112 INFO [train.py:812] (2/8) Epoch 5, batch 1650, loss[loss=0.2127, simple_loss=0.3026, pruned_loss=0.06137, over 7121.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2939, pruned_loss=0.06962, over 1422010.09 frames.], batch size: 21, lr: 1.35e-03
+2022-05-14 01:58:36,748 INFO [train.py:812] (2/8) Epoch 5, batch 1700, loss[loss=0.2567, simple_loss=0.3394, pruned_loss=0.08699, over 7333.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2935, pruned_loss=0.06894, over 1424002.46 frames.], batch size: 22, lr: 1.35e-03
+2022-05-14 01:59:35,632 INFO [train.py:812] (2/8) Epoch 5, batch 1750, loss[loss=0.2226, simple_loss=0.3053, pruned_loss=0.06993, over 7276.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2927, pruned_loss=0.069, over 1423471.10 frames.], batch size: 24, lr: 1.34e-03
+2022-05-14 02:00:34,964 INFO [train.py:812] (2/8) Epoch 5, batch 1800, loss[loss=0.2162, simple_loss=0.2978, pruned_loss=0.06729, over 7328.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2938, pruned_loss=0.06985, over 1425887.20 frames.], batch size: 21, lr: 1.34e-03
+2022-05-14 02:01:33,480 INFO [train.py:812] (2/8) Epoch 5, batch 1850, loss[loss=0.2392, simple_loss=0.3192, pruned_loss=0.07967, over 6388.00 frames.], tot_loss[loss=0.2168, simple_loss=0.294, pruned_loss=0.06974, over 1426093.28 frames.], batch size: 38, lr: 1.34e-03
+2022-05-14 02:02:31,902 INFO [train.py:812] (2/8) Epoch 5, batch 1900, loss[loss=0.2548, simple_loss=0.3265, pruned_loss=0.09156, over 7111.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2927, pruned_loss=0.06876, over 1427747.13 frames.], batch size: 21, lr: 1.34e-03
+2022-05-14 02:03:30,590 INFO [train.py:812] (2/8) Epoch 5, batch 1950, loss[loss=0.1915, simple_loss=0.2629, pruned_loss=0.06001, over 7152.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2935, pruned_loss=0.06893, over 1428055.75 frames.], batch size: 18, lr: 1.34e-03
+2022-05-14 02:04:28,246 INFO [train.py:812] (2/8) Epoch 5, batch 2000, loss[loss=0.2331, simple_loss=0.3048, pruned_loss=0.08074, over 7327.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2932, pruned_loss=0.06912, over 1425589.32 frames.], batch size: 25, lr: 1.34e-03
+2022-05-14 02:05:26,934 INFO [train.py:812] (2/8) Epoch 5, batch 2050, loss[loss=0.2396, simple_loss=0.3227, pruned_loss=0.07826, over 7308.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2923, pruned_loss=0.06849, over 1430308.09 frames.], batch size: 24, lr: 1.34e-03
+2022-05-14 02:06:25,380 INFO [train.py:812] (2/8) Epoch 5, batch 2100, loss[loss=0.1843, simple_loss=0.2522, pruned_loss=0.05823, over 7403.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2914, pruned_loss=0.0682, over 1433267.02 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:07:23,973 INFO [train.py:812] (2/8) Epoch 5, batch 2150, loss[loss=0.2138, simple_loss=0.2877, pruned_loss=0.06996, over 7064.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2931, pruned_loss=0.06888, over 1432166.44 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:08:21,801 INFO [train.py:812] (2/8) Epoch 5, batch 2200, loss[loss=0.2038, simple_loss=0.2897, pruned_loss=0.05888, over 7338.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2923, pruned_loss=0.06855, over 1433816.15 frames.], batch size: 22, lr: 1.33e-03
+2022-05-14 02:09:20,789 INFO [train.py:812] (2/8) Epoch 5, batch 2250, loss[loss=0.2005, simple_loss=0.2825, pruned_loss=0.05919, over 7381.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2921, pruned_loss=0.06821, over 1431634.20 frames.], batch size: 23, lr: 1.33e-03
+2022-05-14 02:10:20,197 INFO [train.py:812] (2/8) Epoch 5, batch 2300, loss[loss=0.2013, simple_loss=0.2744, pruned_loss=0.06409, over 7273.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2924, pruned_loss=0.06836, over 1430291.36 frames.], batch size: 17, lr: 1.33e-03
+2022-05-14 02:11:18,992 INFO [train.py:812] (2/8) Epoch 5, batch 2350, loss[loss=0.2265, simple_loss=0.2921, pruned_loss=0.08052, over 7436.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2925, pruned_loss=0.06794, over 1434024.45 frames.], batch size: 18, lr: 1.33e-03
+2022-05-14 02:12:18,595 INFO [train.py:812] (2/8) Epoch 5, batch 2400, loss[loss=0.2634, simple_loss=0.342, pruned_loss=0.09243, over 7220.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2925, pruned_loss=0.06831, over 1435907.09 frames.], batch size: 21, lr: 1.32e-03
+2022-05-14 02:13:16,802 INFO [train.py:812] (2/8) Epoch 5, batch 2450, loss[loss=0.214, simple_loss=0.2856, pruned_loss=0.07118, over 7271.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2928, pruned_loss=0.06834, over 1435396.73 frames.], batch size: 18, lr: 1.32e-03
+2022-05-14 02:14:14,133 INFO [train.py:812] (2/8) Epoch 5, batch 2500, loss[loss=0.2496, simple_loss=0.3349, pruned_loss=0.08214, over 7208.00 frames.], tot_loss[loss=0.2142, simple_loss=0.292, pruned_loss=0.06815, over 1433506.12 frames.], batch size: 22, lr: 1.32e-03
+2022-05-14 02:15:13,113 INFO [train.py:812] (2/8) Epoch 5, batch 2550, loss[loss=0.2295, simple_loss=0.2998, pruned_loss=0.07958, over 7151.00 frames.], tot_loss[loss=0.215, simple_loss=0.2929, pruned_loss=0.06853, over 1433799.45 frames.], batch size: 20, lr: 1.32e-03
+2022-05-14 02:16:11,267 INFO [train.py:812] (2/8) Epoch 5, batch 2600, loss[loss=0.1976, simple_loss=0.2838, pruned_loss=0.05569, over 7314.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2937, pruned_loss=0.0692, over 1432112.19 frames.], batch size: 21, lr: 1.32e-03
+2022-05-14 02:17:10,972 INFO [train.py:812] (2/8) Epoch 5, batch 2650, loss[loss=0.1736, simple_loss=0.2516, pruned_loss=0.04774, over 7008.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2935, pruned_loss=0.06904, over 1430409.80 frames.], batch size: 16, lr: 1.32e-03
+2022-05-14 02:18:10,462 INFO [train.py:812] (2/8) Epoch 5, batch 2700, loss[loss=0.1719, simple_loss=0.2523, pruned_loss=0.04573, over 7269.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2933, pruned_loss=0.0687, over 1432856.54 frames.], batch size: 18, lr: 1.32e-03
+2022-05-14 02:19:10,226 INFO [train.py:812] (2/8) Epoch 5, batch 2750, loss[loss=0.2144, simple_loss=0.2957, pruned_loss=0.06658, over 7352.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2935, pruned_loss=0.06896, over 1433209.92 frames.], batch size: 19, lr: 1.31e-03
+2022-05-14 02:20:09,512 INFO [train.py:812] (2/8) Epoch 5, batch 2800, loss[loss=0.1847, simple_loss=0.2658, pruned_loss=0.05176, over 7137.00 frames.], tot_loss[loss=0.2141, simple_loss=0.2923, pruned_loss=0.068, over 1433765.23 frames.], batch size: 17, lr: 1.31e-03
+2022-05-14 02:21:07,411 INFO [train.py:812] (2/8) Epoch 5, batch 2850, loss[loss=0.2176, simple_loss=0.3056, pruned_loss=0.06478, over 6600.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2933, pruned_loss=0.06855, over 1430574.48 frames.], batch size: 31, lr: 1.31e-03
+2022-05-14 02:22:06,258 INFO [train.py:812] (2/8) Epoch 5, batch 2900, loss[loss=0.2146, simple_loss=0.3039, pruned_loss=0.06264, over 7280.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2935, pruned_loss=0.06856, over 1428482.63 frames.], batch size: 24, lr: 1.31e-03
+2022-05-14 02:23:05,706 INFO [train.py:812] (2/8) Epoch 5, batch 2950, loss[loss=0.2283, simple_loss=0.3046, pruned_loss=0.07603, over 7330.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2919, pruned_loss=0.06798, over 1427731.89 frames.], batch size: 22, lr: 1.31e-03
+2022-05-14 02:24:04,415 INFO [train.py:812] (2/8) Epoch 5, batch 3000, loss[loss=0.24, simple_loss=0.3167, pruned_loss=0.0817, over 7176.00 frames.], tot_loss[loss=0.2139, simple_loss=0.292, pruned_loss=0.06797, over 1424260.95 frames.], batch size: 26, lr: 1.31e-03
+2022-05-14 02:24:04,416 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 02:24:12,114 INFO [train.py:841] (2/8) Epoch 5, validation: loss=0.1705, simple_loss=0.2732, pruned_loss=0.03391, over 698248.00 frames.
+2022-05-14 02:25:11,805 INFO [train.py:812] (2/8) Epoch 5, batch 3050, loss[loss=0.212, simple_loss=0.3067, pruned_loss=0.05864, over 7207.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2927, pruned_loss=0.06788, over 1428762.70 frames.], batch size: 22, lr: 1.31e-03
+2022-05-14 02:26:09,561 INFO [train.py:812] (2/8) Epoch 5, batch 3100, loss[loss=0.215, simple_loss=0.2943, pruned_loss=0.06785, over 7232.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2932, pruned_loss=0.06882, over 1427140.53 frames.], batch size: 20, lr: 1.30e-03
+2022-05-14 02:27:19,073 INFO [train.py:812] (2/8) Epoch 5, batch 3150, loss[loss=0.2413, simple_loss=0.3176, pruned_loss=0.08251, over 7307.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2932, pruned_loss=0.06847, over 1427979.09 frames.], batch size: 25, lr: 1.30e-03
+2022-05-14 02:28:18,317 INFO [train.py:812] (2/8) Epoch 5, batch 3200, loss[loss=0.1807, simple_loss=0.2622, pruned_loss=0.04953, over 7354.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2924, pruned_loss=0.06822, over 1428701.80 frames.], batch size: 19, lr: 1.30e-03
+2022-05-14 02:29:17,243 INFO [train.py:812] (2/8) Epoch 5, batch 3250, loss[loss=0.2242, simple_loss=0.2908, pruned_loss=0.07875, over 7168.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2913, pruned_loss=0.06783, over 1427489.70 frames.], batch size: 18, lr: 1.30e-03
+2022-05-14 02:30:15,407 INFO [train.py:812] (2/8) Epoch 5, batch 3300, loss[loss=0.2262, simple_loss=0.3048, pruned_loss=0.07381, over 7150.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2923, pruned_loss=0.06826, over 1422602.73 frames.], batch size: 26, lr: 1.30e-03
+2022-05-14 02:31:14,127 INFO [train.py:812] (2/8) Epoch 5, batch 3350, loss[loss=0.2645, simple_loss=0.328, pruned_loss=0.1005, over 7122.00 frames.], tot_loss[loss=0.214, simple_loss=0.2922, pruned_loss=0.06796, over 1425132.78 frames.], batch size: 21, lr: 1.30e-03
+2022-05-14 02:32:12,542 INFO [train.py:812] (2/8) Epoch 5, batch 3400, loss[loss=0.1866, simple_loss=0.2847, pruned_loss=0.04425, over 7240.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2925, pruned_loss=0.06842, over 1426561.58 frames.], batch size: 20, lr: 1.30e-03
+2022-05-14 02:33:11,810 INFO [train.py:812] (2/8) Epoch 5, batch 3450, loss[loss=0.2269, simple_loss=0.3075, pruned_loss=0.07309, over 7206.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2924, pruned_loss=0.06835, over 1426725.18 frames.], batch size: 23, lr: 1.29e-03
+2022-05-14 02:34:10,836 INFO [train.py:812] (2/8) Epoch 5, batch 3500, loss[loss=0.2194, simple_loss=0.2997, pruned_loss=0.06955, over 7326.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2923, pruned_loss=0.06819, over 1429819.34 frames.], batch size: 20, lr: 1.29e-03
+2022-05-14 02:35:38,309 INFO [train.py:812] (2/8) Epoch 5, batch 3550, loss[loss=0.2485, simple_loss=0.3234, pruned_loss=0.08682, over 7415.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2918, pruned_loss=0.06763, over 1424531.51 frames.], batch size: 21, lr: 1.29e-03
+2022-05-14 02:36:46,045 INFO [train.py:812] (2/8) Epoch 5, batch 3600, loss[loss=0.1911, simple_loss=0.2689, pruned_loss=0.05664, over 7259.00 frames.], tot_loss[loss=0.2126, simple_loss=0.291, pruned_loss=0.0671, over 1420695.95 frames.], batch size: 19, lr: 1.29e-03
+2022-05-14 02:38:13,278 INFO [train.py:812] (2/8) Epoch 5, batch 3650, loss[loss=0.2307, simple_loss=0.3122, pruned_loss=0.07461, over 6786.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2922, pruned_loss=0.06815, over 1415963.99 frames.], batch size: 31, lr: 1.29e-03
+2022-05-14 02:39:12,938 INFO [train.py:812] (2/8) Epoch 5, batch 3700, loss[loss=0.2058, simple_loss=0.2765, pruned_loss=0.06755, over 7162.00 frames.], tot_loss[loss=0.212, simple_loss=0.2899, pruned_loss=0.06704, over 1420270.12 frames.], batch size: 18, lr: 1.29e-03
+2022-05-14 02:40:11,641 INFO [train.py:812] (2/8) Epoch 5, batch 3750, loss[loss=0.181, simple_loss=0.2457, pruned_loss=0.05814, over 6748.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2898, pruned_loss=0.06647, over 1420857.67 frames.], batch size: 15, lr: 1.29e-03
+2022-05-14 02:41:09,955 INFO [train.py:812] (2/8) Epoch 5, batch 3800, loss[loss=0.1936, simple_loss=0.2716, pruned_loss=0.05779, over 7277.00 frames.], tot_loss[loss=0.212, simple_loss=0.2902, pruned_loss=0.06687, over 1421816.85 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:42:07,618 INFO [train.py:812] (2/8) Epoch 5, batch 3850, loss[loss=0.1857, simple_loss=0.2769, pruned_loss=0.04725, over 7409.00 frames.], tot_loss[loss=0.2131, simple_loss=0.291, pruned_loss=0.06758, over 1421061.66 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:43:06,301 INFO [train.py:812] (2/8) Epoch 5, batch 3900, loss[loss=0.2216, simple_loss=0.2961, pruned_loss=0.07356, over 7170.00 frames.], tot_loss[loss=0.213, simple_loss=0.2909, pruned_loss=0.06757, over 1418396.28 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:44:04,238 INFO [train.py:812] (2/8) Epoch 5, batch 3950, loss[loss=0.2151, simple_loss=0.3048, pruned_loss=0.06273, over 7412.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2903, pruned_loss=0.06705, over 1415648.99 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:45:02,161 INFO [train.py:812] (2/8) Epoch 5, batch 4000, loss[loss=0.1925, simple_loss=0.2802, pruned_loss=0.05237, over 7433.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2917, pruned_loss=0.06783, over 1418495.40 frames.], batch size: 20, lr: 1.28e-03
+2022-05-14 02:46:01,623 INFO [train.py:812] (2/8) Epoch 5, batch 4050, loss[loss=0.2116, simple_loss=0.3076, pruned_loss=0.0578, over 7233.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2908, pruned_loss=0.06732, over 1420677.57 frames.], batch size: 21, lr: 1.28e-03
+2022-05-14 02:46:59,622 INFO [train.py:812] (2/8) Epoch 5, batch 4100, loss[loss=0.2078, simple_loss=0.2708, pruned_loss=0.07239, over 7283.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2923, pruned_loss=0.06802, over 1417586.95 frames.], batch size: 18, lr: 1.28e-03
+2022-05-14 02:47:58,851 INFO [train.py:812] (2/8) Epoch 5, batch 4150, loss[loss=0.1958, simple_loss=0.2832, pruned_loss=0.05421, over 7224.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2935, pruned_loss=0.06881, over 1415447.55 frames.], batch size: 22, lr: 1.27e-03
+2022-05-14 02:48:57,954 INFO [train.py:812] (2/8) Epoch 5, batch 4200, loss[loss=0.2392, simple_loss=0.3027, pruned_loss=0.08789, over 7141.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2938, pruned_loss=0.06901, over 1414150.64 frames.], batch size: 17, lr: 1.27e-03
+2022-05-14 02:49:57,152 INFO [train.py:812] (2/8) Epoch 5, batch 4250, loss[loss=0.1972, simple_loss=0.2829, pruned_loss=0.05575, over 7070.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2933, pruned_loss=0.06863, over 1415153.32 frames.], batch size: 18, lr: 1.27e-03
+2022-05-14 02:50:54,438 INFO [train.py:812] (2/8) Epoch 5, batch 4300, loss[loss=0.2104, simple_loss=0.2885, pruned_loss=0.06616, over 7140.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2945, pruned_loss=0.06912, over 1415532.31 frames.], batch size: 20, lr: 1.27e-03
+2022-05-14 02:51:52,661 INFO [train.py:812] (2/8) Epoch 5, batch 4350, loss[loss=0.2362, simple_loss=0.32, pruned_loss=0.07625, over 7418.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2952, pruned_loss=0.0695, over 1414038.16 frames.], batch size: 21, lr: 1.27e-03
+2022-05-14 02:52:52,060 INFO [train.py:812] (2/8) Epoch 5, batch 4400, loss[loss=0.1966, simple_loss=0.2795, pruned_loss=0.05689, over 7255.00 frames.], tot_loss[loss=0.217, simple_loss=0.2951, pruned_loss=0.06946, over 1410406.66 frames.], batch size: 19, lr: 1.27e-03
+2022-05-14 02:53:51,758 INFO [train.py:812] (2/8) Epoch 5, batch 4450, loss[loss=0.1863, simple_loss=0.2695, pruned_loss=0.05156, over 6679.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2954, pruned_loss=0.06961, over 1404499.53 frames.], batch size: 31, lr: 1.27e-03
+2022-05-14 02:54:49,527 INFO [train.py:812] (2/8) Epoch 5, batch 4500, loss[loss=0.2789, simple_loss=0.3386, pruned_loss=0.1096, over 5011.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2963, pruned_loss=0.06999, over 1395425.18 frames.], batch size: 54, lr: 1.27e-03
+2022-05-14 02:55:48,875 INFO [train.py:812] (2/8) Epoch 5, batch 4550, loss[loss=0.2731, simple_loss=0.319, pruned_loss=0.1136, over 4732.00 frames.], tot_loss[loss=0.2232, simple_loss=0.2996, pruned_loss=0.07338, over 1341339.07 frames.], batch size: 52, lr: 1.26e-03
+2022-05-14 02:56:57,109 INFO [train.py:812] (2/8) Epoch 6, batch 0, loss[loss=0.203, simple_loss=0.2849, pruned_loss=0.06057, over 7155.00 frames.], tot_loss[loss=0.203, simple_loss=0.2849, pruned_loss=0.06057, over 7155.00 frames.], batch size: 19, lr: 1.21e-03
+2022-05-14 02:57:56,755 INFO [train.py:812] (2/8) Epoch 6, batch 50, loss[loss=0.2415, simple_loss=0.3144, pruned_loss=0.08431, over 5131.00 frames.], tot_loss[loss=0.2135, simple_loss=0.291, pruned_loss=0.06799, over 318500.72 frames.], batch size: 52, lr: 1.21e-03
+2022-05-14 02:58:56,402 INFO [train.py:812] (2/8) Epoch 6, batch 100, loss[loss=0.1975, simple_loss=0.2761, pruned_loss=0.05949, over 7150.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2934, pruned_loss=0.06916, over 561696.64 frames.], batch size: 20, lr: 1.21e-03
+2022-05-14 02:59:55,389 INFO [train.py:812] (2/8) Epoch 6, batch 150, loss[loss=0.2086, simple_loss=0.2886, pruned_loss=0.06431, over 6706.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2914, pruned_loss=0.06704, over 750079.76 frames.], batch size: 31, lr: 1.21e-03
+2022-05-14 03:00:54,860 INFO [train.py:812] (2/8) Epoch 6, batch 200, loss[loss=0.1928, simple_loss=0.2647, pruned_loss=0.06043, over 7403.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2916, pruned_loss=0.06696, over 899348.25 frames.], batch size: 18, lr: 1.21e-03
+2022-05-14 03:01:54,415 INFO [train.py:812] (2/8) Epoch 6, batch 250, loss[loss=0.2201, simple_loss=0.2983, pruned_loss=0.07094, over 7325.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2902, pruned_loss=0.0654, over 1019180.19 frames.], batch size: 22, lr: 1.21e-03
+2022-05-14 03:02:54,514 INFO [train.py:812] (2/8) Epoch 6, batch 300, loss[loss=0.1992, simple_loss=0.2878, pruned_loss=0.05533, over 7231.00 frames.], tot_loss[loss=0.209, simple_loss=0.2886, pruned_loss=0.06472, over 1112382.66 frames.], batch size: 20, lr: 1.21e-03
+2022-05-14 03:03:51,873 INFO [train.py:812] (2/8) Epoch 6, batch 350, loss[loss=0.1932, simple_loss=0.2742, pruned_loss=0.05609, over 7324.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2865, pruned_loss=0.06368, over 1185284.68 frames.], batch size: 20, lr: 1.20e-03
+2022-05-14 03:04:49,930 INFO [train.py:812] (2/8) Epoch 6, batch 400, loss[loss=0.2345, simple_loss=0.318, pruned_loss=0.07556, over 7380.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2892, pruned_loss=0.06509, over 1236869.90 frames.], batch size: 23, lr: 1.20e-03
+2022-05-14 03:05:47,791 INFO [train.py:812] (2/8) Epoch 6, batch 450, loss[loss=0.1828, simple_loss=0.2602, pruned_loss=0.05273, over 6816.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2896, pruned_loss=0.06553, over 1279683.62 frames.], batch size: 15, lr: 1.20e-03
+2022-05-14 03:06:47,347 INFO [train.py:812] (2/8) Epoch 6, batch 500, loss[loss=0.2621, simple_loss=0.3257, pruned_loss=0.09929, over 4651.00 frames.], tot_loss[loss=0.211, simple_loss=0.2899, pruned_loss=0.06602, over 1308309.38 frames.], batch size: 52, lr: 1.20e-03
+2022-05-14 03:07:45,161 INFO [train.py:812] (2/8) Epoch 6, batch 550, loss[loss=0.2406, simple_loss=0.3241, pruned_loss=0.07856, over 6587.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2901, pruned_loss=0.06584, over 1332807.67 frames.], batch size: 38, lr: 1.20e-03
+2022-05-14 03:08:43,999 INFO [train.py:812] (2/8) Epoch 6, batch 600, loss[loss=0.2165, simple_loss=0.2952, pruned_loss=0.06893, over 7142.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2886, pruned_loss=0.06543, over 1352131.42 frames.], batch size: 20, lr: 1.20e-03
+2022-05-14 03:09:42,698 INFO [train.py:812] (2/8) Epoch 6, batch 650, loss[loss=0.1977, simple_loss=0.2818, pruned_loss=0.05679, over 7421.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2886, pruned_loss=0.06501, over 1367014.32 frames.], batch size: 21, lr: 1.20e-03
+2022-05-14 03:10:42,148 INFO [train.py:812] (2/8) Epoch 6, batch 700, loss[loss=0.1898, simple_loss=0.2728, pruned_loss=0.05342, over 6756.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2889, pruned_loss=0.06461, over 1378067.92 frames.], batch size: 15, lr: 1.20e-03
+2022-05-14 03:11:41,184 INFO [train.py:812] (2/8) Epoch 6, batch 750, loss[loss=0.2261, simple_loss=0.3058, pruned_loss=0.07316, over 7215.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2906, pruned_loss=0.06579, over 1387805.70 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:12:41,100 INFO [train.py:812] (2/8) Epoch 6, batch 800, loss[loss=0.1721, simple_loss=0.2578, pruned_loss=0.04326, over 7215.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2885, pruned_loss=0.06491, over 1398621.89 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:13:40,483 INFO [train.py:812] (2/8) Epoch 6, batch 850, loss[loss=0.2527, simple_loss=0.3467, pruned_loss=0.07938, over 7195.00 frames.], tot_loss[loss=0.2094, simple_loss=0.289, pruned_loss=0.06486, over 1404373.30 frames.], batch size: 23, lr: 1.19e-03
+2022-05-14 03:14:39,813 INFO [train.py:812] (2/8) Epoch 6, batch 900, loss[loss=0.2412, simple_loss=0.3238, pruned_loss=0.07927, over 7410.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2902, pruned_loss=0.0652, over 1406243.59 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:15:38,551 INFO [train.py:812] (2/8) Epoch 6, batch 950, loss[loss=0.1906, simple_loss=0.253, pruned_loss=0.06408, over 7147.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2903, pruned_loss=0.06501, over 1406158.96 frames.], batch size: 17, lr: 1.19e-03
+2022-05-14 03:16:38,020 INFO [train.py:812] (2/8) Epoch 6, batch 1000, loss[loss=0.2042, simple_loss=0.2882, pruned_loss=0.06008, over 7420.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2903, pruned_loss=0.06527, over 1408932.12 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:17:36,232 INFO [train.py:812] (2/8) Epoch 6, batch 1050, loss[loss=0.2002, simple_loss=0.2753, pruned_loss=0.06257, over 7320.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2904, pruned_loss=0.06559, over 1413300.63 frames.], batch size: 20, lr: 1.19e-03
+2022-05-14 03:18:39,064 INFO [train.py:812] (2/8) Epoch 6, batch 1100, loss[loss=0.2232, simple_loss=0.3003, pruned_loss=0.07302, over 7316.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2909, pruned_loss=0.06612, over 1409046.27 frames.], batch size: 21, lr: 1.19e-03
+2022-05-14 03:19:37,380 INFO [train.py:812] (2/8) Epoch 6, batch 1150, loss[loss=0.209, simple_loss=0.2853, pruned_loss=0.06634, over 7144.00 frames.], tot_loss[loss=0.212, simple_loss=0.2917, pruned_loss=0.06615, over 1413928.09 frames.], batch size: 20, lr: 1.19e-03
+2022-05-14 03:20:36,650 INFO [train.py:812] (2/8) Epoch 6, batch 1200, loss[loss=0.2124, simple_loss=0.2895, pruned_loss=0.06769, over 7196.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2905, pruned_loss=0.06566, over 1415022.86 frames.], batch size: 26, lr: 1.18e-03
+2022-05-14 03:21:34,756 INFO [train.py:812] (2/8) Epoch 6, batch 1250, loss[loss=0.203, simple_loss=0.2974, pruned_loss=0.05432, over 7149.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2892, pruned_loss=0.0652, over 1413905.18 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:22:34,580 INFO [train.py:812] (2/8) Epoch 6, batch 1300, loss[loss=0.2124, simple_loss=0.2917, pruned_loss=0.06651, over 7354.00 frames.], tot_loss[loss=0.2099, simple_loss=0.289, pruned_loss=0.06542, over 1412251.93 frames.], batch size: 19, lr: 1.18e-03
+2022-05-14 03:23:33,471 INFO [train.py:812] (2/8) Epoch 6, batch 1350, loss[loss=0.2419, simple_loss=0.3164, pruned_loss=0.08367, over 7070.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2886, pruned_loss=0.06537, over 1415076.63 frames.], batch size: 28, lr: 1.18e-03
+2022-05-14 03:24:32,550 INFO [train.py:812] (2/8) Epoch 6, batch 1400, loss[loss=0.1893, simple_loss=0.2874, pruned_loss=0.04562, over 7323.00 frames.], tot_loss[loss=0.209, simple_loss=0.2883, pruned_loss=0.06488, over 1419034.91 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:25:31,692 INFO [train.py:812] (2/8) Epoch 6, batch 1450, loss[loss=0.2008, simple_loss=0.2917, pruned_loss=0.05497, over 7424.00 frames.], tot_loss[loss=0.2084, simple_loss=0.288, pruned_loss=0.0644, over 1420877.80 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:26:31,152 INFO [train.py:812] (2/8) Epoch 6, batch 1500, loss[loss=0.2157, simple_loss=0.3058, pruned_loss=0.06275, over 7140.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2885, pruned_loss=0.06468, over 1421288.16 frames.], batch size: 20, lr: 1.18e-03
+2022-05-14 03:27:30,161 INFO [train.py:812] (2/8) Epoch 6, batch 1550, loss[loss=0.1889, simple_loss=0.266, pruned_loss=0.0559, over 7284.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2885, pruned_loss=0.06454, over 1423346.32 frames.], batch size: 17, lr: 1.18e-03
+2022-05-14 03:28:29,749 INFO [train.py:812] (2/8) Epoch 6, batch 1600, loss[loss=0.2359, simple_loss=0.3012, pruned_loss=0.08533, over 7435.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2883, pruned_loss=0.06468, over 1416877.73 frames.], batch size: 20, lr: 1.17e-03
+2022-05-14 03:29:29,243 INFO [train.py:812] (2/8) Epoch 6, batch 1650, loss[loss=0.2243, simple_loss=0.3037, pruned_loss=0.07249, over 7314.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2881, pruned_loss=0.06434, over 1416515.95 frames.], batch size: 25, lr: 1.17e-03
+2022-05-14 03:30:27,893 INFO [train.py:812] (2/8) Epoch 6, batch 1700, loss[loss=0.2168, simple_loss=0.293, pruned_loss=0.07034, over 7200.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2887, pruned_loss=0.06492, over 1414629.62 frames.], batch size: 22, lr: 1.17e-03
+2022-05-14 03:31:26,906 INFO [train.py:812] (2/8) Epoch 6, batch 1750, loss[loss=0.2079, simple_loss=0.2769, pruned_loss=0.06945, over 7269.00 frames.], tot_loss[loss=0.21, simple_loss=0.2889, pruned_loss=0.06556, over 1411386.21 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:32:26,456 INFO [train.py:812] (2/8) Epoch 6, batch 1800, loss[loss=0.2793, simple_loss=0.3354, pruned_loss=0.1116, over 4710.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2889, pruned_loss=0.06518, over 1413033.91 frames.], batch size: 53, lr: 1.17e-03
+2022-05-14 03:33:25,527 INFO [train.py:812] (2/8) Epoch 6, batch 1850, loss[loss=0.1755, simple_loss=0.2579, pruned_loss=0.04652, over 7169.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2879, pruned_loss=0.0643, over 1416489.50 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:34:24,874 INFO [train.py:812] (2/8) Epoch 6, batch 1900, loss[loss=0.1844, simple_loss=0.2552, pruned_loss=0.05686, over 7135.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2881, pruned_loss=0.06491, over 1416027.50 frames.], batch size: 17, lr: 1.17e-03
+2022-05-14 03:35:23,963 INFO [train.py:812] (2/8) Epoch 6, batch 1950, loss[loss=0.2156, simple_loss=0.2986, pruned_loss=0.06634, over 7133.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2888, pruned_loss=0.065, over 1420483.64 frames.], batch size: 21, lr: 1.17e-03
+2022-05-14 03:36:21,514 INFO [train.py:812] (2/8) Epoch 6, batch 2000, loss[loss=0.23, simple_loss=0.2893, pruned_loss=0.08531, over 7283.00 frames.], tot_loss[loss=0.209, simple_loss=0.2885, pruned_loss=0.06473, over 1423756.96 frames.], batch size: 18, lr: 1.17e-03
+2022-05-14 03:37:19,515 INFO [train.py:812] (2/8) Epoch 6, batch 2050, loss[loss=0.2078, simple_loss=0.2962, pruned_loss=0.05975, over 7101.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2897, pruned_loss=0.06544, over 1423858.03 frames.], batch size: 28, lr: 1.16e-03
+2022-05-14 03:38:19,352 INFO [train.py:812] (2/8) Epoch 6, batch 2100, loss[loss=0.2024, simple_loss=0.2851, pruned_loss=0.05986, over 6216.00 frames.], tot_loss[loss=0.21, simple_loss=0.2895, pruned_loss=0.06527, over 1425504.34 frames.], batch size: 37, lr: 1.16e-03
+2022-05-14 03:39:18,985 INFO [train.py:812] (2/8) Epoch 6, batch 2150, loss[loss=0.1849, simple_loss=0.2785, pruned_loss=0.04565, over 7140.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2899, pruned_loss=0.0655, over 1430300.77 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:40:18,678 INFO [train.py:812] (2/8) Epoch 6, batch 2200, loss[loss=0.2292, simple_loss=0.3024, pruned_loss=0.07804, over 7148.00 frames.], tot_loss[loss=0.2085, simple_loss=0.288, pruned_loss=0.06448, over 1427423.53 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:41:17,642 INFO [train.py:812] (2/8) Epoch 6, batch 2250, loss[loss=0.2043, simple_loss=0.28, pruned_loss=0.06425, over 7358.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2875, pruned_loss=0.06388, over 1426048.70 frames.], batch size: 19, lr: 1.16e-03
+2022-05-14 03:42:16,719 INFO [train.py:812] (2/8) Epoch 6, batch 2300, loss[loss=0.2156, simple_loss=0.3067, pruned_loss=0.06228, over 7294.00 frames.], tot_loss[loss=0.208, simple_loss=0.2875, pruned_loss=0.06419, over 1422835.74 frames.], batch size: 24, lr: 1.16e-03
+2022-05-14 03:43:15,827 INFO [train.py:812] (2/8) Epoch 6, batch 2350, loss[loss=0.2452, simple_loss=0.3234, pruned_loss=0.08352, over 7205.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2867, pruned_loss=0.06436, over 1421831.88 frames.], batch size: 21, lr: 1.16e-03
+2022-05-14 03:44:15,948 INFO [train.py:812] (2/8) Epoch 6, batch 2400, loss[loss=0.2416, simple_loss=0.3074, pruned_loss=0.08795, over 7313.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2862, pruned_loss=0.06376, over 1422022.74 frames.], batch size: 20, lr: 1.16e-03
+2022-05-14 03:45:14,486 INFO [train.py:812] (2/8) Epoch 6, batch 2450, loss[loss=0.1803, simple_loss=0.2525, pruned_loss=0.05402, over 6832.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2858, pruned_loss=0.06341, over 1421355.56 frames.], batch size: 15, lr: 1.16e-03
+2022-05-14 03:46:13,711 INFO [train.py:812] (2/8) Epoch 6, batch 2500, loss[loss=0.1844, simple_loss=0.2784, pruned_loss=0.04519, over 7340.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2864, pruned_loss=0.06339, over 1420513.03 frames.], batch size: 22, lr: 1.15e-03
+2022-05-14 03:47:11,228 INFO [train.py:812] (2/8) Epoch 6, batch 2550, loss[loss=0.1497, simple_loss=0.2375, pruned_loss=0.03099, over 6871.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2863, pruned_loss=0.06311, over 1422669.83 frames.], batch size: 15, lr: 1.15e-03
+2022-05-14 03:48:09,668 INFO [train.py:812] (2/8) Epoch 6, batch 2600, loss[loss=0.2053, simple_loss=0.3026, pruned_loss=0.05403, over 7316.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2867, pruned_loss=0.06325, over 1425585.02 frames.], batch size: 21, lr: 1.15e-03
+2022-05-14 03:49:08,325 INFO [train.py:812] (2/8) Epoch 6, batch 2650, loss[loss=0.2652, simple_loss=0.3415, pruned_loss=0.09451, over 7320.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2881, pruned_loss=0.06427, over 1423437.73 frames.], batch size: 25, lr: 1.15e-03
+2022-05-14 03:50:08,411 INFO [train.py:812] (2/8) Epoch 6, batch 2700, loss[loss=0.1751, simple_loss=0.2547, pruned_loss=0.04778, over 6798.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2875, pruned_loss=0.06359, over 1425538.91 frames.], batch size: 15, lr: 1.15e-03
+2022-05-14 03:51:06,477 INFO [train.py:812] (2/8) Epoch 6, batch 2750, loss[loss=0.2299, simple_loss=0.3095, pruned_loss=0.0751, over 7234.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2878, pruned_loss=0.06332, over 1423436.24 frames.], batch size: 20, lr: 1.15e-03
+2022-05-14 03:52:05,463 INFO [train.py:812] (2/8) Epoch 6, batch 2800, loss[loss=0.167, simple_loss=0.2605, pruned_loss=0.03677, over 7273.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2871, pruned_loss=0.06294, over 1421366.99 frames.], batch size: 18, lr: 1.15e-03
+2022-05-14 03:53:03,382 INFO [train.py:812] (2/8) Epoch 6, batch 2850, loss[loss=0.1718, simple_loss=0.2424, pruned_loss=0.05058, over 7276.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2867, pruned_loss=0.0628, over 1418383.40 frames.], batch size: 17, lr: 1.15e-03
+2022-05-14 03:54:00,907 INFO [train.py:812] (2/8) Epoch 6, batch 2900, loss[loss=0.2006, simple_loss=0.2904, pruned_loss=0.05535, over 6795.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2859, pruned_loss=0.06214, over 1420855.80 frames.], batch size: 31, lr: 1.15e-03
+2022-05-14 03:54:58,713 INFO [train.py:812] (2/8) Epoch 6, batch 2950, loss[loss=0.1904, simple_loss=0.2872, pruned_loss=0.04686, over 7147.00 frames.], tot_loss[loss=0.2053, simple_loss=0.286, pruned_loss=0.06226, over 1420808.55 frames.], batch size: 20, lr: 1.14e-03
+2022-05-14 03:55:55,714 INFO [train.py:812] (2/8) Epoch 6, batch 3000, loss[loss=0.2158, simple_loss=0.3011, pruned_loss=0.06528, over 7229.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2873, pruned_loss=0.0631, over 1419577.73 frames.], batch size: 20, lr: 1.14e-03
+2022-05-14 03:55:55,715 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 03:56:03,338 INFO [train.py:841] (2/8) Epoch 6, validation: loss=0.1668, simple_loss=0.2696, pruned_loss=0.03205, over 698248.00 frames.
+2022-05-14 03:57:02,144 INFO [train.py:812] (2/8) Epoch 6, batch 3050, loss[loss=0.2338, simple_loss=0.3066, pruned_loss=0.08055, over 7194.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2867, pruned_loss=0.06288, over 1425758.84 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 03:58:01,745 INFO [train.py:812] (2/8) Epoch 6, batch 3100, loss[loss=0.2032, simple_loss=0.2853, pruned_loss=0.06056, over 7335.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2858, pruned_loss=0.06262, over 1423963.43 frames.], batch size: 22, lr: 1.14e-03
+2022-05-14 03:58:58,841 INFO [train.py:812] (2/8) Epoch 6, batch 3150, loss[loss=0.2341, simple_loss=0.308, pruned_loss=0.08005, over 7190.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2863, pruned_loss=0.06291, over 1424008.31 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 03:59:57,534 INFO [train.py:812] (2/8) Epoch 6, batch 3200, loss[loss=0.2138, simple_loss=0.2989, pruned_loss=0.06437, over 7229.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2866, pruned_loss=0.06317, over 1424918.97 frames.], batch size: 21, lr: 1.14e-03
+2022-05-14 04:00:56,299 INFO [train.py:812] (2/8) Epoch 6, batch 3250, loss[loss=0.179, simple_loss=0.2712, pruned_loss=0.0434, over 7363.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2862, pruned_loss=0.06279, over 1425338.02 frames.], batch size: 19, lr: 1.14e-03
+2022-05-14 04:01:55,498 INFO [train.py:812] (2/8) Epoch 6, batch 3300, loss[loss=0.2107, simple_loss=0.2964, pruned_loss=0.06251, over 7202.00 frames.], tot_loss[loss=0.207, simple_loss=0.2874, pruned_loss=0.06324, over 1420913.98 frames.], batch size: 23, lr: 1.14e-03
+2022-05-14 04:02:54,579 INFO [train.py:812] (2/8) Epoch 6, batch 3350, loss[loss=0.1811, simple_loss=0.2695, pruned_loss=0.04632, over 7249.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2869, pruned_loss=0.06289, over 1425650.87 frames.], batch size: 19, lr: 1.14e-03
+2022-05-14 04:03:53,972 INFO [train.py:812] (2/8) Epoch 6, batch 3400, loss[loss=0.2115, simple_loss=0.2864, pruned_loss=0.06827, over 7304.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2869, pruned_loss=0.06276, over 1425354.50 frames.], batch size: 24, lr: 1.14e-03
+2022-05-14 04:04:52,398 INFO [train.py:812] (2/8) Epoch 6, batch 3450, loss[loss=0.2187, simple_loss=0.3081, pruned_loss=0.06465, over 7409.00 frames.], tot_loss[loss=0.207, simple_loss=0.2882, pruned_loss=0.06288, over 1427577.17 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:05:50,783 INFO [train.py:812] (2/8) Epoch 6, batch 3500, loss[loss=0.23, simple_loss=0.3084, pruned_loss=0.0758, over 7207.00 frames.], tot_loss[loss=0.206, simple_loss=0.2868, pruned_loss=0.06262, over 1423961.98 frames.], batch size: 22, lr: 1.13e-03
+2022-05-14 04:06:49,150 INFO [train.py:812] (2/8) Epoch 6, batch 3550, loss[loss=0.2059, simple_loss=0.2854, pruned_loss=0.06317, over 7310.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2869, pruned_loss=0.06248, over 1426846.69 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:07:47,616 INFO [train.py:812] (2/8) Epoch 6, batch 3600, loss[loss=0.1744, simple_loss=0.2575, pruned_loss=0.04564, over 7163.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2855, pruned_loss=0.06192, over 1428072.78 frames.], batch size: 18, lr: 1.13e-03
+2022-05-14 04:08:46,810 INFO [train.py:812] (2/8) Epoch 6, batch 3650, loss[loss=0.218, simple_loss=0.2957, pruned_loss=0.07018, over 7419.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2856, pruned_loss=0.06234, over 1427500.27 frames.], batch size: 21, lr: 1.13e-03
+2022-05-14 04:09:44,224 INFO [train.py:812] (2/8) Epoch 6, batch 3700, loss[loss=0.2252, simple_loss=0.3115, pruned_loss=0.06948, over 7237.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2857, pruned_loss=0.0624, over 1425431.93 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:10:41,362 INFO [train.py:812] (2/8) Epoch 6, batch 3750, loss[loss=0.2124, simple_loss=0.2979, pruned_loss=0.06341, over 7388.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2858, pruned_loss=0.06273, over 1423649.84 frames.], batch size: 23, lr: 1.13e-03
+2022-05-14 04:11:40,722 INFO [train.py:812] (2/8) Epoch 6, batch 3800, loss[loss=0.2097, simple_loss=0.2926, pruned_loss=0.06342, over 7233.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2851, pruned_loss=0.06258, over 1418681.46 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:12:39,883 INFO [train.py:812] (2/8) Epoch 6, batch 3850, loss[loss=0.2066, simple_loss=0.2854, pruned_loss=0.0639, over 7422.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2869, pruned_loss=0.06364, over 1419471.45 frames.], batch size: 20, lr: 1.13e-03
+2022-05-14 04:13:39,013 INFO [train.py:812] (2/8) Epoch 6, batch 3900, loss[loss=0.211, simple_loss=0.2745, pruned_loss=0.07374, over 7396.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2875, pruned_loss=0.0644, over 1424046.51 frames.], batch size: 18, lr: 1.13e-03
+2022-05-14 04:14:38,336 INFO [train.py:812] (2/8) Epoch 6, batch 3950, loss[loss=0.228, simple_loss=0.3215, pruned_loss=0.06727, over 7293.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2863, pruned_loss=0.06354, over 1423747.56 frames.], batch size: 24, lr: 1.12e-03
+2022-05-14 04:15:37,078 INFO [train.py:812] (2/8) Epoch 6, batch 4000, loss[loss=0.2225, simple_loss=0.2987, pruned_loss=0.07322, over 7185.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2863, pruned_loss=0.06338, over 1426683.18 frames.], batch size: 23, lr: 1.12e-03
+2022-05-14 04:16:34,947 INFO [train.py:812] (2/8) Epoch 6, batch 4050, loss[loss=0.2543, simple_loss=0.321, pruned_loss=0.09384, over 7288.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2869, pruned_loss=0.06373, over 1427600.33 frames.], batch size: 24, lr: 1.12e-03
+2022-05-14 04:17:34,681 INFO [train.py:812] (2/8) Epoch 6, batch 4100, loss[loss=0.1846, simple_loss=0.2677, pruned_loss=0.05071, over 7404.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2856, pruned_loss=0.06336, over 1427625.21 frames.], batch size: 18, lr: 1.12e-03
+2022-05-14 04:18:33,902 INFO [train.py:812] (2/8) Epoch 6, batch 4150, loss[loss=0.238, simple_loss=0.3208, pruned_loss=0.07756, over 6757.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2852, pruned_loss=0.0632, over 1426758.82 frames.], batch size: 31, lr: 1.12e-03
+2022-05-14 04:19:32,914 INFO [train.py:812] (2/8) Epoch 6, batch 4200, loss[loss=0.2071, simple_loss=0.2976, pruned_loss=0.05831, over 7118.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2846, pruned_loss=0.06305, over 1428412.61 frames.], batch size: 21, lr: 1.12e-03
+2022-05-14 04:20:33,094 INFO [train.py:812] (2/8) Epoch 6, batch 4250, loss[loss=0.2395, simple_loss=0.3194, pruned_loss=0.07983, over 7375.00 frames.], tot_loss[loss=0.2053, simple_loss=0.285, pruned_loss=0.06283, over 1428515.41 frames.], batch size: 23, lr: 1.12e-03
+2022-05-14 04:21:32,448 INFO [train.py:812] (2/8) Epoch 6, batch 4300, loss[loss=0.2148, simple_loss=0.2844, pruned_loss=0.07262, over 7062.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2846, pruned_loss=0.06302, over 1423641.48 frames.], batch size: 18, lr: 1.12e-03
+2022-05-14 04:22:31,650 INFO [train.py:812] (2/8) Epoch 6, batch 4350, loss[loss=0.2186, simple_loss=0.2915, pruned_loss=0.0728, over 7225.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2844, pruned_loss=0.06288, over 1424193.38 frames.], batch size: 21, lr: 1.12e-03
+2022-05-14 04:23:31,434 INFO [train.py:812] (2/8) Epoch 6, batch 4400, loss[loss=0.1988, simple_loss=0.2783, pruned_loss=0.05968, over 7423.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2836, pruned_loss=0.06261, over 1422291.29 frames.], batch size: 20, lr: 1.12e-03
+2022-05-14 04:24:30,567 INFO [train.py:812] (2/8) Epoch 6, batch 4450, loss[loss=0.1621, simple_loss=0.247, pruned_loss=0.03859, over 7275.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2832, pruned_loss=0.0626, over 1407683.47 frames.], batch size: 17, lr: 1.11e-03
+2022-05-14 04:25:38,563 INFO [train.py:812] (2/8) Epoch 6, batch 4500, loss[loss=0.2205, simple_loss=0.3026, pruned_loss=0.06924, over 7228.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2813, pruned_loss=0.062, over 1406761.66 frames.], batch size: 20, lr: 1.11e-03
+2022-05-14 04:26:36,426 INFO [train.py:812] (2/8) Epoch 6, batch 4550, loss[loss=0.3243, simple_loss=0.3697, pruned_loss=0.1395, over 5152.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2843, pruned_loss=0.06469, over 1356952.16 frames.], batch size: 52, lr: 1.11e-03
+2022-05-14 04:27:44,580 INFO [train.py:812] (2/8) Epoch 7, batch 0, loss[loss=0.1735, simple_loss=0.255, pruned_loss=0.04598, over 7416.00 frames.], tot_loss[loss=0.1735, simple_loss=0.255, pruned_loss=0.04598, over 7416.00 frames.], batch size: 18, lr: 1.07e-03
+2022-05-14 04:28:43,246 INFO [train.py:812] (2/8) Epoch 7, batch 50, loss[loss=0.1752, simple_loss=0.2533, pruned_loss=0.04857, over 7400.00 frames.], tot_loss[loss=0.198, simple_loss=0.2781, pruned_loss=0.05899, over 322815.50 frames.], batch size: 18, lr: 1.07e-03
+2022-05-14 04:29:42,462 INFO [train.py:812] (2/8) Epoch 7, batch 100, loss[loss=0.1869, simple_loss=0.2663, pruned_loss=0.05373, over 7150.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2808, pruned_loss=0.05973, over 568076.77 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:30:41,780 INFO [train.py:812] (2/8) Epoch 7, batch 150, loss[loss=0.2127, simple_loss=0.2877, pruned_loss=0.06887, over 7147.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2832, pruned_loss=0.06086, over 757943.75 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:31:41,613 INFO [train.py:812] (2/8) Epoch 7, batch 200, loss[loss=0.2514, simple_loss=0.3279, pruned_loss=0.08746, over 7375.00 frames.], tot_loss[loss=0.2029, simple_loss=0.284, pruned_loss=0.06088, over 906405.67 frames.], batch size: 23, lr: 1.06e-03
+2022-05-14 04:32:39,938 INFO [train.py:812] (2/8) Epoch 7, batch 250, loss[loss=0.2203, simple_loss=0.3044, pruned_loss=0.06811, over 7149.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2834, pruned_loss=0.06053, over 1020693.78 frames.], batch size: 20, lr: 1.06e-03
+2022-05-14 04:33:39,413 INFO [train.py:812] (2/8) Epoch 7, batch 300, loss[loss=0.1825, simple_loss=0.25, pruned_loss=0.05745, over 6820.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2833, pruned_loss=0.06042, over 1106789.49 frames.], batch size: 15, lr: 1.06e-03
+2022-05-14 04:34:57,025 INFO [train.py:812] (2/8) Epoch 7, batch 350, loss[loss=0.1928, simple_loss=0.2789, pruned_loss=0.05342, over 7118.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2821, pruned_loss=0.05978, over 1177047.43 frames.], batch size: 21, lr: 1.06e-03
+2022-05-14 04:35:53,856 INFO [train.py:812] (2/8) Epoch 7, batch 400, loss[loss=0.1952, simple_loss=0.2756, pruned_loss=0.05738, over 7169.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2833, pruned_loss=0.06027, over 1229882.45 frames.], batch size: 18, lr: 1.06e-03
+2022-05-14 04:37:20,597 INFO [train.py:812] (2/8) Epoch 7, batch 450, loss[loss=0.1681, simple_loss=0.2548, pruned_loss=0.04063, over 7370.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2839, pruned_loss=0.0608, over 1275641.13 frames.], batch size: 19, lr: 1.06e-03
+2022-05-14 04:38:43,153 INFO [train.py:812] (2/8) Epoch 7, batch 500, loss[loss=0.1902, simple_loss=0.2689, pruned_loss=0.05573, over 6197.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2847, pruned_loss=0.06111, over 1304927.12 frames.], batch size: 37, lr: 1.06e-03
+2022-05-14 04:39:42,051 INFO [train.py:812] (2/8) Epoch 7, batch 550, loss[loss=0.2363, simple_loss=0.32, pruned_loss=0.07626, over 7125.00 frames.], tot_loss[loss=0.202, simple_loss=0.2832, pruned_loss=0.06039, over 1330268.84 frames.], batch size: 21, lr: 1.06e-03
+2022-05-14 04:40:39,503 INFO [train.py:812] (2/8) Epoch 7, batch 600, loss[loss=0.2389, simple_loss=0.313, pruned_loss=0.08238, over 7058.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2844, pruned_loss=0.06102, over 1348650.42 frames.], batch size: 28, lr: 1.06e-03
+2022-05-14 04:41:38,883 INFO [train.py:812] (2/8) Epoch 7, batch 650, loss[loss=0.2967, simple_loss=0.3419, pruned_loss=0.1258, over 4714.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2838, pruned_loss=0.06076, over 1364583.71 frames.], batch size: 53, lr: 1.05e-03
+2022-05-14 04:42:37,617 INFO [train.py:812] (2/8) Epoch 7, batch 700, loss[loss=0.1847, simple_loss=0.2733, pruned_loss=0.04801, over 7160.00 frames.], tot_loss[loss=0.2005, simple_loss=0.282, pruned_loss=0.05957, over 1378149.32 frames.], batch size: 18, lr: 1.05e-03
+2022-05-14 04:43:36,170 INFO [train.py:812] (2/8) Epoch 7, batch 750, loss[loss=0.2027, simple_loss=0.2845, pruned_loss=0.06043, over 6738.00 frames.], tot_loss[loss=0.2006, simple_loss=0.282, pruned_loss=0.05962, over 1390598.15 frames.], batch size: 31, lr: 1.05e-03
+2022-05-14 04:44:33,657 INFO [train.py:812] (2/8) Epoch 7, batch 800, loss[loss=0.1995, simple_loss=0.2941, pruned_loss=0.0524, over 7333.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2826, pruned_loss=0.0604, over 1391910.38 frames.], batch size: 20, lr: 1.05e-03
+2022-05-14 04:45:32,929 INFO [train.py:812] (2/8) Epoch 7, batch 850, loss[loss=0.2017, simple_loss=0.2799, pruned_loss=0.06174, over 7291.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2823, pruned_loss=0.06015, over 1398627.47 frames.], batch size: 24, lr: 1.05e-03
+2022-05-14 04:46:32,344 INFO [train.py:812] (2/8) Epoch 7, batch 900, loss[loss=0.261, simple_loss=0.3373, pruned_loss=0.09238, over 7381.00 frames.], tot_loss[loss=0.201, simple_loss=0.2821, pruned_loss=0.05997, over 1404057.45 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:47:31,121 INFO [train.py:812] (2/8) Epoch 7, batch 950, loss[loss=0.2279, simple_loss=0.3258, pruned_loss=0.06503, over 7390.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2824, pruned_loss=0.05991, over 1408216.92 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:48:29,684 INFO [train.py:812] (2/8) Epoch 7, batch 1000, loss[loss=0.203, simple_loss=0.2899, pruned_loss=0.05805, over 7371.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2827, pruned_loss=0.06038, over 1410128.80 frames.], batch size: 23, lr: 1.05e-03
+2022-05-14 04:49:29,138 INFO [train.py:812] (2/8) Epoch 7, batch 1050, loss[loss=0.1927, simple_loss=0.2812, pruned_loss=0.05213, over 7157.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2835, pruned_loss=0.06034, over 1417069.22 frames.], batch size: 19, lr: 1.05e-03
+2022-05-14 04:50:29,062 INFO [train.py:812] (2/8) Epoch 7, batch 1100, loss[loss=0.2385, simple_loss=0.3274, pruned_loss=0.07479, over 7253.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2831, pruned_loss=0.06015, over 1420232.78 frames.], batch size: 25, lr: 1.05e-03
+2022-05-14 04:51:28,385 INFO [train.py:812] (2/8) Epoch 7, batch 1150, loss[loss=0.1798, simple_loss=0.2544, pruned_loss=0.0526, over 7136.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2821, pruned_loss=0.05944, over 1418942.43 frames.], batch size: 17, lr: 1.05e-03
+2022-05-14 04:52:28,294 INFO [train.py:812] (2/8) Epoch 7, batch 1200, loss[loss=0.1862, simple_loss=0.253, pruned_loss=0.05965, over 6841.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2823, pruned_loss=0.05971, over 1412898.13 frames.], batch size: 15, lr: 1.04e-03
+2022-05-14 04:53:27,874 INFO [train.py:812] (2/8) Epoch 7, batch 1250, loss[loss=0.2, simple_loss=0.288, pruned_loss=0.05597, over 7234.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2819, pruned_loss=0.05979, over 1415950.22 frames.], batch size: 20, lr: 1.04e-03
+2022-05-14 04:54:25,602 INFO [train.py:812] (2/8) Epoch 7, batch 1300, loss[loss=0.1861, simple_loss=0.2574, pruned_loss=0.0574, over 7286.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2807, pruned_loss=0.05913, over 1416955.20 frames.], batch size: 17, lr: 1.04e-03
+2022-05-14 04:55:24,136 INFO [train.py:812] (2/8) Epoch 7, batch 1350, loss[loss=0.2143, simple_loss=0.2943, pruned_loss=0.06718, over 7418.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2809, pruned_loss=0.05894, over 1421801.61 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 04:56:22,885 INFO [train.py:812] (2/8) Epoch 7, batch 1400, loss[loss=0.2001, simple_loss=0.2855, pruned_loss=0.05739, over 7158.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2813, pruned_loss=0.05919, over 1419701.06 frames.], batch size: 19, lr: 1.04e-03
+2022-05-14 04:57:22,032 INFO [train.py:812] (2/8) Epoch 7, batch 1450, loss[loss=0.2109, simple_loss=0.2937, pruned_loss=0.06408, over 6669.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2814, pruned_loss=0.05944, over 1420172.91 frames.], batch size: 31, lr: 1.04e-03
+2022-05-14 04:58:20,155 INFO [train.py:812] (2/8) Epoch 7, batch 1500, loss[loss=0.2259, simple_loss=0.3051, pruned_loss=0.0733, over 7417.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2814, pruned_loss=0.05901, over 1423407.82 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 04:59:18,876 INFO [train.py:812] (2/8) Epoch 7, batch 1550, loss[loss=0.2538, simple_loss=0.3376, pruned_loss=0.085, over 7152.00 frames.], tot_loss[loss=0.201, simple_loss=0.2825, pruned_loss=0.05975, over 1417818.13 frames.], batch size: 26, lr: 1.04e-03
+2022-05-14 05:00:18,917 INFO [train.py:812] (2/8) Epoch 7, batch 1600, loss[loss=0.1934, simple_loss=0.2841, pruned_loss=0.05133, over 7122.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2821, pruned_loss=0.05975, over 1424287.65 frames.], batch size: 21, lr: 1.04e-03
+2022-05-14 05:01:18,243 INFO [train.py:812] (2/8) Epoch 7, batch 1650, loss[loss=0.1925, simple_loss=0.2606, pruned_loss=0.06218, over 7069.00 frames.], tot_loss[loss=0.2013, simple_loss=0.282, pruned_loss=0.06033, over 1418245.98 frames.], batch size: 18, lr: 1.04e-03
+2022-05-14 05:02:16,810 INFO [train.py:812] (2/8) Epoch 7, batch 1700, loss[loss=0.2222, simple_loss=0.3023, pruned_loss=0.07106, over 7206.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2813, pruned_loss=0.05997, over 1417628.83 frames.], batch size: 22, lr: 1.04e-03
+2022-05-14 05:03:15,987 INFO [train.py:812] (2/8) Epoch 7, batch 1750, loss[loss=0.2336, simple_loss=0.3131, pruned_loss=0.07704, over 7341.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2818, pruned_loss=0.06037, over 1413085.04 frames.], batch size: 22, lr: 1.04e-03
+2022-05-14 05:04:14,615 INFO [train.py:812] (2/8) Epoch 7, batch 1800, loss[loss=0.2058, simple_loss=0.2883, pruned_loss=0.06164, over 7318.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2833, pruned_loss=0.06088, over 1415622.73 frames.], batch size: 25, lr: 1.03e-03
+2022-05-14 05:05:13,136 INFO [train.py:812] (2/8) Epoch 7, batch 1850, loss[loss=0.17, simple_loss=0.2501, pruned_loss=0.04493, over 6983.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2825, pruned_loss=0.06031, over 1417510.91 frames.], batch size: 16, lr: 1.03e-03
+2022-05-14 05:06:10,514 INFO [train.py:812] (2/8) Epoch 7, batch 1900, loss[loss=0.1702, simple_loss=0.2585, pruned_loss=0.04095, over 7061.00 frames.], tot_loss[loss=0.2011, simple_loss=0.282, pruned_loss=0.06015, over 1414247.09 frames.], batch size: 18, lr: 1.03e-03
+2022-05-14 05:07:08,607 INFO [train.py:812] (2/8) Epoch 7, batch 1950, loss[loss=0.2512, simple_loss=0.3152, pruned_loss=0.09358, over 7290.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2815, pruned_loss=0.05995, over 1417397.99 frames.], batch size: 18, lr: 1.03e-03
+2022-05-14 05:08:07,325 INFO [train.py:812] (2/8) Epoch 7, batch 2000, loss[loss=0.2102, simple_loss=0.2962, pruned_loss=0.0621, over 7310.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2814, pruned_loss=0.05991, over 1418097.22 frames.], batch size: 25, lr: 1.03e-03
+2022-05-14 05:09:04,290 INFO [train.py:812] (2/8) Epoch 7, batch 2050, loss[loss=0.203, simple_loss=0.2948, pruned_loss=0.05554, over 7271.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2827, pruned_loss=0.06055, over 1415340.12 frames.], batch size: 24, lr: 1.03e-03
+2022-05-14 05:10:01,687 INFO [train.py:812] (2/8) Epoch 7, batch 2100, loss[loss=0.2069, simple_loss=0.2766, pruned_loss=0.0686, over 6991.00 frames.], tot_loss[loss=0.2013, simple_loss=0.282, pruned_loss=0.06031, over 1418303.25 frames.], batch size: 16, lr: 1.03e-03
+2022-05-14 05:11:00,087 INFO [train.py:812] (2/8) Epoch 7, batch 2150, loss[loss=0.1984, simple_loss=0.2864, pruned_loss=0.05522, over 7399.00 frames.], tot_loss[loss=0.201, simple_loss=0.2824, pruned_loss=0.05986, over 1423924.32 frames.], batch size: 21, lr: 1.03e-03
+2022-05-14 05:11:57,835 INFO [train.py:812] (2/8) Epoch 7, batch 2200, loss[loss=0.1523, simple_loss=0.2234, pruned_loss=0.0406, over 7131.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2825, pruned_loss=0.0599, over 1422389.30 frames.], batch size: 17, lr: 1.03e-03
+2022-05-14 05:12:56,792 INFO [train.py:812] (2/8) Epoch 7, batch 2250, loss[loss=0.2146, simple_loss=0.2758, pruned_loss=0.07675, over 7278.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2826, pruned_loss=0.06001, over 1417266.35 frames.], batch size: 17, lr: 1.03e-03
+2022-05-14 05:13:54,322 INFO [train.py:812] (2/8) Epoch 7, batch 2300, loss[loss=0.209, simple_loss=0.2924, pruned_loss=0.06281, over 7211.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2826, pruned_loss=0.06005, over 1419884.48 frames.], batch size: 23, lr: 1.03e-03
+2022-05-14 05:14:53,675 INFO [train.py:812] (2/8) Epoch 7, batch 2350, loss[loss=0.2059, simple_loss=0.2892, pruned_loss=0.06125, over 7415.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2823, pruned_loss=0.06008, over 1417553.85 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:15:53,750 INFO [train.py:812] (2/8) Epoch 7, batch 2400, loss[loss=0.1664, simple_loss=0.2473, pruned_loss=0.04279, over 7270.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2821, pruned_loss=0.0603, over 1421758.47 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:16:51,042 INFO [train.py:812] (2/8) Epoch 7, batch 2450, loss[loss=0.202, simple_loss=0.292, pruned_loss=0.05601, over 7415.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2816, pruned_loss=0.05971, over 1417842.87 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:17:49,491 INFO [train.py:812] (2/8) Epoch 7, batch 2500, loss[loss=0.2013, simple_loss=0.2853, pruned_loss=0.05866, over 7325.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2819, pruned_loss=0.05994, over 1416825.95 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:18:48,411 INFO [train.py:812] (2/8) Epoch 7, batch 2550, loss[loss=0.2306, simple_loss=0.303, pruned_loss=0.07911, over 7416.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2823, pruned_loss=0.05978, over 1423326.04 frames.], batch size: 20, lr: 1.02e-03
+2022-05-14 05:19:47,311 INFO [train.py:812] (2/8) Epoch 7, batch 2600, loss[loss=0.2372, simple_loss=0.3093, pruned_loss=0.08251, over 7170.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2827, pruned_loss=0.06004, over 1417922.42 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:20:45,573 INFO [train.py:812] (2/8) Epoch 7, batch 2650, loss[loss=0.1986, simple_loss=0.2689, pruned_loss=0.06419, over 7155.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2822, pruned_loss=0.06028, over 1417393.47 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:21:44,762 INFO [train.py:812] (2/8) Epoch 7, batch 2700, loss[loss=0.1866, simple_loss=0.265, pruned_loss=0.05415, over 7194.00 frames.], tot_loss[loss=0.2021, simple_loss=0.283, pruned_loss=0.06058, over 1419532.31 frames.], batch size: 16, lr: 1.02e-03
+2022-05-14 05:22:44,407 INFO [train.py:812] (2/8) Epoch 7, batch 2750, loss[loss=0.1668, simple_loss=0.2486, pruned_loss=0.04248, over 7405.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2837, pruned_loss=0.06086, over 1419846.59 frames.], batch size: 18, lr: 1.02e-03
+2022-05-14 05:23:44,357 INFO [train.py:812] (2/8) Epoch 7, batch 2800, loss[loss=0.1971, simple_loss=0.2691, pruned_loss=0.06251, over 6981.00 frames.], tot_loss[loss=0.2021, simple_loss=0.283, pruned_loss=0.0606, over 1417971.14 frames.], batch size: 16, lr: 1.02e-03
+2022-05-14 05:24:43,854 INFO [train.py:812] (2/8) Epoch 7, batch 2850, loss[loss=0.2436, simple_loss=0.3172, pruned_loss=0.08504, over 7329.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2808, pruned_loss=0.05939, over 1422486.14 frames.], batch size: 21, lr: 1.02e-03
+2022-05-14 05:25:43,737 INFO [train.py:812] (2/8) Epoch 7, batch 2900, loss[loss=0.2248, simple_loss=0.2963, pruned_loss=0.07665, over 4979.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2803, pruned_loss=0.05866, over 1424535.05 frames.], batch size: 52, lr: 1.02e-03
+2022-05-14 05:26:42,753 INFO [train.py:812] (2/8) Epoch 7, batch 2950, loss[loss=0.2064, simple_loss=0.2921, pruned_loss=0.06035, over 7294.00 frames.], tot_loss[loss=0.2004, simple_loss=0.282, pruned_loss=0.0594, over 1424736.01 frames.], batch size: 25, lr: 1.01e-03
+2022-05-14 05:27:42,436 INFO [train.py:812] (2/8) Epoch 7, batch 3000, loss[loss=0.2275, simple_loss=0.3069, pruned_loss=0.07408, over 7166.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2824, pruned_loss=0.05948, over 1426490.73 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:27:42,437 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 05:27:49,661 INFO [train.py:841] (2/8) Epoch 7, validation: loss=0.1637, simple_loss=0.2662, pruned_loss=0.03066, over 698248.00 frames.
+2022-05-14 05:28:48,979 INFO [train.py:812] (2/8) Epoch 7, batch 3050, loss[loss=0.2258, simple_loss=0.3041, pruned_loss=0.07372, over 7142.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2827, pruned_loss=0.05988, over 1426668.20 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:29:48,881 INFO [train.py:812] (2/8) Epoch 7, batch 3100, loss[loss=0.2063, simple_loss=0.2955, pruned_loss=0.05858, over 7162.00 frames.], tot_loss[loss=0.2018, simple_loss=0.283, pruned_loss=0.06027, over 1424044.84 frames.], batch size: 26, lr: 1.01e-03
+2022-05-14 05:30:48,417 INFO [train.py:812] (2/8) Epoch 7, batch 3150, loss[loss=0.207, simple_loss=0.2804, pruned_loss=0.0668, over 7062.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2824, pruned_loss=0.0597, over 1427219.92 frames.], batch size: 28, lr: 1.01e-03
+2022-05-14 05:31:47,520 INFO [train.py:812] (2/8) Epoch 7, batch 3200, loss[loss=0.2097, simple_loss=0.3012, pruned_loss=0.05909, over 7342.00 frames.], tot_loss[loss=0.201, simple_loss=0.2825, pruned_loss=0.05976, over 1423446.34 frames.], batch size: 22, lr: 1.01e-03
+2022-05-14 05:32:46,949 INFO [train.py:812] (2/8) Epoch 7, batch 3250, loss[loss=0.2303, simple_loss=0.3176, pruned_loss=0.07154, over 7067.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2815, pruned_loss=0.05938, over 1423092.16 frames.], batch size: 28, lr: 1.01e-03
+2022-05-14 05:33:46,316 INFO [train.py:812] (2/8) Epoch 7, batch 3300, loss[loss=0.1923, simple_loss=0.2865, pruned_loss=0.04901, over 7154.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2831, pruned_loss=0.05972, over 1418984.89 frames.], batch size: 20, lr: 1.01e-03
+2022-05-14 05:34:45,879 INFO [train.py:812] (2/8) Epoch 7, batch 3350, loss[loss=0.1952, simple_loss=0.2746, pruned_loss=0.05792, over 7169.00 frames.], tot_loss[loss=0.201, simple_loss=0.2833, pruned_loss=0.05936, over 1420291.36 frames.], batch size: 19, lr: 1.01e-03
+2022-05-14 05:35:44,954 INFO [train.py:812] (2/8) Epoch 7, batch 3400, loss[loss=0.221, simple_loss=0.3005, pruned_loss=0.07078, over 7112.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2833, pruned_loss=0.05916, over 1422772.03 frames.], batch size: 21, lr: 1.01e-03
+2022-05-14 05:36:43,587 INFO [train.py:812] (2/8) Epoch 7, batch 3450, loss[loss=0.2417, simple_loss=0.3302, pruned_loss=0.07661, over 7281.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2828, pruned_loss=0.05892, over 1420768.99 frames.], batch size: 24, lr: 1.01e-03
+2022-05-14 05:37:43,072 INFO [train.py:812] (2/8) Epoch 7, batch 3500, loss[loss=0.1938, simple_loss=0.2837, pruned_loss=0.05196, over 7223.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2828, pruned_loss=0.05887, over 1423211.15 frames.], batch size: 21, lr: 1.01e-03
+2022-05-14 05:38:41,454 INFO [train.py:812] (2/8) Epoch 7, batch 3550, loss[loss=0.2083, simple_loss=0.2933, pruned_loss=0.0616, over 7400.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2826, pruned_loss=0.05855, over 1424701.33 frames.], batch size: 23, lr: 1.01e-03
+2022-05-14 05:39:40,563 INFO [train.py:812] (2/8) Epoch 7, batch 3600, loss[loss=0.2043, simple_loss=0.2924, pruned_loss=0.05815, over 7212.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2822, pruned_loss=0.05853, over 1425850.29 frames.], batch size: 21, lr: 1.00e-03
+2022-05-14 05:40:39,079 INFO [train.py:812] (2/8) Epoch 7, batch 3650, loss[loss=0.2259, simple_loss=0.3026, pruned_loss=0.07459, over 7063.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2825, pruned_loss=0.05907, over 1422826.33 frames.], batch size: 28, lr: 1.00e-03
+2022-05-14 05:41:38,804 INFO [train.py:812] (2/8) Epoch 7, batch 3700, loss[loss=0.198, simple_loss=0.2786, pruned_loss=0.05873, over 7437.00 frames.], tot_loss[loss=0.198, simple_loss=0.2801, pruned_loss=0.05796, over 1424231.52 frames.], batch size: 20, lr: 1.00e-03
+2022-05-14 05:42:38,017 INFO [train.py:812] (2/8) Epoch 7, batch 3750, loss[loss=0.275, simple_loss=0.3316, pruned_loss=0.1092, over 5056.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2805, pruned_loss=0.05823, over 1424126.74 frames.], batch size: 52, lr: 1.00e-03
+2022-05-14 05:43:37,572 INFO [train.py:812] (2/8) Epoch 7, batch 3800, loss[loss=0.1675, simple_loss=0.2466, pruned_loss=0.04422, over 7354.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2799, pruned_loss=0.0575, over 1420917.07 frames.], batch size: 19, lr: 1.00e-03
+2022-05-14 05:44:35,596 INFO [train.py:812] (2/8) Epoch 7, batch 3850, loss[loss=0.1806, simple_loss=0.2586, pruned_loss=0.05125, over 7126.00 frames.], tot_loss[loss=0.1969, simple_loss=0.279, pruned_loss=0.05741, over 1423764.64 frames.], batch size: 17, lr: 1.00e-03
+2022-05-14 05:45:34,807 INFO [train.py:812] (2/8) Epoch 7, batch 3900, loss[loss=0.1869, simple_loss=0.2665, pruned_loss=0.05369, over 7150.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2783, pruned_loss=0.05699, over 1424867.73 frames.], batch size: 18, lr: 1.00e-03
+2022-05-14 05:46:31,677 INFO [train.py:812] (2/8) Epoch 7, batch 3950, loss[loss=0.1959, simple_loss=0.2863, pruned_loss=0.05276, over 7338.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2782, pruned_loss=0.05707, over 1426353.93 frames.], batch size: 22, lr: 9.99e-04
+2022-05-14 05:47:30,572 INFO [train.py:812] (2/8) Epoch 7, batch 4000, loss[loss=0.2242, simple_loss=0.3077, pruned_loss=0.07036, over 6711.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2778, pruned_loss=0.05652, over 1430740.30 frames.], batch size: 31, lr: 9.98e-04
+2022-05-14 05:48:29,682 INFO [train.py:812] (2/8) Epoch 7, batch 4050, loss[loss=0.1794, simple_loss=0.2637, pruned_loss=0.04758, over 7172.00 frames.], tot_loss[loss=0.1959, simple_loss=0.278, pruned_loss=0.05693, over 1428955.51 frames.], batch size: 18, lr: 9.98e-04
+2022-05-14 05:49:28,782 INFO [train.py:812] (2/8) Epoch 7, batch 4100, loss[loss=0.1991, simple_loss=0.2843, pruned_loss=0.057, over 7112.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2787, pruned_loss=0.05802, over 1424560.73 frames.], batch size: 21, lr: 9.97e-04
+2022-05-14 05:50:26,074 INFO [train.py:812] (2/8) Epoch 7, batch 4150, loss[loss=0.1982, simple_loss=0.2799, pruned_loss=0.05823, over 7208.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2783, pruned_loss=0.05757, over 1425248.51 frames.], batch size: 23, lr: 9.96e-04
+2022-05-14 05:51:25,280 INFO [train.py:812] (2/8) Epoch 7, batch 4200, loss[loss=0.1696, simple_loss=0.2511, pruned_loss=0.0441, over 7301.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2775, pruned_loss=0.05659, over 1427668.55 frames.], batch size: 17, lr: 9.95e-04
+2022-05-14 05:52:24,687 INFO [train.py:812] (2/8) Epoch 7, batch 4250, loss[loss=0.1655, simple_loss=0.2526, pruned_loss=0.03924, over 7434.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2788, pruned_loss=0.05748, over 1423181.98 frames.], batch size: 20, lr: 9.95e-04
+2022-05-14 05:53:23,911 INFO [train.py:812] (2/8) Epoch 7, batch 4300, loss[loss=0.2319, simple_loss=0.3077, pruned_loss=0.078, over 7238.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2805, pruned_loss=0.0584, over 1417445.86 frames.], batch size: 20, lr: 9.94e-04
+2022-05-14 05:54:23,292 INFO [train.py:812] (2/8) Epoch 7, batch 4350, loss[loss=0.2135, simple_loss=0.2936, pruned_loss=0.06667, over 6501.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2812, pruned_loss=0.05865, over 1411536.75 frames.], batch size: 38, lr: 9.93e-04
+2022-05-14 05:55:22,296 INFO [train.py:812] (2/8) Epoch 7, batch 4400, loss[loss=0.2276, simple_loss=0.3152, pruned_loss=0.06998, over 6769.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2808, pruned_loss=0.05901, over 1413389.79 frames.], batch size: 31, lr: 9.92e-04
+2022-05-14 05:56:20,594 INFO [train.py:812] (2/8) Epoch 7, batch 4450, loss[loss=0.2129, simple_loss=0.2962, pruned_loss=0.06482, over 7211.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2804, pruned_loss=0.05858, over 1408897.29 frames.], batch size: 22, lr: 9.92e-04
+2022-05-14 05:57:24,428 INFO [train.py:812] (2/8) Epoch 7, batch 4500, loss[loss=0.2145, simple_loss=0.3, pruned_loss=0.06453, over 7201.00 frames.], tot_loss[loss=0.2, simple_loss=0.2815, pruned_loss=0.05927, over 1406744.25 frames.], batch size: 22, lr: 9.91e-04
+2022-05-14 05:58:22,215 INFO [train.py:812] (2/8) Epoch 7, batch 4550, loss[loss=0.2627, simple_loss=0.3353, pruned_loss=0.09508, over 4484.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2834, pruned_loss=0.06, over 1390470.74 frames.], batch size: 52, lr: 9.90e-04
+2022-05-14 05:59:32,648 INFO [train.py:812] (2/8) Epoch 8, batch 0, loss[loss=0.2145, simple_loss=0.2989, pruned_loss=0.06503, over 7333.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2989, pruned_loss=0.06503, over 7333.00 frames.], batch size: 22, lr: 9.49e-04
+2022-05-14 06:00:31,159 INFO [train.py:812] (2/8) Epoch 8, batch 50, loss[loss=0.2044, simple_loss=0.2803, pruned_loss=0.06428, over 7140.00 frames.], tot_loss[loss=0.203, simple_loss=0.286, pruned_loss=0.05994, over 320577.13 frames.], batch size: 17, lr: 9.48e-04
+2022-05-14 06:01:30,460 INFO [train.py:812] (2/8) Epoch 8, batch 100, loss[loss=0.1863, simple_loss=0.2771, pruned_loss=0.04775, over 7299.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2821, pruned_loss=0.05652, over 568792.95 frames.], batch size: 25, lr: 9.48e-04
+2022-05-14 06:02:29,695 INFO [train.py:812] (2/8) Epoch 8, batch 150, loss[loss=0.211, simple_loss=0.3005, pruned_loss=0.0608, over 7115.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2801, pruned_loss=0.05641, over 757942.20 frames.], batch size: 21, lr: 9.47e-04
+2022-05-14 06:03:26,754 INFO [train.py:812] (2/8) Epoch 8, batch 200, loss[loss=0.22, simple_loss=0.3078, pruned_loss=0.06605, over 7206.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2805, pruned_loss=0.05657, over 906887.72 frames.], batch size: 22, lr: 9.46e-04
+2022-05-14 06:04:24,364 INFO [train.py:812] (2/8) Epoch 8, batch 250, loss[loss=0.2028, simple_loss=0.2957, pruned_loss=0.05498, over 7124.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2802, pruned_loss=0.05648, over 1020180.62 frames.], batch size: 21, lr: 9.46e-04
+2022-05-14 06:05:21,314 INFO [train.py:812] (2/8) Epoch 8, batch 300, loss[loss=0.2108, simple_loss=0.2818, pruned_loss=0.06994, over 7064.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2799, pruned_loss=0.0564, over 1106322.70 frames.], batch size: 18, lr: 9.45e-04
+2022-05-14 06:06:19,884 INFO [train.py:812] (2/8) Epoch 8, batch 350, loss[loss=0.1917, simple_loss=0.2822, pruned_loss=0.05057, over 7102.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2793, pruned_loss=0.05674, over 1178616.50 frames.], batch size: 21, lr: 9.44e-04
+2022-05-14 06:07:19,499 INFO [train.py:812] (2/8) Epoch 8, batch 400, loss[loss=0.2475, simple_loss=0.309, pruned_loss=0.09305, over 5122.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2788, pruned_loss=0.05617, over 1232100.56 frames.], batch size: 52, lr: 9.43e-04
+2022-05-14 06:08:18,806 INFO [train.py:812] (2/8) Epoch 8, batch 450, loss[loss=0.1597, simple_loss=0.2438, pruned_loss=0.0378, over 7186.00 frames.], tot_loss[loss=0.195, simple_loss=0.2777, pruned_loss=0.05619, over 1273821.54 frames.], batch size: 16, lr: 9.43e-04
+2022-05-14 06:09:18,366 INFO [train.py:812] (2/8) Epoch 8, batch 500, loss[loss=0.1796, simple_loss=0.2713, pruned_loss=0.0439, over 7213.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2781, pruned_loss=0.05615, over 1306219.87 frames.], batch size: 23, lr: 9.42e-04
+2022-05-14 06:10:16,959 INFO [train.py:812] (2/8) Epoch 8, batch 550, loss[loss=0.2116, simple_loss=0.2972, pruned_loss=0.06297, over 7213.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2778, pruned_loss=0.05591, over 1333503.61 frames.], batch size: 23, lr: 9.41e-04
+2022-05-14 06:11:16,907 INFO [train.py:812] (2/8) Epoch 8, batch 600, loss[loss=0.1996, simple_loss=0.2899, pruned_loss=0.05469, over 7217.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2793, pruned_loss=0.05606, over 1353591.48 frames.], batch size: 21, lr: 9.41e-04
+2022-05-14 06:12:15,257 INFO [train.py:812] (2/8) Epoch 8, batch 650, loss[loss=0.182, simple_loss=0.2664, pruned_loss=0.04877, over 7258.00 frames.], tot_loss[loss=0.195, simple_loss=0.2785, pruned_loss=0.05577, over 1368697.26 frames.], batch size: 19, lr: 9.40e-04
+2022-05-14 06:13:14,249 INFO [train.py:812] (2/8) Epoch 8, batch 700, loss[loss=0.2217, simple_loss=0.2975, pruned_loss=0.07294, over 5245.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2791, pruned_loss=0.05651, over 1376641.15 frames.], batch size: 54, lr: 9.39e-04
+2022-05-14 06:14:13,342 INFO [train.py:812] (2/8) Epoch 8, batch 750, loss[loss=0.2032, simple_loss=0.2724, pruned_loss=0.06696, over 7364.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2785, pruned_loss=0.05618, over 1385766.86 frames.], batch size: 19, lr: 9.39e-04
+2022-05-14 06:15:12,816 INFO [train.py:812] (2/8) Epoch 8, batch 800, loss[loss=0.22, simple_loss=0.3052, pruned_loss=0.06737, over 6272.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2794, pruned_loss=0.05677, over 1390215.45 frames.], batch size: 37, lr: 9.38e-04
+2022-05-14 06:16:12,236 INFO [train.py:812] (2/8) Epoch 8, batch 850, loss[loss=0.1676, simple_loss=0.2429, pruned_loss=0.04612, over 7418.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2774, pruned_loss=0.05596, over 1399107.57 frames.], batch size: 18, lr: 9.37e-04
+2022-05-14 06:17:11,304 INFO [train.py:812] (2/8) Epoch 8, batch 900, loss[loss=0.197, simple_loss=0.2763, pruned_loss=0.05884, over 6817.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2767, pruned_loss=0.0553, over 1398776.19 frames.], batch size: 31, lr: 9.36e-04
+2022-05-14 06:18:09,038 INFO [train.py:812] (2/8) Epoch 8, batch 950, loss[loss=0.2029, simple_loss=0.2875, pruned_loss=0.05914, over 7242.00 frames.], tot_loss[loss=0.194, simple_loss=0.2774, pruned_loss=0.05528, over 1404353.65 frames.], batch size: 20, lr: 9.36e-04
+2022-05-14 06:19:08,067 INFO [train.py:812] (2/8) Epoch 8, batch 1000, loss[loss=0.1758, simple_loss=0.2614, pruned_loss=0.04512, over 7218.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2778, pruned_loss=0.05536, over 1408795.51 frames.], batch size: 21, lr: 9.35e-04
+2022-05-14 06:20:06,230 INFO [train.py:812] (2/8) Epoch 8, batch 1050, loss[loss=0.1469, simple_loss=0.2293, pruned_loss=0.03223, over 7126.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2792, pruned_loss=0.05623, over 1406634.64 frames.], batch size: 17, lr: 9.34e-04
+2022-05-14 06:21:04,768 INFO [train.py:812] (2/8) Epoch 8, batch 1100, loss[loss=0.2102, simple_loss=0.2988, pruned_loss=0.06076, over 7206.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2796, pruned_loss=0.05674, over 1411662.44 frames.], batch size: 22, lr: 9.34e-04
+2022-05-14 06:22:02,860 INFO [train.py:812] (2/8) Epoch 8, batch 1150, loss[loss=0.2267, simple_loss=0.3026, pruned_loss=0.07538, over 5063.00 frames.], tot_loss[loss=0.1967, simple_loss=0.28, pruned_loss=0.05665, over 1416792.32 frames.], batch size: 52, lr: 9.33e-04
+2022-05-14 06:23:10,921 INFO [train.py:812] (2/8) Epoch 8, batch 1200, loss[loss=0.174, simple_loss=0.2638, pruned_loss=0.04212, over 7148.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2788, pruned_loss=0.05578, over 1420392.12 frames.], batch size: 20, lr: 9.32e-04
+2022-05-14 06:24:10,141 INFO [train.py:812] (2/8) Epoch 8, batch 1250, loss[loss=0.1394, simple_loss=0.2241, pruned_loss=0.02733, over 7291.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2778, pruned_loss=0.05568, over 1418978.92 frames.], batch size: 18, lr: 9.32e-04
+2022-05-14 06:25:09,443 INFO [train.py:812] (2/8) Epoch 8, batch 1300, loss[loss=0.2161, simple_loss=0.3, pruned_loss=0.06609, over 7145.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2783, pruned_loss=0.05608, over 1415560.27 frames.], batch size: 20, lr: 9.31e-04
+2022-05-14 06:26:08,272 INFO [train.py:812] (2/8) Epoch 8, batch 1350, loss[loss=0.241, simple_loss=0.3158, pruned_loss=0.08308, over 7158.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2783, pruned_loss=0.05609, over 1414580.78 frames.], batch size: 19, lr: 9.30e-04
+2022-05-14 06:27:08,001 INFO [train.py:812] (2/8) Epoch 8, batch 1400, loss[loss=0.149, simple_loss=0.238, pruned_loss=0.03003, over 7269.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2786, pruned_loss=0.05582, over 1415648.00 frames.], batch size: 18, lr: 9.30e-04
+2022-05-14 06:28:06,887 INFO [train.py:812] (2/8) Epoch 8, batch 1450, loss[loss=0.2212, simple_loss=0.2948, pruned_loss=0.07377, over 7151.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2781, pruned_loss=0.05526, over 1415178.57 frames.], batch size: 18, lr: 9.29e-04
+2022-05-14 06:29:06,704 INFO [train.py:812] (2/8) Epoch 8, batch 1500, loss[loss=0.1535, simple_loss=0.2342, pruned_loss=0.03639, over 7408.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2767, pruned_loss=0.05508, over 1415426.16 frames.], batch size: 18, lr: 9.28e-04
+2022-05-14 06:30:05,550 INFO [train.py:812] (2/8) Epoch 8, batch 1550, loss[loss=0.2518, simple_loss=0.3234, pruned_loss=0.09014, over 7208.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2767, pruned_loss=0.05515, over 1420595.66 frames.], batch size: 22, lr: 9.28e-04
+2022-05-14 06:31:05,136 INFO [train.py:812] (2/8) Epoch 8, batch 1600, loss[loss=0.1822, simple_loss=0.2763, pruned_loss=0.04406, over 6308.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2778, pruned_loss=0.05562, over 1421277.07 frames.], batch size: 37, lr: 9.27e-04
+2022-05-14 06:32:04,301 INFO [train.py:812] (2/8) Epoch 8, batch 1650, loss[loss=0.2108, simple_loss=0.285, pruned_loss=0.06833, over 7299.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2778, pruned_loss=0.05541, over 1419297.41 frames.], batch size: 24, lr: 9.26e-04
+2022-05-14 06:33:04,111 INFO [train.py:812] (2/8) Epoch 8, batch 1700, loss[loss=0.213, simple_loss=0.306, pruned_loss=0.05999, over 7326.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2784, pruned_loss=0.05543, over 1420635.85 frames.], batch size: 21, lr: 9.26e-04
+2022-05-14 06:34:03,594 INFO [train.py:812] (2/8) Epoch 8, batch 1750, loss[loss=0.1916, simple_loss=0.2789, pruned_loss=0.05212, over 7333.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2776, pruned_loss=0.055, over 1420419.38 frames.], batch size: 22, lr: 9.25e-04
+2022-05-14 06:35:12,521 INFO [train.py:812] (2/8) Epoch 8, batch 1800, loss[loss=0.1696, simple_loss=0.262, pruned_loss=0.03858, over 7339.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2768, pruned_loss=0.0549, over 1421417.93 frames.], batch size: 22, lr: 9.24e-04
+2022-05-14 06:36:21,368 INFO [train.py:812] (2/8) Epoch 8, batch 1850, loss[loss=0.1696, simple_loss=0.2629, pruned_loss=0.03812, over 7231.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2782, pruned_loss=0.05561, over 1422611.10 frames.], batch size: 20, lr: 9.24e-04
+2022-05-14 06:37:30,721 INFO [train.py:812] (2/8) Epoch 8, batch 1900, loss[loss=0.1933, simple_loss=0.2861, pruned_loss=0.05027, over 7298.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2765, pruned_loss=0.0548, over 1421387.63 frames.], batch size: 25, lr: 9.23e-04
+2022-05-14 06:38:48,462 INFO [train.py:812] (2/8) Epoch 8, batch 1950, loss[loss=0.1691, simple_loss=0.2504, pruned_loss=0.04387, over 7433.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2764, pruned_loss=0.05454, over 1426258.18 frames.], batch size: 17, lr: 9.22e-04
+2022-05-14 06:40:06,957 INFO [train.py:812] (2/8) Epoch 8, batch 2000, loss[loss=0.199, simple_loss=0.2915, pruned_loss=0.05321, over 7120.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2768, pruned_loss=0.05506, over 1427140.45 frames.], batch size: 21, lr: 9.22e-04
+2022-05-14 06:41:06,023 INFO [train.py:812] (2/8) Epoch 8, batch 2050, loss[loss=0.2414, simple_loss=0.312, pruned_loss=0.08546, over 5304.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2783, pruned_loss=0.05603, over 1421663.35 frames.], batch size: 53, lr: 9.21e-04
+2022-05-14 06:42:04,965 INFO [train.py:812] (2/8) Epoch 8, batch 2100, loss[loss=0.2022, simple_loss=0.2794, pruned_loss=0.06247, over 7233.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2788, pruned_loss=0.05651, over 1418150.73 frames.], batch size: 20, lr: 9.20e-04
+2022-05-14 06:43:03,995 INFO [train.py:812] (2/8) Epoch 8, batch 2150, loss[loss=0.2007, simple_loss=0.2839, pruned_loss=0.05874, over 7199.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2787, pruned_loss=0.05635, over 1419717.25 frames.], batch size: 22, lr: 9.20e-04
+2022-05-14 06:44:02,982 INFO [train.py:812] (2/8) Epoch 8, batch 2200, loss[loss=0.1932, simple_loss=0.2712, pruned_loss=0.05758, over 7267.00 frames.], tot_loss[loss=0.194, simple_loss=0.277, pruned_loss=0.0555, over 1418091.23 frames.], batch size: 24, lr: 9.19e-04
+2022-05-14 06:45:01,869 INFO [train.py:812] (2/8) Epoch 8, batch 2250, loss[loss=0.2187, simple_loss=0.308, pruned_loss=0.06469, over 7212.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2768, pruned_loss=0.05616, over 1412518.47 frames.], batch size: 23, lr: 9.18e-04
+2022-05-14 06:46:00,790 INFO [train.py:812] (2/8) Epoch 8, batch 2300, loss[loss=0.1624, simple_loss=0.2459, pruned_loss=0.03941, over 7400.00 frames.], tot_loss[loss=0.1951, simple_loss=0.277, pruned_loss=0.0566, over 1413238.83 frames.], batch size: 18, lr: 9.18e-04
+2022-05-14 06:46:59,574 INFO [train.py:812] (2/8) Epoch 8, batch 2350, loss[loss=0.1464, simple_loss=0.2363, pruned_loss=0.02824, over 7063.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2775, pruned_loss=0.0564, over 1413070.85 frames.], batch size: 18, lr: 9.17e-04
+2022-05-14 06:47:58,464 INFO [train.py:812] (2/8) Epoch 8, batch 2400, loss[loss=0.16, simple_loss=0.2511, pruned_loss=0.03442, over 7259.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2767, pruned_loss=0.05571, over 1417374.48 frames.], batch size: 19, lr: 9.16e-04
+2022-05-14 06:48:57,531 INFO [train.py:812] (2/8) Epoch 8, batch 2450, loss[loss=0.1778, simple_loss=0.2758, pruned_loss=0.03992, over 7294.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2777, pruned_loss=0.0559, over 1423660.63 frames.], batch size: 24, lr: 9.16e-04
+2022-05-14 06:49:57,000 INFO [train.py:812] (2/8) Epoch 8, batch 2500, loss[loss=0.1908, simple_loss=0.2887, pruned_loss=0.04642, over 7316.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2779, pruned_loss=0.05585, over 1421478.01 frames.], batch size: 21, lr: 9.15e-04
+2022-05-14 06:50:55,762 INFO [train.py:812] (2/8) Epoch 8, batch 2550, loss[loss=0.2062, simple_loss=0.2805, pruned_loss=0.06597, over 7345.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2773, pruned_loss=0.05572, over 1425447.83 frames.], batch size: 19, lr: 9.14e-04
+2022-05-14 06:51:54,446 INFO [train.py:812] (2/8) Epoch 8, batch 2600, loss[loss=0.1962, simple_loss=0.2774, pruned_loss=0.0575, over 6760.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2771, pruned_loss=0.0558, over 1425429.58 frames.], batch size: 15, lr: 9.14e-04
+2022-05-14 06:52:51,850 INFO [train.py:812] (2/8) Epoch 8, batch 2650, loss[loss=0.1794, simple_loss=0.2742, pruned_loss=0.04226, over 7118.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2763, pruned_loss=0.0553, over 1427020.37 frames.], batch size: 21, lr: 9.13e-04
+2022-05-14 06:53:49,750 INFO [train.py:812] (2/8) Epoch 8, batch 2700, loss[loss=0.1652, simple_loss=0.2424, pruned_loss=0.044, over 6876.00 frames.], tot_loss[loss=0.192, simple_loss=0.2746, pruned_loss=0.05469, over 1429054.86 frames.], batch size: 15, lr: 9.12e-04
+2022-05-14 06:54:48,264 INFO [train.py:812] (2/8) Epoch 8, batch 2750, loss[loss=0.2007, simple_loss=0.2614, pruned_loss=0.06998, over 7007.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2742, pruned_loss=0.05474, over 1427901.51 frames.], batch size: 16, lr: 9.12e-04
+2022-05-14 06:55:46,854 INFO [train.py:812] (2/8) Epoch 8, batch 2800, loss[loss=0.2112, simple_loss=0.3005, pruned_loss=0.06093, over 7142.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2757, pruned_loss=0.05528, over 1427929.41 frames.], batch size: 20, lr: 9.11e-04
+2022-05-14 06:56:44,433 INFO [train.py:812] (2/8) Epoch 8, batch 2850, loss[loss=0.2248, simple_loss=0.3038, pruned_loss=0.07291, over 7183.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2759, pruned_loss=0.05514, over 1426318.80 frames.], batch size: 22, lr: 9.11e-04
+2022-05-14 06:57:43,811 INFO [train.py:812] (2/8) Epoch 8, batch 2900, loss[loss=0.1913, simple_loss=0.2669, pruned_loss=0.05785, over 7135.00 frames.], tot_loss[loss=0.193, simple_loss=0.2763, pruned_loss=0.05483, over 1425516.40 frames.], batch size: 17, lr: 9.10e-04
+2022-05-14 06:58:42,757 INFO [train.py:812] (2/8) Epoch 8, batch 2950, loss[loss=0.1784, simple_loss=0.2656, pruned_loss=0.04563, over 7062.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2755, pruned_loss=0.0545, over 1424136.29 frames.], batch size: 18, lr: 9.09e-04
+2022-05-14 06:59:42,242 INFO [train.py:812] (2/8) Epoch 8, batch 3000, loss[loss=0.2661, simple_loss=0.3242, pruned_loss=0.104, over 4668.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2768, pruned_loss=0.05528, over 1420674.88 frames.], batch size: 52, lr: 9.09e-04
+2022-05-14 06:59:42,242 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 06:59:50,551 INFO [train.py:841] (2/8) Epoch 8, validation: loss=0.1612, simple_loss=0.2635, pruned_loss=0.0294, over 698248.00 frames.
+2022-05-14 07:00:48,451 INFO [train.py:812] (2/8) Epoch 8, batch 3050, loss[loss=0.1892, simple_loss=0.2794, pruned_loss=0.04949, over 6478.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2772, pruned_loss=0.0559, over 1413763.13 frames.], batch size: 38, lr: 9.08e-04
+2022-05-14 07:01:48,159 INFO [train.py:812] (2/8) Epoch 8, batch 3100, loss[loss=0.1534, simple_loss=0.2429, pruned_loss=0.03192, over 7267.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2765, pruned_loss=0.05537, over 1418214.81 frames.], batch size: 19, lr: 9.07e-04
+2022-05-14 07:02:45,304 INFO [train.py:812] (2/8) Epoch 8, batch 3150, loss[loss=0.1703, simple_loss=0.255, pruned_loss=0.0428, over 7427.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2759, pruned_loss=0.05546, over 1419756.21 frames.], batch size: 20, lr: 9.07e-04
+2022-05-14 07:03:44,358 INFO [train.py:812] (2/8) Epoch 8, batch 3200, loss[loss=0.1985, simple_loss=0.2726, pruned_loss=0.06218, over 7436.00 frames.], tot_loss[loss=0.193, simple_loss=0.2758, pruned_loss=0.05509, over 1422989.76 frames.], batch size: 20, lr: 9.06e-04
+2022-05-14 07:04:43,317 INFO [train.py:812] (2/8) Epoch 8, batch 3250, loss[loss=0.2006, simple_loss=0.2899, pruned_loss=0.05562, over 7001.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2765, pruned_loss=0.05523, over 1422703.83 frames.], batch size: 28, lr: 9.05e-04
+2022-05-14 07:05:41,212 INFO [train.py:812] (2/8) Epoch 8, batch 3300, loss[loss=0.2362, simple_loss=0.3128, pruned_loss=0.07985, over 6765.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2754, pruned_loss=0.05434, over 1421532.75 frames.], batch size: 31, lr: 9.05e-04
+2022-05-14 07:06:40,432 INFO [train.py:812] (2/8) Epoch 8, batch 3350, loss[loss=0.1784, simple_loss=0.2631, pruned_loss=0.04686, over 7435.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2752, pruned_loss=0.05391, over 1419151.23 frames.], batch size: 20, lr: 9.04e-04
+2022-05-14 07:07:39,822 INFO [train.py:812] (2/8) Epoch 8, batch 3400, loss[loss=0.1987, simple_loss=0.2687, pruned_loss=0.06433, over 6727.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2752, pruned_loss=0.05416, over 1417803.06 frames.], batch size: 31, lr: 9.04e-04
+2022-05-14 07:08:38,541 INFO [train.py:812] (2/8) Epoch 8, batch 3450, loss[loss=0.1762, simple_loss=0.2651, pruned_loss=0.04369, over 7408.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2761, pruned_loss=0.05451, over 1421108.98 frames.], batch size: 18, lr: 9.03e-04
+2022-05-14 07:09:37,985 INFO [train.py:812] (2/8) Epoch 8, batch 3500, loss[loss=0.194, simple_loss=0.2814, pruned_loss=0.05328, over 7379.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2775, pruned_loss=0.05528, over 1420960.97 frames.], batch size: 23, lr: 9.02e-04
+2022-05-14 07:10:37,040 INFO [train.py:812] (2/8) Epoch 8, batch 3550, loss[loss=0.1688, simple_loss=0.2572, pruned_loss=0.04022, over 7259.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2769, pruned_loss=0.05501, over 1422183.78 frames.], batch size: 19, lr: 9.02e-04
+2022-05-14 07:11:36,653 INFO [train.py:812] (2/8) Epoch 8, batch 3600, loss[loss=0.1704, simple_loss=0.2481, pruned_loss=0.04638, over 7284.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2755, pruned_loss=0.05469, over 1420698.15 frames.], batch size: 17, lr: 9.01e-04
+2022-05-14 07:12:33,625 INFO [train.py:812] (2/8) Epoch 8, batch 3650, loss[loss=0.1945, simple_loss=0.292, pruned_loss=0.0485, over 7419.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2772, pruned_loss=0.05558, over 1415478.56 frames.], batch size: 21, lr: 9.01e-04
+2022-05-14 07:13:32,674 INFO [train.py:812] (2/8) Epoch 8, batch 3700, loss[loss=0.1649, simple_loss=0.2522, pruned_loss=0.03882, over 7217.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2765, pruned_loss=0.05504, over 1419326.20 frames.], batch size: 21, lr: 9.00e-04
+2022-05-14 07:14:31,408 INFO [train.py:812] (2/8) Epoch 8, batch 3750, loss[loss=0.2059, simple_loss=0.2906, pruned_loss=0.06056, over 7167.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2751, pruned_loss=0.05422, over 1416463.56 frames.], batch size: 19, lr: 8.99e-04
+2022-05-14 07:15:30,608 INFO [train.py:812] (2/8) Epoch 8, batch 3800, loss[loss=0.2051, simple_loss=0.2909, pruned_loss=0.05964, over 7278.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2764, pruned_loss=0.05464, over 1419260.99 frames.], batch size: 24, lr: 8.99e-04
+2022-05-14 07:16:28,746 INFO [train.py:812] (2/8) Epoch 8, batch 3850, loss[loss=0.234, simple_loss=0.3146, pruned_loss=0.07665, over 7211.00 frames.], tot_loss[loss=0.193, simple_loss=0.2767, pruned_loss=0.05467, over 1417501.99 frames.], batch size: 21, lr: 8.98e-04
+2022-05-14 07:17:33,253 INFO [train.py:812] (2/8) Epoch 8, batch 3900, loss[loss=0.1819, simple_loss=0.2685, pruned_loss=0.04764, over 7431.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2754, pruned_loss=0.05418, over 1421564.05 frames.], batch size: 20, lr: 8.97e-04
+2022-05-14 07:18:32,354 INFO [train.py:812] (2/8) Epoch 8, batch 3950, loss[loss=0.1731, simple_loss=0.2519, pruned_loss=0.04714, over 7012.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2751, pruned_loss=0.05402, over 1423808.28 frames.], batch size: 16, lr: 8.97e-04
+2022-05-14 07:19:31,389 INFO [train.py:812] (2/8) Epoch 8, batch 4000, loss[loss=0.1926, simple_loss=0.2768, pruned_loss=0.05425, over 7141.00 frames.], tot_loss[loss=0.192, simple_loss=0.2758, pruned_loss=0.05409, over 1422509.03 frames.], batch size: 20, lr: 8.96e-04
+2022-05-14 07:20:29,698 INFO [train.py:812] (2/8) Epoch 8, batch 4050, loss[loss=0.2041, simple_loss=0.2867, pruned_loss=0.06077, over 7403.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2761, pruned_loss=0.05479, over 1425710.35 frames.], batch size: 21, lr: 8.96e-04
+2022-05-14 07:21:29,476 INFO [train.py:812] (2/8) Epoch 8, batch 4100, loss[loss=0.1539, simple_loss=0.2326, pruned_loss=0.03759, over 7272.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2766, pruned_loss=0.05524, over 1419370.38 frames.], batch size: 17, lr: 8.95e-04
+2022-05-14 07:22:28,433 INFO [train.py:812] (2/8) Epoch 8, batch 4150, loss[loss=0.2258, simple_loss=0.3028, pruned_loss=0.07438, over 7336.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2779, pruned_loss=0.05565, over 1413119.36 frames.], batch size: 22, lr: 8.94e-04
+2022-05-14 07:23:28,038 INFO [train.py:812] (2/8) Epoch 8, batch 4200, loss[loss=0.2049, simple_loss=0.2797, pruned_loss=0.06507, over 7150.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2782, pruned_loss=0.05552, over 1416253.65 frames.], batch size: 20, lr: 8.94e-04
+2022-05-14 07:24:27,289 INFO [train.py:812] (2/8) Epoch 8, batch 4250, loss[loss=0.2301, simple_loss=0.3069, pruned_loss=0.07669, over 7206.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2776, pruned_loss=0.05515, over 1420102.99 frames.], batch size: 22, lr: 8.93e-04
+2022-05-14 07:25:26,240 INFO [train.py:812] (2/8) Epoch 8, batch 4300, loss[loss=0.1881, simple_loss=0.277, pruned_loss=0.04965, over 7319.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2773, pruned_loss=0.05513, over 1417931.68 frames.], batch size: 21, lr: 8.93e-04
+2022-05-14 07:26:25,342 INFO [train.py:812] (2/8) Epoch 8, batch 4350, loss[loss=0.1941, simple_loss=0.3004, pruned_loss=0.04391, over 7447.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2761, pruned_loss=0.05486, over 1414275.31 frames.], batch size: 22, lr: 8.92e-04
+2022-05-14 07:27:24,454 INFO [train.py:812] (2/8) Epoch 8, batch 4400, loss[loss=0.2167, simple_loss=0.2949, pruned_loss=0.0692, over 7089.00 frames.], tot_loss[loss=0.1921, simple_loss=0.275, pruned_loss=0.05464, over 1417656.04 frames.], batch size: 28, lr: 8.91e-04
+2022-05-14 07:28:23,729 INFO [train.py:812] (2/8) Epoch 8, batch 4450, loss[loss=0.221, simple_loss=0.3089, pruned_loss=0.06656, over 7325.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2748, pruned_loss=0.05445, over 1417259.54 frames.], batch size: 20, lr: 8.91e-04
+2022-05-14 07:29:23,599 INFO [train.py:812] (2/8) Epoch 8, batch 4500, loss[loss=0.1916, simple_loss=0.259, pruned_loss=0.06213, over 7166.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2743, pruned_loss=0.0543, over 1414530.88 frames.], batch size: 18, lr: 8.90e-04
+2022-05-14 07:30:22,904 INFO [train.py:812] (2/8) Epoch 8, batch 4550, loss[loss=0.157, simple_loss=0.2326, pruned_loss=0.0407, over 7266.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2739, pruned_loss=0.05499, over 1397132.52 frames.], batch size: 17, lr: 8.90e-04
+2022-05-14 07:31:33,259 INFO [train.py:812] (2/8) Epoch 9, batch 0, loss[loss=0.199, simple_loss=0.2824, pruned_loss=0.05779, over 7179.00 frames.], tot_loss[loss=0.199, simple_loss=0.2824, pruned_loss=0.05779, over 7179.00 frames.], batch size: 23, lr: 8.54e-04
+2022-05-14 07:32:31,239 INFO [train.py:812] (2/8) Epoch 9, batch 50, loss[loss=0.2003, simple_loss=0.2786, pruned_loss=0.061, over 7100.00 frames.], tot_loss[loss=0.1958, simple_loss=0.279, pruned_loss=0.05624, over 319242.50 frames.], batch size: 28, lr: 8.53e-04
+2022-05-14 07:33:31,088 INFO [train.py:812] (2/8) Epoch 9, batch 100, loss[loss=0.1849, simple_loss=0.2838, pruned_loss=0.04303, over 7230.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2743, pruned_loss=0.05407, over 566497.07 frames.], batch size: 20, lr: 8.53e-04
+2022-05-14 07:34:29,384 INFO [train.py:812] (2/8) Epoch 9, batch 150, loss[loss=0.2211, simple_loss=0.2903, pruned_loss=0.076, over 4814.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2745, pruned_loss=0.05346, over 753034.65 frames.], batch size: 52, lr: 8.52e-04
+2022-05-14 07:35:29,135 INFO [train.py:812] (2/8) Epoch 9, batch 200, loss[loss=0.2201, simple_loss=0.297, pruned_loss=0.07161, over 7209.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2746, pruned_loss=0.05323, over 902725.32 frames.], batch size: 22, lr: 8.51e-04
+2022-05-14 07:36:28,014 INFO [train.py:812] (2/8) Epoch 9, batch 250, loss[loss=0.1871, simple_loss=0.2768, pruned_loss=0.04869, over 7431.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2744, pruned_loss=0.05286, over 1018792.78 frames.], batch size: 20, lr: 8.51e-04
+2022-05-14 07:37:25,191 INFO [train.py:812] (2/8) Epoch 9, batch 300, loss[loss=0.1699, simple_loss=0.2635, pruned_loss=0.03815, over 7345.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2745, pruned_loss=0.0528, over 1104501.98 frames.], batch size: 22, lr: 8.50e-04
+2022-05-14 07:38:25,015 INFO [train.py:812] (2/8) Epoch 9, batch 350, loss[loss=0.1592, simple_loss=0.2504, pruned_loss=0.03396, over 7168.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2727, pruned_loss=0.05215, over 1179109.76 frames.], batch size: 19, lr: 8.50e-04
+2022-05-14 07:39:24,187 INFO [train.py:812] (2/8) Epoch 9, batch 400, loss[loss=0.1603, simple_loss=0.236, pruned_loss=0.04229, over 7135.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2726, pruned_loss=0.05179, over 1238223.30 frames.], batch size: 17, lr: 8.49e-04
+2022-05-14 07:40:21,413 INFO [train.py:812] (2/8) Epoch 9, batch 450, loss[loss=0.1835, simple_loss=0.256, pruned_loss=0.05551, over 7264.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2722, pruned_loss=0.05212, over 1278491.80 frames.], batch size: 19, lr: 8.49e-04
+2022-05-14 07:41:19,783 INFO [train.py:812] (2/8) Epoch 9, batch 500, loss[loss=0.1478, simple_loss=0.233, pruned_loss=0.03132, over 7409.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2731, pruned_loss=0.05271, over 1311100.11 frames.], batch size: 18, lr: 8.48e-04
+2022-05-14 07:42:19,032 INFO [train.py:812] (2/8) Epoch 9, batch 550, loss[loss=0.1745, simple_loss=0.2647, pruned_loss=0.04214, over 7074.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2719, pruned_loss=0.0517, over 1338568.61 frames.], batch size: 18, lr: 8.48e-04
+2022-05-14 07:43:17,544 INFO [train.py:812] (2/8) Epoch 9, batch 600, loss[loss=0.1777, simple_loss=0.2596, pruned_loss=0.04794, over 7445.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2723, pruned_loss=0.05195, over 1361005.79 frames.], batch size: 19, lr: 8.47e-04
+2022-05-14 07:44:16,644 INFO [train.py:812] (2/8) Epoch 9, batch 650, loss[loss=0.1661, simple_loss=0.251, pruned_loss=0.0406, over 7369.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2721, pruned_loss=0.05183, over 1374527.53 frames.], batch size: 19, lr: 8.46e-04
+2022-05-14 07:45:15,374 INFO [train.py:812] (2/8) Epoch 9, batch 700, loss[loss=0.1664, simple_loss=0.2526, pruned_loss=0.0401, over 7436.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2721, pruned_loss=0.05204, over 1387154.25 frames.], batch size: 20, lr: 8.46e-04
+2022-05-14 07:46:13,740 INFO [train.py:812] (2/8) Epoch 9, batch 750, loss[loss=0.1585, simple_loss=0.2422, pruned_loss=0.03743, over 7167.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2727, pruned_loss=0.05222, over 1390773.15 frames.], batch size: 18, lr: 8.45e-04
+2022-05-14 07:47:13,055 INFO [train.py:812] (2/8) Epoch 9, batch 800, loss[loss=0.1837, simple_loss=0.2769, pruned_loss=0.04528, over 7383.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2715, pruned_loss=0.05141, over 1397212.67 frames.], batch size: 23, lr: 8.45e-04
+2022-05-14 07:48:11,325 INFO [train.py:812] (2/8) Epoch 9, batch 850, loss[loss=0.2192, simple_loss=0.3028, pruned_loss=0.06779, over 7326.00 frames.], tot_loss[loss=0.189, simple_loss=0.2732, pruned_loss=0.0524, over 1402198.75 frames.], batch size: 21, lr: 8.44e-04
+2022-05-14 07:49:11,223 INFO [train.py:812] (2/8) Epoch 9, batch 900, loss[loss=0.197, simple_loss=0.2934, pruned_loss=0.05033, over 7220.00 frames.], tot_loss[loss=0.1883, simple_loss=0.273, pruned_loss=0.05178, over 1411295.79 frames.], batch size: 21, lr: 8.44e-04
+2022-05-14 07:50:10,497 INFO [train.py:812] (2/8) Epoch 9, batch 950, loss[loss=0.1639, simple_loss=0.2499, pruned_loss=0.03898, over 7327.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2742, pruned_loss=0.05253, over 1409600.54 frames.], batch size: 20, lr: 8.43e-04
+2022-05-14 07:51:10,495 INFO [train.py:812] (2/8) Epoch 9, batch 1000, loss[loss=0.1963, simple_loss=0.2794, pruned_loss=0.05656, over 7433.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2739, pruned_loss=0.05268, over 1413590.11 frames.], batch size: 20, lr: 8.43e-04
+2022-05-14 07:52:08,961 INFO [train.py:812] (2/8) Epoch 9, batch 1050, loss[loss=0.1906, simple_loss=0.2739, pruned_loss=0.05362, over 7268.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2732, pruned_loss=0.05213, over 1417331.70 frames.], batch size: 19, lr: 8.42e-04
+2022-05-14 07:53:07,748 INFO [train.py:812] (2/8) Epoch 9, batch 1100, loss[loss=0.1643, simple_loss=0.2392, pruned_loss=0.04467, over 7279.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2744, pruned_loss=0.05262, over 1420537.89 frames.], batch size: 17, lr: 8.41e-04
+2022-05-14 07:54:04,868 INFO [train.py:812] (2/8) Epoch 9, batch 1150, loss[loss=0.2011, simple_loss=0.289, pruned_loss=0.05653, over 7300.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2741, pruned_loss=0.05262, over 1421467.82 frames.], batch size: 25, lr: 8.41e-04
+2022-05-14 07:55:04,936 INFO [train.py:812] (2/8) Epoch 9, batch 1200, loss[loss=0.1719, simple_loss=0.2708, pruned_loss=0.03646, over 7427.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2729, pruned_loss=0.052, over 1423367.71 frames.], batch size: 20, lr: 8.40e-04
+2022-05-14 07:56:02,845 INFO [train.py:812] (2/8) Epoch 9, batch 1250, loss[loss=0.1609, simple_loss=0.243, pruned_loss=0.03936, over 6768.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2726, pruned_loss=0.05226, over 1418693.10 frames.], batch size: 15, lr: 8.40e-04
+2022-05-14 07:57:02,082 INFO [train.py:812] (2/8) Epoch 9, batch 1300, loss[loss=0.2237, simple_loss=0.3086, pruned_loss=0.06944, over 7159.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2732, pruned_loss=0.05267, over 1415025.35 frames.], batch size: 19, lr: 8.39e-04
+2022-05-14 07:58:01,342 INFO [train.py:812] (2/8) Epoch 9, batch 1350, loss[loss=0.1833, simple_loss=0.2683, pruned_loss=0.04918, over 7437.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2732, pruned_loss=0.05267, over 1419641.43 frames.], batch size: 20, lr: 8.39e-04
+2022-05-14 07:59:00,866 INFO [train.py:812] (2/8) Epoch 9, batch 1400, loss[loss=0.2004, simple_loss=0.29, pruned_loss=0.0554, over 7226.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2733, pruned_loss=0.05245, over 1416032.53 frames.], batch size: 21, lr: 8.38e-04
+2022-05-14 07:59:57,892 INFO [train.py:812] (2/8) Epoch 9, batch 1450, loss[loss=0.1873, simple_loss=0.2817, pruned_loss=0.04651, over 7321.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2714, pruned_loss=0.05162, over 1420513.47 frames.], batch size: 21, lr: 8.38e-04
+2022-05-14 08:00:55,530 INFO [train.py:812] (2/8) Epoch 9, batch 1500, loss[loss=0.1864, simple_loss=0.2732, pruned_loss=0.04982, over 7228.00 frames.], tot_loss[loss=0.188, simple_loss=0.2723, pruned_loss=0.05192, over 1422909.86 frames.], batch size: 20, lr: 8.37e-04
+2022-05-14 08:01:53,802 INFO [train.py:812] (2/8) Epoch 9, batch 1550, loss[loss=0.1966, simple_loss=0.2732, pruned_loss=0.06001, over 7212.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2719, pruned_loss=0.05186, over 1422078.85 frames.], batch size: 22, lr: 8.37e-04
+2022-05-14 08:02:52,000 INFO [train.py:812] (2/8) Epoch 9, batch 1600, loss[loss=0.1684, simple_loss=0.2521, pruned_loss=0.04233, over 7067.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2728, pruned_loss=0.05228, over 1420092.71 frames.], batch size: 18, lr: 8.36e-04
+2022-05-14 08:03:49,504 INFO [train.py:812] (2/8) Epoch 9, batch 1650, loss[loss=0.1689, simple_loss=0.2621, pruned_loss=0.0379, over 7125.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2732, pruned_loss=0.05222, over 1420921.73 frames.], batch size: 21, lr: 8.35e-04
+2022-05-14 08:04:47,907 INFO [train.py:812] (2/8) Epoch 9, batch 1700, loss[loss=0.2115, simple_loss=0.2986, pruned_loss=0.06224, over 7153.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2742, pruned_loss=0.05274, over 1419401.93 frames.], batch size: 20, lr: 8.35e-04
+2022-05-14 08:05:46,545 INFO [train.py:812] (2/8) Epoch 9, batch 1750, loss[loss=0.1479, simple_loss=0.2428, pruned_loss=0.02649, over 7324.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2733, pruned_loss=0.05208, over 1421153.93 frames.], batch size: 21, lr: 8.34e-04
+2022-05-14 08:06:45,593 INFO [train.py:812] (2/8) Epoch 9, batch 1800, loss[loss=0.1587, simple_loss=0.2516, pruned_loss=0.03287, over 7230.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2731, pruned_loss=0.05189, over 1418003.94 frames.], batch size: 20, lr: 8.34e-04
+2022-05-14 08:07:44,991 INFO [train.py:812] (2/8) Epoch 9, batch 1850, loss[loss=0.1531, simple_loss=0.2406, pruned_loss=0.03283, over 7239.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2737, pruned_loss=0.05203, over 1421282.33 frames.], batch size: 20, lr: 8.33e-04
+2022-05-14 08:08:44,858 INFO [train.py:812] (2/8) Epoch 9, batch 1900, loss[loss=0.204, simple_loss=0.2868, pruned_loss=0.06062, over 7147.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2749, pruned_loss=0.0529, over 1419066.00 frames.], batch size: 19, lr: 8.33e-04
+2022-05-14 08:09:44,224 INFO [train.py:812] (2/8) Epoch 9, batch 1950, loss[loss=0.1904, simple_loss=0.2812, pruned_loss=0.04977, over 7114.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2743, pruned_loss=0.0524, over 1419888.33 frames.], batch size: 21, lr: 8.32e-04
+2022-05-14 08:10:44,120 INFO [train.py:812] (2/8) Epoch 9, batch 2000, loss[loss=0.2197, simple_loss=0.299, pruned_loss=0.07021, over 7296.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2732, pruned_loss=0.05219, over 1420956.92 frames.], batch size: 24, lr: 8.32e-04
+2022-05-14 08:11:43,578 INFO [train.py:812] (2/8) Epoch 9, batch 2050, loss[loss=0.1719, simple_loss=0.2423, pruned_loss=0.0507, over 7275.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2738, pruned_loss=0.05303, over 1421606.32 frames.], batch size: 17, lr: 8.31e-04
+2022-05-14 08:12:43,236 INFO [train.py:812] (2/8) Epoch 9, batch 2100, loss[loss=0.1818, simple_loss=0.2677, pruned_loss=0.04793, over 7252.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2735, pruned_loss=0.0529, over 1422519.01 frames.], batch size: 19, lr: 8.31e-04
+2022-05-14 08:13:42,060 INFO [train.py:812] (2/8) Epoch 9, batch 2150, loss[loss=0.2193, simple_loss=0.2877, pruned_loss=0.07541, over 7058.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2731, pruned_loss=0.05262, over 1424459.80 frames.], batch size: 18, lr: 8.30e-04
+2022-05-14 08:14:40,836 INFO [train.py:812] (2/8) Epoch 9, batch 2200, loss[loss=0.1712, simple_loss=0.2484, pruned_loss=0.04701, over 7280.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2725, pruned_loss=0.05247, over 1422717.89 frames.], batch size: 17, lr: 8.30e-04
+2022-05-14 08:15:40,319 INFO [train.py:812] (2/8) Epoch 9, batch 2250, loss[loss=0.1674, simple_loss=0.2544, pruned_loss=0.04021, over 7165.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2716, pruned_loss=0.05192, over 1423778.58 frames.], batch size: 18, lr: 8.29e-04
+2022-05-14 08:16:40,192 INFO [train.py:812] (2/8) Epoch 9, batch 2300, loss[loss=0.1953, simple_loss=0.2809, pruned_loss=0.05486, over 7145.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2725, pruned_loss=0.05225, over 1425045.95 frames.], batch size: 20, lr: 8.29e-04
+2022-05-14 08:17:37,468 INFO [train.py:812] (2/8) Epoch 9, batch 2350, loss[loss=0.2042, simple_loss=0.2903, pruned_loss=0.059, over 6645.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2735, pruned_loss=0.05279, over 1423258.39 frames.], batch size: 31, lr: 8.28e-04
+2022-05-14 08:18:37,027 INFO [train.py:812] (2/8) Epoch 9, batch 2400, loss[loss=0.1689, simple_loss=0.2462, pruned_loss=0.04584, over 7283.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2743, pruned_loss=0.05322, over 1423459.30 frames.], batch size: 18, lr: 8.28e-04
+2022-05-14 08:19:36,216 INFO [train.py:812] (2/8) Epoch 9, batch 2450, loss[loss=0.1785, simple_loss=0.2565, pruned_loss=0.05027, over 7410.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2737, pruned_loss=0.05283, over 1425588.76 frames.], batch size: 18, lr: 8.27e-04
+2022-05-14 08:20:34,803 INFO [train.py:812] (2/8) Epoch 9, batch 2500, loss[loss=0.1965, simple_loss=0.281, pruned_loss=0.05603, over 7198.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2741, pruned_loss=0.05259, over 1424430.99 frames.], batch size: 22, lr: 8.27e-04
+2022-05-14 08:21:43,990 INFO [train.py:812] (2/8) Epoch 9, batch 2550, loss[loss=0.1537, simple_loss=0.2329, pruned_loss=0.03719, over 7138.00 frames.], tot_loss[loss=0.1886, simple_loss=0.273, pruned_loss=0.05212, over 1422387.27 frames.], batch size: 17, lr: 8.26e-04
+2022-05-14 08:22:42,420 INFO [train.py:812] (2/8) Epoch 9, batch 2600, loss[loss=0.2382, simple_loss=0.319, pruned_loss=0.0787, over 7358.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2735, pruned_loss=0.05243, over 1420512.93 frames.], batch size: 23, lr: 8.25e-04
+2022-05-14 08:23:41,185 INFO [train.py:812] (2/8) Epoch 9, batch 2650, loss[loss=0.2447, simple_loss=0.3004, pruned_loss=0.09453, over 5215.00 frames.], tot_loss[loss=0.1889, simple_loss=0.273, pruned_loss=0.05241, over 1419157.35 frames.], batch size: 52, lr: 8.25e-04
+2022-05-14 08:24:39,377 INFO [train.py:812] (2/8) Epoch 9, batch 2700, loss[loss=0.1766, simple_loss=0.2774, pruned_loss=0.0379, over 7334.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2739, pruned_loss=0.05259, over 1420095.20 frames.], batch size: 22, lr: 8.24e-04
+2022-05-14 08:25:38,211 INFO [train.py:812] (2/8) Epoch 9, batch 2750, loss[loss=0.1981, simple_loss=0.2883, pruned_loss=0.05396, over 7326.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2731, pruned_loss=0.05207, over 1424014.25 frames.], batch size: 20, lr: 8.24e-04
+2022-05-14 08:26:37,795 INFO [train.py:812] (2/8) Epoch 9, batch 2800, loss[loss=0.1883, simple_loss=0.2671, pruned_loss=0.05474, over 7201.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2731, pruned_loss=0.05179, over 1426981.97 frames.], batch size: 22, lr: 8.23e-04
+2022-05-14 08:27:35,907 INFO [train.py:812] (2/8) Epoch 9, batch 2850, loss[loss=0.1989, simple_loss=0.2886, pruned_loss=0.05458, over 7158.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2723, pruned_loss=0.05129, over 1428902.64 frames.], batch size: 19, lr: 8.23e-04
+2022-05-14 08:28:33,952 INFO [train.py:812] (2/8) Epoch 9, batch 2900, loss[loss=0.1845, simple_loss=0.2796, pruned_loss=0.04473, over 7320.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2722, pruned_loss=0.05116, over 1427301.20 frames.], batch size: 21, lr: 8.22e-04
+2022-05-14 08:29:31,236 INFO [train.py:812] (2/8) Epoch 9, batch 2950, loss[loss=0.1837, simple_loss=0.2545, pruned_loss=0.05643, over 7275.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2727, pruned_loss=0.05145, over 1423383.40 frames.], batch size: 18, lr: 8.22e-04
+2022-05-14 08:30:30,199 INFO [train.py:812] (2/8) Epoch 9, batch 3000, loss[loss=0.185, simple_loss=0.274, pruned_loss=0.04799, over 7292.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2723, pruned_loss=0.05143, over 1422249.35 frames.], batch size: 24, lr: 8.21e-04
+2022-05-14 08:30:30,200 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 08:30:38,338 INFO [train.py:841] (2/8) Epoch 9, validation: loss=0.1602, simple_loss=0.262, pruned_loss=0.0292, over 698248.00 frames.
+2022-05-14 08:31:37,160 INFO [train.py:812] (2/8) Epoch 9, batch 3050, loss[loss=0.1698, simple_loss=0.2482, pruned_loss=0.04575, over 7325.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2729, pruned_loss=0.05197, over 1418342.86 frames.], batch size: 20, lr: 8.21e-04
+2022-05-14 08:32:34,702 INFO [train.py:812] (2/8) Epoch 9, batch 3100, loss[loss=0.1986, simple_loss=0.2807, pruned_loss=0.05825, over 6614.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2741, pruned_loss=0.05286, over 1414000.02 frames.], batch size: 31, lr: 8.20e-04
+2022-05-14 08:33:32,683 INFO [train.py:812] (2/8) Epoch 9, batch 3150, loss[loss=0.2001, simple_loss=0.2846, pruned_loss=0.05783, over 7164.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2734, pruned_loss=0.05258, over 1417664.63 frames.], batch size: 19, lr: 8.20e-04
+2022-05-14 08:34:32,438 INFO [train.py:812] (2/8) Epoch 9, batch 3200, loss[loss=0.1989, simple_loss=0.2951, pruned_loss=0.05137, over 7143.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2733, pruned_loss=0.05248, over 1420993.14 frames.], batch size: 20, lr: 8.19e-04
+2022-05-14 08:35:31,365 INFO [train.py:812] (2/8) Epoch 9, batch 3250, loss[loss=0.2418, simple_loss=0.3144, pruned_loss=0.08458, over 5020.00 frames.], tot_loss[loss=0.189, simple_loss=0.2735, pruned_loss=0.05222, over 1419440.41 frames.], batch size: 52, lr: 8.19e-04
+2022-05-14 08:36:46,153 INFO [train.py:812] (2/8) Epoch 9, batch 3300, loss[loss=0.1881, simple_loss=0.275, pruned_loss=0.05065, over 7206.00 frames.], tot_loss[loss=0.188, simple_loss=0.2727, pruned_loss=0.05167, over 1419866.47 frames.], batch size: 22, lr: 8.18e-04
+2022-05-14 08:37:52,674 INFO [train.py:812] (2/8) Epoch 9, batch 3350, loss[loss=0.198, simple_loss=0.2842, pruned_loss=0.05591, over 7253.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2723, pruned_loss=0.05129, over 1423950.55 frames.], batch size: 19, lr: 8.18e-04
+2022-05-14 08:38:51,550 INFO [train.py:812] (2/8) Epoch 9, batch 3400, loss[loss=0.2366, simple_loss=0.3233, pruned_loss=0.07494, over 6686.00 frames.], tot_loss[loss=0.1883, simple_loss=0.273, pruned_loss=0.05178, over 1422093.44 frames.], batch size: 31, lr: 8.17e-04
+2022-05-14 08:39:59,371 INFO [train.py:812] (2/8) Epoch 9, batch 3450, loss[loss=0.1591, simple_loss=0.2417, pruned_loss=0.03822, over 7399.00 frames.], tot_loss[loss=0.1894, simple_loss=0.274, pruned_loss=0.05234, over 1423981.74 frames.], batch size: 18, lr: 8.17e-04
+2022-05-14 08:41:27,462 INFO [train.py:812] (2/8) Epoch 9, batch 3500, loss[loss=0.1786, simple_loss=0.2691, pruned_loss=0.044, over 7159.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2743, pruned_loss=0.05233, over 1425110.85 frames.], batch size: 19, lr: 8.16e-04
+2022-05-14 08:42:35,747 INFO [train.py:812] (2/8) Epoch 9, batch 3550, loss[loss=0.1564, simple_loss=0.2385, pruned_loss=0.0372, over 7163.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2727, pruned_loss=0.05141, over 1426376.16 frames.], batch size: 18, lr: 8.16e-04
+2022-05-14 08:43:34,789 INFO [train.py:812] (2/8) Epoch 9, batch 3600, loss[loss=0.1542, simple_loss=0.2348, pruned_loss=0.03686, over 7288.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2727, pruned_loss=0.05119, over 1423849.14 frames.], batch size: 18, lr: 8.15e-04
+2022-05-14 08:44:32,173 INFO [train.py:812] (2/8) Epoch 9, batch 3650, loss[loss=0.1746, simple_loss=0.2496, pruned_loss=0.04984, over 7135.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2718, pruned_loss=0.05082, over 1425087.34 frames.], batch size: 17, lr: 8.15e-04
+2022-05-14 08:45:31,312 INFO [train.py:812] (2/8) Epoch 9, batch 3700, loss[loss=0.1781, simple_loss=0.281, pruned_loss=0.03759, over 7286.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2729, pruned_loss=0.05121, over 1425481.93 frames.], batch size: 25, lr: 8.14e-04
+2022-05-14 08:46:29,960 INFO [train.py:812] (2/8) Epoch 9, batch 3750, loss[loss=0.1869, simple_loss=0.2724, pruned_loss=0.05068, over 7429.00 frames.], tot_loss[loss=0.1888, simple_loss=0.274, pruned_loss=0.05177, over 1424472.55 frames.], batch size: 20, lr: 8.14e-04
+2022-05-14 08:47:29,001 INFO [train.py:812] (2/8) Epoch 9, batch 3800, loss[loss=0.1497, simple_loss=0.2314, pruned_loss=0.03399, over 7391.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2736, pruned_loss=0.05154, over 1427336.15 frames.], batch size: 18, lr: 8.13e-04
+2022-05-14 08:48:27,807 INFO [train.py:812] (2/8) Epoch 9, batch 3850, loss[loss=0.15, simple_loss=0.2367, pruned_loss=0.03163, over 7306.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2734, pruned_loss=0.05178, over 1429240.44 frames.], batch size: 17, lr: 8.13e-04
+2022-05-14 08:49:26,812 INFO [train.py:812] (2/8) Epoch 9, batch 3900, loss[loss=0.199, simple_loss=0.2795, pruned_loss=0.05924, over 5087.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2738, pruned_loss=0.05194, over 1426443.62 frames.], batch size: 52, lr: 8.12e-04
+2022-05-14 08:50:26,341 INFO [train.py:812] (2/8) Epoch 9, batch 3950, loss[loss=0.1897, simple_loss=0.2822, pruned_loss=0.04861, over 6702.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2734, pruned_loss=0.05165, over 1426722.79 frames.], batch size: 31, lr: 8.12e-04
+2022-05-14 08:51:25,800 INFO [train.py:812] (2/8) Epoch 9, batch 4000, loss[loss=0.1894, simple_loss=0.2838, pruned_loss=0.04749, over 7213.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2744, pruned_loss=0.05221, over 1426454.95 frames.], batch size: 21, lr: 8.11e-04
+2022-05-14 08:52:25,217 INFO [train.py:812] (2/8) Epoch 9, batch 4050, loss[loss=0.1706, simple_loss=0.2499, pruned_loss=0.04564, over 7408.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2731, pruned_loss=0.05165, over 1425550.00 frames.], batch size: 18, lr: 8.11e-04
+2022-05-14 08:53:24,993 INFO [train.py:812] (2/8) Epoch 9, batch 4100, loss[loss=0.1564, simple_loss=0.2281, pruned_loss=0.04234, over 7136.00 frames.], tot_loss[loss=0.1875, simple_loss=0.272, pruned_loss=0.05149, over 1425943.57 frames.], batch size: 17, lr: 8.10e-04
+2022-05-14 08:54:24,680 INFO [train.py:812] (2/8) Epoch 9, batch 4150, loss[loss=0.2046, simple_loss=0.3011, pruned_loss=0.05403, over 7116.00 frames.], tot_loss[loss=0.1876, simple_loss=0.272, pruned_loss=0.05163, over 1421144.03 frames.], batch size: 28, lr: 8.10e-04
+2022-05-14 08:55:24,386 INFO [train.py:812] (2/8) Epoch 9, batch 4200, loss[loss=0.1774, simple_loss=0.2605, pruned_loss=0.04714, over 7338.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2705, pruned_loss=0.05111, over 1422669.55 frames.], batch size: 20, lr: 8.09e-04
+2022-05-14 08:56:23,006 INFO [train.py:812] (2/8) Epoch 9, batch 4250, loss[loss=0.1648, simple_loss=0.2401, pruned_loss=0.04474, over 7140.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2704, pruned_loss=0.05129, over 1419462.24 frames.], batch size: 17, lr: 8.09e-04
+2022-05-14 08:57:22,986 INFO [train.py:812] (2/8) Epoch 9, batch 4300, loss[loss=0.2262, simple_loss=0.3161, pruned_loss=0.06816, over 7411.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2701, pruned_loss=0.05148, over 1415471.23 frames.], batch size: 21, lr: 8.08e-04
+2022-05-14 08:58:21,477 INFO [train.py:812] (2/8) Epoch 9, batch 4350, loss[loss=0.1504, simple_loss=0.2294, pruned_loss=0.03569, over 7274.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2694, pruned_loss=0.05066, over 1421300.15 frames.], batch size: 17, lr: 8.08e-04
+2022-05-14 08:59:21,260 INFO [train.py:812] (2/8) Epoch 9, batch 4400, loss[loss=0.2103, simple_loss=0.2988, pruned_loss=0.06086, over 7065.00 frames.], tot_loss[loss=0.186, simple_loss=0.2698, pruned_loss=0.05116, over 1416729.73 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:00:19,332 INFO [train.py:812] (2/8) Epoch 9, batch 4450, loss[loss=0.194, simple_loss=0.2765, pruned_loss=0.05571, over 6990.00 frames.], tot_loss[loss=0.1859, simple_loss=0.269, pruned_loss=0.05139, over 1411739.16 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:01:19,093 INFO [train.py:812] (2/8) Epoch 9, batch 4500, loss[loss=0.2062, simple_loss=0.2881, pruned_loss=0.06214, over 7120.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2712, pruned_loss=0.05287, over 1393413.97 frames.], batch size: 28, lr: 8.07e-04
+2022-05-14 09:02:17,083 INFO [train.py:812] (2/8) Epoch 9, batch 4550, loss[loss=0.2182, simple_loss=0.3024, pruned_loss=0.06698, over 6340.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2752, pruned_loss=0.05524, over 1352856.85 frames.], batch size: 37, lr: 8.06e-04
+2022-05-14 09:03:24,803 INFO [train.py:812] (2/8) Epoch 10, batch 0, loss[loss=0.1806, simple_loss=0.272, pruned_loss=0.04462, over 7409.00 frames.], tot_loss[loss=0.1806, simple_loss=0.272, pruned_loss=0.04462, over 7409.00 frames.], batch size: 21, lr: 7.75e-04
+2022-05-14 09:04:24,005 INFO [train.py:812] (2/8) Epoch 10, batch 50, loss[loss=0.2202, simple_loss=0.3188, pruned_loss=0.06082, over 7209.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2726, pruned_loss=0.05048, over 321688.00 frames.], batch size: 23, lr: 7.74e-04
+2022-05-14 09:05:23,100 INFO [train.py:812] (2/8) Epoch 10, batch 100, loss[loss=0.2436, simple_loss=0.3132, pruned_loss=0.08702, over 4742.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2696, pruned_loss=0.05041, over 558320.72 frames.], batch size: 52, lr: 7.74e-04
+2022-05-14 09:06:22,299 INFO [train.py:812] (2/8) Epoch 10, batch 150, loss[loss=0.1568, simple_loss=0.2517, pruned_loss=0.03096, over 7432.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2694, pruned_loss=0.05018, over 751148.62 frames.], batch size: 20, lr: 7.73e-04
+2022-05-14 09:07:20,689 INFO [train.py:812] (2/8) Epoch 10, batch 200, loss[loss=0.1811, simple_loss=0.2693, pruned_loss=0.04641, over 7434.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2704, pruned_loss=0.051, over 898230.97 frames.], batch size: 20, lr: 7.73e-04
+2022-05-14 09:08:19,957 INFO [train.py:812] (2/8) Epoch 10, batch 250, loss[loss=0.1556, simple_loss=0.2434, pruned_loss=0.03386, over 7151.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2719, pruned_loss=0.0513, over 1010597.21 frames.], batch size: 18, lr: 7.72e-04
+2022-05-14 09:09:19,149 INFO [train.py:812] (2/8) Epoch 10, batch 300, loss[loss=0.2026, simple_loss=0.2845, pruned_loss=0.06033, over 7325.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2718, pruned_loss=0.05082, over 1104523.80 frames.], batch size: 20, lr: 7.72e-04
+2022-05-14 09:10:16,341 INFO [train.py:812] (2/8) Epoch 10, batch 350, loss[loss=0.1677, simple_loss=0.2563, pruned_loss=0.03953, over 7209.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2712, pruned_loss=0.04995, over 1172909.49 frames.], batch size: 23, lr: 7.71e-04
+2022-05-14 09:11:15,058 INFO [train.py:812] (2/8) Epoch 10, batch 400, loss[loss=0.1747, simple_loss=0.2724, pruned_loss=0.03849, over 7188.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2717, pruned_loss=0.05025, over 1223782.56 frames.], batch size: 26, lr: 7.71e-04
+2022-05-14 09:12:14,068 INFO [train.py:812] (2/8) Epoch 10, batch 450, loss[loss=0.1866, simple_loss=0.2718, pruned_loss=0.05072, over 6245.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2724, pruned_loss=0.05049, over 1262606.70 frames.], batch size: 37, lr: 7.71e-04
+2022-05-14 09:13:13,635 INFO [train.py:812] (2/8) Epoch 10, batch 500, loss[loss=0.1701, simple_loss=0.2651, pruned_loss=0.03753, over 7162.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2729, pruned_loss=0.05108, over 1297444.51 frames.], batch size: 19, lr: 7.70e-04
+2022-05-14 09:14:12,269 INFO [train.py:812] (2/8) Epoch 10, batch 550, loss[loss=0.1712, simple_loss=0.2536, pruned_loss=0.04439, over 7109.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2725, pruned_loss=0.05089, over 1325659.16 frames.], batch size: 17, lr: 7.70e-04
+2022-05-14 09:15:10,134 INFO [train.py:812] (2/8) Epoch 10, batch 600, loss[loss=0.2107, simple_loss=0.279, pruned_loss=0.07119, over 7282.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2733, pruned_loss=0.05129, over 1346380.05 frames.], batch size: 18, lr: 7.69e-04
+2022-05-14 09:16:08,343 INFO [train.py:812] (2/8) Epoch 10, batch 650, loss[loss=0.2114, simple_loss=0.2909, pruned_loss=0.06596, over 7189.00 frames.], tot_loss[loss=0.1875, simple_loss=0.273, pruned_loss=0.05102, over 1362786.33 frames.], batch size: 26, lr: 7.69e-04
+2022-05-14 09:17:07,948 INFO [train.py:812] (2/8) Epoch 10, batch 700, loss[loss=0.1833, simple_loss=0.2797, pruned_loss=0.04345, over 7308.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2725, pruned_loss=0.05084, over 1377315.13 frames.], batch size: 25, lr: 7.68e-04
+2022-05-14 09:18:07,541 INFO [train.py:812] (2/8) Epoch 10, batch 750, loss[loss=0.1873, simple_loss=0.271, pruned_loss=0.05178, over 7432.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2721, pruned_loss=0.05111, over 1386933.28 frames.], batch size: 20, lr: 7.68e-04
+2022-05-14 09:19:06,601 INFO [train.py:812] (2/8) Epoch 10, batch 800, loss[loss=0.1729, simple_loss=0.264, pruned_loss=0.04089, over 7297.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2719, pruned_loss=0.05131, over 1394398.20 frames.], batch size: 24, lr: 7.67e-04
+2022-05-14 09:20:06,055 INFO [train.py:812] (2/8) Epoch 10, batch 850, loss[loss=0.2141, simple_loss=0.2947, pruned_loss=0.06674, over 6232.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2726, pruned_loss=0.05123, over 1398108.39 frames.], batch size: 37, lr: 7.67e-04
+2022-05-14 09:21:05,148 INFO [train.py:812] (2/8) Epoch 10, batch 900, loss[loss=0.1942, simple_loss=0.2825, pruned_loss=0.05298, over 7327.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2721, pruned_loss=0.05067, over 1407483.88 frames.], batch size: 21, lr: 7.66e-04
+2022-05-14 09:22:03,784 INFO [train.py:812] (2/8) Epoch 10, batch 950, loss[loss=0.1971, simple_loss=0.2799, pruned_loss=0.05714, over 7120.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2725, pruned_loss=0.05065, over 1406934.07 frames.], batch size: 26, lr: 7.66e-04
+2022-05-14 09:23:02,561 INFO [train.py:812] (2/8) Epoch 10, batch 1000, loss[loss=0.1754, simple_loss=0.2557, pruned_loss=0.04755, over 7325.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2715, pruned_loss=0.05008, over 1414277.73 frames.], batch size: 20, lr: 7.66e-04
+2022-05-14 09:24:00,829 INFO [train.py:812] (2/8) Epoch 10, batch 1050, loss[loss=0.195, simple_loss=0.2908, pruned_loss=0.04958, over 7025.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2713, pruned_loss=0.05014, over 1416796.52 frames.], batch size: 28, lr: 7.65e-04
+2022-05-14 09:24:59,373 INFO [train.py:812] (2/8) Epoch 10, batch 1100, loss[loss=0.1767, simple_loss=0.2675, pruned_loss=0.04292, over 7078.00 frames.], tot_loss[loss=0.186, simple_loss=0.2712, pruned_loss=0.05038, over 1416992.71 frames.], batch size: 28, lr: 7.65e-04
+2022-05-14 09:25:57,286 INFO [train.py:812] (2/8) Epoch 10, batch 1150, loss[loss=0.1742, simple_loss=0.2521, pruned_loss=0.0481, over 7340.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2709, pruned_loss=0.05018, over 1420960.58 frames.], batch size: 20, lr: 7.64e-04
+2022-05-14 09:26:55,700 INFO [train.py:812] (2/8) Epoch 10, batch 1200, loss[loss=0.2238, simple_loss=0.3099, pruned_loss=0.06885, over 7198.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2714, pruned_loss=0.05003, over 1420229.14 frames.], batch size: 23, lr: 7.64e-04
+2022-05-14 09:27:55,471 INFO [train.py:812] (2/8) Epoch 10, batch 1250, loss[loss=0.1637, simple_loss=0.2362, pruned_loss=0.04563, over 7272.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2715, pruned_loss=0.05032, over 1418487.97 frames.], batch size: 17, lr: 7.63e-04
+2022-05-14 09:28:54,764 INFO [train.py:812] (2/8) Epoch 10, batch 1300, loss[loss=0.1872, simple_loss=0.2617, pruned_loss=0.05632, over 6995.00 frames.], tot_loss[loss=0.186, simple_loss=0.2708, pruned_loss=0.0506, over 1416705.84 frames.], batch size: 16, lr: 7.63e-04
+2022-05-14 09:29:54,255 INFO [train.py:812] (2/8) Epoch 10, batch 1350, loss[loss=0.1747, simple_loss=0.2688, pruned_loss=0.04028, over 7328.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2705, pruned_loss=0.05063, over 1415454.07 frames.], batch size: 21, lr: 7.62e-04
+2022-05-14 09:30:53,082 INFO [train.py:812] (2/8) Epoch 10, batch 1400, loss[loss=0.2176, simple_loss=0.2972, pruned_loss=0.06901, over 7125.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2714, pruned_loss=0.0504, over 1418953.93 frames.], batch size: 21, lr: 7.62e-04
+2022-05-14 09:31:52,603 INFO [train.py:812] (2/8) Epoch 10, batch 1450, loss[loss=0.2256, simple_loss=0.3251, pruned_loss=0.06302, over 7295.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2703, pruned_loss=0.04994, over 1419919.57 frames.], batch size: 25, lr: 7.62e-04
+2022-05-14 09:32:51,554 INFO [train.py:812] (2/8) Epoch 10, batch 1500, loss[loss=0.1969, simple_loss=0.2696, pruned_loss=0.06209, over 5291.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2709, pruned_loss=0.0503, over 1416269.30 frames.], batch size: 53, lr: 7.61e-04
+2022-05-14 09:33:51,496 INFO [train.py:812] (2/8) Epoch 10, batch 1550, loss[loss=0.1774, simple_loss=0.2689, pruned_loss=0.04294, over 7362.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2706, pruned_loss=0.05003, over 1419924.39 frames.], batch size: 19, lr: 7.61e-04
+2022-05-14 09:34:49,172 INFO [train.py:812] (2/8) Epoch 10, batch 1600, loss[loss=0.1787, simple_loss=0.2599, pruned_loss=0.04872, over 7255.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2704, pruned_loss=0.0504, over 1418592.16 frames.], batch size: 19, lr: 7.60e-04
+2022-05-14 09:35:46,384 INFO [train.py:812] (2/8) Epoch 10, batch 1650, loss[loss=0.1863, simple_loss=0.272, pruned_loss=0.05033, over 7414.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2694, pruned_loss=0.04994, over 1416097.85 frames.], batch size: 21, lr: 7.60e-04
+2022-05-14 09:36:44,418 INFO [train.py:812] (2/8) Epoch 10, batch 1700, loss[loss=0.2008, simple_loss=0.292, pruned_loss=0.05481, over 7277.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2694, pruned_loss=0.04992, over 1413540.95 frames.], batch size: 24, lr: 7.59e-04
+2022-05-14 09:37:43,562 INFO [train.py:812] (2/8) Epoch 10, batch 1750, loss[loss=0.1473, simple_loss=0.2177, pruned_loss=0.03844, over 6744.00 frames.], tot_loss[loss=0.186, simple_loss=0.2707, pruned_loss=0.05069, over 1405278.26 frames.], batch size: 15, lr: 7.59e-04
+2022-05-14 09:38:41,648 INFO [train.py:812] (2/8) Epoch 10, batch 1800, loss[loss=0.2185, simple_loss=0.3085, pruned_loss=0.06427, over 7359.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2709, pruned_loss=0.05086, over 1410917.87 frames.], batch size: 19, lr: 7.59e-04
+2022-05-14 09:39:39,911 INFO [train.py:812] (2/8) Epoch 10, batch 1850, loss[loss=0.1943, simple_loss=0.2711, pruned_loss=0.05876, over 7366.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2709, pruned_loss=0.05084, over 1411619.85 frames.], batch size: 19, lr: 7.58e-04
+2022-05-14 09:40:38,491 INFO [train.py:812] (2/8) Epoch 10, batch 1900, loss[loss=0.1729, simple_loss=0.253, pruned_loss=0.04638, over 7279.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2705, pruned_loss=0.0505, over 1416215.15 frames.], batch size: 18, lr: 7.58e-04
+2022-05-14 09:41:37,150 INFO [train.py:812] (2/8) Epoch 10, batch 1950, loss[loss=0.2203, simple_loss=0.2965, pruned_loss=0.07202, over 7199.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2697, pruned_loss=0.05033, over 1415003.79 frames.], batch size: 23, lr: 7.57e-04
+2022-05-14 09:42:35,059 INFO [train.py:812] (2/8) Epoch 10, batch 2000, loss[loss=0.1748, simple_loss=0.2675, pruned_loss=0.04108, over 7226.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2688, pruned_loss=0.0495, over 1418796.15 frames.], batch size: 20, lr: 7.57e-04
+2022-05-14 09:43:34,924 INFO [train.py:812] (2/8) Epoch 10, batch 2050, loss[loss=0.2347, simple_loss=0.3111, pruned_loss=0.07916, over 7185.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2689, pruned_loss=0.04936, over 1420363.84 frames.], batch size: 23, lr: 7.56e-04
+2022-05-14 09:44:34,079 INFO [train.py:812] (2/8) Epoch 10, batch 2100, loss[loss=0.1738, simple_loss=0.2696, pruned_loss=0.03901, over 7146.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2685, pruned_loss=0.04885, over 1424555.75 frames.], batch size: 20, lr: 7.56e-04
+2022-05-14 09:45:31,450 INFO [train.py:812] (2/8) Epoch 10, batch 2150, loss[loss=0.1527, simple_loss=0.2446, pruned_loss=0.0304, over 7434.00 frames.], tot_loss[loss=0.182, simple_loss=0.2675, pruned_loss=0.04826, over 1426927.14 frames.], batch size: 18, lr: 7.56e-04
+2022-05-14 09:46:28,652 INFO [train.py:812] (2/8) Epoch 10, batch 2200, loss[loss=0.1835, simple_loss=0.2739, pruned_loss=0.04654, over 6353.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2689, pruned_loss=0.0489, over 1427209.45 frames.], batch size: 37, lr: 7.55e-04
+2022-05-14 09:47:27,357 INFO [train.py:812] (2/8) Epoch 10, batch 2250, loss[loss=0.1853, simple_loss=0.2763, pruned_loss=0.04711, over 7326.00 frames.], tot_loss[loss=0.1834, simple_loss=0.269, pruned_loss=0.04887, over 1428660.29 frames.], batch size: 21, lr: 7.55e-04
+2022-05-14 09:48:25,639 INFO [train.py:812] (2/8) Epoch 10, batch 2300, loss[loss=0.1728, simple_loss=0.2683, pruned_loss=0.03871, over 7141.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2699, pruned_loss=0.04924, over 1426938.90 frames.], batch size: 20, lr: 7.54e-04
+2022-05-14 09:49:24,917 INFO [train.py:812] (2/8) Epoch 10, batch 2350, loss[loss=0.1874, simple_loss=0.2704, pruned_loss=0.0522, over 7218.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2695, pruned_loss=0.04948, over 1424802.24 frames.], batch size: 22, lr: 7.54e-04
+2022-05-14 09:50:22,144 INFO [train.py:812] (2/8) Epoch 10, batch 2400, loss[loss=0.165, simple_loss=0.2455, pruned_loss=0.04224, over 7290.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2681, pruned_loss=0.04838, over 1426894.41 frames.], batch size: 18, lr: 7.53e-04
+2022-05-14 09:51:20,801 INFO [train.py:812] (2/8) Epoch 10, batch 2450, loss[loss=0.1972, simple_loss=0.2696, pruned_loss=0.06245, over 7064.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2684, pruned_loss=0.04851, over 1430201.80 frames.], batch size: 18, lr: 7.53e-04
+2022-05-14 09:52:18,418 INFO [train.py:812] (2/8) Epoch 10, batch 2500, loss[loss=0.1697, simple_loss=0.2668, pruned_loss=0.03634, over 7317.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2679, pruned_loss=0.04821, over 1428112.34 frames.], batch size: 21, lr: 7.53e-04
+2022-05-14 09:53:18,333 INFO [train.py:812] (2/8) Epoch 10, batch 2550, loss[loss=0.1983, simple_loss=0.2858, pruned_loss=0.05546, over 7216.00 frames.], tot_loss[loss=0.182, simple_loss=0.2675, pruned_loss=0.04829, over 1426329.98 frames.], batch size: 21, lr: 7.52e-04
+2022-05-14 09:54:18,072 INFO [train.py:812] (2/8) Epoch 10, batch 2600, loss[loss=0.1763, simple_loss=0.264, pruned_loss=0.04428, over 7145.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2678, pruned_loss=0.04848, over 1429270.34 frames.], batch size: 26, lr: 7.52e-04
+2022-05-14 09:55:17,734 INFO [train.py:812] (2/8) Epoch 10, batch 2650, loss[loss=0.2053, simple_loss=0.2921, pruned_loss=0.05925, over 7337.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2693, pruned_loss=0.04907, over 1425400.31 frames.], batch size: 22, lr: 7.51e-04
+2022-05-14 09:56:16,819 INFO [train.py:812] (2/8) Epoch 10, batch 2700, loss[loss=0.1965, simple_loss=0.2847, pruned_loss=0.05417, over 6803.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2693, pruned_loss=0.04913, over 1426049.18 frames.], batch size: 31, lr: 7.51e-04
+2022-05-14 09:57:23,635 INFO [train.py:812] (2/8) Epoch 10, batch 2750, loss[loss=0.2084, simple_loss=0.2996, pruned_loss=0.05858, over 6882.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2689, pruned_loss=0.04921, over 1423812.42 frames.], batch size: 31, lr: 7.50e-04
+2022-05-14 09:58:22,149 INFO [train.py:812] (2/8) Epoch 10, batch 2800, loss[loss=0.2681, simple_loss=0.3288, pruned_loss=0.1037, over 7402.00 frames.], tot_loss[loss=0.1841, simple_loss=0.269, pruned_loss=0.04957, over 1429461.28 frames.], batch size: 23, lr: 7.50e-04
+2022-05-14 09:59:21,336 INFO [train.py:812] (2/8) Epoch 10, batch 2850, loss[loss=0.1711, simple_loss=0.2664, pruned_loss=0.03785, over 7337.00 frames.], tot_loss[loss=0.184, simple_loss=0.2693, pruned_loss=0.04941, over 1427354.83 frames.], batch size: 22, lr: 7.50e-04
+2022-05-14 10:00:20,872 INFO [train.py:812] (2/8) Epoch 10, batch 2900, loss[loss=0.1927, simple_loss=0.2878, pruned_loss=0.0488, over 7108.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2688, pruned_loss=0.04926, over 1426075.54 frames.], batch size: 21, lr: 7.49e-04
+2022-05-14 10:01:19,221 INFO [train.py:812] (2/8) Epoch 10, batch 2950, loss[loss=0.1506, simple_loss=0.2357, pruned_loss=0.03277, over 7276.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2687, pruned_loss=0.04971, over 1426402.80 frames.], batch size: 18, lr: 7.49e-04
+2022-05-14 10:02:18,347 INFO [train.py:812] (2/8) Epoch 10, batch 3000, loss[loss=0.1554, simple_loss=0.2297, pruned_loss=0.04058, over 7284.00 frames.], tot_loss[loss=0.184, simple_loss=0.2685, pruned_loss=0.04974, over 1425733.13 frames.], batch size: 17, lr: 7.48e-04
+2022-05-14 10:02:18,349 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 10:02:25,810 INFO [train.py:841] (2/8) Epoch 10, validation: loss=0.1584, simple_loss=0.26, pruned_loss=0.0284, over 698248.00 frames.
+2022-05-14 10:03:25,416 INFO [train.py:812] (2/8) Epoch 10, batch 3050, loss[loss=0.1866, simple_loss=0.2715, pruned_loss=0.05088, over 7161.00 frames.], tot_loss[loss=0.184, simple_loss=0.2685, pruned_loss=0.04978, over 1425195.95 frames.], batch size: 19, lr: 7.48e-04
+2022-05-14 10:04:24,619 INFO [train.py:812] (2/8) Epoch 10, batch 3100, loss[loss=0.1881, simple_loss=0.2804, pruned_loss=0.04795, over 7112.00 frames.], tot_loss[loss=0.1843, simple_loss=0.269, pruned_loss=0.04984, over 1428130.42 frames.], batch size: 21, lr: 7.47e-04
+2022-05-14 10:05:24,379 INFO [train.py:812] (2/8) Epoch 10, batch 3150, loss[loss=0.1974, simple_loss=0.2858, pruned_loss=0.05447, over 7325.00 frames.], tot_loss[loss=0.185, simple_loss=0.2697, pruned_loss=0.0501, over 1424712.29 frames.], batch size: 21, lr: 7.47e-04
+2022-05-14 10:06:23,646 INFO [train.py:812] (2/8) Epoch 10, batch 3200, loss[loss=0.1691, simple_loss=0.2549, pruned_loss=0.04163, over 7246.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2683, pruned_loss=0.04916, over 1425148.10 frames.], batch size: 20, lr: 7.47e-04
+2022-05-14 10:07:23,032 INFO [train.py:812] (2/8) Epoch 10, batch 3250, loss[loss=0.1944, simple_loss=0.2935, pruned_loss=0.0477, over 7418.00 frames.], tot_loss[loss=0.184, simple_loss=0.2693, pruned_loss=0.0494, over 1426281.14 frames.], batch size: 21, lr: 7.46e-04
+2022-05-14 10:08:22,153 INFO [train.py:812] (2/8) Epoch 10, batch 3300, loss[loss=0.2075, simple_loss=0.2897, pruned_loss=0.06266, over 7205.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2693, pruned_loss=0.04884, over 1427429.11 frames.], batch size: 22, lr: 7.46e-04
+2022-05-14 10:09:21,726 INFO [train.py:812] (2/8) Epoch 10, batch 3350, loss[loss=0.1973, simple_loss=0.2905, pruned_loss=0.05203, over 7206.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2692, pruned_loss=0.04852, over 1428436.98 frames.], batch size: 23, lr: 7.45e-04
+2022-05-14 10:10:20,627 INFO [train.py:812] (2/8) Epoch 10, batch 3400, loss[loss=0.1765, simple_loss=0.2523, pruned_loss=0.05037, over 7280.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2691, pruned_loss=0.04895, over 1424417.31 frames.], batch size: 17, lr: 7.45e-04
+2022-05-14 10:11:20,163 INFO [train.py:812] (2/8) Epoch 10, batch 3450, loss[loss=0.1998, simple_loss=0.293, pruned_loss=0.05332, over 7304.00 frames.], tot_loss[loss=0.1845, simple_loss=0.27, pruned_loss=0.04952, over 1424008.10 frames.], batch size: 24, lr: 7.45e-04
+2022-05-14 10:12:19,084 INFO [train.py:812] (2/8) Epoch 10, batch 3500, loss[loss=0.214, simple_loss=0.3107, pruned_loss=0.05867, over 7411.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2693, pruned_loss=0.04885, over 1423429.32 frames.], batch size: 21, lr: 7.44e-04
+2022-05-14 10:13:18,715 INFO [train.py:812] (2/8) Epoch 10, batch 3550, loss[loss=0.2024, simple_loss=0.2827, pruned_loss=0.06098, over 7093.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2681, pruned_loss=0.04847, over 1426382.52 frames.], batch size: 28, lr: 7.44e-04
+2022-05-14 10:14:16,935 INFO [train.py:812] (2/8) Epoch 10, batch 3600, loss[loss=0.2089, simple_loss=0.284, pruned_loss=0.06693, over 6985.00 frames.], tot_loss[loss=0.1825, simple_loss=0.268, pruned_loss=0.04847, over 1426857.29 frames.], batch size: 28, lr: 7.43e-04
+2022-05-14 10:15:16,468 INFO [train.py:812] (2/8) Epoch 10, batch 3650, loss[loss=0.1644, simple_loss=0.2449, pruned_loss=0.04191, over 7072.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2681, pruned_loss=0.04859, over 1422739.36 frames.], batch size: 18, lr: 7.43e-04
+2022-05-14 10:16:15,514 INFO [train.py:812] (2/8) Epoch 10, batch 3700, loss[loss=0.133, simple_loss=0.2155, pruned_loss=0.02524, over 7268.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2681, pruned_loss=0.04804, over 1424954.62 frames.], batch size: 17, lr: 7.43e-04
+2022-05-14 10:17:15,220 INFO [train.py:812] (2/8) Epoch 10, batch 3750, loss[loss=0.1714, simple_loss=0.2574, pruned_loss=0.04272, over 7166.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2688, pruned_loss=0.04852, over 1428176.26 frames.], batch size: 19, lr: 7.42e-04
+2022-05-14 10:18:14,389 INFO [train.py:812] (2/8) Epoch 10, batch 3800, loss[loss=0.1846, simple_loss=0.2715, pruned_loss=0.04884, over 7441.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2692, pruned_loss=0.04882, over 1426256.84 frames.], batch size: 20, lr: 7.42e-04
+2022-05-14 10:19:12,957 INFO [train.py:812] (2/8) Epoch 10, batch 3850, loss[loss=0.1704, simple_loss=0.2485, pruned_loss=0.04614, over 7070.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2699, pruned_loss=0.04925, over 1425516.89 frames.], batch size: 18, lr: 7.41e-04
+2022-05-14 10:20:21,763 INFO [train.py:812] (2/8) Epoch 10, batch 3900, loss[loss=0.1694, simple_loss=0.2553, pruned_loss=0.04181, over 7158.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2699, pruned_loss=0.04952, over 1427417.60 frames.], batch size: 19, lr: 7.41e-04
+2022-05-14 10:21:21,326 INFO [train.py:812] (2/8) Epoch 10, batch 3950, loss[loss=0.251, simple_loss=0.316, pruned_loss=0.09303, over 5208.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2703, pruned_loss=0.05012, over 1421993.24 frames.], batch size: 52, lr: 7.41e-04
+2022-05-14 10:22:19,903 INFO [train.py:812] (2/8) Epoch 10, batch 4000, loss[loss=0.1577, simple_loss=0.2518, pruned_loss=0.03179, over 7249.00 frames.], tot_loss[loss=0.1858, simple_loss=0.271, pruned_loss=0.05029, over 1422709.53 frames.], batch size: 19, lr: 7.40e-04
+2022-05-14 10:23:18,819 INFO [train.py:812] (2/8) Epoch 10, batch 4050, loss[loss=0.1598, simple_loss=0.2475, pruned_loss=0.03609, over 7130.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2717, pruned_loss=0.05038, over 1423275.45 frames.], batch size: 17, lr: 7.40e-04
+2022-05-14 10:24:16,989 INFO [train.py:812] (2/8) Epoch 10, batch 4100, loss[loss=0.2073, simple_loss=0.2961, pruned_loss=0.05925, over 7323.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2711, pruned_loss=0.05003, over 1425164.12 frames.], batch size: 21, lr: 7.39e-04
+2022-05-14 10:25:16,585 INFO [train.py:812] (2/8) Epoch 10, batch 4150, loss[loss=0.1742, simple_loss=0.2495, pruned_loss=0.0495, over 7427.00 frames.], tot_loss[loss=0.1855, simple_loss=0.271, pruned_loss=0.04996, over 1425406.29 frames.], batch size: 18, lr: 7.39e-04
+2022-05-14 10:26:14,857 INFO [train.py:812] (2/8) Epoch 10, batch 4200, loss[loss=0.1645, simple_loss=0.2531, pruned_loss=0.03801, over 7295.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2708, pruned_loss=0.04994, over 1427485.55 frames.], batch size: 24, lr: 7.39e-04
+2022-05-14 10:27:14,018 INFO [train.py:812] (2/8) Epoch 10, batch 4250, loss[loss=0.1583, simple_loss=0.2328, pruned_loss=0.04196, over 7261.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2713, pruned_loss=0.05023, over 1422869.10 frames.], batch size: 17, lr: 7.38e-04
+2022-05-14 10:28:13,173 INFO [train.py:812] (2/8) Epoch 10, batch 4300, loss[loss=0.2468, simple_loss=0.3248, pruned_loss=0.08443, over 7316.00 frames.], tot_loss[loss=0.1857, simple_loss=0.271, pruned_loss=0.05024, over 1416778.14 frames.], batch size: 24, lr: 7.38e-04
+2022-05-14 10:29:10,973 INFO [train.py:812] (2/8) Epoch 10, batch 4350, loss[loss=0.2337, simple_loss=0.297, pruned_loss=0.08516, over 4968.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2731, pruned_loss=0.05162, over 1406678.17 frames.], batch size: 53, lr: 7.37e-04
+2022-05-14 10:30:10,258 INFO [train.py:812] (2/8) Epoch 10, batch 4400, loss[loss=0.232, simple_loss=0.3092, pruned_loss=0.07734, over 7201.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2731, pruned_loss=0.05183, over 1409477.90 frames.], batch size: 22, lr: 7.37e-04
+2022-05-14 10:31:10,035 INFO [train.py:812] (2/8) Epoch 10, batch 4450, loss[loss=0.2349, simple_loss=0.3014, pruned_loss=0.0842, over 5002.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2736, pruned_loss=0.05226, over 1394414.94 frames.], batch size: 52, lr: 7.37e-04
+2022-05-14 10:32:09,135 INFO [train.py:812] (2/8) Epoch 10, batch 4500, loss[loss=0.2171, simple_loss=0.3071, pruned_loss=0.06357, over 7143.00 frames.], tot_loss[loss=0.1884, simple_loss=0.273, pruned_loss=0.05192, over 1390610.08 frames.], batch size: 20, lr: 7.36e-04
+2022-05-14 10:33:08,674 INFO [train.py:812] (2/8) Epoch 10, batch 4550, loss[loss=0.1912, simple_loss=0.2833, pruned_loss=0.04957, over 7197.00 frames.], tot_loss[loss=0.189, simple_loss=0.2729, pruned_loss=0.05248, over 1371370.16 frames.], batch size: 26, lr: 7.36e-04
+2022-05-14 10:34:22,338 INFO [train.py:812] (2/8) Epoch 11, batch 0, loss[loss=0.2005, simple_loss=0.2837, pruned_loss=0.05868, over 7424.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2837, pruned_loss=0.05868, over 7424.00 frames.], batch size: 20, lr: 7.08e-04
+2022-05-14 10:35:21,278 INFO [train.py:812] (2/8) Epoch 11, batch 50, loss[loss=0.1768, simple_loss=0.2718, pruned_loss=0.0409, over 7436.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2704, pruned_loss=0.04814, over 323096.65 frames.], batch size: 20, lr: 7.08e-04
+2022-05-14 10:36:19,854 INFO [train.py:812] (2/8) Epoch 11, batch 100, loss[loss=0.1557, simple_loss=0.2378, pruned_loss=0.03677, over 7274.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2689, pruned_loss=0.04788, over 566821.90 frames.], batch size: 18, lr: 7.08e-04
+2022-05-14 10:37:28,460 INFO [train.py:812] (2/8) Epoch 11, batch 150, loss[loss=0.1794, simple_loss=0.2546, pruned_loss=0.05208, over 6773.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2712, pruned_loss=0.04872, over 759599.70 frames.], batch size: 15, lr: 7.07e-04
+2022-05-14 10:38:36,329 INFO [train.py:812] (2/8) Epoch 11, batch 200, loss[loss=0.1591, simple_loss=0.2323, pruned_loss=0.04289, over 7410.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2696, pruned_loss=0.04852, over 906823.00 frames.], batch size: 18, lr: 7.07e-04
+2022-05-14 10:39:34,531 INFO [train.py:812] (2/8) Epoch 11, batch 250, loss[loss=0.1853, simple_loss=0.2755, pruned_loss=0.04755, over 6403.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2676, pruned_loss=0.04738, over 1022059.26 frames.], batch size: 38, lr: 7.06e-04
+2022-05-14 10:40:50,470 INFO [train.py:812] (2/8) Epoch 11, batch 300, loss[loss=0.2354, simple_loss=0.2969, pruned_loss=0.0869, over 5133.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2672, pruned_loss=0.04682, over 1113567.39 frames.], batch size: 53, lr: 7.06e-04
+2022-05-14 10:41:47,854 INFO [train.py:812] (2/8) Epoch 11, batch 350, loss[loss=0.1802, simple_loss=0.2731, pruned_loss=0.04363, over 6831.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2684, pruned_loss=0.0476, over 1185937.48 frames.], batch size: 31, lr: 7.06e-04
+2022-05-14 10:43:03,984 INFO [train.py:812] (2/8) Epoch 11, batch 400, loss[loss=0.1909, simple_loss=0.2852, pruned_loss=0.04828, over 7431.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2673, pruned_loss=0.04743, over 1240076.81 frames.], batch size: 20, lr: 7.05e-04
+2022-05-14 10:44:13,169 INFO [train.py:812] (2/8) Epoch 11, batch 450, loss[loss=0.1968, simple_loss=0.2878, pruned_loss=0.05289, over 7232.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2661, pruned_loss=0.04723, over 1280942.43 frames.], batch size: 20, lr: 7.05e-04
+2022-05-14 10:45:12,581 INFO [train.py:812] (2/8) Epoch 11, batch 500, loss[loss=0.1873, simple_loss=0.2758, pruned_loss=0.04935, over 7326.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2662, pruned_loss=0.0473, over 1315536.07 frames.], batch size: 20, lr: 7.04e-04
+2022-05-14 10:46:12,063 INFO [train.py:812] (2/8) Epoch 11, batch 550, loss[loss=0.1613, simple_loss=0.2481, pruned_loss=0.03722, over 7068.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2665, pruned_loss=0.04759, over 1341056.77 frames.], batch size: 18, lr: 7.04e-04
+2022-05-14 10:47:11,317 INFO [train.py:812] (2/8) Epoch 11, batch 600, loss[loss=0.167, simple_loss=0.2516, pruned_loss=0.04124, over 7002.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2672, pruned_loss=0.04753, over 1360150.10 frames.], batch size: 16, lr: 7.04e-04
+2022-05-14 10:48:09,759 INFO [train.py:812] (2/8) Epoch 11, batch 650, loss[loss=0.1522, simple_loss=0.2299, pruned_loss=0.03727, over 7129.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2673, pruned_loss=0.04796, over 1365239.75 frames.], batch size: 17, lr: 7.03e-04
+2022-05-14 10:49:08,459 INFO [train.py:812] (2/8) Epoch 11, batch 700, loss[loss=0.1832, simple_loss=0.2672, pruned_loss=0.04961, over 6815.00 frames.], tot_loss[loss=0.1818, simple_loss=0.268, pruned_loss=0.04779, over 1375563.49 frames.], batch size: 15, lr: 7.03e-04
+2022-05-14 10:50:07,687 INFO [train.py:812] (2/8) Epoch 11, batch 750, loss[loss=0.1824, simple_loss=0.2689, pruned_loss=0.048, over 7136.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2674, pruned_loss=0.04793, over 1381495.16 frames.], batch size: 20, lr: 7.03e-04
+2022-05-14 10:51:05,911 INFO [train.py:812] (2/8) Epoch 11, batch 800, loss[loss=0.1796, simple_loss=0.2725, pruned_loss=0.04329, over 7134.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2664, pruned_loss=0.04723, over 1393535.77 frames.], batch size: 26, lr: 7.02e-04
+2022-05-14 10:52:03,628 INFO [train.py:812] (2/8) Epoch 11, batch 850, loss[loss=0.1971, simple_loss=0.2806, pruned_loss=0.05676, over 7332.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2665, pruned_loss=0.04723, over 1397276.94 frames.], batch size: 20, lr: 7.02e-04
+2022-05-14 10:53:01,819 INFO [train.py:812] (2/8) Epoch 11, batch 900, loss[loss=0.1902, simple_loss=0.2686, pruned_loss=0.05591, over 7436.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2668, pruned_loss=0.04713, over 1406447.14 frames.], batch size: 20, lr: 7.02e-04
+2022-05-14 10:54:00,449 INFO [train.py:812] (2/8) Epoch 11, batch 950, loss[loss=0.1583, simple_loss=0.2302, pruned_loss=0.04318, over 6992.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2668, pruned_loss=0.04748, over 1409059.44 frames.], batch size: 16, lr: 7.01e-04
+2022-05-14 10:54:58,951 INFO [train.py:812] (2/8) Epoch 11, batch 1000, loss[loss=0.1966, simple_loss=0.281, pruned_loss=0.05615, over 7286.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2663, pruned_loss=0.04704, over 1412914.00 frames.], batch size: 25, lr: 7.01e-04
+2022-05-14 10:55:58,045 INFO [train.py:812] (2/8) Epoch 11, batch 1050, loss[loss=0.1975, simple_loss=0.2869, pruned_loss=0.05406, over 7270.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2689, pruned_loss=0.04834, over 1407435.42 frames.], batch size: 19, lr: 7.00e-04
+2022-05-14 10:56:57,226 INFO [train.py:812] (2/8) Epoch 11, batch 1100, loss[loss=0.161, simple_loss=0.2454, pruned_loss=0.03827, over 7164.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2683, pruned_loss=0.0477, over 1412621.68 frames.], batch size: 18, lr: 7.00e-04
+2022-05-14 10:57:56,859 INFO [train.py:812] (2/8) Epoch 11, batch 1150, loss[loss=0.1947, simple_loss=0.2621, pruned_loss=0.06361, over 7075.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2678, pruned_loss=0.04753, over 1417190.46 frames.], batch size: 18, lr: 7.00e-04
+2022-05-14 10:58:55,463 INFO [train.py:812] (2/8) Epoch 11, batch 1200, loss[loss=0.193, simple_loss=0.2757, pruned_loss=0.05512, over 7266.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2661, pruned_loss=0.04731, over 1419809.62 frames.], batch size: 16, lr: 6.99e-04
+2022-05-14 10:59:53,782 INFO [train.py:812] (2/8) Epoch 11, batch 1250, loss[loss=0.1799, simple_loss=0.2493, pruned_loss=0.0553, over 7117.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2653, pruned_loss=0.04719, over 1423743.06 frames.], batch size: 17, lr: 6.99e-04
+2022-05-14 11:00:50,427 INFO [train.py:812] (2/8) Epoch 11, batch 1300, loss[loss=0.1954, simple_loss=0.2859, pruned_loss=0.0524, over 7321.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2655, pruned_loss=0.04712, over 1420159.54 frames.], batch size: 21, lr: 6.99e-04
+2022-05-14 11:01:49,328 INFO [train.py:812] (2/8) Epoch 11, batch 1350, loss[loss=0.1765, simple_loss=0.2695, pruned_loss=0.04175, over 7324.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2649, pruned_loss=0.04672, over 1424400.12 frames.], batch size: 21, lr: 6.98e-04
+2022-05-14 11:02:46,392 INFO [train.py:812] (2/8) Epoch 11, batch 1400, loss[loss=0.1675, simple_loss=0.2433, pruned_loss=0.04587, over 7149.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2649, pruned_loss=0.04711, over 1427529.68 frames.], batch size: 19, lr: 6.98e-04
+2022-05-14 11:03:44,645 INFO [train.py:812] (2/8) Epoch 11, batch 1450, loss[loss=0.1903, simple_loss=0.2736, pruned_loss=0.05346, over 7290.00 frames.], tot_loss[loss=0.1801, simple_loss=0.266, pruned_loss=0.04709, over 1427580.27 frames.], batch size: 17, lr: 6.97e-04
+2022-05-14 11:04:41,554 INFO [train.py:812] (2/8) Epoch 11, batch 1500, loss[loss=0.1796, simple_loss=0.2709, pruned_loss=0.0442, over 7137.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2661, pruned_loss=0.04709, over 1426241.12 frames.], batch size: 28, lr: 6.97e-04
+2022-05-14 11:05:41,365 INFO [train.py:812] (2/8) Epoch 11, batch 1550, loss[loss=0.1717, simple_loss=0.2556, pruned_loss=0.04387, over 7436.00 frames.], tot_loss[loss=0.181, simple_loss=0.2671, pruned_loss=0.04748, over 1424580.68 frames.], batch size: 20, lr: 6.97e-04
+2022-05-14 11:06:38,920 INFO [train.py:812] (2/8) Epoch 11, batch 1600, loss[loss=0.1849, simple_loss=0.2722, pruned_loss=0.04877, over 6853.00 frames.], tot_loss[loss=0.181, simple_loss=0.2668, pruned_loss=0.04763, over 1418883.78 frames.], batch size: 31, lr: 6.96e-04
+2022-05-14 11:07:38,261 INFO [train.py:812] (2/8) Epoch 11, batch 1650, loss[loss=0.1749, simple_loss=0.245, pruned_loss=0.05244, over 6830.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2671, pruned_loss=0.04782, over 1418097.48 frames.], batch size: 15, lr: 6.96e-04
+2022-05-14 11:08:37,012 INFO [train.py:812] (2/8) Epoch 11, batch 1700, loss[loss=0.1547, simple_loss=0.2386, pruned_loss=0.0354, over 6797.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2675, pruned_loss=0.04767, over 1417151.10 frames.], batch size: 15, lr: 6.96e-04
+2022-05-14 11:09:36,817 INFO [train.py:812] (2/8) Epoch 11, batch 1750, loss[loss=0.1885, simple_loss=0.2765, pruned_loss=0.05023, over 7126.00 frames.], tot_loss[loss=0.1813, simple_loss=0.267, pruned_loss=0.0478, over 1413096.55 frames.], batch size: 21, lr: 6.95e-04
+2022-05-14 11:10:35,743 INFO [train.py:812] (2/8) Epoch 11, batch 1800, loss[loss=0.2539, simple_loss=0.3199, pruned_loss=0.09392, over 5156.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2676, pruned_loss=0.04781, over 1413625.03 frames.], batch size: 53, lr: 6.95e-04
+2022-05-14 11:11:35,350 INFO [train.py:812] (2/8) Epoch 11, batch 1850, loss[loss=0.197, simple_loss=0.282, pruned_loss=0.056, over 6495.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2672, pruned_loss=0.04733, over 1417314.82 frames.], batch size: 38, lr: 6.95e-04
+2022-05-14 11:12:33,307 INFO [train.py:812] (2/8) Epoch 11, batch 1900, loss[loss=0.1816, simple_loss=0.2829, pruned_loss=0.04012, over 7319.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2666, pruned_loss=0.04721, over 1421836.15 frames.], batch size: 21, lr: 6.94e-04
+2022-05-14 11:13:32,941 INFO [train.py:812] (2/8) Epoch 11, batch 1950, loss[loss=0.2118, simple_loss=0.2995, pruned_loss=0.06199, over 7346.00 frames.], tot_loss[loss=0.1809, simple_loss=0.267, pruned_loss=0.0474, over 1421030.93 frames.], batch size: 19, lr: 6.94e-04
+2022-05-14 11:14:32,083 INFO [train.py:812] (2/8) Epoch 11, batch 2000, loss[loss=0.1473, simple_loss=0.2255, pruned_loss=0.03448, over 7181.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2675, pruned_loss=0.04755, over 1422492.72 frames.], batch size: 18, lr: 6.93e-04
+2022-05-14 11:15:30,893 INFO [train.py:812] (2/8) Epoch 11, batch 2050, loss[loss=0.1365, simple_loss=0.2176, pruned_loss=0.02776, over 7282.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2669, pruned_loss=0.04718, over 1424732.63 frames.], batch size: 17, lr: 6.93e-04
+2022-05-14 11:16:30,529 INFO [train.py:812] (2/8) Epoch 11, batch 2100, loss[loss=0.2027, simple_loss=0.2869, pruned_loss=0.0593, over 7394.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2674, pruned_loss=0.04745, over 1425253.22 frames.], batch size: 23, lr: 6.93e-04
+2022-05-14 11:17:37,594 INFO [train.py:812] (2/8) Epoch 11, batch 2150, loss[loss=0.1679, simple_loss=0.2573, pruned_loss=0.03928, over 7168.00 frames.], tot_loss[loss=0.181, simple_loss=0.2672, pruned_loss=0.04739, over 1425544.83 frames.], batch size: 18, lr: 6.92e-04
+2022-05-14 11:18:36,037 INFO [train.py:812] (2/8) Epoch 11, batch 2200, loss[loss=0.186, simple_loss=0.277, pruned_loss=0.0475, over 7230.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2681, pruned_loss=0.04786, over 1424145.38 frames.], batch size: 20, lr: 6.92e-04
+2022-05-14 11:19:35,026 INFO [train.py:812] (2/8) Epoch 11, batch 2250, loss[loss=0.1841, simple_loss=0.2805, pruned_loss=0.04381, over 7341.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2686, pruned_loss=0.0478, over 1427583.46 frames.], batch size: 22, lr: 6.92e-04
+2022-05-14 11:20:34,377 INFO [train.py:812] (2/8) Epoch 11, batch 2300, loss[loss=0.1833, simple_loss=0.2638, pruned_loss=0.05137, over 7131.00 frames.], tot_loss[loss=0.1831, simple_loss=0.269, pruned_loss=0.04857, over 1427436.43 frames.], batch size: 26, lr: 6.91e-04
+2022-05-14 11:21:33,297 INFO [train.py:812] (2/8) Epoch 11, batch 2350, loss[loss=0.2267, simple_loss=0.3113, pruned_loss=0.07108, over 6852.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2678, pruned_loss=0.04774, over 1429619.73 frames.], batch size: 31, lr: 6.91e-04
+2022-05-14 11:22:32,016 INFO [train.py:812] (2/8) Epoch 11, batch 2400, loss[loss=0.1806, simple_loss=0.2738, pruned_loss=0.04371, over 7325.00 frames.], tot_loss[loss=0.1811, simple_loss=0.267, pruned_loss=0.04756, over 1423135.91 frames.], batch size: 21, lr: 6.91e-04
+2022-05-14 11:23:31,182 INFO [train.py:812] (2/8) Epoch 11, batch 2450, loss[loss=0.1614, simple_loss=0.246, pruned_loss=0.03836, over 6974.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2665, pruned_loss=0.04748, over 1423010.00 frames.], batch size: 16, lr: 6.90e-04
+2022-05-14 11:24:30,273 INFO [train.py:812] (2/8) Epoch 11, batch 2500, loss[loss=0.1606, simple_loss=0.2535, pruned_loss=0.03384, over 7150.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2677, pruned_loss=0.04759, over 1421888.91 frames.], batch size: 19, lr: 6.90e-04
+2022-05-14 11:25:29,316 INFO [train.py:812] (2/8) Epoch 11, batch 2550, loss[loss=0.1792, simple_loss=0.2563, pruned_loss=0.05098, over 7212.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2666, pruned_loss=0.04697, over 1426186.85 frames.], batch size: 16, lr: 6.90e-04
+2022-05-14 11:26:27,802 INFO [train.py:812] (2/8) Epoch 11, batch 2600, loss[loss=0.2019, simple_loss=0.2843, pruned_loss=0.05971, over 7389.00 frames.], tot_loss[loss=0.1811, simple_loss=0.267, pruned_loss=0.04757, over 1428322.99 frames.], batch size: 23, lr: 6.89e-04
+2022-05-14 11:27:26,155 INFO [train.py:812] (2/8) Epoch 11, batch 2650, loss[loss=0.1556, simple_loss=0.2274, pruned_loss=0.0419, over 7009.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2674, pruned_loss=0.04756, over 1424402.50 frames.], batch size: 16, lr: 6.89e-04
+2022-05-14 11:28:23,549 INFO [train.py:812] (2/8) Epoch 11, batch 2700, loss[loss=0.1841, simple_loss=0.2815, pruned_loss=0.04332, over 7411.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2678, pruned_loss=0.04757, over 1427127.24 frames.], batch size: 21, lr: 6.89e-04
+2022-05-14 11:29:20,995 INFO [train.py:812] (2/8) Epoch 11, batch 2750, loss[loss=0.1497, simple_loss=0.2373, pruned_loss=0.03108, over 7286.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2663, pruned_loss=0.04706, over 1425300.14 frames.], batch size: 18, lr: 6.88e-04
+2022-05-14 11:30:18,039 INFO [train.py:812] (2/8) Epoch 11, batch 2800, loss[loss=0.189, simple_loss=0.2814, pruned_loss=0.04826, over 7158.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2664, pruned_loss=0.04696, over 1424576.44 frames.], batch size: 19, lr: 6.88e-04
+2022-05-14 11:31:17,637 INFO [train.py:812] (2/8) Epoch 11, batch 2850, loss[loss=0.1753, simple_loss=0.2702, pruned_loss=0.04017, over 7324.00 frames.], tot_loss[loss=0.18, simple_loss=0.2658, pruned_loss=0.04709, over 1424537.42 frames.], batch size: 21, lr: 6.87e-04
+2022-05-14 11:32:14,487 INFO [train.py:812] (2/8) Epoch 11, batch 2900, loss[loss=0.2358, simple_loss=0.3152, pruned_loss=0.07815, over 7219.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2658, pruned_loss=0.04698, over 1427064.97 frames.], batch size: 23, lr: 6.87e-04
+2022-05-14 11:33:13,348 INFO [train.py:812] (2/8) Epoch 11, batch 2950, loss[loss=0.1802, simple_loss=0.2655, pruned_loss=0.04749, over 7192.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2665, pruned_loss=0.04711, over 1424600.79 frames.], batch size: 22, lr: 6.87e-04
+2022-05-14 11:34:12,256 INFO [train.py:812] (2/8) Epoch 11, batch 3000, loss[loss=0.1685, simple_loss=0.2505, pruned_loss=0.04324, over 7168.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2663, pruned_loss=0.04696, over 1423582.40 frames.], batch size: 18, lr: 6.86e-04
+2022-05-14 11:34:12,257 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 11:34:19,822 INFO [train.py:841] (2/8) Epoch 11, validation: loss=0.1564, simple_loss=0.2581, pruned_loss=0.02737, over 698248.00 frames.
+2022-05-14 11:35:18,330 INFO [train.py:812] (2/8) Epoch 11, batch 3050, loss[loss=0.1738, simple_loss=0.2668, pruned_loss=0.04038, over 7131.00 frames.], tot_loss[loss=0.18, simple_loss=0.266, pruned_loss=0.04704, over 1427451.15 frames.], batch size: 26, lr: 6.86e-04
+2022-05-14 11:36:16,722 INFO [train.py:812] (2/8) Epoch 11, batch 3100, loss[loss=0.1316, simple_loss=0.2147, pruned_loss=0.02427, over 7421.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2661, pruned_loss=0.04707, over 1425394.49 frames.], batch size: 18, lr: 6.86e-04
+2022-05-14 11:37:16,184 INFO [train.py:812] (2/8) Epoch 11, batch 3150, loss[loss=0.1588, simple_loss=0.2341, pruned_loss=0.04179, over 7277.00 frames.], tot_loss[loss=0.18, simple_loss=0.2655, pruned_loss=0.04724, over 1427343.83 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:38:15,167 INFO [train.py:812] (2/8) Epoch 11, batch 3200, loss[loss=0.1585, simple_loss=0.246, pruned_loss=0.03545, over 7153.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2655, pruned_loss=0.04734, over 1429003.06 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:39:14,892 INFO [train.py:812] (2/8) Epoch 11, batch 3250, loss[loss=0.1773, simple_loss=0.2558, pruned_loss=0.04936, over 7071.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2657, pruned_loss=0.04728, over 1430649.80 frames.], batch size: 18, lr: 6.85e-04
+2022-05-14 11:40:14,268 INFO [train.py:812] (2/8) Epoch 11, batch 3300, loss[loss=0.1904, simple_loss=0.2819, pruned_loss=0.0494, over 6248.00 frames.], tot_loss[loss=0.18, simple_loss=0.2655, pruned_loss=0.04728, over 1429717.72 frames.], batch size: 37, lr: 6.84e-04
+2022-05-14 11:41:13,846 INFO [train.py:812] (2/8) Epoch 11, batch 3350, loss[loss=0.1661, simple_loss=0.2534, pruned_loss=0.0394, over 7112.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2669, pruned_loss=0.04781, over 1424085.92 frames.], batch size: 21, lr: 6.84e-04
+2022-05-14 11:42:12,402 INFO [train.py:812] (2/8) Epoch 11, batch 3400, loss[loss=0.1494, simple_loss=0.2335, pruned_loss=0.03265, over 7004.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2665, pruned_loss=0.04742, over 1421779.55 frames.], batch size: 16, lr: 6.84e-04
+2022-05-14 11:43:11,484 INFO [train.py:812] (2/8) Epoch 11, batch 3450, loss[loss=0.1837, simple_loss=0.2798, pruned_loss=0.04381, over 7120.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2672, pruned_loss=0.04763, over 1424301.83 frames.], batch size: 21, lr: 6.83e-04
+2022-05-14 11:44:10,163 INFO [train.py:812] (2/8) Epoch 11, batch 3500, loss[loss=0.1622, simple_loss=0.2414, pruned_loss=0.04146, over 7409.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2668, pruned_loss=0.04735, over 1426278.28 frames.], batch size: 18, lr: 6.83e-04
+2022-05-14 11:45:10,021 INFO [train.py:812] (2/8) Epoch 11, batch 3550, loss[loss=0.1798, simple_loss=0.2779, pruned_loss=0.04091, over 6257.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2661, pruned_loss=0.04671, over 1424638.18 frames.], batch size: 37, lr: 6.83e-04
+2022-05-14 11:46:08,748 INFO [train.py:812] (2/8) Epoch 11, batch 3600, loss[loss=0.1751, simple_loss=0.2631, pruned_loss=0.04354, over 6300.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2664, pruned_loss=0.04707, over 1420098.71 frames.], batch size: 37, lr: 6.82e-04
+2022-05-14 11:47:07,760 INFO [train.py:812] (2/8) Epoch 11, batch 3650, loss[loss=0.1789, simple_loss=0.2739, pruned_loss=0.04195, over 7111.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2663, pruned_loss=0.04646, over 1422130.81 frames.], batch size: 21, lr: 6.82e-04
+2022-05-14 11:48:06,898 INFO [train.py:812] (2/8) Epoch 11, batch 3700, loss[loss=0.1835, simple_loss=0.2699, pruned_loss=0.04858, over 7118.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2675, pruned_loss=0.04742, over 1418468.98 frames.], batch size: 21, lr: 6.82e-04
+2022-05-14 11:49:06,525 INFO [train.py:812] (2/8) Epoch 11, batch 3750, loss[loss=0.1958, simple_loss=0.2818, pruned_loss=0.05492, over 7437.00 frames.], tot_loss[loss=0.181, simple_loss=0.2675, pruned_loss=0.04727, over 1424167.22 frames.], batch size: 20, lr: 6.81e-04
+2022-05-14 11:50:05,386 INFO [train.py:812] (2/8) Epoch 11, batch 3800, loss[loss=0.1783, simple_loss=0.2734, pruned_loss=0.04158, over 7295.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2669, pruned_loss=0.04704, over 1422896.74 frames.], batch size: 24, lr: 6.81e-04
+2022-05-14 11:51:04,551 INFO [train.py:812] (2/8) Epoch 11, batch 3850, loss[loss=0.1883, simple_loss=0.2809, pruned_loss=0.04781, over 7207.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2668, pruned_loss=0.04677, over 1427373.35 frames.], batch size: 22, lr: 6.81e-04
+2022-05-14 11:52:01,421 INFO [train.py:812] (2/8) Epoch 11, batch 3900, loss[loss=0.193, simple_loss=0.2753, pruned_loss=0.05537, over 7378.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2664, pruned_loss=0.04666, over 1428455.18 frames.], batch size: 23, lr: 6.80e-04
+2022-05-14 11:53:00,918 INFO [train.py:812] (2/8) Epoch 11, batch 3950, loss[loss=0.1921, simple_loss=0.2764, pruned_loss=0.05392, over 7431.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2669, pruned_loss=0.04713, over 1426629.15 frames.], batch size: 20, lr: 6.80e-04
+2022-05-14 11:53:59,463 INFO [train.py:812] (2/8) Epoch 11, batch 4000, loss[loss=0.1754, simple_loss=0.2663, pruned_loss=0.04226, over 7225.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2676, pruned_loss=0.04811, over 1418459.76 frames.], batch size: 21, lr: 6.80e-04
+2022-05-14 11:54:58,986 INFO [train.py:812] (2/8) Epoch 11, batch 4050, loss[loss=0.1991, simple_loss=0.269, pruned_loss=0.06458, over 7195.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2678, pruned_loss=0.04843, over 1418651.57 frames.], batch size: 22, lr: 6.79e-04
+2022-05-14 11:55:57,975 INFO [train.py:812] (2/8) Epoch 11, batch 4100, loss[loss=0.1918, simple_loss=0.2851, pruned_loss=0.04923, over 7218.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2675, pruned_loss=0.04791, over 1418331.90 frames.], batch size: 22, lr: 6.79e-04
+2022-05-14 11:56:56,032 INFO [train.py:812] (2/8) Epoch 11, batch 4150, loss[loss=0.1733, simple_loss=0.2608, pruned_loss=0.04292, over 6946.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2684, pruned_loss=0.04814, over 1415906.90 frames.], batch size: 31, lr: 6.79e-04
+2022-05-14 11:57:54,858 INFO [train.py:812] (2/8) Epoch 11, batch 4200, loss[loss=0.1833, simple_loss=0.2836, pruned_loss=0.0415, over 6969.00 frames.], tot_loss[loss=0.1819, simple_loss=0.268, pruned_loss=0.04786, over 1416194.51 frames.], batch size: 28, lr: 6.78e-04
+2022-05-14 11:58:54,362 INFO [train.py:812] (2/8) Epoch 11, batch 4250, loss[loss=0.2437, simple_loss=0.3184, pruned_loss=0.08445, over 5353.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2677, pruned_loss=0.04822, over 1415709.35 frames.], batch size: 52, lr: 6.78e-04
+2022-05-14 11:59:53,056 INFO [train.py:812] (2/8) Epoch 11, batch 4300, loss[loss=0.2307, simple_loss=0.3156, pruned_loss=0.07292, over 5065.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2687, pruned_loss=0.04887, over 1411501.17 frames.], batch size: 52, lr: 6.78e-04
+2022-05-14 12:00:52,212 INFO [train.py:812] (2/8) Epoch 11, batch 4350, loss[loss=0.1438, simple_loss=0.2323, pruned_loss=0.02767, over 7232.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2688, pruned_loss=0.04873, over 1409294.63 frames.], batch size: 20, lr: 6.77e-04
+2022-05-14 12:01:50,172 INFO [train.py:812] (2/8) Epoch 11, batch 4400, loss[loss=0.1807, simple_loss=0.2702, pruned_loss=0.04559, over 7197.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2691, pruned_loss=0.04873, over 1414496.54 frames.], batch size: 22, lr: 6.77e-04
+2022-05-14 12:02:49,050 INFO [train.py:812] (2/8) Epoch 11, batch 4450, loss[loss=0.1983, simple_loss=0.2868, pruned_loss=0.05493, over 7230.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2716, pruned_loss=0.04993, over 1416954.38 frames.], batch size: 20, lr: 6.77e-04
+2022-05-14 12:03:48,069 INFO [train.py:812] (2/8) Epoch 11, batch 4500, loss[loss=0.1956, simple_loss=0.2804, pruned_loss=0.05542, over 4998.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2719, pruned_loss=0.04975, over 1408955.34 frames.], batch size: 52, lr: 6.76e-04
+2022-05-14 12:04:46,791 INFO [train.py:812] (2/8) Epoch 11, batch 4550, loss[loss=0.2205, simple_loss=0.3008, pruned_loss=0.07014, over 5072.00 frames.], tot_loss[loss=0.1888, simple_loss=0.274, pruned_loss=0.05185, over 1345248.09 frames.], batch size: 53, lr: 6.76e-04
+2022-05-14 12:05:54,961 INFO [train.py:812] (2/8) Epoch 12, batch 0, loss[loss=0.1784, simple_loss=0.263, pruned_loss=0.04692, over 7407.00 frames.], tot_loss[loss=0.1784, simple_loss=0.263, pruned_loss=0.04692, over 7407.00 frames.], batch size: 21, lr: 6.52e-04
+2022-05-14 12:06:54,746 INFO [train.py:812] (2/8) Epoch 12, batch 50, loss[loss=0.2004, simple_loss=0.2776, pruned_loss=0.06161, over 5208.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2658, pruned_loss=0.0463, over 319371.05 frames.], batch size: 52, lr: 6.52e-04
+2022-05-14 12:07:53,907 INFO [train.py:812] (2/8) Epoch 12, batch 100, loss[loss=0.1753, simple_loss=0.2664, pruned_loss=0.04213, over 6208.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2656, pruned_loss=0.04637, over 558360.21 frames.], batch size: 37, lr: 6.51e-04
+2022-05-14 12:08:53,453 INFO [train.py:812] (2/8) Epoch 12, batch 150, loss[loss=0.1457, simple_loss=0.2294, pruned_loss=0.03106, over 7296.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2676, pruned_loss=0.0463, over 749110.22 frames.], batch size: 17, lr: 6.51e-04
+2022-05-14 12:09:52,491 INFO [train.py:812] (2/8) Epoch 12, batch 200, loss[loss=0.1929, simple_loss=0.2816, pruned_loss=0.05208, over 7203.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2682, pruned_loss=0.04673, over 897126.49 frames.], batch size: 22, lr: 6.51e-04
+2022-05-14 12:10:51,853 INFO [train.py:812] (2/8) Epoch 12, batch 250, loss[loss=0.1711, simple_loss=0.249, pruned_loss=0.04661, over 6872.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2671, pruned_loss=0.04681, over 1015351.41 frames.], batch size: 31, lr: 6.50e-04
+2022-05-14 12:11:51,035 INFO [train.py:812] (2/8) Epoch 12, batch 300, loss[loss=0.1989, simple_loss=0.2869, pruned_loss=0.05544, over 7210.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2674, pruned_loss=0.04663, over 1099001.91 frames.], batch size: 22, lr: 6.50e-04
+2022-05-14 12:12:50,781 INFO [train.py:812] (2/8) Epoch 12, batch 350, loss[loss=0.1892, simple_loss=0.2789, pruned_loss=0.04972, over 7344.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2657, pruned_loss=0.04588, over 1166168.53 frames.], batch size: 22, lr: 6.50e-04
+2022-05-14 12:13:50,257 INFO [train.py:812] (2/8) Epoch 12, batch 400, loss[loss=0.1671, simple_loss=0.2684, pruned_loss=0.03287, over 7350.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2654, pruned_loss=0.04558, over 1221368.04 frames.], batch size: 22, lr: 6.49e-04
+2022-05-14 12:14:48,359 INFO [train.py:812] (2/8) Epoch 12, batch 450, loss[loss=0.1382, simple_loss=0.2379, pruned_loss=0.01929, over 7152.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2649, pruned_loss=0.04514, over 1269651.11 frames.], batch size: 19, lr: 6.49e-04
+2022-05-14 12:15:47,353 INFO [train.py:812] (2/8) Epoch 12, batch 500, loss[loss=0.2, simple_loss=0.2776, pruned_loss=0.06116, over 7385.00 frames.], tot_loss[loss=0.1782, simple_loss=0.265, pruned_loss=0.04569, over 1304643.65 frames.], batch size: 23, lr: 6.49e-04
+2022-05-14 12:16:45,612 INFO [train.py:812] (2/8) Epoch 12, batch 550, loss[loss=0.1335, simple_loss=0.2223, pruned_loss=0.02232, over 7407.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2643, pruned_loss=0.04576, over 1331167.55 frames.], batch size: 21, lr: 6.48e-04
+2022-05-14 12:17:43,575 INFO [train.py:812] (2/8) Epoch 12, batch 600, loss[loss=0.1635, simple_loss=0.2719, pruned_loss=0.0275, over 7325.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2637, pruned_loss=0.04526, over 1349234.15 frames.], batch size: 22, lr: 6.48e-04
+2022-05-14 12:18:41,728 INFO [train.py:812] (2/8) Epoch 12, batch 650, loss[loss=0.2007, simple_loss=0.2955, pruned_loss=0.05291, over 7378.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2622, pruned_loss=0.04451, over 1369769.56 frames.], batch size: 23, lr: 6.48e-04
+2022-05-14 12:19:49,918 INFO [train.py:812] (2/8) Epoch 12, batch 700, loss[loss=0.2006, simple_loss=0.2832, pruned_loss=0.05901, over 7331.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2633, pruned_loss=0.04486, over 1380619.34 frames.], batch size: 24, lr: 6.47e-04
+2022-05-14 12:20:48,719 INFO [train.py:812] (2/8) Epoch 12, batch 750, loss[loss=0.1833, simple_loss=0.2757, pruned_loss=0.04544, over 7327.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2647, pruned_loss=0.04548, over 1386222.17 frames.], batch size: 20, lr: 6.47e-04
+2022-05-14 12:21:48,018 INFO [train.py:812] (2/8) Epoch 12, batch 800, loss[loss=0.1634, simple_loss=0.2449, pruned_loss=0.04094, over 7416.00 frames.], tot_loss[loss=0.1787, simple_loss=0.265, pruned_loss=0.04619, over 1399750.67 frames.], batch size: 18, lr: 6.47e-04
+2022-05-14 12:22:46,126 INFO [train.py:812] (2/8) Epoch 12, batch 850, loss[loss=0.1827, simple_loss=0.2741, pruned_loss=0.0456, over 6830.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2653, pruned_loss=0.04604, over 1403848.31 frames.], batch size: 31, lr: 6.46e-04
+2022-05-14 12:23:43,976 INFO [train.py:812] (2/8) Epoch 12, batch 900, loss[loss=0.1827, simple_loss=0.2751, pruned_loss=0.04515, over 7330.00 frames.], tot_loss[loss=0.179, simple_loss=0.2657, pruned_loss=0.04616, over 1408295.03 frames.], batch size: 22, lr: 6.46e-04
+2022-05-14 12:24:43,751 INFO [train.py:812] (2/8) Epoch 12, batch 950, loss[loss=0.1705, simple_loss=0.2571, pruned_loss=0.04192, over 7429.00 frames.], tot_loss[loss=0.1791, simple_loss=0.266, pruned_loss=0.04605, over 1412738.01 frames.], batch size: 20, lr: 6.46e-04
+2022-05-14 12:25:42,232 INFO [train.py:812] (2/8) Epoch 12, batch 1000, loss[loss=0.164, simple_loss=0.2564, pruned_loss=0.03582, over 7154.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2658, pruned_loss=0.04556, over 1415928.90 frames.], batch size: 19, lr: 6.46e-04
+2022-05-14 12:26:41,694 INFO [train.py:812] (2/8) Epoch 12, batch 1050, loss[loss=0.1628, simple_loss=0.2392, pruned_loss=0.04321, over 6989.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2656, pruned_loss=0.04539, over 1415483.23 frames.], batch size: 16, lr: 6.45e-04
+2022-05-14 12:27:40,723 INFO [train.py:812] (2/8) Epoch 12, batch 1100, loss[loss=0.1561, simple_loss=0.2418, pruned_loss=0.03515, over 7171.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2667, pruned_loss=0.04582, over 1418832.66 frames.], batch size: 19, lr: 6.45e-04
+2022-05-14 12:28:40,258 INFO [train.py:812] (2/8) Epoch 12, batch 1150, loss[loss=0.1995, simple_loss=0.2757, pruned_loss=0.06166, over 5009.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2659, pruned_loss=0.04564, over 1421339.22 frames.], batch size: 53, lr: 6.45e-04
+2022-05-14 12:29:38,127 INFO [train.py:812] (2/8) Epoch 12, batch 1200, loss[loss=0.1663, simple_loss=0.2548, pruned_loss=0.03883, over 7113.00 frames.], tot_loss[loss=0.1788, simple_loss=0.266, pruned_loss=0.04585, over 1423873.19 frames.], batch size: 21, lr: 6.44e-04
+2022-05-14 12:30:37,010 INFO [train.py:812] (2/8) Epoch 12, batch 1250, loss[loss=0.16, simple_loss=0.2348, pruned_loss=0.04261, over 6996.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2664, pruned_loss=0.04632, over 1424740.56 frames.], batch size: 16, lr: 6.44e-04
+2022-05-14 12:31:36,698 INFO [train.py:812] (2/8) Epoch 12, batch 1300, loss[loss=0.199, simple_loss=0.2709, pruned_loss=0.06351, over 7330.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2655, pruned_loss=0.04574, over 1427380.44 frames.], batch size: 20, lr: 6.44e-04
+2022-05-14 12:32:34,886 INFO [train.py:812] (2/8) Epoch 12, batch 1350, loss[loss=0.1793, simple_loss=0.2706, pruned_loss=0.04397, over 7330.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2661, pruned_loss=0.04643, over 1424742.29 frames.], batch size: 21, lr: 6.43e-04
+2022-05-14 12:33:34,157 INFO [train.py:812] (2/8) Epoch 12, batch 1400, loss[loss=0.1694, simple_loss=0.2716, pruned_loss=0.03365, over 7326.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2649, pruned_loss=0.04612, over 1421645.03 frames.], batch size: 21, lr: 6.43e-04
+2022-05-14 12:34:33,411 INFO [train.py:812] (2/8) Epoch 12, batch 1450, loss[loss=0.1685, simple_loss=0.2517, pruned_loss=0.04259, over 7067.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2652, pruned_loss=0.04615, over 1421856.33 frames.], batch size: 18, lr: 6.43e-04
+2022-05-14 12:35:32,027 INFO [train.py:812] (2/8) Epoch 12, batch 1500, loss[loss=0.2115, simple_loss=0.2996, pruned_loss=0.06171, over 7206.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2655, pruned_loss=0.04634, over 1426612.61 frames.], batch size: 23, lr: 6.42e-04
+2022-05-14 12:36:36,866 INFO [train.py:812] (2/8) Epoch 12, batch 1550, loss[loss=0.1671, simple_loss=0.2681, pruned_loss=0.03304, over 7237.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2639, pruned_loss=0.04546, over 1426050.41 frames.], batch size: 20, lr: 6.42e-04
+2022-05-14 12:37:35,855 INFO [train.py:812] (2/8) Epoch 12, batch 1600, loss[loss=0.1841, simple_loss=0.2605, pruned_loss=0.05388, over 7349.00 frames.], tot_loss[loss=0.178, simple_loss=0.2648, pruned_loss=0.04556, over 1426545.52 frames.], batch size: 19, lr: 6.42e-04
+2022-05-14 12:38:44,985 INFO [train.py:812] (2/8) Epoch 12, batch 1650, loss[loss=0.1955, simple_loss=0.2865, pruned_loss=0.05223, over 7369.00 frames.], tot_loss[loss=0.1782, simple_loss=0.265, pruned_loss=0.04569, over 1426859.88 frames.], batch size: 23, lr: 6.42e-04
+2022-05-14 12:39:52,050 INFO [train.py:812] (2/8) Epoch 12, batch 1700, loss[loss=0.1772, simple_loss=0.2602, pruned_loss=0.04709, over 7217.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2657, pruned_loss=0.04539, over 1427353.57 frames.], batch size: 21, lr: 6.41e-04
+2022-05-14 12:40:51,341 INFO [train.py:812] (2/8) Epoch 12, batch 1750, loss[loss=0.1911, simple_loss=0.2754, pruned_loss=0.05341, over 7195.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2655, pruned_loss=0.0451, over 1428615.80 frames.], batch size: 26, lr: 6.41e-04
+2022-05-14 12:41:58,803 INFO [train.py:812] (2/8) Epoch 12, batch 1800, loss[loss=0.1415, simple_loss=0.2201, pruned_loss=0.03146, over 6993.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2648, pruned_loss=0.04544, over 1429582.10 frames.], batch size: 16, lr: 6.41e-04
+2022-05-14 12:43:07,997 INFO [train.py:812] (2/8) Epoch 12, batch 1850, loss[loss=0.195, simple_loss=0.2774, pruned_loss=0.05625, over 7097.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2651, pruned_loss=0.04599, over 1427295.82 frames.], batch size: 26, lr: 6.40e-04
+2022-05-14 12:44:16,798 INFO [train.py:812] (2/8) Epoch 12, batch 1900, loss[loss=0.1581, simple_loss=0.2438, pruned_loss=0.03614, over 7414.00 frames.], tot_loss[loss=0.178, simple_loss=0.2646, pruned_loss=0.04573, over 1428968.50 frames.], batch size: 20, lr: 6.40e-04
+2022-05-14 12:45:34,902 INFO [train.py:812] (2/8) Epoch 12, batch 1950, loss[loss=0.1789, simple_loss=0.2521, pruned_loss=0.05283, over 6988.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2635, pruned_loss=0.0453, over 1427987.66 frames.], batch size: 16, lr: 6.40e-04
+2022-05-14 12:46:34,649 INFO [train.py:812] (2/8) Epoch 12, batch 2000, loss[loss=0.1715, simple_loss=0.2658, pruned_loss=0.03865, over 6357.00 frames.], tot_loss[loss=0.178, simple_loss=0.2646, pruned_loss=0.04568, over 1425902.74 frames.], batch size: 38, lr: 6.39e-04
+2022-05-14 12:47:34,767 INFO [train.py:812] (2/8) Epoch 12, batch 2050, loss[loss=0.2131, simple_loss=0.2908, pruned_loss=0.06765, over 7375.00 frames.], tot_loss[loss=0.1775, simple_loss=0.264, pruned_loss=0.04557, over 1423552.18 frames.], batch size: 23, lr: 6.39e-04
+2022-05-14 12:48:34,250 INFO [train.py:812] (2/8) Epoch 12, batch 2100, loss[loss=0.1771, simple_loss=0.2717, pruned_loss=0.04129, over 6963.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2633, pruned_loss=0.04525, over 1427892.46 frames.], batch size: 32, lr: 6.39e-04
+2022-05-14 12:49:34,280 INFO [train.py:812] (2/8) Epoch 12, batch 2150, loss[loss=0.1537, simple_loss=0.2396, pruned_loss=0.03392, over 7258.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2635, pruned_loss=0.04567, over 1423329.97 frames.], batch size: 16, lr: 6.38e-04
+2022-05-14 12:50:33,510 INFO [train.py:812] (2/8) Epoch 12, batch 2200, loss[loss=0.1835, simple_loss=0.2685, pruned_loss=0.04928, over 7431.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2637, pruned_loss=0.04592, over 1427251.25 frames.], batch size: 20, lr: 6.38e-04
+2022-05-14 12:51:31,625 INFO [train.py:812] (2/8) Epoch 12, batch 2250, loss[loss=0.2008, simple_loss=0.2861, pruned_loss=0.0577, over 7121.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2633, pruned_loss=0.04548, over 1425652.11 frames.], batch size: 17, lr: 6.38e-04
+2022-05-14 12:52:29,476 INFO [train.py:812] (2/8) Epoch 12, batch 2300, loss[loss=0.1692, simple_loss=0.2615, pruned_loss=0.03842, over 7361.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2646, pruned_loss=0.04595, over 1423865.87 frames.], batch size: 19, lr: 6.38e-04
+2022-05-14 12:53:28,557 INFO [train.py:812] (2/8) Epoch 12, batch 2350, loss[loss=0.2091, simple_loss=0.2906, pruned_loss=0.06373, over 7296.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2641, pruned_loss=0.04575, over 1426139.00 frames.], batch size: 24, lr: 6.37e-04
+2022-05-14 12:54:27,659 INFO [train.py:812] (2/8) Epoch 12, batch 2400, loss[loss=0.1875, simple_loss=0.2713, pruned_loss=0.05187, over 7109.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2653, pruned_loss=0.04606, over 1428380.13 frames.], batch size: 21, lr: 6.37e-04
+2022-05-14 12:55:26,371 INFO [train.py:812] (2/8) Epoch 12, batch 2450, loss[loss=0.1571, simple_loss=0.2487, pruned_loss=0.03274, over 7233.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2656, pruned_loss=0.04589, over 1426148.43 frames.], batch size: 20, lr: 6.37e-04
+2022-05-14 12:56:25,360 INFO [train.py:812] (2/8) Epoch 12, batch 2500, loss[loss=0.203, simple_loss=0.2745, pruned_loss=0.0657, over 7073.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2647, pruned_loss=0.04557, over 1425187.21 frames.], batch size: 18, lr: 6.36e-04
+2022-05-14 12:57:24,978 INFO [train.py:812] (2/8) Epoch 12, batch 2550, loss[loss=0.1832, simple_loss=0.2625, pruned_loss=0.05197, over 7294.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2653, pruned_loss=0.0455, over 1427722.00 frames.], batch size: 17, lr: 6.36e-04
+2022-05-14 12:58:23,567 INFO [train.py:812] (2/8) Epoch 12, batch 2600, loss[loss=0.2166, simple_loss=0.3096, pruned_loss=0.06177, over 7284.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2653, pruned_loss=0.04575, over 1422859.81 frames.], batch size: 24, lr: 6.36e-04
+2022-05-14 12:59:22,539 INFO [train.py:812] (2/8) Epoch 12, batch 2650, loss[loss=0.1631, simple_loss=0.2494, pruned_loss=0.03836, over 7255.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2658, pruned_loss=0.04618, over 1419194.24 frames.], batch size: 19, lr: 6.36e-04
+2022-05-14 13:00:21,717 INFO [train.py:812] (2/8) Epoch 12, batch 2700, loss[loss=0.1924, simple_loss=0.2817, pruned_loss=0.0515, over 7304.00 frames.], tot_loss[loss=0.179, simple_loss=0.2655, pruned_loss=0.04623, over 1422702.36 frames.], batch size: 25, lr: 6.35e-04
+2022-05-14 13:01:21,381 INFO [train.py:812] (2/8) Epoch 12, batch 2750, loss[loss=0.1685, simple_loss=0.2582, pruned_loss=0.03942, over 7438.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2645, pruned_loss=0.04563, over 1425252.54 frames.], batch size: 20, lr: 6.35e-04
+2022-05-14 13:02:20,489 INFO [train.py:812] (2/8) Epoch 12, batch 2800, loss[loss=0.1684, simple_loss=0.267, pruned_loss=0.03489, over 7121.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2645, pruned_loss=0.04533, over 1426258.73 frames.], batch size: 21, lr: 6.35e-04
+2022-05-14 13:03:19,878 INFO [train.py:812] (2/8) Epoch 12, batch 2850, loss[loss=0.188, simple_loss=0.2878, pruned_loss=0.04411, over 7316.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2643, pruned_loss=0.04553, over 1428488.16 frames.], batch size: 21, lr: 6.34e-04
+2022-05-14 13:04:18,949 INFO [train.py:812] (2/8) Epoch 12, batch 2900, loss[loss=0.199, simple_loss=0.277, pruned_loss=0.06049, over 7293.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2656, pruned_loss=0.04615, over 1424167.89 frames.], batch size: 24, lr: 6.34e-04
+2022-05-14 13:05:18,612 INFO [train.py:812] (2/8) Epoch 12, batch 2950, loss[loss=0.1715, simple_loss=0.2645, pruned_loss=0.03927, over 7221.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2652, pruned_loss=0.04584, over 1419744.37 frames.], batch size: 21, lr: 6.34e-04
+2022-05-14 13:06:17,598 INFO [train.py:812] (2/8) Epoch 12, batch 3000, loss[loss=0.2016, simple_loss=0.295, pruned_loss=0.05407, over 7249.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2656, pruned_loss=0.04581, over 1421532.68 frames.], batch size: 25, lr: 6.33e-04
+2022-05-14 13:06:17,599 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 13:06:26,032 INFO [train.py:841] (2/8) Epoch 12, validation: loss=0.1553, simple_loss=0.2571, pruned_loss=0.02678, over 698248.00 frames.
+2022-05-14 13:07:25,233 INFO [train.py:812] (2/8) Epoch 12, batch 3050, loss[loss=0.1997, simple_loss=0.282, pruned_loss=0.05867, over 7381.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2665, pruned_loss=0.04619, over 1420066.32 frames.], batch size: 23, lr: 6.33e-04
+2022-05-14 13:08:24,598 INFO [train.py:812] (2/8) Epoch 12, batch 3100, loss[loss=0.2154, simple_loss=0.2962, pruned_loss=0.06729, over 7328.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2645, pruned_loss=0.04525, over 1422378.44 frames.], batch size: 20, lr: 6.33e-04
+2022-05-14 13:09:23,971 INFO [train.py:812] (2/8) Epoch 12, batch 3150, loss[loss=0.1831, simple_loss=0.2736, pruned_loss=0.0463, over 7379.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2637, pruned_loss=0.04479, over 1423914.85 frames.], batch size: 23, lr: 6.33e-04
+2022-05-14 13:10:22,789 INFO [train.py:812] (2/8) Epoch 12, batch 3200, loss[loss=0.1841, simple_loss=0.2708, pruned_loss=0.04871, over 7112.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2641, pruned_loss=0.04517, over 1423718.14 frames.], batch size: 21, lr: 6.32e-04
+2022-05-14 13:11:22,011 INFO [train.py:812] (2/8) Epoch 12, batch 3250, loss[loss=0.1859, simple_loss=0.2866, pruned_loss=0.04263, over 7407.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2646, pruned_loss=0.04519, over 1425201.48 frames.], batch size: 21, lr: 6.32e-04
+2022-05-14 13:12:21,124 INFO [train.py:812] (2/8) Epoch 12, batch 3300, loss[loss=0.1804, simple_loss=0.2557, pruned_loss=0.05257, over 6995.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2654, pruned_loss=0.04546, over 1425960.64 frames.], batch size: 16, lr: 6.32e-04
+2022-05-14 13:13:18,551 INFO [train.py:812] (2/8) Epoch 12, batch 3350, loss[loss=0.1654, simple_loss=0.239, pruned_loss=0.04589, over 7282.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2652, pruned_loss=0.04567, over 1426389.61 frames.], batch size: 18, lr: 6.31e-04
+2022-05-14 13:14:17,040 INFO [train.py:812] (2/8) Epoch 12, batch 3400, loss[loss=0.2289, simple_loss=0.3009, pruned_loss=0.07848, over 6360.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2647, pruned_loss=0.04558, over 1420593.36 frames.], batch size: 38, lr: 6.31e-04
+2022-05-14 13:15:16,594 INFO [train.py:812] (2/8) Epoch 12, batch 3450, loss[loss=0.1687, simple_loss=0.263, pruned_loss=0.03723, over 7125.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2643, pruned_loss=0.04542, over 1418784.48 frames.], batch size: 21, lr: 6.31e-04
+2022-05-14 13:16:15,022 INFO [train.py:812] (2/8) Epoch 12, batch 3500, loss[loss=0.1627, simple_loss=0.2554, pruned_loss=0.035, over 7322.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2645, pruned_loss=0.04538, over 1424715.93 frames.], batch size: 21, lr: 6.31e-04
+2022-05-14 13:17:13,776 INFO [train.py:812] (2/8) Epoch 12, batch 3550, loss[loss=0.1523, simple_loss=0.2361, pruned_loss=0.03424, over 7015.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2643, pruned_loss=0.04509, over 1423361.88 frames.], batch size: 16, lr: 6.30e-04
+2022-05-14 13:18:12,626 INFO [train.py:812] (2/8) Epoch 12, batch 3600, loss[loss=0.1794, simple_loss=0.2755, pruned_loss=0.04158, over 7242.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2644, pruned_loss=0.04486, over 1425781.87 frames.], batch size: 20, lr: 6.30e-04
+2022-05-14 13:19:11,478 INFO [train.py:812] (2/8) Epoch 12, batch 3650, loss[loss=0.177, simple_loss=0.2749, pruned_loss=0.03958, over 7424.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2643, pruned_loss=0.04438, over 1424726.49 frames.], batch size: 20, lr: 6.30e-04
+2022-05-14 13:20:08,352 INFO [train.py:812] (2/8) Epoch 12, batch 3700, loss[loss=0.186, simple_loss=0.2825, pruned_loss=0.04471, over 6807.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2641, pruned_loss=0.04463, over 1421924.15 frames.], batch size: 31, lr: 6.29e-04
+2022-05-14 13:21:06,288 INFO [train.py:812] (2/8) Epoch 12, batch 3750, loss[loss=0.2128, simple_loss=0.3018, pruned_loss=0.06191, over 7373.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2643, pruned_loss=0.04456, over 1425980.76 frames.], batch size: 23, lr: 6.29e-04
+2022-05-14 13:22:05,728 INFO [train.py:812] (2/8) Epoch 12, batch 3800, loss[loss=0.184, simple_loss=0.274, pruned_loss=0.04699, over 7190.00 frames.], tot_loss[loss=0.1765, simple_loss=0.264, pruned_loss=0.04453, over 1429244.46 frames.], batch size: 26, lr: 6.29e-04
+2022-05-14 13:23:04,609 INFO [train.py:812] (2/8) Epoch 12, batch 3850, loss[loss=0.178, simple_loss=0.275, pruned_loss=0.04057, over 7124.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2638, pruned_loss=0.04464, over 1429129.56 frames.], batch size: 21, lr: 6.29e-04
+2022-05-14 13:24:03,606 INFO [train.py:812] (2/8) Epoch 12, batch 3900, loss[loss=0.1738, simple_loss=0.2595, pruned_loss=0.04401, over 7419.00 frames.], tot_loss[loss=0.1768, simple_loss=0.264, pruned_loss=0.04482, over 1429858.16 frames.], batch size: 20, lr: 6.28e-04
+2022-05-14 13:25:02,860 INFO [train.py:812] (2/8) Epoch 12, batch 3950, loss[loss=0.1722, simple_loss=0.2695, pruned_loss=0.03746, over 7228.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2634, pruned_loss=0.04484, over 1431662.26 frames.], batch size: 20, lr: 6.28e-04
+2022-05-14 13:26:01,808 INFO [train.py:812] (2/8) Epoch 12, batch 4000, loss[loss=0.172, simple_loss=0.2665, pruned_loss=0.03878, over 7411.00 frames.], tot_loss[loss=0.178, simple_loss=0.2647, pruned_loss=0.04568, over 1426471.88 frames.], batch size: 21, lr: 6.28e-04
+2022-05-14 13:27:01,300 INFO [train.py:812] (2/8) Epoch 12, batch 4050, loss[loss=0.1534, simple_loss=0.2519, pruned_loss=0.02745, over 7438.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2649, pruned_loss=0.04562, over 1424726.08 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:28:00,460 INFO [train.py:812] (2/8) Epoch 12, batch 4100, loss[loss=0.1848, simple_loss=0.2704, pruned_loss=0.04957, over 7329.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2653, pruned_loss=0.04591, over 1421308.08 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:28:59,925 INFO [train.py:812] (2/8) Epoch 12, batch 4150, loss[loss=0.1782, simple_loss=0.2639, pruned_loss=0.04622, over 7243.00 frames.], tot_loss[loss=0.178, simple_loss=0.2651, pruned_loss=0.04543, over 1422510.82 frames.], batch size: 20, lr: 6.27e-04
+2022-05-14 13:29:59,350 INFO [train.py:812] (2/8) Epoch 12, batch 4200, loss[loss=0.1936, simple_loss=0.2741, pruned_loss=0.05655, over 7327.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2661, pruned_loss=0.04551, over 1421418.34 frames.], batch size: 22, lr: 6.27e-04
+2022-05-14 13:30:59,182 INFO [train.py:812] (2/8) Epoch 12, batch 4250, loss[loss=0.1505, simple_loss=0.2335, pruned_loss=0.03377, over 7414.00 frames.], tot_loss[loss=0.1777, simple_loss=0.265, pruned_loss=0.04516, over 1424082.47 frames.], batch size: 18, lr: 6.26e-04
+2022-05-14 13:31:58,553 INFO [train.py:812] (2/8) Epoch 12, batch 4300, loss[loss=0.193, simple_loss=0.2831, pruned_loss=0.05138, over 7235.00 frames.], tot_loss[loss=0.177, simple_loss=0.264, pruned_loss=0.04496, over 1417565.89 frames.], batch size: 20, lr: 6.26e-04
+2022-05-14 13:32:57,464 INFO [train.py:812] (2/8) Epoch 12, batch 4350, loss[loss=0.1894, simple_loss=0.2719, pruned_loss=0.05342, over 7203.00 frames.], tot_loss[loss=0.176, simple_loss=0.2625, pruned_loss=0.04477, over 1419692.99 frames.], batch size: 22, lr: 6.26e-04
+2022-05-14 13:33:56,601 INFO [train.py:812] (2/8) Epoch 12, batch 4400, loss[loss=0.1685, simple_loss=0.2542, pruned_loss=0.04145, over 7314.00 frames.], tot_loss[loss=0.176, simple_loss=0.2625, pruned_loss=0.04472, over 1418332.54 frames.], batch size: 21, lr: 6.25e-04
+2022-05-14 13:34:56,775 INFO [train.py:812] (2/8) Epoch 12, batch 4450, loss[loss=0.1696, simple_loss=0.2612, pruned_loss=0.03902, over 6383.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2615, pruned_loss=0.04497, over 1405853.29 frames.], batch size: 37, lr: 6.25e-04
+2022-05-14 13:35:55,753 INFO [train.py:812] (2/8) Epoch 12, batch 4500, loss[loss=0.1818, simple_loss=0.2746, pruned_loss=0.04446, over 6394.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2619, pruned_loss=0.04573, over 1388373.75 frames.], batch size: 38, lr: 6.25e-04
+2022-05-14 13:36:54,585 INFO [train.py:812] (2/8) Epoch 12, batch 4550, loss[loss=0.206, simple_loss=0.2906, pruned_loss=0.06075, over 4939.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2638, pruned_loss=0.04751, over 1350614.61 frames.], batch size: 53, lr: 6.25e-04
+2022-05-14 13:38:08,548 INFO [train.py:812] (2/8) Epoch 13, batch 0, loss[loss=0.1709, simple_loss=0.2676, pruned_loss=0.03708, over 7149.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2676, pruned_loss=0.03708, over 7149.00 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:39:08,085 INFO [train.py:812] (2/8) Epoch 13, batch 50, loss[loss=0.1853, simple_loss=0.2687, pruned_loss=0.0509, over 7235.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2607, pruned_loss=0.04412, over 319113.33 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:40:06,195 INFO [train.py:812] (2/8) Epoch 13, batch 100, loss[loss=0.1993, simple_loss=0.2813, pruned_loss=0.05862, over 7197.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2642, pruned_loss=0.04496, over 565337.07 frames.], batch size: 23, lr: 6.03e-04
+2022-05-14 13:41:05,019 INFO [train.py:812] (2/8) Epoch 13, batch 150, loss[loss=0.1681, simple_loss=0.2619, pruned_loss=0.03712, over 7140.00 frames.], tot_loss[loss=0.177, simple_loss=0.2645, pruned_loss=0.04474, over 754556.51 frames.], batch size: 20, lr: 6.03e-04
+2022-05-14 13:42:04,300 INFO [train.py:812] (2/8) Epoch 13, batch 200, loss[loss=0.1601, simple_loss=0.2492, pruned_loss=0.03545, over 7151.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2639, pruned_loss=0.04437, over 900534.17 frames.], batch size: 20, lr: 6.02e-04
+2022-05-14 13:43:03,803 INFO [train.py:812] (2/8) Epoch 13, batch 250, loss[loss=0.1483, simple_loss=0.229, pruned_loss=0.03384, over 7181.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2629, pruned_loss=0.04375, over 1014701.94 frames.], batch size: 16, lr: 6.02e-04
+2022-05-14 13:44:02,523 INFO [train.py:812] (2/8) Epoch 13, batch 300, loss[loss=0.1804, simple_loss=0.2608, pruned_loss=0.05002, over 7147.00 frames.], tot_loss[loss=0.175, simple_loss=0.2625, pruned_loss=0.04372, over 1104765.11 frames.], batch size: 20, lr: 6.02e-04
+2022-05-14 13:45:01,887 INFO [train.py:812] (2/8) Epoch 13, batch 350, loss[loss=0.1901, simple_loss=0.2817, pruned_loss=0.0492, over 7134.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2652, pruned_loss=0.04479, over 1176713.19 frames.], batch size: 28, lr: 6.01e-04
+2022-05-14 13:46:00,662 INFO [train.py:812] (2/8) Epoch 13, batch 400, loss[loss=0.1528, simple_loss=0.2413, pruned_loss=0.03214, over 7362.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2647, pruned_loss=0.04431, over 1233742.10 frames.], batch size: 19, lr: 6.01e-04
+2022-05-14 13:46:57,907 INFO [train.py:812] (2/8) Epoch 13, batch 450, loss[loss=0.1634, simple_loss=0.2603, pruned_loss=0.03326, over 7329.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2629, pruned_loss=0.04368, over 1277612.60 frames.], batch size: 21, lr: 6.01e-04
+2022-05-14 13:47:55,554 INFO [train.py:812] (2/8) Epoch 13, batch 500, loss[loss=0.164, simple_loss=0.2539, pruned_loss=0.03699, over 6398.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2615, pruned_loss=0.0434, over 1310596.69 frames.], batch size: 38, lr: 6.01e-04
+2022-05-14 13:48:55,162 INFO [train.py:812] (2/8) Epoch 13, batch 550, loss[loss=0.1897, simple_loss=0.2791, pruned_loss=0.05014, over 7366.00 frames.], tot_loss[loss=0.1748, simple_loss=0.262, pruned_loss=0.04382, over 1333037.28 frames.], batch size: 23, lr: 6.00e-04
+2022-05-14 13:49:53,967 INFO [train.py:812] (2/8) Epoch 13, batch 600, loss[loss=0.1549, simple_loss=0.227, pruned_loss=0.04139, over 6780.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2615, pruned_loss=0.04409, over 1346579.85 frames.], batch size: 15, lr: 6.00e-04
+2022-05-14 13:50:53,007 INFO [train.py:812] (2/8) Epoch 13, batch 650, loss[loss=0.1725, simple_loss=0.2515, pruned_loss=0.0467, over 7269.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2625, pruned_loss=0.044, over 1366613.08 frames.], batch size: 18, lr: 6.00e-04
+2022-05-14 13:51:52,326 INFO [train.py:812] (2/8) Epoch 13, batch 700, loss[loss=0.1837, simple_loss=0.2601, pruned_loss=0.05361, over 7242.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2626, pruned_loss=0.04388, over 1384606.30 frames.], batch size: 16, lr: 6.00e-04
+2022-05-14 13:52:51,779 INFO [train.py:812] (2/8) Epoch 13, batch 750, loss[loss=0.1994, simple_loss=0.2898, pruned_loss=0.0545, over 7206.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2624, pruned_loss=0.04333, over 1396350.99 frames.], batch size: 23, lr: 5.99e-04
+2022-05-14 13:53:50,413 INFO [train.py:812] (2/8) Epoch 13, batch 800, loss[loss=0.1905, simple_loss=0.2825, pruned_loss=0.04924, over 7211.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2625, pruned_loss=0.04369, over 1406122.38 frames.], batch size: 22, lr: 5.99e-04
+2022-05-14 13:54:49,276 INFO [train.py:812] (2/8) Epoch 13, batch 850, loss[loss=0.1582, simple_loss=0.2433, pruned_loss=0.03657, over 7139.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2628, pruned_loss=0.04373, over 1411769.88 frames.], batch size: 17, lr: 5.99e-04
+2022-05-14 13:55:48,205 INFO [train.py:812] (2/8) Epoch 13, batch 900, loss[loss=0.1688, simple_loss=0.264, pruned_loss=0.03677, over 7322.00 frames.], tot_loss[loss=0.174, simple_loss=0.2619, pruned_loss=0.04309, over 1414974.82 frames.], batch size: 20, lr: 5.99e-04
+2022-05-14 13:56:52,996 INFO [train.py:812] (2/8) Epoch 13, batch 950, loss[loss=0.1949, simple_loss=0.2805, pruned_loss=0.05464, over 7190.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2622, pruned_loss=0.04337, over 1415236.26 frames.], batch size: 26, lr: 5.98e-04
+2022-05-14 13:57:52,237 INFO [train.py:812] (2/8) Epoch 13, batch 1000, loss[loss=0.2084, simple_loss=0.29, pruned_loss=0.06338, over 6322.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2628, pruned_loss=0.04372, over 1415066.23 frames.], batch size: 37, lr: 5.98e-04
+2022-05-14 13:58:51,876 INFO [train.py:812] (2/8) Epoch 13, batch 1050, loss[loss=0.1511, simple_loss=0.2415, pruned_loss=0.03031, over 7259.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2616, pruned_loss=0.04329, over 1417206.73 frames.], batch size: 19, lr: 5.98e-04
+2022-05-14 13:59:49,695 INFO [train.py:812] (2/8) Epoch 13, batch 1100, loss[loss=0.1691, simple_loss=0.2691, pruned_loss=0.03458, over 7373.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2624, pruned_loss=0.04369, over 1422628.45 frames.], batch size: 23, lr: 5.97e-04
+2022-05-14 14:00:49,269 INFO [train.py:812] (2/8) Epoch 13, batch 1150, loss[loss=0.1658, simple_loss=0.2582, pruned_loss=0.03669, over 7320.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2618, pruned_loss=0.04337, over 1425134.26 frames.], batch size: 20, lr: 5.97e-04
+2022-05-14 14:01:48,649 INFO [train.py:812] (2/8) Epoch 13, batch 1200, loss[loss=0.1764, simple_loss=0.2591, pruned_loss=0.04688, over 4734.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2619, pruned_loss=0.04344, over 1421889.54 frames.], batch size: 52, lr: 5.97e-04
+2022-05-14 14:02:48,269 INFO [train.py:812] (2/8) Epoch 13, batch 1250, loss[loss=0.173, simple_loss=0.2657, pruned_loss=0.04015, over 7152.00 frames.], tot_loss[loss=0.175, simple_loss=0.2623, pruned_loss=0.04381, over 1419213.19 frames.], batch size: 19, lr: 5.97e-04
+2022-05-14 14:03:47,345 INFO [train.py:812] (2/8) Epoch 13, batch 1300, loss[loss=0.186, simple_loss=0.2697, pruned_loss=0.05115, over 7056.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2618, pruned_loss=0.04375, over 1419998.70 frames.], batch size: 18, lr: 5.96e-04
+2022-05-14 14:04:46,575 INFO [train.py:812] (2/8) Epoch 13, batch 1350, loss[loss=0.1992, simple_loss=0.2804, pruned_loss=0.05904, over 5211.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2627, pruned_loss=0.04433, over 1417161.78 frames.], batch size: 52, lr: 5.96e-04
+2022-05-14 14:05:45,496 INFO [train.py:812] (2/8) Epoch 13, batch 1400, loss[loss=0.1644, simple_loss=0.2664, pruned_loss=0.03117, over 7280.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2638, pruned_loss=0.04475, over 1416312.37 frames.], batch size: 25, lr: 5.96e-04
+2022-05-14 14:06:43,976 INFO [train.py:812] (2/8) Epoch 13, batch 1450, loss[loss=0.1769, simple_loss=0.2743, pruned_loss=0.03973, over 7320.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2633, pruned_loss=0.04414, over 1414402.67 frames.], batch size: 21, lr: 5.96e-04
+2022-05-14 14:07:42,553 INFO [train.py:812] (2/8) Epoch 13, batch 1500, loss[loss=0.1871, simple_loss=0.2766, pruned_loss=0.0488, over 7212.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2632, pruned_loss=0.04392, over 1418040.78 frames.], batch size: 23, lr: 5.95e-04
+2022-05-14 14:08:42,624 INFO [train.py:812] (2/8) Epoch 13, batch 1550, loss[loss=0.1995, simple_loss=0.2964, pruned_loss=0.05127, over 7052.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2636, pruned_loss=0.04407, over 1419635.88 frames.], batch size: 28, lr: 5.95e-04
+2022-05-14 14:09:41,283 INFO [train.py:812] (2/8) Epoch 13, batch 1600, loss[loss=0.1782, simple_loss=0.2721, pruned_loss=0.04212, over 7304.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2639, pruned_loss=0.04434, over 1419593.68 frames.], batch size: 25, lr: 5.95e-04
+2022-05-14 14:10:39,356 INFO [train.py:812] (2/8) Epoch 13, batch 1650, loss[loss=0.2035, simple_loss=0.2885, pruned_loss=0.05925, over 7266.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2633, pruned_loss=0.04444, over 1422376.99 frames.], batch size: 24, lr: 5.95e-04
+2022-05-14 14:11:36,464 INFO [train.py:812] (2/8) Epoch 13, batch 1700, loss[loss=0.1486, simple_loss=0.2405, pruned_loss=0.02836, over 7145.00 frames.], tot_loss[loss=0.176, simple_loss=0.2631, pruned_loss=0.04444, over 1418513.10 frames.], batch size: 17, lr: 5.94e-04
+2022-05-14 14:12:34,777 INFO [train.py:812] (2/8) Epoch 13, batch 1750, loss[loss=0.1893, simple_loss=0.2688, pruned_loss=0.0549, over 7154.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2621, pruned_loss=0.04414, over 1421316.87 frames.], batch size: 26, lr: 5.94e-04
+2022-05-14 14:13:34,197 INFO [train.py:812] (2/8) Epoch 13, batch 1800, loss[loss=0.1527, simple_loss=0.2359, pruned_loss=0.03477, over 6993.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2635, pruned_loss=0.04458, over 1427216.23 frames.], batch size: 16, lr: 5.94e-04
+2022-05-14 14:14:33,812 INFO [train.py:812] (2/8) Epoch 13, batch 1850, loss[loss=0.1934, simple_loss=0.2909, pruned_loss=0.04798, over 7333.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2631, pruned_loss=0.04403, over 1427685.71 frames.], batch size: 22, lr: 5.94e-04
+2022-05-14 14:15:33,272 INFO [train.py:812] (2/8) Epoch 13, batch 1900, loss[loss=0.1704, simple_loss=0.2553, pruned_loss=0.04279, over 7227.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2628, pruned_loss=0.0441, over 1428360.25 frames.], batch size: 20, lr: 5.93e-04
+2022-05-14 14:16:32,248 INFO [train.py:812] (2/8) Epoch 13, batch 1950, loss[loss=0.1403, simple_loss=0.2215, pruned_loss=0.02955, over 7263.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2621, pruned_loss=0.04363, over 1428489.96 frames.], batch size: 17, lr: 5.93e-04
+2022-05-14 14:17:31,555 INFO [train.py:812] (2/8) Epoch 13, batch 2000, loss[loss=0.1566, simple_loss=0.2354, pruned_loss=0.0389, over 7402.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2612, pruned_loss=0.0433, over 1428732.16 frames.], batch size: 17, lr: 5.93e-04
+2022-05-14 14:18:40,079 INFO [train.py:812] (2/8) Epoch 13, batch 2050, loss[loss=0.1497, simple_loss=0.239, pruned_loss=0.03017, over 7153.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2612, pruned_loss=0.04354, over 1422013.54 frames.], batch size: 19, lr: 5.93e-04
+2022-05-14 14:19:39,663 INFO [train.py:812] (2/8) Epoch 13, batch 2100, loss[loss=0.1789, simple_loss=0.2632, pruned_loss=0.04734, over 7151.00 frames.], tot_loss[loss=0.1748, simple_loss=0.262, pruned_loss=0.04381, over 1421980.67 frames.], batch size: 19, lr: 5.92e-04
+2022-05-14 14:20:39,440 INFO [train.py:812] (2/8) Epoch 13, batch 2150, loss[loss=0.1395, simple_loss=0.2248, pruned_loss=0.02708, over 7278.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2619, pruned_loss=0.0435, over 1422981.58 frames.], batch size: 18, lr: 5.92e-04
+2022-05-14 14:21:36,905 INFO [train.py:812] (2/8) Epoch 13, batch 2200, loss[loss=0.1811, simple_loss=0.2695, pruned_loss=0.04637, over 7328.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2617, pruned_loss=0.0433, over 1423314.81 frames.], batch size: 20, lr: 5.92e-04
+2022-05-14 14:22:35,523 INFO [train.py:812] (2/8) Epoch 13, batch 2250, loss[loss=0.1808, simple_loss=0.2806, pruned_loss=0.04051, over 7052.00 frames.], tot_loss[loss=0.174, simple_loss=0.2615, pruned_loss=0.04328, over 1421698.39 frames.], batch size: 28, lr: 5.91e-04
+2022-05-14 14:23:34,266 INFO [train.py:812] (2/8) Epoch 13, batch 2300, loss[loss=0.1703, simple_loss=0.2632, pruned_loss=0.0387, over 7117.00 frames.], tot_loss[loss=0.174, simple_loss=0.2617, pruned_loss=0.04319, over 1425222.70 frames.], batch size: 21, lr: 5.91e-04
+2022-05-14 14:24:34,072 INFO [train.py:812] (2/8) Epoch 13, batch 2350, loss[loss=0.1768, simple_loss=0.2638, pruned_loss=0.04492, over 7152.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2621, pruned_loss=0.04343, over 1426270.59 frames.], batch size: 19, lr: 5.91e-04
+2022-05-14 14:25:33,554 INFO [train.py:812] (2/8) Epoch 13, batch 2400, loss[loss=0.1479, simple_loss=0.2327, pruned_loss=0.03149, over 7165.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2619, pruned_loss=0.04288, over 1427291.93 frames.], batch size: 17, lr: 5.91e-04
+2022-05-14 14:26:31,980 INFO [train.py:812] (2/8) Epoch 13, batch 2450, loss[loss=0.1653, simple_loss=0.2574, pruned_loss=0.03664, over 7211.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2619, pruned_loss=0.04301, over 1425927.11 frames.], batch size: 21, lr: 5.90e-04
+2022-05-14 14:27:30,759 INFO [train.py:812] (2/8) Epoch 13, batch 2500, loss[loss=0.1647, simple_loss=0.2464, pruned_loss=0.04153, over 7272.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2625, pruned_loss=0.04348, over 1426580.25 frames.], batch size: 18, lr: 5.90e-04
+2022-05-14 14:28:30,428 INFO [train.py:812] (2/8) Epoch 13, batch 2550, loss[loss=0.1486, simple_loss=0.2308, pruned_loss=0.0332, over 7237.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2624, pruned_loss=0.04336, over 1428066.99 frames.], batch size: 16, lr: 5.90e-04
+2022-05-14 14:29:29,643 INFO [train.py:812] (2/8) Epoch 13, batch 2600, loss[loss=0.1885, simple_loss=0.2677, pruned_loss=0.05465, over 7214.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2623, pruned_loss=0.04373, over 1424209.01 frames.], batch size: 16, lr: 5.90e-04
+2022-05-14 14:30:29,025 INFO [train.py:812] (2/8) Epoch 13, batch 2650, loss[loss=0.1775, simple_loss=0.2471, pruned_loss=0.05395, over 7003.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2622, pruned_loss=0.04373, over 1422809.98 frames.], batch size: 16, lr: 5.89e-04
+2022-05-14 14:31:27,709 INFO [train.py:812] (2/8) Epoch 13, batch 2700, loss[loss=0.1502, simple_loss=0.2286, pruned_loss=0.03588, over 6995.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2612, pruned_loss=0.04325, over 1423973.93 frames.], batch size: 16, lr: 5.89e-04
+2022-05-14 14:32:27,068 INFO [train.py:812] (2/8) Epoch 13, batch 2750, loss[loss=0.2105, simple_loss=0.3013, pruned_loss=0.05988, over 7108.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2618, pruned_loss=0.04376, over 1421937.58 frames.], batch size: 21, lr: 5.89e-04
+2022-05-14 14:33:24,880 INFO [train.py:812] (2/8) Epoch 13, batch 2800, loss[loss=0.1585, simple_loss=0.2387, pruned_loss=0.03921, over 7140.00 frames.], tot_loss[loss=0.175, simple_loss=0.2624, pruned_loss=0.04381, over 1422305.94 frames.], batch size: 17, lr: 5.89e-04
+2022-05-14 14:34:24,909 INFO [train.py:812] (2/8) Epoch 13, batch 2850, loss[loss=0.1672, simple_loss=0.2531, pruned_loss=0.04061, over 7386.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2627, pruned_loss=0.04397, over 1428237.98 frames.], batch size: 23, lr: 5.88e-04
+2022-05-14 14:35:22,595 INFO [train.py:812] (2/8) Epoch 13, batch 2900, loss[loss=0.145, simple_loss=0.2377, pruned_loss=0.02617, over 7352.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2639, pruned_loss=0.04428, over 1425503.67 frames.], batch size: 19, lr: 5.88e-04
+2022-05-14 14:36:21,968 INFO [train.py:812] (2/8) Epoch 13, batch 2950, loss[loss=0.1661, simple_loss=0.2586, pruned_loss=0.03678, over 7113.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2629, pruned_loss=0.04406, over 1427186.87 frames.], batch size: 21, lr: 5.88e-04
+2022-05-14 14:37:20,733 INFO [train.py:812] (2/8) Epoch 13, batch 3000, loss[loss=0.1431, simple_loss=0.2217, pruned_loss=0.03223, over 7282.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2627, pruned_loss=0.04377, over 1427823.43 frames.], batch size: 17, lr: 5.88e-04
+2022-05-14 14:37:20,734 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 14:37:28,226 INFO [train.py:841] (2/8) Epoch 13, validation: loss=0.1549, simple_loss=0.2559, pruned_loss=0.02694, over 698248.00 frames.
+2022-05-14 14:38:28,321 INFO [train.py:812] (2/8) Epoch 13, batch 3050, loss[loss=0.1602, simple_loss=0.241, pruned_loss=0.0397, over 7138.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2623, pruned_loss=0.04366, over 1428154.87 frames.], batch size: 17, lr: 5.87e-04
+2022-05-14 14:39:27,851 INFO [train.py:812] (2/8) Epoch 13, batch 3100, loss[loss=0.1845, simple_loss=0.2659, pruned_loss=0.0515, over 7118.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2616, pruned_loss=0.0437, over 1427665.20 frames.], batch size: 21, lr: 5.87e-04
+2022-05-14 14:40:36,451 INFO [train.py:812] (2/8) Epoch 13, batch 3150, loss[loss=0.1677, simple_loss=0.2564, pruned_loss=0.0395, over 7307.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2627, pruned_loss=0.04398, over 1425103.30 frames.], batch size: 25, lr: 5.87e-04
+2022-05-14 14:41:35,464 INFO [train.py:812] (2/8) Epoch 13, batch 3200, loss[loss=0.227, simple_loss=0.2989, pruned_loss=0.07755, over 5092.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2635, pruned_loss=0.04415, over 1426342.39 frames.], batch size: 52, lr: 5.87e-04
+2022-05-14 14:42:44,570 INFO [train.py:812] (2/8) Epoch 13, batch 3250, loss[loss=0.1702, simple_loss=0.2307, pruned_loss=0.05481, over 7263.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2626, pruned_loss=0.04385, over 1428325.22 frames.], batch size: 17, lr: 5.86e-04
+2022-05-14 14:43:53,101 INFO [train.py:812] (2/8) Epoch 13, batch 3300, loss[loss=0.178, simple_loss=0.2625, pruned_loss=0.04677, over 7322.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2618, pruned_loss=0.04343, over 1428128.70 frames.], batch size: 20, lr: 5.86e-04
+2022-05-14 14:44:51,614 INFO [train.py:812] (2/8) Epoch 13, batch 3350, loss[loss=0.1494, simple_loss=0.2231, pruned_loss=0.0378, over 7429.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2619, pruned_loss=0.04384, over 1421078.29 frames.], batch size: 17, lr: 5.86e-04
+2022-05-14 14:46:18,923 INFO [train.py:812] (2/8) Epoch 13, batch 3400, loss[loss=0.1969, simple_loss=0.2895, pruned_loss=0.05213, over 7380.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2625, pruned_loss=0.04417, over 1424636.80 frames.], batch size: 23, lr: 5.86e-04
+2022-05-14 14:47:27,732 INFO [train.py:812] (2/8) Epoch 13, batch 3450, loss[loss=0.1383, simple_loss=0.2236, pruned_loss=0.02649, over 7419.00 frames.], tot_loss[loss=0.1761, simple_loss=0.263, pruned_loss=0.04458, over 1413793.92 frames.], batch size: 18, lr: 5.85e-04
+2022-05-14 14:48:26,518 INFO [train.py:812] (2/8) Epoch 13, batch 3500, loss[loss=0.1794, simple_loss=0.2771, pruned_loss=0.04084, over 6982.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2636, pruned_loss=0.04499, over 1416553.39 frames.], batch size: 32, lr: 5.85e-04
+2022-05-14 14:49:26,047 INFO [train.py:812] (2/8) Epoch 13, batch 3550, loss[loss=0.1554, simple_loss=0.2373, pruned_loss=0.03678, over 6981.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2637, pruned_loss=0.04502, over 1421849.95 frames.], batch size: 16, lr: 5.85e-04
+2022-05-14 14:50:24,014 INFO [train.py:812] (2/8) Epoch 13, batch 3600, loss[loss=0.1633, simple_loss=0.2407, pruned_loss=0.04301, over 7283.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2626, pruned_loss=0.04424, over 1421205.82 frames.], batch size: 18, lr: 5.85e-04
+2022-05-14 14:51:22,136 INFO [train.py:812] (2/8) Epoch 13, batch 3650, loss[loss=0.1751, simple_loss=0.2634, pruned_loss=0.04339, over 7421.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2638, pruned_loss=0.04473, over 1423902.38 frames.], batch size: 21, lr: 5.84e-04
+2022-05-14 14:52:20,923 INFO [train.py:812] (2/8) Epoch 13, batch 3700, loss[loss=0.161, simple_loss=0.2486, pruned_loss=0.03667, over 7247.00 frames.], tot_loss[loss=0.1761, simple_loss=0.263, pruned_loss=0.04466, over 1424734.87 frames.], batch size: 19, lr: 5.84e-04
+2022-05-14 14:53:20,281 INFO [train.py:812] (2/8) Epoch 13, batch 3750, loss[loss=0.1916, simple_loss=0.2904, pruned_loss=0.04641, over 7414.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2627, pruned_loss=0.04408, over 1425466.42 frames.], batch size: 21, lr: 5.84e-04
+2022-05-14 14:54:19,189 INFO [train.py:812] (2/8) Epoch 13, batch 3800, loss[loss=0.1794, simple_loss=0.267, pruned_loss=0.04587, over 7046.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2634, pruned_loss=0.04446, over 1429779.15 frames.], batch size: 28, lr: 5.84e-04
+2022-05-14 14:55:18,441 INFO [train.py:812] (2/8) Epoch 13, batch 3850, loss[loss=0.1877, simple_loss=0.2759, pruned_loss=0.04976, over 7198.00 frames.], tot_loss[loss=0.1766, simple_loss=0.264, pruned_loss=0.04466, over 1427220.31 frames.], batch size: 22, lr: 5.83e-04
+2022-05-14 14:56:16,999 INFO [train.py:812] (2/8) Epoch 13, batch 3900, loss[loss=0.2013, simple_loss=0.2972, pruned_loss=0.05269, over 7278.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2638, pruned_loss=0.04472, over 1425418.71 frames.], batch size: 24, lr: 5.83e-04
+2022-05-14 14:57:16,822 INFO [train.py:812] (2/8) Epoch 13, batch 3950, loss[loss=0.1763, simple_loss=0.2684, pruned_loss=0.04213, over 7205.00 frames.], tot_loss[loss=0.1755, simple_loss=0.263, pruned_loss=0.04396, over 1424670.70 frames.], batch size: 23, lr: 5.83e-04
+2022-05-14 14:58:15,081 INFO [train.py:812] (2/8) Epoch 13, batch 4000, loss[loss=0.1394, simple_loss=0.2179, pruned_loss=0.0305, over 7134.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2629, pruned_loss=0.04396, over 1424086.76 frames.], batch size: 17, lr: 5.83e-04
+2022-05-14 14:59:14,567 INFO [train.py:812] (2/8) Epoch 13, batch 4050, loss[loss=0.1774, simple_loss=0.2811, pruned_loss=0.03692, over 7242.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2623, pruned_loss=0.04359, over 1425428.38 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:00:14,085 INFO [train.py:812] (2/8) Epoch 13, batch 4100, loss[loss=0.1939, simple_loss=0.2902, pruned_loss=0.04881, over 7150.00 frames.], tot_loss[loss=0.174, simple_loss=0.261, pruned_loss=0.04348, over 1425162.29 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:01:13,337 INFO [train.py:812] (2/8) Epoch 13, batch 4150, loss[loss=0.1731, simple_loss=0.2599, pruned_loss=0.0431, over 7443.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2621, pruned_loss=0.04415, over 1419498.25 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:02:11,346 INFO [train.py:812] (2/8) Epoch 13, batch 4200, loss[loss=0.1757, simple_loss=0.2624, pruned_loss=0.04449, over 7143.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2612, pruned_loss=0.04367, over 1422237.90 frames.], batch size: 20, lr: 5.82e-04
+2022-05-14 15:03:10,126 INFO [train.py:812] (2/8) Epoch 13, batch 4250, loss[loss=0.1902, simple_loss=0.2809, pruned_loss=0.0497, over 7209.00 frames.], tot_loss[loss=0.174, simple_loss=0.2609, pruned_loss=0.04357, over 1419563.09 frames.], batch size: 26, lr: 5.81e-04
+2022-05-14 15:04:08,194 INFO [train.py:812] (2/8) Epoch 13, batch 4300, loss[loss=0.1564, simple_loss=0.2388, pruned_loss=0.03703, over 7442.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2621, pruned_loss=0.04421, over 1417489.24 frames.], batch size: 20, lr: 5.81e-04
+2022-05-14 15:05:06,835 INFO [train.py:812] (2/8) Epoch 13, batch 4350, loss[loss=0.1256, simple_loss=0.2096, pruned_loss=0.02082, over 7011.00 frames.], tot_loss[loss=0.175, simple_loss=0.2617, pruned_loss=0.04413, over 1411571.26 frames.], batch size: 16, lr: 5.81e-04
+2022-05-14 15:06:06,109 INFO [train.py:812] (2/8) Epoch 13, batch 4400, loss[loss=0.1989, simple_loss=0.2838, pruned_loss=0.05701, over 5108.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2607, pruned_loss=0.04389, over 1410012.42 frames.], batch size: 52, lr: 5.81e-04
+2022-05-14 15:07:04,943 INFO [train.py:812] (2/8) Epoch 13, batch 4450, loss[loss=0.2149, simple_loss=0.2985, pruned_loss=0.0656, over 7288.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2603, pruned_loss=0.04372, over 1407617.89 frames.], batch size: 24, lr: 5.81e-04
+2022-05-14 15:08:03,270 INFO [train.py:812] (2/8) Epoch 13, batch 4500, loss[loss=0.1836, simple_loss=0.2765, pruned_loss=0.0454, over 7417.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2619, pruned_loss=0.04434, over 1388241.37 frames.], batch size: 21, lr: 5.80e-04
+2022-05-14 15:09:01,520 INFO [train.py:812] (2/8) Epoch 13, batch 4550, loss[loss=0.1734, simple_loss=0.2599, pruned_loss=0.04344, over 5184.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2648, pruned_loss=0.04614, over 1354761.46 frames.], batch size: 52, lr: 5.80e-04
+2022-05-14 15:10:14,177 INFO [train.py:812] (2/8) Epoch 14, batch 0, loss[loss=0.173, simple_loss=0.2603, pruned_loss=0.04289, over 7359.00 frames.], tot_loss[loss=0.173, simple_loss=0.2603, pruned_loss=0.04289, over 7359.00 frames.], batch size: 23, lr: 5.61e-04
+2022-05-14 15:11:14,042 INFO [train.py:812] (2/8) Epoch 14, batch 50, loss[loss=0.1649, simple_loss=0.2436, pruned_loss=0.04315, over 7107.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2566, pruned_loss=0.04318, over 322232.28 frames.], batch size: 21, lr: 5.61e-04
+2022-05-14 15:12:13,812 INFO [train.py:812] (2/8) Epoch 14, batch 100, loss[loss=0.2137, simple_loss=0.305, pruned_loss=0.06123, over 7144.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2591, pruned_loss=0.0428, over 572561.33 frames.], batch size: 20, lr: 5.61e-04
+2022-05-14 15:13:13,198 INFO [train.py:812] (2/8) Epoch 14, batch 150, loss[loss=0.1656, simple_loss=0.2408, pruned_loss=0.04521, over 7024.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2591, pruned_loss=0.04188, over 763119.08 frames.], batch size: 16, lr: 5.61e-04
+2022-05-14 15:14:11,611 INFO [train.py:812] (2/8) Epoch 14, batch 200, loss[loss=0.1814, simple_loss=0.276, pruned_loss=0.04346, over 7200.00 frames.], tot_loss[loss=0.172, simple_loss=0.26, pruned_loss=0.04197, over 910467.32 frames.], batch size: 22, lr: 5.60e-04
+2022-05-14 15:15:09,283 INFO [train.py:812] (2/8) Epoch 14, batch 250, loss[loss=0.1913, simple_loss=0.2844, pruned_loss=0.0491, over 7216.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2606, pruned_loss=0.04227, over 1026607.16 frames.], batch size: 22, lr: 5.60e-04
+2022-05-14 15:16:07,597 INFO [train.py:812] (2/8) Epoch 14, batch 300, loss[loss=0.1807, simple_loss=0.264, pruned_loss=0.04874, over 7414.00 frames.], tot_loss[loss=0.1736, simple_loss=0.262, pruned_loss=0.04261, over 1112570.18 frames.], batch size: 21, lr: 5.60e-04
+2022-05-14 15:17:06,822 INFO [train.py:812] (2/8) Epoch 14, batch 350, loss[loss=0.147, simple_loss=0.2363, pruned_loss=0.02888, over 7434.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2603, pruned_loss=0.04274, over 1180874.57 frames.], batch size: 20, lr: 5.60e-04
+2022-05-14 15:18:11,781 INFO [train.py:812] (2/8) Epoch 14, batch 400, loss[loss=0.2028, simple_loss=0.2882, pruned_loss=0.05869, over 7096.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2602, pruned_loss=0.04308, over 1230502.21 frames.], batch size: 28, lr: 5.59e-04
+2022-05-14 15:19:10,165 INFO [train.py:812] (2/8) Epoch 14, batch 450, loss[loss=0.2163, simple_loss=0.304, pruned_loss=0.06431, over 6226.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2617, pruned_loss=0.04333, over 1272386.66 frames.], batch size: 38, lr: 5.59e-04
+2022-05-14 15:20:09,614 INFO [train.py:812] (2/8) Epoch 14, batch 500, loss[loss=0.1812, simple_loss=0.2691, pruned_loss=0.04661, over 7143.00 frames.], tot_loss[loss=0.174, simple_loss=0.2614, pruned_loss=0.0433, over 1300243.72 frames.], batch size: 28, lr: 5.59e-04
+2022-05-14 15:21:08,777 INFO [train.py:812] (2/8) Epoch 14, batch 550, loss[loss=0.1966, simple_loss=0.2891, pruned_loss=0.05204, over 6717.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2617, pruned_loss=0.04366, over 1326291.24 frames.], batch size: 38, lr: 5.59e-04
+2022-05-14 15:22:08,318 INFO [train.py:812] (2/8) Epoch 14, batch 600, loss[loss=0.1929, simple_loss=0.2838, pruned_loss=0.05101, over 7316.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2603, pruned_loss=0.04292, over 1348628.16 frames.], batch size: 21, lr: 5.59e-04
+2022-05-14 15:23:07,040 INFO [train.py:812] (2/8) Epoch 14, batch 650, loss[loss=0.1693, simple_loss=0.2531, pruned_loss=0.04275, over 7063.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2605, pruned_loss=0.0429, over 1360574.13 frames.], batch size: 18, lr: 5.58e-04
+2022-05-14 15:24:06,555 INFO [train.py:812] (2/8) Epoch 14, batch 700, loss[loss=0.1507, simple_loss=0.2298, pruned_loss=0.03578, over 7299.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2611, pruned_loss=0.04289, over 1375741.90 frames.], batch size: 18, lr: 5.58e-04
+2022-05-14 15:25:05,445 INFO [train.py:812] (2/8) Epoch 14, batch 750, loss[loss=0.1672, simple_loss=0.2602, pruned_loss=0.03705, over 7213.00 frames.], tot_loss[loss=0.173, simple_loss=0.2605, pruned_loss=0.04271, over 1382573.60 frames.], batch size: 23, lr: 5.58e-04
+2022-05-14 15:26:04,461 INFO [train.py:812] (2/8) Epoch 14, batch 800, loss[loss=0.1779, simple_loss=0.2776, pruned_loss=0.03909, over 7307.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2603, pruned_loss=0.042, over 1391893.47 frames.], batch size: 25, lr: 5.58e-04
+2022-05-14 15:27:03,726 INFO [train.py:812] (2/8) Epoch 14, batch 850, loss[loss=0.1638, simple_loss=0.2627, pruned_loss=0.03246, over 7226.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2599, pruned_loss=0.04179, over 1399944.75 frames.], batch size: 21, lr: 5.57e-04
+2022-05-14 15:28:02,927 INFO [train.py:812] (2/8) Epoch 14, batch 900, loss[loss=0.1593, simple_loss=0.2474, pruned_loss=0.03559, over 7161.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2601, pruned_loss=0.04207, over 1402642.47 frames.], batch size: 18, lr: 5.57e-04
+2022-05-14 15:29:01,798 INFO [train.py:812] (2/8) Epoch 14, batch 950, loss[loss=0.17, simple_loss=0.26, pruned_loss=0.03999, over 7228.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2602, pruned_loss=0.04212, over 1403615.11 frames.], batch size: 21, lr: 5.57e-04
+2022-05-14 15:30:01,468 INFO [train.py:812] (2/8) Epoch 14, batch 1000, loss[loss=0.1986, simple_loss=0.2951, pruned_loss=0.05101, over 7210.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2596, pruned_loss=0.04178, over 1410437.99 frames.], batch size: 22, lr: 5.57e-04
+2022-05-14 15:31:00,118 INFO [train.py:812] (2/8) Epoch 14, batch 1050, loss[loss=0.2033, simple_loss=0.285, pruned_loss=0.06084, over 7429.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2599, pruned_loss=0.04231, over 1410926.15 frames.], batch size: 21, lr: 5.56e-04
+2022-05-14 15:31:57,359 INFO [train.py:812] (2/8) Epoch 14, batch 1100, loss[loss=0.1859, simple_loss=0.2778, pruned_loss=0.04699, over 6776.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2598, pruned_loss=0.04233, over 1410193.66 frames.], batch size: 31, lr: 5.56e-04
+2022-05-14 15:32:55,042 INFO [train.py:812] (2/8) Epoch 14, batch 1150, loss[loss=0.18, simple_loss=0.271, pruned_loss=0.04445, over 7338.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2606, pruned_loss=0.04224, over 1409973.28 frames.], batch size: 22, lr: 5.56e-04
+2022-05-14 15:33:54,468 INFO [train.py:812] (2/8) Epoch 14, batch 1200, loss[loss=0.2101, simple_loss=0.2801, pruned_loss=0.07005, over 5407.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2605, pruned_loss=0.04241, over 1410336.10 frames.], batch size: 52, lr: 5.56e-04
+2022-05-14 15:34:52,744 INFO [train.py:812] (2/8) Epoch 14, batch 1250, loss[loss=0.1573, simple_loss=0.2409, pruned_loss=0.03684, over 7440.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2607, pruned_loss=0.04197, over 1414881.73 frames.], batch size: 20, lr: 5.56e-04
+2022-05-14 15:35:51,083 INFO [train.py:812] (2/8) Epoch 14, batch 1300, loss[loss=0.1584, simple_loss=0.2425, pruned_loss=0.03718, over 7264.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2601, pruned_loss=0.04169, over 1418556.29 frames.], batch size: 19, lr: 5.55e-04
+2022-05-14 15:36:49,528 INFO [train.py:812] (2/8) Epoch 14, batch 1350, loss[loss=0.1495, simple_loss=0.2373, pruned_loss=0.03082, over 7275.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2596, pruned_loss=0.04159, over 1422163.03 frames.], batch size: 18, lr: 5.55e-04
+2022-05-14 15:37:48,220 INFO [train.py:812] (2/8) Epoch 14, batch 1400, loss[loss=0.1625, simple_loss=0.2504, pruned_loss=0.03726, over 7162.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2611, pruned_loss=0.04275, over 1418170.48 frames.], batch size: 18, lr: 5.55e-04
+2022-05-14 15:38:45,036 INFO [train.py:812] (2/8) Epoch 14, batch 1450, loss[loss=0.1444, simple_loss=0.2237, pruned_loss=0.03255, over 7281.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2615, pruned_loss=0.0429, over 1421435.00 frames.], batch size: 17, lr: 5.55e-04
+2022-05-14 15:39:43,870 INFO [train.py:812] (2/8) Epoch 14, batch 1500, loss[loss=0.1518, simple_loss=0.2406, pruned_loss=0.03151, over 7269.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2602, pruned_loss=0.04234, over 1423869.29 frames.], batch size: 17, lr: 5.54e-04
+2022-05-14 15:40:41,992 INFO [train.py:812] (2/8) Epoch 14, batch 1550, loss[loss=0.167, simple_loss=0.261, pruned_loss=0.03651, over 6537.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2603, pruned_loss=0.04236, over 1418449.15 frames.], batch size: 38, lr: 5.54e-04
+2022-05-14 15:41:40,136 INFO [train.py:812] (2/8) Epoch 14, batch 1600, loss[loss=0.1485, simple_loss=0.2442, pruned_loss=0.02641, over 7402.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2603, pruned_loss=0.04207, over 1417311.37 frames.], batch size: 21, lr: 5.54e-04
+2022-05-14 15:42:38,935 INFO [train.py:812] (2/8) Epoch 14, batch 1650, loss[loss=0.185, simple_loss=0.2704, pruned_loss=0.04981, over 7233.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2609, pruned_loss=0.04204, over 1419844.91 frames.], batch size: 20, lr: 5.54e-04
+2022-05-14 15:43:38,140 INFO [train.py:812] (2/8) Epoch 14, batch 1700, loss[loss=0.1719, simple_loss=0.2685, pruned_loss=0.03764, over 6612.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2613, pruned_loss=0.04225, over 1419468.38 frames.], batch size: 38, lr: 5.54e-04
+2022-05-14 15:44:37,149 INFO [train.py:812] (2/8) Epoch 14, batch 1750, loss[loss=0.1453, simple_loss=0.227, pruned_loss=0.03178, over 7272.00 frames.], tot_loss[loss=0.172, simple_loss=0.2604, pruned_loss=0.04182, over 1421206.03 frames.], batch size: 17, lr: 5.53e-04
+2022-05-14 15:45:37,327 INFO [train.py:812] (2/8) Epoch 14, batch 1800, loss[loss=0.1818, simple_loss=0.2742, pruned_loss=0.04467, over 7148.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2606, pruned_loss=0.04203, over 1425563.54 frames.], batch size: 20, lr: 5.53e-04
+2022-05-14 15:46:35,086 INFO [train.py:812] (2/8) Epoch 14, batch 1850, loss[loss=0.1962, simple_loss=0.289, pruned_loss=0.05166, over 7312.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2618, pruned_loss=0.04274, over 1425804.47 frames.], batch size: 25, lr: 5.53e-04
+2022-05-14 15:47:33,722 INFO [train.py:812] (2/8) Epoch 14, batch 1900, loss[loss=0.195, simple_loss=0.2827, pruned_loss=0.05361, over 6617.00 frames.], tot_loss[loss=0.1741, simple_loss=0.262, pruned_loss=0.04312, over 1421276.94 frames.], batch size: 38, lr: 5.53e-04
+2022-05-14 15:48:32,701 INFO [train.py:812] (2/8) Epoch 14, batch 1950, loss[loss=0.1878, simple_loss=0.2738, pruned_loss=0.05088, over 7252.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2625, pruned_loss=0.04321, over 1422087.28 frames.], batch size: 19, lr: 5.52e-04
+2022-05-14 15:49:32,351 INFO [train.py:812] (2/8) Epoch 14, batch 2000, loss[loss=0.1612, simple_loss=0.2621, pruned_loss=0.03014, over 7345.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2617, pruned_loss=0.04257, over 1423497.36 frames.], batch size: 22, lr: 5.52e-04
+2022-05-14 15:50:31,354 INFO [train.py:812] (2/8) Epoch 14, batch 2050, loss[loss=0.1721, simple_loss=0.2704, pruned_loss=0.03691, over 7385.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2615, pruned_loss=0.04265, over 1425608.18 frames.], batch size: 23, lr: 5.52e-04
+2022-05-14 15:51:31,086 INFO [train.py:812] (2/8) Epoch 14, batch 2100, loss[loss=0.203, simple_loss=0.2873, pruned_loss=0.05933, over 7230.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2629, pruned_loss=0.04323, over 1424694.96 frames.], batch size: 20, lr: 5.52e-04
+2022-05-14 15:52:30,492 INFO [train.py:812] (2/8) Epoch 14, batch 2150, loss[loss=0.1736, simple_loss=0.2613, pruned_loss=0.04289, over 7190.00 frames.], tot_loss[loss=0.174, simple_loss=0.262, pruned_loss=0.04297, over 1427616.07 frames.], batch size: 26, lr: 5.52e-04
+2022-05-14 15:53:29,899 INFO [train.py:812] (2/8) Epoch 14, batch 2200, loss[loss=0.1818, simple_loss=0.2595, pruned_loss=0.05209, over 7431.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2621, pruned_loss=0.04307, over 1426251.70 frames.], batch size: 20, lr: 5.51e-04
+2022-05-14 15:54:28,286 INFO [train.py:812] (2/8) Epoch 14, batch 2250, loss[loss=0.1516, simple_loss=0.2452, pruned_loss=0.02897, over 7231.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2615, pruned_loss=0.04268, over 1427325.07 frames.], batch size: 20, lr: 5.51e-04
+2022-05-14 15:55:26,895 INFO [train.py:812] (2/8) Epoch 14, batch 2300, loss[loss=0.1832, simple_loss=0.2705, pruned_loss=0.04792, over 7061.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2601, pruned_loss=0.0421, over 1427450.99 frames.], batch size: 28, lr: 5.51e-04
+2022-05-14 15:56:25,011 INFO [train.py:812] (2/8) Epoch 14, batch 2350, loss[loss=0.2438, simple_loss=0.3173, pruned_loss=0.08519, over 5340.00 frames.], tot_loss[loss=0.172, simple_loss=0.2603, pruned_loss=0.04191, over 1426843.86 frames.], batch size: 52, lr: 5.51e-04
+2022-05-14 15:57:24,307 INFO [train.py:812] (2/8) Epoch 14, batch 2400, loss[loss=0.1587, simple_loss=0.2451, pruned_loss=0.03615, over 7281.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2587, pruned_loss=0.04099, over 1428111.62 frames.], batch size: 17, lr: 5.50e-04
+2022-05-14 15:58:23,348 INFO [train.py:812] (2/8) Epoch 14, batch 2450, loss[loss=0.2117, simple_loss=0.3012, pruned_loss=0.06114, over 6767.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2587, pruned_loss=0.04116, over 1430511.90 frames.], batch size: 31, lr: 5.50e-04
+2022-05-14 15:59:21,595 INFO [train.py:812] (2/8) Epoch 14, batch 2500, loss[loss=0.1527, simple_loss=0.2396, pruned_loss=0.0329, over 7277.00 frames.], tot_loss[loss=0.171, simple_loss=0.2592, pruned_loss=0.04141, over 1425955.31 frames.], batch size: 17, lr: 5.50e-04
+2022-05-14 16:00:19,960 INFO [train.py:812] (2/8) Epoch 14, batch 2550, loss[loss=0.1871, simple_loss=0.2817, pruned_loss=0.04629, over 7347.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2602, pruned_loss=0.04206, over 1421634.45 frames.], batch size: 25, lr: 5.50e-04
+2022-05-14 16:01:19,225 INFO [train.py:812] (2/8) Epoch 14, batch 2600, loss[loss=0.1752, simple_loss=0.2683, pruned_loss=0.04105, over 7414.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2603, pruned_loss=0.04174, over 1418752.95 frames.], batch size: 21, lr: 5.50e-04
+2022-05-14 16:02:16,353 INFO [train.py:812] (2/8) Epoch 14, batch 2650, loss[loss=0.1585, simple_loss=0.2528, pruned_loss=0.03212, over 7120.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2607, pruned_loss=0.04192, over 1416748.15 frames.], batch size: 21, lr: 5.49e-04
+2022-05-14 16:03:15,379 INFO [train.py:812] (2/8) Epoch 14, batch 2700, loss[loss=0.1621, simple_loss=0.2453, pruned_loss=0.03945, over 6999.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2608, pruned_loss=0.04183, over 1421402.40 frames.], batch size: 16, lr: 5.49e-04
+2022-05-14 16:04:13,419 INFO [train.py:812] (2/8) Epoch 14, batch 2750, loss[loss=0.1793, simple_loss=0.2702, pruned_loss=0.04421, over 7272.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2607, pruned_loss=0.04198, over 1426455.55 frames.], batch size: 24, lr: 5.49e-04
+2022-05-14 16:05:11,587 INFO [train.py:812] (2/8) Epoch 14, batch 2800, loss[loss=0.1519, simple_loss=0.2276, pruned_loss=0.03811, over 7139.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2602, pruned_loss=0.04162, over 1425386.16 frames.], batch size: 17, lr: 5.49e-04
+2022-05-14 16:06:10,660 INFO [train.py:812] (2/8) Epoch 14, batch 2850, loss[loss=0.1894, simple_loss=0.285, pruned_loss=0.04686, over 7407.00 frames.], tot_loss[loss=0.1717, simple_loss=0.26, pruned_loss=0.0417, over 1426374.35 frames.], batch size: 21, lr: 5.48e-04
+2022-05-14 16:07:10,186 INFO [train.py:812] (2/8) Epoch 14, batch 2900, loss[loss=0.1764, simple_loss=0.2793, pruned_loss=0.0368, over 7115.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2608, pruned_loss=0.04176, over 1427635.18 frames.], batch size: 21, lr: 5.48e-04
+2022-05-14 16:08:08,880 INFO [train.py:812] (2/8) Epoch 14, batch 2950, loss[loss=0.2065, simple_loss=0.28, pruned_loss=0.06652, over 7207.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2604, pruned_loss=0.0415, over 1429142.80 frames.], batch size: 23, lr: 5.48e-04
+2022-05-14 16:09:07,645 INFO [train.py:812] (2/8) Epoch 14, batch 3000, loss[loss=0.1874, simple_loss=0.2765, pruned_loss=0.04909, over 7296.00 frames.], tot_loss[loss=0.171, simple_loss=0.2595, pruned_loss=0.04126, over 1429901.25 frames.], batch size: 24, lr: 5.48e-04
+2022-05-14 16:09:07,646 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 16:09:15,054 INFO [train.py:841] (2/8) Epoch 14, validation: loss=0.1549, simple_loss=0.2556, pruned_loss=0.02713, over 698248.00 frames.
+2022-05-14 16:10:14,215 INFO [train.py:812] (2/8) Epoch 14, batch 3050, loss[loss=0.1461, simple_loss=0.2287, pruned_loss=0.03174, over 7295.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2599, pruned_loss=0.04149, over 1429716.97 frames.], batch size: 17, lr: 5.48e-04
+2022-05-14 16:11:13,822 INFO [train.py:812] (2/8) Epoch 14, batch 3100, loss[loss=0.1781, simple_loss=0.2702, pruned_loss=0.04295, over 7214.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2605, pruned_loss=0.04187, over 1430919.47 frames.], batch size: 23, lr: 5.47e-04
+2022-05-14 16:12:13,376 INFO [train.py:812] (2/8) Epoch 14, batch 3150, loss[loss=0.2332, simple_loss=0.299, pruned_loss=0.08369, over 5226.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2599, pruned_loss=0.04176, over 1429922.56 frames.], batch size: 52, lr: 5.47e-04
+2022-05-14 16:13:13,718 INFO [train.py:812] (2/8) Epoch 14, batch 3200, loss[loss=0.1455, simple_loss=0.2468, pruned_loss=0.02214, over 7342.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2595, pruned_loss=0.04144, over 1429790.23 frames.], batch size: 22, lr: 5.47e-04
+2022-05-14 16:14:11,602 INFO [train.py:812] (2/8) Epoch 14, batch 3250, loss[loss=0.2029, simple_loss=0.2864, pruned_loss=0.05972, over 7217.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2601, pruned_loss=0.04207, over 1426729.56 frames.], batch size: 26, lr: 5.47e-04
+2022-05-14 16:15:10,587 INFO [train.py:812] (2/8) Epoch 14, batch 3300, loss[loss=0.1468, simple_loss=0.2394, pruned_loss=0.02706, over 7166.00 frames.], tot_loss[loss=0.172, simple_loss=0.26, pruned_loss=0.04201, over 1423225.25 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:16:09,594 INFO [train.py:812] (2/8) Epoch 14, batch 3350, loss[loss=0.1745, simple_loss=0.2551, pruned_loss=0.04691, over 7418.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2604, pruned_loss=0.04219, over 1425475.34 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:17:08,389 INFO [train.py:812] (2/8) Epoch 14, batch 3400, loss[loss=0.165, simple_loss=0.2534, pruned_loss=0.03829, over 7167.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2597, pruned_loss=0.04155, over 1426661.71 frames.], batch size: 18, lr: 5.46e-04
+2022-05-14 16:18:17,664 INFO [train.py:812] (2/8) Epoch 14, batch 3450, loss[loss=0.1795, simple_loss=0.2739, pruned_loss=0.04258, over 7429.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2601, pruned_loss=0.04186, over 1426072.53 frames.], batch size: 22, lr: 5.46e-04
+2022-05-14 16:19:16,781 INFO [train.py:812] (2/8) Epoch 14, batch 3500, loss[loss=0.1721, simple_loss=0.2602, pruned_loss=0.04199, over 7340.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2599, pruned_loss=0.04187, over 1427698.98 frames.], batch size: 22, lr: 5.46e-04
+2022-05-14 16:20:15,509 INFO [train.py:812] (2/8) Epoch 14, batch 3550, loss[loss=0.1689, simple_loss=0.2728, pruned_loss=0.03244, over 7316.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2604, pruned_loss=0.04202, over 1427928.35 frames.], batch size: 21, lr: 5.45e-04
+2022-05-14 16:21:14,193 INFO [train.py:812] (2/8) Epoch 14, batch 3600, loss[loss=0.1628, simple_loss=0.2524, pruned_loss=0.03664, over 7359.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2593, pruned_loss=0.04166, over 1430882.44 frames.], batch size: 19, lr: 5.45e-04
+2022-05-14 16:22:13,046 INFO [train.py:812] (2/8) Epoch 14, batch 3650, loss[loss=0.193, simple_loss=0.2777, pruned_loss=0.05419, over 7239.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2597, pruned_loss=0.04187, over 1430302.11 frames.], batch size: 20, lr: 5.45e-04
+2022-05-14 16:23:12,478 INFO [train.py:812] (2/8) Epoch 14, batch 3700, loss[loss=0.2129, simple_loss=0.3099, pruned_loss=0.05802, over 7280.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2608, pruned_loss=0.0424, over 1422070.03 frames.], batch size: 24, lr: 5.45e-04
+2022-05-14 16:24:11,565 INFO [train.py:812] (2/8) Epoch 14, batch 3750, loss[loss=0.2265, simple_loss=0.3077, pruned_loss=0.0726, over 4963.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2619, pruned_loss=0.04265, over 1420578.76 frames.], batch size: 52, lr: 5.45e-04
+2022-05-14 16:25:11,063 INFO [train.py:812] (2/8) Epoch 14, batch 3800, loss[loss=0.1508, simple_loss=0.2235, pruned_loss=0.03906, over 6989.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2624, pruned_loss=0.04313, over 1420110.45 frames.], batch size: 16, lr: 5.44e-04
+2022-05-14 16:26:09,753 INFO [train.py:812] (2/8) Epoch 14, batch 3850, loss[loss=0.171, simple_loss=0.262, pruned_loss=0.04002, over 7198.00 frames.], tot_loss[loss=0.1738, simple_loss=0.262, pruned_loss=0.04278, over 1421434.54 frames.], batch size: 22, lr: 5.44e-04
+2022-05-14 16:27:08,501 INFO [train.py:812] (2/8) Epoch 14, batch 3900, loss[loss=0.1706, simple_loss=0.2672, pruned_loss=0.03697, over 7327.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2618, pruned_loss=0.04228, over 1423601.40 frames.], batch size: 21, lr: 5.44e-04
+2022-05-14 16:28:07,612 INFO [train.py:812] (2/8) Epoch 14, batch 3950, loss[loss=0.2274, simple_loss=0.3024, pruned_loss=0.07619, over 4813.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2606, pruned_loss=0.04187, over 1421306.13 frames.], batch size: 53, lr: 5.44e-04
+2022-05-14 16:29:06,376 INFO [train.py:812] (2/8) Epoch 14, batch 4000, loss[loss=0.1723, simple_loss=0.2702, pruned_loss=0.03724, over 7351.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2613, pruned_loss=0.04193, over 1422626.40 frames.], batch size: 22, lr: 5.43e-04
+2022-05-14 16:30:03,968 INFO [train.py:812] (2/8) Epoch 14, batch 4050, loss[loss=0.1431, simple_loss=0.2244, pruned_loss=0.03094, over 7214.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2598, pruned_loss=0.04151, over 1423739.13 frames.], batch size: 16, lr: 5.43e-04
+2022-05-14 16:31:03,495 INFO [train.py:812] (2/8) Epoch 14, batch 4100, loss[loss=0.2058, simple_loss=0.2879, pruned_loss=0.06186, over 6625.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2598, pruned_loss=0.04188, over 1420861.08 frames.], batch size: 31, lr: 5.43e-04
+2022-05-14 16:32:02,256 INFO [train.py:812] (2/8) Epoch 14, batch 4150, loss[loss=0.144, simple_loss=0.238, pruned_loss=0.02505, over 7214.00 frames.], tot_loss[loss=0.1712, simple_loss=0.259, pruned_loss=0.04175, over 1420703.64 frames.], batch size: 21, lr: 5.43e-04
+2022-05-14 16:33:01,721 INFO [train.py:812] (2/8) Epoch 14, batch 4200, loss[loss=0.1574, simple_loss=0.2334, pruned_loss=0.04071, over 7277.00 frames.], tot_loss[loss=0.1704, simple_loss=0.258, pruned_loss=0.04145, over 1421933.59 frames.], batch size: 17, lr: 5.43e-04
+2022-05-14 16:34:00,231 INFO [train.py:812] (2/8) Epoch 14, batch 4250, loss[loss=0.1973, simple_loss=0.2841, pruned_loss=0.05527, over 6461.00 frames.], tot_loss[loss=0.1711, simple_loss=0.259, pruned_loss=0.04157, over 1415900.94 frames.], batch size: 38, lr: 5.42e-04
+2022-05-14 16:34:59,091 INFO [train.py:812] (2/8) Epoch 14, batch 4300, loss[loss=0.1722, simple_loss=0.2721, pruned_loss=0.03617, over 7223.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2594, pruned_loss=0.0418, over 1412167.12 frames.], batch size: 21, lr: 5.42e-04
+2022-05-14 16:35:56,840 INFO [train.py:812] (2/8) Epoch 14, batch 4350, loss[loss=0.164, simple_loss=0.2408, pruned_loss=0.04358, over 6767.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2595, pruned_loss=0.04213, over 1408258.66 frames.], batch size: 15, lr: 5.42e-04
+2022-05-14 16:37:01,590 INFO [train.py:812] (2/8) Epoch 14, batch 4400, loss[loss=0.1712, simple_loss=0.2671, pruned_loss=0.03762, over 7136.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2595, pruned_loss=0.04198, over 1401119.05 frames.], batch size: 20, lr: 5.42e-04
+2022-05-14 16:38:00,474 INFO [train.py:812] (2/8) Epoch 14, batch 4450, loss[loss=0.1924, simple_loss=0.2681, pruned_loss=0.05835, over 4942.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2604, pruned_loss=0.04208, over 1391381.48 frames.], batch size: 52, lr: 5.42e-04
+2022-05-14 16:38:59,688 INFO [train.py:812] (2/8) Epoch 14, batch 4500, loss[loss=0.1861, simple_loss=0.2668, pruned_loss=0.05269, over 5188.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2608, pruned_loss=0.04277, over 1376518.43 frames.], batch size: 52, lr: 5.41e-04
+2022-05-14 16:40:07,821 INFO [train.py:812] (2/8) Epoch 14, batch 4550, loss[loss=0.1747, simple_loss=0.2687, pruned_loss=0.04037, over 6704.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2613, pruned_loss=0.04325, over 1366841.90 frames.], batch size: 31, lr: 5.41e-04
+2022-05-14 16:41:16,664 INFO [train.py:812] (2/8) Epoch 15, batch 0, loss[loss=0.1729, simple_loss=0.2631, pruned_loss=0.04134, over 7087.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2631, pruned_loss=0.04134, over 7087.00 frames.], batch size: 28, lr: 5.25e-04
+2022-05-14 16:42:15,475 INFO [train.py:812] (2/8) Epoch 15, batch 50, loss[loss=0.2036, simple_loss=0.2926, pruned_loss=0.05725, over 4911.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2604, pruned_loss=0.04216, over 321677.96 frames.], batch size: 52, lr: 5.24e-04
+2022-05-14 16:43:15,410 INFO [train.py:812] (2/8) Epoch 15, batch 100, loss[loss=0.1554, simple_loss=0.2522, pruned_loss=0.02931, over 7162.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2587, pruned_loss=0.03986, over 568556.34 frames.], batch size: 18, lr: 5.24e-04
+2022-05-14 16:44:31,102 INFO [train.py:812] (2/8) Epoch 15, batch 150, loss[loss=0.21, simple_loss=0.2942, pruned_loss=0.0629, over 7124.00 frames.], tot_loss[loss=0.1727, simple_loss=0.262, pruned_loss=0.04171, over 758755.42 frames.], batch size: 21, lr: 5.24e-04
+2022-05-14 16:45:30,977 INFO [train.py:812] (2/8) Epoch 15, batch 200, loss[loss=0.1733, simple_loss=0.2577, pruned_loss=0.04442, over 7332.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2626, pruned_loss=0.0423, over 902853.43 frames.], batch size: 20, lr: 5.24e-04
+2022-05-14 16:46:49,161 INFO [train.py:812] (2/8) Epoch 15, batch 250, loss[loss=0.1739, simple_loss=0.2751, pruned_loss=0.03632, over 6620.00 frames.], tot_loss[loss=0.172, simple_loss=0.261, pruned_loss=0.04153, over 1019477.10 frames.], batch size: 38, lr: 5.24e-04
+2022-05-14 16:48:07,492 INFO [train.py:812] (2/8) Epoch 15, batch 300, loss[loss=0.1473, simple_loss=0.2252, pruned_loss=0.03474, over 7136.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2601, pruned_loss=0.04124, over 1109973.89 frames.], batch size: 17, lr: 5.23e-04
+2022-05-14 16:49:06,736 INFO [train.py:812] (2/8) Epoch 15, batch 350, loss[loss=0.1567, simple_loss=0.2392, pruned_loss=0.03712, over 6819.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2596, pruned_loss=0.04151, over 1171804.18 frames.], batch size: 15, lr: 5.23e-04
+2022-05-14 16:50:06,839 INFO [train.py:812] (2/8) Epoch 15, batch 400, loss[loss=0.1605, simple_loss=0.2632, pruned_loss=0.02888, over 7149.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2595, pruned_loss=0.04149, over 1226591.31 frames.], batch size: 20, lr: 5.23e-04
+2022-05-14 16:51:05,888 INFO [train.py:812] (2/8) Epoch 15, batch 450, loss[loss=0.1682, simple_loss=0.2495, pruned_loss=0.04339, over 7162.00 frames.], tot_loss[loss=0.1708, simple_loss=0.259, pruned_loss=0.04125, over 1270973.17 frames.], batch size: 19, lr: 5.23e-04
+2022-05-14 16:52:05,399 INFO [train.py:812] (2/8) Epoch 15, batch 500, loss[loss=0.1544, simple_loss=0.2405, pruned_loss=0.03411, over 7418.00 frames.], tot_loss[loss=0.171, simple_loss=0.2593, pruned_loss=0.0413, over 1302686.02 frames.], batch size: 20, lr: 5.23e-04
+2022-05-14 16:53:04,819 INFO [train.py:812] (2/8) Epoch 15, batch 550, loss[loss=0.1359, simple_loss=0.2203, pruned_loss=0.02572, over 7275.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2588, pruned_loss=0.04089, over 1331948.12 frames.], batch size: 18, lr: 5.22e-04
+2022-05-14 16:54:04,512 INFO [train.py:812] (2/8) Epoch 15, batch 600, loss[loss=0.1676, simple_loss=0.2642, pruned_loss=0.03545, over 7236.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2575, pruned_loss=0.04015, over 1354976.46 frames.], batch size: 20, lr: 5.22e-04
+2022-05-14 16:55:03,726 INFO [train.py:812] (2/8) Epoch 15, batch 650, loss[loss=0.2014, simple_loss=0.2915, pruned_loss=0.05568, over 7334.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2585, pruned_loss=0.0405, over 1369346.35 frames.], batch size: 22, lr: 5.22e-04
+2022-05-14 16:56:03,040 INFO [train.py:812] (2/8) Epoch 15, batch 700, loss[loss=0.1507, simple_loss=0.2448, pruned_loss=0.02831, over 7335.00 frames.], tot_loss[loss=0.171, simple_loss=0.2599, pruned_loss=0.04106, over 1382265.54 frames.], batch size: 20, lr: 5.22e-04
+2022-05-14 16:57:02,256 INFO [train.py:812] (2/8) Epoch 15, batch 750, loss[loss=0.1577, simple_loss=0.2557, pruned_loss=0.02984, over 7345.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2595, pruned_loss=0.04078, over 1389548.23 frames.], batch size: 22, lr: 5.22e-04
+2022-05-14 16:58:01,660 INFO [train.py:812] (2/8) Epoch 15, batch 800, loss[loss=0.1619, simple_loss=0.2513, pruned_loss=0.03624, over 7327.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2594, pruned_loss=0.04076, over 1397993.96 frames.], batch size: 22, lr: 5.21e-04
+2022-05-14 16:59:00,996 INFO [train.py:812] (2/8) Epoch 15, batch 850, loss[loss=0.1449, simple_loss=0.2396, pruned_loss=0.02506, over 7129.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2599, pruned_loss=0.04113, over 1400909.72 frames.], batch size: 17, lr: 5.21e-04
+2022-05-14 17:00:00,530 INFO [train.py:812] (2/8) Epoch 15, batch 900, loss[loss=0.1551, simple_loss=0.2475, pruned_loss=0.03137, over 7260.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2591, pruned_loss=0.04109, over 1396048.95 frames.], batch size: 19, lr: 5.21e-04
+2022-05-14 17:00:59,822 INFO [train.py:812] (2/8) Epoch 15, batch 950, loss[loss=0.172, simple_loss=0.2674, pruned_loss=0.03828, over 7336.00 frames.], tot_loss[loss=0.1714, simple_loss=0.26, pruned_loss=0.04137, over 1405135.21 frames.], batch size: 22, lr: 5.21e-04
+2022-05-14 17:01:59,705 INFO [train.py:812] (2/8) Epoch 15, batch 1000, loss[loss=0.2202, simple_loss=0.3001, pruned_loss=0.07015, over 7091.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2602, pruned_loss=0.04125, over 1406228.67 frames.], batch size: 28, lr: 5.21e-04
+2022-05-14 17:02:57,914 INFO [train.py:812] (2/8) Epoch 15, batch 1050, loss[loss=0.1422, simple_loss=0.2281, pruned_loss=0.02814, over 7271.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2592, pruned_loss=0.04086, over 1412236.41 frames.], batch size: 18, lr: 5.20e-04
+2022-05-14 17:03:56,825 INFO [train.py:812] (2/8) Epoch 15, batch 1100, loss[loss=0.1587, simple_loss=0.2484, pruned_loss=0.03455, over 7270.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2589, pruned_loss=0.04118, over 1416098.69 frames.], batch size: 17, lr: 5.20e-04
+2022-05-14 17:04:54,468 INFO [train.py:812] (2/8) Epoch 15, batch 1150, loss[loss=0.1831, simple_loss=0.2791, pruned_loss=0.04356, over 7418.00 frames.], tot_loss[loss=0.171, simple_loss=0.2591, pruned_loss=0.0414, over 1421528.87 frames.], batch size: 21, lr: 5.20e-04
+2022-05-14 17:05:54,080 INFO [train.py:812] (2/8) Epoch 15, batch 1200, loss[loss=0.1608, simple_loss=0.2542, pruned_loss=0.03369, over 7424.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2585, pruned_loss=0.04131, over 1423497.68 frames.], batch size: 20, lr: 5.20e-04
+2022-05-14 17:06:52,030 INFO [train.py:812] (2/8) Epoch 15, batch 1250, loss[loss=0.2028, simple_loss=0.273, pruned_loss=0.06624, over 7351.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2595, pruned_loss=0.04149, over 1426290.84 frames.], batch size: 19, lr: 5.20e-04
+2022-05-14 17:07:51,284 INFO [train.py:812] (2/8) Epoch 15, batch 1300, loss[loss=0.1736, simple_loss=0.2683, pruned_loss=0.03945, over 6380.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2596, pruned_loss=0.04165, over 1420257.36 frames.], batch size: 38, lr: 5.19e-04
+2022-05-14 17:08:51,291 INFO [train.py:812] (2/8) Epoch 15, batch 1350, loss[loss=0.1485, simple_loss=0.2281, pruned_loss=0.03443, over 6980.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2606, pruned_loss=0.04227, over 1421704.78 frames.], batch size: 16, lr: 5.19e-04
+2022-05-14 17:09:50,448 INFO [train.py:812] (2/8) Epoch 15, batch 1400, loss[loss=0.1806, simple_loss=0.2747, pruned_loss=0.04331, over 7313.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2605, pruned_loss=0.04209, over 1421245.32 frames.], batch size: 24, lr: 5.19e-04
+2022-05-14 17:10:49,136 INFO [train.py:812] (2/8) Epoch 15, batch 1450, loss[loss=0.193, simple_loss=0.2904, pruned_loss=0.0478, over 7369.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2601, pruned_loss=0.04129, over 1419028.71 frames.], batch size: 23, lr: 5.19e-04
+2022-05-14 17:11:46,392 INFO [train.py:812] (2/8) Epoch 15, batch 1500, loss[loss=0.1607, simple_loss=0.2587, pruned_loss=0.03132, over 7134.00 frames.], tot_loss[loss=0.1713, simple_loss=0.26, pruned_loss=0.04126, over 1412830.26 frames.], batch size: 20, lr: 5.19e-04
+2022-05-14 17:12:45,413 INFO [train.py:812] (2/8) Epoch 15, batch 1550, loss[loss=0.1544, simple_loss=0.2497, pruned_loss=0.02953, over 7118.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2586, pruned_loss=0.04055, over 1417461.50 frames.], batch size: 21, lr: 5.18e-04
+2022-05-14 17:13:44,515 INFO [train.py:812] (2/8) Epoch 15, batch 1600, loss[loss=0.1626, simple_loss=0.2513, pruned_loss=0.03695, over 7407.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2582, pruned_loss=0.04041, over 1419122.82 frames.], batch size: 21, lr: 5.18e-04
+2022-05-14 17:14:43,359 INFO [train.py:812] (2/8) Epoch 15, batch 1650, loss[loss=0.1871, simple_loss=0.2786, pruned_loss=0.04779, over 7187.00 frames.], tot_loss[loss=0.17, simple_loss=0.2587, pruned_loss=0.04066, over 1423977.15 frames.], batch size: 23, lr: 5.18e-04
+2022-05-14 17:15:42,377 INFO [train.py:812] (2/8) Epoch 15, batch 1700, loss[loss=0.1544, simple_loss=0.2447, pruned_loss=0.03204, over 7307.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2574, pruned_loss=0.04009, over 1427499.73 frames.], batch size: 25, lr: 5.18e-04
+2022-05-14 17:16:41,861 INFO [train.py:812] (2/8) Epoch 15, batch 1750, loss[loss=0.1978, simple_loss=0.2958, pruned_loss=0.04994, over 7101.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2583, pruned_loss=0.04058, over 1430440.03 frames.], batch size: 28, lr: 5.18e-04
+2022-05-14 17:17:41,420 INFO [train.py:812] (2/8) Epoch 15, batch 1800, loss[loss=0.1361, simple_loss=0.2151, pruned_loss=0.0285, over 7272.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2578, pruned_loss=0.04027, over 1427742.95 frames.], batch size: 17, lr: 5.17e-04
+2022-05-14 17:18:41,018 INFO [train.py:812] (2/8) Epoch 15, batch 1850, loss[loss=0.1714, simple_loss=0.2532, pruned_loss=0.04486, over 7160.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2585, pruned_loss=0.04065, over 1431610.21 frames.], batch size: 18, lr: 5.17e-04
+2022-05-14 17:19:40,984 INFO [train.py:812] (2/8) Epoch 15, batch 1900, loss[loss=0.1772, simple_loss=0.272, pruned_loss=0.04122, over 7108.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2583, pruned_loss=0.0406, over 1431387.84 frames.], batch size: 21, lr: 5.17e-04
+2022-05-14 17:20:40,330 INFO [train.py:812] (2/8) Epoch 15, batch 1950, loss[loss=0.2073, simple_loss=0.2925, pruned_loss=0.06104, over 7262.00 frames.], tot_loss[loss=0.17, simple_loss=0.2583, pruned_loss=0.04084, over 1431576.90 frames.], batch size: 18, lr: 5.17e-04
+2022-05-14 17:21:39,017 INFO [train.py:812] (2/8) Epoch 15, batch 2000, loss[loss=0.1652, simple_loss=0.2559, pruned_loss=0.03723, over 6574.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2589, pruned_loss=0.0414, over 1427536.86 frames.], batch size: 37, lr: 5.17e-04
+2022-05-14 17:22:38,291 INFO [train.py:812] (2/8) Epoch 15, batch 2050, loss[loss=0.1593, simple_loss=0.2547, pruned_loss=0.03195, over 7301.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2605, pruned_loss=0.042, over 1429311.32 frames.], batch size: 25, lr: 5.16e-04
+2022-05-14 17:23:37,397 INFO [train.py:812] (2/8) Epoch 15, batch 2100, loss[loss=0.1329, simple_loss=0.2096, pruned_loss=0.0281, over 7403.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2591, pruned_loss=0.04161, over 1423076.85 frames.], batch size: 18, lr: 5.16e-04
+2022-05-14 17:24:36,099 INFO [train.py:812] (2/8) Epoch 15, batch 2150, loss[loss=0.1973, simple_loss=0.2821, pruned_loss=0.05625, over 7201.00 frames.], tot_loss[loss=0.17, simple_loss=0.258, pruned_loss=0.04095, over 1421096.84 frames.], batch size: 22, lr: 5.16e-04
+2022-05-14 17:25:35,471 INFO [train.py:812] (2/8) Epoch 15, batch 2200, loss[loss=0.1786, simple_loss=0.2663, pruned_loss=0.04544, over 7435.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2589, pruned_loss=0.04118, over 1420887.62 frames.], batch size: 20, lr: 5.16e-04
+2022-05-14 17:26:33,940 INFO [train.py:812] (2/8) Epoch 15, batch 2250, loss[loss=0.1519, simple_loss=0.2491, pruned_loss=0.02737, over 7148.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2587, pruned_loss=0.04098, over 1422452.97 frames.], batch size: 28, lr: 5.16e-04
+2022-05-14 17:27:32,333 INFO [train.py:812] (2/8) Epoch 15, batch 2300, loss[loss=0.1491, simple_loss=0.2271, pruned_loss=0.03559, over 6786.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2582, pruned_loss=0.04074, over 1422359.28 frames.], batch size: 15, lr: 5.15e-04
+2022-05-14 17:28:30,792 INFO [train.py:812] (2/8) Epoch 15, batch 2350, loss[loss=0.1575, simple_loss=0.2326, pruned_loss=0.04117, over 7412.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2584, pruned_loss=0.04098, over 1424663.54 frames.], batch size: 18, lr: 5.15e-04
+2022-05-14 17:29:30,880 INFO [train.py:812] (2/8) Epoch 15, batch 2400, loss[loss=0.1718, simple_loss=0.2433, pruned_loss=0.05014, over 7411.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2601, pruned_loss=0.04178, over 1421775.21 frames.], batch size: 18, lr: 5.15e-04
+2022-05-14 17:30:30,105 INFO [train.py:812] (2/8) Epoch 15, batch 2450, loss[loss=0.1631, simple_loss=0.2542, pruned_loss=0.036, over 7401.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2596, pruned_loss=0.0416, over 1422338.64 frames.], batch size: 21, lr: 5.15e-04
+2022-05-14 17:31:29,622 INFO [train.py:812] (2/8) Epoch 15, batch 2500, loss[loss=0.1882, simple_loss=0.2771, pruned_loss=0.0497, over 7323.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2602, pruned_loss=0.04157, over 1423449.44 frames.], batch size: 21, lr: 5.15e-04
+2022-05-14 17:32:27,882 INFO [train.py:812] (2/8) Epoch 15, batch 2550, loss[loss=0.1454, simple_loss=0.2304, pruned_loss=0.03014, over 7158.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2607, pruned_loss=0.04172, over 1426345.73 frames.], batch size: 18, lr: 5.14e-04
+2022-05-14 17:33:27,549 INFO [train.py:812] (2/8) Epoch 15, batch 2600, loss[loss=0.1923, simple_loss=0.2743, pruned_loss=0.05515, over 7208.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2615, pruned_loss=0.04247, over 1421414.05 frames.], batch size: 23, lr: 5.14e-04
+2022-05-14 17:34:25,847 INFO [train.py:812] (2/8) Epoch 15, batch 2650, loss[loss=0.1527, simple_loss=0.2492, pruned_loss=0.02814, over 7276.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2609, pruned_loss=0.04197, over 1421413.17 frames.], batch size: 25, lr: 5.14e-04
+2022-05-14 17:35:25,202 INFO [train.py:812] (2/8) Epoch 15, batch 2700, loss[loss=0.178, simple_loss=0.2748, pruned_loss=0.04063, over 7321.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2615, pruned_loss=0.04201, over 1423835.24 frames.], batch size: 21, lr: 5.14e-04
+2022-05-14 17:36:24,261 INFO [train.py:812] (2/8) Epoch 15, batch 2750, loss[loss=0.1749, simple_loss=0.2652, pruned_loss=0.04227, over 7278.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2606, pruned_loss=0.04159, over 1424290.29 frames.], batch size: 24, lr: 5.14e-04
+2022-05-14 17:37:23,471 INFO [train.py:812] (2/8) Epoch 15, batch 2800, loss[loss=0.1806, simple_loss=0.2742, pruned_loss=0.04346, over 7138.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2607, pruned_loss=0.04138, over 1427079.56 frames.], batch size: 20, lr: 5.14e-04
+2022-05-14 17:38:20,795 INFO [train.py:812] (2/8) Epoch 15, batch 2850, loss[loss=0.1709, simple_loss=0.2582, pruned_loss=0.0418, over 6807.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2606, pruned_loss=0.04149, over 1427425.89 frames.], batch size: 15, lr: 5.13e-04
+2022-05-14 17:39:21,011 INFO [train.py:812] (2/8) Epoch 15, batch 2900, loss[loss=0.2041, simple_loss=0.2871, pruned_loss=0.06053, over 7358.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2611, pruned_loss=0.04212, over 1423801.16 frames.], batch size: 23, lr: 5.13e-04
+2022-05-14 17:40:19,999 INFO [train.py:812] (2/8) Epoch 15, batch 2950, loss[loss=0.183, simple_loss=0.2708, pruned_loss=0.04757, over 7434.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2614, pruned_loss=0.04207, over 1425448.30 frames.], batch size: 20, lr: 5.13e-04
+2022-05-14 17:41:19,155 INFO [train.py:812] (2/8) Epoch 15, batch 3000, loss[loss=0.1799, simple_loss=0.2715, pruned_loss=0.04413, over 7153.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2609, pruned_loss=0.04205, over 1422672.96 frames.], batch size: 19, lr: 5.13e-04
+2022-05-14 17:41:19,156 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 17:41:26,767 INFO [train.py:841] (2/8) Epoch 15, validation: loss=0.1543, simple_loss=0.2544, pruned_loss=0.02713, over 698248.00 frames.
+2022-05-14 17:42:25,635 INFO [train.py:812] (2/8) Epoch 15, batch 3050, loss[loss=0.1668, simple_loss=0.2465, pruned_loss=0.04358, over 7265.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2601, pruned_loss=0.04139, over 1426264.40 frames.], batch size: 16, lr: 5.13e-04
+2022-05-14 17:43:23,114 INFO [train.py:812] (2/8) Epoch 15, batch 3100, loss[loss=0.1623, simple_loss=0.2595, pruned_loss=0.0325, over 7336.00 frames.], tot_loss[loss=0.1712, simple_loss=0.26, pruned_loss=0.04125, over 1422583.98 frames.], batch size: 20, lr: 5.12e-04
+2022-05-14 17:44:21,955 INFO [train.py:812] (2/8) Epoch 15, batch 3150, loss[loss=0.1604, simple_loss=0.2434, pruned_loss=0.03868, over 7288.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2596, pruned_loss=0.04147, over 1427725.38 frames.], batch size: 17, lr: 5.12e-04
+2022-05-14 17:45:20,569 INFO [train.py:812] (2/8) Epoch 15, batch 3200, loss[loss=0.1507, simple_loss=0.2395, pruned_loss=0.03093, over 7082.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2591, pruned_loss=0.04137, over 1428094.30 frames.], batch size: 28, lr: 5.12e-04
+2022-05-14 17:46:20,196 INFO [train.py:812] (2/8) Epoch 15, batch 3250, loss[loss=0.1677, simple_loss=0.256, pruned_loss=0.03969, over 7055.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2579, pruned_loss=0.04077, over 1428293.15 frames.], batch size: 18, lr: 5.12e-04
+2022-05-14 17:47:18,745 INFO [train.py:812] (2/8) Epoch 15, batch 3300, loss[loss=0.1667, simple_loss=0.2455, pruned_loss=0.04399, over 7289.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2562, pruned_loss=0.03981, over 1426897.53 frames.], batch size: 17, lr: 5.12e-04
+2022-05-14 17:48:17,422 INFO [train.py:812] (2/8) Epoch 15, batch 3350, loss[loss=0.1839, simple_loss=0.2696, pruned_loss=0.04906, over 7187.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2579, pruned_loss=0.04048, over 1426341.08 frames.], batch size: 23, lr: 5.11e-04
+2022-05-14 17:49:14,697 INFO [train.py:812] (2/8) Epoch 15, batch 3400, loss[loss=0.1649, simple_loss=0.2631, pruned_loss=0.03328, over 7220.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2588, pruned_loss=0.04045, over 1423213.25 frames.], batch size: 21, lr: 5.11e-04
+2022-05-14 17:50:13,362 INFO [train.py:812] (2/8) Epoch 15, batch 3450, loss[loss=0.1665, simple_loss=0.2651, pruned_loss=0.03397, over 7051.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2598, pruned_loss=0.04091, over 1420057.58 frames.], batch size: 28, lr: 5.11e-04
+2022-05-14 17:51:13,182 INFO [train.py:812] (2/8) Epoch 15, batch 3500, loss[loss=0.1947, simple_loss=0.2874, pruned_loss=0.05105, over 7118.00 frames.], tot_loss[loss=0.17, simple_loss=0.2587, pruned_loss=0.04063, over 1425459.11 frames.], batch size: 26, lr: 5.11e-04
+2022-05-14 17:52:12,826 INFO [train.py:812] (2/8) Epoch 15, batch 3550, loss[loss=0.1524, simple_loss=0.2424, pruned_loss=0.03122, over 7243.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2587, pruned_loss=0.04053, over 1426953.14 frames.], batch size: 20, lr: 5.11e-04
+2022-05-14 17:53:11,440 INFO [train.py:812] (2/8) Epoch 15, batch 3600, loss[loss=0.1457, simple_loss=0.2376, pruned_loss=0.02689, over 7317.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2588, pruned_loss=0.04079, over 1423483.18 frames.], batch size: 21, lr: 5.11e-04
+2022-05-14 17:54:10,558 INFO [train.py:812] (2/8) Epoch 15, batch 3650, loss[loss=0.1874, simple_loss=0.2848, pruned_loss=0.04505, over 7261.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2589, pruned_loss=0.04081, over 1424592.64 frames.], batch size: 19, lr: 5.10e-04
+2022-05-14 17:55:10,191 INFO [train.py:812] (2/8) Epoch 15, batch 3700, loss[loss=0.1514, simple_loss=0.2453, pruned_loss=0.0287, over 7430.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2594, pruned_loss=0.04123, over 1421985.46 frames.], batch size: 20, lr: 5.10e-04
+2022-05-14 17:56:09,471 INFO [train.py:812] (2/8) Epoch 15, batch 3750, loss[loss=0.1982, simple_loss=0.2804, pruned_loss=0.05805, over 5410.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2596, pruned_loss=0.04148, over 1424655.47 frames.], batch size: 52, lr: 5.10e-04
+2022-05-14 17:57:14,311 INFO [train.py:812] (2/8) Epoch 15, batch 3800, loss[loss=0.1568, simple_loss=0.2406, pruned_loss=0.0365, over 7450.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2601, pruned_loss=0.04155, over 1426557.83 frames.], batch size: 19, lr: 5.10e-04
+2022-05-14 17:58:12,039 INFO [train.py:812] (2/8) Epoch 15, batch 3850, loss[loss=0.2232, simple_loss=0.309, pruned_loss=0.06869, over 7242.00 frames.], tot_loss[loss=0.1713, simple_loss=0.26, pruned_loss=0.04125, over 1428748.73 frames.], batch size: 20, lr: 5.10e-04
+2022-05-14 17:59:11,852 INFO [train.py:812] (2/8) Epoch 15, batch 3900, loss[loss=0.1484, simple_loss=0.2403, pruned_loss=0.02829, over 7257.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2597, pruned_loss=0.04133, over 1426204.40 frames.], batch size: 19, lr: 5.09e-04
+2022-05-14 18:00:11,036 INFO [train.py:812] (2/8) Epoch 15, batch 3950, loss[loss=0.1833, simple_loss=0.2677, pruned_loss=0.04941, over 7359.00 frames.], tot_loss[loss=0.171, simple_loss=0.2592, pruned_loss=0.04141, over 1423016.17 frames.], batch size: 19, lr: 5.09e-04
+2022-05-14 18:01:10,580 INFO [train.py:812] (2/8) Epoch 15, batch 4000, loss[loss=0.1646, simple_loss=0.2671, pruned_loss=0.03101, over 7229.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2592, pruned_loss=0.04119, over 1422894.16 frames.], batch size: 21, lr: 5.09e-04
+2022-05-14 18:02:09,583 INFO [train.py:812] (2/8) Epoch 15, batch 4050, loss[loss=0.1649, simple_loss=0.2624, pruned_loss=0.03369, over 7223.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2586, pruned_loss=0.04026, over 1427107.73 frames.], batch size: 21, lr: 5.09e-04
+2022-05-14 18:03:08,716 INFO [train.py:812] (2/8) Epoch 15, batch 4100, loss[loss=0.1972, simple_loss=0.2929, pruned_loss=0.05075, over 7209.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2589, pruned_loss=0.04069, over 1418965.44 frames.], batch size: 23, lr: 5.09e-04
+2022-05-14 18:04:07,595 INFO [train.py:812] (2/8) Epoch 15, batch 4150, loss[loss=0.2373, simple_loss=0.3086, pruned_loss=0.08306, over 4745.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2592, pruned_loss=0.04125, over 1412386.53 frames.], batch size: 53, lr: 5.08e-04
+2022-05-14 18:05:07,075 INFO [train.py:812] (2/8) Epoch 15, batch 4200, loss[loss=0.1554, simple_loss=0.2515, pruned_loss=0.02969, over 7228.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2579, pruned_loss=0.0408, over 1410147.31 frames.], batch size: 20, lr: 5.08e-04
+2022-05-14 18:06:06,020 INFO [train.py:812] (2/8) Epoch 15, batch 4250, loss[loss=0.1531, simple_loss=0.2388, pruned_loss=0.03369, over 7073.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2575, pruned_loss=0.04087, over 1408176.45 frames.], batch size: 18, lr: 5.08e-04
+2022-05-14 18:07:05,204 INFO [train.py:812] (2/8) Epoch 15, batch 4300, loss[loss=0.1454, simple_loss=0.2245, pruned_loss=0.03311, over 7209.00 frames.], tot_loss[loss=0.1702, simple_loss=0.258, pruned_loss=0.04126, over 1404044.69 frames.], batch size: 16, lr: 5.08e-04
+2022-05-14 18:08:04,130 INFO [train.py:812] (2/8) Epoch 15, batch 4350, loss[loss=0.1733, simple_loss=0.2657, pruned_loss=0.0404, over 7327.00 frames.], tot_loss[loss=0.17, simple_loss=0.2584, pruned_loss=0.04079, over 1408215.88 frames.], batch size: 21, lr: 5.08e-04
+2022-05-14 18:09:03,564 INFO [train.py:812] (2/8) Epoch 15, batch 4400, loss[loss=0.1437, simple_loss=0.2364, pruned_loss=0.02555, over 7146.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2578, pruned_loss=0.04055, over 1410483.51 frames.], batch size: 19, lr: 5.08e-04
+2022-05-14 18:10:02,497 INFO [train.py:812] (2/8) Epoch 15, batch 4450, loss[loss=0.138, simple_loss=0.2227, pruned_loss=0.02667, over 7157.00 frames.], tot_loss[loss=0.169, simple_loss=0.2569, pruned_loss=0.04061, over 1402951.21 frames.], batch size: 18, lr: 5.07e-04
+2022-05-14 18:11:01,365 INFO [train.py:812] (2/8) Epoch 15, batch 4500, loss[loss=0.1675, simple_loss=0.2549, pruned_loss=0.04007, over 7458.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2573, pruned_loss=0.04073, over 1394192.48 frames.], batch size: 19, lr: 5.07e-04
+2022-05-14 18:11:59,640 INFO [train.py:812] (2/8) Epoch 15, batch 4550, loss[loss=0.2304, simple_loss=0.3078, pruned_loss=0.07652, over 4697.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2587, pruned_loss=0.04185, over 1367536.07 frames.], batch size: 52, lr: 5.07e-04
+2022-05-14 18:13:08,752 INFO [train.py:812] (2/8) Epoch 16, batch 0, loss[loss=0.1827, simple_loss=0.272, pruned_loss=0.04667, over 7301.00 frames.], tot_loss[loss=0.1827, simple_loss=0.272, pruned_loss=0.04667, over 7301.00 frames.], batch size: 24, lr: 4.92e-04
+2022-05-14 18:14:07,982 INFO [train.py:812] (2/8) Epoch 16, batch 50, loss[loss=0.161, simple_loss=0.2432, pruned_loss=0.03944, over 7398.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2619, pruned_loss=0.04193, over 320675.39 frames.], batch size: 18, lr: 4.92e-04
+2022-05-14 18:15:07,119 INFO [train.py:812] (2/8) Epoch 16, batch 100, loss[loss=0.173, simple_loss=0.2647, pruned_loss=0.04058, over 7330.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2591, pruned_loss=0.04093, over 564019.73 frames.], batch size: 20, lr: 4.92e-04
+2022-05-14 18:16:06,340 INFO [train.py:812] (2/8) Epoch 16, batch 150, loss[loss=0.1624, simple_loss=0.2621, pruned_loss=0.03137, over 7149.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2596, pruned_loss=0.04157, over 753819.71 frames.], batch size: 20, lr: 4.92e-04
+2022-05-14 18:17:15,049 INFO [train.py:812] (2/8) Epoch 16, batch 200, loss[loss=0.1668, simple_loss=0.268, pruned_loss=0.03284, over 7108.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2585, pruned_loss=0.0404, over 898172.81 frames.], batch size: 21, lr: 4.91e-04
+2022-05-14 18:18:13,073 INFO [train.py:812] (2/8) Epoch 16, batch 250, loss[loss=0.1516, simple_loss=0.2401, pruned_loss=0.03156, over 7156.00 frames.], tot_loss[loss=0.1691, simple_loss=0.258, pruned_loss=0.04011, over 1015032.48 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:19:12,327 INFO [train.py:812] (2/8) Epoch 16, batch 300, loss[loss=0.1559, simple_loss=0.2465, pruned_loss=0.03269, over 7155.00 frames.], tot_loss[loss=0.1683, simple_loss=0.257, pruned_loss=0.03973, over 1108662.47 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:20:11,382 INFO [train.py:812] (2/8) Epoch 16, batch 350, loss[loss=0.145, simple_loss=0.2307, pruned_loss=0.02965, over 7278.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2577, pruned_loss=0.04008, over 1179680.48 frames.], batch size: 18, lr: 4.91e-04
+2022-05-14 18:21:11,298 INFO [train.py:812] (2/8) Epoch 16, batch 400, loss[loss=0.1545, simple_loss=0.2423, pruned_loss=0.03339, over 7258.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2589, pruned_loss=0.03995, over 1234509.69 frames.], batch size: 19, lr: 4.91e-04
+2022-05-14 18:22:10,133 INFO [train.py:812] (2/8) Epoch 16, batch 450, loss[loss=0.1477, simple_loss=0.2444, pruned_loss=0.02549, over 7423.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2588, pruned_loss=0.04002, over 1281383.33 frames.], batch size: 20, lr: 4.91e-04
+2022-05-14 18:23:09,260 INFO [train.py:812] (2/8) Epoch 16, batch 500, loss[loss=0.2097, simple_loss=0.3022, pruned_loss=0.05858, over 7178.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2589, pruned_loss=0.03993, over 1318084.59 frames.], batch size: 23, lr: 4.90e-04
+2022-05-14 18:24:07,724 INFO [train.py:812] (2/8) Epoch 16, batch 550, loss[loss=0.1549, simple_loss=0.242, pruned_loss=0.03394, over 7288.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2577, pruned_loss=0.03969, over 1345311.67 frames.], batch size: 18, lr: 4.90e-04
+2022-05-14 18:25:07,651 INFO [train.py:812] (2/8) Epoch 16, batch 600, loss[loss=0.1774, simple_loss=0.2642, pruned_loss=0.04532, over 7163.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2575, pruned_loss=0.0396, over 1360517.10 frames.], batch size: 19, lr: 4.90e-04
+2022-05-14 18:26:06,740 INFO [train.py:812] (2/8) Epoch 16, batch 650, loss[loss=0.1975, simple_loss=0.2845, pruned_loss=0.05528, over 6361.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2575, pruned_loss=0.03984, over 1372884.00 frames.], batch size: 38, lr: 4.90e-04
+2022-05-14 18:27:05,467 INFO [train.py:812] (2/8) Epoch 16, batch 700, loss[loss=0.1852, simple_loss=0.2752, pruned_loss=0.0476, over 6974.00 frames.], tot_loss[loss=0.169, simple_loss=0.2579, pruned_loss=0.04009, over 1385751.85 frames.], batch size: 28, lr: 4.90e-04
+2022-05-14 18:28:04,358 INFO [train.py:812] (2/8) Epoch 16, batch 750, loss[loss=0.2019, simple_loss=0.2824, pruned_loss=0.06067, over 7154.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2571, pruned_loss=0.03971, over 1394426.28 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:29:03,807 INFO [train.py:812] (2/8) Epoch 16, batch 800, loss[loss=0.1679, simple_loss=0.2623, pruned_loss=0.03678, over 7248.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2572, pruned_loss=0.03973, over 1401717.72 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:30:02,509 INFO [train.py:812] (2/8) Epoch 16, batch 850, loss[loss=0.1529, simple_loss=0.25, pruned_loss=0.02795, over 7149.00 frames.], tot_loss[loss=0.1691, simple_loss=0.258, pruned_loss=0.04006, over 1403426.55 frames.], batch size: 20, lr: 4.89e-04
+2022-05-14 18:31:02,364 INFO [train.py:812] (2/8) Epoch 16, batch 900, loss[loss=0.1623, simple_loss=0.2534, pruned_loss=0.0356, over 7371.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2584, pruned_loss=0.04033, over 1402726.92 frames.], batch size: 19, lr: 4.89e-04
+2022-05-14 18:32:01,910 INFO [train.py:812] (2/8) Epoch 16, batch 950, loss[loss=0.177, simple_loss=0.2686, pruned_loss=0.04271, over 7441.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2579, pruned_loss=0.04011, over 1406109.96 frames.], batch size: 20, lr: 4.89e-04
+2022-05-14 18:33:00,789 INFO [train.py:812] (2/8) Epoch 16, batch 1000, loss[loss=0.1627, simple_loss=0.258, pruned_loss=0.03375, over 7296.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2569, pruned_loss=0.03976, over 1412514.91 frames.], batch size: 25, lr: 4.89e-04
+2022-05-14 18:33:59,605 INFO [train.py:812] (2/8) Epoch 16, batch 1050, loss[loss=0.1565, simple_loss=0.2427, pruned_loss=0.03509, over 7324.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2572, pruned_loss=0.03983, over 1417802.78 frames.], batch size: 20, lr: 4.88e-04
+2022-05-14 18:34:59,559 INFO [train.py:812] (2/8) Epoch 16, batch 1100, loss[loss=0.15, simple_loss=0.2337, pruned_loss=0.03319, over 7354.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2568, pruned_loss=0.03972, over 1420237.21 frames.], batch size: 19, lr: 4.88e-04
+2022-05-14 18:35:59,304 INFO [train.py:812] (2/8) Epoch 16, batch 1150, loss[loss=0.197, simple_loss=0.2743, pruned_loss=0.05981, over 4807.00 frames.], tot_loss[loss=0.167, simple_loss=0.2556, pruned_loss=0.03922, over 1420717.81 frames.], batch size: 52, lr: 4.88e-04
+2022-05-14 18:36:59,228 INFO [train.py:812] (2/8) Epoch 16, batch 1200, loss[loss=0.169, simple_loss=0.2605, pruned_loss=0.03874, over 7109.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2564, pruned_loss=0.03929, over 1419308.50 frames.], batch size: 21, lr: 4.88e-04
+2022-05-14 18:37:58,850 INFO [train.py:812] (2/8) Epoch 16, batch 1250, loss[loss=0.1471, simple_loss=0.2265, pruned_loss=0.03388, over 6736.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2561, pruned_loss=0.03949, over 1418983.15 frames.], batch size: 15, lr: 4.88e-04
+2022-05-14 18:38:58,780 INFO [train.py:812] (2/8) Epoch 16, batch 1300, loss[loss=0.2287, simple_loss=0.3007, pruned_loss=0.07839, over 7196.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2572, pruned_loss=0.03964, over 1425620.76 frames.], batch size: 22, lr: 4.88e-04
+2022-05-14 18:39:58,305 INFO [train.py:812] (2/8) Epoch 16, batch 1350, loss[loss=0.1495, simple_loss=0.2345, pruned_loss=0.03224, over 7159.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2571, pruned_loss=0.03979, over 1418966.32 frames.], batch size: 19, lr: 4.87e-04
+2022-05-14 18:40:58,008 INFO [train.py:812] (2/8) Epoch 16, batch 1400, loss[loss=0.1726, simple_loss=0.2695, pruned_loss=0.03785, over 7335.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2578, pruned_loss=0.03978, over 1416909.26 frames.], batch size: 22, lr: 4.87e-04
+2022-05-14 18:41:57,513 INFO [train.py:812] (2/8) Epoch 16, batch 1450, loss[loss=0.1794, simple_loss=0.2735, pruned_loss=0.04266, over 7398.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2581, pruned_loss=0.04017, over 1422869.84 frames.], batch size: 21, lr: 4.87e-04
+2022-05-14 18:43:06,576 INFO [train.py:812] (2/8) Epoch 16, batch 1500, loss[loss=0.1694, simple_loss=0.2626, pruned_loss=0.03814, over 7192.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2577, pruned_loss=0.03985, over 1422869.74 frames.], batch size: 23, lr: 4.87e-04
+2022-05-14 18:44:06,054 INFO [train.py:812] (2/8) Epoch 16, batch 1550, loss[loss=0.1316, simple_loss=0.2189, pruned_loss=0.02214, over 6807.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2571, pruned_loss=0.03973, over 1421282.51 frames.], batch size: 15, lr: 4.87e-04
+2022-05-14 18:45:05,966 INFO [train.py:812] (2/8) Epoch 16, batch 1600, loss[loss=0.1328, simple_loss=0.2154, pruned_loss=0.0251, over 6788.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2574, pruned_loss=0.04007, over 1423631.22 frames.], batch size: 15, lr: 4.87e-04
+2022-05-14 18:46:05,458 INFO [train.py:812] (2/8) Epoch 16, batch 1650, loss[loss=0.1758, simple_loss=0.2798, pruned_loss=0.03588, over 7140.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2573, pruned_loss=0.04013, over 1424571.42 frames.], batch size: 20, lr: 4.86e-04
+2022-05-14 18:47:14,902 INFO [train.py:812] (2/8) Epoch 16, batch 1700, loss[loss=0.1785, simple_loss=0.2709, pruned_loss=0.04303, over 7407.00 frames.], tot_loss[loss=0.168, simple_loss=0.2567, pruned_loss=0.03966, over 1424955.56 frames.], batch size: 18, lr: 4.86e-04
+2022-05-14 18:48:31,559 INFO [train.py:812] (2/8) Epoch 16, batch 1750, loss[loss=0.1699, simple_loss=0.2642, pruned_loss=0.03784, over 7380.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2574, pruned_loss=0.03999, over 1424431.72 frames.], batch size: 23, lr: 4.86e-04
+2022-05-14 18:49:49,346 INFO [train.py:812] (2/8) Epoch 16, batch 1800, loss[loss=0.1728, simple_loss=0.2622, pruned_loss=0.04167, over 7360.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2575, pruned_loss=0.04009, over 1422802.82 frames.], batch size: 19, lr: 4.86e-04
+2022-05-14 18:50:57,668 INFO [train.py:812] (2/8) Epoch 16, batch 1850, loss[loss=0.1982, simple_loss=0.3019, pruned_loss=0.04725, over 7147.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2573, pruned_loss=0.03984, over 1425348.96 frames.], batch size: 20, lr: 4.86e-04
+2022-05-14 18:51:57,517 INFO [train.py:812] (2/8) Epoch 16, batch 1900, loss[loss=0.1998, simple_loss=0.296, pruned_loss=0.05181, over 7319.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2568, pruned_loss=0.03966, over 1429028.28 frames.], batch size: 25, lr: 4.86e-04
+2022-05-14 18:52:55,109 INFO [train.py:812] (2/8) Epoch 16, batch 1950, loss[loss=0.1743, simple_loss=0.2675, pruned_loss=0.04055, over 7195.00 frames.], tot_loss[loss=0.169, simple_loss=0.2579, pruned_loss=0.04008, over 1429860.08 frames.], batch size: 23, lr: 4.85e-04
+2022-05-14 18:53:54,403 INFO [train.py:812] (2/8) Epoch 16, batch 2000, loss[loss=0.2207, simple_loss=0.3002, pruned_loss=0.07057, over 5295.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2585, pruned_loss=0.04012, over 1424162.86 frames.], batch size: 52, lr: 4.85e-04
+2022-05-14 18:54:53,355 INFO [train.py:812] (2/8) Epoch 16, batch 2050, loss[loss=0.1978, simple_loss=0.2815, pruned_loss=0.05706, over 6078.00 frames.], tot_loss[loss=0.17, simple_loss=0.2588, pruned_loss=0.04061, over 1422607.11 frames.], batch size: 37, lr: 4.85e-04
+2022-05-14 18:55:52,717 INFO [train.py:812] (2/8) Epoch 16, batch 2100, loss[loss=0.1699, simple_loss=0.2645, pruned_loss=0.03769, over 7123.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2597, pruned_loss=0.04085, over 1423277.71 frames.], batch size: 21, lr: 4.85e-04
+2022-05-14 18:56:51,657 INFO [train.py:812] (2/8) Epoch 16, batch 2150, loss[loss=0.1526, simple_loss=0.2385, pruned_loss=0.03341, over 7258.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2599, pruned_loss=0.04064, over 1418127.13 frames.], batch size: 19, lr: 4.85e-04
+2022-05-14 18:57:50,992 INFO [train.py:812] (2/8) Epoch 16, batch 2200, loss[loss=0.1623, simple_loss=0.2558, pruned_loss=0.03437, over 7193.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2591, pruned_loss=0.04066, over 1415399.21 frames.], batch size: 22, lr: 4.84e-04
+2022-05-14 18:58:50,185 INFO [train.py:812] (2/8) Epoch 16, batch 2250, loss[loss=0.1582, simple_loss=0.2461, pruned_loss=0.03515, over 7422.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2579, pruned_loss=0.04018, over 1417102.31 frames.], batch size: 21, lr: 4.84e-04
+2022-05-14 18:59:49,556 INFO [train.py:812] (2/8) Epoch 16, batch 2300, loss[loss=0.1799, simple_loss=0.2706, pruned_loss=0.04463, over 7198.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2584, pruned_loss=0.04028, over 1419107.15 frames.], batch size: 23, lr: 4.84e-04
+2022-05-14 19:00:48,683 INFO [train.py:812] (2/8) Epoch 16, batch 2350, loss[loss=0.1787, simple_loss=0.2702, pruned_loss=0.0436, over 7276.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2575, pruned_loss=0.03986, over 1421647.54 frames.], batch size: 25, lr: 4.84e-04
+2022-05-14 19:01:48,354 INFO [train.py:812] (2/8) Epoch 16, batch 2400, loss[loss=0.2106, simple_loss=0.301, pruned_loss=0.06014, over 7293.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2569, pruned_loss=0.0399, over 1425195.73 frames.], batch size: 25, lr: 4.84e-04
+2022-05-14 19:02:47,250 INFO [train.py:812] (2/8) Epoch 16, batch 2450, loss[loss=0.1701, simple_loss=0.2578, pruned_loss=0.04116, over 6806.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2574, pruned_loss=0.03976, over 1424134.59 frames.], batch size: 31, lr: 4.84e-04
+2022-05-14 19:03:46,830 INFO [train.py:812] (2/8) Epoch 16, batch 2500, loss[loss=0.167, simple_loss=0.2586, pruned_loss=0.03774, over 7215.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2562, pruned_loss=0.0391, over 1428000.14 frames.], batch size: 21, lr: 4.83e-04
+2022-05-14 19:04:46,113 INFO [train.py:812] (2/8) Epoch 16, batch 2550, loss[loss=0.1513, simple_loss=0.2498, pruned_loss=0.02637, over 7148.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2559, pruned_loss=0.03921, over 1424591.27 frames.], batch size: 20, lr: 4.83e-04
+2022-05-14 19:05:45,579 INFO [train.py:812] (2/8) Epoch 16, batch 2600, loss[loss=0.1506, simple_loss=0.2449, pruned_loss=0.02822, over 7358.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2556, pruned_loss=0.03915, over 1423345.20 frames.], batch size: 19, lr: 4.83e-04
+2022-05-14 19:06:45,277 INFO [train.py:812] (2/8) Epoch 16, batch 2650, loss[loss=0.1679, simple_loss=0.2615, pruned_loss=0.03713, over 7386.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2561, pruned_loss=0.03945, over 1424062.89 frames.], batch size: 23, lr: 4.83e-04
+2022-05-14 19:07:45,168 INFO [train.py:812] (2/8) Epoch 16, batch 2700, loss[loss=0.1781, simple_loss=0.2784, pruned_loss=0.03886, over 7196.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2571, pruned_loss=0.04, over 1421459.84 frames.], batch size: 26, lr: 4.83e-04
+2022-05-14 19:08:44,301 INFO [train.py:812] (2/8) Epoch 16, batch 2750, loss[loss=0.1392, simple_loss=0.2237, pruned_loss=0.02735, over 7277.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2571, pruned_loss=0.03954, over 1424980.07 frames.], batch size: 18, lr: 4.83e-04
+2022-05-14 19:09:44,179 INFO [train.py:812] (2/8) Epoch 16, batch 2800, loss[loss=0.1859, simple_loss=0.2742, pruned_loss=0.0488, over 7214.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2575, pruned_loss=0.03956, over 1427227.09 frames.], batch size: 21, lr: 4.82e-04
+2022-05-14 19:10:43,382 INFO [train.py:812] (2/8) Epoch 16, batch 2850, loss[loss=0.1499, simple_loss=0.2374, pruned_loss=0.0312, over 7172.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2581, pruned_loss=0.04012, over 1425310.54 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:11:42,829 INFO [train.py:812] (2/8) Epoch 16, batch 2900, loss[loss=0.14, simple_loss=0.2291, pruned_loss=0.02547, over 7174.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2574, pruned_loss=0.03952, over 1428129.22 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:12:41,624 INFO [train.py:812] (2/8) Epoch 16, batch 2950, loss[loss=0.1602, simple_loss=0.2583, pruned_loss=0.03109, over 7347.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2577, pruned_loss=0.03976, over 1424576.40 frames.], batch size: 22, lr: 4.82e-04
+2022-05-14 19:13:40,833 INFO [train.py:812] (2/8) Epoch 16, batch 3000, loss[loss=0.1636, simple_loss=0.2516, pruned_loss=0.03781, over 7419.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2575, pruned_loss=0.04003, over 1428695.81 frames.], batch size: 21, lr: 4.82e-04
+2022-05-14 19:13:40,834 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 19:13:48,992 INFO [train.py:841] (2/8) Epoch 16, validation: loss=0.1537, simple_loss=0.2535, pruned_loss=0.02695, over 698248.00 frames.
+2022-05-14 19:14:47,148 INFO [train.py:812] (2/8) Epoch 16, batch 3050, loss[loss=0.1585, simple_loss=0.232, pruned_loss=0.04249, over 7415.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2567, pruned_loss=0.0399, over 1427110.84 frames.], batch size: 18, lr: 4.82e-04
+2022-05-14 19:15:46,737 INFO [train.py:812] (2/8) Epoch 16, batch 3100, loss[loss=0.2345, simple_loss=0.3059, pruned_loss=0.08158, over 7205.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2569, pruned_loss=0.04, over 1427288.03 frames.], batch size: 23, lr: 4.81e-04
+2022-05-14 19:16:44,974 INFO [train.py:812] (2/8) Epoch 16, batch 3150, loss[loss=0.141, simple_loss=0.222, pruned_loss=0.03, over 7153.00 frames.], tot_loss[loss=0.1682, simple_loss=0.257, pruned_loss=0.03964, over 1424376.79 frames.], batch size: 18, lr: 4.81e-04
+2022-05-14 19:17:47,857 INFO [train.py:812] (2/8) Epoch 16, batch 3200, loss[loss=0.206, simple_loss=0.2903, pruned_loss=0.06086, over 7276.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2583, pruned_loss=0.04004, over 1423734.38 frames.], batch size: 24, lr: 4.81e-04
+2022-05-14 19:18:47,168 INFO [train.py:812] (2/8) Epoch 16, batch 3250, loss[loss=0.1903, simple_loss=0.2854, pruned_loss=0.04766, over 7321.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2572, pruned_loss=0.03986, over 1424644.05 frames.], batch size: 21, lr: 4.81e-04
+2022-05-14 19:19:45,410 INFO [train.py:812] (2/8) Epoch 16, batch 3300, loss[loss=0.1804, simple_loss=0.2791, pruned_loss=0.04085, over 7280.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2583, pruned_loss=0.03977, over 1428831.99 frames.], batch size: 25, lr: 4.81e-04
+2022-05-14 19:20:42,556 INFO [train.py:812] (2/8) Epoch 16, batch 3350, loss[loss=0.1539, simple_loss=0.2445, pruned_loss=0.03162, over 7234.00 frames.], tot_loss[loss=0.1689, simple_loss=0.258, pruned_loss=0.03993, over 1430949.48 frames.], batch size: 20, lr: 4.81e-04
+2022-05-14 19:21:41,196 INFO [train.py:812] (2/8) Epoch 16, batch 3400, loss[loss=0.1729, simple_loss=0.2642, pruned_loss=0.04084, over 7066.00 frames.], tot_loss[loss=0.1687, simple_loss=0.258, pruned_loss=0.03972, over 1428205.80 frames.], batch size: 28, lr: 4.80e-04
+2022-05-14 19:22:40,327 INFO [train.py:812] (2/8) Epoch 16, batch 3450, loss[loss=0.1613, simple_loss=0.2481, pruned_loss=0.03729, over 7369.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2574, pruned_loss=0.03974, over 1429815.65 frames.], batch size: 19, lr: 4.80e-04
+2022-05-14 19:23:40,337 INFO [train.py:812] (2/8) Epoch 16, batch 3500, loss[loss=0.179, simple_loss=0.2721, pruned_loss=0.04291, over 7320.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2572, pruned_loss=0.04011, over 1428183.36 frames.], batch size: 21, lr: 4.80e-04
+2022-05-14 19:24:39,219 INFO [train.py:812] (2/8) Epoch 16, batch 3550, loss[loss=0.2027, simple_loss=0.2881, pruned_loss=0.05868, over 7217.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2582, pruned_loss=0.04069, over 1424523.45 frames.], batch size: 26, lr: 4.80e-04
+2022-05-14 19:25:38,879 INFO [train.py:812] (2/8) Epoch 16, batch 3600, loss[loss=0.2129, simple_loss=0.3074, pruned_loss=0.05925, over 7315.00 frames.], tot_loss[loss=0.1704, simple_loss=0.259, pruned_loss=0.04091, over 1426147.57 frames.], batch size: 21, lr: 4.80e-04
+2022-05-14 19:26:37,922 INFO [train.py:812] (2/8) Epoch 16, batch 3650, loss[loss=0.1779, simple_loss=0.2496, pruned_loss=0.05313, over 7289.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2582, pruned_loss=0.0404, over 1426406.98 frames.], batch size: 18, lr: 4.80e-04
+2022-05-14 19:27:36,131 INFO [train.py:812] (2/8) Epoch 16, batch 3700, loss[loss=0.1421, simple_loss=0.2225, pruned_loss=0.0308, over 6791.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2578, pruned_loss=0.04016, over 1423154.23 frames.], batch size: 15, lr: 4.79e-04
+2022-05-14 19:28:35,322 INFO [train.py:812] (2/8) Epoch 16, batch 3750, loss[loss=0.1887, simple_loss=0.274, pruned_loss=0.05168, over 7280.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2577, pruned_loss=0.04008, over 1420469.36 frames.], batch size: 25, lr: 4.79e-04
+2022-05-14 19:29:33,342 INFO [train.py:812] (2/8) Epoch 16, batch 3800, loss[loss=0.1373, simple_loss=0.22, pruned_loss=0.0273, over 7151.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2583, pruned_loss=0.04014, over 1424550.54 frames.], batch size: 17, lr: 4.79e-04
+2022-05-14 19:30:31,551 INFO [train.py:812] (2/8) Epoch 16, batch 3850, loss[loss=0.1494, simple_loss=0.2316, pruned_loss=0.03365, over 7262.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2584, pruned_loss=0.04022, over 1420739.67 frames.], batch size: 18, lr: 4.79e-04
+2022-05-14 19:31:29,706 INFO [train.py:812] (2/8) Epoch 16, batch 3900, loss[loss=0.1665, simple_loss=0.2649, pruned_loss=0.03403, over 7226.00 frames.], tot_loss[loss=0.17, simple_loss=0.2589, pruned_loss=0.04058, over 1422942.54 frames.], batch size: 21, lr: 4.79e-04
+2022-05-14 19:32:28,967 INFO [train.py:812] (2/8) Epoch 16, batch 3950, loss[loss=0.168, simple_loss=0.2659, pruned_loss=0.03506, over 7239.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2588, pruned_loss=0.04033, over 1421812.19 frames.], batch size: 20, lr: 4.79e-04
+2022-05-14 19:33:27,633 INFO [train.py:812] (2/8) Epoch 16, batch 4000, loss[loss=0.1661, simple_loss=0.2624, pruned_loss=0.03485, over 7318.00 frames.], tot_loss[loss=0.169, simple_loss=0.2582, pruned_loss=0.03991, over 1419310.48 frames.], batch size: 21, lr: 4.79e-04
+2022-05-14 19:34:27,162 INFO [train.py:812] (2/8) Epoch 16, batch 4050, loss[loss=0.1563, simple_loss=0.2335, pruned_loss=0.03956, over 7171.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2579, pruned_loss=0.03982, over 1417409.17 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:35:27,342 INFO [train.py:812] (2/8) Epoch 16, batch 4100, loss[loss=0.1429, simple_loss=0.234, pruned_loss=0.02592, over 7164.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2575, pruned_loss=0.03963, over 1423747.25 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:36:26,214 INFO [train.py:812] (2/8) Epoch 16, batch 4150, loss[loss=0.1716, simple_loss=0.2652, pruned_loss=0.03899, over 7079.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2577, pruned_loss=0.03984, over 1418609.94 frames.], batch size: 28, lr: 4.78e-04
+2022-05-14 19:37:25,121 INFO [train.py:812] (2/8) Epoch 16, batch 4200, loss[loss=0.1517, simple_loss=0.2359, pruned_loss=0.0337, over 7013.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2575, pruned_loss=0.03965, over 1418265.77 frames.], batch size: 16, lr: 4.78e-04
+2022-05-14 19:38:24,443 INFO [train.py:812] (2/8) Epoch 16, batch 4250, loss[loss=0.1832, simple_loss=0.258, pruned_loss=0.05425, over 7166.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2568, pruned_loss=0.03985, over 1417342.21 frames.], batch size: 18, lr: 4.78e-04
+2022-05-14 19:39:23,833 INFO [train.py:812] (2/8) Epoch 16, batch 4300, loss[loss=0.1726, simple_loss=0.2562, pruned_loss=0.0445, over 6850.00 frames.], tot_loss[loss=0.1672, simple_loss=0.256, pruned_loss=0.03917, over 1412427.45 frames.], batch size: 31, lr: 4.78e-04
+2022-05-14 19:40:22,728 INFO [train.py:812] (2/8) Epoch 16, batch 4350, loss[loss=0.1365, simple_loss=0.2348, pruned_loss=0.01911, over 7167.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2557, pruned_loss=0.03881, over 1415530.56 frames.], batch size: 18, lr: 4.77e-04
+2022-05-14 19:41:21,977 INFO [train.py:812] (2/8) Epoch 16, batch 4400, loss[loss=0.1764, simple_loss=0.2728, pruned_loss=0.04004, over 7119.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2564, pruned_loss=0.03891, over 1415532.30 frames.], batch size: 21, lr: 4.77e-04
+2022-05-14 19:42:18,615 INFO [train.py:812] (2/8) Epoch 16, batch 4450, loss[loss=0.2145, simple_loss=0.3111, pruned_loss=0.05896, over 7194.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2567, pruned_loss=0.03896, over 1409891.40 frames.], batch size: 22, lr: 4.77e-04
+2022-05-14 19:43:16,033 INFO [train.py:812] (2/8) Epoch 16, batch 4500, loss[loss=0.142, simple_loss=0.225, pruned_loss=0.0295, over 7148.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2567, pruned_loss=0.03934, over 1400341.46 frames.], batch size: 17, lr: 4.77e-04
+2022-05-14 19:44:12,838 INFO [train.py:812] (2/8) Epoch 16, batch 4550, loss[loss=0.1728, simple_loss=0.2563, pruned_loss=0.04468, over 4680.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2599, pruned_loss=0.04158, over 1350091.25 frames.], batch size: 52, lr: 4.77e-04
+2022-05-14 19:45:27,028 INFO [train.py:812] (2/8) Epoch 17, batch 0, loss[loss=0.1672, simple_loss=0.2525, pruned_loss=0.04099, over 7116.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2525, pruned_loss=0.04099, over 7116.00 frames.], batch size: 21, lr: 4.63e-04
+2022-05-14 19:46:26,102 INFO [train.py:812] (2/8) Epoch 17, batch 50, loss[loss=0.1892, simple_loss=0.2777, pruned_loss=0.0504, over 7313.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2605, pruned_loss=0.04328, over 317438.75 frames.], batch size: 21, lr: 4.63e-04
+2022-05-14 19:47:25,016 INFO [train.py:812] (2/8) Epoch 17, batch 100, loss[loss=0.1704, simple_loss=0.2633, pruned_loss=0.03876, over 7143.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2572, pruned_loss=0.04014, over 559593.43 frames.], batch size: 20, lr: 4.63e-04
+2022-05-14 19:48:23,591 INFO [train.py:812] (2/8) Epoch 17, batch 150, loss[loss=0.1449, simple_loss=0.2191, pruned_loss=0.03538, over 7000.00 frames.], tot_loss[loss=0.168, simple_loss=0.2566, pruned_loss=0.0397, over 747646.01 frames.], batch size: 16, lr: 4.63e-04
+2022-05-14 19:49:23,066 INFO [train.py:812] (2/8) Epoch 17, batch 200, loss[loss=0.1573, simple_loss=0.2474, pruned_loss=0.03363, over 7141.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2584, pruned_loss=0.03973, over 897060.46 frames.], batch size: 17, lr: 4.63e-04
+2022-05-14 19:50:21,442 INFO [train.py:812] (2/8) Epoch 17, batch 250, loss[loss=0.1506, simple_loss=0.2391, pruned_loss=0.03106, over 7255.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2582, pruned_loss=0.03965, over 1016374.34 frames.], batch size: 19, lr: 4.63e-04
+2022-05-14 19:51:20,347 INFO [train.py:812] (2/8) Epoch 17, batch 300, loss[loss=0.1437, simple_loss=0.2242, pruned_loss=0.03154, over 7072.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2578, pruned_loss=0.03966, over 1102024.85 frames.], batch size: 18, lr: 4.62e-04
+2022-05-14 19:52:19,560 INFO [train.py:812] (2/8) Epoch 17, batch 350, loss[loss=0.1649, simple_loss=0.2419, pruned_loss=0.0439, over 7244.00 frames.], tot_loss[loss=0.168, simple_loss=0.2567, pruned_loss=0.03971, over 1172174.12 frames.], batch size: 16, lr: 4.62e-04
+2022-05-14 19:53:18,623 INFO [train.py:812] (2/8) Epoch 17, batch 400, loss[loss=0.2133, simple_loss=0.3062, pruned_loss=0.06025, over 4832.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2574, pruned_loss=0.0398, over 1227514.04 frames.], batch size: 53, lr: 4.62e-04
+2022-05-14 19:54:16,197 INFO [train.py:812] (2/8) Epoch 17, batch 450, loss[loss=0.1239, simple_loss=0.211, pruned_loss=0.01839, over 7360.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2575, pruned_loss=0.03979, over 1267851.29 frames.], batch size: 19, lr: 4.62e-04
+2022-05-14 19:55:14,835 INFO [train.py:812] (2/8) Epoch 17, batch 500, loss[loss=0.1495, simple_loss=0.2243, pruned_loss=0.03732, over 7169.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2565, pruned_loss=0.03919, over 1301304.81 frames.], batch size: 18, lr: 4.62e-04
+2022-05-14 19:56:13,701 INFO [train.py:812] (2/8) Epoch 17, batch 550, loss[loss=0.1749, simple_loss=0.2404, pruned_loss=0.05468, over 7130.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2562, pruned_loss=0.03898, over 1327300.78 frames.], batch size: 17, lr: 4.62e-04
+2022-05-14 19:57:12,588 INFO [train.py:812] (2/8) Epoch 17, batch 600, loss[loss=0.1653, simple_loss=0.2702, pruned_loss=0.03016, over 7044.00 frames.], tot_loss[loss=0.168, simple_loss=0.2573, pruned_loss=0.03931, over 1342252.18 frames.], batch size: 28, lr: 4.62e-04
+2022-05-14 19:58:11,624 INFO [train.py:812] (2/8) Epoch 17, batch 650, loss[loss=0.1407, simple_loss=0.2283, pruned_loss=0.02652, over 7334.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2572, pruned_loss=0.03913, over 1360608.53 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 19:59:10,291 INFO [train.py:812] (2/8) Epoch 17, batch 700, loss[loss=0.1628, simple_loss=0.2551, pruned_loss=0.03524, over 7269.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2582, pruned_loss=0.03939, over 1367264.55 frames.], batch size: 19, lr: 4.61e-04
+2022-05-14 20:00:09,353 INFO [train.py:812] (2/8) Epoch 17, batch 750, loss[loss=0.181, simple_loss=0.2662, pruned_loss=0.04788, over 7137.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2583, pruned_loss=0.03973, over 1376173.34 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 20:01:08,200 INFO [train.py:812] (2/8) Epoch 17, batch 800, loss[loss=0.1513, simple_loss=0.2405, pruned_loss=0.03102, over 7154.00 frames.], tot_loss[loss=0.1687, simple_loss=0.258, pruned_loss=0.03975, over 1387008.35 frames.], batch size: 19, lr: 4.61e-04
+2022-05-14 20:02:07,163 INFO [train.py:812] (2/8) Epoch 17, batch 850, loss[loss=0.1707, simple_loss=0.2606, pruned_loss=0.0404, over 6353.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2569, pruned_loss=0.0396, over 1396027.11 frames.], batch size: 38, lr: 4.61e-04
+2022-05-14 20:03:05,135 INFO [train.py:812] (2/8) Epoch 17, batch 900, loss[loss=0.1723, simple_loss=0.2565, pruned_loss=0.0441, over 7326.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2574, pruned_loss=0.03941, over 1407498.22 frames.], batch size: 20, lr: 4.61e-04
+2022-05-14 20:04:03,147 INFO [train.py:812] (2/8) Epoch 17, batch 950, loss[loss=0.1498, simple_loss=0.2309, pruned_loss=0.03438, over 7148.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2563, pruned_loss=0.03893, over 1412734.74 frames.], batch size: 17, lr: 4.60e-04
+2022-05-14 20:05:01,746 INFO [train.py:812] (2/8) Epoch 17, batch 1000, loss[loss=0.1821, simple_loss=0.2798, pruned_loss=0.04218, over 7114.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2572, pruned_loss=0.03947, over 1416831.00 frames.], batch size: 21, lr: 4.60e-04
+2022-05-14 20:06:00,416 INFO [train.py:812] (2/8) Epoch 17, batch 1050, loss[loss=0.1942, simple_loss=0.2969, pruned_loss=0.04576, over 7330.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2563, pruned_loss=0.03904, over 1420732.65 frames.], batch size: 22, lr: 4.60e-04
+2022-05-14 20:06:59,591 INFO [train.py:812] (2/8) Epoch 17, batch 1100, loss[loss=0.1744, simple_loss=0.2624, pruned_loss=0.04319, over 7289.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2565, pruned_loss=0.03888, over 1421048.43 frames.], batch size: 24, lr: 4.60e-04
+2022-05-14 20:07:58,271 INFO [train.py:812] (2/8) Epoch 17, batch 1150, loss[loss=0.1822, simple_loss=0.2765, pruned_loss=0.0439, over 7308.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2571, pruned_loss=0.0389, over 1422597.18 frames.], batch size: 24, lr: 4.60e-04
+2022-05-14 20:08:57,634 INFO [train.py:812] (2/8) Epoch 17, batch 1200, loss[loss=0.2437, simple_loss=0.3257, pruned_loss=0.08091, over 7316.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2576, pruned_loss=0.03949, over 1419964.64 frames.], batch size: 25, lr: 4.60e-04
+2022-05-14 20:09:55,620 INFO [train.py:812] (2/8) Epoch 17, batch 1250, loss[loss=0.1587, simple_loss=0.2396, pruned_loss=0.03894, over 7269.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2576, pruned_loss=0.03974, over 1415119.45 frames.], batch size: 18, lr: 4.60e-04
+2022-05-14 20:10:53,529 INFO [train.py:812] (2/8) Epoch 17, batch 1300, loss[loss=0.1589, simple_loss=0.254, pruned_loss=0.03183, over 7339.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2568, pruned_loss=0.03984, over 1413155.95 frames.], batch size: 22, lr: 4.59e-04
+2022-05-14 20:11:51,716 INFO [train.py:812] (2/8) Epoch 17, batch 1350, loss[loss=0.1591, simple_loss=0.2471, pruned_loss=0.03555, over 6993.00 frames.], tot_loss[loss=0.1682, simple_loss=0.257, pruned_loss=0.03974, over 1418291.25 frames.], batch size: 16, lr: 4.59e-04
+2022-05-14 20:12:51,097 INFO [train.py:812] (2/8) Epoch 17, batch 1400, loss[loss=0.1746, simple_loss=0.2599, pruned_loss=0.0447, over 7151.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2559, pruned_loss=0.03959, over 1420101.40 frames.], batch size: 20, lr: 4.59e-04
+2022-05-14 20:13:49,653 INFO [train.py:812] (2/8) Epoch 17, batch 1450, loss[loss=0.1714, simple_loss=0.2633, pruned_loss=0.03977, over 7328.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2554, pruned_loss=0.03892, over 1420051.90 frames.], batch size: 22, lr: 4.59e-04
+2022-05-14 20:14:48,946 INFO [train.py:812] (2/8) Epoch 17, batch 1500, loss[loss=0.1762, simple_loss=0.2577, pruned_loss=0.04735, over 7256.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2543, pruned_loss=0.0386, over 1425467.71 frames.], batch size: 19, lr: 4.59e-04
+2022-05-14 20:15:57,360 INFO [train.py:812] (2/8) Epoch 17, batch 1550, loss[loss=0.1588, simple_loss=0.2456, pruned_loss=0.03598, over 7219.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2546, pruned_loss=0.03861, over 1422775.39 frames.], batch size: 21, lr: 4.59e-04
+2022-05-14 20:16:56,816 INFO [train.py:812] (2/8) Epoch 17, batch 1600, loss[loss=0.1631, simple_loss=0.2634, pruned_loss=0.0314, over 7431.00 frames.], tot_loss[loss=0.1652, simple_loss=0.254, pruned_loss=0.03823, over 1427103.10 frames.], batch size: 20, lr: 4.58e-04
+2022-05-14 20:17:55,348 INFO [train.py:812] (2/8) Epoch 17, batch 1650, loss[loss=0.1724, simple_loss=0.2675, pruned_loss=0.03866, over 7414.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2555, pruned_loss=0.03897, over 1429337.47 frames.], batch size: 21, lr: 4.58e-04
+2022-05-14 20:18:53,694 INFO [train.py:812] (2/8) Epoch 17, batch 1700, loss[loss=0.1856, simple_loss=0.2737, pruned_loss=0.04882, over 5036.00 frames.], tot_loss[loss=0.1671, simple_loss=0.256, pruned_loss=0.03908, over 1423395.02 frames.], batch size: 52, lr: 4.58e-04
+2022-05-14 20:19:52,405 INFO [train.py:812] (2/8) Epoch 17, batch 1750, loss[loss=0.2047, simple_loss=0.2872, pruned_loss=0.06111, over 7373.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2572, pruned_loss=0.03985, over 1414455.36 frames.], batch size: 23, lr: 4.58e-04
+2022-05-14 20:20:51,549 INFO [train.py:812] (2/8) Epoch 17, batch 1800, loss[loss=0.1839, simple_loss=0.2731, pruned_loss=0.04733, over 7185.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2565, pruned_loss=0.03922, over 1415740.72 frames.], batch size: 23, lr: 4.58e-04
+2022-05-14 20:21:48,767 INFO [train.py:812] (2/8) Epoch 17, batch 1850, loss[loss=0.1763, simple_loss=0.2687, pruned_loss=0.04199, over 6486.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2565, pruned_loss=0.03962, over 1417298.61 frames.], batch size: 38, lr: 4.58e-04
+2022-05-14 20:22:47,371 INFO [train.py:812] (2/8) Epoch 17, batch 1900, loss[loss=0.1788, simple_loss=0.2653, pruned_loss=0.04612, over 7427.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2574, pruned_loss=0.04013, over 1421605.98 frames.], batch size: 20, lr: 4.58e-04
+2022-05-14 20:23:46,134 INFO [train.py:812] (2/8) Epoch 17, batch 1950, loss[loss=0.1457, simple_loss=0.2466, pruned_loss=0.02243, over 7304.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2572, pruned_loss=0.03981, over 1424002.49 frames.], batch size: 21, lr: 4.57e-04
+2022-05-14 20:24:44,624 INFO [train.py:812] (2/8) Epoch 17, batch 2000, loss[loss=0.1628, simple_loss=0.2481, pruned_loss=0.03875, over 7265.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2575, pruned_loss=0.03976, over 1425392.59 frames.], batch size: 19, lr: 4.57e-04
+2022-05-14 20:25:43,662 INFO [train.py:812] (2/8) Epoch 17, batch 2050, loss[loss=0.1434, simple_loss=0.2317, pruned_loss=0.02758, over 7412.00 frames.], tot_loss[loss=0.1673, simple_loss=0.256, pruned_loss=0.0393, over 1428963.28 frames.], batch size: 18, lr: 4.57e-04
+2022-05-14 20:26:43,361 INFO [train.py:812] (2/8) Epoch 17, batch 2100, loss[loss=0.1592, simple_loss=0.2485, pruned_loss=0.03502, over 7415.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2557, pruned_loss=0.03879, over 1429292.65 frames.], batch size: 21, lr: 4.57e-04
+2022-05-14 20:27:42,662 INFO [train.py:812] (2/8) Epoch 17, batch 2150, loss[loss=0.1712, simple_loss=0.2503, pruned_loss=0.04607, over 7349.00 frames.], tot_loss[loss=0.167, simple_loss=0.2558, pruned_loss=0.0391, over 1425907.75 frames.], batch size: 19, lr: 4.57e-04
+2022-05-14 20:28:40,127 INFO [train.py:812] (2/8) Epoch 17, batch 2200, loss[loss=0.1741, simple_loss=0.2726, pruned_loss=0.03782, over 7349.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2559, pruned_loss=0.03895, over 1423137.26 frames.], batch size: 22, lr: 4.57e-04
+2022-05-14 20:29:39,278 INFO [train.py:812] (2/8) Epoch 17, batch 2250, loss[loss=0.175, simple_loss=0.2607, pruned_loss=0.04467, over 7413.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2569, pruned_loss=0.03929, over 1425124.55 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:30:37,980 INFO [train.py:812] (2/8) Epoch 17, batch 2300, loss[loss=0.1802, simple_loss=0.2682, pruned_loss=0.04613, over 7322.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2567, pruned_loss=0.03908, over 1423564.73 frames.], batch size: 24, lr: 4.56e-04
+2022-05-14 20:31:36,708 INFO [train.py:812] (2/8) Epoch 17, batch 2350, loss[loss=0.172, simple_loss=0.2545, pruned_loss=0.04475, over 7378.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2559, pruned_loss=0.03878, over 1426752.22 frames.], batch size: 23, lr: 4.56e-04
+2022-05-14 20:32:36,103 INFO [train.py:812] (2/8) Epoch 17, batch 2400, loss[loss=0.1481, simple_loss=0.2271, pruned_loss=0.03458, over 6995.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2554, pruned_loss=0.03855, over 1424448.31 frames.], batch size: 16, lr: 4.56e-04
+2022-05-14 20:33:34,529 INFO [train.py:812] (2/8) Epoch 17, batch 2450, loss[loss=0.1817, simple_loss=0.2756, pruned_loss=0.0439, over 7338.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2545, pruned_loss=0.03844, over 1423965.84 frames.], batch size: 22, lr: 4.56e-04
+2022-05-14 20:34:34,265 INFO [train.py:812] (2/8) Epoch 17, batch 2500, loss[loss=0.2114, simple_loss=0.3, pruned_loss=0.06139, over 7224.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2541, pruned_loss=0.03852, over 1423345.37 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:35:31,562 INFO [train.py:812] (2/8) Epoch 17, batch 2550, loss[loss=0.1571, simple_loss=0.2471, pruned_loss=0.03352, over 7217.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2548, pruned_loss=0.03889, over 1417605.18 frames.], batch size: 21, lr: 4.56e-04
+2022-05-14 20:36:37,551 INFO [train.py:812] (2/8) Epoch 17, batch 2600, loss[loss=0.1909, simple_loss=0.2658, pruned_loss=0.05806, over 6948.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2557, pruned_loss=0.03885, over 1420595.95 frames.], batch size: 28, lr: 4.55e-04
+2022-05-14 20:37:36,696 INFO [train.py:812] (2/8) Epoch 17, batch 2650, loss[loss=0.1601, simple_loss=0.2456, pruned_loss=0.0373, over 7355.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2564, pruned_loss=0.0394, over 1419125.73 frames.], batch size: 19, lr: 4.55e-04
+2022-05-14 20:38:34,787 INFO [train.py:812] (2/8) Epoch 17, batch 2700, loss[loss=0.207, simple_loss=0.2939, pruned_loss=0.06004, over 7332.00 frames.], tot_loss[loss=0.167, simple_loss=0.2554, pruned_loss=0.03927, over 1422287.98 frames.], batch size: 22, lr: 4.55e-04
+2022-05-14 20:39:32,812 INFO [train.py:812] (2/8) Epoch 17, batch 2750, loss[loss=0.1583, simple_loss=0.2645, pruned_loss=0.0261, over 7164.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2554, pruned_loss=0.03892, over 1422533.26 frames.], batch size: 19, lr: 4.55e-04
+2022-05-14 20:40:31,942 INFO [train.py:812] (2/8) Epoch 17, batch 2800, loss[loss=0.2139, simple_loss=0.2984, pruned_loss=0.06474, over 4864.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2545, pruned_loss=0.03853, over 1421975.50 frames.], batch size: 52, lr: 4.55e-04
+2022-05-14 20:41:30,553 INFO [train.py:812] (2/8) Epoch 17, batch 2850, loss[loss=0.1665, simple_loss=0.2644, pruned_loss=0.03434, over 7306.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2547, pruned_loss=0.03824, over 1421998.75 frames.], batch size: 21, lr: 4.55e-04
+2022-05-14 20:42:28,892 INFO [train.py:812] (2/8) Epoch 17, batch 2900, loss[loss=0.1547, simple_loss=0.2544, pruned_loss=0.02745, over 7235.00 frames.], tot_loss[loss=0.167, simple_loss=0.2559, pruned_loss=0.03903, over 1417835.16 frames.], batch size: 20, lr: 4.55e-04
+2022-05-14 20:43:27,764 INFO [train.py:812] (2/8) Epoch 17, batch 2950, loss[loss=0.1418, simple_loss=0.2278, pruned_loss=0.02791, over 7280.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2568, pruned_loss=0.03899, over 1418087.63 frames.], batch size: 18, lr: 4.54e-04
+2022-05-14 20:44:36,162 INFO [train.py:812] (2/8) Epoch 17, batch 3000, loss[loss=0.1639, simple_loss=0.2553, pruned_loss=0.03623, over 7142.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2564, pruned_loss=0.03848, over 1423669.04 frames.], batch size: 20, lr: 4.54e-04
+2022-05-14 20:44:36,162 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 20:44:43,902 INFO [train.py:841] (2/8) Epoch 17, validation: loss=0.1538, simple_loss=0.2534, pruned_loss=0.02708, over 698248.00 frames.
+2022-05-14 20:45:42,794 INFO [train.py:812] (2/8) Epoch 17, batch 3050, loss[loss=0.1636, simple_loss=0.2471, pruned_loss=0.0401, over 6492.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2572, pruned_loss=0.03905, over 1423443.36 frames.], batch size: 38, lr: 4.54e-04
+2022-05-14 20:46:41,076 INFO [train.py:812] (2/8) Epoch 17, batch 3100, loss[loss=0.1776, simple_loss=0.2679, pruned_loss=0.04372, over 7299.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2572, pruned_loss=0.03919, over 1420437.57 frames.], batch size: 25, lr: 4.54e-04
+2022-05-14 20:47:58,626 INFO [train.py:812] (2/8) Epoch 17, batch 3150, loss[loss=0.1661, simple_loss=0.2574, pruned_loss=0.03741, over 7329.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2564, pruned_loss=0.03923, over 1419333.08 frames.], batch size: 20, lr: 4.54e-04
+2022-05-14 20:49:07,336 INFO [train.py:812] (2/8) Epoch 17, batch 3200, loss[loss=0.1535, simple_loss=0.2433, pruned_loss=0.0319, over 7357.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2572, pruned_loss=0.0398, over 1418805.60 frames.], batch size: 19, lr: 4.54e-04
+2022-05-14 20:50:25,527 INFO [train.py:812] (2/8) Epoch 17, batch 3250, loss[loss=0.1619, simple_loss=0.2414, pruned_loss=0.0412, over 7062.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2568, pruned_loss=0.03964, over 1424343.53 frames.], batch size: 18, lr: 4.54e-04
+2022-05-14 20:51:34,463 INFO [train.py:812] (2/8) Epoch 17, batch 3300, loss[loss=0.208, simple_loss=0.3002, pruned_loss=0.05786, over 7159.00 frames.], tot_loss[loss=0.169, simple_loss=0.2577, pruned_loss=0.04013, over 1424738.86 frames.], batch size: 19, lr: 4.53e-04
+2022-05-14 20:52:33,319 INFO [train.py:812] (2/8) Epoch 17, batch 3350, loss[loss=0.1741, simple_loss=0.2703, pruned_loss=0.03898, over 7341.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2582, pruned_loss=0.03996, over 1426113.29 frames.], batch size: 22, lr: 4.53e-04
+2022-05-14 20:53:32,419 INFO [train.py:812] (2/8) Epoch 17, batch 3400, loss[loss=0.1878, simple_loss=0.2771, pruned_loss=0.04931, over 7133.00 frames.], tot_loss[loss=0.169, simple_loss=0.258, pruned_loss=0.04005, over 1423142.72 frames.], batch size: 20, lr: 4.53e-04
+2022-05-14 20:54:31,695 INFO [train.py:812] (2/8) Epoch 17, batch 3450, loss[loss=0.17, simple_loss=0.2633, pruned_loss=0.03833, over 7336.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2571, pruned_loss=0.03985, over 1424140.05 frames.], batch size: 20, lr: 4.53e-04
+2022-05-14 20:55:30,348 INFO [train.py:812] (2/8) Epoch 17, batch 3500, loss[loss=0.181, simple_loss=0.2719, pruned_loss=0.04501, over 7220.00 frames.], tot_loss[loss=0.168, simple_loss=0.2567, pruned_loss=0.03965, over 1423739.96 frames.], batch size: 22, lr: 4.53e-04
+2022-05-14 20:56:29,298 INFO [train.py:812] (2/8) Epoch 17, batch 3550, loss[loss=0.1559, simple_loss=0.25, pruned_loss=0.03086, over 7109.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2569, pruned_loss=0.03915, over 1426263.79 frames.], batch size: 21, lr: 4.53e-04
+2022-05-14 20:57:28,815 INFO [train.py:812] (2/8) Epoch 17, batch 3600, loss[loss=0.1256, simple_loss=0.2199, pruned_loss=0.01565, over 7282.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2568, pruned_loss=0.03846, over 1427288.85 frames.], batch size: 18, lr: 4.52e-04
+2022-05-14 20:58:27,783 INFO [train.py:812] (2/8) Epoch 17, batch 3650, loss[loss=0.1727, simple_loss=0.2602, pruned_loss=0.04259, over 7319.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2559, pruned_loss=0.03837, over 1430772.00 frames.], batch size: 21, lr: 4.52e-04
+2022-05-14 20:59:27,708 INFO [train.py:812] (2/8) Epoch 17, batch 3700, loss[loss=0.1751, simple_loss=0.2714, pruned_loss=0.03938, over 7141.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2556, pruned_loss=0.03832, over 1430429.40 frames.], batch size: 20, lr: 4.52e-04
+2022-05-14 21:00:26,362 INFO [train.py:812] (2/8) Epoch 17, batch 3750, loss[loss=0.1726, simple_loss=0.2804, pruned_loss=0.0324, over 6290.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2559, pruned_loss=0.03838, over 1427950.01 frames.], batch size: 37, lr: 4.52e-04
+2022-05-14 21:01:24,380 INFO [train.py:812] (2/8) Epoch 17, batch 3800, loss[loss=0.1759, simple_loss=0.2653, pruned_loss=0.04323, over 6404.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2565, pruned_loss=0.03835, over 1426248.66 frames.], batch size: 38, lr: 4.52e-04
+2022-05-14 21:02:23,153 INFO [train.py:812] (2/8) Epoch 17, batch 3850, loss[loss=0.146, simple_loss=0.2291, pruned_loss=0.03143, over 6989.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2559, pruned_loss=0.038, over 1426033.22 frames.], batch size: 16, lr: 4.52e-04
+2022-05-14 21:03:22,483 INFO [train.py:812] (2/8) Epoch 17, batch 3900, loss[loss=0.1852, simple_loss=0.2696, pruned_loss=0.05044, over 7204.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2543, pruned_loss=0.03756, over 1428141.53 frames.], batch size: 22, lr: 4.52e-04
+2022-05-14 21:04:21,492 INFO [train.py:812] (2/8) Epoch 17, batch 3950, loss[loss=0.1742, simple_loss=0.2632, pruned_loss=0.04264, over 7197.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2561, pruned_loss=0.03854, over 1427428.60 frames.], batch size: 23, lr: 4.51e-04
+2022-05-14 21:05:20,843 INFO [train.py:812] (2/8) Epoch 17, batch 4000, loss[loss=0.1539, simple_loss=0.2396, pruned_loss=0.03412, over 7277.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2558, pruned_loss=0.0387, over 1428343.25 frames.], batch size: 18, lr: 4.51e-04
+2022-05-14 21:06:19,936 INFO [train.py:812] (2/8) Epoch 17, batch 4050, loss[loss=0.1865, simple_loss=0.2858, pruned_loss=0.04355, over 6742.00 frames.], tot_loss[loss=0.1671, simple_loss=0.256, pruned_loss=0.03911, over 1425344.57 frames.], batch size: 31, lr: 4.51e-04
+2022-05-14 21:07:19,010 INFO [train.py:812] (2/8) Epoch 17, batch 4100, loss[loss=0.1705, simple_loss=0.261, pruned_loss=0.04001, over 6524.00 frames.], tot_loss[loss=0.168, simple_loss=0.2575, pruned_loss=0.03925, over 1424596.30 frames.], batch size: 38, lr: 4.51e-04
+2022-05-14 21:08:18,270 INFO [train.py:812] (2/8) Epoch 17, batch 4150, loss[loss=0.164, simple_loss=0.2471, pruned_loss=0.04042, over 7136.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2557, pruned_loss=0.03884, over 1423766.77 frames.], batch size: 17, lr: 4.51e-04
+2022-05-14 21:09:17,114 INFO [train.py:812] (2/8) Epoch 17, batch 4200, loss[loss=0.1713, simple_loss=0.2714, pruned_loss=0.03557, over 7111.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2563, pruned_loss=0.03898, over 1422954.14 frames.], batch size: 26, lr: 4.51e-04
+2022-05-14 21:10:16,231 INFO [train.py:812] (2/8) Epoch 17, batch 4250, loss[loss=0.1479, simple_loss=0.247, pruned_loss=0.0244, over 7274.00 frames.], tot_loss[loss=0.167, simple_loss=0.2565, pruned_loss=0.03876, over 1424548.97 frames.], batch size: 18, lr: 4.51e-04
+2022-05-14 21:11:15,269 INFO [train.py:812] (2/8) Epoch 17, batch 4300, loss[loss=0.176, simple_loss=0.264, pruned_loss=0.04403, over 7065.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2554, pruned_loss=0.03848, over 1422464.06 frames.], batch size: 18, lr: 4.50e-04
+2022-05-14 21:12:14,026 INFO [train.py:812] (2/8) Epoch 17, batch 4350, loss[loss=0.1387, simple_loss=0.2086, pruned_loss=0.03438, over 7163.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2554, pruned_loss=0.03845, over 1421371.19 frames.], batch size: 18, lr: 4.50e-04
+2022-05-14 21:13:12,855 INFO [train.py:812] (2/8) Epoch 17, batch 4400, loss[loss=0.1773, simple_loss=0.2693, pruned_loss=0.04262, over 7212.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2554, pruned_loss=0.03843, over 1420020.56 frames.], batch size: 21, lr: 4.50e-04
+2022-05-14 21:14:12,283 INFO [train.py:812] (2/8) Epoch 17, batch 4450, loss[loss=0.1441, simple_loss=0.2256, pruned_loss=0.03135, over 7130.00 frames.], tot_loss[loss=0.1668, simple_loss=0.256, pruned_loss=0.03877, over 1415675.70 frames.], batch size: 17, lr: 4.50e-04
+2022-05-14 21:15:12,311 INFO [train.py:812] (2/8) Epoch 17, batch 4500, loss[loss=0.1684, simple_loss=0.2619, pruned_loss=0.03743, over 7224.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2548, pruned_loss=0.03868, over 1415029.46 frames.], batch size: 20, lr: 4.50e-04
+2022-05-14 21:16:11,535 INFO [train.py:812] (2/8) Epoch 17, batch 4550, loss[loss=0.1848, simple_loss=0.26, pruned_loss=0.05483, over 5241.00 frames.], tot_loss[loss=0.167, simple_loss=0.2545, pruned_loss=0.03971, over 1379540.37 frames.], batch size: 52, lr: 4.50e-04
+2022-05-14 21:17:18,423 INFO [train.py:812] (2/8) Epoch 18, batch 0, loss[loss=0.1657, simple_loss=0.2534, pruned_loss=0.03905, over 7226.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2534, pruned_loss=0.03905, over 7226.00 frames.], batch size: 20, lr: 4.38e-04
+2022-05-14 21:18:18,228 INFO [train.py:812] (2/8) Epoch 18, batch 50, loss[loss=0.1436, simple_loss=0.2224, pruned_loss=0.03234, over 7014.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2506, pruned_loss=0.0379, over 323157.02 frames.], batch size: 16, lr: 4.38e-04
+2022-05-14 21:19:17,378 INFO [train.py:812] (2/8) Epoch 18, batch 100, loss[loss=0.1682, simple_loss=0.246, pruned_loss=0.04524, over 7169.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2519, pruned_loss=0.0372, over 564958.53 frames.], batch size: 18, lr: 4.37e-04
+2022-05-14 21:20:15,722 INFO [train.py:812] (2/8) Epoch 18, batch 150, loss[loss=0.1635, simple_loss=0.2602, pruned_loss=0.03343, over 7145.00 frames.], tot_loss[loss=0.164, simple_loss=0.2527, pruned_loss=0.03762, over 752529.79 frames.], batch size: 20, lr: 4.37e-04
+2022-05-14 21:21:13,580 INFO [train.py:812] (2/8) Epoch 18, batch 200, loss[loss=0.1388, simple_loss=0.229, pruned_loss=0.02433, over 7172.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2532, pruned_loss=0.03709, over 903886.72 frames.], batch size: 18, lr: 4.37e-04
+2022-05-14 21:22:12,979 INFO [train.py:812] (2/8) Epoch 18, batch 250, loss[loss=0.1468, simple_loss=0.2489, pruned_loss=0.02232, over 6804.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2549, pruned_loss=0.03777, over 1021183.46 frames.], batch size: 31, lr: 4.37e-04
+2022-05-14 21:23:11,924 INFO [train.py:812] (2/8) Epoch 18, batch 300, loss[loss=0.1649, simple_loss=0.2501, pruned_loss=0.03981, over 7144.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2544, pruned_loss=0.03791, over 1105324.06 frames.], batch size: 28, lr: 4.37e-04
+2022-05-14 21:24:11,082 INFO [train.py:812] (2/8) Epoch 18, batch 350, loss[loss=0.1702, simple_loss=0.261, pruned_loss=0.03974, over 7325.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2543, pruned_loss=0.03809, over 1172598.27 frames.], batch size: 22, lr: 4.37e-04
+2022-05-14 21:25:08,902 INFO [train.py:812] (2/8) Epoch 18, batch 400, loss[loss=0.1399, simple_loss=0.221, pruned_loss=0.02938, over 7225.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2553, pruned_loss=0.0381, over 1232944.55 frames.], batch size: 16, lr: 4.37e-04
+2022-05-14 21:26:06,612 INFO [train.py:812] (2/8) Epoch 18, batch 450, loss[loss=0.1626, simple_loss=0.2597, pruned_loss=0.03268, over 7216.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2559, pruned_loss=0.03791, over 1276297.22 frames.], batch size: 22, lr: 4.36e-04
+2022-05-14 21:27:06,222 INFO [train.py:812] (2/8) Epoch 18, batch 500, loss[loss=0.1662, simple_loss=0.2615, pruned_loss=0.03545, over 7334.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2558, pruned_loss=0.03814, over 1312572.12 frames.], batch size: 22, lr: 4.36e-04
+2022-05-14 21:28:04,627 INFO [train.py:812] (2/8) Epoch 18, batch 550, loss[loss=0.1662, simple_loss=0.2483, pruned_loss=0.04205, over 7145.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03801, over 1339233.73 frames.], batch size: 17, lr: 4.36e-04
+2022-05-14 21:29:02,325 INFO [train.py:812] (2/8) Epoch 18, batch 600, loss[loss=0.1711, simple_loss=0.2671, pruned_loss=0.03757, over 6190.00 frames.], tot_loss[loss=0.1672, simple_loss=0.257, pruned_loss=0.03873, over 1356916.63 frames.], batch size: 37, lr: 4.36e-04
+2022-05-14 21:30:01,247 INFO [train.py:812] (2/8) Epoch 18, batch 650, loss[loss=0.2292, simple_loss=0.3089, pruned_loss=0.07474, over 5158.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2572, pruned_loss=0.03857, over 1369457.60 frames.], batch size: 53, lr: 4.36e-04
+2022-05-14 21:30:59,627 INFO [train.py:812] (2/8) Epoch 18, batch 700, loss[loss=0.1782, simple_loss=0.2689, pruned_loss=0.04376, over 7321.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2567, pruned_loss=0.03859, over 1380902.45 frames.], batch size: 21, lr: 4.36e-04
+2022-05-14 21:31:59,690 INFO [train.py:812] (2/8) Epoch 18, batch 750, loss[loss=0.1325, simple_loss=0.2187, pruned_loss=0.02315, over 7397.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2554, pruned_loss=0.03836, over 1391251.87 frames.], batch size: 18, lr: 4.36e-04
+2022-05-14 21:32:57,571 INFO [train.py:812] (2/8) Epoch 18, batch 800, loss[loss=0.1677, simple_loss=0.2662, pruned_loss=0.03456, over 7321.00 frames.], tot_loss[loss=0.165, simple_loss=0.2547, pruned_loss=0.03769, over 1403046.62 frames.], batch size: 21, lr: 4.36e-04
+2022-05-14 21:33:57,263 INFO [train.py:812] (2/8) Epoch 18, batch 850, loss[loss=0.155, simple_loss=0.2553, pruned_loss=0.02734, over 7414.00 frames.], tot_loss[loss=0.1644, simple_loss=0.254, pruned_loss=0.03744, over 1406545.02 frames.], batch size: 21, lr: 4.35e-04
+2022-05-14 21:34:56,173 INFO [train.py:812] (2/8) Epoch 18, batch 900, loss[loss=0.1741, simple_loss=0.2733, pruned_loss=0.03748, over 7202.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2555, pruned_loss=0.03782, over 1406757.20 frames.], batch size: 22, lr: 4.35e-04
+2022-05-14 21:35:54,623 INFO [train.py:812] (2/8) Epoch 18, batch 950, loss[loss=0.1419, simple_loss=0.2251, pruned_loss=0.02935, over 7253.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2557, pruned_loss=0.03799, over 1410181.68 frames.], batch size: 19, lr: 4.35e-04
+2022-05-14 21:36:52,269 INFO [train.py:812] (2/8) Epoch 18, batch 1000, loss[loss=0.1779, simple_loss=0.2679, pruned_loss=0.04399, over 7294.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2555, pruned_loss=0.03758, over 1415818.46 frames.], batch size: 24, lr: 4.35e-04
+2022-05-14 21:37:51,918 INFO [train.py:812] (2/8) Epoch 18, batch 1050, loss[loss=0.1406, simple_loss=0.2245, pruned_loss=0.02833, over 7277.00 frames.], tot_loss[loss=0.165, simple_loss=0.2546, pruned_loss=0.03776, over 1418093.66 frames.], batch size: 17, lr: 4.35e-04
+2022-05-14 21:38:50,485 INFO [train.py:812] (2/8) Epoch 18, batch 1100, loss[loss=0.1859, simple_loss=0.2669, pruned_loss=0.05246, over 7313.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2552, pruned_loss=0.03825, over 1421480.97 frames.], batch size: 25, lr: 4.35e-04
+2022-05-14 21:39:48,087 INFO [train.py:812] (2/8) Epoch 18, batch 1150, loss[loss=0.1805, simple_loss=0.2664, pruned_loss=0.04731, over 7394.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2547, pruned_loss=0.03786, over 1419256.48 frames.], batch size: 23, lr: 4.35e-04
+2022-05-14 21:40:45,339 INFO [train.py:812] (2/8) Epoch 18, batch 1200, loss[loss=0.1503, simple_loss=0.2379, pruned_loss=0.03136, over 7281.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2545, pruned_loss=0.03808, over 1417277.55 frames.], batch size: 18, lr: 4.34e-04
+2022-05-14 21:41:44,611 INFO [train.py:812] (2/8) Epoch 18, batch 1250, loss[loss=0.1814, simple_loss=0.2684, pruned_loss=0.04719, over 7408.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2542, pruned_loss=0.03805, over 1419005.08 frames.], batch size: 21, lr: 4.34e-04
+2022-05-14 21:42:42,166 INFO [train.py:812] (2/8) Epoch 18, batch 1300, loss[loss=0.1687, simple_loss=0.2617, pruned_loss=0.03785, over 7157.00 frames.], tot_loss[loss=0.1649, simple_loss=0.254, pruned_loss=0.03788, over 1420111.03 frames.], batch size: 26, lr: 4.34e-04
+2022-05-14 21:43:41,335 INFO [train.py:812] (2/8) Epoch 18, batch 1350, loss[loss=0.1233, simple_loss=0.2046, pruned_loss=0.02105, over 6993.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2537, pruned_loss=0.03734, over 1422595.52 frames.], batch size: 16, lr: 4.34e-04
+2022-05-14 21:44:39,653 INFO [train.py:812] (2/8) Epoch 18, batch 1400, loss[loss=0.1629, simple_loss=0.2594, pruned_loss=0.03316, over 7112.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2546, pruned_loss=0.03757, over 1423892.90 frames.], batch size: 21, lr: 4.34e-04
+2022-05-14 21:45:38,204 INFO [train.py:812] (2/8) Epoch 18, batch 1450, loss[loss=0.1541, simple_loss=0.2498, pruned_loss=0.02924, over 7148.00 frames.], tot_loss[loss=0.165, simple_loss=0.2548, pruned_loss=0.03761, over 1421995.40 frames.], batch size: 20, lr: 4.34e-04
+2022-05-14 21:46:36,910 INFO [train.py:812] (2/8) Epoch 18, batch 1500, loss[loss=0.1696, simple_loss=0.2712, pruned_loss=0.034, over 7303.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2548, pruned_loss=0.03779, over 1413569.72 frames.], batch size: 25, lr: 4.34e-04
+2022-05-14 21:47:35,828 INFO [train.py:812] (2/8) Epoch 18, batch 1550, loss[loss=0.1536, simple_loss=0.2424, pruned_loss=0.03243, over 7152.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2543, pruned_loss=0.03746, over 1420839.25 frames.], batch size: 19, lr: 4.33e-04
+2022-05-14 21:48:33,736 INFO [train.py:812] (2/8) Epoch 18, batch 1600, loss[loss=0.1619, simple_loss=0.2504, pruned_loss=0.03669, over 7424.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2544, pruned_loss=0.03736, over 1421584.56 frames.], batch size: 20, lr: 4.33e-04
+2022-05-14 21:49:33,286 INFO [train.py:812] (2/8) Epoch 18, batch 1650, loss[loss=0.142, simple_loss=0.2257, pruned_loss=0.02915, over 7276.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2547, pruned_loss=0.03753, over 1420860.01 frames.], batch size: 17, lr: 4.33e-04
+2022-05-14 21:50:30,804 INFO [train.py:812] (2/8) Epoch 18, batch 1700, loss[loss=0.1693, simple_loss=0.2501, pruned_loss=0.04424, over 7352.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2548, pruned_loss=0.03739, over 1423749.28 frames.], batch size: 19, lr: 4.33e-04
+2022-05-14 21:51:29,627 INFO [train.py:812] (2/8) Epoch 18, batch 1750, loss[loss=0.1624, simple_loss=0.255, pruned_loss=0.03491, over 7315.00 frames.], tot_loss[loss=0.164, simple_loss=0.254, pruned_loss=0.03703, over 1425084.93 frames.], batch size: 21, lr: 4.33e-04
+2022-05-14 21:52:27,543 INFO [train.py:812] (2/8) Epoch 18, batch 1800, loss[loss=0.1881, simple_loss=0.2782, pruned_loss=0.04903, over 7231.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2533, pruned_loss=0.0366, over 1428911.66 frames.], batch size: 20, lr: 4.33e-04
+2022-05-14 21:53:27,374 INFO [train.py:812] (2/8) Epoch 18, batch 1850, loss[loss=0.2059, simple_loss=0.2868, pruned_loss=0.06255, over 4783.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2526, pruned_loss=0.03688, over 1426245.83 frames.], batch size: 52, lr: 4.33e-04
+2022-05-14 21:54:25,906 INFO [train.py:812] (2/8) Epoch 18, batch 1900, loss[loss=0.1807, simple_loss=0.2796, pruned_loss=0.04088, over 7314.00 frames.], tot_loss[loss=0.1642, simple_loss=0.254, pruned_loss=0.03724, over 1426948.10 frames.], batch size: 21, lr: 4.33e-04
+2022-05-14 21:55:25,270 INFO [train.py:812] (2/8) Epoch 18, batch 1950, loss[loss=0.1865, simple_loss=0.2765, pruned_loss=0.04827, over 7326.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2548, pruned_loss=0.03774, over 1424068.33 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 21:56:23,568 INFO [train.py:812] (2/8) Epoch 18, batch 2000, loss[loss=0.1858, simple_loss=0.2668, pruned_loss=0.05242, over 4777.00 frames.], tot_loss[loss=0.165, simple_loss=0.2542, pruned_loss=0.03795, over 1423887.60 frames.], batch size: 52, lr: 4.32e-04
+2022-05-14 21:57:27,189 INFO [train.py:812] (2/8) Epoch 18, batch 2050, loss[loss=0.1526, simple_loss=0.2535, pruned_loss=0.02591, over 7102.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2545, pruned_loss=0.03838, over 1420243.14 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 21:58:25,562 INFO [train.py:812] (2/8) Epoch 18, batch 2100, loss[loss=0.1962, simple_loss=0.2993, pruned_loss=0.04654, over 6702.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2546, pruned_loss=0.03841, over 1415756.94 frames.], batch size: 31, lr: 4.32e-04
+2022-05-14 21:59:24,613 INFO [train.py:812] (2/8) Epoch 18, batch 2150, loss[loss=0.1711, simple_loss=0.2711, pruned_loss=0.03553, over 7221.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2549, pruned_loss=0.03827, over 1417508.44 frames.], batch size: 21, lr: 4.32e-04
+2022-05-14 22:00:22,637 INFO [train.py:812] (2/8) Epoch 18, batch 2200, loss[loss=0.1453, simple_loss=0.2282, pruned_loss=0.0312, over 7209.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2541, pruned_loss=0.03778, over 1420224.39 frames.], batch size: 16, lr: 4.32e-04
+2022-05-14 22:01:21,995 INFO [train.py:812] (2/8) Epoch 18, batch 2250, loss[loss=0.1517, simple_loss=0.2305, pruned_loss=0.03645, over 7010.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2536, pruned_loss=0.03779, over 1423876.00 frames.], batch size: 16, lr: 4.32e-04
+2022-05-14 22:02:21,444 INFO [train.py:812] (2/8) Epoch 18, batch 2300, loss[loss=0.164, simple_loss=0.2569, pruned_loss=0.03555, over 7151.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2553, pruned_loss=0.03843, over 1425905.00 frames.], batch size: 20, lr: 4.31e-04
+2022-05-14 22:03:21,214 INFO [train.py:812] (2/8) Epoch 18, batch 2350, loss[loss=0.1837, simple_loss=0.2838, pruned_loss=0.04179, over 7170.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2549, pruned_loss=0.03834, over 1425595.62 frames.], batch size: 26, lr: 4.31e-04
+2022-05-14 22:04:20,401 INFO [train.py:812] (2/8) Epoch 18, batch 2400, loss[loss=0.1887, simple_loss=0.2952, pruned_loss=0.04117, over 6500.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2556, pruned_loss=0.03846, over 1425022.90 frames.], batch size: 38, lr: 4.31e-04
+2022-05-14 22:05:18,775 INFO [train.py:812] (2/8) Epoch 18, batch 2450, loss[loss=0.1377, simple_loss=0.2288, pruned_loss=0.02329, over 7152.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2549, pruned_loss=0.03821, over 1426248.64 frames.], batch size: 19, lr: 4.31e-04
+2022-05-14 22:06:16,640 INFO [train.py:812] (2/8) Epoch 18, batch 2500, loss[loss=0.175, simple_loss=0.2734, pruned_loss=0.03828, over 7110.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2562, pruned_loss=0.03848, over 1418978.08 frames.], batch size: 21, lr: 4.31e-04
+2022-05-14 22:07:15,273 INFO [train.py:812] (2/8) Epoch 18, batch 2550, loss[loss=0.1466, simple_loss=0.2468, pruned_loss=0.02321, over 7313.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2557, pruned_loss=0.03866, over 1419734.55 frames.], batch size: 21, lr: 4.31e-04
+2022-05-14 22:08:14,569 INFO [train.py:812] (2/8) Epoch 18, batch 2600, loss[loss=0.1621, simple_loss=0.2366, pruned_loss=0.04383, over 7209.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2557, pruned_loss=0.03855, over 1418854.75 frames.], batch size: 16, lr: 4.31e-04
+2022-05-14 22:09:14,554 INFO [train.py:812] (2/8) Epoch 18, batch 2650, loss[loss=0.197, simple_loss=0.2816, pruned_loss=0.05623, over 7351.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2558, pruned_loss=0.03866, over 1420660.70 frames.], batch size: 19, lr: 4.31e-04
+2022-05-14 22:10:13,352 INFO [train.py:812] (2/8) Epoch 18, batch 2700, loss[loss=0.1405, simple_loss=0.2256, pruned_loss=0.02776, over 7291.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2541, pruned_loss=0.03833, over 1420168.96 frames.], batch size: 18, lr: 4.30e-04
+2022-05-14 22:11:12,906 INFO [train.py:812] (2/8) Epoch 18, batch 2750, loss[loss=0.1587, simple_loss=0.2539, pruned_loss=0.03179, over 7150.00 frames.], tot_loss[loss=0.1652, simple_loss=0.254, pruned_loss=0.0382, over 1418173.03 frames.], batch size: 20, lr: 4.30e-04
+2022-05-14 22:12:10,444 INFO [train.py:812] (2/8) Epoch 18, batch 2800, loss[loss=0.1701, simple_loss=0.2582, pruned_loss=0.04103, over 7327.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2534, pruned_loss=0.0377, over 1417659.40 frames.], batch size: 21, lr: 4.30e-04
+2022-05-14 22:13:09,279 INFO [train.py:812] (2/8) Epoch 18, batch 2850, loss[loss=0.1807, simple_loss=0.2653, pruned_loss=0.04799, over 7321.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2539, pruned_loss=0.03757, over 1420794.11 frames.], batch size: 25, lr: 4.30e-04
+2022-05-14 22:14:17,881 INFO [train.py:812] (2/8) Epoch 18, batch 2900, loss[loss=0.1911, simple_loss=0.2751, pruned_loss=0.05358, over 7188.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2549, pruned_loss=0.03798, over 1423287.62 frames.], batch size: 22, lr: 4.30e-04
+2022-05-14 22:15:17,350 INFO [train.py:812] (2/8) Epoch 18, batch 2950, loss[loss=0.1847, simple_loss=0.2799, pruned_loss=0.04475, over 6463.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2552, pruned_loss=0.03829, over 1419956.45 frames.], batch size: 37, lr: 4.30e-04
+2022-05-14 22:16:16,203 INFO [train.py:812] (2/8) Epoch 18, batch 3000, loss[loss=0.2095, simple_loss=0.281, pruned_loss=0.06901, over 7296.00 frames.], tot_loss[loss=0.1665, simple_loss=0.256, pruned_loss=0.03852, over 1418194.02 frames.], batch size: 25, lr: 4.30e-04
+2022-05-14 22:16:16,204 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 22:16:23,834 INFO [train.py:841] (2/8) Epoch 18, validation: loss=0.153, simple_loss=0.2523, pruned_loss=0.02686, over 698248.00 frames.
+2022-05-14 22:17:22,911 INFO [train.py:812] (2/8) Epoch 18, batch 3050, loss[loss=0.1828, simple_loss=0.2807, pruned_loss=0.04245, over 7123.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2561, pruned_loss=0.03859, over 1417558.35 frames.], batch size: 21, lr: 4.29e-04
+2022-05-14 22:18:21,082 INFO [train.py:812] (2/8) Epoch 18, batch 3100, loss[loss=0.1639, simple_loss=0.2562, pruned_loss=0.03587, over 7239.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2562, pruned_loss=0.03882, over 1418709.25 frames.], batch size: 20, lr: 4.29e-04
+2022-05-14 22:19:19,579 INFO [train.py:812] (2/8) Epoch 18, batch 3150, loss[loss=0.1602, simple_loss=0.2523, pruned_loss=0.03404, over 7269.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2556, pruned_loss=0.03861, over 1421113.45 frames.], batch size: 19, lr: 4.29e-04
+2022-05-14 22:20:18,602 INFO [train.py:812] (2/8) Epoch 18, batch 3200, loss[loss=0.1816, simple_loss=0.2718, pruned_loss=0.04572, over 6796.00 frames.], tot_loss[loss=0.166, simple_loss=0.2552, pruned_loss=0.03841, over 1419383.23 frames.], batch size: 31, lr: 4.29e-04
+2022-05-14 22:21:17,363 INFO [train.py:812] (2/8) Epoch 18, batch 3250, loss[loss=0.1601, simple_loss=0.2577, pruned_loss=0.03119, over 7377.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2543, pruned_loss=0.03767, over 1422287.46 frames.], batch size: 23, lr: 4.29e-04
+2022-05-14 22:22:16,095 INFO [train.py:812] (2/8) Epoch 18, batch 3300, loss[loss=0.145, simple_loss=0.2297, pruned_loss=0.03018, over 7161.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2542, pruned_loss=0.03751, over 1426827.25 frames.], batch size: 18, lr: 4.29e-04
+2022-05-14 22:23:15,277 INFO [train.py:812] (2/8) Epoch 18, batch 3350, loss[loss=0.15, simple_loss=0.2376, pruned_loss=0.0312, over 7435.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2545, pruned_loss=0.03742, over 1427001.15 frames.], batch size: 18, lr: 4.29e-04
+2022-05-14 22:24:13,573 INFO [train.py:812] (2/8) Epoch 18, batch 3400, loss[loss=0.1759, simple_loss=0.2646, pruned_loss=0.04362, over 7380.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2552, pruned_loss=0.03754, over 1430079.74 frames.], batch size: 23, lr: 4.29e-04
+2022-05-14 22:25:13,426 INFO [train.py:812] (2/8) Epoch 18, batch 3450, loss[loss=0.1624, simple_loss=0.2408, pruned_loss=0.04197, over 7409.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2556, pruned_loss=0.03777, over 1430679.34 frames.], batch size: 18, lr: 4.28e-04
+2022-05-14 22:26:12,110 INFO [train.py:812] (2/8) Epoch 18, batch 3500, loss[loss=0.1868, simple_loss=0.2692, pruned_loss=0.05216, over 6449.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2549, pruned_loss=0.03767, over 1433112.89 frames.], batch size: 38, lr: 4.28e-04
+2022-05-14 22:27:09,544 INFO [train.py:812] (2/8) Epoch 18, batch 3550, loss[loss=0.1746, simple_loss=0.2618, pruned_loss=0.04365, over 7196.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2542, pruned_loss=0.03746, over 1431217.20 frames.], batch size: 23, lr: 4.28e-04
+2022-05-14 22:28:09,173 INFO [train.py:812] (2/8) Epoch 18, batch 3600, loss[loss=0.1889, simple_loss=0.2711, pruned_loss=0.05333, over 7222.00 frames.], tot_loss[loss=0.1644, simple_loss=0.254, pruned_loss=0.03739, over 1432344.91 frames.], batch size: 21, lr: 4.28e-04
+2022-05-14 22:29:08,001 INFO [train.py:812] (2/8) Epoch 18, batch 3650, loss[loss=0.1807, simple_loss=0.2737, pruned_loss=0.04382, over 7327.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2545, pruned_loss=0.03761, over 1423229.96 frames.], batch size: 22, lr: 4.28e-04
+2022-05-14 22:30:06,375 INFO [train.py:812] (2/8) Epoch 18, batch 3700, loss[loss=0.1564, simple_loss=0.243, pruned_loss=0.03489, over 7010.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2556, pruned_loss=0.03776, over 1424510.16 frames.], batch size: 16, lr: 4.28e-04
+2022-05-14 22:31:03,709 INFO [train.py:812] (2/8) Epoch 18, batch 3750, loss[loss=0.1606, simple_loss=0.25, pruned_loss=0.03565, over 7282.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2559, pruned_loss=0.03766, over 1426906.38 frames.], batch size: 25, lr: 4.28e-04
+2022-05-14 22:32:02,176 INFO [train.py:812] (2/8) Epoch 18, batch 3800, loss[loss=0.1664, simple_loss=0.2598, pruned_loss=0.03646, over 7354.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2547, pruned_loss=0.03743, over 1427134.54 frames.], batch size: 19, lr: 4.28e-04
+2022-05-14 22:33:01,936 INFO [train.py:812] (2/8) Epoch 18, batch 3850, loss[loss=0.1451, simple_loss=0.2398, pruned_loss=0.02518, over 7417.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2543, pruned_loss=0.03737, over 1426377.50 frames.], batch size: 18, lr: 4.27e-04
+2022-05-14 22:34:00,987 INFO [train.py:812] (2/8) Epoch 18, batch 3900, loss[loss=0.177, simple_loss=0.271, pruned_loss=0.04147, over 7127.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2546, pruned_loss=0.03779, over 1422291.12 frames.], batch size: 21, lr: 4.27e-04
+2022-05-14 22:35:00,693 INFO [train.py:812] (2/8) Epoch 18, batch 3950, loss[loss=0.1698, simple_loss=0.2697, pruned_loss=0.03495, over 7035.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2535, pruned_loss=0.03742, over 1423797.25 frames.], batch size: 28, lr: 4.27e-04
+2022-05-14 22:35:58,194 INFO [train.py:812] (2/8) Epoch 18, batch 4000, loss[loss=0.154, simple_loss=0.2429, pruned_loss=0.03257, over 6869.00 frames.], tot_loss[loss=0.164, simple_loss=0.2534, pruned_loss=0.03735, over 1424305.76 frames.], batch size: 15, lr: 4.27e-04
+2022-05-14 22:36:56,548 INFO [train.py:812] (2/8) Epoch 18, batch 4050, loss[loss=0.1668, simple_loss=0.258, pruned_loss=0.0378, over 7121.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2537, pruned_loss=0.03725, over 1427401.70 frames.], batch size: 28, lr: 4.27e-04
+2022-05-14 22:37:55,338 INFO [train.py:812] (2/8) Epoch 18, batch 4100, loss[loss=0.2022, simple_loss=0.2919, pruned_loss=0.05624, over 7153.00 frames.], tot_loss[loss=0.165, simple_loss=0.2545, pruned_loss=0.03781, over 1424163.96 frames.], batch size: 20, lr: 4.27e-04
+2022-05-14 22:38:54,559 INFO [train.py:812] (2/8) Epoch 18, batch 4150, loss[loss=0.1499, simple_loss=0.247, pruned_loss=0.02637, over 7322.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2538, pruned_loss=0.03736, over 1422682.83 frames.], batch size: 20, lr: 4.27e-04
+2022-05-14 22:39:53,792 INFO [train.py:812] (2/8) Epoch 18, batch 4200, loss[loss=0.1544, simple_loss=0.2459, pruned_loss=0.03142, over 7000.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2519, pruned_loss=0.03698, over 1421936.64 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:40:53,069 INFO [train.py:812] (2/8) Epoch 18, batch 4250, loss[loss=0.171, simple_loss=0.2531, pruned_loss=0.0444, over 6772.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2517, pruned_loss=0.03706, over 1417017.55 frames.], batch size: 31, lr: 4.26e-04
+2022-05-14 22:41:52,119 INFO [train.py:812] (2/8) Epoch 18, batch 4300, loss[loss=0.1541, simple_loss=0.2261, pruned_loss=0.04105, over 7001.00 frames.], tot_loss[loss=0.163, simple_loss=0.2516, pruned_loss=0.03725, over 1417973.12 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:42:51,597 INFO [train.py:812] (2/8) Epoch 18, batch 4350, loss[loss=0.1719, simple_loss=0.2633, pruned_loss=0.04028, over 7213.00 frames.], tot_loss[loss=0.1644, simple_loss=0.253, pruned_loss=0.03795, over 1405205.20 frames.], batch size: 21, lr: 4.26e-04
+2022-05-14 22:43:50,339 INFO [train.py:812] (2/8) Epoch 18, batch 4400, loss[loss=0.1348, simple_loss=0.2273, pruned_loss=0.02119, over 7062.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2539, pruned_loss=0.03814, over 1399842.65 frames.], batch size: 18, lr: 4.26e-04
+2022-05-14 22:44:47,950 INFO [train.py:812] (2/8) Epoch 18, batch 4450, loss[loss=0.1878, simple_loss=0.2778, pruned_loss=0.04886, over 6295.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2548, pruned_loss=0.0383, over 1391279.46 frames.], batch size: 37, lr: 4.26e-04
+2022-05-14 22:45:55,867 INFO [train.py:812] (2/8) Epoch 18, batch 4500, loss[loss=0.1538, simple_loss=0.2359, pruned_loss=0.03582, over 7003.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2556, pruned_loss=0.03872, over 1378750.09 frames.], batch size: 16, lr: 4.26e-04
+2022-05-14 22:46:55,056 INFO [train.py:812] (2/8) Epoch 18, batch 4550, loss[loss=0.1579, simple_loss=0.2467, pruned_loss=0.03454, over 7164.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2557, pruned_loss=0.03883, over 1369296.13 frames.], batch size: 19, lr: 4.26e-04
+2022-05-14 22:48:10,084 INFO [train.py:812] (2/8) Epoch 19, batch 0, loss[loss=0.1929, simple_loss=0.2842, pruned_loss=0.05084, over 7342.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2842, pruned_loss=0.05084, over 7342.00 frames.], batch size: 25, lr: 4.15e-04
+2022-05-14 22:49:27,468 INFO [train.py:812] (2/8) Epoch 19, batch 50, loss[loss=0.1864, simple_loss=0.2881, pruned_loss=0.04234, over 7343.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2538, pruned_loss=0.03686, over 325511.65 frames.], batch size: 22, lr: 4.15e-04
+2022-05-14 22:50:35,550 INFO [train.py:812] (2/8) Epoch 19, batch 100, loss[loss=0.1816, simple_loss=0.2778, pruned_loss=0.04267, over 7351.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2552, pruned_loss=0.03789, over 575055.33 frames.], batch size: 22, lr: 4.14e-04
+2022-05-14 22:51:34,799 INFO [train.py:812] (2/8) Epoch 19, batch 150, loss[loss=0.1798, simple_loss=0.286, pruned_loss=0.03686, over 7215.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2527, pruned_loss=0.03674, over 764280.61 frames.], batch size: 21, lr: 4.14e-04
+2022-05-14 22:53:02,392 INFO [train.py:812] (2/8) Epoch 19, batch 200, loss[loss=0.1334, simple_loss=0.2205, pruned_loss=0.02314, over 7278.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2532, pruned_loss=0.03712, over 910036.48 frames.], batch size: 17, lr: 4.14e-04
+2022-05-14 22:54:01,874 INFO [train.py:812] (2/8) Epoch 19, batch 250, loss[loss=0.1565, simple_loss=0.246, pruned_loss=0.03349, over 6782.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2537, pruned_loss=0.03726, over 1026173.14 frames.], batch size: 31, lr: 4.14e-04
+2022-05-14 22:55:01,085 INFO [train.py:812] (2/8) Epoch 19, batch 300, loss[loss=0.1444, simple_loss=0.2336, pruned_loss=0.02764, over 7236.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2532, pruned_loss=0.03703, over 1116512.87 frames.], batch size: 20, lr: 4.14e-04
+2022-05-14 22:56:00,985 INFO [train.py:812] (2/8) Epoch 19, batch 350, loss[loss=0.1717, simple_loss=0.2619, pruned_loss=0.04079, over 6730.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2529, pruned_loss=0.03711, over 1182405.32 frames.], batch size: 31, lr: 4.14e-04
+2022-05-14 22:56:59,180 INFO [train.py:812] (2/8) Epoch 19, batch 400, loss[loss=0.1495, simple_loss=0.2364, pruned_loss=0.03126, over 7061.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2538, pruned_loss=0.03749, over 1233499.48 frames.], batch size: 18, lr: 4.14e-04
+2022-05-14 22:57:58,783 INFO [train.py:812] (2/8) Epoch 19, batch 450, loss[loss=0.1811, simple_loss=0.2701, pruned_loss=0.04607, over 7330.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2545, pruned_loss=0.03768, over 1275134.84 frames.], batch size: 22, lr: 4.14e-04
+2022-05-14 22:58:57,682 INFO [train.py:812] (2/8) Epoch 19, batch 500, loss[loss=0.1401, simple_loss=0.2266, pruned_loss=0.02682, over 7147.00 frames.], tot_loss[loss=0.165, simple_loss=0.2548, pruned_loss=0.03761, over 1305898.06 frames.], batch size: 17, lr: 4.13e-04
+2022-05-14 22:59:57,489 INFO [train.py:812] (2/8) Epoch 19, batch 550, loss[loss=0.1498, simple_loss=0.2251, pruned_loss=0.03729, over 7304.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2541, pruned_loss=0.03707, over 1335990.11 frames.], batch size: 17, lr: 4.13e-04
+2022-05-14 23:00:56,146 INFO [train.py:812] (2/8) Epoch 19, batch 600, loss[loss=0.1399, simple_loss=0.225, pruned_loss=0.02742, over 7276.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2541, pruned_loss=0.03735, over 1356347.57 frames.], batch size: 18, lr: 4.13e-04
+2022-05-14 23:01:55,591 INFO [train.py:812] (2/8) Epoch 19, batch 650, loss[loss=0.1586, simple_loss=0.2491, pruned_loss=0.03404, over 7122.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2531, pruned_loss=0.03673, over 1375682.47 frames.], batch size: 21, lr: 4.13e-04
+2022-05-14 23:02:54,270 INFO [train.py:812] (2/8) Epoch 19, batch 700, loss[loss=0.1888, simple_loss=0.2716, pruned_loss=0.05297, over 5195.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2544, pruned_loss=0.03709, over 1385615.62 frames.], batch size: 52, lr: 4.13e-04
+2022-05-14 23:03:53,411 INFO [train.py:812] (2/8) Epoch 19, batch 750, loss[loss=0.1583, simple_loss=0.2487, pruned_loss=0.03399, over 7161.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2549, pruned_loss=0.03745, over 1393710.00 frames.], batch size: 19, lr: 4.13e-04
+2022-05-14 23:04:52,303 INFO [train.py:812] (2/8) Epoch 19, batch 800, loss[loss=0.1806, simple_loss=0.2746, pruned_loss=0.04336, over 6927.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2553, pruned_loss=0.03764, over 1397047.03 frames.], batch size: 32, lr: 4.13e-04
+2022-05-14 23:05:50,933 INFO [train.py:812] (2/8) Epoch 19, batch 850, loss[loss=0.1731, simple_loss=0.2555, pruned_loss=0.04537, over 7057.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2555, pruned_loss=0.03764, over 1403907.19 frames.], batch size: 18, lr: 4.13e-04
+2022-05-14 23:06:50,005 INFO [train.py:812] (2/8) Epoch 19, batch 900, loss[loss=0.1609, simple_loss=0.2419, pruned_loss=0.03992, over 7230.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2554, pruned_loss=0.03762, over 1410479.36 frames.], batch size: 16, lr: 4.12e-04
+2022-05-14 23:07:49,436 INFO [train.py:812] (2/8) Epoch 19, batch 950, loss[loss=0.1691, simple_loss=0.2659, pruned_loss=0.03609, over 7382.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2542, pruned_loss=0.03712, over 1413187.99 frames.], batch size: 23, lr: 4.12e-04
+2022-05-14 23:08:48,695 INFO [train.py:812] (2/8) Epoch 19, batch 1000, loss[loss=0.1395, simple_loss=0.2381, pruned_loss=0.02047, over 7148.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2541, pruned_loss=0.03685, over 1419792.54 frames.], batch size: 20, lr: 4.12e-04
+2022-05-14 23:09:47,806 INFO [train.py:812] (2/8) Epoch 19, batch 1050, loss[loss=0.2004, simple_loss=0.2896, pruned_loss=0.05557, over 7270.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2542, pruned_loss=0.03712, over 1418695.31 frames.], batch size: 25, lr: 4.12e-04
+2022-05-14 23:10:45,896 INFO [train.py:812] (2/8) Epoch 19, batch 1100, loss[loss=0.1772, simple_loss=0.266, pruned_loss=0.04425, over 7322.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2536, pruned_loss=0.037, over 1418935.27 frames.], batch size: 20, lr: 4.12e-04
+2022-05-14 23:11:43,620 INFO [train.py:812] (2/8) Epoch 19, batch 1150, loss[loss=0.1862, simple_loss=0.2795, pruned_loss=0.04646, over 7287.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2542, pruned_loss=0.03731, over 1419517.27 frames.], batch size: 24, lr: 4.12e-04
+2022-05-14 23:12:42,326 INFO [train.py:812] (2/8) Epoch 19, batch 1200, loss[loss=0.2047, simple_loss=0.277, pruned_loss=0.06624, over 5112.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2537, pruned_loss=0.03723, over 1414038.98 frames.], batch size: 52, lr: 4.12e-04
+2022-05-14 23:13:40,379 INFO [train.py:812] (2/8) Epoch 19, batch 1250, loss[loss=0.1515, simple_loss=0.2475, pruned_loss=0.02769, over 7123.00 frames.], tot_loss[loss=0.164, simple_loss=0.2539, pruned_loss=0.03708, over 1415233.38 frames.], batch size: 21, lr: 4.12e-04
+2022-05-14 23:14:39,567 INFO [train.py:812] (2/8) Epoch 19, batch 1300, loss[loss=0.149, simple_loss=0.236, pruned_loss=0.03107, over 7163.00 frames.], tot_loss[loss=0.1648, simple_loss=0.255, pruned_loss=0.03733, over 1414956.93 frames.], batch size: 19, lr: 4.12e-04
+2022-05-14 23:15:38,788 INFO [train.py:812] (2/8) Epoch 19, batch 1350, loss[loss=0.1899, simple_loss=0.2667, pruned_loss=0.0565, over 7012.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2556, pruned_loss=0.03776, over 1412817.12 frames.], batch size: 28, lr: 4.11e-04
+2022-05-14 23:16:38,069 INFO [train.py:812] (2/8) Epoch 19, batch 1400, loss[loss=0.1462, simple_loss=0.2305, pruned_loss=0.03099, over 7070.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2541, pruned_loss=0.03721, over 1411288.16 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:17:42,421 INFO [train.py:812] (2/8) Epoch 19, batch 1450, loss[loss=0.1712, simple_loss=0.2691, pruned_loss=0.03661, over 7310.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2529, pruned_loss=0.03638, over 1418103.65 frames.], batch size: 21, lr: 4.11e-04
+2022-05-14 23:18:41,298 INFO [train.py:812] (2/8) Epoch 19, batch 1500, loss[loss=0.1416, simple_loss=0.2276, pruned_loss=0.02779, over 7261.00 frames.], tot_loss[loss=0.1637, simple_loss=0.254, pruned_loss=0.03663, over 1421813.54 frames.], batch size: 19, lr: 4.11e-04
+2022-05-14 23:19:40,447 INFO [train.py:812] (2/8) Epoch 19, batch 1550, loss[loss=0.1594, simple_loss=0.2548, pruned_loss=0.03204, over 7408.00 frames.], tot_loss[loss=0.1637, simple_loss=0.254, pruned_loss=0.03675, over 1424889.87 frames.], batch size: 21, lr: 4.11e-04
+2022-05-14 23:20:39,979 INFO [train.py:812] (2/8) Epoch 19, batch 1600, loss[loss=0.1791, simple_loss=0.271, pruned_loss=0.04364, over 7224.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2531, pruned_loss=0.03662, over 1423714.82 frames.], batch size: 22, lr: 4.11e-04
+2022-05-14 23:21:39,521 INFO [train.py:812] (2/8) Epoch 19, batch 1650, loss[loss=0.1661, simple_loss=0.2428, pruned_loss=0.0447, over 7166.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2534, pruned_loss=0.03724, over 1423068.75 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:22:38,921 INFO [train.py:812] (2/8) Epoch 19, batch 1700, loss[loss=0.1626, simple_loss=0.2447, pruned_loss=0.04028, over 7166.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2532, pruned_loss=0.03726, over 1423567.17 frames.], batch size: 18, lr: 4.11e-04
+2022-05-14 23:23:37,797 INFO [train.py:812] (2/8) Epoch 19, batch 1750, loss[loss=0.1611, simple_loss=0.2594, pruned_loss=0.03137, over 7148.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2545, pruned_loss=0.0374, over 1415291.85 frames.], batch size: 20, lr: 4.10e-04
+2022-05-14 23:24:36,353 INFO [train.py:812] (2/8) Epoch 19, batch 1800, loss[loss=0.1465, simple_loss=0.2399, pruned_loss=0.0266, over 7254.00 frames.], tot_loss[loss=0.1647, simple_loss=0.255, pruned_loss=0.03724, over 1416743.65 frames.], batch size: 19, lr: 4.10e-04
+2022-05-14 23:25:35,726 INFO [train.py:812] (2/8) Epoch 19, batch 1850, loss[loss=0.1809, simple_loss=0.2765, pruned_loss=0.04269, over 7289.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2548, pruned_loss=0.03706, over 1422456.87 frames.], batch size: 24, lr: 4.10e-04
+2022-05-14 23:26:34,567 INFO [train.py:812] (2/8) Epoch 19, batch 1900, loss[loss=0.1702, simple_loss=0.2596, pruned_loss=0.04041, over 7139.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2547, pruned_loss=0.03742, over 1420441.35 frames.], batch size: 28, lr: 4.10e-04
+2022-05-14 23:27:34,155 INFO [train.py:812] (2/8) Epoch 19, batch 1950, loss[loss=0.1349, simple_loss=0.2179, pruned_loss=0.02596, over 7008.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2546, pruned_loss=0.03739, over 1420700.95 frames.], batch size: 16, lr: 4.10e-04
+2022-05-14 23:28:32,908 INFO [train.py:812] (2/8) Epoch 19, batch 2000, loss[loss=0.1764, simple_loss=0.2727, pruned_loss=0.04005, over 7143.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2543, pruned_loss=0.03742, over 1423990.08 frames.], batch size: 20, lr: 4.10e-04
+2022-05-14 23:29:32,683 INFO [train.py:812] (2/8) Epoch 19, batch 2050, loss[loss=0.197, simple_loss=0.2808, pruned_loss=0.05653, over 7329.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2542, pruned_loss=0.03743, over 1424388.62 frames.], batch size: 25, lr: 4.10e-04
+2022-05-14 23:30:30,658 INFO [train.py:812] (2/8) Epoch 19, batch 2100, loss[loss=0.1485, simple_loss=0.2465, pruned_loss=0.02526, over 7156.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2542, pruned_loss=0.03724, over 1425093.94 frames.], batch size: 19, lr: 4.10e-04
+2022-05-14 23:31:30,577 INFO [train.py:812] (2/8) Epoch 19, batch 2150, loss[loss=0.18, simple_loss=0.2694, pruned_loss=0.04536, over 7210.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2534, pruned_loss=0.03719, over 1421280.84 frames.], batch size: 21, lr: 4.09e-04
+2022-05-14 23:32:29,963 INFO [train.py:812] (2/8) Epoch 19, batch 2200, loss[loss=0.1985, simple_loss=0.2901, pruned_loss=0.05346, over 7117.00 frames.], tot_loss[loss=0.1634, simple_loss=0.253, pruned_loss=0.03688, over 1425476.61 frames.], batch size: 21, lr: 4.09e-04
+2022-05-14 23:33:29,291 INFO [train.py:812] (2/8) Epoch 19, batch 2250, loss[loss=0.1361, simple_loss=0.234, pruned_loss=0.01914, over 6551.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2525, pruned_loss=0.03645, over 1424676.21 frames.], batch size: 38, lr: 4.09e-04
+2022-05-14 23:34:27,800 INFO [train.py:812] (2/8) Epoch 19, batch 2300, loss[loss=0.1794, simple_loss=0.2704, pruned_loss=0.04418, over 7370.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2526, pruned_loss=0.03638, over 1426087.03 frames.], batch size: 23, lr: 4.09e-04
+2022-05-14 23:35:25,969 INFO [train.py:812] (2/8) Epoch 19, batch 2350, loss[loss=0.1431, simple_loss=0.2268, pruned_loss=0.02964, over 7294.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2527, pruned_loss=0.0365, over 1422747.02 frames.], batch size: 17, lr: 4.09e-04
+2022-05-14 23:36:25,345 INFO [train.py:812] (2/8) Epoch 19, batch 2400, loss[loss=0.184, simple_loss=0.2773, pruned_loss=0.04529, over 7153.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2527, pruned_loss=0.03656, over 1419207.81 frames.], batch size: 20, lr: 4.09e-04
+2022-05-14 23:37:24,207 INFO [train.py:812] (2/8) Epoch 19, batch 2450, loss[loss=0.1847, simple_loss=0.2819, pruned_loss=0.04374, over 7145.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2529, pruned_loss=0.0363, over 1421080.48 frames.], batch size: 20, lr: 4.09e-04
+2022-05-14 23:38:23,515 INFO [train.py:812] (2/8) Epoch 19, batch 2500, loss[loss=0.1805, simple_loss=0.2747, pruned_loss=0.04315, over 7143.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2523, pruned_loss=0.03628, over 1419915.55 frames.], batch size: 26, lr: 4.09e-04
+2022-05-14 23:39:23,050 INFO [train.py:812] (2/8) Epoch 19, batch 2550, loss[loss=0.1907, simple_loss=0.2898, pruned_loss=0.04579, over 7280.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2524, pruned_loss=0.0361, over 1419737.47 frames.], batch size: 24, lr: 4.08e-04
+2022-05-14 23:40:21,741 INFO [train.py:812] (2/8) Epoch 19, batch 2600, loss[loss=0.1606, simple_loss=0.242, pruned_loss=0.03954, over 6995.00 frames.], tot_loss[loss=0.1629, simple_loss=0.253, pruned_loss=0.03633, over 1423785.82 frames.], batch size: 16, lr: 4.08e-04
+2022-05-14 23:41:20,980 INFO [train.py:812] (2/8) Epoch 19, batch 2650, loss[loss=0.1869, simple_loss=0.2672, pruned_loss=0.0533, over 7289.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2536, pruned_loss=0.03657, over 1425675.73 frames.], batch size: 24, lr: 4.08e-04
+2022-05-14 23:42:20,838 INFO [train.py:812] (2/8) Epoch 19, batch 2700, loss[loss=0.1915, simple_loss=0.2887, pruned_loss=0.04714, over 7290.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2526, pruned_loss=0.03601, over 1428980.98 frames.], batch size: 25, lr: 4.08e-04
+2022-05-14 23:43:20,350 INFO [train.py:812] (2/8) Epoch 19, batch 2750, loss[loss=0.175, simple_loss=0.2661, pruned_loss=0.0419, over 7407.00 frames.], tot_loss[loss=0.164, simple_loss=0.2542, pruned_loss=0.03686, over 1429141.06 frames.], batch size: 21, lr: 4.08e-04
+2022-05-14 23:44:19,810 INFO [train.py:812] (2/8) Epoch 19, batch 2800, loss[loss=0.1647, simple_loss=0.2593, pruned_loss=0.03505, over 7061.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2541, pruned_loss=0.03676, over 1429976.47 frames.], batch size: 18, lr: 4.08e-04
+2022-05-14 23:45:18,634 INFO [train.py:812] (2/8) Epoch 19, batch 2850, loss[loss=0.1749, simple_loss=0.2634, pruned_loss=0.04317, over 7142.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2548, pruned_loss=0.0372, over 1426065.81 frames.], batch size: 19, lr: 4.08e-04
+2022-05-14 23:46:17,158 INFO [train.py:812] (2/8) Epoch 19, batch 2900, loss[loss=0.1616, simple_loss=0.2601, pruned_loss=0.03152, over 7178.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2542, pruned_loss=0.03729, over 1423781.72 frames.], batch size: 26, lr: 4.08e-04
+2022-05-14 23:47:15,950 INFO [train.py:812] (2/8) Epoch 19, batch 2950, loss[loss=0.1342, simple_loss=0.2157, pruned_loss=0.02639, over 7280.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2539, pruned_loss=0.03651, over 1429421.47 frames.], batch size: 17, lr: 4.08e-04
+2022-05-14 23:48:15,115 INFO [train.py:812] (2/8) Epoch 19, batch 3000, loss[loss=0.1872, simple_loss=0.2694, pruned_loss=0.05246, over 4890.00 frames.], tot_loss[loss=0.163, simple_loss=0.2532, pruned_loss=0.03639, over 1428840.00 frames.], batch size: 52, lr: 4.07e-04
+2022-05-14 23:48:15,116 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-14 23:48:22,685 INFO [train.py:841] (2/8) Epoch 19, validation: loss=0.1531, simple_loss=0.2523, pruned_loss=0.02694, over 698248.00 frames.
+2022-05-14 23:49:22,399 INFO [train.py:812] (2/8) Epoch 19, batch 3050, loss[loss=0.1681, simple_loss=0.2564, pruned_loss=0.03991, over 7213.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2534, pruned_loss=0.03651, over 1430614.81 frames.], batch size: 23, lr: 4.07e-04
+2022-05-14 23:50:21,359 INFO [train.py:812] (2/8) Epoch 19, batch 3100, loss[loss=0.2147, simple_loss=0.2965, pruned_loss=0.06642, over 6243.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2536, pruned_loss=0.03658, over 1431611.59 frames.], batch size: 37, lr: 4.07e-04
+2022-05-14 23:51:20,042 INFO [train.py:812] (2/8) Epoch 19, batch 3150, loss[loss=0.1514, simple_loss=0.2382, pruned_loss=0.03227, over 7286.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2548, pruned_loss=0.03716, over 1428791.60 frames.], batch size: 18, lr: 4.07e-04
+2022-05-14 23:52:18,618 INFO [train.py:812] (2/8) Epoch 19, batch 3200, loss[loss=0.1576, simple_loss=0.2489, pruned_loss=0.03311, over 7151.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2551, pruned_loss=0.0371, over 1427342.59 frames.], batch size: 19, lr: 4.07e-04
+2022-05-14 23:53:18,015 INFO [train.py:812] (2/8) Epoch 19, batch 3250, loss[loss=0.1264, simple_loss=0.2066, pruned_loss=0.02314, over 7366.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2558, pruned_loss=0.03751, over 1424801.71 frames.], batch size: 19, lr: 4.07e-04
+2022-05-14 23:54:16,316 INFO [train.py:812] (2/8) Epoch 19, batch 3300, loss[loss=0.1849, simple_loss=0.2695, pruned_loss=0.05014, over 6417.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2559, pruned_loss=0.03749, over 1425419.13 frames.], batch size: 37, lr: 4.07e-04
+2022-05-14 23:55:15,322 INFO [train.py:812] (2/8) Epoch 19, batch 3350, loss[loss=0.1711, simple_loss=0.2719, pruned_loss=0.03513, over 7131.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2546, pruned_loss=0.03703, over 1424857.28 frames.], batch size: 21, lr: 4.07e-04
+2022-05-14 23:56:14,420 INFO [train.py:812] (2/8) Epoch 19, batch 3400, loss[loss=0.1784, simple_loss=0.2574, pruned_loss=0.04968, over 7284.00 frames.], tot_loss[loss=0.164, simple_loss=0.2542, pruned_loss=0.03688, over 1425799.58 frames.], batch size: 18, lr: 4.06e-04
+2022-05-14 23:57:14,078 INFO [train.py:812] (2/8) Epoch 19, batch 3450, loss[loss=0.1518, simple_loss=0.2389, pruned_loss=0.03233, over 7360.00 frames.], tot_loss[loss=0.1647, simple_loss=0.254, pruned_loss=0.03769, over 1420854.92 frames.], batch size: 19, lr: 4.06e-04
+2022-05-14 23:58:13,080 INFO [train.py:812] (2/8) Epoch 19, batch 3500, loss[loss=0.1618, simple_loss=0.2493, pruned_loss=0.03711, over 7286.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2542, pruned_loss=0.03774, over 1423763.78 frames.], batch size: 18, lr: 4.06e-04
+2022-05-14 23:59:12,671 INFO [train.py:812] (2/8) Epoch 19, batch 3550, loss[loss=0.1483, simple_loss=0.2234, pruned_loss=0.03657, over 7131.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2532, pruned_loss=0.03714, over 1423353.20 frames.], batch size: 17, lr: 4.06e-04
+2022-05-15 00:00:11,666 INFO [train.py:812] (2/8) Epoch 19, batch 3600, loss[loss=0.2035, simple_loss=0.277, pruned_loss=0.06502, over 7191.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2539, pruned_loss=0.03741, over 1420699.59 frames.], batch size: 23, lr: 4.06e-04
+2022-05-15 00:01:11,063 INFO [train.py:812] (2/8) Epoch 19, batch 3650, loss[loss=0.1611, simple_loss=0.2558, pruned_loss=0.03317, over 7334.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2549, pruned_loss=0.03761, over 1414891.64 frames.], batch size: 20, lr: 4.06e-04
+2022-05-15 00:02:10,078 INFO [train.py:812] (2/8) Epoch 19, batch 3700, loss[loss=0.161, simple_loss=0.2528, pruned_loss=0.03457, over 7412.00 frames.], tot_loss[loss=0.165, simple_loss=0.2549, pruned_loss=0.03755, over 1416993.26 frames.], batch size: 21, lr: 4.06e-04
+2022-05-15 00:03:09,353 INFO [train.py:812] (2/8) Epoch 19, batch 3750, loss[loss=0.1745, simple_loss=0.2619, pruned_loss=0.04352, over 7382.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2546, pruned_loss=0.03762, over 1413683.45 frames.], batch size: 23, lr: 4.06e-04
+2022-05-15 00:04:08,216 INFO [train.py:812] (2/8) Epoch 19, batch 3800, loss[loss=0.1791, simple_loss=0.259, pruned_loss=0.04959, over 7373.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2551, pruned_loss=0.03772, over 1419070.34 frames.], batch size: 19, lr: 4.06e-04
+2022-05-15 00:05:06,749 INFO [train.py:812] (2/8) Epoch 19, batch 3850, loss[loss=0.1376, simple_loss=0.2248, pruned_loss=0.02522, over 7155.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2549, pruned_loss=0.03778, over 1416842.65 frames.], batch size: 18, lr: 4.05e-04
+2022-05-15 00:06:04,372 INFO [train.py:812] (2/8) Epoch 19, batch 3900, loss[loss=0.1709, simple_loss=0.2585, pruned_loss=0.0416, over 7116.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2556, pruned_loss=0.0379, over 1414437.17 frames.], batch size: 21, lr: 4.05e-04
+2022-05-15 00:07:04,143 INFO [train.py:812] (2/8) Epoch 19, batch 3950, loss[loss=0.1677, simple_loss=0.2572, pruned_loss=0.03909, over 7172.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2554, pruned_loss=0.03786, over 1416444.47 frames.], batch size: 18, lr: 4.05e-04
+2022-05-15 00:08:03,278 INFO [train.py:812] (2/8) Epoch 19, batch 4000, loss[loss=0.1896, simple_loss=0.2647, pruned_loss=0.05729, over 4927.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2552, pruned_loss=0.0378, over 1417699.94 frames.], batch size: 52, lr: 4.05e-04
+2022-05-15 00:09:00,795 INFO [train.py:812] (2/8) Epoch 19, batch 4050, loss[loss=0.1458, simple_loss=0.2199, pruned_loss=0.03589, over 6798.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2549, pruned_loss=0.03764, over 1415001.97 frames.], batch size: 15, lr: 4.05e-04
+2022-05-15 00:09:59,474 INFO [train.py:812] (2/8) Epoch 19, batch 4100, loss[loss=0.1643, simple_loss=0.243, pruned_loss=0.04276, over 5136.00 frames.], tot_loss[loss=0.1662, simple_loss=0.256, pruned_loss=0.03822, over 1415395.90 frames.], batch size: 52, lr: 4.05e-04
+2022-05-15 00:10:57,146 INFO [train.py:812] (2/8) Epoch 19, batch 4150, loss[loss=0.1752, simple_loss=0.2669, pruned_loss=0.04175, over 7390.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2549, pruned_loss=0.03794, over 1420408.88 frames.], batch size: 23, lr: 4.05e-04
+2022-05-15 00:11:56,836 INFO [train.py:812] (2/8) Epoch 19, batch 4200, loss[loss=0.1583, simple_loss=0.2502, pruned_loss=0.03317, over 7206.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2543, pruned_loss=0.03769, over 1419161.36 frames.], batch size: 23, lr: 4.05e-04
+2022-05-15 00:12:56,152 INFO [train.py:812] (2/8) Epoch 19, batch 4250, loss[loss=0.1682, simple_loss=0.233, pruned_loss=0.0517, over 6823.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2536, pruned_loss=0.03742, over 1419116.38 frames.], batch size: 15, lr: 4.04e-04
+2022-05-15 00:14:05,102 INFO [train.py:812] (2/8) Epoch 19, batch 4300, loss[loss=0.187, simple_loss=0.28, pruned_loss=0.04701, over 7135.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2535, pruned_loss=0.0377, over 1418361.24 frames.], batch size: 26, lr: 4.04e-04
+2022-05-15 00:15:04,946 INFO [train.py:812] (2/8) Epoch 19, batch 4350, loss[loss=0.1693, simple_loss=0.2561, pruned_loss=0.04122, over 7168.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2531, pruned_loss=0.03726, over 1416808.49 frames.], batch size: 18, lr: 4.04e-04
+2022-05-15 00:16:03,311 INFO [train.py:812] (2/8) Epoch 19, batch 4400, loss[loss=0.1666, simple_loss=0.2617, pruned_loss=0.03575, over 6314.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2532, pruned_loss=0.03729, over 1413418.96 frames.], batch size: 38, lr: 4.04e-04
+2022-05-15 00:17:02,482 INFO [train.py:812] (2/8) Epoch 19, batch 4450, loss[loss=0.1707, simple_loss=0.2479, pruned_loss=0.04678, over 6820.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2526, pruned_loss=0.03729, over 1407449.88 frames.], batch size: 15, lr: 4.04e-04
+2022-05-15 00:18:02,034 INFO [train.py:812] (2/8) Epoch 19, batch 4500, loss[loss=0.1737, simple_loss=0.2754, pruned_loss=0.03606, over 7151.00 frames.], tot_loss[loss=0.165, simple_loss=0.2539, pruned_loss=0.03803, over 1393594.58 frames.], batch size: 20, lr: 4.04e-04
+2022-05-15 00:19:01,074 INFO [train.py:812] (2/8) Epoch 19, batch 4550, loss[loss=0.1729, simple_loss=0.2549, pruned_loss=0.04542, over 6543.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2533, pruned_loss=0.03847, over 1365691.32 frames.], batch size: 38, lr: 4.04e-04
+2022-05-15 00:20:09,397 INFO [train.py:812] (2/8) Epoch 20, batch 0, loss[loss=0.1531, simple_loss=0.2502, pruned_loss=0.02797, over 7343.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2502, pruned_loss=0.02797, over 7343.00 frames.], batch size: 19, lr: 3.94e-04
+2022-05-15 00:21:09,604 INFO [train.py:812] (2/8) Epoch 20, batch 50, loss[loss=0.1462, simple_loss=0.2331, pruned_loss=0.02967, over 7272.00 frames.], tot_loss[loss=0.1626, simple_loss=0.254, pruned_loss=0.03557, over 320731.24 frames.], batch size: 18, lr: 3.94e-04
+2022-05-15 00:22:08,824 INFO [train.py:812] (2/8) Epoch 20, batch 100, loss[loss=0.1769, simple_loss=0.2631, pruned_loss=0.04533, over 5071.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2528, pruned_loss=0.03545, over 565507.96 frames.], batch size: 52, lr: 3.94e-04
+2022-05-15 00:23:08,484 INFO [train.py:812] (2/8) Epoch 20, batch 150, loss[loss=0.1721, simple_loss=0.2737, pruned_loss=0.03524, over 7311.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2551, pruned_loss=0.03632, over 755650.97 frames.], batch size: 21, lr: 3.94e-04
+2022-05-15 00:24:07,745 INFO [train.py:812] (2/8) Epoch 20, batch 200, loss[loss=0.151, simple_loss=0.245, pruned_loss=0.02852, over 7337.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2551, pruned_loss=0.03692, over 902379.85 frames.], batch size: 22, lr: 3.93e-04
+2022-05-15 00:25:08,006 INFO [train.py:812] (2/8) Epoch 20, batch 250, loss[loss=0.1764, simple_loss=0.2711, pruned_loss=0.04088, over 7342.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2538, pruned_loss=0.03671, over 1021558.96 frames.], batch size: 22, lr: 3.93e-04
+2022-05-15 00:26:07,270 INFO [train.py:812] (2/8) Epoch 20, batch 300, loss[loss=0.1711, simple_loss=0.2558, pruned_loss=0.04319, over 7197.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2542, pruned_loss=0.03645, over 1111343.10 frames.], batch size: 23, lr: 3.93e-04
+2022-05-15 00:27:07,174 INFO [train.py:812] (2/8) Epoch 20, batch 350, loss[loss=0.161, simple_loss=0.2592, pruned_loss=0.03134, over 7149.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2543, pruned_loss=0.03646, over 1184135.47 frames.], batch size: 20, lr: 3.93e-04
+2022-05-15 00:28:05,117 INFO [train.py:812] (2/8) Epoch 20, batch 400, loss[loss=0.1678, simple_loss=0.2622, pruned_loss=0.03672, over 7144.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2551, pruned_loss=0.03655, over 1237299.54 frames.], batch size: 20, lr: 3.93e-04
+2022-05-15 00:29:03,591 INFO [train.py:812] (2/8) Epoch 20, batch 450, loss[loss=0.2046, simple_loss=0.3017, pruned_loss=0.05373, over 7380.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2557, pruned_loss=0.03693, over 1273659.39 frames.], batch size: 23, lr: 3.93e-04
+2022-05-15 00:30:01,913 INFO [train.py:812] (2/8) Epoch 20, batch 500, loss[loss=0.1528, simple_loss=0.2441, pruned_loss=0.03069, over 7225.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2556, pruned_loss=0.03697, over 1305776.87 frames.], batch size: 21, lr: 3.93e-04
+2022-05-15 00:31:00,460 INFO [train.py:812] (2/8) Epoch 20, batch 550, loss[loss=0.1607, simple_loss=0.2585, pruned_loss=0.03141, over 6729.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2548, pruned_loss=0.03653, over 1332488.24 frames.], batch size: 31, lr: 3.93e-04
+2022-05-15 00:32:00,114 INFO [train.py:812] (2/8) Epoch 20, batch 600, loss[loss=0.1378, simple_loss=0.2188, pruned_loss=0.02843, over 7152.00 frames.], tot_loss[loss=0.163, simple_loss=0.2533, pruned_loss=0.03631, over 1355296.20 frames.], batch size: 18, lr: 3.93e-04
+2022-05-15 00:32:59,172 INFO [train.py:812] (2/8) Epoch 20, batch 650, loss[loss=0.1774, simple_loss=0.2662, pruned_loss=0.04432, over 7154.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2534, pruned_loss=0.036, over 1369991.73 frames.], batch size: 18, lr: 3.92e-04
+2022-05-15 00:33:55,660 INFO [train.py:812] (2/8) Epoch 20, batch 700, loss[loss=0.1701, simple_loss=0.2527, pruned_loss=0.04379, over 7233.00 frames.], tot_loss[loss=0.163, simple_loss=0.254, pruned_loss=0.036, over 1384029.40 frames.], batch size: 20, lr: 3.92e-04
+2022-05-15 00:34:54,548 INFO [train.py:812] (2/8) Epoch 20, batch 750, loss[loss=0.1723, simple_loss=0.2773, pruned_loss=0.03369, over 7317.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2535, pruned_loss=0.03564, over 1394471.22 frames.], batch size: 25, lr: 3.92e-04
+2022-05-15 00:35:51,669 INFO [train.py:812] (2/8) Epoch 20, batch 800, loss[loss=0.1406, simple_loss=0.2242, pruned_loss=0.02848, over 7404.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2529, pruned_loss=0.03569, over 1403860.48 frames.], batch size: 18, lr: 3.92e-04
+2022-05-15 00:36:56,618 INFO [train.py:812] (2/8) Epoch 20, batch 850, loss[loss=0.1893, simple_loss=0.2774, pruned_loss=0.05061, over 7070.00 frames.], tot_loss[loss=0.162, simple_loss=0.2525, pruned_loss=0.03568, over 1411158.67 frames.], batch size: 28, lr: 3.92e-04
+2022-05-15 00:37:55,424 INFO [train.py:812] (2/8) Epoch 20, batch 900, loss[loss=0.1662, simple_loss=0.2464, pruned_loss=0.04297, over 7359.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2525, pruned_loss=0.03616, over 1415756.34 frames.], batch size: 19, lr: 3.92e-04
+2022-05-15 00:38:53,707 INFO [train.py:812] (2/8) Epoch 20, batch 950, loss[loss=0.1554, simple_loss=0.252, pruned_loss=0.02937, over 7244.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2536, pruned_loss=0.03693, over 1419117.04 frames.], batch size: 20, lr: 3.92e-04
+2022-05-15 00:39:52,436 INFO [train.py:812] (2/8) Epoch 20, batch 1000, loss[loss=0.2036, simple_loss=0.2978, pruned_loss=0.0547, over 7288.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2539, pruned_loss=0.03681, over 1420416.94 frames.], batch size: 24, lr: 3.92e-04
+2022-05-15 00:40:51,900 INFO [train.py:812] (2/8) Epoch 20, batch 1050, loss[loss=0.194, simple_loss=0.2813, pruned_loss=0.05333, over 7196.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2535, pruned_loss=0.03673, over 1420291.90 frames.], batch size: 22, lr: 3.92e-04
+2022-05-15 00:41:50,550 INFO [train.py:812] (2/8) Epoch 20, batch 1100, loss[loss=0.159, simple_loss=0.2583, pruned_loss=0.02991, over 7193.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2534, pruned_loss=0.03687, over 1415604.70 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:42:49,016 INFO [train.py:812] (2/8) Epoch 20, batch 1150, loss[loss=0.1878, simple_loss=0.286, pruned_loss=0.0448, over 7301.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2536, pruned_loss=0.03661, over 1419702.12 frames.], batch size: 24, lr: 3.91e-04
+2022-05-15 00:43:48,283 INFO [train.py:812] (2/8) Epoch 20, batch 1200, loss[loss=0.1678, simple_loss=0.2625, pruned_loss=0.03656, over 7319.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2522, pruned_loss=0.03609, over 1424963.94 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:44:47,753 INFO [train.py:812] (2/8) Epoch 20, batch 1250, loss[loss=0.1228, simple_loss=0.2056, pruned_loss=0.02002, over 7135.00 frames.], tot_loss[loss=0.162, simple_loss=0.2522, pruned_loss=0.03588, over 1425272.85 frames.], batch size: 17, lr: 3.91e-04
+2022-05-15 00:45:46,868 INFO [train.py:812] (2/8) Epoch 20, batch 1300, loss[loss=0.1723, simple_loss=0.2621, pruned_loss=0.04125, over 7120.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2525, pruned_loss=0.03624, over 1427257.33 frames.], batch size: 21, lr: 3.91e-04
+2022-05-15 00:46:46,851 INFO [train.py:812] (2/8) Epoch 20, batch 1350, loss[loss=0.1546, simple_loss=0.2439, pruned_loss=0.03264, over 7196.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2528, pruned_loss=0.03588, over 1428410.62 frames.], batch size: 22, lr: 3.91e-04
+2022-05-15 00:47:55,897 INFO [train.py:812] (2/8) Epoch 20, batch 1400, loss[loss=0.1538, simple_loss=0.2429, pruned_loss=0.03236, over 7163.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2527, pruned_loss=0.03598, over 1430097.93 frames.], batch size: 26, lr: 3.91e-04
+2022-05-15 00:48:55,551 INFO [train.py:812] (2/8) Epoch 20, batch 1450, loss[loss=0.1733, simple_loss=0.2645, pruned_loss=0.04109, over 7196.00 frames.], tot_loss[loss=0.164, simple_loss=0.2539, pruned_loss=0.03706, over 1428467.82 frames.], batch size: 26, lr: 3.91e-04
+2022-05-15 00:49:54,737 INFO [train.py:812] (2/8) Epoch 20, batch 1500, loss[loss=0.1513, simple_loss=0.2537, pruned_loss=0.02447, over 7386.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2556, pruned_loss=0.03775, over 1426719.82 frames.], batch size: 23, lr: 3.91e-04
+2022-05-15 00:51:04,080 INFO [train.py:812] (2/8) Epoch 20, batch 1550, loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03321, over 7423.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2549, pruned_loss=0.03743, over 1428681.69 frames.], batch size: 20, lr: 3.91e-04
+2022-05-15 00:52:22,069 INFO [train.py:812] (2/8) Epoch 20, batch 1600, loss[loss=0.1805, simple_loss=0.2707, pruned_loss=0.04519, over 7331.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2549, pruned_loss=0.03722, over 1423555.86 frames.], batch size: 22, lr: 3.90e-04
+2022-05-15 00:53:19,531 INFO [train.py:812] (2/8) Epoch 20, batch 1650, loss[loss=0.1591, simple_loss=0.253, pruned_loss=0.03257, over 7185.00 frames.], tot_loss[loss=0.165, simple_loss=0.2553, pruned_loss=0.03733, over 1420481.63 frames.], batch size: 23, lr: 3.90e-04
+2022-05-15 00:54:36,072 INFO [train.py:812] (2/8) Epoch 20, batch 1700, loss[loss=0.1329, simple_loss=0.2196, pruned_loss=0.02314, over 7160.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2544, pruned_loss=0.03725, over 1420345.42 frames.], batch size: 19, lr: 3.90e-04
+2022-05-15 00:55:43,686 INFO [train.py:812] (2/8) Epoch 20, batch 1750, loss[loss=0.1693, simple_loss=0.2541, pruned_loss=0.04219, over 7326.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2536, pruned_loss=0.03666, over 1425965.59 frames.], batch size: 22, lr: 3.90e-04
+2022-05-15 00:56:42,661 INFO [train.py:812] (2/8) Epoch 20, batch 1800, loss[loss=0.1611, simple_loss=0.2594, pruned_loss=0.03135, over 7301.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2534, pruned_loss=0.03609, over 1424807.72 frames.], batch size: 25, lr: 3.90e-04
+2022-05-15 00:57:42,326 INFO [train.py:812] (2/8) Epoch 20, batch 1850, loss[loss=0.1325, simple_loss=0.2257, pruned_loss=0.01961, over 7082.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2534, pruned_loss=0.03599, over 1428348.35 frames.], batch size: 18, lr: 3.90e-04
+2022-05-15 00:58:41,675 INFO [train.py:812] (2/8) Epoch 20, batch 1900, loss[loss=0.139, simple_loss=0.238, pruned_loss=0.01996, over 7233.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2533, pruned_loss=0.03572, over 1428879.53 frames.], batch size: 20, lr: 3.90e-04
+2022-05-15 00:59:40,058 INFO [train.py:812] (2/8) Epoch 20, batch 1950, loss[loss=0.1591, simple_loss=0.2528, pruned_loss=0.03268, over 6303.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2517, pruned_loss=0.03537, over 1428785.46 frames.], batch size: 37, lr: 3.90e-04
+2022-05-15 01:00:37,500 INFO [train.py:812] (2/8) Epoch 20, batch 2000, loss[loss=0.1504, simple_loss=0.2479, pruned_loss=0.02641, over 7236.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2506, pruned_loss=0.03519, over 1429462.61 frames.], batch size: 20, lr: 3.90e-04
+2022-05-15 01:01:35,459 INFO [train.py:812] (2/8) Epoch 20, batch 2050, loss[loss=0.1696, simple_loss=0.258, pruned_loss=0.04065, over 7218.00 frames.], tot_loss[loss=0.16, simple_loss=0.2499, pruned_loss=0.03508, over 1428974.84 frames.], batch size: 21, lr: 3.89e-04
+2022-05-15 01:02:33,044 INFO [train.py:812] (2/8) Epoch 20, batch 2100, loss[loss=0.1696, simple_loss=0.2596, pruned_loss=0.03981, over 7443.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2497, pruned_loss=0.0347, over 1431711.57 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:03:30,905 INFO [train.py:812] (2/8) Epoch 20, batch 2150, loss[loss=0.1916, simple_loss=0.2802, pruned_loss=0.0515, over 7218.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2513, pruned_loss=0.0354, over 1425151.61 frames.], batch size: 22, lr: 3.89e-04
+2022-05-15 01:04:30,267 INFO [train.py:812] (2/8) Epoch 20, batch 2200, loss[loss=0.1583, simple_loss=0.2374, pruned_loss=0.03963, over 6817.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2511, pruned_loss=0.03569, over 1420709.60 frames.], batch size: 15, lr: 3.89e-04
+2022-05-15 01:05:28,860 INFO [train.py:812] (2/8) Epoch 20, batch 2250, loss[loss=0.1621, simple_loss=0.2607, pruned_loss=0.03175, over 7151.00 frames.], tot_loss[loss=0.161, simple_loss=0.2507, pruned_loss=0.03558, over 1422868.58 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:06:27,811 INFO [train.py:812] (2/8) Epoch 20, batch 2300, loss[loss=0.1775, simple_loss=0.2679, pruned_loss=0.04351, over 7372.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2515, pruned_loss=0.03608, over 1423065.67 frames.], batch size: 23, lr: 3.89e-04
+2022-05-15 01:07:25,467 INFO [train.py:812] (2/8) Epoch 20, batch 2350, loss[loss=0.1596, simple_loss=0.2542, pruned_loss=0.03251, over 7316.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2521, pruned_loss=0.0362, over 1421827.63 frames.], batch size: 21, lr: 3.89e-04
+2022-05-15 01:08:24,201 INFO [train.py:812] (2/8) Epoch 20, batch 2400, loss[loss=0.1374, simple_loss=0.2364, pruned_loss=0.01922, over 7425.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2518, pruned_loss=0.03624, over 1423717.61 frames.], batch size: 20, lr: 3.89e-04
+2022-05-15 01:09:23,907 INFO [train.py:812] (2/8) Epoch 20, batch 2450, loss[loss=0.162, simple_loss=0.2555, pruned_loss=0.03424, over 7102.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2512, pruned_loss=0.03601, over 1426730.03 frames.], batch size: 28, lr: 3.89e-04
+2022-05-15 01:10:23,010 INFO [train.py:812] (2/8) Epoch 20, batch 2500, loss[loss=0.1728, simple_loss=0.2557, pruned_loss=0.0449, over 7166.00 frames.], tot_loss[loss=0.161, simple_loss=0.2506, pruned_loss=0.03571, over 1425006.86 frames.], batch size: 26, lr: 3.88e-04
+2022-05-15 01:11:22,819 INFO [train.py:812] (2/8) Epoch 20, batch 2550, loss[loss=0.1509, simple_loss=0.2399, pruned_loss=0.03093, over 7328.00 frames.], tot_loss[loss=0.161, simple_loss=0.2504, pruned_loss=0.03581, over 1424053.18 frames.], batch size: 20, lr: 3.88e-04
+2022-05-15 01:12:22,060 INFO [train.py:812] (2/8) Epoch 20, batch 2600, loss[loss=0.1681, simple_loss=0.2646, pruned_loss=0.03578, over 6785.00 frames.], tot_loss[loss=0.1612, simple_loss=0.251, pruned_loss=0.03569, over 1424818.55 frames.], batch size: 31, lr: 3.88e-04
+2022-05-15 01:13:22,179 INFO [train.py:812] (2/8) Epoch 20, batch 2650, loss[loss=0.147, simple_loss=0.2348, pruned_loss=0.02965, over 6987.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2507, pruned_loss=0.03559, over 1426052.91 frames.], batch size: 16, lr: 3.88e-04
+2022-05-15 01:14:21,646 INFO [train.py:812] (2/8) Epoch 20, batch 2700, loss[loss=0.1582, simple_loss=0.2445, pruned_loss=0.03596, over 7385.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2502, pruned_loss=0.03523, over 1427405.50 frames.], batch size: 23, lr: 3.88e-04
+2022-05-15 01:15:21,496 INFO [train.py:812] (2/8) Epoch 20, batch 2750, loss[loss=0.1642, simple_loss=0.2646, pruned_loss=0.03191, over 7224.00 frames.], tot_loss[loss=0.161, simple_loss=0.251, pruned_loss=0.03548, over 1425682.19 frames.], batch size: 23, lr: 3.88e-04
+2022-05-15 01:16:20,982 INFO [train.py:812] (2/8) Epoch 20, batch 2800, loss[loss=0.1403, simple_loss=0.2238, pruned_loss=0.02842, over 7171.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2518, pruned_loss=0.03554, over 1429452.77 frames.], batch size: 18, lr: 3.88e-04
+2022-05-15 01:17:20,836 INFO [train.py:812] (2/8) Epoch 20, batch 2850, loss[loss=0.177, simple_loss=0.2736, pruned_loss=0.04018, over 7408.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2516, pruned_loss=0.03577, over 1431183.34 frames.], batch size: 21, lr: 3.88e-04
+2022-05-15 01:18:20,076 INFO [train.py:812] (2/8) Epoch 20, batch 2900, loss[loss=0.1578, simple_loss=0.2535, pruned_loss=0.031, over 7171.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2515, pruned_loss=0.03582, over 1426320.48 frames.], batch size: 26, lr: 3.88e-04
+2022-05-15 01:19:19,541 INFO [train.py:812] (2/8) Epoch 20, batch 2950, loss[loss=0.1687, simple_loss=0.2593, pruned_loss=0.0391, over 7240.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2527, pruned_loss=0.03606, over 1430445.77 frames.], batch size: 20, lr: 3.87e-04
+2022-05-15 01:20:18,536 INFO [train.py:812] (2/8) Epoch 20, batch 3000, loss[loss=0.2304, simple_loss=0.3213, pruned_loss=0.0697, over 7386.00 frames.], tot_loss[loss=0.163, simple_loss=0.2534, pruned_loss=0.0363, over 1429904.35 frames.], batch size: 23, lr: 3.87e-04
+2022-05-15 01:20:18,537 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 01:20:27,134 INFO [train.py:841] (2/8) Epoch 20, validation: loss=0.1532, simple_loss=0.2519, pruned_loss=0.02723, over 698248.00 frames.
+2022-05-15 01:21:26,427 INFO [train.py:812] (2/8) Epoch 20, batch 3050, loss[loss=0.1609, simple_loss=0.2529, pruned_loss=0.03444, over 7161.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2528, pruned_loss=0.03606, over 1431513.88 frames.], batch size: 19, lr: 3.87e-04
+2022-05-15 01:22:25,387 INFO [train.py:812] (2/8) Epoch 20, batch 3100, loss[loss=0.1581, simple_loss=0.2542, pruned_loss=0.03098, over 7118.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2531, pruned_loss=0.03586, over 1430462.99 frames.], batch size: 21, lr: 3.87e-04
+2022-05-15 01:23:24,546 INFO [train.py:812] (2/8) Epoch 20, batch 3150, loss[loss=0.1303, simple_loss=0.2136, pruned_loss=0.02351, over 7259.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2532, pruned_loss=0.03656, over 1431466.42 frames.], batch size: 18, lr: 3.87e-04
+2022-05-15 01:24:21,331 INFO [train.py:812] (2/8) Epoch 20, batch 3200, loss[loss=0.1888, simple_loss=0.2879, pruned_loss=0.04491, over 6739.00 frames.], tot_loss[loss=0.1623, simple_loss=0.252, pruned_loss=0.03626, over 1431032.98 frames.], batch size: 31, lr: 3.87e-04
+2022-05-15 01:25:18,747 INFO [train.py:812] (2/8) Epoch 20, batch 3250, loss[loss=0.1575, simple_loss=0.2444, pruned_loss=0.03525, over 7063.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2528, pruned_loss=0.03637, over 1427874.01 frames.], batch size: 18, lr: 3.87e-04
+2022-05-15 01:26:16,472 INFO [train.py:812] (2/8) Epoch 20, batch 3300, loss[loss=0.1551, simple_loss=0.2398, pruned_loss=0.03521, over 7135.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2527, pruned_loss=0.03626, over 1426188.71 frames.], batch size: 17, lr: 3.87e-04
+2022-05-15 01:27:14,129 INFO [train.py:812] (2/8) Epoch 20, batch 3350, loss[loss=0.1516, simple_loss=0.2494, pruned_loss=0.02693, over 7142.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2526, pruned_loss=0.03632, over 1426362.51 frames.], batch size: 20, lr: 3.87e-04
+2022-05-15 01:28:13,194 INFO [train.py:812] (2/8) Epoch 20, batch 3400, loss[loss=0.1542, simple_loss=0.2376, pruned_loss=0.03544, over 7272.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2524, pruned_loss=0.03625, over 1425569.40 frames.], batch size: 17, lr: 3.87e-04
+2022-05-15 01:29:12,363 INFO [train.py:812] (2/8) Epoch 20, batch 3450, loss[loss=0.151, simple_loss=0.2488, pruned_loss=0.0266, over 7229.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2526, pruned_loss=0.03639, over 1424390.08 frames.], batch size: 20, lr: 3.86e-04
+2022-05-15 01:30:11,788 INFO [train.py:812] (2/8) Epoch 20, batch 3500, loss[loss=0.1674, simple_loss=0.2564, pruned_loss=0.03919, over 7251.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2517, pruned_loss=0.0357, over 1423753.72 frames.], batch size: 19, lr: 3.86e-04
+2022-05-15 01:31:11,499 INFO [train.py:812] (2/8) Epoch 20, batch 3550, loss[loss=0.159, simple_loss=0.2557, pruned_loss=0.03114, over 7119.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2519, pruned_loss=0.03574, over 1426492.39 frames.], batch size: 21, lr: 3.86e-04
+2022-05-15 01:32:10,997 INFO [train.py:812] (2/8) Epoch 20, batch 3600, loss[loss=0.1675, simple_loss=0.2574, pruned_loss=0.03874, over 7204.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2519, pruned_loss=0.03586, over 1429520.13 frames.], batch size: 23, lr: 3.86e-04
+2022-05-15 01:33:10,981 INFO [train.py:812] (2/8) Epoch 20, batch 3650, loss[loss=0.1554, simple_loss=0.247, pruned_loss=0.03184, over 7320.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2521, pruned_loss=0.03601, over 1429558.38 frames.], batch size: 21, lr: 3.86e-04
+2022-05-15 01:34:09,095 INFO [train.py:812] (2/8) Epoch 20, batch 3700, loss[loss=0.1347, simple_loss=0.2185, pruned_loss=0.02542, over 7160.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2524, pruned_loss=0.03624, over 1431764.41 frames.], batch size: 18, lr: 3.86e-04
+2022-05-15 01:35:08,005 INFO [train.py:812] (2/8) Epoch 20, batch 3750, loss[loss=0.1673, simple_loss=0.2675, pruned_loss=0.03356, over 7100.00 frames.], tot_loss[loss=0.162, simple_loss=0.252, pruned_loss=0.03601, over 1426751.08 frames.], batch size: 28, lr: 3.86e-04
+2022-05-15 01:36:06,434 INFO [train.py:812] (2/8) Epoch 20, batch 3800, loss[loss=0.1485, simple_loss=0.2404, pruned_loss=0.0283, over 7332.00 frames.], tot_loss[loss=0.162, simple_loss=0.2518, pruned_loss=0.03609, over 1421405.73 frames.], batch size: 20, lr: 3.86e-04
+2022-05-15 01:37:04,405 INFO [train.py:812] (2/8) Epoch 20, batch 3850, loss[loss=0.1539, simple_loss=0.2359, pruned_loss=0.03593, over 7269.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2515, pruned_loss=0.03558, over 1419352.27 frames.], batch size: 17, lr: 3.86e-04
+2022-05-15 01:38:02,160 INFO [train.py:812] (2/8) Epoch 20, batch 3900, loss[loss=0.1441, simple_loss=0.2409, pruned_loss=0.02368, over 7106.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2521, pruned_loss=0.03582, over 1416535.90 frames.], batch size: 21, lr: 3.85e-04
+2022-05-15 01:39:01,289 INFO [train.py:812] (2/8) Epoch 20, batch 3950, loss[loss=0.1438, simple_loss=0.2314, pruned_loss=0.02808, over 7328.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2517, pruned_loss=0.03568, over 1411390.25 frames.], batch size: 20, lr: 3.85e-04
+2022-05-15 01:39:59,108 INFO [train.py:812] (2/8) Epoch 20, batch 4000, loss[loss=0.1413, simple_loss=0.2291, pruned_loss=0.02674, over 7159.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2514, pruned_loss=0.03587, over 1409021.47 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:40:58,257 INFO [train.py:812] (2/8) Epoch 20, batch 4050, loss[loss=0.1444, simple_loss=0.2459, pruned_loss=0.02146, over 7325.00 frames.], tot_loss[loss=0.1622, simple_loss=0.252, pruned_loss=0.03619, over 1406633.73 frames.], batch size: 20, lr: 3.85e-04
+2022-05-15 01:41:57,208 INFO [train.py:812] (2/8) Epoch 20, batch 4100, loss[loss=0.1732, simple_loss=0.2608, pruned_loss=0.0428, over 7283.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2508, pruned_loss=0.03599, over 1407046.77 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:42:56,561 INFO [train.py:812] (2/8) Epoch 20, batch 4150, loss[loss=0.1495, simple_loss=0.2328, pruned_loss=0.03311, over 7066.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2497, pruned_loss=0.03534, over 1410867.33 frames.], batch size: 18, lr: 3.85e-04
+2022-05-15 01:43:53,659 INFO [train.py:812] (2/8) Epoch 20, batch 4200, loss[loss=0.1573, simple_loss=0.2403, pruned_loss=0.03715, over 7198.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2507, pruned_loss=0.03591, over 1404931.70 frames.], batch size: 16, lr: 3.85e-04
+2022-05-15 01:44:52,593 INFO [train.py:812] (2/8) Epoch 20, batch 4250, loss[loss=0.1965, simple_loss=0.2892, pruned_loss=0.05193, over 7210.00 frames.], tot_loss[loss=0.161, simple_loss=0.2504, pruned_loss=0.03584, over 1403370.72 frames.], batch size: 23, lr: 3.85e-04
+2022-05-15 01:45:49,893 INFO [train.py:812] (2/8) Epoch 20, batch 4300, loss[loss=0.1693, simple_loss=0.2688, pruned_loss=0.03491, over 7230.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2511, pruned_loss=0.03581, over 1400879.59 frames.], batch size: 21, lr: 3.85e-04
+2022-05-15 01:46:49,036 INFO [train.py:812] (2/8) Epoch 20, batch 4350, loss[loss=0.1914, simple_loss=0.2758, pruned_loss=0.05357, over 5259.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2499, pruned_loss=0.03563, over 1404183.64 frames.], batch size: 52, lr: 3.84e-04
+2022-05-15 01:47:48,042 INFO [train.py:812] (2/8) Epoch 20, batch 4400, loss[loss=0.1645, simple_loss=0.2597, pruned_loss=0.03464, over 7162.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2501, pruned_loss=0.03557, over 1399642.35 frames.], batch size: 19, lr: 3.84e-04
+2022-05-15 01:48:47,111 INFO [train.py:812] (2/8) Epoch 20, batch 4450, loss[loss=0.1409, simple_loss=0.2238, pruned_loss=0.02899, over 6805.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2506, pruned_loss=0.03619, over 1389279.94 frames.], batch size: 15, lr: 3.84e-04
+2022-05-15 01:49:45,783 INFO [train.py:812] (2/8) Epoch 20, batch 4500, loss[loss=0.1662, simple_loss=0.2636, pruned_loss=0.03438, over 7198.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2513, pruned_loss=0.0361, over 1382226.63 frames.], batch size: 23, lr: 3.84e-04
+2022-05-15 01:50:44,465 INFO [train.py:812] (2/8) Epoch 20, batch 4550, loss[loss=0.1706, simple_loss=0.2682, pruned_loss=0.03653, over 6440.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2537, pruned_loss=0.03773, over 1338652.39 frames.], batch size: 38, lr: 3.84e-04
+2022-05-15 01:51:55,160 INFO [train.py:812] (2/8) Epoch 21, batch 0, loss[loss=0.1568, simple_loss=0.2417, pruned_loss=0.03594, over 6981.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2417, pruned_loss=0.03594, over 6981.00 frames.], batch size: 16, lr: 3.75e-04
+2022-05-15 01:52:55,021 INFO [train.py:812] (2/8) Epoch 21, batch 50, loss[loss=0.1738, simple_loss=0.2744, pruned_loss=0.03664, over 6452.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2545, pruned_loss=0.03661, over 323056.04 frames.], batch size: 37, lr: 3.75e-04
+2022-05-15 01:53:53,841 INFO [train.py:812] (2/8) Epoch 21, batch 100, loss[loss=0.1684, simple_loss=0.2547, pruned_loss=0.041, over 7250.00 frames.], tot_loss[loss=0.1636, simple_loss=0.254, pruned_loss=0.03659, over 567426.72 frames.], batch size: 16, lr: 3.75e-04
+2022-05-15 01:54:52,708 INFO [train.py:812] (2/8) Epoch 21, batch 150, loss[loss=0.1455, simple_loss=0.2365, pruned_loss=0.02724, over 7156.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2526, pruned_loss=0.03609, over 755990.98 frames.], batch size: 18, lr: 3.75e-04
+2022-05-15 01:55:51,318 INFO [train.py:812] (2/8) Epoch 21, batch 200, loss[loss=0.167, simple_loss=0.2674, pruned_loss=0.03327, over 6787.00 frames.], tot_loss[loss=0.1627, simple_loss=0.253, pruned_loss=0.03623, over 900868.19 frames.], batch size: 31, lr: 3.75e-04
+2022-05-15 01:56:53,973 INFO [train.py:812] (2/8) Epoch 21, batch 250, loss[loss=0.1604, simple_loss=0.2498, pruned_loss=0.03551, over 7161.00 frames.], tot_loss[loss=0.162, simple_loss=0.2523, pruned_loss=0.03583, over 1012139.89 frames.], batch size: 19, lr: 3.75e-04
+2022-05-15 01:57:52,816 INFO [train.py:812] (2/8) Epoch 21, batch 300, loss[loss=0.1541, simple_loss=0.2348, pruned_loss=0.03673, over 7286.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2527, pruned_loss=0.03635, over 1101552.24 frames.], batch size: 18, lr: 3.75e-04
+2022-05-15 01:58:49,822 INFO [train.py:812] (2/8) Epoch 21, batch 350, loss[loss=0.1364, simple_loss=0.2261, pruned_loss=0.02335, over 7263.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2525, pruned_loss=0.03617, over 1170182.21 frames.], batch size: 19, lr: 3.74e-04
+2022-05-15 01:59:47,327 INFO [train.py:812] (2/8) Epoch 21, batch 400, loss[loss=0.1803, simple_loss=0.2692, pruned_loss=0.04571, over 7063.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2524, pruned_loss=0.03569, over 1230009.85 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:00:46,715 INFO [train.py:812] (2/8) Epoch 21, batch 450, loss[loss=0.1709, simple_loss=0.262, pruned_loss=0.03984, over 7056.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2519, pruned_loss=0.03527, over 1273257.60 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:01:45,879 INFO [train.py:812] (2/8) Epoch 21, batch 500, loss[loss=0.1524, simple_loss=0.2464, pruned_loss=0.0292, over 7068.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2518, pruned_loss=0.03526, over 1312121.07 frames.], batch size: 28, lr: 3.74e-04
+2022-05-15 02:02:44,639 INFO [train.py:812] (2/8) Epoch 21, batch 550, loss[loss=0.1285, simple_loss=0.2119, pruned_loss=0.02257, over 7179.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2506, pruned_loss=0.03458, over 1337865.91 frames.], batch size: 16, lr: 3.74e-04
+2022-05-15 02:03:42,789 INFO [train.py:812] (2/8) Epoch 21, batch 600, loss[loss=0.1979, simple_loss=0.2937, pruned_loss=0.05103, over 7201.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2515, pruned_loss=0.03498, over 1355731.41 frames.], batch size: 22, lr: 3.74e-04
+2022-05-15 02:04:42,158 INFO [train.py:812] (2/8) Epoch 21, batch 650, loss[loss=0.1675, simple_loss=0.2454, pruned_loss=0.04485, over 7121.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2507, pruned_loss=0.03497, over 1370629.84 frames.], batch size: 17, lr: 3.74e-04
+2022-05-15 02:05:41,118 INFO [train.py:812] (2/8) Epoch 21, batch 700, loss[loss=0.1593, simple_loss=0.2602, pruned_loss=0.02923, over 7232.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2518, pruned_loss=0.03534, over 1380313.21 frames.], batch size: 20, lr: 3.74e-04
+2022-05-15 02:06:40,203 INFO [train.py:812] (2/8) Epoch 21, batch 750, loss[loss=0.1422, simple_loss=0.2252, pruned_loss=0.02964, over 7411.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2522, pruned_loss=0.03565, over 1385421.36 frames.], batch size: 18, lr: 3.74e-04
+2022-05-15 02:07:37,517 INFO [train.py:812] (2/8) Epoch 21, batch 800, loss[loss=0.153, simple_loss=0.2464, pruned_loss=0.02984, over 7233.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2524, pruned_loss=0.03616, over 1384509.20 frames.], batch size: 20, lr: 3.73e-04
+2022-05-15 02:08:37,256 INFO [train.py:812] (2/8) Epoch 21, batch 850, loss[loss=0.1663, simple_loss=0.2572, pruned_loss=0.03774, over 7316.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2513, pruned_loss=0.03559, over 1390316.10 frames.], batch size: 25, lr: 3.73e-04
+2022-05-15 02:09:36,860 INFO [train.py:812] (2/8) Epoch 21, batch 900, loss[loss=0.1579, simple_loss=0.249, pruned_loss=0.03344, over 7227.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2504, pruned_loss=0.03512, over 1399755.85 frames.], batch size: 20, lr: 3.73e-04
+2022-05-15 02:10:36,704 INFO [train.py:812] (2/8) Epoch 21, batch 950, loss[loss=0.155, simple_loss=0.248, pruned_loss=0.03099, over 7326.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2512, pruned_loss=0.03549, over 1405739.93 frames.], batch size: 22, lr: 3.73e-04
+2022-05-15 02:11:34,902 INFO [train.py:812] (2/8) Epoch 21, batch 1000, loss[loss=0.1869, simple_loss=0.2772, pruned_loss=0.04833, over 7199.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2517, pruned_loss=0.03545, over 1405071.15 frames.], batch size: 23, lr: 3.73e-04
+2022-05-15 02:12:42,503 INFO [train.py:812] (2/8) Epoch 21, batch 1050, loss[loss=0.1681, simple_loss=0.266, pruned_loss=0.03515, over 7410.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2528, pruned_loss=0.03612, over 1406235.61 frames.], batch size: 21, lr: 3.73e-04
+2022-05-15 02:13:41,818 INFO [train.py:812] (2/8) Epoch 21, batch 1100, loss[loss=0.1628, simple_loss=0.2445, pruned_loss=0.04056, over 6879.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2512, pruned_loss=0.03531, over 1407483.85 frames.], batch size: 15, lr: 3.73e-04
+2022-05-15 02:14:40,535 INFO [train.py:812] (2/8) Epoch 21, batch 1150, loss[loss=0.153, simple_loss=0.2357, pruned_loss=0.03516, over 7286.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2505, pruned_loss=0.03488, over 1413213.01 frames.], batch size: 24, lr: 3.73e-04
+2022-05-15 02:15:37,797 INFO [train.py:812] (2/8) Epoch 21, batch 1200, loss[loss=0.144, simple_loss=0.2268, pruned_loss=0.03064, over 7276.00 frames.], tot_loss[loss=0.161, simple_loss=0.2516, pruned_loss=0.03518, over 1415172.63 frames.], batch size: 18, lr: 3.73e-04
+2022-05-15 02:16:37,261 INFO [train.py:812] (2/8) Epoch 21, batch 1250, loss[loss=0.1812, simple_loss=0.2802, pruned_loss=0.0411, over 7301.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2509, pruned_loss=0.03497, over 1417322.13 frames.], batch size: 24, lr: 3.73e-04
+2022-05-15 02:17:36,464 INFO [train.py:812] (2/8) Epoch 21, batch 1300, loss[loss=0.1537, simple_loss=0.2406, pruned_loss=0.03339, over 7068.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2502, pruned_loss=0.03516, over 1415974.18 frames.], batch size: 18, lr: 3.72e-04
+2022-05-15 02:18:34,031 INFO [train.py:812] (2/8) Epoch 21, batch 1350, loss[loss=0.1694, simple_loss=0.2732, pruned_loss=0.03278, over 7336.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2494, pruned_loss=0.03497, over 1422997.42 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:19:32,907 INFO [train.py:812] (2/8) Epoch 21, batch 1400, loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03054, over 7370.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2495, pruned_loss=0.03494, over 1425628.27 frames.], batch size: 23, lr: 3.72e-04
+2022-05-15 02:20:31,803 INFO [train.py:812] (2/8) Epoch 21, batch 1450, loss[loss=0.1789, simple_loss=0.2638, pruned_loss=0.04698, over 4835.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2492, pruned_loss=0.03516, over 1419744.26 frames.], batch size: 52, lr: 3.72e-04
+2022-05-15 02:21:30,171 INFO [train.py:812] (2/8) Epoch 21, batch 1500, loss[loss=0.1763, simple_loss=0.2722, pruned_loss=0.04021, over 7325.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2508, pruned_loss=0.03582, over 1417865.09 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:22:29,839 INFO [train.py:812] (2/8) Epoch 21, batch 1550, loss[loss=0.1744, simple_loss=0.254, pruned_loss=0.04737, over 6957.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2518, pruned_loss=0.03659, over 1420128.30 frames.], batch size: 32, lr: 3.72e-04
+2022-05-15 02:23:26,749 INFO [train.py:812] (2/8) Epoch 21, batch 1600, loss[loss=0.1703, simple_loss=0.2583, pruned_loss=0.0412, over 7321.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2517, pruned_loss=0.03591, over 1421054.31 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:24:25,764 INFO [train.py:812] (2/8) Epoch 21, batch 1650, loss[loss=0.1649, simple_loss=0.2601, pruned_loss=0.03486, over 7342.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2519, pruned_loss=0.03601, over 1421949.14 frames.], batch size: 20, lr: 3.72e-04
+2022-05-15 02:25:24,254 INFO [train.py:812] (2/8) Epoch 21, batch 1700, loss[loss=0.1667, simple_loss=0.2683, pruned_loss=0.03257, over 7345.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2505, pruned_loss=0.03539, over 1421915.06 frames.], batch size: 22, lr: 3.72e-04
+2022-05-15 02:26:22,311 INFO [train.py:812] (2/8) Epoch 21, batch 1750, loss[loss=0.1381, simple_loss=0.2204, pruned_loss=0.0279, over 7416.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2509, pruned_loss=0.03542, over 1422631.30 frames.], batch size: 18, lr: 3.72e-04
+2022-05-15 02:27:21,196 INFO [train.py:812] (2/8) Epoch 21, batch 1800, loss[loss=0.1864, simple_loss=0.276, pruned_loss=0.04844, over 7210.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2512, pruned_loss=0.0356, over 1424154.79 frames.], batch size: 23, lr: 3.71e-04
+2022-05-15 02:28:20,361 INFO [train.py:812] (2/8) Epoch 21, batch 1850, loss[loss=0.1241, simple_loss=0.1974, pruned_loss=0.0254, over 7416.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2512, pruned_loss=0.03562, over 1423024.48 frames.], batch size: 18, lr: 3.71e-04
+2022-05-15 02:29:19,103 INFO [train.py:812] (2/8) Epoch 21, batch 1900, loss[loss=0.1528, simple_loss=0.235, pruned_loss=0.0353, over 7162.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2509, pruned_loss=0.03568, over 1424559.58 frames.], batch size: 19, lr: 3.71e-04
+2022-05-15 02:30:18,946 INFO [train.py:812] (2/8) Epoch 21, batch 1950, loss[loss=0.1716, simple_loss=0.2596, pruned_loss=0.04185, over 7261.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2507, pruned_loss=0.03533, over 1428130.20 frames.], batch size: 19, lr: 3.71e-04
+2022-05-15 02:31:18,445 INFO [train.py:812] (2/8) Epoch 21, batch 2000, loss[loss=0.1628, simple_loss=0.2526, pruned_loss=0.03656, over 6821.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2502, pruned_loss=0.03521, over 1424705.33 frames.], batch size: 31, lr: 3.71e-04
+2022-05-15 02:32:18,158 INFO [train.py:812] (2/8) Epoch 21, batch 2050, loss[loss=0.1427, simple_loss=0.2342, pruned_loss=0.02561, over 7219.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2504, pruned_loss=0.03543, over 1424297.22 frames.], batch size: 21, lr: 3.71e-04
+2022-05-15 02:33:17,372 INFO [train.py:812] (2/8) Epoch 21, batch 2100, loss[loss=0.1431, simple_loss=0.233, pruned_loss=0.02657, over 7062.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2506, pruned_loss=0.03544, over 1422885.62 frames.], batch size: 18, lr: 3.71e-04
+2022-05-15 02:34:16,893 INFO [train.py:812] (2/8) Epoch 21, batch 2150, loss[loss=0.1422, simple_loss=0.227, pruned_loss=0.02875, over 7180.00 frames.], tot_loss[loss=0.1608, simple_loss=0.251, pruned_loss=0.03532, over 1422243.23 frames.], batch size: 16, lr: 3.71e-04
+2022-05-15 02:35:14,482 INFO [train.py:812] (2/8) Epoch 21, batch 2200, loss[loss=0.1838, simple_loss=0.2781, pruned_loss=0.04474, over 7202.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2505, pruned_loss=0.03506, over 1424606.98 frames.], batch size: 22, lr: 3.71e-04
+2022-05-15 02:36:12,371 INFO [train.py:812] (2/8) Epoch 21, batch 2250, loss[loss=0.1678, simple_loss=0.2761, pruned_loss=0.02976, over 7207.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2503, pruned_loss=0.03473, over 1425298.59 frames.], batch size: 22, lr: 3.71e-04
+2022-05-15 02:37:12,530 INFO [train.py:812] (2/8) Epoch 21, batch 2300, loss[loss=0.1736, simple_loss=0.2635, pruned_loss=0.04183, over 5290.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2496, pruned_loss=0.03473, over 1423005.05 frames.], batch size: 53, lr: 3.71e-04
+2022-05-15 02:38:11,392 INFO [train.py:812] (2/8) Epoch 21, batch 2350, loss[loss=0.1856, simple_loss=0.2629, pruned_loss=0.05414, over 7291.00 frames.], tot_loss[loss=0.161, simple_loss=0.2513, pruned_loss=0.03531, over 1418258.31 frames.], batch size: 24, lr: 3.70e-04
+2022-05-15 02:39:10,739 INFO [train.py:812] (2/8) Epoch 21, batch 2400, loss[loss=0.158, simple_loss=0.2508, pruned_loss=0.03264, over 7209.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2507, pruned_loss=0.03485, over 1420666.53 frames.], batch size: 23, lr: 3.70e-04
+2022-05-15 02:40:10,443 INFO [train.py:812] (2/8) Epoch 21, batch 2450, loss[loss=0.157, simple_loss=0.2414, pruned_loss=0.03628, over 7155.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2506, pruned_loss=0.03491, over 1421229.66 frames.], batch size: 19, lr: 3.70e-04
+2022-05-15 02:41:09,424 INFO [train.py:812] (2/8) Epoch 21, batch 2500, loss[loss=0.1513, simple_loss=0.246, pruned_loss=0.02828, over 7415.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2508, pruned_loss=0.03491, over 1422669.56 frames.], batch size: 21, lr: 3.70e-04
+2022-05-15 02:42:07,849 INFO [train.py:812] (2/8) Epoch 21, batch 2550, loss[loss=0.1831, simple_loss=0.2694, pruned_loss=0.04842, over 5015.00 frames.], tot_loss[loss=0.1614, simple_loss=0.252, pruned_loss=0.03536, over 1420181.81 frames.], batch size: 53, lr: 3.70e-04
+2022-05-15 02:43:06,158 INFO [train.py:812] (2/8) Epoch 21, batch 2600, loss[loss=0.1541, simple_loss=0.2399, pruned_loss=0.03417, over 7060.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2524, pruned_loss=0.0356, over 1421727.16 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:44:05,924 INFO [train.py:812] (2/8) Epoch 21, batch 2650, loss[loss=0.1755, simple_loss=0.2552, pruned_loss=0.04795, over 7334.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2527, pruned_loss=0.03603, over 1417789.63 frames.], batch size: 20, lr: 3.70e-04
+2022-05-15 02:45:04,725 INFO [train.py:812] (2/8) Epoch 21, batch 2700, loss[loss=0.136, simple_loss=0.2204, pruned_loss=0.02584, over 7424.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2524, pruned_loss=0.03599, over 1421093.34 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:46:03,845 INFO [train.py:812] (2/8) Epoch 21, batch 2750, loss[loss=0.1449, simple_loss=0.2358, pruned_loss=0.02703, over 7169.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2527, pruned_loss=0.03601, over 1421689.53 frames.], batch size: 18, lr: 3.70e-04
+2022-05-15 02:47:03,116 INFO [train.py:812] (2/8) Epoch 21, batch 2800, loss[loss=0.1697, simple_loss=0.2694, pruned_loss=0.03504, over 7375.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2518, pruned_loss=0.0354, over 1425342.53 frames.], batch size: 23, lr: 3.70e-04
+2022-05-15 02:48:12,155 INFO [train.py:812] (2/8) Epoch 21, batch 2850, loss[loss=0.1786, simple_loss=0.2666, pruned_loss=0.04528, over 7198.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2516, pruned_loss=0.03546, over 1420609.43 frames.], batch size: 23, lr: 3.69e-04
+2022-05-15 02:49:11,140 INFO [train.py:812] (2/8) Epoch 21, batch 2900, loss[loss=0.1804, simple_loss=0.2735, pruned_loss=0.04368, over 7096.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2517, pruned_loss=0.03558, over 1416867.94 frames.], batch size: 28, lr: 3.69e-04
+2022-05-15 02:50:09,822 INFO [train.py:812] (2/8) Epoch 21, batch 2950, loss[loss=0.1538, simple_loss=0.2387, pruned_loss=0.03445, over 7351.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2513, pruned_loss=0.03511, over 1415784.54 frames.], batch size: 19, lr: 3.69e-04
+2022-05-15 02:51:09,039 INFO [train.py:812] (2/8) Epoch 21, batch 3000, loss[loss=0.171, simple_loss=0.2588, pruned_loss=0.04165, over 6631.00 frames.], tot_loss[loss=0.161, simple_loss=0.2515, pruned_loss=0.03525, over 1415022.14 frames.], batch size: 31, lr: 3.69e-04
+2022-05-15 02:51:09,040 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 02:51:16,350 INFO [train.py:841] (2/8) Epoch 21, validation: loss=0.153, simple_loss=0.2519, pruned_loss=0.02704, over 698248.00 frames.
+2022-05-15 02:52:35,379 INFO [train.py:812] (2/8) Epoch 21, batch 3050, loss[loss=0.1303, simple_loss=0.2171, pruned_loss=0.0218, over 7271.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2514, pruned_loss=0.03524, over 1415372.11 frames.], batch size: 18, lr: 3.69e-04
+2022-05-15 02:53:33,027 INFO [train.py:812] (2/8) Epoch 21, batch 3100, loss[loss=0.1693, simple_loss=0.2574, pruned_loss=0.04061, over 7380.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2521, pruned_loss=0.03601, over 1414163.55 frames.], batch size: 23, lr: 3.69e-04
+2022-05-15 02:55:01,603 INFO [train.py:812] (2/8) Epoch 21, batch 3150, loss[loss=0.2053, simple_loss=0.3023, pruned_loss=0.05412, over 7303.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2521, pruned_loss=0.036, over 1418589.30 frames.], batch size: 24, lr: 3.69e-04
+2022-05-15 02:56:00,663 INFO [train.py:812] (2/8) Epoch 21, batch 3200, loss[loss=0.1776, simple_loss=0.2708, pruned_loss=0.0422, over 7319.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2529, pruned_loss=0.03643, over 1422818.27 frames.], batch size: 21, lr: 3.69e-04
+2022-05-15 02:57:00,394 INFO [train.py:812] (2/8) Epoch 21, batch 3250, loss[loss=0.1427, simple_loss=0.2335, pruned_loss=0.02597, over 7068.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2524, pruned_loss=0.03596, over 1421804.25 frames.], batch size: 18, lr: 3.69e-04
+2022-05-15 02:58:08,768 INFO [train.py:812] (2/8) Epoch 21, batch 3300, loss[loss=0.1453, simple_loss=0.2362, pruned_loss=0.02718, over 7144.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2521, pruned_loss=0.03552, over 1423586.48 frames.], batch size: 17, lr: 3.69e-04
+2022-05-15 02:59:08,380 INFO [train.py:812] (2/8) Epoch 21, batch 3350, loss[loss=0.1604, simple_loss=0.2522, pruned_loss=0.03432, over 7233.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2517, pruned_loss=0.03542, over 1419981.16 frames.], batch size: 20, lr: 3.68e-04
+2022-05-15 03:00:06,868 INFO [train.py:812] (2/8) Epoch 21, batch 3400, loss[loss=0.1725, simple_loss=0.2648, pruned_loss=0.04008, over 6497.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2518, pruned_loss=0.03564, over 1416427.21 frames.], batch size: 38, lr: 3.68e-04
+2022-05-15 03:01:06,245 INFO [train.py:812] (2/8) Epoch 21, batch 3450, loss[loss=0.1693, simple_loss=0.2691, pruned_loss=0.03473, over 7320.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2522, pruned_loss=0.03566, over 1415058.41 frames.], batch size: 21, lr: 3.68e-04
+2022-05-15 03:02:05,066 INFO [train.py:812] (2/8) Epoch 21, batch 3500, loss[loss=0.1559, simple_loss=0.2515, pruned_loss=0.03016, over 7033.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2525, pruned_loss=0.03555, over 1410666.89 frames.], batch size: 28, lr: 3.68e-04
+2022-05-15 03:03:04,136 INFO [train.py:812] (2/8) Epoch 21, batch 3550, loss[loss=0.141, simple_loss=0.2159, pruned_loss=0.03304, over 7278.00 frames.], tot_loss[loss=0.161, simple_loss=0.2514, pruned_loss=0.03527, over 1414487.56 frames.], batch size: 17, lr: 3.68e-04
+2022-05-15 03:04:02,910 INFO [train.py:812] (2/8) Epoch 21, batch 3600, loss[loss=0.1642, simple_loss=0.2626, pruned_loss=0.03288, over 7379.00 frames.], tot_loss[loss=0.162, simple_loss=0.2524, pruned_loss=0.03574, over 1411661.26 frames.], batch size: 23, lr: 3.68e-04
+2022-05-15 03:05:02,882 INFO [train.py:812] (2/8) Epoch 21, batch 3650, loss[loss=0.1781, simple_loss=0.268, pruned_loss=0.04403, over 7138.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2528, pruned_loss=0.03572, over 1412788.34 frames.], batch size: 26, lr: 3.68e-04
+2022-05-15 03:06:01,341 INFO [train.py:812] (2/8) Epoch 21, batch 3700, loss[loss=0.146, simple_loss=0.2456, pruned_loss=0.02318, over 7315.00 frames.], tot_loss[loss=0.162, simple_loss=0.253, pruned_loss=0.03552, over 1413387.85 frames.], batch size: 21, lr: 3.68e-04
+2022-05-15 03:07:01,182 INFO [train.py:812] (2/8) Epoch 21, batch 3750, loss[loss=0.1803, simple_loss=0.2667, pruned_loss=0.04694, over 7287.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2518, pruned_loss=0.03532, over 1417109.76 frames.], batch size: 25, lr: 3.68e-04
+2022-05-15 03:07:59,608 INFO [train.py:812] (2/8) Epoch 21, batch 3800, loss[loss=0.1633, simple_loss=0.2598, pruned_loss=0.03339, over 7196.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2513, pruned_loss=0.03501, over 1417512.32 frames.], batch size: 26, lr: 3.68e-04
+2022-05-15 03:08:58,692 INFO [train.py:812] (2/8) Epoch 21, batch 3850, loss[loss=0.1855, simple_loss=0.2811, pruned_loss=0.04497, over 7329.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2521, pruned_loss=0.0352, over 1418210.64 frames.], batch size: 20, lr: 3.68e-04
+2022-05-15 03:09:55,534 INFO [train.py:812] (2/8) Epoch 21, batch 3900, loss[loss=0.146, simple_loss=0.2322, pruned_loss=0.02985, over 7244.00 frames.], tot_loss[loss=0.161, simple_loss=0.2519, pruned_loss=0.03502, over 1421605.57 frames.], batch size: 19, lr: 3.67e-04
+2022-05-15 03:10:53,541 INFO [train.py:812] (2/8) Epoch 21, batch 3950, loss[loss=0.1398, simple_loss=0.2232, pruned_loss=0.02821, over 7399.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2527, pruned_loss=0.03542, over 1416566.79 frames.], batch size: 18, lr: 3.67e-04
+2022-05-15 03:11:51,913 INFO [train.py:812] (2/8) Epoch 21, batch 4000, loss[loss=0.1478, simple_loss=0.2298, pruned_loss=0.0329, over 7359.00 frames.], tot_loss[loss=0.1618, simple_loss=0.253, pruned_loss=0.03534, over 1421209.93 frames.], batch size: 19, lr: 3.67e-04
+2022-05-15 03:12:50,963 INFO [train.py:812] (2/8) Epoch 21, batch 4050, loss[loss=0.2114, simple_loss=0.2947, pruned_loss=0.06401, over 5472.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2522, pruned_loss=0.03521, over 1419143.91 frames.], batch size: 54, lr: 3.67e-04
+2022-05-15 03:13:49,285 INFO [train.py:812] (2/8) Epoch 21, batch 4100, loss[loss=0.1634, simple_loss=0.2601, pruned_loss=0.03333, over 7216.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2528, pruned_loss=0.03565, over 1411650.88 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:14:46,149 INFO [train.py:812] (2/8) Epoch 21, batch 4150, loss[loss=0.1727, simple_loss=0.2689, pruned_loss=0.03825, over 7071.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2536, pruned_loss=0.036, over 1412555.47 frames.], batch size: 18, lr: 3.67e-04
+2022-05-15 03:15:43,930 INFO [train.py:812] (2/8) Epoch 21, batch 4200, loss[loss=0.1398, simple_loss=0.2411, pruned_loss=0.01921, over 6674.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2534, pruned_loss=0.03564, over 1411638.43 frames.], batch size: 31, lr: 3.67e-04
+2022-05-15 03:16:47,809 INFO [train.py:812] (2/8) Epoch 21, batch 4250, loss[loss=0.1641, simple_loss=0.2596, pruned_loss=0.03432, over 7227.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2517, pruned_loss=0.03508, over 1416211.12 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:17:46,957 INFO [train.py:812] (2/8) Epoch 21, batch 4300, loss[loss=0.1532, simple_loss=0.2536, pruned_loss=0.02644, over 7289.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2509, pruned_loss=0.03451, over 1416603.75 frames.], batch size: 24, lr: 3.67e-04
+2022-05-15 03:18:45,851 INFO [train.py:812] (2/8) Epoch 21, batch 4350, loss[loss=0.1471, simple_loss=0.2447, pruned_loss=0.02471, over 7224.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2506, pruned_loss=0.03483, over 1417038.39 frames.], batch size: 21, lr: 3.67e-04
+2022-05-15 03:19:43,038 INFO [train.py:812] (2/8) Epoch 21, batch 4400, loss[loss=0.1759, simple_loss=0.2584, pruned_loss=0.04669, over 7163.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2508, pruned_loss=0.03488, over 1415743.24 frames.], batch size: 18, lr: 3.66e-04
+2022-05-15 03:20:42,017 INFO [train.py:812] (2/8) Epoch 21, batch 4450, loss[loss=0.1514, simple_loss=0.2309, pruned_loss=0.0359, over 7421.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2508, pruned_loss=0.03511, over 1408495.72 frames.], batch size: 17, lr: 3.66e-04
+2022-05-15 03:21:40,282 INFO [train.py:812] (2/8) Epoch 21, batch 4500, loss[loss=0.1439, simple_loss=0.2269, pruned_loss=0.03046, over 7014.00 frames.], tot_loss[loss=0.1605, simple_loss=0.251, pruned_loss=0.035, over 1410335.99 frames.], batch size: 16, lr: 3.66e-04
+2022-05-15 03:22:39,945 INFO [train.py:812] (2/8) Epoch 21, batch 4550, loss[loss=0.1713, simple_loss=0.2531, pruned_loss=0.04471, over 4868.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2507, pruned_loss=0.03526, over 1394290.35 frames.], batch size: 52, lr: 3.66e-04
+2022-05-15 03:23:52,242 INFO [train.py:812] (2/8) Epoch 22, batch 0, loss[loss=0.1864, simple_loss=0.2813, pruned_loss=0.04582, over 7293.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2813, pruned_loss=0.04582, over 7293.00 frames.], batch size: 25, lr: 3.58e-04
+2022-05-15 03:24:50,146 INFO [train.py:812] (2/8) Epoch 22, batch 50, loss[loss=0.1498, simple_loss=0.2417, pruned_loss=0.02897, over 7144.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2512, pruned_loss=0.03534, over 318718.45 frames.], batch size: 18, lr: 3.58e-04
+2022-05-15 03:25:49,147 INFO [train.py:812] (2/8) Epoch 22, batch 100, loss[loss=0.1589, simple_loss=0.2439, pruned_loss=0.03692, over 7117.00 frames.], tot_loss[loss=0.161, simple_loss=0.2515, pruned_loss=0.03523, over 563949.99 frames.], batch size: 21, lr: 3.58e-04
+2022-05-15 03:26:47,183 INFO [train.py:812] (2/8) Epoch 22, batch 150, loss[loss=0.1526, simple_loss=0.2459, pruned_loss=0.02965, over 7325.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2512, pruned_loss=0.03478, over 754010.75 frames.], batch size: 21, lr: 3.58e-04
+2022-05-15 03:27:46,017 INFO [train.py:812] (2/8) Epoch 22, batch 200, loss[loss=0.16, simple_loss=0.2608, pruned_loss=0.02958, over 7328.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2516, pruned_loss=0.0347, over 901696.41 frames.], batch size: 22, lr: 3.58e-04
+2022-05-15 03:28:43,581 INFO [train.py:812] (2/8) Epoch 22, batch 250, loss[loss=0.1434, simple_loss=0.2312, pruned_loss=0.02782, over 7251.00 frames.], tot_loss[loss=0.161, simple_loss=0.2519, pruned_loss=0.03506, over 1015037.87 frames.], batch size: 19, lr: 3.57e-04
+2022-05-15 03:29:41,572 INFO [train.py:812] (2/8) Epoch 22, batch 300, loss[loss=0.1621, simple_loss=0.247, pruned_loss=0.03862, over 7232.00 frames.], tot_loss[loss=0.1615, simple_loss=0.252, pruned_loss=0.03547, over 1107665.66 frames.], batch size: 20, lr: 3.57e-04
+2022-05-15 03:30:39,468 INFO [train.py:812] (2/8) Epoch 22, batch 350, loss[loss=0.1496, simple_loss=0.2468, pruned_loss=0.02626, over 7147.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2508, pruned_loss=0.03504, over 1179177.12 frames.], batch size: 19, lr: 3.57e-04
+2022-05-15 03:31:38,295 INFO [train.py:812] (2/8) Epoch 22, batch 400, loss[loss=0.1721, simple_loss=0.2785, pruned_loss=0.03288, over 7219.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2511, pruned_loss=0.03499, over 1231931.19 frames.], batch size: 21, lr: 3.57e-04
+2022-05-15 03:32:37,275 INFO [train.py:812] (2/8) Epoch 22, batch 450, loss[loss=0.2177, simple_loss=0.2976, pruned_loss=0.06888, over 4911.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2507, pruned_loss=0.03509, over 1274373.67 frames.], batch size: 52, lr: 3.57e-04
+2022-05-15 03:33:36,495 INFO [train.py:812] (2/8) Epoch 22, batch 500, loss[loss=0.1938, simple_loss=0.2953, pruned_loss=0.04612, over 7310.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2523, pruned_loss=0.03531, over 1309731.07 frames.], batch size: 25, lr: 3.57e-04
+2022-05-15 03:34:33,233 INFO [train.py:812] (2/8) Epoch 22, batch 550, loss[loss=0.1565, simple_loss=0.2433, pruned_loss=0.03483, over 7439.00 frames.], tot_loss[loss=0.162, simple_loss=0.2529, pruned_loss=0.03551, over 1332852.60 frames.], batch size: 20, lr: 3.57e-04
+2022-05-15 03:35:32,154 INFO [train.py:812] (2/8) Epoch 22, batch 600, loss[loss=0.1556, simple_loss=0.2538, pruned_loss=0.0287, over 7320.00 frames.], tot_loss[loss=0.1606, simple_loss=0.251, pruned_loss=0.03506, over 1354020.71 frames.], batch size: 22, lr: 3.57e-04
+2022-05-15 03:36:31,006 INFO [train.py:812] (2/8) Epoch 22, batch 650, loss[loss=0.1479, simple_loss=0.2478, pruned_loss=0.02406, over 7328.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2519, pruned_loss=0.03524, over 1369357.43 frames.], batch size: 22, lr: 3.57e-04
+2022-05-15 03:37:30,480 INFO [train.py:812] (2/8) Epoch 22, batch 700, loss[loss=0.1834, simple_loss=0.2737, pruned_loss=0.04652, over 7286.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2512, pruned_loss=0.03509, over 1377795.80 frames.], batch size: 25, lr: 3.57e-04
+2022-05-15 03:38:28,388 INFO [train.py:812] (2/8) Epoch 22, batch 750, loss[loss=0.1944, simple_loss=0.2751, pruned_loss=0.05689, over 7158.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2506, pruned_loss=0.03535, over 1386069.31 frames.], batch size: 18, lr: 3.57e-04
+2022-05-15 03:39:28,259 INFO [train.py:812] (2/8) Epoch 22, batch 800, loss[loss=0.1521, simple_loss=0.2536, pruned_loss=0.02534, over 7274.00 frames.], tot_loss[loss=0.161, simple_loss=0.2512, pruned_loss=0.03538, over 1398392.31 frames.], batch size: 25, lr: 3.56e-04
+2022-05-15 03:40:27,685 INFO [train.py:812] (2/8) Epoch 22, batch 850, loss[loss=0.1696, simple_loss=0.2606, pruned_loss=0.03933, over 7404.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2509, pruned_loss=0.03522, over 1404072.90 frames.], batch size: 18, lr: 3.56e-04
+2022-05-15 03:41:26,133 INFO [train.py:812] (2/8) Epoch 22, batch 900, loss[loss=0.1409, simple_loss=0.2294, pruned_loss=0.02618, over 6370.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2503, pruned_loss=0.03474, over 1407566.78 frames.], batch size: 37, lr: 3.56e-04
+2022-05-15 03:42:25,445 INFO [train.py:812] (2/8) Epoch 22, batch 950, loss[loss=0.12, simple_loss=0.2057, pruned_loss=0.01717, over 7281.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2497, pruned_loss=0.03456, over 1410039.67 frames.], batch size: 18, lr: 3.56e-04
+2022-05-15 03:43:24,202 INFO [train.py:812] (2/8) Epoch 22, batch 1000, loss[loss=0.1682, simple_loss=0.2565, pruned_loss=0.03992, over 7172.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2515, pruned_loss=0.03516, over 1410518.03 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:44:23,454 INFO [train.py:812] (2/8) Epoch 22, batch 1050, loss[loss=0.1661, simple_loss=0.2581, pruned_loss=0.03704, over 7325.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2506, pruned_loss=0.03477, over 1414489.65 frames.], batch size: 22, lr: 3.56e-04
+2022-05-15 03:45:23,002 INFO [train.py:812] (2/8) Epoch 22, batch 1100, loss[loss=0.1881, simple_loss=0.2737, pruned_loss=0.05128, over 6380.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2506, pruned_loss=0.03511, over 1418205.44 frames.], batch size: 38, lr: 3.56e-04
+2022-05-15 03:46:20,334 INFO [train.py:812] (2/8) Epoch 22, batch 1150, loss[loss=0.1381, simple_loss=0.225, pruned_loss=0.02561, over 7262.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2502, pruned_loss=0.03502, over 1419852.36 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:47:19,433 INFO [train.py:812] (2/8) Epoch 22, batch 1200, loss[loss=0.1712, simple_loss=0.2607, pruned_loss=0.04081, over 7306.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2497, pruned_loss=0.03481, over 1420664.98 frames.], batch size: 25, lr: 3.56e-04
+2022-05-15 03:48:18,944 INFO [train.py:812] (2/8) Epoch 22, batch 1250, loss[loss=0.1357, simple_loss=0.2137, pruned_loss=0.02891, over 7018.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2488, pruned_loss=0.03437, over 1420523.47 frames.], batch size: 16, lr: 3.56e-04
+2022-05-15 03:49:19,108 INFO [train.py:812] (2/8) Epoch 22, batch 1300, loss[loss=0.1561, simple_loss=0.2507, pruned_loss=0.03074, over 7156.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2488, pruned_loss=0.03444, over 1418862.39 frames.], batch size: 19, lr: 3.56e-04
+2022-05-15 03:50:16,171 INFO [train.py:812] (2/8) Epoch 22, batch 1350, loss[loss=0.1465, simple_loss=0.2423, pruned_loss=0.02535, over 7413.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2485, pruned_loss=0.03426, over 1423257.66 frames.], batch size: 21, lr: 3.55e-04
+2022-05-15 03:51:15,329 INFO [train.py:812] (2/8) Epoch 22, batch 1400, loss[loss=0.1912, simple_loss=0.277, pruned_loss=0.05265, over 7211.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2481, pruned_loss=0.03442, over 1420040.88 frames.], batch size: 22, lr: 3.55e-04
+2022-05-15 03:52:14,206 INFO [train.py:812] (2/8) Epoch 22, batch 1450, loss[loss=0.1786, simple_loss=0.2591, pruned_loss=0.04904, over 7424.00 frames.], tot_loss[loss=0.1593, simple_loss=0.249, pruned_loss=0.03475, over 1424361.07 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:53:13,824 INFO [train.py:812] (2/8) Epoch 22, batch 1500, loss[loss=0.1438, simple_loss=0.2361, pruned_loss=0.02568, over 7231.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2496, pruned_loss=0.03504, over 1426303.82 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:54:13,399 INFO [train.py:812] (2/8) Epoch 22, batch 1550, loss[loss=0.1794, simple_loss=0.2679, pruned_loss=0.0454, over 7235.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2496, pruned_loss=0.03497, over 1428926.03 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:55:12,246 INFO [train.py:812] (2/8) Epoch 22, batch 1600, loss[loss=0.1364, simple_loss=0.2214, pruned_loss=0.02569, over 7243.00 frames.], tot_loss[loss=0.159, simple_loss=0.249, pruned_loss=0.03454, over 1430368.49 frames.], batch size: 16, lr: 3.55e-04
+2022-05-15 03:56:08,983 INFO [train.py:812] (2/8) Epoch 22, batch 1650, loss[loss=0.1629, simple_loss=0.2658, pruned_loss=0.03, over 6692.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03436, over 1432060.42 frames.], batch size: 31, lr: 3.55e-04
+2022-05-15 03:57:06,970 INFO [train.py:812] (2/8) Epoch 22, batch 1700, loss[loss=0.1646, simple_loss=0.2633, pruned_loss=0.033, over 7338.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2487, pruned_loss=0.0339, over 1434602.52 frames.], batch size: 22, lr: 3.55e-04
+2022-05-15 03:58:03,875 INFO [train.py:812] (2/8) Epoch 22, batch 1750, loss[loss=0.1739, simple_loss=0.2626, pruned_loss=0.0426, over 7231.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2495, pruned_loss=0.03431, over 1433352.59 frames.], batch size: 20, lr: 3.55e-04
+2022-05-15 03:59:03,696 INFO [train.py:812] (2/8) Epoch 22, batch 1800, loss[loss=0.1331, simple_loss=0.2152, pruned_loss=0.02547, over 7292.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2489, pruned_loss=0.03434, over 1429813.03 frames.], batch size: 17, lr: 3.55e-04
+2022-05-15 04:00:02,163 INFO [train.py:812] (2/8) Epoch 22, batch 1850, loss[loss=0.1429, simple_loss=0.2477, pruned_loss=0.01906, over 6429.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2487, pruned_loss=0.03417, over 1426163.41 frames.], batch size: 37, lr: 3.55e-04
+2022-05-15 04:01:00,866 INFO [train.py:812] (2/8) Epoch 22, batch 1900, loss[loss=0.216, simple_loss=0.285, pruned_loss=0.07346, over 4908.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2494, pruned_loss=0.03465, over 1424437.60 frames.], batch size: 54, lr: 3.54e-04
+2022-05-15 04:02:00,142 INFO [train.py:812] (2/8) Epoch 22, batch 1950, loss[loss=0.168, simple_loss=0.2462, pruned_loss=0.04491, over 7268.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2497, pruned_loss=0.03486, over 1425141.68 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:02:59,576 INFO [train.py:812] (2/8) Epoch 22, batch 2000, loss[loss=0.1649, simple_loss=0.2677, pruned_loss=0.03103, over 7329.00 frames.], tot_loss[loss=0.1598, simple_loss=0.25, pruned_loss=0.03477, over 1427775.82 frames.], batch size: 20, lr: 3.54e-04
+2022-05-15 04:03:58,504 INFO [train.py:812] (2/8) Epoch 22, batch 2050, loss[loss=0.182, simple_loss=0.2598, pruned_loss=0.05213, over 7271.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2511, pruned_loss=0.03508, over 1428756.73 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:04:58,111 INFO [train.py:812] (2/8) Epoch 22, batch 2100, loss[loss=0.1569, simple_loss=0.2358, pruned_loss=0.03899, over 7425.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2509, pruned_loss=0.03482, over 1427609.02 frames.], batch size: 18, lr: 3.54e-04
+2022-05-15 04:05:56,577 INFO [train.py:812] (2/8) Epoch 22, batch 2150, loss[loss=0.1687, simple_loss=0.249, pruned_loss=0.04426, over 7161.00 frames.], tot_loss[loss=0.16, simple_loss=0.2505, pruned_loss=0.03474, over 1423559.87 frames.], batch size: 18, lr: 3.54e-04
+2022-05-15 04:06:54,944 INFO [train.py:812] (2/8) Epoch 22, batch 2200, loss[loss=0.163, simple_loss=0.2645, pruned_loss=0.03077, over 7124.00 frames.], tot_loss[loss=0.1592, simple_loss=0.25, pruned_loss=0.03425, over 1426782.48 frames.], batch size: 21, lr: 3.54e-04
+2022-05-15 04:07:52,614 INFO [train.py:812] (2/8) Epoch 22, batch 2250, loss[loss=0.1371, simple_loss=0.2196, pruned_loss=0.02728, over 7259.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2506, pruned_loss=0.03464, over 1424279.73 frames.], batch size: 16, lr: 3.54e-04
+2022-05-15 04:08:49,580 INFO [train.py:812] (2/8) Epoch 22, batch 2300, loss[loss=0.2105, simple_loss=0.2854, pruned_loss=0.06776, over 5149.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2512, pruned_loss=0.03489, over 1425288.58 frames.], batch size: 52, lr: 3.54e-04
+2022-05-15 04:09:48,030 INFO [train.py:812] (2/8) Epoch 22, batch 2350, loss[loss=0.1754, simple_loss=0.2664, pruned_loss=0.04219, over 6503.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2508, pruned_loss=0.0348, over 1427846.38 frames.], batch size: 38, lr: 3.54e-04
+2022-05-15 04:10:57,275 INFO [train.py:812] (2/8) Epoch 22, batch 2400, loss[loss=0.1378, simple_loss=0.222, pruned_loss=0.02679, over 7146.00 frames.], tot_loss[loss=0.16, simple_loss=0.2504, pruned_loss=0.03483, over 1426924.79 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:11:56,481 INFO [train.py:812] (2/8) Epoch 22, batch 2450, loss[loss=0.157, simple_loss=0.2386, pruned_loss=0.03772, over 7270.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2498, pruned_loss=0.03446, over 1425011.38 frames.], batch size: 17, lr: 3.54e-04
+2022-05-15 04:12:56,107 INFO [train.py:812] (2/8) Epoch 22, batch 2500, loss[loss=0.1475, simple_loss=0.2378, pruned_loss=0.0286, over 7417.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2492, pruned_loss=0.03419, over 1422401.23 frames.], batch size: 21, lr: 3.53e-04
+2022-05-15 04:13:55,346 INFO [train.py:812] (2/8) Epoch 22, batch 2550, loss[loss=0.1919, simple_loss=0.2634, pruned_loss=0.0602, over 7451.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2498, pruned_loss=0.03468, over 1421200.60 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:14:54,427 INFO [train.py:812] (2/8) Epoch 22, batch 2600, loss[loss=0.149, simple_loss=0.2484, pruned_loss=0.02485, over 7154.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2512, pruned_loss=0.03495, over 1418060.97 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:15:53,320 INFO [train.py:812] (2/8) Epoch 22, batch 2650, loss[loss=0.1374, simple_loss=0.229, pruned_loss=0.02292, over 7255.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2498, pruned_loss=0.03445, over 1422244.49 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:16:52,246 INFO [train.py:812] (2/8) Epoch 22, batch 2700, loss[loss=0.1268, simple_loss=0.2132, pruned_loss=0.0202, over 7159.00 frames.], tot_loss[loss=0.159, simple_loss=0.2494, pruned_loss=0.03429, over 1420592.66 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:17:51,013 INFO [train.py:812] (2/8) Epoch 22, batch 2750, loss[loss=0.1571, simple_loss=0.2414, pruned_loss=0.03637, over 7062.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2496, pruned_loss=0.03441, over 1420027.71 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:18:49,820 INFO [train.py:812] (2/8) Epoch 22, batch 2800, loss[loss=0.1381, simple_loss=0.2324, pruned_loss=0.02193, over 7273.00 frames.], tot_loss[loss=0.159, simple_loss=0.2493, pruned_loss=0.0344, over 1420764.36 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:19:48,487 INFO [train.py:812] (2/8) Epoch 22, batch 2850, loss[loss=0.1569, simple_loss=0.2445, pruned_loss=0.03462, over 7156.00 frames.], tot_loss[loss=0.1591, simple_loss=0.249, pruned_loss=0.0346, over 1418727.74 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:20:47,853 INFO [train.py:812] (2/8) Epoch 22, batch 2900, loss[loss=0.1528, simple_loss=0.2446, pruned_loss=0.03049, over 7154.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2497, pruned_loss=0.03455, over 1421594.08 frames.], batch size: 19, lr: 3.53e-04
+2022-05-15 04:21:47,234 INFO [train.py:812] (2/8) Epoch 22, batch 2950, loss[loss=0.1556, simple_loss=0.2472, pruned_loss=0.03195, over 7402.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2494, pruned_loss=0.03461, over 1421525.00 frames.], batch size: 21, lr: 3.53e-04
+2022-05-15 04:22:47,054 INFO [train.py:812] (2/8) Epoch 22, batch 3000, loss[loss=0.1365, simple_loss=0.2301, pruned_loss=0.02144, over 7169.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2499, pruned_loss=0.03443, over 1425663.16 frames.], batch size: 18, lr: 3.53e-04
+2022-05-15 04:22:47,055 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 04:22:54,482 INFO [train.py:841] (2/8) Epoch 22, validation: loss=0.1529, simple_loss=0.2512, pruned_loss=0.02731, over 698248.00 frames.
+2022-05-15 04:23:53,803 INFO [train.py:812] (2/8) Epoch 22, batch 3050, loss[loss=0.183, simple_loss=0.2695, pruned_loss=0.04823, over 7148.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2502, pruned_loss=0.03467, over 1427380.28 frames.], batch size: 28, lr: 3.52e-04
+2022-05-15 04:24:53,851 INFO [train.py:812] (2/8) Epoch 22, batch 3100, loss[loss=0.1803, simple_loss=0.261, pruned_loss=0.04982, over 5072.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2499, pruned_loss=0.03464, over 1427359.63 frames.], batch size: 52, lr: 3.52e-04
+2022-05-15 04:25:52,324 INFO [train.py:812] (2/8) Epoch 22, batch 3150, loss[loss=0.1637, simple_loss=0.2583, pruned_loss=0.03459, over 7419.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2494, pruned_loss=0.03465, over 1424607.92 frames.], batch size: 21, lr: 3.52e-04
+2022-05-15 04:26:51,017 INFO [train.py:812] (2/8) Epoch 22, batch 3200, loss[loss=0.1676, simple_loss=0.259, pruned_loss=0.03809, over 7066.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2495, pruned_loss=0.0347, over 1426367.67 frames.], batch size: 18, lr: 3.52e-04
+2022-05-15 04:27:50,213 INFO [train.py:812] (2/8) Epoch 22, batch 3250, loss[loss=0.1471, simple_loss=0.2213, pruned_loss=0.03644, over 6997.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2496, pruned_loss=0.03476, over 1427690.04 frames.], batch size: 16, lr: 3.52e-04
+2022-05-15 04:28:47,780 INFO [train.py:812] (2/8) Epoch 22, batch 3300, loss[loss=0.155, simple_loss=0.2426, pruned_loss=0.03372, over 7426.00 frames.], tot_loss[loss=0.161, simple_loss=0.2514, pruned_loss=0.03528, over 1429765.59 frames.], batch size: 20, lr: 3.52e-04
+2022-05-15 04:29:46,921 INFO [train.py:812] (2/8) Epoch 22, batch 3350, loss[loss=0.1452, simple_loss=0.2259, pruned_loss=0.03228, over 7360.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2515, pruned_loss=0.03508, over 1428920.28 frames.], batch size: 19, lr: 3.52e-04
+2022-05-15 04:30:46,404 INFO [train.py:812] (2/8) Epoch 22, batch 3400, loss[loss=0.1694, simple_loss=0.2551, pruned_loss=0.04184, over 7149.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2519, pruned_loss=0.03539, over 1426254.52 frames.], batch size: 17, lr: 3.52e-04
+2022-05-15 04:31:45,547 INFO [train.py:812] (2/8) Epoch 22, batch 3450, loss[loss=0.1545, simple_loss=0.2517, pruned_loss=0.02863, over 7343.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2519, pruned_loss=0.03523, over 1427781.63 frames.], batch size: 22, lr: 3.52e-04
+2022-05-15 04:32:45,185 INFO [train.py:812] (2/8) Epoch 22, batch 3500, loss[loss=0.1642, simple_loss=0.2593, pruned_loss=0.03455, over 7330.00 frames.], tot_loss[loss=0.161, simple_loss=0.252, pruned_loss=0.03503, over 1429729.19 frames.], batch size: 22, lr: 3.52e-04
+2022-05-15 04:33:44,230 INFO [train.py:812] (2/8) Epoch 22, batch 3550, loss[loss=0.1649, simple_loss=0.2641, pruned_loss=0.03283, over 6887.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2528, pruned_loss=0.03508, over 1428020.13 frames.], batch size: 31, lr: 3.52e-04
+2022-05-15 04:34:43,630 INFO [train.py:812] (2/8) Epoch 22, batch 3600, loss[loss=0.1254, simple_loss=0.2139, pruned_loss=0.0185, over 7282.00 frames.], tot_loss[loss=0.161, simple_loss=0.2519, pruned_loss=0.03498, over 1422186.25 frames.], batch size: 17, lr: 3.51e-04
+2022-05-15 04:35:42,263 INFO [train.py:812] (2/8) Epoch 22, batch 3650, loss[loss=0.1753, simple_loss=0.2683, pruned_loss=0.04113, over 7369.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2515, pruned_loss=0.03498, over 1424622.07 frames.], batch size: 23, lr: 3.51e-04
+2022-05-15 04:36:47,192 INFO [train.py:812] (2/8) Epoch 22, batch 3700, loss[loss=0.1647, simple_loss=0.2463, pruned_loss=0.04153, over 7233.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2512, pruned_loss=0.03474, over 1426327.51 frames.], batch size: 21, lr: 3.51e-04
+2022-05-15 04:37:46,509 INFO [train.py:812] (2/8) Epoch 22, batch 3750, loss[loss=0.1502, simple_loss=0.2292, pruned_loss=0.03559, over 6992.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2512, pruned_loss=0.03466, over 1429908.59 frames.], batch size: 16, lr: 3.51e-04
+2022-05-15 04:38:46,125 INFO [train.py:812] (2/8) Epoch 22, batch 3800, loss[loss=0.176, simple_loss=0.2622, pruned_loss=0.04493, over 5177.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2504, pruned_loss=0.0345, over 1424362.36 frames.], batch size: 52, lr: 3.51e-04
+2022-05-15 04:39:43,948 INFO [train.py:812] (2/8) Epoch 22, batch 3850, loss[loss=0.1745, simple_loss=0.2776, pruned_loss=0.03566, over 7236.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2506, pruned_loss=0.03423, over 1426256.40 frames.], batch size: 20, lr: 3.51e-04
+2022-05-15 04:40:43,465 INFO [train.py:812] (2/8) Epoch 22, batch 3900, loss[loss=0.1684, simple_loss=0.2553, pruned_loss=0.04072, over 6247.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2498, pruned_loss=0.03393, over 1426993.34 frames.], batch size: 37, lr: 3.51e-04
+2022-05-15 04:41:41,332 INFO [train.py:812] (2/8) Epoch 22, batch 3950, loss[loss=0.132, simple_loss=0.2118, pruned_loss=0.0261, over 7291.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2493, pruned_loss=0.03404, over 1425603.47 frames.], batch size: 17, lr: 3.51e-04
+2022-05-15 04:42:39,861 INFO [train.py:812] (2/8) Epoch 22, batch 4000, loss[loss=0.1676, simple_loss=0.2702, pruned_loss=0.03251, over 7320.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2501, pruned_loss=0.03423, over 1425373.95 frames.], batch size: 21, lr: 3.51e-04
+2022-05-15 04:43:37,370 INFO [train.py:812] (2/8) Epoch 22, batch 4050, loss[loss=0.1407, simple_loss=0.2312, pruned_loss=0.02506, over 7352.00 frames.], tot_loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03427, over 1423233.16 frames.], batch size: 19, lr: 3.51e-04
+2022-05-15 04:44:35,623 INFO [train.py:812] (2/8) Epoch 22, batch 4100, loss[loss=0.15, simple_loss=0.2443, pruned_loss=0.02785, over 7328.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2503, pruned_loss=0.03433, over 1424132.47 frames.], batch size: 20, lr: 3.51e-04
+2022-05-15 04:45:34,807 INFO [train.py:812] (2/8) Epoch 22, batch 4150, loss[loss=0.1582, simple_loss=0.2382, pruned_loss=0.03912, over 7057.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2501, pruned_loss=0.03432, over 1420068.59 frames.], batch size: 18, lr: 3.51e-04
+2022-05-15 04:46:33,508 INFO [train.py:812] (2/8) Epoch 22, batch 4200, loss[loss=0.1961, simple_loss=0.2774, pruned_loss=0.05736, over 7144.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2511, pruned_loss=0.03487, over 1415795.74 frames.], batch size: 20, lr: 3.50e-04
+2022-05-15 04:47:30,296 INFO [train.py:812] (2/8) Epoch 22, batch 4250, loss[loss=0.1555, simple_loss=0.2551, pruned_loss=0.02794, over 6751.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2517, pruned_loss=0.03553, over 1408985.67 frames.], batch size: 31, lr: 3.50e-04
+2022-05-15 04:48:27,302 INFO [train.py:812] (2/8) Epoch 22, batch 4300, loss[loss=0.1739, simple_loss=0.2672, pruned_loss=0.04035, over 7290.00 frames.], tot_loss[loss=0.161, simple_loss=0.2518, pruned_loss=0.03505, over 1410871.84 frames.], batch size: 24, lr: 3.50e-04
+2022-05-15 04:49:26,473 INFO [train.py:812] (2/8) Epoch 22, batch 4350, loss[loss=0.1567, simple_loss=0.2561, pruned_loss=0.02867, over 7332.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2518, pruned_loss=0.035, over 1408085.87 frames.], batch size: 22, lr: 3.50e-04
+2022-05-15 04:50:35,270 INFO [train.py:812] (2/8) Epoch 22, batch 4400, loss[loss=0.1504, simple_loss=0.2468, pruned_loss=0.02701, over 7115.00 frames.], tot_loss[loss=0.1612, simple_loss=0.252, pruned_loss=0.03524, over 1402614.84 frames.], batch size: 21, lr: 3.50e-04
+2022-05-15 04:51:33,771 INFO [train.py:812] (2/8) Epoch 22, batch 4450, loss[loss=0.1419, simple_loss=0.2371, pruned_loss=0.02337, over 7330.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2531, pruned_loss=0.03583, over 1399099.71 frames.], batch size: 22, lr: 3.50e-04
+2022-05-15 04:52:33,289 INFO [train.py:812] (2/8) Epoch 22, batch 4500, loss[loss=0.1644, simple_loss=0.2629, pruned_loss=0.03296, over 7070.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2543, pruned_loss=0.03665, over 1388281.83 frames.], batch size: 28, lr: 3.50e-04
+2022-05-15 04:53:50,569 INFO [train.py:812] (2/8) Epoch 22, batch 4550, loss[loss=0.2059, simple_loss=0.2854, pruned_loss=0.06315, over 5144.00 frames.], tot_loss[loss=0.166, simple_loss=0.2563, pruned_loss=0.03789, over 1345959.36 frames.], batch size: 52, lr: 3.50e-04
+2022-05-15 04:55:29,965 INFO [train.py:812] (2/8) Epoch 23, batch 0, loss[loss=0.1289, simple_loss=0.2147, pruned_loss=0.02152, over 6785.00 frames.], tot_loss[loss=0.1289, simple_loss=0.2147, pruned_loss=0.02152, over 6785.00 frames.], batch size: 15, lr: 3.42e-04
+2022-05-15 04:56:28,537 INFO [train.py:812] (2/8) Epoch 23, batch 50, loss[loss=0.1422, simple_loss=0.2349, pruned_loss=0.02477, over 7153.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2458, pruned_loss=0.03304, over 319404.32 frames.], batch size: 19, lr: 3.42e-04
+2022-05-15 04:57:26,783 INFO [train.py:812] (2/8) Epoch 23, batch 100, loss[loss=0.1511, simple_loss=0.2282, pruned_loss=0.03697, over 7275.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2499, pruned_loss=0.03415, over 566472.78 frames.], batch size: 18, lr: 3.42e-04
+2022-05-15 04:58:25,158 INFO [train.py:812] (2/8) Epoch 23, batch 150, loss[loss=0.15, simple_loss=0.2382, pruned_loss=0.03088, over 7301.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2511, pruned_loss=0.03426, over 754125.23 frames.], batch size: 24, lr: 3.42e-04
+2022-05-15 04:59:34,123 INFO [train.py:812] (2/8) Epoch 23, batch 200, loss[loss=0.154, simple_loss=0.2485, pruned_loss=0.02972, over 6234.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2505, pruned_loss=0.03411, over 901963.27 frames.], batch size: 38, lr: 3.42e-04
+2022-05-15 05:00:33,210 INFO [train.py:812] (2/8) Epoch 23, batch 250, loss[loss=0.1667, simple_loss=0.267, pruned_loss=0.0332, over 7197.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2501, pruned_loss=0.03403, over 1017584.02 frames.], batch size: 23, lr: 3.42e-04
+2022-05-15 05:01:30,503 INFO [train.py:812] (2/8) Epoch 23, batch 300, loss[loss=0.1441, simple_loss=0.2347, pruned_loss=0.02675, over 7157.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2491, pruned_loss=0.0339, over 1103154.98 frames.], batch size: 19, lr: 3.42e-04
+2022-05-15 05:02:29,198 INFO [train.py:812] (2/8) Epoch 23, batch 350, loss[loss=0.1533, simple_loss=0.2532, pruned_loss=0.0267, over 7337.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2482, pruned_loss=0.03346, over 1177903.52 frames.], batch size: 22, lr: 3.42e-04
+2022-05-15 05:03:27,248 INFO [train.py:812] (2/8) Epoch 23, batch 400, loss[loss=0.186, simple_loss=0.283, pruned_loss=0.04446, over 7204.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2482, pruned_loss=0.03372, over 1230886.07 frames.], batch size: 23, lr: 3.42e-04
+2022-05-15 05:04:26,532 INFO [train.py:812] (2/8) Epoch 23, batch 450, loss[loss=0.1798, simple_loss=0.2707, pruned_loss=0.04442, over 7277.00 frames.], tot_loss[loss=0.159, simple_loss=0.2496, pruned_loss=0.03418, over 1271896.42 frames.], batch size: 24, lr: 3.42e-04
+2022-05-15 05:05:24,824 INFO [train.py:812] (2/8) Epoch 23, batch 500, loss[loss=0.1379, simple_loss=0.2191, pruned_loss=0.02831, over 6839.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2496, pruned_loss=0.03409, over 1306762.45 frames.], batch size: 15, lr: 3.41e-04
+2022-05-15 05:06:21,985 INFO [train.py:812] (2/8) Epoch 23, batch 550, loss[loss=0.1846, simple_loss=0.2703, pruned_loss=0.0494, over 7290.00 frames.], tot_loss[loss=0.1582, simple_loss=0.249, pruned_loss=0.03372, over 1337227.38 frames.], batch size: 24, lr: 3.41e-04
+2022-05-15 05:07:20,874 INFO [train.py:812] (2/8) Epoch 23, batch 600, loss[loss=0.1658, simple_loss=0.2521, pruned_loss=0.03974, over 7129.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2497, pruned_loss=0.03391, over 1359348.15 frames.], batch size: 21, lr: 3.41e-04
+2022-05-15 05:08:19,923 INFO [train.py:812] (2/8) Epoch 23, batch 650, loss[loss=0.1552, simple_loss=0.2437, pruned_loss=0.03337, over 6809.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2502, pruned_loss=0.03435, over 1374507.12 frames.], batch size: 31, lr: 3.41e-04
+2022-05-15 05:09:19,497 INFO [train.py:812] (2/8) Epoch 23, batch 700, loss[loss=0.1733, simple_loss=0.2622, pruned_loss=0.04219, over 5162.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2506, pruned_loss=0.0345, over 1380531.55 frames.], batch size: 52, lr: 3.41e-04
+2022-05-15 05:10:18,458 INFO [train.py:812] (2/8) Epoch 23, batch 750, loss[loss=0.1594, simple_loss=0.2511, pruned_loss=0.03381, over 7210.00 frames.], tot_loss[loss=0.1592, simple_loss=0.25, pruned_loss=0.0342, over 1391783.88 frames.], batch size: 23, lr: 3.41e-04
+2022-05-15 05:11:17,881 INFO [train.py:812] (2/8) Epoch 23, batch 800, loss[loss=0.1492, simple_loss=0.2415, pruned_loss=0.02841, over 7362.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2499, pruned_loss=0.03394, over 1395401.53 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:12:15,511 INFO [train.py:812] (2/8) Epoch 23, batch 850, loss[loss=0.1632, simple_loss=0.2488, pruned_loss=0.03878, over 7427.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2502, pruned_loss=0.03415, over 1403942.74 frames.], batch size: 20, lr: 3.41e-04
+2022-05-15 05:13:14,598 INFO [train.py:812] (2/8) Epoch 23, batch 900, loss[loss=0.1631, simple_loss=0.2554, pruned_loss=0.03534, over 7163.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2502, pruned_loss=0.03397, over 1408107.86 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:14:13,169 INFO [train.py:812] (2/8) Epoch 23, batch 950, loss[loss=0.1747, simple_loss=0.2716, pruned_loss=0.03887, over 7140.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2503, pruned_loss=0.03371, over 1410449.13 frames.], batch size: 28, lr: 3.41e-04
+2022-05-15 05:15:13,119 INFO [train.py:812] (2/8) Epoch 23, batch 1000, loss[loss=0.1675, simple_loss=0.2594, pruned_loss=0.03776, over 7351.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2511, pruned_loss=0.03398, over 1417638.49 frames.], batch size: 19, lr: 3.41e-04
+2022-05-15 05:16:12,065 INFO [train.py:812] (2/8) Epoch 23, batch 1050, loss[loss=0.1929, simple_loss=0.2824, pruned_loss=0.05166, over 5005.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2512, pruned_loss=0.03458, over 1418269.47 frames.], batch size: 52, lr: 3.41e-04
+2022-05-15 05:17:10,934 INFO [train.py:812] (2/8) Epoch 23, batch 1100, loss[loss=0.142, simple_loss=0.2303, pruned_loss=0.0269, over 7274.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2518, pruned_loss=0.03451, over 1418700.63 frames.], batch size: 17, lr: 3.40e-04
+2022-05-15 05:18:09,882 INFO [train.py:812] (2/8) Epoch 23, batch 1150, loss[loss=0.1537, simple_loss=0.2472, pruned_loss=0.0301, over 7433.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2526, pruned_loss=0.03484, over 1422120.79 frames.], batch size: 20, lr: 3.40e-04
+2022-05-15 05:19:09,609 INFO [train.py:812] (2/8) Epoch 23, batch 1200, loss[loss=0.1712, simple_loss=0.2615, pruned_loss=0.04044, over 7288.00 frames.], tot_loss[loss=0.1607, simple_loss=0.252, pruned_loss=0.03467, over 1421216.27 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:20:07,294 INFO [train.py:812] (2/8) Epoch 23, batch 1250, loss[loss=0.1522, simple_loss=0.2216, pruned_loss=0.04142, over 6777.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2506, pruned_loss=0.03448, over 1424183.81 frames.], batch size: 15, lr: 3.40e-04
+2022-05-15 05:21:05,554 INFO [train.py:812] (2/8) Epoch 23, batch 1300, loss[loss=0.1818, simple_loss=0.2722, pruned_loss=0.04566, over 7189.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2504, pruned_loss=0.03438, over 1426416.53 frames.], batch size: 23, lr: 3.40e-04
+2022-05-15 05:22:03,083 INFO [train.py:812] (2/8) Epoch 23, batch 1350, loss[loss=0.1406, simple_loss=0.2252, pruned_loss=0.02801, over 7280.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2493, pruned_loss=0.03371, over 1427510.63 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:23:02,546 INFO [train.py:812] (2/8) Epoch 23, batch 1400, loss[loss=0.1686, simple_loss=0.257, pruned_loss=0.04009, over 7123.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.03361, over 1427398.65 frames.], batch size: 21, lr: 3.40e-04
+2022-05-15 05:24:01,073 INFO [train.py:812] (2/8) Epoch 23, batch 1450, loss[loss=0.1279, simple_loss=0.2132, pruned_loss=0.02129, over 7417.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2495, pruned_loss=0.03376, over 1421483.01 frames.], batch size: 18, lr: 3.40e-04
+2022-05-15 05:24:59,795 INFO [train.py:812] (2/8) Epoch 23, batch 1500, loss[loss=0.1859, simple_loss=0.2753, pruned_loss=0.04821, over 7061.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2488, pruned_loss=0.0337, over 1423914.38 frames.], batch size: 28, lr: 3.40e-04
+2022-05-15 05:25:58,346 INFO [train.py:812] (2/8) Epoch 23, batch 1550, loss[loss=0.1432, simple_loss=0.2379, pruned_loss=0.02419, over 7359.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2495, pruned_loss=0.03372, over 1414959.33 frames.], batch size: 19, lr: 3.40e-04
+2022-05-15 05:26:57,175 INFO [train.py:812] (2/8) Epoch 23, batch 1600, loss[loss=0.1953, simple_loss=0.2798, pruned_loss=0.05539, over 7217.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2507, pruned_loss=0.03446, over 1413325.35 frames.], batch size: 21, lr: 3.40e-04
+2022-05-15 05:27:55,178 INFO [train.py:812] (2/8) Epoch 23, batch 1650, loss[loss=0.1745, simple_loss=0.2732, pruned_loss=0.03788, over 7366.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2507, pruned_loss=0.03447, over 1415641.98 frames.], batch size: 23, lr: 3.40e-04
+2022-05-15 05:28:54,107 INFO [train.py:812] (2/8) Epoch 23, batch 1700, loss[loss=0.1467, simple_loss=0.2299, pruned_loss=0.03172, over 7406.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2504, pruned_loss=0.03467, over 1416419.14 frames.], batch size: 18, lr: 3.39e-04
+2022-05-15 05:29:50,567 INFO [train.py:812] (2/8) Epoch 23, batch 1750, loss[loss=0.2154, simple_loss=0.2912, pruned_loss=0.06983, over 7153.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2505, pruned_loss=0.03466, over 1415043.62 frames.], batch size: 26, lr: 3.39e-04
+2022-05-15 05:30:48,705 INFO [train.py:812] (2/8) Epoch 23, batch 1800, loss[loss=0.1975, simple_loss=0.2958, pruned_loss=0.04961, over 5175.00 frames.], tot_loss[loss=0.16, simple_loss=0.2507, pruned_loss=0.03467, over 1413189.17 frames.], batch size: 53, lr: 3.39e-04
+2022-05-15 05:31:46,090 INFO [train.py:812] (2/8) Epoch 23, batch 1850, loss[loss=0.1668, simple_loss=0.2599, pruned_loss=0.03691, over 7433.00 frames.], tot_loss[loss=0.1592, simple_loss=0.25, pruned_loss=0.03415, over 1417862.67 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:32:43,998 INFO [train.py:812] (2/8) Epoch 23, batch 1900, loss[loss=0.1684, simple_loss=0.2649, pruned_loss=0.03598, over 7137.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2494, pruned_loss=0.03402, over 1420735.69 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:33:42,406 INFO [train.py:812] (2/8) Epoch 23, batch 1950, loss[loss=0.1807, simple_loss=0.2819, pruned_loss=0.03975, over 7141.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2507, pruned_loss=0.03484, over 1417683.81 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:34:41,193 INFO [train.py:812] (2/8) Epoch 23, batch 2000, loss[loss=0.1494, simple_loss=0.2438, pruned_loss=0.02754, over 7258.00 frames.], tot_loss[loss=0.1601, simple_loss=0.251, pruned_loss=0.03458, over 1420549.93 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:35:40,298 INFO [train.py:812] (2/8) Epoch 23, batch 2050, loss[loss=0.1712, simple_loss=0.2571, pruned_loss=0.04261, over 7243.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2505, pruned_loss=0.03447, over 1425160.39 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:36:39,477 INFO [train.py:812] (2/8) Epoch 23, batch 2100, loss[loss=0.1665, simple_loss=0.2606, pruned_loss=0.03618, over 7207.00 frames.], tot_loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03432, over 1420720.54 frames.], batch size: 23, lr: 3.39e-04
+2022-05-15 05:37:37,948 INFO [train.py:812] (2/8) Epoch 23, batch 2150, loss[loss=0.1542, simple_loss=0.2433, pruned_loss=0.03255, over 7158.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2499, pruned_loss=0.03437, over 1421349.19 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:38:37,637 INFO [train.py:812] (2/8) Epoch 23, batch 2200, loss[loss=0.1465, simple_loss=0.2332, pruned_loss=0.02985, over 7145.00 frames.], tot_loss[loss=0.16, simple_loss=0.2503, pruned_loss=0.03485, over 1416607.23 frames.], batch size: 20, lr: 3.39e-04
+2022-05-15 05:39:36,703 INFO [train.py:812] (2/8) Epoch 23, batch 2250, loss[loss=0.1493, simple_loss=0.2389, pruned_loss=0.02985, over 7163.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2503, pruned_loss=0.03473, over 1413544.24 frames.], batch size: 19, lr: 3.39e-04
+2022-05-15 05:40:35,583 INFO [train.py:812] (2/8) Epoch 23, batch 2300, loss[loss=0.1639, simple_loss=0.2608, pruned_loss=0.03353, over 7316.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2494, pruned_loss=0.03419, over 1414332.06 frames.], batch size: 21, lr: 3.38e-04
+2022-05-15 05:41:34,385 INFO [train.py:812] (2/8) Epoch 23, batch 2350, loss[loss=0.1582, simple_loss=0.2585, pruned_loss=0.02892, over 7321.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2491, pruned_loss=0.03405, over 1416112.11 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:42:33,216 INFO [train.py:812] (2/8) Epoch 23, batch 2400, loss[loss=0.1706, simple_loss=0.259, pruned_loss=0.04111, over 7305.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2493, pruned_loss=0.03406, over 1419237.13 frames.], batch size: 24, lr: 3.38e-04
+2022-05-15 05:43:31,222 INFO [train.py:812] (2/8) Epoch 23, batch 2450, loss[loss=0.1701, simple_loss=0.2582, pruned_loss=0.04098, over 7213.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2503, pruned_loss=0.03409, over 1422894.20 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:44:30,340 INFO [train.py:812] (2/8) Epoch 23, batch 2500, loss[loss=0.1598, simple_loss=0.2509, pruned_loss=0.03432, over 6491.00 frames.], tot_loss[loss=0.1582, simple_loss=0.249, pruned_loss=0.03368, over 1420438.91 frames.], batch size: 38, lr: 3.38e-04
+2022-05-15 05:45:29,333 INFO [train.py:812] (2/8) Epoch 23, batch 2550, loss[loss=0.1713, simple_loss=0.2682, pruned_loss=0.03722, over 7378.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03356, over 1421060.50 frames.], batch size: 23, lr: 3.38e-04
+2022-05-15 05:46:26,774 INFO [train.py:812] (2/8) Epoch 23, batch 2600, loss[loss=0.1664, simple_loss=0.2642, pruned_loss=0.03433, over 7339.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2489, pruned_loss=0.03365, over 1425275.48 frames.], batch size: 22, lr: 3.38e-04
+2022-05-15 05:47:25,313 INFO [train.py:812] (2/8) Epoch 23, batch 2650, loss[loss=0.1735, simple_loss=0.2661, pruned_loss=0.04047, over 7270.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2489, pruned_loss=0.03437, over 1423037.82 frames.], batch size: 25, lr: 3.38e-04
+2022-05-15 05:48:25,316 INFO [train.py:812] (2/8) Epoch 23, batch 2700, loss[loss=0.1666, simple_loss=0.2621, pruned_loss=0.03549, over 7161.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2496, pruned_loss=0.03443, over 1422205.52 frames.], batch size: 19, lr: 3.38e-04
+2022-05-15 05:49:24,348 INFO [train.py:812] (2/8) Epoch 23, batch 2750, loss[loss=0.1334, simple_loss=0.2224, pruned_loss=0.02218, over 7164.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2492, pruned_loss=0.03468, over 1420089.46 frames.], batch size: 18, lr: 3.38e-04
+2022-05-15 05:50:23,652 INFO [train.py:812] (2/8) Epoch 23, batch 2800, loss[loss=0.1423, simple_loss=0.2308, pruned_loss=0.02683, over 7156.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2496, pruned_loss=0.03491, over 1419449.28 frames.], batch size: 18, lr: 3.38e-04
+2022-05-15 05:51:22,632 INFO [train.py:812] (2/8) Epoch 23, batch 2850, loss[loss=0.1893, simple_loss=0.2842, pruned_loss=0.04717, over 7046.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2498, pruned_loss=0.03474, over 1421495.08 frames.], batch size: 28, lr: 3.38e-04
+2022-05-15 05:52:22,319 INFO [train.py:812] (2/8) Epoch 23, batch 2900, loss[loss=0.1714, simple_loss=0.2634, pruned_loss=0.03965, over 7308.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2504, pruned_loss=0.03465, over 1423138.14 frames.], batch size: 25, lr: 3.37e-04
+2022-05-15 05:53:20,357 INFO [train.py:812] (2/8) Epoch 23, batch 2950, loss[loss=0.1771, simple_loss=0.2671, pruned_loss=0.04352, over 7198.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2504, pruned_loss=0.03448, over 1423923.69 frames.], batch size: 22, lr: 3.37e-04
+2022-05-15 05:54:18,786 INFO [train.py:812] (2/8) Epoch 23, batch 3000, loss[loss=0.1267, simple_loss=0.2089, pruned_loss=0.02229, over 6995.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2505, pruned_loss=0.03411, over 1423487.89 frames.], batch size: 16, lr: 3.37e-04
+2022-05-15 05:54:18,787 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 05:54:28,115 INFO [train.py:841] (2/8) Epoch 23, validation: loss=0.153, simple_loss=0.251, pruned_loss=0.02752, over 698248.00 frames.
+2022-05-15 05:55:26,696 INFO [train.py:812] (2/8) Epoch 23, batch 3050, loss[loss=0.1348, simple_loss=0.224, pruned_loss=0.02276, over 7154.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2506, pruned_loss=0.03423, over 1426413.72 frames.], batch size: 19, lr: 3.37e-04
+2022-05-15 05:56:31,536 INFO [train.py:812] (2/8) Epoch 23, batch 3100, loss[loss=0.1419, simple_loss=0.235, pruned_loss=0.0244, over 7236.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2499, pruned_loss=0.03412, over 1425103.66 frames.], batch size: 20, lr: 3.37e-04
+2022-05-15 05:57:30,936 INFO [train.py:812] (2/8) Epoch 23, batch 3150, loss[loss=0.1622, simple_loss=0.2498, pruned_loss=0.03729, over 7329.00 frames.], tot_loss[loss=0.1595, simple_loss=0.25, pruned_loss=0.03445, over 1426475.76 frames.], batch size: 20, lr: 3.37e-04
+2022-05-15 05:58:30,534 INFO [train.py:812] (2/8) Epoch 23, batch 3200, loss[loss=0.173, simple_loss=0.2658, pruned_loss=0.04015, over 7110.00 frames.], tot_loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03427, over 1427271.09 frames.], batch size: 21, lr: 3.37e-04
+2022-05-15 05:59:29,505 INFO [train.py:812] (2/8) Epoch 23, batch 3250, loss[loss=0.1631, simple_loss=0.2547, pruned_loss=0.0358, over 6288.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2508, pruned_loss=0.03483, over 1422098.91 frames.], batch size: 37, lr: 3.37e-04
+2022-05-15 06:00:29,699 INFO [train.py:812] (2/8) Epoch 23, batch 3300, loss[loss=0.182, simple_loss=0.2726, pruned_loss=0.04567, over 7276.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2513, pruned_loss=0.03469, over 1422421.86 frames.], batch size: 24, lr: 3.37e-04
+2022-05-15 06:01:29,090 INFO [train.py:812] (2/8) Epoch 23, batch 3350, loss[loss=0.1614, simple_loss=0.2585, pruned_loss=0.03213, over 7187.00 frames.], tot_loss[loss=0.159, simple_loss=0.2499, pruned_loss=0.03402, over 1426865.41 frames.], batch size: 26, lr: 3.37e-04
+2022-05-15 06:02:28,644 INFO [train.py:812] (2/8) Epoch 23, batch 3400, loss[loss=0.1491, simple_loss=0.2408, pruned_loss=0.02867, over 7149.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.03368, over 1428021.22 frames.], batch size: 19, lr: 3.37e-04
+2022-05-15 06:03:27,847 INFO [train.py:812] (2/8) Epoch 23, batch 3450, loss[loss=0.1416, simple_loss=0.2209, pruned_loss=0.03118, over 6752.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2483, pruned_loss=0.03341, over 1429316.05 frames.], batch size: 15, lr: 3.37e-04
+2022-05-15 06:04:27,421 INFO [train.py:812] (2/8) Epoch 23, batch 3500, loss[loss=0.1585, simple_loss=0.2429, pruned_loss=0.03709, over 6798.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2485, pruned_loss=0.0332, over 1430253.27 frames.], batch size: 15, lr: 3.37e-04
+2022-05-15 06:05:25,895 INFO [train.py:812] (2/8) Epoch 23, batch 3550, loss[loss=0.1479, simple_loss=0.2325, pruned_loss=0.03167, over 7411.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2479, pruned_loss=0.03313, over 1429452.25 frames.], batch size: 18, lr: 3.36e-04
+2022-05-15 06:06:25,042 INFO [train.py:812] (2/8) Epoch 23, batch 3600, loss[loss=0.138, simple_loss=0.2241, pruned_loss=0.02595, over 7286.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2494, pruned_loss=0.03377, over 1430891.92 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:07:24,128 INFO [train.py:812] (2/8) Epoch 23, batch 3650, loss[loss=0.1725, simple_loss=0.2741, pruned_loss=0.0355, over 6503.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2488, pruned_loss=0.03351, over 1431014.07 frames.], batch size: 38, lr: 3.36e-04
+2022-05-15 06:08:33,459 INFO [train.py:812] (2/8) Epoch 23, batch 3700, loss[loss=0.1701, simple_loss=0.2588, pruned_loss=0.04072, over 7153.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2497, pruned_loss=0.0339, over 1430014.31 frames.], batch size: 19, lr: 3.36e-04
+2022-05-15 06:09:32,120 INFO [train.py:812] (2/8) Epoch 23, batch 3750, loss[loss=0.1323, simple_loss=0.2112, pruned_loss=0.02676, over 7279.00 frames.], tot_loss[loss=0.1586, simple_loss=0.25, pruned_loss=0.03359, over 1427368.14 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:10:31,405 INFO [train.py:812] (2/8) Epoch 23, batch 3800, loss[loss=0.1754, simple_loss=0.2738, pruned_loss=0.03851, over 7388.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2499, pruned_loss=0.03352, over 1428912.41 frames.], batch size: 23, lr: 3.36e-04
+2022-05-15 06:11:30,123 INFO [train.py:812] (2/8) Epoch 23, batch 3850, loss[loss=0.156, simple_loss=0.2495, pruned_loss=0.03129, over 7030.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2496, pruned_loss=0.03347, over 1429280.42 frames.], batch size: 28, lr: 3.36e-04
+2022-05-15 06:12:28,297 INFO [train.py:812] (2/8) Epoch 23, batch 3900, loss[loss=0.1645, simple_loss=0.2667, pruned_loss=0.03115, over 7117.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2498, pruned_loss=0.034, over 1429671.96 frames.], batch size: 21, lr: 3.36e-04
+2022-05-15 06:13:25,762 INFO [train.py:812] (2/8) Epoch 23, batch 3950, loss[loss=0.1545, simple_loss=0.2441, pruned_loss=0.03247, over 7168.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2502, pruned_loss=0.03424, over 1428988.95 frames.], batch size: 19, lr: 3.36e-04
+2022-05-15 06:14:22,990 INFO [train.py:812] (2/8) Epoch 23, batch 4000, loss[loss=0.1388, simple_loss=0.2224, pruned_loss=0.02757, over 7305.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2491, pruned_loss=0.03405, over 1426053.65 frames.], batch size: 17, lr: 3.36e-04
+2022-05-15 06:15:21,469 INFO [train.py:812] (2/8) Epoch 23, batch 4050, loss[loss=0.1376, simple_loss=0.2196, pruned_loss=0.02783, over 6832.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2497, pruned_loss=0.03457, over 1420772.99 frames.], batch size: 15, lr: 3.36e-04
+2022-05-15 06:16:21,869 INFO [train.py:812] (2/8) Epoch 23, batch 4100, loss[loss=0.1457, simple_loss=0.2266, pruned_loss=0.03244, over 7258.00 frames.], tot_loss[loss=0.159, simple_loss=0.249, pruned_loss=0.03453, over 1418228.41 frames.], batch size: 16, lr: 3.36e-04
+2022-05-15 06:17:19,528 INFO [train.py:812] (2/8) Epoch 23, batch 4150, loss[loss=0.1605, simple_loss=0.2517, pruned_loss=0.03463, over 7333.00 frames.], tot_loss[loss=0.1596, simple_loss=0.25, pruned_loss=0.03461, over 1417600.08 frames.], batch size: 21, lr: 3.35e-04
+2022-05-15 06:18:18,941 INFO [train.py:812] (2/8) Epoch 23, batch 4200, loss[loss=0.1442, simple_loss=0.2193, pruned_loss=0.03457, over 7012.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2502, pruned_loss=0.03466, over 1421964.91 frames.], batch size: 16, lr: 3.35e-04
+2022-05-15 06:19:17,906 INFO [train.py:812] (2/8) Epoch 23, batch 4250, loss[loss=0.1469, simple_loss=0.2471, pruned_loss=0.02334, over 7229.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2503, pruned_loss=0.03429, over 1423194.96 frames.], batch size: 20, lr: 3.35e-04
+2022-05-15 06:20:16,265 INFO [train.py:812] (2/8) Epoch 23, batch 4300, loss[loss=0.1462, simple_loss=0.2256, pruned_loss=0.03344, over 7161.00 frames.], tot_loss[loss=0.1583, simple_loss=0.249, pruned_loss=0.03374, over 1419607.44 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:21:15,789 INFO [train.py:812] (2/8) Epoch 23, batch 4350, loss[loss=0.1527, simple_loss=0.2382, pruned_loss=0.03358, over 7229.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2483, pruned_loss=0.03354, over 1421072.10 frames.], batch size: 16, lr: 3.35e-04
+2022-05-15 06:22:15,703 INFO [train.py:812] (2/8) Epoch 23, batch 4400, loss[loss=0.1582, simple_loss=0.2472, pruned_loss=0.03456, over 7060.00 frames.], tot_loss[loss=0.158, simple_loss=0.2481, pruned_loss=0.03394, over 1418707.36 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:23:14,861 INFO [train.py:812] (2/8) Epoch 23, batch 4450, loss[loss=0.1829, simple_loss=0.2671, pruned_loss=0.04938, over 5295.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2485, pruned_loss=0.03404, over 1412574.48 frames.], batch size: 52, lr: 3.35e-04
+2022-05-15 06:24:12,959 INFO [train.py:812] (2/8) Epoch 23, batch 4500, loss[loss=0.1581, simple_loss=0.2447, pruned_loss=0.03568, over 7061.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2484, pruned_loss=0.03348, over 1411558.02 frames.], batch size: 18, lr: 3.35e-04
+2022-05-15 06:25:11,006 INFO [train.py:812] (2/8) Epoch 23, batch 4550, loss[loss=0.1995, simple_loss=0.2804, pruned_loss=0.05925, over 4980.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2516, pruned_loss=0.03557, over 1355308.35 frames.], batch size: 54, lr: 3.35e-04
+2022-05-15 06:26:16,419 INFO [train.py:812] (2/8) Epoch 24, batch 0, loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03088, over 7213.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03088, over 7213.00 frames.], batch size: 16, lr: 3.28e-04
+2022-05-15 06:27:14,050 INFO [train.py:812] (2/8) Epoch 24, batch 50, loss[loss=0.1316, simple_loss=0.2191, pruned_loss=0.02201, over 7281.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03212, over 316688.48 frames.], batch size: 17, lr: 3.28e-04
+2022-05-15 06:28:13,469 INFO [train.py:812] (2/8) Epoch 24, batch 100, loss[loss=0.162, simple_loss=0.2554, pruned_loss=0.03433, over 7328.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2496, pruned_loss=0.03253, over 567303.75 frames.], batch size: 20, lr: 3.28e-04
+2022-05-15 06:29:11,043 INFO [train.py:812] (2/8) Epoch 24, batch 150, loss[loss=0.1928, simple_loss=0.2803, pruned_loss=0.05272, over 7385.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2499, pruned_loss=0.03336, over 753121.77 frames.], batch size: 23, lr: 3.28e-04
+2022-05-15 06:30:10,078 INFO [train.py:812] (2/8) Epoch 24, batch 200, loss[loss=0.1722, simple_loss=0.2662, pruned_loss=0.03909, over 7183.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03361, over 903577.58 frames.], batch size: 22, lr: 3.28e-04
+2022-05-15 06:31:07,638 INFO [train.py:812] (2/8) Epoch 24, batch 250, loss[loss=0.1395, simple_loss=0.2383, pruned_loss=0.02031, over 7414.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2485, pruned_loss=0.03329, over 1015400.79 frames.], batch size: 21, lr: 3.28e-04
+2022-05-15 06:32:07,186 INFO [train.py:812] (2/8) Epoch 24, batch 300, loss[loss=0.1654, simple_loss=0.2543, pruned_loss=0.03824, over 7149.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2472, pruned_loss=0.0323, over 1106750.30 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:33:03,993 INFO [train.py:812] (2/8) Epoch 24, batch 350, loss[loss=0.1835, simple_loss=0.2674, pruned_loss=0.04984, over 7296.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2472, pruned_loss=0.03219, over 1178572.97 frames.], batch size: 25, lr: 3.27e-04
+2022-05-15 06:34:01,085 INFO [train.py:812] (2/8) Epoch 24, batch 400, loss[loss=0.174, simple_loss=0.2646, pruned_loss=0.04169, over 7304.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2481, pruned_loss=0.03356, over 1228791.22 frames.], batch size: 24, lr: 3.27e-04
+2022-05-15 06:34:58,959 INFO [train.py:812] (2/8) Epoch 24, batch 450, loss[loss=0.1723, simple_loss=0.2645, pruned_loss=0.04003, over 7142.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2483, pruned_loss=0.03319, over 1274822.67 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:35:57,367 INFO [train.py:812] (2/8) Epoch 24, batch 500, loss[loss=0.1567, simple_loss=0.2441, pruned_loss=0.03468, over 7365.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2478, pruned_loss=0.03274, over 1307296.79 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:36:55,890 INFO [train.py:812] (2/8) Epoch 24, batch 550, loss[loss=0.1813, simple_loss=0.2697, pruned_loss=0.04642, over 7210.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2485, pruned_loss=0.03317, over 1335671.81 frames.], batch size: 22, lr: 3.27e-04
+2022-05-15 06:37:55,425 INFO [train.py:812] (2/8) Epoch 24, batch 600, loss[loss=0.1371, simple_loss=0.2202, pruned_loss=0.02704, over 7367.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2477, pruned_loss=0.03292, over 1354616.50 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:38:54,602 INFO [train.py:812] (2/8) Epoch 24, batch 650, loss[loss=0.1505, simple_loss=0.2377, pruned_loss=0.03166, over 7364.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2475, pruned_loss=0.03302, over 1364926.96 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:39:54,716 INFO [train.py:812] (2/8) Epoch 24, batch 700, loss[loss=0.1699, simple_loss=0.2653, pruned_loss=0.0373, over 7191.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2464, pruned_loss=0.03284, over 1382254.89 frames.], batch size: 26, lr: 3.27e-04
+2022-05-15 06:40:53,832 INFO [train.py:812] (2/8) Epoch 24, batch 750, loss[loss=0.1366, simple_loss=0.2088, pruned_loss=0.03225, over 7001.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03287, over 1393097.12 frames.], batch size: 16, lr: 3.27e-04
+2022-05-15 06:41:53,097 INFO [train.py:812] (2/8) Epoch 24, batch 800, loss[loss=0.1537, simple_loss=0.2413, pruned_loss=0.03305, over 7260.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2475, pruned_loss=0.03252, over 1399670.95 frames.], batch size: 19, lr: 3.27e-04
+2022-05-15 06:42:52,221 INFO [train.py:812] (2/8) Epoch 24, batch 850, loss[loss=0.1643, simple_loss=0.2576, pruned_loss=0.03545, over 6857.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.03268, over 1406127.94 frames.], batch size: 32, lr: 3.27e-04
+2022-05-15 06:43:51,470 INFO [train.py:812] (2/8) Epoch 24, batch 900, loss[loss=0.1437, simple_loss=0.2344, pruned_loss=0.02656, over 7431.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2467, pruned_loss=0.03208, over 1412347.64 frames.], batch size: 20, lr: 3.27e-04
+2022-05-15 06:44:50,581 INFO [train.py:812] (2/8) Epoch 24, batch 950, loss[loss=0.1529, simple_loss=0.2495, pruned_loss=0.0281, over 6610.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2461, pruned_loss=0.03183, over 1417572.86 frames.], batch size: 38, lr: 3.26e-04
+2022-05-15 06:45:49,544 INFO [train.py:812] (2/8) Epoch 24, batch 1000, loss[loss=0.1642, simple_loss=0.2614, pruned_loss=0.0335, over 7317.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2467, pruned_loss=0.03229, over 1419716.38 frames.], batch size: 21, lr: 3.26e-04
+2022-05-15 06:46:47,313 INFO [train.py:812] (2/8) Epoch 24, batch 1050, loss[loss=0.1465, simple_loss=0.2421, pruned_loss=0.02542, over 7233.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2474, pruned_loss=0.03288, over 1413301.12 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:47:46,418 INFO [train.py:812] (2/8) Epoch 24, batch 1100, loss[loss=0.1653, simple_loss=0.2608, pruned_loss=0.03491, over 7153.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2474, pruned_loss=0.03297, over 1412730.93 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:48:44,959 INFO [train.py:812] (2/8) Epoch 24, batch 1150, loss[loss=0.167, simple_loss=0.2625, pruned_loss=0.03574, over 6336.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2474, pruned_loss=0.03315, over 1415719.88 frames.], batch size: 38, lr: 3.26e-04
+2022-05-15 06:49:42,952 INFO [train.py:812] (2/8) Epoch 24, batch 1200, loss[loss=0.1494, simple_loss=0.2319, pruned_loss=0.0335, over 7161.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2473, pruned_loss=0.03309, over 1418430.36 frames.], batch size: 18, lr: 3.26e-04
+2022-05-15 06:50:50,709 INFO [train.py:812] (2/8) Epoch 24, batch 1250, loss[loss=0.1519, simple_loss=0.2394, pruned_loss=0.03215, over 7333.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2471, pruned_loss=0.03333, over 1418471.27 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:51:49,903 INFO [train.py:812] (2/8) Epoch 24, batch 1300, loss[loss=0.1539, simple_loss=0.2509, pruned_loss=0.02846, over 6899.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2473, pruned_loss=0.03302, over 1419583.92 frames.], batch size: 31, lr: 3.26e-04
+2022-05-15 06:52:48,827 INFO [train.py:812] (2/8) Epoch 24, batch 1350, loss[loss=0.1463, simple_loss=0.2257, pruned_loss=0.03349, over 7402.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2482, pruned_loss=0.03352, over 1425509.91 frames.], batch size: 18, lr: 3.26e-04
+2022-05-15 06:53:46,292 INFO [train.py:812] (2/8) Epoch 24, batch 1400, loss[loss=0.2123, simple_loss=0.2963, pruned_loss=0.06413, over 7196.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2487, pruned_loss=0.03355, over 1424461.86 frames.], batch size: 26, lr: 3.26e-04
+2022-05-15 06:55:13,449 INFO [train.py:812] (2/8) Epoch 24, batch 1450, loss[loss=0.1758, simple_loss=0.261, pruned_loss=0.04531, over 7149.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2491, pruned_loss=0.03379, over 1422088.89 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:56:21,939 INFO [train.py:812] (2/8) Epoch 24, batch 1500, loss[loss=0.1381, simple_loss=0.2315, pruned_loss=0.02234, over 7146.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2481, pruned_loss=0.0336, over 1420980.41 frames.], batch size: 20, lr: 3.26e-04
+2022-05-15 06:57:21,235 INFO [train.py:812] (2/8) Epoch 24, batch 1550, loss[loss=0.1916, simple_loss=0.2959, pruned_loss=0.04369, over 6741.00 frames.], tot_loss[loss=0.1577, simple_loss=0.248, pruned_loss=0.03372, over 1421066.24 frames.], batch size: 31, lr: 3.26e-04
+2022-05-15 06:58:39,397 INFO [train.py:812] (2/8) Epoch 24, batch 1600, loss[loss=0.1673, simple_loss=0.2477, pruned_loss=0.04343, over 7331.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2483, pruned_loss=0.0334, over 1423172.45 frames.], batch size: 20, lr: 3.25e-04
+2022-05-15 06:59:37,740 INFO [train.py:812] (2/8) Epoch 24, batch 1650, loss[loss=0.1158, simple_loss=0.1992, pruned_loss=0.01616, over 6784.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2484, pruned_loss=0.03325, over 1415175.22 frames.], batch size: 15, lr: 3.25e-04
+2022-05-15 07:00:36,788 INFO [train.py:812] (2/8) Epoch 24, batch 1700, loss[loss=0.1722, simple_loss=0.2813, pruned_loss=0.03155, over 7311.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2483, pruned_loss=0.03319, over 1418565.86 frames.], batch size: 21, lr: 3.25e-04
+2022-05-15 07:01:34,453 INFO [train.py:812] (2/8) Epoch 24, batch 1750, loss[loss=0.1299, simple_loss=0.2093, pruned_loss=0.02522, over 7068.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2487, pruned_loss=0.03316, over 1420023.48 frames.], batch size: 18, lr: 3.25e-04
+2022-05-15 07:02:33,276 INFO [train.py:812] (2/8) Epoch 24, batch 1800, loss[loss=0.1694, simple_loss=0.2655, pruned_loss=0.03663, over 7344.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2487, pruned_loss=0.033, over 1420302.83 frames.], batch size: 22, lr: 3.25e-04
+2022-05-15 07:03:31,325 INFO [train.py:812] (2/8) Epoch 24, batch 1850, loss[loss=0.1442, simple_loss=0.2341, pruned_loss=0.02712, over 7278.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2487, pruned_loss=0.03321, over 1424311.33 frames.], batch size: 24, lr: 3.25e-04
+2022-05-15 07:04:30,220 INFO [train.py:812] (2/8) Epoch 24, batch 1900, loss[loss=0.15, simple_loss=0.25, pruned_loss=0.02501, over 7080.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2484, pruned_loss=0.03338, over 1422002.75 frames.], batch size: 28, lr: 3.25e-04
+2022-05-15 07:05:29,103 INFO [train.py:812] (2/8) Epoch 24, batch 1950, loss[loss=0.164, simple_loss=0.2605, pruned_loss=0.03374, over 7116.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03319, over 1423798.45 frames.], batch size: 21, lr: 3.25e-04
+2022-05-15 07:06:27,364 INFO [train.py:812] (2/8) Epoch 24, batch 2000, loss[loss=0.1623, simple_loss=0.2484, pruned_loss=0.03811, over 5255.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2497, pruned_loss=0.03378, over 1422255.74 frames.], batch size: 53, lr: 3.25e-04
+2022-05-15 07:07:25,812 INFO [train.py:812] (2/8) Epoch 24, batch 2050, loss[loss=0.1647, simple_loss=0.2525, pruned_loss=0.0384, over 7417.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03358, over 1421709.92 frames.], batch size: 20, lr: 3.25e-04
+2022-05-15 07:08:23,658 INFO [train.py:812] (2/8) Epoch 24, batch 2100, loss[loss=0.1771, simple_loss=0.2617, pruned_loss=0.04622, over 6991.00 frames.], tot_loss[loss=0.158, simple_loss=0.2492, pruned_loss=0.03338, over 1422387.35 frames.], batch size: 16, lr: 3.25e-04
+2022-05-15 07:09:22,551 INFO [train.py:812] (2/8) Epoch 24, batch 2150, loss[loss=0.2038, simple_loss=0.2784, pruned_loss=0.06459, over 4938.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2487, pruned_loss=0.03343, over 1419929.97 frames.], batch size: 53, lr: 3.25e-04
+2022-05-15 07:10:21,849 INFO [train.py:812] (2/8) Epoch 24, batch 2200, loss[loss=0.1407, simple_loss=0.2286, pruned_loss=0.02641, over 7139.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2486, pruned_loss=0.03345, over 1419216.16 frames.], batch size: 17, lr: 3.25e-04
+2022-05-15 07:11:20,915 INFO [train.py:812] (2/8) Epoch 24, batch 2250, loss[loss=0.165, simple_loss=0.2616, pruned_loss=0.03419, over 7302.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2498, pruned_loss=0.0338, over 1410152.55 frames.], batch size: 25, lr: 3.24e-04
+2022-05-15 07:12:20,012 INFO [train.py:812] (2/8) Epoch 24, batch 2300, loss[loss=0.1191, simple_loss=0.2001, pruned_loss=0.01909, over 7280.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2485, pruned_loss=0.03337, over 1417424.12 frames.], batch size: 17, lr: 3.24e-04
+2022-05-15 07:13:18,845 INFO [train.py:812] (2/8) Epoch 24, batch 2350, loss[loss=0.15, simple_loss=0.2499, pruned_loss=0.02506, over 7331.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2495, pruned_loss=0.03355, over 1418279.25 frames.], batch size: 22, lr: 3.24e-04
+2022-05-15 07:14:18,392 INFO [train.py:812] (2/8) Epoch 24, batch 2400, loss[loss=0.1226, simple_loss=0.2126, pruned_loss=0.01627, over 7203.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2498, pruned_loss=0.03337, over 1421549.90 frames.], batch size: 16, lr: 3.24e-04
+2022-05-15 07:15:15,758 INFO [train.py:812] (2/8) Epoch 24, batch 2450, loss[loss=0.1865, simple_loss=0.2711, pruned_loss=0.05099, over 7238.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2498, pruned_loss=0.03364, over 1418401.18 frames.], batch size: 20, lr: 3.24e-04
+2022-05-15 07:16:21,438 INFO [train.py:812] (2/8) Epoch 24, batch 2500, loss[loss=0.1625, simple_loss=0.2535, pruned_loss=0.03576, over 7313.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03356, over 1418896.82 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:17:19,988 INFO [train.py:812] (2/8) Epoch 24, batch 2550, loss[loss=0.1919, simple_loss=0.2714, pruned_loss=0.05613, over 5078.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2487, pruned_loss=0.03335, over 1413659.60 frames.], batch size: 52, lr: 3.24e-04
+2022-05-15 07:18:18,698 INFO [train.py:812] (2/8) Epoch 24, batch 2600, loss[loss=0.1527, simple_loss=0.2441, pruned_loss=0.03068, over 7292.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2492, pruned_loss=0.03319, over 1416560.83 frames.], batch size: 18, lr: 3.24e-04
+2022-05-15 07:19:17,317 INFO [train.py:812] (2/8) Epoch 24, batch 2650, loss[loss=0.1871, simple_loss=0.2874, pruned_loss=0.04338, over 7314.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2486, pruned_loss=0.03314, over 1416778.19 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:20:16,533 INFO [train.py:812] (2/8) Epoch 24, batch 2700, loss[loss=0.1636, simple_loss=0.2637, pruned_loss=0.03176, over 7350.00 frames.], tot_loss[loss=0.1578, simple_loss=0.249, pruned_loss=0.03334, over 1421674.85 frames.], batch size: 22, lr: 3.24e-04
+2022-05-15 07:21:16,043 INFO [train.py:812] (2/8) Epoch 24, batch 2750, loss[loss=0.1605, simple_loss=0.2611, pruned_loss=0.02996, over 7403.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2482, pruned_loss=0.03282, over 1424955.65 frames.], batch size: 21, lr: 3.24e-04
+2022-05-15 07:22:15,053 INFO [train.py:812] (2/8) Epoch 24, batch 2800, loss[loss=0.1521, simple_loss=0.2396, pruned_loss=0.03223, over 7224.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2485, pruned_loss=0.03309, over 1421733.72 frames.], batch size: 20, lr: 3.24e-04
+2022-05-15 07:23:13,159 INFO [train.py:812] (2/8) Epoch 24, batch 2850, loss[loss=0.1457, simple_loss=0.2351, pruned_loss=0.02811, over 7351.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2497, pruned_loss=0.0335, over 1422706.14 frames.], batch size: 19, lr: 3.24e-04
+2022-05-15 07:24:12,090 INFO [train.py:812] (2/8) Epoch 24, batch 2900, loss[loss=0.159, simple_loss=0.2512, pruned_loss=0.03338, over 7288.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2507, pruned_loss=0.03393, over 1422363.26 frames.], batch size: 25, lr: 3.24e-04
+2022-05-15 07:25:09,867 INFO [train.py:812] (2/8) Epoch 24, batch 2950, loss[loss=0.1225, simple_loss=0.2058, pruned_loss=0.01964, over 7270.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2498, pruned_loss=0.03366, over 1425810.97 frames.], batch size: 17, lr: 3.23e-04
+2022-05-15 07:26:08,040 INFO [train.py:812] (2/8) Epoch 24, batch 3000, loss[loss=0.1327, simple_loss=0.2295, pruned_loss=0.01791, over 7113.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2499, pruned_loss=0.03391, over 1421733.58 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:26:08,041 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 07:26:15,602 INFO [train.py:841] (2/8) Epoch 24, validation: loss=0.1537, simple_loss=0.2513, pruned_loss=0.02802, over 698248.00 frames.
+2022-05-15 07:27:15,003 INFO [train.py:812] (2/8) Epoch 24, batch 3050, loss[loss=0.1715, simple_loss=0.2563, pruned_loss=0.04332, over 7265.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2505, pruned_loss=0.03435, over 1417276.86 frames.], batch size: 18, lr: 3.23e-04
+2022-05-15 07:28:13,635 INFO [train.py:812] (2/8) Epoch 24, batch 3100, loss[loss=0.1532, simple_loss=0.2528, pruned_loss=0.02677, over 6765.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2491, pruned_loss=0.03389, over 1420938.71 frames.], batch size: 31, lr: 3.23e-04
+2022-05-15 07:29:12,200 INFO [train.py:812] (2/8) Epoch 24, batch 3150, loss[loss=0.1776, simple_loss=0.2318, pruned_loss=0.06169, over 6993.00 frames.], tot_loss[loss=0.1587, simple_loss=0.249, pruned_loss=0.0342, over 1422718.56 frames.], batch size: 16, lr: 3.23e-04
+2022-05-15 07:30:11,694 INFO [train.py:812] (2/8) Epoch 24, batch 3200, loss[loss=0.1445, simple_loss=0.2405, pruned_loss=0.0243, over 7314.00 frames.], tot_loss[loss=0.1586, simple_loss=0.249, pruned_loss=0.03412, over 1426934.26 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:31:10,168 INFO [train.py:812] (2/8) Epoch 24, batch 3250, loss[loss=0.1307, simple_loss=0.2151, pruned_loss=0.02319, over 7168.00 frames.], tot_loss[loss=0.158, simple_loss=0.2484, pruned_loss=0.03377, over 1428326.21 frames.], batch size: 18, lr: 3.23e-04
+2022-05-15 07:32:09,103 INFO [train.py:812] (2/8) Epoch 24, batch 3300, loss[loss=0.1715, simple_loss=0.2681, pruned_loss=0.0375, over 7307.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2488, pruned_loss=0.03334, over 1428296.89 frames.], batch size: 24, lr: 3.23e-04
+2022-05-15 07:33:06,613 INFO [train.py:812] (2/8) Epoch 24, batch 3350, loss[loss=0.1529, simple_loss=0.2512, pruned_loss=0.02731, over 7282.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2494, pruned_loss=0.03373, over 1424563.44 frames.], batch size: 24, lr: 3.23e-04
+2022-05-15 07:34:04,976 INFO [train.py:812] (2/8) Epoch 24, batch 3400, loss[loss=0.1793, simple_loss=0.268, pruned_loss=0.04534, over 7361.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.03369, over 1428592.02 frames.], batch size: 19, lr: 3.23e-04
+2022-05-15 07:35:03,126 INFO [train.py:812] (2/8) Epoch 24, batch 3450, loss[loss=0.1663, simple_loss=0.2716, pruned_loss=0.03046, over 7336.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2504, pruned_loss=0.03383, over 1423261.93 frames.], batch size: 22, lr: 3.23e-04
+2022-05-15 07:36:01,795 INFO [train.py:812] (2/8) Epoch 24, batch 3500, loss[loss=0.1391, simple_loss=0.2266, pruned_loss=0.02583, over 6813.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2491, pruned_loss=0.03318, over 1421519.22 frames.], batch size: 15, lr: 3.23e-04
+2022-05-15 07:37:00,362 INFO [train.py:812] (2/8) Epoch 24, batch 3550, loss[loss=0.1496, simple_loss=0.2448, pruned_loss=0.02721, over 7126.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2485, pruned_loss=0.03269, over 1423766.38 frames.], batch size: 21, lr: 3.23e-04
+2022-05-15 07:38:00,112 INFO [train.py:812] (2/8) Epoch 24, batch 3600, loss[loss=0.1493, simple_loss=0.2441, pruned_loss=0.0272, over 7081.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2491, pruned_loss=0.03277, over 1423776.32 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:38:57,462 INFO [train.py:812] (2/8) Epoch 24, batch 3650, loss[loss=0.1777, simple_loss=0.2603, pruned_loss=0.04756, over 7354.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2504, pruned_loss=0.03371, over 1425052.31 frames.], batch size: 19, lr: 3.22e-04
+2022-05-15 07:39:55,858 INFO [train.py:812] (2/8) Epoch 24, batch 3700, loss[loss=0.1586, simple_loss=0.2536, pruned_loss=0.03178, over 6384.00 frames.], tot_loss[loss=0.159, simple_loss=0.2501, pruned_loss=0.03393, over 1422405.26 frames.], batch size: 37, lr: 3.22e-04
+2022-05-15 07:40:52,808 INFO [train.py:812] (2/8) Epoch 24, batch 3750, loss[loss=0.1463, simple_loss=0.2337, pruned_loss=0.02945, over 7290.00 frames.], tot_loss[loss=0.1586, simple_loss=0.25, pruned_loss=0.03355, over 1423193.95 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:41:51,841 INFO [train.py:812] (2/8) Epoch 24, batch 3800, loss[loss=0.1293, simple_loss=0.2207, pruned_loss=0.01899, over 7442.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2483, pruned_loss=0.03275, over 1424733.70 frames.], batch size: 20, lr: 3.22e-04
+2022-05-15 07:42:51,208 INFO [train.py:812] (2/8) Epoch 24, batch 3850, loss[loss=0.1644, simple_loss=0.2581, pruned_loss=0.03535, over 4317.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2486, pruned_loss=0.03319, over 1420278.74 frames.], batch size: 52, lr: 3.22e-04
+2022-05-15 07:43:50,740 INFO [train.py:812] (2/8) Epoch 24, batch 3900, loss[loss=0.165, simple_loss=0.2616, pruned_loss=0.03419, over 6690.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2484, pruned_loss=0.03324, over 1417092.24 frames.], batch size: 31, lr: 3.22e-04
+2022-05-15 07:44:49,670 INFO [train.py:812] (2/8) Epoch 24, batch 3950, loss[loss=0.1449, simple_loss=0.2301, pruned_loss=0.02988, over 7140.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2486, pruned_loss=0.03305, over 1416863.22 frames.], batch size: 17, lr: 3.22e-04
+2022-05-15 07:45:48,718 INFO [train.py:812] (2/8) Epoch 24, batch 4000, loss[loss=0.1482, simple_loss=0.2424, pruned_loss=0.02698, over 7207.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2484, pruned_loss=0.03291, over 1414793.03 frames.], batch size: 22, lr: 3.22e-04
+2022-05-15 07:46:47,066 INFO [train.py:812] (2/8) Epoch 24, batch 4050, loss[loss=0.163, simple_loss=0.2487, pruned_loss=0.03867, over 5119.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2484, pruned_loss=0.03289, over 1415689.21 frames.], batch size: 52, lr: 3.22e-04
+2022-05-15 07:47:46,725 INFO [train.py:812] (2/8) Epoch 24, batch 4100, loss[loss=0.1395, simple_loss=0.2261, pruned_loss=0.02646, over 7290.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2485, pruned_loss=0.03312, over 1416124.19 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:48:45,769 INFO [train.py:812] (2/8) Epoch 24, batch 4150, loss[loss=0.1544, simple_loss=0.2392, pruned_loss=0.03481, over 6991.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03355, over 1417888.87 frames.], batch size: 16, lr: 3.22e-04
+2022-05-15 07:49:44,880 INFO [train.py:812] (2/8) Epoch 24, batch 4200, loss[loss=0.1386, simple_loss=0.2225, pruned_loss=0.02734, over 7280.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2495, pruned_loss=0.03393, over 1418371.01 frames.], batch size: 18, lr: 3.22e-04
+2022-05-15 07:50:44,110 INFO [train.py:812] (2/8) Epoch 24, batch 4250, loss[loss=0.1695, simple_loss=0.2635, pruned_loss=0.0378, over 7363.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2494, pruned_loss=0.03369, over 1415932.61 frames.], batch size: 23, lr: 3.22e-04
+2022-05-15 07:51:43,361 INFO [train.py:812] (2/8) Epoch 24, batch 4300, loss[loss=0.1464, simple_loss=0.2281, pruned_loss=0.03235, over 6741.00 frames.], tot_loss[loss=0.158, simple_loss=0.2487, pruned_loss=0.03363, over 1415154.84 frames.], batch size: 15, lr: 3.21e-04
+2022-05-15 07:52:41,809 INFO [train.py:812] (2/8) Epoch 24, batch 4350, loss[loss=0.1759, simple_loss=0.2625, pruned_loss=0.04467, over 6788.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2493, pruned_loss=0.0338, over 1411941.58 frames.], batch size: 31, lr: 3.21e-04
+2022-05-15 07:53:40,607 INFO [train.py:812] (2/8) Epoch 24, batch 4400, loss[loss=0.1596, simple_loss=0.2545, pruned_loss=0.03235, over 6535.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2507, pruned_loss=0.03446, over 1407310.87 frames.], batch size: 38, lr: 3.21e-04
+2022-05-15 07:54:38,514 INFO [train.py:812] (2/8) Epoch 24, batch 4450, loss[loss=0.1557, simple_loss=0.2563, pruned_loss=0.02753, over 6252.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2498, pruned_loss=0.03405, over 1410353.09 frames.], batch size: 37, lr: 3.21e-04
+2022-05-15 07:55:37,559 INFO [train.py:812] (2/8) Epoch 24, batch 4500, loss[loss=0.1594, simple_loss=0.2603, pruned_loss=0.02928, over 6452.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2508, pruned_loss=0.03441, over 1396911.24 frames.], batch size: 38, lr: 3.21e-04
+2022-05-15 07:56:36,607 INFO [train.py:812] (2/8) Epoch 24, batch 4550, loss[loss=0.1554, simple_loss=0.2581, pruned_loss=0.02636, over 7269.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2506, pruned_loss=0.03446, over 1384586.92 frames.], batch size: 24, lr: 3.21e-04
+2022-05-15 07:57:47,750 INFO [train.py:812] (2/8) Epoch 25, batch 0, loss[loss=0.1648, simple_loss=0.2644, pruned_loss=0.0326, over 7075.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2644, pruned_loss=0.0326, over 7075.00 frames.], batch size: 18, lr: 3.15e-04
+2022-05-15 07:58:47,133 INFO [train.py:812] (2/8) Epoch 25, batch 50, loss[loss=0.1418, simple_loss=0.2266, pruned_loss=0.02857, over 7261.00 frames.], tot_loss[loss=0.163, simple_loss=0.2525, pruned_loss=0.03675, over 322394.07 frames.], batch size: 19, lr: 3.15e-04
+2022-05-15 07:59:46,784 INFO [train.py:812] (2/8) Epoch 25, batch 100, loss[loss=0.1393, simple_loss=0.2334, pruned_loss=0.02254, over 7331.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2507, pruned_loss=0.03492, over 570783.87 frames.], batch size: 20, lr: 3.15e-04
+2022-05-15 08:00:45,754 INFO [train.py:812] (2/8) Epoch 25, batch 150, loss[loss=0.1505, simple_loss=0.2481, pruned_loss=0.02651, over 7328.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2492, pruned_loss=0.03368, over 762548.90 frames.], batch size: 21, lr: 3.14e-04
+2022-05-15 08:01:45,526 INFO [train.py:812] (2/8) Epoch 25, batch 200, loss[loss=0.1598, simple_loss=0.2411, pruned_loss=0.03927, over 6762.00 frames.], tot_loss[loss=0.157, simple_loss=0.248, pruned_loss=0.03301, over 908176.88 frames.], batch size: 15, lr: 3.14e-04
+2022-05-15 08:02:44,457 INFO [train.py:812] (2/8) Epoch 25, batch 250, loss[loss=0.1535, simple_loss=0.2565, pruned_loss=0.02527, over 7237.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2476, pruned_loss=0.03241, over 1019288.99 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:03:43,957 INFO [train.py:812] (2/8) Epoch 25, batch 300, loss[loss=0.1721, simple_loss=0.2634, pruned_loss=0.04037, over 7169.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2489, pruned_loss=0.03314, over 1112414.32 frames.], batch size: 19, lr: 3.14e-04
+2022-05-15 08:04:42,717 INFO [train.py:812] (2/8) Epoch 25, batch 350, loss[loss=0.1661, simple_loss=0.2569, pruned_loss=0.03765, over 7205.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2478, pruned_loss=0.03289, over 1181922.63 frames.], batch size: 23, lr: 3.14e-04
+2022-05-15 08:05:50,917 INFO [train.py:812] (2/8) Epoch 25, batch 400, loss[loss=0.1445, simple_loss=0.2399, pruned_loss=0.02458, over 7232.00 frames.], tot_loss[loss=0.156, simple_loss=0.2473, pruned_loss=0.03239, over 1236754.82 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:06:49,140 INFO [train.py:812] (2/8) Epoch 25, batch 450, loss[loss=0.1583, simple_loss=0.2602, pruned_loss=0.02823, over 7051.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2465, pruned_loss=0.03216, over 1277468.50 frames.], batch size: 28, lr: 3.14e-04
+2022-05-15 08:07:48,546 INFO [train.py:812] (2/8) Epoch 25, batch 500, loss[loss=0.148, simple_loss=0.2301, pruned_loss=0.03293, over 7171.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2468, pruned_loss=0.03229, over 1312571.00 frames.], batch size: 18, lr: 3.14e-04
+2022-05-15 08:08:47,660 INFO [train.py:812] (2/8) Epoch 25, batch 550, loss[loss=0.1417, simple_loss=0.2341, pruned_loss=0.02464, over 7162.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2474, pruned_loss=0.03243, over 1340149.15 frames.], batch size: 18, lr: 3.14e-04
+2022-05-15 08:09:45,622 INFO [train.py:812] (2/8) Epoch 25, batch 600, loss[loss=0.1861, simple_loss=0.2722, pruned_loss=0.05001, over 7189.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2479, pruned_loss=0.03264, over 1359094.86 frames.], batch size: 23, lr: 3.14e-04
+2022-05-15 08:10:45,003 INFO [train.py:812] (2/8) Epoch 25, batch 650, loss[loss=0.1414, simple_loss=0.2251, pruned_loss=0.0289, over 7256.00 frames.], tot_loss[loss=0.156, simple_loss=0.2468, pruned_loss=0.03255, over 1372274.34 frames.], batch size: 17, lr: 3.14e-04
+2022-05-15 08:11:43,846 INFO [train.py:812] (2/8) Epoch 25, batch 700, loss[loss=0.1444, simple_loss=0.2262, pruned_loss=0.03137, over 6830.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2466, pruned_loss=0.03239, over 1387845.91 frames.], batch size: 15, lr: 3.14e-04
+2022-05-15 08:12:43,012 INFO [train.py:812] (2/8) Epoch 25, batch 750, loss[loss=0.1595, simple_loss=0.2494, pruned_loss=0.03481, over 7230.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2474, pruned_loss=0.03238, over 1398903.59 frames.], batch size: 20, lr: 3.14e-04
+2022-05-15 08:13:42,683 INFO [train.py:812] (2/8) Epoch 25, batch 800, loss[loss=0.1629, simple_loss=0.2501, pruned_loss=0.03781, over 7417.00 frames.], tot_loss[loss=0.157, simple_loss=0.2482, pruned_loss=0.03293, over 1405733.86 frames.], batch size: 21, lr: 3.14e-04
+2022-05-15 08:14:42,179 INFO [train.py:812] (2/8) Epoch 25, batch 850, loss[loss=0.1665, simple_loss=0.2609, pruned_loss=0.03609, over 7323.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2484, pruned_loss=0.03306, over 1407476.06 frames.], batch size: 21, lr: 3.13e-04
+2022-05-15 08:15:39,808 INFO [train.py:812] (2/8) Epoch 25, batch 900, loss[loss=0.1955, simple_loss=0.2843, pruned_loss=0.05336, over 7256.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2493, pruned_loss=0.03371, over 1410056.82 frames.], batch size: 25, lr: 3.13e-04
+2022-05-15 08:16:38,341 INFO [train.py:812] (2/8) Epoch 25, batch 950, loss[loss=0.1933, simple_loss=0.2747, pruned_loss=0.056, over 5339.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2493, pruned_loss=0.03377, over 1404924.95 frames.], batch size: 52, lr: 3.13e-04
+2022-05-15 08:17:38,345 INFO [train.py:812] (2/8) Epoch 25, batch 1000, loss[loss=0.1861, simple_loss=0.2724, pruned_loss=0.04991, over 7416.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2491, pruned_loss=0.03359, over 1411770.69 frames.], batch size: 21, lr: 3.13e-04
+2022-05-15 08:18:37,745 INFO [train.py:812] (2/8) Epoch 25, batch 1050, loss[loss=0.1446, simple_loss=0.2408, pruned_loss=0.02414, over 7324.00 frames.], tot_loss[loss=0.1577, simple_loss=0.249, pruned_loss=0.03325, over 1418587.17 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:19:35,298 INFO [train.py:812] (2/8) Epoch 25, batch 1100, loss[loss=0.1453, simple_loss=0.2384, pruned_loss=0.02607, over 7335.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2483, pruned_loss=0.03305, over 1421453.94 frames.], batch size: 22, lr: 3.13e-04
+2022-05-15 08:20:32,124 INFO [train.py:812] (2/8) Epoch 25, batch 1150, loss[loss=0.1813, simple_loss=0.2862, pruned_loss=0.03816, over 7200.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2488, pruned_loss=0.03319, over 1424658.79 frames.], batch size: 23, lr: 3.13e-04
+2022-05-15 08:21:31,790 INFO [train.py:812] (2/8) Epoch 25, batch 1200, loss[loss=0.155, simple_loss=0.2437, pruned_loss=0.03316, over 7369.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2483, pruned_loss=0.03305, over 1424241.57 frames.], batch size: 23, lr: 3.13e-04
+2022-05-15 08:22:29,883 INFO [train.py:812] (2/8) Epoch 25, batch 1250, loss[loss=0.1451, simple_loss=0.2433, pruned_loss=0.02342, over 7141.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2483, pruned_loss=0.03333, over 1423224.42 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:23:28,189 INFO [train.py:812] (2/8) Epoch 25, batch 1300, loss[loss=0.1453, simple_loss=0.2294, pruned_loss=0.03058, over 7217.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2491, pruned_loss=0.03393, over 1421516.49 frames.], batch size: 16, lr: 3.13e-04
+2022-05-15 08:24:27,594 INFO [train.py:812] (2/8) Epoch 25, batch 1350, loss[loss=0.1556, simple_loss=0.2489, pruned_loss=0.03117, over 6494.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2491, pruned_loss=0.03404, over 1421377.27 frames.], batch size: 38, lr: 3.13e-04
+2022-05-15 08:25:27,048 INFO [train.py:812] (2/8) Epoch 25, batch 1400, loss[loss=0.138, simple_loss=0.2205, pruned_loss=0.02779, over 7260.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2497, pruned_loss=0.03384, over 1426283.77 frames.], batch size: 17, lr: 3.13e-04
+2022-05-15 08:26:26,000 INFO [train.py:812] (2/8) Epoch 25, batch 1450, loss[loss=0.1682, simple_loss=0.2638, pruned_loss=0.03627, over 7147.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2497, pruned_loss=0.03399, over 1421772.20 frames.], batch size: 20, lr: 3.13e-04
+2022-05-15 08:27:24,396 INFO [train.py:812] (2/8) Epoch 25, batch 1500, loss[loss=0.1362, simple_loss=0.2285, pruned_loss=0.02194, over 6902.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2495, pruned_loss=0.03374, over 1420965.20 frames.], batch size: 32, lr: 3.13e-04
+2022-05-15 08:28:23,166 INFO [train.py:812] (2/8) Epoch 25, batch 1550, loss[loss=0.1542, simple_loss=0.2448, pruned_loss=0.03178, over 7276.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2494, pruned_loss=0.03339, over 1422232.46 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:29:22,833 INFO [train.py:812] (2/8) Epoch 25, batch 1600, loss[loss=0.1477, simple_loss=0.2338, pruned_loss=0.03084, over 6782.00 frames.], tot_loss[loss=0.159, simple_loss=0.2502, pruned_loss=0.03388, over 1420802.14 frames.], batch size: 15, lr: 3.12e-04
+2022-05-15 08:30:21,979 INFO [train.py:812] (2/8) Epoch 25, batch 1650, loss[loss=0.1781, simple_loss=0.269, pruned_loss=0.04356, over 7217.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2495, pruned_loss=0.03373, over 1421737.38 frames.], batch size: 21, lr: 3.12e-04
+2022-05-15 08:31:21,074 INFO [train.py:812] (2/8) Epoch 25, batch 1700, loss[loss=0.1506, simple_loss=0.2382, pruned_loss=0.03154, over 7347.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2484, pruned_loss=0.03327, over 1420602.46 frames.], batch size: 23, lr: 3.12e-04
+2022-05-15 08:32:19,159 INFO [train.py:812] (2/8) Epoch 25, batch 1750, loss[loss=0.1363, simple_loss=0.2176, pruned_loss=0.02747, over 7158.00 frames.], tot_loss[loss=0.157, simple_loss=0.2482, pruned_loss=0.03291, over 1423530.52 frames.], batch size: 17, lr: 3.12e-04
+2022-05-15 08:33:18,561 INFO [train.py:812] (2/8) Epoch 25, batch 1800, loss[loss=0.1288, simple_loss=0.2102, pruned_loss=0.02365, over 6996.00 frames.], tot_loss[loss=0.1568, simple_loss=0.248, pruned_loss=0.03281, over 1423284.75 frames.], batch size: 16, lr: 3.12e-04
+2022-05-15 08:34:17,299 INFO [train.py:812] (2/8) Epoch 25, batch 1850, loss[loss=0.1278, simple_loss=0.2112, pruned_loss=0.02219, over 6801.00 frames.], tot_loss[loss=0.156, simple_loss=0.247, pruned_loss=0.0325, over 1419748.47 frames.], batch size: 15, lr: 3.12e-04
+2022-05-15 08:35:20,955 INFO [train.py:812] (2/8) Epoch 25, batch 1900, loss[loss=0.1789, simple_loss=0.2742, pruned_loss=0.04176, over 7291.00 frames.], tot_loss[loss=0.157, simple_loss=0.2477, pruned_loss=0.03311, over 1422087.68 frames.], batch size: 25, lr: 3.12e-04
+2022-05-15 08:36:19,615 INFO [train.py:812] (2/8) Epoch 25, batch 1950, loss[loss=0.1597, simple_loss=0.2457, pruned_loss=0.03681, over 7259.00 frames.], tot_loss[loss=0.157, simple_loss=0.2475, pruned_loss=0.0332, over 1424671.35 frames.], batch size: 19, lr: 3.12e-04
+2022-05-15 08:37:18,258 INFO [train.py:812] (2/8) Epoch 25, batch 2000, loss[loss=0.1572, simple_loss=0.2517, pruned_loss=0.03137, over 7150.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2473, pruned_loss=0.03304, over 1425132.93 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:38:16,615 INFO [train.py:812] (2/8) Epoch 25, batch 2050, loss[loss=0.1879, simple_loss=0.2872, pruned_loss=0.04425, over 7308.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2467, pruned_loss=0.0324, over 1428156.19 frames.], batch size: 21, lr: 3.12e-04
+2022-05-15 08:39:15,895 INFO [train.py:812] (2/8) Epoch 25, batch 2100, loss[loss=0.1546, simple_loss=0.2351, pruned_loss=0.03704, over 7264.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2464, pruned_loss=0.03211, over 1424650.70 frames.], batch size: 19, lr: 3.12e-04
+2022-05-15 08:40:13,636 INFO [train.py:812] (2/8) Epoch 25, batch 2150, loss[loss=0.1471, simple_loss=0.2395, pruned_loss=0.02734, over 7425.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2466, pruned_loss=0.03213, over 1423423.21 frames.], batch size: 20, lr: 3.12e-04
+2022-05-15 08:41:13,377 INFO [train.py:812] (2/8) Epoch 25, batch 2200, loss[loss=0.1404, simple_loss=0.2181, pruned_loss=0.03134, over 6742.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2454, pruned_loss=0.03191, over 1421914.82 frames.], batch size: 15, lr: 3.12e-04
+2022-05-15 08:42:11,782 INFO [train.py:812] (2/8) Epoch 25, batch 2250, loss[loss=0.1444, simple_loss=0.2288, pruned_loss=0.02999, over 7072.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2458, pruned_loss=0.03216, over 1417673.00 frames.], batch size: 18, lr: 3.12e-04
+2022-05-15 08:43:09,218 INFO [train.py:812] (2/8) Epoch 25, batch 2300, loss[loss=0.147, simple_loss=0.227, pruned_loss=0.03353, over 6748.00 frames.], tot_loss[loss=0.155, simple_loss=0.2458, pruned_loss=0.03211, over 1418643.96 frames.], batch size: 15, lr: 3.11e-04
+2022-05-15 08:44:06,013 INFO [train.py:812] (2/8) Epoch 25, batch 2350, loss[loss=0.1439, simple_loss=0.247, pruned_loss=0.02036, over 7314.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2464, pruned_loss=0.03209, over 1418807.74 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:45:05,375 INFO [train.py:812] (2/8) Epoch 25, batch 2400, loss[loss=0.1482, simple_loss=0.2333, pruned_loss=0.03153, over 7348.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2481, pruned_loss=0.03282, over 1423208.96 frames.], batch size: 19, lr: 3.11e-04
+2022-05-15 08:46:04,719 INFO [train.py:812] (2/8) Epoch 25, batch 2450, loss[loss=0.1591, simple_loss=0.2331, pruned_loss=0.04261, over 7136.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2486, pruned_loss=0.03263, over 1422246.17 frames.], batch size: 17, lr: 3.11e-04
+2022-05-15 08:47:04,442 INFO [train.py:812] (2/8) Epoch 25, batch 2500, loss[loss=0.1573, simple_loss=0.2606, pruned_loss=0.02704, over 7403.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2476, pruned_loss=0.03245, over 1422284.84 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:48:03,453 INFO [train.py:812] (2/8) Epoch 25, batch 2550, loss[loss=0.1435, simple_loss=0.2325, pruned_loss=0.02722, over 7423.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2481, pruned_loss=0.03263, over 1423096.55 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:49:03,056 INFO [train.py:812] (2/8) Epoch 25, batch 2600, loss[loss=0.1487, simple_loss=0.2293, pruned_loss=0.03404, over 7150.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.03259, over 1420782.91 frames.], batch size: 17, lr: 3.11e-04
+2022-05-15 08:50:01,831 INFO [train.py:812] (2/8) Epoch 25, batch 2650, loss[loss=0.168, simple_loss=0.2667, pruned_loss=0.03467, over 7199.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2489, pruned_loss=0.03309, over 1422759.31 frames.], batch size: 22, lr: 3.11e-04
+2022-05-15 08:51:09,485 INFO [train.py:812] (2/8) Epoch 25, batch 2700, loss[loss=0.1647, simple_loss=0.2565, pruned_loss=0.03645, over 7074.00 frames.], tot_loss[loss=0.157, simple_loss=0.2484, pruned_loss=0.03284, over 1424971.75 frames.], batch size: 18, lr: 3.11e-04
+2022-05-15 08:52:06,973 INFO [train.py:812] (2/8) Epoch 25, batch 2750, loss[loss=0.1461, simple_loss=0.2423, pruned_loss=0.02498, over 7145.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03289, over 1419881.80 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:53:06,564 INFO [train.py:812] (2/8) Epoch 25, batch 2800, loss[loss=0.1728, simple_loss=0.2551, pruned_loss=0.04525, over 7252.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2473, pruned_loss=0.03295, over 1421245.74 frames.], batch size: 19, lr: 3.11e-04
+2022-05-15 08:54:05,514 INFO [train.py:812] (2/8) Epoch 25, batch 2850, loss[loss=0.153, simple_loss=0.248, pruned_loss=0.02906, over 7423.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2469, pruned_loss=0.03298, over 1419219.76 frames.], batch size: 20, lr: 3.11e-04
+2022-05-15 08:55:04,641 INFO [train.py:812] (2/8) Epoch 25, batch 2900, loss[loss=0.1894, simple_loss=0.28, pruned_loss=0.04939, over 7194.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2482, pruned_loss=0.03344, over 1419656.32 frames.], batch size: 23, lr: 3.11e-04
+2022-05-15 08:56:02,079 INFO [train.py:812] (2/8) Epoch 25, batch 2950, loss[loss=0.1611, simple_loss=0.2521, pruned_loss=0.03507, over 7116.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2481, pruned_loss=0.0329, over 1425003.63 frames.], batch size: 21, lr: 3.11e-04
+2022-05-15 08:57:29,073 INFO [train.py:812] (2/8) Epoch 25, batch 3000, loss[loss=0.1641, simple_loss=0.2605, pruned_loss=0.03389, over 6896.00 frames.], tot_loss[loss=0.156, simple_loss=0.2471, pruned_loss=0.03241, over 1428406.00 frames.], batch size: 31, lr: 3.10e-04
+2022-05-15 08:57:29,075 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 08:57:46,643 INFO [train.py:841] (2/8) Epoch 25, validation: loss=0.1532, simple_loss=0.2507, pruned_loss=0.02787, over 698248.00 frames.
+2022-05-15 08:58:45,927 INFO [train.py:812] (2/8) Epoch 25, batch 3050, loss[loss=0.1667, simple_loss=0.2726, pruned_loss=0.03036, over 7113.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03251, over 1428593.14 frames.], batch size: 21, lr: 3.10e-04
+2022-05-15 08:59:53,864 INFO [train.py:812] (2/8) Epoch 25, batch 3100, loss[loss=0.1506, simple_loss=0.2295, pruned_loss=0.03582, over 6773.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2462, pruned_loss=0.03227, over 1429522.80 frames.], batch size: 15, lr: 3.10e-04
+2022-05-15 09:01:01,452 INFO [train.py:812] (2/8) Epoch 25, batch 3150, loss[loss=0.1382, simple_loss=0.2273, pruned_loss=0.02451, over 7270.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03263, over 1431257.29 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:02:01,440 INFO [train.py:812] (2/8) Epoch 25, batch 3200, loss[loss=0.1511, simple_loss=0.2424, pruned_loss=0.02985, over 4982.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2473, pruned_loss=0.03275, over 1429456.04 frames.], batch size: 53, lr: 3.10e-04
+2022-05-15 09:03:00,349 INFO [train.py:812] (2/8) Epoch 25, batch 3250, loss[loss=0.1673, simple_loss=0.2573, pruned_loss=0.03864, over 7239.00 frames.], tot_loss[loss=0.157, simple_loss=0.2477, pruned_loss=0.03313, over 1427107.17 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:03:59,273 INFO [train.py:812] (2/8) Epoch 25, batch 3300, loss[loss=0.1278, simple_loss=0.2125, pruned_loss=0.02158, over 7163.00 frames.], tot_loss[loss=0.157, simple_loss=0.2479, pruned_loss=0.0331, over 1426512.19 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:04:58,476 INFO [train.py:812] (2/8) Epoch 25, batch 3350, loss[loss=0.146, simple_loss=0.2308, pruned_loss=0.03064, over 7260.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2475, pruned_loss=0.03273, over 1423608.37 frames.], batch size: 19, lr: 3.10e-04
+2022-05-15 09:05:57,548 INFO [train.py:812] (2/8) Epoch 25, batch 3400, loss[loss=0.1409, simple_loss=0.2252, pruned_loss=0.02824, over 7275.00 frames.], tot_loss[loss=0.1565, simple_loss=0.247, pruned_loss=0.033, over 1424838.71 frames.], batch size: 17, lr: 3.10e-04
+2022-05-15 09:06:55,962 INFO [train.py:812] (2/8) Epoch 25, batch 3450, loss[loss=0.1506, simple_loss=0.253, pruned_loss=0.0241, over 7226.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2469, pruned_loss=0.03273, over 1421184.69 frames.], batch size: 21, lr: 3.10e-04
+2022-05-15 09:07:54,091 INFO [train.py:812] (2/8) Epoch 25, batch 3500, loss[loss=0.1471, simple_loss=0.2334, pruned_loss=0.03038, over 7128.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2468, pruned_loss=0.03298, over 1422354.30 frames.], batch size: 17, lr: 3.10e-04
+2022-05-15 09:08:53,536 INFO [train.py:812] (2/8) Epoch 25, batch 3550, loss[loss=0.1668, simple_loss=0.2663, pruned_loss=0.0336, over 7326.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2476, pruned_loss=0.03317, over 1424056.80 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:09:52,741 INFO [train.py:812] (2/8) Epoch 25, batch 3600, loss[loss=0.2067, simple_loss=0.2907, pruned_loss=0.0614, over 7199.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2487, pruned_loss=0.0334, over 1421904.40 frames.], batch size: 23, lr: 3.10e-04
+2022-05-15 09:10:51,741 INFO [train.py:812] (2/8) Epoch 25, batch 3650, loss[loss=0.1778, simple_loss=0.2702, pruned_loss=0.04277, over 6425.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2484, pruned_loss=0.03332, over 1417435.11 frames.], batch size: 37, lr: 3.10e-04
+2022-05-15 09:11:51,326 INFO [train.py:812] (2/8) Epoch 25, batch 3700, loss[loss=0.158, simple_loss=0.2468, pruned_loss=0.03455, over 7426.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2473, pruned_loss=0.03288, over 1420860.71 frames.], batch size: 20, lr: 3.10e-04
+2022-05-15 09:12:50,558 INFO [train.py:812] (2/8) Epoch 25, batch 3750, loss[loss=0.1714, simple_loss=0.2633, pruned_loss=0.03977, over 7373.00 frames.], tot_loss[loss=0.1572, simple_loss=0.248, pruned_loss=0.03321, over 1423195.13 frames.], batch size: 23, lr: 3.09e-04
+2022-05-15 09:13:50,183 INFO [train.py:812] (2/8) Epoch 25, batch 3800, loss[loss=0.1793, simple_loss=0.2626, pruned_loss=0.04798, over 5281.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2483, pruned_loss=0.03342, over 1422746.92 frames.], batch size: 53, lr: 3.09e-04
+2022-05-15 09:14:48,002 INFO [train.py:812] (2/8) Epoch 25, batch 3850, loss[loss=0.1481, simple_loss=0.2369, pruned_loss=0.02971, over 7291.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03321, over 1422557.09 frames.], batch size: 18, lr: 3.09e-04
+2022-05-15 09:15:47,046 INFO [train.py:812] (2/8) Epoch 25, batch 3900, loss[loss=0.1543, simple_loss=0.2373, pruned_loss=0.03566, over 7256.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2485, pruned_loss=0.0331, over 1422339.01 frames.], batch size: 19, lr: 3.09e-04
+2022-05-15 09:16:44,713 INFO [train.py:812] (2/8) Epoch 25, batch 3950, loss[loss=0.1427, simple_loss=0.2226, pruned_loss=0.03146, over 7425.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2486, pruned_loss=0.03309, over 1424323.56 frames.], batch size: 18, lr: 3.09e-04
+2022-05-15 09:17:43,597 INFO [train.py:812] (2/8) Epoch 25, batch 4000, loss[loss=0.1684, simple_loss=0.2636, pruned_loss=0.0366, over 7324.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2488, pruned_loss=0.03304, over 1423511.56 frames.], batch size: 21, lr: 3.09e-04
+2022-05-15 09:18:42,643 INFO [train.py:812] (2/8) Epoch 25, batch 4050, loss[loss=0.1463, simple_loss=0.2418, pruned_loss=0.02543, over 7428.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2487, pruned_loss=0.03309, over 1421939.15 frames.], batch size: 20, lr: 3.09e-04
+2022-05-15 09:19:41,940 INFO [train.py:812] (2/8) Epoch 25, batch 4100, loss[loss=0.1643, simple_loss=0.2549, pruned_loss=0.03688, over 6588.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2487, pruned_loss=0.03288, over 1423500.89 frames.], batch size: 38, lr: 3.09e-04
+2022-05-15 09:20:41,047 INFO [train.py:812] (2/8) Epoch 25, batch 4150, loss[loss=0.1529, simple_loss=0.2416, pruned_loss=0.03208, over 7216.00 frames.], tot_loss[loss=0.157, simple_loss=0.2484, pruned_loss=0.0328, over 1419400.20 frames.], batch size: 21, lr: 3.09e-04
+2022-05-15 09:21:39,850 INFO [train.py:812] (2/8) Epoch 25, batch 4200, loss[loss=0.1754, simple_loss=0.2696, pruned_loss=0.04059, over 7211.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2497, pruned_loss=0.03287, over 1420808.89 frames.], batch size: 23, lr: 3.09e-04
+2022-05-15 09:22:38,434 INFO [train.py:812] (2/8) Epoch 25, batch 4250, loss[loss=0.1981, simple_loss=0.2835, pruned_loss=0.05637, over 6479.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2491, pruned_loss=0.03292, over 1415389.68 frames.], batch size: 38, lr: 3.09e-04
+2022-05-15 09:23:37,030 INFO [train.py:812] (2/8) Epoch 25, batch 4300, loss[loss=0.1541, simple_loss=0.2471, pruned_loss=0.03057, over 7156.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2488, pruned_loss=0.03312, over 1414617.97 frames.], batch size: 19, lr: 3.09e-04
+2022-05-15 09:24:36,222 INFO [train.py:812] (2/8) Epoch 25, batch 4350, loss[loss=0.158, simple_loss=0.2539, pruned_loss=0.03108, over 7277.00 frames.], tot_loss[loss=0.157, simple_loss=0.2479, pruned_loss=0.03305, over 1415512.20 frames.], batch size: 25, lr: 3.09e-04
+2022-05-15 09:25:35,434 INFO [train.py:812] (2/8) Epoch 25, batch 4400, loss[loss=0.1675, simple_loss=0.2682, pruned_loss=0.03343, over 7281.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2486, pruned_loss=0.0331, over 1413968.72 frames.], batch size: 24, lr: 3.09e-04
+2022-05-15 09:26:34,092 INFO [train.py:812] (2/8) Epoch 25, batch 4450, loss[loss=0.164, simple_loss=0.2617, pruned_loss=0.03313, over 7304.00 frames.], tot_loss[loss=0.158, simple_loss=0.2495, pruned_loss=0.03321, over 1404465.15 frames.], batch size: 25, lr: 3.09e-04
+2022-05-15 09:27:33,017 INFO [train.py:812] (2/8) Epoch 25, batch 4500, loss[loss=0.1782, simple_loss=0.2614, pruned_loss=0.04746, over 4940.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2511, pruned_loss=0.03416, over 1388315.15 frames.], batch size: 52, lr: 3.08e-04
+2022-05-15 09:28:30,322 INFO [train.py:812] (2/8) Epoch 25, batch 4550, loss[loss=0.1922, simple_loss=0.272, pruned_loss=0.05616, over 5287.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2521, pruned_loss=0.03446, over 1350073.09 frames.], batch size: 55, lr: 3.08e-04
+2022-05-15 09:29:36,546 INFO [train.py:812] (2/8) Epoch 26, batch 0, loss[loss=0.1714, simple_loss=0.2704, pruned_loss=0.03621, over 7208.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2704, pruned_loss=0.03621, over 7208.00 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:30:35,851 INFO [train.py:812] (2/8) Epoch 26, batch 50, loss[loss=0.1516, simple_loss=0.2523, pruned_loss=0.02544, over 7320.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2449, pruned_loss=0.03092, over 322871.13 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:31:35,514 INFO [train.py:812] (2/8) Epoch 26, batch 100, loss[loss=0.19, simple_loss=0.2651, pruned_loss=0.05744, over 4792.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2477, pruned_loss=0.0317, over 566715.63 frames.], batch size: 52, lr: 3.02e-04
+2022-05-15 09:32:35,331 INFO [train.py:812] (2/8) Epoch 26, batch 150, loss[loss=0.1517, simple_loss=0.2364, pruned_loss=0.03352, over 7275.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2494, pruned_loss=0.03274, over 760354.77 frames.], batch size: 17, lr: 3.02e-04
+2022-05-15 09:33:34,900 INFO [train.py:812] (2/8) Epoch 26, batch 200, loss[loss=0.174, simple_loss=0.2606, pruned_loss=0.04372, over 7390.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2469, pruned_loss=0.03167, over 907076.82 frames.], batch size: 23, lr: 3.02e-04
+2022-05-15 09:34:32,549 INFO [train.py:812] (2/8) Epoch 26, batch 250, loss[loss=0.1484, simple_loss=0.2416, pruned_loss=0.02757, over 7210.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.03232, over 1019767.59 frames.], batch size: 22, lr: 3.02e-04
+2022-05-15 09:35:31,862 INFO [train.py:812] (2/8) Epoch 26, batch 300, loss[loss=0.1293, simple_loss=0.221, pruned_loss=0.0188, over 7328.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2482, pruned_loss=0.03248, over 1106150.88 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:36:29,848 INFO [train.py:812] (2/8) Epoch 26, batch 350, loss[loss=0.1497, simple_loss=0.2439, pruned_loss=0.02779, over 7162.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2472, pruned_loss=0.03235, over 1175898.11 frames.], batch size: 18, lr: 3.02e-04
+2022-05-15 09:37:29,641 INFO [train.py:812] (2/8) Epoch 26, batch 400, loss[loss=0.1238, simple_loss=0.2104, pruned_loss=0.01862, over 7409.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2478, pruned_loss=0.0325, over 1233210.92 frames.], batch size: 18, lr: 3.02e-04
+2022-05-15 09:38:28,199 INFO [train.py:812] (2/8) Epoch 26, batch 450, loss[loss=0.1628, simple_loss=0.2614, pruned_loss=0.03212, over 7408.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2468, pruned_loss=0.03205, over 1273967.94 frames.], batch size: 21, lr: 3.02e-04
+2022-05-15 09:39:25,647 INFO [train.py:812] (2/8) Epoch 26, batch 500, loss[loss=0.1861, simple_loss=0.276, pruned_loss=0.04811, over 7370.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2476, pruned_loss=0.03243, over 1302201.44 frames.], batch size: 23, lr: 3.02e-04
+2022-05-15 09:40:22,333 INFO [train.py:812] (2/8) Epoch 26, batch 550, loss[loss=0.1675, simple_loss=0.2664, pruned_loss=0.03426, over 7238.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2464, pruned_loss=0.03229, over 1328582.31 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:41:20,607 INFO [train.py:812] (2/8) Epoch 26, batch 600, loss[loss=0.1693, simple_loss=0.2548, pruned_loss=0.04186, over 7101.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2467, pruned_loss=0.03243, over 1347433.07 frames.], batch size: 28, lr: 3.02e-04
+2022-05-15 09:42:19,344 INFO [train.py:812] (2/8) Epoch 26, batch 650, loss[loss=0.1456, simple_loss=0.2405, pruned_loss=0.02535, over 7333.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2456, pruned_loss=0.03198, over 1362215.33 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:43:17,904 INFO [train.py:812] (2/8) Epoch 26, batch 700, loss[loss=0.1451, simple_loss=0.2388, pruned_loss=0.02564, over 7143.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2462, pruned_loss=0.03227, over 1374664.21 frames.], batch size: 20, lr: 3.02e-04
+2022-05-15 09:44:17,493 INFO [train.py:812] (2/8) Epoch 26, batch 750, loss[loss=0.1465, simple_loss=0.2385, pruned_loss=0.02726, over 7429.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2469, pruned_loss=0.03248, over 1389751.77 frames.], batch size: 20, lr: 3.01e-04
+2022-05-15 09:45:17,283 INFO [train.py:812] (2/8) Epoch 26, batch 800, loss[loss=0.1718, simple_loss=0.2636, pruned_loss=0.04002, over 6772.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03255, over 1394576.95 frames.], batch size: 31, lr: 3.01e-04
+2022-05-15 09:46:14,827 INFO [train.py:812] (2/8) Epoch 26, batch 850, loss[loss=0.1485, simple_loss=0.2411, pruned_loss=0.0279, over 7112.00 frames.], tot_loss[loss=0.156, simple_loss=0.2474, pruned_loss=0.0323, over 1405214.06 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:47:13,158 INFO [train.py:812] (2/8) Epoch 26, batch 900, loss[loss=0.1304, simple_loss=0.2157, pruned_loss=0.02255, over 6788.00 frames.], tot_loss[loss=0.156, simple_loss=0.2472, pruned_loss=0.03239, over 1405620.16 frames.], batch size: 15, lr: 3.01e-04
+2022-05-15 09:48:12,073 INFO [train.py:812] (2/8) Epoch 26, batch 950, loss[loss=0.1289, simple_loss=0.2097, pruned_loss=0.02407, over 7289.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2474, pruned_loss=0.03208, over 1412288.40 frames.], batch size: 17, lr: 3.01e-04
+2022-05-15 09:49:11,032 INFO [train.py:812] (2/8) Epoch 26, batch 1000, loss[loss=0.1749, simple_loss=0.2725, pruned_loss=0.03867, over 7122.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2479, pruned_loss=0.0322, over 1412041.20 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:50:10,501 INFO [train.py:812] (2/8) Epoch 26, batch 1050, loss[loss=0.1569, simple_loss=0.2497, pruned_loss=0.03211, over 5180.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2483, pruned_loss=0.03236, over 1412754.81 frames.], batch size: 52, lr: 3.01e-04
+2022-05-15 09:51:08,589 INFO [train.py:812] (2/8) Epoch 26, batch 1100, loss[loss=0.1617, simple_loss=0.2568, pruned_loss=0.03326, over 7110.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2488, pruned_loss=0.03252, over 1414266.64 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:52:08,139 INFO [train.py:812] (2/8) Epoch 26, batch 1150, loss[loss=0.1781, simple_loss=0.2716, pruned_loss=0.04224, over 7378.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2483, pruned_loss=0.03231, over 1418364.92 frames.], batch size: 23, lr: 3.01e-04
+2022-05-15 09:53:08,261 INFO [train.py:812] (2/8) Epoch 26, batch 1200, loss[loss=0.1387, simple_loss=0.2227, pruned_loss=0.02733, over 7134.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03251, over 1422197.70 frames.], batch size: 17, lr: 3.01e-04
+2022-05-15 09:54:07,379 INFO [train.py:812] (2/8) Epoch 26, batch 1250, loss[loss=0.1622, simple_loss=0.2538, pruned_loss=0.03534, over 7319.00 frames.], tot_loss[loss=0.157, simple_loss=0.2485, pruned_loss=0.03275, over 1423883.50 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:55:11,135 INFO [train.py:812] (2/8) Epoch 26, batch 1300, loss[loss=0.1602, simple_loss=0.2401, pruned_loss=0.0401, over 7435.00 frames.], tot_loss[loss=0.1569, simple_loss=0.248, pruned_loss=0.03288, over 1427565.59 frames.], batch size: 20, lr: 3.01e-04
+2022-05-15 09:56:09,542 INFO [train.py:812] (2/8) Epoch 26, batch 1350, loss[loss=0.167, simple_loss=0.2624, pruned_loss=0.03579, over 7331.00 frames.], tot_loss[loss=0.157, simple_loss=0.2482, pruned_loss=0.0329, over 1427736.73 frames.], batch size: 21, lr: 3.01e-04
+2022-05-15 09:57:07,825 INFO [train.py:812] (2/8) Epoch 26, batch 1400, loss[loss=0.164, simple_loss=0.2587, pruned_loss=0.03463, over 7342.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2481, pruned_loss=0.03285, over 1428021.18 frames.], batch size: 22, lr: 3.01e-04
+2022-05-15 09:58:05,640 INFO [train.py:812] (2/8) Epoch 26, batch 1450, loss[loss=0.1262, simple_loss=0.2102, pruned_loss=0.02115, over 7006.00 frames.], tot_loss[loss=0.1567, simple_loss=0.248, pruned_loss=0.03271, over 1429426.67 frames.], batch size: 16, lr: 3.01e-04
+2022-05-15 09:59:03,854 INFO [train.py:812] (2/8) Epoch 26, batch 1500, loss[loss=0.1409, simple_loss=0.2333, pruned_loss=0.02428, over 7216.00 frames.], tot_loss[loss=0.156, simple_loss=0.2471, pruned_loss=0.03248, over 1428997.46 frames.], batch size: 21, lr: 3.00e-04
+2022-05-15 10:00:02,488 INFO [train.py:812] (2/8) Epoch 26, batch 1550, loss[loss=0.1464, simple_loss=0.2258, pruned_loss=0.03349, over 7130.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2465, pruned_loss=0.03229, over 1428020.95 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:01:01,518 INFO [train.py:812] (2/8) Epoch 26, batch 1600, loss[loss=0.1628, simple_loss=0.2592, pruned_loss=0.03318, over 7135.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2481, pruned_loss=0.03262, over 1425355.86 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:02:00,574 INFO [train.py:812] (2/8) Epoch 26, batch 1650, loss[loss=0.153, simple_loss=0.2443, pruned_loss=0.03084, over 7085.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2466, pruned_loss=0.03218, over 1426406.79 frames.], batch size: 28, lr: 3.00e-04
+2022-05-15 10:02:59,782 INFO [train.py:812] (2/8) Epoch 26, batch 1700, loss[loss=0.164, simple_loss=0.2649, pruned_loss=0.03153, over 7315.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2472, pruned_loss=0.03217, over 1426054.24 frames.], batch size: 21, lr: 3.00e-04
+2022-05-15 10:04:07,535 INFO [train.py:812] (2/8) Epoch 26, batch 1750, loss[loss=0.1456, simple_loss=0.2293, pruned_loss=0.03095, over 7125.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2469, pruned_loss=0.03184, over 1425182.47 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:05:06,522 INFO [train.py:812] (2/8) Epoch 26, batch 1800, loss[loss=0.1534, simple_loss=0.2492, pruned_loss=0.02881, over 7145.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2468, pruned_loss=0.03185, over 1421500.62 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:06:05,264 INFO [train.py:812] (2/8) Epoch 26, batch 1850, loss[loss=0.1509, simple_loss=0.2482, pruned_loss=0.02678, over 7437.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2464, pruned_loss=0.03152, over 1422662.07 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:07:04,823 INFO [train.py:812] (2/8) Epoch 26, batch 1900, loss[loss=0.1373, simple_loss=0.2196, pruned_loss=0.02754, over 7135.00 frames.], tot_loss[loss=0.156, simple_loss=0.2477, pruned_loss=0.03214, over 1423252.08 frames.], batch size: 17, lr: 3.00e-04
+2022-05-15 10:08:02,591 INFO [train.py:812] (2/8) Epoch 26, batch 1950, loss[loss=0.1889, simple_loss=0.2723, pruned_loss=0.05279, over 4978.00 frames.], tot_loss[loss=0.156, simple_loss=0.2475, pruned_loss=0.03231, over 1420958.87 frames.], batch size: 53, lr: 3.00e-04
+2022-05-15 10:09:00,907 INFO [train.py:812] (2/8) Epoch 26, batch 2000, loss[loss=0.1371, simple_loss=0.2263, pruned_loss=0.02396, over 7162.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2471, pruned_loss=0.03252, over 1417612.37 frames.], batch size: 19, lr: 3.00e-04
+2022-05-15 10:10:00,122 INFO [train.py:812] (2/8) Epoch 26, batch 2050, loss[loss=0.167, simple_loss=0.2609, pruned_loss=0.03648, over 7320.00 frames.], tot_loss[loss=0.1559, simple_loss=0.247, pruned_loss=0.03245, over 1418625.83 frames.], batch size: 20, lr: 3.00e-04
+2022-05-15 10:10:59,274 INFO [train.py:812] (2/8) Epoch 26, batch 2100, loss[loss=0.1822, simple_loss=0.2644, pruned_loss=0.05, over 7202.00 frames.], tot_loss[loss=0.157, simple_loss=0.2483, pruned_loss=0.03285, over 1418246.36 frames.], batch size: 22, lr: 3.00e-04
+2022-05-15 10:11:58,142 INFO [train.py:812] (2/8) Epoch 26, batch 2150, loss[loss=0.1348, simple_loss=0.2277, pruned_loss=0.02091, over 7177.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2487, pruned_loss=0.0328, over 1420817.67 frames.], batch size: 18, lr: 3.00e-04
+2022-05-15 10:12:57,677 INFO [train.py:812] (2/8) Epoch 26, batch 2200, loss[loss=0.1646, simple_loss=0.2606, pruned_loss=0.03436, over 7002.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2484, pruned_loss=0.03231, over 1423096.86 frames.], batch size: 28, lr: 3.00e-04
+2022-05-15 10:13:56,438 INFO [train.py:812] (2/8) Epoch 26, batch 2250, loss[loss=0.1799, simple_loss=0.2655, pruned_loss=0.04716, over 7376.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2476, pruned_loss=0.03225, over 1425480.33 frames.], batch size: 23, lr: 3.00e-04
+2022-05-15 10:14:54,875 INFO [train.py:812] (2/8) Epoch 26, batch 2300, loss[loss=0.1477, simple_loss=0.2308, pruned_loss=0.0323, over 7059.00 frames.], tot_loss[loss=0.157, simple_loss=0.2486, pruned_loss=0.03277, over 1426001.22 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:15:54,158 INFO [train.py:812] (2/8) Epoch 26, batch 2350, loss[loss=0.1403, simple_loss=0.2274, pruned_loss=0.02664, over 7250.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2481, pruned_loss=0.0329, over 1426382.96 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:16:53,707 INFO [train.py:812] (2/8) Epoch 26, batch 2400, loss[loss=0.168, simple_loss=0.259, pruned_loss=0.03843, over 7384.00 frames.], tot_loss[loss=0.157, simple_loss=0.2479, pruned_loss=0.03307, over 1423478.34 frames.], batch size: 23, lr: 2.99e-04
+2022-05-15 10:17:52,703 INFO [train.py:812] (2/8) Epoch 26, batch 2450, loss[loss=0.1516, simple_loss=0.249, pruned_loss=0.02712, over 6679.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2477, pruned_loss=0.03293, over 1421728.29 frames.], batch size: 31, lr: 2.99e-04
+2022-05-15 10:18:50,828 INFO [train.py:812] (2/8) Epoch 26, batch 2500, loss[loss=0.1577, simple_loss=0.2474, pruned_loss=0.034, over 7351.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2465, pruned_loss=0.03252, over 1423599.16 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:19:48,017 INFO [train.py:812] (2/8) Epoch 26, batch 2550, loss[loss=0.1402, simple_loss=0.2256, pruned_loss=0.02733, over 7418.00 frames.], tot_loss[loss=0.1555, simple_loss=0.246, pruned_loss=0.03247, over 1426188.00 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:20:46,854 INFO [train.py:812] (2/8) Epoch 26, batch 2600, loss[loss=0.1488, simple_loss=0.2379, pruned_loss=0.0299, over 7164.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2459, pruned_loss=0.03218, over 1424457.34 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:21:44,648 INFO [train.py:812] (2/8) Epoch 26, batch 2650, loss[loss=0.1809, simple_loss=0.2849, pruned_loss=0.03843, over 7085.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2466, pruned_loss=0.03229, over 1420293.49 frames.], batch size: 28, lr: 2.99e-04
+2022-05-15 10:22:43,728 INFO [train.py:812] (2/8) Epoch 26, batch 2700, loss[loss=0.1399, simple_loss=0.2262, pruned_loss=0.02683, over 7263.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2471, pruned_loss=0.03256, over 1420980.29 frames.], batch size: 19, lr: 2.99e-04
+2022-05-15 10:23:42,366 INFO [train.py:812] (2/8) Epoch 26, batch 2750, loss[loss=0.1938, simple_loss=0.292, pruned_loss=0.04778, over 7311.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2483, pruned_loss=0.03306, over 1413984.55 frames.], batch size: 25, lr: 2.99e-04
+2022-05-15 10:24:40,489 INFO [train.py:812] (2/8) Epoch 26, batch 2800, loss[loss=0.1525, simple_loss=0.2511, pruned_loss=0.0269, over 7274.00 frames.], tot_loss[loss=0.156, simple_loss=0.2474, pruned_loss=0.03231, over 1416326.35 frames.], batch size: 18, lr: 2.99e-04
+2022-05-15 10:25:38,076 INFO [train.py:812] (2/8) Epoch 26, batch 2850, loss[loss=0.1805, simple_loss=0.273, pruned_loss=0.04399, over 7409.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2462, pruned_loss=0.03218, over 1411397.12 frames.], batch size: 21, lr: 2.99e-04
+2022-05-15 10:26:37,768 INFO [train.py:812] (2/8) Epoch 26, batch 2900, loss[loss=0.1742, simple_loss=0.2718, pruned_loss=0.03823, over 7149.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2457, pruned_loss=0.03188, over 1417375.56 frames.], batch size: 20, lr: 2.99e-04
+2022-05-15 10:27:35,286 INFO [train.py:812] (2/8) Epoch 26, batch 2950, loss[loss=0.1413, simple_loss=0.2361, pruned_loss=0.02321, over 7326.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03178, over 1418522.12 frames.], batch size: 20, lr: 2.99e-04
+2022-05-15 10:28:33,133 INFO [train.py:812] (2/8) Epoch 26, batch 3000, loss[loss=0.1708, simple_loss=0.2734, pruned_loss=0.03411, over 6424.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2469, pruned_loss=0.0319, over 1422121.90 frames.], batch size: 38, lr: 2.99e-04
+2022-05-15 10:28:33,134 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 10:28:40,783 INFO [train.py:841] (2/8) Epoch 26, validation: loss=0.1534, simple_loss=0.2507, pruned_loss=0.02805, over 698248.00 frames.
+2022-05-15 10:29:38,824 INFO [train.py:812] (2/8) Epoch 26, batch 3050, loss[loss=0.1561, simple_loss=0.2534, pruned_loss=0.02939, over 7322.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2476, pruned_loss=0.03212, over 1421458.96 frames.], batch size: 22, lr: 2.99e-04
+2022-05-15 10:30:38,777 INFO [train.py:812] (2/8) Epoch 26, batch 3100, loss[loss=0.1412, simple_loss=0.2398, pruned_loss=0.02134, over 7270.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2478, pruned_loss=0.03243, over 1419287.00 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:31:36,291 INFO [train.py:812] (2/8) Epoch 26, batch 3150, loss[loss=0.1496, simple_loss=0.2301, pruned_loss=0.03452, over 7144.00 frames.], tot_loss[loss=0.1565, simple_loss=0.248, pruned_loss=0.03248, over 1417652.91 frames.], batch size: 17, lr: 2.98e-04
+2022-05-15 10:32:35,706 INFO [train.py:812] (2/8) Epoch 26, batch 3200, loss[loss=0.1461, simple_loss=0.2442, pruned_loss=0.02402, over 7153.00 frames.], tot_loss[loss=0.1567, simple_loss=0.248, pruned_loss=0.03269, over 1420533.13 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:33:35,123 INFO [train.py:812] (2/8) Epoch 26, batch 3250, loss[loss=0.134, simple_loss=0.224, pruned_loss=0.02203, over 7268.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2465, pruned_loss=0.03217, over 1423606.41 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:34:33,017 INFO [train.py:812] (2/8) Epoch 26, batch 3300, loss[loss=0.1533, simple_loss=0.246, pruned_loss=0.0303, over 7167.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2467, pruned_loss=0.03217, over 1416553.01 frames.], batch size: 26, lr: 2.98e-04
+2022-05-15 10:35:31,880 INFO [train.py:812] (2/8) Epoch 26, batch 3350, loss[loss=0.1729, simple_loss=0.2712, pruned_loss=0.0373, over 7327.00 frames.], tot_loss[loss=0.155, simple_loss=0.2462, pruned_loss=0.03187, over 1413890.72 frames.], batch size: 21, lr: 2.98e-04
+2022-05-15 10:36:31,836 INFO [train.py:812] (2/8) Epoch 26, batch 3400, loss[loss=0.1537, simple_loss=0.2411, pruned_loss=0.03315, over 6248.00 frames.], tot_loss[loss=0.155, simple_loss=0.2461, pruned_loss=0.03197, over 1419799.72 frames.], batch size: 38, lr: 2.98e-04
+2022-05-15 10:37:30,434 INFO [train.py:812] (2/8) Epoch 26, batch 3450, loss[loss=0.1415, simple_loss=0.2195, pruned_loss=0.03178, over 7165.00 frames.], tot_loss[loss=0.1551, simple_loss=0.246, pruned_loss=0.03207, over 1419085.94 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:38:29,756 INFO [train.py:812] (2/8) Epoch 26, batch 3500, loss[loss=0.1668, simple_loss=0.2614, pruned_loss=0.03612, over 7369.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2468, pruned_loss=0.03229, over 1418212.52 frames.], batch size: 23, lr: 2.98e-04
+2022-05-15 10:39:28,316 INFO [train.py:812] (2/8) Epoch 26, batch 3550, loss[loss=0.1416, simple_loss=0.2398, pruned_loss=0.02164, over 7429.00 frames.], tot_loss[loss=0.1552, simple_loss=0.246, pruned_loss=0.03222, over 1420436.46 frames.], batch size: 21, lr: 2.98e-04
+2022-05-15 10:40:26,263 INFO [train.py:812] (2/8) Epoch 26, batch 3600, loss[loss=0.17, simple_loss=0.2633, pruned_loss=0.03837, over 7193.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2458, pruned_loss=0.03232, over 1425047.86 frames.], batch size: 23, lr: 2.98e-04
+2022-05-15 10:41:25,808 INFO [train.py:812] (2/8) Epoch 26, batch 3650, loss[loss=0.1491, simple_loss=0.2349, pruned_loss=0.03166, over 7269.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2462, pruned_loss=0.03179, over 1426597.42 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:42:23,952 INFO [train.py:812] (2/8) Epoch 26, batch 3700, loss[loss=0.156, simple_loss=0.2459, pruned_loss=0.03301, over 7068.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2459, pruned_loss=0.03189, over 1424862.65 frames.], batch size: 18, lr: 2.98e-04
+2022-05-15 10:43:22,966 INFO [train.py:812] (2/8) Epoch 26, batch 3750, loss[loss=0.1758, simple_loss=0.2697, pruned_loss=0.0409, over 7157.00 frames.], tot_loss[loss=0.155, simple_loss=0.2461, pruned_loss=0.03191, over 1422779.41 frames.], batch size: 19, lr: 2.98e-04
+2022-05-15 10:44:21,245 INFO [train.py:812] (2/8) Epoch 26, batch 3800, loss[loss=0.1361, simple_loss=0.2277, pruned_loss=0.02225, over 6207.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2468, pruned_loss=0.03197, over 1419600.44 frames.], batch size: 37, lr: 2.98e-04
+2022-05-15 10:45:20,410 INFO [train.py:812] (2/8) Epoch 26, batch 3850, loss[loss=0.1482, simple_loss=0.2471, pruned_loss=0.02461, over 7150.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2464, pruned_loss=0.03188, over 1418323.89 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:46:19,971 INFO [train.py:812] (2/8) Epoch 26, batch 3900, loss[loss=0.1273, simple_loss=0.2178, pruned_loss=0.01844, over 7434.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2472, pruned_loss=0.03215, over 1420585.72 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:47:17,425 INFO [train.py:812] (2/8) Epoch 26, batch 3950, loss[loss=0.1613, simple_loss=0.2527, pruned_loss=0.03499, over 7239.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2473, pruned_loss=0.03246, over 1425085.91 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:48:16,825 INFO [train.py:812] (2/8) Epoch 26, batch 4000, loss[loss=0.1421, simple_loss=0.2331, pruned_loss=0.02562, over 7421.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03284, over 1417614.10 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:49:15,494 INFO [train.py:812] (2/8) Epoch 26, batch 4050, loss[loss=0.1358, simple_loss=0.2339, pruned_loss=0.01884, over 7413.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2478, pruned_loss=0.03255, over 1419365.50 frames.], batch size: 21, lr: 2.97e-04
+2022-05-15 10:50:14,946 INFO [train.py:812] (2/8) Epoch 26, batch 4100, loss[loss=0.1547, simple_loss=0.2492, pruned_loss=0.03015, over 7420.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2492, pruned_loss=0.03329, over 1417554.69 frames.], batch size: 21, lr: 2.97e-04
+2022-05-15 10:51:14,791 INFO [train.py:812] (2/8) Epoch 26, batch 4150, loss[loss=0.125, simple_loss=0.2126, pruned_loss=0.01872, over 7259.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2479, pruned_loss=0.03268, over 1423043.09 frames.], batch size: 19, lr: 2.97e-04
+2022-05-15 10:52:13,191 INFO [train.py:812] (2/8) Epoch 26, batch 4200, loss[loss=0.1408, simple_loss=0.2483, pruned_loss=0.01664, over 7135.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2479, pruned_loss=0.03278, over 1420384.90 frames.], batch size: 28, lr: 2.97e-04
+2022-05-15 10:53:19,318 INFO [train.py:812] (2/8) Epoch 26, batch 4250, loss[loss=0.1501, simple_loss=0.2296, pruned_loss=0.03528, over 7170.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03317, over 1419892.05 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:54:17,957 INFO [train.py:812] (2/8) Epoch 26, batch 4300, loss[loss=0.1539, simple_loss=0.2575, pruned_loss=0.02516, over 7211.00 frames.], tot_loss[loss=0.1571, simple_loss=0.248, pruned_loss=0.03314, over 1423014.94 frames.], batch size: 26, lr: 2.97e-04
+2022-05-15 10:55:15,904 INFO [train.py:812] (2/8) Epoch 26, batch 4350, loss[loss=0.16, simple_loss=0.2432, pruned_loss=0.03846, over 7228.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2475, pruned_loss=0.03284, over 1416213.86 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:56:15,122 INFO [train.py:812] (2/8) Epoch 26, batch 4400, loss[loss=0.155, simple_loss=0.2393, pruned_loss=0.0354, over 7067.00 frames.], tot_loss[loss=0.157, simple_loss=0.2484, pruned_loss=0.03281, over 1416145.89 frames.], batch size: 18, lr: 2.97e-04
+2022-05-15 10:57:23,158 INFO [train.py:812] (2/8) Epoch 26, batch 4450, loss[loss=0.1392, simple_loss=0.2323, pruned_loss=0.02307, over 7293.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2479, pruned_loss=0.03246, over 1414504.18 frames.], batch size: 24, lr: 2.97e-04
+2022-05-15 10:58:40,623 INFO [train.py:812] (2/8) Epoch 26, batch 4500, loss[loss=0.1561, simple_loss=0.2438, pruned_loss=0.03416, over 7324.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03263, over 1398918.97 frames.], batch size: 20, lr: 2.97e-04
+2022-05-15 10:59:48,423 INFO [train.py:812] (2/8) Epoch 26, batch 4550, loss[loss=0.1874, simple_loss=0.2746, pruned_loss=0.05013, over 5030.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2479, pruned_loss=0.03297, over 1388827.07 frames.], batch size: 52, lr: 2.97e-04
+2022-05-15 11:01:05,794 INFO [train.py:812] (2/8) Epoch 27, batch 0, loss[loss=0.1601, simple_loss=0.2444, pruned_loss=0.03794, over 7152.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2444, pruned_loss=0.03794, over 7152.00 frames.], batch size: 18, lr: 2.91e-04
+2022-05-15 11:02:14,256 INFO [train.py:812] (2/8) Epoch 27, batch 50, loss[loss=0.1264, simple_loss=0.2087, pruned_loss=0.02208, over 7274.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2451, pruned_loss=0.03279, over 318724.44 frames.], batch size: 17, lr: 2.91e-04
+2022-05-15 11:03:12,460 INFO [train.py:812] (2/8) Epoch 27, batch 100, loss[loss=0.1296, simple_loss=0.2135, pruned_loss=0.02283, over 7289.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2453, pruned_loss=0.0312, over 562978.93 frames.], batch size: 17, lr: 2.91e-04
+2022-05-15 11:04:11,557 INFO [train.py:812] (2/8) Epoch 27, batch 150, loss[loss=0.173, simple_loss=0.2731, pruned_loss=0.0364, over 6529.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2469, pruned_loss=0.03203, over 751911.89 frames.], batch size: 38, lr: 2.91e-04
+2022-05-15 11:05:08,309 INFO [train.py:812] (2/8) Epoch 27, batch 200, loss[loss=0.1391, simple_loss=0.2415, pruned_loss=0.0183, over 7113.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2464, pruned_loss=0.0325, over 895307.66 frames.], batch size: 26, lr: 2.91e-04
+2022-05-15 11:06:06,623 INFO [train.py:812] (2/8) Epoch 27, batch 250, loss[loss=0.1537, simple_loss=0.2513, pruned_loss=0.02811, over 6402.00 frames.], tot_loss[loss=0.156, simple_loss=0.2471, pruned_loss=0.03247, over 1007115.52 frames.], batch size: 38, lr: 2.91e-04
+2022-05-15 11:07:05,727 INFO [train.py:812] (2/8) Epoch 27, batch 300, loss[loss=0.1779, simple_loss=0.2767, pruned_loss=0.03955, over 6375.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2477, pruned_loss=0.0325, over 1100846.41 frames.], batch size: 37, lr: 2.91e-04
+2022-05-15 11:08:04,240 INFO [train.py:812] (2/8) Epoch 27, batch 350, loss[loss=0.1576, simple_loss=0.2641, pruned_loss=0.02552, over 6813.00 frames.], tot_loss[loss=0.1567, simple_loss=0.248, pruned_loss=0.03269, over 1168644.84 frames.], batch size: 31, lr: 2.91e-04
+2022-05-15 11:09:03,270 INFO [train.py:812] (2/8) Epoch 27, batch 400, loss[loss=0.1675, simple_loss=0.2604, pruned_loss=0.03732, over 7149.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2482, pruned_loss=0.03273, over 1229283.43 frames.], batch size: 20, lr: 2.91e-04
+2022-05-15 11:10:01,854 INFO [train.py:812] (2/8) Epoch 27, batch 450, loss[loss=0.1678, simple_loss=0.2606, pruned_loss=0.03744, over 7235.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2478, pruned_loss=0.03262, over 1276706.47 frames.], batch size: 20, lr: 2.91e-04
+2022-05-15 11:10:59,674 INFO [train.py:812] (2/8) Epoch 27, batch 500, loss[loss=0.169, simple_loss=0.2455, pruned_loss=0.04621, over 5239.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2468, pruned_loss=0.03202, over 1309173.91 frames.], batch size: 52, lr: 2.91e-04
+2022-05-15 11:11:59,504 INFO [train.py:812] (2/8) Epoch 27, batch 550, loss[loss=0.1827, simple_loss=0.2756, pruned_loss=0.04484, over 7200.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.03234, over 1333343.76 frames.], batch size: 22, lr: 2.90e-04
+2022-05-15 11:12:58,967 INFO [train.py:812] (2/8) Epoch 27, batch 600, loss[loss=0.1493, simple_loss=0.2419, pruned_loss=0.02837, over 7259.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2472, pruned_loss=0.03219, over 1355811.49 frames.], batch size: 19, lr: 2.90e-04
+2022-05-15 11:13:58,663 INFO [train.py:812] (2/8) Epoch 27, batch 650, loss[loss=0.1429, simple_loss=0.2327, pruned_loss=0.02655, over 7277.00 frames.], tot_loss[loss=0.155, simple_loss=0.2466, pruned_loss=0.03174, over 1372534.08 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:14:57,635 INFO [train.py:812] (2/8) Epoch 27, batch 700, loss[loss=0.1273, simple_loss=0.2294, pruned_loss=0.0126, over 7119.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2472, pruned_loss=0.03164, over 1380744.05 frames.], batch size: 21, lr: 2.90e-04
+2022-05-15 11:16:01,096 INFO [train.py:812] (2/8) Epoch 27, batch 750, loss[loss=0.1646, simple_loss=0.2561, pruned_loss=0.03661, over 7142.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2473, pruned_loss=0.03175, over 1390482.55 frames.], batch size: 20, lr: 2.90e-04
+2022-05-15 11:17:00,106 INFO [train.py:812] (2/8) Epoch 27, batch 800, loss[loss=0.1615, simple_loss=0.2498, pruned_loss=0.03658, over 7240.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2471, pruned_loss=0.03179, over 1396243.34 frames.], batch size: 20, lr: 2.90e-04
+2022-05-15 11:17:59,358 INFO [train.py:812] (2/8) Epoch 27, batch 850, loss[loss=0.1578, simple_loss=0.2523, pruned_loss=0.03163, over 5106.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2478, pruned_loss=0.03196, over 1398866.84 frames.], batch size: 52, lr: 2.90e-04
+2022-05-15 11:18:57,702 INFO [train.py:812] (2/8) Epoch 27, batch 900, loss[loss=0.1567, simple_loss=0.2422, pruned_loss=0.03557, over 7410.00 frames.], tot_loss[loss=0.1553, simple_loss=0.247, pruned_loss=0.03184, over 1408264.86 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:19:56,358 INFO [train.py:812] (2/8) Epoch 27, batch 950, loss[loss=0.139, simple_loss=0.2278, pruned_loss=0.02513, over 7284.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2477, pruned_loss=0.03165, over 1409718.03 frames.], batch size: 16, lr: 2.90e-04
+2022-05-15 11:20:55,289 INFO [train.py:812] (2/8) Epoch 27, batch 1000, loss[loss=0.1948, simple_loss=0.2875, pruned_loss=0.05111, over 7305.00 frames.], tot_loss[loss=0.1559, simple_loss=0.248, pruned_loss=0.03195, over 1413009.71 frames.], batch size: 24, lr: 2.90e-04
+2022-05-15 11:21:53,182 INFO [train.py:812] (2/8) Epoch 27, batch 1050, loss[loss=0.1734, simple_loss=0.2682, pruned_loss=0.03924, over 7211.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2475, pruned_loss=0.03183, over 1419017.04 frames.], batch size: 23, lr: 2.90e-04
+2022-05-15 11:22:52,379 INFO [train.py:812] (2/8) Epoch 27, batch 1100, loss[loss=0.1686, simple_loss=0.2677, pruned_loss=0.03476, over 7191.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2472, pruned_loss=0.03198, over 1422788.39 frames.], batch size: 22, lr: 2.90e-04
+2022-05-15 11:23:52,075 INFO [train.py:812] (2/8) Epoch 27, batch 1150, loss[loss=0.1435, simple_loss=0.2333, pruned_loss=0.02685, over 7164.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2479, pruned_loss=0.03242, over 1423907.67 frames.], batch size: 19, lr: 2.90e-04
+2022-05-15 11:24:50,336 INFO [train.py:812] (2/8) Epoch 27, batch 1200, loss[loss=0.1366, simple_loss=0.2297, pruned_loss=0.02177, over 7297.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2475, pruned_loss=0.03213, over 1427451.05 frames.], batch size: 24, lr: 2.90e-04
+2022-05-15 11:25:49,801 INFO [train.py:812] (2/8) Epoch 27, batch 1250, loss[loss=0.1734, simple_loss=0.2707, pruned_loss=0.03809, over 6570.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.03189, over 1426762.17 frames.], batch size: 38, lr: 2.90e-04
+2022-05-15 11:26:48,357 INFO [train.py:812] (2/8) Epoch 27, batch 1300, loss[loss=0.1314, simple_loss=0.2219, pruned_loss=0.02049, over 7285.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2466, pruned_loss=0.03189, over 1422566.05 frames.], batch size: 18, lr: 2.90e-04
+2022-05-15 11:27:46,495 INFO [train.py:812] (2/8) Epoch 27, batch 1350, loss[loss=0.1294, simple_loss=0.2181, pruned_loss=0.02036, over 7422.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2454, pruned_loss=0.0316, over 1426487.45 frames.], batch size: 18, lr: 2.89e-04
+2022-05-15 11:28:44,267 INFO [train.py:812] (2/8) Epoch 27, batch 1400, loss[loss=0.1753, simple_loss=0.2775, pruned_loss=0.03651, over 7197.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2454, pruned_loss=0.0317, over 1419576.50 frames.], batch size: 23, lr: 2.89e-04
+2022-05-15 11:29:43,172 INFO [train.py:812] (2/8) Epoch 27, batch 1450, loss[loss=0.1332, simple_loss=0.227, pruned_loss=0.01968, over 7286.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2458, pruned_loss=0.03188, over 1421377.08 frames.], batch size: 18, lr: 2.89e-04
+2022-05-15 11:30:41,590 INFO [train.py:812] (2/8) Epoch 27, batch 1500, loss[loss=0.1798, simple_loss=0.2715, pruned_loss=0.04404, over 5375.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2458, pruned_loss=0.03182, over 1417960.58 frames.], batch size: 52, lr: 2.89e-04
+2022-05-15 11:31:41,137 INFO [train.py:812] (2/8) Epoch 27, batch 1550, loss[loss=0.1581, simple_loss=0.2557, pruned_loss=0.03021, over 7122.00 frames.], tot_loss[loss=0.1548, simple_loss=0.246, pruned_loss=0.03186, over 1420784.34 frames.], batch size: 21, lr: 2.89e-04
+2022-05-15 11:32:40,461 INFO [train.py:812] (2/8) Epoch 27, batch 1600, loss[loss=0.1388, simple_loss=0.225, pruned_loss=0.02632, over 7259.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2447, pruned_loss=0.03156, over 1424969.44 frames.], batch size: 19, lr: 2.89e-04
+2022-05-15 11:33:39,618 INFO [train.py:812] (2/8) Epoch 27, batch 1650, loss[loss=0.177, simple_loss=0.2798, pruned_loss=0.03704, over 7187.00 frames.], tot_loss[loss=0.1538, simple_loss=0.245, pruned_loss=0.03132, over 1429702.96 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:34:37,985 INFO [train.py:812] (2/8) Epoch 27, batch 1700, loss[loss=0.1537, simple_loss=0.2484, pruned_loss=0.02952, over 7344.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2455, pruned_loss=0.03138, over 1430885.17 frames.], batch size: 22, lr: 2.89e-04
+2022-05-15 11:35:35,781 INFO [train.py:812] (2/8) Epoch 27, batch 1750, loss[loss=0.1684, simple_loss=0.2668, pruned_loss=0.03502, over 7205.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2463, pruned_loss=0.03197, over 1431354.14 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:36:34,415 INFO [train.py:812] (2/8) Epoch 27, batch 1800, loss[loss=0.1635, simple_loss=0.272, pruned_loss=0.02747, over 7103.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2467, pruned_loss=0.03216, over 1429903.09 frames.], batch size: 21, lr: 2.89e-04
+2022-05-15 11:37:32,435 INFO [train.py:812] (2/8) Epoch 27, batch 1850, loss[loss=0.1713, simple_loss=0.2518, pruned_loss=0.04544, over 4908.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2463, pruned_loss=0.03196, over 1429842.05 frames.], batch size: 52, lr: 2.89e-04
+2022-05-15 11:38:30,799 INFO [train.py:812] (2/8) Epoch 27, batch 1900, loss[loss=0.131, simple_loss=0.2247, pruned_loss=0.01861, over 7347.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2452, pruned_loss=0.03165, over 1428259.36 frames.], batch size: 19, lr: 2.89e-04
+2022-05-15 11:39:30,044 INFO [train.py:812] (2/8) Epoch 27, batch 1950, loss[loss=0.1586, simple_loss=0.2525, pruned_loss=0.03232, over 6153.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2457, pruned_loss=0.03173, over 1424012.24 frames.], batch size: 37, lr: 2.89e-04
+2022-05-15 11:40:29,357 INFO [train.py:812] (2/8) Epoch 27, batch 2000, loss[loss=0.1722, simple_loss=0.2676, pruned_loss=0.03843, over 6687.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2453, pruned_loss=0.03176, over 1421738.85 frames.], batch size: 31, lr: 2.89e-04
+2022-05-15 11:41:28,622 INFO [train.py:812] (2/8) Epoch 27, batch 2050, loss[loss=0.1712, simple_loss=0.2608, pruned_loss=0.04083, over 7182.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2464, pruned_loss=0.03209, over 1424863.85 frames.], batch size: 26, lr: 2.89e-04
+2022-05-15 11:42:27,681 INFO [train.py:812] (2/8) Epoch 27, batch 2100, loss[loss=0.1483, simple_loss=0.2424, pruned_loss=0.02704, over 7218.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2463, pruned_loss=0.03216, over 1423553.24 frames.], batch size: 22, lr: 2.89e-04
+2022-05-15 11:43:25,344 INFO [train.py:812] (2/8) Epoch 27, batch 2150, loss[loss=0.1763, simple_loss=0.2734, pruned_loss=0.03957, over 7307.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2475, pruned_loss=0.03252, over 1427189.49 frames.], batch size: 25, lr: 2.89e-04
+2022-05-15 11:44:23,767 INFO [train.py:812] (2/8) Epoch 27, batch 2200, loss[loss=0.165, simple_loss=0.2595, pruned_loss=0.03526, over 7230.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2478, pruned_loss=0.03245, over 1425302.92 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:45:23,013 INFO [train.py:812] (2/8) Epoch 27, batch 2250, loss[loss=0.1238, simple_loss=0.2094, pruned_loss=0.01912, over 6990.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2476, pruned_loss=0.03227, over 1430428.87 frames.], batch size: 16, lr: 2.88e-04
+2022-05-15 11:46:21,590 INFO [train.py:812] (2/8) Epoch 27, batch 2300, loss[loss=0.1402, simple_loss=0.2261, pruned_loss=0.02717, over 7131.00 frames.], tot_loss[loss=0.156, simple_loss=0.2475, pruned_loss=0.03224, over 1432532.83 frames.], batch size: 17, lr: 2.88e-04
+2022-05-15 11:47:19,549 INFO [train.py:812] (2/8) Epoch 27, batch 2350, loss[loss=0.1576, simple_loss=0.2659, pruned_loss=0.02458, over 7139.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2479, pruned_loss=0.03218, over 1431624.84 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:48:16,533 INFO [train.py:812] (2/8) Epoch 27, batch 2400, loss[loss=0.175, simple_loss=0.2736, pruned_loss=0.03824, over 7298.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2479, pruned_loss=0.03219, over 1433566.43 frames.], batch size: 24, lr: 2.88e-04
+2022-05-15 11:49:16,164 INFO [train.py:812] (2/8) Epoch 27, batch 2450, loss[loss=0.1606, simple_loss=0.2622, pruned_loss=0.0295, over 7228.00 frames.], tot_loss[loss=0.156, simple_loss=0.2479, pruned_loss=0.03207, over 1436846.43 frames.], batch size: 20, lr: 2.88e-04
+2022-05-15 11:50:15,232 INFO [train.py:812] (2/8) Epoch 27, batch 2500, loss[loss=0.1484, simple_loss=0.2557, pruned_loss=0.02054, over 7211.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2477, pruned_loss=0.032, over 1438007.09 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 11:51:13,616 INFO [train.py:812] (2/8) Epoch 27, batch 2550, loss[loss=0.1703, simple_loss=0.2625, pruned_loss=0.03905, over 6759.00 frames.], tot_loss[loss=0.156, simple_loss=0.248, pruned_loss=0.03196, over 1434718.46 frames.], batch size: 31, lr: 2.88e-04
+2022-05-15 11:52:12,743 INFO [train.py:812] (2/8) Epoch 27, batch 2600, loss[loss=0.1446, simple_loss=0.2363, pruned_loss=0.02646, over 7226.00 frames.], tot_loss[loss=0.156, simple_loss=0.2479, pruned_loss=0.03208, over 1434454.88 frames.], batch size: 16, lr: 2.88e-04
+2022-05-15 11:53:12,232 INFO [train.py:812] (2/8) Epoch 27, batch 2650, loss[loss=0.1489, simple_loss=0.2434, pruned_loss=0.02716, over 7273.00 frames.], tot_loss[loss=0.156, simple_loss=0.2479, pruned_loss=0.032, over 1430004.44 frames.], batch size: 24, lr: 2.88e-04
+2022-05-15 11:54:11,603 INFO [train.py:812] (2/8) Epoch 27, batch 2700, loss[loss=0.1574, simple_loss=0.2584, pruned_loss=0.02815, over 7332.00 frames.], tot_loss[loss=0.1563, simple_loss=0.248, pruned_loss=0.03225, over 1428603.50 frames.], batch size: 22, lr: 2.88e-04
+2022-05-15 11:55:10,411 INFO [train.py:812] (2/8) Epoch 27, batch 2750, loss[loss=0.1417, simple_loss=0.2237, pruned_loss=0.0298, over 7165.00 frames.], tot_loss[loss=0.156, simple_loss=0.2477, pruned_loss=0.03215, over 1427651.76 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:56:08,583 INFO [train.py:812] (2/8) Epoch 27, batch 2800, loss[loss=0.1746, simple_loss=0.2662, pruned_loss=0.04151, over 7296.00 frames.], tot_loss[loss=0.1554, simple_loss=0.247, pruned_loss=0.03188, over 1427316.79 frames.], batch size: 25, lr: 2.88e-04
+2022-05-15 11:57:08,019 INFO [train.py:812] (2/8) Epoch 27, batch 2850, loss[loss=0.1704, simple_loss=0.2607, pruned_loss=0.04007, over 7257.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2469, pruned_loss=0.03184, over 1427118.05 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:58:06,919 INFO [train.py:812] (2/8) Epoch 27, batch 2900, loss[loss=0.1542, simple_loss=0.2383, pruned_loss=0.03509, over 7157.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2466, pruned_loss=0.03179, over 1426334.70 frames.], batch size: 19, lr: 2.88e-04
+2022-05-15 11:59:06,548 INFO [train.py:812] (2/8) Epoch 27, batch 2950, loss[loss=0.1411, simple_loss=0.2403, pruned_loss=0.02096, over 7116.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2471, pruned_loss=0.03171, over 1419142.88 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 12:00:05,491 INFO [train.py:812] (2/8) Epoch 27, batch 3000, loss[loss=0.1551, simple_loss=0.2554, pruned_loss=0.02739, over 7407.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2471, pruned_loss=0.03179, over 1418361.86 frames.], batch size: 21, lr: 2.88e-04
+2022-05-15 12:00:05,493 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 12:00:12,945 INFO [train.py:841] (2/8) Epoch 27, validation: loss=0.1528, simple_loss=0.25, pruned_loss=0.02785, over 698248.00 frames.
+2022-05-15 12:01:11,895 INFO [train.py:812] (2/8) Epoch 27, batch 3050, loss[loss=0.1645, simple_loss=0.264, pruned_loss=0.03255, over 7120.00 frames.], tot_loss[loss=0.1548, simple_loss=0.246, pruned_loss=0.03184, over 1410392.05 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:02:10,835 INFO [train.py:812] (2/8) Epoch 27, batch 3100, loss[loss=0.1579, simple_loss=0.2609, pruned_loss=0.02751, over 7325.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2465, pruned_loss=0.03162, over 1416591.35 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:03:20,310 INFO [train.py:812] (2/8) Epoch 27, batch 3150, loss[loss=0.1726, simple_loss=0.2596, pruned_loss=0.04273, over 7213.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.03224, over 1417764.81 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:04:19,320 INFO [train.py:812] (2/8) Epoch 27, batch 3200, loss[loss=0.1873, simple_loss=0.2741, pruned_loss=0.05021, over 7185.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2479, pruned_loss=0.03241, over 1420088.03 frames.], batch size: 23, lr: 2.87e-04
+2022-05-15 12:05:18,914 INFO [train.py:812] (2/8) Epoch 27, batch 3250, loss[loss=0.1529, simple_loss=0.25, pruned_loss=0.02792, over 6302.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.03265, over 1420213.74 frames.], batch size: 37, lr: 2.87e-04
+2022-05-15 12:06:17,785 INFO [train.py:812] (2/8) Epoch 27, batch 3300, loss[loss=0.1471, simple_loss=0.2434, pruned_loss=0.02537, over 6827.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2469, pruned_loss=0.03216, over 1419177.05 frames.], batch size: 31, lr: 2.87e-04
+2022-05-15 12:07:17,057 INFO [train.py:812] (2/8) Epoch 27, batch 3350, loss[loss=0.1543, simple_loss=0.2583, pruned_loss=0.0251, over 7343.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2476, pruned_loss=0.03213, over 1420146.14 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:08:16,180 INFO [train.py:812] (2/8) Epoch 27, batch 3400, loss[loss=0.1641, simple_loss=0.2592, pruned_loss=0.03446, over 7154.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2481, pruned_loss=0.03252, over 1417710.78 frames.], batch size: 20, lr: 2.87e-04
+2022-05-15 12:09:14,984 INFO [train.py:812] (2/8) Epoch 27, batch 3450, loss[loss=0.1892, simple_loss=0.2797, pruned_loss=0.04937, over 7338.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2481, pruned_loss=0.03239, over 1421378.38 frames.], batch size: 22, lr: 2.87e-04
+2022-05-15 12:10:13,331 INFO [train.py:812] (2/8) Epoch 27, batch 3500, loss[loss=0.1354, simple_loss=0.2226, pruned_loss=0.02412, over 6767.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.03228, over 1423417.66 frames.], batch size: 15, lr: 2.87e-04
+2022-05-15 12:11:13,075 INFO [train.py:812] (2/8) Epoch 27, batch 3550, loss[loss=0.1596, simple_loss=0.2491, pruned_loss=0.0351, over 5174.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03211, over 1416514.21 frames.], batch size: 53, lr: 2.87e-04
+2022-05-15 12:12:10,926 INFO [train.py:812] (2/8) Epoch 27, batch 3600, loss[loss=0.146, simple_loss=0.2443, pruned_loss=0.02383, over 7157.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2474, pruned_loss=0.03251, over 1413941.83 frames.], batch size: 19, lr: 2.87e-04
+2022-05-15 12:13:10,318 INFO [train.py:812] (2/8) Epoch 27, batch 3650, loss[loss=0.1374, simple_loss=0.2207, pruned_loss=0.02704, over 7077.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03264, over 1414555.69 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:14:09,326 INFO [train.py:812] (2/8) Epoch 27, batch 3700, loss[loss=0.1549, simple_loss=0.2371, pruned_loss=0.03636, over 7276.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2472, pruned_loss=0.03264, over 1413476.89 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:15:08,332 INFO [train.py:812] (2/8) Epoch 27, batch 3750, loss[loss=0.1447, simple_loss=0.2373, pruned_loss=0.02607, over 7229.00 frames.], tot_loss[loss=0.155, simple_loss=0.2454, pruned_loss=0.03228, over 1416857.50 frames.], batch size: 21, lr: 2.87e-04
+2022-05-15 12:16:08,053 INFO [train.py:812] (2/8) Epoch 27, batch 3800, loss[loss=0.1304, simple_loss=0.2256, pruned_loss=0.01758, over 7325.00 frames.], tot_loss[loss=0.154, simple_loss=0.2446, pruned_loss=0.03174, over 1420496.35 frames.], batch size: 20, lr: 2.87e-04
+2022-05-15 12:17:07,775 INFO [train.py:812] (2/8) Epoch 27, batch 3850, loss[loss=0.1399, simple_loss=0.2298, pruned_loss=0.02498, over 7407.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2463, pruned_loss=0.03257, over 1413746.14 frames.], batch size: 18, lr: 2.87e-04
+2022-05-15 12:18:06,244 INFO [train.py:812] (2/8) Epoch 27, batch 3900, loss[loss=0.1825, simple_loss=0.2763, pruned_loss=0.04439, over 7028.00 frames.], tot_loss[loss=0.1561, simple_loss=0.247, pruned_loss=0.03258, over 1414439.08 frames.], batch size: 28, lr: 2.86e-04
+2022-05-15 12:19:04,968 INFO [train.py:812] (2/8) Epoch 27, batch 3950, loss[loss=0.1471, simple_loss=0.2332, pruned_loss=0.03055, over 7366.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2474, pruned_loss=0.03276, over 1418654.64 frames.], batch size: 19, lr: 2.86e-04
+2022-05-15 12:20:04,222 INFO [train.py:812] (2/8) Epoch 27, batch 4000, loss[loss=0.1524, simple_loss=0.2551, pruned_loss=0.02488, over 7057.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2466, pruned_loss=0.03208, over 1424179.17 frames.], batch size: 28, lr: 2.86e-04
+2022-05-15 12:21:04,107 INFO [train.py:812] (2/8) Epoch 27, batch 4050, loss[loss=0.1659, simple_loss=0.2514, pruned_loss=0.0402, over 7321.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2469, pruned_loss=0.03209, over 1424958.46 frames.], batch size: 20, lr: 2.86e-04
+2022-05-15 12:22:03,546 INFO [train.py:812] (2/8) Epoch 27, batch 4100, loss[loss=0.1376, simple_loss=0.236, pruned_loss=0.01959, over 7322.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2463, pruned_loss=0.03211, over 1423401.96 frames.], batch size: 20, lr: 2.86e-04
+2022-05-15 12:23:02,359 INFO [train.py:812] (2/8) Epoch 27, batch 4150, loss[loss=0.1597, simple_loss=0.2551, pruned_loss=0.03215, over 7120.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2463, pruned_loss=0.03196, over 1420884.09 frames.], batch size: 21, lr: 2.86e-04
+2022-05-15 12:23:59,498 INFO [train.py:812] (2/8) Epoch 27, batch 4200, loss[loss=0.1621, simple_loss=0.2597, pruned_loss=0.03223, over 7335.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2454, pruned_loss=0.03158, over 1422664.93 frames.], batch size: 22, lr: 2.86e-04
+2022-05-15 12:24:57,506 INFO [train.py:812] (2/8) Epoch 27, batch 4250, loss[loss=0.1573, simple_loss=0.2463, pruned_loss=0.0342, over 7421.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2471, pruned_loss=0.03197, over 1415573.34 frames.], batch size: 21, lr: 2.86e-04
+2022-05-15 12:25:55,491 INFO [train.py:812] (2/8) Epoch 27, batch 4300, loss[loss=0.1373, simple_loss=0.2269, pruned_loss=0.02379, over 6699.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.03192, over 1413926.11 frames.], batch size: 31, lr: 2.86e-04
+2022-05-15 12:26:54,779 INFO [train.py:812] (2/8) Epoch 27, batch 4350, loss[loss=0.1402, simple_loss=0.2321, pruned_loss=0.02414, over 7002.00 frames.], tot_loss[loss=0.155, simple_loss=0.2469, pruned_loss=0.0316, over 1413321.13 frames.], batch size: 16, lr: 2.86e-04
+2022-05-15 12:27:53,345 INFO [train.py:812] (2/8) Epoch 27, batch 4400, loss[loss=0.1463, simple_loss=0.238, pruned_loss=0.02729, over 6310.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2476, pruned_loss=0.0321, over 1401125.51 frames.], batch size: 37, lr: 2.86e-04
+2022-05-15 12:28:51,266 INFO [train.py:812] (2/8) Epoch 27, batch 4450, loss[loss=0.1402, simple_loss=0.2333, pruned_loss=0.02353, over 7340.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2472, pruned_loss=0.0322, over 1396871.27 frames.], batch size: 22, lr: 2.86e-04
+2022-05-15 12:29:50,409 INFO [train.py:812] (2/8) Epoch 27, batch 4500, loss[loss=0.1596, simple_loss=0.2494, pruned_loss=0.03487, over 7170.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2482, pruned_loss=0.03269, over 1387679.41 frames.], batch size: 18, lr: 2.86e-04
+2022-05-15 12:30:49,289 INFO [train.py:812] (2/8) Epoch 27, batch 4550, loss[loss=0.1899, simple_loss=0.2682, pruned_loss=0.05579, over 5023.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2469, pruned_loss=0.03287, over 1371166.59 frames.], batch size: 52, lr: 2.86e-04
+2022-05-15 12:32:00,090 INFO [train.py:812] (2/8) Epoch 28, batch 0, loss[loss=0.1405, simple_loss=0.2294, pruned_loss=0.02576, over 7256.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2294, pruned_loss=0.02576, over 7256.00 frames.], batch size: 19, lr: 2.81e-04
+2022-05-15 12:32:59,368 INFO [train.py:812] (2/8) Epoch 28, batch 50, loss[loss=0.1465, simple_loss=0.2382, pruned_loss=0.02738, over 7268.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2427, pruned_loss=0.02996, over 320841.12 frames.], batch size: 19, lr: 2.81e-04
+2022-05-15 12:33:58,540 INFO [train.py:812] (2/8) Epoch 28, batch 100, loss[loss=0.155, simple_loss=0.2544, pruned_loss=0.02776, over 7140.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2448, pruned_loss=0.03118, over 564887.37 frames.], batch size: 20, lr: 2.80e-04
+2022-05-15 12:35:03,228 INFO [train.py:812] (2/8) Epoch 28, batch 150, loss[loss=0.1627, simple_loss=0.2562, pruned_loss=0.03454, over 6572.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2455, pruned_loss=0.0313, over 753307.01 frames.], batch size: 39, lr: 2.80e-04
+2022-05-15 12:36:01,532 INFO [train.py:812] (2/8) Epoch 28, batch 200, loss[loss=0.1901, simple_loss=0.2747, pruned_loss=0.05274, over 7194.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2456, pruned_loss=0.03153, over 899624.32 frames.], batch size: 23, lr: 2.80e-04
+2022-05-15 12:36:59,687 INFO [train.py:812] (2/8) Epoch 28, batch 250, loss[loss=0.162, simple_loss=0.252, pruned_loss=0.03599, over 7281.00 frames.], tot_loss[loss=0.154, simple_loss=0.2456, pruned_loss=0.03123, over 1015498.19 frames.], batch size: 24, lr: 2.80e-04
+2022-05-15 12:37:58,305 INFO [train.py:812] (2/8) Epoch 28, batch 300, loss[loss=0.1728, simple_loss=0.2694, pruned_loss=0.03814, over 6825.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2467, pruned_loss=0.0317, over 1105647.35 frames.], batch size: 31, lr: 2.80e-04
+2022-05-15 12:38:57,249 INFO [train.py:812] (2/8) Epoch 28, batch 350, loss[loss=0.1532, simple_loss=0.2507, pruned_loss=0.02786, over 7160.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2458, pruned_loss=0.03145, over 1177583.03 frames.], batch size: 19, lr: 2.80e-04
+2022-05-15 12:39:55,236 INFO [train.py:812] (2/8) Epoch 28, batch 400, loss[loss=0.1494, simple_loss=0.2323, pruned_loss=0.03318, over 7131.00 frames.], tot_loss[loss=0.1546, simple_loss=0.246, pruned_loss=0.03162, over 1233056.37 frames.], batch size: 17, lr: 2.80e-04
+2022-05-15 12:40:54,500 INFO [train.py:812] (2/8) Epoch 28, batch 450, loss[loss=0.1755, simple_loss=0.2671, pruned_loss=0.04199, over 7318.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2469, pruned_loss=0.03179, over 1269766.77 frames.], batch size: 25, lr: 2.80e-04
+2022-05-15 12:41:53,063 INFO [train.py:812] (2/8) Epoch 28, batch 500, loss[loss=0.1374, simple_loss=0.229, pruned_loss=0.02295, over 7327.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.0319, over 1307215.41 frames.], batch size: 21, lr: 2.80e-04
+2022-05-15 12:42:52,291 INFO [train.py:812] (2/8) Epoch 28, batch 550, loss[loss=0.1479, simple_loss=0.2335, pruned_loss=0.03109, over 7074.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2464, pruned_loss=0.03207, over 1329357.92 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:43:51,386 INFO [train.py:812] (2/8) Epoch 28, batch 600, loss[loss=0.1391, simple_loss=0.2312, pruned_loss=0.02345, over 7330.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2464, pruned_loss=0.03218, over 1347921.46 frames.], batch size: 20, lr: 2.80e-04
+2022-05-15 12:44:49,181 INFO [train.py:812] (2/8) Epoch 28, batch 650, loss[loss=0.1904, simple_loss=0.2907, pruned_loss=0.04508, over 7148.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2463, pruned_loss=0.03163, over 1366295.88 frames.], batch size: 28, lr: 2.80e-04
+2022-05-15 12:45:47,941 INFO [train.py:812] (2/8) Epoch 28, batch 700, loss[loss=0.1431, simple_loss=0.224, pruned_loss=0.03108, over 7065.00 frames.], tot_loss[loss=0.1544, simple_loss=0.246, pruned_loss=0.0314, over 1380641.25 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:46:48,081 INFO [train.py:812] (2/8) Epoch 28, batch 750, loss[loss=0.1552, simple_loss=0.2465, pruned_loss=0.0319, over 7221.00 frames.], tot_loss[loss=0.154, simple_loss=0.2453, pruned_loss=0.03131, over 1391742.24 frames.], batch size: 21, lr: 2.80e-04
+2022-05-15 12:47:47,244 INFO [train.py:812] (2/8) Epoch 28, batch 800, loss[loss=0.1614, simple_loss=0.2566, pruned_loss=0.03307, over 7123.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2457, pruned_loss=0.03156, over 1397375.07 frames.], batch size: 28, lr: 2.80e-04
+2022-05-15 12:48:46,865 INFO [train.py:812] (2/8) Epoch 28, batch 850, loss[loss=0.1737, simple_loss=0.2667, pruned_loss=0.04032, over 7301.00 frames.], tot_loss[loss=0.1545, simple_loss=0.246, pruned_loss=0.03148, over 1405338.94 frames.], batch size: 25, lr: 2.80e-04
+2022-05-15 12:49:45,703 INFO [train.py:812] (2/8) Epoch 28, batch 900, loss[loss=0.1331, simple_loss=0.2158, pruned_loss=0.02523, over 6997.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2468, pruned_loss=0.03165, over 1407253.33 frames.], batch size: 16, lr: 2.80e-04
+2022-05-15 12:50:44,997 INFO [train.py:812] (2/8) Epoch 28, batch 950, loss[loss=0.1634, simple_loss=0.2433, pruned_loss=0.04176, over 7161.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2469, pruned_loss=0.03172, over 1409451.43 frames.], batch size: 18, lr: 2.80e-04
+2022-05-15 12:51:43,942 INFO [train.py:812] (2/8) Epoch 28, batch 1000, loss[loss=0.163, simple_loss=0.2575, pruned_loss=0.03428, over 7414.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2466, pruned_loss=0.03178, over 1414932.49 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 12:52:42,475 INFO [train.py:812] (2/8) Epoch 28, batch 1050, loss[loss=0.1469, simple_loss=0.2472, pruned_loss=0.0233, over 7421.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2466, pruned_loss=0.03181, over 1414965.22 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 12:53:50,426 INFO [train.py:812] (2/8) Epoch 28, batch 1100, loss[loss=0.1474, simple_loss=0.2348, pruned_loss=0.02998, over 7067.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03205, over 1414667.56 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 12:54:49,834 INFO [train.py:812] (2/8) Epoch 28, batch 1150, loss[loss=0.1765, simple_loss=0.2625, pruned_loss=0.04527, over 7197.00 frames.], tot_loss[loss=0.1553, simple_loss=0.246, pruned_loss=0.0323, over 1420571.17 frames.], batch size: 23, lr: 2.79e-04
+2022-05-15 12:55:48,172 INFO [train.py:812] (2/8) Epoch 28, batch 1200, loss[loss=0.1614, simple_loss=0.2456, pruned_loss=0.03857, over 7127.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2461, pruned_loss=0.03217, over 1424337.38 frames.], batch size: 17, lr: 2.79e-04
+2022-05-15 12:56:47,632 INFO [train.py:812] (2/8) Epoch 28, batch 1250, loss[loss=0.1282, simple_loss=0.218, pruned_loss=0.01916, over 7122.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03174, over 1422650.08 frames.], batch size: 17, lr: 2.79e-04
+2022-05-15 12:57:56,215 INFO [train.py:812] (2/8) Epoch 28, batch 1300, loss[loss=0.1255, simple_loss=0.2058, pruned_loss=0.02264, over 7290.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2462, pruned_loss=0.03184, over 1419043.91 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 12:58:55,622 INFO [train.py:812] (2/8) Epoch 28, batch 1350, loss[loss=0.1602, simple_loss=0.2452, pruned_loss=0.03761, over 7352.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2458, pruned_loss=0.03177, over 1419105.47 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:00:02,772 INFO [train.py:812] (2/8) Epoch 28, batch 1400, loss[loss=0.1455, simple_loss=0.2323, pruned_loss=0.02929, over 7049.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2455, pruned_loss=0.03155, over 1418573.86 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 13:01:30,488 INFO [train.py:812] (2/8) Epoch 28, batch 1450, loss[loss=0.1351, simple_loss=0.2361, pruned_loss=0.01703, over 7337.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2444, pruned_loss=0.03103, over 1420969.24 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 13:02:27,759 INFO [train.py:812] (2/8) Epoch 28, batch 1500, loss[loss=0.1623, simple_loss=0.2602, pruned_loss=0.03222, over 7114.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03134, over 1422912.24 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 13:03:25,153 INFO [train.py:812] (2/8) Epoch 28, batch 1550, loss[loss=0.1473, simple_loss=0.2252, pruned_loss=0.03472, over 7166.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2464, pruned_loss=0.03168, over 1420326.82 frames.], batch size: 16, lr: 2.79e-04
+2022-05-15 13:04:33,681 INFO [train.py:812] (2/8) Epoch 28, batch 1600, loss[loss=0.1737, simple_loss=0.2777, pruned_loss=0.03491, over 7415.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2458, pruned_loss=0.03141, over 1424147.29 frames.], batch size: 21, lr: 2.79e-04
+2022-05-15 13:05:32,117 INFO [train.py:812] (2/8) Epoch 28, batch 1650, loss[loss=0.1472, simple_loss=0.2388, pruned_loss=0.02784, over 7059.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2459, pruned_loss=0.03151, over 1424223.78 frames.], batch size: 18, lr: 2.79e-04
+2022-05-15 13:06:30,572 INFO [train.py:812] (2/8) Epoch 28, batch 1700, loss[loss=0.1409, simple_loss=0.2258, pruned_loss=0.02803, over 7365.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.0317, over 1425624.40 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:07:29,477 INFO [train.py:812] (2/8) Epoch 28, batch 1750, loss[loss=0.1561, simple_loss=0.2486, pruned_loss=0.03175, over 6826.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2453, pruned_loss=0.03123, over 1426852.34 frames.], batch size: 31, lr: 2.79e-04
+2022-05-15 13:08:28,869 INFO [train.py:812] (2/8) Epoch 28, batch 1800, loss[loss=0.1534, simple_loss=0.2535, pruned_loss=0.02661, over 7228.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2456, pruned_loss=0.03158, over 1426191.15 frames.], batch size: 20, lr: 2.79e-04
+2022-05-15 13:09:27,169 INFO [train.py:812] (2/8) Epoch 28, batch 1850, loss[loss=0.1404, simple_loss=0.2232, pruned_loss=0.02882, over 7146.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2457, pruned_loss=0.03143, over 1429202.00 frames.], batch size: 19, lr: 2.79e-04
+2022-05-15 13:10:26,317 INFO [train.py:812] (2/8) Epoch 28, batch 1900, loss[loss=0.1355, simple_loss=0.2211, pruned_loss=0.02495, over 7282.00 frames.], tot_loss[loss=0.155, simple_loss=0.2461, pruned_loss=0.03195, over 1429437.85 frames.], batch size: 17, lr: 2.78e-04
+2022-05-15 13:11:24,510 INFO [train.py:812] (2/8) Epoch 28, batch 1950, loss[loss=0.1719, simple_loss=0.2669, pruned_loss=0.03839, over 6545.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2467, pruned_loss=0.03225, over 1424820.37 frames.], batch size: 38, lr: 2.78e-04
+2022-05-15 13:12:23,341 INFO [train.py:812] (2/8) Epoch 28, batch 2000, loss[loss=0.1567, simple_loss=0.259, pruned_loss=0.0272, over 7228.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2469, pruned_loss=0.03222, over 1424098.04 frames.], batch size: 21, lr: 2.78e-04
+2022-05-15 13:13:21,535 INFO [train.py:812] (2/8) Epoch 28, batch 2050, loss[loss=0.1721, simple_loss=0.2537, pruned_loss=0.04521, over 7206.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.03272, over 1422804.47 frames.], batch size: 23, lr: 2.78e-04
+2022-05-15 13:14:21,000 INFO [train.py:812] (2/8) Epoch 28, batch 2100, loss[loss=0.1749, simple_loss=0.2645, pruned_loss=0.04262, over 7297.00 frames.], tot_loss[loss=0.156, simple_loss=0.2475, pruned_loss=0.03224, over 1422799.35 frames.], batch size: 25, lr: 2.78e-04
+2022-05-15 13:15:20,656 INFO [train.py:812] (2/8) Epoch 28, batch 2150, loss[loss=0.13, simple_loss=0.2084, pruned_loss=0.02582, over 7128.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03216, over 1421163.69 frames.], batch size: 17, lr: 2.78e-04
+2022-05-15 13:16:19,070 INFO [train.py:812] (2/8) Epoch 28, batch 2200, loss[loss=0.1641, simple_loss=0.2636, pruned_loss=0.03227, over 7292.00 frames.], tot_loss[loss=0.156, simple_loss=0.2473, pruned_loss=0.03241, over 1420541.96 frames.], batch size: 24, lr: 2.78e-04
+2022-05-15 13:17:18,197 INFO [train.py:812] (2/8) Epoch 28, batch 2250, loss[loss=0.1653, simple_loss=0.2675, pruned_loss=0.03159, over 7328.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03217, over 1423309.10 frames.], batch size: 22, lr: 2.78e-04
+2022-05-15 13:18:16,762 INFO [train.py:812] (2/8) Epoch 28, batch 2300, loss[loss=0.1447, simple_loss=0.2447, pruned_loss=0.02237, over 7147.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2473, pruned_loss=0.03186, over 1420593.32 frames.], batch size: 20, lr: 2.78e-04
+2022-05-15 13:19:16,357 INFO [train.py:812] (2/8) Epoch 28, batch 2350, loss[loss=0.1651, simple_loss=0.2612, pruned_loss=0.0345, over 7166.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2472, pruned_loss=0.03181, over 1419274.92 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:20:14,236 INFO [train.py:812] (2/8) Epoch 28, batch 2400, loss[loss=0.1598, simple_loss=0.2544, pruned_loss=0.03263, over 7224.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2474, pruned_loss=0.03185, over 1423066.91 frames.], batch size: 23, lr: 2.78e-04
+2022-05-15 13:21:14,082 INFO [train.py:812] (2/8) Epoch 28, batch 2450, loss[loss=0.1653, simple_loss=0.2618, pruned_loss=0.0344, over 6245.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2462, pruned_loss=0.03124, over 1423455.58 frames.], batch size: 37, lr: 2.78e-04
+2022-05-15 13:22:13,013 INFO [train.py:812] (2/8) Epoch 28, batch 2500, loss[loss=0.1323, simple_loss=0.2186, pruned_loss=0.02299, over 6799.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2456, pruned_loss=0.03143, over 1420347.28 frames.], batch size: 15, lr: 2.78e-04
+2022-05-15 13:23:12,413 INFO [train.py:812] (2/8) Epoch 28, batch 2550, loss[loss=0.1451, simple_loss=0.2305, pruned_loss=0.02986, over 7263.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.03149, over 1421133.68 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:24:10,724 INFO [train.py:812] (2/8) Epoch 28, batch 2600, loss[loss=0.1493, simple_loss=0.2545, pruned_loss=0.02202, over 7236.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2462, pruned_loss=0.03156, over 1420838.17 frames.], batch size: 20, lr: 2.78e-04
+2022-05-15 13:25:09,949 INFO [train.py:812] (2/8) Epoch 28, batch 2650, loss[loss=0.1398, simple_loss=0.2307, pruned_loss=0.02442, over 6996.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2465, pruned_loss=0.03152, over 1419986.63 frames.], batch size: 16, lr: 2.78e-04
+2022-05-15 13:26:09,005 INFO [train.py:812] (2/8) Epoch 28, batch 2700, loss[loss=0.1458, simple_loss=0.2333, pruned_loss=0.02915, over 7311.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2462, pruned_loss=0.03138, over 1421929.60 frames.], batch size: 21, lr: 2.78e-04
+2022-05-15 13:27:07,534 INFO [train.py:812] (2/8) Epoch 28, batch 2750, loss[loss=0.1612, simple_loss=0.2528, pruned_loss=0.03474, over 7252.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2466, pruned_loss=0.03145, over 1420672.82 frames.], batch size: 19, lr: 2.78e-04
+2022-05-15 13:28:05,907 INFO [train.py:812] (2/8) Epoch 28, batch 2800, loss[loss=0.1737, simple_loss=0.2732, pruned_loss=0.03705, over 7232.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2466, pruned_loss=0.03159, over 1416183.57 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:29:05,086 INFO [train.py:812] (2/8) Epoch 28, batch 2850, loss[loss=0.1348, simple_loss=0.2147, pruned_loss=0.02747, over 7135.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2464, pruned_loss=0.03143, over 1420300.93 frames.], batch size: 17, lr: 2.77e-04
+2022-05-15 13:30:03,004 INFO [train.py:812] (2/8) Epoch 28, batch 2900, loss[loss=0.1876, simple_loss=0.2885, pruned_loss=0.04335, over 7293.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2474, pruned_loss=0.03166, over 1419064.14 frames.], batch size: 25, lr: 2.77e-04
+2022-05-15 13:31:01,409 INFO [train.py:812] (2/8) Epoch 28, batch 2950, loss[loss=0.1515, simple_loss=0.2542, pruned_loss=0.02444, over 7193.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2471, pruned_loss=0.03182, over 1422633.59 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:32:00,616 INFO [train.py:812] (2/8) Epoch 28, batch 3000, loss[loss=0.1688, simple_loss=0.2623, pruned_loss=0.03766, over 7074.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2479, pruned_loss=0.03198, over 1424708.75 frames.], batch size: 28, lr: 2.77e-04
+2022-05-15 13:32:00,617 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 13:32:08,090 INFO [train.py:841] (2/8) Epoch 28, validation: loss=0.1523, simple_loss=0.2496, pruned_loss=0.02748, over 698248.00 frames.
+2022-05-15 13:33:05,909 INFO [train.py:812] (2/8) Epoch 28, batch 3050, loss[loss=0.129, simple_loss=0.2165, pruned_loss=0.02078, over 7137.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2476, pruned_loss=0.03189, over 1426450.79 frames.], batch size: 17, lr: 2.77e-04
+2022-05-15 13:34:04,040 INFO [train.py:812] (2/8) Epoch 28, batch 3100, loss[loss=0.1713, simple_loss=0.2561, pruned_loss=0.0433, over 7390.00 frames.], tot_loss[loss=0.1552, simple_loss=0.247, pruned_loss=0.03169, over 1425073.51 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:35:03,613 INFO [train.py:812] (2/8) Epoch 28, batch 3150, loss[loss=0.1194, simple_loss=0.2101, pruned_loss=0.01433, over 7405.00 frames.], tot_loss[loss=0.155, simple_loss=0.2463, pruned_loss=0.03181, over 1423668.36 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:36:02,627 INFO [train.py:812] (2/8) Epoch 28, batch 3200, loss[loss=0.1499, simple_loss=0.251, pruned_loss=0.02445, over 7318.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2468, pruned_loss=0.0318, over 1424235.67 frames.], batch size: 21, lr: 2.77e-04
+2022-05-15 13:37:02,642 INFO [train.py:812] (2/8) Epoch 28, batch 3250, loss[loss=0.1446, simple_loss=0.2352, pruned_loss=0.02702, over 7171.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2465, pruned_loss=0.03184, over 1423138.87 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:37:59,660 INFO [train.py:812] (2/8) Epoch 28, batch 3300, loss[loss=0.1489, simple_loss=0.2221, pruned_loss=0.03782, over 7013.00 frames.], tot_loss[loss=0.155, simple_loss=0.2466, pruned_loss=0.0317, over 1422117.33 frames.], batch size: 16, lr: 2.77e-04
+2022-05-15 13:38:57,852 INFO [train.py:812] (2/8) Epoch 28, batch 3350, loss[loss=0.1622, simple_loss=0.2498, pruned_loss=0.03735, over 7382.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2468, pruned_loss=0.03184, over 1419265.09 frames.], batch size: 23, lr: 2.77e-04
+2022-05-15 13:39:56,930 INFO [train.py:812] (2/8) Epoch 28, batch 3400, loss[loss=0.1336, simple_loss=0.2306, pruned_loss=0.01835, over 7324.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2466, pruned_loss=0.03185, over 1421513.96 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:40:56,427 INFO [train.py:812] (2/8) Epoch 28, batch 3450, loss[loss=0.148, simple_loss=0.2406, pruned_loss=0.02766, over 7184.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.03185, over 1422535.68 frames.], batch size: 22, lr: 2.77e-04
+2022-05-15 13:41:55,468 INFO [train.py:812] (2/8) Epoch 28, batch 3500, loss[loss=0.1439, simple_loss=0.231, pruned_loss=0.02836, over 7052.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03173, over 1422244.09 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:42:54,600 INFO [train.py:812] (2/8) Epoch 28, batch 3550, loss[loss=0.1541, simple_loss=0.2545, pruned_loss=0.02681, over 7334.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03165, over 1423045.45 frames.], batch size: 22, lr: 2.77e-04
+2022-05-15 13:43:53,653 INFO [train.py:812] (2/8) Epoch 28, batch 3600, loss[loss=0.1377, simple_loss=0.2235, pruned_loss=0.02595, over 7061.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.03161, over 1422162.54 frames.], batch size: 18, lr: 2.77e-04
+2022-05-15 13:44:53,137 INFO [train.py:812] (2/8) Epoch 28, batch 3650, loss[loss=0.1844, simple_loss=0.2832, pruned_loss=0.04276, over 7402.00 frames.], tot_loss[loss=0.1541, simple_loss=0.246, pruned_loss=0.0311, over 1423026.64 frames.], batch size: 21, lr: 2.77e-04
+2022-05-15 13:45:51,487 INFO [train.py:812] (2/8) Epoch 28, batch 3700, loss[loss=0.1473, simple_loss=0.2386, pruned_loss=0.028, over 7431.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2459, pruned_loss=0.03088, over 1424003.53 frames.], batch size: 20, lr: 2.77e-04
+2022-05-15 13:46:50,287 INFO [train.py:812] (2/8) Epoch 28, batch 3750, loss[loss=0.1934, simple_loss=0.2742, pruned_loss=0.0563, over 5095.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2462, pruned_loss=0.03142, over 1420225.82 frames.], batch size: 52, lr: 2.76e-04
+2022-05-15 13:47:49,378 INFO [train.py:812] (2/8) Epoch 28, batch 3800, loss[loss=0.1335, simple_loss=0.2158, pruned_loss=0.02554, over 7292.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2462, pruned_loss=0.03151, over 1422476.79 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:48:48,486 INFO [train.py:812] (2/8) Epoch 28, batch 3850, loss[loss=0.1433, simple_loss=0.2429, pruned_loss=0.02187, over 7165.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2467, pruned_loss=0.03142, over 1426917.57 frames.], batch size: 19, lr: 2.76e-04
+2022-05-15 13:49:47,452 INFO [train.py:812] (2/8) Epoch 28, batch 3900, loss[loss=0.1422, simple_loss=0.2366, pruned_loss=0.02387, over 7199.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2459, pruned_loss=0.03097, over 1426047.49 frames.], batch size: 22, lr: 2.76e-04
+2022-05-15 13:50:47,232 INFO [train.py:812] (2/8) Epoch 28, batch 3950, loss[loss=0.1698, simple_loss=0.2668, pruned_loss=0.03643, over 7208.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2461, pruned_loss=0.03112, over 1426917.83 frames.], batch size: 22, lr: 2.76e-04
+2022-05-15 13:51:46,169 INFO [train.py:812] (2/8) Epoch 28, batch 4000, loss[loss=0.1794, simple_loss=0.2652, pruned_loss=0.04677, over 6683.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2452, pruned_loss=0.03131, over 1423909.01 frames.], batch size: 31, lr: 2.76e-04
+2022-05-15 13:52:45,724 INFO [train.py:812] (2/8) Epoch 28, batch 4050, loss[loss=0.1647, simple_loss=0.2596, pruned_loss=0.03489, over 5283.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2465, pruned_loss=0.0315, over 1417204.31 frames.], batch size: 53, lr: 2.76e-04
+2022-05-15 13:53:44,803 INFO [train.py:812] (2/8) Epoch 28, batch 4100, loss[loss=0.1437, simple_loss=0.2303, pruned_loss=0.02854, over 7124.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2463, pruned_loss=0.03153, over 1418907.50 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:54:49,337 INFO [train.py:812] (2/8) Epoch 28, batch 4150, loss[loss=0.1444, simple_loss=0.2385, pruned_loss=0.02514, over 7150.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2465, pruned_loss=0.03161, over 1423816.55 frames.], batch size: 19, lr: 2.76e-04
+2022-05-15 13:55:47,963 INFO [train.py:812] (2/8) Epoch 28, batch 4200, loss[loss=0.1842, simple_loss=0.2776, pruned_loss=0.04537, over 5257.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03248, over 1418179.25 frames.], batch size: 52, lr: 2.76e-04
+2022-05-15 13:56:46,359 INFO [train.py:812] (2/8) Epoch 28, batch 4250, loss[loss=0.1399, simple_loss=0.2297, pruned_loss=0.02501, over 7060.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2484, pruned_loss=0.03241, over 1415491.93 frames.], batch size: 18, lr: 2.76e-04
+2022-05-15 13:57:45,246 INFO [train.py:812] (2/8) Epoch 28, batch 4300, loss[loss=0.1488, simple_loss=0.2404, pruned_loss=0.02857, over 7121.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2481, pruned_loss=0.03239, over 1417389.50 frames.], batch size: 17, lr: 2.76e-04
+2022-05-15 13:58:44,141 INFO [train.py:812] (2/8) Epoch 28, batch 4350, loss[loss=0.1557, simple_loss=0.2521, pruned_loss=0.02962, over 7223.00 frames.], tot_loss[loss=0.1563, simple_loss=0.248, pruned_loss=0.03232, over 1417366.27 frames.], batch size: 21, lr: 2.76e-04
+2022-05-15 13:59:42,418 INFO [train.py:812] (2/8) Epoch 28, batch 4400, loss[loss=0.1516, simple_loss=0.2569, pruned_loss=0.02313, over 6444.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2471, pruned_loss=0.03193, over 1409094.11 frames.], batch size: 37, lr: 2.76e-04
+2022-05-15 14:00:51,518 INFO [train.py:812] (2/8) Epoch 28, batch 4450, loss[loss=0.12, simple_loss=0.2029, pruned_loss=0.01851, over 6847.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2474, pruned_loss=0.03248, over 1404403.32 frames.], batch size: 15, lr: 2.76e-04
+2022-05-15 14:01:50,414 INFO [train.py:812] (2/8) Epoch 28, batch 4500, loss[loss=0.1678, simple_loss=0.2697, pruned_loss=0.03297, over 7222.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2475, pruned_loss=0.03248, over 1391227.69 frames.], batch size: 21, lr: 2.76e-04
+2022-05-15 14:02:49,656 INFO [train.py:812] (2/8) Epoch 28, batch 4550, loss[loss=0.1634, simple_loss=0.2593, pruned_loss=0.03378, over 6505.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2481, pruned_loss=0.03319, over 1361605.88 frames.], batch size: 38, lr: 2.76e-04
+2022-05-15 14:04:01,547 INFO [train.py:812] (2/8) Epoch 29, batch 0, loss[loss=0.1606, simple_loss=0.2672, pruned_loss=0.02697, over 7109.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2672, pruned_loss=0.02697, over 7109.00 frames.], batch size: 28, lr: 2.71e-04
+2022-05-15 14:05:00,865 INFO [train.py:812] (2/8) Epoch 29, batch 50, loss[loss=0.1592, simple_loss=0.2609, pruned_loss=0.02877, over 7288.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2478, pruned_loss=0.03301, over 323180.77 frames.], batch size: 24, lr: 2.71e-04
+2022-05-15 14:05:59,990 INFO [train.py:812] (2/8) Epoch 29, batch 100, loss[loss=0.1817, simple_loss=0.2767, pruned_loss=0.04336, over 7318.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2477, pruned_loss=0.03309, over 568774.16 frames.], batch size: 21, lr: 2.71e-04
+2022-05-15 14:06:58,558 INFO [train.py:812] (2/8) Epoch 29, batch 150, loss[loss=0.1405, simple_loss=0.2415, pruned_loss=0.01977, over 7239.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2475, pruned_loss=0.0322, over 758951.03 frames.], batch size: 20, lr: 2.71e-04
+2022-05-15 14:07:56,833 INFO [train.py:812] (2/8) Epoch 29, batch 200, loss[loss=0.1431, simple_loss=0.2309, pruned_loss=0.02767, over 7063.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2454, pruned_loss=0.03105, over 908241.53 frames.], batch size: 18, lr: 2.71e-04
+2022-05-15 14:08:56,091 INFO [train.py:812] (2/8) Epoch 29, batch 250, loss[loss=0.1753, simple_loss=0.2577, pruned_loss=0.04644, over 5194.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03089, over 1019054.66 frames.], batch size: 54, lr: 2.71e-04
+2022-05-15 14:09:54,911 INFO [train.py:812] (2/8) Epoch 29, batch 300, loss[loss=0.1734, simple_loss=0.2529, pruned_loss=0.04693, over 7170.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2462, pruned_loss=0.03149, over 1108676.99 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:10:53,103 INFO [train.py:812] (2/8) Epoch 29, batch 350, loss[loss=0.1526, simple_loss=0.2393, pruned_loss=0.03297, over 7061.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2461, pruned_loss=0.03128, over 1180311.10 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:11:51,409 INFO [train.py:812] (2/8) Epoch 29, batch 400, loss[loss=0.1584, simple_loss=0.2545, pruned_loss=0.0311, over 7142.00 frames.], tot_loss[loss=0.1539, simple_loss=0.246, pruned_loss=0.03089, over 1236208.86 frames.], batch size: 20, lr: 2.70e-04
+2022-05-15 14:12:49,826 INFO [train.py:812] (2/8) Epoch 29, batch 450, loss[loss=0.1644, simple_loss=0.264, pruned_loss=0.03245, over 7105.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2463, pruned_loss=0.03137, over 1282527.70 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:13:47,245 INFO [train.py:812] (2/8) Epoch 29, batch 500, loss[loss=0.1858, simple_loss=0.2851, pruned_loss=0.04326, over 4819.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2463, pruned_loss=0.03158, over 1309992.32 frames.], batch size: 52, lr: 2.70e-04
+2022-05-15 14:14:46,076 INFO [train.py:812] (2/8) Epoch 29, batch 550, loss[loss=0.1669, simple_loss=0.2532, pruned_loss=0.04031, over 7215.00 frames.], tot_loss[loss=0.1555, simple_loss=0.247, pruned_loss=0.032, over 1332084.91 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:15:44,271 INFO [train.py:812] (2/8) Epoch 29, batch 600, loss[loss=0.1549, simple_loss=0.2403, pruned_loss=0.03479, over 7262.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2459, pruned_loss=0.03156, over 1348723.86 frames.], batch size: 19, lr: 2.70e-04
+2022-05-15 14:16:43,601 INFO [train.py:812] (2/8) Epoch 29, batch 650, loss[loss=0.1565, simple_loss=0.2374, pruned_loss=0.03776, over 7060.00 frames.], tot_loss[loss=0.1539, simple_loss=0.245, pruned_loss=0.03141, over 1367142.59 frames.], batch size: 18, lr: 2.70e-04
+2022-05-15 14:17:43,340 INFO [train.py:812] (2/8) Epoch 29, batch 700, loss[loss=0.1492, simple_loss=0.2373, pruned_loss=0.03053, over 4910.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2452, pruned_loss=0.03155, over 1376156.13 frames.], batch size: 52, lr: 2.70e-04
+2022-05-15 14:18:41,551 INFO [train.py:812] (2/8) Epoch 29, batch 750, loss[loss=0.1411, simple_loss=0.2397, pruned_loss=0.02124, over 7429.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2451, pruned_loss=0.03139, over 1382445.03 frames.], batch size: 20, lr: 2.70e-04
+2022-05-15 14:19:40,276 INFO [train.py:812] (2/8) Epoch 29, batch 800, loss[loss=0.148, simple_loss=0.2469, pruned_loss=0.02457, over 7126.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2456, pruned_loss=0.03151, over 1388093.76 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:20:39,292 INFO [train.py:812] (2/8) Epoch 29, batch 850, loss[loss=0.171, simple_loss=0.2552, pruned_loss=0.04338, over 6427.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2462, pruned_loss=0.0316, over 1393115.22 frames.], batch size: 37, lr: 2.70e-04
+2022-05-15 14:21:38,044 INFO [train.py:812] (2/8) Epoch 29, batch 900, loss[loss=0.1586, simple_loss=0.2494, pruned_loss=0.03392, over 6720.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2458, pruned_loss=0.03131, over 1399776.77 frames.], batch size: 31, lr: 2.70e-04
+2022-05-15 14:22:37,042 INFO [train.py:812] (2/8) Epoch 29, batch 950, loss[loss=0.1496, simple_loss=0.2482, pruned_loss=0.02546, over 7187.00 frames.], tot_loss[loss=0.154, simple_loss=0.2454, pruned_loss=0.03135, over 1408634.03 frames.], batch size: 22, lr: 2.70e-04
+2022-05-15 14:23:36,640 INFO [train.py:812] (2/8) Epoch 29, batch 1000, loss[loss=0.1637, simple_loss=0.2486, pruned_loss=0.03939, over 6793.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2446, pruned_loss=0.03136, over 1414463.81 frames.], batch size: 15, lr: 2.70e-04
+2022-05-15 14:24:36,188 INFO [train.py:812] (2/8) Epoch 29, batch 1050, loss[loss=0.1441, simple_loss=0.2411, pruned_loss=0.02351, over 7422.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.03074, over 1419553.62 frames.], batch size: 21, lr: 2.70e-04
+2022-05-15 14:25:35,346 INFO [train.py:812] (2/8) Epoch 29, batch 1100, loss[loss=0.1427, simple_loss=0.2258, pruned_loss=0.02978, over 7275.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2446, pruned_loss=0.03059, over 1422432.00 frames.], batch size: 17, lr: 2.70e-04
+2022-05-15 14:26:34,944 INFO [train.py:812] (2/8) Epoch 29, batch 1150, loss[loss=0.1735, simple_loss=0.2653, pruned_loss=0.04085, over 7066.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2455, pruned_loss=0.03116, over 1421773.53 frames.], batch size: 28, lr: 2.70e-04
+2022-05-15 14:27:33,738 INFO [train.py:812] (2/8) Epoch 29, batch 1200, loss[loss=0.1552, simple_loss=0.2495, pruned_loss=0.03045, over 7082.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2465, pruned_loss=0.03137, over 1424634.37 frames.], batch size: 28, lr: 2.70e-04
+2022-05-15 14:28:32,478 INFO [train.py:812] (2/8) Epoch 29, batch 1250, loss[loss=0.1748, simple_loss=0.2677, pruned_loss=0.04094, over 7198.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2462, pruned_loss=0.03146, over 1419520.39 frames.], batch size: 22, lr: 2.70e-04
+2022-05-15 14:29:29,505 INFO [train.py:812] (2/8) Epoch 29, batch 1300, loss[loss=0.1469, simple_loss=0.2448, pruned_loss=0.02447, over 7144.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2457, pruned_loss=0.031, over 1421998.15 frames.], batch size: 20, lr: 2.69e-04
+2022-05-15 14:30:28,424 INFO [train.py:812] (2/8) Epoch 29, batch 1350, loss[loss=0.1467, simple_loss=0.2473, pruned_loss=0.02306, over 7118.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.03102, over 1427035.54 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:31:27,372 INFO [train.py:812] (2/8) Epoch 29, batch 1400, loss[loss=0.152, simple_loss=0.2257, pruned_loss=0.03912, over 7293.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2454, pruned_loss=0.03118, over 1428415.64 frames.], batch size: 17, lr: 2.69e-04
+2022-05-15 14:32:26,335 INFO [train.py:812] (2/8) Epoch 29, batch 1450, loss[loss=0.1645, simple_loss=0.2585, pruned_loss=0.03518, over 7275.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2454, pruned_loss=0.03117, over 1432237.13 frames.], batch size: 24, lr: 2.69e-04
+2022-05-15 14:33:24,398 INFO [train.py:812] (2/8) Epoch 29, batch 1500, loss[loss=0.1615, simple_loss=0.247, pruned_loss=0.038, over 7328.00 frames.], tot_loss[loss=0.1546, simple_loss=0.246, pruned_loss=0.03157, over 1428321.83 frames.], batch size: 20, lr: 2.69e-04
+2022-05-15 14:34:23,846 INFO [train.py:812] (2/8) Epoch 29, batch 1550, loss[loss=0.1693, simple_loss=0.2694, pruned_loss=0.03461, over 7220.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03133, over 1430043.86 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:35:22,640 INFO [train.py:812] (2/8) Epoch 29, batch 1600, loss[loss=0.1165, simple_loss=0.2057, pruned_loss=0.01366, over 6760.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2462, pruned_loss=0.03139, over 1427731.40 frames.], batch size: 15, lr: 2.69e-04
+2022-05-15 14:36:22,716 INFO [train.py:812] (2/8) Epoch 29, batch 1650, loss[loss=0.1259, simple_loss=0.2096, pruned_loss=0.02107, over 6764.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2457, pruned_loss=0.03148, over 1429119.39 frames.], batch size: 15, lr: 2.69e-04
+2022-05-15 14:37:22,178 INFO [train.py:812] (2/8) Epoch 29, batch 1700, loss[loss=0.1447, simple_loss=0.2398, pruned_loss=0.02475, over 7262.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.03104, over 1431301.84 frames.], batch size: 19, lr: 2.69e-04
+2022-05-15 14:38:21,727 INFO [train.py:812] (2/8) Epoch 29, batch 1750, loss[loss=0.1298, simple_loss=0.2326, pruned_loss=0.01348, over 7109.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2452, pruned_loss=0.03111, over 1433421.17 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:39:20,837 INFO [train.py:812] (2/8) Epoch 29, batch 1800, loss[loss=0.1507, simple_loss=0.2309, pruned_loss=0.03521, over 7425.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2448, pruned_loss=0.03095, over 1423492.47 frames.], batch size: 17, lr: 2.69e-04
+2022-05-15 14:40:20,275 INFO [train.py:812] (2/8) Epoch 29, batch 1850, loss[loss=0.142, simple_loss=0.2278, pruned_loss=0.02806, over 7410.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2448, pruned_loss=0.03111, over 1426018.83 frames.], batch size: 18, lr: 2.69e-04
+2022-05-15 14:41:18,791 INFO [train.py:812] (2/8) Epoch 29, batch 1900, loss[loss=0.1532, simple_loss=0.2429, pruned_loss=0.0318, over 7156.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2439, pruned_loss=0.03054, over 1426045.52 frames.], batch size: 26, lr: 2.69e-04
+2022-05-15 14:42:17,742 INFO [train.py:812] (2/8) Epoch 29, batch 1950, loss[loss=0.174, simple_loss=0.2674, pruned_loss=0.04028, over 7330.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2441, pruned_loss=0.03057, over 1427819.98 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:43:16,651 INFO [train.py:812] (2/8) Epoch 29, batch 2000, loss[loss=0.163, simple_loss=0.2559, pruned_loss=0.03509, over 7206.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2444, pruned_loss=0.03061, over 1430762.07 frames.], batch size: 23, lr: 2.69e-04
+2022-05-15 14:44:14,137 INFO [train.py:812] (2/8) Epoch 29, batch 2050, loss[loss=0.1655, simple_loss=0.2673, pruned_loss=0.03191, over 7324.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2444, pruned_loss=0.03048, over 1424047.69 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:45:11,929 INFO [train.py:812] (2/8) Epoch 29, batch 2100, loss[loss=0.1939, simple_loss=0.2902, pruned_loss=0.04874, over 7290.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2434, pruned_loss=0.03005, over 1425347.84 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:46:11,706 INFO [train.py:812] (2/8) Epoch 29, batch 2150, loss[loss=0.1737, simple_loss=0.2616, pruned_loss=0.04291, over 7217.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.03043, over 1426169.61 frames.], batch size: 21, lr: 2.69e-04
+2022-05-15 14:47:09,930 INFO [train.py:812] (2/8) Epoch 29, batch 2200, loss[loss=0.17, simple_loss=0.2607, pruned_loss=0.03967, over 7294.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2445, pruned_loss=0.03054, over 1420702.80 frames.], batch size: 25, lr: 2.69e-04
+2022-05-15 14:48:08,318 INFO [train.py:812] (2/8) Epoch 29, batch 2250, loss[loss=0.1634, simple_loss=0.262, pruned_loss=0.03234, over 7121.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03089, over 1425396.86 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:49:05,765 INFO [train.py:812] (2/8) Epoch 29, batch 2300, loss[loss=0.1718, simple_loss=0.2583, pruned_loss=0.04261, over 7327.00 frames.], tot_loss[loss=0.153, simple_loss=0.2449, pruned_loss=0.03052, over 1426866.49 frames.], batch size: 24, lr: 2.68e-04
+2022-05-15 14:50:03,943 INFO [train.py:812] (2/8) Epoch 29, batch 2350, loss[loss=0.1404, simple_loss=0.2271, pruned_loss=0.02682, over 7065.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2455, pruned_loss=0.03087, over 1424483.48 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:51:02,208 INFO [train.py:812] (2/8) Epoch 29, batch 2400, loss[loss=0.1641, simple_loss=0.2528, pruned_loss=0.03772, over 7357.00 frames.], tot_loss[loss=0.153, simple_loss=0.2448, pruned_loss=0.03058, over 1425554.99 frames.], batch size: 19, lr: 2.68e-04
+2022-05-15 14:51:59,576 INFO [train.py:812] (2/8) Epoch 29, batch 2450, loss[loss=0.1472, simple_loss=0.2377, pruned_loss=0.02839, over 7107.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2458, pruned_loss=0.03125, over 1417404.90 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:52:57,610 INFO [train.py:812] (2/8) Epoch 29, batch 2500, loss[loss=0.1278, simple_loss=0.2187, pruned_loss=0.01842, over 7416.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2444, pruned_loss=0.03064, over 1420249.54 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:53:56,703 INFO [train.py:812] (2/8) Epoch 29, batch 2550, loss[loss=0.135, simple_loss=0.2203, pruned_loss=0.02488, over 7154.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2446, pruned_loss=0.03082, over 1417365.48 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:54:55,315 INFO [train.py:812] (2/8) Epoch 29, batch 2600, loss[loss=0.1648, simple_loss=0.2608, pruned_loss=0.03438, over 7203.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2444, pruned_loss=0.03086, over 1416680.79 frames.], batch size: 23, lr: 2.68e-04
+2022-05-15 14:56:04,286 INFO [train.py:812] (2/8) Epoch 29, batch 2650, loss[loss=0.1375, simple_loss=0.222, pruned_loss=0.02652, over 7405.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2444, pruned_loss=0.03113, over 1418743.49 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 14:57:02,545 INFO [train.py:812] (2/8) Epoch 29, batch 2700, loss[loss=0.1949, simple_loss=0.2654, pruned_loss=0.06224, over 5062.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2441, pruned_loss=0.03124, over 1418592.93 frames.], batch size: 52, lr: 2.68e-04
+2022-05-15 14:58:00,029 INFO [train.py:812] (2/8) Epoch 29, batch 2750, loss[loss=0.1582, simple_loss=0.2478, pruned_loss=0.03436, over 7316.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2453, pruned_loss=0.03163, over 1413544.53 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 14:59:07,971 INFO [train.py:812] (2/8) Epoch 29, batch 2800, loss[loss=0.174, simple_loss=0.275, pruned_loss=0.0365, over 7335.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2456, pruned_loss=0.03127, over 1417522.15 frames.], batch size: 22, lr: 2.68e-04
+2022-05-15 15:00:06,415 INFO [train.py:812] (2/8) Epoch 29, batch 2850, loss[loss=0.1251, simple_loss=0.2146, pruned_loss=0.01784, over 7263.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2446, pruned_loss=0.03082, over 1418560.07 frames.], batch size: 19, lr: 2.68e-04
+2022-05-15 15:01:14,252 INFO [train.py:812] (2/8) Epoch 29, batch 2900, loss[loss=0.1384, simple_loss=0.2181, pruned_loss=0.02934, over 7287.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2447, pruned_loss=0.03083, over 1418030.94 frames.], batch size: 17, lr: 2.68e-04
+2022-05-15 15:02:42,658 INFO [train.py:812] (2/8) Epoch 29, batch 2950, loss[loss=0.1255, simple_loss=0.2066, pruned_loss=0.0222, over 7143.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2433, pruned_loss=0.03083, over 1417886.61 frames.], batch size: 17, lr: 2.68e-04
+2022-05-15 15:03:40,336 INFO [train.py:812] (2/8) Epoch 29, batch 3000, loss[loss=0.1451, simple_loss=0.2405, pruned_loss=0.02486, over 7236.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2443, pruned_loss=0.03071, over 1418666.28 frames.], batch size: 20, lr: 2.68e-04
+2022-05-15 15:03:40,337 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 15:03:47,851 INFO [train.py:841] (2/8) Epoch 29, validation: loss=0.153, simple_loss=0.2498, pruned_loss=0.02809, over 698248.00 frames.
+2022-05-15 15:04:46,862 INFO [train.py:812] (2/8) Epoch 29, batch 3050, loss[loss=0.159, simple_loss=0.2483, pruned_loss=0.03489, over 7150.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03088, over 1421553.00 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 15:05:54,530 INFO [train.py:812] (2/8) Epoch 29, batch 3100, loss[loss=0.1321, simple_loss=0.2194, pruned_loss=0.02241, over 7272.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2436, pruned_loss=0.03066, over 1418669.30 frames.], batch size: 18, lr: 2.68e-04
+2022-05-15 15:06:53,592 INFO [train.py:812] (2/8) Epoch 29, batch 3150, loss[loss=0.1773, simple_loss=0.2828, pruned_loss=0.03589, over 7224.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03073, over 1422546.54 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 15:07:52,440 INFO [train.py:812] (2/8) Epoch 29, batch 3200, loss[loss=0.1463, simple_loss=0.2467, pruned_loss=0.02295, over 7098.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2451, pruned_loss=0.03077, over 1422170.56 frames.], batch size: 21, lr: 2.68e-04
+2022-05-15 15:08:52,119 INFO [train.py:812] (2/8) Epoch 29, batch 3250, loss[loss=0.1271, simple_loss=0.2156, pruned_loss=0.01927, over 7260.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.0308, over 1422891.59 frames.], batch size: 16, lr: 2.67e-04
+2022-05-15 15:09:50,368 INFO [train.py:812] (2/8) Epoch 29, batch 3300, loss[loss=0.1576, simple_loss=0.2521, pruned_loss=0.03148, over 7222.00 frames.], tot_loss[loss=0.154, simple_loss=0.2457, pruned_loss=0.03112, over 1421831.41 frames.], batch size: 21, lr: 2.67e-04
+2022-05-15 15:10:48,351 INFO [train.py:812] (2/8) Epoch 29, batch 3350, loss[loss=0.1682, simple_loss=0.2586, pruned_loss=0.03886, over 7122.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2453, pruned_loss=0.03112, over 1419701.18 frames.], batch size: 28, lr: 2.67e-04
+2022-05-15 15:11:47,202 INFO [train.py:812] (2/8) Epoch 29, batch 3400, loss[loss=0.1641, simple_loss=0.2536, pruned_loss=0.03729, over 7068.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2452, pruned_loss=0.03113, over 1417798.04 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:12:46,910 INFO [train.py:812] (2/8) Epoch 29, batch 3450, loss[loss=0.1358, simple_loss=0.2176, pruned_loss=0.02699, over 7275.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2453, pruned_loss=0.03115, over 1419349.73 frames.], batch size: 17, lr: 2.67e-04
+2022-05-15 15:13:45,908 INFO [train.py:812] (2/8) Epoch 29, batch 3500, loss[loss=0.1407, simple_loss=0.2363, pruned_loss=0.02253, over 6792.00 frames.], tot_loss[loss=0.1536, simple_loss=0.245, pruned_loss=0.03106, over 1419187.52 frames.], batch size: 31, lr: 2.67e-04
+2022-05-15 15:14:51,711 INFO [train.py:812] (2/8) Epoch 29, batch 3550, loss[loss=0.1283, simple_loss=0.2191, pruned_loss=0.01875, over 7298.00 frames.], tot_loss[loss=0.153, simple_loss=0.2443, pruned_loss=0.03079, over 1423433.57 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:15:51,041 INFO [train.py:812] (2/8) Epoch 29, batch 3600, loss[loss=0.1286, simple_loss=0.2168, pruned_loss=0.02023, over 6783.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2449, pruned_loss=0.03096, over 1423555.38 frames.], batch size: 15, lr: 2.67e-04
+2022-05-15 15:16:50,742 INFO [train.py:812] (2/8) Epoch 29, batch 3650, loss[loss=0.1714, simple_loss=0.2657, pruned_loss=0.0385, over 7326.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03069, over 1426614.83 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:17:49,972 INFO [train.py:812] (2/8) Epoch 29, batch 3700, loss[loss=0.163, simple_loss=0.2588, pruned_loss=0.03362, over 7193.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2449, pruned_loss=0.03075, over 1426360.45 frames.], batch size: 23, lr: 2.67e-04
+2022-05-15 15:18:49,037 INFO [train.py:812] (2/8) Epoch 29, batch 3750, loss[loss=0.1928, simple_loss=0.2801, pruned_loss=0.05276, over 4994.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2454, pruned_loss=0.03103, over 1425607.81 frames.], batch size: 52, lr: 2.67e-04
+2022-05-15 15:19:48,067 INFO [train.py:812] (2/8) Epoch 29, batch 3800, loss[loss=0.1517, simple_loss=0.248, pruned_loss=0.02766, over 7435.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.03108, over 1426364.28 frames.], batch size: 20, lr: 2.67e-04
+2022-05-15 15:20:46,938 INFO [train.py:812] (2/8) Epoch 29, batch 3850, loss[loss=0.1772, simple_loss=0.2752, pruned_loss=0.0396, over 7390.00 frames.], tot_loss[loss=0.1542, simple_loss=0.246, pruned_loss=0.03121, over 1426951.35 frames.], batch size: 23, lr: 2.67e-04
+2022-05-15 15:21:44,961 INFO [train.py:812] (2/8) Epoch 29, batch 3900, loss[loss=0.1566, simple_loss=0.2488, pruned_loss=0.03223, over 7297.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2459, pruned_loss=0.03113, over 1429646.05 frames.], batch size: 24, lr: 2.67e-04
+2022-05-15 15:22:44,170 INFO [train.py:812] (2/8) Epoch 29, batch 3950, loss[loss=0.1257, simple_loss=0.2145, pruned_loss=0.01845, over 7412.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2471, pruned_loss=0.03137, over 1430767.47 frames.], batch size: 18, lr: 2.67e-04
+2022-05-15 15:23:43,019 INFO [train.py:812] (2/8) Epoch 29, batch 4000, loss[loss=0.1543, simple_loss=0.2523, pruned_loss=0.0282, over 7352.00 frames.], tot_loss[loss=0.155, simple_loss=0.247, pruned_loss=0.0315, over 1430202.73 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:24:42,291 INFO [train.py:812] (2/8) Epoch 29, batch 4050, loss[loss=0.1276, simple_loss=0.2126, pruned_loss=0.02124, over 7269.00 frames.], tot_loss[loss=0.155, simple_loss=0.2468, pruned_loss=0.03162, over 1428909.50 frames.], batch size: 17, lr: 2.67e-04
+2022-05-15 15:25:40,981 INFO [train.py:812] (2/8) Epoch 29, batch 4100, loss[loss=0.175, simple_loss=0.2759, pruned_loss=0.03708, over 7330.00 frames.], tot_loss[loss=0.1553, simple_loss=0.247, pruned_loss=0.03179, over 1429678.42 frames.], batch size: 22, lr: 2.67e-04
+2022-05-15 15:26:40,393 INFO [train.py:812] (2/8) Epoch 29, batch 4150, loss[loss=0.147, simple_loss=0.2485, pruned_loss=0.02276, over 7330.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2462, pruned_loss=0.03138, over 1423591.48 frames.], batch size: 21, lr: 2.67e-04
+2022-05-15 15:27:39,315 INFO [train.py:812] (2/8) Epoch 29, batch 4200, loss[loss=0.1449, simple_loss=0.2367, pruned_loss=0.02655, over 7257.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2459, pruned_loss=0.03126, over 1420132.90 frames.], batch size: 19, lr: 2.66e-04
+2022-05-15 15:28:38,670 INFO [train.py:812] (2/8) Epoch 29, batch 4250, loss[loss=0.1554, simple_loss=0.2534, pruned_loss=0.02867, over 6848.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.03092, over 1421281.19 frames.], batch size: 31, lr: 2.66e-04
+2022-05-15 15:29:36,727 INFO [train.py:812] (2/8) Epoch 29, batch 4300, loss[loss=0.1692, simple_loss=0.2477, pruned_loss=0.0453, over 7166.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03076, over 1417601.51 frames.], batch size: 18, lr: 2.66e-04
+2022-05-15 15:30:35,682 INFO [train.py:812] (2/8) Epoch 29, batch 4350, loss[loss=0.1453, simple_loss=0.2399, pruned_loss=0.02537, over 7322.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03085, over 1418588.49 frames.], batch size: 21, lr: 2.66e-04
+2022-05-15 15:31:34,533 INFO [train.py:812] (2/8) Epoch 29, batch 4400, loss[loss=0.1704, simple_loss=0.2709, pruned_loss=0.03498, over 7280.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2454, pruned_loss=0.03115, over 1410867.24 frames.], batch size: 24, lr: 2.66e-04
+2022-05-15 15:32:33,522 INFO [train.py:812] (2/8) Epoch 29, batch 4450, loss[loss=0.1642, simple_loss=0.256, pruned_loss=0.03619, over 6464.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.03109, over 1402109.20 frames.], batch size: 38, lr: 2.66e-04
+2022-05-15 15:33:31,916 INFO [train.py:812] (2/8) Epoch 29, batch 4500, loss[loss=0.166, simple_loss=0.2609, pruned_loss=0.03549, over 7203.00 frames.], tot_loss[loss=0.155, simple_loss=0.2467, pruned_loss=0.03162, over 1379657.51 frames.], batch size: 22, lr: 2.66e-04
+2022-05-15 15:34:29,704 INFO [train.py:812] (2/8) Epoch 29, batch 4550, loss[loss=0.1677, simple_loss=0.2582, pruned_loss=0.03856, over 5173.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2478, pruned_loss=0.03213, over 1360113.02 frames.], batch size: 52, lr: 2.66e-04
+2022-05-15 15:35:40,813 INFO [train.py:812] (2/8) Epoch 30, batch 0, loss[loss=0.1325, simple_loss=0.2251, pruned_loss=0.01994, over 7331.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2251, pruned_loss=0.01994, over 7331.00 frames.], batch size: 20, lr: 2.62e-04
+2022-05-15 15:36:39,957 INFO [train.py:812] (2/8) Epoch 30, batch 50, loss[loss=0.1529, simple_loss=0.2366, pruned_loss=0.03457, over 7282.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2449, pruned_loss=0.03117, over 324231.20 frames.], batch size: 18, lr: 2.62e-04
+2022-05-15 15:37:39,028 INFO [train.py:812] (2/8) Epoch 30, batch 100, loss[loss=0.138, simple_loss=0.2153, pruned_loss=0.03036, over 7278.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2424, pruned_loss=0.03048, over 572172.62 frames.], batch size: 17, lr: 2.62e-04
+2022-05-15 15:38:38,754 INFO [train.py:812] (2/8) Epoch 30, batch 150, loss[loss=0.1668, simple_loss=0.2634, pruned_loss=0.03509, over 7309.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2446, pruned_loss=0.03201, over 749737.16 frames.], batch size: 24, lr: 2.62e-04
+2022-05-15 15:39:36,196 INFO [train.py:812] (2/8) Epoch 30, batch 200, loss[loss=0.1543, simple_loss=0.2452, pruned_loss=0.03173, over 7358.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2454, pruned_loss=0.03206, over 899945.73 frames.], batch size: 19, lr: 2.61e-04
+2022-05-15 15:40:35,796 INFO [train.py:812] (2/8) Epoch 30, batch 250, loss[loss=0.1385, simple_loss=0.2258, pruned_loss=0.02556, over 6830.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03142, over 1016239.85 frames.], batch size: 15, lr: 2.61e-04
+2022-05-15 15:41:34,898 INFO [train.py:812] (2/8) Epoch 30, batch 300, loss[loss=0.1396, simple_loss=0.2316, pruned_loss=0.02383, over 7278.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2466, pruned_loss=0.03127, over 1109003.14 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:42:33,926 INFO [train.py:812] (2/8) Epoch 30, batch 350, loss[loss=0.1456, simple_loss=0.2363, pruned_loss=0.02751, over 7340.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.03104, over 1181409.11 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:43:32,150 INFO [train.py:812] (2/8) Epoch 30, batch 400, loss[loss=0.1547, simple_loss=0.2544, pruned_loss=0.02744, over 7273.00 frames.], tot_loss[loss=0.1541, simple_loss=0.246, pruned_loss=0.03107, over 1237473.98 frames.], batch size: 24, lr: 2.61e-04
+2022-05-15 15:44:30,885 INFO [train.py:812] (2/8) Epoch 30, batch 450, loss[loss=0.1394, simple_loss=0.2407, pruned_loss=0.01901, over 7417.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.03108, over 1279460.90 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:45:28,630 INFO [train.py:812] (2/8) Epoch 30, batch 500, loss[loss=0.1472, simple_loss=0.2329, pruned_loss=0.03073, over 7330.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2452, pruned_loss=0.0311, over 1307778.42 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:46:27,331 INFO [train.py:812] (2/8) Epoch 30, batch 550, loss[loss=0.1771, simple_loss=0.2689, pruned_loss=0.04265, over 7274.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2458, pruned_loss=0.03116, over 1335589.53 frames.], batch size: 24, lr: 2.61e-04
+2022-05-15 15:47:24,857 INFO [train.py:812] (2/8) Epoch 30, batch 600, loss[loss=0.1573, simple_loss=0.2471, pruned_loss=0.03376, over 7205.00 frames.], tot_loss[loss=0.1543, simple_loss=0.246, pruned_loss=0.03133, over 1351031.81 frames.], batch size: 22, lr: 2.61e-04
+2022-05-15 15:48:22,461 INFO [train.py:812] (2/8) Epoch 30, batch 650, loss[loss=0.1555, simple_loss=0.2387, pruned_loss=0.03613, over 7071.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2462, pruned_loss=0.03122, over 1366079.68 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:49:20,306 INFO [train.py:812] (2/8) Epoch 30, batch 700, loss[loss=0.1537, simple_loss=0.2402, pruned_loss=0.0336, over 7332.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2471, pruned_loss=0.03178, over 1374467.66 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:50:18,865 INFO [train.py:812] (2/8) Epoch 30, batch 750, loss[loss=0.124, simple_loss=0.2149, pruned_loss=0.01661, over 7239.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.03153, over 1382045.50 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:51:17,426 INFO [train.py:812] (2/8) Epoch 30, batch 800, loss[loss=0.1599, simple_loss=0.264, pruned_loss=0.02786, over 7339.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2461, pruned_loss=0.03146, over 1388384.21 frames.], batch size: 22, lr: 2.61e-04
+2022-05-15 15:52:16,530 INFO [train.py:812] (2/8) Epoch 30, batch 850, loss[loss=0.1438, simple_loss=0.2379, pruned_loss=0.02482, over 7060.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2444, pruned_loss=0.0309, over 1397196.60 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:53:14,182 INFO [train.py:812] (2/8) Epoch 30, batch 900, loss[loss=0.1659, simple_loss=0.2612, pruned_loss=0.03528, over 7227.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2449, pruned_loss=0.03122, over 1401427.57 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:54:13,180 INFO [train.py:812] (2/8) Epoch 30, batch 950, loss[loss=0.1426, simple_loss=0.2339, pruned_loss=0.02564, over 7112.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2456, pruned_loss=0.03148, over 1407713.20 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:55:11,580 INFO [train.py:812] (2/8) Epoch 30, batch 1000, loss[loss=0.1669, simple_loss=0.2613, pruned_loss=0.03629, over 7157.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2465, pruned_loss=0.03125, over 1411574.78 frames.], batch size: 20, lr: 2.61e-04
+2022-05-15 15:56:10,065 INFO [train.py:812] (2/8) Epoch 30, batch 1050, loss[loss=0.1324, simple_loss=0.2193, pruned_loss=0.02281, over 7262.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2468, pruned_loss=0.03148, over 1408052.58 frames.], batch size: 18, lr: 2.61e-04
+2022-05-15 15:57:08,269 INFO [train.py:812] (2/8) Epoch 30, batch 1100, loss[loss=0.1678, simple_loss=0.2546, pruned_loss=0.04056, over 7326.00 frames.], tot_loss[loss=0.1557, simple_loss=0.248, pruned_loss=0.0317, over 1417397.20 frames.], batch size: 21, lr: 2.61e-04
+2022-05-15 15:58:07,686 INFO [train.py:812] (2/8) Epoch 30, batch 1150, loss[loss=0.1465, simple_loss=0.2297, pruned_loss=0.03167, over 6994.00 frames.], tot_loss[loss=0.1555, simple_loss=0.248, pruned_loss=0.03155, over 1418908.60 frames.], batch size: 16, lr: 2.61e-04
+2022-05-15 15:59:06,098 INFO [train.py:812] (2/8) Epoch 30, batch 1200, loss[loss=0.1544, simple_loss=0.2446, pruned_loss=0.03209, over 7166.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2471, pruned_loss=0.03067, over 1423511.34 frames.], batch size: 19, lr: 2.61e-04
+2022-05-15 16:00:14,959 INFO [train.py:812] (2/8) Epoch 30, batch 1250, loss[loss=0.1663, simple_loss=0.2484, pruned_loss=0.04211, over 4927.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2462, pruned_loss=0.0306, over 1418248.13 frames.], batch size: 53, lr: 2.60e-04
+2022-05-15 16:01:13,727 INFO [train.py:812] (2/8) Epoch 30, batch 1300, loss[loss=0.142, simple_loss=0.2391, pruned_loss=0.02241, over 7347.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2457, pruned_loss=0.03054, over 1419726.74 frames.], batch size: 22, lr: 2.60e-04
+2022-05-15 16:02:13,437 INFO [train.py:812] (2/8) Epoch 30, batch 1350, loss[loss=0.1804, simple_loss=0.2696, pruned_loss=0.04559, over 6511.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2467, pruned_loss=0.03117, over 1420542.27 frames.], batch size: 38, lr: 2.60e-04
+2022-05-15 16:03:12,436 INFO [train.py:812] (2/8) Epoch 30, batch 1400, loss[loss=0.1628, simple_loss=0.2305, pruned_loss=0.0475, over 7178.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2464, pruned_loss=0.0312, over 1420998.53 frames.], batch size: 16, lr: 2.60e-04
+2022-05-15 16:04:10,792 INFO [train.py:812] (2/8) Epoch 30, batch 1450, loss[loss=0.1459, simple_loss=0.2511, pruned_loss=0.02037, over 7116.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2459, pruned_loss=0.03073, over 1419458.11 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:05:09,037 INFO [train.py:812] (2/8) Epoch 30, batch 1500, loss[loss=0.1367, simple_loss=0.2277, pruned_loss=0.02283, over 7268.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2461, pruned_loss=0.03108, over 1417884.24 frames.], batch size: 19, lr: 2.60e-04
+2022-05-15 16:06:06,397 INFO [train.py:812] (2/8) Epoch 30, batch 1550, loss[loss=0.1667, simple_loss=0.258, pruned_loss=0.03775, over 7202.00 frames.], tot_loss[loss=0.154, simple_loss=0.2457, pruned_loss=0.03115, over 1418631.40 frames.], batch size: 23, lr: 2.60e-04
+2022-05-15 16:07:03,132 INFO [train.py:812] (2/8) Epoch 30, batch 1600, loss[loss=0.1616, simple_loss=0.2638, pruned_loss=0.02973, over 7316.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2469, pruned_loss=0.03184, over 1419949.22 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:08:02,732 INFO [train.py:812] (2/8) Epoch 30, batch 1650, loss[loss=0.2038, simple_loss=0.2856, pruned_loss=0.06102, over 7184.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2465, pruned_loss=0.03155, over 1423995.16 frames.], batch size: 26, lr: 2.60e-04
+2022-05-15 16:09:00,128 INFO [train.py:812] (2/8) Epoch 30, batch 1700, loss[loss=0.1358, simple_loss=0.2233, pruned_loss=0.02417, over 7148.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2468, pruned_loss=0.03175, over 1426971.31 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:09:58,748 INFO [train.py:812] (2/8) Epoch 30, batch 1750, loss[loss=0.1768, simple_loss=0.2706, pruned_loss=0.04153, over 7150.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2465, pruned_loss=0.03149, over 1423045.85 frames.], batch size: 20, lr: 2.60e-04
+2022-05-15 16:10:56,859 INFO [train.py:812] (2/8) Epoch 30, batch 1800, loss[loss=0.1821, simple_loss=0.2741, pruned_loss=0.04504, over 4501.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2456, pruned_loss=0.03126, over 1420043.86 frames.], batch size: 52, lr: 2.60e-04
+2022-05-15 16:11:55,124 INFO [train.py:812] (2/8) Epoch 30, batch 1850, loss[loss=0.1629, simple_loss=0.2556, pruned_loss=0.03504, over 7112.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.03159, over 1424366.26 frames.], batch size: 21, lr: 2.60e-04
+2022-05-15 16:12:53,262 INFO [train.py:812] (2/8) Epoch 30, batch 1900, loss[loss=0.1386, simple_loss=0.2205, pruned_loss=0.02839, over 6852.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2459, pruned_loss=0.03146, over 1426973.19 frames.], batch size: 15, lr: 2.60e-04
+2022-05-15 16:13:52,781 INFO [train.py:812] (2/8) Epoch 30, batch 1950, loss[loss=0.1443, simple_loss=0.2234, pruned_loss=0.03265, over 7270.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2458, pruned_loss=0.03141, over 1428779.99 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:14:51,521 INFO [train.py:812] (2/8) Epoch 30, batch 2000, loss[loss=0.149, simple_loss=0.2432, pruned_loss=0.02737, over 7330.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2461, pruned_loss=0.03164, over 1430557.22 frames.], batch size: 22, lr: 2.60e-04
+2022-05-15 16:15:50,899 INFO [train.py:812] (2/8) Epoch 30, batch 2050, loss[loss=0.1814, simple_loss=0.2684, pruned_loss=0.04722, over 7188.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2458, pruned_loss=0.03135, over 1430760.40 frames.], batch size: 23, lr: 2.60e-04
+2022-05-15 16:16:49,858 INFO [train.py:812] (2/8) Epoch 30, batch 2100, loss[loss=0.1752, simple_loss=0.2695, pruned_loss=0.04049, over 7138.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2449, pruned_loss=0.03117, over 1430357.11 frames.], batch size: 20, lr: 2.60e-04
+2022-05-15 16:17:48,188 INFO [train.py:812] (2/8) Epoch 30, batch 2150, loss[loss=0.138, simple_loss=0.2272, pruned_loss=0.02437, over 7142.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.03092, over 1428367.42 frames.], batch size: 17, lr: 2.60e-04
+2022-05-15 16:18:47,069 INFO [train.py:812] (2/8) Epoch 30, batch 2200, loss[loss=0.1697, simple_loss=0.2625, pruned_loss=0.03844, over 7302.00 frames.], tot_loss[loss=0.153, simple_loss=0.2447, pruned_loss=0.0307, over 1423320.33 frames.], batch size: 24, lr: 2.60e-04
+2022-05-15 16:19:45,888 INFO [train.py:812] (2/8) Epoch 30, batch 2250, loss[loss=0.1498, simple_loss=0.2444, pruned_loss=0.02763, over 7154.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2455, pruned_loss=0.03133, over 1421848.49 frames.], batch size: 26, lr: 2.59e-04
+2022-05-15 16:20:43,568 INFO [train.py:812] (2/8) Epoch 30, batch 2300, loss[loss=0.1544, simple_loss=0.2468, pruned_loss=0.03103, over 7326.00 frames.], tot_loss[loss=0.154, simple_loss=0.2455, pruned_loss=0.03125, over 1417770.21 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:21:42,683 INFO [train.py:812] (2/8) Epoch 30, batch 2350, loss[loss=0.1577, simple_loss=0.2544, pruned_loss=0.03052, over 7339.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03078, over 1420430.28 frames.], batch size: 22, lr: 2.59e-04
+2022-05-15 16:22:41,689 INFO [train.py:812] (2/8) Epoch 30, batch 2400, loss[loss=0.154, simple_loss=0.2522, pruned_loss=0.0279, over 7281.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03062, over 1422068.97 frames.], batch size: 25, lr: 2.59e-04
+2022-05-15 16:23:41,384 INFO [train.py:812] (2/8) Epoch 30, batch 2450, loss[loss=0.1522, simple_loss=0.2496, pruned_loss=0.02737, over 7132.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2442, pruned_loss=0.03025, over 1426281.89 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:24:39,655 INFO [train.py:812] (2/8) Epoch 30, batch 2500, loss[loss=0.1412, simple_loss=0.2287, pruned_loss=0.02688, over 6793.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2433, pruned_loss=0.03009, over 1430145.16 frames.], batch size: 15, lr: 2.59e-04
+2022-05-15 16:25:38,953 INFO [train.py:812] (2/8) Epoch 30, batch 2550, loss[loss=0.1264, simple_loss=0.2094, pruned_loss=0.0217, over 7412.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2431, pruned_loss=0.03011, over 1426778.06 frames.], batch size: 18, lr: 2.59e-04
+2022-05-15 16:26:37,781 INFO [train.py:812] (2/8) Epoch 30, batch 2600, loss[loss=0.1698, simple_loss=0.2703, pruned_loss=0.03471, over 7117.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03017, over 1425490.08 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:27:37,283 INFO [train.py:812] (2/8) Epoch 30, batch 2650, loss[loss=0.1263, simple_loss=0.2114, pruned_loss=0.0206, over 7137.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2426, pruned_loss=0.02976, over 1427759.37 frames.], batch size: 17, lr: 2.59e-04
+2022-05-15 16:28:36,171 INFO [train.py:812] (2/8) Epoch 30, batch 2700, loss[loss=0.1487, simple_loss=0.2431, pruned_loss=0.02714, over 7110.00 frames.], tot_loss[loss=0.152, simple_loss=0.2436, pruned_loss=0.0302, over 1428724.57 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:29:34,404 INFO [train.py:812] (2/8) Epoch 30, batch 2750, loss[loss=0.1547, simple_loss=0.247, pruned_loss=0.03124, over 7240.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2447, pruned_loss=0.03048, over 1424788.78 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:30:32,049 INFO [train.py:812] (2/8) Epoch 30, batch 2800, loss[loss=0.1391, simple_loss=0.239, pruned_loss=0.01964, over 7339.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03073, over 1424132.34 frames.], batch size: 22, lr: 2.59e-04
+2022-05-15 16:31:31,630 INFO [train.py:812] (2/8) Epoch 30, batch 2850, loss[loss=0.1615, simple_loss=0.2559, pruned_loss=0.03355, over 7231.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2447, pruned_loss=0.03059, over 1419204.32 frames.], batch size: 20, lr: 2.59e-04
+2022-05-15 16:32:29,830 INFO [train.py:812] (2/8) Epoch 30, batch 2900, loss[loss=0.1351, simple_loss=0.2136, pruned_loss=0.02827, over 7000.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2444, pruned_loss=0.03044, over 1422628.02 frames.], batch size: 16, lr: 2.59e-04
+2022-05-15 16:33:36,391 INFO [train.py:812] (2/8) Epoch 30, batch 2950, loss[loss=0.1553, simple_loss=0.2616, pruned_loss=0.02448, over 6296.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2434, pruned_loss=0.03023, over 1423904.35 frames.], batch size: 38, lr: 2.59e-04
+2022-05-15 16:34:35,559 INFO [train.py:812] (2/8) Epoch 30, batch 3000, loss[loss=0.1464, simple_loss=0.2464, pruned_loss=0.02314, over 7117.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.03025, over 1426316.17 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:34:35,560 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 16:34:43,057 INFO [train.py:841] (2/8) Epoch 30, validation: loss=0.1528, simple_loss=0.2494, pruned_loss=0.02809, over 698248.00 frames.
+2022-05-15 16:35:41,792 INFO [train.py:812] (2/8) Epoch 30, batch 3050, loss[loss=0.151, simple_loss=0.2488, pruned_loss=0.02658, over 7117.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03013, over 1427802.84 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:36:40,846 INFO [train.py:812] (2/8) Epoch 30, batch 3100, loss[loss=0.1539, simple_loss=0.2549, pruned_loss=0.02642, over 7418.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.03006, over 1427342.00 frames.], batch size: 21, lr: 2.59e-04
+2022-05-15 16:37:40,500 INFO [train.py:812] (2/8) Epoch 30, batch 3150, loss[loss=0.1469, simple_loss=0.2313, pruned_loss=0.03132, over 7167.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2432, pruned_loss=0.03002, over 1422340.56 frames.], batch size: 18, lr: 2.59e-04
+2022-05-15 16:38:39,679 INFO [train.py:812] (2/8) Epoch 30, batch 3200, loss[loss=0.16, simple_loss=0.2477, pruned_loss=0.03612, over 7264.00 frames.], tot_loss[loss=0.1518, simple_loss=0.243, pruned_loss=0.0303, over 1425799.79 frames.], batch size: 19, lr: 2.59e-04
+2022-05-15 16:39:38,880 INFO [train.py:812] (2/8) Epoch 30, batch 3250, loss[loss=0.1781, simple_loss=0.274, pruned_loss=0.04113, over 7093.00 frames.], tot_loss[loss=0.1519, simple_loss=0.243, pruned_loss=0.0304, over 1421639.65 frames.], batch size: 28, lr: 2.59e-04
+2022-05-15 16:40:36,543 INFO [train.py:812] (2/8) Epoch 30, batch 3300, loss[loss=0.1633, simple_loss=0.2617, pruned_loss=0.03241, over 7336.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2434, pruned_loss=0.03023, over 1424402.94 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 16:41:35,439 INFO [train.py:812] (2/8) Epoch 30, batch 3350, loss[loss=0.1382, simple_loss=0.225, pruned_loss=0.02567, over 7289.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2433, pruned_loss=0.03052, over 1428252.70 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:42:33,353 INFO [train.py:812] (2/8) Epoch 30, batch 3400, loss[loss=0.1866, simple_loss=0.2545, pruned_loss=0.05937, over 4711.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2432, pruned_loss=0.03027, over 1424382.71 frames.], batch size: 52, lr: 2.58e-04
+2022-05-15 16:43:31,878 INFO [train.py:812] (2/8) Epoch 30, batch 3450, loss[loss=0.1691, simple_loss=0.2661, pruned_loss=0.03611, over 7284.00 frames.], tot_loss[loss=0.152, simple_loss=0.2433, pruned_loss=0.03038, over 1421211.55 frames.], batch size: 24, lr: 2.58e-04
+2022-05-15 16:44:30,291 INFO [train.py:812] (2/8) Epoch 30, batch 3500, loss[loss=0.1973, simple_loss=0.298, pruned_loss=0.04826, over 7190.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2438, pruned_loss=0.03066, over 1423675.99 frames.], batch size: 26, lr: 2.58e-04
+2022-05-15 16:45:29,361 INFO [train.py:812] (2/8) Epoch 30, batch 3550, loss[loss=0.143, simple_loss=0.2309, pruned_loss=0.02754, over 7162.00 frames.], tot_loss[loss=0.152, simple_loss=0.2432, pruned_loss=0.03039, over 1423013.43 frames.], batch size: 18, lr: 2.58e-04
+2022-05-15 16:46:28,170 INFO [train.py:812] (2/8) Epoch 30, batch 3600, loss[loss=0.1645, simple_loss=0.242, pruned_loss=0.04349, over 7246.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2436, pruned_loss=0.03049, over 1427501.04 frames.], batch size: 19, lr: 2.58e-04
+2022-05-15 16:47:27,378 INFO [train.py:812] (2/8) Epoch 30, batch 3650, loss[loss=0.1767, simple_loss=0.2686, pruned_loss=0.04238, over 6836.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2449, pruned_loss=0.03099, over 1429251.47 frames.], batch size: 31, lr: 2.58e-04
+2022-05-15 16:48:25,018 INFO [train.py:812] (2/8) Epoch 30, batch 3700, loss[loss=0.1368, simple_loss=0.2228, pruned_loss=0.02534, over 7274.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2444, pruned_loss=0.03071, over 1429397.55 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:49:23,804 INFO [train.py:812] (2/8) Epoch 30, batch 3750, loss[loss=0.1769, simple_loss=0.2806, pruned_loss=0.03662, over 7005.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03083, over 1432097.38 frames.], batch size: 28, lr: 2.58e-04
+2022-05-15 16:50:21,202 INFO [train.py:812] (2/8) Epoch 30, batch 3800, loss[loss=0.1634, simple_loss=0.2654, pruned_loss=0.03068, over 7225.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2458, pruned_loss=0.03081, over 1424237.99 frames.], batch size: 22, lr: 2.58e-04
+2022-05-15 16:51:18,884 INFO [train.py:812] (2/8) Epoch 30, batch 3850, loss[loss=0.1447, simple_loss=0.2267, pruned_loss=0.03138, over 6761.00 frames.], tot_loss[loss=0.153, simple_loss=0.2452, pruned_loss=0.0304, over 1424713.71 frames.], batch size: 15, lr: 2.58e-04
+2022-05-15 16:52:16,797 INFO [train.py:812] (2/8) Epoch 30, batch 3900, loss[loss=0.1589, simple_loss=0.2294, pruned_loss=0.04419, over 7139.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2455, pruned_loss=0.03073, over 1425010.04 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 16:53:15,078 INFO [train.py:812] (2/8) Epoch 30, batch 3950, loss[loss=0.1694, simple_loss=0.2525, pruned_loss=0.04311, over 7383.00 frames.], tot_loss[loss=0.154, simple_loss=0.2461, pruned_loss=0.03096, over 1419351.82 frames.], batch size: 23, lr: 2.58e-04
+2022-05-15 16:54:13,854 INFO [train.py:812] (2/8) Epoch 30, batch 4000, loss[loss=0.1687, simple_loss=0.2533, pruned_loss=0.04207, over 7274.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2477, pruned_loss=0.03157, over 1417488.82 frames.], batch size: 25, lr: 2.58e-04
+2022-05-15 16:55:12,939 INFO [train.py:812] (2/8) Epoch 30, batch 4050, loss[loss=0.1543, simple_loss=0.2456, pruned_loss=0.03157, over 7077.00 frames.], tot_loss[loss=0.155, simple_loss=0.2471, pruned_loss=0.03144, over 1417873.80 frames.], batch size: 28, lr: 2.58e-04
+2022-05-15 16:56:10,948 INFO [train.py:812] (2/8) Epoch 30, batch 4100, loss[loss=0.1794, simple_loss=0.2797, pruned_loss=0.03953, over 7328.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2467, pruned_loss=0.03105, over 1420565.46 frames.], batch size: 21, lr: 2.58e-04
+2022-05-15 16:57:19,273 INFO [train.py:812] (2/8) Epoch 30, batch 4150, loss[loss=0.1325, simple_loss=0.2311, pruned_loss=0.01692, over 7211.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2458, pruned_loss=0.03102, over 1421972.31 frames.], batch size: 21, lr: 2.58e-04
+2022-05-15 16:58:17,927 INFO [train.py:812] (2/8) Epoch 30, batch 4200, loss[loss=0.1388, simple_loss=0.2346, pruned_loss=0.02154, over 7432.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2462, pruned_loss=0.03125, over 1422709.46 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 16:59:24,884 INFO [train.py:812] (2/8) Epoch 30, batch 4250, loss[loss=0.1581, simple_loss=0.2538, pruned_loss=0.03121, over 7368.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2467, pruned_loss=0.03142, over 1417988.96 frames.], batch size: 23, lr: 2.58e-04
+2022-05-15 17:00:23,185 INFO [train.py:812] (2/8) Epoch 30, batch 4300, loss[loss=0.1222, simple_loss=0.2082, pruned_loss=0.01809, over 7281.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.0311, over 1421621.92 frames.], batch size: 17, lr: 2.58e-04
+2022-05-15 17:01:31,693 INFO [train.py:812] (2/8) Epoch 30, batch 4350, loss[loss=0.1577, simple_loss=0.2515, pruned_loss=0.03199, over 7233.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2452, pruned_loss=0.03106, over 1423659.51 frames.], batch size: 20, lr: 2.58e-04
+2022-05-15 17:02:30,873 INFO [train.py:812] (2/8) Epoch 30, batch 4400, loss[loss=0.1419, simple_loss=0.2336, pruned_loss=0.02515, over 7223.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.0307, over 1419432.78 frames.], batch size: 20, lr: 2.57e-04
+2022-05-15 17:03:47,894 INFO [train.py:812] (2/8) Epoch 30, batch 4450, loss[loss=0.1578, simple_loss=0.2488, pruned_loss=0.03345, over 6503.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03072, over 1414624.78 frames.], batch size: 38, lr: 2.57e-04
+2022-05-15 17:04:54,621 INFO [train.py:812] (2/8) Epoch 30, batch 4500, loss[loss=0.193, simple_loss=0.2776, pruned_loss=0.05417, over 5036.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2461, pruned_loss=0.03118, over 1400027.53 frames.], batch size: 53, lr: 2.57e-04
+2022-05-15 17:05:52,204 INFO [train.py:812] (2/8) Epoch 30, batch 4550, loss[loss=0.1656, simple_loss=0.2514, pruned_loss=0.03995, over 5029.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2484, pruned_loss=0.03204, over 1359254.35 frames.], batch size: 52, lr: 2.57e-04
+2022-05-15 17:07:08,076 INFO [train.py:812] (2/8) Epoch 31, batch 0, loss[loss=0.1367, simple_loss=0.2305, pruned_loss=0.02147, over 7319.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2305, pruned_loss=0.02147, over 7319.00 frames.], batch size: 20, lr: 2.53e-04
+2022-05-15 17:08:07,411 INFO [train.py:812] (2/8) Epoch 31, batch 50, loss[loss=0.1502, simple_loss=0.2488, pruned_loss=0.02576, over 7265.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2449, pruned_loss=0.03174, over 316765.69 frames.], batch size: 19, lr: 2.53e-04
+2022-05-15 17:09:06,200 INFO [train.py:812] (2/8) Epoch 31, batch 100, loss[loss=0.1662, simple_loss=0.262, pruned_loss=0.03523, over 7390.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03178, over 561456.41 frames.], batch size: 23, lr: 2.53e-04
+2022-05-15 17:10:05,002 INFO [train.py:812] (2/8) Epoch 31, batch 150, loss[loss=0.1551, simple_loss=0.2465, pruned_loss=0.03192, over 7201.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2432, pruned_loss=0.0307, over 756472.64 frames.], batch size: 22, lr: 2.53e-04
+2022-05-15 17:11:03,885 INFO [train.py:812] (2/8) Epoch 31, batch 200, loss[loss=0.1846, simple_loss=0.2653, pruned_loss=0.05188, over 4773.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2418, pruned_loss=0.03025, over 900851.27 frames.], batch size: 52, lr: 2.53e-04
+2022-05-15 17:12:02,396 INFO [train.py:812] (2/8) Epoch 31, batch 250, loss[loss=0.1601, simple_loss=0.26, pruned_loss=0.03016, over 7292.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03045, over 1015024.73 frames.], batch size: 25, lr: 2.53e-04
+2022-05-15 17:13:01,819 INFO [train.py:812] (2/8) Epoch 31, batch 300, loss[loss=0.1305, simple_loss=0.2315, pruned_loss=0.01473, over 7314.00 frames.], tot_loss[loss=0.1532, simple_loss=0.245, pruned_loss=0.03067, over 1106300.91 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:13:59,727 INFO [train.py:812] (2/8) Epoch 31, batch 350, loss[loss=0.1464, simple_loss=0.2358, pruned_loss=0.02848, over 7170.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03078, over 1173217.35 frames.], batch size: 18, lr: 2.53e-04
+2022-05-15 17:14:57,247 INFO [train.py:812] (2/8) Epoch 31, batch 400, loss[loss=0.1498, simple_loss=0.2455, pruned_loss=0.02705, over 7218.00 frames.], tot_loss[loss=0.1532, simple_loss=0.245, pruned_loss=0.03073, over 1224329.17 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:15:56,097 INFO [train.py:812] (2/8) Epoch 31, batch 450, loss[loss=0.1862, simple_loss=0.2783, pruned_loss=0.047, over 7180.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2455, pruned_loss=0.03062, over 1265431.73 frames.], batch size: 26, lr: 2.53e-04
+2022-05-15 17:16:55,561 INFO [train.py:812] (2/8) Epoch 31, batch 500, loss[loss=0.145, simple_loss=0.2218, pruned_loss=0.03408, over 7282.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2451, pruned_loss=0.03059, over 1300270.14 frames.], batch size: 17, lr: 2.53e-04
+2022-05-15 17:17:54,502 INFO [train.py:812] (2/8) Epoch 31, batch 550, loss[loss=0.1442, simple_loss=0.2448, pruned_loss=0.02181, over 7423.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03068, over 1327672.16 frames.], batch size: 21, lr: 2.53e-04
+2022-05-15 17:18:53,057 INFO [train.py:812] (2/8) Epoch 31, batch 600, loss[loss=0.131, simple_loss=0.2166, pruned_loss=0.02272, over 7062.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2463, pruned_loss=0.03105, over 1346904.16 frames.], batch size: 18, lr: 2.53e-04
+2022-05-15 17:19:50,583 INFO [train.py:812] (2/8) Epoch 31, batch 650, loss[loss=0.1621, simple_loss=0.2546, pruned_loss=0.03485, over 7140.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2455, pruned_loss=0.03074, over 1368187.88 frames.], batch size: 20, lr: 2.53e-04
+2022-05-15 17:20:49,363 INFO [train.py:812] (2/8) Epoch 31, batch 700, loss[loss=0.1537, simple_loss=0.2364, pruned_loss=0.03549, over 7219.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.03092, over 1378440.26 frames.], batch size: 16, lr: 2.52e-04
+2022-05-15 17:21:47,371 INFO [train.py:812] (2/8) Epoch 31, batch 750, loss[loss=0.1379, simple_loss=0.2324, pruned_loss=0.02164, over 7240.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03079, over 1386342.53 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:22:46,095 INFO [train.py:812] (2/8) Epoch 31, batch 800, loss[loss=0.1424, simple_loss=0.2354, pruned_loss=0.02473, over 7326.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2449, pruned_loss=0.0306, over 1394437.38 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:23:44,736 INFO [train.py:812] (2/8) Epoch 31, batch 850, loss[loss=0.1675, simple_loss=0.257, pruned_loss=0.039, over 7426.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.03061, over 1398615.20 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:24:43,293 INFO [train.py:812] (2/8) Epoch 31, batch 900, loss[loss=0.1427, simple_loss=0.2238, pruned_loss=0.03077, over 7215.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2443, pruned_loss=0.03061, over 1403967.02 frames.], batch size: 16, lr: 2.52e-04
+2022-05-15 17:25:42,340 INFO [train.py:812] (2/8) Epoch 31, batch 950, loss[loss=0.1626, simple_loss=0.2608, pruned_loss=0.03223, over 7107.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2443, pruned_loss=0.03063, over 1405285.96 frames.], batch size: 28, lr: 2.52e-04
+2022-05-15 17:26:41,325 INFO [train.py:812] (2/8) Epoch 31, batch 1000, loss[loss=0.1457, simple_loss=0.24, pruned_loss=0.02572, over 7336.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2438, pruned_loss=0.03047, over 1408546.86 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:27:40,601 INFO [train.py:812] (2/8) Epoch 31, batch 1050, loss[loss=0.1671, simple_loss=0.2579, pruned_loss=0.0381, over 7029.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03071, over 1410492.41 frames.], batch size: 28, lr: 2.52e-04
+2022-05-15 17:28:39,402 INFO [train.py:812] (2/8) Epoch 31, batch 1100, loss[loss=0.1813, simple_loss=0.2675, pruned_loss=0.04756, over 7062.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03046, over 1414969.68 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:29:38,122 INFO [train.py:812] (2/8) Epoch 31, batch 1150, loss[loss=0.1557, simple_loss=0.2321, pruned_loss=0.03961, over 7062.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2438, pruned_loss=0.03067, over 1416700.89 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:30:36,856 INFO [train.py:812] (2/8) Epoch 31, batch 1200, loss[loss=0.1771, simple_loss=0.2699, pruned_loss=0.04219, over 7193.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2436, pruned_loss=0.03039, over 1418303.88 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:31:36,136 INFO [train.py:812] (2/8) Epoch 31, batch 1250, loss[loss=0.1385, simple_loss=0.2255, pruned_loss=0.02576, over 7413.00 frames.], tot_loss[loss=0.1524, simple_loss=0.244, pruned_loss=0.03039, over 1417266.09 frames.], batch size: 18, lr: 2.52e-04
+2022-05-15 17:32:35,749 INFO [train.py:812] (2/8) Epoch 31, batch 1300, loss[loss=0.157, simple_loss=0.2566, pruned_loss=0.02873, over 7121.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2443, pruned_loss=0.03064, over 1417305.31 frames.], batch size: 26, lr: 2.52e-04
+2022-05-15 17:33:34,080 INFO [train.py:812] (2/8) Epoch 31, batch 1350, loss[loss=0.1374, simple_loss=0.2215, pruned_loss=0.02662, over 7138.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2455, pruned_loss=0.03071, over 1414700.41 frames.], batch size: 17, lr: 2.52e-04
+2022-05-15 17:34:32,630 INFO [train.py:812] (2/8) Epoch 31, batch 1400, loss[loss=0.1829, simple_loss=0.2807, pruned_loss=0.04254, over 7327.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2459, pruned_loss=0.03109, over 1419319.33 frames.], batch size: 22, lr: 2.52e-04
+2022-05-15 17:35:31,403 INFO [train.py:812] (2/8) Epoch 31, batch 1450, loss[loss=0.151, simple_loss=0.2464, pruned_loss=0.0278, over 7144.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2458, pruned_loss=0.03083, over 1419465.10 frames.], batch size: 20, lr: 2.52e-04
+2022-05-15 17:36:30,347 INFO [train.py:812] (2/8) Epoch 31, batch 1500, loss[loss=0.1802, simple_loss=0.271, pruned_loss=0.04472, over 7305.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2463, pruned_loss=0.03067, over 1425525.75 frames.], batch size: 25, lr: 2.52e-04
+2022-05-15 17:37:27,929 INFO [train.py:812] (2/8) Epoch 31, batch 1550, loss[loss=0.1715, simple_loss=0.2595, pruned_loss=0.04174, over 7304.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.03059, over 1426495.45 frames.], batch size: 25, lr: 2.52e-04
+2022-05-15 17:38:27,363 INFO [train.py:812] (2/8) Epoch 31, batch 1600, loss[loss=0.1561, simple_loss=0.2431, pruned_loss=0.0345, over 7256.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2444, pruned_loss=0.03039, over 1427468.88 frames.], batch size: 19, lr: 2.52e-04
+2022-05-15 17:39:26,047 INFO [train.py:812] (2/8) Epoch 31, batch 1650, loss[loss=0.1346, simple_loss=0.2327, pruned_loss=0.01823, over 7123.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03041, over 1427769.29 frames.], batch size: 21, lr: 2.52e-04
+2022-05-15 17:40:24,534 INFO [train.py:812] (2/8) Epoch 31, batch 1700, loss[loss=0.1779, simple_loss=0.2594, pruned_loss=0.04819, over 7301.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2435, pruned_loss=0.03039, over 1424835.51 frames.], batch size: 24, lr: 2.52e-04
+2022-05-15 17:41:22,577 INFO [train.py:812] (2/8) Epoch 31, batch 1750, loss[loss=0.1599, simple_loss=0.2591, pruned_loss=0.0303, over 7379.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2445, pruned_loss=0.0306, over 1427433.53 frames.], batch size: 23, lr: 2.52e-04
+2022-05-15 17:42:21,640 INFO [train.py:812] (2/8) Epoch 31, batch 1800, loss[loss=0.14, simple_loss=0.2345, pruned_loss=0.02275, over 7448.00 frames.], tot_loss[loss=0.1525, simple_loss=0.244, pruned_loss=0.03052, over 1422668.46 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 17:43:20,079 INFO [train.py:812] (2/8) Epoch 31, batch 1850, loss[loss=0.1434, simple_loss=0.2335, pruned_loss=0.02664, over 7152.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2436, pruned_loss=0.03028, over 1421495.40 frames.], batch size: 17, lr: 2.51e-04
+2022-05-15 17:44:19,015 INFO [train.py:812] (2/8) Epoch 31, batch 1900, loss[loss=0.1462, simple_loss=0.243, pruned_loss=0.02475, over 7321.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.03024, over 1425558.80 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 17:45:17,823 INFO [train.py:812] (2/8) Epoch 31, batch 1950, loss[loss=0.1601, simple_loss=0.2486, pruned_loss=0.03585, over 7401.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02988, over 1425523.13 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:46:16,475 INFO [train.py:812] (2/8) Epoch 31, batch 2000, loss[loss=0.1676, simple_loss=0.2674, pruned_loss=0.03391, over 7165.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2421, pruned_loss=0.02945, over 1427170.05 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:47:15,231 INFO [train.py:812] (2/8) Epoch 31, batch 2050, loss[loss=0.1686, simple_loss=0.2657, pruned_loss=0.03573, over 7220.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2417, pruned_loss=0.02945, over 1424757.01 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 17:48:13,819 INFO [train.py:812] (2/8) Epoch 31, batch 2100, loss[loss=0.1486, simple_loss=0.2392, pruned_loss=0.02902, over 7162.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2424, pruned_loss=0.0297, over 1423311.59 frames.], batch size: 19, lr: 2.51e-04
+2022-05-15 17:49:12,922 INFO [train.py:812] (2/8) Epoch 31, batch 2150, loss[loss=0.129, simple_loss=0.2187, pruned_loss=0.01968, over 7152.00 frames.], tot_loss[loss=0.1504, simple_loss=0.242, pruned_loss=0.02942, over 1426828.08 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:50:11,052 INFO [train.py:812] (2/8) Epoch 31, batch 2200, loss[loss=0.1352, simple_loss=0.223, pruned_loss=0.02371, over 7055.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02973, over 1428626.69 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:51:08,605 INFO [train.py:812] (2/8) Epoch 31, batch 2250, loss[loss=0.1761, simple_loss=0.2785, pruned_loss=0.03689, over 7209.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2437, pruned_loss=0.02989, over 1427707.16 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:52:08,121 INFO [train.py:812] (2/8) Epoch 31, batch 2300, loss[loss=0.1411, simple_loss=0.2264, pruned_loss=0.02787, over 7255.00 frames.], tot_loss[loss=0.152, simple_loss=0.2439, pruned_loss=0.03, over 1429548.64 frames.], batch size: 19, lr: 2.51e-04
+2022-05-15 17:53:06,409 INFO [train.py:812] (2/8) Epoch 31, batch 2350, loss[loss=0.1317, simple_loss=0.2137, pruned_loss=0.02484, over 7446.00 frames.], tot_loss[loss=0.1523, simple_loss=0.244, pruned_loss=0.03027, over 1429800.32 frames.], batch size: 19, lr: 2.51e-04
+2022-05-15 17:54:10,961 INFO [train.py:812] (2/8) Epoch 31, batch 2400, loss[loss=0.1548, simple_loss=0.2436, pruned_loss=0.03298, over 7217.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03073, over 1428036.50 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 17:55:08,402 INFO [train.py:812] (2/8) Epoch 31, batch 2450, loss[loss=0.1516, simple_loss=0.2421, pruned_loss=0.03049, over 7228.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2452, pruned_loss=0.03102, over 1424280.55 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 17:56:07,153 INFO [train.py:812] (2/8) Epoch 31, batch 2500, loss[loss=0.1541, simple_loss=0.2454, pruned_loss=0.03147, over 7333.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.03048, over 1427150.84 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 17:57:05,819 INFO [train.py:812] (2/8) Epoch 31, batch 2550, loss[loss=0.1475, simple_loss=0.2342, pruned_loss=0.03039, over 7206.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2438, pruned_loss=0.03044, over 1428750.34 frames.], batch size: 23, lr: 2.51e-04
+2022-05-15 17:58:14,110 INFO [train.py:812] (2/8) Epoch 31, batch 2600, loss[loss=0.1346, simple_loss=0.2285, pruned_loss=0.02031, over 7418.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03022, over 1427847.28 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 17:59:11,565 INFO [train.py:812] (2/8) Epoch 31, batch 2650, loss[loss=0.1844, simple_loss=0.2878, pruned_loss=0.04045, over 7416.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2443, pruned_loss=0.03038, over 1424166.83 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 18:00:10,466 INFO [train.py:812] (2/8) Epoch 31, batch 2700, loss[loss=0.1611, simple_loss=0.2561, pruned_loss=0.03304, over 7282.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03019, over 1417736.28 frames.], batch size: 25, lr: 2.51e-04
+2022-05-15 18:01:09,674 INFO [train.py:812] (2/8) Epoch 31, batch 2750, loss[loss=0.1563, simple_loss=0.2492, pruned_loss=0.03169, over 7146.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.03026, over 1418847.21 frames.], batch size: 20, lr: 2.51e-04
+2022-05-15 18:02:09,007 INFO [train.py:812] (2/8) Epoch 31, batch 2800, loss[loss=0.1585, simple_loss=0.2443, pruned_loss=0.03639, over 7173.00 frames.], tot_loss[loss=0.1522, simple_loss=0.244, pruned_loss=0.03025, over 1421556.17 frames.], batch size: 18, lr: 2.51e-04
+2022-05-15 18:03:06,851 INFO [train.py:812] (2/8) Epoch 31, batch 2850, loss[loss=0.1844, simple_loss=0.2727, pruned_loss=0.048, over 7201.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2451, pruned_loss=0.03075, over 1420360.39 frames.], batch size: 22, lr: 2.51e-04
+2022-05-15 18:04:06,628 INFO [train.py:812] (2/8) Epoch 31, batch 2900, loss[loss=0.1487, simple_loss=0.2424, pruned_loss=0.02753, over 7112.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2454, pruned_loss=0.03094, over 1424223.92 frames.], batch size: 21, lr: 2.51e-04
+2022-05-15 18:05:04,895 INFO [train.py:812] (2/8) Epoch 31, batch 2950, loss[loss=0.1462, simple_loss=0.2328, pruned_loss=0.02979, over 7268.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03073, over 1423389.14 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:06:03,445 INFO [train.py:812] (2/8) Epoch 31, batch 3000, loss[loss=0.1352, simple_loss=0.2294, pruned_loss=0.02049, over 7329.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2441, pruned_loss=0.03064, over 1423142.24 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:06:03,446 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 18:06:10,972 INFO [train.py:841] (2/8) Epoch 31, validation: loss=0.1541, simple_loss=0.25, pruned_loss=0.02913, over 698248.00 frames.
+2022-05-15 18:07:09,528 INFO [train.py:812] (2/8) Epoch 31, batch 3050, loss[loss=0.1333, simple_loss=0.2279, pruned_loss=0.01934, over 7009.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03082, over 1422579.77 frames.], batch size: 16, lr: 2.50e-04
+2022-05-15 18:08:09,219 INFO [train.py:812] (2/8) Epoch 31, batch 3100, loss[loss=0.1651, simple_loss=0.2581, pruned_loss=0.03605, over 7290.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03081, over 1426013.98 frames.], batch size: 25, lr: 2.50e-04
+2022-05-15 18:09:08,153 INFO [train.py:812] (2/8) Epoch 31, batch 3150, loss[loss=0.1229, simple_loss=0.2017, pruned_loss=0.02203, over 6999.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2447, pruned_loss=0.0311, over 1424307.45 frames.], batch size: 16, lr: 2.50e-04
+2022-05-15 18:10:05,061 INFO [train.py:812] (2/8) Epoch 31, batch 3200, loss[loss=0.1687, simple_loss=0.2516, pruned_loss=0.04286, over 7208.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2443, pruned_loss=0.03106, over 1416643.84 frames.], batch size: 23, lr: 2.50e-04
+2022-05-15 18:11:03,067 INFO [train.py:812] (2/8) Epoch 31, batch 3250, loss[loss=0.1697, simple_loss=0.2686, pruned_loss=0.0354, over 7145.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.03102, over 1415698.17 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:12:02,660 INFO [train.py:812] (2/8) Epoch 31, batch 3300, loss[loss=0.1388, simple_loss=0.2205, pruned_loss=0.02854, over 7286.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2446, pruned_loss=0.03063, over 1422076.38 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:13:01,589 INFO [train.py:812] (2/8) Epoch 31, batch 3350, loss[loss=0.1629, simple_loss=0.2501, pruned_loss=0.03781, over 7223.00 frames.], tot_loss[loss=0.1525, simple_loss=0.244, pruned_loss=0.03053, over 1421631.52 frames.], batch size: 21, lr: 2.50e-04
+2022-05-15 18:14:00,857 INFO [train.py:812] (2/8) Epoch 31, batch 3400, loss[loss=0.1678, simple_loss=0.2615, pruned_loss=0.03705, over 7292.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03011, over 1421280.73 frames.], batch size: 25, lr: 2.50e-04
+2022-05-15 18:14:57,856 INFO [train.py:812] (2/8) Epoch 31, batch 3450, loss[loss=0.1461, simple_loss=0.2457, pruned_loss=0.02323, over 6628.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2442, pruned_loss=0.0303, over 1425751.92 frames.], batch size: 38, lr: 2.50e-04
+2022-05-15 18:15:56,076 INFO [train.py:812] (2/8) Epoch 31, batch 3500, loss[loss=0.1868, simple_loss=0.2838, pruned_loss=0.04489, over 7375.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2445, pruned_loss=0.03038, over 1426728.84 frames.], batch size: 23, lr: 2.50e-04
+2022-05-15 18:16:54,981 INFO [train.py:812] (2/8) Epoch 31, batch 3550, loss[loss=0.1365, simple_loss=0.226, pruned_loss=0.02349, over 7428.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2448, pruned_loss=0.0305, over 1428312.90 frames.], batch size: 20, lr: 2.50e-04
+2022-05-15 18:17:52,436 INFO [train.py:812] (2/8) Epoch 31, batch 3600, loss[loss=0.1774, simple_loss=0.2643, pruned_loss=0.04522, over 7296.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2462, pruned_loss=0.03101, over 1422966.50 frames.], batch size: 24, lr: 2.50e-04
+2022-05-15 18:18:51,249 INFO [train.py:812] (2/8) Epoch 31, batch 3650, loss[loss=0.1218, simple_loss=0.206, pruned_loss=0.01883, over 7153.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2456, pruned_loss=0.03074, over 1421831.83 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:19:50,481 INFO [train.py:812] (2/8) Epoch 31, batch 3700, loss[loss=0.1171, simple_loss=0.2025, pruned_loss=0.01583, over 7283.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2446, pruned_loss=0.03062, over 1424096.65 frames.], batch size: 17, lr: 2.50e-04
+2022-05-15 18:20:49,315 INFO [train.py:812] (2/8) Epoch 31, batch 3750, loss[loss=0.1463, simple_loss=0.2383, pruned_loss=0.02713, over 7253.00 frames.], tot_loss[loss=0.1524, simple_loss=0.244, pruned_loss=0.03035, over 1422162.14 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:21:49,288 INFO [train.py:812] (2/8) Epoch 31, batch 3800, loss[loss=0.1502, simple_loss=0.237, pruned_loss=0.03174, over 7268.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2444, pruned_loss=0.03061, over 1425033.17 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:22:47,453 INFO [train.py:812] (2/8) Epoch 31, batch 3850, loss[loss=0.1287, simple_loss=0.2255, pruned_loss=0.01593, over 7067.00 frames.], tot_loss[loss=0.153, simple_loss=0.2449, pruned_loss=0.03054, over 1424057.21 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:23:45,714 INFO [train.py:812] (2/8) Epoch 31, batch 3900, loss[loss=0.1554, simple_loss=0.2491, pruned_loss=0.0309, over 7295.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.0301, over 1428210.26 frames.], batch size: 24, lr: 2.50e-04
+2022-05-15 18:24:43,598 INFO [train.py:812] (2/8) Epoch 31, batch 3950, loss[loss=0.1406, simple_loss=0.2379, pruned_loss=0.02169, over 7360.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03022, over 1428443.50 frames.], batch size: 19, lr: 2.50e-04
+2022-05-15 18:25:41,721 INFO [train.py:812] (2/8) Epoch 31, batch 4000, loss[loss=0.1311, simple_loss=0.2189, pruned_loss=0.02161, over 7155.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03074, over 1426098.81 frames.], batch size: 18, lr: 2.50e-04
+2022-05-15 18:26:41,007 INFO [train.py:812] (2/8) Epoch 31, batch 4050, loss[loss=0.1608, simple_loss=0.2566, pruned_loss=0.0325, over 7287.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03073, over 1425108.12 frames.], batch size: 24, lr: 2.49e-04
+2022-05-15 18:27:40,659 INFO [train.py:812] (2/8) Epoch 31, batch 4100, loss[loss=0.1599, simple_loss=0.2557, pruned_loss=0.03206, over 7164.00 frames.], tot_loss[loss=0.1532, simple_loss=0.245, pruned_loss=0.03073, over 1426712.97 frames.], batch size: 19, lr: 2.49e-04
+2022-05-15 18:28:39,547 INFO [train.py:812] (2/8) Epoch 31, batch 4150, loss[loss=0.1588, simple_loss=0.2616, pruned_loss=0.02798, over 7432.00 frames.], tot_loss[loss=0.153, simple_loss=0.2449, pruned_loss=0.03053, over 1428462.69 frames.], batch size: 22, lr: 2.49e-04
+2022-05-15 18:29:38,558 INFO [train.py:812] (2/8) Epoch 31, batch 4200, loss[loss=0.1292, simple_loss=0.2155, pruned_loss=0.02145, over 6766.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2442, pruned_loss=0.0302, over 1430789.93 frames.], batch size: 15, lr: 2.49e-04
+2022-05-15 18:30:36,489 INFO [train.py:812] (2/8) Epoch 31, batch 4250, loss[loss=0.1517, simple_loss=0.2443, pruned_loss=0.0296, over 7162.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03017, over 1426996.69 frames.], batch size: 26, lr: 2.49e-04
+2022-05-15 18:31:35,772 INFO [train.py:812] (2/8) Epoch 31, batch 4300, loss[loss=0.1536, simple_loss=0.2388, pruned_loss=0.03416, over 7286.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.03002, over 1429788.16 frames.], batch size: 24, lr: 2.49e-04
+2022-05-15 18:32:33,412 INFO [train.py:812] (2/8) Epoch 31, batch 4350, loss[loss=0.1514, simple_loss=0.2503, pruned_loss=0.0262, over 7129.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.02973, over 1421267.91 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:33:32,234 INFO [train.py:812] (2/8) Epoch 31, batch 4400, loss[loss=0.1588, simple_loss=0.2639, pruned_loss=0.02687, over 7108.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02993, over 1410452.45 frames.], batch size: 21, lr: 2.49e-04
+2022-05-15 18:34:30,886 INFO [train.py:812] (2/8) Epoch 31, batch 4450, loss[loss=0.1442, simple_loss=0.2449, pruned_loss=0.02174, over 6416.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2443, pruned_loss=0.0304, over 1409235.17 frames.], batch size: 37, lr: 2.49e-04
+2022-05-15 18:35:30,123 INFO [train.py:812] (2/8) Epoch 31, batch 4500, loss[loss=0.1444, simple_loss=0.2406, pruned_loss=0.0241, over 6261.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2456, pruned_loss=0.03072, over 1385373.77 frames.], batch size: 37, lr: 2.49e-04
+2022-05-15 18:36:28,942 INFO [train.py:812] (2/8) Epoch 31, batch 4550, loss[loss=0.1833, simple_loss=0.2711, pruned_loss=0.04771, over 5254.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2468, pruned_loss=0.03131, over 1356619.58 frames.], batch size: 52, lr: 2.49e-04
+2022-05-15 18:37:36,644 INFO [train.py:812] (2/8) Epoch 32, batch 0, loss[loss=0.1542, simple_loss=0.2446, pruned_loss=0.03185, over 4774.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2446, pruned_loss=0.03185, over 4774.00 frames.], batch size: 52, lr: 2.45e-04
+2022-05-15 18:38:34,936 INFO [train.py:812] (2/8) Epoch 32, batch 50, loss[loss=0.1596, simple_loss=0.2581, pruned_loss=0.03052, over 6432.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2531, pruned_loss=0.03288, over 319624.26 frames.], batch size: 38, lr: 2.45e-04
+2022-05-15 18:39:33,408 INFO [train.py:812] (2/8) Epoch 32, batch 100, loss[loss=0.155, simple_loss=0.2533, pruned_loss=0.02839, over 7272.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2469, pruned_loss=0.03037, over 566236.45 frames.], batch size: 25, lr: 2.45e-04
+2022-05-15 18:40:32,479 INFO [train.py:812] (2/8) Epoch 32, batch 150, loss[loss=0.1539, simple_loss=0.2483, pruned_loss=0.02977, over 7166.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2455, pruned_loss=0.03049, over 757485.28 frames.], batch size: 26, lr: 2.45e-04
+2022-05-15 18:41:31,070 INFO [train.py:812] (2/8) Epoch 32, batch 200, loss[loss=0.126, simple_loss=0.2018, pruned_loss=0.02511, over 7002.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2433, pruned_loss=0.03016, over 902586.94 frames.], batch size: 16, lr: 2.45e-04
+2022-05-15 18:42:29,426 INFO [train.py:812] (2/8) Epoch 32, batch 250, loss[loss=0.1518, simple_loss=0.2534, pruned_loss=0.02514, over 7296.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.03076, over 1022794.49 frames.], batch size: 24, lr: 2.45e-04
+2022-05-15 18:43:28,929 INFO [train.py:812] (2/8) Epoch 32, batch 300, loss[loss=0.1794, simple_loss=0.2769, pruned_loss=0.04101, over 7270.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03084, over 1113845.55 frames.], batch size: 24, lr: 2.45e-04
+2022-05-15 18:44:28,373 INFO [train.py:812] (2/8) Epoch 32, batch 350, loss[loss=0.1629, simple_loss=0.2552, pruned_loss=0.0353, over 7110.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2451, pruned_loss=0.0308, over 1181933.72 frames.], batch size: 28, lr: 2.45e-04
+2022-05-15 18:45:27,064 INFO [train.py:812] (2/8) Epoch 32, batch 400, loss[loss=0.1573, simple_loss=0.2547, pruned_loss=0.02992, over 7147.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2454, pruned_loss=0.03102, over 1236961.12 frames.], batch size: 26, lr: 2.45e-04
+2022-05-15 18:46:25,980 INFO [train.py:812] (2/8) Epoch 32, batch 450, loss[loss=0.1599, simple_loss=0.2578, pruned_loss=0.03096, over 7301.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03075, over 1277168.42 frames.], batch size: 21, lr: 2.45e-04
+2022-05-15 18:47:25,085 INFO [train.py:812] (2/8) Epoch 32, batch 500, loss[loss=0.1452, simple_loss=0.2385, pruned_loss=0.02595, over 7328.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03006, over 1312764.64 frames.], batch size: 22, lr: 2.45e-04
+2022-05-15 18:48:23,085 INFO [train.py:812] (2/8) Epoch 32, batch 550, loss[loss=0.1534, simple_loss=0.26, pruned_loss=0.02337, over 7346.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02991, over 1340618.02 frames.], batch size: 22, lr: 2.45e-04
+2022-05-15 18:49:22,851 INFO [train.py:812] (2/8) Epoch 32, batch 600, loss[loss=0.134, simple_loss=0.2205, pruned_loss=0.02377, over 7131.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2437, pruned_loss=0.02977, over 1363145.78 frames.], batch size: 17, lr: 2.45e-04
+2022-05-15 18:50:21,223 INFO [train.py:812] (2/8) Epoch 32, batch 650, loss[loss=0.135, simple_loss=0.2243, pruned_loss=0.0229, over 7004.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02976, over 1378669.05 frames.], batch size: 16, lr: 2.45e-04
+2022-05-15 18:51:18,830 INFO [train.py:812] (2/8) Epoch 32, batch 700, loss[loss=0.1703, simple_loss=0.2668, pruned_loss=0.03692, over 7206.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2445, pruned_loss=0.03028, over 1387745.50 frames.], batch size: 23, lr: 2.45e-04
+2022-05-15 18:52:17,787 INFO [train.py:812] (2/8) Epoch 32, batch 750, loss[loss=0.1536, simple_loss=0.2475, pruned_loss=0.02984, over 7122.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2447, pruned_loss=0.03036, over 1395754.60 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 18:53:17,313 INFO [train.py:812] (2/8) Epoch 32, batch 800, loss[loss=0.1467, simple_loss=0.2309, pruned_loss=0.03122, over 7272.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.03, over 1400948.58 frames.], batch size: 18, lr: 2.44e-04
+2022-05-15 18:54:15,902 INFO [train.py:812] (2/8) Epoch 32, batch 850, loss[loss=0.1739, simple_loss=0.2745, pruned_loss=0.0367, over 7271.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03014, over 1408621.29 frames.], batch size: 25, lr: 2.44e-04
+2022-05-15 18:55:14,221 INFO [train.py:812] (2/8) Epoch 32, batch 900, loss[loss=0.1412, simple_loss=0.2452, pruned_loss=0.01861, over 7330.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2453, pruned_loss=0.03001, over 1411350.48 frames.], batch size: 22, lr: 2.44e-04
+2022-05-15 18:56:22,070 INFO [train.py:812] (2/8) Epoch 32, batch 950, loss[loss=0.1311, simple_loss=0.2202, pruned_loss=0.02096, over 6808.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.02998, over 1412774.33 frames.], batch size: 15, lr: 2.44e-04
+2022-05-15 18:57:31,049 INFO [train.py:812] (2/8) Epoch 32, batch 1000, loss[loss=0.1378, simple_loss=0.2257, pruned_loss=0.02499, over 7430.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.03, over 1416180.90 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 18:58:30,362 INFO [train.py:812] (2/8) Epoch 32, batch 1050, loss[loss=0.1406, simple_loss=0.2289, pruned_loss=0.02622, over 7240.00 frames.], tot_loss[loss=0.1515, simple_loss=0.243, pruned_loss=0.02999, over 1420443.85 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 18:59:29,291 INFO [train.py:812] (2/8) Epoch 32, batch 1100, loss[loss=0.1564, simple_loss=0.2632, pruned_loss=0.0248, over 7194.00 frames.], tot_loss[loss=0.1514, simple_loss=0.243, pruned_loss=0.02994, over 1418882.15 frames.], batch size: 22, lr: 2.44e-04
+2022-05-15 19:00:36,757 INFO [train.py:812] (2/8) Epoch 32, batch 1150, loss[loss=0.134, simple_loss=0.2178, pruned_loss=0.02511, over 7132.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2439, pruned_loss=0.03, over 1422783.97 frames.], batch size: 17, lr: 2.44e-04
+2022-05-15 19:01:36,488 INFO [train.py:812] (2/8) Epoch 32, batch 1200, loss[loss=0.143, simple_loss=0.2452, pruned_loss=0.02041, over 7422.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2425, pruned_loss=0.02947, over 1424951.69 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:02:45,181 INFO [train.py:812] (2/8) Epoch 32, batch 1250, loss[loss=0.1768, simple_loss=0.2636, pruned_loss=0.04499, over 7205.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2433, pruned_loss=0.03003, over 1417590.01 frames.], batch size: 23, lr: 2.44e-04
+2022-05-15 19:03:53,729 INFO [train.py:812] (2/8) Epoch 32, batch 1300, loss[loss=0.1808, simple_loss=0.279, pruned_loss=0.04128, over 7145.00 frames.], tot_loss[loss=0.1524, simple_loss=0.244, pruned_loss=0.03038, over 1423507.51 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:05:00,944 INFO [train.py:812] (2/8) Epoch 32, batch 1350, loss[loss=0.16, simple_loss=0.2512, pruned_loss=0.03445, over 7329.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03046, over 1422017.84 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:05:59,735 INFO [train.py:812] (2/8) Epoch 32, batch 1400, loss[loss=0.1661, simple_loss=0.2645, pruned_loss=0.03385, over 7238.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2432, pruned_loss=0.03008, over 1422519.14 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:06:57,258 INFO [train.py:812] (2/8) Epoch 32, batch 1450, loss[loss=0.1488, simple_loss=0.2441, pruned_loss=0.02674, over 7325.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.03016, over 1424042.58 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:08:05,681 INFO [train.py:812] (2/8) Epoch 32, batch 1500, loss[loss=0.1678, simple_loss=0.2547, pruned_loss=0.04046, over 4722.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02987, over 1422186.01 frames.], batch size: 53, lr: 2.44e-04
+2022-05-15 19:09:04,195 INFO [train.py:812] (2/8) Epoch 32, batch 1550, loss[loss=0.1342, simple_loss=0.2189, pruned_loss=0.02475, over 7409.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02995, over 1421476.03 frames.], batch size: 18, lr: 2.44e-04
+2022-05-15 19:10:03,424 INFO [train.py:812] (2/8) Epoch 32, batch 1600, loss[loss=0.1414, simple_loss=0.2393, pruned_loss=0.02176, over 7200.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.02998, over 1417651.44 frames.], batch size: 23, lr: 2.44e-04
+2022-05-15 19:11:01,507 INFO [train.py:812] (2/8) Epoch 32, batch 1650, loss[loss=0.1393, simple_loss=0.2384, pruned_loss=0.02006, over 7421.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2447, pruned_loss=0.03006, over 1416786.07 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:12:00,702 INFO [train.py:812] (2/8) Epoch 32, batch 1700, loss[loss=0.1445, simple_loss=0.2385, pruned_loss=0.02527, over 7112.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2449, pruned_loss=0.03032, over 1412313.15 frames.], batch size: 21, lr: 2.44e-04
+2022-05-15 19:12:59,709 INFO [train.py:812] (2/8) Epoch 32, batch 1750, loss[loss=0.1732, simple_loss=0.2564, pruned_loss=0.045, over 5304.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2446, pruned_loss=0.03002, over 1410969.71 frames.], batch size: 53, lr: 2.44e-04
+2022-05-15 19:14:04,669 INFO [train.py:812] (2/8) Epoch 32, batch 1800, loss[loss=0.1698, simple_loss=0.2714, pruned_loss=0.03413, over 7226.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2461, pruned_loss=0.03039, over 1411989.51 frames.], batch size: 20, lr: 2.44e-04
+2022-05-15 19:15:03,157 INFO [train.py:812] (2/8) Epoch 32, batch 1850, loss[loss=0.1431, simple_loss=0.2322, pruned_loss=0.02693, over 7000.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2461, pruned_loss=0.03073, over 1405988.09 frames.], batch size: 16, lr: 2.44e-04
+2022-05-15 19:16:02,152 INFO [train.py:812] (2/8) Epoch 32, batch 1900, loss[loss=0.1583, simple_loss=0.2521, pruned_loss=0.03227, over 7364.00 frames.], tot_loss[loss=0.1529, simple_loss=0.245, pruned_loss=0.03043, over 1412177.20 frames.], batch size: 19, lr: 2.44e-04
+2022-05-15 19:17:00,597 INFO [train.py:812] (2/8) Epoch 32, batch 1950, loss[loss=0.1425, simple_loss=0.2452, pruned_loss=0.01994, over 7361.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03029, over 1418672.98 frames.], batch size: 19, lr: 2.43e-04
+2022-05-15 19:18:00,429 INFO [train.py:812] (2/8) Epoch 32, batch 2000, loss[loss=0.1168, simple_loss=0.1987, pruned_loss=0.01745, over 7286.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2447, pruned_loss=0.03023, over 1420654.20 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:18:57,509 INFO [train.py:812] (2/8) Epoch 32, batch 2050, loss[loss=0.1367, simple_loss=0.233, pruned_loss=0.02022, over 7145.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2444, pruned_loss=0.0303, over 1416709.69 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:19:56,210 INFO [train.py:812] (2/8) Epoch 32, batch 2100, loss[loss=0.1215, simple_loss=0.203, pruned_loss=0.02003, over 6818.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2457, pruned_loss=0.03056, over 1417102.22 frames.], batch size: 15, lr: 2.43e-04
+2022-05-15 19:20:54,963 INFO [train.py:812] (2/8) Epoch 32, batch 2150, loss[loss=0.1516, simple_loss=0.2556, pruned_loss=0.02377, over 7219.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2456, pruned_loss=0.03031, over 1420821.55 frames.], batch size: 21, lr: 2.43e-04
+2022-05-15 19:21:53,674 INFO [train.py:812] (2/8) Epoch 32, batch 2200, loss[loss=0.1663, simple_loss=0.2655, pruned_loss=0.03355, over 7191.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2442, pruned_loss=0.03015, over 1423666.22 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:22:52,760 INFO [train.py:812] (2/8) Epoch 32, batch 2250, loss[loss=0.1464, simple_loss=0.2255, pruned_loss=0.03367, over 7067.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.02997, over 1424864.15 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:23:52,310 INFO [train.py:812] (2/8) Epoch 32, batch 2300, loss[loss=0.1473, simple_loss=0.2486, pruned_loss=0.02299, over 7338.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.02998, over 1422190.37 frames.], batch size: 22, lr: 2.43e-04
+2022-05-15 19:24:49,713 INFO [train.py:812] (2/8) Epoch 32, batch 2350, loss[loss=0.124, simple_loss=0.2115, pruned_loss=0.01819, over 7277.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2445, pruned_loss=0.0303, over 1425589.65 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:25:48,511 INFO [train.py:812] (2/8) Epoch 32, batch 2400, loss[loss=0.1496, simple_loss=0.2397, pruned_loss=0.02981, over 7321.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03086, over 1420924.41 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:26:47,719 INFO [train.py:812] (2/8) Epoch 32, batch 2450, loss[loss=0.1606, simple_loss=0.2612, pruned_loss=0.02997, over 7208.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03068, over 1423163.03 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:27:46,272 INFO [train.py:812] (2/8) Epoch 32, batch 2500, loss[loss=0.1146, simple_loss=0.1945, pruned_loss=0.01732, over 7271.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03071, over 1424887.47 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:28:44,155 INFO [train.py:812] (2/8) Epoch 32, batch 2550, loss[loss=0.1363, simple_loss=0.2262, pruned_loss=0.0232, over 7341.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2448, pruned_loss=0.03052, over 1421973.62 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:29:41,340 INFO [train.py:812] (2/8) Epoch 32, batch 2600, loss[loss=0.1287, simple_loss=0.2063, pruned_loss=0.02554, over 7144.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.03056, over 1420796.26 frames.], batch size: 17, lr: 2.43e-04
+2022-05-15 19:30:39,822 INFO [train.py:812] (2/8) Epoch 32, batch 2650, loss[loss=0.1563, simple_loss=0.2573, pruned_loss=0.0277, over 7127.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2439, pruned_loss=0.03018, over 1423407.54 frames.], batch size: 26, lr: 2.43e-04
+2022-05-15 19:31:39,427 INFO [train.py:812] (2/8) Epoch 32, batch 2700, loss[loss=0.1449, simple_loss=0.2415, pruned_loss=0.02413, over 7320.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2436, pruned_loss=0.03012, over 1422684.62 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:32:37,299 INFO [train.py:812] (2/8) Epoch 32, batch 2750, loss[loss=0.1728, simple_loss=0.2595, pruned_loss=0.04307, over 7039.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2437, pruned_loss=0.03024, over 1424818.65 frames.], batch size: 28, lr: 2.43e-04
+2022-05-15 19:33:35,528 INFO [train.py:812] (2/8) Epoch 32, batch 2800, loss[loss=0.1454, simple_loss=0.2272, pruned_loss=0.03176, over 7405.00 frames.], tot_loss[loss=0.1518, simple_loss=0.243, pruned_loss=0.03025, over 1424147.90 frames.], batch size: 18, lr: 2.43e-04
+2022-05-15 19:34:34,366 INFO [train.py:812] (2/8) Epoch 32, batch 2850, loss[loss=0.157, simple_loss=0.2547, pruned_loss=0.02964, over 6490.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2427, pruned_loss=0.02991, over 1421207.88 frames.], batch size: 37, lr: 2.43e-04
+2022-05-15 19:35:32,666 INFO [train.py:812] (2/8) Epoch 32, batch 2900, loss[loss=0.1418, simple_loss=0.2472, pruned_loss=0.01823, over 7230.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2439, pruned_loss=0.03024, over 1424810.03 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:36:31,007 INFO [train.py:812] (2/8) Epoch 32, batch 2950, loss[loss=0.1575, simple_loss=0.2552, pruned_loss=0.02988, over 7203.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2445, pruned_loss=0.03022, over 1417212.69 frames.], batch size: 23, lr: 2.43e-04
+2022-05-15 19:37:29,685 INFO [train.py:812] (2/8) Epoch 32, batch 3000, loss[loss=0.1605, simple_loss=0.2596, pruned_loss=0.03067, over 7426.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2451, pruned_loss=0.03053, over 1418568.17 frames.], batch size: 20, lr: 2.43e-04
+2022-05-15 19:37:29,686 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 19:37:37,094 INFO [train.py:841] (2/8) Epoch 32, validation: loss=0.1532, simple_loss=0.2494, pruned_loss=0.02852, over 698248.00 frames.
+2022-05-15 19:38:35,481 INFO [train.py:812] (2/8) Epoch 32, batch 3050, loss[loss=0.1445, simple_loss=0.2367, pruned_loss=0.02619, over 7294.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2449, pruned_loss=0.03051, over 1422523.45 frames.], batch size: 25, lr: 2.43e-04
+2022-05-15 19:39:34,805 INFO [train.py:812] (2/8) Epoch 32, batch 3100, loss[loss=0.1672, simple_loss=0.2606, pruned_loss=0.03686, over 7074.00 frames.], tot_loss[loss=0.153, simple_loss=0.245, pruned_loss=0.03053, over 1425909.11 frames.], batch size: 28, lr: 2.42e-04
+2022-05-15 19:40:34,128 INFO [train.py:812] (2/8) Epoch 32, batch 3150, loss[loss=0.1334, simple_loss=0.2206, pruned_loss=0.0231, over 7269.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03071, over 1423788.97 frames.], batch size: 17, lr: 2.42e-04
+2022-05-15 19:41:32,541 INFO [train.py:812] (2/8) Epoch 32, batch 3200, loss[loss=0.1565, simple_loss=0.25, pruned_loss=0.03147, over 7114.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2459, pruned_loss=0.03083, over 1426731.14 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:42:31,642 INFO [train.py:812] (2/8) Epoch 32, batch 3250, loss[loss=0.1437, simple_loss=0.2414, pruned_loss=0.02299, over 7341.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.03052, over 1427234.63 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 19:43:31,259 INFO [train.py:812] (2/8) Epoch 32, batch 3300, loss[loss=0.1251, simple_loss=0.2144, pruned_loss=0.01795, over 7437.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.0302, over 1424252.40 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:44:30,446 INFO [train.py:812] (2/8) Epoch 32, batch 3350, loss[loss=0.1543, simple_loss=0.259, pruned_loss=0.02486, over 7307.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2427, pruned_loss=0.02997, over 1425464.32 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:45:29,620 INFO [train.py:812] (2/8) Epoch 32, batch 3400, loss[loss=0.1478, simple_loss=0.2499, pruned_loss=0.0228, over 7336.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03046, over 1422369.51 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:46:27,575 INFO [train.py:812] (2/8) Epoch 32, batch 3450, loss[loss=0.1666, simple_loss=0.259, pruned_loss=0.03711, over 7189.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2454, pruned_loss=0.03047, over 1425445.78 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 19:47:26,347 INFO [train.py:812] (2/8) Epoch 32, batch 3500, loss[loss=0.1555, simple_loss=0.2425, pruned_loss=0.03425, over 7302.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2456, pruned_loss=0.03057, over 1428323.68 frames.], batch size: 24, lr: 2.42e-04
+2022-05-15 19:48:25,276 INFO [train.py:812] (2/8) Epoch 32, batch 3550, loss[loss=0.1472, simple_loss=0.2439, pruned_loss=0.02523, over 7372.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03014, over 1431559.56 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:49:24,689 INFO [train.py:812] (2/8) Epoch 32, batch 3600, loss[loss=0.1579, simple_loss=0.262, pruned_loss=0.02684, over 6480.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2439, pruned_loss=0.02998, over 1429475.41 frames.], batch size: 37, lr: 2.42e-04
+2022-05-15 19:50:24,029 INFO [train.py:812] (2/8) Epoch 32, batch 3650, loss[loss=0.1444, simple_loss=0.2451, pruned_loss=0.02183, over 7240.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2442, pruned_loss=0.02984, over 1429086.87 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:51:24,137 INFO [train.py:812] (2/8) Epoch 32, batch 3700, loss[loss=0.1331, simple_loss=0.2167, pruned_loss=0.02478, over 7137.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02983, over 1430704.95 frames.], batch size: 17, lr: 2.42e-04
+2022-05-15 19:52:22,802 INFO [train.py:812] (2/8) Epoch 32, batch 3750, loss[loss=0.1754, simple_loss=0.2715, pruned_loss=0.03965, over 7197.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02971, over 1426201.62 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:53:21,629 INFO [train.py:812] (2/8) Epoch 32, batch 3800, loss[loss=0.1648, simple_loss=0.2506, pruned_loss=0.03949, over 7368.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02965, over 1427071.01 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:54:19,346 INFO [train.py:812] (2/8) Epoch 32, batch 3850, loss[loss=0.174, simple_loss=0.263, pruned_loss=0.04251, over 7429.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2429, pruned_loss=0.02977, over 1428826.86 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 19:55:27,957 INFO [train.py:812] (2/8) Epoch 32, batch 3900, loss[loss=0.1375, simple_loss=0.226, pruned_loss=0.02447, over 7156.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.03001, over 1430147.65 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 19:56:25,319 INFO [train.py:812] (2/8) Epoch 32, batch 3950, loss[loss=0.1562, simple_loss=0.2535, pruned_loss=0.02943, over 7227.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2441, pruned_loss=0.03052, over 1424157.56 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 19:57:24,489 INFO [train.py:812] (2/8) Epoch 32, batch 4000, loss[loss=0.1223, simple_loss=0.2075, pruned_loss=0.01854, over 7411.00 frames.], tot_loss[loss=0.1528, simple_loss=0.244, pruned_loss=0.03074, over 1421389.12 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 19:58:22,810 INFO [train.py:812] (2/8) Epoch 32, batch 4050, loss[loss=0.162, simple_loss=0.2732, pruned_loss=0.02543, over 7386.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2443, pruned_loss=0.03074, over 1419789.50 frames.], batch size: 23, lr: 2.42e-04
+2022-05-15 19:59:20,910 INFO [train.py:812] (2/8) Epoch 32, batch 4100, loss[loss=0.1632, simple_loss=0.2587, pruned_loss=0.03389, over 7199.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03072, over 1417566.09 frames.], batch size: 22, lr: 2.42e-04
+2022-05-15 20:00:19,819 INFO [train.py:812] (2/8) Epoch 32, batch 4150, loss[loss=0.1593, simple_loss=0.2683, pruned_loss=0.02517, over 7222.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2446, pruned_loss=0.03063, over 1421002.70 frames.], batch size: 21, lr: 2.42e-04
+2022-05-15 20:01:19,605 INFO [train.py:812] (2/8) Epoch 32, batch 4200, loss[loss=0.1386, simple_loss=0.2367, pruned_loss=0.02027, over 7336.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2435, pruned_loss=0.03081, over 1421126.32 frames.], batch size: 20, lr: 2.42e-04
+2022-05-15 20:02:17,834 INFO [train.py:812] (2/8) Epoch 32, batch 4250, loss[loss=0.1465, simple_loss=0.2421, pruned_loss=0.02543, over 7259.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2437, pruned_loss=0.03083, over 1419572.24 frames.], batch size: 19, lr: 2.42e-04
+2022-05-15 20:03:17,416 INFO [train.py:812] (2/8) Epoch 32, batch 4300, loss[loss=0.1694, simple_loss=0.2492, pruned_loss=0.0448, over 7428.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2431, pruned_loss=0.03075, over 1419588.23 frames.], batch size: 18, lr: 2.42e-04
+2022-05-15 20:04:16,082 INFO [train.py:812] (2/8) Epoch 32, batch 4350, loss[loss=0.1179, simple_loss=0.2027, pruned_loss=0.01649, over 7169.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2442, pruned_loss=0.0312, over 1420425.45 frames.], batch size: 18, lr: 2.41e-04
+2022-05-15 20:05:14,954 INFO [train.py:812] (2/8) Epoch 32, batch 4400, loss[loss=0.1638, simple_loss=0.2681, pruned_loss=0.02971, over 7288.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2455, pruned_loss=0.03175, over 1406747.23 frames.], batch size: 25, lr: 2.41e-04
+2022-05-15 20:06:12,556 INFO [train.py:812] (2/8) Epoch 32, batch 4450, loss[loss=0.1325, simple_loss=0.2119, pruned_loss=0.02657, over 6835.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2458, pruned_loss=0.03185, over 1404039.53 frames.], batch size: 15, lr: 2.41e-04
+2022-05-15 20:07:11,382 INFO [train.py:812] (2/8) Epoch 32, batch 4500, loss[loss=0.1568, simple_loss=0.2515, pruned_loss=0.03099, over 6795.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2458, pruned_loss=0.03185, over 1394502.29 frames.], batch size: 31, lr: 2.41e-04
+2022-05-15 20:08:09,885 INFO [train.py:812] (2/8) Epoch 32, batch 4550, loss[loss=0.1773, simple_loss=0.2722, pruned_loss=0.04118, over 5167.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2456, pruned_loss=0.03281, over 1358569.99 frames.], batch size: 54, lr: 2.41e-04
+2022-05-15 20:09:17,615 INFO [train.py:812] (2/8) Epoch 33, batch 0, loss[loss=0.1635, simple_loss=0.2606, pruned_loss=0.03317, over 6871.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2606, pruned_loss=0.03317, over 6871.00 frames.], batch size: 31, lr: 2.38e-04
+2022-05-15 20:10:15,726 INFO [train.py:812] (2/8) Epoch 33, batch 50, loss[loss=0.1749, simple_loss=0.2631, pruned_loss=0.04331, over 5013.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2464, pruned_loss=0.02994, over 313497.66 frames.], batch size: 52, lr: 2.38e-04
+2022-05-15 20:11:14,517 INFO [train.py:812] (2/8) Epoch 33, batch 100, loss[loss=0.1482, simple_loss=0.2459, pruned_loss=0.02522, over 6540.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2454, pruned_loss=0.02989, over 558179.63 frames.], batch size: 38, lr: 2.38e-04
+2022-05-15 20:12:13,172 INFO [train.py:812] (2/8) Epoch 33, batch 150, loss[loss=0.1605, simple_loss=0.2572, pruned_loss=0.03191, over 7184.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2466, pruned_loss=0.03064, over 750538.30 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:13:12,886 INFO [train.py:812] (2/8) Epoch 33, batch 200, loss[loss=0.1324, simple_loss=0.2094, pruned_loss=0.02775, over 7000.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2457, pruned_loss=0.03051, over 893545.44 frames.], batch size: 16, lr: 2.37e-04
+2022-05-15 20:14:10,198 INFO [train.py:812] (2/8) Epoch 33, batch 250, loss[loss=0.152, simple_loss=0.2435, pruned_loss=0.03031, over 7234.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2449, pruned_loss=0.02993, over 1009224.06 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:15:09,036 INFO [train.py:812] (2/8) Epoch 33, batch 300, loss[loss=0.1576, simple_loss=0.2683, pruned_loss=0.02341, over 6654.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2464, pruned_loss=0.03018, over 1092546.83 frames.], batch size: 31, lr: 2.37e-04
+2022-05-15 20:16:07,534 INFO [train.py:812] (2/8) Epoch 33, batch 350, loss[loss=0.1354, simple_loss=0.2201, pruned_loss=0.02535, over 7415.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2468, pruned_loss=0.03016, over 1162626.46 frames.], batch size: 18, lr: 2.37e-04
+2022-05-15 20:17:07,054 INFO [train.py:812] (2/8) Epoch 33, batch 400, loss[loss=0.1608, simple_loss=0.2557, pruned_loss=0.03293, over 7433.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2456, pruned_loss=0.03007, over 1219765.86 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:18:06,525 INFO [train.py:812] (2/8) Epoch 33, batch 450, loss[loss=0.1643, simple_loss=0.258, pruned_loss=0.03531, over 6650.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03025, over 1262157.13 frames.], batch size: 31, lr: 2.37e-04
+2022-05-15 20:19:06,149 INFO [train.py:812] (2/8) Epoch 33, batch 500, loss[loss=0.1763, simple_loss=0.2622, pruned_loss=0.0452, over 7195.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2453, pruned_loss=0.0303, over 1300574.42 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:20:04,353 INFO [train.py:812] (2/8) Epoch 33, batch 550, loss[loss=0.157, simple_loss=0.2536, pruned_loss=0.03027, over 7308.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2461, pruned_loss=0.03048, over 1328637.50 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:21:03,177 INFO [train.py:812] (2/8) Epoch 33, batch 600, loss[loss=0.1861, simple_loss=0.2688, pruned_loss=0.0517, over 7308.00 frames.], tot_loss[loss=0.1536, simple_loss=0.246, pruned_loss=0.03059, over 1346537.95 frames.], batch size: 24, lr: 2.37e-04
+2022-05-15 20:22:00,734 INFO [train.py:812] (2/8) Epoch 33, batch 650, loss[loss=0.1645, simple_loss=0.2651, pruned_loss=0.03197, over 7153.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2458, pruned_loss=0.0306, over 1363592.43 frames.], batch size: 26, lr: 2.37e-04
+2022-05-15 20:23:00,265 INFO [train.py:812] (2/8) Epoch 33, batch 700, loss[loss=0.1479, simple_loss=0.2318, pruned_loss=0.03197, over 7120.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2465, pruned_loss=0.03137, over 1375048.58 frames.], batch size: 17, lr: 2.37e-04
+2022-05-15 20:23:58,660 INFO [train.py:812] (2/8) Epoch 33, batch 750, loss[loss=0.1543, simple_loss=0.2616, pruned_loss=0.02345, over 7218.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2465, pruned_loss=0.03136, over 1380507.64 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:24:57,933 INFO [train.py:812] (2/8) Epoch 33, batch 800, loss[loss=0.1393, simple_loss=0.2265, pruned_loss=0.02604, over 7437.00 frames.], tot_loss[loss=0.154, simple_loss=0.2454, pruned_loss=0.03126, over 1391701.98 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:25:55,898 INFO [train.py:812] (2/8) Epoch 33, batch 850, loss[loss=0.1616, simple_loss=0.2569, pruned_loss=0.03314, over 7383.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.0308, over 1399176.14 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:26:54,547 INFO [train.py:812] (2/8) Epoch 33, batch 900, loss[loss=0.1638, simple_loss=0.2528, pruned_loss=0.03746, over 7192.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2438, pruned_loss=0.03045, over 1408807.22 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:27:51,780 INFO [train.py:812] (2/8) Epoch 33, batch 950, loss[loss=0.1528, simple_loss=0.2514, pruned_loss=0.02711, over 7436.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.03051, over 1412891.14 frames.], batch size: 20, lr: 2.37e-04
+2022-05-15 20:28:51,353 INFO [train.py:812] (2/8) Epoch 33, batch 1000, loss[loss=0.1378, simple_loss=0.2379, pruned_loss=0.01883, over 7197.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2433, pruned_loss=0.03019, over 1412972.13 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:29:49,397 INFO [train.py:812] (2/8) Epoch 33, batch 1050, loss[loss=0.1472, simple_loss=0.2397, pruned_loss=0.02733, over 7086.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.02996, over 1411926.03 frames.], batch size: 28, lr: 2.37e-04
+2022-05-15 20:30:48,621 INFO [train.py:812] (2/8) Epoch 33, batch 1100, loss[loss=0.1661, simple_loss=0.2666, pruned_loss=0.03281, over 7281.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2436, pruned_loss=0.03026, over 1417075.56 frames.], batch size: 24, lr: 2.37e-04
+2022-05-15 20:31:47,033 INFO [train.py:812] (2/8) Epoch 33, batch 1150, loss[loss=0.1565, simple_loss=0.2532, pruned_loss=0.02986, over 7217.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02979, over 1418074.76 frames.], batch size: 23, lr: 2.37e-04
+2022-05-15 20:32:51,450 INFO [train.py:812] (2/8) Epoch 33, batch 1200, loss[loss=0.1643, simple_loss=0.261, pruned_loss=0.03387, over 7163.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.03016, over 1421123.07 frames.], batch size: 26, lr: 2.37e-04
+2022-05-15 20:33:50,444 INFO [train.py:812] (2/8) Epoch 33, batch 1250, loss[loss=0.157, simple_loss=0.2519, pruned_loss=0.03105, over 6629.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2447, pruned_loss=0.03023, over 1420099.89 frames.], batch size: 38, lr: 2.37e-04
+2022-05-15 20:34:50,281 INFO [train.py:812] (2/8) Epoch 33, batch 1300, loss[loss=0.1498, simple_loss=0.2497, pruned_loss=0.02497, over 7214.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.03011, over 1420913.56 frames.], batch size: 21, lr: 2.37e-04
+2022-05-15 20:35:49,582 INFO [train.py:812] (2/8) Epoch 33, batch 1350, loss[loss=0.133, simple_loss=0.2122, pruned_loss=0.02691, over 7279.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.0299, over 1420469.84 frames.], batch size: 17, lr: 2.37e-04
+2022-05-15 20:36:48,919 INFO [train.py:812] (2/8) Epoch 33, batch 1400, loss[loss=0.1519, simple_loss=0.2602, pruned_loss=0.02184, over 7150.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2436, pruned_loss=0.02984, over 1421780.28 frames.], batch size: 20, lr: 2.36e-04
+2022-05-15 20:37:47,494 INFO [train.py:812] (2/8) Epoch 33, batch 1450, loss[loss=0.1524, simple_loss=0.2512, pruned_loss=0.02677, over 6824.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02993, over 1424679.73 frames.], batch size: 31, lr: 2.36e-04
+2022-05-15 20:38:46,317 INFO [train.py:812] (2/8) Epoch 33, batch 1500, loss[loss=0.2049, simple_loss=0.2919, pruned_loss=0.05895, over 4784.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2445, pruned_loss=0.03043, over 1421798.44 frames.], batch size: 52, lr: 2.36e-04
+2022-05-15 20:39:44,997 INFO [train.py:812] (2/8) Epoch 33, batch 1550, loss[loss=0.1603, simple_loss=0.2523, pruned_loss=0.03409, over 7210.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03026, over 1418485.11 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:40:43,839 INFO [train.py:812] (2/8) Epoch 33, batch 1600, loss[loss=0.1399, simple_loss=0.2389, pruned_loss=0.02051, over 7416.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03026, over 1420068.88 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:41:42,724 INFO [train.py:812] (2/8) Epoch 33, batch 1650, loss[loss=0.1602, simple_loss=0.2578, pruned_loss=0.03128, over 7215.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03027, over 1421042.16 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:42:41,819 INFO [train.py:812] (2/8) Epoch 33, batch 1700, loss[loss=0.1762, simple_loss=0.2739, pruned_loss=0.03921, over 7298.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2453, pruned_loss=0.03043, over 1422825.26 frames.], batch size: 24, lr: 2.36e-04
+2022-05-15 20:43:40,836 INFO [train.py:812] (2/8) Epoch 33, batch 1750, loss[loss=0.1628, simple_loss=0.2519, pruned_loss=0.03679, over 7056.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2463, pruned_loss=0.03093, over 1415548.18 frames.], batch size: 28, lr: 2.36e-04
+2022-05-15 20:44:39,997 INFO [train.py:812] (2/8) Epoch 33, batch 1800, loss[loss=0.1251, simple_loss=0.2219, pruned_loss=0.0141, over 7262.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2459, pruned_loss=0.03057, over 1419134.73 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:45:38,874 INFO [train.py:812] (2/8) Epoch 33, batch 1850, loss[loss=0.1397, simple_loss=0.2393, pruned_loss=0.02, over 7315.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2457, pruned_loss=0.0307, over 1422099.41 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:46:37,416 INFO [train.py:812] (2/8) Epoch 33, batch 1900, loss[loss=0.1487, simple_loss=0.2449, pruned_loss=0.02624, over 7380.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2451, pruned_loss=0.03022, over 1424706.54 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 20:47:35,891 INFO [train.py:812] (2/8) Epoch 33, batch 1950, loss[loss=0.1593, simple_loss=0.2568, pruned_loss=0.03091, over 7301.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2455, pruned_loss=0.03068, over 1423676.11 frames.], batch size: 24, lr: 2.36e-04
+2022-05-15 20:48:34,898 INFO [train.py:812] (2/8) Epoch 33, batch 2000, loss[loss=0.1519, simple_loss=0.2433, pruned_loss=0.03029, over 6134.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2451, pruned_loss=0.0307, over 1425439.70 frames.], batch size: 37, lr: 2.36e-04
+2022-05-15 20:49:32,707 INFO [train.py:812] (2/8) Epoch 33, batch 2050, loss[loss=0.1437, simple_loss=0.2332, pruned_loss=0.02712, over 7170.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03071, over 1425477.60 frames.], batch size: 18, lr: 2.36e-04
+2022-05-15 20:50:32,328 INFO [train.py:812] (2/8) Epoch 33, batch 2100, loss[loss=0.1407, simple_loss=0.2337, pruned_loss=0.02387, over 7154.00 frames.], tot_loss[loss=0.1532, simple_loss=0.245, pruned_loss=0.03067, over 1427394.91 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:51:30,239 INFO [train.py:812] (2/8) Epoch 33, batch 2150, loss[loss=0.16, simple_loss=0.2406, pruned_loss=0.03974, over 7419.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03072, over 1428711.91 frames.], batch size: 18, lr: 2.36e-04
+2022-05-15 20:52:28,373 INFO [train.py:812] (2/8) Epoch 33, batch 2200, loss[loss=0.1794, simple_loss=0.2633, pruned_loss=0.04776, over 4745.00 frames.], tot_loss[loss=0.1532, simple_loss=0.245, pruned_loss=0.03071, over 1421922.39 frames.], batch size: 52, lr: 2.36e-04
+2022-05-15 20:53:26,614 INFO [train.py:812] (2/8) Epoch 33, batch 2250, loss[loss=0.1802, simple_loss=0.2669, pruned_loss=0.0467, over 7213.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03069, over 1419373.57 frames.], batch size: 26, lr: 2.36e-04
+2022-05-15 20:54:25,515 INFO [train.py:812] (2/8) Epoch 33, batch 2300, loss[loss=0.1658, simple_loss=0.2638, pruned_loss=0.03389, over 7213.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2441, pruned_loss=0.03067, over 1418228.11 frames.], batch size: 22, lr: 2.36e-04
+2022-05-15 20:55:24,374 INFO [train.py:812] (2/8) Epoch 33, batch 2350, loss[loss=0.1475, simple_loss=0.2255, pruned_loss=0.03474, over 7201.00 frames.], tot_loss[loss=0.152, simple_loss=0.2432, pruned_loss=0.0304, over 1422080.55 frames.], batch size: 16, lr: 2.36e-04
+2022-05-15 20:56:22,959 INFO [train.py:812] (2/8) Epoch 33, batch 2400, loss[loss=0.1612, simple_loss=0.2555, pruned_loss=0.03343, over 7441.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2435, pruned_loss=0.03061, over 1423603.91 frames.], batch size: 20, lr: 2.36e-04
+2022-05-15 20:57:40,439 INFO [train.py:812] (2/8) Epoch 33, batch 2450, loss[loss=0.1483, simple_loss=0.2464, pruned_loss=0.02511, over 7247.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2438, pruned_loss=0.03057, over 1426021.74 frames.], batch size: 19, lr: 2.36e-04
+2022-05-15 20:58:40,074 INFO [train.py:812] (2/8) Epoch 33, batch 2500, loss[loss=0.1684, simple_loss=0.2616, pruned_loss=0.03764, over 7319.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.03, over 1428024.53 frames.], batch size: 21, lr: 2.36e-04
+2022-05-15 20:59:48,295 INFO [train.py:812] (2/8) Epoch 33, batch 2550, loss[loss=0.1507, simple_loss=0.2423, pruned_loss=0.02959, over 7394.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2425, pruned_loss=0.03, over 1428001.43 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 21:00:46,802 INFO [train.py:812] (2/8) Epoch 33, batch 2600, loss[loss=0.1736, simple_loss=0.275, pruned_loss=0.03617, over 7188.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2428, pruned_loss=0.03016, over 1428209.30 frames.], batch size: 23, lr: 2.36e-04
+2022-05-15 21:01:44,969 INFO [train.py:812] (2/8) Epoch 33, batch 2650, loss[loss=0.1587, simple_loss=0.2369, pruned_loss=0.04026, over 7196.00 frames.], tot_loss[loss=0.1517, simple_loss=0.243, pruned_loss=0.03019, over 1423208.56 frames.], batch size: 16, lr: 2.35e-04
+2022-05-15 21:02:52,793 INFO [train.py:812] (2/8) Epoch 33, batch 2700, loss[loss=0.143, simple_loss=0.2403, pruned_loss=0.02284, over 7424.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2431, pruned_loss=0.02998, over 1424994.68 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:04:10,610 INFO [train.py:812] (2/8) Epoch 33, batch 2750, loss[loss=0.1473, simple_loss=0.229, pruned_loss=0.03281, over 7268.00 frames.], tot_loss[loss=0.1512, simple_loss=0.243, pruned_loss=0.02975, over 1425930.00 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:05:09,523 INFO [train.py:812] (2/8) Epoch 33, batch 2800, loss[loss=0.1525, simple_loss=0.2526, pruned_loss=0.02621, over 7206.00 frames.], tot_loss[loss=0.151, simple_loss=0.2426, pruned_loss=0.0297, over 1424325.62 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:06:07,214 INFO [train.py:812] (2/8) Epoch 33, batch 2850, loss[loss=0.1487, simple_loss=0.2482, pruned_loss=0.02463, over 7323.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2422, pruned_loss=0.02958, over 1426019.42 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:07:06,356 INFO [train.py:812] (2/8) Epoch 33, batch 2900, loss[loss=0.189, simple_loss=0.2805, pruned_loss=0.04871, over 7273.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2433, pruned_loss=0.03014, over 1424940.52 frames.], batch size: 25, lr: 2.35e-04
+2022-05-15 21:08:04,491 INFO [train.py:812] (2/8) Epoch 33, batch 2950, loss[loss=0.1437, simple_loss=0.2306, pruned_loss=0.02841, over 7435.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2443, pruned_loss=0.0303, over 1426997.13 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:09:12,197 INFO [train.py:812] (2/8) Epoch 33, batch 3000, loss[loss=0.1355, simple_loss=0.2246, pruned_loss=0.02326, over 7061.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2443, pruned_loss=0.03021, over 1426716.73 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:09:12,198 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 21:09:19,691 INFO [train.py:841] (2/8) Epoch 33, validation: loss=0.1535, simple_loss=0.2493, pruned_loss=0.02886, over 698248.00 frames.
+2022-05-15 21:10:18,080 INFO [train.py:812] (2/8) Epoch 33, batch 3050, loss[loss=0.1552, simple_loss=0.2544, pruned_loss=0.02802, over 6433.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2433, pruned_loss=0.02979, over 1424074.41 frames.], batch size: 38, lr: 2.35e-04
+2022-05-15 21:11:15,950 INFO [train.py:812] (2/8) Epoch 33, batch 3100, loss[loss=0.1661, simple_loss=0.2612, pruned_loss=0.03543, over 7384.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02954, over 1425055.86 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:12:14,888 INFO [train.py:812] (2/8) Epoch 33, batch 3150, loss[loss=0.1374, simple_loss=0.2331, pruned_loss=0.02082, over 7061.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2421, pruned_loss=0.02933, over 1422313.96 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:13:13,028 INFO [train.py:812] (2/8) Epoch 33, batch 3200, loss[loss=0.1272, simple_loss=0.2118, pruned_loss=0.02129, over 7181.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2424, pruned_loss=0.0293, over 1422990.51 frames.], batch size: 16, lr: 2.35e-04
+2022-05-15 21:14:11,705 INFO [train.py:812] (2/8) Epoch 33, batch 3250, loss[loss=0.1472, simple_loss=0.2365, pruned_loss=0.02891, over 7283.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2426, pruned_loss=0.02958, over 1421343.45 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:15:11,679 INFO [train.py:812] (2/8) Epoch 33, batch 3300, loss[loss=0.1617, simple_loss=0.2579, pruned_loss=0.03277, over 7242.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2418, pruned_loss=0.02916, over 1426106.56 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:16:10,520 INFO [train.py:812] (2/8) Epoch 33, batch 3350, loss[loss=0.1746, simple_loss=0.2739, pruned_loss=0.03762, over 7310.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.0291, over 1429101.63 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:17:09,951 INFO [train.py:812] (2/8) Epoch 33, batch 3400, loss[loss=0.1521, simple_loss=0.235, pruned_loss=0.0346, over 7273.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2415, pruned_loss=0.02895, over 1428770.28 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:18:09,761 INFO [train.py:812] (2/8) Epoch 33, batch 3450, loss[loss=0.1483, simple_loss=0.2395, pruned_loss=0.02852, over 7340.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.0293, over 1432951.62 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:19:07,580 INFO [train.py:812] (2/8) Epoch 33, batch 3500, loss[loss=0.1541, simple_loss=0.2499, pruned_loss=0.02911, over 7376.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02951, over 1428823.98 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:20:05,793 INFO [train.py:812] (2/8) Epoch 33, batch 3550, loss[loss=0.1291, simple_loss=0.2128, pruned_loss=0.02277, over 7414.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02965, over 1426969.24 frames.], batch size: 18, lr: 2.35e-04
+2022-05-15 21:21:04,539 INFO [train.py:812] (2/8) Epoch 33, batch 3600, loss[loss=0.1515, simple_loss=0.2375, pruned_loss=0.03279, over 7327.00 frames.], tot_loss[loss=0.151, simple_loss=0.2432, pruned_loss=0.02935, over 1424074.97 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:22:03,664 INFO [train.py:812] (2/8) Epoch 33, batch 3650, loss[loss=0.1468, simple_loss=0.2408, pruned_loss=0.02639, over 7337.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2427, pruned_loss=0.02925, over 1424017.81 frames.], batch size: 20, lr: 2.35e-04
+2022-05-15 21:23:02,541 INFO [train.py:812] (2/8) Epoch 33, batch 3700, loss[loss=0.1413, simple_loss=0.2278, pruned_loss=0.02742, over 7281.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2441, pruned_loss=0.02957, over 1426986.62 frames.], batch size: 17, lr: 2.35e-04
+2022-05-15 21:24:01,171 INFO [train.py:812] (2/8) Epoch 33, batch 3750, loss[loss=0.1666, simple_loss=0.2671, pruned_loss=0.0331, over 7230.00 frames.], tot_loss[loss=0.1517, simple_loss=0.244, pruned_loss=0.02968, over 1427062.00 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:25:00,724 INFO [train.py:812] (2/8) Epoch 33, batch 3800, loss[loss=0.1632, simple_loss=0.2607, pruned_loss=0.03282, over 7200.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2433, pruned_loss=0.02983, over 1427784.21 frames.], batch size: 23, lr: 2.35e-04
+2022-05-15 21:25:58,507 INFO [train.py:812] (2/8) Epoch 33, batch 3850, loss[loss=0.1618, simple_loss=0.266, pruned_loss=0.02876, over 7320.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02957, over 1427988.27 frames.], batch size: 21, lr: 2.35e-04
+2022-05-15 21:26:57,078 INFO [train.py:812] (2/8) Epoch 33, batch 3900, loss[loss=0.1474, simple_loss=0.2271, pruned_loss=0.03387, over 6730.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2448, pruned_loss=0.02993, over 1428592.61 frames.], batch size: 15, lr: 2.35e-04
+2022-05-15 21:27:55,700 INFO [train.py:812] (2/8) Epoch 33, batch 3950, loss[loss=0.1475, simple_loss=0.2314, pruned_loss=0.03177, over 7401.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2454, pruned_loss=0.03045, over 1430830.04 frames.], batch size: 18, lr: 2.34e-04
+2022-05-15 21:28:55,477 INFO [train.py:812] (2/8) Epoch 33, batch 4000, loss[loss=0.1602, simple_loss=0.264, pruned_loss=0.02819, over 6175.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.03, over 1431257.99 frames.], batch size: 37, lr: 2.34e-04
+2022-05-15 21:29:54,328 INFO [train.py:812] (2/8) Epoch 33, batch 4050, loss[loss=0.1389, simple_loss=0.2224, pruned_loss=0.02776, over 7285.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2441, pruned_loss=0.03022, over 1427308.43 frames.], batch size: 18, lr: 2.34e-04
+2022-05-15 21:30:52,672 INFO [train.py:812] (2/8) Epoch 33, batch 4100, loss[loss=0.1471, simple_loss=0.2405, pruned_loss=0.02683, over 7178.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2428, pruned_loss=0.02989, over 1420631.55 frames.], batch size: 26, lr: 2.34e-04
+2022-05-15 21:31:50,548 INFO [train.py:812] (2/8) Epoch 33, batch 4150, loss[loss=0.1389, simple_loss=0.2269, pruned_loss=0.02546, over 7204.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02965, over 1420790.46 frames.], batch size: 16, lr: 2.34e-04
+2022-05-15 21:32:49,099 INFO [train.py:812] (2/8) Epoch 33, batch 4200, loss[loss=0.1484, simple_loss=0.2488, pruned_loss=0.02397, over 7261.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2431, pruned_loss=0.02996, over 1419420.26 frames.], batch size: 19, lr: 2.34e-04
+2022-05-15 21:33:48,267 INFO [train.py:812] (2/8) Epoch 33, batch 4250, loss[loss=0.1421, simple_loss=0.238, pruned_loss=0.02312, over 7442.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2429, pruned_loss=0.02982, over 1420306.01 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:34:46,555 INFO [train.py:812] (2/8) Epoch 33, batch 4300, loss[loss=0.1571, simple_loss=0.2518, pruned_loss=0.03116, over 6680.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2432, pruned_loss=0.02975, over 1419254.32 frames.], batch size: 31, lr: 2.34e-04
+2022-05-15 21:35:44,800 INFO [train.py:812] (2/8) Epoch 33, batch 4350, loss[loss=0.1549, simple_loss=0.2501, pruned_loss=0.02984, over 7224.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02945, over 1415334.99 frames.], batch size: 21, lr: 2.34e-04
+2022-05-15 21:36:43,617 INFO [train.py:812] (2/8) Epoch 33, batch 4400, loss[loss=0.1616, simple_loss=0.2556, pruned_loss=0.03382, over 7140.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.0295, over 1414062.77 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:37:42,038 INFO [train.py:812] (2/8) Epoch 33, batch 4450, loss[loss=0.1597, simple_loss=0.2664, pruned_loss=0.0265, over 7342.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.02949, over 1407536.31 frames.], batch size: 22, lr: 2.34e-04
+2022-05-15 21:38:41,154 INFO [train.py:812] (2/8) Epoch 33, batch 4500, loss[loss=0.1441, simple_loss=0.2435, pruned_loss=0.02238, over 7142.00 frames.], tot_loss[loss=0.152, simple_loss=0.2445, pruned_loss=0.02972, over 1397662.58 frames.], batch size: 20, lr: 2.34e-04
+2022-05-15 21:39:39,844 INFO [train.py:812] (2/8) Epoch 33, batch 4550, loss[loss=0.1466, simple_loss=0.233, pruned_loss=0.03011, over 5156.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2448, pruned_loss=0.02979, over 1376537.87 frames.], batch size: 52, lr: 2.34e-04
+2022-05-15 21:40:52,132 INFO [train.py:812] (2/8) Epoch 34, batch 0, loss[loss=0.1698, simple_loss=0.2576, pruned_loss=0.04099, over 7434.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2576, pruned_loss=0.04099, over 7434.00 frames.], batch size: 20, lr: 2.31e-04
+2022-05-15 21:41:51,334 INFO [train.py:812] (2/8) Epoch 34, batch 50, loss[loss=0.147, simple_loss=0.2494, pruned_loss=0.02227, over 7089.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2401, pruned_loss=0.02822, over 324890.94 frames.], batch size: 28, lr: 2.30e-04
+2022-05-15 21:42:51,070 INFO [train.py:812] (2/8) Epoch 34, batch 100, loss[loss=0.1579, simple_loss=0.2597, pruned_loss=0.028, over 7111.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2434, pruned_loss=0.02874, over 566088.06 frames.], batch size: 21, lr: 2.30e-04
+2022-05-15 21:43:50,369 INFO [train.py:812] (2/8) Epoch 34, batch 150, loss[loss=0.1493, simple_loss=0.2366, pruned_loss=0.03099, over 7061.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02891, over 755574.10 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:44:49,688 INFO [train.py:812] (2/8) Epoch 34, batch 200, loss[loss=0.1426, simple_loss=0.227, pruned_loss=0.02905, over 7273.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2408, pruned_loss=0.02833, over 905361.18 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:45:48,840 INFO [train.py:812] (2/8) Epoch 34, batch 250, loss[loss=0.1488, simple_loss=0.2426, pruned_loss=0.02755, over 4880.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2406, pruned_loss=0.02844, over 1011263.90 frames.], batch size: 52, lr: 2.30e-04
+2022-05-15 21:46:48,758 INFO [train.py:812] (2/8) Epoch 34, batch 300, loss[loss=0.1551, simple_loss=0.2526, pruned_loss=0.02884, over 7384.00 frames.], tot_loss[loss=0.1499, simple_loss=0.242, pruned_loss=0.02895, over 1101543.64 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 21:47:46,237 INFO [train.py:812] (2/8) Epoch 34, batch 350, loss[loss=0.1347, simple_loss=0.22, pruned_loss=0.0247, over 7124.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02953, over 1166644.33 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:48:46,227 INFO [train.py:812] (2/8) Epoch 34, batch 400, loss[loss=0.1571, simple_loss=0.2565, pruned_loss=0.02887, over 7413.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02948, over 1227976.45 frames.], batch size: 21, lr: 2.30e-04
+2022-05-15 21:49:44,744 INFO [train.py:812] (2/8) Epoch 34, batch 450, loss[loss=0.1414, simple_loss=0.2311, pruned_loss=0.02587, over 7396.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2429, pruned_loss=0.02885, over 1272747.21 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:50:44,205 INFO [train.py:812] (2/8) Epoch 34, batch 500, loss[loss=0.1496, simple_loss=0.2457, pruned_loss=0.02674, over 7296.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2438, pruned_loss=0.02941, over 1305798.69 frames.], batch size: 24, lr: 2.30e-04
+2022-05-15 21:51:42,499 INFO [train.py:812] (2/8) Epoch 34, batch 550, loss[loss=0.1528, simple_loss=0.2482, pruned_loss=0.02866, over 6360.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02956, over 1329539.04 frames.], batch size: 37, lr: 2.30e-04
+2022-05-15 21:52:57,377 INFO [train.py:812] (2/8) Epoch 34, batch 600, loss[loss=0.1774, simple_loss=0.2646, pruned_loss=0.04512, over 7290.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2437, pruned_loss=0.02928, over 1351610.91 frames.], batch size: 25, lr: 2.30e-04
+2022-05-15 21:53:55,933 INFO [train.py:812] (2/8) Epoch 34, batch 650, loss[loss=0.1508, simple_loss=0.2296, pruned_loss=0.03598, over 7161.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2447, pruned_loss=0.02981, over 1370105.13 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:54:54,860 INFO [train.py:812] (2/8) Epoch 34, batch 700, loss[loss=0.1409, simple_loss=0.2271, pruned_loss=0.02734, over 7130.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.02952, over 1377116.82 frames.], batch size: 17, lr: 2.30e-04
+2022-05-15 21:55:51,395 INFO [train.py:812] (2/8) Epoch 34, batch 750, loss[loss=0.1558, simple_loss=0.247, pruned_loss=0.03229, over 7226.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2446, pruned_loss=0.02996, over 1388829.93 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 21:56:50,461 INFO [train.py:812] (2/8) Epoch 34, batch 800, loss[loss=0.1383, simple_loss=0.2314, pruned_loss=0.02257, over 7280.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2451, pruned_loss=0.02993, over 1394709.58 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 21:57:49,837 INFO [train.py:812] (2/8) Epoch 34, batch 850, loss[loss=0.1526, simple_loss=0.247, pruned_loss=0.02906, over 6479.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2442, pruned_loss=0.02939, over 1403906.36 frames.], batch size: 37, lr: 2.30e-04
+2022-05-15 21:58:48,165 INFO [train.py:812] (2/8) Epoch 34, batch 900, loss[loss=0.2024, simple_loss=0.2829, pruned_loss=0.06094, over 5060.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2429, pruned_loss=0.02897, over 1408911.97 frames.], batch size: 53, lr: 2.30e-04
+2022-05-15 21:59:45,323 INFO [train.py:812] (2/8) Epoch 34, batch 950, loss[loss=0.1585, simple_loss=0.246, pruned_loss=0.03547, over 7274.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.02929, over 1408178.48 frames.], batch size: 18, lr: 2.30e-04
+2022-05-15 22:00:43,716 INFO [train.py:812] (2/8) Epoch 34, batch 1000, loss[loss=0.1427, simple_loss=0.2347, pruned_loss=0.02537, over 7428.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.02921, over 1409686.22 frames.], batch size: 20, lr: 2.30e-04
+2022-05-15 22:01:41,763 INFO [train.py:812] (2/8) Epoch 34, batch 1050, loss[loss=0.1527, simple_loss=0.2482, pruned_loss=0.02861, over 7166.00 frames.], tot_loss[loss=0.151, simple_loss=0.2432, pruned_loss=0.02937, over 1415868.59 frames.], batch size: 19, lr: 2.30e-04
+2022-05-15 22:02:40,788 INFO [train.py:812] (2/8) Epoch 34, batch 1100, loss[loss=0.1469, simple_loss=0.251, pruned_loss=0.02138, over 6501.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2435, pruned_loss=0.02936, over 1413825.84 frames.], batch size: 37, lr: 2.30e-04
+2022-05-15 22:03:39,408 INFO [train.py:812] (2/8) Epoch 34, batch 1150, loss[loss=0.1306, simple_loss=0.2262, pruned_loss=0.01748, over 7419.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2436, pruned_loss=0.02929, over 1416833.09 frames.], batch size: 20, lr: 2.30e-04
+2022-05-15 22:04:38,149 INFO [train.py:812] (2/8) Epoch 34, batch 1200, loss[loss=0.1616, simple_loss=0.2534, pruned_loss=0.0349, over 7189.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.02952, over 1420816.60 frames.], batch size: 23, lr: 2.30e-04
+2022-05-15 22:05:35,688 INFO [train.py:812] (2/8) Epoch 34, batch 1250, loss[loss=0.1546, simple_loss=0.2595, pruned_loss=0.02485, over 7346.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02967, over 1418082.09 frames.], batch size: 22, lr: 2.30e-04
+2022-05-15 22:06:34,731 INFO [train.py:812] (2/8) Epoch 34, batch 1300, loss[loss=0.1802, simple_loss=0.2683, pruned_loss=0.04604, over 7140.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2424, pruned_loss=0.02974, over 1417975.84 frames.], batch size: 26, lr: 2.30e-04
+2022-05-15 22:07:33,170 INFO [train.py:812] (2/8) Epoch 34, batch 1350, loss[loss=0.187, simple_loss=0.2666, pruned_loss=0.05369, over 7222.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2421, pruned_loss=0.02975, over 1418842.90 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:08:32,141 INFO [train.py:812] (2/8) Epoch 34, batch 1400, loss[loss=0.1575, simple_loss=0.2498, pruned_loss=0.03254, over 7258.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2419, pruned_loss=0.02972, over 1422180.39 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:09:31,085 INFO [train.py:812] (2/8) Epoch 34, batch 1450, loss[loss=0.1625, simple_loss=0.2609, pruned_loss=0.03205, over 7410.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2419, pruned_loss=0.02963, over 1425819.71 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:10:29,313 INFO [train.py:812] (2/8) Epoch 34, batch 1500, loss[loss=0.1739, simple_loss=0.2713, pruned_loss=0.03824, over 7396.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2423, pruned_loss=0.02962, over 1424592.74 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:11:28,597 INFO [train.py:812] (2/8) Epoch 34, batch 1550, loss[loss=0.1637, simple_loss=0.2595, pruned_loss=0.03393, over 7272.00 frames.], tot_loss[loss=0.1512, simple_loss=0.243, pruned_loss=0.02974, over 1421690.74 frames.], batch size: 24, lr: 2.29e-04
+2022-05-15 22:12:27,924 INFO [train.py:812] (2/8) Epoch 34, batch 1600, loss[loss=0.1426, simple_loss=0.2338, pruned_loss=0.02572, over 7323.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2425, pruned_loss=0.02942, over 1422898.68 frames.], batch size: 20, lr: 2.29e-04
+2022-05-15 22:13:26,006 INFO [train.py:812] (2/8) Epoch 34, batch 1650, loss[loss=0.1764, simple_loss=0.271, pruned_loss=0.0409, over 7200.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02948, over 1422694.75 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:14:25,227 INFO [train.py:812] (2/8) Epoch 34, batch 1700, loss[loss=0.155, simple_loss=0.2561, pruned_loss=0.02692, over 7371.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02948, over 1426409.71 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:15:24,018 INFO [train.py:812] (2/8) Epoch 34, batch 1750, loss[loss=0.1528, simple_loss=0.2425, pruned_loss=0.03152, over 7050.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2438, pruned_loss=0.02969, over 1421520.34 frames.], batch size: 28, lr: 2.29e-04
+2022-05-15 22:16:22,625 INFO [train.py:812] (2/8) Epoch 34, batch 1800, loss[loss=0.1405, simple_loss=0.2221, pruned_loss=0.02942, over 7283.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02983, over 1422962.74 frames.], batch size: 17, lr: 2.29e-04
+2022-05-15 22:17:21,602 INFO [train.py:812] (2/8) Epoch 34, batch 1850, loss[loss=0.1465, simple_loss=0.243, pruned_loss=0.02503, over 7324.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2428, pruned_loss=0.02977, over 1414850.03 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:18:20,744 INFO [train.py:812] (2/8) Epoch 34, batch 1900, loss[loss=0.1555, simple_loss=0.249, pruned_loss=0.03098, over 6745.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02945, over 1410521.82 frames.], batch size: 31, lr: 2.29e-04
+2022-05-15 22:19:17,929 INFO [train.py:812] (2/8) Epoch 34, batch 1950, loss[loss=0.1302, simple_loss=0.2218, pruned_loss=0.01925, over 7017.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02971, over 1416750.31 frames.], batch size: 16, lr: 2.29e-04
+2022-05-15 22:20:16,776 INFO [train.py:812] (2/8) Epoch 34, batch 2000, loss[loss=0.1296, simple_loss=0.2167, pruned_loss=0.02119, over 7405.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.02991, over 1422362.95 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:21:15,725 INFO [train.py:812] (2/8) Epoch 34, batch 2050, loss[loss=0.1866, simple_loss=0.2807, pruned_loss=0.04625, over 7135.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2433, pruned_loss=0.0299, over 1421632.15 frames.], batch size: 26, lr: 2.29e-04
+2022-05-15 22:22:14,731 INFO [train.py:812] (2/8) Epoch 34, batch 2100, loss[loss=0.1708, simple_loss=0.2597, pruned_loss=0.04096, over 7221.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2437, pruned_loss=0.02992, over 1424048.22 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:23:12,291 INFO [train.py:812] (2/8) Epoch 34, batch 2150, loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02927, over 7259.00 frames.], tot_loss[loss=0.151, simple_loss=0.2427, pruned_loss=0.02964, over 1423844.74 frames.], batch size: 24, lr: 2.29e-04
+2022-05-15 22:24:11,540 INFO [train.py:812] (2/8) Epoch 34, batch 2200, loss[loss=0.1521, simple_loss=0.2453, pruned_loss=0.02948, over 7319.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02996, over 1426721.94 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:25:10,882 INFO [train.py:812] (2/8) Epoch 34, batch 2250, loss[loss=0.135, simple_loss=0.2251, pruned_loss=0.02247, over 7257.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.03012, over 1422921.79 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:26:09,582 INFO [train.py:812] (2/8) Epoch 34, batch 2300, loss[loss=0.1585, simple_loss=0.255, pruned_loss=0.03097, over 7153.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2451, pruned_loss=0.03012, over 1424043.52 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:27:08,003 INFO [train.py:812] (2/8) Epoch 34, batch 2350, loss[loss=0.1502, simple_loss=0.2399, pruned_loss=0.03029, over 7148.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.02994, over 1424629.71 frames.], batch size: 19, lr: 2.29e-04
+2022-05-15 22:28:06,537 INFO [train.py:812] (2/8) Epoch 34, batch 2400, loss[loss=0.173, simple_loss=0.2643, pruned_loss=0.0409, over 7368.00 frames.], tot_loss[loss=0.1512, simple_loss=0.243, pruned_loss=0.02964, over 1426594.86 frames.], batch size: 23, lr: 2.29e-04
+2022-05-15 22:29:04,648 INFO [train.py:812] (2/8) Epoch 34, batch 2450, loss[loss=0.1634, simple_loss=0.2617, pruned_loss=0.03256, over 7217.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2439, pruned_loss=0.02951, over 1420568.98 frames.], batch size: 21, lr: 2.29e-04
+2022-05-15 22:30:04,443 INFO [train.py:812] (2/8) Epoch 34, batch 2500, loss[loss=0.1348, simple_loss=0.2164, pruned_loss=0.0266, over 6978.00 frames.], tot_loss[loss=0.151, simple_loss=0.2439, pruned_loss=0.02905, over 1418926.71 frames.], batch size: 16, lr: 2.29e-04
+2022-05-15 22:31:02,272 INFO [train.py:812] (2/8) Epoch 34, batch 2550, loss[loss=0.1804, simple_loss=0.278, pruned_loss=0.04142, over 7344.00 frames.], tot_loss[loss=0.151, simple_loss=0.2436, pruned_loss=0.02921, over 1420937.50 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:32:00,114 INFO [train.py:812] (2/8) Epoch 34, batch 2600, loss[loss=0.1382, simple_loss=0.2241, pruned_loss=0.02618, over 7060.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2446, pruned_loss=0.02988, over 1420555.95 frames.], batch size: 18, lr: 2.29e-04
+2022-05-15 22:32:58,097 INFO [train.py:812] (2/8) Epoch 34, batch 2650, loss[loss=0.1516, simple_loss=0.2492, pruned_loss=0.02694, over 7335.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2437, pruned_loss=0.02988, over 1421015.30 frames.], batch size: 22, lr: 2.29e-04
+2022-05-15 22:33:56,977 INFO [train.py:812] (2/8) Epoch 34, batch 2700, loss[loss=0.1414, simple_loss=0.2186, pruned_loss=0.03205, over 7286.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2437, pruned_loss=0.02987, over 1425702.25 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 22:34:55,302 INFO [train.py:812] (2/8) Epoch 34, batch 2750, loss[loss=0.1465, simple_loss=0.2405, pruned_loss=0.02624, over 7323.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02966, over 1424901.01 frames.], batch size: 21, lr: 2.28e-04
+2022-05-15 22:35:54,064 INFO [train.py:812] (2/8) Epoch 34, batch 2800, loss[loss=0.1468, simple_loss=0.2295, pruned_loss=0.03204, over 7422.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02949, over 1429978.77 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 22:36:52,774 INFO [train.py:812] (2/8) Epoch 34, batch 2850, loss[loss=0.1479, simple_loss=0.2437, pruned_loss=0.02607, over 7222.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02948, over 1430798.46 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:37:50,564 INFO [train.py:812] (2/8) Epoch 34, batch 2900, loss[loss=0.1591, simple_loss=0.2562, pruned_loss=0.03103, over 7147.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02946, over 1427200.24 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:38:49,629 INFO [train.py:812] (2/8) Epoch 34, batch 2950, loss[loss=0.1557, simple_loss=0.2534, pruned_loss=0.02898, over 7144.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.02939, over 1426739.64 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:39:49,326 INFO [train.py:812] (2/8) Epoch 34, batch 3000, loss[loss=0.151, simple_loss=0.237, pruned_loss=0.03254, over 7365.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.02947, over 1427141.57 frames.], batch size: 19, lr: 2.28e-04
+2022-05-15 22:39:49,327 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-15 22:39:56,835 INFO [train.py:841] (2/8) Epoch 34, validation: loss=0.1534, simple_loss=0.2492, pruned_loss=0.02878, over 698248.00 frames.
+2022-05-15 22:40:55,232 INFO [train.py:812] (2/8) Epoch 34, batch 3050, loss[loss=0.1522, simple_loss=0.2451, pruned_loss=0.02965, over 7358.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2441, pruned_loss=0.02954, over 1427599.30 frames.], batch size: 19, lr: 2.28e-04
+2022-05-15 22:41:53,723 INFO [train.py:812] (2/8) Epoch 34, batch 3100, loss[loss=0.1292, simple_loss=0.2166, pruned_loss=0.0209, over 7213.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2437, pruned_loss=0.02943, over 1429883.11 frames.], batch size: 16, lr: 2.28e-04
+2022-05-15 22:42:52,770 INFO [train.py:812] (2/8) Epoch 34, batch 3150, loss[loss=0.1399, simple_loss=0.2192, pruned_loss=0.03031, over 7277.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.02911, over 1429542.19 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:43:51,519 INFO [train.py:812] (2/8) Epoch 34, batch 3200, loss[loss=0.1715, simple_loss=0.2607, pruned_loss=0.04113, over 5018.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02962, over 1425436.64 frames.], batch size: 53, lr: 2.28e-04
+2022-05-15 22:44:49,455 INFO [train.py:812] (2/8) Epoch 34, batch 3250, loss[loss=0.1352, simple_loss=0.224, pruned_loss=0.02323, over 7145.00 frames.], tot_loss[loss=0.151, simple_loss=0.2427, pruned_loss=0.02967, over 1422459.77 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:45:48,017 INFO [train.py:812] (2/8) Epoch 34, batch 3300, loss[loss=0.164, simple_loss=0.255, pruned_loss=0.03653, over 7020.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2431, pruned_loss=0.02988, over 1419553.14 frames.], batch size: 28, lr: 2.28e-04
+2022-05-15 22:46:47,351 INFO [train.py:812] (2/8) Epoch 34, batch 3350, loss[loss=0.1423, simple_loss=0.2504, pruned_loss=0.01708, over 7140.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2419, pruned_loss=0.02947, over 1422033.59 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:47:45,298 INFO [train.py:812] (2/8) Epoch 34, batch 3400, loss[loss=0.1592, simple_loss=0.2451, pruned_loss=0.03668, over 7200.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2423, pruned_loss=0.02942, over 1422154.12 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:48:43,975 INFO [train.py:812] (2/8) Epoch 34, batch 3450, loss[loss=0.1253, simple_loss=0.2208, pruned_loss=0.01492, over 6993.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2425, pruned_loss=0.02943, over 1427647.43 frames.], batch size: 16, lr: 2.28e-04
+2022-05-15 22:49:41,429 INFO [train.py:812] (2/8) Epoch 34, batch 3500, loss[loss=0.1569, simple_loss=0.2489, pruned_loss=0.03241, over 7200.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2442, pruned_loss=0.02984, over 1429178.03 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:50:38,737 INFO [train.py:812] (2/8) Epoch 34, batch 3550, loss[loss=0.1273, simple_loss=0.215, pruned_loss=0.01978, over 7277.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2439, pruned_loss=0.02947, over 1430393.62 frames.], batch size: 17, lr: 2.28e-04
+2022-05-15 22:51:37,803 INFO [train.py:812] (2/8) Epoch 34, batch 3600, loss[loss=0.1696, simple_loss=0.263, pruned_loss=0.03813, over 7333.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2442, pruned_loss=0.02943, over 1432303.40 frames.], batch size: 21, lr: 2.28e-04
+2022-05-15 22:52:35,097 INFO [train.py:812] (2/8) Epoch 34, batch 3650, loss[loss=0.1415, simple_loss=0.245, pruned_loss=0.01905, over 6183.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2446, pruned_loss=0.02985, over 1427291.93 frames.], batch size: 37, lr: 2.28e-04
+2022-05-15 22:53:34,806 INFO [train.py:812] (2/8) Epoch 34, batch 3700, loss[loss=0.1523, simple_loss=0.26, pruned_loss=0.02235, over 7235.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02958, over 1422691.41 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:54:33,342 INFO [train.py:812] (2/8) Epoch 34, batch 3750, loss[loss=0.1473, simple_loss=0.2443, pruned_loss=0.02509, over 7314.00 frames.], tot_loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02957, over 1419575.31 frames.], batch size: 24, lr: 2.28e-04
+2022-05-15 22:55:32,406 INFO [train.py:812] (2/8) Epoch 34, batch 3800, loss[loss=0.1471, simple_loss=0.2492, pruned_loss=0.02253, over 7149.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02937, over 1424209.15 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:56:31,701 INFO [train.py:812] (2/8) Epoch 34, batch 3850, loss[loss=0.1709, simple_loss=0.2616, pruned_loss=0.04009, over 7178.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2431, pruned_loss=0.02991, over 1426390.60 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:57:28,723 INFO [train.py:812] (2/8) Epoch 34, batch 3900, loss[loss=0.1807, simple_loss=0.2781, pruned_loss=0.04169, over 7193.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02965, over 1425230.93 frames.], batch size: 23, lr: 2.28e-04
+2022-05-15 22:58:46,454 INFO [train.py:812] (2/8) Epoch 34, batch 3950, loss[loss=0.146, simple_loss=0.2412, pruned_loss=0.02542, over 7324.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2438, pruned_loss=0.02964, over 1422519.53 frames.], batch size: 20, lr: 2.28e-04
+2022-05-15 22:59:45,590 INFO [train.py:812] (2/8) Epoch 34, batch 4000, loss[loss=0.1415, simple_loss=0.2233, pruned_loss=0.02979, over 7058.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2436, pruned_loss=0.02932, over 1423098.37 frames.], batch size: 18, lr: 2.28e-04
+2022-05-15 23:00:53,093 INFO [train.py:812] (2/8) Epoch 34, batch 4050, loss[loss=0.1555, simple_loss=0.249, pruned_loss=0.03095, over 7169.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2443, pruned_loss=0.02975, over 1418177.48 frames.], batch size: 26, lr: 2.27e-04
+2022-05-15 23:01:51,480 INFO [train.py:812] (2/8) Epoch 34, batch 4100, loss[loss=0.1632, simple_loss=0.263, pruned_loss=0.03169, over 6291.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2452, pruned_loss=0.03009, over 1418735.09 frames.], batch size: 37, lr: 2.27e-04
+2022-05-15 23:02:49,333 INFO [train.py:812] (2/8) Epoch 34, batch 4150, loss[loss=0.1255, simple_loss=0.2085, pruned_loss=0.02126, over 7405.00 frames.], tot_loss[loss=0.152, simple_loss=0.2442, pruned_loss=0.0299, over 1418075.31 frames.], batch size: 18, lr: 2.27e-04
+2022-05-15 23:03:57,831 INFO [train.py:812] (2/8) Epoch 34, batch 4200, loss[loss=0.1421, simple_loss=0.2337, pruned_loss=0.02522, over 7233.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.02972, over 1420451.82 frames.], batch size: 20, lr: 2.27e-04
+2022-05-15 23:05:06,365 INFO [train.py:812] (2/8) Epoch 34, batch 4250, loss[loss=0.1348, simple_loss=0.2155, pruned_loss=0.02705, over 7129.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2438, pruned_loss=0.02949, over 1420106.33 frames.], batch size: 17, lr: 2.27e-04
+2022-05-15 23:06:05,065 INFO [train.py:812] (2/8) Epoch 34, batch 4300, loss[loss=0.1441, simple_loss=0.2224, pruned_loss=0.03295, over 6999.00 frames.], tot_loss[loss=0.1515, simple_loss=0.244, pruned_loss=0.02952, over 1422009.96 frames.], batch size: 16, lr: 2.27e-04
+2022-05-15 23:07:13,192 INFO [train.py:812] (2/8) Epoch 34, batch 4350, loss[loss=0.1335, simple_loss=0.2196, pruned_loss=0.02369, over 7223.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2442, pruned_loss=0.02976, over 1417771.20 frames.], batch size: 16, lr: 2.27e-04
+2022-05-15 23:08:12,762 INFO [train.py:812] (2/8) Epoch 34, batch 4400, loss[loss=0.1252, simple_loss=0.2123, pruned_loss=0.0191, over 7165.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02966, over 1418824.17 frames.], batch size: 18, lr: 2.27e-04
+2022-05-15 23:09:11,221 INFO [train.py:812] (2/8) Epoch 34, batch 4450, loss[loss=0.1556, simple_loss=0.2475, pruned_loss=0.03184, over 7195.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2448, pruned_loss=0.03009, over 1401653.29 frames.], batch size: 23, lr: 2.27e-04
+2022-05-15 23:10:19,456 INFO [train.py:812] (2/8) Epoch 34, batch 4500, loss[loss=0.172, simple_loss=0.2573, pruned_loss=0.04332, over 5073.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2449, pruned_loss=0.03034, over 1391484.09 frames.], batch size: 52, lr: 2.27e-04
+2022-05-15 23:11:16,020 INFO [train.py:812] (2/8) Epoch 34, batch 4550, loss[loss=0.2299, simple_loss=0.3073, pruned_loss=0.07623, over 5064.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2469, pruned_loss=0.03125, over 1350358.38 frames.], batch size: 52, lr: 2.27e-04
+2022-05-15 23:12:20,544 INFO [train.py:812] (2/8) Epoch 35, batch 0, loss[loss=0.1602, simple_loss=0.2524, pruned_loss=0.03404, over 7229.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2524, pruned_loss=0.03404, over 7229.00 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:13:24,531 INFO [train.py:812] (2/8) Epoch 35, batch 50, loss[loss=0.1721, simple_loss=0.2666, pruned_loss=0.03881, over 7302.00 frames.], tot_loss[loss=0.1547, simple_loss=0.248, pruned_loss=0.03073, over 318300.69 frames.], batch size: 24, lr: 2.24e-04
+2022-05-15 23:14:23,040 INFO [train.py:812] (2/8) Epoch 35, batch 100, loss[loss=0.1674, simple_loss=0.2641, pruned_loss=0.03535, over 7215.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2458, pruned_loss=0.0298, over 568543.11 frames.], batch size: 26, lr: 2.24e-04
+2022-05-15 23:15:22,493 INFO [train.py:812] (2/8) Epoch 35, batch 150, loss[loss=0.1817, simple_loss=0.2758, pruned_loss=0.04381, over 7384.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2461, pruned_loss=0.03034, over 760779.42 frames.], batch size: 23, lr: 2.24e-04
+2022-05-15 23:16:21,320 INFO [train.py:812] (2/8) Epoch 35, batch 200, loss[loss=0.1396, simple_loss=0.2301, pruned_loss=0.02453, over 7081.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02963, over 909532.18 frames.], batch size: 18, lr: 2.24e-04
+2022-05-15 23:17:21,132 INFO [train.py:812] (2/8) Epoch 35, batch 250, loss[loss=0.1594, simple_loss=0.2478, pruned_loss=0.03549, over 7226.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.0294, over 1027065.00 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:18:18,839 INFO [train.py:812] (2/8) Epoch 35, batch 300, loss[loss=0.1372, simple_loss=0.2221, pruned_loss=0.02613, over 7159.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02916, over 1113656.15 frames.], batch size: 19, lr: 2.24e-04
+2022-05-15 23:19:18,449 INFO [train.py:812] (2/8) Epoch 35, batch 350, loss[loss=0.1643, simple_loss=0.2572, pruned_loss=0.03573, over 7202.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02899, over 1185257.94 frames.], batch size: 23, lr: 2.24e-04
+2022-05-15 23:20:16,873 INFO [train.py:812] (2/8) Epoch 35, batch 400, loss[loss=0.1495, simple_loss=0.2404, pruned_loss=0.02928, over 7317.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2423, pruned_loss=0.02913, over 1239601.69 frames.], batch size: 20, lr: 2.24e-04
+2022-05-15 23:21:15,065 INFO [train.py:812] (2/8) Epoch 35, batch 450, loss[loss=0.1545, simple_loss=0.2545, pruned_loss=0.02726, over 6789.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02912, over 1284507.33 frames.], batch size: 31, lr: 2.24e-04
+2022-05-15 23:22:13,109 INFO [train.py:812] (2/8) Epoch 35, batch 500, loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.0307, over 7333.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2425, pruned_loss=0.02965, over 1313890.91 frames.], batch size: 20, lr: 2.23e-04
+2022-05-15 23:23:12,694 INFO [train.py:812] (2/8) Epoch 35, batch 550, loss[loss=0.1313, simple_loss=0.2156, pruned_loss=0.02355, over 7057.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2417, pruned_loss=0.02929, over 1334675.71 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:24:10,886 INFO [train.py:812] (2/8) Epoch 35, batch 600, loss[loss=0.1616, simple_loss=0.2557, pruned_loss=0.03371, over 7336.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2424, pruned_loss=0.02907, over 1353574.00 frames.], batch size: 22, lr: 2.23e-04
+2022-05-15 23:25:10,092 INFO [train.py:812] (2/8) Epoch 35, batch 650, loss[loss=0.1339, simple_loss=0.2243, pruned_loss=0.02179, over 7166.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02919, over 1372517.44 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:26:08,923 INFO [train.py:812] (2/8) Epoch 35, batch 700, loss[loss=0.1429, simple_loss=0.2358, pruned_loss=0.02499, over 7280.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02902, over 1386508.96 frames.], batch size: 17, lr: 2.23e-04
+2022-05-15 23:27:08,854 INFO [train.py:812] (2/8) Epoch 35, batch 750, loss[loss=0.1276, simple_loss=0.2162, pruned_loss=0.01947, over 7249.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2413, pruned_loss=0.02872, over 1392659.38 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:28:07,085 INFO [train.py:812] (2/8) Epoch 35, batch 800, loss[loss=0.156, simple_loss=0.2524, pruned_loss=0.02977, over 7224.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2422, pruned_loss=0.02883, over 1401654.32 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:29:06,737 INFO [train.py:812] (2/8) Epoch 35, batch 850, loss[loss=0.1832, simple_loss=0.2763, pruned_loss=0.04508, over 7287.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.0291, over 1402708.60 frames.], batch size: 24, lr: 2.23e-04
+2022-05-15 23:30:05,620 INFO [train.py:812] (2/8) Epoch 35, batch 900, loss[loss=0.1843, simple_loss=0.2676, pruned_loss=0.05054, over 4928.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2434, pruned_loss=0.02918, over 1406655.88 frames.], batch size: 52, lr: 2.23e-04
+2022-05-15 23:31:04,508 INFO [train.py:812] (2/8) Epoch 35, batch 950, loss[loss=0.1518, simple_loss=0.2484, pruned_loss=0.02757, over 7266.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02917, over 1410194.23 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:32:02,584 INFO [train.py:812] (2/8) Epoch 35, batch 1000, loss[loss=0.1699, simple_loss=0.2591, pruned_loss=0.04035, over 7021.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.0295, over 1412130.31 frames.], batch size: 32, lr: 2.23e-04
+2022-05-15 23:33:01,148 INFO [train.py:812] (2/8) Epoch 35, batch 1050, loss[loss=0.1749, simple_loss=0.2773, pruned_loss=0.03624, over 7413.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2427, pruned_loss=0.02932, over 1417030.31 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:33:59,689 INFO [train.py:812] (2/8) Epoch 35, batch 1100, loss[loss=0.124, simple_loss=0.2118, pruned_loss=0.01809, over 7355.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02885, over 1420715.83 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:34:58,668 INFO [train.py:812] (2/8) Epoch 35, batch 1150, loss[loss=0.1488, simple_loss=0.2417, pruned_loss=0.02793, over 7206.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2424, pruned_loss=0.02908, over 1423339.74 frames.], batch size: 23, lr: 2.23e-04
+2022-05-15 23:35:56,577 INFO [train.py:812] (2/8) Epoch 35, batch 1200, loss[loss=0.1368, simple_loss=0.2253, pruned_loss=0.02413, over 7273.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2425, pruned_loss=0.02911, over 1426787.41 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:36:54,993 INFO [train.py:812] (2/8) Epoch 35, batch 1250, loss[loss=0.158, simple_loss=0.2656, pruned_loss=0.02514, over 7334.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.02944, over 1424387.92 frames.], batch size: 22, lr: 2.23e-04
+2022-05-15 23:37:53,435 INFO [train.py:812] (2/8) Epoch 35, batch 1300, loss[loss=0.1407, simple_loss=0.2381, pruned_loss=0.02167, over 7171.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.02924, over 1419946.14 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:38:52,777 INFO [train.py:812] (2/8) Epoch 35, batch 1350, loss[loss=0.184, simple_loss=0.2727, pruned_loss=0.04767, over 7014.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02934, over 1422203.74 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:39:51,257 INFO [train.py:812] (2/8) Epoch 35, batch 1400, loss[loss=0.1522, simple_loss=0.249, pruned_loss=0.02772, over 7340.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2438, pruned_loss=0.0298, over 1419933.02 frames.], batch size: 20, lr: 2.23e-04
+2022-05-15 23:40:50,632 INFO [train.py:812] (2/8) Epoch 35, batch 1450, loss[loss=0.1492, simple_loss=0.2458, pruned_loss=0.02634, over 7250.00 frames.], tot_loss[loss=0.1522, simple_loss=0.244, pruned_loss=0.03025, over 1418615.25 frames.], batch size: 19, lr: 2.23e-04
+2022-05-15 23:41:50,034 INFO [train.py:812] (2/8) Epoch 35, batch 1500, loss[loss=0.1235, simple_loss=0.2065, pruned_loss=0.0203, over 7147.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.0297, over 1420019.95 frames.], batch size: 17, lr: 2.23e-04
+2022-05-15 23:42:48,879 INFO [train.py:812] (2/8) Epoch 35, batch 1550, loss[loss=0.196, simple_loss=0.2986, pruned_loss=0.04673, over 7225.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02957, over 1420169.17 frames.], batch size: 21, lr: 2.23e-04
+2022-05-15 23:43:47,282 INFO [train.py:812] (2/8) Epoch 35, batch 1600, loss[loss=0.1606, simple_loss=0.2516, pruned_loss=0.03481, over 7128.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2427, pruned_loss=0.02892, over 1421861.56 frames.], batch size: 28, lr: 2.23e-04
+2022-05-15 23:44:46,443 INFO [train.py:812] (2/8) Epoch 35, batch 1650, loss[loss=0.1269, simple_loss=0.2054, pruned_loss=0.02423, over 7418.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02914, over 1427166.21 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:45:45,293 INFO [train.py:812] (2/8) Epoch 35, batch 1700, loss[loss=0.1668, simple_loss=0.2551, pruned_loss=0.0392, over 5051.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02922, over 1426481.06 frames.], batch size: 52, lr: 2.23e-04
+2022-05-15 23:46:45,278 INFO [train.py:812] (2/8) Epoch 35, batch 1750, loss[loss=0.1296, simple_loss=0.2234, pruned_loss=0.0179, over 7156.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02857, over 1426829.40 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:47:44,677 INFO [train.py:812] (2/8) Epoch 35, batch 1800, loss[loss=0.1432, simple_loss=0.2479, pruned_loss=0.01923, over 7279.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2402, pruned_loss=0.02796, over 1430726.53 frames.], batch size: 25, lr: 2.23e-04
+2022-05-15 23:48:43,669 INFO [train.py:812] (2/8) Epoch 35, batch 1850, loss[loss=0.123, simple_loss=0.2179, pruned_loss=0.01408, over 7070.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2408, pruned_loss=0.02853, over 1426865.54 frames.], batch size: 18, lr: 2.23e-04
+2022-05-15 23:49:42,139 INFO [train.py:812] (2/8) Epoch 35, batch 1900, loss[loss=0.1575, simple_loss=0.2467, pruned_loss=0.0341, over 7381.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2412, pruned_loss=0.02882, over 1426328.00 frames.], batch size: 23, lr: 2.22e-04
+2022-05-15 23:50:50,955 INFO [train.py:812] (2/8) Epoch 35, batch 1950, loss[loss=0.1525, simple_loss=0.2376, pruned_loss=0.03367, over 7166.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2425, pruned_loss=0.02942, over 1424913.94 frames.], batch size: 18, lr: 2.22e-04
+2022-05-15 23:51:48,108 INFO [train.py:812] (2/8) Epoch 35, batch 2000, loss[loss=0.1469, simple_loss=0.2438, pruned_loss=0.02504, over 6440.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02905, over 1420427.57 frames.], batch size: 38, lr: 2.22e-04
+2022-05-15 23:52:46,834 INFO [train.py:812] (2/8) Epoch 35, batch 2050, loss[loss=0.1513, simple_loss=0.2406, pruned_loss=0.03099, over 7123.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2431, pruned_loss=0.02957, over 1422075.07 frames.], batch size: 21, lr: 2.22e-04
+2022-05-15 23:53:45,680 INFO [train.py:812] (2/8) Epoch 35, batch 2100, loss[loss=0.1547, simple_loss=0.2477, pruned_loss=0.03088, over 7412.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2438, pruned_loss=0.02975, over 1424918.40 frames.], batch size: 21, lr: 2.22e-04
+2022-05-15 23:54:43,319 INFO [train.py:812] (2/8) Epoch 35, batch 2150, loss[loss=0.1464, simple_loss=0.2457, pruned_loss=0.02358, over 6455.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2441, pruned_loss=0.02982, over 1428657.38 frames.], batch size: 38, lr: 2.22e-04
+2022-05-15 23:55:40,399 INFO [train.py:812] (2/8) Epoch 35, batch 2200, loss[loss=0.1351, simple_loss=0.2284, pruned_loss=0.02094, over 7421.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02982, over 1424733.26 frames.], batch size: 20, lr: 2.22e-04
+2022-05-15 23:56:39,581 INFO [train.py:812] (2/8) Epoch 35, batch 2250, loss[loss=0.1357, simple_loss=0.2254, pruned_loss=0.02297, over 7290.00 frames.], tot_loss[loss=0.1518, simple_loss=0.244, pruned_loss=0.02981, over 1422550.99 frames.], batch size: 18, lr: 2.22e-04
+2022-05-15 23:57:38,197 INFO [train.py:812] (2/8) Epoch 35, batch 2300, loss[loss=0.1533, simple_loss=0.2425, pruned_loss=0.0321, over 7166.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2439, pruned_loss=0.02998, over 1418990.54 frames.], batch size: 26, lr: 2.22e-04
+2022-05-15 23:58:36,525 INFO [train.py:812] (2/8) Epoch 35, batch 2350, loss[loss=0.1711, simple_loss=0.2751, pruned_loss=0.03355, over 7061.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02954, over 1417872.76 frames.], batch size: 28, lr: 2.22e-04
+2022-05-15 23:59:34,360 INFO [train.py:812] (2/8) Epoch 35, batch 2400, loss[loss=0.1325, simple_loss=0.2163, pruned_loss=0.02439, over 6980.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2437, pruned_loss=0.02981, over 1423000.36 frames.], batch size: 16, lr: 2.22e-04
+2022-05-16 00:00:32,001 INFO [train.py:812] (2/8) Epoch 35, batch 2450, loss[loss=0.1511, simple_loss=0.2414, pruned_loss=0.03041, over 7438.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.02935, over 1422328.82 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:01:31,440 INFO [train.py:812] (2/8) Epoch 35, batch 2500, loss[loss=0.1796, simple_loss=0.2779, pruned_loss=0.04062, over 6417.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02936, over 1424250.45 frames.], batch size: 38, lr: 2.22e-04
+2022-05-16 00:02:30,463 INFO [train.py:812] (2/8) Epoch 35, batch 2550, loss[loss=0.1497, simple_loss=0.2521, pruned_loss=0.02362, over 7117.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02924, over 1424008.85 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:03:28,734 INFO [train.py:812] (2/8) Epoch 35, batch 2600, loss[loss=0.1513, simple_loss=0.247, pruned_loss=0.02779, over 7194.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2423, pruned_loss=0.02934, over 1423021.87 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:04:26,534 INFO [train.py:812] (2/8) Epoch 35, batch 2650, loss[loss=0.1668, simple_loss=0.261, pruned_loss=0.0363, over 7196.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2421, pruned_loss=0.02932, over 1422283.38 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:05:25,227 INFO [train.py:812] (2/8) Epoch 35, batch 2700, loss[loss=0.1445, simple_loss=0.2389, pruned_loss=0.02508, over 7132.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2418, pruned_loss=0.02919, over 1424552.81 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:06:24,234 INFO [train.py:812] (2/8) Epoch 35, batch 2750, loss[loss=0.1386, simple_loss=0.2303, pruned_loss=0.02347, over 7311.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02897, over 1424985.67 frames.], batch size: 21, lr: 2.22e-04
+2022-05-16 00:07:23,045 INFO [train.py:812] (2/8) Epoch 35, batch 2800, loss[loss=0.1426, simple_loss=0.2279, pruned_loss=0.02871, over 7319.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02906, over 1425501.43 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:08:20,725 INFO [train.py:812] (2/8) Epoch 35, batch 2850, loss[loss=0.1594, simple_loss=0.2505, pruned_loss=0.03417, over 7167.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02881, over 1423254.07 frames.], batch size: 19, lr: 2.22e-04
+2022-05-16 00:09:20,167 INFO [train.py:812] (2/8) Epoch 35, batch 2900, loss[loss=0.1543, simple_loss=0.2494, pruned_loss=0.02955, over 6297.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02899, over 1422756.83 frames.], batch size: 37, lr: 2.22e-04
+2022-05-16 00:10:18,322 INFO [train.py:812] (2/8) Epoch 35, batch 2950, loss[loss=0.1298, simple_loss=0.2214, pruned_loss=0.01907, over 7192.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.02922, over 1416160.32 frames.], batch size: 16, lr: 2.22e-04
+2022-05-16 00:11:17,616 INFO [train.py:812] (2/8) Epoch 35, batch 3000, loss[loss=0.1755, simple_loss=0.2666, pruned_loss=0.04218, over 7380.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02923, over 1420346.09 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:11:17,618 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-16 00:11:25,086 INFO [train.py:841] (2/8) Epoch 35, validation: loss=0.1528, simple_loss=0.2485, pruned_loss=0.02851, over 698248.00 frames.
+2022-05-16 00:12:24,391 INFO [train.py:812] (2/8) Epoch 35, batch 3050, loss[loss=0.1345, simple_loss=0.2339, pruned_loss=0.01753, over 7241.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02898, over 1423474.23 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:13:22,776 INFO [train.py:812] (2/8) Epoch 35, batch 3100, loss[loss=0.1498, simple_loss=0.2499, pruned_loss=0.02488, over 7367.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02922, over 1419888.02 frames.], batch size: 23, lr: 2.22e-04
+2022-05-16 00:14:22,589 INFO [train.py:812] (2/8) Epoch 35, batch 3150, loss[loss=0.1417, simple_loss=0.2351, pruned_loss=0.02414, over 7216.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2413, pruned_loss=0.02893, over 1422241.33 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:15:21,813 INFO [train.py:812] (2/8) Epoch 35, batch 3200, loss[loss=0.1513, simple_loss=0.2476, pruned_loss=0.02749, over 7191.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.02925, over 1426872.47 frames.], batch size: 22, lr: 2.22e-04
+2022-05-16 00:16:21,593 INFO [train.py:812] (2/8) Epoch 35, batch 3250, loss[loss=0.1399, simple_loss=0.2265, pruned_loss=0.02664, over 7443.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2424, pruned_loss=0.02928, over 1426322.29 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:17:21,156 INFO [train.py:812] (2/8) Epoch 35, batch 3300, loss[loss=0.1161, simple_loss=0.2094, pruned_loss=0.01144, over 7435.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02885, over 1427238.31 frames.], batch size: 20, lr: 2.22e-04
+2022-05-16 00:18:19,926 INFO [train.py:812] (2/8) Epoch 35, batch 3350, loss[loss=0.1431, simple_loss=0.2459, pruned_loss=0.02019, over 7427.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2431, pruned_loss=0.02886, over 1430522.47 frames.], batch size: 20, lr: 2.21e-04
+2022-05-16 00:19:17,114 INFO [train.py:812] (2/8) Epoch 35, batch 3400, loss[loss=0.1472, simple_loss=0.2384, pruned_loss=0.028, over 7267.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02905, over 1427234.31 frames.], batch size: 18, lr: 2.21e-04
+2022-05-16 00:20:15,912 INFO [train.py:812] (2/8) Epoch 35, batch 3450, loss[loss=0.124, simple_loss=0.2132, pruned_loss=0.01736, over 7010.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02916, over 1430074.12 frames.], batch size: 16, lr: 2.21e-04
+2022-05-16 00:21:14,725 INFO [train.py:812] (2/8) Epoch 35, batch 3500, loss[loss=0.1498, simple_loss=0.2488, pruned_loss=0.02534, over 7330.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02914, over 1428589.96 frames.], batch size: 22, lr: 2.21e-04
+2022-05-16 00:22:12,829 INFO [train.py:812] (2/8) Epoch 35, batch 3550, loss[loss=0.1545, simple_loss=0.2535, pruned_loss=0.02773, over 6807.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02914, over 1421594.21 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:23:10,731 INFO [train.py:812] (2/8) Epoch 35, batch 3600, loss[loss=0.1739, simple_loss=0.2599, pruned_loss=0.04394, over 7210.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02899, over 1419959.87 frames.], batch size: 22, lr: 2.21e-04
+2022-05-16 00:24:08,623 INFO [train.py:812] (2/8) Epoch 35, batch 3650, loss[loss=0.1525, simple_loss=0.2543, pruned_loss=0.02531, over 7289.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2427, pruned_loss=0.02893, over 1421089.83 frames.], batch size: 25, lr: 2.21e-04
+2022-05-16 00:25:06,917 INFO [train.py:812] (2/8) Epoch 35, batch 3700, loss[loss=0.136, simple_loss=0.2348, pruned_loss=0.01858, over 6497.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02876, over 1420451.60 frames.], batch size: 38, lr: 2.21e-04
+2022-05-16 00:26:05,701 INFO [train.py:812] (2/8) Epoch 35, batch 3750, loss[loss=0.1748, simple_loss=0.2691, pruned_loss=0.04019, over 5245.00 frames.], tot_loss[loss=0.15, simple_loss=0.2426, pruned_loss=0.0287, over 1418013.09 frames.], batch size: 53, lr: 2.21e-04
+2022-05-16 00:27:04,268 INFO [train.py:812] (2/8) Epoch 35, batch 3800, loss[loss=0.1562, simple_loss=0.2517, pruned_loss=0.03037, over 6667.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2433, pruned_loss=0.02923, over 1418653.51 frames.], batch size: 31, lr: 2.21e-04
+2022-05-16 00:28:02,104 INFO [train.py:812] (2/8) Epoch 35, batch 3850, loss[loss=0.1829, simple_loss=0.2543, pruned_loss=0.05579, over 7290.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02933, over 1421728.21 frames.], batch size: 24, lr: 2.21e-04
+2022-05-16 00:29:00,963 INFO [train.py:812] (2/8) Epoch 35, batch 3900, loss[loss=0.1331, simple_loss=0.2175, pruned_loss=0.02438, over 7221.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.0293, over 1418433.74 frames.], batch size: 16, lr: 2.21e-04
+2022-05-16 00:30:00,065 INFO [train.py:812] (2/8) Epoch 35, batch 3950, loss[loss=0.1459, simple_loss=0.2349, pruned_loss=0.02841, over 7130.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02903, over 1418495.25 frames.], batch size: 17, lr: 2.21e-04
+2022-05-16 00:30:58,359 INFO [train.py:812] (2/8) Epoch 35, batch 4000, loss[loss=0.1279, simple_loss=0.2152, pruned_loss=0.02032, over 7013.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2418, pruned_loss=0.02843, over 1418562.29 frames.], batch size: 16, lr: 2.21e-04
+2022-05-16 00:32:02,090 INFO [train.py:812] (2/8) Epoch 35, batch 4050, loss[loss=0.1492, simple_loss=0.2442, pruned_loss=0.02708, over 6413.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2422, pruned_loss=0.02839, over 1422194.47 frames.], batch size: 38, lr: 2.21e-04
+2022-05-16 00:33:00,881 INFO [train.py:812] (2/8) Epoch 35, batch 4100, loss[loss=0.1471, simple_loss=0.2426, pruned_loss=0.02578, over 7225.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2427, pruned_loss=0.02859, over 1427251.18 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:33:59,513 INFO [train.py:812] (2/8) Epoch 35, batch 4150, loss[loss=0.1446, simple_loss=0.2431, pruned_loss=0.02305, over 7315.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02864, over 1425757.36 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:34:58,342 INFO [train.py:812] (2/8) Epoch 35, batch 4200, loss[loss=0.1595, simple_loss=0.2523, pruned_loss=0.03337, over 7328.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02917, over 1423807.55 frames.], batch size: 21, lr: 2.21e-04
+2022-05-16 00:35:57,139 INFO [train.py:812] (2/8) Epoch 35, batch 4250, loss[loss=0.1453, simple_loss=0.2267, pruned_loss=0.03194, over 7298.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02903, over 1427776.30 frames.], batch size: 17, lr: 2.21e-04
+2022-05-16 00:36:55,259 INFO [train.py:812] (2/8) Epoch 35, batch 4300, loss[loss=0.1649, simple_loss=0.2503, pruned_loss=0.03968, over 7174.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2412, pruned_loss=0.02888, over 1418796.69 frames.], batch size: 26, lr: 2.21e-04
+2022-05-16 00:37:53,243 INFO [train.py:812] (2/8) Epoch 35, batch 4350, loss[loss=0.1423, simple_loss=0.2347, pruned_loss=0.02495, over 7295.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.02927, over 1414621.61 frames.], batch size: 24, lr: 2.21e-04
+2022-05-16 00:38:52,039 INFO [train.py:812] (2/8) Epoch 35, batch 4400, loss[loss=0.1297, simple_loss=0.2195, pruned_loss=0.01992, over 7165.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02958, over 1410293.31 frames.], batch size: 19, lr: 2.21e-04
+2022-05-16 00:39:50,125 INFO [train.py:812] (2/8) Epoch 35, batch 4450, loss[loss=0.1362, simple_loss=0.2388, pruned_loss=0.01685, over 6829.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02974, over 1395132.78 frames.], batch size: 32, lr: 2.21e-04
+2022-05-16 00:40:48,500 INFO [train.py:812] (2/8) Epoch 35, batch 4500, loss[loss=0.1693, simple_loss=0.264, pruned_loss=0.03734, over 7169.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02997, over 1381791.88 frames.], batch size: 26, lr: 2.21e-04
+2022-05-16 00:41:45,660 INFO [train.py:812] (2/8) Epoch 35, batch 4550, loss[loss=0.169, simple_loss=0.2471, pruned_loss=0.04547, over 4908.00 frames.], tot_loss[loss=0.154, simple_loss=0.2459, pruned_loss=0.03106, over 1356421.82 frames.], batch size: 54, lr: 2.21e-04
+2022-05-16 00:42:50,917 INFO [train.py:812] (2/8) Epoch 36, batch 0, loss[loss=0.1418, simple_loss=0.2414, pruned_loss=0.02113, over 7316.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2414, pruned_loss=0.02113, over 7316.00 frames.], batch size: 20, lr: 2.18e-04
+2022-05-16 00:43:50,522 INFO [train.py:812] (2/8) Epoch 36, batch 50, loss[loss=0.1664, simple_loss=0.2586, pruned_loss=0.03709, over 7427.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02953, over 316908.40 frames.], batch size: 20, lr: 2.18e-04
+2022-05-16 00:44:48,776 INFO [train.py:812] (2/8) Epoch 36, batch 100, loss[loss=0.1559, simple_loss=0.2463, pruned_loss=0.03274, over 5028.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2401, pruned_loss=0.02788, over 562481.39 frames.], batch size: 53, lr: 2.17e-04
+2022-05-16 00:45:47,291 INFO [train.py:812] (2/8) Epoch 36, batch 150, loss[loss=0.1484, simple_loss=0.2505, pruned_loss=0.02313, over 7232.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2417, pruned_loss=0.0284, over 751868.63 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:46:46,270 INFO [train.py:812] (2/8) Epoch 36, batch 200, loss[loss=0.1413, simple_loss=0.2387, pruned_loss=0.02199, over 7318.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2429, pruned_loss=0.02892, over 901552.48 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 00:47:45,329 INFO [train.py:812] (2/8) Epoch 36, batch 250, loss[loss=0.1463, simple_loss=0.2413, pruned_loss=0.02565, over 7167.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02904, over 1020860.43 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:48:43,645 INFO [train.py:812] (2/8) Epoch 36, batch 300, loss[loss=0.1599, simple_loss=0.2518, pruned_loss=0.03401, over 7180.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02869, over 1105053.90 frames.], batch size: 26, lr: 2.17e-04
+2022-05-16 00:49:42,212 INFO [train.py:812] (2/8) Epoch 36, batch 350, loss[loss=0.1319, simple_loss=0.2213, pruned_loss=0.02125, over 6698.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2422, pruned_loss=0.0283, over 1174316.28 frames.], batch size: 31, lr: 2.17e-04
+2022-05-16 00:50:40,235 INFO [train.py:812] (2/8) Epoch 36, batch 400, loss[loss=0.1708, simple_loss=0.2551, pruned_loss=0.04322, over 7199.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02878, over 1230315.23 frames.], batch size: 22, lr: 2.17e-04
+2022-05-16 00:51:39,732 INFO [train.py:812] (2/8) Epoch 36, batch 450, loss[loss=0.1651, simple_loss=0.2542, pruned_loss=0.03797, over 7187.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02908, over 1278194.20 frames.], batch size: 26, lr: 2.17e-04
+2022-05-16 00:52:38,603 INFO [train.py:812] (2/8) Epoch 36, batch 500, loss[loss=0.1976, simple_loss=0.2854, pruned_loss=0.05491, over 7204.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2441, pruned_loss=0.02928, over 1310242.41 frames.], batch size: 23, lr: 2.17e-04
+2022-05-16 00:53:37,426 INFO [train.py:812] (2/8) Epoch 36, batch 550, loss[loss=0.1641, simple_loss=0.2571, pruned_loss=0.03551, over 7428.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2437, pruned_loss=0.02906, over 1336759.64 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:54:35,812 INFO [train.py:812] (2/8) Epoch 36, batch 600, loss[loss=0.1514, simple_loss=0.2464, pruned_loss=0.02824, over 7210.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02885, over 1359436.77 frames.], batch size: 23, lr: 2.17e-04
+2022-05-16 00:55:34,917 INFO [train.py:812] (2/8) Epoch 36, batch 650, loss[loss=0.1391, simple_loss=0.236, pruned_loss=0.02108, over 7149.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2413, pruned_loss=0.02866, over 1373800.13 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:56:33,800 INFO [train.py:812] (2/8) Epoch 36, batch 700, loss[loss=0.1646, simple_loss=0.2443, pruned_loss=0.04249, over 7260.00 frames.], tot_loss[loss=0.149, simple_loss=0.2409, pruned_loss=0.02855, over 1385139.39 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 00:57:42,628 INFO [train.py:812] (2/8) Epoch 36, batch 750, loss[loss=0.1592, simple_loss=0.2479, pruned_loss=0.03528, over 7320.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2413, pruned_loss=0.02894, over 1384364.55 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 00:58:59,877 INFO [train.py:812] (2/8) Epoch 36, batch 800, loss[loss=0.1647, simple_loss=0.2606, pruned_loss=0.03436, over 7429.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.02924, over 1392460.28 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 00:59:58,307 INFO [train.py:812] (2/8) Epoch 36, batch 850, loss[loss=0.1475, simple_loss=0.2487, pruned_loss=0.02317, over 7213.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2425, pruned_loss=0.02913, over 1394406.07 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 01:00:57,418 INFO [train.py:812] (2/8) Epoch 36, batch 900, loss[loss=0.1325, simple_loss=0.227, pruned_loss=0.01903, over 6760.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02904, over 1401453.52 frames.], batch size: 31, lr: 2.17e-04
+2022-05-16 01:01:55,213 INFO [train.py:812] (2/8) Epoch 36, batch 950, loss[loss=0.1475, simple_loss=0.2314, pruned_loss=0.03181, over 7019.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.02923, over 1405085.82 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:03:03,136 INFO [train.py:812] (2/8) Epoch 36, batch 1000, loss[loss=0.1463, simple_loss=0.227, pruned_loss=0.03282, over 7275.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.0292, over 1406528.21 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:04:02,087 INFO [train.py:812] (2/8) Epoch 36, batch 1050, loss[loss=0.1216, simple_loss=0.2065, pruned_loss=0.01838, over 7353.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02932, over 1407569.39 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 01:05:09,922 INFO [train.py:812] (2/8) Epoch 36, batch 1100, loss[loss=0.1532, simple_loss=0.2547, pruned_loss=0.02587, over 7211.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2433, pruned_loss=0.02978, over 1407820.34 frames.], batch size: 22, lr: 2.17e-04
+2022-05-16 01:06:19,150 INFO [train.py:812] (2/8) Epoch 36, batch 1150, loss[loss=0.1546, simple_loss=0.2569, pruned_loss=0.02612, over 7277.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2424, pruned_loss=0.02925, over 1413367.47 frames.], batch size: 24, lr: 2.17e-04
+2022-05-16 01:07:18,010 INFO [train.py:812] (2/8) Epoch 36, batch 1200, loss[loss=0.1426, simple_loss=0.2315, pruned_loss=0.02683, over 7282.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2435, pruned_loss=0.02934, over 1408542.03 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:08:16,993 INFO [train.py:812] (2/8) Epoch 36, batch 1250, loss[loss=0.1477, simple_loss=0.2336, pruned_loss=0.0309, over 6993.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02897, over 1409872.38 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:09:23,879 INFO [train.py:812] (2/8) Epoch 36, batch 1300, loss[loss=0.1459, simple_loss=0.2261, pruned_loss=0.03288, over 7144.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.0289, over 1413781.05 frames.], batch size: 17, lr: 2.17e-04
+2022-05-16 01:10:23,447 INFO [train.py:812] (2/8) Epoch 36, batch 1350, loss[loss=0.1294, simple_loss=0.2135, pruned_loss=0.02268, over 7271.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02872, over 1418763.60 frames.], batch size: 19, lr: 2.17e-04
+2022-05-16 01:11:21,645 INFO [train.py:812] (2/8) Epoch 36, batch 1400, loss[loss=0.1404, simple_loss=0.2203, pruned_loss=0.03022, over 6987.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02898, over 1417345.31 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:12:20,463 INFO [train.py:812] (2/8) Epoch 36, batch 1450, loss[loss=0.1378, simple_loss=0.223, pruned_loss=0.02632, over 7238.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.02941, over 1414769.15 frames.], batch size: 16, lr: 2.17e-04
+2022-05-16 01:13:19,128 INFO [train.py:812] (2/8) Epoch 36, batch 1500, loss[loss=0.1451, simple_loss=0.237, pruned_loss=0.02666, over 7322.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02941, over 1419434.46 frames.], batch size: 21, lr: 2.17e-04
+2022-05-16 01:14:17,131 INFO [train.py:812] (2/8) Epoch 36, batch 1550, loss[loss=0.1512, simple_loss=0.2492, pruned_loss=0.0266, over 7239.00 frames.], tot_loss[loss=0.151, simple_loss=0.2436, pruned_loss=0.02917, over 1420960.64 frames.], batch size: 20, lr: 2.17e-04
+2022-05-16 01:15:14,895 INFO [train.py:812] (2/8) Epoch 36, batch 1600, loss[loss=0.1887, simple_loss=0.2864, pruned_loss=0.04551, over 7376.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02913, over 1420761.95 frames.], batch size: 23, lr: 2.16e-04
+2022-05-16 01:16:13,263 INFO [train.py:812] (2/8) Epoch 36, batch 1650, loss[loss=0.1618, simple_loss=0.2554, pruned_loss=0.03407, over 7180.00 frames.], tot_loss[loss=0.1505, simple_loss=0.243, pruned_loss=0.029, over 1421841.45 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:17:10,739 INFO [train.py:812] (2/8) Epoch 36, batch 1700, loss[loss=0.1576, simple_loss=0.255, pruned_loss=0.03008, over 7296.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2432, pruned_loss=0.02875, over 1424147.67 frames.], batch size: 25, lr: 2.16e-04
+2022-05-16 01:18:09,641 INFO [train.py:812] (2/8) Epoch 36, batch 1750, loss[loss=0.1359, simple_loss=0.2235, pruned_loss=0.02418, over 7278.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2433, pruned_loss=0.02911, over 1420124.15 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:19:07,097 INFO [train.py:812] (2/8) Epoch 36, batch 1800, loss[loss=0.1671, simple_loss=0.2611, pruned_loss=0.03655, over 7181.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2438, pruned_loss=0.02935, over 1422235.45 frames.], batch size: 23, lr: 2.16e-04
+2022-05-16 01:20:05,569 INFO [train.py:812] (2/8) Epoch 36, batch 1850, loss[loss=0.1422, simple_loss=0.2371, pruned_loss=0.02362, over 7113.00 frames.], tot_loss[loss=0.1507, simple_loss=0.243, pruned_loss=0.02924, over 1424748.12 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:21:04,170 INFO [train.py:812] (2/8) Epoch 36, batch 1900, loss[loss=0.1498, simple_loss=0.2504, pruned_loss=0.02458, over 6695.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02944, over 1424680.29 frames.], batch size: 31, lr: 2.16e-04
+2022-05-16 01:22:03,014 INFO [train.py:812] (2/8) Epoch 36, batch 1950, loss[loss=0.1398, simple_loss=0.2387, pruned_loss=0.02049, over 7236.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02907, over 1422693.79 frames.], batch size: 20, lr: 2.16e-04
+2022-05-16 01:23:01,524 INFO [train.py:812] (2/8) Epoch 36, batch 2000, loss[loss=0.1391, simple_loss=0.2314, pruned_loss=0.02341, over 7001.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2435, pruned_loss=0.0292, over 1420122.57 frames.], batch size: 16, lr: 2.16e-04
+2022-05-16 01:24:00,257 INFO [train.py:812] (2/8) Epoch 36, batch 2050, loss[loss=0.1595, simple_loss=0.253, pruned_loss=0.03304, over 7319.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2436, pruned_loss=0.02912, over 1425112.84 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:24:59,290 INFO [train.py:812] (2/8) Epoch 36, batch 2100, loss[loss=0.1463, simple_loss=0.2458, pruned_loss=0.02341, over 7419.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02879, over 1423463.80 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:25:59,142 INFO [train.py:812] (2/8) Epoch 36, batch 2150, loss[loss=0.1321, simple_loss=0.2253, pruned_loss=0.01939, over 7253.00 frames.], tot_loss[loss=0.149, simple_loss=0.2417, pruned_loss=0.02822, over 1425755.92 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:26:58,709 INFO [train.py:812] (2/8) Epoch 36, batch 2200, loss[loss=0.1318, simple_loss=0.2142, pruned_loss=0.02468, over 7412.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2417, pruned_loss=0.02855, over 1425072.45 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:27:57,340 INFO [train.py:812] (2/8) Epoch 36, batch 2250, loss[loss=0.1494, simple_loss=0.2528, pruned_loss=0.02304, over 7343.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2424, pruned_loss=0.02834, over 1421038.08 frames.], batch size: 22, lr: 2.16e-04
+2022-05-16 01:28:55,630 INFO [train.py:812] (2/8) Epoch 36, batch 2300, loss[loss=0.1412, simple_loss=0.2218, pruned_loss=0.03033, over 7132.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.02881, over 1424564.04 frames.], batch size: 17, lr: 2.16e-04
+2022-05-16 01:29:55,104 INFO [train.py:812] (2/8) Epoch 36, batch 2350, loss[loss=0.1819, simple_loss=0.2689, pruned_loss=0.0474, over 5341.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02912, over 1423544.32 frames.], batch size: 52, lr: 2.16e-04
+2022-05-16 01:30:54,486 INFO [train.py:812] (2/8) Epoch 36, batch 2400, loss[loss=0.1432, simple_loss=0.2352, pruned_loss=0.02558, over 7410.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02903, over 1426195.56 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:31:54,045 INFO [train.py:812] (2/8) Epoch 36, batch 2450, loss[loss=0.1321, simple_loss=0.2173, pruned_loss=0.02344, over 7166.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2427, pruned_loss=0.02935, over 1422316.67 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:32:52,237 INFO [train.py:812] (2/8) Epoch 36, batch 2500, loss[loss=0.1577, simple_loss=0.2541, pruned_loss=0.03059, over 7141.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.0294, over 1425782.84 frames.], batch size: 20, lr: 2.16e-04
+2022-05-16 01:33:51,371 INFO [train.py:812] (2/8) Epoch 36, batch 2550, loss[loss=0.1497, simple_loss=0.2459, pruned_loss=0.02674, over 7359.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02976, over 1423146.26 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:34:50,029 INFO [train.py:812] (2/8) Epoch 36, batch 2600, loss[loss=0.1427, simple_loss=0.2372, pruned_loss=0.02413, over 7152.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02972, over 1423968.89 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:35:48,586 INFO [train.py:812] (2/8) Epoch 36, batch 2650, loss[loss=0.2243, simple_loss=0.3074, pruned_loss=0.07062, over 5026.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2437, pruned_loss=0.02992, over 1422196.18 frames.], batch size: 52, lr: 2.16e-04
+2022-05-16 01:36:46,991 INFO [train.py:812] (2/8) Epoch 36, batch 2700, loss[loss=0.146, simple_loss=0.2437, pruned_loss=0.02415, over 7316.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2432, pruned_loss=0.02978, over 1423269.00 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:37:45,790 INFO [train.py:812] (2/8) Epoch 36, batch 2750, loss[loss=0.1477, simple_loss=0.2448, pruned_loss=0.02534, over 7102.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02946, over 1425744.48 frames.], batch size: 21, lr: 2.16e-04
+2022-05-16 01:38:44,968 INFO [train.py:812] (2/8) Epoch 36, batch 2800, loss[loss=0.1756, simple_loss=0.2674, pruned_loss=0.04189, over 7208.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2419, pruned_loss=0.02942, over 1426792.38 frames.], batch size: 22, lr: 2.16e-04
+2022-05-16 01:39:44,958 INFO [train.py:812] (2/8) Epoch 36, batch 2850, loss[loss=0.1271, simple_loss=0.2154, pruned_loss=0.01937, over 7274.00 frames.], tot_loss[loss=0.15, simple_loss=0.2414, pruned_loss=0.02931, over 1427556.94 frames.], batch size: 17, lr: 2.16e-04
+2022-05-16 01:40:43,909 INFO [train.py:812] (2/8) Epoch 36, batch 2900, loss[loss=0.1472, simple_loss=0.2447, pruned_loss=0.02485, over 7248.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2409, pruned_loss=0.02935, over 1426981.48 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:41:42,646 INFO [train.py:812] (2/8) Epoch 36, batch 2950, loss[loss=0.1281, simple_loss=0.2172, pruned_loss=0.01943, over 7163.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2418, pruned_loss=0.02919, over 1424886.52 frames.], batch size: 18, lr: 2.16e-04
+2022-05-16 01:42:41,190 INFO [train.py:812] (2/8) Epoch 36, batch 3000, loss[loss=0.1488, simple_loss=0.2417, pruned_loss=0.02797, over 7171.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02952, over 1421888.67 frames.], batch size: 19, lr: 2.16e-04
+2022-05-16 01:42:41,191 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-16 01:42:48,527 INFO [train.py:841] (2/8) Epoch 36, validation: loss=0.1533, simple_loss=0.2487, pruned_loss=0.02893, over 698248.00 frames.
+2022-05-16 01:43:48,423 INFO [train.py:812] (2/8) Epoch 36, batch 3050, loss[loss=0.1974, simple_loss=0.2939, pruned_loss=0.05039, over 7318.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02948, over 1424563.51 frames.], batch size: 24, lr: 2.16e-04
+2022-05-16 01:44:47,693 INFO [train.py:812] (2/8) Epoch 36, batch 3100, loss[loss=0.1709, simple_loss=0.2687, pruned_loss=0.03653, over 7312.00 frames.], tot_loss[loss=0.151, simple_loss=0.2435, pruned_loss=0.02925, over 1428912.29 frames.], batch size: 25, lr: 2.15e-04
+2022-05-16 01:45:47,512 INFO [train.py:812] (2/8) Epoch 36, batch 3150, loss[loss=0.194, simple_loss=0.2746, pruned_loss=0.05672, over 7354.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02945, over 1427309.15 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:46:46,134 INFO [train.py:812] (2/8) Epoch 36, batch 3200, loss[loss=0.1298, simple_loss=0.2118, pruned_loss=0.02389, over 7141.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2437, pruned_loss=0.02977, over 1421835.74 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 01:47:45,903 INFO [train.py:812] (2/8) Epoch 36, batch 3250, loss[loss=0.1775, simple_loss=0.2675, pruned_loss=0.04379, over 5223.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02951, over 1419749.55 frames.], batch size: 52, lr: 2.15e-04
+2022-05-16 01:48:53,223 INFO [train.py:812] (2/8) Epoch 36, batch 3300, loss[loss=0.1646, simple_loss=0.2585, pruned_loss=0.03538, over 7203.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2437, pruned_loss=0.02972, over 1423134.20 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:49:52,250 INFO [train.py:812] (2/8) Epoch 36, batch 3350, loss[loss=0.1547, simple_loss=0.2499, pruned_loss=0.02973, over 7202.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02961, over 1427587.56 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 01:50:50,255 INFO [train.py:812] (2/8) Epoch 36, batch 3400, loss[loss=0.1519, simple_loss=0.235, pruned_loss=0.03444, over 7252.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02927, over 1425806.36 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 01:51:53,849 INFO [train.py:812] (2/8) Epoch 36, batch 3450, loss[loss=0.1355, simple_loss=0.2179, pruned_loss=0.02654, over 7250.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2427, pruned_loss=0.02922, over 1423215.21 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 01:52:52,271 INFO [train.py:812] (2/8) Epoch 36, batch 3500, loss[loss=0.1647, simple_loss=0.2749, pruned_loss=0.02724, over 7412.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02902, over 1420463.86 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 01:53:50,966 INFO [train.py:812] (2/8) Epoch 36, batch 3550, loss[loss=0.153, simple_loss=0.2558, pruned_loss=0.02508, over 7093.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02894, over 1423829.25 frames.], batch size: 28, lr: 2.15e-04
+2022-05-16 01:54:49,012 INFO [train.py:812] (2/8) Epoch 36, batch 3600, loss[loss=0.1742, simple_loss=0.2594, pruned_loss=0.04446, over 7293.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02899, over 1421478.69 frames.], batch size: 25, lr: 2.15e-04
+2022-05-16 01:55:48,146 INFO [train.py:812] (2/8) Epoch 36, batch 3650, loss[loss=0.1573, simple_loss=0.2528, pruned_loss=0.03084, over 7285.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2429, pruned_loss=0.02896, over 1423266.42 frames.], batch size: 24, lr: 2.15e-04
+2022-05-16 01:56:46,030 INFO [train.py:812] (2/8) Epoch 36, batch 3700, loss[loss=0.1645, simple_loss=0.2572, pruned_loss=0.03593, over 7105.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02901, over 1426170.28 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 01:57:44,753 INFO [train.py:812] (2/8) Epoch 36, batch 3750, loss[loss=0.1736, simple_loss=0.2716, pruned_loss=0.0378, over 7330.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2432, pruned_loss=0.0292, over 1424924.80 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 01:58:43,594 INFO [train.py:812] (2/8) Epoch 36, batch 3800, loss[loss=0.1346, simple_loss=0.2227, pruned_loss=0.02327, over 7348.00 frames.], tot_loss[loss=0.151, simple_loss=0.2437, pruned_loss=0.0292, over 1427422.31 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 01:59:42,776 INFO [train.py:812] (2/8) Epoch 36, batch 3850, loss[loss=0.1394, simple_loss=0.2249, pruned_loss=0.02696, over 7011.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.02923, over 1422987.59 frames.], batch size: 16, lr: 2.15e-04
+2022-05-16 02:00:41,790 INFO [train.py:812] (2/8) Epoch 36, batch 3900, loss[loss=0.1533, simple_loss=0.2484, pruned_loss=0.02905, over 7193.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.02945, over 1425432.97 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 02:01:40,059 INFO [train.py:812] (2/8) Epoch 36, batch 3950, loss[loss=0.159, simple_loss=0.2487, pruned_loss=0.03463, over 6675.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2438, pruned_loss=0.02945, over 1423259.12 frames.], batch size: 31, lr: 2.15e-04
+2022-05-16 02:02:38,475 INFO [train.py:812] (2/8) Epoch 36, batch 4000, loss[loss=0.163, simple_loss=0.2577, pruned_loss=0.03418, over 7081.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2447, pruned_loss=0.02998, over 1423388.22 frames.], batch size: 28, lr: 2.15e-04
+2022-05-16 02:03:36,273 INFO [train.py:812] (2/8) Epoch 36, batch 4050, loss[loss=0.1609, simple_loss=0.253, pruned_loss=0.0344, over 7222.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2444, pruned_loss=0.02958, over 1427087.35 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:04:34,901 INFO [train.py:812] (2/8) Epoch 36, batch 4100, loss[loss=0.1485, simple_loss=0.2279, pruned_loss=0.03457, over 7105.00 frames.], tot_loss[loss=0.152, simple_loss=0.2445, pruned_loss=0.02979, over 1426583.15 frames.], batch size: 17, lr: 2.15e-04
+2022-05-16 02:05:34,475 INFO [train.py:812] (2/8) Epoch 36, batch 4150, loss[loss=0.1808, simple_loss=0.2798, pruned_loss=0.04094, over 7207.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02951, over 1419263.82 frames.], batch size: 23, lr: 2.15e-04
+2022-05-16 02:06:32,904 INFO [train.py:812] (2/8) Epoch 36, batch 4200, loss[loss=0.136, simple_loss=0.2299, pruned_loss=0.02099, over 7234.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02934, over 1417820.85 frames.], batch size: 20, lr: 2.15e-04
+2022-05-16 02:07:31,910 INFO [train.py:812] (2/8) Epoch 36, batch 4250, loss[loss=0.1672, simple_loss=0.2614, pruned_loss=0.03644, over 7210.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2422, pruned_loss=0.02924, over 1416557.41 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 02:08:31,061 INFO [train.py:812] (2/8) Epoch 36, batch 4300, loss[loss=0.1532, simple_loss=0.2545, pruned_loss=0.02602, over 7202.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2421, pruned_loss=0.02936, over 1412221.34 frames.], batch size: 22, lr: 2.15e-04
+2022-05-16 02:09:30,583 INFO [train.py:812] (2/8) Epoch 36, batch 4350, loss[loss=0.1385, simple_loss=0.2362, pruned_loss=0.02039, over 7423.00 frames.], tot_loss[loss=0.15, simple_loss=0.2415, pruned_loss=0.02922, over 1411650.86 frames.], batch size: 20, lr: 2.15e-04
+2022-05-16 02:10:29,637 INFO [train.py:812] (2/8) Epoch 36, batch 4400, loss[loss=0.1598, simple_loss=0.2479, pruned_loss=0.03587, over 7348.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2414, pruned_loss=0.02889, over 1416189.70 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 02:11:29,803 INFO [train.py:812] (2/8) Epoch 36, batch 4450, loss[loss=0.153, simple_loss=0.2577, pruned_loss=0.0242, over 7217.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2408, pruned_loss=0.02884, over 1406242.21 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:12:28,148 INFO [train.py:812] (2/8) Epoch 36, batch 4500, loss[loss=0.1536, simple_loss=0.2478, pruned_loss=0.0297, over 7229.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2403, pruned_loss=0.02877, over 1394879.93 frames.], batch size: 21, lr: 2.15e-04
+2022-05-16 02:13:26,411 INFO [train.py:812] (2/8) Epoch 36, batch 4550, loss[loss=0.1525, simple_loss=0.2424, pruned_loss=0.03131, over 7247.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2411, pruned_loss=0.02939, over 1358056.91 frames.], batch size: 19, lr: 2.15e-04
+2022-05-16 02:14:35,966 INFO [train.py:812] (2/8) Epoch 37, batch 0, loss[loss=0.1455, simple_loss=0.2387, pruned_loss=0.02617, over 7331.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2387, pruned_loss=0.02617, over 7331.00 frames.], batch size: 22, lr: 2.12e-04
+2022-05-16 02:15:34,996 INFO [train.py:812] (2/8) Epoch 37, batch 50, loss[loss=0.1406, simple_loss=0.222, pruned_loss=0.02958, over 7067.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02906, over 322284.82 frames.], batch size: 18, lr: 2.12e-04
+2022-05-16 02:16:33,844 INFO [train.py:812] (2/8) Epoch 37, batch 100, loss[loss=0.131, simple_loss=0.2281, pruned_loss=0.01698, over 7328.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2438, pruned_loss=0.02957, over 567244.84 frames.], batch size: 20, lr: 2.12e-04
+2022-05-16 02:17:32,802 INFO [train.py:812] (2/8) Epoch 37, batch 150, loss[loss=0.1585, simple_loss=0.2528, pruned_loss=0.03208, over 7077.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2441, pruned_loss=0.0297, over 754997.03 frames.], batch size: 28, lr: 2.11e-04
+2022-05-16 02:18:31,116 INFO [train.py:812] (2/8) Epoch 37, batch 200, loss[loss=0.1563, simple_loss=0.258, pruned_loss=0.02734, over 7319.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2453, pruned_loss=0.02962, over 906404.01 frames.], batch size: 21, lr: 2.11e-04
+2022-05-16 02:19:29,649 INFO [train.py:812] (2/8) Epoch 37, batch 250, loss[loss=0.1318, simple_loss=0.2238, pruned_loss=0.01988, over 7255.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2437, pruned_loss=0.02891, over 1018027.53 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:20:28,585 INFO [train.py:812] (2/8) Epoch 37, batch 300, loss[loss=0.1671, simple_loss=0.2599, pruned_loss=0.03713, over 7333.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2438, pruned_loss=0.02924, over 1104636.60 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:21:27,105 INFO [train.py:812] (2/8) Epoch 37, batch 350, loss[loss=0.1349, simple_loss=0.2273, pruned_loss=0.02128, over 7162.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02952, over 1173808.68 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:22:25,668 INFO [train.py:812] (2/8) Epoch 37, batch 400, loss[loss=0.1577, simple_loss=0.2535, pruned_loss=0.031, over 7235.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02913, over 1233468.99 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:23:24,541 INFO [train.py:812] (2/8) Epoch 37, batch 450, loss[loss=0.1552, simple_loss=0.2538, pruned_loss=0.02829, over 7154.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2432, pruned_loss=0.02894, over 1277825.87 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:24:21,908 INFO [train.py:812] (2/8) Epoch 37, batch 500, loss[loss=0.15, simple_loss=0.2433, pruned_loss=0.02833, over 7242.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2429, pruned_loss=0.02869, over 1307404.17 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:25:21,169 INFO [train.py:812] (2/8) Epoch 37, batch 550, loss[loss=0.134, simple_loss=0.2181, pruned_loss=0.025, over 7065.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2435, pruned_loss=0.02933, over 1324154.29 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:26:19,455 INFO [train.py:812] (2/8) Epoch 37, batch 600, loss[loss=0.1368, simple_loss=0.2257, pruned_loss=0.02393, over 7415.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.0288, over 1348834.06 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:27:18,100 INFO [train.py:812] (2/8) Epoch 37, batch 650, loss[loss=0.1239, simple_loss=0.2116, pruned_loss=0.01814, over 7130.00 frames.], tot_loss[loss=0.149, simple_loss=0.241, pruned_loss=0.02848, over 1369114.92 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:28:16,745 INFO [train.py:812] (2/8) Epoch 37, batch 700, loss[loss=0.1415, simple_loss=0.2354, pruned_loss=0.02382, over 7229.00 frames.], tot_loss[loss=0.1486, simple_loss=0.241, pruned_loss=0.02815, over 1381428.33 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:29:16,761 INFO [train.py:812] (2/8) Epoch 37, batch 750, loss[loss=0.1365, simple_loss=0.2239, pruned_loss=0.02452, over 7168.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2412, pruned_loss=0.02816, over 1390713.46 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:30:15,255 INFO [train.py:812] (2/8) Epoch 37, batch 800, loss[loss=0.1316, simple_loss=0.2212, pruned_loss=0.02096, over 7418.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2417, pruned_loss=0.02857, over 1400772.15 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:31:14,045 INFO [train.py:812] (2/8) Epoch 37, batch 850, loss[loss=0.134, simple_loss=0.2214, pruned_loss=0.02329, over 7259.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02919, over 1400201.90 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:32:12,862 INFO [train.py:812] (2/8) Epoch 37, batch 900, loss[loss=0.1389, simple_loss=0.2237, pruned_loss=0.02707, over 7063.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2418, pruned_loss=0.02863, over 1408186.33 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:33:11,831 INFO [train.py:812] (2/8) Epoch 37, batch 950, loss[loss=0.1188, simple_loss=0.2057, pruned_loss=0.01592, over 7280.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02889, over 1411540.92 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:34:09,793 INFO [train.py:812] (2/8) Epoch 37, batch 1000, loss[loss=0.1677, simple_loss=0.2609, pruned_loss=0.0372, over 6733.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2411, pruned_loss=0.02824, over 1413946.84 frames.], batch size: 31, lr: 2.11e-04
+2022-05-16 02:35:08,650 INFO [train.py:812] (2/8) Epoch 37, batch 1050, loss[loss=0.1521, simple_loss=0.2433, pruned_loss=0.03045, over 7369.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2404, pruned_loss=0.02814, over 1418219.17 frames.], batch size: 23, lr: 2.11e-04
+2022-05-16 02:36:07,858 INFO [train.py:812] (2/8) Epoch 37, batch 1100, loss[loss=0.1446, simple_loss=0.2428, pruned_loss=0.02319, over 7226.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2402, pruned_loss=0.02847, over 1418811.26 frames.], batch size: 21, lr: 2.11e-04
+2022-05-16 02:37:06,613 INFO [train.py:812] (2/8) Epoch 37, batch 1150, loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02873, over 4947.00 frames.], tot_loss[loss=0.1483, simple_loss=0.24, pruned_loss=0.02835, over 1417276.48 frames.], batch size: 52, lr: 2.11e-04
+2022-05-16 02:38:04,300 INFO [train.py:812] (2/8) Epoch 37, batch 1200, loss[loss=0.1704, simple_loss=0.2558, pruned_loss=0.04249, over 7137.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02905, over 1419623.76 frames.], batch size: 20, lr: 2.11e-04
+2022-05-16 02:39:03,404 INFO [train.py:812] (2/8) Epoch 37, batch 1250, loss[loss=0.1426, simple_loss=0.2402, pruned_loss=0.02254, over 7197.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2435, pruned_loss=0.02906, over 1419482.03 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:40:01,883 INFO [train.py:812] (2/8) Epoch 37, batch 1300, loss[loss=0.1459, simple_loss=0.228, pruned_loss=0.03191, over 7135.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2436, pruned_loss=0.02927, over 1421477.66 frames.], batch size: 17, lr: 2.11e-04
+2022-05-16 02:41:00,871 INFO [train.py:812] (2/8) Epoch 37, batch 1350, loss[loss=0.1615, simple_loss=0.2448, pruned_loss=0.03911, over 7067.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2441, pruned_loss=0.0297, over 1417772.84 frames.], batch size: 18, lr: 2.11e-04
+2022-05-16 02:41:59,962 INFO [train.py:812] (2/8) Epoch 37, batch 1400, loss[loss=0.1313, simple_loss=0.2218, pruned_loss=0.02038, over 6998.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2434, pruned_loss=0.02944, over 1417202.77 frames.], batch size: 16, lr: 2.11e-04
+2022-05-16 02:42:58,494 INFO [train.py:812] (2/8) Epoch 37, batch 1450, loss[loss=0.158, simple_loss=0.2542, pruned_loss=0.03093, over 7285.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2436, pruned_loss=0.02938, over 1419383.77 frames.], batch size: 24, lr: 2.11e-04
+2022-05-16 02:43:56,628 INFO [train.py:812] (2/8) Epoch 37, batch 1500, loss[loss=0.176, simple_loss=0.2808, pruned_loss=0.03564, over 7263.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2442, pruned_loss=0.0298, over 1415601.09 frames.], batch size: 24, lr: 2.11e-04
+2022-05-16 02:44:55,881 INFO [train.py:812] (2/8) Epoch 37, batch 1550, loss[loss=0.1479, simple_loss=0.2448, pruned_loss=0.02549, over 6767.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02962, over 1411407.52 frames.], batch size: 31, lr: 2.11e-04
+2022-05-16 02:45:54,002 INFO [train.py:812] (2/8) Epoch 37, batch 1600, loss[loss=0.1654, simple_loss=0.2554, pruned_loss=0.03766, over 7374.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02908, over 1412752.02 frames.], batch size: 23, lr: 2.11e-04
+2022-05-16 02:46:52,094 INFO [train.py:812] (2/8) Epoch 37, batch 1650, loss[loss=0.1974, simple_loss=0.2969, pruned_loss=0.04899, over 7202.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02903, over 1415518.61 frames.], batch size: 22, lr: 2.11e-04
+2022-05-16 02:47:50,654 INFO [train.py:812] (2/8) Epoch 37, batch 1700, loss[loss=0.1454, simple_loss=0.2406, pruned_loss=0.02507, over 7156.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02951, over 1414229.29 frames.], batch size: 19, lr: 2.11e-04
+2022-05-16 02:48:48,768 INFO [train.py:812] (2/8) Epoch 37, batch 1750, loss[loss=0.1426, simple_loss=0.2353, pruned_loss=0.02493, over 7356.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2427, pruned_loss=0.02956, over 1407490.92 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:49:47,214 INFO [train.py:812] (2/8) Epoch 37, batch 1800, loss[loss=0.1721, simple_loss=0.2673, pruned_loss=0.0385, over 7302.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.03012, over 1409301.87 frames.], batch size: 24, lr: 2.10e-04
+2022-05-16 02:50:46,346 INFO [train.py:812] (2/8) Epoch 37, batch 1850, loss[loss=0.1317, simple_loss=0.2253, pruned_loss=0.019, over 7247.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2433, pruned_loss=0.02996, over 1410578.48 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:51:45,056 INFO [train.py:812] (2/8) Epoch 37, batch 1900, loss[loss=0.1553, simple_loss=0.2485, pruned_loss=0.03103, over 6808.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02997, over 1416217.34 frames.], batch size: 31, lr: 2.10e-04
+2022-05-16 02:52:44,044 INFO [train.py:812] (2/8) Epoch 37, batch 1950, loss[loss=0.1617, simple_loss=0.2595, pruned_loss=0.03195, over 7224.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2429, pruned_loss=0.0293, over 1419731.93 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:53:42,340 INFO [train.py:812] (2/8) Epoch 37, batch 2000, loss[loss=0.1604, simple_loss=0.2594, pruned_loss=0.03073, over 7405.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02927, over 1416581.56 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:54:41,770 INFO [train.py:812] (2/8) Epoch 37, batch 2050, loss[loss=0.1441, simple_loss=0.2473, pruned_loss=0.02043, over 7243.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2427, pruned_loss=0.02929, over 1420473.87 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 02:55:38,567 INFO [train.py:812] (2/8) Epoch 37, batch 2100, loss[loss=0.1604, simple_loss=0.2559, pruned_loss=0.03242, over 7144.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2419, pruned_loss=0.02925, over 1420920.25 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 02:56:46,818 INFO [train.py:812] (2/8) Epoch 37, batch 2150, loss[loss=0.1419, simple_loss=0.2424, pruned_loss=0.02068, over 7412.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2421, pruned_loss=0.02931, over 1418795.77 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 02:57:45,098 INFO [train.py:812] (2/8) Epoch 37, batch 2200, loss[loss=0.1534, simple_loss=0.2455, pruned_loss=0.03062, over 7252.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2413, pruned_loss=0.02891, over 1420930.13 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 02:58:53,431 INFO [train.py:812] (2/8) Epoch 37, batch 2250, loss[loss=0.1477, simple_loss=0.2505, pruned_loss=0.02241, over 7141.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02889, over 1421338.91 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 03:00:01,339 INFO [train.py:812] (2/8) Epoch 37, batch 2300, loss[loss=0.1688, simple_loss=0.2669, pruned_loss=0.03541, over 7201.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2425, pruned_loss=0.02883, over 1419774.42 frames.], batch size: 23, lr: 2.10e-04
+2022-05-16 03:01:01,002 INFO [train.py:812] (2/8) Epoch 37, batch 2350, loss[loss=0.1185, simple_loss=0.1999, pruned_loss=0.01852, over 7284.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2429, pruned_loss=0.02906, over 1413395.86 frames.], batch size: 17, lr: 2.10e-04
+2022-05-16 03:01:59,215 INFO [train.py:812] (2/8) Epoch 37, batch 2400, loss[loss=0.154, simple_loss=0.2566, pruned_loss=0.02568, over 7318.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.02861, over 1419472.28 frames.], batch size: 25, lr: 2.10e-04
+2022-05-16 03:02:57,107 INFO [train.py:812] (2/8) Epoch 37, batch 2450, loss[loss=0.1626, simple_loss=0.2466, pruned_loss=0.0393, over 7145.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02882, over 1424762.10 frames.], batch size: 26, lr: 2.10e-04
+2022-05-16 03:04:04,665 INFO [train.py:812] (2/8) Epoch 37, batch 2500, loss[loss=0.1401, simple_loss=0.2266, pruned_loss=0.02674, over 7161.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02859, over 1427659.56 frames.], batch size: 19, lr: 2.10e-04
+2022-05-16 03:05:04,379 INFO [train.py:812] (2/8) Epoch 37, batch 2550, loss[loss=0.1604, simple_loss=0.2575, pruned_loss=0.03165, over 7290.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2411, pruned_loss=0.02879, over 1427961.69 frames.], batch size: 24, lr: 2.10e-04
+2022-05-16 03:06:02,642 INFO [train.py:812] (2/8) Epoch 37, batch 2600, loss[loss=0.1224, simple_loss=0.2091, pruned_loss=0.01789, over 7223.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2415, pruned_loss=0.02865, over 1425275.13 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:07:21,590 INFO [train.py:812] (2/8) Epoch 37, batch 2650, loss[loss=0.1862, simple_loss=0.2774, pruned_loss=0.04747, over 7206.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2422, pruned_loss=0.0288, over 1428325.28 frames.], batch size: 22, lr: 2.10e-04
+2022-05-16 03:08:19,638 INFO [train.py:812] (2/8) Epoch 37, batch 2700, loss[loss=0.1622, simple_loss=0.2583, pruned_loss=0.03308, over 6473.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2424, pruned_loss=0.02911, over 1424276.53 frames.], batch size: 38, lr: 2.10e-04
+2022-05-16 03:09:18,868 INFO [train.py:812] (2/8) Epoch 37, batch 2750, loss[loss=0.185, simple_loss=0.27, pruned_loss=0.04997, over 5115.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02904, over 1425226.29 frames.], batch size: 52, lr: 2.10e-04
+2022-05-16 03:10:16,995 INFO [train.py:812] (2/8) Epoch 37, batch 2800, loss[loss=0.1356, simple_loss=0.2261, pruned_loss=0.02253, over 7278.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2418, pruned_loss=0.02878, over 1429508.95 frames.], batch size: 18, lr: 2.10e-04
+2022-05-16 03:11:34,359 INFO [train.py:812] (2/8) Epoch 37, batch 2850, loss[loss=0.1567, simple_loss=0.2602, pruned_loss=0.02664, over 6360.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02875, over 1427133.80 frames.], batch size: 37, lr: 2.10e-04
+2022-05-16 03:12:32,631 INFO [train.py:812] (2/8) Epoch 37, batch 2900, loss[loss=0.1241, simple_loss=0.2111, pruned_loss=0.0185, over 6980.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2415, pruned_loss=0.02837, over 1427374.69 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:13:31,836 INFO [train.py:812] (2/8) Epoch 37, batch 2950, loss[loss=0.1481, simple_loss=0.2399, pruned_loss=0.02817, over 7429.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2416, pruned_loss=0.02857, over 1423386.94 frames.], batch size: 20, lr: 2.10e-04
+2022-05-16 03:14:30,566 INFO [train.py:812] (2/8) Epoch 37, batch 3000, loss[loss=0.1423, simple_loss=0.2368, pruned_loss=0.02394, over 7219.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2418, pruned_loss=0.02872, over 1419886.09 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 03:14:30,567 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-16 03:14:38,087 INFO [train.py:841] (2/8) Epoch 37, validation: loss=0.1539, simple_loss=0.2491, pruned_loss=0.02931, over 698248.00 frames.
+2022-05-16 03:15:37,723 INFO [train.py:812] (2/8) Epoch 37, batch 3050, loss[loss=0.142, simple_loss=0.2202, pruned_loss=0.03191, over 6783.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.02909, over 1418326.74 frames.], batch size: 15, lr: 2.10e-04
+2022-05-16 03:16:36,461 INFO [train.py:812] (2/8) Epoch 37, batch 3100, loss[loss=0.1361, simple_loss=0.2282, pruned_loss=0.02196, over 7063.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02908, over 1416971.15 frames.], batch size: 18, lr: 2.10e-04
+2022-05-16 03:17:34,873 INFO [train.py:812] (2/8) Epoch 37, batch 3150, loss[loss=0.1303, simple_loss=0.2052, pruned_loss=0.02767, over 7004.00 frames.], tot_loss[loss=0.15, simple_loss=0.2419, pruned_loss=0.02902, over 1416484.89 frames.], batch size: 16, lr: 2.10e-04
+2022-05-16 03:18:33,952 INFO [train.py:812] (2/8) Epoch 37, batch 3200, loss[loss=0.1678, simple_loss=0.2511, pruned_loss=0.04219, over 5046.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02913, over 1417686.64 frames.], batch size: 52, lr: 2.10e-04
+2022-05-16 03:19:33,504 INFO [train.py:812] (2/8) Epoch 37, batch 3250, loss[loss=0.1721, simple_loss=0.2574, pruned_loss=0.0434, over 7210.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02883, over 1417649.10 frames.], batch size: 22, lr: 2.10e-04
+2022-05-16 03:20:31,428 INFO [train.py:812] (2/8) Epoch 37, batch 3300, loss[loss=0.1838, simple_loss=0.2735, pruned_loss=0.04707, over 7411.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02895, over 1415340.07 frames.], batch size: 21, lr: 2.10e-04
+2022-05-16 03:21:29,308 INFO [train.py:812] (2/8) Epoch 37, batch 3350, loss[loss=0.1644, simple_loss=0.2607, pruned_loss=0.03407, over 7395.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02927, over 1410829.89 frames.], batch size: 23, lr: 2.09e-04
+2022-05-16 03:22:27,822 INFO [train.py:812] (2/8) Epoch 37, batch 3400, loss[loss=0.1246, simple_loss=0.2012, pruned_loss=0.02393, over 7150.00 frames.], tot_loss[loss=0.15, simple_loss=0.2421, pruned_loss=0.02893, over 1415826.31 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:23:27,194 INFO [train.py:812] (2/8) Epoch 37, batch 3450, loss[loss=0.1478, simple_loss=0.2252, pruned_loss=0.03522, over 7286.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2415, pruned_loss=0.02884, over 1419137.51 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:24:25,212 INFO [train.py:812] (2/8) Epoch 37, batch 3500, loss[loss=0.14, simple_loss=0.2281, pruned_loss=0.02595, over 7361.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02902, over 1416984.47 frames.], batch size: 19, lr: 2.09e-04
+2022-05-16 03:25:24,455 INFO [train.py:812] (2/8) Epoch 37, batch 3550, loss[loss=0.1539, simple_loss=0.238, pruned_loss=0.03492, over 7230.00 frames.], tot_loss[loss=0.149, simple_loss=0.2412, pruned_loss=0.02835, over 1414341.88 frames.], batch size: 16, lr: 2.09e-04
+2022-05-16 03:26:23,181 INFO [train.py:812] (2/8) Epoch 37, batch 3600, loss[loss=0.1285, simple_loss=0.2208, pruned_loss=0.01811, over 6992.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2404, pruned_loss=0.02813, over 1420720.26 frames.], batch size: 16, lr: 2.09e-04
+2022-05-16 03:27:22,101 INFO [train.py:812] (2/8) Epoch 37, batch 3650, loss[loss=0.1509, simple_loss=0.2484, pruned_loss=0.02672, over 7154.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2404, pruned_loss=0.02823, over 1423132.66 frames.], batch size: 19, lr: 2.09e-04
+2022-05-16 03:28:20,567 INFO [train.py:812] (2/8) Epoch 37, batch 3700, loss[loss=0.1533, simple_loss=0.248, pruned_loss=0.02928, over 7232.00 frames.], tot_loss[loss=0.1483, simple_loss=0.24, pruned_loss=0.02825, over 1426687.22 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:29:19,746 INFO [train.py:812] (2/8) Epoch 37, batch 3750, loss[loss=0.1594, simple_loss=0.2501, pruned_loss=0.03432, over 7289.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02894, over 1423691.82 frames.], batch size: 24, lr: 2.09e-04
+2022-05-16 03:30:17,094 INFO [train.py:812] (2/8) Epoch 37, batch 3800, loss[loss=0.1244, simple_loss=0.2068, pruned_loss=0.02101, over 7283.00 frames.], tot_loss[loss=0.149, simple_loss=0.2411, pruned_loss=0.02846, over 1425198.46 frames.], batch size: 17, lr: 2.09e-04
+2022-05-16 03:31:15,850 INFO [train.py:812] (2/8) Epoch 37, batch 3850, loss[loss=0.1794, simple_loss=0.274, pruned_loss=0.04238, over 5298.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02883, over 1424145.90 frames.], batch size: 53, lr: 2.09e-04
+2022-05-16 03:32:12,576 INFO [train.py:812] (2/8) Epoch 37, batch 3900, loss[loss=0.131, simple_loss=0.2204, pruned_loss=0.02078, over 7329.00 frames.], tot_loss[loss=0.149, simple_loss=0.2411, pruned_loss=0.02839, over 1425716.41 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:33:11,532 INFO [train.py:812] (2/8) Epoch 37, batch 3950, loss[loss=0.1448, simple_loss=0.2356, pruned_loss=0.027, over 7258.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2415, pruned_loss=0.02876, over 1426876.87 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:34:09,773 INFO [train.py:812] (2/8) Epoch 37, batch 4000, loss[loss=0.1423, simple_loss=0.2325, pruned_loss=0.02607, over 7160.00 frames.], tot_loss[loss=0.1489, simple_loss=0.241, pruned_loss=0.02839, over 1428731.40 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:35:09,272 INFO [train.py:812] (2/8) Epoch 37, batch 4050, loss[loss=0.1606, simple_loss=0.2555, pruned_loss=0.03288, over 7153.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2402, pruned_loss=0.02807, over 1427122.52 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:36:06,883 INFO [train.py:812] (2/8) Epoch 37, batch 4100, loss[loss=0.1407, simple_loss=0.234, pruned_loss=0.02369, over 7314.00 frames.], tot_loss[loss=0.1487, simple_loss=0.241, pruned_loss=0.02817, over 1424286.13 frames.], batch size: 25, lr: 2.09e-04
+2022-05-16 03:37:05,675 INFO [train.py:812] (2/8) Epoch 37, batch 4150, loss[loss=0.1508, simple_loss=0.2495, pruned_loss=0.02602, over 7198.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2405, pruned_loss=0.02791, over 1426328.83 frames.], batch size: 21, lr: 2.09e-04
+2022-05-16 03:38:02,988 INFO [train.py:812] (2/8) Epoch 37, batch 4200, loss[loss=0.1521, simple_loss=0.256, pruned_loss=0.02408, over 7342.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2405, pruned_loss=0.02763, over 1428408.44 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:39:02,509 INFO [train.py:812] (2/8) Epoch 37, batch 4250, loss[loss=0.1595, simple_loss=0.2459, pruned_loss=0.03656, over 7207.00 frames.], tot_loss[loss=0.148, simple_loss=0.2405, pruned_loss=0.02782, over 1430736.26 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:40:00,915 INFO [train.py:812] (2/8) Epoch 37, batch 4300, loss[loss=0.1454, simple_loss=0.2373, pruned_loss=0.02673, over 7327.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2413, pruned_loss=0.02853, over 1424825.00 frames.], batch size: 20, lr: 2.09e-04
+2022-05-16 03:41:00,688 INFO [train.py:812] (2/8) Epoch 37, batch 4350, loss[loss=0.1427, simple_loss=0.2435, pruned_loss=0.02095, over 7342.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2412, pruned_loss=0.02818, over 1429536.28 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:41:59,222 INFO [train.py:812] (2/8) Epoch 37, batch 4400, loss[loss=0.1737, simple_loss=0.2698, pruned_loss=0.03881, over 7334.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2423, pruned_loss=0.02849, over 1421989.27 frames.], batch size: 22, lr: 2.09e-04
+2022-05-16 03:42:59,057 INFO [train.py:812] (2/8) Epoch 37, batch 4450, loss[loss=0.1404, simple_loss=0.2272, pruned_loss=0.02677, over 7411.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2434, pruned_loss=0.02891, over 1420491.40 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:43:58,021 INFO [train.py:812] (2/8) Epoch 37, batch 4500, loss[loss=0.1456, simple_loss=0.2302, pruned_loss=0.03043, over 7279.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2422, pruned_loss=0.02831, over 1414805.53 frames.], batch size: 18, lr: 2.09e-04
+2022-05-16 03:44:56,288 INFO [train.py:812] (2/8) Epoch 37, batch 4550, loss[loss=0.1551, simple_loss=0.2548, pruned_loss=0.02768, over 6481.00 frames.], tot_loss[loss=0.1512, simple_loss=0.244, pruned_loss=0.02918, over 1391786.82 frames.], batch size: 38, lr: 2.09e-04
+2022-05-16 03:46:01,507 INFO [train.py:812] (2/8) Epoch 38, batch 0, loss[loss=0.1424, simple_loss=0.2306, pruned_loss=0.02704, over 7367.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2306, pruned_loss=0.02704, over 7367.00 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:47:10,797 INFO [train.py:812] (2/8) Epoch 38, batch 50, loss[loss=0.1331, simple_loss=0.2287, pruned_loss=0.01875, over 6476.00 frames.], tot_loss[loss=0.145, simple_loss=0.2375, pruned_loss=0.02626, over 323267.18 frames.], batch size: 38, lr: 2.06e-04
+2022-05-16 03:48:09,432 INFO [train.py:812] (2/8) Epoch 38, batch 100, loss[loss=0.1441, simple_loss=0.2311, pruned_loss=0.02852, over 7269.00 frames.], tot_loss[loss=0.1497, simple_loss=0.243, pruned_loss=0.02823, over 561274.37 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:49:08,234 INFO [train.py:812] (2/8) Epoch 38, batch 150, loss[loss=0.1652, simple_loss=0.2666, pruned_loss=0.0319, over 7381.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2443, pruned_loss=0.02957, over 749800.07 frames.], batch size: 23, lr: 2.06e-04
+2022-05-16 03:50:07,476 INFO [train.py:812] (2/8) Epoch 38, batch 200, loss[loss=0.144, simple_loss=0.2396, pruned_loss=0.02418, over 7415.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.0291, over 897762.97 frames.], batch size: 21, lr: 2.06e-04
+2022-05-16 03:51:06,647 INFO [train.py:812] (2/8) Epoch 38, batch 250, loss[loss=0.14, simple_loss=0.228, pruned_loss=0.02597, over 7350.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2418, pruned_loss=0.0288, over 1015783.10 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:52:05,160 INFO [train.py:812] (2/8) Epoch 38, batch 300, loss[loss=0.1532, simple_loss=0.2574, pruned_loss=0.02449, over 7230.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02912, over 1105609.01 frames.], batch size: 20, lr: 2.06e-04
+2022-05-16 03:53:04,631 INFO [train.py:812] (2/8) Epoch 38, batch 350, loss[loss=0.1352, simple_loss=0.2274, pruned_loss=0.02146, over 7261.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2422, pruned_loss=0.02866, over 1173079.96 frames.], batch size: 19, lr: 2.06e-04
+2022-05-16 03:54:02,509 INFO [train.py:812] (2/8) Epoch 38, batch 400, loss[loss=0.1144, simple_loss=0.1991, pruned_loss=0.01482, over 7298.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2416, pruned_loss=0.02855, over 1233270.02 frames.], batch size: 17, lr: 2.06e-04
+2022-05-16 03:55:02,009 INFO [train.py:812] (2/8) Epoch 38, batch 450, loss[loss=0.1469, simple_loss=0.2467, pruned_loss=0.02357, over 7110.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2418, pruned_loss=0.02856, over 1276342.58 frames.], batch size: 21, lr: 2.06e-04
+2022-05-16 03:56:00,724 INFO [train.py:812] (2/8) Epoch 38, batch 500, loss[loss=0.1227, simple_loss=0.2151, pruned_loss=0.01514, over 7278.00 frames.], tot_loss[loss=0.1488, simple_loss=0.241, pruned_loss=0.02826, over 1312184.45 frames.], batch size: 18, lr: 2.06e-04
+2022-05-16 03:56:58,647 INFO [train.py:812] (2/8) Epoch 38, batch 550, loss[loss=0.1366, simple_loss=0.2363, pruned_loss=0.01851, over 7326.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2405, pruned_loss=0.0282, over 1336109.53 frames.], batch size: 20, lr: 2.06e-04
+2022-05-16 03:57:56,237 INFO [train.py:812] (2/8) Epoch 38, batch 600, loss[loss=0.1735, simple_loss=0.2656, pruned_loss=0.04072, over 7372.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2418, pruned_loss=0.0284, over 1357843.81 frames.], batch size: 23, lr: 2.06e-04
+2022-05-16 03:58:54,201 INFO [train.py:812] (2/8) Epoch 38, batch 650, loss[loss=0.1542, simple_loss=0.2498, pruned_loss=0.02928, over 7318.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02887, over 1373973.65 frames.], batch size: 22, lr: 2.06e-04
+2022-05-16 03:59:53,353 INFO [train.py:812] (2/8) Epoch 38, batch 700, loss[loss=0.1525, simple_loss=0.2419, pruned_loss=0.03159, over 7159.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02866, over 1386267.99 frames.], batch size: 18, lr: 2.06e-04
+2022-05-16 04:00:52,139 INFO [train.py:812] (2/8) Epoch 38, batch 750, loss[loss=0.1566, simple_loss=0.2508, pruned_loss=0.03122, over 7366.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2423, pruned_loss=0.02854, over 1400602.40 frames.], batch size: 23, lr: 2.05e-04
+2022-05-16 04:01:50,367 INFO [train.py:812] (2/8) Epoch 38, batch 800, loss[loss=0.1382, simple_loss=0.2271, pruned_loss=0.02471, over 7412.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2427, pruned_loss=0.0284, over 1408567.81 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:02:49,123 INFO [train.py:812] (2/8) Epoch 38, batch 850, loss[loss=0.1442, simple_loss=0.2385, pruned_loss=0.02496, over 7356.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2428, pruned_loss=0.02822, over 1411593.03 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:03:47,715 INFO [train.py:812] (2/8) Epoch 38, batch 900, loss[loss=0.1449, simple_loss=0.2447, pruned_loss=0.02254, over 7313.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2422, pruned_loss=0.02799, over 1413878.92 frames.], batch size: 24, lr: 2.05e-04
+2022-05-16 04:04:46,167 INFO [train.py:812] (2/8) Epoch 38, batch 950, loss[loss=0.134, simple_loss=0.233, pruned_loss=0.01747, over 7254.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2431, pruned_loss=0.02853, over 1419440.05 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:05:44,671 INFO [train.py:812] (2/8) Epoch 38, batch 1000, loss[loss=0.1496, simple_loss=0.2439, pruned_loss=0.02765, over 7200.00 frames.], tot_loss[loss=0.15, simple_loss=0.2431, pruned_loss=0.02843, over 1422048.45 frames.], batch size: 22, lr: 2.05e-04
+2022-05-16 04:06:43,932 INFO [train.py:812] (2/8) Epoch 38, batch 1050, loss[loss=0.1754, simple_loss=0.2604, pruned_loss=0.04519, over 7329.00 frames.], tot_loss[loss=0.15, simple_loss=0.2431, pruned_loss=0.02842, over 1423406.70 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:07:41,760 INFO [train.py:812] (2/8) Epoch 38, batch 1100, loss[loss=0.1244, simple_loss=0.2033, pruned_loss=0.02273, over 6851.00 frames.], tot_loss[loss=0.15, simple_loss=0.2431, pruned_loss=0.02848, over 1426628.98 frames.], batch size: 15, lr: 2.05e-04
+2022-05-16 04:08:41,050 INFO [train.py:812] (2/8) Epoch 38, batch 1150, loss[loss=0.1267, simple_loss=0.211, pruned_loss=0.02115, over 7266.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.02851, over 1422754.16 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:09:40,640 INFO [train.py:812] (2/8) Epoch 38, batch 1200, loss[loss=0.1454, simple_loss=0.2364, pruned_loss=0.0272, over 7221.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2425, pruned_loss=0.02849, over 1424840.43 frames.], batch size: 26, lr: 2.05e-04
+2022-05-16 04:10:39,736 INFO [train.py:812] (2/8) Epoch 38, batch 1250, loss[loss=0.1521, simple_loss=0.2421, pruned_loss=0.031, over 6547.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2431, pruned_loss=0.02871, over 1428194.26 frames.], batch size: 37, lr: 2.05e-04
+2022-05-16 04:11:38,491 INFO [train.py:812] (2/8) Epoch 38, batch 1300, loss[loss=0.126, simple_loss=0.2147, pruned_loss=0.0186, over 7270.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2439, pruned_loss=0.02912, over 1427920.30 frames.], batch size: 17, lr: 2.05e-04
+2022-05-16 04:12:36,177 INFO [train.py:812] (2/8) Epoch 38, batch 1350, loss[loss=0.1504, simple_loss=0.2489, pruned_loss=0.02593, over 7111.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02871, over 1422213.06 frames.], batch size: 21, lr: 2.05e-04
+2022-05-16 04:13:33,879 INFO [train.py:812] (2/8) Epoch 38, batch 1400, loss[loss=0.1505, simple_loss=0.2509, pruned_loss=0.02501, over 7299.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.02829, over 1421564.13 frames.], batch size: 24, lr: 2.05e-04
+2022-05-16 04:14:32,882 INFO [train.py:812] (2/8) Epoch 38, batch 1450, loss[loss=0.1943, simple_loss=0.287, pruned_loss=0.05077, over 7206.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02902, over 1425732.83 frames.], batch size: 22, lr: 2.05e-04
+2022-05-16 04:15:31,456 INFO [train.py:812] (2/8) Epoch 38, batch 1500, loss[loss=0.1503, simple_loss=0.2394, pruned_loss=0.03054, over 7285.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.0289, over 1426368.45 frames.], batch size: 25, lr: 2.05e-04
+2022-05-16 04:16:30,123 INFO [train.py:812] (2/8) Epoch 38, batch 1550, loss[loss=0.1417, simple_loss=0.2384, pruned_loss=0.02255, over 7241.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2424, pruned_loss=0.02885, over 1423783.26 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:17:27,388 INFO [train.py:812] (2/8) Epoch 38, batch 1600, loss[loss=0.1302, simple_loss=0.2226, pruned_loss=0.01891, over 7260.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2427, pruned_loss=0.02886, over 1426311.83 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:18:25,542 INFO [train.py:812] (2/8) Epoch 38, batch 1650, loss[loss=0.1647, simple_loss=0.2616, pruned_loss=0.03389, over 7135.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2427, pruned_loss=0.02873, over 1425726.24 frames.], batch size: 28, lr: 2.05e-04
+2022-05-16 04:19:24,096 INFO [train.py:812] (2/8) Epoch 38, batch 1700, loss[loss=0.1547, simple_loss=0.2427, pruned_loss=0.03334, over 7166.00 frames.], tot_loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.02862, over 1425618.05 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:20:24,536 INFO [train.py:812] (2/8) Epoch 38, batch 1750, loss[loss=0.1436, simple_loss=0.2336, pruned_loss=0.02686, over 5126.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02893, over 1423197.74 frames.], batch size: 52, lr: 2.05e-04
+2022-05-16 04:21:23,197 INFO [train.py:812] (2/8) Epoch 38, batch 1800, loss[loss=0.1655, simple_loss=0.2743, pruned_loss=0.02832, over 7334.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.0289, over 1419657.18 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:22:21,144 INFO [train.py:812] (2/8) Epoch 38, batch 1850, loss[loss=0.1466, simple_loss=0.2429, pruned_loss=0.02519, over 7274.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2415, pruned_loss=0.02866, over 1421572.27 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:23:20,142 INFO [train.py:812] (2/8) Epoch 38, batch 1900, loss[loss=0.141, simple_loss=0.2261, pruned_loss=0.02791, over 6792.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2422, pruned_loss=0.02855, over 1424389.12 frames.], batch size: 15, lr: 2.05e-04
+2022-05-16 04:24:18,767 INFO [train.py:812] (2/8) Epoch 38, batch 1950, loss[loss=0.1441, simple_loss=0.2398, pruned_loss=0.02415, over 7243.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2429, pruned_loss=0.02876, over 1426870.02 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:25:17,614 INFO [train.py:812] (2/8) Epoch 38, batch 2000, loss[loss=0.1149, simple_loss=0.1983, pruned_loss=0.01577, over 7404.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2423, pruned_loss=0.02857, over 1425587.68 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:26:16,379 INFO [train.py:812] (2/8) Epoch 38, batch 2050, loss[loss=0.1296, simple_loss=0.2217, pruned_loss=0.01878, over 7262.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2421, pruned_loss=0.02849, over 1423377.64 frames.], batch size: 19, lr: 2.05e-04
+2022-05-16 04:27:14,047 INFO [train.py:812] (2/8) Epoch 38, batch 2100, loss[loss=0.1686, simple_loss=0.2618, pruned_loss=0.03766, over 7156.00 frames.], tot_loss[loss=0.1505, simple_loss=0.243, pruned_loss=0.02895, over 1417432.45 frames.], batch size: 26, lr: 2.05e-04
+2022-05-16 04:28:12,416 INFO [train.py:812] (2/8) Epoch 38, batch 2150, loss[loss=0.1446, simple_loss=0.2356, pruned_loss=0.02685, over 7061.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2427, pruned_loss=0.02876, over 1417629.15 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:29:11,059 INFO [train.py:812] (2/8) Epoch 38, batch 2200, loss[loss=0.1213, simple_loss=0.2144, pruned_loss=0.0141, over 7065.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2436, pruned_loss=0.02885, over 1419337.65 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:30:15,081 INFO [train.py:812] (2/8) Epoch 38, batch 2250, loss[loss=0.1295, simple_loss=0.2241, pruned_loss=0.01743, over 6229.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2432, pruned_loss=0.02844, over 1417798.16 frames.], batch size: 37, lr: 2.05e-04
+2022-05-16 04:31:14,133 INFO [train.py:812] (2/8) Epoch 38, batch 2300, loss[loss=0.1384, simple_loss=0.2272, pruned_loss=0.02477, over 7068.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2427, pruned_loss=0.02818, over 1421578.62 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:32:13,290 INFO [train.py:812] (2/8) Epoch 38, batch 2350, loss[loss=0.1466, simple_loss=0.2473, pruned_loss=0.02298, over 7342.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2425, pruned_loss=0.0281, over 1419396.44 frames.], batch size: 20, lr: 2.05e-04
+2022-05-16 04:33:12,174 INFO [train.py:812] (2/8) Epoch 38, batch 2400, loss[loss=0.1338, simple_loss=0.2216, pruned_loss=0.02299, over 7424.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2416, pruned_loss=0.028, over 1424857.00 frames.], batch size: 18, lr: 2.05e-04
+2022-05-16 04:34:10,776 INFO [train.py:812] (2/8) Epoch 38, batch 2450, loss[loss=0.1495, simple_loss=0.2447, pruned_loss=0.02719, over 7326.00 frames.], tot_loss[loss=0.1489, simple_loss=0.242, pruned_loss=0.02792, over 1427217.63 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:35:08,788 INFO [train.py:812] (2/8) Epoch 38, batch 2500, loss[loss=0.1436, simple_loss=0.2317, pruned_loss=0.02776, over 7169.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2414, pruned_loss=0.02774, over 1426555.90 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:36:06,744 INFO [train.py:812] (2/8) Epoch 38, batch 2550, loss[loss=0.1251, simple_loss=0.212, pruned_loss=0.01911, over 7152.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2411, pruned_loss=0.02768, over 1424198.63 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:37:05,275 INFO [train.py:812] (2/8) Epoch 38, batch 2600, loss[loss=0.1632, simple_loss=0.2521, pruned_loss=0.03713, over 7429.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2406, pruned_loss=0.02803, over 1423289.27 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:38:03,410 INFO [train.py:812] (2/8) Epoch 38, batch 2650, loss[loss=0.1805, simple_loss=0.2822, pruned_loss=0.03939, over 7215.00 frames.], tot_loss[loss=0.1485, simple_loss=0.241, pruned_loss=0.02802, over 1425024.71 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:39:01,015 INFO [train.py:812] (2/8) Epoch 38, batch 2700, loss[loss=0.1579, simple_loss=0.2479, pruned_loss=0.0339, over 7230.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2401, pruned_loss=0.02782, over 1424276.30 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:39:59,843 INFO [train.py:812] (2/8) Epoch 38, batch 2750, loss[loss=0.1515, simple_loss=0.2525, pruned_loss=0.02523, over 7358.00 frames.], tot_loss[loss=0.1489, simple_loss=0.241, pruned_loss=0.02833, over 1425377.17 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 04:40:57,547 INFO [train.py:812] (2/8) Epoch 38, batch 2800, loss[loss=0.1725, simple_loss=0.2657, pruned_loss=0.03969, over 7286.00 frames.], tot_loss[loss=0.1485, simple_loss=0.241, pruned_loss=0.02804, over 1423682.13 frames.], batch size: 24, lr: 2.04e-04
+2022-05-16 04:41:55,561 INFO [train.py:812] (2/8) Epoch 38, batch 2850, loss[loss=0.1573, simple_loss=0.2532, pruned_loss=0.0307, over 7409.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2413, pruned_loss=0.02815, over 1424319.81 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 04:42:54,112 INFO [train.py:812] (2/8) Epoch 38, batch 2900, loss[loss=0.1455, simple_loss=0.2268, pruned_loss=0.0321, over 7146.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2411, pruned_loss=0.02826, over 1424553.15 frames.], batch size: 17, lr: 2.04e-04
+2022-05-16 04:43:53,031 INFO [train.py:812] (2/8) Epoch 38, batch 2950, loss[loss=0.1485, simple_loss=0.2415, pruned_loss=0.02772, over 7431.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2417, pruned_loss=0.02835, over 1429133.06 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:44:52,074 INFO [train.py:812] (2/8) Epoch 38, batch 3000, loss[loss=0.1677, simple_loss=0.2541, pruned_loss=0.04071, over 7204.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2415, pruned_loss=0.02819, over 1428994.00 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:44:52,076 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-16 04:44:59,417 INFO [train.py:841] (2/8) Epoch 38, validation: loss=0.1532, simple_loss=0.2484, pruned_loss=0.02898, over 698248.00 frames.
+2022-05-16 04:45:58,529 INFO [train.py:812] (2/8) Epoch 38, batch 3050, loss[loss=0.1447, simple_loss=0.2295, pruned_loss=0.02993, over 7172.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.0285, over 1429126.49 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:46:56,194 INFO [train.py:812] (2/8) Epoch 38, batch 3100, loss[loss=0.1801, simple_loss=0.2664, pruned_loss=0.04694, over 7217.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02907, over 1422380.58 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 04:47:54,591 INFO [train.py:812] (2/8) Epoch 38, batch 3150, loss[loss=0.1478, simple_loss=0.246, pruned_loss=0.02483, over 7393.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2418, pruned_loss=0.02881, over 1420115.27 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 04:48:52,444 INFO [train.py:812] (2/8) Epoch 38, batch 3200, loss[loss=0.153, simple_loss=0.2503, pruned_loss=0.02787, over 7105.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2417, pruned_loss=0.02894, over 1424734.52 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 04:49:51,325 INFO [train.py:812] (2/8) Epoch 38, batch 3250, loss[loss=0.1318, simple_loss=0.2206, pruned_loss=0.02146, over 7281.00 frames.], tot_loss[loss=0.1493, simple_loss=0.241, pruned_loss=0.02878, over 1426123.51 frames.], batch size: 18, lr: 2.04e-04
+2022-05-16 04:50:49,189 INFO [train.py:812] (2/8) Epoch 38, batch 3300, loss[loss=0.1329, simple_loss=0.2318, pruned_loss=0.01697, over 7239.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.02888, over 1425319.91 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:51:47,400 INFO [train.py:812] (2/8) Epoch 38, batch 3350, loss[loss=0.1667, simple_loss=0.2543, pruned_loss=0.03959, over 7195.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02921, over 1425965.36 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 04:52:45,657 INFO [train.py:812] (2/8) Epoch 38, batch 3400, loss[loss=0.177, simple_loss=0.2673, pruned_loss=0.04341, over 6847.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02885, over 1430095.27 frames.], batch size: 31, lr: 2.04e-04
+2022-05-16 04:53:45,258 INFO [train.py:812] (2/8) Epoch 38, batch 3450, loss[loss=0.1409, simple_loss=0.2369, pruned_loss=0.02239, over 7429.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2428, pruned_loss=0.02888, over 1432243.19 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:54:43,623 INFO [train.py:812] (2/8) Epoch 38, batch 3500, loss[loss=0.1402, simple_loss=0.2342, pruned_loss=0.02307, over 7238.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2421, pruned_loss=0.02853, over 1430533.16 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:55:41,852 INFO [train.py:812] (2/8) Epoch 38, batch 3550, loss[loss=0.1526, simple_loss=0.2512, pruned_loss=0.02702, over 7146.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2433, pruned_loss=0.02872, over 1430637.60 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 04:56:49,626 INFO [train.py:812] (2/8) Epoch 38, batch 3600, loss[loss=0.1761, simple_loss=0.2742, pruned_loss=0.03896, over 6711.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2437, pruned_loss=0.0288, over 1428565.13 frames.], batch size: 31, lr: 2.04e-04
+2022-05-16 04:57:48,346 INFO [train.py:812] (2/8) Epoch 38, batch 3650, loss[loss=0.1748, simple_loss=0.2653, pruned_loss=0.04216, over 7110.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2432, pruned_loss=0.02881, over 1430989.78 frames.], batch size: 28, lr: 2.04e-04
+2022-05-16 04:58:46,217 INFO [train.py:812] (2/8) Epoch 38, batch 3700, loss[loss=0.1457, simple_loss=0.2408, pruned_loss=0.02527, over 7301.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02881, over 1423332.87 frames.], batch size: 24, lr: 2.04e-04
+2022-05-16 05:00:03,388 INFO [train.py:812] (2/8) Epoch 38, batch 3750, loss[loss=0.1546, simple_loss=0.249, pruned_loss=0.03007, over 7165.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2428, pruned_loss=0.02891, over 1418523.70 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 05:01:01,778 INFO [train.py:812] (2/8) Epoch 38, batch 3800, loss[loss=0.1908, simple_loss=0.2907, pruned_loss=0.04549, over 7370.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2421, pruned_loss=0.02859, over 1419006.06 frames.], batch size: 23, lr: 2.04e-04
+2022-05-16 05:02:01,298 INFO [train.py:812] (2/8) Epoch 38, batch 3850, loss[loss=0.1554, simple_loss=0.2523, pruned_loss=0.02919, over 7106.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02888, over 1421097.09 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 05:03:01,096 INFO [train.py:812] (2/8) Epoch 38, batch 3900, loss[loss=0.154, simple_loss=0.2468, pruned_loss=0.0306, over 7333.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02913, over 1423831.58 frames.], batch size: 20, lr: 2.04e-04
+2022-05-16 05:03:59,292 INFO [train.py:812] (2/8) Epoch 38, batch 3950, loss[loss=0.1626, simple_loss=0.2499, pruned_loss=0.03766, over 7202.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2417, pruned_loss=0.02894, over 1418500.82 frames.], batch size: 22, lr: 2.04e-04
+2022-05-16 05:04:56,834 INFO [train.py:812] (2/8) Epoch 38, batch 4000, loss[loss=0.1474, simple_loss=0.23, pruned_loss=0.0324, over 7168.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2415, pruned_loss=0.02904, over 1419331.44 frames.], batch size: 19, lr: 2.04e-04
+2022-05-16 05:06:06,178 INFO [train.py:812] (2/8) Epoch 38, batch 4050, loss[loss=0.1475, simple_loss=0.2267, pruned_loss=0.0342, over 7287.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2414, pruned_loss=0.02867, over 1411884.60 frames.], batch size: 17, lr: 2.04e-04
+2022-05-16 05:07:14,614 INFO [train.py:812] (2/8) Epoch 38, batch 4100, loss[loss=0.1518, simple_loss=0.254, pruned_loss=0.02483, over 7195.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2419, pruned_loss=0.02838, over 1413578.66 frames.], batch size: 21, lr: 2.04e-04
+2022-05-16 05:08:13,921 INFO [train.py:812] (2/8) Epoch 38, batch 4150, loss[loss=0.1493, simple_loss=0.2404, pruned_loss=0.02914, over 7261.00 frames.], tot_loss[loss=0.1489, simple_loss=0.241, pruned_loss=0.02837, over 1413253.99 frames.], batch size: 19, lr: 2.03e-04
+2022-05-16 05:09:21,272 INFO [train.py:812] (2/8) Epoch 38, batch 4200, loss[loss=0.1804, simple_loss=0.2804, pruned_loss=0.04022, over 7297.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2408, pruned_loss=0.02791, over 1414544.22 frames.], batch size: 24, lr: 2.03e-04
+2022-05-16 05:10:29,483 INFO [train.py:812] (2/8) Epoch 38, batch 4250, loss[loss=0.1611, simple_loss=0.257, pruned_loss=0.03264, over 7240.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2417, pruned_loss=0.02803, over 1414228.28 frames.], batch size: 20, lr: 2.03e-04
+2022-05-16 05:11:27,925 INFO [train.py:812] (2/8) Epoch 38, batch 4300, loss[loss=0.1805, simple_loss=0.263, pruned_loss=0.04905, over 5092.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2404, pruned_loss=0.02788, over 1411061.05 frames.], batch size: 53, lr: 2.03e-04
+2022-05-16 05:12:26,583 INFO [train.py:812] (2/8) Epoch 38, batch 4350, loss[loss=0.1312, simple_loss=0.2152, pruned_loss=0.02358, over 7011.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2397, pruned_loss=0.02782, over 1412947.85 frames.], batch size: 16, lr: 2.03e-04
+2022-05-16 05:13:26,094 INFO [train.py:812] (2/8) Epoch 38, batch 4400, loss[loss=0.1344, simple_loss=0.226, pruned_loss=0.0214, over 7208.00 frames.], tot_loss[loss=0.147, simple_loss=0.2391, pruned_loss=0.02748, over 1414060.32 frames.], batch size: 16, lr: 2.03e-04
+2022-05-16 05:14:25,866 INFO [train.py:812] (2/8) Epoch 38, batch 4450, loss[loss=0.1392, simple_loss=0.2273, pruned_loss=0.02553, over 6760.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2384, pruned_loss=0.02736, over 1406035.75 frames.], batch size: 15, lr: 2.03e-04
+2022-05-16 05:15:24,197 INFO [train.py:812] (2/8) Epoch 38, batch 4500, loss[loss=0.1502, simple_loss=0.2386, pruned_loss=0.03095, over 6465.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2386, pruned_loss=0.0279, over 1382497.22 frames.], batch size: 38, lr: 2.03e-04
+2022-05-16 05:16:23,030 INFO [train.py:812] (2/8) Epoch 38, batch 4550, loss[loss=0.1758, simple_loss=0.2556, pruned_loss=0.04796, over 5356.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2382, pruned_loss=0.02818, over 1355608.96 frames.], batch size: 52, lr: 2.03e-04
+2022-05-16 05:17:28,540 INFO [train.py:812] (2/8) Epoch 39, batch 0, loss[loss=0.1471, simple_loss=0.2461, pruned_loss=0.02399, over 7262.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2461, pruned_loss=0.02399, over 7262.00 frames.], batch size: 19, lr: 2.01e-04
+2022-05-16 05:18:26,906 INFO [train.py:812] (2/8) Epoch 39, batch 50, loss[loss=0.1383, simple_loss=0.237, pruned_loss=0.01984, over 7151.00 frames.], tot_loss[loss=0.1499, simple_loss=0.244, pruned_loss=0.02787, over 320027.53 frames.], batch size: 20, lr: 2.01e-04
+2022-05-16 05:19:25,796 INFO [train.py:812] (2/8) Epoch 39, batch 100, loss[loss=0.1511, simple_loss=0.2537, pruned_loss=0.02426, over 6732.00 frames.], tot_loss[loss=0.1498, simple_loss=0.243, pruned_loss=0.0283, over 565135.41 frames.], batch size: 31, lr: 2.01e-04
+2022-05-16 05:20:24,084 INFO [train.py:812] (2/8) Epoch 39, batch 150, loss[loss=0.1533, simple_loss=0.2456, pruned_loss=0.03055, over 7155.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2416, pruned_loss=0.02872, over 754220.07 frames.], batch size: 18, lr: 2.01e-04
+2022-05-16 05:21:22,510 INFO [train.py:812] (2/8) Epoch 39, batch 200, loss[loss=0.1412, simple_loss=0.2213, pruned_loss=0.0306, over 7428.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02945, over 900748.08 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:22:20,494 INFO [train.py:812] (2/8) Epoch 39, batch 250, loss[loss=0.1476, simple_loss=0.245, pruned_loss=0.02513, over 6164.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2436, pruned_loss=0.02931, over 1016989.53 frames.], batch size: 37, lr: 2.00e-04
+2022-05-16 05:23:19,077 INFO [train.py:812] (2/8) Epoch 39, batch 300, loss[loss=0.1362, simple_loss=0.2198, pruned_loss=0.02627, over 7443.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02935, over 1112840.70 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:24:17,716 INFO [train.py:812] (2/8) Epoch 39, batch 350, loss[loss=0.171, simple_loss=0.2673, pruned_loss=0.0373, over 7294.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02891, over 1179076.60 frames.], batch size: 24, lr: 2.00e-04
+2022-05-16 05:25:17,172 INFO [train.py:812] (2/8) Epoch 39, batch 400, loss[loss=0.1552, simple_loss=0.2428, pruned_loss=0.03379, over 7216.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2413, pruned_loss=0.02843, over 1229250.36 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:26:16,271 INFO [train.py:812] (2/8) Epoch 39, batch 450, loss[loss=0.1613, simple_loss=0.2406, pruned_loss=0.041, over 7199.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2412, pruned_loss=0.02835, over 1274197.76 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:27:15,112 INFO [train.py:812] (2/8) Epoch 39, batch 500, loss[loss=0.1497, simple_loss=0.2539, pruned_loss=0.02282, over 7148.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02824, over 1302077.19 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:28:14,647 INFO [train.py:812] (2/8) Epoch 39, batch 550, loss[loss=0.1508, simple_loss=0.2496, pruned_loss=0.02601, over 7439.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2404, pruned_loss=0.02805, over 1328093.75 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:29:14,822 INFO [train.py:812] (2/8) Epoch 39, batch 600, loss[loss=0.1377, simple_loss=0.2237, pruned_loss=0.02581, over 7167.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2407, pruned_loss=0.02816, over 1346218.64 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:30:14,575 INFO [train.py:812] (2/8) Epoch 39, batch 650, loss[loss=0.1301, simple_loss=0.2099, pruned_loss=0.02514, over 7280.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2409, pruned_loss=0.02814, over 1365734.53 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:31:13,689 INFO [train.py:812] (2/8) Epoch 39, batch 700, loss[loss=0.1392, simple_loss=0.2317, pruned_loss=0.02339, over 6797.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2403, pruned_loss=0.02822, over 1377627.78 frames.], batch size: 15, lr: 2.00e-04
+2022-05-16 05:32:12,655 INFO [train.py:812] (2/8) Epoch 39, batch 750, loss[loss=0.1629, simple_loss=0.27, pruned_loss=0.02793, over 6273.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2392, pruned_loss=0.02757, over 1385927.04 frames.], batch size: 37, lr: 2.00e-04
+2022-05-16 05:33:12,319 INFO [train.py:812] (2/8) Epoch 39, batch 800, loss[loss=0.1337, simple_loss=0.2308, pruned_loss=0.01834, over 7232.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2394, pruned_loss=0.0276, over 1398884.19 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:34:10,576 INFO [train.py:812] (2/8) Epoch 39, batch 850, loss[loss=0.1825, simple_loss=0.2734, pruned_loss=0.04578, over 7015.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2394, pruned_loss=0.0275, over 1404868.79 frames.], batch size: 28, lr: 2.00e-04
+2022-05-16 05:35:08,794 INFO [train.py:812] (2/8) Epoch 39, batch 900, loss[loss=0.1764, simple_loss=0.2777, pruned_loss=0.03755, over 7427.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2399, pruned_loss=0.02775, over 1402914.62 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:36:07,976 INFO [train.py:812] (2/8) Epoch 39, batch 950, loss[loss=0.1268, simple_loss=0.2157, pruned_loss=0.01894, over 7134.00 frames.], tot_loss[loss=0.1487, simple_loss=0.241, pruned_loss=0.02819, over 1405113.12 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:37:07,598 INFO [train.py:812] (2/8) Epoch 39, batch 1000, loss[loss=0.1449, simple_loss=0.2376, pruned_loss=0.02609, over 7364.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2415, pruned_loss=0.02855, over 1408480.28 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:38:06,526 INFO [train.py:812] (2/8) Epoch 39, batch 1050, loss[loss=0.1506, simple_loss=0.2489, pruned_loss=0.02611, over 6718.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2413, pruned_loss=0.02845, over 1411093.52 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:39:05,110 INFO [train.py:812] (2/8) Epoch 39, batch 1100, loss[loss=0.1469, simple_loss=0.2477, pruned_loss=0.02298, over 7381.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2404, pruned_loss=0.02848, over 1414733.26 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:40:03,845 INFO [train.py:812] (2/8) Epoch 39, batch 1150, loss[loss=0.1412, simple_loss=0.2303, pruned_loss=0.02602, over 7255.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2395, pruned_loss=0.0281, over 1418795.83 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:41:02,323 INFO [train.py:812] (2/8) Epoch 39, batch 1200, loss[loss=0.1729, simple_loss=0.2554, pruned_loss=0.04514, over 6860.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2399, pruned_loss=0.02867, over 1420294.48 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:42:00,507 INFO [train.py:812] (2/8) Epoch 39, batch 1250, loss[loss=0.1307, simple_loss=0.2267, pruned_loss=0.01731, over 7431.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2401, pruned_loss=0.02843, over 1420304.85 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:42:59,382 INFO [train.py:812] (2/8) Epoch 39, batch 1300, loss[loss=0.1265, simple_loss=0.209, pruned_loss=0.02196, over 7274.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2396, pruned_loss=0.02808, over 1423676.31 frames.], batch size: 17, lr: 2.00e-04
+2022-05-16 05:43:56,663 INFO [train.py:812] (2/8) Epoch 39, batch 1350, loss[loss=0.1777, simple_loss=0.2676, pruned_loss=0.04396, over 7325.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2396, pruned_loss=0.02788, over 1424203.63 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:45:05,758 INFO [train.py:812] (2/8) Epoch 39, batch 1400, loss[loss=0.1377, simple_loss=0.2333, pruned_loss=0.02108, over 7157.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2398, pruned_loss=0.02801, over 1423669.04 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:46:03,927 INFO [train.py:812] (2/8) Epoch 39, batch 1450, loss[loss=0.1895, simple_loss=0.2746, pruned_loss=0.05224, over 7326.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2411, pruned_loss=0.02825, over 1423920.38 frames.], batch size: 25, lr: 2.00e-04
+2022-05-16 05:47:01,544 INFO [train.py:812] (2/8) Epoch 39, batch 1500, loss[loss=0.1774, simple_loss=0.2712, pruned_loss=0.04178, over 7117.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2408, pruned_loss=0.02834, over 1422511.09 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:48:00,116 INFO [train.py:812] (2/8) Epoch 39, batch 1550, loss[loss=0.1479, simple_loss=0.244, pruned_loss=0.02589, over 7217.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2402, pruned_loss=0.02839, over 1422432.19 frames.], batch size: 22, lr: 2.00e-04
+2022-05-16 05:48:59,840 INFO [train.py:812] (2/8) Epoch 39, batch 1600, loss[loss=0.1771, simple_loss=0.2688, pruned_loss=0.04266, over 6774.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2407, pruned_loss=0.02876, over 1425068.17 frames.], batch size: 31, lr: 2.00e-04
+2022-05-16 05:49:57,798 INFO [train.py:812] (2/8) Epoch 39, batch 1650, loss[loss=0.161, simple_loss=0.2577, pruned_loss=0.03217, over 7221.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2413, pruned_loss=0.02881, over 1424542.31 frames.], batch size: 21, lr: 2.00e-04
+2022-05-16 05:51:01,153 INFO [train.py:812] (2/8) Epoch 39, batch 1700, loss[loss=0.1497, simple_loss=0.2438, pruned_loss=0.02777, over 7086.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2418, pruned_loss=0.02872, over 1426360.56 frames.], batch size: 28, lr: 2.00e-04
+2022-05-16 05:51:59,349 INFO [train.py:812] (2/8) Epoch 39, batch 1750, loss[loss=0.1324, simple_loss=0.2239, pruned_loss=0.02048, over 7432.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2421, pruned_loss=0.02869, over 1426266.99 frames.], batch size: 20, lr: 2.00e-04
+2022-05-16 05:52:58,582 INFO [train.py:812] (2/8) Epoch 39, batch 1800, loss[loss=0.1668, simple_loss=0.253, pruned_loss=0.04031, over 7212.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2418, pruned_loss=0.02843, over 1424417.21 frames.], batch size: 23, lr: 2.00e-04
+2022-05-16 05:53:57,569 INFO [train.py:812] (2/8) Epoch 39, batch 1850, loss[loss=0.1667, simple_loss=0.2501, pruned_loss=0.04168, over 7167.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2413, pruned_loss=0.02849, over 1422060.58 frames.], batch size: 19, lr: 2.00e-04
+2022-05-16 05:54:55,916 INFO [train.py:812] (2/8) Epoch 39, batch 1900, loss[loss=0.1463, simple_loss=0.2413, pruned_loss=0.02562, over 7285.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2413, pruned_loss=0.02852, over 1424474.35 frames.], batch size: 18, lr: 2.00e-04
+2022-05-16 05:55:54,013 INFO [train.py:812] (2/8) Epoch 39, batch 1950, loss[loss=0.1357, simple_loss=0.2401, pruned_loss=0.01562, over 7316.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2412, pruned_loss=0.02849, over 1424309.00 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 05:56:52,305 INFO [train.py:812] (2/8) Epoch 39, batch 2000, loss[loss=0.1369, simple_loss=0.2308, pruned_loss=0.02146, over 7257.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2419, pruned_loss=0.02871, over 1423533.96 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 05:57:50,318 INFO [train.py:812] (2/8) Epoch 39, batch 2050, loss[loss=0.1369, simple_loss=0.235, pruned_loss=0.01941, over 7308.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2421, pruned_loss=0.02874, over 1422054.82 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 05:58:49,534 INFO [train.py:812] (2/8) Epoch 39, batch 2100, loss[loss=0.1234, simple_loss=0.2038, pruned_loss=0.02144, over 6794.00 frames.], tot_loss[loss=0.149, simple_loss=0.2409, pruned_loss=0.0285, over 1423307.87 frames.], batch size: 15, lr: 1.99e-04
+2022-05-16 05:59:47,696 INFO [train.py:812] (2/8) Epoch 39, batch 2150, loss[loss=0.1475, simple_loss=0.2417, pruned_loss=0.02665, over 7276.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2409, pruned_loss=0.02862, over 1420878.03 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:00:46,899 INFO [train.py:812] (2/8) Epoch 39, batch 2200, loss[loss=0.1473, simple_loss=0.234, pruned_loss=0.03023, over 7204.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2415, pruned_loss=0.02885, over 1421428.29 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:01:46,021 INFO [train.py:812] (2/8) Epoch 39, batch 2250, loss[loss=0.1372, simple_loss=0.2218, pruned_loss=0.02625, over 7142.00 frames.], tot_loss[loss=0.149, simple_loss=0.2403, pruned_loss=0.02883, over 1425072.66 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:02:45,399 INFO [train.py:812] (2/8) Epoch 39, batch 2300, loss[loss=0.1394, simple_loss=0.2286, pruned_loss=0.02507, over 7159.00 frames.], tot_loss[loss=0.1494, simple_loss=0.241, pruned_loss=0.02887, over 1424486.99 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:03:45,421 INFO [train.py:812] (2/8) Epoch 39, batch 2350, loss[loss=0.1415, simple_loss=0.2333, pruned_loss=0.02482, over 7243.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2402, pruned_loss=0.02858, over 1425925.17 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:04:43,837 INFO [train.py:812] (2/8) Epoch 39, batch 2400, loss[loss=0.17, simple_loss=0.2652, pruned_loss=0.03742, over 7144.00 frames.], tot_loss[loss=0.149, simple_loss=0.2408, pruned_loss=0.02862, over 1429235.13 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:05:41,782 INFO [train.py:812] (2/8) Epoch 39, batch 2450, loss[loss=0.1397, simple_loss=0.2263, pruned_loss=0.02656, over 7414.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2403, pruned_loss=0.02828, over 1429782.70 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:06:40,888 INFO [train.py:812] (2/8) Epoch 39, batch 2500, loss[loss=0.1292, simple_loss=0.2143, pruned_loss=0.022, over 7415.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2402, pruned_loss=0.02824, over 1428145.69 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:07:38,139 INFO [train.py:812] (2/8) Epoch 39, batch 2550, loss[loss=0.1436, simple_loss=0.2481, pruned_loss=0.01958, over 7429.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2402, pruned_loss=0.028, over 1432295.67 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:08:37,353 INFO [train.py:812] (2/8) Epoch 39, batch 2600, loss[loss=0.1733, simple_loss=0.2647, pruned_loss=0.04094, over 7176.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2413, pruned_loss=0.0282, over 1429915.64 frames.], batch size: 26, lr: 1.99e-04
+2022-05-16 06:09:36,141 INFO [train.py:812] (2/8) Epoch 39, batch 2650, loss[loss=0.162, simple_loss=0.2574, pruned_loss=0.03333, over 7121.00 frames.], tot_loss[loss=0.149, simple_loss=0.2411, pruned_loss=0.02841, over 1431183.02 frames.], batch size: 28, lr: 1.99e-04
+2022-05-16 06:10:34,088 INFO [train.py:812] (2/8) Epoch 39, batch 2700, loss[loss=0.1911, simple_loss=0.2902, pruned_loss=0.04599, over 7287.00 frames.], tot_loss[loss=0.1489, simple_loss=0.241, pruned_loss=0.02837, over 1428737.95 frames.], batch size: 25, lr: 1.99e-04
+2022-05-16 06:11:32,736 INFO [train.py:812] (2/8) Epoch 39, batch 2750, loss[loss=0.1327, simple_loss=0.2248, pruned_loss=0.02027, over 7151.00 frames.], tot_loss[loss=0.1488, simple_loss=0.241, pruned_loss=0.02833, over 1428470.16 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:12:31,399 INFO [train.py:812] (2/8) Epoch 39, batch 2800, loss[loss=0.1454, simple_loss=0.2431, pruned_loss=0.02385, over 7330.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02826, over 1425362.15 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:13:29,248 INFO [train.py:812] (2/8) Epoch 39, batch 2850, loss[loss=0.1437, simple_loss=0.2363, pruned_loss=0.02556, over 6455.00 frames.], tot_loss[loss=0.1493, simple_loss=0.242, pruned_loss=0.02836, over 1425397.49 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:14:28,562 INFO [train.py:812] (2/8) Epoch 39, batch 2900, loss[loss=0.1616, simple_loss=0.2534, pruned_loss=0.03491, over 7314.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.0285, over 1424526.86 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 06:15:27,624 INFO [train.py:812] (2/8) Epoch 39, batch 2950, loss[loss=0.1521, simple_loss=0.2493, pruned_loss=0.02744, over 7321.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2411, pruned_loss=0.02821, over 1427968.72 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:16:26,913 INFO [train.py:812] (2/8) Epoch 39, batch 3000, loss[loss=0.1459, simple_loss=0.2411, pruned_loss=0.02535, over 7231.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2419, pruned_loss=0.02851, over 1428613.01 frames.], batch size: 20, lr: 1.99e-04
+2022-05-16 06:16:26,914 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-16 06:16:34,437 INFO [train.py:841] (2/8) Epoch 39, validation: loss=0.153, simple_loss=0.2484, pruned_loss=0.02885, over 698248.00 frames.
+2022-05-16 06:17:33,442 INFO [train.py:812] (2/8) Epoch 39, batch 3050, loss[loss=0.1803, simple_loss=0.2513, pruned_loss=0.0547, over 7135.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2419, pruned_loss=0.02866, over 1425669.74 frames.], batch size: 17, lr: 1.99e-04
+2022-05-16 06:18:32,238 INFO [train.py:812] (2/8) Epoch 39, batch 3100, loss[loss=0.1451, simple_loss=0.2478, pruned_loss=0.02119, over 6635.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02843, over 1417821.90 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:19:30,255 INFO [train.py:812] (2/8) Epoch 39, batch 3150, loss[loss=0.1523, simple_loss=0.2511, pruned_loss=0.02681, over 7417.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02837, over 1422929.03 frames.], batch size: 21, lr: 1.99e-04
+2022-05-16 06:20:28,869 INFO [train.py:812] (2/8) Epoch 39, batch 3200, loss[loss=0.1434, simple_loss=0.2332, pruned_loss=0.02677, over 6299.00 frames.], tot_loss[loss=0.149, simple_loss=0.2416, pruned_loss=0.02823, over 1423753.04 frames.], batch size: 37, lr: 1.99e-04
+2022-05-16 06:21:26,201 INFO [train.py:812] (2/8) Epoch 39, batch 3250, loss[loss=0.1634, simple_loss=0.2535, pruned_loss=0.03668, over 6284.00 frames.], tot_loss[loss=0.1492, simple_loss=0.242, pruned_loss=0.02814, over 1423670.73 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:22:25,453 INFO [train.py:812] (2/8) Epoch 39, batch 3300, loss[loss=0.148, simple_loss=0.2437, pruned_loss=0.02614, over 7162.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2418, pruned_loss=0.0284, over 1424215.30 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:23:24,289 INFO [train.py:812] (2/8) Epoch 39, batch 3350, loss[loss=0.1195, simple_loss=0.2, pruned_loss=0.0195, over 7134.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2404, pruned_loss=0.02791, over 1426048.77 frames.], batch size: 17, lr: 1.99e-04
+2022-05-16 06:24:23,015 INFO [train.py:812] (2/8) Epoch 39, batch 3400, loss[loss=0.1444, simple_loss=0.2417, pruned_loss=0.0236, over 7358.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2399, pruned_loss=0.02773, over 1427646.34 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:25:22,168 INFO [train.py:812] (2/8) Epoch 39, batch 3450, loss[loss=0.1499, simple_loss=0.2672, pruned_loss=0.01628, over 7180.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2402, pruned_loss=0.02807, over 1420291.86 frames.], batch size: 23, lr: 1.99e-04
+2022-05-16 06:26:21,431 INFO [train.py:812] (2/8) Epoch 39, batch 3500, loss[loss=0.1415, simple_loss=0.2294, pruned_loss=0.02681, over 7159.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02815, over 1421725.76 frames.], batch size: 19, lr: 1.99e-04
+2022-05-16 06:27:20,247 INFO [train.py:812] (2/8) Epoch 39, batch 3550, loss[loss=0.1573, simple_loss=0.2548, pruned_loss=0.02992, over 7342.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2405, pruned_loss=0.02819, over 1424170.87 frames.], batch size: 22, lr: 1.99e-04
+2022-05-16 06:28:19,534 INFO [train.py:812] (2/8) Epoch 39, batch 3600, loss[loss=0.1352, simple_loss=0.2101, pruned_loss=0.03012, over 7286.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2403, pruned_loss=0.02792, over 1424654.52 frames.], batch size: 18, lr: 1.99e-04
+2022-05-16 06:29:18,046 INFO [train.py:812] (2/8) Epoch 39, batch 3650, loss[loss=0.1504, simple_loss=0.2398, pruned_loss=0.03043, over 7072.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2402, pruned_loss=0.0278, over 1425921.88 frames.], batch size: 28, lr: 1.99e-04
+2022-05-16 06:30:16,884 INFO [train.py:812] (2/8) Epoch 39, batch 3700, loss[loss=0.1679, simple_loss=0.2613, pruned_loss=0.03729, over 6701.00 frames.], tot_loss[loss=0.148, simple_loss=0.2404, pruned_loss=0.02782, over 1422904.74 frames.], batch size: 38, lr: 1.99e-04
+2022-05-16 06:31:16,255 INFO [train.py:812] (2/8) Epoch 39, batch 3750, loss[loss=0.1757, simple_loss=0.2608, pruned_loss=0.04527, over 7193.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2402, pruned_loss=0.02776, over 1416469.18 frames.], batch size: 23, lr: 1.98e-04
+2022-05-16 06:32:15,543 INFO [train.py:812] (2/8) Epoch 39, batch 3800, loss[loss=0.1283, simple_loss=0.219, pruned_loss=0.0188, over 7354.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2397, pruned_loss=0.02723, over 1422943.45 frames.], batch size: 19, lr: 1.98e-04
+2022-05-16 06:33:12,750 INFO [train.py:812] (2/8) Epoch 39, batch 3850, loss[loss=0.183, simple_loss=0.2673, pruned_loss=0.0493, over 5188.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2403, pruned_loss=0.02779, over 1419549.03 frames.], batch size: 52, lr: 1.98e-04
+2022-05-16 06:34:10,691 INFO [train.py:812] (2/8) Epoch 39, batch 3900, loss[loss=0.1771, simple_loss=0.2733, pruned_loss=0.04041, over 7147.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2405, pruned_loss=0.02782, over 1419922.25 frames.], batch size: 28, lr: 1.98e-04
+2022-05-16 06:35:09,061 INFO [train.py:812] (2/8) Epoch 39, batch 3950, loss[loss=0.1593, simple_loss=0.2508, pruned_loss=0.03387, over 7273.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2401, pruned_loss=0.02753, over 1421936.70 frames.], batch size: 25, lr: 1.98e-04
+2022-05-16 06:36:07,263 INFO [train.py:812] (2/8) Epoch 39, batch 4000, loss[loss=0.1353, simple_loss=0.2255, pruned_loss=0.02251, over 6833.00 frames.], tot_loss[loss=0.1477, simple_loss=0.24, pruned_loss=0.02773, over 1424680.13 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:37:03,577 INFO [train.py:812] (2/8) Epoch 39, batch 4050, loss[loss=0.1443, simple_loss=0.2355, pruned_loss=0.02658, over 6727.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2401, pruned_loss=0.02758, over 1422892.05 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:38:02,731 INFO [train.py:812] (2/8) Epoch 39, batch 4100, loss[loss=0.1606, simple_loss=0.2682, pruned_loss=0.02653, over 7217.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2395, pruned_loss=0.02745, over 1421505.57 frames.], batch size: 21, lr: 1.98e-04
+2022-05-16 06:39:01,751 INFO [train.py:812] (2/8) Epoch 39, batch 4150, loss[loss=0.1469, simple_loss=0.2495, pruned_loss=0.02212, over 7220.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2394, pruned_loss=0.0272, over 1419262.67 frames.], batch size: 21, lr: 1.98e-04
+2022-05-16 06:40:00,309 INFO [train.py:812] (2/8) Epoch 39, batch 4200, loss[loss=0.1473, simple_loss=0.2335, pruned_loss=0.03055, over 6815.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2409, pruned_loss=0.02778, over 1418187.47 frames.], batch size: 31, lr: 1.98e-04
+2022-05-16 06:40:58,787 INFO [train.py:812] (2/8) Epoch 39, batch 4250, loss[loss=0.1482, simple_loss=0.234, pruned_loss=0.03125, over 7141.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2409, pruned_loss=0.02785, over 1415764.25 frames.], batch size: 17, lr: 1.98e-04
+2022-05-16 06:41:58,202 INFO [train.py:812] (2/8) Epoch 39, batch 4300, loss[loss=0.1559, simple_loss=0.2474, pruned_loss=0.03221, over 7292.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02874, over 1416674.02 frames.], batch size: 25, lr: 1.98e-04
+2022-05-16 06:42:56,993 INFO [train.py:812] (2/8) Epoch 39, batch 4350, loss[loss=0.1559, simple_loss=0.2526, pruned_loss=0.02961, over 7435.00 frames.], tot_loss[loss=0.15, simple_loss=0.2425, pruned_loss=0.02872, over 1413495.89 frames.], batch size: 20, lr: 1.98e-04
+2022-05-16 06:43:56,258 INFO [train.py:812] (2/8) Epoch 39, batch 4400, loss[loss=0.1558, simple_loss=0.2473, pruned_loss=0.03217, over 7332.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2436, pruned_loss=0.02943, over 1410385.35 frames.], batch size: 22, lr: 1.98e-04
+2022-05-16 06:44:54,113 INFO [train.py:812] (2/8) Epoch 39, batch 4450, loss[loss=0.1243, simple_loss=0.2131, pruned_loss=0.0177, over 7006.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2443, pruned_loss=0.02967, over 1397226.94 frames.], batch size: 16, lr: 1.98e-04
+2022-05-16 06:45:52,378 INFO [train.py:812] (2/8) Epoch 39, batch 4500, loss[loss=0.139, simple_loss=0.2264, pruned_loss=0.02581, over 7172.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2448, pruned_loss=0.02972, over 1386160.23 frames.], batch size: 18, lr: 1.98e-04
+2022-05-16 06:46:49,710 INFO [train.py:812] (2/8) Epoch 39, batch 4550, loss[loss=0.2066, simple_loss=0.2989, pruned_loss=0.05717, over 4921.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2463, pruned_loss=0.03093, over 1347700.88 frames.], batch size: 52, lr: 1.98e-04
+2022-05-16 06:47:54,891 INFO [train.py:812] (2/8) Epoch 40, batch 0, loss[loss=0.214, simple_loss=0.3165, pruned_loss=0.0558, over 7310.00 frames.], tot_loss[loss=0.214, simple_loss=0.3165, pruned_loss=0.0558, over 7310.00 frames.], batch size: 24, lr: 1.96e-04
+2022-05-16 06:48:53,195 INFO [train.py:812] (2/8) Epoch 40, batch 50, loss[loss=0.1115, simple_loss=0.1925, pruned_loss=0.01525, over 7305.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2462, pruned_loss=0.02961, over 316609.57 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 06:49:52,151 INFO [train.py:812] (2/8) Epoch 40, batch 100, loss[loss=0.1501, simple_loss=0.246, pruned_loss=0.02709, over 7361.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2424, pruned_loss=0.02866, over 561328.35 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 06:50:51,442 INFO [train.py:812] (2/8) Epoch 40, batch 150, loss[loss=0.1495, simple_loss=0.2467, pruned_loss=0.02614, over 7228.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2396, pruned_loss=0.02843, over 753550.45 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:51:50,281 INFO [train.py:812] (2/8) Epoch 40, batch 200, loss[loss=0.1405, simple_loss=0.2305, pruned_loss=0.02522, over 7432.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2414, pruned_loss=0.02895, over 901991.11 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 06:52:48,882 INFO [train.py:812] (2/8) Epoch 40, batch 250, loss[loss=0.1525, simple_loss=0.2511, pruned_loss=0.02698, over 7442.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.02851, over 1016014.12 frames.], batch size: 22, lr: 1.95e-04
+2022-05-16 06:53:47,829 INFO [train.py:812] (2/8) Epoch 40, batch 300, loss[loss=0.1294, simple_loss=0.2258, pruned_loss=0.01653, over 7265.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2408, pruned_loss=0.02819, over 1106498.55 frames.], batch size: 24, lr: 1.95e-04
+2022-05-16 06:54:46,914 INFO [train.py:812] (2/8) Epoch 40, batch 350, loss[loss=0.1668, simple_loss=0.2621, pruned_loss=0.03568, over 7153.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2412, pruned_loss=0.02878, over 1171144.67 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:55:45,287 INFO [train.py:812] (2/8) Epoch 40, batch 400, loss[loss=0.1521, simple_loss=0.2529, pruned_loss=0.02562, over 7149.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02877, over 1228179.80 frames.], batch size: 26, lr: 1.95e-04
+2022-05-16 06:56:53,568 INFO [train.py:812] (2/8) Epoch 40, batch 450, loss[loss=0.1764, simple_loss=0.2648, pruned_loss=0.04399, over 7309.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2409, pruned_loss=0.02797, over 1272192.80 frames.], batch size: 25, lr: 1.95e-04
+2022-05-16 06:57:52,470 INFO [train.py:812] (2/8) Epoch 40, batch 500, loss[loss=0.1357, simple_loss=0.2345, pruned_loss=0.01846, over 7320.00 frames.], tot_loss[loss=0.148, simple_loss=0.2404, pruned_loss=0.02779, over 1305131.14 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 06:58:59,583 INFO [train.py:812] (2/8) Epoch 40, batch 550, loss[loss=0.1732, simple_loss=0.2685, pruned_loss=0.0389, over 7235.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2401, pruned_loss=0.02798, over 1326844.83 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 06:59:58,452 INFO [train.py:812] (2/8) Epoch 40, batch 600, loss[loss=0.1328, simple_loss=0.2234, pruned_loss=0.02112, over 7259.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2393, pruned_loss=0.02776, over 1348411.11 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 07:01:07,491 INFO [train.py:812] (2/8) Epoch 40, batch 650, loss[loss=0.1392, simple_loss=0.2346, pruned_loss=0.02191, over 7223.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2394, pruned_loss=0.02771, over 1366782.12 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 07:02:07,009 INFO [train.py:812] (2/8) Epoch 40, batch 700, loss[loss=0.1394, simple_loss=0.2222, pruned_loss=0.02827, over 7268.00 frames.], tot_loss[loss=0.1479, simple_loss=0.24, pruned_loss=0.02793, over 1380170.39 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:03:06,179 INFO [train.py:812] (2/8) Epoch 40, batch 750, loss[loss=0.142, simple_loss=0.2254, pruned_loss=0.02927, over 7360.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2396, pruned_loss=0.02771, over 1386340.76 frames.], batch size: 19, lr: 1.95e-04
+2022-05-16 07:04:05,500 INFO [train.py:812] (2/8) Epoch 40, batch 800, loss[loss=0.1542, simple_loss=0.2526, pruned_loss=0.02792, over 7112.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2393, pruned_loss=0.02753, over 1395422.95 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:05:03,755 INFO [train.py:812] (2/8) Epoch 40, batch 850, loss[loss=0.1272, simple_loss=0.215, pruned_loss=0.01973, over 7138.00 frames.], tot_loss[loss=0.1477, simple_loss=0.24, pruned_loss=0.02768, over 1402232.05 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 07:06:12,335 INFO [train.py:812] (2/8) Epoch 40, batch 900, loss[loss=0.168, simple_loss=0.2691, pruned_loss=0.03351, over 7203.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2407, pruned_loss=0.02776, over 1408488.49 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:07:10,693 INFO [train.py:812] (2/8) Epoch 40, batch 950, loss[loss=0.1594, simple_loss=0.2482, pruned_loss=0.0353, over 5030.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2412, pruned_loss=0.02791, over 1412115.52 frames.], batch size: 52, lr: 1.95e-04
+2022-05-16 07:08:20,202 INFO [train.py:812] (2/8) Epoch 40, batch 1000, loss[loss=0.1496, simple_loss=0.2435, pruned_loss=0.02786, over 7118.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2415, pruned_loss=0.02784, over 1411352.99 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:09:19,145 INFO [train.py:812] (2/8) Epoch 40, batch 1050, loss[loss=0.1495, simple_loss=0.2508, pruned_loss=0.02408, over 7224.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2416, pruned_loss=0.0278, over 1410020.65 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:10:42,477 INFO [train.py:812] (2/8) Epoch 40, batch 1100, loss[loss=0.1508, simple_loss=0.2371, pruned_loss=0.03227, over 7173.00 frames.], tot_loss[loss=0.148, simple_loss=0.241, pruned_loss=0.02756, over 1408097.97 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:11:40,910 INFO [train.py:812] (2/8) Epoch 40, batch 1150, loss[loss=0.1508, simple_loss=0.2486, pruned_loss=0.02647, over 6691.00 frames.], tot_loss[loss=0.1472, simple_loss=0.24, pruned_loss=0.02726, over 1414898.55 frames.], batch size: 31, lr: 1.95e-04
+2022-05-16 07:12:38,503 INFO [train.py:812] (2/8) Epoch 40, batch 1200, loss[loss=0.1469, simple_loss=0.2461, pruned_loss=0.02379, over 6418.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2406, pruned_loss=0.02749, over 1417473.52 frames.], batch size: 38, lr: 1.95e-04
+2022-05-16 07:13:37,100 INFO [train.py:812] (2/8) Epoch 40, batch 1250, loss[loss=0.1416, simple_loss=0.239, pruned_loss=0.02211, over 7307.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2401, pruned_loss=0.02752, over 1420692.52 frames.], batch size: 25, lr: 1.95e-04
+2022-05-16 07:14:35,225 INFO [train.py:812] (2/8) Epoch 40, batch 1300, loss[loss=0.1737, simple_loss=0.2672, pruned_loss=0.04011, over 7444.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2403, pruned_loss=0.02745, over 1421409.05 frames.], batch size: 20, lr: 1.95e-04
+2022-05-16 07:15:33,946 INFO [train.py:812] (2/8) Epoch 40, batch 1350, loss[loss=0.1479, simple_loss=0.2447, pruned_loss=0.02553, over 6560.00 frames.], tot_loss[loss=0.1478, simple_loss=0.24, pruned_loss=0.02777, over 1421616.93 frames.], batch size: 37, lr: 1.95e-04
+2022-05-16 07:16:32,342 INFO [train.py:812] (2/8) Epoch 40, batch 1400, loss[loss=0.1466, simple_loss=0.2472, pruned_loss=0.02299, over 6488.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2406, pruned_loss=0.02765, over 1423023.97 frames.], batch size: 38, lr: 1.95e-04
+2022-05-16 07:17:30,660 INFO [train.py:812] (2/8) Epoch 40, batch 1450, loss[loss=0.1548, simple_loss=0.2497, pruned_loss=0.02995, over 7196.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2405, pruned_loss=0.02729, over 1424702.53 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:18:29,819 INFO [train.py:812] (2/8) Epoch 40, batch 1500, loss[loss=0.1477, simple_loss=0.231, pruned_loss=0.03217, over 7124.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2412, pruned_loss=0.02787, over 1425984.89 frames.], batch size: 17, lr: 1.95e-04
+2022-05-16 07:19:28,119 INFO [train.py:812] (2/8) Epoch 40, batch 1550, loss[loss=0.156, simple_loss=0.246, pruned_loss=0.03297, over 7197.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2407, pruned_loss=0.02779, over 1423884.23 frames.], batch size: 23, lr: 1.95e-04
+2022-05-16 07:20:27,126 INFO [train.py:812] (2/8) Epoch 40, batch 1600, loss[loss=0.1453, simple_loss=0.2443, pruned_loss=0.02311, over 7068.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2409, pruned_loss=0.02778, over 1426457.93 frames.], batch size: 28, lr: 1.95e-04
+2022-05-16 07:21:25,474 INFO [train.py:812] (2/8) Epoch 40, batch 1650, loss[loss=0.1878, simple_loss=0.2825, pruned_loss=0.04656, over 5343.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2417, pruned_loss=0.0284, over 1419933.00 frames.], batch size: 54, lr: 1.95e-04
+2022-05-16 07:22:23,881 INFO [train.py:812] (2/8) Epoch 40, batch 1700, loss[loss=0.1427, simple_loss=0.2231, pruned_loss=0.03118, over 7011.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2412, pruned_loss=0.02861, over 1413303.56 frames.], batch size: 16, lr: 1.95e-04
+2022-05-16 07:23:23,260 INFO [train.py:812] (2/8) Epoch 40, batch 1750, loss[loss=0.1413, simple_loss=0.233, pruned_loss=0.0248, over 7318.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2409, pruned_loss=0.02836, over 1415270.60 frames.], batch size: 21, lr: 1.95e-04
+2022-05-16 07:24:22,410 INFO [train.py:812] (2/8) Epoch 40, batch 1800, loss[loss=0.1572, simple_loss=0.2569, pruned_loss=0.02878, over 7335.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2417, pruned_loss=0.0284, over 1417039.28 frames.], batch size: 22, lr: 1.95e-04
+2022-05-16 07:25:21,046 INFO [train.py:812] (2/8) Epoch 40, batch 1850, loss[loss=0.136, simple_loss=0.2253, pruned_loss=0.02333, over 7076.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02825, over 1420653.48 frames.], batch size: 18, lr: 1.95e-04
+2022-05-16 07:26:20,225 INFO [train.py:812] (2/8) Epoch 40, batch 1900, loss[loss=0.1584, simple_loss=0.2502, pruned_loss=0.03332, over 7161.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2424, pruned_loss=0.0283, over 1424950.94 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:27:17,890 INFO [train.py:812] (2/8) Epoch 40, batch 1950, loss[loss=0.178, simple_loss=0.2633, pruned_loss=0.04632, over 5193.00 frames.], tot_loss[loss=0.1502, simple_loss=0.243, pruned_loss=0.02868, over 1419605.33 frames.], batch size: 52, lr: 1.94e-04
+2022-05-16 07:28:16,411 INFO [train.py:812] (2/8) Epoch 40, batch 2000, loss[loss=0.1507, simple_loss=0.2435, pruned_loss=0.02896, over 7064.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2423, pruned_loss=0.02838, over 1422778.74 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:29:15,097 INFO [train.py:812] (2/8) Epoch 40, batch 2050, loss[loss=0.1425, simple_loss=0.2389, pruned_loss=0.02306, over 7429.00 frames.], tot_loss[loss=0.149, simple_loss=0.2417, pruned_loss=0.02813, over 1426962.39 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:30:14,379 INFO [train.py:812] (2/8) Epoch 40, batch 2100, loss[loss=0.1298, simple_loss=0.2182, pruned_loss=0.02068, over 7405.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2412, pruned_loss=0.02803, over 1426356.04 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:31:12,643 INFO [train.py:812] (2/8) Epoch 40, batch 2150, loss[loss=0.16, simple_loss=0.2589, pruned_loss=0.03059, over 7149.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2409, pruned_loss=0.02787, over 1430397.20 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:32:11,379 INFO [train.py:812] (2/8) Epoch 40, batch 2200, loss[loss=0.1723, simple_loss=0.2623, pruned_loss=0.04115, over 7236.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2408, pruned_loss=0.02766, over 1433417.68 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:33:10,314 INFO [train.py:812] (2/8) Epoch 40, batch 2250, loss[loss=0.1814, simple_loss=0.2725, pruned_loss=0.04514, over 7199.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2411, pruned_loss=0.02765, over 1431697.16 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:34:08,376 INFO [train.py:812] (2/8) Epoch 40, batch 2300, loss[loss=0.158, simple_loss=0.2482, pruned_loss=0.03392, over 7431.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2405, pruned_loss=0.02783, over 1428709.50 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:35:07,182 INFO [train.py:812] (2/8) Epoch 40, batch 2350, loss[loss=0.1674, simple_loss=0.2685, pruned_loss=0.0332, over 7326.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2399, pruned_loss=0.02754, over 1427358.06 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:36:06,636 INFO [train.py:812] (2/8) Epoch 40, batch 2400, loss[loss=0.16, simple_loss=0.2494, pruned_loss=0.03524, over 7194.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2401, pruned_loss=0.02778, over 1427092.94 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:37:04,708 INFO [train.py:812] (2/8) Epoch 40, batch 2450, loss[loss=0.1568, simple_loss=0.2546, pruned_loss=0.02948, over 7061.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02826, over 1422116.89 frames.], batch size: 28, lr: 1.94e-04
+2022-05-16 07:38:03,593 INFO [train.py:812] (2/8) Epoch 40, batch 2500, loss[loss=0.1392, simple_loss=0.2337, pruned_loss=0.0223, over 7412.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2414, pruned_loss=0.02809, over 1419392.58 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:39:02,631 INFO [train.py:812] (2/8) Epoch 40, batch 2550, loss[loss=0.1576, simple_loss=0.2556, pruned_loss=0.02975, over 7076.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2418, pruned_loss=0.02839, over 1419751.38 frames.], batch size: 28, lr: 1.94e-04
+2022-05-16 07:40:02,268 INFO [train.py:812] (2/8) Epoch 40, batch 2600, loss[loss=0.1317, simple_loss=0.2223, pruned_loss=0.02055, over 7333.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2409, pruned_loss=0.0282, over 1419324.18 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:40:59,586 INFO [train.py:812] (2/8) Epoch 40, batch 2650, loss[loss=0.1355, simple_loss=0.2194, pruned_loss=0.02574, over 7162.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2406, pruned_loss=0.02818, over 1421546.52 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:42:08,100 INFO [train.py:812] (2/8) Epoch 40, batch 2700, loss[loss=0.1774, simple_loss=0.276, pruned_loss=0.03942, over 7154.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2413, pruned_loss=0.02808, over 1422738.12 frames.], batch size: 26, lr: 1.94e-04
+2022-05-16 07:43:06,183 INFO [train.py:812] (2/8) Epoch 40, batch 2750, loss[loss=0.1632, simple_loss=0.2661, pruned_loss=0.03017, over 7305.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2413, pruned_loss=0.0279, over 1425110.62 frames.], batch size: 24, lr: 1.94e-04
+2022-05-16 07:44:05,705 INFO [train.py:812] (2/8) Epoch 40, batch 2800, loss[loss=0.1312, simple_loss=0.2261, pruned_loss=0.01815, over 7461.00 frames.], tot_loss[loss=0.149, simple_loss=0.2419, pruned_loss=0.02801, over 1422494.60 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:45:02,891 INFO [train.py:812] (2/8) Epoch 40, batch 2850, loss[loss=0.1438, simple_loss=0.2453, pruned_loss=0.02116, over 6378.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2417, pruned_loss=0.0279, over 1420095.07 frames.], batch size: 38, lr: 1.94e-04
+2022-05-16 07:46:01,098 INFO [train.py:812] (2/8) Epoch 40, batch 2900, loss[loss=0.1286, simple_loss=0.2144, pruned_loss=0.02137, over 7066.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2412, pruned_loss=0.02775, over 1419799.14 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:46:58,666 INFO [train.py:812] (2/8) Epoch 40, batch 2950, loss[loss=0.1611, simple_loss=0.2607, pruned_loss=0.03071, over 7280.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2418, pruned_loss=0.02768, over 1418856.43 frames.], batch size: 24, lr: 1.94e-04
+2022-05-16 07:47:56,494 INFO [train.py:812] (2/8) Epoch 40, batch 3000, loss[loss=0.1791, simple_loss=0.2663, pruned_loss=0.04593, over 7338.00 frames.], tot_loss[loss=0.149, simple_loss=0.2424, pruned_loss=0.02779, over 1413875.45 frames.], batch size: 22, lr: 1.94e-04
+2022-05-16 07:47:56,495 INFO [train.py:832] (2/8) Computing validation loss
+2022-05-16 07:48:04,107 INFO [train.py:841] (2/8) Epoch 40, validation: loss=0.1534, simple_loss=0.2485, pruned_loss=0.02916, over 698248.00 frames.
+2022-05-16 07:49:02,575 INFO [train.py:812] (2/8) Epoch 40, batch 3050, loss[loss=0.1524, simple_loss=0.2527, pruned_loss=0.0261, over 7348.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2421, pruned_loss=0.02758, over 1415728.15 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:50:01,835 INFO [train.py:812] (2/8) Epoch 40, batch 3100, loss[loss=0.1466, simple_loss=0.2353, pruned_loss=0.02896, over 7186.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2424, pruned_loss=0.02766, over 1417947.53 frames.], batch size: 26, lr: 1.94e-04
+2022-05-16 07:51:00,383 INFO [train.py:812] (2/8) Epoch 40, batch 3150, loss[loss=0.1518, simple_loss=0.2457, pruned_loss=0.02898, over 7130.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2421, pruned_loss=0.02776, over 1421385.01 frames.], batch size: 20, lr: 1.94e-04
+2022-05-16 07:51:59,398 INFO [train.py:812] (2/8) Epoch 40, batch 3200, loss[loss=0.1814, simple_loss=0.2749, pruned_loss=0.04402, over 5131.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2428, pruned_loss=0.02795, over 1422291.61 frames.], batch size: 53, lr: 1.94e-04
+2022-05-16 07:52:57,276 INFO [train.py:812] (2/8) Epoch 40, batch 3250, loss[loss=0.1549, simple_loss=0.2418, pruned_loss=0.03398, over 7383.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2431, pruned_loss=0.02791, over 1420773.57 frames.], batch size: 23, lr: 1.94e-04
+2022-05-16 07:53:57,054 INFO [train.py:812] (2/8) Epoch 40, batch 3300, loss[loss=0.163, simple_loss=0.2639, pruned_loss=0.03102, over 7119.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2427, pruned_loss=0.02808, over 1419430.25 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:54:55,915 INFO [train.py:812] (2/8) Epoch 40, batch 3350, loss[loss=0.1724, simple_loss=0.2715, pruned_loss=0.03666, over 7119.00 frames.], tot_loss[loss=0.1496, simple_loss=0.243, pruned_loss=0.0281, over 1417129.07 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:55:55,666 INFO [train.py:812] (2/8) Epoch 40, batch 3400, loss[loss=0.1527, simple_loss=0.2565, pruned_loss=0.02443, over 7163.00 frames.], tot_loss[loss=0.149, simple_loss=0.2422, pruned_loss=0.02795, over 1417984.35 frames.], batch size: 19, lr: 1.94e-04
+2022-05-16 07:56:54,697 INFO [train.py:812] (2/8) Epoch 40, batch 3450, loss[loss=0.1194, simple_loss=0.2033, pruned_loss=0.01775, over 7281.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2424, pruned_loss=0.02793, over 1416965.44 frames.], batch size: 17, lr: 1.94e-04
+2022-05-16 07:57:54,426 INFO [train.py:812] (2/8) Epoch 40, batch 3500, loss[loss=0.1357, simple_loss=0.2321, pruned_loss=0.0197, over 7308.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2424, pruned_loss=0.0277, over 1418503.57 frames.], batch size: 21, lr: 1.94e-04
+2022-05-16 07:58:53,139 INFO [train.py:812] (2/8) Epoch 40, batch 3550, loss[loss=0.1454, simple_loss=0.2399, pruned_loss=0.02541, over 7060.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2413, pruned_loss=0.0276, over 1419760.45 frames.], batch size: 18, lr: 1.94e-04
+2022-05-16 07:59:51,356 INFO [train.py:812] (2/8) Epoch 40, batch 3600, loss[loss=0.1657, simple_loss=0.2539, pruned_loss=0.03873, over 4852.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2405, pruned_loss=0.02746, over 1416588.24 frames.], batch size: 52, lr: 1.94e-04
+2022-05-16 08:00:51,213 INFO [train.py:812] (2/8) Epoch 40, batch 3650, loss[loss=0.1587, simple_loss=0.2569, pruned_loss=0.0302, over 6388.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2407, pruned_loss=0.02754, over 1418095.90 frames.], batch size: 37, lr: 1.94e-04
+2022-05-16 08:01:49,905 INFO [train.py:812] (2/8) Epoch 40, batch 3700, loss[loss=0.1602, simple_loss=0.2435, pruned_loss=0.03851, over 7132.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2414, pruned_loss=0.02769, over 1421665.74 frames.], batch size: 17, lr: 1.94e-04
+2022-05-16 08:02:46,989 INFO [train.py:812] (2/8) Epoch 40, batch 3750, loss[loss=0.1313, simple_loss=0.2268, pruned_loss=0.01794, over 7366.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2418, pruned_loss=0.02782, over 1419159.90 frames.], batch size: 19, lr: 1.93e-04
+2022-05-16 08:03:45,476 INFO [train.py:812] (2/8) Epoch 40, batch 3800, loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02811, over 6993.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2419, pruned_loss=0.02783, over 1423617.30 frames.], batch size: 16, lr: 1.93e-04
+2022-05-16 08:04:42,407 INFO [train.py:812] (2/8) Epoch 40, batch 3850, loss[loss=0.1339, simple_loss=0.2284, pruned_loss=0.01966, over 7418.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2412, pruned_loss=0.0277, over 1420839.14 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:05:41,434 INFO [train.py:812] (2/8) Epoch 40, batch 3900, loss[loss=0.1588, simple_loss=0.2666, pruned_loss=0.0255, over 7192.00 frames.], tot_loss[loss=0.148, simple_loss=0.2409, pruned_loss=0.02757, over 1421705.18 frames.], batch size: 23, lr: 1.93e-04
+2022-05-16 08:06:40,226 INFO [train.py:812] (2/8) Epoch 40, batch 3950, loss[loss=0.1539, simple_loss=0.2357, pruned_loss=0.03602, over 7064.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2407, pruned_loss=0.02754, over 1417769.92 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:07:38,726 INFO [train.py:812] (2/8) Epoch 40, batch 4000, loss[loss=0.1382, simple_loss=0.2356, pruned_loss=0.02039, over 7144.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2411, pruned_loss=0.02781, over 1417214.23 frames.], batch size: 17, lr: 1.93e-04
+2022-05-16 08:08:36,085 INFO [train.py:812] (2/8) Epoch 40, batch 4050, loss[loss=0.2021, simple_loss=0.2854, pruned_loss=0.05936, over 7208.00 frames.], tot_loss[loss=0.149, simple_loss=0.2416, pruned_loss=0.02819, over 1421288.64 frames.], batch size: 22, lr: 1.93e-04
+2022-05-16 08:09:35,651 INFO [train.py:812] (2/8) Epoch 40, batch 4100, loss[loss=0.1586, simple_loss=0.2521, pruned_loss=0.03257, over 7227.00 frames.], tot_loss[loss=0.149, simple_loss=0.2416, pruned_loss=0.02822, over 1421633.76 frames.], batch size: 20, lr: 1.93e-04
+2022-05-16 08:10:34,246 INFO [train.py:812] (2/8) Epoch 40, batch 4150, loss[loss=0.146, simple_loss=0.2381, pruned_loss=0.02695, over 7290.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2414, pruned_loss=0.02813, over 1422921.35 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:11:32,962 INFO [train.py:812] (2/8) Epoch 40, batch 4200, loss[loss=0.1235, simple_loss=0.2156, pruned_loss=0.01574, over 7160.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2414, pruned_loss=0.02794, over 1424746.74 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:12:31,937 INFO [train.py:812] (2/8) Epoch 40, batch 4250, loss[loss=0.1436, simple_loss=0.2384, pruned_loss=0.02435, over 7318.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2407, pruned_loss=0.02808, over 1420467.26 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:13:30,175 INFO [train.py:812] (2/8) Epoch 40, batch 4300, loss[loss=0.1401, simple_loss=0.2391, pruned_loss=0.0205, over 7154.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2404, pruned_loss=0.02775, over 1420893.01 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:14:29,548 INFO [train.py:812] (2/8) Epoch 40, batch 4350, loss[loss=0.1492, simple_loss=0.2461, pruned_loss=0.02619, over 7319.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2403, pruned_loss=0.0276, over 1422407.73 frames.], batch size: 20, lr: 1.93e-04
+2022-05-16 08:15:29,002 INFO [train.py:812] (2/8) Epoch 40, batch 4400, loss[loss=0.143, simple_loss=0.2341, pruned_loss=0.02596, over 6783.00 frames.], tot_loss[loss=0.148, simple_loss=0.2409, pruned_loss=0.02758, over 1422655.93 frames.], batch size: 31, lr: 1.93e-04
+2022-05-16 08:16:26,680 INFO [train.py:812] (2/8) Epoch 40, batch 4450, loss[loss=0.1407, simple_loss=0.2292, pruned_loss=0.0261, over 7152.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2412, pruned_loss=0.02781, over 1410269.42 frames.], batch size: 18, lr: 1.93e-04
+2022-05-16 08:17:25,845 INFO [train.py:812] (2/8) Epoch 40, batch 4500, loss[loss=0.1433, simple_loss=0.2416, pruned_loss=0.0225, over 7213.00 frames.], tot_loss[loss=0.149, simple_loss=0.2417, pruned_loss=0.02816, over 1403113.79 frames.], batch size: 21, lr: 1.93e-04
+2022-05-16 08:18:25,943 INFO [train.py:812] (2/8) Epoch 40, batch 4550, loss[loss=0.1297, simple_loss=0.2117, pruned_loss=0.02381, over 6771.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2384, pruned_loss=0.02766, over 1393899.65 frames.], batch size: 15, lr: 1.93e-04
+2022-05-16 08:19:10,602 INFO [train.py:1030] (2/8) Done!