2022-05-13 19:15:59,539 INFO [train.py:876] (4/8) Training started
2022-05-13 19:15:59,540 INFO [train.py:886] (4/8) Device: cuda:4
2022-05-13 19:15:59,543 INFO [train.py:895] (4/8) {'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 19:15:59,543 INFO [train.py:897] (4/8) About to create model
2022-05-13 19:16:00,243 INFO [train.py:901] (4/8) Number of model parameters: 116553580
2022-05-13 19:16:07,585 INFO [train.py:916] (4/8) Using DDP
2022-05-13 19:16:09,396 INFO [asr_datamodule.py:391] (4/8) About to get train-clean-100 cuts
2022-05-13 19:16:18,085 INFO [asr_datamodule.py:398] (4/8) About to get train-clean-360 cuts
2022-05-13 19:16:54,677 INFO [asr_datamodule.py:405] (4/8) About to get train-other-500 cuts
2022-05-13 19:17:49,264 INFO [asr_datamodule.py:209] (4/8) Enable MUSAN
2022-05-13 19:17:49,264 INFO [asr_datamodule.py:210] (4/8) About to get Musan cuts
2022-05-13 19:17:51,275 INFO [asr_datamodule.py:238] (4/8) Enable SpecAugment
2022-05-13 19:17:51,276 INFO [asr_datamodule.py:239] (4/8) Time warp factor: 80
2022-05-13 19:17:51,276 INFO [asr_datamodule.py:251] (4/8) Num frame mask: 10
2022-05-13 19:17:51,276 INFO [asr_datamodule.py:264] (4/8) About to create train dataset
2022-05-13 19:17:51,276 INFO [asr_datamodule.py:292] (4/8) Using BucketingSampler.
2022-05-13 19:17:56,285 INFO [asr_datamodule.py:308] (4/8) About to create train dataloader
2022-05-13 19:17:56,286 INFO [asr_datamodule.py:412] (4/8) About to get dev-clean cuts
2022-05-13 19:17:56,619 INFO [asr_datamodule.py:417] (4/8) About to get dev-other cuts
2022-05-13 19:17:56,806 INFO [asr_datamodule.py:339] (4/8) About to create dev dataset
2022-05-13 19:17:56,818 INFO [asr_datamodule.py:358] (4/8) About to create dev dataloader
2022-05-13 19:17:56,818 INFO [train.py:1078] (4/8) Sanity check -- see if any of the batches in epoch 1 would cause OOM.
2022-05-13 19:18:18,394 INFO [distributed.py:874] (4/8) Reducer buckets have been rebuilt in this iteration.
2022-05-13 19:18:41,990 INFO [train.py:812] (4/8) Epoch 1, batch 0, loss[loss=0.7648, simple_loss=1.53, pruned_loss=6.588, over 7271.00 frames.], tot_loss[loss=0.7648, simple_loss=1.53, pruned_loss=6.588, over 7271.00 frames.], batch size: 17, lr: 3.00e-03
2022-05-13 19:19:41,272 INFO [train.py:812] (4/8) Epoch 1, batch 50, loss[loss=0.4832, simple_loss=0.9664, pruned_loss=7.049, over 7167.00 frames.], tot_loss[loss=0.5565, simple_loss=1.113, pruned_loss=7.115, over 323781.91 frames.], batch size: 19, lr: 3.00e-03
2022-05-13 19:20:39,817 INFO [train.py:812] (4/8) Epoch 1, batch 100, loss[loss=0.3784, simple_loss=0.7568, pruned_loss=6.53, over 7010.00 frames.], tot_loss[loss=0.4931, simple_loss=0.9861, pruned_loss=6.961, over 566803.75 frames.], batch size: 16, lr: 3.00e-03
2022-05-13 19:21:38,648 INFO [train.py:812] (4/8) Epoch 1, batch 150, loss[loss=0.3756, simple_loss=0.7512, pruned_loss=6.773, over 6997.00 frames.], tot_loss[loss=0.463, simple_loss=0.926, pruned_loss=6.873, over 758181.76 frames.], batch size: 16, lr: 3.00e-03
2022-05-13 19:22:36,953 INFO [train.py:812] (4/8) Epoch 1, batch 200, loss[loss=0.4447, simple_loss=0.8894, pruned_loss=6.826, over 7275.00 frames.], tot_loss[loss=0.4423, simple_loss=0.8845, pruned_loss=6.839, over 908430.83 frames.], batch size: 25, lr: 3.00e-03
2022-05-13 19:23:35,681 INFO [train.py:812] (4/8) Epoch 1, batch 250, loss[loss=0.4043, simple_loss=0.8087, pruned_loss=6.889, over 7313.00 frames.], tot_loss[loss=0.4289, simple_loss=0.8578, pruned_loss=6.833, over 1017318.61 frames.], batch size: 21, lr: 3.00e-03
2022-05-13 19:24:34,036 INFO [train.py:812] (4/8) Epoch 1, batch 300, loss[loss=0.4121, simple_loss=0.8242, pruned_loss=6.872, over 7334.00 frames.], tot_loss[loss=0.418, simple_loss=0.8361, pruned_loss=6.827, over 1109518.70 frames.], batch size: 25, lr: 3.00e-03
2022-05-13 19:25:33,447 INFO [train.py:812] (4/8) Epoch 1, batch 350, loss[loss=0.3592, simple_loss=0.7184, pruned_loss=6.74, over 7265.00 frames.], tot_loss[loss=0.4105, simple_loss=0.821, pruned_loss=6.82, over 1179133.12 frames.], batch size: 19, lr: 3.00e-03
2022-05-13 19:26:31,633 INFO [train.py:812] (4/8) Epoch 1, batch 400, loss[loss=0.3769, simple_loss=0.7538, pruned_loss=6.845, over 7416.00 frames.], tot_loss[loss=0.4023, simple_loss=0.8047, pruned_loss=6.803, over 1231336.60 frames.], batch size: 21, lr: 3.00e-03
2022-05-13 19:27:30,036 INFO [train.py:812] (4/8) Epoch 1, batch 450, loss[loss=0.3742, simple_loss=0.7484, pruned_loss=6.902, over 7411.00 frames.], tot_loss[loss=0.3925, simple_loss=0.785, pruned_loss=6.786, over 1267423.76 frames.], batch size: 21, lr: 2.99e-03
2022-05-13 19:28:29,387 INFO [train.py:812] (4/8) Epoch 1, batch 500, loss[loss=0.3405, simple_loss=0.6809, pruned_loss=6.778, over 7205.00 frames.], tot_loss[loss=0.3778, simple_loss=0.7555, pruned_loss=6.769, over 1303952.73 frames.], batch size: 22, lr: 2.99e-03
2022-05-13 19:29:27,222 INFO [train.py:812] (4/8) Epoch 1, batch 550, loss[loss=0.29, simple_loss=0.58, pruned_loss=6.806, over 7353.00 frames.], tot_loss[loss=0.3631, simple_loss=0.7262, pruned_loss=6.766, over 1330893.34 frames.], batch size: 22, lr: 2.99e-03
2022-05-13 19:30:26,695 INFO [train.py:812] (4/8) Epoch 1, batch 600, loss[loss=0.2987, simple_loss=0.5974, pruned_loss=6.785, over 7127.00 frames.], tot_loss[loss=0.3471, simple_loss=0.6943, pruned_loss=6.761, over 1350998.97 frames.], batch size: 21, lr: 2.99e-03
2022-05-13 19:31:24,377 INFO [train.py:812] (4/8) Epoch 1, batch 650, loss[loss=0.2305, simple_loss=0.4609, pruned_loss=6.597, over 7007.00 frames.], tot_loss[loss=0.3314, simple_loss=0.6628, pruned_loss=6.753, over 1369531.01 frames.], batch size: 16, lr: 2.99e-03
2022-05-13 19:32:22,734 INFO [train.py:812] (4/8) Epoch 1, batch 700, loss[loss=0.2858, simple_loss=0.5716, pruned_loss=6.846, over 7190.00 frames.], tot_loss[loss=0.316, simple_loss=0.632, pruned_loss=6.743, over 1380731.44 frames.], batch size: 23, lr: 2.99e-03
2022-05-13 19:33:21,785 INFO [train.py:812] (4/8) Epoch 1, batch 750, loss[loss=0.2439, simple_loss=0.4878, pruned_loss=6.549, over 7282.00 frames.], tot_loss[loss=0.301, simple_loss=0.602, pruned_loss=6.732, over 1392316.71 frames.], batch size: 17, lr: 2.98e-03
2022-05-13 19:34:19,632 INFO [train.py:812] (4/8) Epoch 1, batch 800, loss[loss=0.2503, simple_loss=0.5006, pruned_loss=6.701, over 7109.00 frames.], tot_loss[loss=0.2905, simple_loss=0.581, pruned_loss=6.732, over 1397298.86 frames.], batch size: 21, lr: 2.98e-03
2022-05-13 19:35:17,941 INFO [train.py:812] (4/8) Epoch 1, batch 850, loss[loss=0.2378, simple_loss=0.4756, pruned_loss=6.774, over 7220.00 frames.], tot_loss[loss=0.2798, simple_loss=0.5597, pruned_loss=6.732, over 1402376.38 frames.], batch size: 21, lr: 2.98e-03
2022-05-13 19:36:17,408 INFO [train.py:812] (4/8) Epoch 1, batch 900, loss[loss=0.2485, simple_loss=0.497, pruned_loss=6.806, over 7328.00 frames.], tot_loss[loss=0.2705, simple_loss=0.5409, pruned_loss=6.731, over 1407374.77 frames.], batch size: 21, lr: 2.98e-03
2022-05-13 19:37:15,467 INFO [train.py:812] (4/8) Epoch 1, batch 950, loss[loss=0.2052, simple_loss=0.4104, pruned_loss=6.581, over 7005.00 frames.], tot_loss[loss=0.2638, simple_loss=0.5277, pruned_loss=6.738, over 1405040.20 frames.], batch size: 16, lr: 2.97e-03
2022-05-13 19:38:15,222 INFO [train.py:812] (4/8) Epoch 1, batch 1000, loss[loss=0.2023, simple_loss=0.4047, pruned_loss=6.503, over 7420.00 frames.], tot_loss[loss=0.2574, simple_loss=0.5149, pruned_loss=6.738, over 1405734.11 frames.], batch size: 17, lr: 2.97e-03
2022-05-13 19:39:14,095 INFO [train.py:812] (4/8) Epoch 1, batch 1050, loss[loss=0.205, simple_loss=0.4099, pruned_loss=6.657, over 7000.00 frames.], tot_loss[loss=0.2515, simple_loss=0.503, pruned_loss=6.744, over 1407422.06 frames.], batch size: 16, lr: 2.97e-03
2022-05-13 19:40:12,428 INFO [train.py:812] (4/8) Epoch 1, batch 1100, loss[loss=0.2628, simple_loss=0.5255, pruned_loss=6.905, over 7190.00 frames.], tot_loss[loss=0.246, simple_loss=0.492, pruned_loss=6.75, over 1410982.20 frames.], batch size: 22, lr: 2.96e-03
2022-05-13 19:41:10,373 INFO [train.py:812] (4/8) Epoch 1, batch 1150, loss[loss=0.2277, simple_loss=0.4554, pruned_loss=6.832, over 6723.00 frames.], tot_loss[loss=0.2397, simple_loss=0.4794, pruned_loss=6.748, over 1411362.96 frames.], batch size: 31, lr: 2.96e-03
2022-05-13 19:42:08,523 INFO [train.py:812] (4/8) Epoch 1, batch 1200, loss[loss=0.2134, simple_loss=0.4269, pruned_loss=6.871, over 7191.00 frames.], tot_loss[loss=0.2348, simple_loss=0.4696, pruned_loss=6.75, over 1418972.47 frames.], batch size: 26, lr: 2.96e-03
2022-05-13 19:43:07,161 INFO [train.py:812] (4/8) Epoch 1, batch 1250, loss[loss=0.2317, simple_loss=0.4635, pruned_loss=6.831, over 7374.00 frames.], tot_loss[loss=0.231, simple_loss=0.462, pruned_loss=6.753, over 1414156.32 frames.], batch size: 23, lr: 2.95e-03
2022-05-13 19:44:06,123 INFO [train.py:812] (4/8) Epoch 1, batch 1300, loss[loss=0.2148, simple_loss=0.4296, pruned_loss=6.844, over 7315.00 frames.], tot_loss[loss=0.2264, simple_loss=0.4529, pruned_loss=6.757, over 1422399.17 frames.], batch size: 24, lr: 2.95e-03
2022-05-13 19:45:04,276 INFO [train.py:812] (4/8) Epoch 1, batch 1350, loss[loss=0.1861, simple_loss=0.3722, pruned_loss=6.597, over 7147.00 frames.], tot_loss[loss=0.2216, simple_loss=0.4433, pruned_loss=6.751, over 1424095.63 frames.], batch size: 20, lr: 2.95e-03
2022-05-13 19:46:03,477 INFO [train.py:812] (4/8) Epoch 1, batch 1400, loss[loss=0.2001, simple_loss=0.4002, pruned_loss=6.85, over 7280.00 frames.], tot_loss[loss=0.2203, simple_loss=0.4406, pruned_loss=6.759, over 1419433.93 frames.], batch size: 24, lr: 2.94e-03
2022-05-13 19:47:02,122 INFO [train.py:812] (4/8) Epoch 1, batch 1450, loss[loss=0.202, simple_loss=0.4039, pruned_loss=6.797, over 7143.00 frames.], tot_loss[loss=0.2175, simple_loss=0.4349, pruned_loss=6.76, over 1419863.36 frames.], batch size: 17, lr: 2.94e-03
2022-05-13 19:48:00,925 INFO [train.py:812] (4/8) Epoch 1, batch 1500, loss[loss=0.2077, simple_loss=0.4154, pruned_loss=6.853, over 7302.00 frames.], tot_loss[loss=0.2156, simple_loss=0.4312, pruned_loss=6.763, over 1422598.05 frames.], batch size: 24, lr: 2.94e-03
2022-05-13 19:48:59,489 INFO [train.py:812] (4/8) Epoch 1, batch 1550, loss[loss=0.2217, simple_loss=0.4433, pruned_loss=6.74, over 7115.00 frames.], tot_loss[loss=0.2131, simple_loss=0.4261, pruned_loss=6.762, over 1422816.74 frames.], batch size: 21, lr: 2.93e-03
2022-05-13 19:49:59,142 INFO [train.py:812] (4/8) Epoch 1, batch 1600, loss[loss=0.1996, simple_loss=0.3992, pruned_loss=6.722, over 7319.00 frames.], tot_loss[loss=0.2107, simple_loss=0.4214, pruned_loss=6.759, over 1421076.06 frames.], batch size: 20, lr: 2.93e-03
2022-05-13 19:50:59,009 INFO [train.py:812] (4/8) Epoch 1, batch 1650, loss[loss=0.1906, simple_loss=0.3812, pruned_loss=6.666, over 7154.00 frames.], tot_loss[loss=0.2088, simple_loss=0.4175, pruned_loss=6.756, over 1422927.72 frames.], batch size: 18, lr: 2.92e-03
2022-05-13 19:51:59,063 INFO [train.py:812] (4/8) Epoch 1, batch 1700, loss[loss=0.2215, simple_loss=0.4429, pruned_loss=6.864, over 6231.00 frames.], tot_loss[loss=0.2074, simple_loss=0.4148, pruned_loss=6.762, over 1419474.82 frames.], batch size: 37, lr: 2.92e-03
2022-05-13 19:52:58,902 INFO [train.py:812] (4/8) Epoch 1, batch 1750, loss[loss=0.2082, simple_loss=0.4164, pruned_loss=6.809, over 6552.00 frames.], tot_loss[loss=0.2045, simple_loss=0.409, pruned_loss=6.76, over 1420282.17 frames.], batch size: 38, lr: 2.91e-03
2022-05-13 19:54:00,190 INFO [train.py:812] (4/8) Epoch 1, batch 1800, loss[loss=0.1691, simple_loss=0.3383, pruned_loss=6.682, over 7129.00 frames.], tot_loss[loss=0.2025, simple_loss=0.405, pruned_loss=6.759, over 1420107.81 frames.], batch size: 28, lr: 2.91e-03
2022-05-13 19:54:58,674 INFO [train.py:812] (4/8) Epoch 1, batch 1850, loss[loss=0.2312, simple_loss=0.4624, pruned_loss=6.711, over 5061.00 frames.], tot_loss[loss=0.201, simple_loss=0.4021, pruned_loss=6.76, over 1420395.78 frames.], batch size: 52, lr: 2.91e-03
2022-05-13 19:55:56,998 INFO [train.py:812] (4/8) Epoch 1, batch 1900, loss[loss=0.1785, simple_loss=0.3571, pruned_loss=6.744, over 7254.00 frames.], tot_loss[loss=0.2001, simple_loss=0.4002, pruned_loss=6.76, over 1420382.01 frames.], batch size: 19, lr: 2.90e-03
2022-05-13 19:56:55,447 INFO [train.py:812] (4/8) Epoch 1, batch 1950, loss[loss=0.1943, simple_loss=0.3887, pruned_loss=6.766, over 7318.00 frames.], tot_loss[loss=0.1988, simple_loss=0.3975, pruned_loss=6.763, over 1423075.49 frames.], batch size: 21, lr: 2.90e-03
2022-05-13 19:57:54,275 INFO [train.py:812] (4/8) Epoch 1, batch 2000, loss[loss=0.1922, simple_loss=0.3845, pruned_loss=6.724, over 6791.00 frames.], tot_loss[loss=0.197, simple_loss=0.394, pruned_loss=6.764, over 1423492.70 frames.], batch size: 15, lr: 2.89e-03
2022-05-13 19:58:53,064 INFO [train.py:812] (4/8) Epoch 1, batch 2050, loss[loss=0.1964, simple_loss=0.3928, pruned_loss=6.873, over 7157.00 frames.], tot_loss[loss=0.1953, simple_loss=0.3906, pruned_loss=6.761, over 1421362.56 frames.], batch size: 26, lr: 2.89e-03
2022-05-13 19:59:51,422 INFO [train.py:812] (4/8) Epoch 1, batch 2100, loss[loss=0.1895, simple_loss=0.379, pruned_loss=6.736, over 7171.00 frames.], tot_loss[loss=0.1944, simple_loss=0.3889, pruned_loss=6.761, over 1418172.26 frames.], batch size: 18, lr: 2.88e-03
2022-05-13 20:00:49,526 INFO [train.py:812] (4/8) Epoch 1, batch 2150, loss[loss=0.2127, simple_loss=0.4254, pruned_loss=6.81, over 7340.00 frames.], tot_loss[loss=0.1927, simple_loss=0.3854, pruned_loss=6.756, over 1421893.87 frames.], batch size: 22, lr: 2.88e-03
2022-05-13 20:01:48,629 INFO [train.py:812] (4/8) Epoch 1, batch 2200, loss[loss=0.195, simple_loss=0.39, pruned_loss=6.716, over 7305.00 frames.], tot_loss[loss=0.1919, simple_loss=0.3838, pruned_loss=6.756, over 1420907.64 frames.], batch size: 25, lr: 2.87e-03
2022-05-13 20:02:47,465 INFO [train.py:812] (4/8) Epoch 1, batch 2250, loss[loss=0.2039, simple_loss=0.4079, pruned_loss=6.871, over 7221.00 frames.], tot_loss[loss=0.1909, simple_loss=0.3819, pruned_loss=6.75, over 1419265.77 frames.], batch size: 21, lr: 2.86e-03
2022-05-13 20:03:45,867 INFO [train.py:812] (4/8) Epoch 1, batch 2300, loss[loss=0.1625, simple_loss=0.3249, pruned_loss=6.705, over 7258.00 frames.], tot_loss[loss=0.1899, simple_loss=0.3798, pruned_loss=6.748, over 1414780.78 frames.], batch size: 19, lr: 2.86e-03
2022-05-13 20:04:43,221 INFO [train.py:812] (4/8) Epoch 1, batch 2350, loss[loss=0.2211, simple_loss=0.4423, pruned_loss=6.797, over 5293.00 frames.], tot_loss[loss=0.1896, simple_loss=0.3792, pruned_loss=6.751, over 1414466.39 frames.], batch size: 52, lr: 2.85e-03
2022-05-13 20:05:42,787 INFO [train.py:812] (4/8) Epoch 1, batch 2400, loss[loss=0.1689, simple_loss=0.3377, pruned_loss=6.662, over 7434.00 frames.], tot_loss[loss=0.1885, simple_loss=0.3769, pruned_loss=6.75, over 1412034.61 frames.], batch size: 20, lr: 2.85e-03
2022-05-13 20:06:41,409 INFO [train.py:812] (4/8) Epoch 1, batch 2450, loss[loss=0.2416, simple_loss=0.4832, pruned_loss=6.871, over 5232.00 frames.], tot_loss[loss=0.1877, simple_loss=0.3755, pruned_loss=6.75, over 1413151.61 frames.], batch size: 52, lr: 2.84e-03
2022-05-13 20:07:40,729 INFO [train.py:812] (4/8) Epoch 1, batch 2500, loss[loss=0.1794, simple_loss=0.3589, pruned_loss=6.728, over 7324.00 frames.], tot_loss[loss=0.1869, simple_loss=0.3738, pruned_loss=6.745, over 1418599.98 frames.], batch size: 20, lr: 2.84e-03
2022-05-13 20:08:39,347 INFO [train.py:812] (4/8) Epoch 1, batch 2550, loss[loss=0.1588, simple_loss=0.3177, pruned_loss=6.669, over 7422.00 frames.], tot_loss[loss=0.1872, simple_loss=0.3744, pruned_loss=6.741, over 1419112.42 frames.], batch size: 18, lr: 2.83e-03
2022-05-13 20:09:37,902 INFO [train.py:812] (4/8) Epoch 1, batch 2600, loss[loss=0.2015, simple_loss=0.4031, pruned_loss=6.865, over 7234.00 frames.], tot_loss[loss=0.1859, simple_loss=0.3718, pruned_loss=6.737, over 1421936.53 frames.], batch size: 20, lr: 2.83e-03
2022-05-13 20:10:35,865 INFO [train.py:812] (4/8) Epoch 1, batch 2650, loss[loss=0.1742, simple_loss=0.3484, pruned_loss=6.746, over 7231.00 frames.], tot_loss[loss=0.1849, simple_loss=0.3698, pruned_loss=6.738, over 1424001.17 frames.], batch size: 20, lr: 2.82e-03
2022-05-13 20:11:35,630 INFO [train.py:812] (4/8) Epoch 1, batch 2700, loss[loss=0.1782, simple_loss=0.3565, pruned_loss=6.746, over 7138.00 frames.], tot_loss[loss=0.1846, simple_loss=0.3692, pruned_loss=6.739, over 1422995.13 frames.], batch size: 20, lr: 2.81e-03
2022-05-13 20:12:32,557 INFO [train.py:812] (4/8) Epoch 1, batch 2750, loss[loss=0.1753, simple_loss=0.3506, pruned_loss=6.752, over 7315.00 frames.], tot_loss[loss=0.1843, simple_loss=0.3686, pruned_loss=6.743, over 1422885.98 frames.], batch size: 20, lr: 2.81e-03
2022-05-13 20:13:32,048 INFO [train.py:812] (4/8) Epoch 1, batch 2800, loss[loss=0.1943, simple_loss=0.3886, pruned_loss=6.798, over 7146.00 frames.], tot_loss[loss=0.1843, simple_loss=0.3687, pruned_loss=6.744, over 1421752.14 frames.], batch size: 20, lr: 2.80e-03
2022-05-13 20:14:30,981 INFO [train.py:812] (4/8) Epoch 1, batch 2850, loss[loss=0.1605, simple_loss=0.3209, pruned_loss=6.647, over 7357.00 frames.], tot_loss[loss=0.1833, simple_loss=0.3666, pruned_loss=6.742, over 1425293.06 frames.], batch size: 19, lr: 2.80e-03
2022-05-13 20:15:28,496 INFO [train.py:812] (4/8) Epoch 1, batch 2900, loss[loss=0.2076, simple_loss=0.4152, pruned_loss=6.772, over 7327.00 frames.], tot_loss[loss=0.1841, simple_loss=0.3681, pruned_loss=6.744, over 1421106.53 frames.], batch size: 20, lr: 2.79e-03
2022-05-13 20:16:27,583 INFO [train.py:812] (4/8) Epoch 1, batch 2950, loss[loss=0.1887, simple_loss=0.3775, pruned_loss=6.807, over 7170.00 frames.], tot_loss[loss=0.1835, simple_loss=0.3669, pruned_loss=6.74, over 1416900.75 frames.], batch size: 26, lr: 2.78e-03
2022-05-13 20:17:26,743 INFO [train.py:812] (4/8) Epoch 1, batch 3000, loss[loss=0.3601, simple_loss=0.3893, pruned_loss=1.654, over 7272.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3654, pruned_loss=6.713, over 1421117.19 frames.], batch size: 17, lr: 2.78e-03
2022-05-13 20:17:26,744 INFO [train.py:832] (4/8) Computing validation loss
2022-05-13 20:17:34,928 INFO [train.py:841] (4/8) Epoch 1, validation: loss=2.094, simple_loss=0.4148, pruned_loss=1.887, over 698248.00 frames.
2022-05-13 20:18:33,869 INFO [train.py:812] (4/8) Epoch 1, batch 3050, loss[loss=0.2836, simple_loss=0.3801, pruned_loss=0.935, over 6579.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3741, pruned_loss=5.505, over 1420754.87 frames.], batch size: 38, lr: 2.77e-03
2022-05-13 20:19:33,927 INFO [train.py:812] (4/8) Epoch 1, batch 3100, loss[loss=0.2683, simple_loss=0.4146, pruned_loss=0.61, over 7418.00 frames.], tot_loss[loss=0.2427, simple_loss=0.3699, pruned_loss=4.429, over 1426452.31 frames.], batch size: 21, lr: 2.77e-03
2022-05-13 20:20:32,562 INFO [train.py:812] (4/8) Epoch 1, batch 3150, loss[loss=0.2239, simple_loss=0.3764, pruned_loss=0.3569, over 7409.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3668, pruned_loss=3.54, over 1427561.10 frames.], batch size: 21, lr: 2.76e-03
2022-05-13 20:21:30,567 INFO [train.py:812] (4/8) Epoch 1, batch 3200, loss[loss=0.234, simple_loss=0.4047, pruned_loss=0.316, over 7300.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3657, pruned_loss=2.83, over 1423982.13 frames.], batch size: 24, lr: 2.75e-03
2022-05-13 20:22:29,477 INFO [train.py:812] (4/8) Epoch 1, batch 3250, loss[loss=0.1819, simple_loss=0.3261, pruned_loss=0.189, over 7143.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3634, pruned_loss=2.259, over 1423367.96 frames.], batch size: 20, lr: 2.75e-03
2022-05-13 20:23:28,339 INFO [train.py:812] (4/8) Epoch 1, batch 3300, loss[loss=0.2212, simple_loss=0.3905, pruned_loss=0.2594, over 7384.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3636, pruned_loss=1.815, over 1418667.99 frames.], batch size: 23, lr: 2.74e-03
2022-05-13 20:24:25,737 INFO [train.py:812] (4/8) Epoch 1, batch 3350, loss[loss=0.2236, simple_loss=0.3982, pruned_loss=0.2452, over 7307.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3626, pruned_loss=1.455, over 1423304.99 frames.], batch size: 24, lr: 2.73e-03
2022-05-13 20:25:24,234 INFO [train.py:812] (4/8) Epoch 1, batch 3400, loss[loss=0.1668, simple_loss=0.3056, pruned_loss=0.1395, over 7249.00 frames.], tot_loss[loss=0.213, simple_loss=0.3621, pruned_loss=1.177, over 1423616.78 frames.], batch size: 19, lr: 2.73e-03
2022-05-13 20:26:22,133 INFO [train.py:812] (4/8) Epoch 1, batch 3450, loss[loss=0.2041, simple_loss=0.3723, pruned_loss=0.1794, over 7263.00 frames.], tot_loss[loss=0.2098, simple_loss=0.3613, pruned_loss=0.9592, over 1422546.83 frames.], batch size: 25, lr: 2.72e-03
2022-05-13 20:27:20,161 INFO [train.py:812] (4/8) Epoch 1, batch 3500, loss[loss=0.2189, simple_loss=0.3933, pruned_loss=0.222, over 7189.00 frames.], tot_loss[loss=0.2067, simple_loss=0.3601, pruned_loss=0.7873, over 1420601.60 frames.], batch size: 26, lr: 2.72e-03
2022-05-13 20:28:19,228 INFO [train.py:812] (4/8) Epoch 1, batch 3550, loss[loss=0.1871, simple_loss=0.3432, pruned_loss=0.1545, over 7216.00 frames.], tot_loss[loss=0.2036, simple_loss=0.358, pruned_loss=0.651, over 1422577.06 frames.], batch size: 21, lr: 2.71e-03
2022-05-13 20:29:18,098 INFO [train.py:812] (4/8) Epoch 1, batch 3600, loss[loss=0.1873, simple_loss=0.338, pruned_loss=0.1827, over 7005.00 frames.], tot_loss[loss=0.2015, simple_loss=0.3568, pruned_loss=0.546, over 1421566.41 frames.], batch size: 16, lr: 2.70e-03
2022-05-13 20:30:25,545 INFO [train.py:812] (4/8) Epoch 1, batch 3650, loss[loss=0.1905, simple_loss=0.3479, pruned_loss=0.1656, over 7232.00 frames.], tot_loss[loss=0.1991, simple_loss=0.3551, pruned_loss=0.4612, over 1422393.96 frames.], batch size: 21, lr: 2.70e-03
2022-05-13 20:32:10,016 INFO [train.py:812] (4/8) Epoch 1, batch 3700, loss[loss=0.19, simple_loss=0.351, pruned_loss=0.1444, over 6652.00 frames.], tot_loss[loss=0.197, simple_loss=0.3533, pruned_loss=0.394, over 1425816.73 frames.], batch size: 31, lr: 2.69e-03
2022-05-13 20:33:27,102 INFO [train.py:812] (4/8) Epoch 1, batch 3750, loss[loss=0.1742, simple_loss=0.3208, pruned_loss=0.1384, over 7284.00 frames.], tot_loss[loss=0.1958, simple_loss=0.3526, pruned_loss=0.3446, over 1417383.62 frames.], batch size: 18, lr: 2.68e-03
2022-05-13 20:34:26,656 INFO [train.py:812] (4/8) Epoch 1, batch 3800, loss[loss=0.1479, simple_loss=0.2763, pruned_loss=0.09714, over 7120.00 frames.], tot_loss[loss=0.1944, simple_loss=0.3513, pruned_loss=0.3032, over 1417193.68 frames.], batch size: 17, lr: 2.68e-03
2022-05-13 20:35:25,748 INFO [train.py:812] (4/8) Epoch 1, batch 3850, loss[loss=0.1641, simple_loss=0.3035, pruned_loss=0.1236, over 7131.00 frames.], tot_loss[loss=0.1928, simple_loss=0.3497, pruned_loss=0.2692, over 1422609.68 frames.], batch size: 17, lr: 2.67e-03
2022-05-13 20:36:24,066 INFO [train.py:812] (4/8) Epoch 1, batch 3900, loss[loss=0.1866, simple_loss=0.3399, pruned_loss=0.1666, over 7226.00 frames.], tot_loss[loss=0.1923, simple_loss=0.3497, pruned_loss=0.2445, over 1419714.16 frames.], batch size: 16, lr: 2.66e-03
2022-05-13 20:37:21,120 INFO [train.py:812] (4/8) Epoch 1, batch 3950, loss[loss=0.1647, simple_loss=0.3043, pruned_loss=0.1251, over 6821.00 frames.], tot_loss[loss=0.1906, simple_loss=0.3475, pruned_loss=0.2234, over 1417516.29 frames.], batch size: 15, lr: 2.66e-03
2022-05-13 20:38:27,959 INFO [train.py:812] (4/8) Epoch 1, batch 4000, loss[loss=0.2025, simple_loss=0.3736, pruned_loss=0.1568, over 7322.00 frames.], tot_loss[loss=0.191, simple_loss=0.3488, pruned_loss=0.2086, over 1419856.17 frames.], batch size: 21, lr: 2.65e-03
2022-05-13 20:39:26,728 INFO [train.py:812] (4/8) Epoch 1, batch 4050, loss[loss=0.1739, simple_loss=0.3251, pruned_loss=0.1138, over 7080.00 frames.], tot_loss[loss=0.1902, simple_loss=0.348, pruned_loss=0.195, over 1421785.01 frames.], batch size: 28, lr: 2.64e-03
2022-05-13 20:40:25,268 INFO [train.py:812] (4/8) Epoch 1, batch 4100, loss[loss=0.1739, simple_loss=0.3209, pruned_loss=0.1343, over 7254.00 frames.], tot_loss[loss=0.1881, simple_loss=0.3448, pruned_loss=0.183, over 1421579.95 frames.], batch size: 19, lr: 2.64e-03
2022-05-13 20:41:23,936 INFO [train.py:812] (4/8) Epoch 1, batch 4150, loss[loss=0.1656, simple_loss=0.3048, pruned_loss=0.1318, over 7060.00 frames.], tot_loss[loss=0.1885, simple_loss=0.3459, pruned_loss=0.1753, over 1425944.08 frames.], batch size: 18, lr: 2.63e-03
2022-05-13 20:42:22,986 INFO [train.py:812] (4/8) Epoch 1, batch 4200, loss[loss=0.1798, simple_loss=0.3344, pruned_loss=0.1263, over 7199.00 frames.], tot_loss[loss=0.1878, simple_loss=0.3451, pruned_loss=0.1679, over 1425058.67 frames.], batch size: 22, lr: 2.63e-03
2022-05-13 20:43:21,439 INFO [train.py:812] (4/8) Epoch 1, batch 4250, loss[loss=0.1791, simple_loss=0.3301, pruned_loss=0.1406, over 7439.00 frames.], tot_loss[loss=0.1882, simple_loss=0.346, pruned_loss=0.1637, over 1423638.07 frames.], batch size: 20, lr: 2.62e-03
2022-05-13 20:44:20,463 INFO [train.py:812] (4/8) Epoch 1, batch 4300, loss[loss=0.1859, simple_loss=0.341, pruned_loss=0.154, over 7056.00 frames.], tot_loss[loss=0.1878, simple_loss=0.3455, pruned_loss=0.1599, over 1422735.60 frames.], batch size: 28, lr: 2.61e-03
2022-05-13 20:45:18,971 INFO [train.py:812] (4/8) Epoch 1, batch 4350, loss[loss=0.1893, simple_loss=0.3472, pruned_loss=0.1573, over 7432.00 frames.], tot_loss[loss=0.1881, simple_loss=0.3463, pruned_loss=0.1568, over 1426742.24 frames.], batch size: 20, lr: 2.61e-03
2022-05-13 20:46:18,354 INFO [train.py:812] (4/8) Epoch 1, batch 4400, loss[loss=0.1697, simple_loss=0.3136, pruned_loss=0.1293, over 7265.00 frames.], tot_loss[loss=0.1881, simple_loss=0.3466, pruned_loss=0.1539, over 1424218.74 frames.], batch size: 18, lr: 2.60e-03
2022-05-13 20:47:17,295 INFO [train.py:812] (4/8) Epoch 1, batch 4450, loss[loss=0.1786, simple_loss=0.3309, pruned_loss=0.132, over 7431.00 frames.], tot_loss[loss=0.1883, simple_loss=0.3473, pruned_loss=0.1513, over 1423641.74 frames.], batch size: 20, lr: 2.59e-03
2022-05-13 20:48:16,740 INFO [train.py:812] (4/8) Epoch 1, batch 4500, loss[loss=0.2188, simple_loss=0.4012, pruned_loss=0.1822, over 6773.00 frames.], tot_loss[loss=0.1882, simple_loss=0.3472, pruned_loss=0.1492, over 1413795.13 frames.], batch size: 38, lr: 2.59e-03
2022-05-13 20:49:13,805 INFO [train.py:812] (4/8) Epoch 1, batch 4550, loss[loss=0.1977, simple_loss=0.3622, pruned_loss=0.1657, over 5137.00 frames.], tot_loss[loss=0.1895, simple_loss=0.3496, pruned_loss=0.1503, over 1395368.92 frames.], batch size: 52, lr: 2.58e-03
2022-05-13 20:50:25,946 INFO [train.py:812] (4/8) Epoch 2, batch 0, loss[loss=0.1981, simple_loss=0.3622, pruned_loss=0.1695, over 7139.00 frames.], tot_loss[loss=0.1981, simple_loss=0.3622, pruned_loss=0.1695, over 7139.00 frames.], batch size: 26, lr: 2.56e-03
2022-05-13 20:51:25,844 INFO [train.py:812] (4/8) Epoch 2, batch 50, loss[loss=0.1701, simple_loss=0.3185, pruned_loss=0.1084, over 7228.00 frames.], tot_loss[loss=0.1822, simple_loss=0.3376, pruned_loss=0.1339, over 311111.01 frames.], batch size: 20, lr: 2.55e-03
2022-05-13 20:52:24,857 INFO [train.py:812] (4/8) Epoch 2, batch 100, loss[loss=0.1928, simple_loss=0.3532, pruned_loss=0.1618, over 7433.00 frames.], tot_loss[loss=0.1825, simple_loss=0.3381, pruned_loss=0.1341, over 558745.00 frames.], batch size: 20, lr: 2.54e-03
2022-05-13 20:53:23,906 INFO [train.py:812] (4/8) Epoch 2, batch 150, loss[loss=0.1771, simple_loss=0.3301, pruned_loss=0.1207, over 7330.00 frames.], tot_loss[loss=0.1815, simple_loss=0.3364, pruned_loss=0.1332, over 749423.20 frames.], batch size: 20, lr: 2.54e-03
2022-05-13 20:54:21,310 INFO [train.py:812] (4/8) Epoch 2, batch 200, loss[loss=0.1772, simple_loss=0.3281, pruned_loss=0.1312, over 7161.00 frames.], tot_loss[loss=0.1809, simple_loss=0.3355, pruned_loss=0.1319, over 899402.64 frames.], batch size: 19, lr: 2.53e-03
2022-05-13 20:55:19,837 INFO [train.py:812] (4/8) Epoch 2, batch 250, loss[loss=0.1912, simple_loss=0.3566, pruned_loss=0.1291, over 7377.00 frames.], tot_loss[loss=0.1811, simple_loss=0.336, pruned_loss=0.1313, over 1014649.31 frames.], batch size: 23, lr: 2.53e-03
2022-05-13 20:56:18,135 INFO [train.py:812] (4/8) Epoch 2, batch 300, loss[loss=0.1832, simple_loss=0.3404, pruned_loss=0.1305, over 7251.00 frames.], tot_loss[loss=0.1818, simple_loss=0.3372, pruned_loss=0.1314, over 1104050.87 frames.], batch size: 19, lr: 2.52e-03
2022-05-13 20:57:16,226 INFO [train.py:812] (4/8) Epoch 2, batch 350, loss[loss=0.1711, simple_loss=0.3191, pruned_loss=0.1151, over 7218.00 frames.], tot_loss[loss=0.1813, simple_loss=0.3364, pruned_loss=0.1309, over 1173207.63 frames.], batch size: 21, lr: 2.51e-03
2022-05-13 20:58:14,758 INFO [train.py:812] (4/8) Epoch 2, batch 400, loss[loss=0.1965, simple_loss=0.3639, pruned_loss=0.1453, over 7145.00 frames.], tot_loss[loss=0.1814, simple_loss=0.3366, pruned_loss=0.131, over 1229849.51 frames.], batch size: 20, lr: 2.51e-03
2022-05-13 20:59:13,909 INFO [train.py:812] (4/8) Epoch 2, batch 450, loss[loss=0.1689, simple_loss=0.315, pruned_loss=0.1142, over 7169.00 frames.], tot_loss[loss=0.1807, simple_loss=0.3355, pruned_loss=0.129, over 1275148.48 frames.], batch size: 19, lr: 2.50e-03
2022-05-13 21:00:12,350 INFO [train.py:812] (4/8) Epoch 2, batch 500, loss[loss=0.1634, simple_loss=0.3033, pruned_loss=0.118, over 7160.00 frames.], tot_loss[loss=0.1799, simple_loss=0.3343, pruned_loss=0.1277, over 1307416.14 frames.], batch size: 18, lr: 2.49e-03
2022-05-13 21:01:12,114 INFO [train.py:812] (4/8) Epoch 2, batch 550, loss[loss=0.1691, simple_loss=0.3147, pruned_loss=0.117, over 7355.00 frames.], tot_loss[loss=0.18, simple_loss=0.3343, pruned_loss=0.1281, over 1332158.96 frames.], batch size: 19, lr: 2.49e-03
2022-05-13 21:02:10,000 INFO [train.py:812] (4/8) Epoch 2, batch 600, loss[loss=0.1862, simple_loss=0.3473, pruned_loss=0.1258, over 7379.00 frames.], tot_loss[loss=0.1801, simple_loss=0.3347, pruned_loss=0.1274, over 1352902.84 frames.], batch size: 23, lr: 2.48e-03
2022-05-13 21:03:08,995 INFO [train.py:812] (4/8) Epoch 2, batch 650, loss[loss=0.1715, simple_loss=0.3193, pruned_loss=0.1188, over 7283.00 frames.], tot_loss[loss=0.1807, simple_loss=0.3357, pruned_loss=0.1285, over 1367414.22 frames.], batch size: 18, lr: 2.48e-03
2022-05-13 21:04:08,349 INFO [train.py:812] (4/8) Epoch 2, batch 700, loss[loss=0.2235, simple_loss=0.4047, pruned_loss=0.2116, over 4987.00 frames.], tot_loss[loss=0.1803, simple_loss=0.335, pruned_loss=0.1279, over 1379554.33 frames.], batch size: 52, lr: 2.47e-03
2022-05-13 21:05:07,225 INFO [train.py:812] (4/8) Epoch 2, batch 750, loss[loss=0.1994, simple_loss=0.3648, pruned_loss=0.1699, over 7251.00 frames.], tot_loss[loss=0.1803, simple_loss=0.3352, pruned_loss=0.1271, over 1391192.98 frames.], batch size: 19, lr: 2.46e-03
2022-05-13 21:06:06,467 INFO [train.py:812] (4/8) Epoch 2, batch 800, loss[loss=0.178, simple_loss=0.3301, pruned_loss=0.1291, over 7453.00 frames.], tot_loss[loss=0.179, simple_loss=0.3329, pruned_loss=0.1249, over 1401124.59 frames.], batch size: 19, lr: 2.46e-03
2022-05-13 21:07:06,090 INFO [train.py:812] (4/8) Epoch 2, batch 850, loss[loss=0.1839, simple_loss=0.3417, pruned_loss=0.1305, over 7323.00 frames.], tot_loss[loss=0.1781, simple_loss=0.3313, pruned_loss=0.1241, over 1408349.72 frames.], batch size: 20, lr: 2.45e-03
2022-05-13 21:08:05,124 INFO [train.py:812] (4/8) Epoch 2, batch 900, loss[loss=0.1696, simple_loss=0.3162, pruned_loss=0.1153, over 7436.00 frames.], tot_loss[loss=0.1781, simple_loss=0.3314, pruned_loss=0.1242, over 1412655.65 frames.], batch size: 20, lr: 2.45e-03
2022-05-13 21:09:04,128 INFO [train.py:812] (4/8) Epoch 2, batch 950, loss[loss=0.1602, simple_loss=0.3015, pruned_loss=0.09488, over 7260.00 frames.], tot_loss[loss=0.1785, simple_loss=0.3321, pruned_loss=0.1249, over 1415146.16 frames.], batch size: 19, lr: 2.44e-03
2022-05-13 21:10:02,106 INFO [train.py:812] (4/8) Epoch 2, batch 1000, loss[loss=0.1843, simple_loss=0.3408, pruned_loss=0.1392, over 6752.00 frames.], tot_loss[loss=0.1779, simple_loss=0.3311, pruned_loss=0.1237, over 1416392.47 frames.], batch size: 31, lr: 2.43e-03
2022-05-13 21:11:00,259 INFO [train.py:812] (4/8) Epoch 2, batch 1050, loss[loss=0.1821, simple_loss=0.3374, pruned_loss=0.1337, over 7424.00 frames.], tot_loss[loss=0.178, simple_loss=0.3312, pruned_loss=0.1241, over 1418256.37 frames.], batch size: 20, lr: 2.43e-03
2022-05-13 21:11:59,255 INFO [train.py:812] (4/8) Epoch 2, batch 1100, loss[loss=0.1649, simple_loss=0.308, pruned_loss=0.109, over 7161.00 frames.], tot_loss[loss=0.1781, simple_loss=0.3316, pruned_loss=0.1236, over 1420120.83 frames.], batch size: 18, lr: 2.42e-03
2022-05-13 21:12:57,575 INFO [train.py:812] (4/8) Epoch 2, batch 1150, loss[loss=0.1704, simple_loss=0.3183, pruned_loss=0.1131, over 7229.00 frames.], tot_loss[loss=0.1775, simple_loss=0.3305, pruned_loss=0.1227, over 1423776.37 frames.], batch size: 20, lr: 2.41e-03
2022-05-13 21:13:56,176 INFO [train.py:812] (4/8) Epoch 2, batch 1200, loss[loss=0.1907, simple_loss=0.3568, pruned_loss=0.123, over 7037.00 frames.], tot_loss[loss=0.1779, simple_loss=0.3311, pruned_loss=0.1232, over 1423052.42 frames.], batch size: 28, lr: 2.41e-03
2022-05-13 21:14:54,777 INFO [train.py:812] (4/8) Epoch 2, batch 1250, loss[loss=0.1588, simple_loss=0.2977, pruned_loss=0.09935, over 7283.00 frames.], tot_loss[loss=0.1782, simple_loss=0.3317, pruned_loss=0.1236, over 1424088.22 frames.], batch size: 18, lr: 2.40e-03
2022-05-13 21:15:53,348 INFO [train.py:812] (4/8) Epoch 2, batch 1300, loss[loss=0.1867, simple_loss=0.3473, pruned_loss=0.1308, over 7219.00 frames.], tot_loss[loss=0.178, simple_loss=0.3313, pruned_loss=0.1233, over 1417768.83 frames.], batch size: 21, lr: 2.40e-03
2022-05-13 21:16:52,358 INFO [train.py:812] (4/8) Epoch 2, batch 1350, loss[loss=0.1627, simple_loss=0.3035, pruned_loss=0.1093, over 7286.00 frames.], tot_loss[loss=0.1769, simple_loss=0.3296, pruned_loss=0.1214, over 1420656.68 frames.], batch size: 17, lr: 2.39e-03
2022-05-13 21:17:49,938 INFO [train.py:812] (4/8) Epoch 2, batch 1400, loss[loss=0.175, simple_loss=0.3301, pruned_loss=0.09967, over 7230.00 frames.], tot_loss[loss=0.1772, simple_loss=0.3301, pruned_loss=0.1218, over 1419279.77 frames.], batch size: 21, lr: 2.39e-03
2022-05-13 21:18:49,273 INFO [train.py:812] (4/8) Epoch 2, batch 1450, loss[loss=0.3322, simple_loss=0.3625, pruned_loss=0.1509, over 7176.00 frames.], tot_loss[loss=0.2012, simple_loss=0.3322, pruned_loss=0.1243, over 1422972.88 frames.], batch size: 26, lr: 2.38e-03
2022-05-13 21:19:47,678 INFO [train.py:812] (4/8) Epoch 2, batch 1500, loss[loss=0.3282, simple_loss=0.3727, pruned_loss=0.1418, over 6397.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3352, pruned_loss=0.1263, over 1422008.46 frames.], batch size: 38, lr: 2.37e-03
2022-05-13 21:20:45,894 INFO [train.py:812] (4/8) Epoch 2, batch 1550, loss[loss=0.268, simple_loss=0.3169, pruned_loss=0.1095, over 7419.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3352, pruned_loss=0.1249, over 1425357.12 frames.], batch size: 20, lr: 2.37e-03
2022-05-13 21:21:43,118 INFO [train.py:812] (4/8) Epoch 2, batch 1600, loss[loss=0.2558, simple_loss=0.3005, pruned_loss=0.1055, over 7161.00 frames.], tot_loss[loss=0.2467, simple_loss=0.3327, pruned_loss=0.1224, over 1424094.76 frames.], batch size: 18, lr: 2.36e-03
2022-05-13 21:22:41,923 INFO [train.py:812] (4/8) Epoch 2, batch 1650, loss[loss=0.2808, simple_loss=0.3387, pruned_loss=0.1114, over 7441.00 frames.], tot_loss[loss=0.2551, simple_loss=0.333, pruned_loss=0.1213, over 1424806.70 frames.], batch size: 20, lr: 2.36e-03
2022-05-13 21:23:40,003 INFO [train.py:812] (4/8) Epoch 2, batch 1700, loss[loss=0.3276, simple_loss=0.3687, pruned_loss=0.1432, over 7415.00 frames.], tot_loss[loss=0.2611, simple_loss=0.3327, pruned_loss=0.1202, over 1424348.15 frames.], batch size: 21, lr: 2.35e-03
2022-05-13 21:24:38,975 INFO [train.py:812] (4/8) Epoch 2, batch 1750, loss[loss=0.2579, simple_loss=0.3025, pruned_loss=0.1067, over 7277.00 frames.], tot_loss[loss=0.2671, simple_loss=0.3337, pruned_loss=0.1201, over 1424277.23 frames.], batch size: 18, lr: 2.34e-03
2022-05-13 21:25:38,307 INFO [train.py:812] (4/8) Epoch 2, batch 1800, loss[loss=0.2553, simple_loss=0.318, pruned_loss=0.09635, over 7354.00 frames.], tot_loss[loss=0.2694, simple_loss=0.3329, pruned_loss=0.1184, over 1425199.88 frames.], batch size: 19, lr: 2.34e-03
2022-05-13 21:26:37,483 INFO [train.py:812] (4/8) Epoch 2, batch 1850, loss[loss=0.2329, simple_loss=0.3123, pruned_loss=0.07679, over 7325.00 frames.], tot_loss[loss=0.2706, simple_loss=0.3314, pruned_loss=0.1169, over 1425571.85 frames.], batch size: 20, lr: 2.33e-03
2022-05-13 21:27:35,691 INFO [train.py:812] (4/8) Epoch 2, batch 1900, loss[loss=0.2255, simple_loss=0.2855, pruned_loss=0.08278, over 6992.00 frames.], tot_loss[loss=0.2722, simple_loss=0.3321, pruned_loss=0.1155, over 1429679.74 frames.], batch size: 16, lr: 2.33e-03
2022-05-13 21:28:33,669 INFO [train.py:812] (4/8) Epoch 2, batch 1950, loss[loss=0.2158, simple_loss=0.2805, pruned_loss=0.07557, over 7295.00 frames.], tot_loss[loss=0.275, simple_loss=0.3334, pruned_loss=0.1155, over 1430151.98 frames.], batch size: 18, lr: 2.32e-03
2022-05-13 21:29:31,795 INFO [train.py:812] (4/8) Epoch 2, batch 2000, loss[loss=0.2914, simple_loss=0.3529, pruned_loss=0.115, over 7122.00 frames.], tot_loss[loss=0.2778, simple_loss=0.335, pruned_loss=0.1159, over 1424222.39 frames.], batch size: 21, lr: 2.32e-03
2022-05-13 21:30:31,552 INFO [train.py:812] (4/8) Epoch 2, batch 2050, loss[loss=0.3262, simple_loss=0.3645, pruned_loss=0.1439, over 7061.00 frames.], tot_loss[loss=0.2768, simple_loss=0.3335, pruned_loss=0.1145, over 1424530.07 frames.], batch size: 28, lr: 2.31e-03
2022-05-13 21:31:31,051 INFO [train.py:812] (4/8) Epoch 2, batch 2100, loss[loss=0.2744, simple_loss=0.3284, pruned_loss=0.1102, over 7427.00 frames.], tot_loss[loss=0.2763, simple_loss=0.3331, pruned_loss=0.1132, over 1424928.42 frames.], batch size: 18, lr: 2.31e-03
2022-05-13 21:32:30,572 INFO [train.py:812] (4/8) Epoch 2, batch 2150, loss[loss=0.2948, simple_loss=0.3567, pruned_loss=0.1164, over 7411.00 frames.], tot_loss[loss=0.2766, simple_loss=0.3328, pruned_loss=0.1128, over 1423461.21 frames.], batch size: 21, lr: 2.30e-03
2022-05-13 21:33:29,449 INFO [train.py:812] (4/8) Epoch 2, batch 2200, loss[loss=0.2695, simple_loss=0.3323, pruned_loss=0.1033, over 7110.00 frames.], tot_loss[loss=0.2756, simple_loss=0.332, pruned_loss=0.1117, over 1423141.72 frames.], batch size: 21, lr: 2.29e-03
2022-05-13 21:34:29,305 INFO [train.py:812] (4/8) Epoch 2, batch 2250, loss[loss=0.2765, simple_loss=0.3365, pruned_loss=0.1082, over 7225.00 frames.], tot_loss[loss=0.2751, simple_loss=0.3315, pruned_loss=0.111, over 1424382.65 frames.], batch size: 21, lr: 2.29e-03
2022-05-13 21:35:27,782 INFO [train.py:812] (4/8) Epoch 2, batch 2300, loss[loss=0.2622, simple_loss=0.3226, pruned_loss=0.1009, over 7197.00 frames.], tot_loss[loss=0.2748, simple_loss=0.3312, pruned_loss=0.1105, over 1424844.15 frames.], batch size: 22, lr: 2.28e-03
2022-05-13 21:36:26,831 INFO [train.py:812] (4/8) Epoch 2, batch 2350, loss[loss=0.3273, simple_loss=0.3803, pruned_loss=0.1372, over 7232.00 frames.], tot_loss[loss=0.2768, simple_loss=0.3329, pruned_loss=0.1113, over 1422951.37 frames.], batch size: 20, lr: 2.28e-03
2022-05-13 21:37:24,981 INFO [train.py:812] (4/8) Epoch 2, batch 2400, loss[loss=0.2921, simple_loss=0.353, pruned_loss=0.1156, over 7313.00 frames.], tot_loss[loss=0.276, simple_loss=0.3323, pruned_loss=0.1106, over 1423566.94 frames.], batch size: 21, lr: 2.27e-03
2022-05-13 21:38:23,793 INFO [train.py:812] (4/8) Epoch 2, batch 2450, loss[loss=0.2511, simple_loss=0.3186, pruned_loss=0.09182, over 7319.00 frames.], tot_loss[loss=0.2752, simple_loss=0.3318, pruned_loss=0.1099, over 1426930.59 frames.], batch size: 21, lr: 2.27e-03
2022-05-13 21:39:23,283 INFO [train.py:812] (4/8) Epoch 2, batch 2500, loss[loss=0.35, simple_loss=0.3957, pruned_loss=0.1522, over 7167.00 frames.], tot_loss[loss=0.2759, simple_loss=0.3325, pruned_loss=0.11, over 1427277.04 frames.], batch size: 26, lr: 2.26e-03
2022-05-13 21:40:21,940 INFO [train.py:812] (4/8) Epoch 2, batch 2550, loss[loss=0.2732, simple_loss=0.3187, pruned_loss=0.1139, over 7414.00 frames.], tot_loss[loss=0.2769, simple_loss=0.3333, pruned_loss=0.1106, over 1427792.39 frames.], batch size: 17, lr: 2.26e-03
2022-05-13 21:41:21,070 INFO [train.py:812] (4/8) Epoch 2, batch 2600, loss[loss=0.2919, simple_loss=0.347, pruned_loss=0.1183, over 7187.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3305, pruned_loss=0.1085, over 1429148.76 frames.], batch size: 26, lr: 2.25e-03
2022-05-13 21:42:20,634 INFO [train.py:812] (4/8) Epoch 2, batch 2650, loss[loss=0.3301, simple_loss=0.3667, pruned_loss=0.1467, over 6349.00 frames.], tot_loss[loss=0.2727, simple_loss=0.3296, pruned_loss=0.1081, over 1427897.57 frames.], batch size: 38, lr: 2.25e-03
2022-05-13 21:43:18,324 INFO [train.py:812] (4/8) Epoch 2, batch 2700, loss[loss=0.3422, simple_loss=0.3905, pruned_loss=0.1469, over 6952.00 frames.], tot_loss[loss=0.2712, simple_loss=0.3287, pruned_loss=0.107, over 1427360.67 frames.], batch size: 32, lr: 2.24e-03
2022-05-13 21:44:17,963 INFO [train.py:812] (4/8) Epoch 2, batch 2750, loss[loss=0.2722, simple_loss=0.3306, pruned_loss=0.1069, over 7279.00 frames.], tot_loss[loss=0.2716, simple_loss=0.329, pruned_loss=0.1072, over 1423427.14 frames.], batch size: 24, lr: 2.24e-03
2022-05-13 21:45:15,695 INFO [train.py:812] (4/8) Epoch 2, batch 2800, loss[loss=0.255, simple_loss=0.3244, pruned_loss=0.09276, over 7191.00 frames.], tot_loss[loss=0.2715, simple_loss=0.3291, pruned_loss=0.1071, over 1426955.57 frames.], batch size: 23, lr: 2.23e-03
2022-05-13 21:46:14,855 INFO [train.py:812] (4/8) Epoch 2, batch 2850, loss[loss=0.2914, simple_loss=0.3443, pruned_loss=0.1192, over 7284.00 frames.], tot_loss[loss=0.2705, simple_loss=0.3286, pruned_loss=0.1063, over 1426058.91 frames.], batch size: 24, lr: 2.23e-03
2022-05-13 21:47:13,481 INFO [train.py:812] (4/8) Epoch 2, batch 2900, loss[loss=0.3403, simple_loss=0.3779, pruned_loss=0.1513, over 7232.00 frames.], tot_loss[loss=0.2711, simple_loss=0.3292, pruned_loss=0.1066, over 1420994.45 frames.], batch size: 20, lr: 2.22e-03
2022-05-13 21:48:11,748 INFO [train.py:812] (4/8) Epoch 2, batch 2950, loss[loss=0.3186, simple_loss=0.3696, pruned_loss=0.1338, over 7244.00 frames.], tot_loss[loss=0.27, simple_loss=0.3285, pruned_loss=0.1058, over 1421978.42 frames.], batch size: 20, lr: 2.22e-03
2022-05-13 21:49:10,841 INFO [train.py:812] (4/8) Epoch 2, batch 3000, loss[loss=0.2677, simple_loss=0.3027, pruned_loss=0.1163, over 7263.00 frames.], tot_loss[loss=0.2686, simple_loss=0.3273, pruned_loss=0.105, over 1426515.54 frames.], batch size: 17, lr: 2.21e-03
2022-05-13 21:49:10,842 INFO [train.py:832] (4/8) Computing validation loss
2022-05-13 21:49:18,580 INFO [train.py:841] (4/8) Epoch 2, validation: loss=0.2016, simple_loss=0.2977, pruned_loss=0.0527, over 698248.00 frames.
2022-05-13 21:50:17,422 INFO [train.py:812] (4/8) Epoch 2, batch 3050, loss[loss=0.2484, simple_loss=0.3002, pruned_loss=0.09831, over 7279.00 frames.], tot_loss[loss=0.2688, simple_loss=0.3277, pruned_loss=0.105, over 1421789.58 frames.], batch size: 18, lr: 2.20e-03
2022-05-13 21:51:15,123 INFO [train.py:812] (4/8) Epoch 2, batch 3100, loss[loss=0.3728, simple_loss=0.3891, pruned_loss=0.1782, over 4842.00 frames.], tot_loss[loss=0.268, simple_loss=0.3271, pruned_loss=0.1045, over 1420939.33 frames.], batch size: 53, lr: 2.20e-03
2022-05-13 21:52:13,942 INFO [train.py:812] (4/8) Epoch 2, batch 3150, loss[loss=0.2371, simple_loss=0.2835, pruned_loss=0.09535, over 6790.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3268, pruned_loss=0.1043, over 1423338.22 frames.], batch size: 15, lr: 2.19e-03
2022-05-13 21:53:13,039 INFO [train.py:812] (4/8) Epoch 2, batch 3200, loss[loss=0.3622, simple_loss=0.3948, pruned_loss=0.1648, over 4915.00 frames.], tot_loss[loss=0.27, simple_loss=0.3286, pruned_loss=0.1057, over 1412818.79 frames.], batch size: 52, lr: 2.19e-03
2022-05-13 21:54:12,613 INFO [train.py:812] (4/8) Epoch 2, batch 3250, loss[loss=0.2466, simple_loss=0.3133, pruned_loss=0.08993, over 7199.00 frames.], tot_loss[loss=0.27, simple_loss=0.3289, pruned_loss=0.1055, over 1415692.45 frames.], batch size: 23, lr: 2.18e-03
2022-05-13 21:55:12,231 INFO [train.py:812] (4/8) Epoch 2, batch 3300, loss[loss=0.2858, simple_loss=0.3416, pruned_loss=0.115, over 7205.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3269, pruned_loss=0.1039, over 1420431.52 frames.], batch size: 22, lr: 2.18e-03
2022-05-13 21:56:11,982 INFO [train.py:812] (4/8) Epoch 2, batch 3350, loss[loss=0.2701, simple_loss=0.3323, pruned_loss=0.1039, over 7196.00 frames.], tot_loss[loss=0.2688, simple_loss=0.3285, pruned_loss=0.1046, over 1422867.90 frames.], batch size: 26, lr: 2.18e-03
2022-05-13 21:57:11,186 INFO [train.py:812] (4/8) Epoch 2, batch 3400, loss[loss=0.2183, simple_loss=0.2794, pruned_loss=0.0786, over 7148.00 frames.], tot_loss[loss=0.2674, simple_loss=0.327, pruned_loss=0.1039, over 1424706.44 frames.], batch size: 17, lr: 2.17e-03
2022-05-13 21:58:14,493 INFO [train.py:812] (4/8) Epoch 2, batch 3450, loss[loss=0.3451, simple_loss=0.4042, pruned_loss=0.143, over 7262.00 frames.], tot_loss[loss=0.2687, simple_loss=0.328, pruned_loss=0.1047, over 1426583.63 frames.], batch size: 24, lr: 2.17e-03
2022-05-13 21:59:13,382 INFO [train.py:812] (4/8) Epoch 2, batch 3500, loss[loss=0.2939, simple_loss=0.356, pruned_loss=0.1159, over 6356.00 frames.], tot_loss[loss=0.269, simple_loss=0.3285, pruned_loss=0.1048, over 1423495.59 frames.], batch size: 37, lr: 2.16e-03
2022-05-13 22:00:12,697 INFO [train.py:812] (4/8) Epoch 2, batch 3550, loss[loss=0.3074, simple_loss=0.3679, pruned_loss=0.1234, over 7264.00 frames.], tot_loss[loss=0.2684, simple_loss=0.3286, pruned_loss=0.1041, over 1423600.87 frames.], batch size: 25, lr: 2.16e-03
2022-05-13 22:01:11,598 INFO [train.py:812] (4/8) Epoch 2, batch 3600, loss[loss=0.2503, simple_loss=0.3172, pruned_loss=0.09166, over 7223.00 frames.], tot_loss[loss=0.2682, simple_loss=0.3287, pruned_loss=0.1038, over 1425019.05 frames.], batch size: 20, lr: 2.15e-03
2022-05-13 22:02:11,439 INFO [train.py:812] (4/8) Epoch 2, batch 3650, loss[loss=0.2839, simple_loss=0.3359, pruned_loss=0.1159, over 6813.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3277, pruned_loss=0.1031, over 1427057.33 frames.], batch size: 15, lr: 2.15e-03
2022-05-13 22:03:10,448 INFO [train.py:812] (4/8) Epoch 2, batch 3700, loss[loss=0.2562, simple_loss=0.3122, pruned_loss=0.1001, over 7172.00 frames.], tot_loss[loss=0.2673, simple_loss=0.3284, pruned_loss=0.1031, over 1429562.97 frames.], batch size: 19, lr: 2.14e-03
2022-05-13 22:04:09,802 INFO [train.py:812] (4/8) Epoch 2, batch 3750, loss[loss=0.2931, simple_loss=0.3538, pruned_loss=0.1162, over 7260.00 frames.], tot_loss[loss=0.2671, simple_loss=0.3282, pruned_loss=0.103, over 1430086.75 frames.], batch size: 24, lr: 2.14e-03
2022-05-13 22:05:09,270 INFO [train.py:812] (4/8) Epoch 2, batch 3800, loss[loss=0.2598, simple_loss=0.3151, pruned_loss=0.1022, over 6777.00 frames.], tot_loss[loss=0.2673, simple_loss=0.3279, pruned_loss=0.1033, over 1428719.39 frames.], batch size: 15, lr: 2.13e-03
2022-05-13 22:06:07,966 INFO [train.py:812] (4/8) Epoch 2, batch 3850, loss[loss=0.2781, simple_loss=0.338, pruned_loss=0.1091, over 7173.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3285, pruned_loss=0.103, over 1430853.67 frames.], batch size: 26, lr: 2.13e-03
2022-05-13 22:07:06,188 INFO [train.py:812] (4/8) Epoch 2, batch 3900, loss[loss=0.2486, simple_loss=0.3204, pruned_loss=0.0884, over 7268.00 frames.], tot_loss[loss=0.2655, simple_loss=0.3272, pruned_loss=0.1019, over 1430735.33 frames.], batch size: 24, lr: 2.12e-03
2022-05-13 22:08:05,669 INFO [train.py:812] (4/8) Epoch 2, batch 3950, loss[loss=0.2816, simple_loss=0.3498, pruned_loss=0.1067, over 7110.00 frames.], tot_loss[loss=0.2647, simple_loss=0.3266, pruned_loss=0.1013, over 1428397.34 frames.], batch size: 21, lr: 2.12e-03
2022-05-13 22:09:04,770 INFO [train.py:812] (4/8) Epoch 2, batch 4000, loss[loss=0.3071, simple_loss=0.3523, pruned_loss=0.131, over 7201.00 frames.], tot_loss[loss=0.2635, simple_loss=0.3257, pruned_loss=0.1007, over 1428410.95 frames.], batch size: 22, lr: 2.11e-03
2022-05-13 22:10:02,678 INFO [train.py:812] (4/8) Epoch 2, batch 4050, loss[loss=0.3302, simple_loss=0.3886, pruned_loss=0.1359, over 6868.00 frames.], tot_loss[loss=0.2637, simple_loss=0.326, pruned_loss=0.1007, over 1426767.59 frames.], batch size: 31, lr: 2.11e-03
2022-05-13 22:11:01,216 INFO [train.py:812] (4/8) Epoch 2, batch 4100, loss[loss=0.266, simple_loss=0.3262, pruned_loss=0.1028, over 7218.00 frames.], tot_loss[loss=0.2651, simple_loss=0.3266, pruned_loss=0.1018, over 1421436.87 frames.], batch size: 21, lr: 2.10e-03
2022-05-13 22:11:59,878 INFO [train.py:812] (4/8) Epoch 2, batch 4150, loss[loss=0.2466, simple_loss=0.3156, pruned_loss=0.08881, over 6834.00 frames.], tot_loss[loss=0.2635, simple_loss=0.3254, pruned_loss=0.1008, over 1420593.59 frames.], batch size: 31, lr: 2.10e-03
2022-05-13 22:12:58,522 INFO [train.py:812] (4/8) Epoch 2, batch 4200, loss[loss=0.2357, simple_loss=0.2955, pruned_loss=0.08793, over 7267.00 frames.], tot_loss[loss=0.2623, simple_loss=0.3243, pruned_loss=0.1002, over 1419004.71 frames.], batch size: 18, lr: 2.10e-03
2022-05-13 22:13:58,094 INFO [train.py:812] (4/8) Epoch 2, batch 4250, loss[loss=0.2113, simple_loss=0.2896, pruned_loss=0.06648, over 7270.00 frames.], tot_loss[loss=0.263, simple_loss=0.3246, pruned_loss=0.1008, over 1414640.92 frames.], batch size: 18, lr: 2.09e-03
2022-05-13 22:14:56,718 INFO [train.py:812] (4/8) Epoch 2, batch 4300, loss[loss=0.2565, simple_loss=0.3318, pruned_loss=0.0906, over 7305.00 frames.], tot_loss[loss=0.264, simple_loss=0.3254, pruned_loss=0.1013, over 1414213.04 frames.], batch size: 25, lr: 2.09e-03
2022-05-13 22:15:55,432 INFO [train.py:812] (4/8) Epoch 2, batch 4350, loss[loss=0.2035, simple_loss=0.2714, pruned_loss=0.06776, over 6981.00 frames.], tot_loss[loss=0.2641, simple_loss=0.3262, pruned_loss=0.101, over 1414456.37 frames.], batch size: 16, lr: 2.08e-03
2022-05-13 22:16:54,205 INFO [train.py:812] (4/8) Epoch 2, batch 4400, loss[loss=0.235, simple_loss=0.3188, pruned_loss=0.0756, over 7317.00 frames.], tot_loss[loss=0.2639, simple_loss=0.326, pruned_loss=0.1009, over 1408764.18 frames.], batch size: 21, lr: 2.08e-03
2022-05-13 22:17:52,726 INFO [train.py:812] (4/8) Epoch 2, batch 4450, loss[loss=0.2797, simple_loss=0.3425, pruned_loss=0.1084, over 6527.00 frames.], tot_loss[loss=0.2647, simple_loss=0.3266, pruned_loss=0.1014, over 1401013.63 frames.], batch size: 38, lr: 2.07e-03
2022-05-13 22:18:50,560 INFO [train.py:812] (4/8) Epoch 2, batch 4500, loss[loss=0.248, simple_loss=0.3123, pruned_loss=0.09183, over 6478.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3251, pruned_loss=0.1007, over 1387501.74 frames.], batch size: 38, lr: 2.07e-03
2022-05-13 22:19:49,231 INFO [train.py:812] (4/8) Epoch 2, batch 4550, loss[loss=0.3471, simple_loss=0.3786, pruned_loss=0.1578, over 4915.00 frames.], tot_loss[loss=0.2676, simple_loss=0.3284, pruned_loss=0.1034, over 1356133.70 frames.], batch size: 52, lr: 2.06e-03
2022-05-13 22:20:58,922 INFO [train.py:812] (4/8) Epoch 3, batch 0, loss[loss=0.2288, simple_loss=0.2863, pruned_loss=0.08567, over 7287.00 frames.], tot_loss[loss=0.2288, simple_loss=0.2863, pruned_loss=0.08567, over 7287.00 frames.], batch size: 17, lr: 2.02e-03
2022-05-13 22:21:58,063 INFO [train.py:812] (4/8) Epoch 3, batch 50, loss[loss=0.2774, simple_loss=0.3393, pruned_loss=0.1078, over 7296.00 frames.], tot_loss[loss=0.2609, simple_loss=0.3226, pruned_loss=0.09962, over 322271.71 frames.], batch size: 25, lr: 2.02e-03
2022-05-13 22:22:56,169 INFO [train.py:812] (4/8) Epoch 3, batch 100, loss[loss=0.2523, simple_loss=0.3064, pruned_loss=0.09911, over 6994.00 frames.], tot_loss[loss=0.2569, simple_loss=0.3213, pruned_loss=0.09622, over 569489.37 frames.], batch size: 16, lr: 2.01e-03
2022-05-13 22:23:56,095 INFO [train.py:812] (4/8) Epoch 3, batch 150, loss[loss=0.2776, simple_loss=0.3386, pruned_loss=0.1083, over 6790.00 frames.], tot_loss[loss=0.2554, simple_loss=0.3202, pruned_loss=0.09527, over 761811.99 frames.], batch size: 31, lr: 2.01e-03
2022-05-13 22:24:53,586 INFO [train.py:812] (4/8) Epoch 3, batch 200, loss[loss=0.2165, simple_loss=0.2764, pruned_loss=0.07832, over 6859.00 frames.], tot_loss[loss=0.2552, simple_loss=0.3198, pruned_loss=0.09528, over 901325.86 frames.], batch size: 15, lr: 2.00e-03
2022-05-13 22:25:53,020 INFO [train.py:812] (4/8) Epoch 3, batch 250, loss[loss=0.2501, simple_loss=0.3224, pruned_loss=0.08892, over 7353.00 frames.], tot_loss[loss=0.2565, simple_loss=0.3213, pruned_loss=0.09586, over 1011702.63 frames.], batch size: 19, lr: 2.00e-03
2022-05-13 22:26:52,125 INFO [train.py:812] (4/8) Epoch 3, batch 300, loss[loss=0.2888, simple_loss=0.3427, pruned_loss=0.1175, over 6803.00 frames.], tot_loss[loss=0.2571, simple_loss=0.3225, pruned_loss=0.09585, over 1101894.40 frames.], batch size: 32, lr: 2.00e-03
2022-05-13 22:27:51,981 INFO [train.py:812] (4/8) Epoch 3, batch 350, loss[loss=0.2431, simple_loss=0.3189, pruned_loss=0.08369, over 7323.00 frames.], tot_loss[loss=0.2568, simple_loss=0.3222, pruned_loss=0.09565, over 1171638.02 frames.], batch size: 21, lr: 1.99e-03
2022-05-13 22:29:00,806 INFO [train.py:812] (4/8) Epoch 3, batch 400, loss[loss=0.2379, simple_loss=0.3164, pruned_loss=0.07965, over 7295.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3229, pruned_loss=0.09668, over 1222395.41 frames.], batch size: 24, lr: 1.99e-03
2022-05-13 22:29:59,468 INFO [train.py:812] (4/8) Epoch 3, batch 450, loss[loss=0.2861, simple_loss=0.3492, pruned_loss=0.1115, over 7219.00 frames.], tot_loss[loss=0.2569, simple_loss=0.3222, pruned_loss=0.0958, over 1262931.41 frames.], batch size: 22, lr: 1.98e-03
2022-05-13 22:31:07,392 INFO [train.py:812] (4/8) Epoch 3, batch 500, loss[loss=0.1914, simple_loss=0.2607, pruned_loss=0.06102, over 6987.00 frames.], tot_loss[loss=0.2554, simple_loss=0.321, pruned_loss=0.0949, over 1301305.72 frames.], batch size: 16, lr: 1.98e-03
2022-05-13 22:32:54,332 INFO [train.py:812] (4/8) Epoch 3, batch 550, loss[loss=0.2142, simple_loss=0.2933, pruned_loss=0.0676, over 7224.00 frames.], tot_loss[loss=0.2539, simple_loss=0.3204, pruned_loss=0.0937, over 1331443.09 frames.], batch size: 21, lr: 1.98e-03
2022-05-13 22:34:03,099 INFO [train.py:812] (4/8) Epoch 3, batch 600, loss[loss=0.3001, simple_loss=0.3743, pruned_loss=0.113, over 7283.00 frames.], tot_loss[loss=0.2548, simple_loss=0.3209, pruned_loss=0.09435, over 1351839.68 frames.], batch size: 25, lr: 1.97e-03
2022-05-13 22:35:02,667 INFO [train.py:812] (4/8) Epoch 3, batch 650, loss[loss=0.2762, simple_loss=0.3334, pruned_loss=0.1096, over 7362.00 frames.], tot_loss[loss=0.2543, simple_loss=0.3202, pruned_loss=0.0942, over 1367254.58 frames.], batch size: 19, lr: 1.97e-03
2022-05-13 22:36:02,058 INFO [train.py:812] (4/8) Epoch 3, batch 700, loss[loss=0.2721, simple_loss=0.3384, pruned_loss=0.1029, over 7221.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3195, pruned_loss=0.09352, over 1378036.25 frames.], batch size: 21, lr: 1.96e-03
2022-05-13 22:37:01,823 INFO [train.py:812] (4/8) Epoch 3, batch 750, loss[loss=0.2938, simple_loss=0.3522, pruned_loss=0.1177, over 7187.00 frames.], tot_loss[loss=0.2524, simple_loss=0.3189, pruned_loss=0.093, over 1391086.31 frames.], batch size: 23, lr: 1.96e-03
2022-05-13 22:38:00,549 INFO [train.py:812] (4/8) Epoch 3, batch 800, loss[loss=0.2423, simple_loss=0.3224, pruned_loss=0.08109, over 7197.00 frames.], tot_loss[loss=0.2531, simple_loss=0.3193, pruned_loss=0.0934, over 1402244.57 frames.], batch size: 23, lr: 1.96e-03
2022-05-13 22:38:59,715 INFO [train.py:812] (4/8) Epoch 3, batch 850, loss[loss=0.2446, simple_loss=0.3132, pruned_loss=0.08798, over 7321.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3187, pruned_loss=0.09311, over 1410370.80 frames.], batch size: 25, lr: 1.95e-03
2022-05-13 22:39:58,498 INFO [train.py:812] (4/8) Epoch 3, batch 900, loss[loss=0.2525, simple_loss=0.3095, pruned_loss=0.09776, over 7058.00 frames.], tot_loss[loss=0.2536, simple_loss=0.32, pruned_loss=0.0936, over 1412196.48 frames.], batch size: 18, lr: 1.95e-03
2022-05-13 22:40:58,635 INFO [train.py:812] (4/8) Epoch 3, batch 950, loss[loss=0.2372, simple_loss=0.3106, pruned_loss=0.08188, over 7149.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3192, pruned_loss=0.09314, over 1417068.20 frames.], batch size: 20, lr: 1.94e-03
2022-05-13 22:41:58,343 INFO [train.py:812] (4/8) Epoch 3, batch 1000, loss[loss=0.2688, simple_loss=0.3317, pruned_loss=0.1029, over 6813.00 frames.], tot_loss[loss=0.2523, simple_loss=0.3189, pruned_loss=0.09286, over 1416396.16 frames.], batch size: 31, lr: 1.94e-03
2022-05-13 22:42:57,498 INFO [train.py:812] (4/8) Epoch 3, batch 1050, loss[loss=0.1823, simple_loss=0.2559, pruned_loss=0.0544, over 7268.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3182, pruned_loss=0.09277, over 1414550.47 frames.], batch size: 18, lr: 1.94e-03
2022-05-13 22:43:56,790 INFO [train.py:812] (4/8) Epoch 3, batch 1100, loss[loss=0.2836, simple_loss=0.3527, pruned_loss=0.1073, over 7221.00 frames.], tot_loss[loss=0.2534, simple_loss=0.32, pruned_loss=0.09342, over 1419594.69 frames.], batch size: 21, lr: 1.93e-03
2022-05-13 22:44:56,337 INFO [train.py:812] (4/8) Epoch 3, batch 1150, loss[loss=0.2551, simple_loss=0.3293, pruned_loss=0.09047, over 7239.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3184, pruned_loss=0.09256, over 1420812.64 frames.], batch size: 20, lr: 1.93e-03
2022-05-13 22:45:54,824 INFO [train.py:812] (4/8) Epoch 3, batch 1200, loss[loss=0.2193, simple_loss=0.2952, pruned_loss=0.07176, over 7442.00 frames.], tot_loss[loss=0.2528, simple_loss=0.3193, pruned_loss=0.09318, over 1424117.38 frames.], batch size: 20, lr: 1.93e-03
2022-05-13 22:46:52,756 INFO [train.py:812] (4/8) Epoch 3, batch 1250, loss[loss=0.2618, simple_loss=0.3288, pruned_loss=0.09746, over 7423.00 frames.], tot_loss[loss=0.252, simple_loss=0.3183, pruned_loss=0.09285, over 1424367.59 frames.], batch size: 21, lr: 1.92e-03
2022-05-13 22:47:52,036 INFO [train.py:812] (4/8) Epoch 3, batch 1300, loss[loss=0.2423, simple_loss=0.3282, pruned_loss=0.07825, over 7323.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3174, pruned_loss=0.09204, over 1425938.31 frames.], batch size: 21, lr: 1.92e-03
2022-05-13 22:48:50,082 INFO [train.py:812] (4/8) Epoch 3, batch 1350, loss[loss=0.2423, simple_loss=0.3201, pruned_loss=0.0822, over 7440.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3184, pruned_loss=0.09203, over 1425723.94 frames.], batch size: 20, lr: 1.91e-03
2022-05-13 22:49:48,133 INFO [train.py:812] (4/8) Epoch 3, batch 1400, loss[loss=0.2048, simple_loss=0.2814, pruned_loss=0.06415, over 7172.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3178, pruned_loss=0.09132, over 1422936.23 frames.], batch size: 19, lr: 1.91e-03
2022-05-13 22:50:48,086 INFO [train.py:812] (4/8) Epoch 3, batch 1450, loss[loss=0.217, simple_loss=0.2772, pruned_loss=0.07847, over 7135.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3182, pruned_loss=0.09207, over 1419927.88 frames.], batch size: 17, lr: 1.91e-03
2022-05-13 22:51:46,937 INFO [train.py:812] (4/8) Epoch 3, batch 1500, loss[loss=0.2642, simple_loss=0.331, pruned_loss=0.09865, over 7308.00 frames.], tot_loss[loss=0.2514, simple_loss=0.318, pruned_loss=0.0924, over 1418146.42 frames.], batch size: 21, lr: 1.90e-03
2022-05-13 22:52:47,275 INFO [train.py:812] (4/8) Epoch 3, batch 1550, loss[loss=0.2578, simple_loss=0.329, pruned_loss=0.09325, over 7175.00 frames.], tot_loss[loss=0.2507, simple_loss=0.318, pruned_loss=0.09176, over 1422297.69 frames.], batch size: 19, lr: 1.90e-03
2022-05-13 22:53:45,773 INFO [train.py:812] (4/8) Epoch 3, batch 1600, loss[loss=0.2261, simple_loss=0.2917, pruned_loss=0.08029, over 7153.00 frames.], tot_loss[loss=0.2496, simple_loss=0.3171, pruned_loss=0.09103, over 1425333.48 frames.], batch size: 19, lr: 1.90e-03
2022-05-13 22:54:44,633 INFO [train.py:812] (4/8) Epoch 3, batch 1650, loss[loss=0.2597, simple_loss=0.3221, pruned_loss=0.09868, over 7430.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3173, pruned_loss=0.09123, over 1427155.09 frames.], batch size: 20, lr: 1.89e-03
2022-05-13 22:55:42,299 INFO [train.py:812] (4/8) Epoch 3, batch 1700, loss[loss=0.2395, simple_loss=0.3187, pruned_loss=0.08015, over 7135.00 frames.], tot_loss[loss=0.2513, simple_loss=0.3182, pruned_loss=0.0922, over 1418425.68 frames.], batch size: 20, lr: 1.89e-03
2022-05-13 22:56:41,867 INFO [train.py:812] (4/8) Epoch 3, batch 1750, loss[loss=0.2011, simple_loss=0.283, pruned_loss=0.05958, over 7229.00 frames.], tot_loss[loss=0.2496, simple_loss=0.3172, pruned_loss=0.09102, over 1425192.55 frames.], batch size: 20, lr: 1.88e-03
2022-05-13 22:57:40,293 INFO [train.py:812] (4/8) Epoch 3, batch 1800, loss[loss=0.289, simple_loss=0.3438, pruned_loss=0.1171, over 7110.00 frames.], tot_loss[loss=0.2495, simple_loss=0.317, pruned_loss=0.09105, over 1417331.21 frames.], batch size: 21, lr: 1.88e-03
2022-05-13 22:58:39,760 INFO [train.py:812] (4/8) Epoch 3, batch 1850, loss[loss=0.2767, simple_loss=0.3411, pruned_loss=0.1061, over 7407.00 frames.], tot_loss[loss=0.2493, simple_loss=0.3168, pruned_loss=0.0909, over 1418292.14 frames.], batch size: 21, lr: 1.88e-03
2022-05-13 22:59:38,876 INFO [train.py:812] (4/8) Epoch 3, batch 1900, loss[loss=0.2399, simple_loss=0.3045, pruned_loss=0.08764, over 7166.00 frames.], tot_loss[loss=0.2496, simple_loss=0.317, pruned_loss=0.09114, over 1415680.08 frames.], batch size: 18, lr: 1.87e-03
2022-05-13 23:00:38,434 INFO [train.py:812] (4/8) Epoch 3, batch 1950, loss[loss=0.3139, simple_loss=0.3704, pruned_loss=0.1287, over 6698.00 frames.], tot_loss[loss=0.2473, simple_loss=0.3148, pruned_loss=0.0899, over 1416831.13 frames.], batch size: 31, lr: 1.87e-03
2022-05-13 23:01:37,606 INFO [train.py:812] (4/8) Epoch 3, batch 2000, loss[loss=0.2518, simple_loss=0.3184, pruned_loss=0.09263, over 7138.00 frames.], tot_loss[loss=0.2454, simple_loss=0.3134, pruned_loss=0.08865, over 1421513.37 frames.], batch size: 19, lr: 1.87e-03
2022-05-13 23:02:36,935 INFO [train.py:812] (4/8) Epoch 3, batch 2050, loss[loss=0.276, simple_loss=0.3378, pruned_loss=0.1071, over 5221.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3146, pruned_loss=0.08892, over 1421850.31 frames.], batch size: 52, lr: 1.86e-03
2022-05-13 23:03:35,453 INFO [train.py:812] (4/8) Epoch 3, batch 2100, loss[loss=0.2455, simple_loss=0.3258, pruned_loss=0.08265, over 7324.00 frames.], tot_loss[loss=0.2468, simple_loss=0.3153, pruned_loss=0.08919, over 1424981.66 frames.], batch size: 21, lr: 1.86e-03
2022-05-13 23:04:34,070 INFO [train.py:812] (4/8) Epoch 3, batch 2150, loss[loss=0.2576, simple_loss=0.3282, pruned_loss=0.09347, over 7242.00 frames.], tot_loss[loss=0.2451, simple_loss=0.3139, pruned_loss=0.08815, over 1426702.05 frames.], batch size: 20, lr: 1.86e-03
2022-05-13 23:05:32,770 INFO [train.py:812] (4/8) Epoch 3, batch 2200, loss[loss=0.2551, simple_loss=0.3227, pruned_loss=0.09376, over 7138.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3146, pruned_loss=0.08903, over 1426044.83 frames.], batch size: 20, lr: 1.85e-03
2022-05-13 23:06:32,198 INFO [train.py:812] (4/8) Epoch 3, batch 2250, loss[loss=0.2601, simple_loss=0.3196, pruned_loss=0.1003, over 7330.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3161, pruned_loss=0.08952, over 1426402.31 frames.], batch size: 20, lr: 1.85e-03
2022-05-13 23:07:31,573 INFO [train.py:812] (4/8) Epoch 3, batch 2300, loss[loss=0.2096, simple_loss=0.2816, pruned_loss=0.06884, over 7356.00 frames.], tot_loss[loss=0.2477, simple_loss=0.3157, pruned_loss=0.0899, over 1413372.43 frames.], batch size: 19, lr: 1.85e-03
2022-05-13 23:08:31,272 INFO [train.py:812] (4/8) Epoch 3, batch 2350, loss[loss=0.2379, simple_loss=0.3046, pruned_loss=0.08554, over 7252.00 frames.], tot_loss[loss=0.247, simple_loss=0.3154, pruned_loss=0.08932, over 1414539.01 frames.], batch size: 19, lr: 1.84e-03
2022-05-13 23:09:29,613 INFO [train.py:812] (4/8) Epoch 3, batch 2400, loss[loss=0.2617, simple_loss=0.3201, pruned_loss=0.1016, over 7260.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3169, pruned_loss=0.09043, over 1417752.62 frames.], batch size: 19, lr: 1.84e-03
2022-05-13 23:10:29,111 INFO [train.py:812] (4/8) Epoch 3, batch 2450, loss[loss=0.2894, simple_loss=0.359, pruned_loss=0.1099, over 7241.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3177, pruned_loss=0.09086, over 1415744.92 frames.], batch size: 20, lr: 1.84e-03
2022-05-13 23:11:28,076 INFO [train.py:812] (4/8) Epoch 3, batch 2500, loss[loss=0.275, simple_loss=0.3427, pruned_loss=0.1036, over 7159.00 frames.], tot_loss[loss=0.2488, simple_loss=0.317, pruned_loss=0.09028, over 1414307.28 frames.], batch size: 19, lr: 1.83e-03
2022-05-13 23:12:27,746 INFO [train.py:812] (4/8) Epoch 3, batch 2550, loss[loss=0.2421, simple_loss=0.3254, pruned_loss=0.07937, over 7214.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3163, pruned_loss=0.09035, over 1413024.01 frames.], batch size: 21, lr: 1.83e-03
2022-05-13 23:13:27,070 INFO [train.py:812] (4/8) Epoch 3, batch 2600, loss[loss=0.1962, simple_loss=0.271, pruned_loss=0.06067, over 7279.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3148, pruned_loss=0.0892, over 1419475.15 frames.], batch size: 18, lr: 1.83e-03
2022-05-13 23:14:26,421 INFO [train.py:812] (4/8) Epoch 3, batch 2650, loss[loss=0.2532, simple_loss=0.3209, pruned_loss=0.09272, over 7334.00 frames.], tot_loss[loss=0.2457, simple_loss=0.314, pruned_loss=0.08869, over 1418837.91 frames.], batch size: 20, lr: 1.82e-03
2022-05-13 23:15:24,402 INFO [train.py:812] (4/8) Epoch 3, batch 2700, loss[loss=0.1823, simple_loss=0.2574, pruned_loss=0.05359, over 7067.00 frames.], tot_loss[loss=0.2454, simple_loss=0.3139, pruned_loss=0.08849, over 1419339.95 frames.], batch size: 18, lr: 1.82e-03
2022-05-13 23:16:23,939 INFO [train.py:812] (4/8) Epoch 3, batch 2750, loss[loss=0.3263, simple_loss=0.3843, pruned_loss=0.1342, over 7151.00 frames.], tot_loss[loss=0.2448, simple_loss=0.3136, pruned_loss=0.08799, over 1418224.19 frames.], batch size: 26, lr: 1.82e-03
2022-05-13 23:17:22,908 INFO [train.py:812] (4/8) Epoch 3, batch 2800, loss[loss=0.3439, simple_loss=0.3812, pruned_loss=0.1533, over 5100.00 frames.], tot_loss[loss=0.2456, simple_loss=0.314, pruned_loss=0.08858, over 1418475.11 frames.], batch size: 52, lr: 1.81e-03
2022-05-13 23:18:30,778 INFO [train.py:812] (4/8) Epoch 3, batch 2850, loss[loss=0.2702, simple_loss=0.3413, pruned_loss=0.09959, over 7219.00 frames.], tot_loss[loss=0.2455, simple_loss=0.314, pruned_loss=0.08845, over 1420332.18 frames.], batch size: 21, lr: 1.81e-03
2022-05-13 23:19:29,907 INFO [train.py:812] (4/8) Epoch 3, batch 2900, loss[loss=0.3043, simple_loss=0.3596, pruned_loss=0.1245, over 6412.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3136, pruned_loss=0.08812, over 1417376.13 frames.], batch size: 38, lr: 1.81e-03
2022-05-13 23:20:29,311 INFO [train.py:812] (4/8) Epoch 3, batch 2950, loss[loss=0.2732, simple_loss=0.3321, pruned_loss=0.1071, over 7153.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3136, pruned_loss=0.08796, over 1416682.73 frames.], batch size: 26, lr: 1.80e-03
2022-05-13 23:21:28,545 INFO [train.py:812] (4/8) Epoch 3, batch 3000, loss[loss=0.2207, simple_loss=0.3004, pruned_loss=0.07055, over 7339.00 frames.], tot_loss[loss=0.2443, simple_loss=0.313, pruned_loss=0.08777, over 1420110.18 frames.], batch size: 22, lr: 1.80e-03
2022-05-13 23:21:28,547 INFO [train.py:832] (4/8) Computing validation loss
2022-05-13 23:21:36,069 INFO [train.py:841] (4/8) Epoch 3, validation: loss=0.1862, simple_loss=0.2867, pruned_loss=0.04278, over 698248.00 frames.
2022-05-13 23:22:33,844 INFO [train.py:812] (4/8) Epoch 3, batch 3050, loss[loss=0.26, simple_loss=0.3245, pruned_loss=0.09772, over 7409.00 frames.], tot_loss[loss=0.2442, simple_loss=0.3132, pruned_loss=0.08756, over 1425365.23 frames.], batch size: 21, lr: 1.80e-03
2022-05-13 23:23:30,790 INFO [train.py:812] (4/8) Epoch 3, batch 3100, loss[loss=0.236, simple_loss=0.3013, pruned_loss=0.08533, over 7290.00 frames.], tot_loss[loss=0.2428, simple_loss=0.312, pruned_loss=0.08679, over 1428166.20 frames.], batch size: 18, lr: 1.79e-03
2022-05-13 23:24:30,030 INFO [train.py:812] (4/8) Epoch 3, batch 3150, loss[loss=0.2248, simple_loss=0.3076, pruned_loss=0.07095, over 7228.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3111, pruned_loss=0.08652, over 1421926.22 frames.], batch size: 21, lr: 1.79e-03
2022-05-13 23:25:29,453 INFO [train.py:812] (4/8) Epoch 3, batch 3200, loss[loss=0.2559, simple_loss=0.3334, pruned_loss=0.08916, over 7379.00 frames.], tot_loss[loss=0.2425, simple_loss=0.3114, pruned_loss=0.08675, over 1424506.85 frames.], batch size: 23, lr: 1.79e-03
2022-05-13 23:26:29,122 INFO [train.py:812] (4/8) Epoch 3, batch 3250, loss[loss=0.2013, simple_loss=0.2778, pruned_loss=0.06237, over 7153.00 frames.], tot_loss[loss=0.2414, simple_loss=0.311, pruned_loss=0.08586, over 1425250.91 frames.], batch size: 19, lr: 1.79e-03
2022-05-13 23:27:27,205 INFO [train.py:812] (4/8) Epoch 3, batch 3300, loss[loss=0.2552, simple_loss=0.3279, pruned_loss=0.09123, over 7211.00 frames.], tot_loss[loss=0.2397, simple_loss=0.31, pruned_loss=0.08466, over 1427936.72 frames.], batch size: 26, lr: 1.78e-03
2022-05-13 23:28:26,180 INFO [train.py:812] (4/8) Epoch 3, batch 3350, loss[loss=0.2172, simple_loss=0.285, pruned_loss=0.07466, over 7288.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3115, pruned_loss=0.0859, over 1425090.46 frames.], batch size: 18, lr: 1.78e-03
2022-05-13 23:29:23,906 INFO [train.py:812] (4/8) Epoch 3, batch 3400, loss[loss=0.222, simple_loss=0.284, pruned_loss=0.07998, over 7414.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3127, pruned_loss=0.08658, over 1422623.80 frames.], batch size: 18, lr: 1.78e-03
2022-05-13 23:30:22,231 INFO [train.py:812] (4/8) Epoch 3, batch 3450, loss[loss=0.2231, simple_loss=0.2955, pruned_loss=0.07533, over 7274.00 frames.], tot_loss[loss=0.2427, simple_loss=0.3126, pruned_loss=0.08638, over 1420320.33 frames.], batch size: 19, lr: 1.77e-03
2022-05-13 23:31:20,922 INFO [train.py:812] (4/8) Epoch 3, batch 3500, loss[loss=0.2464, simple_loss=0.3177, pruned_loss=0.08753, over 7333.00 frames.], tot_loss[loss=0.2409, simple_loss=0.3112, pruned_loss=0.08526, over 1421091.69 frames.], batch size: 25, lr: 1.77e-03
2022-05-13 23:32:20,547 INFO [train.py:812] (4/8) Epoch 3, batch 3550, loss[loss=0.2597, simple_loss=0.3239, pruned_loss=0.0977, over 7223.00 frames.], tot_loss[loss=0.243, simple_loss=0.313, pruned_loss=0.08651, over 1420294.93 frames.], batch size: 21, lr: 1.77e-03
2022-05-13 23:33:19,836 INFO [train.py:812] (4/8) Epoch 3, batch 3600, loss[loss=0.2145, simple_loss=0.2968, pruned_loss=0.06614, over 7290.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3107, pruned_loss=0.08534, over 1421192.52 frames.], batch size: 24, lr: 1.76e-03
2022-05-13 23:34:19,474 INFO [train.py:812] (4/8) Epoch 3, batch 3650, loss[loss=0.3095, simple_loss=0.3509, pruned_loss=0.134, over 7383.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3101, pruned_loss=0.0854, over 1421748.94 frames.], batch size: 23, lr: 1.76e-03
2022-05-13 23:35:18,555 INFO [train.py:812] (4/8) Epoch 3, batch 3700, loss[loss=0.2211, simple_loss=0.2805, pruned_loss=0.08083, over 7411.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3098, pruned_loss=0.08484, over 1416893.43 frames.], batch size: 18, lr: 1.76e-03
2022-05-13 23:36:18,208 INFO [train.py:812] (4/8) Epoch 3, batch 3750, loss[loss=0.1964, simple_loss=0.2699, pruned_loss=0.06147, over 7277.00 frames.], tot_loss[loss=0.2396, simple_loss=0.3096, pruned_loss=0.08476, over 1422807.04 frames.], batch size: 18, lr: 1.76e-03
2022-05-13 23:37:16,799 INFO [train.py:812] (4/8) Epoch 3, batch 3800, loss[loss=0.2088, simple_loss=0.2817, pruned_loss=0.06797, over 7167.00 frames.], tot_loss[loss=0.2391, simple_loss=0.309, pruned_loss=0.08461, over 1423535.64 frames.], batch size: 18, lr: 1.75e-03
2022-05-13 23:38:16,206 INFO [train.py:812] (4/8) Epoch 3, batch 3850, loss[loss=0.2508, simple_loss=0.3197, pruned_loss=0.09092, over 7339.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3095, pruned_loss=0.08506, over 1422411.99 frames.], batch size: 22, lr: 1.75e-03
2022-05-13 23:39:15,480 INFO [train.py:812] (4/8) Epoch 3, batch 3900, loss[loss=0.2054, simple_loss=0.2869, pruned_loss=0.06192, over 7338.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3086, pruned_loss=0.08418, over 1423957.48 frames.], batch size: 20, lr: 1.75e-03
2022-05-13 23:40:14,819 INFO [train.py:812] (4/8) Epoch 3, batch 3950, loss[loss=0.2788, simple_loss=0.3475, pruned_loss=0.1051, over 7318.00 frames.], tot_loss[loss=0.2396, simple_loss=0.3093, pruned_loss=0.0849, over 1421121.46 frames.], batch size: 21, lr: 1.74e-03
2022-05-13 23:41:13,968 INFO [train.py:812] (4/8) Epoch 3, batch 4000, loss[loss=0.2351, simple_loss=0.307, pruned_loss=0.08155, over 7348.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3095, pruned_loss=0.08443, over 1425432.80 frames.], batch size: 22, lr: 1.74e-03
2022-05-13 23:42:13,690 INFO [train.py:812] (4/8) Epoch 3, batch 4050, loss[loss=0.2915, simple_loss=0.3668, pruned_loss=0.1081, over 7439.00 frames.], tot_loss[loss=0.2384, simple_loss=0.309, pruned_loss=0.08389, over 1426310.74 frames.], batch size: 20, lr: 1.74e-03
2022-05-13 23:43:12,788 INFO [train.py:812] (4/8) Epoch 3, batch 4100, loss[loss=0.2481, simple_loss=0.3102, pruned_loss=0.09304, over 7059.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3103, pruned_loss=0.0846, over 1416153.05 frames.], batch size: 18, lr: 1.73e-03
2022-05-13 23:44:12,470 INFO [train.py:812] (4/8) Epoch 3, batch 4150, loss[loss=0.2526, simple_loss=0.3202, pruned_loss=0.09252, over 7123.00 frames.], tot_loss[loss=0.2396, simple_loss=0.3102, pruned_loss=0.08448, over 1420980.54 frames.], batch size: 21, lr: 1.73e-03
2022-05-13 23:45:10,719 INFO [train.py:812] (4/8) Epoch 3, batch 4200, loss[loss=0.2824, simple_loss=0.3446, pruned_loss=0.1101, over 7123.00 frames.], tot_loss[loss=0.2402, simple_loss=0.311, pruned_loss=0.08473, over 1420607.40 frames.], batch size: 28, lr: 1.73e-03
2022-05-13 23:46:09,933 INFO [train.py:812] (4/8) Epoch 3, batch 4250, loss[loss=0.2707, simple_loss=0.3409, pruned_loss=0.1003, over 7199.00 frames.], tot_loss[loss=0.2397, simple_loss=0.3105, pruned_loss=0.08445, over 1422150.42 frames.], batch size: 22, lr: 1.73e-03
2022-05-13 23:47:09,074 INFO [train.py:812] (4/8) Epoch 3, batch 4300, loss[loss=0.2105, simple_loss=0.2787, pruned_loss=0.07122, over 7069.00 frames.], tot_loss[loss=0.2403, simple_loss=0.311, pruned_loss=0.08484, over 1423876.15 frames.], batch size: 18, lr: 1.72e-03
2022-05-13 23:48:08,220 INFO [train.py:812] (4/8) Epoch 3, batch 4350, loss[loss=0.2358, simple_loss=0.3099, pruned_loss=0.08084, over 7161.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3112, pruned_loss=0.08505, over 1425744.31 frames.], batch size: 20, lr: 1.72e-03
2022-05-13 23:49:06,724 INFO [train.py:812] (4/8) Epoch 3, batch 4400, loss[loss=0.272, simple_loss=0.3473, pruned_loss=0.09833, over 7290.00 frames.], tot_loss[loss=0.2408, simple_loss=0.3111, pruned_loss=0.08525, over 1419623.94 frames.], batch size: 25, lr: 1.72e-03
2022-05-13 23:50:05,677 INFO [train.py:812] (4/8) Epoch 3, batch 4450, loss[loss=0.2153, simple_loss=0.3004, pruned_loss=0.06506, over 7332.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3129, pruned_loss=0.086, over 1411830.42 frames.], batch size: 22, lr: 1.71e-03
2022-05-13 23:51:04,264 INFO [train.py:812] (4/8) Epoch 3, batch 4500, loss[loss=0.263, simple_loss=0.3205, pruned_loss=0.1027, over 7104.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3129, pruned_loss=0.08583, over 1406736.17 frames.], batch size: 21, lr: 1.71e-03
2022-05-13 23:52:01,826 INFO [train.py:812] (4/8) Epoch 3, batch 4550, loss[loss=0.2484, simple_loss=0.3153, pruned_loss=0.09072, over 6438.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3158, pruned_loss=0.0876, over 1378432.97 frames.], batch size: 38, lr: 1.71e-03
2022-05-13 23:53:11,489 INFO [train.py:812] (4/8) Epoch 4, batch 0, loss[loss=0.297, simple_loss=0.3652, pruned_loss=0.1144, over 7200.00 frames.], tot_loss[loss=0.297, simple_loss=0.3652, pruned_loss=0.1144, over 7200.00 frames.], batch size: 23, lr: 1.66e-03
2022-05-13 23:54:10,709 INFO [train.py:812] (4/8) Epoch 4, batch 50, loss[loss=0.1856, simple_loss=0.2644, pruned_loss=0.05345, over 7283.00 frames.], tot_loss[loss=0.2299, simple_loss=0.3031, pruned_loss=0.07835, over 318688.55 frames.], batch size: 17, lr: 1.66e-03
2022-05-13 23:55:09,424 INFO [train.py:812] (4/8) Epoch 4, batch 100, loss[loss=0.2125, simple_loss=0.2838, pruned_loss=0.07058, over 7277.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3032, pruned_loss=0.07932, over 566218.81 frames.], batch size: 17, lr: 1.65e-03
2022-05-13 23:56:09,348 INFO [train.py:812] (4/8) Epoch 4, batch 150, loss[loss=0.2876, simple_loss=0.3535, pruned_loss=0.1108, over 7333.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3059, pruned_loss=0.08158, over 756783.10 frames.], batch size: 22, lr: 1.65e-03
2022-05-13 23:57:08,454 INFO [train.py:812] (4/8) Epoch 4, batch 200, loss[loss=0.2404, simple_loss=0.3211, pruned_loss=0.07989, over 7192.00 frames.], tot_loss[loss=0.2347, simple_loss=0.3063, pruned_loss=0.08152, over 905723.39 frames.], batch size: 23, lr: 1.65e-03
2022-05-13 23:58:07,158 INFO [train.py:812] (4/8) Epoch 4, batch 250, loss[loss=0.2069, simple_loss=0.2905, pruned_loss=0.06166, over 7329.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3075, pruned_loss=0.08155, over 1017513.99 frames.], batch size: 22, lr: 1.64e-03
2022-05-13 23:59:06,610 INFO [train.py:812] (4/8) Epoch 4, batch 300, loss[loss=0.2489, simple_loss=0.3336, pruned_loss=0.0821, over 7384.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3069, pruned_loss=0.08087, over 1111429.99 frames.], batch size: 23, lr: 1.64e-03
2022-05-14 00:00:06,133 INFO [train.py:812] (4/8) Epoch 4, batch 350, loss[loss=0.2521, simple_loss=0.332, pruned_loss=0.0861, over 7321.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3061, pruned_loss=0.08008, over 1182706.96 frames.], batch size: 21, lr: 1.64e-03
2022-05-14 00:01:05,124 INFO [train.py:812] (4/8) Epoch 4, batch 400, loss[loss=0.2463, simple_loss=0.3226, pruned_loss=0.08496, over 7229.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3052, pruned_loss=0.08003, over 1233162.08 frames.], batch size: 20, lr: 1.64e-03
2022-05-14 00:02:04,522 INFO [train.py:812] (4/8) Epoch 4, batch 450, loss[loss=0.258, simple_loss=0.3301, pruned_loss=0.09294, over 7145.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3055, pruned_loss=0.08036, over 1275117.20 frames.], batch size: 20, lr: 1.63e-03
2022-05-14 00:03:03,232 INFO [train.py:812] (4/8) Epoch 4, batch 500, loss[loss=0.2224, simple_loss=0.2944, pruned_loss=0.07526, over 7159.00 frames.], tot_loss[loss=0.2355, simple_loss=0.308, pruned_loss=0.08153, over 1304003.90 frames.], batch size: 19, lr: 1.63e-03
2022-05-14 00:04:02,748 INFO [train.py:812] (4/8) Epoch 4, batch 550, loss[loss=0.2274, simple_loss=0.2937, pruned_loss=0.08051, over 7152.00 frames.], tot_loss[loss=0.234, simple_loss=0.307, pruned_loss=0.08046, over 1329808.86 frames.], batch size: 18, lr: 1.63e-03
2022-05-14 00:05:01,391 INFO [train.py:812] (4/8) Epoch 4, batch 600, loss[loss=0.267, simple_loss=0.338, pruned_loss=0.09796, over 6468.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3068, pruned_loss=0.08091, over 1347853.90 frames.], batch size: 38, lr: 1.63e-03
2022-05-14 00:06:00,851 INFO [train.py:812] (4/8) Epoch 4, batch 650, loss[loss=0.229, simple_loss=0.3114, pruned_loss=0.07329, over 7435.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3058, pruned_loss=0.0798, over 1368200.43 frames.], batch size: 20, lr: 1.62e-03
2022-05-14 00:07:00,184 INFO [train.py:812] (4/8) Epoch 4, batch 700, loss[loss=0.2288, simple_loss=0.31, pruned_loss=0.07374, over 7304.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3042, pruned_loss=0.07877, over 1385978.34 frames.], batch size: 24, lr: 1.62e-03
2022-05-14 00:07:59,211 INFO [train.py:812] (4/8) Epoch 4, batch 750, loss[loss=0.2789, simple_loss=0.342, pruned_loss=0.108, over 7282.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3042, pruned_loss=0.07924, over 1393675.05 frames.], batch size: 24, lr: 1.62e-03
2022-05-14 00:08:58,476 INFO [train.py:812] (4/8) Epoch 4, batch 800, loss[loss=0.2359, simple_loss=0.321, pruned_loss=0.07544, over 7259.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3052, pruned_loss=0.0797, over 1397567.33 frames.], batch size: 19, lr: 1.62e-03
2022-05-14 00:09:58,459 INFO [train.py:812] (4/8) Epoch 4, batch 850, loss[loss=0.2674, simple_loss=0.3242, pruned_loss=0.1053, over 7062.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3064, pruned_loss=0.08004, over 1407199.60 frames.], batch size: 18, lr: 1.61e-03
2022-05-14 00:10:57,743 INFO [train.py:812] (4/8) Epoch 4, batch 900, loss[loss=0.2497, simple_loss=0.3345, pruned_loss=0.08246, over 7121.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3055, pruned_loss=0.07948, over 1414777.67 frames.], batch size: 21, lr: 1.61e-03
2022-05-14 00:11:56,764 INFO [train.py:812] (4/8) Epoch 4, batch 950, loss[loss=0.2731, simple_loss=0.3417, pruned_loss=0.1022, over 7155.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3058, pruned_loss=0.07997, over 1419640.19 frames.], batch size: 26, lr: 1.61e-03
2022-05-14 00:12:55,425 INFO [train.py:812] (4/8) Epoch 4, batch 1000, loss[loss=0.2318, simple_loss=0.3065, pruned_loss=0.07854, over 7274.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3052, pruned_loss=0.07992, over 1420243.53 frames.], batch size: 18, lr: 1.61e-03
2022-05-14 00:13:54,501 INFO [train.py:812] (4/8) Epoch 4, batch 1050, loss[loss=0.2564, simple_loss=0.3324, pruned_loss=0.09018, over 6607.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3051, pruned_loss=0.07954, over 1419238.54 frames.], batch size: 31, lr: 1.60e-03
2022-05-14 00:14:53,494 INFO [train.py:812] (4/8) Epoch 4, batch 1100, loss[loss=0.2343, simple_loss=0.3146, pruned_loss=0.07699, over 7418.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3053, pruned_loss=0.08005, over 1420434.53 frames.], batch size: 21, lr: 1.60e-03
2022-05-14 00:15:52,720 INFO [train.py:812] (4/8) Epoch 4, batch 1150, loss[loss=0.2231, simple_loss=0.3125, pruned_loss=0.06689, over 7310.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3062, pruned_loss=0.07962, over 1417029.03 frames.], batch size: 21, lr: 1.60e-03
2022-05-14 00:16:51,394 INFO [train.py:812] (4/8) Epoch 4, batch 1200, loss[loss=0.2346, simple_loss=0.3156, pruned_loss=0.07681, over 7325.00 frames.], tot_loss[loss=0.233, simple_loss=0.3067, pruned_loss=0.07962, over 1414464.29 frames.], batch size: 21, lr: 1.60e-03
2022-05-14 00:17:50,408 INFO [train.py:812] (4/8) Epoch 4, batch 1250, loss[loss=0.1786, simple_loss=0.2524, pruned_loss=0.05235, over 6835.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3064, pruned_loss=0.07929, over 1412181.30 frames.], batch size: 15, lr: 1.59e-03
2022-05-14 00:18:48,735 INFO [train.py:812] (4/8) Epoch 4, batch 1300, loss[loss=0.3006, simple_loss=0.3561, pruned_loss=0.1226, over 7204.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3054, pruned_loss=0.07896, over 1416385.34 frames.], batch size: 23, lr: 1.59e-03
2022-05-14 00:19:47,570 INFO [train.py:812] (4/8) Epoch 4, batch 1350, loss[loss=0.2555, simple_loss=0.3374, pruned_loss=0.08687, over 7241.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3061, pruned_loss=0.07969, over 1416518.23 frames.], batch size: 20, lr: 1.59e-03
2022-05-14 00:20:44,852 INFO [train.py:812] (4/8) Epoch 4, batch 1400, loss[loss=0.2351, simple_loss=0.3013, pruned_loss=0.08442, over 7191.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3058, pruned_loss=0.08014, over 1419924.22 frames.], batch size: 22, lr: 1.59e-03
2022-05-14 00:21:44,658 INFO [train.py:812] (4/8) Epoch 4, batch 1450, loss[loss=0.2604, simple_loss=0.3235, pruned_loss=0.09869, over 7299.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3066, pruned_loss=0.08001, over 1421963.47 frames.], batch size: 24, lr: 1.59e-03
2022-05-14 00:22:43,716 INFO [train.py:812] (4/8) Epoch 4, batch 1500, loss[loss=0.2625, simple_loss=0.3371, pruned_loss=0.09391, over 7302.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3075, pruned_loss=0.08061, over 1418887.98 frames.], batch size: 24, lr: 1.58e-03
2022-05-14 00:23:43,453 INFO [train.py:812] (4/8) Epoch 4, batch 1550, loss[loss=0.3289, simple_loss=0.3745, pruned_loss=0.1416, over 5299.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3069, pruned_loss=0.08117, over 1417982.03 frames.], batch size: 53, lr: 1.58e-03
2022-05-14 00:24:41,302 INFO [train.py:812] (4/8) Epoch 4, batch 1600, loss[loss=0.227, simple_loss=0.3119, pruned_loss=0.07104, over 7302.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3074, pruned_loss=0.08113, over 1414400.58 frames.], batch size: 25, lr: 1.58e-03
2022-05-14 00:25:40,741 INFO [train.py:812] (4/8) Epoch 4, batch 1650, loss[loss=0.1887, simple_loss=0.2771, pruned_loss=0.05012, over 7325.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3057, pruned_loss=0.08025, over 1416350.31 frames.], batch size: 20, lr: 1.58e-03
2022-05-14 00:26:39,532 INFO [train.py:812] (4/8) Epoch 4, batch 1700, loss[loss=0.2513, simple_loss=0.3273, pruned_loss=0.08761, over 7143.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3058, pruned_loss=0.07994, over 1420245.66 frames.], batch size: 20, lr: 1.57e-03
2022-05-14 00:27:38,790 INFO [train.py:812] (4/8) Epoch 4, batch 1750, loss[loss=0.2291, simple_loss=0.3075, pruned_loss=0.07537, over 7199.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3047, pruned_loss=0.07896, over 1419894.86 frames.], batch size: 22, lr: 1.57e-03
2022-05-14 00:28:45,526 INFO [train.py:812] (4/8) Epoch 4, batch 1800, loss[loss=0.2491, simple_loss=0.3255, pruned_loss=0.08641, over 7218.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3058, pruned_loss=0.07917, over 1421728.24 frames.], batch size: 21, lr: 1.57e-03
2022-05-14 00:29:45,162 INFO [train.py:812] (4/8) Epoch 4, batch 1850, loss[loss=0.2338, simple_loss=0.3011, pruned_loss=0.08323, over 7144.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3058, pruned_loss=0.07867, over 1420371.27 frames.], batch size: 17, lr: 1.57e-03
2022-05-14 00:30:44,399 INFO [train.py:812] (4/8) Epoch 4, batch 1900, loss[loss=0.2409, simple_loss=0.3116, pruned_loss=0.08507, over 7156.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3054, pruned_loss=0.07876, over 1423432.46 frames.], batch size: 19, lr: 1.56e-03
2022-05-14 00:31:43,799 INFO [train.py:812] (4/8) Epoch 4, batch 1950, loss[loss=0.2716, simple_loss=0.3356, pruned_loss=0.1038, over 6634.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3052, pruned_loss=0.07829, over 1428870.61 frames.], batch size: 38, lr: 1.56e-03
2022-05-14 00:32:40,427 INFO [train.py:812] (4/8) Epoch 4, batch 2000, loss[loss=0.2333, simple_loss=0.3127, pruned_loss=0.07689, over 7124.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3063, pruned_loss=0.0788, over 1425757.32 frames.], batch size: 21, lr: 1.56e-03
2022-05-14 00:34:15,590 INFO [train.py:812] (4/8) Epoch 4, batch 2050, loss[loss=0.2639, simple_loss=0.3315, pruned_loss=0.09817, over 6599.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3059, pruned_loss=0.07896, over 1422859.34 frames.], batch size: 31, lr: 1.56e-03
2022-05-14 00:35:41,822 INFO [train.py:812] (4/8) Epoch 4, batch 2100, loss[loss=0.2165, simple_loss=0.2923, pruned_loss=0.07038, over 7322.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3049, pruned_loss=0.07839, over 1421661.25 frames.], batch size: 21, lr: 1.56e-03
2022-05-14 00:36:41,408 INFO [train.py:812] (4/8) Epoch 4, batch 2150, loss[loss=0.227, simple_loss=0.3148, pruned_loss=0.06961, over 7326.00 frames.], tot_loss[loss=0.2286, simple_loss=0.3034, pruned_loss=0.07694, over 1423438.28 frames.], batch size: 22, lr: 1.55e-03
2022-05-14 00:37:40,374 INFO [train.py:812] (4/8) Epoch 4, batch 2200, loss[loss=0.2413, simple_loss=0.3286, pruned_loss=0.07704, over 7226.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3028, pruned_loss=0.07644, over 1425741.44 frames.], batch size: 21, lr: 1.55e-03
2022-05-14 00:38:47,613 INFO [train.py:812] (4/8) Epoch 4, batch 2250, loss[loss=0.319, simple_loss=0.3669, pruned_loss=0.1355, over 5158.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3037, pruned_loss=0.0766, over 1427483.37 frames.], batch size: 52, lr: 1.55e-03
2022-05-14 00:39:45,548 INFO [train.py:812] (4/8) Epoch 4, batch 2300, loss[loss=0.2271, simple_loss=0.2996, pruned_loss=0.07725, over 7168.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3043, pruned_loss=0.07697, over 1430531.33 frames.], batch size: 19, lr: 1.55e-03
2022-05-14 00:40:45,378 INFO [train.py:812] (4/8) Epoch 4, batch 2350, loss[loss=0.24, simple_loss=0.3115, pruned_loss=0.08421, over 7328.00 frames.], tot_loss[loss=0.2289, simple_loss=0.304, pruned_loss=0.07692, over 1431665.90 frames.], batch size: 20, lr: 1.54e-03
2022-05-14 00:41:44,130 INFO [train.py:812] (4/8) Epoch 4, batch 2400, loss[loss=0.2333, simple_loss=0.3039, pruned_loss=0.08137, over 7266.00 frames.], tot_loss[loss=0.2291, simple_loss=0.3048, pruned_loss=0.0767, over 1433353.66 frames.], batch size: 25, lr: 1.54e-03
2022-05-14 00:42:43,282 INFO [train.py:812] (4/8) Epoch 4, batch 2450, loss[loss=0.2263, simple_loss=0.3009, pruned_loss=0.07586, over 7375.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3039, pruned_loss=0.07614, over 1436341.09 frames.], batch size: 23, lr: 1.54e-03
2022-05-14 00:43:42,439 INFO [train.py:812] (4/8) Epoch 4, batch 2500, loss[loss=0.2153, simple_loss=0.287, pruned_loss=0.07177, over 7161.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3038, pruned_loss=0.07631, over 1434009.12 frames.], batch size: 19, lr: 1.54e-03
2022-05-14 00:44:40,440 INFO [train.py:812] (4/8) Epoch 4, batch 2550, loss[loss=0.1743, simple_loss=0.2516, pruned_loss=0.04851, over 7394.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3044, pruned_loss=0.0771, over 1425842.75 frames.], batch size: 18, lr: 1.54e-03
2022-05-14 00:45:38,434 INFO [train.py:812] (4/8) Epoch 4, batch 2600, loss[loss=0.2065, simple_loss=0.2925, pruned_loss=0.06023, over 7237.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3053, pruned_loss=0.07794, over 1426014.50 frames.], batch size: 20, lr: 1.53e-03
2022-05-14 00:46:37,714 INFO [train.py:812] (4/8) Epoch 4, batch 2650, loss[loss=0.2009, simple_loss=0.2648, pruned_loss=0.06853, over 7002.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3059, pruned_loss=0.07833, over 1419485.82 frames.], batch size: 16, lr: 1.53e-03
2022-05-14 00:47:36,753 INFO [train.py:812] (4/8) Epoch 4, batch 2700, loss[loss=0.1826, simple_loss=0.2596, pruned_loss=0.05278, over 6803.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3053, pruned_loss=0.07797, over 1417804.91 frames.], batch size: 15, lr: 1.53e-03
2022-05-14 00:48:35,495 INFO [train.py:812] (4/8) Epoch 4, batch 2750, loss[loss=0.2234, simple_loss=0.3021, pruned_loss=0.0723, over 7249.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3056, pruned_loss=0.0776, over 1421424.92 frames.], batch size: 19, lr: 1.53e-03
2022-05-14 00:49:34,108 INFO [train.py:812] (4/8) Epoch 4, batch 2800, loss[loss=0.2018, simple_loss=0.2796, pruned_loss=0.06203, over 7162.00 frames.], tot_loss[loss=0.227, simple_loss=0.303, pruned_loss=0.07555, over 1423781.51 frames.], batch size: 19, lr: 1.53e-03
2022-05-14 00:50:32,973 INFO [train.py:812] (4/8) Epoch 4, batch 2850, loss[loss=0.3063, simple_loss=0.3639, pruned_loss=0.1243, over 5257.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3024, pruned_loss=0.07558, over 1423527.08 frames.], batch size: 53, lr: 1.52e-03
2022-05-14 00:51:31,215 INFO [train.py:812] (4/8) Epoch 4, batch 2900, loss[loss=0.2714, simple_loss=0.3392, pruned_loss=0.1018, over 6747.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3024, pruned_loss=0.07557, over 1423895.95 frames.], batch size: 31, lr: 1.52e-03
2022-05-14 00:52:31,096 INFO [train.py:812] (4/8) Epoch 4, batch 2950, loss[loss=0.2462, simple_loss=0.3208, pruned_loss=0.08582, over 7076.00 frames.], tot_loss[loss=0.227, simple_loss=0.3026, pruned_loss=0.07568, over 1428140.90 frames.], batch size: 28, lr: 1.52e-03
2022-05-14 00:53:30,067 INFO [train.py:812] (4/8) Epoch 4, batch 3000, loss[loss=0.2688, simple_loss=0.337, pruned_loss=0.1003, over 7138.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3028, pruned_loss=0.07595, over 1426342.09 frames.], batch size: 20, lr: 1.52e-03
2022-05-14 00:53:30,068 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 00:53:37,753 INFO [train.py:841] (4/8) Epoch 4, validation: loss=0.1771, simple_loss=0.279, pruned_loss=0.03761, over 698248.00 frames.
2022-05-14 00:54:36,377 INFO [train.py:812] (4/8) Epoch 4, batch 3050, loss[loss=0.2122, simple_loss=0.2933, pruned_loss=0.0655, over 7104.00 frames.], tot_loss[loss=0.2279, simple_loss=0.3033, pruned_loss=0.07622, over 1420504.96 frames.], batch size: 21, lr: 1.51e-03
2022-05-14 00:55:35,281 INFO [train.py:812] (4/8) Epoch 4, batch 3100, loss[loss=0.2376, simple_loss=0.3111, pruned_loss=0.08206, over 7287.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3026, pruned_loss=0.07598, over 1417377.13 frames.], batch size: 24, lr: 1.51e-03
2022-05-14 00:56:35,142 INFO [train.py:812] (4/8) Epoch 4, batch 3150, loss[loss=0.2422, simple_loss=0.314, pruned_loss=0.08516, over 7275.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3021, pruned_loss=0.07616, over 1421695.56 frames.], batch size: 25, lr: 1.51e-03
2022-05-14 00:57:33,592 INFO [train.py:812] (4/8) Epoch 4, batch 3200, loss[loss=0.201, simple_loss=0.2784, pruned_loss=0.06181, over 7061.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3016, pruned_loss=0.07646, over 1422956.19 frames.], batch size: 18, lr: 1.51e-03
2022-05-14 00:58:32,689 INFO [train.py:812] (4/8) Epoch 4, batch 3250, loss[loss=0.1931, simple_loss=0.2685, pruned_loss=0.05882, over 7254.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3017, pruned_loss=0.0765, over 1423424.84 frames.], batch size: 19, lr: 1.51e-03
2022-05-14 00:59:30,511 INFO [train.py:812] (4/8) Epoch 4, batch 3300, loss[loss=0.238, simple_loss=0.3041, pruned_loss=0.08594, over 7201.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3001, pruned_loss=0.0751, over 1422783.02 frames.], batch size: 23, lr: 1.50e-03
2022-05-14 01:00:29,646 INFO [train.py:812] (4/8) Epoch 4, batch 3350, loss[loss=0.267, simple_loss=0.3428, pruned_loss=0.09566, over 6528.00 frames.], tot_loss[loss=0.2248, simple_loss=0.2996, pruned_loss=0.07503, over 1421118.25 frames.], batch size: 38, lr: 1.50e-03
2022-05-14 01:01:28,324 INFO [train.py:812] (4/8) Epoch 4, batch 3400, loss[loss=0.2148, simple_loss=0.2871, pruned_loss=0.07122, over 6986.00 frames.], tot_loss[loss=0.2253, simple_loss=0.2998, pruned_loss=0.07538, over 1422195.38 frames.], batch size: 16, lr: 1.50e-03
2022-05-14 01:02:28,056 INFO [train.py:812] (4/8) Epoch 4, batch 3450, loss[loss=0.1878, simple_loss=0.2688, pruned_loss=0.05339, over 7160.00 frames.], tot_loss[loss=0.2237, simple_loss=0.2986, pruned_loss=0.07442, over 1426888.44 frames.], batch size: 18, lr: 1.50e-03
2022-05-14 01:03:26,381 INFO [train.py:812] (4/8) Epoch 4, batch 3500, loss[loss=0.2108, simple_loss=0.2998, pruned_loss=0.06087, over 7373.00 frames.], tot_loss[loss=0.2243, simple_loss=0.2991, pruned_loss=0.07476, over 1428340.21 frames.], batch size: 23, lr: 1.50e-03
2022-05-14 01:04:26,016 INFO [train.py:812] (4/8) Epoch 4, batch 3550, loss[loss=0.2784, simple_loss=0.3465, pruned_loss=0.1052, over 7322.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2982, pruned_loss=0.0742, over 1429851.79 frames.], batch size: 24, lr: 1.49e-03
2022-05-14 01:05:25,256 INFO [train.py:812] (4/8) Epoch 4, batch 3600, loss[loss=0.2009, simple_loss=0.2799, pruned_loss=0.06094, over 7414.00 frames.], tot_loss[loss=0.2243, simple_loss=0.2991, pruned_loss=0.07478, over 1428677.52 frames.], batch size: 17, lr: 1.49e-03
2022-05-14 01:06:24,749 INFO [train.py:812] (4/8) Epoch 4, batch 3650, loss[loss=0.2217, simple_loss=0.2906, pruned_loss=0.07641, over 7130.00 frames.], tot_loss[loss=0.2244, simple_loss=0.299, pruned_loss=0.07493, over 1428716.53 frames.], batch size: 17, lr: 1.49e-03
2022-05-14 01:07:24,236 INFO [train.py:812] (4/8) Epoch 4, batch 3700, loss[loss=0.1935, simple_loss=0.2695, pruned_loss=0.05878, over 6989.00 frames.], tot_loss[loss=0.2242, simple_loss=0.2989, pruned_loss=0.07475, over 1427641.02 frames.], batch size: 16, lr: 1.49e-03
2022-05-14 01:08:24,371 INFO [train.py:812] (4/8) Epoch 4, batch 3750, loss[loss=0.2202, simple_loss=0.2907, pruned_loss=0.07483, over 7435.00 frames.], tot_loss[loss=0.2239, simple_loss=0.2985, pruned_loss=0.07469, over 1424696.34 frames.], batch size: 20, lr: 1.49e-03
2022-05-14 01:09:22,772 INFO [train.py:812] (4/8) Epoch 4, batch 3800, loss[loss=0.184, simple_loss=0.2678, pruned_loss=0.05008, over 7067.00 frames.], tot_loss[loss=0.2237, simple_loss=0.2989, pruned_loss=0.0742, over 1420374.86 frames.], batch size: 18, lr: 1.48e-03
2022-05-14 01:10:22,616 INFO [train.py:812] (4/8) Epoch 4, batch 3850, loss[loss=0.1971, simple_loss=0.2712, pruned_loss=0.06145, over 7412.00 frames.], tot_loss[loss=0.223, simple_loss=0.2984, pruned_loss=0.07377, over 1424706.64 frames.], batch size: 18, lr: 1.48e-03
2022-05-14 01:11:21,438 INFO [train.py:812] (4/8) Epoch 4, batch 3900, loss[loss=0.272, simple_loss=0.3308, pruned_loss=0.1066, over 4808.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2987, pruned_loss=0.07388, over 1426052.97 frames.], batch size: 53, lr: 1.48e-03
2022-05-14 01:12:20,482 INFO [train.py:812] (4/8) Epoch 4, batch 3950, loss[loss=0.237, simple_loss=0.2929, pruned_loss=0.09049, over 6778.00 frames.], tot_loss[loss=0.2224, simple_loss=0.2975, pruned_loss=0.07367, over 1424614.61 frames.], batch size: 15, lr: 1.48e-03
2022-05-14 01:13:19,411 INFO [train.py:812] (4/8) Epoch 4, batch 4000, loss[loss=0.2098, simple_loss=0.3018, pruned_loss=0.05893, over 7211.00 frames.], tot_loss[loss=0.224, simple_loss=0.2985, pruned_loss=0.07477, over 1415951.72 frames.], batch size: 21, lr: 1.48e-03
2022-05-14 01:14:18,985 INFO [train.py:812] (4/8) Epoch 4, batch 4050, loss[loss=0.2613, simple_loss=0.3298, pruned_loss=0.09636, over 7410.00 frames.], tot_loss[loss=0.2242, simple_loss=0.2989, pruned_loss=0.07476, over 1418699.73 frames.], batch size: 21, lr: 1.47e-03
2022-05-14 01:15:18,241 INFO [train.py:812] (4/8) Epoch 4, batch 4100, loss[loss=0.2172, simple_loss=0.2961, pruned_loss=0.06919, over 6342.00 frames.], tot_loss[loss=0.226, simple_loss=0.3006, pruned_loss=0.07575, over 1421215.92 frames.], batch size: 37, lr: 1.47e-03
2022-05-14 01:16:17,165 INFO [train.py:812] (4/8) Epoch 4, batch 4150, loss[loss=0.1917, simple_loss=0.2577, pruned_loss=0.06289, over 6988.00 frames.], tot_loss[loss=0.225, simple_loss=0.2993, pruned_loss=0.07528, over 1423543.65 frames.], batch size: 16, lr: 1.47e-03
2022-05-14 01:17:15,914 INFO [train.py:812] (4/8) Epoch 4, batch 4200, loss[loss=0.2414, simple_loss=0.3172, pruned_loss=0.08283, over 7156.00 frames.], tot_loss[loss=0.2252, simple_loss=0.2997, pruned_loss=0.07537, over 1421784.08 frames.], batch size: 19, lr: 1.47e-03
2022-05-14 01:18:15,841 INFO [train.py:812] (4/8) Epoch 4, batch 4250, loss[loss=0.1849, simple_loss=0.2684, pruned_loss=0.05071, over 7360.00 frames.], tot_loss[loss=0.2253, simple_loss=0.2994, pruned_loss=0.07558, over 1413996.98 frames.], batch size: 19, lr: 1.47e-03
2022-05-14 01:19:14,763 INFO [train.py:812] (4/8) Epoch 4, batch 4300, loss[loss=0.2348, simple_loss=0.3004, pruned_loss=0.08458, over 7357.00 frames.], tot_loss[loss=0.2235, simple_loss=0.2972, pruned_loss=0.07492, over 1412486.75 frames.], batch size: 19, lr: 1.47e-03
2022-05-14 01:20:14,300 INFO [train.py:812] (4/8) Epoch 4, batch 4350, loss[loss=0.2632, simple_loss=0.3268, pruned_loss=0.09977, over 6317.00 frames.], tot_loss[loss=0.2222, simple_loss=0.2956, pruned_loss=0.07434, over 1410841.43 frames.], batch size: 37, lr: 1.46e-03
2022-05-14 01:21:13,823 INFO [train.py:812] (4/8) Epoch 4, batch 4400, loss[loss=0.2527, simple_loss=0.3054, pruned_loss=0.1, over 7066.00 frames.], tot_loss[loss=0.223, simple_loss=0.2958, pruned_loss=0.07505, over 1409174.60 frames.], batch size: 18, lr: 1.46e-03
2022-05-14 01:22:13,437 INFO [train.py:812] (4/8) Epoch 4, batch 4450, loss[loss=0.2237, simple_loss=0.3045, pruned_loss=0.0715, over 7373.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2957, pruned_loss=0.07484, over 1400880.26 frames.], batch size: 23, lr: 1.46e-03
2022-05-14 01:23:11,878 INFO [train.py:812] (4/8) Epoch 4, batch 4500, loss[loss=0.2279, simple_loss=0.3008, pruned_loss=0.07749, over 6483.00 frames.], tot_loss[loss=0.223, simple_loss=0.2961, pruned_loss=0.07499, over 1396244.29 frames.], batch size: 38, lr: 1.46e-03
2022-05-14 01:24:10,625 INFO [train.py:812] (4/8) Epoch 4, batch 4550, loss[loss=0.2689, simple_loss=0.3246, pruned_loss=0.1066, over 5262.00 frames.], tot_loss[loss=0.2269, simple_loss=0.2995, pruned_loss=0.07714, over 1361505.34 frames.], batch size: 52, lr: 1.46e-03
2022-05-14 01:25:17,930 INFO [train.py:812] (4/8) Epoch 5, batch 0, loss[loss=0.247, simple_loss=0.3304, pruned_loss=0.08183, over 7201.00 frames.], tot_loss[loss=0.247, simple_loss=0.3304, pruned_loss=0.08183, over 7201.00 frames.], batch size: 23, lr: 1.40e-03
2022-05-14 01:26:16,016 INFO [train.py:812] (4/8) Epoch 5, batch 50, loss[loss=0.2365, simple_loss=0.3205, pruned_loss=0.07628, over 7332.00 frames.], tot_loss[loss=0.2222, simple_loss=0.2993, pruned_loss=0.07254, over 320830.00 frames.], batch size: 22, lr: 1.40e-03
2022-05-14 01:27:13,772 INFO [train.py:812] (4/8) Epoch 5, batch 100, loss[loss=0.2245, simple_loss=0.3129, pruned_loss=0.06801, over 7343.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3007, pruned_loss=0.07377, over 566370.58 frames.], batch size: 22, lr: 1.40e-03
2022-05-14 01:28:13,018 INFO [train.py:812] (4/8) Epoch 5, batch 150, loss[loss=0.257, simple_loss=0.3146, pruned_loss=0.09974, over 4895.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3001, pruned_loss=0.07449, over 754890.60 frames.], batch size: 52, lr: 1.40e-03
2022-05-14 01:29:12,388 INFO [train.py:812] (4/8) Epoch 5, batch 200, loss[loss=0.1946, simple_loss=0.2791, pruned_loss=0.05506, over 7155.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3005, pruned_loss=0.07454, over 903987.76 frames.], batch size: 19, lr: 1.40e-03
2022-05-14 01:30:11,968 INFO [train.py:812] (4/8) Epoch 5, batch 250, loss[loss=0.2352, simple_loss=0.3181, pruned_loss=0.0762, over 7344.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3017, pruned_loss=0.07389, over 1021357.41 frames.], batch size: 22, lr: 1.39e-03
2022-05-14 01:31:10,337 INFO [train.py:812] (4/8) Epoch 5, batch 300, loss[loss=0.2034, simple_loss=0.2688, pruned_loss=0.069, over 7264.00 frames.], tot_loss[loss=0.222, simple_loss=0.2987, pruned_loss=0.0726, over 1113916.01 frames.], batch size: 17, lr: 1.39e-03
2022-05-14 01:32:09,251 INFO [train.py:812] (4/8) Epoch 5, batch 350, loss[loss=0.195, simple_loss=0.2823, pruned_loss=0.05386, over 7160.00 frames.], tot_loss[loss=0.2203, simple_loss=0.2968, pruned_loss=0.07189, over 1182247.92 frames.], batch size: 19, lr: 1.39e-03
2022-05-14 01:33:06,927 INFO [train.py:812] (4/8) Epoch 5, batch 400, loss[loss=0.2156, simple_loss=0.3001, pruned_loss=0.06557, over 7081.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2967, pruned_loss=0.0721, over 1233833.45 frames.], batch size: 28, lr: 1.39e-03
2022-05-14 01:34:05,741 INFO [train.py:812] (4/8) Epoch 5, batch 450, loss[loss=0.231, simple_loss=0.3101, pruned_loss=0.07591, over 7061.00 frames.], tot_loss[loss=0.2197, simple_loss=0.2962, pruned_loss=0.07158, over 1275394.13 frames.], batch size: 28, lr: 1.39e-03
2022-05-14 01:35:05,173 INFO [train.py:812] (4/8) Epoch 5, batch 500, loss[loss=0.1784, simple_loss=0.273, pruned_loss=0.04188, over 7321.00 frames.], tot_loss[loss=0.2179, simple_loss=0.2945, pruned_loss=0.07063, over 1309761.35 frames.], batch size: 21, lr: 1.39e-03
2022-05-14 01:36:04,762 INFO [train.py:812] (4/8) Epoch 5, batch 550, loss[loss=0.2081, simple_loss=0.2885, pruned_loss=0.06388, over 6749.00 frames.], tot_loss[loss=0.2173, simple_loss=0.294, pruned_loss=0.07032, over 1333773.05 frames.], batch size: 31, lr: 1.38e-03
2022-05-14 01:37:04,104 INFO [train.py:812] (4/8) Epoch 5, batch 600, loss[loss=0.1917, simple_loss=0.2568, pruned_loss=0.06334, over 6997.00 frames.], tot_loss[loss=0.2178, simple_loss=0.2939, pruned_loss=0.07084, over 1355429.84 frames.], batch size: 16, lr: 1.38e-03
2022-05-14 01:38:03,180 INFO [train.py:812] (4/8) Epoch 5, batch 650, loss[loss=0.2239, simple_loss=0.2933, pruned_loss=0.07722, over 7319.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2947, pruned_loss=0.07112, over 1369976.10 frames.], batch size: 20, lr: 1.38e-03
2022-05-14 01:39:02,103 INFO [train.py:812] (4/8) Epoch 5, batch 700, loss[loss=0.2782, simple_loss=0.3563, pruned_loss=0.1001, over 7294.00 frames.], tot_loss[loss=0.2204, simple_loss=0.2965, pruned_loss=0.07218, over 1379691.24 frames.], batch size: 25, lr: 1.38e-03
2022-05-14 01:40:01,978 INFO [train.py:812] (4/8) Epoch 5, batch 750, loss[loss=0.1829, simple_loss=0.2657, pruned_loss=0.05008, over 7063.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2956, pruned_loss=0.0714, over 1385046.31 frames.], batch size: 18, lr: 1.38e-03
2022-05-14 01:40:59,752 INFO [train.py:812] (4/8) Epoch 5, batch 800, loss[loss=0.2019, simple_loss=0.2742, pruned_loss=0.06484, over 7070.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2938, pruned_loss=0.07055, over 1396693.25 frames.], batch size: 18, lr: 1.38e-03
2022-05-14 01:41:57,354 INFO [train.py:812] (4/8) Epoch 5, batch 850, loss[loss=0.1977, simple_loss=0.2749, pruned_loss=0.06023, over 7063.00 frames.], tot_loss[loss=0.217, simple_loss=0.2936, pruned_loss=0.07026, over 1396164.36 frames.], batch size: 18, lr: 1.37e-03
2022-05-14 01:42:55,836 INFO [train.py:812] (4/8) Epoch 5, batch 900, loss[loss=0.2465, simple_loss=0.3149, pruned_loss=0.08908, over 7317.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2938, pruned_loss=0.07051, over 1402777.82 frames.], batch size: 21, lr: 1.37e-03
2022-05-14 01:43:53,344 INFO [train.py:812] (4/8) Epoch 5, batch 950, loss[loss=0.2558, simple_loss=0.3368, pruned_loss=0.08745, over 7063.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2942, pruned_loss=0.07064, over 1406760.91 frames.], batch size: 28, lr: 1.37e-03
2022-05-14 01:44:52,025 INFO [train.py:812] (4/8) Epoch 5, batch 1000, loss[loss=0.1876, simple_loss=0.2666, pruned_loss=0.05435, over 7067.00 frames.], tot_loss[loss=0.2179, simple_loss=0.2941, pruned_loss=0.07089, over 1410255.73 frames.], batch size: 18, lr: 1.37e-03
2022-05-14 01:45:49,417 INFO [train.py:812] (4/8) Epoch 5, batch 1050, loss[loss=0.2508, simple_loss=0.3245, pruned_loss=0.08858, over 7296.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2947, pruned_loss=0.07073, over 1415956.34 frames.], batch size: 24, lr: 1.37e-03
2022-05-14 01:46:47,342 INFO [train.py:812] (4/8) Epoch 5, batch 1100, loss[loss=0.2217, simple_loss=0.3045, pruned_loss=0.0694, over 6354.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2955, pruned_loss=0.07093, over 1412688.53 frames.], batch size: 37, lr: 1.37e-03
2022-05-14 01:47:47,034 INFO [train.py:812] (4/8) Epoch 5, batch 1150, loss[loss=0.2186, simple_loss=0.2889, pruned_loss=0.0742, over 7421.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2954, pruned_loss=0.07067, over 1415522.21 frames.], batch size: 20, lr: 1.36e-03
2022-05-14 01:48:45,949 INFO [train.py:812] (4/8) Epoch 5, batch 1200, loss[loss=0.2389, simple_loss=0.3189, pruned_loss=0.07949, over 6281.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2945, pruned_loss=0.07028, over 1416955.98 frames.], batch size: 37, lr: 1.36e-03
2022-05-14 01:49:45,447 INFO [train.py:812] (4/8) Epoch 5, batch 1250, loss[loss=0.1906, simple_loss=0.279, pruned_loss=0.05108, over 7252.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2945, pruned_loss=0.07083, over 1413205.73 frames.], batch size: 19, lr: 1.36e-03
2022-05-14 01:50:43,667 INFO [train.py:812] (4/8) Epoch 5, batch 1300, loss[loss=0.2051, simple_loss=0.285, pruned_loss=0.06259, over 7328.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2958, pruned_loss=0.07089, over 1417147.97 frames.], batch size: 20, lr: 1.36e-03
2022-05-14 01:51:42,405 INFO [train.py:812] (4/8) Epoch 5, batch 1350, loss[loss=0.1738, simple_loss=0.2466, pruned_loss=0.05056, over 7125.00 frames.], tot_loss[loss=0.2191, simple_loss=0.2963, pruned_loss=0.07099, over 1423617.81 frames.], batch size: 17, lr: 1.36e-03
2022-05-14 01:52:39,815 INFO [train.py:812] (4/8) Epoch 5, batch 1400, loss[loss=0.1862, simple_loss=0.2752, pruned_loss=0.04858, over 7239.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2977, pruned_loss=0.07185, over 1419240.78 frames.], batch size: 20, lr: 1.36e-03
2022-05-14 01:53:37,452 INFO [train.py:812] (4/8) Epoch 5, batch 1450, loss[loss=0.1767, simple_loss=0.2467, pruned_loss=0.05336, over 6999.00 frames.], tot_loss[loss=0.2204, simple_loss=0.2976, pruned_loss=0.07161, over 1419643.10 frames.], batch size: 16, lr: 1.35e-03
2022-05-14 01:54:35,089 INFO [train.py:812] (4/8) Epoch 5, batch 1500, loss[loss=0.1892, simple_loss=0.2694, pruned_loss=0.05455, over 7336.00 frames.], tot_loss[loss=0.2198, simple_loss=0.2967, pruned_loss=0.07146, over 1422805.60 frames.], batch size: 20, lr: 1.35e-03
2022-05-14 01:55:34,689 INFO [train.py:812] (4/8) Epoch 5, batch 1550, loss[loss=0.249, simple_loss=0.3225, pruned_loss=0.08776, over 7368.00 frames.], tot_loss[loss=0.2176, simple_loss=0.2944, pruned_loss=0.07039, over 1424723.97 frames.], batch size: 23, lr: 1.35e-03
2022-05-14 01:56:33,042 INFO [train.py:812] (4/8) Epoch 5, batch 1600, loss[loss=0.2143, simple_loss=0.3028, pruned_loss=0.06289, over 7278.00 frames.], tot_loss[loss=0.2171, simple_loss=0.294, pruned_loss=0.07006, over 1423891.03 frames.], batch size: 25, lr: 1.35e-03
2022-05-14 01:57:37,112 INFO [train.py:812] (4/8) Epoch 5, batch 1650, loss[loss=0.223, simple_loss=0.3031, pruned_loss=0.07144, over 7111.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2942, pruned_loss=0.06977, over 1421116.32 frames.], batch size: 21, lr: 1.35e-03
2022-05-14 01:58:36,675 INFO [train.py:812] (4/8) Epoch 5, batch 1700, loss[loss=0.2101, simple_loss=0.2985, pruned_loss=0.06089, over 7340.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2932, pruned_loss=0.06917, over 1423904.71 frames.], batch size: 22, lr: 1.35e-03
2022-05-14 01:59:35,635 INFO [train.py:812] (4/8) Epoch 5, batch 1750, loss[loss=0.1954, simple_loss=0.2818, pruned_loss=0.05453, over 7307.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2938, pruned_loss=0.0697, over 1424202.95 frames.], batch size: 24, lr: 1.34e-03
2022-05-14 02:00:34,957 INFO [train.py:812] (4/8) Epoch 5, batch 1800, loss[loss=0.2422, simple_loss=0.3297, pruned_loss=0.07731, over 7324.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2935, pruned_loss=0.06916, over 1426433.78 frames.], batch size: 21, lr: 1.34e-03
2022-05-14 02:01:33,479 INFO [train.py:812] (4/8) Epoch 5, batch 1850, loss[loss=0.2712, simple_loss=0.334, pruned_loss=0.1042, over 6276.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2941, pruned_loss=0.06923, over 1427104.96 frames.], batch size: 37, lr: 1.34e-03
2022-05-14 02:02:31,902 INFO [train.py:812] (4/8) Epoch 5, batch 1900, loss[loss=0.245, simple_loss=0.3243, pruned_loss=0.08285, over 7121.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2942, pruned_loss=0.0692, over 1428740.89 frames.], batch size: 21, lr: 1.34e-03
2022-05-14 02:03:30,593 INFO [train.py:812] (4/8) Epoch 5, batch 1950, loss[loss=0.1986, simple_loss=0.2743, pruned_loss=0.06146, over 7154.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2936, pruned_loss=0.06865, over 1429190.65 frames.], batch size: 18, lr: 1.34e-03
2022-05-14 02:04:28,245 INFO [train.py:812] (4/8) Epoch 5, batch 2000, loss[loss=0.2175, simple_loss=0.2892, pruned_loss=0.07284, over 7270.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2935, pruned_loss=0.06908, over 1426871.14 frames.], batch size: 25, lr: 1.34e-03
2022-05-14 02:05:26,865 INFO [train.py:812] (4/8) Epoch 5, batch 2050, loss[loss=0.2498, simple_loss=0.3154, pruned_loss=0.09208, over 7269.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2937, pruned_loss=0.06932, over 1431753.04 frames.], batch size: 24, lr: 1.34e-03
2022-05-14 02:06:25,382 INFO [train.py:812] (4/8) Epoch 5, batch 2100, loss[loss=0.1665, simple_loss=0.243, pruned_loss=0.04497, over 7398.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2927, pruned_loss=0.06851, over 1434504.70 frames.], batch size: 18, lr: 1.33e-03
2022-05-14 02:07:23,970 INFO [train.py:812] (4/8) Epoch 5, batch 2150, loss[loss=0.1844, simple_loss=0.2683, pruned_loss=0.05024, over 7061.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2936, pruned_loss=0.06855, over 1432755.91 frames.], batch size: 18, lr: 1.33e-03
2022-05-14 02:08:21,802 INFO [train.py:812] (4/8) Epoch 5, batch 2200, loss[loss=0.2393, simple_loss=0.3225, pruned_loss=0.07811, over 7353.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2936, pruned_loss=0.06908, over 1433899.96 frames.], batch size: 22, lr: 1.33e-03
2022-05-14 02:09:20,784 INFO [train.py:812] (4/8) Epoch 5, batch 2250, loss[loss=0.2511, simple_loss=0.3268, pruned_loss=0.08774, over 7373.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2943, pruned_loss=0.06948, over 1431477.66 frames.], batch size: 23, lr: 1.33e-03
2022-05-14 02:10:20,193 INFO [train.py:812] (4/8) Epoch 5, batch 2300, loss[loss=0.1797, simple_loss=0.2513, pruned_loss=0.05404, over 7265.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2943, pruned_loss=0.06967, over 1429189.75 frames.], batch size: 17, lr: 1.33e-03
2022-05-14 02:11:18,993 INFO [train.py:812] (4/8) Epoch 5, batch 2350, loss[loss=0.183, simple_loss=0.2607, pruned_loss=0.05264, over 7415.00 frames.], tot_loss[loss=0.2158, simple_loss=0.294, pruned_loss=0.06886, over 1432487.74 frames.], batch size: 18, lr: 1.33e-03
2022-05-14 02:12:18,590 INFO [train.py:812] (4/8) Epoch 5, batch 2400, loss[loss=0.2338, simple_loss=0.3258, pruned_loss=0.07088, over 7223.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2933, pruned_loss=0.06848, over 1434064.81 frames.], batch size: 21, lr: 1.32e-03
2022-05-14 02:13:16,797 INFO [train.py:812] (4/8) Epoch 5, batch 2450, loss[loss=0.1863, simple_loss=0.2648, pruned_loss=0.05391, over 7272.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2942, pruned_loss=0.0695, over 1434222.20 frames.], batch size: 18, lr: 1.32e-03
2022-05-14 02:14:14,133 INFO [train.py:812] (4/8) Epoch 5, batch 2500, loss[loss=0.238, simple_loss=0.3112, pruned_loss=0.08245, over 7209.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2933, pruned_loss=0.06927, over 1431825.16 frames.], batch size: 22, lr: 1.32e-03
2022-05-14 02:15:13,119 INFO [train.py:812] (4/8) Epoch 5, batch 2550, loss[loss=0.2312, simple_loss=0.3127, pruned_loss=0.07486, over 7140.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2937, pruned_loss=0.06937, over 1432284.19 frames.], batch size: 20, lr: 1.32e-03
2022-05-14 02:16:11,208 INFO [train.py:812] (4/8) Epoch 5, batch 2600, loss[loss=0.2133, simple_loss=0.301, pruned_loss=0.06281, over 7317.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2941, pruned_loss=0.06957, over 1430940.46 frames.], batch size: 21, lr: 1.32e-03
2022-05-14 02:17:10,908 INFO [train.py:812] (4/8) Epoch 5, batch 2650, loss[loss=0.1846, simple_loss=0.2555, pruned_loss=0.05684, over 6995.00 frames.], tot_loss[loss=0.2154, simple_loss=0.293, pruned_loss=0.06892, over 1429438.98 frames.], batch size: 16, lr: 1.32e-03
2022-05-14 02:18:10,456 INFO [train.py:812] (4/8) Epoch 5, batch 2700, loss[loss=0.1765, simple_loss=0.2503, pruned_loss=0.0514, over 7269.00 frames.], tot_loss[loss=0.2154, simple_loss=0.293, pruned_loss=0.06892, over 1431631.80 frames.], batch size: 18, lr: 1.32e-03
2022-05-14 02:19:10,225 INFO [train.py:812] (4/8) Epoch 5, batch 2750, loss[loss=0.2098, simple_loss=0.2848, pruned_loss=0.06736, over 7348.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2929, pruned_loss=0.06904, over 1432601.19 frames.], batch size: 19, lr: 1.31e-03
2022-05-14 02:20:09,508 INFO [train.py:812] (4/8) Epoch 5, batch 2800, loss[loss=0.1969, simple_loss=0.2756, pruned_loss=0.05909, over 7148.00 frames.], tot_loss[loss=0.2133, simple_loss=0.2912, pruned_loss=0.06766, over 1433243.77 frames.], batch size: 17, lr: 1.31e-03
2022-05-14 02:21:07,406 INFO [train.py:812] (4/8) Epoch 5, batch 2850, loss[loss=0.2613, simple_loss=0.3408, pruned_loss=0.09091, over 6740.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2915, pruned_loss=0.06772, over 1430839.58 frames.], batch size: 31, lr: 1.31e-03
2022-05-14 02:22:06,254 INFO [train.py:812] (4/8) Epoch 5, batch 2900, loss[loss=0.2209, simple_loss=0.3011, pruned_loss=0.07037, over 7281.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2927, pruned_loss=0.06847, over 1428840.24 frames.], batch size: 24, lr: 1.31e-03
2022-05-14 02:23:05,647 INFO [train.py:812] (4/8) Epoch 5, batch 2950, loss[loss=0.2266, simple_loss=0.3056, pruned_loss=0.07377, over 7345.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2914, pruned_loss=0.06783, over 1428320.14 frames.], batch size: 22, lr: 1.31e-03
2022-05-14 02:24:04,416 INFO [train.py:812] (4/8) Epoch 5, batch 3000, loss[loss=0.2049, simple_loss=0.2891, pruned_loss=0.06039, over 7180.00 frames.], tot_loss[loss=0.214, simple_loss=0.2915, pruned_loss=0.06823, over 1423930.76 frames.], batch size: 26, lr: 1.31e-03
2022-05-14 02:24:04,417 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 02:24:12,114 INFO [train.py:841] (4/8) Epoch 5, validation: loss=0.1705, simple_loss=0.2732, pruned_loss=0.03391, over 698248.00 frames.
2022-05-14 02:25:11,800 INFO [train.py:812] (4/8) Epoch 5, batch 3050, loss[loss=0.229, simple_loss=0.299, pruned_loss=0.07947, over 7200.00 frames.], tot_loss[loss=0.2145, simple_loss=0.292, pruned_loss=0.06848, over 1428194.86 frames.], batch size: 22, lr: 1.31e-03
2022-05-14 02:26:09,565 INFO [train.py:812] (4/8) Epoch 5, batch 3100, loss[loss=0.177, simple_loss=0.2596, pruned_loss=0.04715, over 7232.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2922, pruned_loss=0.06838, over 1427409.44 frames.], batch size: 20, lr: 1.30e-03
2022-05-14 02:27:19,072 INFO [train.py:812] (4/8) Epoch 5, batch 3150, loss[loss=0.2521, simple_loss=0.3158, pruned_loss=0.09416, over 7307.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2924, pruned_loss=0.06832, over 1428055.28 frames.], batch size: 25, lr: 1.30e-03
2022-05-14 02:28:18,324 INFO [train.py:812] (4/8) Epoch 5, batch 3200, loss[loss=0.2151, simple_loss=0.2901, pruned_loss=0.07002, over 7368.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2928, pruned_loss=0.0689, over 1429641.71 frames.], batch size: 19, lr: 1.30e-03
2022-05-14 02:29:17,244 INFO [train.py:812] (4/8) Epoch 5, batch 3250, loss[loss=0.2243, simple_loss=0.2859, pruned_loss=0.08142, over 7173.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2929, pruned_loss=0.06885, over 1428187.39 frames.], batch size: 18, lr: 1.30e-03
2022-05-14 02:30:15,401 INFO [train.py:812] (4/8) Epoch 5, batch 3300, loss[loss=0.2109, simple_loss=0.2908, pruned_loss=0.06552, over 7181.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2934, pruned_loss=0.06938, over 1423664.56 frames.], batch size: 26, lr: 1.30e-03
2022-05-14 02:31:14,127 INFO [train.py:812] (4/8) Epoch 5, batch 3350, loss[loss=0.2884, simple_loss=0.345, pruned_loss=0.1159, over 7109.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2935, pruned_loss=0.06879, over 1426393.96 frames.], batch size: 21, lr: 1.30e-03
2022-05-14 02:32:12,543 INFO [train.py:812] (4/8) Epoch 5, batch 3400, loss[loss=0.2336, simple_loss=0.3139, pruned_loss=0.07667, over 7239.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2934, pruned_loss=0.06853, over 1428046.65 frames.], batch size: 20, lr: 1.30e-03
2022-05-14 02:33:11,752 INFO [train.py:812] (4/8) Epoch 5, batch 3450, loss[loss=0.2437, simple_loss=0.324, pruned_loss=0.08171, over 7200.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2935, pruned_loss=0.06875, over 1428103.43 frames.], batch size: 23, lr: 1.29e-03
2022-05-14 02:34:10,777 INFO [train.py:812] (4/8) Epoch 5, batch 3500, loss[loss=0.1725, simple_loss=0.2625, pruned_loss=0.04129, over 7320.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2934, pruned_loss=0.06858, over 1430828.05 frames.], batch size: 20, lr: 1.29e-03
2022-05-14 02:35:38,309 INFO [train.py:812] (4/8) Epoch 5, batch 3550, loss[loss=0.2143, simple_loss=0.301, pruned_loss=0.06382, over 7409.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2935, pruned_loss=0.06813, over 1425583.39 frames.], batch size: 21, lr: 1.29e-03
2022-05-14 02:36:46,049 INFO [train.py:812] (4/8) Epoch 5, batch 3600, loss[loss=0.213, simple_loss=0.2845, pruned_loss=0.07072, over 7263.00 frames.], tot_loss[loss=0.213, simple_loss=0.2916, pruned_loss=0.06723, over 1421779.82 frames.], batch size: 19, lr: 1.29e-03
2022-05-14 02:38:13,282 INFO [train.py:812] (4/8) Epoch 5, batch 3650, loss[loss=0.2201, simple_loss=0.2999, pruned_loss=0.07014, over 6710.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2922, pruned_loss=0.06763, over 1416336.76 frames.], batch size: 31, lr: 1.29e-03
2022-05-14 02:39:12,928 INFO [train.py:812] (4/8) Epoch 5, batch 3700, loss[loss=0.2001, simple_loss=0.2795, pruned_loss=0.06035, over 7169.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2905, pruned_loss=0.06734, over 1419822.50 frames.], batch size: 18, lr: 1.29e-03
2022-05-14 02:40:11,642 INFO [train.py:812] (4/8) Epoch 5, batch 3750, loss[loss=0.2299, simple_loss=0.292, pruned_loss=0.08388, over 6815.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2925, pruned_loss=0.06824, over 1419563.21 frames.], batch size: 15, lr: 1.29e-03
2022-05-14 02:41:09,952 INFO [train.py:812] (4/8) Epoch 5, batch 3800, loss[loss=0.1762, simple_loss=0.2497, pruned_loss=0.05142, over 7279.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2924, pruned_loss=0.06822, over 1421309.97 frames.], batch size: 18, lr: 1.28e-03
2022-05-14 02:42:07,610 INFO [train.py:812] (4/8) Epoch 5, batch 3850, loss[loss=0.2036, simple_loss=0.2838, pruned_loss=0.0617, over 7416.00 frames.], tot_loss[loss=0.2129, simple_loss=0.291, pruned_loss=0.06736, over 1421031.02 frames.], batch size: 21, lr: 1.28e-03
2022-05-14 02:43:06,301 INFO [train.py:812] (4/8) Epoch 5, batch 3900, loss[loss=0.2197, simple_loss=0.2904, pruned_loss=0.07453, over 7175.00 frames.], tot_loss[loss=0.2118, simple_loss=0.2897, pruned_loss=0.06699, over 1417708.70 frames.], batch size: 18, lr: 1.28e-03
2022-05-14 02:44:04,239 INFO [train.py:812] (4/8) Epoch 5, batch 3950, loss[loss=0.2114, simple_loss=0.2854, pruned_loss=0.06867, over 7413.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2904, pruned_loss=0.06775, over 1414634.65 frames.], batch size: 21, lr: 1.28e-03
2022-05-14 02:45:02,165 INFO [train.py:812] (4/8) Epoch 5, batch 4000, loss[loss=0.2118, simple_loss=0.2924, pruned_loss=0.06561, over 7427.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2908, pruned_loss=0.06773, over 1418753.13 frames.], batch size: 20, lr: 1.28e-03
2022-05-14 02:46:01,623 INFO [train.py:812] (4/8) Epoch 5, batch 4050, loss[loss=0.2108, simple_loss=0.3006, pruned_loss=0.06046, over 7217.00 frames.], tot_loss[loss=0.2121, simple_loss=0.2898, pruned_loss=0.06721, over 1422132.33 frames.], batch size: 21, lr: 1.28e-03
2022-05-14 02:46:59,624 INFO [train.py:812] (4/8) Epoch 5, batch 4100, loss[loss=0.199, simple_loss=0.2727, pruned_loss=0.06266, over 7284.00 frames.], tot_loss[loss=0.215, simple_loss=0.2929, pruned_loss=0.06857, over 1419153.67 frames.], batch size: 18, lr: 1.28e-03
2022-05-14 02:47:58,854 INFO [train.py:812] (4/8) Epoch 5, batch 4150, loss[loss=0.2404, simple_loss=0.3111, pruned_loss=0.08489, over 7213.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2931, pruned_loss=0.06893, over 1417319.11 frames.], batch size: 22, lr: 1.27e-03
2022-05-14 02:48:57,888 INFO [train.py:812] (4/8) Epoch 5, batch 4200, loss[loss=0.2154, simple_loss=0.3054, pruned_loss=0.06265, over 7146.00 frames.], tot_loss[loss=0.2163, simple_loss=0.294, pruned_loss=0.06932, over 1415269.14 frames.], batch size: 17, lr: 1.27e-03
2022-05-14 02:49:57,151 INFO [train.py:812] (4/8) Epoch 5, batch 4250, loss[loss=0.2259, simple_loss=0.2941, pruned_loss=0.07885, over 7067.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2931, pruned_loss=0.06888, over 1416583.55 frames.], batch size: 18, lr: 1.27e-03
2022-05-14 02:50:54,439 INFO [train.py:812] (4/8) Epoch 5, batch 4300, loss[loss=0.2132, simple_loss=0.294, pruned_loss=0.06621, over 7150.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2932, pruned_loss=0.06872, over 1416911.10 frames.], batch size: 20, lr: 1.27e-03
2022-05-14 02:51:52,654 INFO [train.py:812] (4/8) Epoch 5, batch 4350, loss[loss=0.1952, simple_loss=0.2875, pruned_loss=0.05149, over 7417.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2939, pruned_loss=0.06914, over 1415349.57 frames.], batch size: 21, lr: 1.27e-03
2022-05-14 02:52:52,061 INFO [train.py:812] (4/8) Epoch 5, batch 4400, loss[loss=0.2049, simple_loss=0.2777, pruned_loss=0.06603, over 7258.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2937, pruned_loss=0.06886, over 1411869.12 frames.], batch size: 19, lr: 1.27e-03
2022-05-14 02:53:51,761 INFO [train.py:812] (4/8) Epoch 5, batch 4450, loss[loss=0.1963, simple_loss=0.2837, pruned_loss=0.05444, over 6882.00 frames.], tot_loss[loss=0.217, simple_loss=0.2949, pruned_loss=0.06953, over 1405570.56 frames.], batch size: 31, lr: 1.27e-03
2022-05-14 02:54:49,533 INFO [train.py:812] (4/8) Epoch 5, batch 4500, loss[loss=0.2598, simple_loss=0.3237, pruned_loss=0.09795, over 4816.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2964, pruned_loss=0.07015, over 1394741.34 frames.], batch size: 52, lr: 1.27e-03
2022-05-14 02:55:48,811 INFO [train.py:812] (4/8) Epoch 5, batch 4550, loss[loss=0.2852, simple_loss=0.3379, pruned_loss=0.1162, over 4860.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2992, pruned_loss=0.07308, over 1337079.29 frames.], batch size: 52, lr: 1.26e-03
2022-05-14 02:56:57,110 INFO [train.py:812] (4/8) Epoch 6, batch 0, loss[loss=0.204, simple_loss=0.2833, pruned_loss=0.06234, over 7159.00 frames.], tot_loss[loss=0.204, simple_loss=0.2833, pruned_loss=0.06234, over 7159.00 frames.], batch size: 19, lr: 1.21e-03
2022-05-14 02:57:56,761 INFO [train.py:812] (4/8) Epoch 6, batch 50, loss[loss=0.2495, simple_loss=0.3042, pruned_loss=0.09736, over 5237.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2927, pruned_loss=0.06895, over 319467.42 frames.], batch size: 52, lr: 1.21e-03
2022-05-14 02:58:56,406 INFO [train.py:812] (4/8) Epoch 6, batch 100, loss[loss=0.2403, simple_loss=0.3201, pruned_loss=0.08028, over 7142.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2941, pruned_loss=0.06817, over 562339.50 frames.], batch size: 20, lr: 1.21e-03
2022-05-14 02:59:55,389 INFO [train.py:812] (4/8) Epoch 6, batch 150, loss[loss=0.2248, simple_loss=0.3105, pruned_loss=0.06952, over 6768.00 frames.], tot_loss[loss=0.2127, simple_loss=0.292, pruned_loss=0.06664, over 749292.44 frames.], batch size: 31, lr: 1.21e-03
2022-05-14 03:00:54,858 INFO [train.py:812] (4/8) Epoch 6, batch 200, loss[loss=0.1972, simple_loss=0.2786, pruned_loss=0.05787, over 7418.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2897, pruned_loss=0.06464, over 899603.21 frames.], batch size: 18, lr: 1.21e-03
2022-05-14 03:01:54,416 INFO [train.py:812] (4/8) Epoch 6, batch 250, loss[loss=0.2265, simple_loss=0.3115, pruned_loss=0.0707, over 7331.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2901, pruned_loss=0.06478, over 1019739.57 frames.], batch size: 22, lr: 1.21e-03
2022-05-14 03:02:54,506 INFO [train.py:812] (4/8) Epoch 6, batch 300, loss[loss=0.1997, simple_loss=0.2869, pruned_loss=0.05628, over 7223.00 frames.], tot_loss[loss=0.2089, simple_loss=0.289, pruned_loss=0.06438, over 1111878.57 frames.], batch size: 20, lr: 1.21e-03
2022-05-14 03:03:51,874 INFO [train.py:812] (4/8) Epoch 6, batch 350, loss[loss=0.2256, simple_loss=0.3075, pruned_loss=0.07183, over 7339.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2878, pruned_loss=0.06496, over 1185296.72 frames.], batch size: 20, lr: 1.20e-03
2022-05-14 03:04:49,930 INFO [train.py:812] (4/8) Epoch 6, batch 400, loss[loss=0.2235, simple_loss=0.3095, pruned_loss=0.0687, over 7380.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2891, pruned_loss=0.06534, over 1236774.51 frames.], batch size: 23, lr: 1.20e-03
2022-05-14 03:05:47,791 INFO [train.py:812] (4/8) Epoch 6, batch 450, loss[loss=0.209, simple_loss=0.2734, pruned_loss=0.07233, over 6794.00 frames.], tot_loss[loss=0.209, simple_loss=0.2883, pruned_loss=0.06483, over 1279220.68 frames.], batch size: 15, lr: 1.20e-03
2022-05-14 03:06:47,289 INFO [train.py:812] (4/8) Epoch 6, batch 500, loss[loss=0.2266, simple_loss=0.3026, pruned_loss=0.07535, over 5100.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2894, pruned_loss=0.06534, over 1308458.15 frames.], batch size: 52, lr: 1.20e-03
2022-05-14 03:07:45,163 INFO [train.py:812] (4/8) Epoch 6, batch 550, loss[loss=0.2108, simple_loss=0.2973, pruned_loss=0.06215, over 6321.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2889, pruned_loss=0.06491, over 1332810.29 frames.], batch size: 37, lr: 1.20e-03
2022-05-14 03:08:43,996 INFO [train.py:812] (4/8) Epoch 6, batch 600, loss[loss=0.2047, simple_loss=0.2813, pruned_loss=0.06404, over 7158.00 frames.], tot_loss[loss=0.209, simple_loss=0.2883, pruned_loss=0.06484, over 1352121.42 frames.], batch size: 20, lr: 1.20e-03
2022-05-14 03:09:42,699 INFO [train.py:812] (4/8) Epoch 6, batch 650, loss[loss=0.2152, simple_loss=0.2997, pruned_loss=0.06535, over 7409.00 frames.], tot_loss[loss=0.209, simple_loss=0.2884, pruned_loss=0.06481, over 1366449.56 frames.], batch size: 21, lr: 1.20e-03
2022-05-14 03:10:42,152 INFO [train.py:812] (4/8) Epoch 6, batch 700, loss[loss=0.2223, simple_loss=0.3007, pruned_loss=0.07194, over 7248.00 frames.], tot_loss[loss=0.2094, simple_loss=0.289, pruned_loss=0.06488, over 1379354.74 frames.], batch size: 16, lr: 1.20e-03
2022-05-14 03:11:41,180 INFO [train.py:812] (4/8) Epoch 6, batch 750, loss[loss=0.2417, simple_loss=0.3216, pruned_loss=0.08084, over 7216.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2904, pruned_loss=0.06532, over 1388565.02 frames.], batch size: 21, lr: 1.19e-03
2022-05-14 03:12:41,105 INFO [train.py:812] (4/8) Epoch 6, batch 800, loss[loss=0.2649, simple_loss=0.3339, pruned_loss=0.09794, over 7226.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2887, pruned_loss=0.06441, over 1399070.07 frames.], batch size: 21, lr: 1.19e-03
2022-05-14 03:13:40,484 INFO [train.py:812] (4/8) Epoch 6, batch 850, loss[loss=0.2194, simple_loss=0.3052, pruned_loss=0.06678, over 7193.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2889, pruned_loss=0.06449, over 1404419.71 frames.], batch size: 23, lr: 1.19e-03
2022-05-14 03:14:39,814 INFO [train.py:812] (4/8) Epoch 6, batch 900, loss[loss=0.2347, simple_loss=0.3199, pruned_loss=0.07478, over 7411.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2893, pruned_loss=0.06473, over 1405715.01 frames.], batch size: 21, lr: 1.19e-03
2022-05-14 03:15:38,550 INFO [train.py:812] (4/8) Epoch 6, batch 950, loss[loss=0.1731, simple_loss=0.2487, pruned_loss=0.04871, over 7134.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2893, pruned_loss=0.0646, over 1406853.07 frames.], batch size: 17, lr: 1.19e-03
2022-05-14 03:16:37,955 INFO [train.py:812] (4/8) Epoch 6, batch 1000, loss[loss=0.204, simple_loss=0.2889, pruned_loss=0.05959, over 7414.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2902, pruned_loss=0.06538, over 1409292.35 frames.], batch size: 21, lr: 1.19e-03
2022-05-14 03:17:36,235 INFO [train.py:812] (4/8) Epoch 6, batch 1050, loss[loss=0.1859, simple_loss=0.2669, pruned_loss=0.05246, over 7327.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2908, pruned_loss=0.06601, over 1414213.23 frames.], batch size: 20, lr: 1.19e-03
2022-05-14 03:18:39,064 INFO [train.py:812] (4/8) Epoch 6, batch 1100, loss[loss=0.1799, simple_loss=0.2646, pruned_loss=0.0476, over 7322.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2916, pruned_loss=0.06659, over 1409767.71 frames.], batch size: 21, lr: 1.19e-03
2022-05-14 03:19:37,381 INFO [train.py:812] (4/8) Epoch 6, batch 1150, loss[loss=0.2503, simple_loss=0.3159, pruned_loss=0.09235, over 7151.00 frames.], tot_loss[loss=0.214, simple_loss=0.2931, pruned_loss=0.06741, over 1413715.86 frames.], batch size: 20, lr: 1.19e-03
2022-05-14 03:20:36,644 INFO [train.py:812] (4/8) Epoch 6, batch 1200, loss[loss=0.2065, simple_loss=0.2897, pruned_loss=0.06163, over 7156.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2913, pruned_loss=0.06656, over 1414448.11 frames.], batch size: 26, lr: 1.18e-03
2022-05-14 03:21:34,757 INFO [train.py:812] (4/8) Epoch 6, batch 1250, loss[loss=0.1942, simple_loss=0.2795, pruned_loss=0.05447, over 7149.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2905, pruned_loss=0.06614, over 1413524.51 frames.], batch size: 20, lr: 1.18e-03
2022-05-14 03:22:34,581 INFO [train.py:812] (4/8) Epoch 6, batch 1300, loss[loss=0.1815, simple_loss=0.257, pruned_loss=0.05304, over 7346.00 frames.], tot_loss[loss=0.2119, simple_loss=0.2901, pruned_loss=0.06691, over 1410940.97 frames.], batch size: 19, lr: 1.18e-03
2022-05-14 03:23:33,469 INFO [train.py:812] (4/8) Epoch 6, batch 1350, loss[loss=0.207, simple_loss=0.2977, pruned_loss=0.05816, over 6990.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2876, pruned_loss=0.06547, over 1414567.01 frames.], batch size: 28, lr: 1.18e-03
2022-05-14 03:24:32,545 INFO [train.py:812] (4/8) Epoch 6, batch 1400, loss[loss=0.192, simple_loss=0.2758, pruned_loss=0.05411, over 7336.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2875, pruned_loss=0.06467, over 1418406.25 frames.], batch size: 20, lr: 1.18e-03
2022-05-14 03:25:31,687 INFO [train.py:812] (4/8) Epoch 6, batch 1450, loss[loss=0.1682, simple_loss=0.2625, pruned_loss=0.03701, over 7430.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2866, pruned_loss=0.06389, over 1420257.65 frames.], batch size: 20, lr: 1.18e-03
2022-05-14 03:26:31,151 INFO [train.py:812] (4/8) Epoch 6, batch 1500, loss[loss=0.2593, simple_loss=0.3342, pruned_loss=0.09215, over 7142.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2868, pruned_loss=0.06404, over 1420774.70 frames.], batch size: 20, lr: 1.18e-03
2022-05-14 03:27:30,168 INFO [train.py:812] (4/8) Epoch 6, batch 1550, loss[loss=0.1584, simple_loss=0.2368, pruned_loss=0.04002, over 7253.00 frames.], tot_loss[loss=0.2073, simple_loss=0.287, pruned_loss=0.06382, over 1423608.99 frames.], batch size: 17, lr: 1.18e-03
2022-05-14 03:28:29,751 INFO [train.py:812] (4/8) Epoch 6, batch 1600, loss[loss=0.2144, simple_loss=0.2953, pruned_loss=0.06676, over 7423.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2873, pruned_loss=0.0642, over 1417032.90 frames.], batch size: 20, lr: 1.17e-03
2022-05-14 03:29:29,243 INFO [train.py:812] (4/8) Epoch 6, batch 1650, loss[loss=0.2519, simple_loss=0.318, pruned_loss=0.09289, over 7328.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2877, pruned_loss=0.06478, over 1416863.31 frames.], batch size: 25, lr: 1.17e-03
2022-05-14 03:30:27,833 INFO [train.py:812] (4/8) Epoch 6, batch 1700, loss[loss=0.2397, simple_loss=0.3087, pruned_loss=0.08537, over 7215.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2883, pruned_loss=0.06493, over 1414662.51 frames.], batch size: 22, lr: 1.17e-03
2022-05-14 03:31:26,907 INFO [train.py:812] (4/8) Epoch 6, batch 1750, loss[loss=0.1658, simple_loss=0.2435, pruned_loss=0.04402, over 7278.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2888, pruned_loss=0.06499, over 1411847.24 frames.], batch size: 18, lr: 1.17e-03
2022-05-14 03:32:26,450 INFO [train.py:812] (4/8) Epoch 6, batch 1800, loss[loss=0.2696, simple_loss=0.3256, pruned_loss=0.1068, over 5164.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2893, pruned_loss=0.06524, over 1413665.72 frames.], batch size: 52, lr: 1.17e-03
2022-05-14 03:33:25,527 INFO [train.py:812] (4/8) Epoch 6, batch 1850, loss[loss=0.2089, simple_loss=0.2888, pruned_loss=0.06452, over 7171.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2891, pruned_loss=0.0652, over 1416448.38 frames.], batch size: 18, lr: 1.17e-03
2022-05-14 03:34:24,874 INFO [train.py:812] (4/8) Epoch 6, batch 1900, loss[loss=0.1829, simple_loss=0.2574, pruned_loss=0.05421, over 7135.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2892, pruned_loss=0.06527, over 1415497.53 frames.], batch size: 17, lr: 1.17e-03
2022-05-14 03:35:23,962 INFO [train.py:812] (4/8) Epoch 6, batch 1950, loss[loss=0.2379, simple_loss=0.3283, pruned_loss=0.07374, over 7108.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2893, pruned_loss=0.06487, over 1420669.10 frames.], batch size: 21, lr: 1.17e-03
2022-05-14 03:36:21,513 INFO [train.py:812] (4/8) Epoch 6, batch 2000, loss[loss=0.2272, simple_loss=0.2949, pruned_loss=0.07975, over 7274.00 frames.], tot_loss[loss=0.2101, simple_loss=0.29, pruned_loss=0.06515, over 1424128.25 frames.], batch size: 18, lr: 1.17e-03
2022-05-14 03:37:19,514 INFO [train.py:812] (4/8) Epoch 6, batch 2050, loss[loss=0.2046, simple_loss=0.2907, pruned_loss=0.05924, over 7033.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2905, pruned_loss=0.06533, over 1424689.82 frames.], batch size: 28, lr: 1.16e-03
2022-05-14 03:38:19,355 INFO [train.py:812] (4/8) Epoch 6, batch 2100, loss[loss=0.2434, simple_loss=0.3209, pruned_loss=0.08296, over 6498.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2905, pruned_loss=0.06521, over 1426003.91 frames.], batch size: 38, lr: 1.16e-03
2022-05-14 03:39:18,996 INFO [train.py:812] (4/8) Epoch 6, batch 2150, loss[loss=0.232, simple_loss=0.306, pruned_loss=0.07905, over 7149.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2891, pruned_loss=0.0645, over 1430771.34 frames.], batch size: 20, lr: 1.16e-03
2022-05-14 03:40:18,673 INFO [train.py:812] (4/8) Epoch 6, batch 2200, loss[loss=0.2483, simple_loss=0.3276, pruned_loss=0.08447, over 7144.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2884, pruned_loss=0.06409, over 1427223.91 frames.], batch size: 20, lr: 1.16e-03
2022-05-14 03:41:17,649 INFO [train.py:812] (4/8) Epoch 6, batch 2250, loss[loss=0.1835, simple_loss=0.2612, pruned_loss=0.0529, over 7360.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2873, pruned_loss=0.06352, over 1425512.34 frames.], batch size: 19, lr: 1.16e-03
2022-05-14 03:42:16,655 INFO [train.py:812] (4/8) Epoch 6, batch 2300, loss[loss=0.1986, simple_loss=0.2807, pruned_loss=0.05828, over 7308.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2872, pruned_loss=0.06362, over 1422197.33 frames.], batch size: 24, lr: 1.16e-03
2022-05-14 03:43:15,834 INFO [train.py:812] (4/8) Epoch 6, batch 2350, loss[loss=0.1873, simple_loss=0.2809, pruned_loss=0.04685, over 7227.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2864, pruned_loss=0.06303, over 1421733.61 frames.], batch size: 21, lr: 1.16e-03
2022-05-14 03:44:15,946 INFO [train.py:812] (4/8) Epoch 6, batch 2400, loss[loss=0.194, simple_loss=0.2839, pruned_loss=0.0521, over 7324.00 frames.], tot_loss[loss=0.205, simple_loss=0.285, pruned_loss=0.06256, over 1421730.08 frames.], batch size: 20, lr: 1.16e-03
2022-05-14 03:45:14,488 INFO [train.py:812] (4/8) Epoch 6, batch 2450, loss[loss=0.1968, simple_loss=0.2749, pruned_loss=0.05938, over 6774.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2837, pruned_loss=0.06193, over 1420993.44 frames.], batch size: 15, lr: 1.16e-03
2022-05-14 03:46:13,712 INFO [train.py:812] (4/8) Epoch 6, batch 2500, loss[loss=0.2195, simple_loss=0.302, pruned_loss=0.06853, over 7326.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2843, pruned_loss=0.06203, over 1419934.83 frames.], batch size: 22, lr: 1.15e-03
2022-05-14 03:47:11,213 INFO [train.py:812] (4/8) Epoch 6, batch 2550, loss[loss=0.1865, simple_loss=0.2564, pruned_loss=0.05837, over 6818.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2841, pruned_loss=0.06176, over 1422242.57 frames.], batch size: 15, lr: 1.15e-03
2022-05-14 03:48:09,669 INFO [train.py:812] (4/8) Epoch 6, batch 2600, loss[loss=0.2077, simple_loss=0.3005, pruned_loss=0.05749, over 7298.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2851, pruned_loss=0.06184, over 1425389.28 frames.], batch size: 21, lr: 1.15e-03
2022-05-14 03:49:08,324 INFO [train.py:812] (4/8) Epoch 6, batch 2650, loss[loss=0.2536, simple_loss=0.3367, pruned_loss=0.08529, over 7273.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2863, pruned_loss=0.06219, over 1423917.15 frames.], batch size: 25, lr: 1.15e-03
2022-05-14 03:50:08,410 INFO [train.py:812] (4/8) Epoch 6, batch 2700, loss[loss=0.2128, simple_loss=0.2837, pruned_loss=0.07099, over 6774.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2867, pruned_loss=0.06251, over 1425865.29 frames.], batch size: 15, lr: 1.15e-03
2022-05-14 03:51:06,476 INFO [train.py:812] (4/8) Epoch 6, batch 2750, loss[loss=0.1813, simple_loss=0.2761, pruned_loss=0.04326, over 7225.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2878, pruned_loss=0.06289, over 1423859.55 frames.], batch size: 20, lr: 1.15e-03
2022-05-14 03:52:05,465 INFO [train.py:812] (4/8) Epoch 6, batch 2800, loss[loss=0.199, simple_loss=0.2825, pruned_loss=0.05771, over 7275.00 frames.], tot_loss[loss=0.207, simple_loss=0.2877, pruned_loss=0.06312, over 1421986.38 frames.], batch size: 18, lr: 1.15e-03
2022-05-14 03:53:03,381 INFO [train.py:812] (4/8) Epoch 6, batch 2850, loss[loss=0.1799, simple_loss=0.2605, pruned_loss=0.04963, over 7282.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2872, pruned_loss=0.06293, over 1419200.25 frames.], batch size: 17, lr: 1.15e-03
2022-05-14 03:54:00,909 INFO [train.py:812] (4/8) Epoch 6, batch 2900, loss[loss=0.1974, simple_loss=0.2785, pruned_loss=0.05812, over 6666.00 frames.], tot_loss[loss=0.206, simple_loss=0.2868, pruned_loss=0.06261, over 1421013.49 frames.], batch size: 31, lr: 1.15e-03
2022-05-14 03:54:58,719 INFO [train.py:812] (4/8) Epoch 6, batch 2950, loss[loss=0.2009, simple_loss=0.2875, pruned_loss=0.05713, over 7154.00 frames.], tot_loss[loss=0.2054, simple_loss=0.286, pruned_loss=0.06237, over 1420902.20 frames.], batch size: 20, lr: 1.14e-03
2022-05-14 03:55:55,714 INFO [train.py:812] (4/8) Epoch 6, batch 3000, loss[loss=0.2054, simple_loss=0.2824, pruned_loss=0.06416, over 7224.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2861, pruned_loss=0.06271, over 1420311.56 frames.], batch size: 20, lr: 1.14e-03
2022-05-14 03:55:55,715 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 03:56:03,339 INFO [train.py:841] (4/8) Epoch 6, validation: loss=0.1668, simple_loss=0.2696, pruned_loss=0.03205, over 698248.00 frames.
2022-05-14 03:57:02,143 INFO [train.py:812] (4/8) Epoch 6, batch 3050, loss[loss=0.2692, simple_loss=0.3388, pruned_loss=0.09984, over 7193.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2855, pruned_loss=0.06241, over 1426050.29 frames.], batch size: 23, lr: 1.14e-03
2022-05-14 03:58:01,681 INFO [train.py:812] (4/8) Epoch 6, batch 3100, loss[loss=0.2157, simple_loss=0.2949, pruned_loss=0.06829, over 7327.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2855, pruned_loss=0.06263, over 1423629.20 frames.], batch size: 22, lr: 1.14e-03
2022-05-14 03:58:58,840 INFO [train.py:812] (4/8) Epoch 6, batch 3150, loss[loss=0.2252, simple_loss=0.3039, pruned_loss=0.07323, over 7219.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2871, pruned_loss=0.06353, over 1423698.24 frames.], batch size: 23, lr: 1.14e-03
2022-05-14 03:59:57,533 INFO [train.py:812] (4/8) Epoch 6, batch 3200, loss[loss=0.2401, simple_loss=0.3147, pruned_loss=0.08273, over 7213.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2875, pruned_loss=0.06368, over 1424578.69 frames.], batch size: 21, lr: 1.14e-03
2022-05-14 04:00:56,302 INFO [train.py:812] (4/8) Epoch 6, batch 3250, loss[loss=0.2126, simple_loss=0.2798, pruned_loss=0.0727, over 7359.00 frames.], tot_loss[loss=0.208, simple_loss=0.2882, pruned_loss=0.06389, over 1424411.10 frames.], batch size: 19, lr: 1.14e-03
2022-05-14 04:01:55,491 INFO [train.py:812] (4/8) Epoch 6, batch 3300, loss[loss=0.2456, simple_loss=0.3194, pruned_loss=0.08592, over 7203.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2888, pruned_loss=0.06447, over 1420752.57 frames.], batch size: 23, lr: 1.14e-03
2022-05-14 04:02:54,523 INFO [train.py:812] (4/8) Epoch 6, batch 3350, loss[loss=0.2001, simple_loss=0.2699, pruned_loss=0.06513, over 7259.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2871, pruned_loss=0.0638, over 1424842.68 frames.], batch size: 19, lr: 1.14e-03
2022-05-14 04:03:53,906 INFO [train.py:812] (4/8) Epoch 6, batch 3400, loss[loss=0.1894, simple_loss=0.2788, pruned_loss=0.04998, over 7273.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2866, pruned_loss=0.06344, over 1425039.69 frames.], batch size: 24, lr: 1.14e-03
2022-05-14 04:04:52,392 INFO [train.py:812] (4/8) Epoch 6, batch 3450, loss[loss=0.1855, simple_loss=0.2778, pruned_loss=0.0466, over 7421.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2883, pruned_loss=0.06413, over 1426984.18 frames.], batch size: 21, lr: 1.13e-03
2022-05-14 04:05:50,783 INFO [train.py:812] (4/8) Epoch 6, batch 3500, loss[loss=0.2049, simple_loss=0.2914, pruned_loss=0.05922, over 7195.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2868, pruned_loss=0.06338, over 1424493.06 frames.], batch size: 22, lr: 1.13e-03
2022-05-14 04:06:49,096 INFO [train.py:812] (4/8) Epoch 6, batch 3550, loss[loss=0.2021, simple_loss=0.3015, pruned_loss=0.05132, over 7323.00 frames.], tot_loss[loss=0.2056, simple_loss=0.286, pruned_loss=0.06258, over 1427289.89 frames.], batch size: 21, lr: 1.13e-03
2022-05-14 04:07:47,617 INFO [train.py:812] (4/8) Epoch 6, batch 3600, loss[loss=0.1877, simple_loss=0.2555, pruned_loss=0.05994, over 7172.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2851, pruned_loss=0.06224, over 1428829.62 frames.], batch size: 18, lr: 1.13e-03
2022-05-14 04:08:46,806 INFO [train.py:812] (4/8) Epoch 6, batch 3650, loss[loss=0.2414, simple_loss=0.3152, pruned_loss=0.08381, over 7414.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2849, pruned_loss=0.06195, over 1428144.24 frames.], batch size: 21, lr: 1.13e-03
2022-05-14 04:09:44,219 INFO [train.py:812] (4/8) Epoch 6, batch 3700, loss[loss=0.2165, simple_loss=0.2966, pruned_loss=0.06823, over 7231.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2852, pruned_loss=0.06192, over 1426043.62 frames.], batch size: 20, lr: 1.13e-03
2022-05-14 04:10:41,359 INFO [train.py:812] (4/8) Epoch 6, batch 3750, loss[loss=0.241, simple_loss=0.3208, pruned_loss=0.0806, over 7366.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2849, pruned_loss=0.06168, over 1424388.13 frames.], batch size: 23, lr: 1.13e-03
2022-05-14 04:11:40,657 INFO [train.py:812] (4/8) Epoch 6, batch 3800, loss[loss=0.2338, simple_loss=0.3183, pruned_loss=0.07459, over 7244.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2844, pruned_loss=0.06136, over 1419937.16 frames.], batch size: 20, lr: 1.13e-03
2022-05-14 04:12:39,822 INFO [train.py:812] (4/8) Epoch 6, batch 3850, loss[loss=0.1746, simple_loss=0.2604, pruned_loss=0.04441, over 7437.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2854, pruned_loss=0.0618, over 1420826.26 frames.], batch size: 20, lr: 1.13e-03
2022-05-14 04:13:39,009 INFO [train.py:812] (4/8) Epoch 6, batch 3900, loss[loss=0.1817, simple_loss=0.2543, pruned_loss=0.05456, over 7405.00 frames.], tot_loss[loss=0.204, simple_loss=0.2848, pruned_loss=0.06163, over 1424997.32 frames.], batch size: 18, lr: 1.13e-03
2022-05-14 04:14:38,338 INFO [train.py:812] (4/8) Epoch 6, batch 3950, loss[loss=0.2354, simple_loss=0.3171, pruned_loss=0.07689, over 7287.00 frames.], tot_loss[loss=0.2037, simple_loss=0.284, pruned_loss=0.06167, over 1423640.25 frames.], batch size: 24, lr: 1.12e-03
2022-05-14 04:15:37,079 INFO [train.py:812] (4/8) Epoch 6, batch 4000, loss[loss=0.255, simple_loss=0.3288, pruned_loss=0.09056, over 7211.00 frames.], tot_loss[loss=0.205, simple_loss=0.2855, pruned_loss=0.06227, over 1426161.92 frames.], batch size: 23, lr: 1.12e-03
2022-05-14 04:16:34,886 INFO [train.py:812] (4/8) Epoch 6, batch 4050, loss[loss=0.2603, simple_loss=0.3329, pruned_loss=0.09389, over 7289.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2865, pruned_loss=0.06287, over 1426874.67 frames.], batch size: 24, lr: 1.12e-03
2022-05-14 04:17:34,622 INFO [train.py:812] (4/8) Epoch 6, batch 4100, loss[loss=0.1884, simple_loss=0.263, pruned_loss=0.05695, over 7415.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2853, pruned_loss=0.06247, over 1427440.23 frames.], batch size: 18, lr: 1.12e-03
2022-05-14 04:18:33,849 INFO [train.py:812] (4/8) Epoch 6, batch 4150, loss[loss=0.2182, simple_loss=0.3089, pruned_loss=0.06372, over 6797.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2845, pruned_loss=0.06223, over 1427605.93 frames.], batch size: 31, lr: 1.12e-03
2022-05-14 04:19:32,908 INFO [train.py:812] (4/8) Epoch 6, batch 4200, loss[loss=0.2346, simple_loss=0.3154, pruned_loss=0.07686, over 7107.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2846, pruned_loss=0.06253, over 1428929.27 frames.], batch size: 21, lr: 1.12e-03
2022-05-14 04:20:33,098 INFO [train.py:812] (4/8) Epoch 6, batch 4250, loss[loss=0.2307, simple_loss=0.3145, pruned_loss=0.07342, over 7376.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2848, pruned_loss=0.06246, over 1429487.60 frames.], batch size: 23, lr: 1.12e-03
2022-05-14 04:21:32,397 INFO [train.py:812] (4/8) Epoch 6, batch 4300, loss[loss=0.1937, simple_loss=0.2835, pruned_loss=0.05192, over 7067.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2851, pruned_loss=0.06281, over 1424142.11 frames.], batch size: 18, lr: 1.12e-03
2022-05-14 04:22:31,661 INFO [train.py:812] (4/8) Epoch 6, batch 4350, loss[loss=0.1845, simple_loss=0.2827, pruned_loss=0.04316, over 7229.00 frames.], tot_loss[loss=0.2052, simple_loss=0.285, pruned_loss=0.06269, over 1424201.69 frames.], batch size: 21, lr: 1.12e-03
2022-05-14 04:23:31,431 INFO [train.py:812] (4/8) Epoch 6, batch 4400, loss[loss=0.203, simple_loss=0.2814, pruned_loss=0.06229, over 7443.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2832, pruned_loss=0.06179, over 1422567.45 frames.], batch size: 20, lr: 1.12e-03
2022-05-14 04:24:30,573 INFO [train.py:812] (4/8) Epoch 6, batch 4450, loss[loss=0.179, simple_loss=0.2543, pruned_loss=0.05183, over 7274.00 frames.], tot_loss[loss=0.204, simple_loss=0.2836, pruned_loss=0.06219, over 1408900.50 frames.], batch size: 17, lr: 1.11e-03
2022-05-14 04:25:38,566 INFO [train.py:812] (4/8) Epoch 6, batch 4500, loss[loss=0.1955, simple_loss=0.2754, pruned_loss=0.0578, over 7232.00 frames.], tot_loss[loss=0.2019, simple_loss=0.281, pruned_loss=0.06139, over 1408245.29 frames.], batch size: 20, lr: 1.11e-03
2022-05-14 04:26:36,432 INFO [train.py:812] (4/8) Epoch 6, batch 4550, loss[loss=0.3067, simple_loss=0.3653, pruned_loss=0.124, over 5127.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2844, pruned_loss=0.06427, over 1359299.34 frames.], batch size: 52, lr: 1.11e-03
2022-05-14 04:27:44,592 INFO [train.py:812] (4/8) Epoch 7, batch 0, loss[loss=0.1818, simple_loss=0.265, pruned_loss=0.0493, over 7412.00 frames.], tot_loss[loss=0.1818, simple_loss=0.265, pruned_loss=0.0493, over 7412.00 frames.], batch size: 18, lr: 1.07e-03
2022-05-14 04:28:43,242 INFO [train.py:812] (4/8) Epoch 7, batch 50, loss[loss=0.1736, simple_loss=0.2482, pruned_loss=0.04948, over 7409.00 frames.], tot_loss[loss=0.1955, simple_loss=0.276, pruned_loss=0.05753, over 323101.49 frames.], batch size: 18, lr: 1.07e-03
2022-05-14 04:29:42,455 INFO [train.py:812] (4/8) Epoch 7, batch 100, loss[loss=0.1879, simple_loss=0.2684, pruned_loss=0.05369, over 7144.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2784, pruned_loss=0.05763, over 567543.02 frames.], batch size: 19, lr: 1.06e-03
2022-05-14 04:30:41,783 INFO [train.py:812] (4/8) Epoch 7, batch 150, loss[loss=0.1945, simple_loss=0.2779, pruned_loss=0.05558, over 7162.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2803, pruned_loss=0.05845, over 757775.76 frames.], batch size: 19, lr: 1.06e-03
2022-05-14 04:31:41,617 INFO [train.py:812] (4/8) Epoch 7, batch 200, loss[loss=0.2638, simple_loss=0.3299, pruned_loss=0.09886, over 7379.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2819, pruned_loss=0.05976, over 907154.22 frames.], batch size: 23, lr: 1.06e-03
2022-05-14 04:32:39,932 INFO [train.py:812] (4/8) Epoch 7, batch 250, loss[loss=0.2269, simple_loss=0.3054, pruned_loss=0.07414, over 7139.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2825, pruned_loss=0.06027, over 1021371.12 frames.], batch size: 20, lr: 1.06e-03
2022-05-14 04:33:39,358 INFO [train.py:812] (4/8) Epoch 7, batch 300, loss[loss=0.1657, simple_loss=0.2377, pruned_loss=0.04683, over 7273.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2829, pruned_loss=0.06016, over 1107525.18 frames.], batch size: 16, lr: 1.06e-03
2022-05-14 04:34:57,021 INFO [train.py:812] (4/8) Epoch 7, batch 350, loss[loss=0.2164, simple_loss=0.2889, pruned_loss=0.07197, over 7119.00 frames.], tot_loss[loss=0.201, simple_loss=0.2826, pruned_loss=0.05974, over 1178837.73 frames.], batch size: 21, lr: 1.06e-03
2022-05-14 04:35:53,852 INFO [train.py:812] (4/8) Epoch 7, batch 400, loss[loss=0.1959, simple_loss=0.2866, pruned_loss=0.05259, over 7160.00 frames.], tot_loss[loss=0.2023, simple_loss=0.284, pruned_loss=0.06027, over 1231005.05 frames.], batch size: 18, lr: 1.06e-03
2022-05-14 04:37:20,598 INFO [train.py:812] (4/8) Epoch 7, batch 450, loss[loss=0.2248, simple_loss=0.2938, pruned_loss=0.07791, over 7360.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2837, pruned_loss=0.06027, over 1276390.72 frames.], batch size: 19, lr: 1.06e-03
2022-05-14 04:38:43,155 INFO [train.py:812] (4/8) Epoch 7, batch 500, loss[loss=0.2099, simple_loss=0.2888, pruned_loss=0.0655, over 6333.00 frames.], tot_loss[loss=0.2027, simple_loss=0.284, pruned_loss=0.06063, over 1305001.76 frames.], batch size: 37, lr: 1.06e-03
2022-05-14 04:39:42,043 INFO [train.py:812] (4/8) Epoch 7, batch 550, loss[loss=0.2172, simple_loss=0.288, pruned_loss=0.07324, over 7116.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2823, pruned_loss=0.06008, over 1329644.85 frames.], batch size: 21, lr: 1.06e-03
2022-05-14 04:40:39,508 INFO [train.py:812] (4/8) Epoch 7, batch 600, loss[loss=0.1951, simple_loss=0.2823, pruned_loss=0.05394, over 7002.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2829, pruned_loss=0.06033, over 1348457.85 frames.], batch size: 28, lr: 1.06e-03
2022-05-14 04:41:38,881 INFO [train.py:812] (4/8) Epoch 7, batch 650, loss[loss=0.2645, simple_loss=0.3286, pruned_loss=0.1002, over 5007.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2812, pruned_loss=0.05946, over 1364712.67 frames.], batch size: 53, lr: 1.05e-03
2022-05-14 04:42:37,558 INFO [train.py:812] (4/8) Epoch 7, batch 700, loss[loss=0.1718, simple_loss=0.2488, pruned_loss=0.04741, over 7168.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2805, pruned_loss=0.05887, over 1379187.80 frames.], batch size: 18, lr: 1.05e-03
2022-05-14 04:43:36,172 INFO [train.py:812] (4/8) Epoch 7, batch 750, loss[loss=0.1875, simple_loss=0.2672, pruned_loss=0.05391, over 6733.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2802, pruned_loss=0.05846, over 1392202.57 frames.], batch size: 31, lr: 1.05e-03
2022-05-14 04:44:33,653 INFO [train.py:812] (4/8) Epoch 7, batch 800, loss[loss=0.1973, simple_loss=0.2807, pruned_loss=0.057, over 7328.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2805, pruned_loss=0.05895, over 1391587.33 frames.], batch size: 20, lr: 1.05e-03
2022-05-14 04:45:32,927 INFO [train.py:812] (4/8) Epoch 7, batch 850, loss[loss=0.2365, simple_loss=0.3091, pruned_loss=0.08192, over 7284.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2807, pruned_loss=0.05895, over 1397652.68 frames.], batch size: 24, lr: 1.05e-03
2022-05-14 04:46:32,281 INFO [train.py:812] (4/8) Epoch 7, batch 900, loss[loss=0.2436, simple_loss=0.3173, pruned_loss=0.08501, over 7380.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2813, pruned_loss=0.05946, over 1403539.80 frames.], batch size: 23, lr: 1.05e-03
2022-05-14 04:47:31,118 INFO [train.py:812] (4/8) Epoch 7, batch 950, loss[loss=0.226, simple_loss=0.3065, pruned_loss=0.07274, over 7369.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2812, pruned_loss=0.05912, over 1408115.70 frames.], batch size: 23, lr: 1.05e-03
2022-05-14 04:48:29,683 INFO [train.py:812] (4/8) Epoch 7, batch 1000, loss[loss=0.1934, simple_loss=0.2944, pruned_loss=0.04617, over 7391.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2806, pruned_loss=0.05895, over 1408154.67 frames.], batch size: 23, lr: 1.05e-03
2022-05-14 04:49:29,140 INFO [train.py:812] (4/8) Epoch 7, batch 1050, loss[loss=0.1673, simple_loss=0.2576, pruned_loss=0.0385, over 7165.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2812, pruned_loss=0.05912, over 1414783.27 frames.], batch size: 19, lr: 1.05e-03
2022-05-14 04:50:29,073 INFO [train.py:812] (4/8) Epoch 7, batch 1100, loss[loss=0.2345, simple_loss=0.3275, pruned_loss=0.07076, over 7234.00 frames.], tot_loss[loss=0.1993, simple_loss=0.281, pruned_loss=0.05885, over 1418353.30 frames.], batch size: 25, lr: 1.05e-03
2022-05-14 04:51:28,387 INFO [train.py:812] (4/8) Epoch 7, batch 1150, loss[loss=0.2082, simple_loss=0.2721, pruned_loss=0.07219, over 7135.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2817, pruned_loss=0.05922, over 1416768.76 frames.], batch size: 17, lr: 1.05e-03
2022-05-14 04:52:28,299 INFO [train.py:812] (4/8) Epoch 7, batch 1200, loss[loss=0.1814, simple_loss=0.2665, pruned_loss=0.04818, over 7268.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2815, pruned_loss=0.05932, over 1412338.06 frames.], batch size: 16, lr: 1.04e-03
2022-05-14 04:53:27,879 INFO [train.py:812] (4/8) Epoch 7, batch 1250, loss[loss=0.1981, simple_loss=0.2821, pruned_loss=0.05704, over 7241.00 frames.], tot_loss[loss=0.201, simple_loss=0.2816, pruned_loss=0.06016, over 1413767.41 frames.], batch size: 20, lr: 1.04e-03
2022-05-14 04:54:25,605 INFO [train.py:812] (4/8) Epoch 7, batch 1300, loss[loss=0.1593, simple_loss=0.2529, pruned_loss=0.03283, over 7277.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2823, pruned_loss=0.06069, over 1415418.06 frames.], batch size: 17, lr: 1.04e-03
2022-05-14 04:55:24,139 INFO [train.py:812] (4/8) Epoch 7, batch 1350, loss[loss=0.1935, simple_loss=0.2792, pruned_loss=0.05396, over 7402.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2827, pruned_loss=0.06037, over 1420500.95 frames.], batch size: 21, lr: 1.04e-03
2022-05-14 04:56:22,886 INFO [train.py:812] (4/8) Epoch 7, batch 1400, loss[loss=0.2055, simple_loss=0.2868, pruned_loss=0.0621, over 7150.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2842, pruned_loss=0.06136, over 1418384.78 frames.], batch size: 19, lr: 1.04e-03
2022-05-14 04:57:22,035 INFO [train.py:812] (4/8) Epoch 7, batch 1450, loss[loss=0.2253, simple_loss=0.3122, pruned_loss=0.06924, over 6805.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2847, pruned_loss=0.06127, over 1418679.79 frames.], batch size: 31, lr: 1.04e-03
2022-05-14 04:58:20,159 INFO [train.py:812] (4/8) Epoch 7, batch 1500, loss[loss=0.1757, simple_loss=0.261, pruned_loss=0.04524, over 7408.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2838, pruned_loss=0.06053, over 1422710.42 frames.], batch size: 21, lr: 1.04e-03
2022-05-14 04:59:18,876 INFO [train.py:812] (4/8) Epoch 7, batch 1550, loss[loss=0.2202, simple_loss=0.2934, pruned_loss=0.0735, over 7113.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2831, pruned_loss=0.06014, over 1417487.62 frames.], batch size: 26, lr: 1.04e-03
2022-05-14 05:00:18,917 INFO [train.py:812] (4/8) Epoch 7, batch 1600, loss[loss=0.2155, simple_loss=0.3054, pruned_loss=0.06279, over 7106.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2825, pruned_loss=0.05952, over 1424425.56 frames.], batch size: 21, lr: 1.04e-03
2022-05-14 05:01:18,244 INFO [train.py:812] (4/8) Epoch 7, batch 1650, loss[loss=0.1526, simple_loss=0.2367, pruned_loss=0.03419, over 7069.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2822, pruned_loss=0.05998, over 1418076.04 frames.], batch size: 18, lr: 1.04e-03
2022-05-14 05:02:16,816 INFO [train.py:812] (4/8) Epoch 7, batch 1700, loss[loss=0.2232, simple_loss=0.3041, pruned_loss=0.07111, over 7201.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2821, pruned_loss=0.06011, over 1417583.14 frames.], batch size: 22, lr: 1.04e-03
2022-05-14 05:03:15,989 INFO [train.py:812] (4/8) Epoch 7, batch 1750, loss[loss=0.2408, simple_loss=0.3189, pruned_loss=0.08138, over 7329.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2823, pruned_loss=0.06034, over 1412403.64 frames.], batch size: 22, lr: 1.04e-03
2022-05-14 05:04:14,620 INFO [train.py:812] (4/8) Epoch 7, batch 1800, loss[loss=0.2351, simple_loss=0.3203, pruned_loss=0.07496, over 7341.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2838, pruned_loss=0.06048, over 1415309.93 frames.], batch size: 25, lr: 1.03e-03
2022-05-14 05:05:13,134 INFO [train.py:812] (4/8) Epoch 7, batch 1850, loss[loss=0.1735, simple_loss=0.2508, pruned_loss=0.04806, over 6995.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2838, pruned_loss=0.0605, over 1417540.86 frames.], batch size: 16, lr: 1.03e-03
2022-05-14 05:06:10,512 INFO [train.py:812] (4/8) Epoch 7, batch 1900, loss[loss=0.1794, simple_loss=0.2615, pruned_loss=0.04866, over 7055.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2845, pruned_loss=0.06095, over 1414411.76 frames.], batch size: 18, lr: 1.03e-03
2022-05-14 05:07:08,611 INFO [train.py:812] (4/8) Epoch 7, batch 1950, loss[loss=0.2084, simple_loss=0.2806, pruned_loss=0.0681, over 7273.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2834, pruned_loss=0.06007, over 1418032.02 frames.], batch size: 18, lr: 1.03e-03
2022-05-14 05:08:07,323 INFO [train.py:812] (4/8) Epoch 7, batch 2000, loss[loss=0.1976, simple_loss=0.2855, pruned_loss=0.05483, over 7294.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2834, pruned_loss=0.06041, over 1418428.23 frames.], batch size: 25, lr: 1.03e-03
2022-05-14 05:09:04,295 INFO [train.py:812] (4/8) Epoch 7, batch 2050, loss[loss=0.2086, simple_loss=0.2884, pruned_loss=0.06434, over 7284.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2845, pruned_loss=0.06156, over 1414939.55 frames.], batch size: 24, lr: 1.03e-03
2022-05-14 05:10:01,686 INFO [train.py:812] (4/8) Epoch 7, batch 2100, loss[loss=0.1612, simple_loss=0.2399, pruned_loss=0.04119, over 7441.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2831, pruned_loss=0.06059, over 1418421.71 frames.], batch size: 17, lr: 1.03e-03
2022-05-14 05:11:00,089 INFO [train.py:812] (4/8) Epoch 7, batch 2150, loss[loss=0.2061, simple_loss=0.2882, pruned_loss=0.06196, over 7408.00 frames.], tot_loss[loss=0.202, simple_loss=0.2836, pruned_loss=0.06023, over 1423866.85 frames.], batch size: 21, lr: 1.03e-03
2022-05-14 05:11:57,839 INFO [train.py:812] (4/8) Epoch 7, batch 2200, loss[loss=0.1767, simple_loss=0.2542, pruned_loss=0.04956, over 7146.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2833, pruned_loss=0.05988, over 1422286.76 frames.], batch size: 17, lr: 1.03e-03
2022-05-14 05:12:56,728 INFO [train.py:812] (4/8) Epoch 7, batch 2250, loss[loss=0.1675, simple_loss=0.2432, pruned_loss=0.04591, over 7270.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2841, pruned_loss=0.06064, over 1417028.64 frames.], batch size: 17, lr: 1.03e-03
2022-05-14 05:13:54,321 INFO [train.py:812] (4/8) Epoch 7, batch 2300, loss[loss=0.2114, simple_loss=0.2907, pruned_loss=0.06611, over 7203.00 frames.], tot_loss[loss=0.202, simple_loss=0.2835, pruned_loss=0.06025, over 1419826.51 frames.], batch size: 23, lr: 1.03e-03
2022-05-14 05:14:53,679 INFO [train.py:812] (4/8) Epoch 7, batch 2350, loss[loss=0.2204, simple_loss=0.2998, pruned_loss=0.07052, over 7412.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2834, pruned_loss=0.06041, over 1417629.63 frames.], batch size: 21, lr: 1.02e-03
2022-05-14 05:15:53,762 INFO [train.py:812] (4/8) Epoch 7, batch 2400, loss[loss=0.1955, simple_loss=0.2692, pruned_loss=0.06086, over 7270.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2823, pruned_loss=0.05995, over 1421123.84 frames.], batch size: 18, lr: 1.02e-03
2022-05-14 05:16:51,043 INFO [train.py:812] (4/8) Epoch 7, batch 2450, loss[loss=0.1818, simple_loss=0.273, pruned_loss=0.04531, over 7412.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2828, pruned_loss=0.06039, over 1417068.38 frames.], batch size: 21, lr: 1.02e-03
2022-05-14 05:17:49,493 INFO [train.py:812] (4/8) Epoch 7, batch 2500, loss[loss=0.2065, simple_loss=0.2848, pruned_loss=0.06404, over 7318.00 frames.], tot_loss[loss=0.2033, simple_loss=0.284, pruned_loss=0.06132, over 1416858.41 frames.], batch size: 21, lr: 1.02e-03
2022-05-14 05:18:48,416 INFO [train.py:812] (4/8) Epoch 7, batch 2550, loss[loss=0.2092, simple_loss=0.288, pruned_loss=0.0652, over 7424.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2827, pruned_loss=0.06037, over 1423275.10 frames.], batch size: 20, lr: 1.02e-03
2022-05-14 05:19:47,252 INFO [train.py:812] (4/8) Epoch 7, batch 2600, loss[loss=0.1797, simple_loss=0.2572, pruned_loss=0.05115, over 7171.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2831, pruned_loss=0.06071, over 1417171.60 frames.], batch size: 18, lr: 1.02e-03
2022-05-14 05:20:45,575 INFO [train.py:812] (4/8) Epoch 7, batch 2650, loss[loss=0.1971, simple_loss=0.277, pruned_loss=0.0586, over 7160.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2831, pruned_loss=0.06061, over 1416866.11 frames.], batch size: 18, lr: 1.02e-03
2022-05-14 05:21:44,762 INFO [train.py:812] (4/8) Epoch 7, batch 2700, loss[loss=0.1792, simple_loss=0.259, pruned_loss=0.0497, over 6846.00 frames.], tot_loss[loss=0.202, simple_loss=0.2828, pruned_loss=0.06059, over 1418841.80 frames.], batch size: 15, lr: 1.02e-03
2022-05-14 05:22:44,408 INFO [train.py:812] (4/8) Epoch 7, batch 2750, loss[loss=0.1571, simple_loss=0.2365, pruned_loss=0.03883, over 7402.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2833, pruned_loss=0.06073, over 1419009.47 frames.], batch size: 18, lr: 1.02e-03
2022-05-14 05:23:44,353 INFO [train.py:812] (4/8) Epoch 7, batch 2800, loss[loss=0.1645, simple_loss=0.2416, pruned_loss=0.04373, over 6983.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2813, pruned_loss=0.05919, over 1417504.90 frames.], batch size: 16, lr: 1.02e-03
2022-05-14 05:24:43,856 INFO [train.py:812] (4/8) Epoch 7, batch 2850, loss[loss=0.1766, simple_loss=0.2574, pruned_loss=0.04789, over 7323.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2795, pruned_loss=0.05831, over 1422708.15 frames.], batch size: 21, lr: 1.02e-03
2022-05-14 05:25:43,747 INFO [train.py:812] (4/8) Epoch 7, batch 2900, loss[loss=0.2758, simple_loss=0.322, pruned_loss=0.1148, over 4987.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2787, pruned_loss=0.05742, over 1425244.48 frames.], batch size: 53, lr: 1.02e-03
2022-05-14 05:26:42,754 INFO [train.py:812] (4/8) Epoch 7, batch 2950, loss[loss=0.2361, simple_loss=0.3152, pruned_loss=0.07851, over 7328.00 frames.], tot_loss[loss=0.198, simple_loss=0.2799, pruned_loss=0.05808, over 1425302.40 frames.], batch size: 25, lr: 1.01e-03
2022-05-14 05:27:42,375 INFO [train.py:812] (4/8) Epoch 7, batch 3000, loss[loss=0.2527, simple_loss=0.3302, pruned_loss=0.08758, over 7171.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2805, pruned_loss=0.0581, over 1427166.92 frames.], batch size: 26, lr: 1.01e-03
2022-05-14 05:27:42,376 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 05:27:49,660 INFO [train.py:841] (4/8) 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] (4/8) Epoch 7, batch 3050, loss[loss=0.2075, simple_loss=0.3043, pruned_loss=0.05534, over 7144.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2802, pruned_loss=0.05817, over 1427648.63 frames.], batch size: 26, lr: 1.01e-03
2022-05-14 05:29:48,820 INFO [train.py:812] (4/8) Epoch 7, batch 3100, loss[loss=0.2292, simple_loss=0.3095, pruned_loss=0.07448, over 7196.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2813, pruned_loss=0.05872, over 1424916.08 frames.], batch size: 26, lr: 1.01e-03
2022-05-14 05:30:48,416 INFO [train.py:812] (4/8) Epoch 7, batch 3150, loss[loss=0.2306, simple_loss=0.3111, pruned_loss=0.07508, over 7034.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2814, pruned_loss=0.0589, over 1428176.11 frames.], batch size: 28, lr: 1.01e-03
2022-05-14 05:31:47,458 INFO [train.py:812] (4/8) Epoch 7, batch 3200, loss[loss=0.2116, simple_loss=0.3001, pruned_loss=0.06153, over 7341.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2822, pruned_loss=0.05911, over 1424343.97 frames.], batch size: 22, lr: 1.01e-03
2022-05-14 05:32:46,892 INFO [train.py:812] (4/8) Epoch 7, batch 3250, loss[loss=0.2202, simple_loss=0.3066, pruned_loss=0.06695, over 7081.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2812, pruned_loss=0.05855, over 1422884.18 frames.], batch size: 28, lr: 1.01e-03
2022-05-14 05:33:46,258 INFO [train.py:812] (4/8) Epoch 7, batch 3300, loss[loss=0.1891, simple_loss=0.287, pruned_loss=0.0456, over 7140.00 frames.], tot_loss[loss=0.199, simple_loss=0.2813, pruned_loss=0.0583, over 1417776.60 frames.], batch size: 20, lr: 1.01e-03
2022-05-14 05:34:45,877 INFO [train.py:812] (4/8) Epoch 7, batch 3350, loss[loss=0.1728, simple_loss=0.2519, pruned_loss=0.04685, over 7149.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2816, pruned_loss=0.05832, over 1419271.81 frames.], batch size: 19, lr: 1.01e-03
2022-05-14 05:35:44,968 INFO [train.py:812] (4/8) Epoch 7, batch 3400, loss[loss=0.1994, simple_loss=0.2958, pruned_loss=0.0515, over 7436.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2811, pruned_loss=0.05791, over 1422825.39 frames.], batch size: 22, lr: 1.01e-03
2022-05-14 05:36:43,532 INFO [train.py:812] (4/8) Epoch 7, batch 3450, loss[loss=0.2177, simple_loss=0.3066, pruned_loss=0.06444, over 7276.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2826, pruned_loss=0.05896, over 1420612.71 frames.], batch size: 24, lr: 1.01e-03
2022-05-14 05:37:43,016 INFO [train.py:812] (4/8) Epoch 7, batch 3500, loss[loss=0.2019, simple_loss=0.2767, pruned_loss=0.06354, over 7220.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2824, pruned_loss=0.05894, over 1423156.11 frames.], batch size: 21, lr: 1.01e-03
2022-05-14 05:38:41,456 INFO [train.py:812] (4/8) Epoch 7, batch 3550, loss[loss=0.1978, simple_loss=0.2728, pruned_loss=0.0614, over 7370.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2814, pruned_loss=0.05845, over 1424191.64 frames.], batch size: 23, lr: 1.01e-03
2022-05-14 05:39:40,564 INFO [train.py:812] (4/8) Epoch 7, batch 3600, loss[loss=0.1897, simple_loss=0.2853, pruned_loss=0.04701, over 7222.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2811, pruned_loss=0.05836, over 1425510.49 frames.], batch size: 21, lr: 1.00e-03
2022-05-14 05:40:39,018 INFO [train.py:812] (4/8) Epoch 7, batch 3650, loss[loss=0.214, simple_loss=0.295, pruned_loss=0.06647, over 7048.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2805, pruned_loss=0.05824, over 1422370.78 frames.], batch size: 28, lr: 1.00e-03
2022-05-14 05:41:38,741 INFO [train.py:812] (4/8) Epoch 7, batch 3700, loss[loss=0.1757, simple_loss=0.2616, pruned_loss=0.0449, over 7434.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2793, pruned_loss=0.05771, over 1423751.30 frames.], batch size: 20, lr: 1.00e-03
2022-05-14 05:42:37,961 INFO [train.py:812] (4/8) Epoch 7, batch 3750, loss[loss=0.2526, simple_loss=0.3226, pruned_loss=0.09124, over 4856.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2791, pruned_loss=0.05753, over 1424186.68 frames.], batch size: 53, lr: 1.00e-03
2022-05-14 05:43:37,516 INFO [train.py:812] (4/8) Epoch 7, batch 3800, loss[loss=0.1861, simple_loss=0.2742, pruned_loss=0.04901, over 7362.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2802, pruned_loss=0.0581, over 1422436.24 frames.], batch size: 19, lr: 1.00e-03
2022-05-14 05:44:35,592 INFO [train.py:812] (4/8) Epoch 7, batch 3850, loss[loss=0.1842, simple_loss=0.2677, pruned_loss=0.05034, over 7144.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2788, pruned_loss=0.05736, over 1425496.70 frames.], batch size: 17, lr: 1.00e-03
2022-05-14 05:45:34,804 INFO [train.py:812] (4/8) Epoch 7, batch 3900, loss[loss=0.1988, simple_loss=0.2737, pruned_loss=0.06198, over 7160.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2799, pruned_loss=0.05863, over 1425643.18 frames.], batch size: 18, lr: 1.00e-03
2022-05-14 05:46:31,676 INFO [train.py:812] (4/8) Epoch 7, batch 3950, loss[loss=0.2002, simple_loss=0.2804, pruned_loss=0.05994, over 7337.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2796, pruned_loss=0.05863, over 1427435.64 frames.], batch size: 22, lr: 9.99e-04
2022-05-14 05:47:30,574 INFO [train.py:812] (4/8) Epoch 7, batch 4000, loss[loss=0.2164, simple_loss=0.2929, pruned_loss=0.06997, over 6883.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2794, pruned_loss=0.05808, over 1431716.93 frames.], batch size: 32, lr: 9.98e-04
2022-05-14 05:48:29,682 INFO [train.py:812] (4/8) Epoch 7, batch 4050, loss[loss=0.1871, simple_loss=0.2835, pruned_loss=0.04536, over 7163.00 frames.], tot_loss[loss=0.199, simple_loss=0.2804, pruned_loss=0.05877, over 1428964.96 frames.], batch size: 18, lr: 9.98e-04
2022-05-14 05:49:28,784 INFO [train.py:812] (4/8) Epoch 7, batch 4100, loss[loss=0.1783, simple_loss=0.2632, pruned_loss=0.04674, over 7129.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2812, pruned_loss=0.05898, over 1424847.98 frames.], batch size: 21, lr: 9.97e-04
2022-05-14 05:50:26,074 INFO [train.py:812] (4/8) Epoch 7, batch 4150, loss[loss=0.237, simple_loss=0.3129, pruned_loss=0.08051, over 7201.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2817, pruned_loss=0.05938, over 1425907.91 frames.], batch size: 23, lr: 9.96e-04
2022-05-14 05:51:25,279 INFO [train.py:812] (4/8) Epoch 7, batch 4200, loss[loss=0.1632, simple_loss=0.2378, pruned_loss=0.04433, over 7285.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2807, pruned_loss=0.05851, over 1427805.35 frames.], batch size: 17, lr: 9.95e-04
2022-05-14 05:52:24,630 INFO [train.py:812] (4/8) Epoch 7, batch 4250, loss[loss=0.1768, simple_loss=0.2618, pruned_loss=0.04589, over 7424.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2803, pruned_loss=0.05794, over 1422372.91 frames.], batch size: 20, lr: 9.95e-04
2022-05-14 05:53:23,919 INFO [train.py:812] (4/8) Epoch 7, batch 4300, loss[loss=0.2339, simple_loss=0.3058, pruned_loss=0.08104, over 7235.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2824, pruned_loss=0.0589, over 1416641.61 frames.], batch size: 20, lr: 9.94e-04
2022-05-14 05:54:23,293 INFO [train.py:812] (4/8) Epoch 7, batch 4350, loss[loss=0.1958, simple_loss=0.2831, pruned_loss=0.05424, over 6448.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2825, pruned_loss=0.05833, over 1411202.60 frames.], batch size: 37, lr: 9.93e-04
2022-05-14 05:55:22,299 INFO [train.py:812] (4/8) Epoch 7, batch 4400, loss[loss=0.2458, simple_loss=0.3243, pruned_loss=0.08368, over 6837.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2817, pruned_loss=0.05845, over 1412103.23 frames.], batch size: 32, lr: 9.92e-04
2022-05-14 05:56:20,595 INFO [train.py:812] (4/8) Epoch 7, batch 4450, loss[loss=0.1895, simple_loss=0.2732, pruned_loss=0.05291, over 7207.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2821, pruned_loss=0.05875, over 1405814.34 frames.], batch size: 22, lr: 9.92e-04
2022-05-14 05:57:24,427 INFO [train.py:812] (4/8) Epoch 7, batch 4500, loss[loss=0.2061, simple_loss=0.2967, pruned_loss=0.05776, over 7224.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2822, pruned_loss=0.05858, over 1403185.10 frames.], batch size: 22, lr: 9.91e-04
2022-05-14 05:58:22,211 INFO [train.py:812] (4/8) Epoch 7, batch 4550, loss[loss=0.2635, simple_loss=0.3277, pruned_loss=0.09968, over 4940.00 frames.], tot_loss[loss=0.2014, simple_loss=0.284, pruned_loss=0.05945, over 1389195.18 frames.], batch size: 52, lr: 9.90e-04
2022-05-14 05:59:32,586 INFO [train.py:812] (4/8) Epoch 8, batch 0, loss[loss=0.2163, simple_loss=0.3068, pruned_loss=0.06289, over 7325.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3068, pruned_loss=0.06289, over 7325.00 frames.], batch size: 22, lr: 9.49e-04
2022-05-14 06:00:31,155 INFO [train.py:812] (4/8) Epoch 8, batch 50, loss[loss=0.1898, simple_loss=0.2656, pruned_loss=0.05699, over 7138.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2824, pruned_loss=0.05692, over 320061.46 frames.], batch size: 17, lr: 9.48e-04
2022-05-14 06:01:30,397 INFO [train.py:812] (4/8) Epoch 8, batch 100, loss[loss=0.2167, simple_loss=0.3041, pruned_loss=0.06465, over 7327.00 frames.], tot_loss[loss=0.1972, simple_loss=0.282, pruned_loss=0.05626, over 568506.55 frames.], batch size: 25, lr: 9.48e-04
2022-05-14 06:02:29,673 INFO [train.py:812] (4/8) Epoch 8, batch 150, loss[loss=0.1877, simple_loss=0.2843, pruned_loss=0.04555, over 7113.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2784, pruned_loss=0.05533, over 758889.95 frames.], batch size: 21, lr: 9.47e-04
2022-05-14 06:03:26,761 INFO [train.py:812] (4/8) Epoch 8, batch 200, loss[loss=0.2033, simple_loss=0.2914, pruned_loss=0.05756, over 7208.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2797, pruned_loss=0.05586, over 907584.26 frames.], batch size: 22, lr: 9.46e-04
2022-05-14 06:04:24,362 INFO [train.py:812] (4/8) Epoch 8, batch 250, loss[loss=0.2013, simple_loss=0.2897, pruned_loss=0.05642, over 7129.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2814, pruned_loss=0.05671, over 1020676.67 frames.], batch size: 21, lr: 9.46e-04
2022-05-14 06:05:21,319 INFO [train.py:812] (4/8) Epoch 8, batch 300, loss[loss=0.1933, simple_loss=0.2747, pruned_loss=0.05598, over 7071.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2815, pruned_loss=0.05662, over 1107145.39 frames.], batch size: 18, lr: 9.45e-04
2022-05-14 06:06:19,883 INFO [train.py:812] (4/8) Epoch 8, batch 350, loss[loss=0.2189, simple_loss=0.3133, pruned_loss=0.06228, over 7106.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2806, pruned_loss=0.05691, over 1178226.30 frames.], batch size: 21, lr: 9.44e-04
2022-05-14 06:07:19,500 INFO [train.py:812] (4/8) Epoch 8, batch 400, loss[loss=0.2435, simple_loss=0.3166, pruned_loss=0.08519, over 5076.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2807, pruned_loss=0.05722, over 1231442.35 frames.], batch size: 52, lr: 9.43e-04
2022-05-14 06:08:18,804 INFO [train.py:812] (4/8) Epoch 8, batch 450, loss[loss=0.1886, simple_loss=0.2693, pruned_loss=0.05398, over 6893.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2804, pruned_loss=0.05754, over 1272173.52 frames.], batch size: 15, lr: 9.43e-04
2022-05-14 06:09:18,367 INFO [train.py:812] (4/8) Epoch 8, batch 500, loss[loss=0.1885, simple_loss=0.2794, pruned_loss=0.04874, over 7189.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2792, pruned_loss=0.05687, over 1305699.30 frames.], batch size: 23, lr: 9.42e-04
2022-05-14 06:10:16,966 INFO [train.py:812] (4/8) Epoch 8, batch 550, loss[loss=0.2024, simple_loss=0.2948, pruned_loss=0.055, over 7205.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2793, pruned_loss=0.05663, over 1333435.26 frames.], batch size: 23, lr: 9.41e-04
2022-05-14 06:11:16,908 INFO [train.py:812] (4/8) Epoch 8, batch 600, loss[loss=0.1997, simple_loss=0.2858, pruned_loss=0.05676, over 7228.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2805, pruned_loss=0.05704, over 1353419.00 frames.], batch size: 21, lr: 9.41e-04
2022-05-14 06:12:15,255 INFO [train.py:812] (4/8) Epoch 8, batch 650, loss[loss=0.1834, simple_loss=0.2641, pruned_loss=0.05137, over 7265.00 frames.], tot_loss[loss=0.1967, simple_loss=0.28, pruned_loss=0.05674, over 1367782.37 frames.], batch size: 19, lr: 9.40e-04
2022-05-14 06:13:14,188 INFO [train.py:812] (4/8) Epoch 8, batch 700, loss[loss=0.1889, simple_loss=0.2735, pruned_loss=0.05218, over 5052.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2805, pruned_loss=0.05701, over 1376250.56 frames.], batch size: 52, lr: 9.39e-04
2022-05-14 06:14:13,340 INFO [train.py:812] (4/8) Epoch 8, batch 750, loss[loss=0.1876, simple_loss=0.2706, pruned_loss=0.0523, over 7363.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2798, pruned_loss=0.05662, over 1384991.31 frames.], batch size: 19, lr: 9.39e-04
2022-05-14 06:15:12,827 INFO [train.py:812] (4/8) Epoch 8, batch 800, loss[loss=0.2113, simple_loss=0.2862, pruned_loss=0.06824, over 6471.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2811, pruned_loss=0.05699, over 1390596.56 frames.], batch size: 38, lr: 9.38e-04
2022-05-14 06:16:12,234 INFO [train.py:812] (4/8) Epoch 8, batch 850, loss[loss=0.1757, simple_loss=0.2508, pruned_loss=0.05032, over 7398.00 frames.], tot_loss[loss=0.1962, simple_loss=0.279, pruned_loss=0.05667, over 1399292.02 frames.], batch size: 18, lr: 9.37e-04
2022-05-14 06:17:11,301 INFO [train.py:812] (4/8) Epoch 8, batch 900, loss[loss=0.219, simple_loss=0.3008, pruned_loss=0.06862, over 6799.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2793, pruned_loss=0.05707, over 1398565.54 frames.], batch size: 31, lr: 9.36e-04
2022-05-14 06:18:09,035 INFO [train.py:812] (4/8) Epoch 8, batch 950, loss[loss=0.1916, simple_loss=0.2826, pruned_loss=0.05035, over 7237.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2805, pruned_loss=0.0574, over 1404578.65 frames.], batch size: 20, lr: 9.36e-04
2022-05-14 06:19:08,070 INFO [train.py:812] (4/8) Epoch 8, batch 1000, loss[loss=0.1978, simple_loss=0.2856, pruned_loss=0.05499, over 7228.00 frames.], tot_loss[loss=0.197, simple_loss=0.2797, pruned_loss=0.0572, over 1409546.55 frames.], batch size: 21, lr: 9.35e-04
2022-05-14 06:20:06,223 INFO [train.py:812] (4/8) Epoch 8, batch 1050, loss[loss=0.2166, simple_loss=0.2858, pruned_loss=0.07369, over 7145.00 frames.], tot_loss[loss=0.198, simple_loss=0.2806, pruned_loss=0.05768, over 1407324.48 frames.], batch size: 17, lr: 9.34e-04
2022-05-14 06:21:04,768 INFO [train.py:812] (4/8) Epoch 8, batch 1100, loss[loss=0.1928, simple_loss=0.2765, pruned_loss=0.05455, over 7203.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2793, pruned_loss=0.05727, over 1412226.74 frames.], batch size: 22, lr: 9.34e-04
2022-05-14 06:22:02,858 INFO [train.py:812] (4/8) Epoch 8, batch 1150, loss[loss=0.3035, simple_loss=0.3533, pruned_loss=0.1268, over 4848.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2799, pruned_loss=0.05717, over 1417137.63 frames.], batch size: 52, lr: 9.33e-04
2022-05-14 06:23:10,864 INFO [train.py:812] (4/8) Epoch 8, batch 1200, loss[loss=0.2058, simple_loss=0.3039, pruned_loss=0.05379, over 7144.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2802, pruned_loss=0.05682, over 1420388.94 frames.], batch size: 20, lr: 9.32e-04
2022-05-14 06:24:10,085 INFO [train.py:812] (4/8) Epoch 8, batch 1250, loss[loss=0.1751, simple_loss=0.2553, pruned_loss=0.04747, over 7278.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2793, pruned_loss=0.0567, over 1419624.55 frames.], batch size: 18, lr: 9.32e-04
2022-05-14 06:25:09,379 INFO [train.py:812] (4/8) Epoch 8, batch 1300, loss[loss=0.1696, simple_loss=0.2527, pruned_loss=0.04321, over 7150.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2796, pruned_loss=0.05658, over 1415892.75 frames.], batch size: 20, lr: 9.31e-04
2022-05-14 06:26:08,270 INFO [train.py:812] (4/8) Epoch 8, batch 1350, loss[loss=0.234, simple_loss=0.3053, pruned_loss=0.08132, over 7165.00 frames.], tot_loss[loss=0.197, simple_loss=0.28, pruned_loss=0.05705, over 1415044.13 frames.], batch size: 19, lr: 9.30e-04
2022-05-14 06:27:08,003 INFO [train.py:812] (4/8) Epoch 8, batch 1400, loss[loss=0.1609, simple_loss=0.2433, pruned_loss=0.0393, over 7288.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2805, pruned_loss=0.05716, over 1415621.81 frames.], batch size: 18, lr: 9.30e-04
2022-05-14 06:28:06,827 INFO [train.py:812] (4/8) Epoch 8, batch 1450, loss[loss=0.1949, simple_loss=0.2697, pruned_loss=0.06005, over 7160.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2803, pruned_loss=0.05699, over 1414962.37 frames.], batch size: 18, lr: 9.29e-04
2022-05-14 06:29:06,642 INFO [train.py:812] (4/8) Epoch 8, batch 1500, loss[loss=0.1535, simple_loss=0.234, pruned_loss=0.0365, over 7400.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2786, pruned_loss=0.05624, over 1415083.22 frames.], batch size: 18, lr: 9.28e-04
2022-05-14 06:30:05,547 INFO [train.py:812] (4/8) Epoch 8, batch 1550, loss[loss=0.1826, simple_loss=0.2698, pruned_loss=0.0477, over 7193.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2779, pruned_loss=0.05557, over 1420223.70 frames.], batch size: 22, lr: 9.28e-04
2022-05-14 06:31:05,144 INFO [train.py:812] (4/8) Epoch 8, batch 1600, loss[loss=0.1928, simple_loss=0.2753, pruned_loss=0.0552, over 6520.00 frames.], tot_loss[loss=0.1956, simple_loss=0.279, pruned_loss=0.05608, over 1420388.13 frames.], batch size: 38, lr: 9.27e-04
2022-05-14 06:32:04,301 INFO [train.py:812] (4/8) Epoch 8, batch 1650, loss[loss=0.1755, simple_loss=0.2627, pruned_loss=0.0441, over 7308.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2786, pruned_loss=0.05584, over 1418521.17 frames.], batch size: 24, lr: 9.26e-04
2022-05-14 06:33:04,119 INFO [train.py:812] (4/8) Epoch 8, batch 1700, loss[loss=0.1912, simple_loss=0.2882, pruned_loss=0.04708, over 7316.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2796, pruned_loss=0.05634, over 1419028.66 frames.], batch size: 21, lr: 9.26e-04
2022-05-14 06:34:03,602 INFO [train.py:812] (4/8) Epoch 8, batch 1750, loss[loss=0.1966, simple_loss=0.2815, pruned_loss=0.05583, over 7344.00 frames.], tot_loss[loss=0.195, simple_loss=0.2782, pruned_loss=0.05592, over 1419603.35 frames.], batch size: 22, lr: 9.25e-04
2022-05-14 06:35:12,526 INFO [train.py:812] (4/8) Epoch 8, batch 1800, loss[loss=0.2391, simple_loss=0.3185, pruned_loss=0.07982, over 7335.00 frames.], tot_loss[loss=0.194, simple_loss=0.2767, pruned_loss=0.0556, over 1420505.62 frames.], batch size: 22, lr: 9.24e-04
2022-05-14 06:36:21,372 INFO [train.py:812] (4/8) Epoch 8, batch 1850, loss[loss=0.206, simple_loss=0.2846, pruned_loss=0.06375, over 7236.00 frames.], tot_loss[loss=0.1949, simple_loss=0.278, pruned_loss=0.05583, over 1422521.81 frames.], batch size: 20, lr: 9.24e-04
2022-05-14 06:37:30,724 INFO [train.py:812] (4/8) Epoch 8, batch 1900, loss[loss=0.2151, simple_loss=0.2955, pruned_loss=0.0673, over 7295.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2774, pruned_loss=0.05559, over 1421792.63 frames.], batch size: 25, lr: 9.23e-04
2022-05-14 06:38:48,463 INFO [train.py:812] (4/8) Epoch 8, batch 1950, loss[loss=0.1647, simple_loss=0.2487, pruned_loss=0.04039, over 7001.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2768, pruned_loss=0.0553, over 1426420.14 frames.], batch size: 16, lr: 9.22e-04
2022-05-14 06:40:06,952 INFO [train.py:812] (4/8) Epoch 8, batch 2000, loss[loss=0.2054, simple_loss=0.3012, pruned_loss=0.05487, over 7106.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2769, pruned_loss=0.0552, over 1426618.76 frames.], batch size: 21, lr: 9.22e-04
2022-05-14 06:41:06,021 INFO [train.py:812] (4/8) Epoch 8, batch 2050, loss[loss=0.2542, simple_loss=0.328, pruned_loss=0.09022, over 5371.00 frames.], tot_loss[loss=0.1949, simple_loss=0.278, pruned_loss=0.05585, over 1420577.73 frames.], batch size: 52, lr: 9.21e-04
2022-05-14 06:42:04,905 INFO [train.py:812] (4/8) Epoch 8, batch 2100, loss[loss=0.1811, simple_loss=0.2694, pruned_loss=0.0464, over 7241.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2789, pruned_loss=0.0564, over 1416690.46 frames.], batch size: 20, lr: 9.20e-04
2022-05-14 06:43:03,995 INFO [train.py:812] (4/8) Epoch 8, batch 2150, loss[loss=0.2258, simple_loss=0.3082, pruned_loss=0.07164, over 7194.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2783, pruned_loss=0.05596, over 1418399.23 frames.], batch size: 22, lr: 9.20e-04
2022-05-14 06:44:02,981 INFO [train.py:812] (4/8) Epoch 8, batch 2200, loss[loss=0.2143, simple_loss=0.2926, pruned_loss=0.06797, over 7278.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2768, pruned_loss=0.05546, over 1417292.73 frames.], batch size: 24, lr: 9.19e-04
2022-05-14 06:45:01,866 INFO [train.py:812] (4/8) Epoch 8, batch 2250, loss[loss=0.1812, simple_loss=0.2756, pruned_loss=0.04337, over 7219.00 frames.], tot_loss[loss=0.1934, simple_loss=0.276, pruned_loss=0.05535, over 1412873.66 frames.], batch size: 23, lr: 9.18e-04
2022-05-14 06:46:00,799 INFO [train.py:812] (4/8) Epoch 8, batch 2300, loss[loss=0.1934, simple_loss=0.2692, pruned_loss=0.05883, over 7403.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2755, pruned_loss=0.05501, over 1412787.63 frames.], batch size: 18, lr: 9.18e-04
2022-05-14 06:46:59,531 INFO [train.py:812] (4/8) Epoch 8, batch 2350, loss[loss=0.1923, simple_loss=0.2655, pruned_loss=0.05955, over 7459.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2769, pruned_loss=0.05564, over 1413285.41 frames.], batch size: 19, lr: 9.17e-04
2022-05-14 06:47:58,466 INFO [train.py:812] (4/8) Epoch 8, batch 2400, loss[loss=0.2057, simple_loss=0.2852, pruned_loss=0.06317, over 7255.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2769, pruned_loss=0.05579, over 1416879.73 frames.], batch size: 19, lr: 9.16e-04
2022-05-14 06:48:57,540 INFO [train.py:812] (4/8) Epoch 8, batch 2450, loss[loss=0.1757, simple_loss=0.2622, pruned_loss=0.04461, over 7277.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2768, pruned_loss=0.0554, over 1423192.18 frames.], batch size: 24, lr: 9.16e-04
2022-05-14 06:49:57,005 INFO [train.py:812] (4/8) Epoch 8, batch 2500, loss[loss=0.2045, simple_loss=0.2923, pruned_loss=0.05832, over 7320.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2776, pruned_loss=0.05596, over 1421035.39 frames.], batch size: 21, lr: 9.15e-04
2022-05-14 06:50:55,699 INFO [train.py:812] (4/8) Epoch 8, batch 2550, loss[loss=0.2116, simple_loss=0.285, pruned_loss=0.06911, over 7370.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2763, pruned_loss=0.05512, over 1425900.80 frames.], batch size: 19, lr: 9.14e-04
2022-05-14 06:51:54,443 INFO [train.py:812] (4/8) Epoch 8, batch 2600, loss[loss=0.1675, simple_loss=0.2411, pruned_loss=0.04695, over 6815.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2767, pruned_loss=0.05507, over 1426695.62 frames.], batch size: 15, lr: 9.14e-04
2022-05-14 06:52:51,876 INFO [train.py:812] (4/8) Epoch 8, batch 2650, loss[loss=0.1847, simple_loss=0.283, pruned_loss=0.04316, over 7115.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2769, pruned_loss=0.05493, over 1427212.33 frames.], batch size: 21, lr: 9.13e-04
2022-05-14 06:53:49,753 INFO [train.py:812] (4/8) Epoch 8, batch 2700, loss[loss=0.2003, simple_loss=0.2631, pruned_loss=0.06876, over 6835.00 frames.], tot_loss[loss=0.193, simple_loss=0.2762, pruned_loss=0.05492, over 1429411.59 frames.], batch size: 15, lr: 9.12e-04
2022-05-14 06:54:48,258 INFO [train.py:812] (4/8) Epoch 8, batch 2750, loss[loss=0.1734, simple_loss=0.2457, pruned_loss=0.05058, over 7009.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2756, pruned_loss=0.05452, over 1428570.71 frames.], batch size: 16, lr: 9.12e-04
2022-05-14 06:55:46,855 INFO [train.py:812] (4/8) Epoch 8, batch 2800, loss[loss=0.1734, simple_loss=0.2685, pruned_loss=0.03921, over 7143.00 frames.], tot_loss[loss=0.192, simple_loss=0.2757, pruned_loss=0.0542, over 1428594.74 frames.], batch size: 20, lr: 9.11e-04
2022-05-14 06:56:44,434 INFO [train.py:812] (4/8) Epoch 8, batch 2850, loss[loss=0.2149, simple_loss=0.2956, pruned_loss=0.06703, over 7197.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2765, pruned_loss=0.05468, over 1426592.93 frames.], batch size: 22, lr: 9.11e-04
2022-05-14 06:57:43,807 INFO [train.py:812] (4/8) Epoch 8, batch 2900, loss[loss=0.199, simple_loss=0.2784, pruned_loss=0.05977, over 7126.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2773, pruned_loss=0.05506, over 1425688.84 frames.], batch size: 17, lr: 9.10e-04
2022-05-14 06:58:42,760 INFO [train.py:812] (4/8) Epoch 8, batch 2950, loss[loss=0.1432, simple_loss=0.2351, pruned_loss=0.02559, over 7048.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2757, pruned_loss=0.05456, over 1425082.08 frames.], batch size: 18, lr: 9.09e-04
2022-05-14 06:59:42,241 INFO [train.py:812] (4/8) Epoch 8, batch 3000, loss[loss=0.2465, simple_loss=0.3245, pruned_loss=0.08421, over 4925.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2755, pruned_loss=0.0543, over 1421854.19 frames.], batch size: 53, lr: 9.09e-04
2022-05-14 06:59:42,242 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 06:59:50,551 INFO [train.py:841] (4/8) Epoch 8, validation: loss=0.1612, simple_loss=0.2635, pruned_loss=0.0294, over 698248.00 frames.
2022-05-14 07:00:48,454 INFO [train.py:812] (4/8) Epoch 8, batch 3050, loss[loss=0.2074, simple_loss=0.2959, pruned_loss=0.05949, over 6344.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2751, pruned_loss=0.05457, over 1414956.96 frames.], batch size: 37, lr: 9.08e-04
2022-05-14 07:01:48,156 INFO [train.py:812] (4/8) Epoch 8, batch 3100, loss[loss=0.1782, simple_loss=0.2681, pruned_loss=0.04415, over 7256.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2751, pruned_loss=0.05432, over 1420015.24 frames.], batch size: 19, lr: 9.07e-04
2022-05-14 07:02:45,307 INFO [train.py:812] (4/8) Epoch 8, batch 3150, loss[loss=0.2104, simple_loss=0.298, pruned_loss=0.06138, over 7440.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2744, pruned_loss=0.05445, over 1421471.92 frames.], batch size: 20, lr: 9.07e-04
2022-05-14 07:03:44,358 INFO [train.py:812] (4/8) Epoch 8, batch 3200, loss[loss=0.1538, simple_loss=0.2399, pruned_loss=0.03382, over 7437.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2742, pruned_loss=0.05414, over 1424452.57 frames.], batch size: 20, lr: 9.06e-04
2022-05-14 07:04:43,314 INFO [train.py:812] (4/8) Epoch 8, batch 3250, loss[loss=0.1917, simple_loss=0.2729, pruned_loss=0.05528, over 7046.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2755, pruned_loss=0.05469, over 1423089.89 frames.], batch size: 28, lr: 9.05e-04
2022-05-14 07:05:41,211 INFO [train.py:812] (4/8) Epoch 8, batch 3300, loss[loss=0.1906, simple_loss=0.2852, pruned_loss=0.04797, over 6709.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2746, pruned_loss=0.05418, over 1422351.61 frames.], batch size: 31, lr: 9.05e-04
2022-05-14 07:06:40,369 INFO [train.py:812] (4/8) Epoch 8, batch 3350, loss[loss=0.1554, simple_loss=0.2471, pruned_loss=0.03186, over 7441.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2748, pruned_loss=0.05445, over 1419958.94 frames.], batch size: 20, lr: 9.04e-04
2022-05-14 07:07:39,823 INFO [train.py:812] (4/8) Epoch 8, batch 3400, loss[loss=0.2204, simple_loss=0.3005, pruned_loss=0.07015, over 6744.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2749, pruned_loss=0.05466, over 1418416.87 frames.], batch size: 31, lr: 9.04e-04
2022-05-14 07:08:38,482 INFO [train.py:812] (4/8) Epoch 8, batch 3450, loss[loss=0.154, simple_loss=0.2467, pruned_loss=0.03064, over 7418.00 frames.], tot_loss[loss=0.193, simple_loss=0.2764, pruned_loss=0.05479, over 1421757.78 frames.], batch size: 18, lr: 9.03e-04
2022-05-14 07:09:37,926 INFO [train.py:812] (4/8) Epoch 8, batch 3500, loss[loss=0.1919, simple_loss=0.2732, pruned_loss=0.05531, over 7363.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2772, pruned_loss=0.05497, over 1420799.46 frames.], batch size: 23, lr: 9.02e-04
2022-05-14 07:10:37,045 INFO [train.py:812] (4/8) Epoch 8, batch 3550, loss[loss=0.1913, simple_loss=0.2778, pruned_loss=0.05243, over 7254.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2772, pruned_loss=0.05525, over 1422515.81 frames.], batch size: 19, lr: 9.02e-04
2022-05-14 07:11:36,656 INFO [train.py:812] (4/8) Epoch 8, batch 3600, loss[loss=0.1518, simple_loss=0.2251, pruned_loss=0.03926, over 7288.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2765, pruned_loss=0.05525, over 1421253.67 frames.], batch size: 17, lr: 9.01e-04
2022-05-14 07:12:33,626 INFO [train.py:812] (4/8) Epoch 8, batch 3650, loss[loss=0.174, simple_loss=0.2658, pruned_loss=0.04113, over 7414.00 frames.], tot_loss[loss=0.196, simple_loss=0.2789, pruned_loss=0.05653, over 1416006.25 frames.], batch size: 21, lr: 9.01e-04
2022-05-14 07:13:32,617 INFO [train.py:812] (4/8) Epoch 8, batch 3700, loss[loss=0.1813, simple_loss=0.2749, pruned_loss=0.04378, over 7219.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2779, pruned_loss=0.0558, over 1420042.70 frames.], batch size: 21, lr: 9.00e-04
2022-05-14 07:14:31,416 INFO [train.py:812] (4/8) Epoch 8, batch 3750, loss[loss=0.1694, simple_loss=0.2671, pruned_loss=0.03585, over 7155.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2769, pruned_loss=0.05495, over 1418007.42 frames.], batch size: 19, lr: 8.99e-04
2022-05-14 07:15:30,613 INFO [train.py:812] (4/8) Epoch 8, batch 3800, loss[loss=0.1979, simple_loss=0.2783, pruned_loss=0.05878, over 7283.00 frames.], tot_loss[loss=0.1944, simple_loss=0.278, pruned_loss=0.05542, over 1420667.38 frames.], batch size: 24, lr: 8.99e-04
2022-05-14 07:16:28,752 INFO [train.py:812] (4/8) Epoch 8, batch 3850, loss[loss=0.179, simple_loss=0.2695, pruned_loss=0.04427, over 7224.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2786, pruned_loss=0.05557, over 1418165.95 frames.], batch size: 21, lr: 8.98e-04
2022-05-14 07:17:33,255 INFO [train.py:812] (4/8) Epoch 8, batch 3900, loss[loss=0.1804, simple_loss=0.268, pruned_loss=0.04643, over 7436.00 frames.], tot_loss[loss=0.1935, simple_loss=0.277, pruned_loss=0.055, over 1421764.62 frames.], batch size: 20, lr: 8.97e-04
2022-05-14 07:18:32,357 INFO [train.py:812] (4/8) Epoch 8, batch 3950, loss[loss=0.1635, simple_loss=0.2424, pruned_loss=0.04227, over 6998.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2764, pruned_loss=0.05504, over 1424118.11 frames.], batch size: 16, lr: 8.97e-04
2022-05-14 07:19:31,327 INFO [train.py:812] (4/8) Epoch 8, batch 4000, loss[loss=0.2034, simple_loss=0.2861, pruned_loss=0.06032, over 7148.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2771, pruned_loss=0.05512, over 1422377.58 frames.], batch size: 20, lr: 8.96e-04
2022-05-14 07:20:29,699 INFO [train.py:812] (4/8) Epoch 8, batch 4050, loss[loss=0.1732, simple_loss=0.2649, pruned_loss=0.04068, over 7411.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2769, pruned_loss=0.05493, over 1424940.39 frames.], batch size: 21, lr: 8.96e-04
2022-05-14 07:21:29,483 INFO [train.py:812] (4/8) Epoch 8, batch 4100, loss[loss=0.1416, simple_loss=0.2184, pruned_loss=0.03238, over 7280.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2769, pruned_loss=0.0552, over 1418238.31 frames.], batch size: 17, lr: 8.95e-04
2022-05-14 07:22:28,429 INFO [train.py:812] (4/8) Epoch 8, batch 4150, loss[loss=0.1842, simple_loss=0.2726, pruned_loss=0.0479, over 7324.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2772, pruned_loss=0.05506, over 1412738.31 frames.], batch size: 22, lr: 8.94e-04
2022-05-14 07:23:28,043 INFO [train.py:812] (4/8) Epoch 8, batch 4200, loss[loss=0.2076, simple_loss=0.2909, pruned_loss=0.06217, over 7149.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2783, pruned_loss=0.05537, over 1415264.87 frames.], batch size: 20, lr: 8.94e-04
2022-05-14 07:24:27,291 INFO [train.py:812] (4/8) Epoch 8, batch 4250, loss[loss=0.223, simple_loss=0.2964, pruned_loss=0.07477, over 7195.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2782, pruned_loss=0.05561, over 1420028.94 frames.], batch size: 22, lr: 8.93e-04
2022-05-14 07:25:26,241 INFO [train.py:812] (4/8) Epoch 8, batch 4300, loss[loss=0.213, simple_loss=0.2947, pruned_loss=0.06562, over 7310.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2773, pruned_loss=0.05582, over 1418368.14 frames.], batch size: 21, lr: 8.93e-04
2022-05-14 07:26:25,355 INFO [train.py:812] (4/8) Epoch 8, batch 4350, loss[loss=0.2347, simple_loss=0.319, pruned_loss=0.07523, over 7120.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2757, pruned_loss=0.05472, over 1414902.94 frames.], batch size: 21, lr: 8.92e-04
2022-05-14 07:27:24,395 INFO [train.py:812] (4/8) Epoch 8, batch 4400, loss[loss=0.2076, simple_loss=0.285, pruned_loss=0.06512, over 7077.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2744, pruned_loss=0.05425, over 1417174.04 frames.], batch size: 28, lr: 8.91e-04
2022-05-14 07:28:23,669 INFO [train.py:812] (4/8) Epoch 8, batch 4450, loss[loss=0.2042, simple_loss=0.3025, pruned_loss=0.05291, over 7319.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2745, pruned_loss=0.05454, over 1417450.34 frames.], batch size: 20, lr: 8.91e-04
2022-05-14 07:29:23,596 INFO [train.py:812] (4/8) Epoch 8, batch 4500, loss[loss=0.1943, simple_loss=0.2675, pruned_loss=0.06054, over 7171.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2746, pruned_loss=0.05483, over 1414651.55 frames.], batch size: 18, lr: 8.90e-04
2022-05-14 07:30:22,910 INFO [train.py:812] (4/8) Epoch 8, batch 4550, loss[loss=0.1399, simple_loss=0.2203, pruned_loss=0.02979, over 7270.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2746, pruned_loss=0.05581, over 1398847.91 frames.], batch size: 17, lr: 8.90e-04
2022-05-14 07:31:33,241 INFO [train.py:812] (4/8) Epoch 9, batch 0, loss[loss=0.2306, simple_loss=0.3122, pruned_loss=0.07455, over 7209.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3122, pruned_loss=0.07455, over 7209.00 frames.], batch size: 23, lr: 8.54e-04
2022-05-14 07:32:31,240 INFO [train.py:812] (4/8) Epoch 9, batch 50, loss[loss=0.1895, simple_loss=0.2718, pruned_loss=0.05362, over 7088.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2774, pruned_loss=0.05364, over 319503.66 frames.], batch size: 28, lr: 8.53e-04
2022-05-14 07:33:31,082 INFO [train.py:812] (4/8) Epoch 9, batch 100, loss[loss=0.1882, simple_loss=0.2821, pruned_loss=0.04721, over 7242.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2736, pruned_loss=0.05287, over 566498.67 frames.], batch size: 20, lr: 8.53e-04
2022-05-14 07:34:29,327 INFO [train.py:812] (4/8) Epoch 9, batch 150, loss[loss=0.1962, simple_loss=0.2781, pruned_loss=0.0571, over 4875.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2727, pruned_loss=0.0518, over 753680.19 frames.], batch size: 52, lr: 8.52e-04
2022-05-14 07:35:29,135 INFO [train.py:812] (4/8) Epoch 9, batch 200, loss[loss=0.2008, simple_loss=0.2826, pruned_loss=0.05953, over 7193.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2729, pruned_loss=0.05209, over 902536.99 frames.], batch size: 22, lr: 8.51e-04
2022-05-14 07:36:28,019 INFO [train.py:812] (4/8) Epoch 9, batch 250, loss[loss=0.2041, simple_loss=0.2849, pruned_loss=0.06169, over 7435.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2725, pruned_loss=0.05219, over 1018854.74 frames.], batch size: 20, lr: 8.51e-04
2022-05-14 07:37:25,201 INFO [train.py:812] (4/8) Epoch 9, batch 300, loss[loss=0.1957, simple_loss=0.2823, pruned_loss=0.05451, over 7326.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2734, pruned_loss=0.0525, over 1104015.94 frames.], batch size: 22, lr: 8.50e-04
2022-05-14 07:38:24,950 INFO [train.py:812] (4/8) Epoch 9, batch 350, loss[loss=0.1663, simple_loss=0.2476, pruned_loss=0.04249, over 7171.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2706, pruned_loss=0.05124, over 1178275.22 frames.], batch size: 19, lr: 8.50e-04
2022-05-14 07:39:24,186 INFO [train.py:812] (4/8) Epoch 9, batch 400, loss[loss=0.1491, simple_loss=0.2275, pruned_loss=0.03533, over 7140.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2714, pruned_loss=0.05119, over 1237260.86 frames.], batch size: 17, lr: 8.49e-04
2022-05-14 07:40:21,413 INFO [train.py:812] (4/8) Epoch 9, batch 450, loss[loss=0.1567, simple_loss=0.2458, pruned_loss=0.0338, over 7258.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2712, pruned_loss=0.05135, over 1277908.68 frames.], batch size: 19, lr: 8.49e-04
2022-05-14 07:41:19,789 INFO [train.py:812] (4/8) Epoch 9, batch 500, loss[loss=0.1717, simple_loss=0.2499, pruned_loss=0.0467, over 7404.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2724, pruned_loss=0.05198, over 1310726.06 frames.], batch size: 18, lr: 8.48e-04
2022-05-14 07:42:19,032 INFO [train.py:812] (4/8) Epoch 9, batch 550, loss[loss=0.1459, simple_loss=0.2245, pruned_loss=0.03362, over 7075.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2718, pruned_loss=0.05165, over 1338199.21 frames.], batch size: 18, lr: 8.48e-04
2022-05-14 07:43:17,530 INFO [train.py:812] (4/8) Epoch 9, batch 600, loss[loss=0.193, simple_loss=0.2726, pruned_loss=0.05664, over 7062.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2716, pruned_loss=0.05137, over 1359898.63 frames.], batch size: 18, lr: 8.47e-04
2022-05-14 07:44:16,645 INFO [train.py:812] (4/8) Epoch 9, batch 650, loss[loss=0.1733, simple_loss=0.2628, pruned_loss=0.04187, over 7357.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2716, pruned_loss=0.05126, over 1373248.08 frames.], batch size: 19, lr: 8.46e-04
2022-05-14 07:45:15,376 INFO [train.py:812] (4/8) Epoch 9, batch 700, loss[loss=0.1388, simple_loss=0.2297, pruned_loss=0.02394, over 7427.00 frames.], tot_loss[loss=0.1875, simple_loss=0.272, pruned_loss=0.05147, over 1386039.80 frames.], batch size: 20, lr: 8.46e-04
2022-05-14 07:46:13,721 INFO [train.py:812] (4/8) Epoch 9, batch 750, loss[loss=0.1815, simple_loss=0.2638, pruned_loss=0.04961, over 7160.00 frames.], tot_loss[loss=0.1889, simple_loss=0.273, pruned_loss=0.05241, over 1388710.88 frames.], batch size: 18, lr: 8.45e-04
2022-05-14 07:47:13,052 INFO [train.py:812] (4/8) Epoch 9, batch 800, loss[loss=0.2147, simple_loss=0.2942, pruned_loss=0.06764, over 7366.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2734, pruned_loss=0.05258, over 1395996.88 frames.], batch size: 23, lr: 8.45e-04
2022-05-14 07:48:11,325 INFO [train.py:812] (4/8) Epoch 9, batch 850, loss[loss=0.1719, simple_loss=0.2592, pruned_loss=0.04236, over 7323.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2727, pruned_loss=0.05213, over 1401173.37 frames.], batch size: 21, lr: 8.44e-04
2022-05-14 07:49:11,216 INFO [train.py:812] (4/8) Epoch 9, batch 900, loss[loss=0.2035, simple_loss=0.2894, pruned_loss=0.05878, over 7221.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2723, pruned_loss=0.05157, over 1410498.16 frames.], batch size: 21, lr: 8.44e-04
2022-05-14 07:50:10,521 INFO [train.py:812] (4/8) Epoch 9, batch 950, loss[loss=0.1626, simple_loss=0.2489, pruned_loss=0.03815, over 7324.00 frames.], tot_loss[loss=0.189, simple_loss=0.2732, pruned_loss=0.05243, over 1408076.32 frames.], batch size: 20, lr: 8.43e-04
2022-05-14 07:51:10,500 INFO [train.py:812] (4/8) Epoch 9, batch 1000, loss[loss=0.1757, simple_loss=0.2579, pruned_loss=0.04675, over 7427.00 frames.], tot_loss[loss=0.1887, simple_loss=0.273, pruned_loss=0.05218, over 1412734.72 frames.], batch size: 20, lr: 8.43e-04
2022-05-14 07:52:08,963 INFO [train.py:812] (4/8) Epoch 9, batch 1050, loss[loss=0.1844, simple_loss=0.268, pruned_loss=0.05036, over 7273.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2737, pruned_loss=0.05251, over 1417217.51 frames.], batch size: 19, lr: 8.42e-04
2022-05-14 07:53:07,737 INFO [train.py:812] (4/8) Epoch 9, batch 1100, loss[loss=0.1788, simple_loss=0.2602, pruned_loss=0.04865, over 7282.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2752, pruned_loss=0.05291, over 1420031.54 frames.], batch size: 17, lr: 8.41e-04
2022-05-14 07:54:04,867 INFO [train.py:812] (4/8) Epoch 9, batch 1150, loss[loss=0.182, simple_loss=0.2704, pruned_loss=0.04685, over 7323.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2734, pruned_loss=0.05198, over 1420954.15 frames.], batch size: 25, lr: 8.41e-04
2022-05-14 07:55:04,933 INFO [train.py:812] (4/8) Epoch 9, batch 1200, loss[loss=0.1714, simple_loss=0.2584, pruned_loss=0.04219, over 7433.00 frames.], tot_loss[loss=0.1886, simple_loss=0.273, pruned_loss=0.05206, over 1420767.17 frames.], batch size: 20, lr: 8.40e-04
2022-05-14 07:56:02,844 INFO [train.py:812] (4/8) Epoch 9, batch 1250, loss[loss=0.1913, simple_loss=0.2634, pruned_loss=0.05956, over 6760.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2732, pruned_loss=0.05287, over 1417325.97 frames.], batch size: 15, lr: 8.40e-04
2022-05-14 07:57:02,081 INFO [train.py:812] (4/8) Epoch 9, batch 1300, loss[loss=0.2043, simple_loss=0.2866, pruned_loss=0.06096, over 7168.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2741, pruned_loss=0.05326, over 1414602.29 frames.], batch size: 19, lr: 8.39e-04
2022-05-14 07:58:01,344 INFO [train.py:812] (4/8) Epoch 9, batch 1350, loss[loss=0.1804, simple_loss=0.2706, pruned_loss=0.04509, over 7414.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2741, pruned_loss=0.05342, over 1419019.50 frames.], batch size: 20, lr: 8.39e-04
2022-05-14 07:59:00,868 INFO [train.py:812] (4/8) Epoch 9, batch 1400, loss[loss=0.1784, simple_loss=0.2657, pruned_loss=0.04551, over 7221.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2739, pruned_loss=0.05371, over 1416109.59 frames.], batch size: 21, lr: 8.38e-04
2022-05-14 07:59:57,888 INFO [train.py:812] (4/8) Epoch 9, batch 1450, loss[loss=0.1891, simple_loss=0.2796, pruned_loss=0.04925, over 7317.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2727, pruned_loss=0.05302, over 1420762.93 frames.], batch size: 21, lr: 8.38e-04
2022-05-14 08:00:55,539 INFO [train.py:812] (4/8) Epoch 9, batch 1500, loss[loss=0.179, simple_loss=0.2741, pruned_loss=0.04192, over 7233.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2734, pruned_loss=0.05316, over 1423310.82 frames.], batch size: 20, lr: 8.37e-04
2022-05-14 08:01:53,805 INFO [train.py:812] (4/8) Epoch 9, batch 1550, loss[loss=0.1657, simple_loss=0.2532, pruned_loss=0.03906, over 7206.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2731, pruned_loss=0.05308, over 1422091.80 frames.], batch size: 22, lr: 8.37e-04
2022-05-14 08:02:52,000 INFO [train.py:812] (4/8) Epoch 9, batch 1600, loss[loss=0.1517, simple_loss=0.2318, pruned_loss=0.03577, over 7069.00 frames.], tot_loss[loss=0.1902, simple_loss=0.274, pruned_loss=0.05317, over 1420292.23 frames.], batch size: 18, lr: 8.36e-04
2022-05-14 08:03:49,505 INFO [train.py:812] (4/8) Epoch 9, batch 1650, loss[loss=0.1809, simple_loss=0.2777, pruned_loss=0.04198, over 7110.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2755, pruned_loss=0.05369, over 1420763.86 frames.], batch size: 21, lr: 8.35e-04
2022-05-14 08:04:47,912 INFO [train.py:812] (4/8) Epoch 9, batch 1700, loss[loss=0.1894, simple_loss=0.2773, pruned_loss=0.05077, over 7142.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2754, pruned_loss=0.05352, over 1419180.57 frames.], batch size: 20, lr: 8.35e-04
2022-05-14 08:05:46,548 INFO [train.py:812] (4/8) Epoch 9, batch 1750, loss[loss=0.2184, simple_loss=0.3113, pruned_loss=0.06272, over 7314.00 frames.], tot_loss[loss=0.19, simple_loss=0.274, pruned_loss=0.05301, over 1421181.83 frames.], batch size: 21, lr: 8.34e-04
2022-05-14 08:06:45,593 INFO [train.py:812] (4/8) Epoch 9, batch 1800, loss[loss=0.1927, simple_loss=0.2828, pruned_loss=0.05124, over 7236.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2738, pruned_loss=0.05291, over 1417835.11 frames.], batch size: 20, lr: 8.34e-04
2022-05-14 08:07:44,992 INFO [train.py:812] (4/8) Epoch 9, batch 1850, loss[loss=0.1719, simple_loss=0.2694, pruned_loss=0.03717, over 7241.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2744, pruned_loss=0.05293, over 1420988.59 frames.], batch size: 20, lr: 8.33e-04
2022-05-14 08:08:44,865 INFO [train.py:812] (4/8) Epoch 9, batch 1900, loss[loss=0.1844, simple_loss=0.2644, pruned_loss=0.05224, over 7155.00 frames.], tot_loss[loss=0.1906, simple_loss=0.275, pruned_loss=0.05307, over 1419586.82 frames.], batch size: 19, lr: 8.33e-04
2022-05-14 08:09:44,230 INFO [train.py:812] (4/8) Epoch 9, batch 1950, loss[loss=0.1915, simple_loss=0.2801, pruned_loss=0.05143, over 7114.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2752, pruned_loss=0.05314, over 1420473.83 frames.], batch size: 21, lr: 8.32e-04
2022-05-14 08:10:44,121 INFO [train.py:812] (4/8) Epoch 9, batch 2000, loss[loss=0.201, simple_loss=0.2871, pruned_loss=0.05742, over 7260.00 frames.], tot_loss[loss=0.189, simple_loss=0.2734, pruned_loss=0.05231, over 1421350.82 frames.], batch size: 24, lr: 8.32e-04
2022-05-14 08:11:43,579 INFO [train.py:812] (4/8) Epoch 9, batch 2050, loss[loss=0.1544, simple_loss=0.2251, pruned_loss=0.04188, over 7285.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2734, pruned_loss=0.05256, over 1420552.36 frames.], batch size: 17, lr: 8.31e-04
2022-05-14 08:12:43,242 INFO [train.py:812] (4/8) Epoch 9, batch 2100, loss[loss=0.1805, simple_loss=0.271, pruned_loss=0.04502, over 7248.00 frames.], tot_loss[loss=0.1885, simple_loss=0.273, pruned_loss=0.05201, over 1422249.18 frames.], batch size: 19, lr: 8.31e-04
2022-05-14 08:13:42,060 INFO [train.py:812] (4/8) Epoch 9, batch 2150, loss[loss=0.1668, simple_loss=0.2452, pruned_loss=0.0442, over 7077.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2725, pruned_loss=0.05185, over 1425070.96 frames.], batch size: 18, lr: 8.30e-04
2022-05-14 08:14:40,838 INFO [train.py:812] (4/8) Epoch 9, batch 2200, loss[loss=0.1793, simple_loss=0.2532, pruned_loss=0.05266, over 7270.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2736, pruned_loss=0.05263, over 1422836.36 frames.], batch size: 17, lr: 8.30e-04
2022-05-14 08:15:40,316 INFO [train.py:812] (4/8) Epoch 9, batch 2250, loss[loss=0.1773, simple_loss=0.2583, pruned_loss=0.0482, over 7153.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2729, pruned_loss=0.0524, over 1423861.70 frames.], batch size: 18, lr: 8.29e-04
2022-05-14 08:16:40,189 INFO [train.py:812] (4/8) Epoch 9, batch 2300, loss[loss=0.172, simple_loss=0.2606, pruned_loss=0.04172, over 7131.00 frames.], tot_loss[loss=0.1898, simple_loss=0.274, pruned_loss=0.05283, over 1425365.78 frames.], batch size: 20, lr: 8.29e-04
2022-05-14 08:17:37,468 INFO [train.py:812] (4/8) Epoch 9, batch 2350, loss[loss=0.2037, simple_loss=0.286, pruned_loss=0.06066, over 6856.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2755, pruned_loss=0.0539, over 1423786.93 frames.], batch size: 31, lr: 8.28e-04
2022-05-14 08:18:37,030 INFO [train.py:812] (4/8) Epoch 9, batch 2400, loss[loss=0.1674, simple_loss=0.2536, pruned_loss=0.04058, over 7270.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2754, pruned_loss=0.05349, over 1423792.73 frames.], batch size: 18, lr: 8.28e-04
2022-05-14 08:19:36,158 INFO [train.py:812] (4/8) Epoch 9, batch 2450, loss[loss=0.1618, simple_loss=0.2443, pruned_loss=0.03963, over 7403.00 frames.], tot_loss[loss=0.191, simple_loss=0.2753, pruned_loss=0.05334, over 1425115.99 frames.], batch size: 18, lr: 8.27e-04
2022-05-14 08:20:34,801 INFO [train.py:812] (4/8) Epoch 9, batch 2500, loss[loss=0.2248, simple_loss=0.3152, pruned_loss=0.06722, over 7203.00 frames.], tot_loss[loss=0.191, simple_loss=0.2754, pruned_loss=0.05328, over 1424312.73 frames.], batch size: 22, lr: 8.27e-04
2022-05-14 08:21:43,994 INFO [train.py:812] (4/8) Epoch 9, batch 2550, loss[loss=0.1496, simple_loss=0.2328, pruned_loss=0.03314, over 7134.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2738, pruned_loss=0.05255, over 1421559.76 frames.], batch size: 17, lr: 8.26e-04
2022-05-14 08:22:42,423 INFO [train.py:812] (4/8) Epoch 9, batch 2600, loss[loss=0.239, simple_loss=0.3264, pruned_loss=0.07576, over 7390.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2749, pruned_loss=0.05283, over 1418956.20 frames.], batch size: 23, lr: 8.25e-04
2022-05-14 08:23:41,184 INFO [train.py:812] (4/8) Epoch 9, batch 2650, loss[loss=0.2198, simple_loss=0.2968, pruned_loss=0.07143, over 4959.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2742, pruned_loss=0.05315, over 1417647.44 frames.], batch size: 52, lr: 8.25e-04
2022-05-14 08:24:39,381 INFO [train.py:812] (4/8) Epoch 9, batch 2700, loss[loss=0.1804, simple_loss=0.2675, pruned_loss=0.0466, over 7333.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2738, pruned_loss=0.05232, over 1418929.63 frames.], batch size: 22, lr: 8.24e-04
2022-05-14 08:25:38,213 INFO [train.py:812] (4/8) Epoch 9, batch 2750, loss[loss=0.1583, simple_loss=0.2539, pruned_loss=0.03136, over 7337.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2731, pruned_loss=0.05174, over 1423252.43 frames.], batch size: 20, lr: 8.24e-04
2022-05-14 08:26:37,732 INFO [train.py:812] (4/8) Epoch 9, batch 2800, loss[loss=0.1743, simple_loss=0.2656, pruned_loss=0.04152, over 7211.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2726, pruned_loss=0.0515, over 1425993.14 frames.], batch size: 22, lr: 8.23e-04
2022-05-14 08:27:35,908 INFO [train.py:812] (4/8) Epoch 9, batch 2850, loss[loss=0.1947, simple_loss=0.2789, pruned_loss=0.05522, over 7158.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2719, pruned_loss=0.0514, over 1428370.71 frames.], batch size: 19, lr: 8.23e-04
2022-05-14 08:28:33,954 INFO [train.py:812] (4/8) Epoch 9, batch 2900, loss[loss=0.1932, simple_loss=0.2816, pruned_loss=0.05238, over 7318.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2722, pruned_loss=0.05137, over 1426827.50 frames.], batch size: 21, lr: 8.22e-04
2022-05-14 08:29:31,235 INFO [train.py:812] (4/8) Epoch 9, batch 2950, loss[loss=0.1705, simple_loss=0.2511, pruned_loss=0.0449, over 7273.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2734, pruned_loss=0.05205, over 1423540.58 frames.], batch size: 18, lr: 8.22e-04
2022-05-14 08:30:30,198 INFO [train.py:812] (4/8) Epoch 9, batch 3000, loss[loss=0.1876, simple_loss=0.2701, pruned_loss=0.05256, over 7265.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2732, pruned_loss=0.0519, over 1421820.93 frames.], batch size: 24, lr: 8.21e-04
2022-05-14 08:30:30,199 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 08:30:38,337 INFO [train.py:841] (4/8) Epoch 9, validation: loss=0.1602, simple_loss=0.262, pruned_loss=0.0292, over 698248.00 frames.
2022-05-14 08:31:37,161 INFO [train.py:812] (4/8) Epoch 9, batch 3050, loss[loss=0.1653, simple_loss=0.2522, pruned_loss=0.0392, over 7321.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2728, pruned_loss=0.05174, over 1418993.44 frames.], batch size: 20, lr: 8.21e-04
2022-05-14 08:32:34,695 INFO [train.py:812] (4/8) Epoch 9, batch 3100, loss[loss=0.2055, simple_loss=0.2876, pruned_loss=0.06171, over 6817.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2747, pruned_loss=0.05256, over 1413892.92 frames.], batch size: 31, lr: 8.20e-04
2022-05-14 08:33:32,680 INFO [train.py:812] (4/8) Epoch 9, batch 3150, loss[loss=0.2034, simple_loss=0.3026, pruned_loss=0.05211, over 7156.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2741, pruned_loss=0.05259, over 1417621.76 frames.], batch size: 19, lr: 8.20e-04
2022-05-14 08:34:32,443 INFO [train.py:812] (4/8) Epoch 9, batch 3200, loss[loss=0.1998, simple_loss=0.3004, pruned_loss=0.04954, over 7143.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2741, pruned_loss=0.05246, over 1421462.82 frames.], batch size: 20, lr: 8.19e-04
2022-05-14 08:35:31,376 INFO [train.py:812] (4/8) Epoch 9, batch 3250, loss[loss=0.2629, simple_loss=0.3358, pruned_loss=0.095, over 5277.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2752, pruned_loss=0.05332, over 1420119.28 frames.], batch size: 53, lr: 8.19e-04
2022-05-14 08:36:46,155 INFO [train.py:812] (4/8) Epoch 9, batch 3300, loss[loss=0.1831, simple_loss=0.2703, pruned_loss=0.04798, over 7197.00 frames.], tot_loss[loss=0.1897, simple_loss=0.274, pruned_loss=0.05276, over 1419923.28 frames.], batch size: 22, lr: 8.18e-04
2022-05-14 08:37:52,678 INFO [train.py:812] (4/8) Epoch 9, batch 3350, loss[loss=0.1639, simple_loss=0.2461, pruned_loss=0.04084, over 7249.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2727, pruned_loss=0.0519, over 1423640.10 frames.], batch size: 19, lr: 8.18e-04
2022-05-14 08:38:51,540 INFO [train.py:812] (4/8) Epoch 9, batch 3400, loss[loss=0.1989, simple_loss=0.2845, pruned_loss=0.05669, over 6866.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2723, pruned_loss=0.0515, over 1422450.78 frames.], batch size: 31, lr: 8.17e-04
2022-05-14 08:39:59,372 INFO [train.py:812] (4/8) Epoch 9, batch 3450, loss[loss=0.1604, simple_loss=0.2391, pruned_loss=0.04088, over 7408.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2723, pruned_loss=0.05142, over 1424936.70 frames.], batch size: 18, lr: 8.17e-04
2022-05-14 08:41:27,459 INFO [train.py:812] (4/8) Epoch 9, batch 3500, loss[loss=0.1789, simple_loss=0.255, pruned_loss=0.05138, over 7165.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2722, pruned_loss=0.05136, over 1425238.30 frames.], batch size: 19, lr: 8.16e-04
2022-05-14 08:42:35,749 INFO [train.py:812] (4/8) Epoch 9, batch 3550, loss[loss=0.172, simple_loss=0.2538, pruned_loss=0.04512, over 7171.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2722, pruned_loss=0.0516, over 1427241.98 frames.], batch size: 18, lr: 8.16e-04
2022-05-14 08:43:34,796 INFO [train.py:812] (4/8) Epoch 9, batch 3600, loss[loss=0.1849, simple_loss=0.2711, pruned_loss=0.04938, over 7277.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2723, pruned_loss=0.05142, over 1424235.00 frames.], batch size: 18, lr: 8.15e-04
2022-05-14 08:44:32,181 INFO [train.py:812] (4/8) Epoch 9, batch 3650, loss[loss=0.191, simple_loss=0.2642, pruned_loss=0.0589, over 7123.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2719, pruned_loss=0.05125, over 1426195.78 frames.], batch size: 17, lr: 8.15e-04
2022-05-14 08:45:31,315 INFO [train.py:812] (4/8) Epoch 9, batch 3700, loss[loss=0.1899, simple_loss=0.2792, pruned_loss=0.05024, over 7308.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2724, pruned_loss=0.05159, over 1427011.20 frames.], batch size: 25, lr: 8.14e-04
2022-05-14 08:46:29,959 INFO [train.py:812] (4/8) Epoch 9, batch 3750, loss[loss=0.1772, simple_loss=0.2685, pruned_loss=0.04293, over 7429.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2736, pruned_loss=0.05213, over 1426120.58 frames.], batch size: 20, lr: 8.14e-04
2022-05-14 08:47:28,944 INFO [train.py:812] (4/8) Epoch 9, batch 3800, loss[loss=0.1477, simple_loss=0.2275, pruned_loss=0.03393, over 7401.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2742, pruned_loss=0.05261, over 1427658.77 frames.], batch size: 18, lr: 8.13e-04
2022-05-14 08:48:27,800 INFO [train.py:812] (4/8) Epoch 9, batch 3850, loss[loss=0.1639, simple_loss=0.2452, pruned_loss=0.04124, over 7284.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2733, pruned_loss=0.05196, over 1429720.97 frames.], batch size: 17, lr: 8.13e-04
2022-05-14 08:49:26,820 INFO [train.py:812] (4/8) Epoch 9, batch 3900, loss[loss=0.1996, simple_loss=0.2774, pruned_loss=0.0609, over 5051.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2735, pruned_loss=0.05168, over 1427297.21 frames.], batch size: 52, lr: 8.12e-04
2022-05-14 08:50:26,275 INFO [train.py:812] (4/8) Epoch 9, batch 3950, loss[loss=0.2123, simple_loss=0.2985, pruned_loss=0.06302, over 6796.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2726, pruned_loss=0.05133, over 1428821.58 frames.], batch size: 31, lr: 8.12e-04
2022-05-14 08:51:25,800 INFO [train.py:812] (4/8) Epoch 9, batch 4000, loss[loss=0.1916, simple_loss=0.2827, pruned_loss=0.05021, over 7225.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2738, pruned_loss=0.05203, over 1428289.55 frames.], batch size: 21, lr: 8.11e-04
2022-05-14 08:52:25,223 INFO [train.py:812] (4/8) Epoch 9, batch 4050, loss[loss=0.1834, simple_loss=0.2664, pruned_loss=0.05017, over 7410.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2728, pruned_loss=0.05209, over 1426841.28 frames.], batch size: 18, lr: 8.11e-04
2022-05-14 08:53:24,994 INFO [train.py:812] (4/8) Epoch 9, batch 4100, loss[loss=0.1881, simple_loss=0.2671, pruned_loss=0.0545, over 7125.00 frames.], tot_loss[loss=0.1884, simple_loss=0.273, pruned_loss=0.05193, over 1427601.99 frames.], batch size: 17, lr: 8.10e-04
2022-05-14 08:54:24,677 INFO [train.py:812] (4/8) Epoch 9, batch 4150, loss[loss=0.2033, simple_loss=0.2939, pruned_loss=0.05637, over 7125.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2726, pruned_loss=0.05204, over 1422521.92 frames.], batch size: 28, lr: 8.10e-04
2022-05-14 08:55:24,380 INFO [train.py:812] (4/8) Epoch 9, batch 4200, loss[loss=0.1653, simple_loss=0.2471, pruned_loss=0.04173, over 7324.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2715, pruned_loss=0.05153, over 1423453.32 frames.], batch size: 20, lr: 8.09e-04
2022-05-14 08:56:23,007 INFO [train.py:812] (4/8) Epoch 9, batch 4250, loss[loss=0.1725, simple_loss=0.2558, pruned_loss=0.04463, over 7130.00 frames.], tot_loss[loss=0.187, simple_loss=0.2708, pruned_loss=0.05158, over 1419315.97 frames.], batch size: 17, lr: 8.09e-04
2022-05-14 08:57:22,988 INFO [train.py:812] (4/8) Epoch 9, batch 4300, loss[loss=0.203, simple_loss=0.2985, pruned_loss=0.05379, over 7417.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2714, pruned_loss=0.05213, over 1414487.22 frames.], batch size: 21, lr: 8.08e-04
2022-05-14 08:58:21,483 INFO [train.py:812] (4/8) Epoch 9, batch 4350, loss[loss=0.1488, simple_loss=0.2273, pruned_loss=0.03517, over 7287.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2705, pruned_loss=0.05145, over 1420358.19 frames.], batch size: 17, lr: 8.08e-04
2022-05-14 08:59:21,261 INFO [train.py:812] (4/8) Epoch 9, batch 4400, loss[loss=0.1994, simple_loss=0.2841, pruned_loss=0.05737, over 7042.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2703, pruned_loss=0.05136, over 1417097.00 frames.], batch size: 28, lr: 8.07e-04
2022-05-14 09:00:19,277 INFO [train.py:812] (4/8) Epoch 9, batch 4450, loss[loss=0.2125, simple_loss=0.2993, pruned_loss=0.06289, over 7072.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2687, pruned_loss=0.05104, over 1412154.46 frames.], batch size: 28, lr: 8.07e-04
2022-05-14 09:01:19,088 INFO [train.py:812] (4/8) Epoch 9, batch 4500, loss[loss=0.2146, simple_loss=0.2909, pruned_loss=0.06911, over 7092.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2699, pruned_loss=0.05198, over 1394504.40 frames.], batch size: 28, lr: 8.07e-04
2022-05-14 09:02:17,096 INFO [train.py:812] (4/8) Epoch 9, batch 4550, loss[loss=0.1798, simple_loss=0.2746, pruned_loss=0.04252, over 6440.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2743, pruned_loss=0.05443, over 1353476.33 frames.], batch size: 38, lr: 8.06e-04
2022-05-14 09:03:24,804 INFO [train.py:812] (4/8) Epoch 10, batch 0, loss[loss=0.2103, simple_loss=0.2957, pruned_loss=0.06242, over 7410.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2957, pruned_loss=0.06242, over 7410.00 frames.], batch size: 21, lr: 7.75e-04
2022-05-14 09:04:24,009 INFO [train.py:812] (4/8) Epoch 10, batch 50, loss[loss=0.1968, simple_loss=0.2872, pruned_loss=0.05323, over 7214.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2718, pruned_loss=0.04987, over 321619.37 frames.], batch size: 23, lr: 7.74e-04
2022-05-14 09:05:23,095 INFO [train.py:812] (4/8) Epoch 10, batch 100, loss[loss=0.216, simple_loss=0.2931, pruned_loss=0.0694, over 5232.00 frames.], tot_loss[loss=0.1852, simple_loss=0.27, pruned_loss=0.05019, over 557011.48 frames.], batch size: 52, lr: 7.74e-04
2022-05-14 09:06:22,298 INFO [train.py:812] (4/8) Epoch 10, batch 150, loss[loss=0.1767, simple_loss=0.2665, pruned_loss=0.04347, over 7431.00 frames.], tot_loss[loss=0.1842, simple_loss=0.27, pruned_loss=0.04921, over 750390.68 frames.], batch size: 20, lr: 7.73e-04
2022-05-14 09:07:20,632 INFO [train.py:812] (4/8) Epoch 10, batch 200, loss[loss=0.1767, simple_loss=0.2607, pruned_loss=0.04635, over 7427.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2703, pruned_loss=0.04929, over 897735.32 frames.], batch size: 20, lr: 7.73e-04
2022-05-14 09:08:19,896 INFO [train.py:812] (4/8) Epoch 10, batch 250, loss[loss=0.188, simple_loss=0.2737, pruned_loss=0.05119, over 7168.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2714, pruned_loss=0.04959, over 1009451.69 frames.], batch size: 18, lr: 7.72e-04
2022-05-14 09:09:19,088 INFO [train.py:812] (4/8) Epoch 10, batch 300, loss[loss=0.1709, simple_loss=0.2619, pruned_loss=0.03994, over 7331.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2702, pruned_loss=0.04968, over 1103084.20 frames.], batch size: 20, lr: 7.72e-04
2022-05-14 09:10:16,345 INFO [train.py:812] (4/8) Epoch 10, batch 350, loss[loss=0.1816, simple_loss=0.2688, pruned_loss=0.04718, over 7188.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2703, pruned_loss=0.04945, over 1170886.42 frames.], batch size: 23, lr: 7.71e-04
2022-05-14 09:11:15,057 INFO [train.py:812] (4/8) Epoch 10, batch 400, loss[loss=0.2006, simple_loss=0.2891, pruned_loss=0.05609, over 7138.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2718, pruned_loss=0.05023, over 1221929.79 frames.], batch size: 26, lr: 7.71e-04
2022-05-14 09:12:14,068 INFO [train.py:812] (4/8) Epoch 10, batch 450, loss[loss=0.1857, simple_loss=0.2683, pruned_loss=0.05154, over 6372.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2717, pruned_loss=0.04964, over 1260742.65 frames.], batch size: 37, lr: 7.71e-04
2022-05-14 09:13:13,644 INFO [train.py:812] (4/8) Epoch 10, batch 500, loss[loss=0.1721, simple_loss=0.2532, pruned_loss=0.04547, over 7159.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2721, pruned_loss=0.04989, over 1296029.20 frames.], batch size: 19, lr: 7.70e-04
2022-05-14 09:14:12,267 INFO [train.py:812] (4/8) Epoch 10, batch 550, loss[loss=0.185, simple_loss=0.2511, pruned_loss=0.05943, over 7133.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2711, pruned_loss=0.04982, over 1323470.23 frames.], batch size: 17, lr: 7.70e-04
2022-05-14 09:15:10,137 INFO [train.py:812] (4/8) Epoch 10, batch 600, loss[loss=0.1647, simple_loss=0.2482, pruned_loss=0.04062, over 7281.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2709, pruned_loss=0.04974, over 1344828.58 frames.], batch size: 18, lr: 7.69e-04
2022-05-14 09:16:08,333 INFO [train.py:812] (4/8) Epoch 10, batch 650, loss[loss=0.211, simple_loss=0.2958, pruned_loss=0.06304, over 7123.00 frames.], tot_loss[loss=0.1856, simple_loss=0.271, pruned_loss=0.05012, over 1361178.42 frames.], batch size: 26, lr: 7.69e-04
2022-05-14 09:17:07,955 INFO [train.py:812] (4/8) Epoch 10, batch 700, loss[loss=0.1931, simple_loss=0.2841, pruned_loss=0.05101, over 7291.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2702, pruned_loss=0.04952, over 1375986.98 frames.], batch size: 25, lr: 7.68e-04
2022-05-14 09:18:07,544 INFO [train.py:812] (4/8) Epoch 10, batch 750, loss[loss=0.1922, simple_loss=0.2766, pruned_loss=0.05394, over 7432.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2704, pruned_loss=0.04963, over 1385986.28 frames.], batch size: 20, lr: 7.68e-04
2022-05-14 09:19:06,541 INFO [train.py:812] (4/8) Epoch 10, batch 800, loss[loss=0.2025, simple_loss=0.2898, pruned_loss=0.05766, over 7288.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2697, pruned_loss=0.04923, over 1393604.51 frames.], batch size: 24, lr: 7.67e-04
2022-05-14 09:20:06,000 INFO [train.py:812] (4/8) Epoch 10, batch 850, loss[loss=0.2024, simple_loss=0.2871, pruned_loss=0.05884, over 6353.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2713, pruned_loss=0.04956, over 1396472.64 frames.], batch size: 38, lr: 7.67e-04
2022-05-14 09:21:05,085 INFO [train.py:812] (4/8) Epoch 10, batch 900, loss[loss=0.1921, simple_loss=0.2759, pruned_loss=0.05414, over 7311.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2714, pruned_loss=0.04961, over 1406044.25 frames.], batch size: 21, lr: 7.66e-04
2022-05-14 09:22:03,783 INFO [train.py:812] (4/8) Epoch 10, batch 950, loss[loss=0.1845, simple_loss=0.2673, pruned_loss=0.05089, over 7187.00 frames.], tot_loss[loss=0.1865, simple_loss=0.272, pruned_loss=0.05052, over 1405984.03 frames.], batch size: 26, lr: 7.66e-04
2022-05-14 09:23:02,560 INFO [train.py:812] (4/8) Epoch 10, batch 1000, loss[loss=0.1708, simple_loss=0.2729, pruned_loss=0.03433, over 7319.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2714, pruned_loss=0.05, over 1414320.56 frames.], batch size: 20, lr: 7.66e-04
2022-05-14 09:24:00,834 INFO [train.py:812] (4/8) Epoch 10, batch 1050, loss[loss=0.1713, simple_loss=0.265, pruned_loss=0.03882, over 7053.00 frames.], tot_loss[loss=0.1858, simple_loss=0.271, pruned_loss=0.05032, over 1416606.26 frames.], batch size: 28, lr: 7.65e-04
2022-05-14 09:24:59,368 INFO [train.py:812] (4/8) Epoch 10, batch 1100, loss[loss=0.1878, simple_loss=0.2764, pruned_loss=0.04966, over 7032.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2719, pruned_loss=0.05061, over 1416913.24 frames.], batch size: 28, lr: 7.65e-04
2022-05-14 09:25:57,283 INFO [train.py:812] (4/8) Epoch 10, batch 1150, loss[loss=0.1683, simple_loss=0.258, pruned_loss=0.03935, over 7334.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2714, pruned_loss=0.05059, over 1421597.30 frames.], batch size: 20, lr: 7.64e-04
2022-05-14 09:26:55,704 INFO [train.py:812] (4/8) Epoch 10, batch 1200, loss[loss=0.2234, simple_loss=0.3092, pruned_loss=0.06876, over 7203.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2727, pruned_loss=0.05111, over 1420051.97 frames.], batch size: 23, lr: 7.64e-04
2022-05-14 09:27:55,413 INFO [train.py:812] (4/8) Epoch 10, batch 1250, loss[loss=0.1496, simple_loss=0.2339, pruned_loss=0.0326, over 7274.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2719, pruned_loss=0.05065, over 1418712.76 frames.], batch size: 17, lr: 7.63e-04
2022-05-14 09:28:54,705 INFO [train.py:812] (4/8) Epoch 10, batch 1300, loss[loss=0.1421, simple_loss=0.2236, pruned_loss=0.03029, over 7010.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2714, pruned_loss=0.05085, over 1416504.70 frames.], batch size: 16, lr: 7.63e-04
2022-05-14 09:29:54,193 INFO [train.py:812] (4/8) Epoch 10, batch 1350, loss[loss=0.1894, simple_loss=0.2786, pruned_loss=0.05011, over 7323.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2717, pruned_loss=0.0509, over 1414087.28 frames.], batch size: 21, lr: 7.62e-04
2022-05-14 09:30:53,024 INFO [train.py:812] (4/8) Epoch 10, batch 1400, loss[loss=0.1916, simple_loss=0.2865, pruned_loss=0.04829, over 7130.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2718, pruned_loss=0.0505, over 1417469.89 frames.], batch size: 21, lr: 7.62e-04
2022-05-14 09:31:52,541 INFO [train.py:812] (4/8) Epoch 10, batch 1450, loss[loss=0.1907, simple_loss=0.2894, pruned_loss=0.04601, over 7316.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2709, pruned_loss=0.04977, over 1418729.52 frames.], batch size: 25, lr: 7.62e-04
2022-05-14 09:32:51,548 INFO [train.py:812] (4/8) Epoch 10, batch 1500, loss[loss=0.2096, simple_loss=0.2941, pruned_loss=0.06256, over 5001.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2715, pruned_loss=0.0501, over 1414753.01 frames.], batch size: 52, lr: 7.61e-04
2022-05-14 09:33:51,497 INFO [train.py:812] (4/8) Epoch 10, batch 1550, loss[loss=0.1738, simple_loss=0.2509, pruned_loss=0.04835, over 7354.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2709, pruned_loss=0.04984, over 1417882.27 frames.], batch size: 19, lr: 7.61e-04
2022-05-14 09:34:49,175 INFO [train.py:812] (4/8) Epoch 10, batch 1600, loss[loss=0.1656, simple_loss=0.2555, pruned_loss=0.0379, over 7249.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2702, pruned_loss=0.04965, over 1417310.94 frames.], batch size: 19, lr: 7.60e-04
2022-05-14 09:35:46,384 INFO [train.py:812] (4/8) Epoch 10, batch 1650, loss[loss=0.1982, simple_loss=0.2915, pruned_loss=0.05241, over 7403.00 frames.], tot_loss[loss=0.1847, simple_loss=0.27, pruned_loss=0.04973, over 1415805.28 frames.], batch size: 21, lr: 7.60e-04
2022-05-14 09:36:44,423 INFO [train.py:812] (4/8) Epoch 10, batch 1700, loss[loss=0.2039, simple_loss=0.2953, pruned_loss=0.05627, over 7276.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2695, pruned_loss=0.04942, over 1414423.48 frames.], batch size: 24, lr: 7.59e-04
2022-05-14 09:37:43,565 INFO [train.py:812] (4/8) Epoch 10, batch 1750, loss[loss=0.1654, simple_loss=0.2408, pruned_loss=0.04497, over 7242.00 frames.], tot_loss[loss=0.1858, simple_loss=0.271, pruned_loss=0.05024, over 1406717.54 frames.], batch size: 16, lr: 7.59e-04
2022-05-14 09:38:41,645 INFO [train.py:812] (4/8) Epoch 10, batch 1800, loss[loss=0.1956, simple_loss=0.2892, pruned_loss=0.05102, over 7354.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2709, pruned_loss=0.05018, over 1411207.10 frames.], batch size: 19, lr: 7.59e-04
2022-05-14 09:39:39,853 INFO [train.py:812] (4/8) Epoch 10, batch 1850, loss[loss=0.2113, simple_loss=0.2784, pruned_loss=0.07215, over 7362.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2721, pruned_loss=0.05077, over 1411991.15 frames.], batch size: 19, lr: 7.58e-04
2022-05-14 09:40:38,489 INFO [train.py:812] (4/8) Epoch 10, batch 1900, loss[loss=0.173, simple_loss=0.2456, pruned_loss=0.05021, over 7283.00 frames.], tot_loss[loss=0.1855, simple_loss=0.271, pruned_loss=0.04999, over 1416630.29 frames.], batch size: 18, lr: 7.58e-04
2022-05-14 09:41:37,150 INFO [train.py:812] (4/8) Epoch 10, batch 1950, loss[loss=0.2396, simple_loss=0.3161, pruned_loss=0.0816, over 7210.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2703, pruned_loss=0.04999, over 1415959.84 frames.], batch size: 23, lr: 7.57e-04
2022-05-14 09:42:35,054 INFO [train.py:812] (4/8) Epoch 10, batch 2000, loss[loss=0.1865, simple_loss=0.2719, pruned_loss=0.05059, over 7242.00 frames.], tot_loss[loss=0.184, simple_loss=0.2695, pruned_loss=0.04929, over 1418629.09 frames.], batch size: 20, lr: 7.57e-04
2022-05-14 09:43:34,861 INFO [train.py:812] (4/8) Epoch 10, batch 2050, loss[loss=0.1766, simple_loss=0.266, pruned_loss=0.04358, over 7198.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2686, pruned_loss=0.04907, over 1420473.05 frames.], batch size: 23, lr: 7.56e-04
2022-05-14 09:44:34,079 INFO [train.py:812] (4/8) Epoch 10, batch 2100, loss[loss=0.2006, simple_loss=0.291, pruned_loss=0.05513, over 7143.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2687, pruned_loss=0.04913, over 1424912.94 frames.], batch size: 20, lr: 7.56e-04
2022-05-14 09:45:31,444 INFO [train.py:812] (4/8) Epoch 10, batch 2150, loss[loss=0.1606, simple_loss=0.2387, pruned_loss=0.04125, over 7419.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2684, pruned_loss=0.04901, over 1427242.57 frames.], batch size: 18, lr: 7.56e-04
2022-05-14 09:46:28,647 INFO [train.py:812] (4/8) Epoch 10, batch 2200, loss[loss=0.1718, simple_loss=0.2614, pruned_loss=0.04106, over 6527.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2687, pruned_loss=0.0487, over 1426952.54 frames.], batch size: 38, lr: 7.55e-04
2022-05-14 09:47:27,357 INFO [train.py:812] (4/8) Epoch 10, batch 2250, loss[loss=0.1862, simple_loss=0.2785, pruned_loss=0.04697, over 7319.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2686, pruned_loss=0.04883, over 1428531.78 frames.], batch size: 21, lr: 7.55e-04
2022-05-14 09:48:25,581 INFO [train.py:812] (4/8) Epoch 10, batch 2300, loss[loss=0.2018, simple_loss=0.2858, pruned_loss=0.05888, over 7146.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2694, pruned_loss=0.04913, over 1426467.59 frames.], batch size: 20, lr: 7.54e-04
2022-05-14 09:49:24,921 INFO [train.py:812] (4/8) Epoch 10, batch 2350, loss[loss=0.1917, simple_loss=0.2801, pruned_loss=0.05164, over 7199.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2686, pruned_loss=0.04913, over 1424686.36 frames.], batch size: 22, lr: 7.54e-04
2022-05-14 09:50:22,140 INFO [train.py:812] (4/8) Epoch 10, batch 2400, loss[loss=0.1868, simple_loss=0.2724, pruned_loss=0.05065, over 7277.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2693, pruned_loss=0.04947, over 1426506.83 frames.], batch size: 18, lr: 7.53e-04
2022-05-14 09:51:20,805 INFO [train.py:812] (4/8) Epoch 10, batch 2450, loss[loss=0.1586, simple_loss=0.2363, pruned_loss=0.04049, over 7062.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2687, pruned_loss=0.04941, over 1430241.26 frames.], batch size: 18, lr: 7.53e-04
2022-05-14 09:52:18,421 INFO [train.py:812] (4/8) Epoch 10, batch 2500, loss[loss=0.2028, simple_loss=0.2949, pruned_loss=0.05537, over 7323.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2686, pruned_loss=0.04909, over 1428515.23 frames.], batch size: 21, lr: 7.53e-04
2022-05-14 09:53:18,341 INFO [train.py:812] (4/8) Epoch 10, batch 2550, loss[loss=0.1848, simple_loss=0.2781, pruned_loss=0.04577, over 7227.00 frames.], tot_loss[loss=0.1839, simple_loss=0.269, pruned_loss=0.04943, over 1426040.63 frames.], batch size: 21, lr: 7.52e-04
2022-05-14 09:54:18,077 INFO [train.py:812] (4/8) Epoch 10, batch 2600, loss[loss=0.2067, simple_loss=0.2877, pruned_loss=0.06287, over 7159.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2687, pruned_loss=0.0493, over 1429133.80 frames.], batch size: 26, lr: 7.52e-04
2022-05-14 09:55:17,734 INFO [train.py:812] (4/8) Epoch 10, batch 2650, loss[loss=0.1812, simple_loss=0.274, pruned_loss=0.04417, over 7333.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2697, pruned_loss=0.04969, over 1425088.28 frames.], batch size: 22, lr: 7.51e-04
2022-05-14 09:56:16,817 INFO [train.py:812] (4/8) Epoch 10, batch 2700, loss[loss=0.1944, simple_loss=0.2882, pruned_loss=0.05036, over 6773.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2691, pruned_loss=0.04932, over 1425021.62 frames.], batch size: 31, lr: 7.51e-04
2022-05-14 09:57:23,633 INFO [train.py:812] (4/8) Epoch 10, batch 2750, loss[loss=0.1804, simple_loss=0.2611, pruned_loss=0.04982, over 6744.00 frames.], tot_loss[loss=0.183, simple_loss=0.2682, pruned_loss=0.0489, over 1422450.12 frames.], batch size: 31, lr: 7.50e-04
2022-05-14 09:58:22,157 INFO [train.py:812] (4/8) Epoch 10, batch 2800, loss[loss=0.1822, simple_loss=0.2627, pruned_loss=0.05086, over 7379.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2683, pruned_loss=0.04876, over 1427779.21 frames.], batch size: 23, lr: 7.50e-04
2022-05-14 09:59:21,337 INFO [train.py:812] (4/8) Epoch 10, batch 2850, loss[loss=0.2049, simple_loss=0.2967, pruned_loss=0.05654, over 7325.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2689, pruned_loss=0.0493, over 1425753.02 frames.], batch size: 22, lr: 7.50e-04
2022-05-14 10:00:20,873 INFO [train.py:812] (4/8) Epoch 10, batch 2900, loss[loss=0.1816, simple_loss=0.2719, pruned_loss=0.04566, over 7109.00 frames.], tot_loss[loss=0.1838, simple_loss=0.269, pruned_loss=0.04933, over 1425356.92 frames.], batch size: 21, lr: 7.49e-04
2022-05-14 10:01:19,220 INFO [train.py:812] (4/8) Epoch 10, batch 2950, loss[loss=0.1551, simple_loss=0.2399, pruned_loss=0.03518, over 7279.00 frames.], tot_loss[loss=0.1838, simple_loss=0.269, pruned_loss=0.04929, over 1425781.90 frames.], batch size: 18, lr: 7.49e-04
2022-05-14 10:02:18,288 INFO [train.py:812] (4/8) Epoch 10, batch 3000, loss[loss=0.152, simple_loss=0.2313, pruned_loss=0.03636, over 7277.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2687, pruned_loss=0.04959, over 1425435.48 frames.], batch size: 17, lr: 7.48e-04
2022-05-14 10:02:18,289 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 10:02:25,810 INFO [train.py:841] (4/8) Epoch 10, validation: loss=0.1584, simple_loss=0.26, pruned_loss=0.0284, over 698248.00 frames.
2022-05-14 10:03:25,417 INFO [train.py:812] (4/8) Epoch 10, batch 3050, loss[loss=0.1806, simple_loss=0.2677, pruned_loss=0.0467, over 7161.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2685, pruned_loss=0.0493, over 1425302.85 frames.], batch size: 19, lr: 7.48e-04
2022-05-14 10:04:24,562 INFO [train.py:812] (4/8) Epoch 10, batch 3100, loss[loss=0.1883, simple_loss=0.2867, pruned_loss=0.0449, over 7122.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2684, pruned_loss=0.04896, over 1428461.20 frames.], batch size: 21, lr: 7.47e-04
2022-05-14 10:05:24,318 INFO [train.py:812] (4/8) Epoch 10, batch 3150, loss[loss=0.2082, simple_loss=0.2898, pruned_loss=0.06331, over 7314.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2683, pruned_loss=0.04922, over 1424559.92 frames.], batch size: 21, lr: 7.47e-04
2022-05-14 10:06:23,645 INFO [train.py:812] (4/8) Epoch 10, batch 3200, loss[loss=0.1598, simple_loss=0.2583, pruned_loss=0.03062, over 7232.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2672, pruned_loss=0.0487, over 1424387.77 frames.], batch size: 20, lr: 7.47e-04
2022-05-14 10:07:23,037 INFO [train.py:812] (4/8) Epoch 10, batch 3250, loss[loss=0.1932, simple_loss=0.2899, pruned_loss=0.04822, over 7405.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2676, pruned_loss=0.04838, over 1424704.51 frames.], batch size: 21, lr: 7.46e-04
2022-05-14 10:08:22,152 INFO [train.py:812] (4/8) Epoch 10, batch 3300, loss[loss=0.2141, simple_loss=0.2979, pruned_loss=0.06517, over 7202.00 frames.], tot_loss[loss=0.1815, simple_loss=0.267, pruned_loss=0.048, over 1425534.36 frames.], batch size: 22, lr: 7.46e-04
2022-05-14 10:09:21,723 INFO [train.py:812] (4/8) Epoch 10, batch 3350, loss[loss=0.1926, simple_loss=0.2769, pruned_loss=0.05412, over 7186.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2675, pruned_loss=0.04782, over 1426989.32 frames.], batch size: 23, lr: 7.45e-04
2022-05-14 10:10:20,629 INFO [train.py:812] (4/8) Epoch 10, batch 3400, loss[loss=0.169, simple_loss=0.2394, pruned_loss=0.04928, over 7286.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2682, pruned_loss=0.04851, over 1423012.60 frames.], batch size: 17, lr: 7.45e-04
2022-05-14 10:11:20,102 INFO [train.py:812] (4/8) Epoch 10, batch 3450, loss[loss=0.1911, simple_loss=0.2825, pruned_loss=0.04983, over 7300.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2683, pruned_loss=0.04855, over 1422126.72 frames.], batch size: 24, lr: 7.45e-04
2022-05-14 10:12:19,083 INFO [train.py:812] (4/8) Epoch 10, batch 3500, loss[loss=0.197, simple_loss=0.2844, pruned_loss=0.05485, over 7418.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2693, pruned_loss=0.04906, over 1422139.48 frames.], batch size: 21, lr: 7.44e-04
2022-05-14 10:13:18,714 INFO [train.py:812] (4/8) Epoch 10, batch 3550, loss[loss=0.203, simple_loss=0.2879, pruned_loss=0.05911, over 7072.00 frames.], tot_loss[loss=0.183, simple_loss=0.2681, pruned_loss=0.04895, over 1425469.34 frames.], batch size: 28, lr: 7.44e-04
2022-05-14 10:14:16,920 INFO [train.py:812] (4/8) Epoch 10, batch 3600, loss[loss=0.2098, simple_loss=0.3013, pruned_loss=0.05911, over 7071.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2685, pruned_loss=0.04883, over 1425913.84 frames.], batch size: 28, lr: 7.43e-04
2022-05-14 10:15:16,464 INFO [train.py:812] (4/8) Epoch 10, batch 3650, loss[loss=0.189, simple_loss=0.2762, pruned_loss=0.05089, over 7063.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2688, pruned_loss=0.04886, over 1422697.81 frames.], batch size: 18, lr: 7.43e-04
2022-05-14 10:16:15,506 INFO [train.py:812] (4/8) Epoch 10, batch 3700, loss[loss=0.1552, simple_loss=0.2302, pruned_loss=0.04007, over 7268.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2691, pruned_loss=0.04889, over 1425652.83 frames.], batch size: 17, lr: 7.43e-04
2022-05-14 10:17:15,206 INFO [train.py:812] (4/8) Epoch 10, batch 3750, loss[loss=0.1693, simple_loss=0.264, pruned_loss=0.0373, over 7162.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2708, pruned_loss=0.04955, over 1427676.42 frames.], batch size: 19, lr: 7.42e-04
2022-05-14 10:18:14,388 INFO [train.py:812] (4/8) Epoch 10, batch 3800, loss[loss=0.1722, simple_loss=0.2574, pruned_loss=0.0435, over 7420.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2707, pruned_loss=0.04979, over 1426289.31 frames.], batch size: 20, lr: 7.42e-04
2022-05-14 10:19:12,955 INFO [train.py:812] (4/8) Epoch 10, batch 3850, loss[loss=0.1459, simple_loss=0.2277, pruned_loss=0.03199, over 7064.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2714, pruned_loss=0.05041, over 1425233.95 frames.], batch size: 18, lr: 7.41e-04
2022-05-14 10:20:21,766 INFO [train.py:812] (4/8) Epoch 10, batch 3900, loss[loss=0.1865, simple_loss=0.2768, pruned_loss=0.04808, over 7161.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2708, pruned_loss=0.05016, over 1426863.77 frames.], batch size: 19, lr: 7.41e-04
2022-05-14 10:21:21,328 INFO [train.py:812] (4/8) Epoch 10, batch 3950, loss[loss=0.2241, simple_loss=0.2904, pruned_loss=0.07886, over 5355.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2711, pruned_loss=0.05017, over 1421246.08 frames.], batch size: 52, lr: 7.41e-04
2022-05-14 10:22:19,906 INFO [train.py:812] (4/8) Epoch 10, batch 4000, loss[loss=0.1647, simple_loss=0.2554, pruned_loss=0.03696, over 7270.00 frames.], tot_loss[loss=0.1859, simple_loss=0.271, pruned_loss=0.05041, over 1422443.64 frames.], batch size: 19, lr: 7.40e-04
2022-05-14 10:23:18,819 INFO [train.py:812] (4/8) Epoch 10, batch 4050, loss[loss=0.2054, simple_loss=0.2904, pruned_loss=0.06027, over 7134.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2707, pruned_loss=0.05, over 1422797.34 frames.], batch size: 17, lr: 7.40e-04
2022-05-14 10:24:16,989 INFO [train.py:812] (4/8) Epoch 10, batch 4100, loss[loss=0.1799, simple_loss=0.2694, pruned_loss=0.04522, over 7317.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2699, pruned_loss=0.04964, over 1425517.15 frames.], batch size: 21, lr: 7.39e-04
2022-05-14 10:25:16,586 INFO [train.py:812] (4/8) Epoch 10, batch 4150, loss[loss=0.1622, simple_loss=0.2449, pruned_loss=0.03968, over 7409.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2703, pruned_loss=0.05007, over 1425898.91 frames.], batch size: 18, lr: 7.39e-04
2022-05-14 10:26:14,796 INFO [train.py:812] (4/8) Epoch 10, batch 4200, loss[loss=0.1823, simple_loss=0.2632, pruned_loss=0.05073, over 7280.00 frames.], tot_loss[loss=0.185, simple_loss=0.2703, pruned_loss=0.04982, over 1427851.91 frames.], batch size: 24, lr: 7.39e-04
2022-05-14 10:27:13,951 INFO [train.py:812] (4/8) Epoch 10, batch 4250, loss[loss=0.2041, simple_loss=0.2779, pruned_loss=0.06516, over 7268.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2704, pruned_loss=0.04973, over 1423059.33 frames.], batch size: 17, lr: 7.38e-04
2022-05-14 10:28:13,110 INFO [train.py:812] (4/8) Epoch 10, batch 4300, loss[loss=0.1836, simple_loss=0.2784, pruned_loss=0.04444, over 7290.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2709, pruned_loss=0.05003, over 1418228.50 frames.], batch size: 24, lr: 7.38e-04
2022-05-14 10:29:10,975 INFO [train.py:812] (4/8) Epoch 10, batch 4350, loss[loss=0.199, simple_loss=0.2779, pruned_loss=0.06003, over 4965.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2721, pruned_loss=0.0505, over 1408601.36 frames.], batch size: 52, lr: 7.37e-04
2022-05-14 10:30:10,254 INFO [train.py:812] (4/8) Epoch 10, batch 4400, loss[loss=0.2314, simple_loss=0.3034, pruned_loss=0.07966, over 7197.00 frames.], tot_loss[loss=0.1877, simple_loss=0.273, pruned_loss=0.05117, over 1410682.66 frames.], batch size: 22, lr: 7.37e-04
2022-05-14 10:31:10,031 INFO [train.py:812] (4/8) Epoch 10, batch 4450, loss[loss=0.2443, simple_loss=0.3142, pruned_loss=0.08721, over 5227.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2735, pruned_loss=0.05191, over 1396824.56 frames.], batch size: 52, lr: 7.37e-04
2022-05-14 10:32:09,139 INFO [train.py:812] (4/8) Epoch 10, batch 4500, loss[loss=0.1927, simple_loss=0.2827, pruned_loss=0.05131, over 7134.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2724, pruned_loss=0.05159, over 1393975.07 frames.], batch size: 20, lr: 7.36e-04
2022-05-14 10:33:08,618 INFO [train.py:812] (4/8) Epoch 10, batch 4550, loss[loss=0.1935, simple_loss=0.2799, pruned_loss=0.05351, over 7144.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2724, pruned_loss=0.05205, over 1374738.67 frames.], batch size: 26, lr: 7.36e-04
2022-05-14 10:34:22,339 INFO [train.py:812] (4/8) Epoch 11, batch 0, loss[loss=0.1983, simple_loss=0.2798, pruned_loss=0.05836, over 7420.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2798, pruned_loss=0.05836, over 7420.00 frames.], batch size: 20, lr: 7.08e-04
2022-05-14 10:35:21,216 INFO [train.py:812] (4/8) Epoch 11, batch 50, loss[loss=0.172, simple_loss=0.262, pruned_loss=0.04104, over 7420.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2729, pruned_loss=0.04994, over 322854.97 frames.], batch size: 20, lr: 7.08e-04
2022-05-14 10:36:19,851 INFO [train.py:812] (4/8) Epoch 11, batch 100, loss[loss=0.1566, simple_loss=0.2348, pruned_loss=0.03922, over 7280.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2709, pruned_loss=0.04909, over 567328.36 frames.], batch size: 18, lr: 7.08e-04
2022-05-14 10:37:28,467 INFO [train.py:812] (4/8) Epoch 11, batch 150, loss[loss=0.1918, simple_loss=0.2633, pruned_loss=0.06013, over 7188.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2736, pruned_loss=0.04991, over 760584.06 frames.], batch size: 16, lr: 7.07e-04
2022-05-14 10:38:36,328 INFO [train.py:812] (4/8) Epoch 11, batch 200, loss[loss=0.1531, simple_loss=0.2371, pruned_loss=0.03453, over 7389.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2722, pruned_loss=0.04964, over 907834.61 frames.], batch size: 18, lr: 7.07e-04
2022-05-14 10:39:34,531 INFO [train.py:812] (4/8) Epoch 11, batch 250, loss[loss=0.1931, simple_loss=0.2815, pruned_loss=0.05231, over 6429.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2707, pruned_loss=0.04876, over 1023487.97 frames.], batch size: 38, lr: 7.06e-04
2022-05-14 10:40:50,467 INFO [train.py:812] (4/8) Epoch 11, batch 300, loss[loss=0.2109, simple_loss=0.2833, pruned_loss=0.06929, over 4995.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2689, pruned_loss=0.04796, over 1114558.63 frames.], batch size: 53, lr: 7.06e-04
2022-05-14 10:41:47,793 INFO [train.py:812] (4/8) Epoch 11, batch 350, loss[loss=0.216, simple_loss=0.2945, pruned_loss=0.06879, over 6771.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2684, pruned_loss=0.04768, over 1187063.60 frames.], batch size: 31, lr: 7.06e-04
2022-05-14 10:43:03,925 INFO [train.py:812] (4/8) Epoch 11, batch 400, loss[loss=0.178, simple_loss=0.2737, pruned_loss=0.04114, over 7429.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2691, pruned_loss=0.0482, over 1240532.39 frames.], batch size: 20, lr: 7.05e-04
2022-05-14 10:44:13,173 INFO [train.py:812] (4/8) Epoch 11, batch 450, loss[loss=0.2054, simple_loss=0.2957, pruned_loss=0.05756, over 7230.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2679, pruned_loss=0.04795, over 1280448.46 frames.], batch size: 20, lr: 7.05e-04
2022-05-14 10:45:12,590 INFO [train.py:812] (4/8) Epoch 11, batch 500, loss[loss=0.181, simple_loss=0.2729, pruned_loss=0.04461, over 7320.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2667, pruned_loss=0.04721, over 1315082.22 frames.], batch size: 20, lr: 7.04e-04
2022-05-14 10:46:12,023 INFO [train.py:812] (4/8) Epoch 11, batch 550, loss[loss=0.1652, simple_loss=0.2518, pruned_loss=0.03931, over 7447.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2673, pruned_loss=0.04726, over 1340256.00 frames.], batch size: 19, lr: 7.04e-04
2022-05-14 10:47:11,314 INFO [train.py:812] (4/8) Epoch 11, batch 600, loss[loss=0.1596, simple_loss=0.2356, pruned_loss=0.04177, over 6998.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2671, pruned_loss=0.04721, over 1359435.82 frames.], batch size: 16, lr: 7.04e-04
2022-05-14 10:48:09,761 INFO [train.py:812] (4/8) Epoch 11, batch 650, loss[loss=0.138, simple_loss=0.2188, pruned_loss=0.02862, over 7137.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2667, pruned_loss=0.04716, over 1364748.46 frames.], batch size: 17, lr: 7.03e-04
2022-05-14 10:49:08,409 INFO [train.py:812] (4/8) Epoch 11, batch 700, loss[loss=0.1573, simple_loss=0.2419, pruned_loss=0.03633, over 6755.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2687, pruned_loss=0.0478, over 1374732.15 frames.], batch size: 15, lr: 7.03e-04
2022-05-14 10:50:07,693 INFO [train.py:812] (4/8) Epoch 11, batch 750, loss[loss=0.1758, simple_loss=0.2637, pruned_loss=0.04393, over 7150.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2681, pruned_loss=0.04799, over 1382012.62 frames.], batch size: 20, lr: 7.03e-04
2022-05-14 10:51:05,914 INFO [train.py:812] (4/8) Epoch 11, batch 800, loss[loss=0.1822, simple_loss=0.2712, pruned_loss=0.04662, over 7189.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2676, pruned_loss=0.04786, over 1393662.39 frames.], batch size: 26, lr: 7.02e-04
2022-05-14 10:52:03,630 INFO [train.py:812] (4/8) Epoch 11, batch 850, loss[loss=0.1857, simple_loss=0.2671, pruned_loss=0.0521, over 7324.00 frames.], tot_loss[loss=0.182, simple_loss=0.268, pruned_loss=0.04799, over 1398369.58 frames.], batch size: 20, lr: 7.02e-04
2022-05-14 10:53:01,757 INFO [train.py:812] (4/8) Epoch 11, batch 900, loss[loss=0.1764, simple_loss=0.2585, pruned_loss=0.04715, over 7418.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2678, pruned_loss=0.04825, over 1406957.99 frames.], batch size: 20, lr: 7.02e-04
2022-05-14 10:54:00,389 INFO [train.py:812] (4/8) Epoch 11, batch 950, loss[loss=0.1668, simple_loss=0.2458, pruned_loss=0.0439, over 7007.00 frames.], tot_loss[loss=0.182, simple_loss=0.2679, pruned_loss=0.04808, over 1409752.48 frames.], batch size: 16, lr: 7.01e-04
2022-05-14 10:54:58,953 INFO [train.py:812] (4/8) Epoch 11, batch 1000, loss[loss=0.1858, simple_loss=0.2819, pruned_loss=0.04487, over 7277.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2679, pruned_loss=0.04781, over 1413522.54 frames.], batch size: 25, lr: 7.01e-04
2022-05-14 10:55:58,046 INFO [train.py:812] (4/8) Epoch 11, batch 1050, loss[loss=0.1732, simple_loss=0.2586, pruned_loss=0.0439, over 7274.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2692, pruned_loss=0.04853, over 1408893.27 frames.], batch size: 19, lr: 7.00e-04
2022-05-14 10:56:57,230 INFO [train.py:812] (4/8) Epoch 11, batch 1100, loss[loss=0.1969, simple_loss=0.2713, pruned_loss=0.06125, over 7160.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2678, pruned_loss=0.04798, over 1413898.72 frames.], batch size: 18, lr: 7.00e-04
2022-05-14 10:57:56,856 INFO [train.py:812] (4/8) Epoch 11, batch 1150, loss[loss=0.209, simple_loss=0.2757, pruned_loss=0.07115, over 7067.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2669, pruned_loss=0.04743, over 1417853.18 frames.], batch size: 18, lr: 7.00e-04
2022-05-14 10:58:55,464 INFO [train.py:812] (4/8) Epoch 11, batch 1200, loss[loss=0.1764, simple_loss=0.2568, pruned_loss=0.04798, over 7212.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2649, pruned_loss=0.04679, over 1420461.92 frames.], batch size: 16, lr: 6.99e-04
2022-05-14 10:59:53,782 INFO [train.py:812] (4/8) Epoch 11, batch 1250, loss[loss=0.1733, simple_loss=0.2489, pruned_loss=0.04883, over 7138.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2659, pruned_loss=0.0476, over 1424410.17 frames.], batch size: 17, lr: 6.99e-04
2022-05-14 11:00:50,427 INFO [train.py:812] (4/8) Epoch 11, batch 1300, loss[loss=0.1956, simple_loss=0.2898, pruned_loss=0.05072, over 7307.00 frames.], tot_loss[loss=0.181, simple_loss=0.2664, pruned_loss=0.04781, over 1421551.33 frames.], batch size: 21, lr: 6.99e-04
2022-05-14 11:01:49,331 INFO [train.py:812] (4/8) Epoch 11, batch 1350, loss[loss=0.1777, simple_loss=0.2637, pruned_loss=0.04587, over 7322.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2661, pruned_loss=0.04745, over 1425315.61 frames.], batch size: 21, lr: 6.98e-04
2022-05-14 11:02:46,389 INFO [train.py:812] (4/8) Epoch 11, batch 1400, loss[loss=0.1484, simple_loss=0.2423, pruned_loss=0.0273, over 7153.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2662, pruned_loss=0.04738, over 1427686.52 frames.], batch size: 19, lr: 6.98e-04
2022-05-14 11:03:44,648 INFO [train.py:812] (4/8) Epoch 11, batch 1450, loss[loss=0.1855, simple_loss=0.2649, pruned_loss=0.05308, over 7267.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2666, pruned_loss=0.04734, over 1428020.44 frames.], batch size: 17, lr: 6.97e-04
2022-05-14 11:04:41,558 INFO [train.py:812] (4/8) Epoch 11, batch 1500, loss[loss=0.1677, simple_loss=0.2622, pruned_loss=0.03654, over 7035.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2671, pruned_loss=0.0476, over 1426403.36 frames.], batch size: 28, lr: 6.97e-04
2022-05-14 11:05:41,362 INFO [train.py:812] (4/8) Epoch 11, batch 1550, loss[loss=0.175, simple_loss=0.2615, pruned_loss=0.04421, over 7435.00 frames.], tot_loss[loss=0.181, simple_loss=0.267, pruned_loss=0.0475, over 1424732.86 frames.], batch size: 20, lr: 6.97e-04
2022-05-14 11:06:38,925 INFO [train.py:812] (4/8) Epoch 11, batch 1600, loss[loss=0.2143, simple_loss=0.2963, pruned_loss=0.0662, over 6740.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2671, pruned_loss=0.04762, over 1418989.59 frames.], batch size: 31, lr: 6.96e-04
2022-05-14 11:07:38,266 INFO [train.py:812] (4/8) Epoch 11, batch 1650, loss[loss=0.1751, simple_loss=0.2526, pruned_loss=0.04881, over 6789.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2668, pruned_loss=0.04737, over 1418580.16 frames.], batch size: 15, lr: 6.96e-04
2022-05-14 11:08:37,009 INFO [train.py:812] (4/8) Epoch 11, batch 1700, loss[loss=0.1951, simple_loss=0.2709, pruned_loss=0.05963, over 6782.00 frames.], tot_loss[loss=0.181, simple_loss=0.2674, pruned_loss=0.04728, over 1417886.62 frames.], batch size: 15, lr: 6.96e-04
2022-05-14 11:09:36,817 INFO [train.py:812] (4/8) Epoch 11, batch 1750, loss[loss=0.1718, simple_loss=0.2644, pruned_loss=0.03959, over 7126.00 frames.], tot_loss[loss=0.1807, simple_loss=0.267, pruned_loss=0.04718, over 1413774.59 frames.], batch size: 21, lr: 6.95e-04
2022-05-14 11:10:35,681 INFO [train.py:812] (4/8) Epoch 11, batch 1800, loss[loss=0.2055, simple_loss=0.2883, pruned_loss=0.06132, over 5128.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2676, pruned_loss=0.04707, over 1413418.75 frames.], batch size: 52, lr: 6.95e-04
2022-05-14 11:11:35,351 INFO [train.py:812] (4/8) Epoch 11, batch 1850, loss[loss=0.1807, simple_loss=0.2711, pruned_loss=0.04521, over 6404.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2675, pruned_loss=0.04702, over 1417403.35 frames.], batch size: 37, lr: 6.95e-04
2022-05-14 11:12:33,305 INFO [train.py:812] (4/8) Epoch 11, batch 1900, loss[loss=0.2385, simple_loss=0.3222, pruned_loss=0.07742, over 7317.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2673, pruned_loss=0.04693, over 1421985.67 frames.], batch size: 21, lr: 6.94e-04
2022-05-14 11:13:32,942 INFO [train.py:812] (4/8) Epoch 11, batch 1950, loss[loss=0.2177, simple_loss=0.296, pruned_loss=0.06964, over 7368.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2671, pruned_loss=0.04705, over 1420938.91 frames.], batch size: 19, lr: 6.94e-04
2022-05-14 11:14:32,025 INFO [train.py:812] (4/8) Epoch 11, batch 2000, loss[loss=0.1761, simple_loss=0.2638, pruned_loss=0.04422, over 7157.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2672, pruned_loss=0.04727, over 1422730.09 frames.], batch size: 18, lr: 6.93e-04
2022-05-14 11:15:30,890 INFO [train.py:812] (4/8) Epoch 11, batch 2050, loss[loss=0.1694, simple_loss=0.245, pruned_loss=0.04688, over 7306.00 frames.], tot_loss[loss=0.181, simple_loss=0.2674, pruned_loss=0.04725, over 1424969.33 frames.], batch size: 17, lr: 6.93e-04
2022-05-14 11:16:30,467 INFO [train.py:812] (4/8) Epoch 11, batch 2100, loss[loss=0.195, simple_loss=0.2786, pruned_loss=0.05575, over 7391.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2679, pruned_loss=0.04761, over 1425345.16 frames.], batch size: 23, lr: 6.93e-04
2022-05-14 11:17:37,595 INFO [train.py:812] (4/8) Epoch 11, batch 2150, loss[loss=0.1598, simple_loss=0.2409, pruned_loss=0.03937, over 7162.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2671, pruned_loss=0.04727, over 1425410.40 frames.], batch size: 18, lr: 6.92e-04
2022-05-14 11:18:36,034 INFO [train.py:812] (4/8) Epoch 11, batch 2200, loss[loss=0.1813, simple_loss=0.2721, pruned_loss=0.04524, over 7233.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2674, pruned_loss=0.04753, over 1423744.09 frames.], batch size: 20, lr: 6.92e-04
2022-05-14 11:19:35,024 INFO [train.py:812] (4/8) Epoch 11, batch 2250, loss[loss=0.167, simple_loss=0.2593, pruned_loss=0.03739, over 7350.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2678, pruned_loss=0.04737, over 1427035.28 frames.], batch size: 22, lr: 6.92e-04
2022-05-14 11:20:34,383 INFO [train.py:812] (4/8) Epoch 11, batch 2300, loss[loss=0.2016, simple_loss=0.2842, pruned_loss=0.05949, over 7162.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2672, pruned_loss=0.04727, over 1427042.03 frames.], batch size: 26, lr: 6.91e-04
2022-05-14 11:21:33,296 INFO [train.py:812] (4/8) Epoch 11, batch 2350, loss[loss=0.1766, simple_loss=0.2663, pruned_loss=0.04348, over 6790.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2658, pruned_loss=0.04656, over 1429645.96 frames.], batch size: 31, lr: 6.91e-04
2022-05-14 11:22:32,008 INFO [train.py:812] (4/8) Epoch 11, batch 2400, loss[loss=0.1897, simple_loss=0.276, pruned_loss=0.05165, over 7321.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2659, pruned_loss=0.0464, over 1423899.60 frames.], batch size: 21, lr: 6.91e-04
2022-05-14 11:23:31,123 INFO [train.py:812] (4/8) Epoch 11, batch 2450, loss[loss=0.1794, simple_loss=0.2722, pruned_loss=0.04327, over 7018.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2659, pruned_loss=0.04688, over 1424033.99 frames.], batch size: 16, lr: 6.90e-04
2022-05-14 11:24:30,214 INFO [train.py:812] (4/8) Epoch 11, batch 2500, loss[loss=0.1892, simple_loss=0.2689, pruned_loss=0.05473, over 7159.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2664, pruned_loss=0.04725, over 1422947.80 frames.], batch size: 19, lr: 6.90e-04
2022-05-14 11:25:29,317 INFO [train.py:812] (4/8) Epoch 11, batch 2550, loss[loss=0.208, simple_loss=0.2834, pruned_loss=0.0663, over 6768.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2658, pruned_loss=0.04654, over 1427008.02 frames.], batch size: 15, lr: 6.90e-04
2022-05-14 11:26:27,798 INFO [train.py:812] (4/8) Epoch 11, batch 2600, loss[loss=0.1979, simple_loss=0.2904, pruned_loss=0.0527, over 7367.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2666, pruned_loss=0.04695, over 1428314.52 frames.], batch size: 23, lr: 6.89e-04
2022-05-14 11:27:26,097 INFO [train.py:812] (4/8) Epoch 11, batch 2650, loss[loss=0.1602, simple_loss=0.2353, pruned_loss=0.04258, over 6992.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2678, pruned_loss=0.04728, over 1423677.40 frames.], batch size: 16, lr: 6.89e-04
2022-05-14 11:28:23,551 INFO [train.py:812] (4/8) Epoch 11, batch 2700, loss[loss=0.1805, simple_loss=0.2816, pruned_loss=0.03968, over 7417.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2686, pruned_loss=0.04788, over 1426578.47 frames.], batch size: 21, lr: 6.89e-04
2022-05-14 11:29:21,001 INFO [train.py:812] (4/8) Epoch 11, batch 2750, loss[loss=0.1776, simple_loss=0.2587, pruned_loss=0.04826, over 7275.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2677, pruned_loss=0.04795, over 1425877.50 frames.], batch size: 18, lr: 6.88e-04
2022-05-14 11:30:17,976 INFO [train.py:812] (4/8) Epoch 11, batch 2800, loss[loss=0.2098, simple_loss=0.2939, pruned_loss=0.06288, over 7161.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2675, pruned_loss=0.04776, over 1424845.81 frames.], batch size: 19, lr: 6.88e-04
2022-05-14 11:31:17,650 INFO [train.py:812] (4/8) Epoch 11, batch 2850, loss[loss=0.2032, simple_loss=0.2852, pruned_loss=0.06061, over 7313.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2677, pruned_loss=0.0477, over 1425083.79 frames.], batch size: 21, lr: 6.87e-04
2022-05-14 11:32:14,490 INFO [train.py:812] (4/8) Epoch 11, batch 2900, loss[loss=0.2114, simple_loss=0.2939, pruned_loss=0.0644, over 7189.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2675, pruned_loss=0.04755, over 1427103.25 frames.], batch size: 23, lr: 6.87e-04
2022-05-14 11:33:13,345 INFO [train.py:812] (4/8) Epoch 11, batch 2950, loss[loss=0.2047, simple_loss=0.298, pruned_loss=0.05573, over 7201.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2676, pruned_loss=0.04737, over 1424978.33 frames.], batch size: 22, lr: 6.87e-04
2022-05-14 11:34:12,259 INFO [train.py:812] (4/8) Epoch 11, batch 3000, loss[loss=0.1672, simple_loss=0.2538, pruned_loss=0.04033, over 7165.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2681, pruned_loss=0.04722, over 1424282.58 frames.], batch size: 18, lr: 6.86e-04
2022-05-14 11:34:12,260 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 11:34:19,822 INFO [train.py:841] (4/8) Epoch 11, validation: loss=0.1564, simple_loss=0.2581, pruned_loss=0.02737, over 698248.00 frames.
2022-05-14 11:35:18,267 INFO [train.py:812] (4/8) Epoch 11, batch 3050, loss[loss=0.1782, simple_loss=0.268, pruned_loss=0.04417, over 7223.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2671, pruned_loss=0.04703, over 1428239.41 frames.], batch size: 26, lr: 6.86e-04
2022-05-14 11:36:16,724 INFO [train.py:812] (4/8) Epoch 11, batch 3100, loss[loss=0.142, simple_loss=0.2283, pruned_loss=0.02787, over 7420.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2678, pruned_loss=0.04773, over 1426145.86 frames.], batch size: 18, lr: 6.86e-04
2022-05-14 11:37:16,186 INFO [train.py:812] (4/8) Epoch 11, batch 3150, loss[loss=0.1612, simple_loss=0.238, pruned_loss=0.04214, over 7266.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2662, pruned_loss=0.04708, over 1428697.72 frames.], batch size: 18, lr: 6.85e-04
2022-05-14 11:38:15,163 INFO [train.py:812] (4/8) Epoch 11, batch 3200, loss[loss=0.1484, simple_loss=0.2224, pruned_loss=0.03719, over 7170.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2649, pruned_loss=0.04674, over 1430480.66 frames.], batch size: 18, lr: 6.85e-04
2022-05-14 11:39:14,891 INFO [train.py:812] (4/8) Epoch 11, batch 3250, loss[loss=0.1681, simple_loss=0.2557, pruned_loss=0.04021, over 7059.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2659, pruned_loss=0.04728, over 1431175.85 frames.], batch size: 18, lr: 6.85e-04
2022-05-14 11:40:14,272 INFO [train.py:812] (4/8) Epoch 11, batch 3300, loss[loss=0.1808, simple_loss=0.2677, pruned_loss=0.04698, over 6497.00 frames.], tot_loss[loss=0.1816, simple_loss=0.267, pruned_loss=0.04807, over 1430049.70 frames.], batch size: 38, lr: 6.84e-04
2022-05-14 11:41:13,845 INFO [train.py:812] (4/8) Epoch 11, batch 3350, loss[loss=0.1885, simple_loss=0.289, pruned_loss=0.04406, over 7119.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2672, pruned_loss=0.04799, over 1424258.27 frames.], batch size: 21, lr: 6.84e-04
2022-05-14 11:42:12,406 INFO [train.py:812] (4/8) Epoch 11, batch 3400, loss[loss=0.1814, simple_loss=0.2665, pruned_loss=0.04815, over 6996.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2672, pruned_loss=0.04798, over 1420926.12 frames.], batch size: 16, lr: 6.84e-04
2022-05-14 11:43:11,478 INFO [train.py:812] (4/8) Epoch 11, batch 3450, loss[loss=0.2072, simple_loss=0.2965, pruned_loss=0.05894, over 7115.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2675, pruned_loss=0.04763, over 1423966.56 frames.], batch size: 21, lr: 6.83e-04
2022-05-14 11:44:10,169 INFO [train.py:812] (4/8) Epoch 11, batch 3500, loss[loss=0.1928, simple_loss=0.2639, pruned_loss=0.06082, over 7413.00 frames.], tot_loss[loss=0.1812, simple_loss=0.267, pruned_loss=0.04767, over 1425438.86 frames.], batch size: 18, lr: 6.83e-04
2022-05-14 11:45:10,020 INFO [train.py:812] (4/8) Epoch 11, batch 3550, loss[loss=0.1681, simple_loss=0.2652, pruned_loss=0.03556, over 6175.00 frames.], tot_loss[loss=0.1812, simple_loss=0.267, pruned_loss=0.04765, over 1423896.43 frames.], batch size: 37, lr: 6.83e-04
2022-05-14 11:46:08,751 INFO [train.py:812] (4/8) Epoch 11, batch 3600, loss[loss=0.2062, simple_loss=0.2793, pruned_loss=0.06653, over 6397.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2673, pruned_loss=0.04801, over 1419889.82 frames.], batch size: 38, lr: 6.82e-04
2022-05-14 11:47:07,764 INFO [train.py:812] (4/8) Epoch 11, batch 3650, loss[loss=0.1811, simple_loss=0.2743, pruned_loss=0.04395, over 7117.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2681, pruned_loss=0.04784, over 1422296.02 frames.], batch size: 21, lr: 6.82e-04
2022-05-14 11:48:06,835 INFO [train.py:812] (4/8) Epoch 11, batch 3700, loss[loss=0.202, simple_loss=0.2928, pruned_loss=0.05564, over 7123.00 frames.], tot_loss[loss=0.1814, simple_loss=0.268, pruned_loss=0.04743, over 1417976.98 frames.], batch size: 21, lr: 6.82e-04
2022-05-14 11:49:06,472 INFO [train.py:812] (4/8) Epoch 11, batch 3750, loss[loss=0.1684, simple_loss=0.2559, pruned_loss=0.04048, over 7431.00 frames.], tot_loss[loss=0.181, simple_loss=0.2678, pruned_loss=0.04716, over 1424355.31 frames.], batch size: 20, lr: 6.81e-04
2022-05-14 11:50:05,385 INFO [train.py:812] (4/8) Epoch 11, batch 3800, loss[loss=0.2023, simple_loss=0.2867, pruned_loss=0.0589, over 7289.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2676, pruned_loss=0.04706, over 1422960.34 frames.], batch size: 24, lr: 6.81e-04
2022-05-14 11:51:04,550 INFO [train.py:812] (4/8) Epoch 11, batch 3850, loss[loss=0.2448, simple_loss=0.3253, pruned_loss=0.08213, over 7203.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2669, pruned_loss=0.04676, over 1428101.34 frames.], batch size: 22, lr: 6.81e-04
2022-05-14 11:52:01,422 INFO [train.py:812] (4/8) Epoch 11, batch 3900, loss[loss=0.1897, simple_loss=0.2709, pruned_loss=0.0542, over 7384.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2665, pruned_loss=0.04683, over 1428486.61 frames.], batch size: 23, lr: 6.80e-04
2022-05-14 11:53:00,856 INFO [train.py:812] (4/8) Epoch 11, batch 3950, loss[loss=0.186, simple_loss=0.2725, pruned_loss=0.04976, over 7437.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2663, pruned_loss=0.04713, over 1427116.88 frames.], batch size: 20, lr: 6.80e-04
2022-05-14 11:53:59,471 INFO [train.py:812] (4/8) Epoch 11, batch 4000, loss[loss=0.1727, simple_loss=0.2665, pruned_loss=0.03948, over 7226.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2664, pruned_loss=0.0475, over 1418157.49 frames.], batch size: 21, lr: 6.80e-04
2022-05-14 11:54:58,917 INFO [train.py:812] (4/8) Epoch 11, batch 4050, loss[loss=0.1798, simple_loss=0.2667, pruned_loss=0.04645, over 7198.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2668, pruned_loss=0.04728, over 1417991.80 frames.], batch size: 22, lr: 6.79e-04
2022-05-14 11:55:57,974 INFO [train.py:812] (4/8) Epoch 11, batch 4100, loss[loss=0.1977, simple_loss=0.2894, pruned_loss=0.05298, over 7193.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2671, pruned_loss=0.0476, over 1418048.32 frames.], batch size: 22, lr: 6.79e-04
2022-05-14 11:56:56,029 INFO [train.py:812] (4/8) Epoch 11, batch 4150, loss[loss=0.2143, simple_loss=0.296, pruned_loss=0.06629, over 6802.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2683, pruned_loss=0.04816, over 1414882.55 frames.], batch size: 31, lr: 6.79e-04
2022-05-14 11:57:54,850 INFO [train.py:812] (4/8) Epoch 11, batch 4200, loss[loss=0.1944, simple_loss=0.2884, pruned_loss=0.05015, over 7008.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2683, pruned_loss=0.04767, over 1416052.81 frames.], batch size: 28, lr: 6.78e-04
2022-05-14 11:58:54,363 INFO [train.py:812] (4/8) Epoch 11, batch 4250, loss[loss=0.2315, simple_loss=0.3084, pruned_loss=0.07726, over 5223.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2683, pruned_loss=0.04765, over 1415676.77 frames.], batch size: 52, lr: 6.78e-04
2022-05-14 11:59:53,057 INFO [train.py:812] (4/8) Epoch 11, batch 4300, loss[loss=0.2156, simple_loss=0.31, pruned_loss=0.06056, over 5152.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2681, pruned_loss=0.04759, over 1412060.19 frames.], batch size: 54, lr: 6.78e-04
2022-05-14 12:00:52,213 INFO [train.py:812] (4/8) Epoch 11, batch 4350, loss[loss=0.1763, simple_loss=0.2696, pruned_loss=0.0415, over 7224.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2693, pruned_loss=0.04808, over 1409643.37 frames.], batch size: 20, lr: 6.77e-04
2022-05-14 12:01:50,107 INFO [train.py:812] (4/8) Epoch 11, batch 4400, loss[loss=0.1987, simple_loss=0.2845, pruned_loss=0.05651, over 7211.00 frames.], tot_loss[loss=0.184, simple_loss=0.2706, pruned_loss=0.04868, over 1415240.48 frames.], batch size: 22, lr: 6.77e-04
2022-05-14 12:02:49,063 INFO [train.py:812] (4/8) Epoch 11, batch 4450, loss[loss=0.1488, simple_loss=0.2324, pruned_loss=0.03253, over 7232.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2718, pruned_loss=0.04892, over 1417759.90 frames.], batch size: 20, lr: 6.77e-04
2022-05-14 12:03:48,063 INFO [train.py:812] (4/8) Epoch 11, batch 4500, loss[loss=0.2333, simple_loss=0.315, pruned_loss=0.07582, over 4890.00 frames.], tot_loss[loss=0.185, simple_loss=0.2718, pruned_loss=0.04907, over 1409255.25 frames.], batch size: 52, lr: 6.76e-04
2022-05-14 12:04:46,789 INFO [train.py:812] (4/8) Epoch 11, batch 4550, loss[loss=0.1919, simple_loss=0.2806, pruned_loss=0.05163, over 5192.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2746, pruned_loss=0.05195, over 1346333.44 frames.], batch size: 53, lr: 6.76e-04
2022-05-14 12:05:54,965 INFO [train.py:812] (4/8) Epoch 12, batch 0, loss[loss=0.1889, simple_loss=0.2846, pruned_loss=0.04666, over 7417.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2846, pruned_loss=0.04666, over 7417.00 frames.], batch size: 21, lr: 6.52e-04
2022-05-14 12:06:54,750 INFO [train.py:812] (4/8) Epoch 12, batch 50, loss[loss=0.1891, simple_loss=0.2776, pruned_loss=0.05029, over 5239.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2639, pruned_loss=0.04445, over 319163.02 frames.], batch size: 52, lr: 6.52e-04
2022-05-14 12:07:53,906 INFO [train.py:812] (4/8) Epoch 12, batch 100, loss[loss=0.1685, simple_loss=0.2599, pruned_loss=0.03855, over 6491.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2662, pruned_loss=0.04569, over 559018.96 frames.], batch size: 38, lr: 6.51e-04
2022-05-14 12:08:53,456 INFO [train.py:812] (4/8) Epoch 12, batch 150, loss[loss=0.1873, simple_loss=0.256, pruned_loss=0.05929, over 7276.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2678, pruned_loss=0.04666, over 748978.02 frames.], batch size: 17, lr: 6.51e-04
2022-05-14 12:09:52,491 INFO [train.py:812] (4/8) Epoch 12, batch 200, loss[loss=0.2113, simple_loss=0.2948, pruned_loss=0.06393, over 7204.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2685, pruned_loss=0.04741, over 896949.82 frames.], batch size: 22, lr: 6.51e-04
2022-05-14 12:10:51,853 INFO [train.py:812] (4/8) Epoch 12, batch 250, loss[loss=0.175, simple_loss=0.2685, pruned_loss=0.0408, over 6806.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2668, pruned_loss=0.04636, over 1014109.60 frames.], batch size: 31, lr: 6.50e-04
2022-05-14 12:11:51,036 INFO [train.py:812] (4/8) Epoch 12, batch 300, loss[loss=0.1837, simple_loss=0.2806, pruned_loss=0.04335, over 7209.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2674, pruned_loss=0.0464, over 1098657.86 frames.], batch size: 22, lr: 6.50e-04
2022-05-14 12:12:50,777 INFO [train.py:812] (4/8) Epoch 12, batch 350, loss[loss=0.1765, simple_loss=0.2719, pruned_loss=0.04056, over 7335.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2666, pruned_loss=0.04591, over 1165782.92 frames.], batch size: 22, lr: 6.50e-04
2022-05-14 12:13:50,252 INFO [train.py:812] (4/8) Epoch 12, batch 400, loss[loss=0.1888, simple_loss=0.2776, pruned_loss=0.05003, over 7332.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2664, pruned_loss=0.0459, over 1220738.93 frames.], batch size: 22, lr: 6.49e-04
2022-05-14 12:14:48,363 INFO [train.py:812] (4/8) Epoch 12, batch 450, loss[loss=0.1686, simple_loss=0.2486, pruned_loss=0.04432, over 7157.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2656, pruned_loss=0.0453, over 1269032.45 frames.], batch size: 19, lr: 6.49e-04
2022-05-14 12:15:47,351 INFO [train.py:812] (4/8) Epoch 12, batch 500, loss[loss=0.2371, simple_loss=0.312, pruned_loss=0.08113, over 7376.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2656, pruned_loss=0.04551, over 1303321.18 frames.], batch size: 23, lr: 6.49e-04
2022-05-14 12:16:45,612 INFO [train.py:812] (4/8) Epoch 12, batch 550, loss[loss=0.1811, simple_loss=0.2709, pruned_loss=0.04568, over 7408.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2649, pruned_loss=0.04547, over 1329923.59 frames.], batch size: 21, lr: 6.48e-04
2022-05-14 12:17:43,510 INFO [train.py:812] (4/8) Epoch 12, batch 600, loss[loss=0.1754, simple_loss=0.2715, pruned_loss=0.03968, over 7329.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2638, pruned_loss=0.04474, over 1350418.18 frames.], batch size: 22, lr: 6.48e-04
2022-05-14 12:18:41,734 INFO [train.py:812] (4/8) Epoch 12, batch 650, loss[loss=0.176, simple_loss=0.2712, pruned_loss=0.04039, over 7387.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2623, pruned_loss=0.04422, over 1371489.47 frames.], batch size: 23, lr: 6.48e-04
2022-05-14 12:19:49,857 INFO [train.py:812] (4/8) Epoch 12, batch 700, loss[loss=0.1857, simple_loss=0.2704, pruned_loss=0.05049, over 7294.00 frames.], tot_loss[loss=0.176, simple_loss=0.2627, pruned_loss=0.04463, over 1382417.97 frames.], batch size: 24, lr: 6.47e-04
2022-05-14 12:20:48,659 INFO [train.py:812] (4/8) Epoch 12, batch 750, loss[loss=0.1471, simple_loss=0.2378, pruned_loss=0.02818, over 7330.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2635, pruned_loss=0.04478, over 1388049.89 frames.], batch size: 20, lr: 6.47e-04
2022-05-14 12:21:47,960 INFO [train.py:812] (4/8) Epoch 12, batch 800, loss[loss=0.1807, simple_loss=0.2631, pruned_loss=0.04917, over 7411.00 frames.], tot_loss[loss=0.1771, simple_loss=0.264, pruned_loss=0.04504, over 1400817.23 frames.], batch size: 18, lr: 6.47e-04
2022-05-14 12:22:46,123 INFO [train.py:812] (4/8) Epoch 12, batch 850, loss[loss=0.1925, simple_loss=0.2911, pruned_loss=0.04697, over 6838.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2653, pruned_loss=0.04565, over 1404852.80 frames.], batch size: 31, lr: 6.46e-04
2022-05-14 12:23:43,973 INFO [train.py:812] (4/8) Epoch 12, batch 900, loss[loss=0.1584, simple_loss=0.2478, pruned_loss=0.03449, over 7331.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2649, pruned_loss=0.04534, over 1408352.71 frames.], batch size: 22, lr: 6.46e-04
2022-05-14 12:24:43,692 INFO [train.py:812] (4/8) Epoch 12, batch 950, loss[loss=0.1775, simple_loss=0.261, pruned_loss=0.04704, over 7427.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2642, pruned_loss=0.04514, over 1413548.42 frames.], batch size: 20, lr: 6.46e-04
2022-05-14 12:25:42,167 INFO [train.py:812] (4/8) Epoch 12, batch 1000, loss[loss=0.1926, simple_loss=0.2785, pruned_loss=0.05333, over 7166.00 frames.], tot_loss[loss=0.178, simple_loss=0.2651, pruned_loss=0.04545, over 1416233.86 frames.], batch size: 19, lr: 6.46e-04
2022-05-14 12:26:41,693 INFO [train.py:812] (4/8) Epoch 12, batch 1050, loss[loss=0.1431, simple_loss=0.2137, pruned_loss=0.03624, over 6980.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2655, pruned_loss=0.04579, over 1415412.14 frames.], batch size: 16, lr: 6.45e-04
2022-05-14 12:27:40,719 INFO [train.py:812] (4/8) Epoch 12, batch 1100, loss[loss=0.1834, simple_loss=0.274, pruned_loss=0.04644, over 7163.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2658, pruned_loss=0.04551, over 1418221.13 frames.], batch size: 19, lr: 6.45e-04
2022-05-14 12:28:40,251 INFO [train.py:812] (4/8) Epoch 12, batch 1150, loss[loss=0.1879, simple_loss=0.2779, pruned_loss=0.04896, over 4715.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2653, pruned_loss=0.0457, over 1421022.75 frames.], batch size: 54, lr: 6.45e-04
2022-05-14 12:29:38,123 INFO [train.py:812] (4/8) Epoch 12, batch 1200, loss[loss=0.1799, simple_loss=0.2647, pruned_loss=0.0476, over 7113.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2645, pruned_loss=0.04526, over 1423682.19 frames.], batch size: 21, lr: 6.44e-04
2022-05-14 12:30:37,011 INFO [train.py:812] (4/8) Epoch 12, batch 1250, loss[loss=0.17, simple_loss=0.2436, pruned_loss=0.04821, over 6995.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2636, pruned_loss=0.04478, over 1424990.26 frames.], batch size: 16, lr: 6.44e-04
2022-05-14 12:31:36,639 INFO [train.py:812] (4/8) Epoch 12, batch 1300, loss[loss=0.2022, simple_loss=0.2834, pruned_loss=0.06046, over 7319.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2638, pruned_loss=0.04472, over 1427206.23 frames.], batch size: 20, lr: 6.44e-04
2022-05-14 12:32:34,815 INFO [train.py:812] (4/8) Epoch 12, batch 1350, loss[loss=0.1836, simple_loss=0.2763, pruned_loss=0.04545, over 7317.00 frames.], tot_loss[loss=0.1771, simple_loss=0.264, pruned_loss=0.04503, over 1424826.01 frames.], batch size: 21, lr: 6.43e-04
2022-05-14 12:33:34,082 INFO [train.py:812] (4/8) Epoch 12, batch 1400, loss[loss=0.1942, simple_loss=0.2764, pruned_loss=0.05604, over 7319.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2642, pruned_loss=0.04516, over 1421821.64 frames.], batch size: 21, lr: 6.43e-04
2022-05-14 12:34:33,347 INFO [train.py:812] (4/8) Epoch 12, batch 1450, loss[loss=0.158, simple_loss=0.2434, pruned_loss=0.03631, over 7056.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2643, pruned_loss=0.04552, over 1421594.07 frames.], batch size: 18, lr: 6.43e-04
2022-05-14 12:35:32,025 INFO [train.py:812] (4/8) Epoch 12, batch 1500, loss[loss=0.1996, simple_loss=0.2839, pruned_loss=0.0577, over 7205.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2642, pruned_loss=0.04549, over 1425448.95 frames.], batch size: 23, lr: 6.42e-04
2022-05-14 12:36:36,805 INFO [train.py:812] (4/8) Epoch 12, batch 1550, loss[loss=0.1944, simple_loss=0.2862, pruned_loss=0.05128, over 7231.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2642, pruned_loss=0.0458, over 1424895.51 frames.], batch size: 20, lr: 6.42e-04
2022-05-14 12:37:35,857 INFO [train.py:812] (4/8) Epoch 12, batch 1600, loss[loss=0.1784, simple_loss=0.2644, pruned_loss=0.04617, over 7357.00 frames.], tot_loss[loss=0.178, simple_loss=0.2647, pruned_loss=0.04568, over 1426090.05 frames.], batch size: 19, lr: 6.42e-04
2022-05-14 12:38:44,922 INFO [train.py:812] (4/8) Epoch 12, batch 1650, loss[loss=0.1825, simple_loss=0.2644, pruned_loss=0.05027, over 7375.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2648, pruned_loss=0.04577, over 1426911.83 frames.], batch size: 23, lr: 6.42e-04
2022-05-14 12:39:52,045 INFO [train.py:812] (4/8) Epoch 12, batch 1700, loss[loss=0.1919, simple_loss=0.2775, pruned_loss=0.05313, over 7228.00 frames.], tot_loss[loss=0.1783, simple_loss=0.265, pruned_loss=0.0458, over 1427678.06 frames.], batch size: 21, lr: 6.41e-04
2022-05-14 12:40:51,348 INFO [train.py:812] (4/8) Epoch 12, batch 1750, loss[loss=0.1825, simple_loss=0.272, pruned_loss=0.04649, over 7170.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2645, pruned_loss=0.04559, over 1428376.86 frames.], batch size: 26, lr: 6.41e-04
2022-05-14 12:41:58,739 INFO [train.py:812] (4/8) Epoch 12, batch 1800, loss[loss=0.1515, simple_loss=0.2331, pruned_loss=0.03496, over 6974.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2634, pruned_loss=0.04508, over 1427747.72 frames.], batch size: 16, lr: 6.41e-04
2022-05-14 12:43:07,992 INFO [train.py:812] (4/8) Epoch 12, batch 1850, loss[loss=0.174, simple_loss=0.2642, pruned_loss=0.04193, over 7139.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2632, pruned_loss=0.04519, over 1426454.59 frames.], batch size: 26, lr: 6.40e-04
2022-05-14 12:44:16,797 INFO [train.py:812] (4/8) Epoch 12, batch 1900, loss[loss=0.1727, simple_loss=0.2572, pruned_loss=0.04417, over 7429.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2632, pruned_loss=0.04523, over 1428739.53 frames.], batch size: 20, lr: 6.40e-04
2022-05-14 12:45:34,902 INFO [train.py:812] (4/8) Epoch 12, batch 1950, loss[loss=0.1477, simple_loss=0.2316, pruned_loss=0.03193, over 7019.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2629, pruned_loss=0.04503, over 1427584.22 frames.], batch size: 16, lr: 6.40e-04
2022-05-14 12:46:34,656 INFO [train.py:812] (4/8) Epoch 12, batch 2000, loss[loss=0.1593, simple_loss=0.2561, pruned_loss=0.03121, over 6493.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2639, pruned_loss=0.04526, over 1426861.00 frames.], batch size: 38, lr: 6.39e-04
2022-05-14 12:47:34,771 INFO [train.py:812] (4/8) Epoch 12, batch 2050, loss[loss=0.1792, simple_loss=0.2739, pruned_loss=0.0423, over 7385.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2637, pruned_loss=0.04512, over 1425078.73 frames.], batch size: 23, lr: 6.39e-04
2022-05-14 12:48:34,244 INFO [train.py:812] (4/8) Epoch 12, batch 2100, loss[loss=0.2014, simple_loss=0.2936, pruned_loss=0.05462, over 6743.00 frames.], tot_loss[loss=0.177, simple_loss=0.2638, pruned_loss=0.04512, over 1428585.96 frames.], batch size: 31, lr: 6.39e-04
2022-05-14 12:49:34,268 INFO [train.py:812] (4/8) Epoch 12, batch 2150, loss[loss=0.178, simple_loss=0.2572, pruned_loss=0.04939, over 6826.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2637, pruned_loss=0.04505, over 1423244.58 frames.], batch size: 15, lr: 6.38e-04
2022-05-14 12:50:33,511 INFO [train.py:812] (4/8) Epoch 12, batch 2200, loss[loss=0.1858, simple_loss=0.2646, pruned_loss=0.05346, over 7421.00 frames.], tot_loss[loss=0.1759, simple_loss=0.263, pruned_loss=0.04446, over 1427366.39 frames.], batch size: 20, lr: 6.38e-04
2022-05-14 12:51:31,623 INFO [train.py:812] (4/8) Epoch 12, batch 2250, loss[loss=0.1763, simple_loss=0.2676, pruned_loss=0.04253, over 7135.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2627, pruned_loss=0.04443, over 1425691.72 frames.], batch size: 17, lr: 6.38e-04
2022-05-14 12:52:29,471 INFO [train.py:812] (4/8) Epoch 12, batch 2300, loss[loss=0.1638, simple_loss=0.2468, pruned_loss=0.04038, over 7359.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2636, pruned_loss=0.04461, over 1424979.10 frames.], batch size: 19, lr: 6.38e-04
2022-05-14 12:53:28,556 INFO [train.py:812] (4/8) Epoch 12, batch 2350, loss[loss=0.2161, simple_loss=0.3088, pruned_loss=0.06168, over 7297.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2635, pruned_loss=0.04485, over 1426907.56 frames.], batch size: 24, lr: 6.37e-04
2022-05-14 12:54:27,655 INFO [train.py:812] (4/8) Epoch 12, batch 2400, loss[loss=0.1912, simple_loss=0.2708, pruned_loss=0.05582, over 7126.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2636, pruned_loss=0.0449, over 1428296.22 frames.], batch size: 21, lr: 6.37e-04
2022-05-14 12:55:26,369 INFO [train.py:812] (4/8) Epoch 12, batch 2450, loss[loss=0.1966, simple_loss=0.2866, pruned_loss=0.05334, over 7240.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2643, pruned_loss=0.04547, over 1426317.57 frames.], batch size: 20, lr: 6.37e-04
2022-05-14 12:56:25,367 INFO [train.py:812] (4/8) Epoch 12, batch 2500, loss[loss=0.1742, simple_loss=0.2552, pruned_loss=0.04666, over 7072.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2638, pruned_loss=0.04535, over 1424865.08 frames.], batch size: 18, lr: 6.36e-04
2022-05-14 12:57:24,980 INFO [train.py:812] (4/8) Epoch 12, batch 2550, loss[loss=0.162, simple_loss=0.243, pruned_loss=0.04054, over 7279.00 frames.], tot_loss[loss=0.1785, simple_loss=0.265, pruned_loss=0.04601, over 1427432.51 frames.], batch size: 17, lr: 6.36e-04
2022-05-14 12:58:23,568 INFO [train.py:812] (4/8) Epoch 12, batch 2600, loss[loss=0.1875, simple_loss=0.2809, pruned_loss=0.04705, over 7283.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2645, pruned_loss=0.04595, over 1421740.27 frames.], batch size: 24, lr: 6.36e-04
2022-05-14 12:59:22,475 INFO [train.py:812] (4/8) Epoch 12, batch 2650, loss[loss=0.1656, simple_loss=0.2513, pruned_loss=0.0399, over 7262.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2653, pruned_loss=0.04626, over 1418257.65 frames.], batch size: 19, lr: 6.36e-04
2022-05-14 13:00:21,652 INFO [train.py:812] (4/8) Epoch 12, batch 2700, loss[loss=0.1821, simple_loss=0.2697, pruned_loss=0.04721, over 7294.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2657, pruned_loss=0.04625, over 1422625.13 frames.], batch size: 25, lr: 6.35e-04
2022-05-14 13:01:21,318 INFO [train.py:812] (4/8) Epoch 12, batch 2750, loss[loss=0.1816, simple_loss=0.2682, pruned_loss=0.04752, over 7446.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2657, pruned_loss=0.04557, over 1425636.20 frames.], batch size: 20, lr: 6.35e-04
2022-05-14 13:02:20,433 INFO [train.py:812] (4/8) Epoch 12, batch 2800, loss[loss=0.2057, simple_loss=0.3048, pruned_loss=0.05332, over 7110.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2659, pruned_loss=0.04578, over 1426642.61 frames.], batch size: 21, lr: 6.35e-04
2022-05-14 13:03:19,815 INFO [train.py:812] (4/8) Epoch 12, batch 2850, loss[loss=0.1581, simple_loss=0.2449, pruned_loss=0.03563, over 7319.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2651, pruned_loss=0.04558, over 1429007.71 frames.], batch size: 21, lr: 6.34e-04
2022-05-14 13:04:18,947 INFO [train.py:812] (4/8) Epoch 12, batch 2900, loss[loss=0.1859, simple_loss=0.2664, pruned_loss=0.05267, over 7313.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2661, pruned_loss=0.04616, over 1425018.26 frames.], batch size: 24, lr: 6.34e-04
2022-05-14 13:05:18,605 INFO [train.py:812] (4/8) Epoch 12, batch 2950, loss[loss=0.2053, simple_loss=0.3003, pruned_loss=0.05516, over 7235.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2657, pruned_loss=0.04625, over 1420917.40 frames.], batch size: 21, lr: 6.34e-04
2022-05-14 13:06:17,602 INFO [train.py:812] (4/8) Epoch 12, batch 3000, loss[loss=0.1768, simple_loss=0.2649, pruned_loss=0.04437, over 7311.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2653, pruned_loss=0.04622, over 1421413.49 frames.], batch size: 25, lr: 6.33e-04
2022-05-14 13:06:17,603 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 13:06:26,032 INFO [train.py:841] (4/8) Epoch 12, validation: loss=0.1553, simple_loss=0.2571, pruned_loss=0.02678, over 698248.00 frames.
2022-05-14 13:07:25,174 INFO [train.py:812] (4/8) Epoch 12, batch 3050, loss[loss=0.1795, simple_loss=0.2686, pruned_loss=0.04516, over 7364.00 frames.], tot_loss[loss=0.1796, simple_loss=0.266, pruned_loss=0.04662, over 1420018.72 frames.], batch size: 23, lr: 6.33e-04
2022-05-14 13:08:24,605 INFO [train.py:812] (4/8) Epoch 12, batch 3100, loss[loss=0.1531, simple_loss=0.2492, pruned_loss=0.02851, over 7324.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2643, pruned_loss=0.04563, over 1421483.19 frames.], batch size: 20, lr: 6.33e-04
2022-05-14 13:09:23,905 INFO [train.py:812] (4/8) Epoch 12, batch 3150, loss[loss=0.1946, simple_loss=0.2927, pruned_loss=0.04824, over 7379.00 frames.], tot_loss[loss=0.1784, simple_loss=0.265, pruned_loss=0.04591, over 1424072.86 frames.], batch size: 23, lr: 6.33e-04
2022-05-14 13:10:22,793 INFO [train.py:812] (4/8) Epoch 12, batch 3200, loss[loss=0.1935, simple_loss=0.2874, pruned_loss=0.0498, over 7112.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2651, pruned_loss=0.04568, over 1424276.30 frames.], batch size: 21, lr: 6.32e-04
2022-05-14 13:11:22,020 INFO [train.py:812] (4/8) Epoch 12, batch 3250, loss[loss=0.1675, simple_loss=0.2545, pruned_loss=0.04026, over 7420.00 frames.], tot_loss[loss=0.179, simple_loss=0.2656, pruned_loss=0.04623, over 1425319.81 frames.], batch size: 21, lr: 6.32e-04
2022-05-14 13:12:21,126 INFO [train.py:812] (4/8) Epoch 12, batch 3300, loss[loss=0.1422, simple_loss=0.2162, pruned_loss=0.03405, over 6996.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2659, pruned_loss=0.04623, over 1426148.92 frames.], batch size: 16, lr: 6.32e-04
2022-05-14 13:13:18,549 INFO [train.py:812] (4/8) Epoch 12, batch 3350, loss[loss=0.1446, simple_loss=0.2234, pruned_loss=0.03292, over 7282.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2651, pruned_loss=0.04602, over 1426690.60 frames.], batch size: 18, lr: 6.31e-04
2022-05-14 13:14:17,034 INFO [train.py:812] (4/8) Epoch 12, batch 3400, loss[loss=0.1981, simple_loss=0.2869, pruned_loss=0.05468, over 6415.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2649, pruned_loss=0.04574, over 1421294.19 frames.], batch size: 37, lr: 6.31e-04
2022-05-14 13:15:16,597 INFO [train.py:812] (4/8) Epoch 12, batch 3450, loss[loss=0.182, simple_loss=0.2781, pruned_loss=0.043, over 7121.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2643, pruned_loss=0.04527, over 1419245.44 frames.], batch size: 21, lr: 6.31e-04
2022-05-14 13:16:15,029 INFO [train.py:812] (4/8) Epoch 12, batch 3500, loss[loss=0.1909, simple_loss=0.2849, pruned_loss=0.04842, over 7307.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2656, pruned_loss=0.0457, over 1424998.93 frames.], batch size: 21, lr: 6.31e-04
2022-05-14 13:17:13,776 INFO [train.py:812] (4/8) Epoch 12, batch 3550, loss[loss=0.1648, simple_loss=0.2355, pruned_loss=0.0471, over 6999.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2652, pruned_loss=0.04555, over 1423787.06 frames.], batch size: 16, lr: 6.30e-04
2022-05-14 13:18:12,627 INFO [train.py:812] (4/8) Epoch 12, batch 3600, loss[loss=0.2067, simple_loss=0.2962, pruned_loss=0.05858, over 7244.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2655, pruned_loss=0.04501, over 1425518.85 frames.], batch size: 20, lr: 6.30e-04
2022-05-14 13:19:11,477 INFO [train.py:812] (4/8) Epoch 12, batch 3650, loss[loss=0.1861, simple_loss=0.2832, pruned_loss=0.04451, over 7428.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2653, pruned_loss=0.04499, over 1424843.63 frames.], batch size: 20, lr: 6.30e-04
2022-05-14 13:20:08,354 INFO [train.py:812] (4/8) Epoch 12, batch 3700, loss[loss=0.1594, simple_loss=0.2557, pruned_loss=0.03161, over 6744.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2645, pruned_loss=0.04426, over 1421558.77 frames.], batch size: 31, lr: 6.29e-04
2022-05-14 13:21:06,288 INFO [train.py:812] (4/8) Epoch 12, batch 3750, loss[loss=0.1831, simple_loss=0.2708, pruned_loss=0.04767, over 7371.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2639, pruned_loss=0.04439, over 1425324.46 frames.], batch size: 23, lr: 6.29e-04
2022-05-14 13:22:05,724 INFO [train.py:812] (4/8) Epoch 12, batch 3800, loss[loss=0.1897, simple_loss=0.2774, pruned_loss=0.05098, over 7158.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2633, pruned_loss=0.04403, over 1428420.28 frames.], batch size: 26, lr: 6.29e-04
2022-05-14 13:23:04,544 INFO [train.py:812] (4/8) Epoch 12, batch 3850, loss[loss=0.1793, simple_loss=0.2711, pruned_loss=0.04371, over 7118.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2632, pruned_loss=0.04405, over 1429050.57 frames.], batch size: 21, lr: 6.29e-04
2022-05-14 13:24:03,544 INFO [train.py:812] (4/8) Epoch 12, batch 3900, loss[loss=0.1801, simple_loss=0.2763, pruned_loss=0.04193, over 7426.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2633, pruned_loss=0.04396, over 1429890.72 frames.], batch size: 20, lr: 6.28e-04
2022-05-14 13:25:02,805 INFO [train.py:812] (4/8) Epoch 12, batch 3950, loss[loss=0.2062, simple_loss=0.2987, pruned_loss=0.05681, over 7243.00 frames.], tot_loss[loss=0.1758, simple_loss=0.263, pruned_loss=0.04427, over 1431257.82 frames.], batch size: 20, lr: 6.28e-04
2022-05-14 13:26:01,751 INFO [train.py:812] (4/8) Epoch 12, batch 4000, loss[loss=0.1791, simple_loss=0.274, pruned_loss=0.0421, over 7419.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2638, pruned_loss=0.04448, over 1426872.89 frames.], batch size: 21, lr: 6.28e-04
2022-05-14 13:27:01,239 INFO [train.py:812] (4/8) Epoch 12, batch 4050, loss[loss=0.1939, simple_loss=0.2944, pruned_loss=0.04665, over 7427.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2632, pruned_loss=0.04447, over 1425252.87 frames.], batch size: 20, lr: 6.27e-04
2022-05-14 13:28:00,398 INFO [train.py:812] (4/8) Epoch 12, batch 4100, loss[loss=0.1556, simple_loss=0.2415, pruned_loss=0.0348, over 7334.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2623, pruned_loss=0.044, over 1422177.86 frames.], batch size: 20, lr: 6.27e-04
2022-05-14 13:28:59,932 INFO [train.py:812] (4/8) Epoch 12, batch 4150, loss[loss=0.1745, simple_loss=0.2609, pruned_loss=0.04405, over 7232.00 frames.], tot_loss[loss=0.1758, simple_loss=0.263, pruned_loss=0.04431, over 1422723.50 frames.], batch size: 20, lr: 6.27e-04
2022-05-14 13:29:59,296 INFO [train.py:812] (4/8) Epoch 12, batch 4200, loss[loss=0.1745, simple_loss=0.2688, pruned_loss=0.04014, over 7342.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2642, pruned_loss=0.04441, over 1421994.18 frames.], batch size: 22, lr: 6.27e-04
2022-05-14 13:30:59,189 INFO [train.py:812] (4/8) Epoch 12, batch 4250, loss[loss=0.1735, simple_loss=0.2505, pruned_loss=0.0482, over 7423.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2626, pruned_loss=0.04429, over 1426008.18 frames.], batch size: 18, lr: 6.26e-04
2022-05-14 13:31:58,494 INFO [train.py:812] (4/8) Epoch 12, batch 4300, loss[loss=0.1967, simple_loss=0.2783, pruned_loss=0.0576, over 7230.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2624, pruned_loss=0.0443, over 1419500.50 frames.], batch size: 20, lr: 6.26e-04
2022-05-14 13:32:57,470 INFO [train.py:812] (4/8) Epoch 12, batch 4350, loss[loss=0.215, simple_loss=0.3024, pruned_loss=0.06381, over 7208.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2616, pruned_loss=0.04438, over 1421210.39 frames.], batch size: 22, lr: 6.26e-04
2022-05-14 13:33:56,604 INFO [train.py:812] (4/8) Epoch 12, batch 4400, loss[loss=0.1832, simple_loss=0.2738, pruned_loss=0.04632, over 7315.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2621, pruned_loss=0.04489, over 1420068.56 frames.], batch size: 21, lr: 6.25e-04
2022-05-14 13:34:56,720 INFO [train.py:812] (4/8) Epoch 12, batch 4450, loss[loss=0.1935, simple_loss=0.2783, pruned_loss=0.0544, over 6428.00 frames.], tot_loss[loss=0.176, simple_loss=0.2614, pruned_loss=0.04528, over 1408360.40 frames.], batch size: 38, lr: 6.25e-04
2022-05-14 13:35:55,753 INFO [train.py:812] (4/8) Epoch 12, batch 4500, loss[loss=0.1823, simple_loss=0.2613, pruned_loss=0.05164, over 6391.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2618, pruned_loss=0.04597, over 1391397.22 frames.], batch size: 37, lr: 6.25e-04
2022-05-14 13:36:54,580 INFO [train.py:812] (4/8) Epoch 12, batch 4550, loss[loss=0.2169, simple_loss=0.2991, pruned_loss=0.06739, over 4947.00 frames.], tot_loss[loss=0.18, simple_loss=0.2642, pruned_loss=0.04789, over 1350803.42 frames.], batch size: 55, lr: 6.25e-04
2022-05-14 13:38:08,555 INFO [train.py:812] (4/8) Epoch 13, batch 0, loss[loss=0.1628, simple_loss=0.2498, pruned_loss=0.03794, over 7139.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2498, pruned_loss=0.03794, over 7139.00 frames.], batch size: 20, lr: 6.03e-04
2022-05-14 13:39:08,085 INFO [train.py:812] (4/8) Epoch 13, batch 50, loss[loss=0.1622, simple_loss=0.261, pruned_loss=0.03171, over 7233.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2626, pruned_loss=0.04422, over 318612.94 frames.], batch size: 20, lr: 6.03e-04
2022-05-14 13:40:06,199 INFO [train.py:812] (4/8) Epoch 13, batch 100, loss[loss=0.1964, simple_loss=0.2771, pruned_loss=0.05781, over 7203.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2658, pruned_loss=0.04528, over 565214.66 frames.], batch size: 23, lr: 6.03e-04
2022-05-14 13:41:05,016 INFO [train.py:812] (4/8) Epoch 13, batch 150, loss[loss=0.1851, simple_loss=0.2778, pruned_loss=0.04622, over 7145.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2669, pruned_loss=0.04481, over 753959.76 frames.], batch size: 20, lr: 6.03e-04
2022-05-14 13:42:04,240 INFO [train.py:812] (4/8) Epoch 13, batch 200, loss[loss=0.1892, simple_loss=0.2732, pruned_loss=0.0526, over 7160.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2657, pruned_loss=0.04494, over 900288.98 frames.], batch size: 20, lr: 6.02e-04
2022-05-14 13:43:03,739 INFO [train.py:812] (4/8) Epoch 13, batch 250, loss[loss=0.1764, simple_loss=0.253, pruned_loss=0.04986, over 6770.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2652, pruned_loss=0.0451, over 1013087.43 frames.], batch size: 15, lr: 6.02e-04
2022-05-14 13:44:02,528 INFO [train.py:812] (4/8) Epoch 13, batch 300, loss[loss=0.1899, simple_loss=0.2798, pruned_loss=0.05, over 7139.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2659, pruned_loss=0.04565, over 1102883.79 frames.], batch size: 20, lr: 6.02e-04
2022-05-14 13:45:01,884 INFO [train.py:812] (4/8) Epoch 13, batch 350, loss[loss=0.1866, simple_loss=0.2736, pruned_loss=0.0498, over 7059.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2646, pruned_loss=0.045, over 1175348.77 frames.], batch size: 28, lr: 6.01e-04
2022-05-14 13:46:00,659 INFO [train.py:812] (4/8) Epoch 13, batch 400, loss[loss=0.1716, simple_loss=0.2612, pruned_loss=0.04097, over 7368.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2641, pruned_loss=0.04476, over 1232871.02 frames.], batch size: 19, lr: 6.01e-04
2022-05-14 13:46:57,906 INFO [train.py:812] (4/8) Epoch 13, batch 450, loss[loss=0.1783, simple_loss=0.2667, pruned_loss=0.04499, over 7315.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2636, pruned_loss=0.04481, over 1277090.39 frames.], batch size: 21, lr: 6.01e-04
2022-05-14 13:47:55,550 INFO [train.py:812] (4/8) Epoch 13, batch 500, loss[loss=0.1862, simple_loss=0.285, pruned_loss=0.04371, over 6293.00 frames.], tot_loss[loss=0.1752, simple_loss=0.262, pruned_loss=0.04424, over 1310770.57 frames.], batch size: 37, lr: 6.01e-04
2022-05-14 13:48:55,160 INFO [train.py:812] (4/8) Epoch 13, batch 550, loss[loss=0.1837, simple_loss=0.2734, pruned_loss=0.04705, over 7362.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2621, pruned_loss=0.04442, over 1333350.72 frames.], batch size: 23, lr: 6.00e-04
2022-05-14 13:49:53,965 INFO [train.py:812] (4/8) Epoch 13, batch 600, loss[loss=0.1547, simple_loss=0.239, pruned_loss=0.03517, over 7235.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2618, pruned_loss=0.04436, over 1347309.17 frames.], batch size: 16, lr: 6.00e-04
2022-05-14 13:50:53,010 INFO [train.py:812] (4/8) Epoch 13, batch 650, loss[loss=0.1627, simple_loss=0.2487, pruned_loss=0.0383, over 7271.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2615, pruned_loss=0.04374, over 1366134.50 frames.], batch size: 18, lr: 6.00e-04
2022-05-14 13:51:52,319 INFO [train.py:812] (4/8) Epoch 13, batch 700, loss[loss=0.1739, simple_loss=0.2455, pruned_loss=0.05114, over 6809.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2624, pruned_loss=0.04432, over 1383318.27 frames.], batch size: 15, lr: 6.00e-04
2022-05-14 13:52:51,778 INFO [train.py:812] (4/8) Epoch 13, batch 750, loss[loss=0.1634, simple_loss=0.2546, pruned_loss=0.03612, over 7201.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2628, pruned_loss=0.04429, over 1395483.27 frames.], batch size: 23, lr: 5.99e-04
2022-05-14 13:53:50,410 INFO [train.py:812] (4/8) Epoch 13, batch 800, loss[loss=0.1776, simple_loss=0.2753, pruned_loss=0.03993, over 7201.00 frames.], tot_loss[loss=0.176, simple_loss=0.2631, pruned_loss=0.0444, over 1403911.20 frames.], batch size: 22, lr: 5.99e-04
2022-05-14 13:54:49,218 INFO [train.py:812] (4/8) Epoch 13, batch 850, loss[loss=0.1477, simple_loss=0.2419, pruned_loss=0.02674, over 7148.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2638, pruned_loss=0.04455, over 1410362.27 frames.], batch size: 17, lr: 5.99e-04
2022-05-14 13:55:48,214 INFO [train.py:812] (4/8) Epoch 13, batch 900, loss[loss=0.169, simple_loss=0.2494, pruned_loss=0.04433, over 7333.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2629, pruned_loss=0.04405, over 1413965.36 frames.], batch size: 20, lr: 5.99e-04
2022-05-14 13:56:52,998 INFO [train.py:812] (4/8) Epoch 13, batch 950, loss[loss=0.1703, simple_loss=0.2633, pruned_loss=0.03862, over 7161.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2629, pruned_loss=0.04414, over 1414068.94 frames.], batch size: 26, lr: 5.98e-04
2022-05-14 13:57:52,235 INFO [train.py:812] (4/8) Epoch 13, batch 1000, loss[loss=0.1771, simple_loss=0.2612, pruned_loss=0.04653, over 6434.00 frames.], tot_loss[loss=0.1764, simple_loss=0.264, pruned_loss=0.04443, over 1414458.93 frames.], batch size: 37, lr: 5.98e-04
2022-05-14 13:58:51,876 INFO [train.py:812] (4/8) Epoch 13, batch 1050, loss[loss=0.1632, simple_loss=0.252, pruned_loss=0.03723, over 7251.00 frames.], tot_loss[loss=0.1759, simple_loss=0.263, pruned_loss=0.04438, over 1415962.84 frames.], batch size: 19, lr: 5.98e-04
2022-05-14 13:59:49,633 INFO [train.py:812] (4/8) Epoch 13, batch 1100, loss[loss=0.1891, simple_loss=0.274, pruned_loss=0.05214, over 7376.00 frames.], tot_loss[loss=0.176, simple_loss=0.2634, pruned_loss=0.0443, over 1422603.46 frames.], batch size: 23, lr: 5.97e-04
2022-05-14 14:00:49,262 INFO [train.py:812] (4/8) Epoch 13, batch 1150, loss[loss=0.1601, simple_loss=0.2512, pruned_loss=0.03455, over 7337.00 frames.], tot_loss[loss=0.1754, simple_loss=0.263, pruned_loss=0.04393, over 1424484.10 frames.], batch size: 20, lr: 5.97e-04
2022-05-14 14:01:48,651 INFO [train.py:812] (4/8) Epoch 13, batch 1200, loss[loss=0.25, simple_loss=0.3141, pruned_loss=0.09295, over 5085.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2622, pruned_loss=0.04361, over 1422042.26 frames.], batch size: 52, lr: 5.97e-04
2022-05-14 14:02:48,262 INFO [train.py:812] (4/8) Epoch 13, batch 1250, loss[loss=0.1742, simple_loss=0.2637, pruned_loss=0.04232, over 7156.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2628, pruned_loss=0.04415, over 1419158.78 frames.], batch size: 19, lr: 5.97e-04
2022-05-14 14:03:47,348 INFO [train.py:812] (4/8) Epoch 13, batch 1300, loss[loss=0.1703, simple_loss=0.2524, pruned_loss=0.04412, over 7075.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2621, pruned_loss=0.04382, over 1419749.84 frames.], batch size: 18, lr: 5.96e-04
2022-05-14 14:04:46,579 INFO [train.py:812] (4/8) Epoch 13, batch 1350, loss[loss=0.2133, simple_loss=0.2863, pruned_loss=0.07014, over 4959.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2632, pruned_loss=0.04413, over 1417503.10 frames.], batch size: 52, lr: 5.96e-04
2022-05-14 14:05:45,496 INFO [train.py:812] (4/8) Epoch 13, batch 1400, loss[loss=0.1804, simple_loss=0.277, pruned_loss=0.04186, over 7302.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2641, pruned_loss=0.04459, over 1416263.02 frames.], batch size: 25, lr: 5.96e-04
2022-05-14 14:06:43,977 INFO [train.py:812] (4/8) Epoch 13, batch 1450, loss[loss=0.1782, simple_loss=0.2745, pruned_loss=0.04095, over 7314.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2639, pruned_loss=0.04434, over 1414281.53 frames.], batch size: 21, lr: 5.96e-04
2022-05-14 14:07:42,547 INFO [train.py:812] (4/8) Epoch 13, batch 1500, loss[loss=0.2066, simple_loss=0.2913, pruned_loss=0.06095, over 7212.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2641, pruned_loss=0.04439, over 1417554.33 frames.], batch size: 23, lr: 5.95e-04
2022-05-14 14:08:42,626 INFO [train.py:812] (4/8) Epoch 13, batch 1550, loss[loss=0.2108, simple_loss=0.3028, pruned_loss=0.05939, over 7073.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2631, pruned_loss=0.04394, over 1420186.74 frames.], batch size: 28, lr: 5.95e-04
2022-05-14 14:09:41,283 INFO [train.py:812] (4/8) Epoch 13, batch 1600, loss[loss=0.198, simple_loss=0.2847, pruned_loss=0.0556, over 7282.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2641, pruned_loss=0.04458, over 1419171.04 frames.], batch size: 25, lr: 5.95e-04
2022-05-14 14:10:39,361 INFO [train.py:812] (4/8) Epoch 13, batch 1650, loss[loss=0.1843, simple_loss=0.2711, pruned_loss=0.04876, over 7306.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2641, pruned_loss=0.04482, over 1421722.29 frames.], batch size: 24, lr: 5.95e-04
2022-05-14 14:11:36,469 INFO [train.py:812] (4/8) Epoch 13, batch 1700, loss[loss=0.1434, simple_loss=0.2354, pruned_loss=0.02566, over 7145.00 frames.], tot_loss[loss=0.176, simple_loss=0.2632, pruned_loss=0.04438, over 1417630.74 frames.], batch size: 17, lr: 5.94e-04
2022-05-14 14:12:34,778 INFO [train.py:812] (4/8) Epoch 13, batch 1750, loss[loss=0.1605, simple_loss=0.2572, pruned_loss=0.0319, over 7184.00 frames.], tot_loss[loss=0.175, simple_loss=0.2621, pruned_loss=0.04391, over 1420868.89 frames.], batch size: 26, lr: 5.94e-04
2022-05-14 14:13:34,200 INFO [train.py:812] (4/8) Epoch 13, batch 1800, loss[loss=0.1597, simple_loss=0.235, pruned_loss=0.04218, over 6997.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2621, pruned_loss=0.04401, over 1426329.91 frames.], batch size: 16, lr: 5.94e-04
2022-05-14 14:14:33,811 INFO [train.py:812] (4/8) Epoch 13, batch 1850, loss[loss=0.1988, simple_loss=0.2979, pruned_loss=0.04979, over 7324.00 frames.], tot_loss[loss=0.1749, simple_loss=0.262, pruned_loss=0.04388, over 1426799.03 frames.], batch size: 22, lr: 5.94e-04
2022-05-14 14:15:33,206 INFO [train.py:812] (4/8) Epoch 13, batch 1900, loss[loss=0.1739, simple_loss=0.2595, pruned_loss=0.04413, over 7234.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2627, pruned_loss=0.04422, over 1427499.98 frames.], batch size: 20, lr: 5.93e-04
2022-05-14 14:16:32,243 INFO [train.py:812] (4/8) Epoch 13, batch 1950, loss[loss=0.1414, simple_loss=0.2179, pruned_loss=0.03243, over 7276.00 frames.], tot_loss[loss=0.1752, simple_loss=0.262, pruned_loss=0.04421, over 1427545.10 frames.], batch size: 17, lr: 5.93e-04
2022-05-14 14:17:31,537 INFO [train.py:812] (4/8) Epoch 13, batch 2000, loss[loss=0.1395, simple_loss=0.2288, pruned_loss=0.02503, over 6989.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2608, pruned_loss=0.04348, over 1427254.07 frames.], batch size: 16, lr: 5.93e-04
2022-05-14 14:18:40,074 INFO [train.py:812] (4/8) Epoch 13, batch 2050, loss[loss=0.1752, simple_loss=0.2613, pruned_loss=0.04453, over 7154.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2599, pruned_loss=0.0432, over 1421213.34 frames.], batch size: 19, lr: 5.93e-04
2022-05-14 14:19:39,660 INFO [train.py:812] (4/8) Epoch 13, batch 2100, loss[loss=0.1725, simple_loss=0.27, pruned_loss=0.03746, over 7165.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2613, pruned_loss=0.04401, over 1421486.69 frames.], batch size: 19, lr: 5.92e-04
2022-05-14 14:20:39,442 INFO [train.py:812] (4/8) Epoch 13, batch 2150, loss[loss=0.1664, simple_loss=0.2577, pruned_loss=0.03758, over 7287.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2615, pruned_loss=0.0438, over 1422129.69 frames.], batch size: 18, lr: 5.92e-04
2022-05-14 14:21:36,886 INFO [train.py:812] (4/8) Epoch 13, batch 2200, loss[loss=0.2026, simple_loss=0.2793, pruned_loss=0.06296, over 7327.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2606, pruned_loss=0.0432, over 1422657.09 frames.], batch size: 20, lr: 5.92e-04
2022-05-14 14:22:35,529 INFO [train.py:812] (4/8) Epoch 13, batch 2250, loss[loss=0.1869, simple_loss=0.2801, pruned_loss=0.04686, over 7090.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2602, pruned_loss=0.04301, over 1420395.28 frames.], batch size: 28, lr: 5.91e-04
2022-05-14 14:23:34,270 INFO [train.py:812] (4/8) Epoch 13, batch 2300, loss[loss=0.1792, simple_loss=0.2724, pruned_loss=0.04299, over 7117.00 frames.], tot_loss[loss=0.174, simple_loss=0.2617, pruned_loss=0.04313, over 1424684.47 frames.], batch size: 21, lr: 5.91e-04
2022-05-14 14:24:34,072 INFO [train.py:812] (4/8) Epoch 13, batch 2350, loss[loss=0.177, simple_loss=0.2573, pruned_loss=0.04837, over 7157.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2626, pruned_loss=0.04365, over 1426330.58 frames.], batch size: 19, lr: 5.91e-04
2022-05-14 14:25:33,545 INFO [train.py:812] (4/8) Epoch 13, batch 2400, loss[loss=0.1709, simple_loss=0.2459, pruned_loss=0.0479, over 7139.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2624, pruned_loss=0.04356, over 1426350.97 frames.], batch size: 17, lr: 5.91e-04
2022-05-14 14:26:31,970 INFO [train.py:812] (4/8) Epoch 13, batch 2450, loss[loss=0.1736, simple_loss=0.2716, pruned_loss=0.03783, over 7215.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2624, pruned_loss=0.04356, over 1426275.25 frames.], batch size: 21, lr: 5.90e-04
2022-05-14 14:27:30,757 INFO [train.py:812] (4/8) Epoch 13, batch 2500, loss[loss=0.1684, simple_loss=0.2487, pruned_loss=0.04403, over 7281.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2624, pruned_loss=0.04376, over 1427320.99 frames.], batch size: 18, lr: 5.90e-04
2022-05-14 14:28:30,428 INFO [train.py:812] (4/8) Epoch 13, batch 2550, loss[loss=0.1655, simple_loss=0.244, pruned_loss=0.04348, over 7219.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2629, pruned_loss=0.04425, over 1429153.79 frames.], batch size: 16, lr: 5.90e-04
2022-05-14 14:29:29,632 INFO [train.py:812] (4/8) Epoch 13, batch 2600, loss[loss=0.1835, simple_loss=0.2655, pruned_loss=0.05076, over 6793.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2625, pruned_loss=0.04431, over 1425733.25 frames.], batch size: 15, lr: 5.90e-04
2022-05-14 14:30:29,024 INFO [train.py:812] (4/8) Epoch 13, batch 2650, loss[loss=0.1722, simple_loss=0.2403, pruned_loss=0.05203, over 6984.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2628, pruned_loss=0.04425, over 1423235.79 frames.], batch size: 16, lr: 5.89e-04
2022-05-14 14:31:27,711 INFO [train.py:812] (4/8) Epoch 13, batch 2700, loss[loss=0.1617, simple_loss=0.239, pruned_loss=0.04221, over 7012.00 frames.], tot_loss[loss=0.175, simple_loss=0.2623, pruned_loss=0.04385, over 1424665.85 frames.], batch size: 16, lr: 5.89e-04
2022-05-14 14:32:27,067 INFO [train.py:812] (4/8) Epoch 13, batch 2750, loss[loss=0.1624, simple_loss=0.2557, pruned_loss=0.03458, over 7108.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2622, pruned_loss=0.04413, over 1422349.65 frames.], batch size: 21, lr: 5.89e-04
2022-05-14 14:33:24,882 INFO [train.py:812] (4/8) Epoch 13, batch 2800, loss[loss=0.1572, simple_loss=0.2355, pruned_loss=0.03944, over 7150.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2628, pruned_loss=0.04419, over 1422042.71 frames.], batch size: 17, lr: 5.89e-04
2022-05-14 14:34:24,902 INFO [train.py:812] (4/8) Epoch 13, batch 2850, loss[loss=0.2114, simple_loss=0.3078, pruned_loss=0.05746, over 7376.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2638, pruned_loss=0.04445, over 1427723.44 frames.], batch size: 23, lr: 5.88e-04
2022-05-14 14:35:22,589 INFO [train.py:812] (4/8) Epoch 13, batch 2900, loss[loss=0.157, simple_loss=0.2391, pruned_loss=0.03748, over 7359.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2638, pruned_loss=0.04417, over 1425260.51 frames.], batch size: 19, lr: 5.88e-04
2022-05-14 14:36:21,963 INFO [train.py:812] (4/8) Epoch 13, batch 2950, loss[loss=0.1917, simple_loss=0.2864, pruned_loss=0.04848, over 7447.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2634, pruned_loss=0.04416, over 1427085.81 frames.], batch size: 22, lr: 5.88e-04
2022-05-14 14:37:20,739 INFO [train.py:812] (4/8) Epoch 13, batch 3000, loss[loss=0.1229, simple_loss=0.209, pruned_loss=0.01837, over 7282.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2631, pruned_loss=0.04397, over 1427079.77 frames.], batch size: 17, lr: 5.88e-04
2022-05-14 14:37:20,740 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 14:37:28,226 INFO [train.py:841] (4/8) Epoch 13, validation: loss=0.1549, simple_loss=0.2559, pruned_loss=0.02694, over 698248.00 frames.
2022-05-14 14:38:28,330 INFO [train.py:812] (4/8) Epoch 13, batch 3050, loss[loss=0.144, simple_loss=0.2312, pruned_loss=0.02841, over 7152.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2628, pruned_loss=0.04396, over 1427821.12 frames.], batch size: 17, lr: 5.87e-04
2022-05-14 14:39:27,858 INFO [train.py:812] (4/8) Epoch 13, batch 3100, loss[loss=0.2118, simple_loss=0.3025, pruned_loss=0.06057, over 7115.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2618, pruned_loss=0.0436, over 1427426.54 frames.], batch size: 21, lr: 5.87e-04
2022-05-14 14:40:36,455 INFO [train.py:812] (4/8) Epoch 13, batch 3150, loss[loss=0.1984, simple_loss=0.2778, pruned_loss=0.05943, over 7331.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2628, pruned_loss=0.0439, over 1424510.70 frames.], batch size: 25, lr: 5.87e-04
2022-05-14 14:41:35,462 INFO [train.py:812] (4/8) Epoch 13, batch 3200, loss[loss=0.2489, simple_loss=0.3142, pruned_loss=0.09184, over 5023.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2639, pruned_loss=0.04436, over 1425726.35 frames.], batch size: 52, lr: 5.87e-04
2022-05-14 14:42:44,510 INFO [train.py:812] (4/8) Epoch 13, batch 3250, loss[loss=0.1479, simple_loss=0.2258, pruned_loss=0.03498, over 7275.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2631, pruned_loss=0.04418, over 1428699.22 frames.], batch size: 17, lr: 5.86e-04
2022-05-14 14:43:53,098 INFO [train.py:812] (4/8) Epoch 13, batch 3300, loss[loss=0.1784, simple_loss=0.2664, pruned_loss=0.04523, over 7335.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2625, pruned_loss=0.04394, over 1428433.92 frames.], batch size: 20, lr: 5.86e-04
2022-05-14 14:44:51,606 INFO [train.py:812] (4/8) Epoch 13, batch 3350, loss[loss=0.145, simple_loss=0.2302, pruned_loss=0.02985, over 7003.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2627, pruned_loss=0.04427, over 1420788.05 frames.], batch size: 16, lr: 5.86e-04
2022-05-14 14:46:18,933 INFO [train.py:812] (4/8) Epoch 13, batch 3400, loss[loss=0.1872, simple_loss=0.2764, pruned_loss=0.04899, over 7384.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2636, pruned_loss=0.04429, over 1424334.96 frames.], batch size: 23, lr: 5.86e-04
2022-05-14 14:47:27,733 INFO [train.py:812] (4/8) Epoch 13, batch 3450, loss[loss=0.1764, simple_loss=0.2616, pruned_loss=0.04557, over 7411.00 frames.], tot_loss[loss=0.176, simple_loss=0.2637, pruned_loss=0.04415, over 1412340.83 frames.], batch size: 18, lr: 5.85e-04
2022-05-14 14:48:26,512 INFO [train.py:812] (4/8) Epoch 13, batch 3500, loss[loss=0.1659, simple_loss=0.2521, pruned_loss=0.03989, over 6762.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2629, pruned_loss=0.0438, over 1414291.11 frames.], batch size: 31, lr: 5.85e-04
2022-05-14 14:49:26,043 INFO [train.py:812] (4/8) Epoch 13, batch 3550, loss[loss=0.1652, simple_loss=0.2456, pruned_loss=0.04239, over 6995.00 frames.], tot_loss[loss=0.175, simple_loss=0.2626, pruned_loss=0.04371, over 1420010.74 frames.], batch size: 16, lr: 5.85e-04
2022-05-14 14:50:24,015 INFO [train.py:812] (4/8) Epoch 13, batch 3600, loss[loss=0.1578, simple_loss=0.2354, pruned_loss=0.04012, over 7287.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2621, pruned_loss=0.04348, over 1420007.91 frames.], batch size: 18, lr: 5.85e-04
2022-05-14 14:51:22,137 INFO [train.py:812] (4/8) Epoch 13, batch 3650, loss[loss=0.1872, simple_loss=0.2763, pruned_loss=0.04906, over 7415.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2627, pruned_loss=0.04356, over 1422902.90 frames.], batch size: 21, lr: 5.84e-04
2022-05-14 14:52:20,920 INFO [train.py:812] (4/8) Epoch 13, batch 3700, loss[loss=0.158, simple_loss=0.2394, pruned_loss=0.03825, over 7263.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2613, pruned_loss=0.04349, over 1423768.27 frames.], batch size: 19, lr: 5.84e-04
2022-05-14 14:53:20,288 INFO [train.py:812] (4/8) Epoch 13, batch 3750, loss[loss=0.1684, simple_loss=0.2733, pruned_loss=0.03175, over 7415.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2607, pruned_loss=0.04312, over 1424288.90 frames.], batch size: 21, lr: 5.84e-04
2022-05-14 14:54:19,192 INFO [train.py:812] (4/8) Epoch 13, batch 3800, loss[loss=0.2015, simple_loss=0.2892, pruned_loss=0.05689, over 7018.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2616, pruned_loss=0.04339, over 1429003.14 frames.], batch size: 28, lr: 5.84e-04
2022-05-14 14:55:18,393 INFO [train.py:812] (4/8) Epoch 13, batch 3850, loss[loss=0.1746, simple_loss=0.2575, pruned_loss=0.04582, over 7201.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2628, pruned_loss=0.0437, over 1426029.00 frames.], batch size: 22, lr: 5.83e-04
2022-05-14 14:56:17,001 INFO [train.py:812] (4/8) Epoch 13, batch 3900, loss[loss=0.2044, simple_loss=0.2865, pruned_loss=0.06118, over 7296.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2628, pruned_loss=0.04336, over 1424790.96 frames.], batch size: 24, lr: 5.83e-04
2022-05-14 14:57:16,824 INFO [train.py:812] (4/8) Epoch 13, batch 3950, loss[loss=0.1773, simple_loss=0.2613, pruned_loss=0.04666, over 7197.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2627, pruned_loss=0.04359, over 1423968.88 frames.], batch size: 23, lr: 5.83e-04
2022-05-14 14:58:15,076 INFO [train.py:812] (4/8) Epoch 13, batch 4000, loss[loss=0.155, simple_loss=0.2414, pruned_loss=0.03431, over 7111.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2625, pruned_loss=0.04343, over 1423274.22 frames.], batch size: 17, lr: 5.83e-04
2022-05-14 14:59:14,567 INFO [train.py:812] (4/8) Epoch 13, batch 4050, loss[loss=0.1622, simple_loss=0.2646, pruned_loss=0.02989, over 7240.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2621, pruned_loss=0.04347, over 1425171.18 frames.], batch size: 20, lr: 5.82e-04
2022-05-14 15:00:14,087 INFO [train.py:812] (4/8) Epoch 13, batch 4100, loss[loss=0.2054, simple_loss=0.2962, pruned_loss=0.05729, over 7145.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2612, pruned_loss=0.04328, over 1424841.95 frames.], batch size: 20, lr: 5.82e-04
2022-05-14 15:01:13,276 INFO [train.py:812] (4/8) Epoch 13, batch 4150, loss[loss=0.1465, simple_loss=0.2342, pruned_loss=0.02939, over 7439.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2627, pruned_loss=0.04398, over 1419708.74 frames.], batch size: 20, lr: 5.82e-04
2022-05-14 15:02:11,345 INFO [train.py:812] (4/8) Epoch 13, batch 4200, loss[loss=0.1713, simple_loss=0.2638, pruned_loss=0.03942, over 7144.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2617, pruned_loss=0.04364, over 1420507.86 frames.], batch size: 20, lr: 5.82e-04
2022-05-14 15:03:10,125 INFO [train.py:812] (4/8) Epoch 13, batch 4250, loss[loss=0.1684, simple_loss=0.2645, pruned_loss=0.03611, over 7198.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2611, pruned_loss=0.04355, over 1418748.83 frames.], batch size: 26, lr: 5.81e-04
2022-05-14 15:04:08,192 INFO [train.py:812] (4/8) Epoch 13, batch 4300, loss[loss=0.164, simple_loss=0.2574, pruned_loss=0.03529, over 7426.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2624, pruned_loss=0.04405, over 1415824.62 frames.], batch size: 20, lr: 5.81e-04
2022-05-14 15:05:06,778 INFO [train.py:812] (4/8) Epoch 13, batch 4350, loss[loss=0.1496, simple_loss=0.2241, pruned_loss=0.03756, over 6995.00 frames.], tot_loss[loss=0.175, simple_loss=0.262, pruned_loss=0.04403, over 1411676.29 frames.], batch size: 16, lr: 5.81e-04
2022-05-14 15:06:06,054 INFO [train.py:812] (4/8) Epoch 13, batch 4400, loss[loss=0.2146, simple_loss=0.2968, pruned_loss=0.0662, over 5172.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2611, pruned_loss=0.04391, over 1410899.77 frames.], batch size: 52, lr: 5.81e-04
2022-05-14 15:07:04,942 INFO [train.py:812] (4/8) Epoch 13, batch 4450, loss[loss=0.2008, simple_loss=0.2816, pruned_loss=0.06, over 7296.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2608, pruned_loss=0.04383, over 1408514.80 frames.], batch size: 24, lr: 5.81e-04
2022-05-14 15:08:03,272 INFO [train.py:812] (4/8) Epoch 13, batch 4500, loss[loss=0.1811, simple_loss=0.2684, pruned_loss=0.04692, over 7415.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2618, pruned_loss=0.04471, over 1389621.61 frames.], batch size: 21, lr: 5.80e-04
2022-05-14 15:09:01,461 INFO [train.py:812] (4/8) Epoch 13, batch 4550, loss[loss=0.1923, simple_loss=0.273, pruned_loss=0.05573, over 5065.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2648, pruned_loss=0.04589, over 1355371.98 frames.], batch size: 52, lr: 5.80e-04
2022-05-14 15:10:14,177 INFO [train.py:812] (4/8) Epoch 14, batch 0, loss[loss=0.194, simple_loss=0.283, pruned_loss=0.05253, over 7395.00 frames.], tot_loss[loss=0.194, simple_loss=0.283, pruned_loss=0.05253, over 7395.00 frames.], batch size: 23, lr: 5.61e-04
2022-05-14 15:11:14,039 INFO [train.py:812] (4/8) Epoch 14, batch 50, loss[loss=0.1893, simple_loss=0.282, pruned_loss=0.0483, over 7121.00 frames.], tot_loss[loss=0.1722, simple_loss=0.258, pruned_loss=0.04318, over 322352.42 frames.], batch size: 21, lr: 5.61e-04
2022-05-14 15:12:13,748 INFO [train.py:812] (4/8) Epoch 14, batch 100, loss[loss=0.178, simple_loss=0.2607, pruned_loss=0.04768, over 7151.00 frames.], tot_loss[loss=0.1726, simple_loss=0.26, pruned_loss=0.04258, over 572349.91 frames.], batch size: 20, lr: 5.61e-04
2022-05-14 15:13:13,205 INFO [train.py:812] (4/8) Epoch 14, batch 150, loss[loss=0.1477, simple_loss=0.2248, pruned_loss=0.03531, over 6999.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2582, pruned_loss=0.04198, over 763183.24 frames.], batch size: 16, lr: 5.61e-04
2022-05-14 15:14:11,613 INFO [train.py:812] (4/8) Epoch 14, batch 200, loss[loss=0.1823, simple_loss=0.2695, pruned_loss=0.04756, over 7202.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2594, pruned_loss=0.04212, over 910394.04 frames.], batch size: 22, lr: 5.60e-04
2022-05-14 15:15:09,288 INFO [train.py:812] (4/8) Epoch 14, batch 250, loss[loss=0.1941, simple_loss=0.2791, pruned_loss=0.05458, over 7219.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2603, pruned_loss=0.04264, over 1026070.35 frames.], batch size: 22, lr: 5.60e-04
2022-05-14 15:16:07,605 INFO [train.py:812] (4/8) Epoch 14, batch 300, loss[loss=0.1905, simple_loss=0.2759, pruned_loss=0.05256, over 7413.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2623, pruned_loss=0.0431, over 1112761.88 frames.], batch size: 21, lr: 5.60e-04
2022-05-14 15:17:06,823 INFO [train.py:812] (4/8) Epoch 14, batch 350, loss[loss=0.186, simple_loss=0.2679, pruned_loss=0.05201, over 7412.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2621, pruned_loss=0.04366, over 1180699.86 frames.], batch size: 20, lr: 5.60e-04
2022-05-14 15:18:11,721 INFO [train.py:812] (4/8) Epoch 14, batch 400, loss[loss=0.18, simple_loss=0.2679, pruned_loss=0.0461, over 7008.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2617, pruned_loss=0.04335, over 1230628.48 frames.], batch size: 28, lr: 5.59e-04
2022-05-14 15:19:10,168 INFO [train.py:812] (4/8) Epoch 14, batch 450, loss[loss=0.2188, simple_loss=0.3035, pruned_loss=0.06702, over 6416.00 frames.], tot_loss[loss=0.174, simple_loss=0.2614, pruned_loss=0.0433, over 1273381.22 frames.], batch size: 37, lr: 5.59e-04
2022-05-14 15:20:09,609 INFO [train.py:812] (4/8) Epoch 14, batch 500, loss[loss=0.2093, simple_loss=0.2922, pruned_loss=0.06318, over 7078.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2605, pruned_loss=0.04303, over 1301701.50 frames.], batch size: 28, lr: 5.59e-04
2022-05-14 15:21:08,775 INFO [train.py:812] (4/8) Epoch 14, batch 550, loss[loss=0.1746, simple_loss=0.2752, pruned_loss=0.03702, over 6392.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2611, pruned_loss=0.04311, over 1326479.72 frames.], batch size: 38, lr: 5.59e-04
2022-05-14 15:22:08,320 INFO [train.py:812] (4/8) Epoch 14, batch 600, loss[loss=0.1567, simple_loss=0.2618, pruned_loss=0.02577, over 7321.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2604, pruned_loss=0.0426, over 1348717.72 frames.], batch size: 21, lr: 5.59e-04
2022-05-14 15:23:07,041 INFO [train.py:812] (4/8) Epoch 14, batch 650, loss[loss=0.1637, simple_loss=0.2546, pruned_loss=0.03642, over 7064.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2607, pruned_loss=0.0426, over 1361444.11 frames.], batch size: 18, lr: 5.58e-04
2022-05-14 15:24:06,559 INFO [train.py:812] (4/8) Epoch 14, batch 700, loss[loss=0.1713, simple_loss=0.2516, pruned_loss=0.04555, over 7283.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2607, pruned_loss=0.04238, over 1376477.25 frames.], batch size: 18, lr: 5.58e-04
2022-05-14 15:25:05,443 INFO [train.py:812] (4/8) Epoch 14, batch 750, loss[loss=0.1614, simple_loss=0.2605, pruned_loss=0.03114, over 7210.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2605, pruned_loss=0.04219, over 1383192.77 frames.], batch size: 23, lr: 5.58e-04
2022-05-14 15:26:04,464 INFO [train.py:812] (4/8) Epoch 14, batch 800, loss[loss=0.1806, simple_loss=0.2748, pruned_loss=0.04319, over 7287.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2615, pruned_loss=0.04279, over 1392066.68 frames.], batch size: 25, lr: 5.58e-04
2022-05-14 15:27:03,670 INFO [train.py:812] (4/8) Epoch 14, batch 850, loss[loss=0.1926, simple_loss=0.2756, pruned_loss=0.05483, over 7208.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2612, pruned_loss=0.04284, over 1399844.69 frames.], batch size: 21, lr: 5.57e-04
2022-05-14 15:28:02,929 INFO [train.py:812] (4/8) Epoch 14, batch 900, loss[loss=0.1512, simple_loss=0.2362, pruned_loss=0.03304, over 7177.00 frames.], tot_loss[loss=0.174, simple_loss=0.2619, pruned_loss=0.04308, over 1403065.14 frames.], batch size: 18, lr: 5.57e-04
2022-05-14 15:29:01,738 INFO [train.py:812] (4/8) Epoch 14, batch 950, loss[loss=0.1627, simple_loss=0.2502, pruned_loss=0.03758, over 7224.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2622, pruned_loss=0.04311, over 1403727.26 frames.], batch size: 21, lr: 5.57e-04
2022-05-14 15:30:01,407 INFO [train.py:812] (4/8) Epoch 14, batch 1000, loss[loss=0.1683, simple_loss=0.2636, pruned_loss=0.03643, over 7191.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2614, pruned_loss=0.04277, over 1410745.82 frames.], batch size: 22, lr: 5.57e-04
2022-05-14 15:31:00,117 INFO [train.py:812] (4/8) Epoch 14, batch 1050, loss[loss=0.1885, simple_loss=0.2695, pruned_loss=0.05373, over 7413.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2609, pruned_loss=0.04241, over 1410523.29 frames.], batch size: 21, lr: 5.56e-04
2022-05-14 15:31:57,358 INFO [train.py:812] (4/8) Epoch 14, batch 1100, loss[loss=0.1818, simple_loss=0.2714, pruned_loss=0.04614, over 6784.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2608, pruned_loss=0.0423, over 1410644.52 frames.], batch size: 31, lr: 5.56e-04
2022-05-14 15:32:55,039 INFO [train.py:812] (4/8) Epoch 14, batch 1150, loss[loss=0.1845, simple_loss=0.274, pruned_loss=0.04746, over 7350.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2616, pruned_loss=0.04253, over 1410090.69 frames.], batch size: 22, lr: 5.56e-04
2022-05-14 15:33:54,462 INFO [train.py:812] (4/8) Epoch 14, batch 1200, loss[loss=0.1935, simple_loss=0.2737, pruned_loss=0.05663, over 4965.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2611, pruned_loss=0.04232, over 1410196.03 frames.], batch size: 54, lr: 5.56e-04
2022-05-14 15:34:52,769 INFO [train.py:812] (4/8) Epoch 14, batch 1250, loss[loss=0.1765, simple_loss=0.2706, pruned_loss=0.04119, over 7434.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2617, pruned_loss=0.04256, over 1414177.70 frames.], batch size: 20, lr: 5.56e-04
2022-05-14 15:35:51,079 INFO [train.py:812] (4/8) Epoch 14, batch 1300, loss[loss=0.1683, simple_loss=0.2475, pruned_loss=0.04452, over 7257.00 frames.], tot_loss[loss=0.1727, simple_loss=0.261, pruned_loss=0.04225, over 1417841.92 frames.], batch size: 19, lr: 5.55e-04
2022-05-14 15:36:49,467 INFO [train.py:812] (4/8) Epoch 14, batch 1350, loss[loss=0.1608, simple_loss=0.2456, pruned_loss=0.03804, over 7265.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2601, pruned_loss=0.04212, over 1422020.82 frames.], batch size: 18, lr: 5.55e-04
2022-05-14 15:37:48,221 INFO [train.py:812] (4/8) Epoch 14, batch 1400, loss[loss=0.1566, simple_loss=0.231, pruned_loss=0.04107, over 7175.00 frames.], tot_loss[loss=0.173, simple_loss=0.261, pruned_loss=0.04253, over 1417929.88 frames.], batch size: 18, lr: 5.55e-04
2022-05-14 15:38:45,034 INFO [train.py:812] (4/8) Epoch 14, batch 1450, loss[loss=0.1351, simple_loss=0.2216, pruned_loss=0.02429, over 7271.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2604, pruned_loss=0.04248, over 1421444.90 frames.], batch size: 17, lr: 5.55e-04
2022-05-14 15:39:43,878 INFO [train.py:812] (4/8) Epoch 14, batch 1500, loss[loss=0.1517, simple_loss=0.2382, pruned_loss=0.03254, over 7281.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2594, pruned_loss=0.04224, over 1422211.10 frames.], batch size: 17, lr: 5.54e-04
2022-05-14 15:40:42,003 INFO [train.py:812] (4/8) Epoch 14, batch 1550, loss[loss=0.1662, simple_loss=0.2522, pruned_loss=0.04012, over 6590.00 frames.], tot_loss[loss=0.172, simple_loss=0.2597, pruned_loss=0.04219, over 1417303.68 frames.], batch size: 38, lr: 5.54e-04
2022-05-14 15:41:40,141 INFO [train.py:812] (4/8) Epoch 14, batch 1600, loss[loss=0.1702, simple_loss=0.2582, pruned_loss=0.04113, over 7415.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2604, pruned_loss=0.04238, over 1416503.84 frames.], batch size: 21, lr: 5.54e-04
2022-05-14 15:42:38,934 INFO [train.py:812] (4/8) Epoch 14, batch 1650, loss[loss=0.1731, simple_loss=0.2628, pruned_loss=0.04167, over 7227.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2607, pruned_loss=0.04225, over 1419045.93 frames.], batch size: 20, lr: 5.54e-04
2022-05-14 15:43:38,136 INFO [train.py:812] (4/8) Epoch 14, batch 1700, loss[loss=0.1667, simple_loss=0.2486, pruned_loss=0.04239, over 6356.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2612, pruned_loss=0.04222, over 1418449.58 frames.], batch size: 37, lr: 5.54e-04
2022-05-14 15:44:37,147 INFO [train.py:812] (4/8) Epoch 14, batch 1750, loss[loss=0.1574, simple_loss=0.2319, pruned_loss=0.0414, over 7274.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2601, pruned_loss=0.04172, over 1420929.18 frames.], batch size: 17, lr: 5.53e-04
2022-05-14 15:45:37,334 INFO [train.py:812] (4/8) Epoch 14, batch 1800, loss[loss=0.177, simple_loss=0.263, pruned_loss=0.04548, over 7148.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2598, pruned_loss=0.04145, over 1425005.27 frames.], batch size: 20, lr: 5.53e-04
2022-05-14 15:46:35,086 INFO [train.py:812] (4/8) Epoch 14, batch 1850, loss[loss=0.1916, simple_loss=0.2795, pruned_loss=0.05186, over 7290.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2604, pruned_loss=0.04194, over 1425027.22 frames.], batch size: 25, lr: 5.53e-04
2022-05-14 15:47:33,725 INFO [train.py:812] (4/8) Epoch 14, batch 1900, loss[loss=0.1668, simple_loss=0.2563, pruned_loss=0.03859, over 6537.00 frames.], tot_loss[loss=0.172, simple_loss=0.2603, pruned_loss=0.04184, over 1421371.52 frames.], batch size: 38, lr: 5.53e-04
2022-05-14 15:48:32,639 INFO [train.py:812] (4/8) Epoch 14, batch 1950, loss[loss=0.1539, simple_loss=0.2323, pruned_loss=0.03775, over 7250.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2608, pruned_loss=0.04232, over 1422933.28 frames.], batch size: 19, lr: 5.52e-04
2022-05-14 15:49:32,352 INFO [train.py:812] (4/8) Epoch 14, batch 2000, loss[loss=0.1709, simple_loss=0.2684, pruned_loss=0.03668, over 7343.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2605, pruned_loss=0.04215, over 1424590.65 frames.], batch size: 22, lr: 5.52e-04
2022-05-14 15:50:31,358 INFO [train.py:812] (4/8) Epoch 14, batch 2050, loss[loss=0.1631, simple_loss=0.2545, pruned_loss=0.03588, over 7373.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2601, pruned_loss=0.0418, over 1426073.68 frames.], batch size: 23, lr: 5.52e-04
2022-05-14 15:51:31,090 INFO [train.py:812] (4/8) Epoch 14, batch 2100, loss[loss=0.1802, simple_loss=0.2768, pruned_loss=0.04178, over 7227.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2615, pruned_loss=0.04245, over 1425290.57 frames.], batch size: 20, lr: 5.52e-04
2022-05-14 15:52:30,499 INFO [train.py:812] (4/8) Epoch 14, batch 2150, loss[loss=0.1893, simple_loss=0.2707, pruned_loss=0.05397, over 7191.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2612, pruned_loss=0.04231, over 1427894.63 frames.], batch size: 26, lr: 5.52e-04
2022-05-14 15:53:29,906 INFO [train.py:812] (4/8) Epoch 14, batch 2200, loss[loss=0.1463, simple_loss=0.2337, pruned_loss=0.02945, over 7435.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2609, pruned_loss=0.04238, over 1425994.76 frames.], batch size: 20, lr: 5.51e-04
2022-05-14 15:54:28,287 INFO [train.py:812] (4/8) Epoch 14, batch 2250, loss[loss=0.1855, simple_loss=0.2768, pruned_loss=0.04709, over 7239.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2611, pruned_loss=0.04233, over 1427589.04 frames.], batch size: 20, lr: 5.51e-04
2022-05-14 15:55:26,899 INFO [train.py:812] (4/8) Epoch 14, batch 2300, loss[loss=0.1823, simple_loss=0.2766, pruned_loss=0.04403, over 7044.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2599, pruned_loss=0.04196, over 1428191.11 frames.], batch size: 28, lr: 5.51e-04
2022-05-14 15:56:25,018 INFO [train.py:812] (4/8) Epoch 14, batch 2350, loss[loss=0.2365, simple_loss=0.306, pruned_loss=0.08353, over 5283.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2592, pruned_loss=0.04156, over 1426978.91 frames.], batch size: 52, lr: 5.51e-04
2022-05-14 15:57:24,251 INFO [train.py:812] (4/8) Epoch 14, batch 2400, loss[loss=0.1573, simple_loss=0.2364, pruned_loss=0.03913, over 7286.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2587, pruned_loss=0.04158, over 1428585.42 frames.], batch size: 17, lr: 5.50e-04
2022-05-14 15:58:23,289 INFO [train.py:812] (4/8) Epoch 14, batch 2450, loss[loss=0.1939, simple_loss=0.2754, pruned_loss=0.05616, over 6817.00 frames.], tot_loss[loss=0.171, simple_loss=0.2589, pruned_loss=0.04159, over 1431323.39 frames.], batch size: 31, lr: 5.50e-04
2022-05-14 15:59:21,596 INFO [train.py:812] (4/8) Epoch 14, batch 2500, loss[loss=0.1492, simple_loss=0.2345, pruned_loss=0.03196, over 7277.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2601, pruned_loss=0.04207, over 1427467.96 frames.], batch size: 17, lr: 5.50e-04
2022-05-14 16:00:19,964 INFO [train.py:812] (4/8) Epoch 14, batch 2550, loss[loss=0.1848, simple_loss=0.2756, pruned_loss=0.04695, over 7303.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2605, pruned_loss=0.04251, over 1423192.88 frames.], batch size: 25, lr: 5.50e-04
2022-05-14 16:01:19,225 INFO [train.py:812] (4/8) Epoch 14, batch 2600, loss[loss=0.1829, simple_loss=0.2749, pruned_loss=0.04542, over 7414.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2602, pruned_loss=0.04236, over 1419516.64 frames.], batch size: 21, lr: 5.50e-04
2022-05-14 16:02:16,359 INFO [train.py:812] (4/8) Epoch 14, batch 2650, loss[loss=0.1511, simple_loss=0.2434, pruned_loss=0.02942, over 7119.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2604, pruned_loss=0.04244, over 1417946.04 frames.], batch size: 21, lr: 5.49e-04
2022-05-14 16:03:15,381 INFO [train.py:812] (4/8) Epoch 14, batch 2700, loss[loss=0.1656, simple_loss=0.244, pruned_loss=0.04363, over 6988.00 frames.], tot_loss[loss=0.1721, simple_loss=0.26, pruned_loss=0.04213, over 1421887.13 frames.], batch size: 16, lr: 5.49e-04
2022-05-14 16:04:13,419 INFO [train.py:812] (4/8) Epoch 14, batch 2750, loss[loss=0.1804, simple_loss=0.2705, pruned_loss=0.0452, over 7306.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2597, pruned_loss=0.04201, over 1427069.95 frames.], batch size: 24, lr: 5.49e-04
2022-05-14 16:05:11,582 INFO [train.py:812] (4/8) Epoch 14, batch 2800, loss[loss=0.1249, simple_loss=0.2147, pruned_loss=0.01753, over 7132.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2596, pruned_loss=0.04203, over 1425221.27 frames.], batch size: 17, lr: 5.49e-04
2022-05-14 16:06:10,652 INFO [train.py:812] (4/8) Epoch 14, batch 2850, loss[loss=0.1834, simple_loss=0.2736, pruned_loss=0.04661, over 7409.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2595, pruned_loss=0.04233, over 1426529.13 frames.], batch size: 21, lr: 5.48e-04
2022-05-14 16:07:10,192 INFO [train.py:812] (4/8) Epoch 14, batch 2900, loss[loss=0.1555, simple_loss=0.2511, pruned_loss=0.02998, over 7122.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2597, pruned_loss=0.04209, over 1427889.06 frames.], batch size: 21, lr: 5.48e-04
2022-05-14 16:08:08,879 INFO [train.py:812] (4/8) Epoch 14, batch 2950, loss[loss=0.179, simple_loss=0.2774, pruned_loss=0.04033, over 7191.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2598, pruned_loss=0.04171, over 1429806.02 frames.], batch size: 23, lr: 5.48e-04
2022-05-14 16:09:07,584 INFO [train.py:812] (4/8) Epoch 14, batch 3000, loss[loss=0.1742, simple_loss=0.2573, pruned_loss=0.04556, over 7279.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2591, pruned_loss=0.04156, over 1430449.59 frames.], batch size: 24, lr: 5.48e-04
2022-05-14 16:09:07,585 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 16:09:15,054 INFO [train.py:841] (4/8) Epoch 14, validation: loss=0.1549, simple_loss=0.2556, pruned_loss=0.02713, over 698248.00 frames.
2022-05-14 16:10:14,210 INFO [train.py:812] (4/8) Epoch 14, batch 3050, loss[loss=0.1308, simple_loss=0.2212, pruned_loss=0.02022, over 7287.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2592, pruned_loss=0.04173, over 1430669.85 frames.], batch size: 17, lr: 5.48e-04
2022-05-14 16:11:13,769 INFO [train.py:812] (4/8) Epoch 14, batch 3100, loss[loss=0.1683, simple_loss=0.2579, pruned_loss=0.03929, over 7204.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2593, pruned_loss=0.04202, over 1432503.58 frames.], batch size: 23, lr: 5.47e-04
2022-05-14 16:12:13,361 INFO [train.py:812] (4/8) Epoch 14, batch 3150, loss[loss=0.1944, simple_loss=0.2744, pruned_loss=0.05718, over 4972.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2587, pruned_loss=0.04195, over 1429974.09 frames.], batch size: 52, lr: 5.47e-04
2022-05-14 16:13:13,726 INFO [train.py:812] (4/8) Epoch 14, batch 3200, loss[loss=0.1676, simple_loss=0.2608, pruned_loss=0.03718, over 7327.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2586, pruned_loss=0.04185, over 1430450.09 frames.], batch size: 22, lr: 5.47e-04
2022-05-14 16:14:11,591 INFO [train.py:812] (4/8) Epoch 14, batch 3250, loss[loss=0.1934, simple_loss=0.2796, pruned_loss=0.0536, over 7136.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2592, pruned_loss=0.04197, over 1427398.54 frames.], batch size: 26, lr: 5.47e-04
2022-05-14 16:15:10,524 INFO [train.py:812] (4/8) Epoch 14, batch 3300, loss[loss=0.1524, simple_loss=0.2349, pruned_loss=0.03497, over 7169.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2591, pruned_loss=0.04207, over 1424098.22 frames.], batch size: 18, lr: 5.46e-04
2022-05-14 16:16:09,534 INFO [train.py:812] (4/8) Epoch 14, batch 3350, loss[loss=0.1549, simple_loss=0.2429, pruned_loss=0.03343, over 7412.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2596, pruned_loss=0.04215, over 1426327.28 frames.], batch size: 18, lr: 5.46e-04
2022-05-14 16:17:08,391 INFO [train.py:812] (4/8) Epoch 14, batch 3400, loss[loss=0.1481, simple_loss=0.2409, pruned_loss=0.02766, over 7178.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2597, pruned_loss=0.0422, over 1427982.53 frames.], batch size: 18, lr: 5.46e-04
2022-05-14 16:18:17,662 INFO [train.py:812] (4/8) Epoch 14, batch 3450, loss[loss=0.1732, simple_loss=0.2619, pruned_loss=0.04223, over 7112.00 frames.], tot_loss[loss=0.1724, simple_loss=0.26, pruned_loss=0.04244, over 1426376.17 frames.], batch size: 21, lr: 5.46e-04
2022-05-14 16:19:16,728 INFO [train.py:812] (4/8) Epoch 14, batch 3500, loss[loss=0.1817, simple_loss=0.27, pruned_loss=0.04675, over 7331.00 frames.], tot_loss[loss=0.172, simple_loss=0.2593, pruned_loss=0.04237, over 1427975.20 frames.], batch size: 22, lr: 5.46e-04
2022-05-14 16:20:15,509 INFO [train.py:812] (4/8) Epoch 14, batch 3550, loss[loss=0.1788, simple_loss=0.2705, pruned_loss=0.04354, over 7318.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2592, pruned_loss=0.04203, over 1428080.39 frames.], batch size: 21, lr: 5.45e-04
2022-05-14 16:21:14,190 INFO [train.py:812] (4/8) Epoch 14, batch 3600, loss[loss=0.179, simple_loss=0.2707, pruned_loss=0.04364, over 7353.00 frames.], tot_loss[loss=0.171, simple_loss=0.2584, pruned_loss=0.04181, over 1430230.14 frames.], batch size: 19, lr: 5.45e-04
2022-05-14 16:22:13,043 INFO [train.py:812] (4/8) Epoch 14, batch 3650, loss[loss=0.1635, simple_loss=0.2623, pruned_loss=0.0324, over 7230.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2582, pruned_loss=0.04174, over 1430013.62 frames.], batch size: 20, lr: 5.45e-04
2022-05-14 16:23:12,482 INFO [train.py:812] (4/8) Epoch 14, batch 3700, loss[loss=0.211, simple_loss=0.3115, pruned_loss=0.05527, over 7281.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2599, pruned_loss=0.04286, over 1421423.92 frames.], batch size: 24, lr: 5.45e-04
2022-05-14 16:24:11,510 INFO [train.py:812] (4/8) Epoch 14, batch 3750, loss[loss=0.1827, simple_loss=0.2652, pruned_loss=0.0501, over 4963.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2602, pruned_loss=0.04286, over 1419538.50 frames.], batch size: 52, lr: 5.45e-04
2022-05-14 16:25:11,056 INFO [train.py:812] (4/8) Epoch 14, batch 3800, loss[loss=0.1425, simple_loss=0.2325, pruned_loss=0.02622, over 6989.00 frames.], tot_loss[loss=0.1734, simple_loss=0.261, pruned_loss=0.04292, over 1419366.62 frames.], batch size: 16, lr: 5.44e-04
2022-05-14 16:26:09,753 INFO [train.py:812] (4/8) Epoch 14, batch 3850, loss[loss=0.2083, simple_loss=0.2882, pruned_loss=0.06418, over 7209.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2607, pruned_loss=0.04278, over 1420228.85 frames.], batch size: 22, lr: 5.44e-04
2022-05-14 16:27:08,435 INFO [train.py:812] (4/8) Epoch 14, batch 3900, loss[loss=0.1773, simple_loss=0.2648, pruned_loss=0.04486, over 7316.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2609, pruned_loss=0.04271, over 1422517.64 frames.], batch size: 21, lr: 5.44e-04
2022-05-14 16:28:07,623 INFO [train.py:812] (4/8) Epoch 14, batch 3950, loss[loss=0.1997, simple_loss=0.2773, pruned_loss=0.06109, over 5360.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2602, pruned_loss=0.04228, over 1421967.83 frames.], batch size: 52, lr: 5.44e-04
2022-05-14 16:29:06,382 INFO [train.py:812] (4/8) Epoch 14, batch 4000, loss[loss=0.1765, simple_loss=0.2717, pruned_loss=0.04064, over 7339.00 frames.], tot_loss[loss=0.174, simple_loss=0.2617, pruned_loss=0.04313, over 1423555.23 frames.], batch size: 22, lr: 5.43e-04
2022-05-14 16:30:03,964 INFO [train.py:812] (4/8) Epoch 14, batch 4050, loss[loss=0.1428, simple_loss=0.2365, pruned_loss=0.02454, over 6820.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2612, pruned_loss=0.04304, over 1424779.74 frames.], batch size: 15, lr: 5.43e-04
2022-05-14 16:31:03,487 INFO [train.py:812] (4/8) Epoch 14, batch 4100, loss[loss=0.1715, simple_loss=0.2618, pruned_loss=0.04062, over 6702.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2605, pruned_loss=0.04302, over 1421384.00 frames.], batch size: 31, lr: 5.43e-04
2022-05-14 16:32:02,254 INFO [train.py:812] (4/8) Epoch 14, batch 4150, loss[loss=0.1792, simple_loss=0.2777, pruned_loss=0.0404, over 7227.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2602, pruned_loss=0.04265, over 1419686.59 frames.], batch size: 21, lr: 5.43e-04
2022-05-14 16:33:01,717 INFO [train.py:812] (4/8) Epoch 14, batch 4200, loss[loss=0.1422, simple_loss=0.2248, pruned_loss=0.02981, over 7286.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2589, pruned_loss=0.04204, over 1420839.95 frames.], batch size: 17, lr: 5.43e-04
2022-05-14 16:34:00,228 INFO [train.py:812] (4/8) Epoch 14, batch 4250, loss[loss=0.1725, simple_loss=0.2627, pruned_loss=0.04109, over 6319.00 frames.], tot_loss[loss=0.1715, simple_loss=0.259, pruned_loss=0.042, over 1415153.48 frames.], batch size: 38, lr: 5.42e-04
2022-05-14 16:34:59,085 INFO [train.py:812] (4/8) Epoch 14, batch 4300, loss[loss=0.1839, simple_loss=0.2796, pruned_loss=0.04411, over 7218.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2596, pruned_loss=0.04228, over 1412042.43 frames.], batch size: 21, lr: 5.42e-04
2022-05-14 16:35:56,837 INFO [train.py:812] (4/8) Epoch 14, batch 4350, loss[loss=0.1299, simple_loss=0.2074, pruned_loss=0.02616, over 6774.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2596, pruned_loss=0.04226, over 1408134.47 frames.], batch size: 15, lr: 5.42e-04
2022-05-14 16:37:01,591 INFO [train.py:812] (4/8) Epoch 14, batch 4400, loss[loss=0.2068, simple_loss=0.3003, pruned_loss=0.05664, over 7148.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2601, pruned_loss=0.04278, over 1402840.95 frames.], batch size: 20, lr: 5.42e-04
2022-05-14 16:38:00,477 INFO [train.py:812] (4/8) Epoch 14, batch 4450, loss[loss=0.2243, simple_loss=0.2898, pruned_loss=0.07941, over 4894.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2612, pruned_loss=0.04363, over 1392979.29 frames.], batch size: 52, lr: 5.42e-04
2022-05-14 16:38:59,693 INFO [train.py:812] (4/8) Epoch 14, batch 4500, loss[loss=0.1923, simple_loss=0.2744, pruned_loss=0.05505, over 5253.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2618, pruned_loss=0.04394, over 1377561.03 frames.], batch size: 53, lr: 5.41e-04
2022-05-14 16:40:07,823 INFO [train.py:812] (4/8) Epoch 14, batch 4550, loss[loss=0.1896, simple_loss=0.281, pruned_loss=0.04909, over 6802.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2614, pruned_loss=0.04405, over 1367019.92 frames.], batch size: 31, lr: 5.41e-04
2022-05-14 16:41:16,664 INFO [train.py:812] (4/8) Epoch 15, batch 0, loss[loss=0.1753, simple_loss=0.2683, pruned_loss=0.04115, over 7035.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2683, pruned_loss=0.04115, over 7035.00 frames.], batch size: 28, lr: 5.25e-04
2022-05-14 16:42:15,487 INFO [train.py:812] (4/8) Epoch 15, batch 50, loss[loss=0.1784, simple_loss=0.2644, pruned_loss=0.04622, over 4799.00 frames.], tot_loss[loss=0.17, simple_loss=0.2589, pruned_loss=0.04057, over 321467.83 frames.], batch size: 52, lr: 5.24e-04
2022-05-14 16:43:15,410 INFO [train.py:812] (4/8) Epoch 15, batch 100, loss[loss=0.1924, simple_loss=0.2899, pruned_loss=0.04748, over 7162.00 frames.], tot_loss[loss=0.17, simple_loss=0.2592, pruned_loss=0.0404, over 567783.24 frames.], batch size: 18, lr: 5.24e-04
2022-05-14 16:44:31,108 INFO [train.py:812] (4/8) Epoch 15, batch 150, loss[loss=0.171, simple_loss=0.2642, pruned_loss=0.03893, over 7116.00 frames.], tot_loss[loss=0.1712, simple_loss=0.261, pruned_loss=0.04075, over 758455.26 frames.], batch size: 21, lr: 5.24e-04
2022-05-14 16:45:30,984 INFO [train.py:812] (4/8) Epoch 15, batch 200, loss[loss=0.1727, simple_loss=0.2641, pruned_loss=0.04064, over 7328.00 frames.], tot_loss[loss=0.172, simple_loss=0.2617, pruned_loss=0.04118, over 902557.72 frames.], batch size: 20, lr: 5.24e-04
2022-05-14 16:46:49,161 INFO [train.py:812] (4/8) Epoch 15, batch 250, loss[loss=0.1756, simple_loss=0.2763, pruned_loss=0.03741, over 6359.00 frames.], tot_loss[loss=0.1714, simple_loss=0.261, pruned_loss=0.0409, over 1019715.61 frames.], batch size: 37, lr: 5.24e-04
2022-05-14 16:48:07,497 INFO [train.py:812] (4/8) Epoch 15, batch 300, loss[loss=0.1637, simple_loss=0.2438, pruned_loss=0.04182, over 7125.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2592, pruned_loss=0.0407, over 1109010.53 frames.], batch size: 17, lr: 5.23e-04
2022-05-14 16:49:06,735 INFO [train.py:812] (4/8) Epoch 15, batch 350, loss[loss=0.156, simple_loss=0.2379, pruned_loss=0.03703, over 7217.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2593, pruned_loss=0.04108, over 1171653.22 frames.], batch size: 16, lr: 5.23e-04
2022-05-14 16:50:06,781 INFO [train.py:812] (4/8) Epoch 15, batch 400, loss[loss=0.1726, simple_loss=0.2699, pruned_loss=0.03769, over 7150.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2595, pruned_loss=0.04122, over 1226809.61 frames.], batch size: 20, lr: 5.23e-04
2022-05-14 16:51:05,888 INFO [train.py:812] (4/8) Epoch 15, batch 450, loss[loss=0.1736, simple_loss=0.2605, pruned_loss=0.04335, over 7169.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2593, pruned_loss=0.04128, over 1271413.96 frames.], batch size: 19, lr: 5.23e-04
2022-05-14 16:52:05,394 INFO [train.py:812] (4/8) Epoch 15, batch 500, loss[loss=0.1486, simple_loss=0.2354, pruned_loss=0.03085, over 7434.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2589, pruned_loss=0.04131, over 1303016.21 frames.], batch size: 20, lr: 5.23e-04
2022-05-14 16:53:04,818 INFO [train.py:812] (4/8) Epoch 15, batch 550, loss[loss=0.1215, simple_loss=0.2064, pruned_loss=0.01828, over 7279.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2588, pruned_loss=0.04136, over 1331696.60 frames.], batch size: 18, lr: 5.22e-04
2022-05-14 16:54:04,513 INFO [train.py:812] (4/8) Epoch 15, batch 600, loss[loss=0.1494, simple_loss=0.2383, pruned_loss=0.03026, over 7243.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2582, pruned_loss=0.0407, over 1354565.79 frames.], batch size: 20, lr: 5.22e-04
2022-05-14 16:55:03,723 INFO [train.py:812] (4/8) Epoch 15, batch 650, loss[loss=0.2042, simple_loss=0.2963, pruned_loss=0.056, over 7348.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2583, pruned_loss=0.04041, over 1369237.97 frames.], batch size: 22, lr: 5.22e-04
2022-05-14 16:56:03,041 INFO [train.py:812] (4/8) Epoch 15, batch 700, loss[loss=0.1585, simple_loss=0.254, pruned_loss=0.03152, over 7334.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2589, pruned_loss=0.04038, over 1382959.77 frames.], batch size: 20, lr: 5.22e-04
2022-05-14 16:57:02,255 INFO [train.py:812] (4/8) Epoch 15, batch 750, loss[loss=0.1776, simple_loss=0.2727, pruned_loss=0.04122, over 7318.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2587, pruned_loss=0.0404, over 1391522.86 frames.], batch size: 22, lr: 5.22e-04
2022-05-14 16:58:01,662 INFO [train.py:812] (4/8) Epoch 15, batch 800, loss[loss=0.1588, simple_loss=0.2551, pruned_loss=0.03131, over 7342.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2588, pruned_loss=0.04027, over 1399803.96 frames.], batch size: 22, lr: 5.21e-04
2022-05-14 16:59:00,997 INFO [train.py:812] (4/8) Epoch 15, batch 850, loss[loss=0.1675, simple_loss=0.2479, pruned_loss=0.0436, over 7132.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2591, pruned_loss=0.04057, over 1402331.44 frames.], batch size: 17, lr: 5.21e-04
2022-05-14 17:00:00,530 INFO [train.py:812] (4/8) Epoch 15, batch 900, loss[loss=0.1631, simple_loss=0.2446, pruned_loss=0.04078, over 7264.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2591, pruned_loss=0.04093, over 1397215.78 frames.], batch size: 19, lr: 5.21e-04
2022-05-14 17:00:59,825 INFO [train.py:812] (4/8) Epoch 15, batch 950, loss[loss=0.2052, simple_loss=0.2981, pruned_loss=0.05611, over 7328.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2603, pruned_loss=0.04144, over 1405566.48 frames.], batch size: 22, lr: 5.21e-04
2022-05-14 17:01:59,703 INFO [train.py:812] (4/8) Epoch 15, batch 1000, loss[loss=0.1849, simple_loss=0.2798, pruned_loss=0.04501, over 7152.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2602, pruned_loss=0.04155, over 1406560.53 frames.], batch size: 28, lr: 5.21e-04
2022-05-14 17:02:57,913 INFO [train.py:812] (4/8) Epoch 15, batch 1050, loss[loss=0.1451, simple_loss=0.231, pruned_loss=0.0296, over 7284.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2601, pruned_loss=0.0417, over 1412692.24 frames.], batch size: 18, lr: 5.20e-04
2022-05-14 17:03:56,824 INFO [train.py:812] (4/8) Epoch 15, batch 1100, loss[loss=0.1945, simple_loss=0.2701, pruned_loss=0.05947, over 7278.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2598, pruned_loss=0.0417, over 1416328.98 frames.], batch size: 17, lr: 5.20e-04
2022-05-14 17:04:54,404 INFO [train.py:812] (4/8) Epoch 15, batch 1150, loss[loss=0.1704, simple_loss=0.2649, pruned_loss=0.038, over 7420.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2588, pruned_loss=0.04118, over 1420803.88 frames.], batch size: 21, lr: 5.20e-04
2022-05-14 17:05:54,078 INFO [train.py:812] (4/8) Epoch 15, batch 1200, loss[loss=0.1526, simple_loss=0.2499, pruned_loss=0.02765, over 7434.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2587, pruned_loss=0.04097, over 1422571.78 frames.], batch size: 20, lr: 5.20e-04
2022-05-14 17:06:52,033 INFO [train.py:812] (4/8) Epoch 15, batch 1250, loss[loss=0.1574, simple_loss=0.2414, pruned_loss=0.03671, over 7355.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2589, pruned_loss=0.04104, over 1425146.70 frames.], batch size: 19, lr: 5.20e-04
2022-05-14 17:07:51,284 INFO [train.py:812] (4/8) Epoch 15, batch 1300, loss[loss=0.1848, simple_loss=0.2655, pruned_loss=0.05199, over 6363.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2587, pruned_loss=0.04099, over 1419124.88 frames.], batch size: 37, lr: 5.19e-04
2022-05-14 17:08:51,287 INFO [train.py:812] (4/8) Epoch 15, batch 1350, loss[loss=0.1633, simple_loss=0.2381, pruned_loss=0.04428, over 7002.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2602, pruned_loss=0.04197, over 1420480.00 frames.], batch size: 16, lr: 5.19e-04
2022-05-14 17:09:50,448 INFO [train.py:812] (4/8) Epoch 15, batch 1400, loss[loss=0.2054, simple_loss=0.2942, pruned_loss=0.05831, over 7304.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2594, pruned_loss=0.04152, over 1420374.15 frames.], batch size: 24, lr: 5.19e-04
2022-05-14 17:10:49,138 INFO [train.py:812] (4/8) Epoch 15, batch 1450, loss[loss=0.168, simple_loss=0.2531, pruned_loss=0.0415, over 7356.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2594, pruned_loss=0.04149, over 1417888.40 frames.], batch size: 23, lr: 5.19e-04
2022-05-14 17:11:46,390 INFO [train.py:812] (4/8) Epoch 15, batch 1500, loss[loss=0.1837, simple_loss=0.2742, pruned_loss=0.0466, over 7151.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2599, pruned_loss=0.04182, over 1411528.34 frames.], batch size: 20, lr: 5.19e-04
2022-05-14 17:12:45,413 INFO [train.py:812] (4/8) Epoch 15, batch 1550, loss[loss=0.1654, simple_loss=0.2676, pruned_loss=0.03163, over 7112.00 frames.], tot_loss[loss=0.1709, simple_loss=0.259, pruned_loss=0.04138, over 1416369.55 frames.], batch size: 21, lr: 5.18e-04
2022-05-14 17:13:44,521 INFO [train.py:812] (4/8) Epoch 15, batch 1600, loss[loss=0.1598, simple_loss=0.2524, pruned_loss=0.03354, over 7407.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2584, pruned_loss=0.04107, over 1418723.82 frames.], batch size: 21, lr: 5.18e-04
2022-05-14 17:14:43,363 INFO [train.py:812] (4/8) Epoch 15, batch 1650, loss[loss=0.184, simple_loss=0.2645, pruned_loss=0.05169, over 7188.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2582, pruned_loss=0.04111, over 1424090.75 frames.], batch size: 23, lr: 5.18e-04
2022-05-14 17:15:42,314 INFO [train.py:812] (4/8) Epoch 15, batch 1700, loss[loss=0.1679, simple_loss=0.2547, pruned_loss=0.04056, over 7304.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2574, pruned_loss=0.04064, over 1427695.09 frames.], batch size: 25, lr: 5.18e-04
2022-05-14 17:16:41,867 INFO [train.py:812] (4/8) Epoch 15, batch 1750, loss[loss=0.1972, simple_loss=0.2896, pruned_loss=0.05245, over 7069.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2575, pruned_loss=0.04081, over 1430510.69 frames.], batch size: 28, lr: 5.18e-04
2022-05-14 17:17:41,423 INFO [train.py:812] (4/8) Epoch 15, batch 1800, loss[loss=0.1395, simple_loss=0.2176, pruned_loss=0.0307, over 7280.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2581, pruned_loss=0.0413, over 1428027.54 frames.], batch size: 17, lr: 5.17e-04
2022-05-14 17:18:41,018 INFO [train.py:812] (4/8) Epoch 15, batch 1850, loss[loss=0.1477, simple_loss=0.2404, pruned_loss=0.0275, over 7148.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2586, pruned_loss=0.04112, over 1432297.32 frames.], batch size: 18, lr: 5.17e-04
2022-05-14 17:19:40,982 INFO [train.py:812] (4/8) Epoch 15, batch 1900, loss[loss=0.2, simple_loss=0.2903, pruned_loss=0.0548, over 7103.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2582, pruned_loss=0.04095, over 1431679.01 frames.], batch size: 21, lr: 5.17e-04
2022-05-14 17:20:40,328 INFO [train.py:812] (4/8) Epoch 15, batch 1950, loss[loss=0.1894, simple_loss=0.2706, pruned_loss=0.05413, over 7269.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2583, pruned_loss=0.04109, over 1431506.01 frames.], batch size: 18, lr: 5.17e-04
2022-05-14 17:21:39,014 INFO [train.py:812] (4/8) Epoch 15, batch 2000, loss[loss=0.1575, simple_loss=0.2524, pruned_loss=0.03135, over 6477.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2586, pruned_loss=0.04106, over 1427057.67 frames.], batch size: 37, lr: 5.17e-04
2022-05-14 17:22:38,284 INFO [train.py:812] (4/8) Epoch 15, batch 2050, loss[loss=0.1798, simple_loss=0.2609, pruned_loss=0.04936, over 7327.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2582, pruned_loss=0.04065, over 1429266.34 frames.], batch size: 25, lr: 5.16e-04
2022-05-14 17:23:37,391 INFO [train.py:812] (4/8) Epoch 15, batch 2100, loss[loss=0.1472, simple_loss=0.2342, pruned_loss=0.03011, over 7403.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2581, pruned_loss=0.04103, over 1422676.24 frames.], batch size: 18, lr: 5.16e-04
2022-05-14 17:24:36,098 INFO [train.py:812] (4/8) Epoch 15, batch 2150, loss[loss=0.1766, simple_loss=0.2647, pruned_loss=0.04421, over 7220.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2578, pruned_loss=0.04085, over 1420072.93 frames.], batch size: 22, lr: 5.16e-04
2022-05-14 17:25:35,469 INFO [train.py:812] (4/8) Epoch 15, batch 2200, loss[loss=0.176, simple_loss=0.2626, pruned_loss=0.04474, over 7438.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2583, pruned_loss=0.04106, over 1420519.98 frames.], batch size: 20, lr: 5.16e-04
2022-05-14 17:26:33,940 INFO [train.py:812] (4/8) Epoch 15, batch 2250, loss[loss=0.1884, simple_loss=0.2796, pruned_loss=0.04856, over 7054.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2583, pruned_loss=0.04108, over 1421352.73 frames.], batch size: 28, lr: 5.16e-04
2022-05-14 17:27:32,338 INFO [train.py:812] (4/8) Epoch 15, batch 2300, loss[loss=0.1645, simple_loss=0.2435, pruned_loss=0.04277, over 7277.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2586, pruned_loss=0.04101, over 1421783.69 frames.], batch size: 16, lr: 5.15e-04
2022-05-14 17:28:30,797 INFO [train.py:812] (4/8) Epoch 15, batch 2350, loss[loss=0.1326, simple_loss=0.2128, pruned_loss=0.02618, over 7414.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2581, pruned_loss=0.04071, over 1424839.95 frames.], batch size: 18, lr: 5.15e-04
2022-05-14 17:29:30,878 INFO [train.py:812] (4/8) Epoch 15, batch 2400, loss[loss=0.1533, simple_loss=0.2294, pruned_loss=0.03866, over 7410.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2599, pruned_loss=0.0416, over 1422349.52 frames.], batch size: 18, lr: 5.15e-04
2022-05-14 17:30:30,104 INFO [train.py:812] (4/8) Epoch 15, batch 2450, loss[loss=0.1635, simple_loss=0.259, pruned_loss=0.03403, over 7412.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2599, pruned_loss=0.04164, over 1423622.97 frames.], batch size: 21, lr: 5.15e-04
2022-05-14 17:31:29,568 INFO [train.py:812] (4/8) Epoch 15, batch 2500, loss[loss=0.1958, simple_loss=0.2875, pruned_loss=0.05207, over 7325.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2606, pruned_loss=0.04155, over 1424775.35 frames.], batch size: 21, lr: 5.15e-04
2022-05-14 17:32:27,888 INFO [train.py:812] (4/8) Epoch 15, batch 2550, loss[loss=0.1484, simple_loss=0.2356, pruned_loss=0.03058, over 7175.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2606, pruned_loss=0.04177, over 1427733.42 frames.], batch size: 18, lr: 5.14e-04
2022-05-14 17:33:27,554 INFO [train.py:812] (4/8) Epoch 15, batch 2600, loss[loss=0.2012, simple_loss=0.2838, pruned_loss=0.05928, over 7215.00 frames.], tot_loss[loss=0.1735, simple_loss=0.262, pruned_loss=0.04249, over 1421837.16 frames.], batch size: 23, lr: 5.14e-04
2022-05-14 17:34:25,789 INFO [train.py:812] (4/8) Epoch 15, batch 2650, loss[loss=0.18, simple_loss=0.2714, pruned_loss=0.04431, over 7289.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2611, pruned_loss=0.04189, over 1422591.21 frames.], batch size: 25, lr: 5.14e-04
2022-05-14 17:35:25,148 INFO [train.py:812] (4/8) Epoch 15, batch 2700, loss[loss=0.1481, simple_loss=0.242, pruned_loss=0.02712, over 7308.00 frames.], tot_loss[loss=0.1722, simple_loss=0.261, pruned_loss=0.04166, over 1424526.31 frames.], batch size: 21, lr: 5.14e-04
2022-05-14 17:36:24,199 INFO [train.py:812] (4/8) Epoch 15, batch 2750, loss[loss=0.165, simple_loss=0.2553, pruned_loss=0.0374, over 7288.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2605, pruned_loss=0.04161, over 1424109.52 frames.], batch size: 24, lr: 5.14e-04
2022-05-14 17:37:23,465 INFO [train.py:812] (4/8) Epoch 15, batch 2800, loss[loss=0.1638, simple_loss=0.2567, pruned_loss=0.0355, over 7143.00 frames.], tot_loss[loss=0.171, simple_loss=0.2598, pruned_loss=0.04113, over 1427273.35 frames.], batch size: 20, lr: 5.14e-04
2022-05-14 17:38:20,797 INFO [train.py:812] (4/8) Epoch 15, batch 2850, loss[loss=0.1777, simple_loss=0.2673, pruned_loss=0.04403, over 7194.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2597, pruned_loss=0.04098, over 1428358.85 frames.], batch size: 16, lr: 5.13e-04
2022-05-14 17:39:21,016 INFO [train.py:812] (4/8) Epoch 15, batch 2900, loss[loss=0.1878, simple_loss=0.2799, pruned_loss=0.04782, over 7412.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2601, pruned_loss=0.04161, over 1424487.07 frames.], batch size: 23, lr: 5.13e-04
2022-05-14 17:40:20,010 INFO [train.py:812] (4/8) Epoch 15, batch 2950, loss[loss=0.1853, simple_loss=0.268, pruned_loss=0.0513, over 7436.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2597, pruned_loss=0.04156, over 1424446.43 frames.], batch size: 20, lr: 5.13e-04
2022-05-14 17:41:19,153 INFO [train.py:812] (4/8) Epoch 15, batch 3000, loss[loss=0.1644, simple_loss=0.2574, pruned_loss=0.03567, over 7154.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2595, pruned_loss=0.0414, over 1423377.62 frames.], batch size: 19, lr: 5.13e-04
2022-05-14 17:41:19,154 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 17:41:26,768 INFO [train.py:841] (4/8) Epoch 15, validation: loss=0.1543, simple_loss=0.2544, pruned_loss=0.02713, over 698248.00 frames.
2022-05-14 17:42:25,640 INFO [train.py:812] (4/8) Epoch 15, batch 3050, loss[loss=0.1397, simple_loss=0.2279, pruned_loss=0.02576, over 7215.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2589, pruned_loss=0.04095, over 1426147.09 frames.], batch size: 16, lr: 5.13e-04
2022-05-14 17:43:23,118 INFO [train.py:812] (4/8) Epoch 15, batch 3100, loss[loss=0.1571, simple_loss=0.2476, pruned_loss=0.0333, over 7325.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2596, pruned_loss=0.04113, over 1421723.05 frames.], batch size: 20, lr: 5.12e-04
2022-05-14 17:44:21,950 INFO [train.py:812] (4/8) Epoch 15, batch 3150, loss[loss=0.1683, simple_loss=0.2391, pruned_loss=0.0487, over 7286.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2588, pruned_loss=0.04107, over 1426906.60 frames.], batch size: 17, lr: 5.12e-04
2022-05-14 17:45:20,568 INFO [train.py:812] (4/8) Epoch 15, batch 3200, loss[loss=0.1748, simple_loss=0.266, pruned_loss=0.04181, over 7126.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2589, pruned_loss=0.04144, over 1427429.98 frames.], batch size: 28, lr: 5.12e-04
2022-05-14 17:46:20,194 INFO [train.py:812] (4/8) Epoch 15, batch 3250, loss[loss=0.158, simple_loss=0.253, pruned_loss=0.03149, over 7052.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2581, pruned_loss=0.04107, over 1427774.18 frames.], batch size: 18, lr: 5.12e-04
2022-05-14 17:47:18,745 INFO [train.py:812] (4/8) Epoch 15, batch 3300, loss[loss=0.1415, simple_loss=0.2189, pruned_loss=0.03212, over 7284.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2575, pruned_loss=0.04096, over 1426479.06 frames.], batch size: 17, lr: 5.12e-04
2022-05-14 17:48:17,421 INFO [train.py:812] (4/8) Epoch 15, batch 3350, loss[loss=0.1856, simple_loss=0.2721, pruned_loss=0.04952, over 7203.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2591, pruned_loss=0.04131, over 1426251.59 frames.], batch size: 23, lr: 5.11e-04
2022-05-14 17:49:14,695 INFO [train.py:812] (4/8) Epoch 15, batch 3400, loss[loss=0.1785, simple_loss=0.2739, pruned_loss=0.04155, over 7236.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2602, pruned_loss=0.04155, over 1422454.90 frames.], batch size: 21, lr: 5.11e-04
2022-05-14 17:50:13,360 INFO [train.py:812] (4/8) Epoch 15, batch 3450, loss[loss=0.1877, simple_loss=0.2769, pruned_loss=0.0492, over 7032.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2607, pruned_loss=0.04177, over 1420009.17 frames.], batch size: 28, lr: 5.11e-04
2022-05-14 17:51:13,185 INFO [train.py:812] (4/8) Epoch 15, batch 3500, loss[loss=0.2019, simple_loss=0.2864, pruned_loss=0.05871, over 7163.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2595, pruned_loss=0.04132, over 1425130.17 frames.], batch size: 26, lr: 5.11e-04
2022-05-14 17:52:12,821 INFO [train.py:812] (4/8) Epoch 15, batch 3550, loss[loss=0.1726, simple_loss=0.2594, pruned_loss=0.04285, over 7238.00 frames.], tot_loss[loss=0.1708, simple_loss=0.259, pruned_loss=0.04128, over 1426865.74 frames.], batch size: 20, lr: 5.11e-04
2022-05-14 17:53:11,373 INFO [train.py:812] (4/8) Epoch 15, batch 3600, loss[loss=0.1919, simple_loss=0.2761, pruned_loss=0.05382, over 7314.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2588, pruned_loss=0.04121, over 1423131.29 frames.], batch size: 21, lr: 5.11e-04
2022-05-14 17:54:10,563 INFO [train.py:812] (4/8) Epoch 15, batch 3650, loss[loss=0.1803, simple_loss=0.2772, pruned_loss=0.04174, over 7256.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2585, pruned_loss=0.04092, over 1424227.02 frames.], batch size: 19, lr: 5.10e-04
2022-05-14 17:55:10,189 INFO [train.py:812] (4/8) Epoch 15, batch 3700, loss[loss=0.1568, simple_loss=0.2462, pruned_loss=0.0337, over 7426.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2592, pruned_loss=0.04088, over 1420641.44 frames.], batch size: 20, lr: 5.10e-04
2022-05-14 17:56:09,470 INFO [train.py:812] (4/8) Epoch 15, batch 3750, loss[loss=0.1836, simple_loss=0.2695, pruned_loss=0.04883, over 4899.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2584, pruned_loss=0.04048, over 1422716.55 frames.], batch size: 52, lr: 5.10e-04
2022-05-14 17:57:14,308 INFO [train.py:812] (4/8) Epoch 15, batch 3800, loss[loss=0.1478, simple_loss=0.233, pruned_loss=0.0313, over 7056.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2585, pruned_loss=0.04016, over 1424891.84 frames.], batch size: 18, lr: 5.10e-04
2022-05-14 17:58:12,037 INFO [train.py:812] (4/8) Epoch 15, batch 3850, loss[loss=0.1963, simple_loss=0.2879, pruned_loss=0.05231, over 7243.00 frames.], tot_loss[loss=0.17, simple_loss=0.2593, pruned_loss=0.04039, over 1427642.01 frames.], batch size: 20, lr: 5.10e-04
2022-05-14 17:59:11,795 INFO [train.py:812] (4/8) Epoch 15, batch 3900, loss[loss=0.1391, simple_loss=0.2231, pruned_loss=0.02754, over 7264.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2582, pruned_loss=0.04015, over 1425552.69 frames.], batch size: 19, lr: 5.09e-04
2022-05-14 18:00:10,980 INFO [train.py:812] (4/8) Epoch 15, batch 3950, loss[loss=0.203, simple_loss=0.2953, pruned_loss=0.05533, over 7357.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2579, pruned_loss=0.04017, over 1421590.36 frames.], batch size: 19, lr: 5.09e-04
2022-05-14 18:01:10,519 INFO [train.py:812] (4/8) Epoch 15, batch 4000, loss[loss=0.1878, simple_loss=0.284, pruned_loss=0.04584, over 7216.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2585, pruned_loss=0.04051, over 1421871.66 frames.], batch size: 21, lr: 5.09e-04
2022-05-14 18:02:09,523 INFO [train.py:812] (4/8) Epoch 15, batch 4050, loss[loss=0.1759, simple_loss=0.2779, pruned_loss=0.037, over 7217.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2592, pruned_loss=0.04053, over 1426139.54 frames.], batch size: 21, lr: 5.09e-04
2022-05-14 18:03:08,715 INFO [train.py:812] (4/8) Epoch 15, batch 4100, loss[loss=0.1963, simple_loss=0.2909, pruned_loss=0.05082, over 7190.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2594, pruned_loss=0.04068, over 1416397.61 frames.], batch size: 23, lr: 5.09e-04
2022-05-14 18:04:07,539 INFO [train.py:812] (4/8) Epoch 15, batch 4150, loss[loss=0.21, simple_loss=0.2849, pruned_loss=0.0675, over 5052.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2599, pruned_loss=0.04113, over 1410915.42 frames.], batch size: 53, lr: 5.08e-04
2022-05-14 18:05:07,019 INFO [train.py:812] (4/8) Epoch 15, batch 4200, loss[loss=0.1476, simple_loss=0.2351, pruned_loss=0.03003, over 7232.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2585, pruned_loss=0.04125, over 1410738.85 frames.], batch size: 20, lr: 5.08e-04
2022-05-14 18:06:05,960 INFO [train.py:812] (4/8) Epoch 15, batch 4250, loss[loss=0.1442, simple_loss=0.228, pruned_loss=0.03023, over 7067.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2589, pruned_loss=0.0415, over 1408917.45 frames.], batch size: 18, lr: 5.08e-04
2022-05-14 18:07:05,136 INFO [train.py:812] (4/8) Epoch 15, batch 4300, loss[loss=0.1408, simple_loss=0.2214, pruned_loss=0.03005, over 6751.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2589, pruned_loss=0.04147, over 1403738.02 frames.], batch size: 15, lr: 5.08e-04
2022-05-14 18:08:04,069 INFO [train.py:812] (4/8) Epoch 15, batch 4350, loss[loss=0.1725, simple_loss=0.2684, pruned_loss=0.03826, over 7319.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2591, pruned_loss=0.04126, over 1407638.14 frames.], batch size: 21, lr: 5.08e-04
2022-05-14 18:09:03,505 INFO [train.py:812] (4/8) Epoch 15, batch 4400, loss[loss=0.1614, simple_loss=0.2664, pruned_loss=0.02817, over 7165.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2579, pruned_loss=0.0405, over 1410905.82 frames.], batch size: 19, lr: 5.08e-04
2022-05-14 18:10:02,438 INFO [train.py:812] (4/8) Epoch 15, batch 4450, loss[loss=0.1789, simple_loss=0.2612, pruned_loss=0.04829, over 7169.00 frames.], tot_loss[loss=0.1694, simple_loss=0.257, pruned_loss=0.04088, over 1402648.86 frames.], batch size: 18, lr: 5.07e-04
2022-05-14 18:11:01,293 INFO [train.py:812] (4/8) Epoch 15, batch 4500, loss[loss=0.1519, simple_loss=0.2368, pruned_loss=0.03353, over 7058.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2574, pruned_loss=0.04109, over 1394431.54 frames.], batch size: 18, lr: 5.07e-04
2022-05-14 18:11:59,586 INFO [train.py:812] (4/8) Epoch 15, batch 4550, loss[loss=0.2532, simple_loss=0.334, pruned_loss=0.08617, over 4799.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2589, pruned_loss=0.04211, over 1366698.80 frames.], batch size: 52, lr: 5.07e-04
2022-05-14 18:13:08,747 INFO [train.py:812] (4/8) Epoch 16, batch 0, loss[loss=0.1943, simple_loss=0.2854, pruned_loss=0.05159, over 7290.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2854, pruned_loss=0.05159, over 7290.00 frames.], batch size: 24, lr: 4.92e-04
2022-05-14 18:14:07,992 INFO [train.py:812] (4/8) Epoch 16, batch 50, loss[loss=0.1341, simple_loss=0.2236, pruned_loss=0.02236, over 7413.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2566, pruned_loss=0.03945, over 321012.42 frames.], batch size: 18, lr: 4.92e-04
2022-05-14 18:15:07,117 INFO [train.py:812] (4/8) Epoch 16, batch 100, loss[loss=0.1695, simple_loss=0.2576, pruned_loss=0.04073, over 7316.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2561, pruned_loss=0.0399, over 563694.52 frames.], batch size: 20, lr: 4.92e-04
2022-05-14 18:16:06,276 INFO [train.py:812] (4/8) Epoch 16, batch 150, loss[loss=0.2026, simple_loss=0.2838, pruned_loss=0.06069, over 7154.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2572, pruned_loss=0.04084, over 754035.99 frames.], batch size: 20, lr: 4.92e-04
2022-05-14 18:17:15,044 INFO [train.py:812] (4/8) Epoch 16, batch 200, loss[loss=0.1958, simple_loss=0.2733, pruned_loss=0.05917, over 7125.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2564, pruned_loss=0.04043, over 897138.27 frames.], batch size: 21, lr: 4.91e-04
2022-05-14 18:18:13,084 INFO [train.py:812] (4/8) Epoch 16, batch 250, loss[loss=0.169, simple_loss=0.2466, pruned_loss=0.04564, over 7159.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2565, pruned_loss=0.03986, over 1013587.28 frames.], batch size: 19, lr: 4.91e-04
2022-05-14 18:19:12,325 INFO [train.py:812] (4/8) Epoch 16, batch 300, loss[loss=0.1424, simple_loss=0.2246, pruned_loss=0.03013, over 7162.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2559, pruned_loss=0.03957, over 1108233.83 frames.], batch size: 19, lr: 4.91e-04
2022-05-14 18:20:11,385 INFO [train.py:812] (4/8) Epoch 16, batch 350, loss[loss=0.1478, simple_loss=0.2386, pruned_loss=0.0285, over 7267.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2561, pruned_loss=0.03922, over 1179531.45 frames.], batch size: 18, lr: 4.91e-04
2022-05-14 18:21:11,292 INFO [train.py:812] (4/8) Epoch 16, batch 400, loss[loss=0.1554, simple_loss=0.2501, pruned_loss=0.03038, over 7259.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2575, pruned_loss=0.03965, over 1233446.30 frames.], batch size: 19, lr: 4.91e-04
2022-05-14 18:22:10,137 INFO [train.py:812] (4/8) Epoch 16, batch 450, loss[loss=0.148, simple_loss=0.236, pruned_loss=0.03002, over 7425.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2579, pruned_loss=0.03986, over 1281482.43 frames.], batch size: 20, lr: 4.91e-04
2022-05-14 18:23:09,255 INFO [train.py:812] (4/8) Epoch 16, batch 500, loss[loss=0.1796, simple_loss=0.2653, pruned_loss=0.04701, over 7178.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2589, pruned_loss=0.04018, over 1318162.93 frames.], batch size: 23, lr: 4.90e-04
2022-05-14 18:24:07,722 INFO [train.py:812] (4/8) Epoch 16, batch 550, loss[loss=0.1457, simple_loss=0.2305, pruned_loss=0.03045, over 7279.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2578, pruned_loss=0.03975, over 1345214.04 frames.], batch size: 18, lr: 4.90e-04
2022-05-14 18:25:07,654 INFO [train.py:812] (4/8) Epoch 16, batch 600, loss[loss=0.1527, simple_loss=0.2396, pruned_loss=0.03291, over 7171.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2563, pruned_loss=0.03907, over 1361525.44 frames.], batch size: 19, lr: 4.90e-04
2022-05-14 18:26:06,740 INFO [train.py:812] (4/8) Epoch 16, batch 650, loss[loss=0.1534, simple_loss=0.256, pruned_loss=0.02539, over 6285.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2561, pruned_loss=0.03911, over 1373308.13 frames.], batch size: 37, lr: 4.90e-04
2022-05-14 18:27:05,468 INFO [train.py:812] (4/8) Epoch 16, batch 700, loss[loss=0.1656, simple_loss=0.2598, pruned_loss=0.03572, over 7180.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2561, pruned_loss=0.03947, over 1385353.18 frames.], batch size: 28, lr: 4.90e-04
2022-05-14 18:28:04,354 INFO [train.py:812] (4/8) Epoch 16, batch 750, loss[loss=0.1375, simple_loss=0.2231, pruned_loss=0.02598, over 7162.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2562, pruned_loss=0.03941, over 1394377.17 frames.], batch size: 19, lr: 4.89e-04
2022-05-14 18:29:03,814 INFO [train.py:812] (4/8) Epoch 16, batch 800, loss[loss=0.1628, simple_loss=0.2474, pruned_loss=0.03907, over 7264.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2564, pruned_loss=0.03941, over 1402061.34 frames.], batch size: 19, lr: 4.89e-04
2022-05-14 18:30:02,510 INFO [train.py:812] (4/8) Epoch 16, batch 850, loss[loss=0.1409, simple_loss=0.2453, pruned_loss=0.0182, over 7148.00 frames.], tot_loss[loss=0.168, simple_loss=0.2569, pruned_loss=0.03958, over 1405079.44 frames.], batch size: 20, lr: 4.89e-04
2022-05-14 18:31:02,368 INFO [train.py:812] (4/8) Epoch 16, batch 900, loss[loss=0.1344, simple_loss=0.2216, pruned_loss=0.02359, over 7370.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2571, pruned_loss=0.03977, over 1403678.88 frames.], batch size: 19, lr: 4.89e-04
2022-05-14 18:32:01,914 INFO [train.py:812] (4/8) Epoch 16, batch 950, loss[loss=0.1717, simple_loss=0.2549, pruned_loss=0.04429, over 7426.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2565, pruned_loss=0.03991, over 1406519.31 frames.], batch size: 20, lr: 4.89e-04
2022-05-14 18:33:00,783 INFO [train.py:812] (4/8) Epoch 16, batch 1000, loss[loss=0.1865, simple_loss=0.2762, pruned_loss=0.04834, over 7294.00 frames.], tot_loss[loss=0.1677, simple_loss=0.256, pruned_loss=0.03963, over 1411903.48 frames.], batch size: 25, lr: 4.89e-04
2022-05-14 18:33:59,600 INFO [train.py:812] (4/8) Epoch 16, batch 1050, loss[loss=0.1656, simple_loss=0.2522, pruned_loss=0.03944, over 7337.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2566, pruned_loss=0.03977, over 1417360.78 frames.], batch size: 20, lr: 4.88e-04
2022-05-14 18:34:59,558 INFO [train.py:812] (4/8) Epoch 16, batch 1100, loss[loss=0.197, simple_loss=0.2747, pruned_loss=0.05967, over 7352.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2567, pruned_loss=0.03977, over 1421507.79 frames.], batch size: 19, lr: 4.88e-04
2022-05-14 18:35:59,304 INFO [train.py:812] (4/8) Epoch 16, batch 1150, loss[loss=0.2019, simple_loss=0.2881, pruned_loss=0.05784, over 5001.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2558, pruned_loss=0.03948, over 1421620.33 frames.], batch size: 52, lr: 4.88e-04
2022-05-14 18:36:59,225 INFO [train.py:812] (4/8) Epoch 16, batch 1200, loss[loss=0.1781, simple_loss=0.2727, pruned_loss=0.04173, over 7125.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2555, pruned_loss=0.03933, over 1419283.29 frames.], batch size: 21, lr: 4.88e-04
2022-05-14 18:37:58,847 INFO [train.py:812] (4/8) Epoch 16, batch 1250, loss[loss=0.1351, simple_loss=0.222, pruned_loss=0.0241, over 6803.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2549, pruned_loss=0.0392, over 1419527.76 frames.], batch size: 15, lr: 4.88e-04
2022-05-14 18:38:58,784 INFO [train.py:812] (4/8) Epoch 16, batch 1300, loss[loss=0.1856, simple_loss=0.2779, pruned_loss=0.04663, over 7204.00 frames.], tot_loss[loss=0.1675, simple_loss=0.256, pruned_loss=0.03952, over 1425469.82 frames.], batch size: 22, lr: 4.88e-04
2022-05-14 18:39:58,305 INFO [train.py:812] (4/8) Epoch 16, batch 1350, loss[loss=0.149, simple_loss=0.2454, pruned_loss=0.02629, over 7157.00 frames.], tot_loss[loss=0.1685, simple_loss=0.257, pruned_loss=0.04003, over 1418599.81 frames.], batch size: 19, lr: 4.87e-04
2022-05-14 18:40:58,007 INFO [train.py:812] (4/8) Epoch 16, batch 1400, loss[loss=0.1768, simple_loss=0.2644, pruned_loss=0.04459, over 7318.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2572, pruned_loss=0.04002, over 1417320.29 frames.], batch size: 22, lr: 4.87e-04
2022-05-14 18:41:57,519 INFO [train.py:812] (4/8) Epoch 16, batch 1450, loss[loss=0.1908, simple_loss=0.2796, pruned_loss=0.05098, over 7421.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2568, pruned_loss=0.0394, over 1423017.23 frames.], batch size: 21, lr: 4.87e-04
2022-05-14 18:43:06,576 INFO [train.py:812] (4/8) Epoch 16, batch 1500, loss[loss=0.1696, simple_loss=0.2591, pruned_loss=0.04001, over 7205.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2569, pruned_loss=0.03942, over 1422406.57 frames.], batch size: 23, lr: 4.87e-04
2022-05-14 18:44:06,049 INFO [train.py:812] (4/8) Epoch 16, batch 1550, loss[loss=0.1265, simple_loss=0.2099, pruned_loss=0.02155, over 6758.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2566, pruned_loss=0.0395, over 1419485.95 frames.], batch size: 15, lr: 4.87e-04
2022-05-14 18:45:05,963 INFO [train.py:812] (4/8) Epoch 16, batch 1600, loss[loss=0.1594, simple_loss=0.2483, pruned_loss=0.03528, over 6826.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2571, pruned_loss=0.03992, over 1421874.49 frames.], batch size: 15, lr: 4.87e-04
2022-05-14 18:46:05,459 INFO [train.py:812] (4/8) Epoch 16, batch 1650, loss[loss=0.1509, simple_loss=0.2396, pruned_loss=0.03109, over 7147.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2572, pruned_loss=0.0399, over 1423610.27 frames.], batch size: 20, lr: 4.86e-04
2022-05-14 18:47:14,895 INFO [train.py:812] (4/8) Epoch 16, batch 1700, loss[loss=0.1845, simple_loss=0.2663, pruned_loss=0.05133, over 7419.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2566, pruned_loss=0.03933, over 1423918.91 frames.], batch size: 18, lr: 4.86e-04
2022-05-14 18:48:31,550 INFO [train.py:812] (4/8) Epoch 16, batch 1750, loss[loss=0.1667, simple_loss=0.2605, pruned_loss=0.03641, over 7387.00 frames.], tot_loss[loss=0.169, simple_loss=0.258, pruned_loss=0.04005, over 1423694.42 frames.], batch size: 23, lr: 4.86e-04
2022-05-14 18:49:49,344 INFO [train.py:812] (4/8) Epoch 16, batch 1800, loss[loss=0.1345, simple_loss=0.2219, pruned_loss=0.02354, over 7360.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2581, pruned_loss=0.04004, over 1422609.32 frames.], batch size: 19, lr: 4.86e-04
2022-05-14 18:50:57,663 INFO [train.py:812] (4/8) Epoch 16, batch 1850, loss[loss=0.1774, simple_loss=0.2777, pruned_loss=0.03853, over 7151.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2573, pruned_loss=0.03973, over 1424978.98 frames.], batch size: 20, lr: 4.86e-04
2022-05-14 18:51:57,514 INFO [train.py:812] (4/8) Epoch 16, batch 1900, loss[loss=0.2154, simple_loss=0.3001, pruned_loss=0.06532, over 7297.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2572, pruned_loss=0.04005, over 1429452.01 frames.], batch size: 25, lr: 4.86e-04
2022-05-14 18:52:55,104 INFO [train.py:812] (4/8) Epoch 16, batch 1950, loss[loss=0.1736, simple_loss=0.2709, pruned_loss=0.03811, over 7217.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2576, pruned_loss=0.03997, over 1430626.73 frames.], batch size: 23, lr: 4.85e-04
2022-05-14 18:53:54,404 INFO [train.py:812] (4/8) Epoch 16, batch 2000, loss[loss=0.2448, simple_loss=0.3125, pruned_loss=0.08856, over 5165.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2579, pruned_loss=0.03987, over 1423111.79 frames.], batch size: 52, lr: 4.85e-04
2022-05-14 18:54:53,354 INFO [train.py:812] (4/8) Epoch 16, batch 2050, loss[loss=0.1817, simple_loss=0.2774, pruned_loss=0.04296, over 6270.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2589, pruned_loss=0.04034, over 1421670.06 frames.], batch size: 37, lr: 4.85e-04
2022-05-14 18:55:52,718 INFO [train.py:812] (4/8) Epoch 16, batch 2100, loss[loss=0.179, simple_loss=0.2702, pruned_loss=0.04392, over 7104.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2594, pruned_loss=0.04025, over 1423093.56 frames.], batch size: 21, lr: 4.85e-04
2022-05-14 18:56:51,656 INFO [train.py:812] (4/8) Epoch 16, batch 2150, loss[loss=0.1678, simple_loss=0.2596, pruned_loss=0.03796, over 7250.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2597, pruned_loss=0.04029, over 1418547.80 frames.], batch size: 19, lr: 4.85e-04
2022-05-14 18:57:50,994 INFO [train.py:812] (4/8) Epoch 16, batch 2200, loss[loss=0.1809, simple_loss=0.2746, pruned_loss=0.04361, over 7202.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2593, pruned_loss=0.03992, over 1415984.31 frames.], batch size: 22, lr: 4.84e-04
2022-05-14 18:58:50,184 INFO [train.py:812] (4/8) Epoch 16, batch 2250, loss[loss=0.2018, simple_loss=0.293, pruned_loss=0.0553, over 7412.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2592, pruned_loss=0.04027, over 1417630.48 frames.], batch size: 21, lr: 4.84e-04
2022-05-14 18:59:49,556 INFO [train.py:812] (4/8) Epoch 16, batch 2300, loss[loss=0.1872, simple_loss=0.2727, pruned_loss=0.05087, over 7210.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2587, pruned_loss=0.03988, over 1419032.49 frames.], batch size: 23, lr: 4.84e-04
2022-05-14 19:00:48,681 INFO [train.py:812] (4/8) Epoch 16, batch 2350, loss[loss=0.2144, simple_loss=0.2998, pruned_loss=0.06452, over 7292.00 frames.], tot_loss[loss=0.1685, simple_loss=0.258, pruned_loss=0.03947, over 1421659.50 frames.], batch size: 25, lr: 4.84e-04
2022-05-14 19:01:48,352 INFO [train.py:812] (4/8) Epoch 16, batch 2400, loss[loss=0.1975, simple_loss=0.2859, pruned_loss=0.05454, over 7316.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2576, pruned_loss=0.0398, over 1425648.81 frames.], batch size: 25, lr: 4.84e-04
2022-05-14 19:02:47,252 INFO [train.py:812] (4/8) Epoch 16, batch 2450, loss[loss=0.1835, simple_loss=0.2714, pruned_loss=0.04777, over 6767.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2578, pruned_loss=0.03972, over 1423847.92 frames.], batch size: 31, lr: 4.84e-04
2022-05-14 19:03:46,835 INFO [train.py:812] (4/8) Epoch 16, batch 2500, loss[loss=0.1603, simple_loss=0.249, pruned_loss=0.03575, over 7227.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2562, pruned_loss=0.03908, over 1427343.78 frames.], batch size: 21, lr: 4.83e-04
2022-05-14 19:04:46,109 INFO [train.py:812] (4/8) Epoch 16, batch 2550, loss[loss=0.1487, simple_loss=0.2444, pruned_loss=0.02653, over 7150.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2551, pruned_loss=0.03874, over 1424044.40 frames.], batch size: 20, lr: 4.83e-04
2022-05-14 19:05:45,582 INFO [train.py:812] (4/8) Epoch 16, batch 2600, loss[loss=0.1419, simple_loss=0.224, pruned_loss=0.0299, over 7355.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2548, pruned_loss=0.03879, over 1423360.68 frames.], batch size: 19, lr: 4.83e-04
2022-05-14 19:06:45,273 INFO [train.py:812] (4/8) Epoch 16, batch 2650, loss[loss=0.1715, simple_loss=0.2579, pruned_loss=0.04259, over 7363.00 frames.], tot_loss[loss=0.1664, simple_loss=0.255, pruned_loss=0.03887, over 1424208.91 frames.], batch size: 23, lr: 4.83e-04
2022-05-14 19:07:45,173 INFO [train.py:812] (4/8) Epoch 16, batch 2700, loss[loss=0.2038, simple_loss=0.3041, pruned_loss=0.05175, over 7187.00 frames.], tot_loss[loss=0.167, simple_loss=0.2556, pruned_loss=0.03923, over 1421734.17 frames.], batch size: 26, lr: 4.83e-04
2022-05-14 19:08:44,239 INFO [train.py:812] (4/8) Epoch 16, batch 2750, loss[loss=0.1527, simple_loss=0.2356, pruned_loss=0.03495, over 7279.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2564, pruned_loss=0.03951, over 1426484.71 frames.], batch size: 18, lr: 4.83e-04
2022-05-14 19:09:44,119 INFO [train.py:812] (4/8) Epoch 16, batch 2800, loss[loss=0.1629, simple_loss=0.2525, pruned_loss=0.03664, over 7224.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2561, pruned_loss=0.03909, over 1427625.42 frames.], batch size: 21, lr: 4.82e-04
2022-05-14 19:10:43,379 INFO [train.py:812] (4/8) Epoch 16, batch 2850, loss[loss=0.1462, simple_loss=0.2404, pruned_loss=0.02602, over 7177.00 frames.], tot_loss[loss=0.1682, simple_loss=0.257, pruned_loss=0.03969, over 1426475.56 frames.], batch size: 18, lr: 4.82e-04
2022-05-14 19:11:42,829 INFO [train.py:812] (4/8) Epoch 16, batch 2900, loss[loss=0.1528, simple_loss=0.23, pruned_loss=0.03779, over 7162.00 frames.], tot_loss[loss=0.168, simple_loss=0.2569, pruned_loss=0.03957, over 1429137.24 frames.], batch size: 18, lr: 4.82e-04
2022-05-14 19:12:41,622 INFO [train.py:812] (4/8) Epoch 16, batch 2950, loss[loss=0.1712, simple_loss=0.2707, pruned_loss=0.03588, over 7353.00 frames.], tot_loss[loss=0.168, simple_loss=0.2569, pruned_loss=0.03952, over 1425059.03 frames.], batch size: 22, lr: 4.82e-04
2022-05-14 19:13:40,832 INFO [train.py:812] (4/8) Epoch 16, batch 3000, loss[loss=0.1811, simple_loss=0.2764, pruned_loss=0.0429, over 7413.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2574, pruned_loss=0.03968, over 1429060.73 frames.], batch size: 21, lr: 4.82e-04
2022-05-14 19:13:40,833 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 19:13:48,992 INFO [train.py:841] (4/8) Epoch 16, validation: loss=0.1537, simple_loss=0.2535, pruned_loss=0.02695, over 698248.00 frames.
2022-05-14 19:14:47,141 INFO [train.py:812] (4/8) Epoch 16, batch 3050, loss[loss=0.1324, simple_loss=0.2175, pruned_loss=0.02359, over 7403.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2566, pruned_loss=0.03939, over 1427419.60 frames.], batch size: 18, lr: 4.82e-04
2022-05-14 19:15:46,681 INFO [train.py:812] (4/8) Epoch 16, batch 3100, loss[loss=0.2176, simple_loss=0.2935, pruned_loss=0.07088, over 7197.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2566, pruned_loss=0.03986, over 1427281.91 frames.], batch size: 23, lr: 4.81e-04
2022-05-14 19:16:44,971 INFO [train.py:812] (4/8) Epoch 16, batch 3150, loss[loss=0.1902, simple_loss=0.2734, pruned_loss=0.05346, over 7167.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2563, pruned_loss=0.03957, over 1424399.74 frames.], batch size: 18, lr: 4.81e-04
2022-05-14 19:17:47,858 INFO [train.py:812] (4/8) Epoch 16, batch 3200, loss[loss=0.1999, simple_loss=0.2952, pruned_loss=0.05231, over 7282.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2576, pruned_loss=0.0403, over 1424650.01 frames.], batch size: 24, lr: 4.81e-04
2022-05-14 19:18:47,169 INFO [train.py:812] (4/8) Epoch 16, batch 3250, loss[loss=0.1622, simple_loss=0.2541, pruned_loss=0.03515, over 7325.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2568, pruned_loss=0.03954, over 1426277.23 frames.], batch size: 21, lr: 4.81e-04
2022-05-14 19:19:45,412 INFO [train.py:812] (4/8) Epoch 16, batch 3300, loss[loss=0.1939, simple_loss=0.2863, pruned_loss=0.05074, over 7333.00 frames.], tot_loss[loss=0.168, simple_loss=0.2571, pruned_loss=0.03942, over 1430524.70 frames.], batch size: 25, lr: 4.81e-04
2022-05-14 19:20:42,556 INFO [train.py:812] (4/8) Epoch 16, batch 3350, loss[loss=0.1577, simple_loss=0.246, pruned_loss=0.03465, over 7237.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2567, pruned_loss=0.03927, over 1432340.04 frames.], batch size: 20, lr: 4.81e-04
2022-05-14 19:21:41,200 INFO [train.py:812] (4/8) Epoch 16, batch 3400, loss[loss=0.1653, simple_loss=0.2674, pruned_loss=0.03165, over 7070.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2572, pruned_loss=0.03952, over 1429302.94 frames.], batch size: 28, lr: 4.80e-04
2022-05-14 19:22:40,327 INFO [train.py:812] (4/8) Epoch 16, batch 3450, loss[loss=0.1446, simple_loss=0.2277, pruned_loss=0.0308, over 7354.00 frames.], tot_loss[loss=0.1681, simple_loss=0.257, pruned_loss=0.03955, over 1430540.42 frames.], batch size: 19, lr: 4.80e-04
2022-05-14 19:23:40,280 INFO [train.py:812] (4/8) Epoch 16, batch 3500, loss[loss=0.1808, simple_loss=0.2712, pruned_loss=0.04515, over 7321.00 frames.], tot_loss[loss=0.1682, simple_loss=0.257, pruned_loss=0.03969, over 1428937.74 frames.], batch size: 21, lr: 4.80e-04
2022-05-14 19:24:39,220 INFO [train.py:812] (4/8) Epoch 16, batch 3550, loss[loss=0.1896, simple_loss=0.2727, pruned_loss=0.05324, over 7141.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2577, pruned_loss=0.03978, over 1424125.22 frames.], batch size: 26, lr: 4.80e-04
2022-05-14 19:25:38,825 INFO [train.py:812] (4/8) Epoch 16, batch 3600, loss[loss=0.1618, simple_loss=0.261, pruned_loss=0.03129, over 7316.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2572, pruned_loss=0.0393, over 1425814.07 frames.], batch size: 21, lr: 4.80e-04
2022-05-14 19:26:37,924 INFO [train.py:812] (4/8) Epoch 16, batch 3650, loss[loss=0.1596, simple_loss=0.236, pruned_loss=0.04158, over 7278.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2567, pruned_loss=0.0393, over 1425997.58 frames.], batch size: 18, lr: 4.80e-04
2022-05-14 19:27:36,131 INFO [train.py:812] (4/8) Epoch 16, batch 3700, loss[loss=0.1494, simple_loss=0.235, pruned_loss=0.03186, over 6805.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2564, pruned_loss=0.03914, over 1423835.54 frames.], batch size: 15, lr: 4.79e-04
2022-05-14 19:28:35,316 INFO [train.py:812] (4/8) Epoch 16, batch 3750, loss[loss=0.2133, simple_loss=0.3121, pruned_loss=0.05721, over 7278.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2568, pruned_loss=0.03919, over 1420995.12 frames.], batch size: 25, lr: 4.79e-04
2022-05-14 19:29:33,341 INFO [train.py:812] (4/8) Epoch 16, batch 3800, loss[loss=0.159, simple_loss=0.244, pruned_loss=0.03695, over 7134.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2569, pruned_loss=0.03926, over 1425500.65 frames.], batch size: 17, lr: 4.79e-04
2022-05-14 19:30:31,492 INFO [train.py:812] (4/8) Epoch 16, batch 3850, loss[loss=0.1345, simple_loss=0.2277, pruned_loss=0.02068, over 7276.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2572, pruned_loss=0.0395, over 1421346.74 frames.], batch size: 18, lr: 4.79e-04
2022-05-14 19:31:29,711 INFO [train.py:812] (4/8) Epoch 16, batch 3900, loss[loss=0.1777, simple_loss=0.2787, pruned_loss=0.03836, over 7222.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2568, pruned_loss=0.03922, over 1423181.14 frames.], batch size: 21, lr: 4.79e-04
2022-05-14 19:32:28,913 INFO [train.py:812] (4/8) Epoch 16, batch 3950, loss[loss=0.1633, simple_loss=0.258, pruned_loss=0.03427, over 7229.00 frames.], tot_loss[loss=0.1676, simple_loss=0.257, pruned_loss=0.03912, over 1422062.44 frames.], batch size: 20, lr: 4.79e-04
2022-05-14 19:33:27,631 INFO [train.py:812] (4/8) Epoch 16, batch 4000, loss[loss=0.1674, simple_loss=0.2564, pruned_loss=0.03917, over 7324.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2579, pruned_loss=0.03952, over 1419552.55 frames.], batch size: 21, lr: 4.79e-04
2022-05-14 19:34:27,161 INFO [train.py:812] (4/8) Epoch 16, batch 4050, loss[loss=0.1736, simple_loss=0.2506, pruned_loss=0.04826, over 7157.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2579, pruned_loss=0.03974, over 1417413.09 frames.], batch size: 18, lr: 4.78e-04
2022-05-14 19:35:27,342 INFO [train.py:812] (4/8) Epoch 16, batch 4100, loss[loss=0.1536, simple_loss=0.2414, pruned_loss=0.03289, over 7168.00 frames.], tot_loss[loss=0.168, simple_loss=0.257, pruned_loss=0.03952, over 1422723.32 frames.], batch size: 18, lr: 4.78e-04
2022-05-14 19:36:26,214 INFO [train.py:812] (4/8) Epoch 16, batch 4150, loss[loss=0.2158, simple_loss=0.2948, pruned_loss=0.06842, over 6997.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2572, pruned_loss=0.03971, over 1417223.79 frames.], batch size: 28, lr: 4.78e-04
2022-05-14 19:37:25,122 INFO [train.py:812] (4/8) Epoch 16, batch 4200, loss[loss=0.1442, simple_loss=0.2244, pruned_loss=0.03196, over 7005.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2561, pruned_loss=0.03951, over 1416960.11 frames.], batch size: 16, lr: 4.78e-04
2022-05-14 19:38:24,442 INFO [train.py:812] (4/8) Epoch 16, batch 4250, loss[loss=0.1898, simple_loss=0.27, pruned_loss=0.05482, over 7154.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2557, pruned_loss=0.03988, over 1417015.79 frames.], batch size: 18, lr: 4.78e-04
2022-05-14 19:39:23,845 INFO [train.py:812] (4/8) Epoch 16, batch 4300, loss[loss=0.1551, simple_loss=0.245, pruned_loss=0.03259, over 6796.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2551, pruned_loss=0.03964, over 1412862.37 frames.], batch size: 31, lr: 4.78e-04
2022-05-14 19:40:22,733 INFO [train.py:812] (4/8) Epoch 16, batch 4350, loss[loss=0.1399, simple_loss=0.2259, pruned_loss=0.02701, over 7167.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2542, pruned_loss=0.03896, over 1416175.33 frames.], batch size: 18, lr: 4.77e-04
2022-05-14 19:41:21,976 INFO [train.py:812] (4/8) Epoch 16, batch 4400, loss[loss=0.1653, simple_loss=0.2626, pruned_loss=0.03402, over 7116.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2544, pruned_loss=0.03896, over 1416975.44 frames.], batch size: 21, lr: 4.77e-04
2022-05-14 19:42:18,618 INFO [train.py:812] (4/8) Epoch 16, batch 4450, loss[loss=0.1772, simple_loss=0.277, pruned_loss=0.03871, over 7200.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2552, pruned_loss=0.03908, over 1411646.50 frames.], batch size: 22, lr: 4.77e-04
2022-05-14 19:43:16,032 INFO [train.py:812] (4/8) Epoch 16, batch 4500, loss[loss=0.1533, simple_loss=0.2361, pruned_loss=0.03527, over 7126.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2559, pruned_loss=0.03917, over 1402023.88 frames.], batch size: 17, lr: 4.77e-04
2022-05-14 19:44:12,837 INFO [train.py:812] (4/8) Epoch 16, batch 4550, loss[loss=0.1911, simple_loss=0.2732, pruned_loss=0.05447, over 4829.00 frames.], tot_loss[loss=0.171, simple_loss=0.2592, pruned_loss=0.04137, over 1350417.75 frames.], batch size: 52, lr: 4.77e-04
2022-05-14 19:45:27,025 INFO [train.py:812] (4/8) Epoch 17, batch 0, loss[loss=0.194, simple_loss=0.2889, pruned_loss=0.04962, over 7099.00 frames.], tot_loss[loss=0.194, simple_loss=0.2889, pruned_loss=0.04962, over 7099.00 frames.], batch size: 21, lr: 4.63e-04
2022-05-14 19:46:26,099 INFO [train.py:812] (4/8) Epoch 17, batch 50, loss[loss=0.1833, simple_loss=0.2787, pruned_loss=0.04394, over 7317.00 frames.], tot_loss[loss=0.1738, simple_loss=0.264, pruned_loss=0.04183, over 317712.01 frames.], batch size: 21, lr: 4.63e-04
2022-05-14 19:47:25,013 INFO [train.py:812] (4/8) Epoch 17, batch 100, loss[loss=0.1777, simple_loss=0.2678, pruned_loss=0.04375, over 7158.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2584, pruned_loss=0.03935, over 560029.82 frames.], batch size: 20, lr: 4.63e-04
2022-05-14 19:48:23,530 INFO [train.py:812] (4/8) Epoch 17, batch 150, loss[loss=0.1533, simple_loss=0.2341, pruned_loss=0.03622, over 6999.00 frames.], tot_loss[loss=0.1666, simple_loss=0.256, pruned_loss=0.03859, over 747820.24 frames.], batch size: 16, lr: 4.63e-04
2022-05-14 19:49:23,013 INFO [train.py:812] (4/8) Epoch 17, batch 200, loss[loss=0.146, simple_loss=0.2214, pruned_loss=0.03533, over 7139.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2576, pruned_loss=0.03934, over 896524.46 frames.], batch size: 17, lr: 4.63e-04
2022-05-14 19:50:21,377 INFO [train.py:812] (4/8) Epoch 17, batch 250, loss[loss=0.1603, simple_loss=0.2541, pruned_loss=0.03321, over 7252.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2576, pruned_loss=0.03941, over 1016061.64 frames.], batch size: 19, lr: 4.63e-04
2022-05-14 19:51:20,303 INFO [train.py:812] (4/8) Epoch 17, batch 300, loss[loss=0.1739, simple_loss=0.2481, pruned_loss=0.04987, over 7460.00 frames.], tot_loss[loss=0.1683, simple_loss=0.258, pruned_loss=0.03928, over 1101917.74 frames.], batch size: 19, lr: 4.62e-04
2022-05-14 19:52:19,497 INFO [train.py:812] (4/8) Epoch 17, batch 350, loss[loss=0.1573, simple_loss=0.235, pruned_loss=0.03979, over 6819.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2577, pruned_loss=0.03952, over 1172309.52 frames.], batch size: 15, lr: 4.62e-04
2022-05-14 19:53:18,621 INFO [train.py:812] (4/8) Epoch 17, batch 400, loss[loss=0.2056, simple_loss=0.28, pruned_loss=0.06557, over 5264.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2573, pruned_loss=0.03922, over 1228036.77 frames.], batch size: 52, lr: 4.62e-04
2022-05-14 19:54:16,194 INFO [train.py:812] (4/8) Epoch 17, batch 450, loss[loss=0.1717, simple_loss=0.2583, pruned_loss=0.04252, over 7361.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2572, pruned_loss=0.03925, over 1269479.81 frames.], batch size: 19, lr: 4.62e-04
2022-05-14 19:55:14,836 INFO [train.py:812] (4/8) Epoch 17, batch 500, loss[loss=0.147, simple_loss=0.23, pruned_loss=0.03195, over 7169.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2561, pruned_loss=0.03903, over 1302539.27 frames.], batch size: 18, lr: 4.62e-04
2022-05-14 19:56:13,703 INFO [train.py:812] (4/8) Epoch 17, batch 550, loss[loss=0.1601, simple_loss=0.2449, pruned_loss=0.03761, over 7129.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2557, pruned_loss=0.03883, over 1328140.59 frames.], batch size: 17, lr: 4.62e-04
2022-05-14 19:57:12,591 INFO [train.py:812] (4/8) Epoch 17, batch 600, loss[loss=0.1785, simple_loss=0.2757, pruned_loss=0.04069, over 7011.00 frames.], tot_loss[loss=0.167, simple_loss=0.256, pruned_loss=0.03905, over 1343659.10 frames.], batch size: 28, lr: 4.62e-04
2022-05-14 19:58:11,566 INFO [train.py:812] (4/8) Epoch 17, batch 650, loss[loss=0.1795, simple_loss=0.2719, pruned_loss=0.04359, over 7339.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2568, pruned_loss=0.03921, over 1361830.98 frames.], batch size: 20, lr: 4.61e-04
2022-05-14 19:59:10,289 INFO [train.py:812] (4/8) Epoch 17, batch 700, loss[loss=0.1687, simple_loss=0.2503, pruned_loss=0.04354, over 7260.00 frames.], tot_loss[loss=0.1687, simple_loss=0.258, pruned_loss=0.03974, over 1368844.71 frames.], batch size: 19, lr: 4.61e-04
2022-05-14 20:00:09,356 INFO [train.py:812] (4/8) Epoch 17, batch 750, loss[loss=0.1843, simple_loss=0.262, pruned_loss=0.05329, over 7140.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2585, pruned_loss=0.03986, over 1378166.62 frames.], batch size: 20, lr: 4.61e-04
2022-05-14 20:01:08,204 INFO [train.py:812] (4/8) Epoch 17, batch 800, loss[loss=0.1684, simple_loss=0.2596, pruned_loss=0.03861, over 7175.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2583, pruned_loss=0.0393, over 1388607.77 frames.], batch size: 19, lr: 4.61e-04
2022-05-14 20:02:07,167 INFO [train.py:812] (4/8) Epoch 17, batch 850, loss[loss=0.1603, simple_loss=0.2487, pruned_loss=0.0359, over 6318.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2568, pruned_loss=0.03883, over 1396489.28 frames.], batch size: 37, lr: 4.61e-04
2022-05-14 20:03:05,135 INFO [train.py:812] (4/8) Epoch 17, batch 900, loss[loss=0.1807, simple_loss=0.2721, pruned_loss=0.04468, over 7342.00 frames.], tot_loss[loss=0.1672, simple_loss=0.257, pruned_loss=0.03873, over 1407997.39 frames.], batch size: 20, lr: 4.61e-04
2022-05-14 20:04:03,152 INFO [train.py:812] (4/8) Epoch 17, batch 950, loss[loss=0.1315, simple_loss=0.2176, pruned_loss=0.02272, over 7135.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2558, pruned_loss=0.038, over 1412509.40 frames.], batch size: 17, lr: 4.60e-04
2022-05-14 20:05:01,748 INFO [train.py:812] (4/8) Epoch 17, batch 1000, loss[loss=0.1538, simple_loss=0.2514, pruned_loss=0.02803, over 7109.00 frames.], tot_loss[loss=0.166, simple_loss=0.256, pruned_loss=0.03798, over 1417020.40 frames.], batch size: 21, lr: 4.60e-04
2022-05-14 20:06:00,355 INFO [train.py:812] (4/8) Epoch 17, batch 1050, loss[loss=0.162, simple_loss=0.2639, pruned_loss=0.03005, over 7352.00 frames.], tot_loss[loss=0.1653, simple_loss=0.255, pruned_loss=0.03781, over 1421048.69 frames.], batch size: 22, lr: 4.60e-04
2022-05-14 20:06:59,575 INFO [train.py:812] (4/8) Epoch 17, batch 1100, loss[loss=0.1693, simple_loss=0.2623, pruned_loss=0.03814, over 7259.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2555, pruned_loss=0.03804, over 1421190.65 frames.], batch size: 24, lr: 4.60e-04
2022-05-14 20:07:58,271 INFO [train.py:812] (4/8) Epoch 17, batch 1150, loss[loss=0.1711, simple_loss=0.2595, pruned_loss=0.04136, over 7301.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2561, pruned_loss=0.03814, over 1422018.14 frames.], batch size: 24, lr: 4.60e-04
2022-05-14 20:08:57,630 INFO [train.py:812] (4/8) Epoch 17, batch 1200, loss[loss=0.2536, simple_loss=0.3412, pruned_loss=0.08294, over 7284.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2564, pruned_loss=0.0389, over 1419826.61 frames.], batch size: 25, lr: 4.60e-04
2022-05-14 20:09:55,621 INFO [train.py:812] (4/8) Epoch 17, batch 1250, loss[loss=0.1432, simple_loss=0.2254, pruned_loss=0.03045, over 7278.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2578, pruned_loss=0.03939, over 1415593.97 frames.], batch size: 18, lr: 4.60e-04
2022-05-14 20:10:53,531 INFO [train.py:812] (4/8) Epoch 17, batch 1300, loss[loss=0.152, simple_loss=0.2527, pruned_loss=0.02569, over 7341.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2573, pruned_loss=0.03943, over 1414083.23 frames.], batch size: 22, lr: 4.59e-04
2022-05-14 20:11:51,655 INFO [train.py:812] (4/8) Epoch 17, batch 1350, loss[loss=0.1493, simple_loss=0.2445, pruned_loss=0.02708, over 7006.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2561, pruned_loss=0.03872, over 1419480.29 frames.], batch size: 16, lr: 4.59e-04
2022-05-14 20:12:51,098 INFO [train.py:812] (4/8) Epoch 17, batch 1400, loss[loss=0.1712, simple_loss=0.2725, pruned_loss=0.03493, over 7153.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2562, pruned_loss=0.03908, over 1420429.34 frames.], batch size: 20, lr: 4.59e-04
2022-05-14 20:13:49,596 INFO [train.py:812] (4/8) Epoch 17, batch 1450, loss[loss=0.1888, simple_loss=0.2699, pruned_loss=0.05383, over 7344.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2567, pruned_loss=0.03922, over 1418979.59 frames.], batch size: 22, lr: 4.59e-04
2022-05-14 20:14:48,952 INFO [train.py:812] (4/8) Epoch 17, batch 1500, loss[loss=0.1635, simple_loss=0.2562, pruned_loss=0.03544, over 7253.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2557, pruned_loss=0.03897, over 1424562.55 frames.], batch size: 19, lr: 4.59e-04
2022-05-14 20:15:57,362 INFO [train.py:812] (4/8) Epoch 17, batch 1550, loss[loss=0.1767, simple_loss=0.2748, pruned_loss=0.03934, over 7227.00 frames.], tot_loss[loss=0.167, simple_loss=0.256, pruned_loss=0.03898, over 1422573.29 frames.], batch size: 21, lr: 4.59e-04
2022-05-14 20:16:56,751 INFO [train.py:812] (4/8) Epoch 17, batch 1600, loss[loss=0.1463, simple_loss=0.2347, pruned_loss=0.02898, over 7423.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2556, pruned_loss=0.03859, over 1426818.99 frames.], batch size: 20, lr: 4.58e-04
2022-05-14 20:17:55,353 INFO [train.py:812] (4/8) Epoch 17, batch 1650, loss[loss=0.1619, simple_loss=0.2598, pruned_loss=0.03203, over 7406.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2566, pruned_loss=0.03885, over 1428486.94 frames.], batch size: 21, lr: 4.58e-04
2022-05-14 20:18:53,703 INFO [train.py:812] (4/8) Epoch 17, batch 1700, loss[loss=0.2356, simple_loss=0.3045, pruned_loss=0.08341, over 5250.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2572, pruned_loss=0.03914, over 1423064.29 frames.], batch size: 53, lr: 4.58e-04
2022-05-14 20:19:52,402 INFO [train.py:812] (4/8) Epoch 17, batch 1750, loss[loss=0.1788, simple_loss=0.2663, pruned_loss=0.04569, over 7387.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2579, pruned_loss=0.03927, over 1414529.27 frames.], batch size: 23, lr: 4.58e-04
2022-05-14 20:20:51,557 INFO [train.py:812] (4/8) Epoch 17, batch 1800, loss[loss=0.1603, simple_loss=0.2607, pruned_loss=0.02994, over 7216.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2576, pruned_loss=0.03905, over 1415392.71 frames.], batch size: 23, lr: 4.58e-04
2022-05-14 20:21:48,759 INFO [train.py:812] (4/8) Epoch 17, batch 1850, loss[loss=0.1544, simple_loss=0.2496, pruned_loss=0.02959, over 6578.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2574, pruned_loss=0.03862, over 1417001.54 frames.], batch size: 38, lr: 4.58e-04
2022-05-14 20:22:47,373 INFO [train.py:812] (4/8) Epoch 17, batch 1900, loss[loss=0.1572, simple_loss=0.249, pruned_loss=0.03274, over 7435.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2568, pruned_loss=0.03881, over 1421485.16 frames.], batch size: 20, lr: 4.58e-04
2022-05-14 20:23:46,074 INFO [train.py:812] (4/8) Epoch 17, batch 1950, loss[loss=0.1739, simple_loss=0.2638, pruned_loss=0.04204, over 7321.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2561, pruned_loss=0.03862, over 1423240.96 frames.], batch size: 21, lr: 4.57e-04
2022-05-14 20:24:44,622 INFO [train.py:812] (4/8) Epoch 17, batch 2000, loss[loss=0.1495, simple_loss=0.2341, pruned_loss=0.03247, over 7260.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2573, pruned_loss=0.03891, over 1424364.55 frames.], batch size: 19, lr: 4.57e-04
2022-05-14 20:25:43,662 INFO [train.py:812] (4/8) Epoch 17, batch 2050, loss[loss=0.1554, simple_loss=0.2366, pruned_loss=0.03712, over 7424.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2561, pruned_loss=0.03873, over 1427356.58 frames.], batch size: 18, lr: 4.57e-04
2022-05-14 20:26:43,366 INFO [train.py:812] (4/8) Epoch 17, batch 2100, loss[loss=0.1914, simple_loss=0.2855, pruned_loss=0.04864, over 7410.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2562, pruned_loss=0.03857, over 1427830.38 frames.], batch size: 21, lr: 4.57e-04
2022-05-14 20:27:42,668 INFO [train.py:812] (4/8) Epoch 17, batch 2150, loss[loss=0.1494, simple_loss=0.236, pruned_loss=0.03139, over 7358.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2561, pruned_loss=0.0385, over 1423652.13 frames.], batch size: 19, lr: 4.57e-04
2022-05-14 20:28:40,070 INFO [train.py:812] (4/8) Epoch 17, batch 2200, loss[loss=0.17, simple_loss=0.2663, pruned_loss=0.03681, over 7344.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2555, pruned_loss=0.03804, over 1420969.55 frames.], batch size: 22, lr: 4.57e-04
2022-05-14 20:29:39,220 INFO [train.py:812] (4/8) Epoch 17, batch 2250, loss[loss=0.1636, simple_loss=0.2623, pruned_loss=0.03242, over 7414.00 frames.], tot_loss[loss=0.166, simple_loss=0.2558, pruned_loss=0.03806, over 1422979.16 frames.], batch size: 21, lr: 4.56e-04
2022-05-14 20:30:37,973 INFO [train.py:812] (4/8) Epoch 17, batch 2300, loss[loss=0.1946, simple_loss=0.2838, pruned_loss=0.0527, over 7312.00 frames.], tot_loss[loss=0.166, simple_loss=0.2559, pruned_loss=0.03809, over 1422553.58 frames.], batch size: 24, lr: 4.56e-04
2022-05-14 20:31:36,717 INFO [train.py:812] (4/8) Epoch 17, batch 2350, loss[loss=0.1854, simple_loss=0.2674, pruned_loss=0.05164, over 7384.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2555, pruned_loss=0.03801, over 1425879.15 frames.], batch size: 23, lr: 4.56e-04
2022-05-14 20:32:36,103 INFO [train.py:812] (4/8) Epoch 17, batch 2400, loss[loss=0.1556, simple_loss=0.2379, pruned_loss=0.03661, over 6972.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2553, pruned_loss=0.03809, over 1424381.20 frames.], batch size: 16, lr: 4.56e-04
2022-05-14 20:33:34,537 INFO [train.py:812] (4/8) Epoch 17, batch 2450, loss[loss=0.1834, simple_loss=0.2807, pruned_loss=0.04307, over 7340.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2549, pruned_loss=0.03825, over 1424504.41 frames.], batch size: 22, lr: 4.56e-04
2022-05-14 20:34:34,267 INFO [train.py:812] (4/8) Epoch 17, batch 2500, loss[loss=0.1754, simple_loss=0.2635, pruned_loss=0.04363, over 7217.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2533, pruned_loss=0.03771, over 1423753.01 frames.], batch size: 21, lr: 4.56e-04
2022-05-14 20:35:31,574 INFO [train.py:812] (4/8) Epoch 17, batch 2550, loss[loss=0.1554, simple_loss=0.2527, pruned_loss=0.02902, over 7210.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2536, pruned_loss=0.03781, over 1418869.76 frames.], batch size: 21, lr: 4.56e-04
2022-05-14 20:36:37,565 INFO [train.py:812] (4/8) Epoch 17, batch 2600, loss[loss=0.1818, simple_loss=0.2888, pruned_loss=0.03738, over 7067.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2547, pruned_loss=0.03816, over 1421846.64 frames.], batch size: 28, lr: 4.55e-04
2022-05-14 20:37:36,696 INFO [train.py:812] (4/8) Epoch 17, batch 2650, loss[loss=0.15, simple_loss=0.2488, pruned_loss=0.02557, over 7353.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2553, pruned_loss=0.03846, over 1420453.95 frames.], batch size: 19, lr: 4.55e-04
2022-05-14 20:38:34,784 INFO [train.py:812] (4/8) Epoch 17, batch 2700, loss[loss=0.1937, simple_loss=0.2874, pruned_loss=0.05, over 7327.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2546, pruned_loss=0.03829, over 1423231.04 frames.], batch size: 22, lr: 4.55e-04
2022-05-14 20:39:32,810 INFO [train.py:812] (4/8) Epoch 17, batch 2750, loss[loss=0.171, simple_loss=0.2635, pruned_loss=0.03927, over 7160.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2553, pruned_loss=0.03879, over 1423374.69 frames.], batch size: 19, lr: 4.55e-04
2022-05-14 20:40:31,892 INFO [train.py:812] (4/8) Epoch 17, batch 2800, loss[loss=0.2231, simple_loss=0.2884, pruned_loss=0.07893, over 4718.00 frames.], tot_loss[loss=0.1661, simple_loss=0.255, pruned_loss=0.03862, over 1422185.29 frames.], batch size: 52, lr: 4.55e-04
2022-05-14 20:41:30,550 INFO [train.py:812] (4/8) Epoch 17, batch 2850, loss[loss=0.1542, simple_loss=0.2527, pruned_loss=0.02779, over 7314.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2557, pruned_loss=0.0387, over 1421480.09 frames.], batch size: 21, lr: 4.55e-04
2022-05-14 20:42:28,892 INFO [train.py:812] (4/8) Epoch 17, batch 2900, loss[loss=0.1625, simple_loss=0.2592, pruned_loss=0.03288, over 7227.00 frames.], tot_loss[loss=0.167, simple_loss=0.2555, pruned_loss=0.03921, over 1417778.38 frames.], batch size: 20, lr: 4.55e-04
2022-05-14 20:43:27,760 INFO [train.py:812] (4/8) Epoch 17, batch 2950, loss[loss=0.1517, simple_loss=0.2384, pruned_loss=0.03249, over 7280.00 frames.], tot_loss[loss=0.1671, simple_loss=0.256, pruned_loss=0.03911, over 1418992.08 frames.], batch size: 18, lr: 4.54e-04
2022-05-14 20:44:36,161 INFO [train.py:812] (4/8) Epoch 17, batch 3000, loss[loss=0.142, simple_loss=0.2354, pruned_loss=0.02428, over 7148.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2558, pruned_loss=0.03837, over 1423605.34 frames.], batch size: 20, lr: 4.54e-04
2022-05-14 20:44:36,161 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 20:44:43,901 INFO [train.py:841] (4/8) Epoch 17, validation: loss=0.1538, simple_loss=0.2534, pruned_loss=0.02708, over 698248.00 frames.
2022-05-14 20:45:42,773 INFO [train.py:812] (4/8) Epoch 17, batch 3050, loss[loss=0.1676, simple_loss=0.2518, pruned_loss=0.04164, over 6404.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2559, pruned_loss=0.03846, over 1422639.45 frames.], batch size: 37, lr: 4.54e-04
2022-05-14 20:46:41,074 INFO [train.py:812] (4/8) Epoch 17, batch 3100, loss[loss=0.1805, simple_loss=0.2732, pruned_loss=0.04395, over 7276.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2569, pruned_loss=0.03901, over 1419508.91 frames.], batch size: 25, lr: 4.54e-04
2022-05-14 20:47:58,627 INFO [train.py:812] (4/8) Epoch 17, batch 3150, loss[loss=0.1484, simple_loss=0.2433, pruned_loss=0.02679, over 7325.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2571, pruned_loss=0.03961, over 1418469.32 frames.], batch size: 20, lr: 4.54e-04
2022-05-14 20:49:07,281 INFO [train.py:812] (4/8) Epoch 17, batch 3200, loss[loss=0.1519, simple_loss=0.2443, pruned_loss=0.02973, over 7354.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2565, pruned_loss=0.03916, over 1418648.35 frames.], batch size: 19, lr: 4.54e-04
2022-05-14 20:50:25,525 INFO [train.py:812] (4/8) Epoch 17, batch 3250, loss[loss=0.1709, simple_loss=0.2585, pruned_loss=0.04168, over 7068.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2562, pruned_loss=0.03895, over 1424530.82 frames.], batch size: 18, lr: 4.54e-04
2022-05-14 20:51:34,403 INFO [train.py:812] (4/8) Epoch 17, batch 3300, loss[loss=0.1957, simple_loss=0.2981, pruned_loss=0.04669, over 7164.00 frames.], tot_loss[loss=0.168, simple_loss=0.2573, pruned_loss=0.03933, over 1424504.42 frames.], batch size: 19, lr: 4.53e-04
2022-05-14 20:52:33,316 INFO [train.py:812] (4/8) Epoch 17, batch 3350, loss[loss=0.1738, simple_loss=0.2733, pruned_loss=0.03715, over 7341.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2578, pruned_loss=0.03943, over 1425549.48 frames.], batch size: 22, lr: 4.53e-04
2022-05-14 20:53:32,427 INFO [train.py:812] (4/8) Epoch 17, batch 3400, loss[loss=0.1752, simple_loss=0.2753, pruned_loss=0.03752, over 7145.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2574, pruned_loss=0.03916, over 1422725.38 frames.], batch size: 20, lr: 4.53e-04
2022-05-14 20:54:31,691 INFO [train.py:812] (4/8) Epoch 17, batch 3450, loss[loss=0.1927, simple_loss=0.2859, pruned_loss=0.04975, over 7326.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2554, pruned_loss=0.03854, over 1424292.03 frames.], batch size: 20, lr: 4.53e-04
2022-05-14 20:55:30,346 INFO [train.py:812] (4/8) Epoch 17, batch 3500, loss[loss=0.1804, simple_loss=0.2684, pruned_loss=0.04614, over 7207.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2554, pruned_loss=0.03863, over 1424665.13 frames.], batch size: 22, lr: 4.53e-04
2022-05-14 20:56:29,309 INFO [train.py:812] (4/8) Epoch 17, batch 3550, loss[loss=0.1819, simple_loss=0.2737, pruned_loss=0.04502, over 7118.00 frames.], tot_loss[loss=0.1666, simple_loss=0.256, pruned_loss=0.03859, over 1427262.36 frames.], batch size: 21, lr: 4.53e-04
2022-05-14 20:57:28,817 INFO [train.py:812] (4/8) Epoch 17, batch 3600, loss[loss=0.1561, simple_loss=0.2414, pruned_loss=0.03544, over 7275.00 frames.], tot_loss[loss=0.1665, simple_loss=0.256, pruned_loss=0.0385, over 1428925.60 frames.], batch size: 18, lr: 4.52e-04
2022-05-14 20:58:27,780 INFO [train.py:812] (4/8) Epoch 17, batch 3650, loss[loss=0.1503, simple_loss=0.2489, pruned_loss=0.02583, over 7316.00 frames.], tot_loss[loss=0.1646, simple_loss=0.254, pruned_loss=0.03762, over 1432022.22 frames.], batch size: 21, lr: 4.52e-04
2022-05-14 20:59:27,702 INFO [train.py:812] (4/8) Epoch 17, batch 3700, loss[loss=0.1477, simple_loss=0.2388, pruned_loss=0.02832, over 7152.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2545, pruned_loss=0.0381, over 1431670.33 frames.], batch size: 20, lr: 4.52e-04
2022-05-14 21:00:26,363 INFO [train.py:812] (4/8) Epoch 17, batch 3750, loss[loss=0.1655, simple_loss=0.2635, pruned_loss=0.03377, over 6105.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2551, pruned_loss=0.03866, over 1428213.52 frames.], batch size: 37, lr: 4.52e-04
2022-05-14 21:01:24,374 INFO [train.py:812] (4/8) Epoch 17, batch 3800, loss[loss=0.1702, simple_loss=0.2658, pruned_loss=0.03736, over 6390.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2559, pruned_loss=0.0387, over 1426716.24 frames.], batch size: 37, lr: 4.52e-04
2022-05-14 21:02:23,092 INFO [train.py:812] (4/8) Epoch 17, batch 3850, loss[loss=0.1392, simple_loss=0.2281, pruned_loss=0.02519, over 6986.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2556, pruned_loss=0.03838, over 1425915.04 frames.], batch size: 16, lr: 4.52e-04
2022-05-14 21:03:22,484 INFO [train.py:812] (4/8) Epoch 17, batch 3900, loss[loss=0.1936, simple_loss=0.2664, pruned_loss=0.06042, over 7202.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2544, pruned_loss=0.03776, over 1428487.71 frames.], batch size: 22, lr: 4.52e-04
2022-05-14 21:04:21,496 INFO [train.py:812] (4/8) Epoch 17, batch 3950, loss[loss=0.157, simple_loss=0.2481, pruned_loss=0.03293, over 7221.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2549, pruned_loss=0.03788, over 1427510.62 frames.], batch size: 23, lr: 4.51e-04
2022-05-14 21:05:20,842 INFO [train.py:812] (4/8) Epoch 17, batch 4000, loss[loss=0.1291, simple_loss=0.2168, pruned_loss=0.02072, over 7288.00 frames.], tot_loss[loss=0.166, simple_loss=0.2555, pruned_loss=0.03829, over 1428179.01 frames.], batch size: 18, lr: 4.51e-04
2022-05-14 21:06:19,934 INFO [train.py:812] (4/8) Epoch 17, batch 4050, loss[loss=0.1861, simple_loss=0.2725, pruned_loss=0.04983, over 6811.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2551, pruned_loss=0.03827, over 1424620.01 frames.], batch size: 31, lr: 4.51e-04
2022-05-14 21:07:19,005 INFO [train.py:812] (4/8) Epoch 17, batch 4100, loss[loss=0.1836, simple_loss=0.2737, pruned_loss=0.04676, over 6480.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2566, pruned_loss=0.03885, over 1423968.52 frames.], batch size: 38, lr: 4.51e-04
2022-05-14 21:08:18,273 INFO [train.py:812] (4/8) Epoch 17, batch 4150, loss[loss=0.1548, simple_loss=0.2327, pruned_loss=0.03845, over 7129.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2557, pruned_loss=0.03878, over 1423230.18 frames.], batch size: 17, lr: 4.51e-04
2022-05-14 21:09:17,059 INFO [train.py:812] (4/8) Epoch 17, batch 4200, loss[loss=0.1707, simple_loss=0.2594, pruned_loss=0.04103, over 7160.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2556, pruned_loss=0.03873, over 1422528.35 frames.], batch size: 26, lr: 4.51e-04
2022-05-14 21:10:16,228 INFO [train.py:812] (4/8) Epoch 17, batch 4250, loss[loss=0.1745, simple_loss=0.2629, pruned_loss=0.04303, over 7290.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2562, pruned_loss=0.03877, over 1423039.15 frames.], batch size: 18, lr: 4.51e-04
2022-05-14 21:11:15,273 INFO [train.py:812] (4/8) Epoch 17, batch 4300, loss[loss=0.1595, simple_loss=0.254, pruned_loss=0.03249, over 7064.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2555, pruned_loss=0.03847, over 1422155.31 frames.], batch size: 18, lr: 4.50e-04
2022-05-14 21:12:14,024 INFO [train.py:812] (4/8) Epoch 17, batch 4350, loss[loss=0.1588, simple_loss=0.2372, pruned_loss=0.04021, over 7171.00 frames.], tot_loss[loss=0.166, simple_loss=0.2553, pruned_loss=0.03835, over 1421268.23 frames.], batch size: 18, lr: 4.50e-04
2022-05-14 21:13:12,860 INFO [train.py:812] (4/8) Epoch 17, batch 4400, loss[loss=0.1658, simple_loss=0.2542, pruned_loss=0.03874, over 7231.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2557, pruned_loss=0.03839, over 1419232.02 frames.], batch size: 21, lr: 4.50e-04
2022-05-14 21:14:12,275 INFO [train.py:812] (4/8) Epoch 17, batch 4450, loss[loss=0.1582, simple_loss=0.2365, pruned_loss=0.03996, over 7135.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2562, pruned_loss=0.03832, over 1415583.30 frames.], batch size: 17, lr: 4.50e-04
2022-05-14 21:15:12,251 INFO [train.py:812] (4/8) Epoch 17, batch 4500, loss[loss=0.1634, simple_loss=0.2602, pruned_loss=0.03327, over 7235.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2549, pruned_loss=0.03823, over 1414374.97 frames.], batch size: 20, lr: 4.50e-04
2022-05-14 21:16:11,545 INFO [train.py:812] (4/8) Epoch 17, batch 4550, loss[loss=0.1882, simple_loss=0.2705, pruned_loss=0.05292, over 4835.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2547, pruned_loss=0.03912, over 1378922.80 frames.], batch size: 53, lr: 4.50e-04
2022-05-14 21:17:18,377 INFO [train.py:812] (4/8) Epoch 18, batch 0, loss[loss=0.1771, simple_loss=0.2632, pruned_loss=0.04549, over 7230.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2632, pruned_loss=0.04549, over 7230.00 frames.], batch size: 20, lr: 4.38e-04
2022-05-14 21:18:18,232 INFO [train.py:812] (4/8) Epoch 18, batch 50, loss[loss=0.1532, simple_loss=0.2381, pruned_loss=0.03415, over 7018.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2508, pruned_loss=0.03733, over 324080.45 frames.], batch size: 16, lr: 4.38e-04
2022-05-14 21:19:17,376 INFO [train.py:812] (4/8) Epoch 18, batch 100, loss[loss=0.1598, simple_loss=0.2417, pruned_loss=0.03897, over 7169.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2532, pruned_loss=0.03752, over 565859.67 frames.], batch size: 18, lr: 4.37e-04
2022-05-14 21:20:15,728 INFO [train.py:812] (4/8) Epoch 18, batch 150, loss[loss=0.1817, simple_loss=0.2782, pruned_loss=0.04257, over 7139.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2547, pruned_loss=0.03784, over 752787.87 frames.], batch size: 20, lr: 4.37e-04
2022-05-14 21:21:13,524 INFO [train.py:812] (4/8) Epoch 18, batch 200, loss[loss=0.1628, simple_loss=0.2428, pruned_loss=0.04137, over 7158.00 frames.], tot_loss[loss=0.166, simple_loss=0.2556, pruned_loss=0.03816, over 903627.44 frames.], batch size: 18, lr: 4.37e-04
2022-05-14 21:22:12,916 INFO [train.py:812] (4/8) Epoch 18, batch 250, loss[loss=0.1587, simple_loss=0.252, pruned_loss=0.03269, over 6642.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2556, pruned_loss=0.03783, over 1021125.86 frames.], batch size: 31, lr: 4.37e-04
2022-05-14 21:23:11,925 INFO [train.py:812] (4/8) Epoch 18, batch 300, loss[loss=0.1825, simple_loss=0.2716, pruned_loss=0.0467, over 7019.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2559, pruned_loss=0.03829, over 1104532.20 frames.], batch size: 28, lr: 4.37e-04
2022-05-14 21:24:11,089 INFO [train.py:812] (4/8) Epoch 18, batch 350, loss[loss=0.171, simple_loss=0.2709, pruned_loss=0.03555, over 7334.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2537, pruned_loss=0.03756, over 1171993.64 frames.], batch size: 22, lr: 4.37e-04
2022-05-14 21:25:08,899 INFO [train.py:812] (4/8) Epoch 18, batch 400, loss[loss=0.1363, simple_loss=0.2201, pruned_loss=0.02629, over 6806.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2541, pruned_loss=0.0377, over 1232113.50 frames.], batch size: 15, lr: 4.37e-04
2022-05-14 21:26:06,613 INFO [train.py:812] (4/8) Epoch 18, batch 450, loss[loss=0.1878, simple_loss=0.2704, pruned_loss=0.05267, over 7215.00 frames.], tot_loss[loss=0.165, simple_loss=0.2546, pruned_loss=0.03775, over 1276051.53 frames.], batch size: 22, lr: 4.36e-04
2022-05-14 21:27:06,222 INFO [train.py:812] (4/8) Epoch 18, batch 500, loss[loss=0.1673, simple_loss=0.2623, pruned_loss=0.03616, over 7332.00 frames.], tot_loss[loss=0.165, simple_loss=0.2545, pruned_loss=0.03773, over 1313253.82 frames.], batch size: 22, lr: 4.36e-04
2022-05-14 21:28:04,630 INFO [train.py:812] (4/8) Epoch 18, batch 550, loss[loss=0.1595, simple_loss=0.2337, pruned_loss=0.04262, over 7127.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2543, pruned_loss=0.03757, over 1339822.08 frames.], batch size: 17, lr: 4.36e-04
2022-05-14 21:29:02,270 INFO [train.py:812] (4/8) Epoch 18, batch 600, loss[loss=0.175, simple_loss=0.2676, pruned_loss=0.04121, over 6375.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2556, pruned_loss=0.03836, over 1357011.20 frames.], batch size: 37, lr: 4.36e-04
2022-05-14 21:30:01,254 INFO [train.py:812] (4/8) Epoch 18, batch 650, loss[loss=0.2054, simple_loss=0.2827, pruned_loss=0.06401, over 5149.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2549, pruned_loss=0.03813, over 1369810.08 frames.], batch size: 53, lr: 4.36e-04
2022-05-14 21:30:59,632 INFO [train.py:812] (4/8) Epoch 18, batch 700, loss[loss=0.1518, simple_loss=0.2457, pruned_loss=0.02899, over 7325.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2548, pruned_loss=0.03805, over 1381264.25 frames.], batch size: 21, lr: 4.36e-04
2022-05-14 21:31:59,632 INFO [train.py:812] (4/8) Epoch 18, batch 750, loss[loss=0.137, simple_loss=0.2186, pruned_loss=0.0277, over 7414.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2538, pruned_loss=0.03782, over 1391935.28 frames.], batch size: 18, lr: 4.36e-04
2022-05-14 21:32:57,569 INFO [train.py:812] (4/8) Epoch 18, batch 800, loss[loss=0.1874, simple_loss=0.2708, pruned_loss=0.05202, over 7321.00 frames.], tot_loss[loss=0.1639, simple_loss=0.253, pruned_loss=0.03742, over 1403618.86 frames.], batch size: 21, lr: 4.36e-04
2022-05-14 21:33:57,266 INFO [train.py:812] (4/8) Epoch 18, batch 850, loss[loss=0.1718, simple_loss=0.2631, pruned_loss=0.0403, over 7409.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2526, pruned_loss=0.03724, over 1406121.33 frames.], batch size: 21, lr: 4.35e-04
2022-05-14 21:34:56,178 INFO [train.py:812] (4/8) Epoch 18, batch 900, loss[loss=0.2052, simple_loss=0.2942, pruned_loss=0.05808, over 7209.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2545, pruned_loss=0.03783, over 1406299.75 frames.], batch size: 22, lr: 4.35e-04
2022-05-14 21:35:54,606 INFO [train.py:812] (4/8) Epoch 18, batch 950, loss[loss=0.1526, simple_loss=0.241, pruned_loss=0.03207, over 7264.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2546, pruned_loss=0.03806, over 1409456.87 frames.], batch size: 19, lr: 4.35e-04
2022-05-14 21:36:52,268 INFO [train.py:812] (4/8) Epoch 18, batch 1000, loss[loss=0.1777, simple_loss=0.2702, pruned_loss=0.04259, over 7275.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2547, pruned_loss=0.03778, over 1413976.66 frames.], batch size: 24, lr: 4.35e-04
2022-05-14 21:37:51,919 INFO [train.py:812] (4/8) Epoch 18, batch 1050, loss[loss=0.1615, simple_loss=0.2319, pruned_loss=0.04556, over 7277.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2542, pruned_loss=0.03784, over 1416034.37 frames.], batch size: 17, lr: 4.35e-04
2022-05-14 21:38:50,482 INFO [train.py:812] (4/8) Epoch 18, batch 1100, loss[loss=0.17, simple_loss=0.2577, pruned_loss=0.04112, over 7292.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2546, pruned_loss=0.03804, over 1419710.34 frames.], batch size: 25, lr: 4.35e-04
2022-05-14 21:39:48,087 INFO [train.py:812] (4/8) Epoch 18, batch 1150, loss[loss=0.1665, simple_loss=0.2484, pruned_loss=0.0423, over 7381.00 frames.], tot_loss[loss=0.165, simple_loss=0.2543, pruned_loss=0.03789, over 1419016.57 frames.], batch size: 23, lr: 4.35e-04
2022-05-14 21:40:45,340 INFO [train.py:812] (4/8) Epoch 18, batch 1200, loss[loss=0.1555, simple_loss=0.2374, pruned_loss=0.03682, over 7280.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2545, pruned_loss=0.03792, over 1415987.28 frames.], batch size: 18, lr: 4.34e-04
2022-05-14 21:41:44,617 INFO [train.py:812] (4/8) Epoch 18, batch 1250, loss[loss=0.1531, simple_loss=0.2534, pruned_loss=0.02644, over 7409.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2548, pruned_loss=0.03812, over 1417297.10 frames.], batch size: 21, lr: 4.34e-04
2022-05-14 21:42:42,170 INFO [train.py:812] (4/8) Epoch 18, batch 1300, loss[loss=0.1756, simple_loss=0.2694, pruned_loss=0.04096, over 7152.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2547, pruned_loss=0.03838, over 1418828.21 frames.], batch size: 26, lr: 4.34e-04
2022-05-14 21:43:41,349 INFO [train.py:812] (4/8) Epoch 18, batch 1350, loss[loss=0.1545, simple_loss=0.2414, pruned_loss=0.03385, over 7424.00 frames.], tot_loss[loss=0.1659, simple_loss=0.255, pruned_loss=0.03843, over 1421920.63 frames.], batch size: 17, lr: 4.34e-04
2022-05-14 21:44:39,597 INFO [train.py:812] (4/8) Epoch 18, batch 1400, loss[loss=0.1647, simple_loss=0.2569, pruned_loss=0.03621, over 7120.00 frames.], tot_loss[loss=0.1654, simple_loss=0.255, pruned_loss=0.03793, over 1423542.89 frames.], batch size: 21, lr: 4.34e-04
2022-05-14 21:45:38,202 INFO [train.py:812] (4/8) Epoch 18, batch 1450, loss[loss=0.1491, simple_loss=0.2548, pruned_loss=0.02171, over 7149.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2552, pruned_loss=0.03781, over 1421766.38 frames.], batch size: 20, lr: 4.34e-04
2022-05-14 21:46:36,913 INFO [train.py:812] (4/8) Epoch 18, batch 1500, loss[loss=0.1482, simple_loss=0.2441, pruned_loss=0.02617, over 7277.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2553, pruned_loss=0.03782, over 1414203.31 frames.], batch size: 25, lr: 4.34e-04
2022-05-14 21:47:35,832 INFO [train.py:812] (4/8) Epoch 18, batch 1550, loss[loss=0.1569, simple_loss=0.2479, pruned_loss=0.03293, over 7153.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2549, pruned_loss=0.03769, over 1421421.66 frames.], batch size: 19, lr: 4.33e-04
2022-05-14 21:48:33,680 INFO [train.py:812] (4/8) Epoch 18, batch 1600, loss[loss=0.1602, simple_loss=0.2446, pruned_loss=0.0379, over 7426.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2553, pruned_loss=0.0379, over 1423644.63 frames.], batch size: 20, lr: 4.33e-04
2022-05-14 21:49:33,291 INFO [train.py:812] (4/8) Epoch 18, batch 1650, loss[loss=0.1523, simple_loss=0.2259, pruned_loss=0.03939, over 7291.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2557, pruned_loss=0.03823, over 1422783.92 frames.], batch size: 17, lr: 4.33e-04
2022-05-14 21:50:30,803 INFO [train.py:812] (4/8) Epoch 18, batch 1700, loss[loss=0.1762, simple_loss=0.2627, pruned_loss=0.04481, over 7358.00 frames.], tot_loss[loss=0.1661, simple_loss=0.256, pruned_loss=0.03814, over 1425564.80 frames.], batch size: 19, lr: 4.33e-04
2022-05-14 21:51:29,629 INFO [train.py:812] (4/8) Epoch 18, batch 1750, loss[loss=0.1964, simple_loss=0.2869, pruned_loss=0.05295, over 7307.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2555, pruned_loss=0.03796, over 1426007.50 frames.], batch size: 21, lr: 4.33e-04
2022-05-14 21:52:27,487 INFO [train.py:812] (4/8) Epoch 18, batch 1800, loss[loss=0.1563, simple_loss=0.2523, pruned_loss=0.03016, over 7230.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2554, pruned_loss=0.03788, over 1430199.51 frames.], batch size: 20, lr: 4.33e-04
2022-05-14 21:53:27,323 INFO [train.py:812] (4/8) Epoch 18, batch 1850, loss[loss=0.1914, simple_loss=0.2706, pruned_loss=0.05608, over 4771.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2539, pruned_loss=0.03766, over 1428139.59 frames.], batch size: 52, lr: 4.33e-04
2022-05-14 21:54:25,904 INFO [train.py:812] (4/8) Epoch 18, batch 1900, loss[loss=0.1678, simple_loss=0.271, pruned_loss=0.03237, over 7306.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2562, pruned_loss=0.03815, over 1428456.82 frames.], batch size: 21, lr: 4.33e-04
2022-05-14 21:55:25,269 INFO [train.py:812] (4/8) Epoch 18, batch 1950, loss[loss=0.1681, simple_loss=0.267, pruned_loss=0.03462, over 7318.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2567, pruned_loss=0.03852, over 1424966.19 frames.], batch size: 21, lr: 4.32e-04
2022-05-14 21:56:23,563 INFO [train.py:812] (4/8) Epoch 18, batch 2000, loss[loss=0.2025, simple_loss=0.286, pruned_loss=0.05945, over 4821.00 frames.], tot_loss[loss=0.166, simple_loss=0.2557, pruned_loss=0.03811, over 1425313.34 frames.], batch size: 52, lr: 4.32e-04
2022-05-14 21:57:27,187 INFO [train.py:812] (4/8) Epoch 18, batch 2050, loss[loss=0.2138, simple_loss=0.2984, pruned_loss=0.06462, over 7122.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2558, pruned_loss=0.03825, over 1420442.37 frames.], batch size: 21, lr: 4.32e-04
2022-05-14 21:58:25,556 INFO [train.py:812] (4/8) Epoch 18, batch 2100, loss[loss=0.1797, simple_loss=0.2802, pruned_loss=0.03962, over 6861.00 frames.], tot_loss[loss=0.166, simple_loss=0.2554, pruned_loss=0.03829, over 1416281.27 frames.], batch size: 31, lr: 4.32e-04
2022-05-14 21:59:24,609 INFO [train.py:812] (4/8) Epoch 18, batch 2150, loss[loss=0.1667, simple_loss=0.2585, pruned_loss=0.03746, over 7224.00 frames.], tot_loss[loss=0.1652, simple_loss=0.255, pruned_loss=0.03772, over 1418086.00 frames.], batch size: 21, lr: 4.32e-04
2022-05-14 22:00:22,633 INFO [train.py:812] (4/8) Epoch 18, batch 2200, loss[loss=0.169, simple_loss=0.2407, pruned_loss=0.04868, over 7198.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03798, over 1421069.55 frames.], batch size: 16, lr: 4.32e-04
2022-05-14 22:01:22,003 INFO [train.py:812] (4/8) Epoch 18, batch 2250, loss[loss=0.1497, simple_loss=0.2331, pruned_loss=0.0332, over 7006.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2551, pruned_loss=0.03802, over 1424103.60 frames.], batch size: 16, lr: 4.32e-04
2022-05-14 22:02:21,440 INFO [train.py:812] (4/8) Epoch 18, batch 2300, loss[loss=0.1586, simple_loss=0.2578, pruned_loss=0.02966, over 7145.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2555, pruned_loss=0.03845, over 1426619.51 frames.], batch size: 20, lr: 4.31e-04
2022-05-14 22:03:21,214 INFO [train.py:812] (4/8) Epoch 18, batch 2350, loss[loss=0.1947, simple_loss=0.2869, pruned_loss=0.05122, over 7157.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2545, pruned_loss=0.0381, over 1426767.68 frames.], batch size: 26, lr: 4.31e-04
2022-05-14 22:04:20,402 INFO [train.py:812] (4/8) Epoch 18, batch 2400, loss[loss=0.187, simple_loss=0.2776, pruned_loss=0.04823, over 6387.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2546, pruned_loss=0.03814, over 1424705.16 frames.], batch size: 38, lr: 4.31e-04
2022-05-14 22:05:18,775 INFO [train.py:812] (4/8) Epoch 18, batch 2450, loss[loss=0.1446, simple_loss=0.2352, pruned_loss=0.02699, over 7172.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2537, pruned_loss=0.03771, over 1425979.10 frames.], batch size: 19, lr: 4.31e-04
2022-05-14 22:06:16,639 INFO [train.py:812] (4/8) Epoch 18, batch 2500, loss[loss=0.1811, simple_loss=0.2714, pruned_loss=0.0454, over 7114.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2552, pruned_loss=0.03826, over 1419198.91 frames.], batch size: 21, lr: 4.31e-04
2022-05-14 22:07:15,276 INFO [train.py:812] (4/8) Epoch 18, batch 2550, loss[loss=0.1624, simple_loss=0.2526, pruned_loss=0.03612, over 7315.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2552, pruned_loss=0.03808, over 1418627.36 frames.], batch size: 21, lr: 4.31e-04
2022-05-14 22:08:14,587 INFO [train.py:812] (4/8) Epoch 18, batch 2600, loss[loss=0.1615, simple_loss=0.2438, pruned_loss=0.03963, over 6829.00 frames.], tot_loss[loss=0.1665, simple_loss=0.256, pruned_loss=0.03849, over 1418127.62 frames.], batch size: 15, lr: 4.31e-04
2022-05-14 22:09:14,558 INFO [train.py:812] (4/8) Epoch 18, batch 2650, loss[loss=0.161, simple_loss=0.2438, pruned_loss=0.03912, over 7352.00 frames.], tot_loss[loss=0.1665, simple_loss=0.256, pruned_loss=0.03849, over 1419164.98 frames.], batch size: 19, lr: 4.31e-04
2022-05-14 22:10:13,355 INFO [train.py:812] (4/8) Epoch 18, batch 2700, loss[loss=0.1192, simple_loss=0.206, pruned_loss=0.01616, over 7275.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2549, pruned_loss=0.03823, over 1419328.22 frames.], batch size: 18, lr: 4.30e-04
2022-05-14 22:11:12,901 INFO [train.py:812] (4/8) Epoch 18, batch 2750, loss[loss=0.162, simple_loss=0.2501, pruned_loss=0.0369, over 7148.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2553, pruned_loss=0.03855, over 1418293.39 frames.], batch size: 20, lr: 4.30e-04
2022-05-14 22:12:10,427 INFO [train.py:812] (4/8) Epoch 18, batch 2800, loss[loss=0.153, simple_loss=0.2525, pruned_loss=0.02682, over 7321.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2547, pruned_loss=0.03824, over 1418017.37 frames.], batch size: 21, lr: 4.30e-04
2022-05-14 22:13:09,212 INFO [train.py:812] (4/8) Epoch 18, batch 2850, loss[loss=0.1722, simple_loss=0.2692, pruned_loss=0.03766, over 7302.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2546, pruned_loss=0.03799, over 1420725.46 frames.], batch size: 25, lr: 4.30e-04
2022-05-14 22:14:17,881 INFO [train.py:812] (4/8) Epoch 18, batch 2900, loss[loss=0.169, simple_loss=0.2544, pruned_loss=0.04182, over 7211.00 frames.], tot_loss[loss=0.166, simple_loss=0.2552, pruned_loss=0.03843, over 1423711.71 frames.], batch size: 22, lr: 4.30e-04
2022-05-14 22:15:17,294 INFO [train.py:812] (4/8) Epoch 18, batch 2950, loss[loss=0.1852, simple_loss=0.2746, pruned_loss=0.04791, over 6332.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2549, pruned_loss=0.03802, over 1420796.54 frames.], batch size: 37, lr: 4.30e-04
2022-05-14 22:16:16,204 INFO [train.py:812] (4/8) Epoch 18, batch 3000, loss[loss=0.2009, simple_loss=0.2841, pruned_loss=0.05882, over 7296.00 frames.], tot_loss[loss=0.166, simple_loss=0.2554, pruned_loss=0.03829, over 1419484.82 frames.], batch size: 25, lr: 4.30e-04
2022-05-14 22:16:16,205 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 22:16:23,833 INFO [train.py:841] (4/8) 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] (4/8) Epoch 18, batch 3050, loss[loss=0.175, simple_loss=0.2588, pruned_loss=0.04562, over 7115.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2556, pruned_loss=0.03854, over 1419023.96 frames.], batch size: 21, lr: 4.29e-04
2022-05-14 22:18:21,081 INFO [train.py:812] (4/8) Epoch 18, batch 3100, loss[loss=0.1573, simple_loss=0.2518, pruned_loss=0.03137, over 7238.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2556, pruned_loss=0.03844, over 1419727.22 frames.], batch size: 20, lr: 4.29e-04
2022-05-14 22:19:19,570 INFO [train.py:812] (4/8) Epoch 18, batch 3150, loss[loss=0.1652, simple_loss=0.2618, pruned_loss=0.0343, over 7256.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2554, pruned_loss=0.03817, over 1421710.99 frames.], batch size: 19, lr: 4.29e-04
2022-05-14 22:20:18,602 INFO [train.py:812] (4/8) Epoch 18, batch 3200, loss[loss=0.1812, simple_loss=0.2677, pruned_loss=0.04738, over 6764.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03802, over 1419753.64 frames.], batch size: 31, lr: 4.29e-04
2022-05-14 22:21:17,364 INFO [train.py:812] (4/8) Epoch 18, batch 3250, loss[loss=0.161, simple_loss=0.2513, pruned_loss=0.03531, over 7370.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2538, pruned_loss=0.03752, over 1423163.88 frames.], batch size: 23, lr: 4.29e-04
2022-05-14 22:22:16,098 INFO [train.py:812] (4/8) Epoch 18, batch 3300, loss[loss=0.1528, simple_loss=0.2342, pruned_loss=0.0357, over 7168.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2536, pruned_loss=0.03701, over 1426730.55 frames.], batch size: 18, lr: 4.29e-04
2022-05-14 22:23:15,276 INFO [train.py:812] (4/8) Epoch 18, batch 3350, loss[loss=0.1329, simple_loss=0.2143, pruned_loss=0.02572, over 7400.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2546, pruned_loss=0.0372, over 1426038.81 frames.], batch size: 18, lr: 4.29e-04
2022-05-14 22:24:13,568 INFO [train.py:812] (4/8) Epoch 18, batch 3400, loss[loss=0.1679, simple_loss=0.258, pruned_loss=0.03887, over 7365.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2547, pruned_loss=0.03712, over 1430066.83 frames.], batch size: 23, lr: 4.29e-04
2022-05-14 22:25:13,427 INFO [train.py:812] (4/8) Epoch 18, batch 3450, loss[loss=0.1531, simple_loss=0.2369, pruned_loss=0.03468, over 7433.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2544, pruned_loss=0.03689, over 1430474.43 frames.], batch size: 18, lr: 4.28e-04
2022-05-14 22:26:12,111 INFO [train.py:812] (4/8) Epoch 18, batch 3500, loss[loss=0.1738, simple_loss=0.2678, pruned_loss=0.03985, over 6471.00 frames.], tot_loss[loss=0.164, simple_loss=0.2541, pruned_loss=0.03697, over 1433062.12 frames.], batch size: 38, lr: 4.28e-04
2022-05-14 22:27:09,546 INFO [train.py:812] (4/8) Epoch 18, batch 3550, loss[loss=0.1576, simple_loss=0.2401, pruned_loss=0.0376, over 7204.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2548, pruned_loss=0.0371, over 1431292.82 frames.], batch size: 23, lr: 4.28e-04
2022-05-14 22:28:09,174 INFO [train.py:812] (4/8) Epoch 18, batch 3600, loss[loss=0.1812, simple_loss=0.2666, pruned_loss=0.04789, over 7220.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2546, pruned_loss=0.03716, over 1432419.15 frames.], batch size: 21, lr: 4.28e-04
2022-05-14 22:29:08,006 INFO [train.py:812] (4/8) Epoch 18, batch 3650, loss[loss=0.1713, simple_loss=0.2712, pruned_loss=0.03571, over 7349.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2544, pruned_loss=0.03709, over 1423418.62 frames.], batch size: 22, lr: 4.28e-04
2022-05-14 22:30:06,375 INFO [train.py:812] (4/8) Epoch 18, batch 3700, loss[loss=0.1418, simple_loss=0.2204, pruned_loss=0.03156, over 6998.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2548, pruned_loss=0.03705, over 1424466.88 frames.], batch size: 16, lr: 4.28e-04
2022-05-14 22:31:03,714 INFO [train.py:812] (4/8) Epoch 18, batch 3750, loss[loss=0.1803, simple_loss=0.2677, pruned_loss=0.04651, over 7290.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2559, pruned_loss=0.03756, over 1426425.79 frames.], batch size: 25, lr: 4.28e-04
2022-05-14 22:32:02,174 INFO [train.py:812] (4/8) Epoch 18, batch 3800, loss[loss=0.1583, simple_loss=0.2544, pruned_loss=0.03105, over 7359.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2547, pruned_loss=0.03716, over 1426371.33 frames.], batch size: 19, lr: 4.28e-04
2022-05-14 22:33:01,934 INFO [train.py:812] (4/8) Epoch 18, batch 3850, loss[loss=0.146, simple_loss=0.2327, pruned_loss=0.02965, over 7410.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2541, pruned_loss=0.03678, over 1424684.38 frames.], batch size: 18, lr: 4.27e-04
2022-05-14 22:34:00,992 INFO [train.py:812] (4/8) Epoch 18, batch 3900, loss[loss=0.1652, simple_loss=0.2637, pruned_loss=0.03333, over 7103.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2544, pruned_loss=0.03714, over 1421673.55 frames.], batch size: 21, lr: 4.27e-04
2022-05-14 22:35:00,690 INFO [train.py:812] (4/8) Epoch 18, batch 3950, loss[loss=0.1672, simple_loss=0.2703, pruned_loss=0.03203, over 7094.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2541, pruned_loss=0.03748, over 1423373.90 frames.], batch size: 28, lr: 4.27e-04
2022-05-14 22:35:58,135 INFO [train.py:812] (4/8) Epoch 18, batch 4000, loss[loss=0.1551, simple_loss=0.2307, pruned_loss=0.03976, over 7228.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2539, pruned_loss=0.03743, over 1423795.59 frames.], batch size: 16, lr: 4.27e-04
2022-05-14 22:36:56,547 INFO [train.py:812] (4/8) Epoch 18, batch 4050, loss[loss=0.1623, simple_loss=0.2504, pruned_loss=0.03706, over 7067.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2547, pruned_loss=0.03782, over 1427484.36 frames.], batch size: 28, lr: 4.27e-04
2022-05-14 22:37:55,335 INFO [train.py:812] (4/8) Epoch 18, batch 4100, loss[loss=0.1646, simple_loss=0.254, pruned_loss=0.03763, over 7155.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2545, pruned_loss=0.03802, over 1423976.53 frames.], batch size: 20, lr: 4.27e-04
2022-05-14 22:38:54,562 INFO [train.py:812] (4/8) Epoch 18, batch 4150, loss[loss=0.1481, simple_loss=0.2442, pruned_loss=0.02597, over 7319.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2551, pruned_loss=0.03817, over 1423295.44 frames.], batch size: 20, lr: 4.27e-04
2022-05-14 22:39:53,791 INFO [train.py:812] (4/8) Epoch 18, batch 4200, loss[loss=0.1538, simple_loss=0.2491, pruned_loss=0.02922, over 7009.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2537, pruned_loss=0.03775, over 1423350.52 frames.], batch size: 16, lr: 4.26e-04
2022-05-14 22:40:53,077 INFO [train.py:812] (4/8) Epoch 18, batch 4250, loss[loss=0.1823, simple_loss=0.2658, pruned_loss=0.04941, over 6662.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2535, pruned_loss=0.03794, over 1419160.95 frames.], batch size: 31, lr: 4.26e-04
2022-05-14 22:41:52,048 INFO [train.py:812] (4/8) Epoch 18, batch 4300, loss[loss=0.1474, simple_loss=0.2208, pruned_loss=0.03702, over 6991.00 frames.], tot_loss[loss=0.1632, simple_loss=0.252, pruned_loss=0.03725, over 1419472.87 frames.], batch size: 16, lr: 4.26e-04
2022-05-14 22:42:51,535 INFO [train.py:812] (4/8) Epoch 18, batch 4350, loss[loss=0.1656, simple_loss=0.2597, pruned_loss=0.0358, over 7226.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2519, pruned_loss=0.03732, over 1407035.02 frames.], batch size: 21, lr: 4.26e-04
2022-05-14 22:43:50,336 INFO [train.py:812] (4/8) Epoch 18, batch 4400, loss[loss=0.1478, simple_loss=0.2353, pruned_loss=0.03013, over 7074.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2528, pruned_loss=0.03735, over 1402354.20 frames.], batch size: 18, lr: 4.26e-04
2022-05-14 22:44:47,951 INFO [train.py:812] (4/8) Epoch 18, batch 4450, loss[loss=0.1598, simple_loss=0.2477, pruned_loss=0.03599, over 6512.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2543, pruned_loss=0.03778, over 1392897.62 frames.], batch size: 38, lr: 4.26e-04
2022-05-14 22:45:55,877 INFO [train.py:812] (4/8) Epoch 18, batch 4500, loss[loss=0.1506, simple_loss=0.2344, pruned_loss=0.03338, over 6986.00 frames.], tot_loss[loss=0.166, simple_loss=0.2555, pruned_loss=0.03822, over 1379677.09 frames.], batch size: 16, lr: 4.26e-04
2022-05-14 22:46:55,059 INFO [train.py:812] (4/8) Epoch 18, batch 4550, loss[loss=0.1621, simple_loss=0.2471, pruned_loss=0.03852, over 7155.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2558, pruned_loss=0.03888, over 1369677.78 frames.], batch size: 19, lr: 4.26e-04
2022-05-14 22:48:10,094 INFO [train.py:812] (4/8) Epoch 19, batch 0, loss[loss=0.1871, simple_loss=0.2745, pruned_loss=0.04981, over 7288.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2745, pruned_loss=0.04981, over 7288.00 frames.], batch size: 25, lr: 4.15e-04
2022-05-14 22:49:27,407 INFO [train.py:812] (4/8) Epoch 19, batch 50, loss[loss=0.1819, simple_loss=0.2749, pruned_loss=0.04449, over 7344.00 frames.], tot_loss[loss=0.166, simple_loss=0.2547, pruned_loss=0.03859, over 325062.81 frames.], batch size: 22, lr: 4.15e-04
2022-05-14 22:50:35,551 INFO [train.py:812] (4/8) Epoch 19, batch 100, loss[loss=0.1895, simple_loss=0.2818, pruned_loss=0.04863, over 7326.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2542, pruned_loss=0.03768, over 574335.21 frames.], batch size: 22, lr: 4.14e-04
2022-05-14 22:51:34,803 INFO [train.py:812] (4/8) Epoch 19, batch 150, loss[loss=0.1568, simple_loss=0.259, pruned_loss=0.0273, over 7217.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2524, pruned_loss=0.03704, over 764234.45 frames.], batch size: 21, lr: 4.14e-04
2022-05-14 22:53:02,390 INFO [train.py:812] (4/8) Epoch 19, batch 200, loss[loss=0.1329, simple_loss=0.2078, pruned_loss=0.029, over 7272.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2525, pruned_loss=0.03698, over 909932.67 frames.], batch size: 17, lr: 4.14e-04
2022-05-14 22:54:01,875 INFO [train.py:812] (4/8) Epoch 19, batch 250, loss[loss=0.1508, simple_loss=0.249, pruned_loss=0.02624, over 6716.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2531, pruned_loss=0.03695, over 1025379.81 frames.], batch size: 31, lr: 4.14e-04
2022-05-14 22:55:01,086 INFO [train.py:812] (4/8) Epoch 19, batch 300, loss[loss=0.1772, simple_loss=0.2703, pruned_loss=0.04203, over 7233.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2543, pruned_loss=0.03711, over 1115470.62 frames.], batch size: 20, lr: 4.14e-04
2022-05-14 22:56:00,982 INFO [train.py:812] (4/8) Epoch 19, batch 350, loss[loss=0.1996, simple_loss=0.2857, pruned_loss=0.05677, over 6752.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2529, pruned_loss=0.03675, over 1182450.18 frames.], batch size: 31, lr: 4.14e-04
2022-05-14 22:56:59,183 INFO [train.py:812] (4/8) Epoch 19, batch 400, loss[loss=0.1556, simple_loss=0.2409, pruned_loss=0.03514, over 7068.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2533, pruned_loss=0.03713, over 1233072.01 frames.], batch size: 18, lr: 4.14e-04
2022-05-14 22:57:58,728 INFO [train.py:812] (4/8) Epoch 19, batch 450, loss[loss=0.1698, simple_loss=0.2588, pruned_loss=0.04041, over 7337.00 frames.], tot_loss[loss=0.164, simple_loss=0.2536, pruned_loss=0.03716, over 1275395.06 frames.], batch size: 22, lr: 4.14e-04
2022-05-14 22:58:57,681 INFO [train.py:812] (4/8) Epoch 19, batch 500, loss[loss=0.1493, simple_loss=0.2322, pruned_loss=0.03322, over 7136.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2548, pruned_loss=0.03745, over 1306094.23 frames.], batch size: 17, lr: 4.13e-04
2022-05-14 22:59:57,491 INFO [train.py:812] (4/8) Epoch 19, batch 550, loss[loss=0.184, simple_loss=0.2585, pruned_loss=0.05476, over 7288.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2537, pruned_loss=0.03694, over 1335795.56 frames.], batch size: 17, lr: 4.13e-04
2022-05-14 23:00:56,147 INFO [train.py:812] (4/8) Epoch 19, batch 600, loss[loss=0.1602, simple_loss=0.2429, pruned_loss=0.03881, over 7285.00 frames.], tot_loss[loss=0.164, simple_loss=0.2537, pruned_loss=0.03714, over 1356386.24 frames.], batch size: 18, lr: 4.13e-04
2022-05-14 23:01:55,592 INFO [train.py:812] (4/8) Epoch 19, batch 650, loss[loss=0.1655, simple_loss=0.2583, pruned_loss=0.03633, over 7119.00 frames.], tot_loss[loss=0.163, simple_loss=0.2528, pruned_loss=0.03659, over 1375726.28 frames.], batch size: 21, lr: 4.13e-04
2022-05-14 23:02:54,267 INFO [train.py:812] (4/8) Epoch 19, batch 700, loss[loss=0.1884, simple_loss=0.2733, pruned_loss=0.05173, over 5116.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2538, pruned_loss=0.03704, over 1386114.55 frames.], batch size: 52, lr: 4.13e-04
2022-05-14 23:03:53,344 INFO [train.py:812] (4/8) Epoch 19, batch 750, loss[loss=0.1511, simple_loss=0.2392, pruned_loss=0.03151, over 7158.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2539, pruned_loss=0.03699, over 1394669.67 frames.], batch size: 19, lr: 4.13e-04
2022-05-14 23:04:52,302 INFO [train.py:812] (4/8) Epoch 19, batch 800, loss[loss=0.1717, simple_loss=0.2618, pruned_loss=0.04082, over 6777.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2545, pruned_loss=0.037, over 1396941.95 frames.], batch size: 31, lr: 4.13e-04
2022-05-14 23:05:50,872 INFO [train.py:812] (4/8) Epoch 19, batch 850, loss[loss=0.1542, simple_loss=0.243, pruned_loss=0.03268, over 7058.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2552, pruned_loss=0.03706, over 1404882.50 frames.], batch size: 18, lr: 4.13e-04
2022-05-14 23:06:49,943 INFO [train.py:812] (4/8) Epoch 19, batch 900, loss[loss=0.1518, simple_loss=0.2304, pruned_loss=0.03666, over 6795.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2556, pruned_loss=0.03749, over 1410092.11 frames.], batch size: 15, lr: 4.12e-04
2022-05-14 23:07:49,372 INFO [train.py:812] (4/8) Epoch 19, batch 950, loss[loss=0.1776, simple_loss=0.2634, pruned_loss=0.04591, over 7366.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2551, pruned_loss=0.03736, over 1412140.53 frames.], batch size: 23, lr: 4.12e-04
2022-05-14 23:08:48,638 INFO [train.py:812] (4/8) Epoch 19, batch 1000, loss[loss=0.1525, simple_loss=0.2557, pruned_loss=0.02462, over 7139.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2558, pruned_loss=0.03754, over 1419354.25 frames.], batch size: 20, lr: 4.12e-04
2022-05-14 23:09:47,748 INFO [train.py:812] (4/8) Epoch 19, batch 1050, loss[loss=0.2125, simple_loss=0.2971, pruned_loss=0.06397, over 7317.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2554, pruned_loss=0.03765, over 1417733.40 frames.], batch size: 25, lr: 4.12e-04
2022-05-14 23:10:45,898 INFO [train.py:812] (4/8) Epoch 19, batch 1100, loss[loss=0.1588, simple_loss=0.2485, pruned_loss=0.03453, over 7321.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2546, pruned_loss=0.03765, over 1418662.38 frames.], batch size: 20, lr: 4.12e-04
2022-05-14 23:11:43,623 INFO [train.py:812] (4/8) Epoch 19, batch 1150, loss[loss=0.1695, simple_loss=0.2542, pruned_loss=0.04241, over 7308.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2545, pruned_loss=0.03781, over 1419172.24 frames.], batch size: 24, lr: 4.12e-04
2022-05-14 23:12:42,329 INFO [train.py:812] (4/8) Epoch 19, batch 1200, loss[loss=0.1993, simple_loss=0.2904, pruned_loss=0.05408, over 4937.00 frames.], tot_loss[loss=0.165, simple_loss=0.2546, pruned_loss=0.03772, over 1413427.69 frames.], batch size: 52, lr: 4.12e-04
2022-05-14 23:13:40,374 INFO [train.py:812] (4/8) Epoch 19, batch 1250, loss[loss=0.1481, simple_loss=0.2459, pruned_loss=0.02518, over 7112.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2542, pruned_loss=0.03724, over 1414117.88 frames.], batch size: 21, lr: 4.12e-04
2022-05-14 23:14:39,570 INFO [train.py:812] (4/8) Epoch 19, batch 1300, loss[loss=0.1711, simple_loss=0.2605, pruned_loss=0.04085, over 7173.00 frames.], tot_loss[loss=0.1647, simple_loss=0.255, pruned_loss=0.03716, over 1413734.48 frames.], batch size: 19, lr: 4.12e-04
2022-05-14 23:15:38,799 INFO [train.py:812] (4/8) Epoch 19, batch 1350, loss[loss=0.17, simple_loss=0.2647, pruned_loss=0.03769, over 7111.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2556, pruned_loss=0.03735, over 1411902.99 frames.], batch size: 28, lr: 4.11e-04
2022-05-14 23:16:38,071 INFO [train.py:812] (4/8) Epoch 19, batch 1400, loss[loss=0.1584, simple_loss=0.2398, pruned_loss=0.03849, over 7064.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2546, pruned_loss=0.03734, over 1409699.98 frames.], batch size: 18, lr: 4.11e-04
2022-05-14 23:17:42,353 INFO [train.py:812] (4/8) Epoch 19, batch 1450, loss[loss=0.167, simple_loss=0.2621, pruned_loss=0.03602, over 7313.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2537, pruned_loss=0.03708, over 1417438.21 frames.], batch size: 21, lr: 4.11e-04
2022-05-14 23:18:41,292 INFO [train.py:812] (4/8) Epoch 19, batch 1500, loss[loss=0.1684, simple_loss=0.2544, pruned_loss=0.04118, over 7253.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2544, pruned_loss=0.03717, over 1421329.39 frames.], batch size: 19, lr: 4.11e-04
2022-05-14 23:19:40,447 INFO [train.py:812] (4/8) Epoch 19, batch 1550, loss[loss=0.1616, simple_loss=0.2633, pruned_loss=0.02996, over 7414.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2535, pruned_loss=0.03682, over 1424262.47 frames.], batch size: 21, lr: 4.11e-04
2022-05-14 23:20:39,977 INFO [train.py:812] (4/8) Epoch 19, batch 1600, loss[loss=0.172, simple_loss=0.2524, pruned_loss=0.04583, over 7198.00 frames.], tot_loss[loss=0.1632, simple_loss=0.253, pruned_loss=0.03668, over 1423239.72 frames.], batch size: 22, lr: 4.11e-04
2022-05-14 23:21:39,521 INFO [train.py:812] (4/8) Epoch 19, batch 1650, loss[loss=0.1645, simple_loss=0.2437, pruned_loss=0.04262, over 7156.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2532, pruned_loss=0.03683, over 1422105.66 frames.], batch size: 18, lr: 4.11e-04
2022-05-14 23:22:38,865 INFO [train.py:812] (4/8) Epoch 19, batch 1700, loss[loss=0.1439, simple_loss=0.2241, pruned_loss=0.03186, over 7162.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2533, pruned_loss=0.03681, over 1422845.24 frames.], batch size: 18, lr: 4.11e-04
2022-05-14 23:23:37,794 INFO [train.py:812] (4/8) Epoch 19, batch 1750, loss[loss=0.1753, simple_loss=0.264, pruned_loss=0.04333, over 7148.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2542, pruned_loss=0.037, over 1414839.90 frames.], batch size: 20, lr: 4.10e-04
2022-05-14 23:24:36,346 INFO [train.py:812] (4/8) Epoch 19, batch 1800, loss[loss=0.1637, simple_loss=0.256, pruned_loss=0.03571, over 7254.00 frames.], tot_loss[loss=0.165, simple_loss=0.2556, pruned_loss=0.03713, over 1415778.59 frames.], batch size: 19, lr: 4.10e-04
2022-05-14 23:25:35,723 INFO [train.py:812] (4/8) Epoch 19, batch 1850, loss[loss=0.172, simple_loss=0.2572, pruned_loss=0.04344, over 7279.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2552, pruned_loss=0.03706, over 1421757.93 frames.], batch size: 24, lr: 4.10e-04
2022-05-14 23:26:34,569 INFO [train.py:812] (4/8) Epoch 19, batch 1900, loss[loss=0.1532, simple_loss=0.2421, pruned_loss=0.03213, over 7107.00 frames.], tot_loss[loss=0.165, simple_loss=0.2551, pruned_loss=0.03742, over 1418909.76 frames.], batch size: 28, lr: 4.10e-04
2022-05-14 23:27:34,101 INFO [train.py:812] (4/8) Epoch 19, batch 1950, loss[loss=0.1471, simple_loss=0.2233, pruned_loss=0.03545, over 6998.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2553, pruned_loss=0.03755, over 1419088.52 frames.], batch size: 16, lr: 4.10e-04
2022-05-14 23:28:32,906 INFO [train.py:812] (4/8) Epoch 19, batch 2000, loss[loss=0.1661, simple_loss=0.2503, pruned_loss=0.04091, over 7148.00 frames.], tot_loss[loss=0.1653, simple_loss=0.255, pruned_loss=0.03777, over 1423045.39 frames.], batch size: 20, lr: 4.10e-04
2022-05-14 23:29:32,684 INFO [train.py:812] (4/8) Epoch 19, batch 2050, loss[loss=0.1952, simple_loss=0.2811, pruned_loss=0.05461, over 7295.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2549, pruned_loss=0.0377, over 1423873.26 frames.], batch size: 25, lr: 4.10e-04
2022-05-14 23:30:30,655 INFO [train.py:812] (4/8) Epoch 19, batch 2100, loss[loss=0.1405, simple_loss=0.2349, pruned_loss=0.02309, over 7158.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2556, pruned_loss=0.03773, over 1424470.26 frames.], batch size: 19, lr: 4.10e-04
2022-05-14 23:31:30,585 INFO [train.py:812] (4/8) Epoch 19, batch 2150, loss[loss=0.1803, simple_loss=0.2754, pruned_loss=0.04262, over 7220.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2555, pruned_loss=0.03784, over 1420594.72 frames.], batch size: 21, lr: 4.09e-04
2022-05-14 23:32:29,964 INFO [train.py:812] (4/8) Epoch 19, batch 2200, loss[loss=0.1959, simple_loss=0.2896, pruned_loss=0.05106, over 7120.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2544, pruned_loss=0.03734, over 1425096.34 frames.], batch size: 21, lr: 4.09e-04
2022-05-14 23:33:29,289 INFO [train.py:812] (4/8) Epoch 19, batch 2250, loss[loss=0.1722, simple_loss=0.2656, pruned_loss=0.03936, over 6434.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2547, pruned_loss=0.03753, over 1423953.15 frames.], batch size: 38, lr: 4.09e-04
2022-05-14 23:34:27,800 INFO [train.py:812] (4/8) Epoch 19, batch 2300, loss[loss=0.1782, simple_loss=0.2624, pruned_loss=0.04696, over 7374.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2537, pruned_loss=0.03697, over 1425942.08 frames.], batch size: 23, lr: 4.09e-04
2022-05-14 23:35:25,969 INFO [train.py:812] (4/8) Epoch 19, batch 2350, loss[loss=0.1446, simple_loss=0.2251, pruned_loss=0.03209, over 7281.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2535, pruned_loss=0.03676, over 1422823.14 frames.], batch size: 17, lr: 4.09e-04
2022-05-14 23:36:25,350 INFO [train.py:812] (4/8) Epoch 19, batch 2400, loss[loss=0.1702, simple_loss=0.2618, pruned_loss=0.03928, over 7147.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2541, pruned_loss=0.03735, over 1418791.83 frames.], batch size: 20, lr: 4.09e-04
2022-05-14 23:37:24,210 INFO [train.py:812] (4/8) Epoch 19, batch 2450, loss[loss=0.1695, simple_loss=0.2568, pruned_loss=0.04107, over 7146.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2533, pruned_loss=0.03704, over 1421408.90 frames.], batch size: 20, lr: 4.09e-04
2022-05-14 23:38:23,513 INFO [train.py:812] (4/8) Epoch 19, batch 2500, loss[loss=0.1668, simple_loss=0.2556, pruned_loss=0.03902, over 7183.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2528, pruned_loss=0.03694, over 1421345.53 frames.], batch size: 26, lr: 4.09e-04
2022-05-14 23:39:22,982 INFO [train.py:812] (4/8) Epoch 19, batch 2550, loss[loss=0.1791, simple_loss=0.2723, pruned_loss=0.04293, over 7263.00 frames.], tot_loss[loss=0.1625, simple_loss=0.252, pruned_loss=0.03644, over 1421187.23 frames.], batch size: 24, lr: 4.08e-04
2022-05-14 23:40:21,747 INFO [train.py:812] (4/8) Epoch 19, batch 2600, loss[loss=0.1705, simple_loss=0.239, pruned_loss=0.05105, over 7004.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2532, pruned_loss=0.03706, over 1425432.47 frames.], batch size: 16, lr: 4.08e-04
2022-05-14 23:41:20,969 INFO [train.py:812] (4/8) Epoch 19, batch 2650, loss[loss=0.1676, simple_loss=0.2633, pruned_loss=0.03591, over 7281.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2535, pruned_loss=0.03711, over 1426884.87 frames.], batch size: 24, lr: 4.08e-04
2022-05-14 23:42:20,838 INFO [train.py:812] (4/8) Epoch 19, batch 2700, loss[loss=0.1875, simple_loss=0.2795, pruned_loss=0.04777, over 7290.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2537, pruned_loss=0.03701, over 1429719.70 frames.], batch size: 25, lr: 4.08e-04
2022-05-14 23:43:20,352 INFO [train.py:812] (4/8) Epoch 19, batch 2750, loss[loss=0.1489, simple_loss=0.2513, pruned_loss=0.02326, over 7411.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2541, pruned_loss=0.03683, over 1428996.88 frames.], batch size: 21, lr: 4.08e-04
2022-05-14 23:44:19,811 INFO [train.py:812] (4/8) Epoch 19, batch 2800, loss[loss=0.1861, simple_loss=0.2831, pruned_loss=0.04456, over 7065.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2541, pruned_loss=0.03674, over 1430218.45 frames.], batch size: 18, lr: 4.08e-04
2022-05-14 23:45:18,636 INFO [train.py:812] (4/8) Epoch 19, batch 2850, loss[loss=0.1606, simple_loss=0.2657, pruned_loss=0.02772, over 7154.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2547, pruned_loss=0.03715, over 1427629.73 frames.], batch size: 19, lr: 4.08e-04
2022-05-14 23:46:17,158 INFO [train.py:812] (4/8) Epoch 19, batch 2900, loss[loss=0.1863, simple_loss=0.2734, pruned_loss=0.04959, over 7140.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2541, pruned_loss=0.03719, over 1424852.32 frames.], batch size: 26, lr: 4.08e-04
2022-05-14 23:47:15,886 INFO [train.py:812] (4/8) Epoch 19, batch 2950, loss[loss=0.1461, simple_loss=0.2248, pruned_loss=0.0337, over 7281.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2541, pruned_loss=0.03686, over 1430459.22 frames.], batch size: 17, lr: 4.08e-04
2022-05-14 23:48:15,119 INFO [train.py:812] (4/8) Epoch 19, batch 3000, loss[loss=0.18, simple_loss=0.2613, pruned_loss=0.04932, over 5374.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2536, pruned_loss=0.03671, over 1430471.76 frames.], batch size: 53, lr: 4.07e-04
2022-05-14 23:48:15,120 INFO [train.py:832] (4/8) Computing validation loss
2022-05-14 23:48:22,685 INFO [train.py:841] (4/8) Epoch 19, validation: loss=0.1531, simple_loss=0.2523, pruned_loss=0.02694, over 698248.00 frames.
2022-05-14 23:49:22,406 INFO [train.py:812] (4/8) Epoch 19, batch 3050, loss[loss=0.1799, simple_loss=0.2699, pruned_loss=0.04498, over 7196.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2547, pruned_loss=0.03723, over 1431498.53 frames.], batch size: 23, lr: 4.07e-04
2022-05-14 23:50:21,361 INFO [train.py:812] (4/8) Epoch 19, batch 3100, loss[loss=0.1608, simple_loss=0.2503, pruned_loss=0.03568, over 6327.00 frames.], tot_loss[loss=0.164, simple_loss=0.2541, pruned_loss=0.03696, over 1432159.73 frames.], batch size: 37, lr: 4.07e-04
2022-05-14 23:51:20,040 INFO [train.py:812] (4/8) Epoch 19, batch 3150, loss[loss=0.1276, simple_loss=0.2165, pruned_loss=0.01933, over 7283.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2549, pruned_loss=0.03728, over 1428942.05 frames.], batch size: 18, lr: 4.07e-04
2022-05-14 23:52:18,559 INFO [train.py:812] (4/8) Epoch 19, batch 3200, loss[loss=0.1758, simple_loss=0.2709, pruned_loss=0.04029, over 7150.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2556, pruned_loss=0.03772, over 1427645.63 frames.], batch size: 19, lr: 4.07e-04
2022-05-14 23:53:18,019 INFO [train.py:812] (4/8) Epoch 19, batch 3250, loss[loss=0.155, simple_loss=0.2433, pruned_loss=0.0333, over 7350.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2555, pruned_loss=0.03735, over 1424538.07 frames.], batch size: 19, lr: 4.07e-04
2022-05-14 23:54:16,320 INFO [train.py:812] (4/8) Epoch 19, batch 3300, loss[loss=0.1639, simple_loss=0.2507, pruned_loss=0.03858, over 6438.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2561, pruned_loss=0.03762, over 1425235.66 frames.], batch size: 37, lr: 4.07e-04
2022-05-14 23:55:15,322 INFO [train.py:812] (4/8) Epoch 19, batch 3350, loss[loss=0.1558, simple_loss=0.2565, pruned_loss=0.02761, over 7115.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2553, pruned_loss=0.03717, over 1424537.31 frames.], batch size: 21, lr: 4.07e-04
2022-05-14 23:56:14,423 INFO [train.py:812] (4/8) Epoch 19, batch 3400, loss[loss=0.1476, simple_loss=0.2295, pruned_loss=0.03282, over 7276.00 frames.], tot_loss[loss=0.164, simple_loss=0.2543, pruned_loss=0.03682, over 1424706.04 frames.], batch size: 18, lr: 4.06e-04
2022-05-14 23:57:14,018 INFO [train.py:812] (4/8) Epoch 19, batch 3450, loss[loss=0.1379, simple_loss=0.2279, pruned_loss=0.02395, over 7351.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2538, pruned_loss=0.03696, over 1420633.98 frames.], batch size: 19, lr: 4.06e-04
2022-05-14 23:58:13,018 INFO [train.py:812] (4/8) Epoch 19, batch 3500, loss[loss=0.1573, simple_loss=0.238, pruned_loss=0.03829, over 7271.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2527, pruned_loss=0.03654, over 1422844.98 frames.], batch size: 18, lr: 4.06e-04
2022-05-14 23:59:12,611 INFO [train.py:812] (4/8) Epoch 19, batch 3550, loss[loss=0.1563, simple_loss=0.2359, pruned_loss=0.03834, over 7141.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2524, pruned_loss=0.03631, over 1423229.24 frames.], batch size: 17, lr: 4.06e-04
2022-05-15 00:00:11,606 INFO [train.py:812] (4/8) Epoch 19, batch 3600, loss[loss=0.2096, simple_loss=0.2877, pruned_loss=0.06569, over 7202.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2532, pruned_loss=0.03669, over 1420978.23 frames.], batch size: 23, lr: 4.06e-04
2022-05-15 00:01:11,003 INFO [train.py:812] (4/8) Epoch 19, batch 3650, loss[loss=0.1295, simple_loss=0.2203, pruned_loss=0.01936, over 7321.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2538, pruned_loss=0.03678, over 1414717.27 frames.], batch size: 20, lr: 4.06e-04
2022-05-15 00:02:10,019 INFO [train.py:812] (4/8) Epoch 19, batch 3700, loss[loss=0.1675, simple_loss=0.2606, pruned_loss=0.03721, over 7411.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2543, pruned_loss=0.03691, over 1416781.15 frames.], batch size: 21, lr: 4.06e-04
2022-05-15 00:03:09,356 INFO [train.py:812] (4/8) Epoch 19, batch 3750, loss[loss=0.1759, simple_loss=0.2662, pruned_loss=0.04277, over 7383.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2542, pruned_loss=0.03734, over 1413089.04 frames.], batch size: 23, lr: 4.06e-04
2022-05-15 00:04:08,159 INFO [train.py:812] (4/8) Epoch 19, batch 3800, loss[loss=0.1506, simple_loss=0.2336, pruned_loss=0.03375, over 7343.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2551, pruned_loss=0.03774, over 1418601.43 frames.], batch size: 19, lr: 4.06e-04
2022-05-15 00:05:06,748 INFO [train.py:812] (4/8) Epoch 19, batch 3850, loss[loss=0.1569, simple_loss=0.2392, pruned_loss=0.03731, over 7167.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03799, over 1416850.23 frames.], batch size: 18, lr: 4.05e-04
2022-05-15 00:06:04,371 INFO [train.py:812] (4/8) Epoch 19, batch 3900, loss[loss=0.1527, simple_loss=0.2508, pruned_loss=0.02734, over 7110.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2556, pruned_loss=0.03807, over 1414632.58 frames.], batch size: 21, lr: 4.05e-04
2022-05-15 00:07:04,144 INFO [train.py:812] (4/8) Epoch 19, batch 3950, loss[loss=0.1869, simple_loss=0.2799, pruned_loss=0.04693, over 7169.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2553, pruned_loss=0.03777, over 1416444.90 frames.], batch size: 18, lr: 4.05e-04
2022-05-15 00:08:03,280 INFO [train.py:812] (4/8) Epoch 19, batch 4000, loss[loss=0.1776, simple_loss=0.2689, pruned_loss=0.04319, over 5072.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2552, pruned_loss=0.03788, over 1417154.51 frames.], batch size: 53, lr: 4.05e-04
2022-05-15 00:09:00,795 INFO [train.py:812] (4/8) Epoch 19, batch 4050, loss[loss=0.1469, simple_loss=0.2252, pruned_loss=0.03429, over 6851.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2541, pruned_loss=0.03752, over 1416120.32 frames.], batch size: 15, lr: 4.05e-04
2022-05-15 00:09:59,480 INFO [train.py:812] (4/8) Epoch 19, batch 4100, loss[loss=0.1979, simple_loss=0.2834, pruned_loss=0.05625, over 4851.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2543, pruned_loss=0.0374, over 1416366.83 frames.], batch size: 52, lr: 4.05e-04
2022-05-15 00:10:57,145 INFO [train.py:812] (4/8) Epoch 19, batch 4150, loss[loss=0.1563, simple_loss=0.2424, pruned_loss=0.03512, over 7379.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2541, pruned_loss=0.03747, over 1421280.54 frames.], batch size: 23, lr: 4.05e-04
2022-05-15 00:11:56,833 INFO [train.py:812] (4/8) Epoch 19, batch 4200, loss[loss=0.1947, simple_loss=0.2746, pruned_loss=0.05741, over 7205.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2532, pruned_loss=0.03703, over 1420026.08 frames.], batch size: 23, lr: 4.05e-04
2022-05-15 00:12:56,145 INFO [train.py:812] (4/8) Epoch 19, batch 4250, loss[loss=0.1375, simple_loss=0.2199, pruned_loss=0.02748, over 6798.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2529, pruned_loss=0.03669, over 1419858.09 frames.], batch size: 15, lr: 4.04e-04
2022-05-15 00:14:05,103 INFO [train.py:812] (4/8) Epoch 19, batch 4300, loss[loss=0.1714, simple_loss=0.2605, pruned_loss=0.0411, over 7172.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2532, pruned_loss=0.03696, over 1419296.48 frames.], batch size: 26, lr: 4.04e-04
2022-05-15 00:15:04,948 INFO [train.py:812] (4/8) Epoch 19, batch 4350, loss[loss=0.142, simple_loss=0.2285, pruned_loss=0.02777, over 7158.00 frames.], tot_loss[loss=0.1627, simple_loss=0.252, pruned_loss=0.03674, over 1416709.74 frames.], batch size: 18, lr: 4.04e-04
2022-05-15 00:16:03,312 INFO [train.py:812] (4/8) Epoch 19, batch 4400, loss[loss=0.1741, simple_loss=0.2672, pruned_loss=0.04048, over 6230.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2523, pruned_loss=0.03696, over 1412256.48 frames.], batch size: 38, lr: 4.04e-04
2022-05-15 00:17:02,493 INFO [train.py:812] (4/8) Epoch 19, batch 4450, loss[loss=0.1255, simple_loss=0.2076, pruned_loss=0.02167, over 7269.00 frames.], tot_loss[loss=0.1622, simple_loss=0.251, pruned_loss=0.0367, over 1407420.11 frames.], batch size: 16, lr: 4.04e-04
2022-05-15 00:18:02,040 INFO [train.py:812] (4/8) Epoch 19, batch 4500, loss[loss=0.1567, simple_loss=0.2426, pruned_loss=0.03536, over 7147.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2523, pruned_loss=0.03754, over 1394028.26 frames.], batch size: 20, lr: 4.04e-04
2022-05-15 00:19:01,078 INFO [train.py:812] (4/8) Epoch 19, batch 4550, loss[loss=0.1825, simple_loss=0.2761, pruned_loss=0.04446, over 6422.00 frames.], tot_loss[loss=0.1643, simple_loss=0.252, pruned_loss=0.03828, over 1366208.75 frames.], batch size: 37, lr: 4.04e-04
2022-05-15 00:20:09,405 INFO [train.py:812] (4/8) Epoch 20, batch 0, loss[loss=0.1393, simple_loss=0.2383, pruned_loss=0.02012, over 7352.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2383, pruned_loss=0.02012, over 7352.00 frames.], batch size: 19, lr: 3.94e-04
2022-05-15 00:21:09,542 INFO [train.py:812] (4/8) Epoch 20, batch 50, loss[loss=0.152, simple_loss=0.2386, pruned_loss=0.03267, over 7265.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2533, pruned_loss=0.03585, over 320481.96 frames.], batch size: 18, lr: 3.94e-04
2022-05-15 00:22:08,833 INFO [train.py:812] (4/8) Epoch 20, batch 100, loss[loss=0.1709, simple_loss=0.2512, pruned_loss=0.04533, over 5117.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2527, pruned_loss=0.03596, over 565573.73 frames.], batch size: 52, lr: 3.94e-04
2022-05-15 00:23:08,481 INFO [train.py:812] (4/8) Epoch 20, batch 150, loss[loss=0.1596, simple_loss=0.2587, pruned_loss=0.03023, over 7319.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2555, pruned_loss=0.03643, over 755436.19 frames.], batch size: 21, lr: 3.94e-04
2022-05-15 00:24:07,755 INFO [train.py:812] (4/8) Epoch 20, batch 200, loss[loss=0.1667, simple_loss=0.2582, pruned_loss=0.03763, over 7329.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2556, pruned_loss=0.0366, over 903001.14 frames.], batch size: 22, lr: 3.93e-04
2022-05-15 00:25:08,006 INFO [train.py:812] (4/8) Epoch 20, batch 250, loss[loss=0.1805, simple_loss=0.2774, pruned_loss=0.04185, over 7333.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2544, pruned_loss=0.03604, over 1022438.30 frames.], batch size: 22, lr: 3.93e-04
2022-05-15 00:26:07,279 INFO [train.py:812] (4/8) Epoch 20, batch 300, loss[loss=0.1599, simple_loss=0.2498, pruned_loss=0.03495, over 7183.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2552, pruned_loss=0.0363, over 1111675.97 frames.], batch size: 23, lr: 3.93e-04
2022-05-15 00:27:07,180 INFO [train.py:812] (4/8) Epoch 20, batch 350, loss[loss=0.1534, simple_loss=0.247, pruned_loss=0.02986, over 7145.00 frames.], tot_loss[loss=0.164, simple_loss=0.2553, pruned_loss=0.03637, over 1183866.61 frames.], batch size: 20, lr: 3.93e-04
2022-05-15 00:28:05,122 INFO [train.py:812] (4/8) Epoch 20, batch 400, loss[loss=0.1872, simple_loss=0.28, pruned_loss=0.04723, over 7152.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2559, pruned_loss=0.03665, over 1236919.89 frames.], batch size: 20, lr: 3.93e-04
2022-05-15 00:29:03,591 INFO [train.py:812] (4/8) Epoch 20, batch 450, loss[loss=0.1923, simple_loss=0.291, pruned_loss=0.04682, over 7373.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2565, pruned_loss=0.03712, over 1274714.46 frames.], batch size: 23, lr: 3.93e-04
2022-05-15 00:30:01,851 INFO [train.py:812] (4/8) Epoch 20, batch 500, loss[loss=0.1357, simple_loss=0.2344, pruned_loss=0.01849, over 7217.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2554, pruned_loss=0.03677, over 1306916.14 frames.], batch size: 21, lr: 3.93e-04
2022-05-15 00:31:00,461 INFO [train.py:812] (4/8) Epoch 20, batch 550, loss[loss=0.1505, simple_loss=0.2514, pruned_loss=0.02484, over 6761.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2545, pruned_loss=0.03638, over 1333609.76 frames.], batch size: 31, lr: 3.93e-04
2022-05-15 00:32:00,098 INFO [train.py:812] (4/8) Epoch 20, batch 600, loss[loss=0.1567, simple_loss=0.2415, pruned_loss=0.03589, over 7159.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2542, pruned_loss=0.03654, over 1356049.75 frames.], batch size: 18, lr: 3.93e-04
2022-05-15 00:32:59,170 INFO [train.py:812] (4/8) Epoch 20, batch 650, loss[loss=0.1527, simple_loss=0.2443, pruned_loss=0.03054, over 7167.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2536, pruned_loss=0.03651, over 1369700.89 frames.], batch size: 18, lr: 3.92e-04
2022-05-15 00:33:55,660 INFO [train.py:812] (4/8) Epoch 20, batch 700, loss[loss=0.1815, simple_loss=0.2683, pruned_loss=0.04736, over 7245.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2542, pruned_loss=0.03644, over 1383457.79 frames.], batch size: 20, lr: 3.92e-04
2022-05-15 00:34:54,549 INFO [train.py:812] (4/8) Epoch 20, batch 750, loss[loss=0.153, simple_loss=0.2549, pruned_loss=0.0256, over 7298.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2527, pruned_loss=0.03596, over 1393680.48 frames.], batch size: 25, lr: 3.92e-04
2022-05-15 00:35:51,667 INFO [train.py:812] (4/8) Epoch 20, batch 800, loss[loss=0.1501, simple_loss=0.2286, pruned_loss=0.03577, over 7417.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2522, pruned_loss=0.03581, over 1402859.28 frames.], batch size: 18, lr: 3.92e-04
2022-05-15 00:36:56,565 INFO [train.py:812] (4/8) Epoch 20, batch 850, loss[loss=0.1621, simple_loss=0.2618, pruned_loss=0.03118, over 7077.00 frames.], tot_loss[loss=0.1616, simple_loss=0.252, pruned_loss=0.03556, over 1410720.69 frames.], batch size: 28, lr: 3.92e-04
2022-05-15 00:37:55,362 INFO [train.py:812] (4/8) Epoch 20, batch 900, loss[loss=0.1734, simple_loss=0.2597, pruned_loss=0.04353, over 7356.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2513, pruned_loss=0.03561, over 1415822.68 frames.], batch size: 19, lr: 3.92e-04
2022-05-15 00:38:53,705 INFO [train.py:812] (4/8) Epoch 20, batch 950, loss[loss=0.1536, simple_loss=0.2569, pruned_loss=0.02518, over 7229.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2524, pruned_loss=0.03606, over 1419729.41 frames.], batch size: 20, lr: 3.92e-04
2022-05-15 00:39:52,437 INFO [train.py:812] (4/8) Epoch 20, batch 1000, loss[loss=0.1619, simple_loss=0.2556, pruned_loss=0.03409, over 7287.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2516, pruned_loss=0.03573, over 1420562.06 frames.], batch size: 24, lr: 3.92e-04
2022-05-15 00:40:51,837 INFO [train.py:812] (4/8) Epoch 20, batch 1050, loss[loss=0.1878, simple_loss=0.2727, pruned_loss=0.05139, over 7179.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2523, pruned_loss=0.03607, over 1419417.07 frames.], batch size: 22, lr: 3.92e-04
2022-05-15 00:41:50,552 INFO [train.py:812] (4/8) Epoch 20, batch 1100, loss[loss=0.1682, simple_loss=0.2503, pruned_loss=0.04304, over 7218.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2525, pruned_loss=0.03632, over 1416113.13 frames.], batch size: 22, lr: 3.91e-04
2022-05-15 00:42:49,023 INFO [train.py:812] (4/8) Epoch 20, batch 1150, loss[loss=0.1886, simple_loss=0.2829, pruned_loss=0.04717, over 7280.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2534, pruned_loss=0.03641, over 1420281.07 frames.], batch size: 24, lr: 3.91e-04
2022-05-15 00:43:48,222 INFO [train.py:812] (4/8) Epoch 20, batch 1200, loss[loss=0.1725, simple_loss=0.2735, pruned_loss=0.03572, over 7340.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2518, pruned_loss=0.03596, over 1425010.63 frames.], batch size: 22, lr: 3.91e-04
2022-05-15 00:44:47,694 INFO [train.py:812] (4/8) Epoch 20, batch 1250, loss[loss=0.1364, simple_loss=0.2201, pruned_loss=0.02636, over 7149.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2518, pruned_loss=0.03589, over 1425995.28 frames.], batch size: 17, lr: 3.91e-04
2022-05-15 00:45:46,808 INFO [train.py:812] (4/8) Epoch 20, batch 1300, loss[loss=0.1678, simple_loss=0.263, pruned_loss=0.03637, over 7103.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2517, pruned_loss=0.03582, over 1427021.46 frames.], batch size: 21, lr: 3.91e-04
2022-05-15 00:46:46,850 INFO [train.py:812] (4/8) Epoch 20, batch 1350, loss[loss=0.2025, simple_loss=0.2908, pruned_loss=0.05708, over 7204.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2519, pruned_loss=0.03629, over 1428699.30 frames.], batch size: 22, lr: 3.91e-04
2022-05-15 00:47:55,896 INFO [train.py:812] (4/8) Epoch 20, batch 1400, loss[loss=0.1649, simple_loss=0.2664, pruned_loss=0.03169, over 7195.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2524, pruned_loss=0.03659, over 1430023.53 frames.], batch size: 26, lr: 3.91e-04
2022-05-15 00:48:55,552 INFO [train.py:812] (4/8) Epoch 20, batch 1450, loss[loss=0.1799, simple_loss=0.2635, pruned_loss=0.04815, over 7217.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2537, pruned_loss=0.03705, over 1429147.78 frames.], batch size: 26, lr: 3.91e-04
2022-05-15 00:49:54,738 INFO [train.py:812] (4/8) Epoch 20, batch 1500, loss[loss=0.2013, simple_loss=0.2844, pruned_loss=0.05913, over 7369.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2552, pruned_loss=0.03771, over 1427368.73 frames.], batch size: 23, lr: 3.91e-04
2022-05-15 00:51:04,079 INFO [train.py:812] (4/8) Epoch 20, batch 1550, loss[loss=0.1471, simple_loss=0.2316, pruned_loss=0.03135, over 7441.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2546, pruned_loss=0.03746, over 1429085.41 frames.], batch size: 20, lr: 3.91e-04
2022-05-15 00:52:22,069 INFO [train.py:812] (4/8) Epoch 20, batch 1600, loss[loss=0.1657, simple_loss=0.2638, pruned_loss=0.03385, over 7324.00 frames.], tot_loss[loss=0.1642, simple_loss=0.254, pruned_loss=0.03718, over 1424595.06 frames.], batch size: 22, lr: 3.90e-04
2022-05-15 00:53:19,539 INFO [train.py:812] (4/8) Epoch 20, batch 1650, loss[loss=0.1758, simple_loss=0.2689, pruned_loss=0.04135, over 7195.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2543, pruned_loss=0.03709, over 1422338.13 frames.], batch size: 23, lr: 3.90e-04
2022-05-15 00:54:36,071 INFO [train.py:812] (4/8) Epoch 20, batch 1700, loss[loss=0.1568, simple_loss=0.245, pruned_loss=0.03435, over 7159.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2536, pruned_loss=0.03683, over 1421226.89 frames.], batch size: 19, lr: 3.90e-04
2022-05-15 00:55:43,687 INFO [train.py:812] (4/8) Epoch 20, batch 1750, loss[loss=0.1531, simple_loss=0.25, pruned_loss=0.02809, over 7338.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2529, pruned_loss=0.03667, over 1426369.49 frames.], batch size: 22, lr: 3.90e-04
2022-05-15 00:56:42,597 INFO [train.py:812] (4/8) Epoch 20, batch 1800, loss[loss=0.1741, simple_loss=0.2762, pruned_loss=0.03597, over 7298.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2533, pruned_loss=0.03657, over 1426306.84 frames.], batch size: 25, lr: 3.90e-04
2022-05-15 00:57:42,326 INFO [train.py:812] (4/8) Epoch 20, batch 1850, loss[loss=0.154, simple_loss=0.242, pruned_loss=0.03304, over 7061.00 frames.], tot_loss[loss=0.163, simple_loss=0.2532, pruned_loss=0.03639, over 1429321.09 frames.], batch size: 18, lr: 3.90e-04
2022-05-15 00:58:41,679 INFO [train.py:812] (4/8) Epoch 20, batch 1900, loss[loss=0.1492, simple_loss=0.2426, pruned_loss=0.02797, over 7244.00 frames.], tot_loss[loss=0.1635, simple_loss=0.254, pruned_loss=0.03654, over 1429853.16 frames.], batch size: 20, lr: 3.90e-04
2022-05-15 00:59:40,058 INFO [train.py:812] (4/8) Epoch 20, batch 1950, loss[loss=0.1584, simple_loss=0.2587, pruned_loss=0.02902, over 6414.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2535, pruned_loss=0.03653, over 1430512.27 frames.], batch size: 38, lr: 3.90e-04
2022-05-15 01:00:37,501 INFO [train.py:812] (4/8) Epoch 20, batch 2000, loss[loss=0.152, simple_loss=0.2467, pruned_loss=0.02861, over 7236.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2521, pruned_loss=0.03592, over 1431242.03 frames.], batch size: 20, lr: 3.90e-04
2022-05-15 01:01:35,458 INFO [train.py:812] (4/8) Epoch 20, batch 2050, loss[loss=0.1658, simple_loss=0.2577, pruned_loss=0.03695, over 7222.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2514, pruned_loss=0.0358, over 1430471.81 frames.], batch size: 21, lr: 3.89e-04
2022-05-15 01:02:33,050 INFO [train.py:812] (4/8) Epoch 20, batch 2100, loss[loss=0.1555, simple_loss=0.2462, pruned_loss=0.03239, over 7431.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2518, pruned_loss=0.03599, over 1432307.13 frames.], batch size: 20, lr: 3.89e-04
2022-05-15 01:03:30,912 INFO [train.py:812] (4/8) Epoch 20, batch 2150, loss[loss=0.1596, simple_loss=0.257, pruned_loss=0.03116, over 7209.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2527, pruned_loss=0.03679, over 1425848.57 frames.], batch size: 22, lr: 3.89e-04
2022-05-15 01:04:30,267 INFO [train.py:812] (4/8) Epoch 20, batch 2200, loss[loss=0.1258, simple_loss=0.2111, pruned_loss=0.02032, over 6808.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2527, pruned_loss=0.03692, over 1421538.81 frames.], batch size: 15, lr: 3.89e-04
2022-05-15 01:05:28,863 INFO [train.py:812] (4/8) Epoch 20, batch 2250, loss[loss=0.1754, simple_loss=0.2715, pruned_loss=0.0397, over 7132.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2526, pruned_loss=0.0366, over 1423581.61 frames.], batch size: 20, lr: 3.89e-04
2022-05-15 01:06:27,811 INFO [train.py:812] (4/8) Epoch 20, batch 2300, loss[loss=0.1756, simple_loss=0.2637, pruned_loss=0.04371, over 7374.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2522, pruned_loss=0.0365, over 1423759.80 frames.], batch size: 23, lr: 3.89e-04
2022-05-15 01:07:25,478 INFO [train.py:812] (4/8) Epoch 20, batch 2350, loss[loss=0.173, simple_loss=0.2722, pruned_loss=0.03685, over 7321.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2526, pruned_loss=0.03614, over 1422135.94 frames.], batch size: 21, lr: 3.89e-04
2022-05-15 01:08:24,201 INFO [train.py:812] (4/8) Epoch 20, batch 2400, loss[loss=0.1598, simple_loss=0.2483, pruned_loss=0.03562, over 7444.00 frames.], tot_loss[loss=0.1622, simple_loss=0.252, pruned_loss=0.03615, over 1424585.96 frames.], batch size: 20, lr: 3.89e-04
2022-05-15 01:09:23,908 INFO [train.py:812] (4/8) Epoch 20, batch 2450, loss[loss=0.1597, simple_loss=0.2553, pruned_loss=0.03207, over 7123.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2518, pruned_loss=0.03586, over 1427630.04 frames.], batch size: 28, lr: 3.89e-04
2022-05-15 01:10:23,014 INFO [train.py:812] (4/8) Epoch 20, batch 2500, loss[loss=0.1724, simple_loss=0.2757, pruned_loss=0.03457, over 7212.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2508, pruned_loss=0.03533, over 1426217.76 frames.], batch size: 26, lr: 3.88e-04
2022-05-15 01:11:22,813 INFO [train.py:812] (4/8) Epoch 20, batch 2550, loss[loss=0.1933, simple_loss=0.2871, pruned_loss=0.04972, over 7330.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2521, pruned_loss=0.03604, over 1424848.00 frames.], batch size: 20, lr: 3.88e-04
2022-05-15 01:12:22,065 INFO [train.py:812] (4/8) Epoch 20, batch 2600, loss[loss=0.1656, simple_loss=0.2543, pruned_loss=0.03846, over 6731.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2527, pruned_loss=0.03614, over 1425452.18 frames.], batch size: 31, lr: 3.88e-04
2022-05-15 01:13:22,174 INFO [train.py:812] (4/8) Epoch 20, batch 2650, loss[loss=0.1594, simple_loss=0.2317, pruned_loss=0.0436, over 7020.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2514, pruned_loss=0.03552, over 1427405.76 frames.], batch size: 16, lr: 3.88e-04
2022-05-15 01:14:21,651 INFO [train.py:812] (4/8) Epoch 20, batch 2700, loss[loss=0.1794, simple_loss=0.269, pruned_loss=0.04497, over 7381.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2516, pruned_loss=0.03575, over 1428483.18 frames.], batch size: 23, lr: 3.88e-04
2022-05-15 01:15:21,494 INFO [train.py:812] (4/8) Epoch 20, batch 2750, loss[loss=0.1587, simple_loss=0.2511, pruned_loss=0.03318, over 7211.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2518, pruned_loss=0.03551, over 1427289.63 frames.], batch size: 23, lr: 3.88e-04
2022-05-15 01:16:20,993 INFO [train.py:812] (4/8) Epoch 20, batch 2800, loss[loss=0.1595, simple_loss=0.2555, pruned_loss=0.03173, over 7148.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2517, pruned_loss=0.03524, over 1430977.12 frames.], batch size: 18, lr: 3.88e-04
2022-05-15 01:17:20,826 INFO [train.py:812] (4/8) Epoch 20, batch 2850, loss[loss=0.1639, simple_loss=0.2547, pruned_loss=0.03655, over 7405.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2519, pruned_loss=0.03544, over 1432617.22 frames.], batch size: 21, lr: 3.88e-04
2022-05-15 01:18:20,015 INFO [train.py:812] (4/8) Epoch 20, batch 2900, loss[loss=0.1859, simple_loss=0.2756, pruned_loss=0.04807, over 7190.00 frames.], tot_loss[loss=0.1611, simple_loss=0.251, pruned_loss=0.03562, over 1428343.16 frames.], batch size: 26, lr: 3.88e-04
2022-05-15 01:19:19,549 INFO [train.py:812] (4/8) Epoch 20, batch 2950, loss[loss=0.1647, simple_loss=0.2548, pruned_loss=0.03723, over 7224.00 frames.], tot_loss[loss=0.162, simple_loss=0.252, pruned_loss=0.03594, over 1432430.04 frames.], batch size: 20, lr: 3.87e-04
2022-05-15 01:20:18,530 INFO [train.py:812] (4/8) Epoch 20, batch 3000, loss[loss=0.1876, simple_loss=0.28, pruned_loss=0.04763, over 7382.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2527, pruned_loss=0.03581, over 1431264.95 frames.], batch size: 23, lr: 3.87e-04
2022-05-15 01:20:18,532 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 01:20:27,133 INFO [train.py:841] (4/8) Epoch 20, validation: loss=0.1532, simple_loss=0.2519, pruned_loss=0.02723, over 698248.00 frames.
2022-05-15 01:21:26,367 INFO [train.py:812] (4/8) Epoch 20, batch 3050, loss[loss=0.1695, simple_loss=0.2478, pruned_loss=0.04556, over 7152.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2521, pruned_loss=0.03562, over 1432455.52 frames.], batch size: 19, lr: 3.87e-04
2022-05-15 01:22:25,319 INFO [train.py:812] (4/8) Epoch 20, batch 3100, loss[loss=0.1461, simple_loss=0.2443, pruned_loss=0.02393, over 7121.00 frames.], tot_loss[loss=0.1614, simple_loss=0.252, pruned_loss=0.03534, over 1431857.40 frames.], batch size: 21, lr: 3.87e-04
2022-05-15 01:23:24,548 INFO [train.py:812] (4/8) Epoch 20, batch 3150, loss[loss=0.1388, simple_loss=0.2368, pruned_loss=0.02037, over 7268.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2517, pruned_loss=0.03533, over 1432714.48 frames.], batch size: 18, lr: 3.87e-04
2022-05-15 01:24:21,335 INFO [train.py:812] (4/8) Epoch 20, batch 3200, loss[loss=0.1853, simple_loss=0.277, pruned_loss=0.04676, over 6733.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2515, pruned_loss=0.03537, over 1431535.49 frames.], batch size: 31, lr: 3.87e-04
2022-05-15 01:25:18,758 INFO [train.py:812] (4/8) Epoch 20, batch 3250, loss[loss=0.1473, simple_loss=0.2331, pruned_loss=0.03079, over 7060.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2517, pruned_loss=0.03552, over 1428428.15 frames.], batch size: 18, lr: 3.87e-04
2022-05-15 01:26:16,471 INFO [train.py:812] (4/8) Epoch 20, batch 3300, loss[loss=0.1487, simple_loss=0.2325, pruned_loss=0.03249, over 7140.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2518, pruned_loss=0.03595, over 1426522.41 frames.], batch size: 17, lr: 3.87e-04
2022-05-15 01:27:14,072 INFO [train.py:812] (4/8) Epoch 20, batch 3350, loss[loss=0.1657, simple_loss=0.2598, pruned_loss=0.03577, over 7142.00 frames.], tot_loss[loss=0.1621, simple_loss=0.252, pruned_loss=0.03608, over 1427299.90 frames.], batch size: 20, lr: 3.87e-04
2022-05-15 01:28:13,190 INFO [train.py:812] (4/8) Epoch 20, batch 3400, loss[loss=0.1242, simple_loss=0.199, pruned_loss=0.02472, over 7281.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2517, pruned_loss=0.03601, over 1427275.97 frames.], batch size: 17, lr: 3.87e-04
2022-05-15 01:29:12,303 INFO [train.py:812] (4/8) Epoch 20, batch 3450, loss[loss=0.1578, simple_loss=0.2532, pruned_loss=0.0312, over 7226.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2525, pruned_loss=0.0363, over 1425203.89 frames.], batch size: 20, lr: 3.86e-04
2022-05-15 01:30:11,787 INFO [train.py:812] (4/8) Epoch 20, batch 3500, loss[loss=0.155, simple_loss=0.2455, pruned_loss=0.03219, over 7262.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2522, pruned_loss=0.03639, over 1424111.40 frames.], batch size: 19, lr: 3.86e-04
2022-05-15 01:31:11,508 INFO [train.py:812] (4/8) Epoch 20, batch 3550, loss[loss=0.1581, simple_loss=0.2545, pruned_loss=0.0308, over 7120.00 frames.], tot_loss[loss=0.163, simple_loss=0.253, pruned_loss=0.03653, over 1427011.06 frames.], batch size: 21, lr: 3.86e-04
2022-05-15 01:32:11,005 INFO [train.py:812] (4/8) Epoch 20, batch 3600, loss[loss=0.1942, simple_loss=0.2878, pruned_loss=0.05032, over 7190.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2536, pruned_loss=0.0364, over 1429456.38 frames.], batch size: 23, lr: 3.86e-04
2022-05-15 01:33:10,980 INFO [train.py:812] (4/8) Epoch 20, batch 3650, loss[loss=0.1808, simple_loss=0.2798, pruned_loss=0.04085, over 7316.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2536, pruned_loss=0.03645, over 1430704.81 frames.], batch size: 21, lr: 3.86e-04
2022-05-15 01:34:09,102 INFO [train.py:812] (4/8) Epoch 20, batch 3700, loss[loss=0.1308, simple_loss=0.2176, pruned_loss=0.02204, over 7161.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2536, pruned_loss=0.03625, over 1432336.67 frames.], batch size: 18, lr: 3.86e-04
2022-05-15 01:35:08,009 INFO [train.py:812] (4/8) Epoch 20, batch 3750, loss[loss=0.1978, simple_loss=0.2854, pruned_loss=0.05508, over 7051.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2532, pruned_loss=0.03628, over 1426089.08 frames.], batch size: 28, lr: 3.86e-04
2022-05-15 01:36:06,434 INFO [train.py:812] (4/8) Epoch 20, batch 3800, loss[loss=0.14, simple_loss=0.2366, pruned_loss=0.02165, over 7325.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2532, pruned_loss=0.03663, over 1421532.67 frames.], batch size: 20, lr: 3.86e-04
2022-05-15 01:37:04,402 INFO [train.py:812] (4/8) Epoch 20, batch 3850, loss[loss=0.1384, simple_loss=0.2228, pruned_loss=0.02703, over 7269.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2526, pruned_loss=0.03626, over 1419921.47 frames.], batch size: 17, lr: 3.86e-04
2022-05-15 01:38:02,163 INFO [train.py:812] (4/8) Epoch 20, batch 3900, loss[loss=0.1607, simple_loss=0.2542, pruned_loss=0.03355, over 7109.00 frames.], tot_loss[loss=0.1624, simple_loss=0.253, pruned_loss=0.03593, over 1417029.01 frames.], batch size: 21, lr: 3.85e-04
2022-05-15 01:39:01,288 INFO [train.py:812] (4/8) Epoch 20, batch 3950, loss[loss=0.1648, simple_loss=0.2485, pruned_loss=0.04059, over 7335.00 frames.], tot_loss[loss=0.1628, simple_loss=0.253, pruned_loss=0.03629, over 1410862.47 frames.], batch size: 20, lr: 3.85e-04
2022-05-15 01:39:59,103 INFO [train.py:812] (4/8) Epoch 20, batch 4000, loss[loss=0.1607, simple_loss=0.2424, pruned_loss=0.03949, over 7158.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2528, pruned_loss=0.03622, over 1409056.20 frames.], batch size: 18, lr: 3.85e-04
2022-05-15 01:40:58,259 INFO [train.py:812] (4/8) Epoch 20, batch 4050, loss[loss=0.1528, simple_loss=0.2422, pruned_loss=0.03165, over 7334.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2528, pruned_loss=0.03673, over 1405810.39 frames.], batch size: 20, lr: 3.85e-04
2022-05-15 01:41:57,206 INFO [train.py:812] (4/8) Epoch 20, batch 4100, loss[loss=0.1417, simple_loss=0.2323, pruned_loss=0.02554, over 7285.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2515, pruned_loss=0.03656, over 1406622.31 frames.], batch size: 18, lr: 3.85e-04
2022-05-15 01:42:56,562 INFO [train.py:812] (4/8) Epoch 20, batch 4150, loss[loss=0.153, simple_loss=0.2441, pruned_loss=0.031, over 7081.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2506, pruned_loss=0.03606, over 1410073.10 frames.], batch size: 18, lr: 3.85e-04
2022-05-15 01:43:53,666 INFO [train.py:812] (4/8) Epoch 20, batch 4200, loss[loss=0.1554, simple_loss=0.2257, pruned_loss=0.0425, over 7239.00 frames.], tot_loss[loss=0.162, simple_loss=0.2512, pruned_loss=0.03639, over 1405584.03 frames.], batch size: 16, lr: 3.85e-04
2022-05-15 01:44:52,593 INFO [train.py:812] (4/8) Epoch 20, batch 4250, loss[loss=0.1568, simple_loss=0.2572, pruned_loss=0.02819, over 7200.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2502, pruned_loss=0.03599, over 1402680.25 frames.], batch size: 23, lr: 3.85e-04
2022-05-15 01:45:49,894 INFO [train.py:812] (4/8) Epoch 20, batch 4300, loss[loss=0.2017, simple_loss=0.2933, pruned_loss=0.05506, over 7220.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2508, pruned_loss=0.03586, over 1400984.05 frames.], batch size: 21, lr: 3.85e-04
2022-05-15 01:46:48,976 INFO [train.py:812] (4/8) Epoch 20, batch 4350, loss[loss=0.1768, simple_loss=0.2578, pruned_loss=0.04785, over 5003.00 frames.], tot_loss[loss=0.1599, simple_loss=0.249, pruned_loss=0.03544, over 1404644.73 frames.], batch size: 53, lr: 3.84e-04
2022-05-15 01:47:48,043 INFO [train.py:812] (4/8) Epoch 20, batch 4400, loss[loss=0.1662, simple_loss=0.2607, pruned_loss=0.03586, over 7163.00 frames.], tot_loss[loss=0.1589, simple_loss=0.248, pruned_loss=0.03493, over 1399650.26 frames.], batch size: 19, lr: 3.84e-04
2022-05-15 01:48:47,109 INFO [train.py:812] (4/8) Epoch 20, batch 4450, loss[loss=0.1285, simple_loss=0.2163, pruned_loss=0.02039, over 6777.00 frames.], tot_loss[loss=0.159, simple_loss=0.2478, pruned_loss=0.03507, over 1390449.93 frames.], batch size: 15, lr: 3.84e-04
2022-05-15 01:49:45,784 INFO [train.py:812] (4/8) Epoch 20, batch 4500, loss[loss=0.1684, simple_loss=0.2596, pruned_loss=0.03864, over 7193.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2484, pruned_loss=0.03503, over 1382479.32 frames.], batch size: 23, lr: 3.84e-04
2022-05-15 01:50:44,403 INFO [train.py:812] (4/8) Epoch 20, batch 4550, loss[loss=0.1437, simple_loss=0.2381, pruned_loss=0.02467, over 6466.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2514, pruned_loss=0.03681, over 1337096.85 frames.], batch size: 38, lr: 3.84e-04
2022-05-15 01:51:55,161 INFO [train.py:812] (4/8) Epoch 21, batch 0, loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02875, over 7000.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02875, over 7000.00 frames.], batch size: 16, lr: 3.75e-04
2022-05-15 01:52:54,960 INFO [train.py:812] (4/8) Epoch 21, batch 50, loss[loss=0.1537, simple_loss=0.2509, pruned_loss=0.02826, over 6457.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2497, pruned_loss=0.03461, over 323710.65 frames.], batch size: 37, lr: 3.75e-04
2022-05-15 01:53:53,835 INFO [train.py:812] (4/8) Epoch 21, batch 100, loss[loss=0.1655, simple_loss=0.2562, pruned_loss=0.03747, over 6790.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2516, pruned_loss=0.03541, over 567174.44 frames.], batch size: 15, lr: 3.75e-04
2022-05-15 01:54:52,692 INFO [train.py:812] (4/8) Epoch 21, batch 150, loss[loss=0.1368, simple_loss=0.2251, pruned_loss=0.02427, over 7171.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2511, pruned_loss=0.03529, over 756383.37 frames.], batch size: 18, lr: 3.75e-04
2022-05-15 01:55:51,316 INFO [train.py:812] (4/8) Epoch 21, batch 200, loss[loss=0.1687, simple_loss=0.2718, pruned_loss=0.03283, over 6818.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2525, pruned_loss=0.03545, over 901518.65 frames.], batch size: 31, lr: 3.75e-04
2022-05-15 01:56:53,957 INFO [train.py:812] (4/8) Epoch 21, batch 250, loss[loss=0.1714, simple_loss=0.2686, pruned_loss=0.0371, over 7160.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2518, pruned_loss=0.03551, over 1012758.67 frames.], batch size: 19, lr: 3.75e-04
2022-05-15 01:57:52,820 INFO [train.py:812] (4/8) Epoch 21, batch 300, loss[loss=0.1332, simple_loss=0.2199, pruned_loss=0.0233, over 7285.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2525, pruned_loss=0.03594, over 1102175.40 frames.], batch size: 18, lr: 3.75e-04
2022-05-15 01:58:49,827 INFO [train.py:812] (4/8) Epoch 21, batch 350, loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03075, over 7260.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2525, pruned_loss=0.03584, over 1170177.98 frames.], batch size: 19, lr: 3.74e-04
2022-05-15 01:59:47,327 INFO [train.py:812] (4/8) Epoch 21, batch 400, loss[loss=0.1396, simple_loss=0.2238, pruned_loss=0.0277, over 7061.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2518, pruned_loss=0.03527, over 1229316.87 frames.], batch size: 18, lr: 3.74e-04
2022-05-15 02:00:46,711 INFO [train.py:812] (4/8) Epoch 21, batch 450, loss[loss=0.1479, simple_loss=0.2388, pruned_loss=0.02848, over 7457.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2517, pruned_loss=0.03529, over 1272456.09 frames.], batch size: 19, lr: 3.74e-04
2022-05-15 02:01:45,876 INFO [train.py:812] (4/8) Epoch 21, batch 500, loss[loss=0.1787, simple_loss=0.2654, pruned_loss=0.04596, over 7065.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2528, pruned_loss=0.03594, over 1310966.40 frames.], batch size: 28, lr: 3.74e-04
2022-05-15 02:02:44,631 INFO [train.py:812] (4/8) Epoch 21, batch 550, loss[loss=0.1734, simple_loss=0.2512, pruned_loss=0.04782, over 6813.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2526, pruned_loss=0.03551, over 1337035.86 frames.], batch size: 15, lr: 3.74e-04
2022-05-15 02:03:42,722 INFO [train.py:812] (4/8) Epoch 21, batch 600, loss[loss=0.1693, simple_loss=0.2617, pruned_loss=0.03847, over 7205.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2526, pruned_loss=0.03539, over 1355592.49 frames.], batch size: 22, lr: 3.74e-04
2022-05-15 02:04:42,156 INFO [train.py:812] (4/8) Epoch 21, batch 650, loss[loss=0.1307, simple_loss=0.2089, pruned_loss=0.02628, over 7134.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2509, pruned_loss=0.03525, over 1370486.23 frames.], batch size: 17, lr: 3.74e-04
2022-05-15 02:05:41,119 INFO [train.py:812] (4/8) Epoch 21, batch 700, loss[loss=0.1731, simple_loss=0.2681, pruned_loss=0.03906, over 7240.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2518, pruned_loss=0.03531, over 1380968.87 frames.], batch size: 20, lr: 3.74e-04
2022-05-15 02:06:40,201 INFO [train.py:812] (4/8) Epoch 21, batch 750, loss[loss=0.1466, simple_loss=0.2239, pruned_loss=0.0347, over 7434.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2519, pruned_loss=0.03555, over 1386025.83 frames.], batch size: 18, lr: 3.74e-04
2022-05-15 02:07:37,518 INFO [train.py:812] (4/8) Epoch 21, batch 800, loss[loss=0.162, simple_loss=0.2505, pruned_loss=0.03671, over 7238.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2513, pruned_loss=0.03561, over 1384267.57 frames.], batch size: 20, lr: 3.73e-04
2022-05-15 02:08:37,261 INFO [train.py:812] (4/8) Epoch 21, batch 850, loss[loss=0.1782, simple_loss=0.2617, pruned_loss=0.04738, over 7309.00 frames.], tot_loss[loss=0.161, simple_loss=0.2508, pruned_loss=0.03564, over 1391515.94 frames.], batch size: 25, lr: 3.73e-04
2022-05-15 02:09:36,872 INFO [train.py:812] (4/8) Epoch 21, batch 900, loss[loss=0.1592, simple_loss=0.255, pruned_loss=0.03168, over 7239.00 frames.], tot_loss[loss=0.1603, simple_loss=0.25, pruned_loss=0.03529, over 1400552.89 frames.], batch size: 20, lr: 3.73e-04
2022-05-15 02:10:36,715 INFO [train.py:812] (4/8) Epoch 21, batch 950, loss[loss=0.184, simple_loss=0.2826, pruned_loss=0.04273, over 7337.00 frames.], tot_loss[loss=0.1614, simple_loss=0.251, pruned_loss=0.03589, over 1406037.44 frames.], batch size: 22, lr: 3.73e-04
2022-05-15 02:11:34,899 INFO [train.py:812] (4/8) Epoch 21, batch 1000, loss[loss=0.1789, simple_loss=0.2716, pruned_loss=0.04307, over 7178.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2518, pruned_loss=0.03596, over 1404840.08 frames.], batch size: 23, lr: 3.73e-04
2022-05-15 02:12:42,512 INFO [train.py:812] (4/8) Epoch 21, batch 1050, loss[loss=0.1541, simple_loss=0.2497, pruned_loss=0.02922, over 7405.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2526, pruned_loss=0.03596, over 1406030.53 frames.], batch size: 21, lr: 3.73e-04
2022-05-15 02:13:41,818 INFO [train.py:812] (4/8) Epoch 21, batch 1100, loss[loss=0.1573, simple_loss=0.2374, pruned_loss=0.03859, over 6802.00 frames.], tot_loss[loss=0.1608, simple_loss=0.251, pruned_loss=0.03532, over 1407449.65 frames.], batch size: 15, lr: 3.73e-04
2022-05-15 02:14:40,541 INFO [train.py:812] (4/8) Epoch 21, batch 1150, loss[loss=0.1828, simple_loss=0.2694, pruned_loss=0.04809, over 7290.00 frames.], tot_loss[loss=0.1599, simple_loss=0.25, pruned_loss=0.0349, over 1412732.67 frames.], batch size: 24, lr: 3.73e-04
2022-05-15 02:15:37,791 INFO [train.py:812] (4/8) Epoch 21, batch 1200, loss[loss=0.1445, simple_loss=0.2254, pruned_loss=0.03176, over 7295.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2503, pruned_loss=0.035, over 1415801.05 frames.], batch size: 18, lr: 3.73e-04
2022-05-15 02:16:37,269 INFO [train.py:812] (4/8) Epoch 21, batch 1250, loss[loss=0.1727, simple_loss=0.2723, pruned_loss=0.03652, over 7298.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2496, pruned_loss=0.03505, over 1418214.28 frames.], batch size: 24, lr: 3.73e-04
2022-05-15 02:17:36,468 INFO [train.py:812] (4/8) Epoch 21, batch 1300, loss[loss=0.1431, simple_loss=0.2301, pruned_loss=0.02801, over 7065.00 frames.], tot_loss[loss=0.16, simple_loss=0.2497, pruned_loss=0.03514, over 1417010.03 frames.], batch size: 18, lr: 3.72e-04
2022-05-15 02:18:34,028 INFO [train.py:812] (4/8) Epoch 21, batch 1350, loss[loss=0.1799, simple_loss=0.2659, pruned_loss=0.04698, over 7333.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2488, pruned_loss=0.0349, over 1423751.65 frames.], batch size: 22, lr: 3.72e-04
2022-05-15 02:19:32,909 INFO [train.py:812] (4/8) Epoch 21, batch 1400, loss[loss=0.171, simple_loss=0.2676, pruned_loss=0.03717, over 7388.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2502, pruned_loss=0.03532, over 1426151.92 frames.], batch size: 23, lr: 3.72e-04
2022-05-15 02:20:31,810 INFO [train.py:812] (4/8) Epoch 21, batch 1450, loss[loss=0.1869, simple_loss=0.2691, pruned_loss=0.05237, over 4711.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2502, pruned_loss=0.03536, over 1420561.73 frames.], batch size: 52, lr: 3.72e-04
2022-05-15 02:21:30,169 INFO [train.py:812] (4/8) Epoch 21, batch 1500, loss[loss=0.1557, simple_loss=0.2621, pruned_loss=0.02465, over 7336.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2516, pruned_loss=0.03575, over 1419017.60 frames.], batch size: 22, lr: 3.72e-04
2022-05-15 02:22:29,838 INFO [train.py:812] (4/8) Epoch 21, batch 1550, loss[loss=0.1712, simple_loss=0.2603, pruned_loss=0.04103, over 6775.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2521, pruned_loss=0.03617, over 1420456.02 frames.], batch size: 31, lr: 3.72e-04
2022-05-15 02:23:26,743 INFO [train.py:812] (4/8) Epoch 21, batch 1600, loss[loss=0.1666, simple_loss=0.2622, pruned_loss=0.03552, over 7340.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2532, pruned_loss=0.03616, over 1421984.64 frames.], batch size: 22, lr: 3.72e-04
2022-05-15 02:24:25,706 INFO [train.py:812] (4/8) Epoch 21, batch 1650, loss[loss=0.1434, simple_loss=0.2339, pruned_loss=0.0265, over 7312.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2531, pruned_loss=0.03629, over 1422633.86 frames.], batch size: 20, lr: 3.72e-04
2022-05-15 02:25:24,255 INFO [train.py:812] (4/8) Epoch 21, batch 1700, loss[loss=0.158, simple_loss=0.2553, pruned_loss=0.03038, over 7337.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2525, pruned_loss=0.03603, over 1422675.62 frames.], batch size: 22, lr: 3.72e-04
2022-05-15 02:26:22,314 INFO [train.py:812] (4/8) Epoch 21, batch 1750, loss[loss=0.1581, simple_loss=0.2395, pruned_loss=0.03832, over 7410.00 frames.], tot_loss[loss=0.162, simple_loss=0.2521, pruned_loss=0.03601, over 1423675.66 frames.], batch size: 18, lr: 3.72e-04
2022-05-15 02:27:21,193 INFO [train.py:812] (4/8) Epoch 21, batch 1800, loss[loss=0.1679, simple_loss=0.2606, pruned_loss=0.0376, over 7206.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2515, pruned_loss=0.03542, over 1425123.42 frames.], batch size: 23, lr: 3.71e-04
2022-05-15 02:28:20,360 INFO [train.py:812] (4/8) Epoch 21, batch 1850, loss[loss=0.1259, simple_loss=0.2112, pruned_loss=0.02031, over 7408.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2509, pruned_loss=0.0352, over 1423780.00 frames.], batch size: 18, lr: 3.71e-04
2022-05-15 02:29:19,107 INFO [train.py:812] (4/8) Epoch 21, batch 1900, loss[loss=0.1454, simple_loss=0.2393, pruned_loss=0.02573, over 7160.00 frames.], tot_loss[loss=0.161, simple_loss=0.2514, pruned_loss=0.03533, over 1425344.50 frames.], batch size: 19, lr: 3.71e-04
2022-05-15 02:30:18,952 INFO [train.py:812] (4/8) Epoch 21, batch 1950, loss[loss=0.1524, simple_loss=0.2461, pruned_loss=0.02934, over 7258.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2505, pruned_loss=0.0349, over 1428464.84 frames.], batch size: 19, lr: 3.71e-04
2022-05-15 02:31:18,453 INFO [train.py:812] (4/8) Epoch 21, batch 2000, loss[loss=0.1654, simple_loss=0.2569, pruned_loss=0.03694, over 6734.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2503, pruned_loss=0.03502, over 1424609.80 frames.], batch size: 31, lr: 3.71e-04
2022-05-15 02:32:18,153 INFO [train.py:812] (4/8) Epoch 21, batch 2050, loss[loss=0.1531, simple_loss=0.2435, pruned_loss=0.03132, over 7227.00 frames.], tot_loss[loss=0.1606, simple_loss=0.251, pruned_loss=0.03508, over 1424803.46 frames.], batch size: 21, lr: 3.71e-04
2022-05-15 02:33:17,369 INFO [train.py:812] (4/8) Epoch 21, batch 2100, loss[loss=0.154, simple_loss=0.2415, pruned_loss=0.03321, over 7066.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2506, pruned_loss=0.03507, over 1423586.85 frames.], batch size: 18, lr: 3.71e-04
2022-05-15 02:34:16,894 INFO [train.py:812] (4/8) Epoch 21, batch 2150, loss[loss=0.1477, simple_loss=0.2258, pruned_loss=0.03481, over 7206.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2511, pruned_loss=0.03532, over 1421574.78 frames.], batch size: 16, lr: 3.71e-04
2022-05-15 02:35:14,484 INFO [train.py:812] (4/8) Epoch 21, batch 2200, loss[loss=0.1844, simple_loss=0.2819, pruned_loss=0.04345, over 7211.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2503, pruned_loss=0.03507, over 1424052.33 frames.], batch size: 22, lr: 3.71e-04
2022-05-15 02:36:12,372 INFO [train.py:812] (4/8) Epoch 21, batch 2250, loss[loss=0.1628, simple_loss=0.2499, pruned_loss=0.0378, over 7206.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2504, pruned_loss=0.03489, over 1425145.66 frames.], batch size: 22, lr: 3.71e-04
2022-05-15 02:37:12,529 INFO [train.py:812] (4/8) Epoch 21, batch 2300, loss[loss=0.1747, simple_loss=0.2549, pruned_loss=0.04727, over 4953.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2496, pruned_loss=0.03503, over 1422857.58 frames.], batch size: 52, lr: 3.71e-04
2022-05-15 02:38:11,392 INFO [train.py:812] (4/8) Epoch 21, batch 2350, loss[loss=0.1692, simple_loss=0.2685, pruned_loss=0.03494, over 7288.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2513, pruned_loss=0.03557, over 1419021.00 frames.], batch size: 24, lr: 3.70e-04
2022-05-15 02:39:10,742 INFO [train.py:812] (4/8) Epoch 21, batch 2400, loss[loss=0.1566, simple_loss=0.2485, pruned_loss=0.03234, over 7215.00 frames.], tot_loss[loss=0.161, simple_loss=0.2508, pruned_loss=0.03562, over 1421308.81 frames.], batch size: 23, lr: 3.70e-04
2022-05-15 02:40:10,446 INFO [train.py:812] (4/8) Epoch 21, batch 2450, loss[loss=0.1635, simple_loss=0.2506, pruned_loss=0.03821, over 7173.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2504, pruned_loss=0.03511, over 1422015.52 frames.], batch size: 19, lr: 3.70e-04
2022-05-15 02:41:09,427 INFO [train.py:812] (4/8) Epoch 21, batch 2500, loss[loss=0.164, simple_loss=0.2573, pruned_loss=0.03536, over 7413.00 frames.], tot_loss[loss=0.1601, simple_loss=0.25, pruned_loss=0.03515, over 1422859.45 frames.], batch size: 21, lr: 3.70e-04
2022-05-15 02:42:07,850 INFO [train.py:812] (4/8) Epoch 21, batch 2550, loss[loss=0.1881, simple_loss=0.2713, pruned_loss=0.05249, over 5091.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2506, pruned_loss=0.03536, over 1420266.20 frames.], batch size: 52, lr: 3.70e-04
2022-05-15 02:43:06,159 INFO [train.py:812] (4/8) Epoch 21, batch 2600, loss[loss=0.1698, simple_loss=0.2616, pruned_loss=0.039, over 7063.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2517, pruned_loss=0.03566, over 1420869.42 frames.], batch size: 18, lr: 3.70e-04
2022-05-15 02:44:05,925 INFO [train.py:812] (4/8) Epoch 21, batch 2650, loss[loss=0.1664, simple_loss=0.2535, pruned_loss=0.03966, over 7320.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2521, pruned_loss=0.03606, over 1416412.96 frames.], batch size: 20, lr: 3.70e-04
2022-05-15 02:45:04,661 INFO [train.py:812] (4/8) Epoch 21, batch 2700, loss[loss=0.1544, simple_loss=0.2405, pruned_loss=0.03419, over 7411.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2514, pruned_loss=0.03539, over 1419971.54 frames.], batch size: 18, lr: 3.70e-04
2022-05-15 02:46:03,787 INFO [train.py:812] (4/8) Epoch 21, batch 2750, loss[loss=0.1407, simple_loss=0.2284, pruned_loss=0.02646, over 7160.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2518, pruned_loss=0.03555, over 1421409.94 frames.], batch size: 18, lr: 3.70e-04
2022-05-15 02:47:03,052 INFO [train.py:812] (4/8) Epoch 21, batch 2800, loss[loss=0.1947, simple_loss=0.2786, pruned_loss=0.05541, over 7390.00 frames.], tot_loss[loss=0.1609, simple_loss=0.251, pruned_loss=0.03544, over 1425312.29 frames.], batch size: 23, lr: 3.70e-04
2022-05-15 02:48:12,162 INFO [train.py:812] (4/8) Epoch 21, batch 2850, loss[loss=0.1858, simple_loss=0.2772, pruned_loss=0.04716, over 7195.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2512, pruned_loss=0.03547, over 1421126.78 frames.], batch size: 23, lr: 3.69e-04
2022-05-15 02:49:11,142 INFO [train.py:812] (4/8) Epoch 21, batch 2900, loss[loss=0.1486, simple_loss=0.2445, pruned_loss=0.02634, over 7018.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2514, pruned_loss=0.0355, over 1416443.00 frames.], batch size: 28, lr: 3.69e-04
2022-05-15 02:50:09,832 INFO [train.py:812] (4/8) Epoch 21, batch 2950, loss[loss=0.1563, simple_loss=0.2481, pruned_loss=0.03231, over 7356.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2511, pruned_loss=0.03498, over 1414278.02 frames.], batch size: 19, lr: 3.69e-04
2022-05-15 02:51:09,045 INFO [train.py:812] (4/8) Epoch 21, batch 3000, loss[loss=0.178, simple_loss=0.266, pruned_loss=0.04499, over 6824.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2504, pruned_loss=0.03488, over 1414267.06 frames.], batch size: 31, lr: 3.69e-04
2022-05-15 02:51:09,046 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 02:51:16,354 INFO [train.py:841] (4/8) Epoch 21, validation: loss=0.153, simple_loss=0.2519, pruned_loss=0.02704, over 698248.00 frames.
2022-05-15 02:52:35,376 INFO [train.py:812] (4/8) Epoch 21, batch 3050, loss[loss=0.166, simple_loss=0.2296, pruned_loss=0.05123, over 7287.00 frames.], tot_loss[loss=0.1599, simple_loss=0.25, pruned_loss=0.03494, over 1414554.53 frames.], batch size: 18, lr: 3.69e-04
2022-05-15 02:53:32,968 INFO [train.py:812] (4/8) Epoch 21, batch 3100, loss[loss=0.18, simple_loss=0.2623, pruned_loss=0.04885, over 7381.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2509, pruned_loss=0.03528, over 1413835.66 frames.], batch size: 23, lr: 3.69e-04
2022-05-15 02:55:01,534 INFO [train.py:812] (4/8) Epoch 21, batch 3150, loss[loss=0.2393, simple_loss=0.3237, pruned_loss=0.07749, over 7277.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2522, pruned_loss=0.03654, over 1418173.72 frames.], batch size: 24, lr: 3.69e-04
2022-05-15 02:56:00,659 INFO [train.py:812] (4/8) Epoch 21, batch 3200, loss[loss=0.1602, simple_loss=0.2512, pruned_loss=0.03459, over 7317.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2529, pruned_loss=0.03679, over 1422988.15 frames.], batch size: 21, lr: 3.69e-04
2022-05-15 02:57:00,394 INFO [train.py:812] (4/8) Epoch 21, batch 3250, loss[loss=0.1657, simple_loss=0.2621, pruned_loss=0.0347, over 7069.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2526, pruned_loss=0.03628, over 1421749.93 frames.], batch size: 18, lr: 3.69e-04
2022-05-15 02:58:08,764 INFO [train.py:812] (4/8) Epoch 21, batch 3300, loss[loss=0.1538, simple_loss=0.2258, pruned_loss=0.04087, over 7137.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2516, pruned_loss=0.03593, over 1423218.80 frames.], batch size: 17, lr: 3.69e-04
2022-05-15 02:59:08,381 INFO [train.py:812] (4/8) Epoch 21, batch 3350, loss[loss=0.1557, simple_loss=0.2503, pruned_loss=0.03058, over 7227.00 frames.], tot_loss[loss=0.1612, simple_loss=0.251, pruned_loss=0.0357, over 1419336.38 frames.], batch size: 20, lr: 3.68e-04
2022-05-15 03:00:06,807 INFO [train.py:812] (4/8) Epoch 21, batch 3400, loss[loss=0.2021, simple_loss=0.2794, pruned_loss=0.06238, over 6423.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2516, pruned_loss=0.03587, over 1415664.57 frames.], batch size: 38, lr: 3.68e-04
2022-05-15 03:01:06,181 INFO [train.py:812] (4/8) Epoch 21, batch 3450, loss[loss=0.1577, simple_loss=0.2599, pruned_loss=0.02776, over 7317.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2526, pruned_loss=0.03613, over 1413872.78 frames.], batch size: 21, lr: 3.68e-04
2022-05-15 03:02:05,066 INFO [train.py:812] (4/8) Epoch 21, batch 3500, loss[loss=0.177, simple_loss=0.2707, pruned_loss=0.0416, over 7090.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2538, pruned_loss=0.03688, over 1408882.00 frames.], batch size: 28, lr: 3.68e-04
2022-05-15 03:03:04,134 INFO [train.py:812] (4/8) Epoch 21, batch 3550, loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03324, over 7285.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2533, pruned_loss=0.03663, over 1413317.00 frames.], batch size: 17, lr: 3.68e-04
2022-05-15 03:04:02,910 INFO [train.py:812] (4/8) Epoch 21, batch 3600, loss[loss=0.1701, simple_loss=0.268, pruned_loss=0.03604, over 7367.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2535, pruned_loss=0.03654, over 1411037.53 frames.], batch size: 23, lr: 3.68e-04
2022-05-15 03:05:02,887 INFO [train.py:812] (4/8) Epoch 21, batch 3650, loss[loss=0.1607, simple_loss=0.2585, pruned_loss=0.03147, over 7134.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2538, pruned_loss=0.03666, over 1413239.84 frames.], batch size: 26, lr: 3.68e-04
2022-05-15 03:06:01,339 INFO [train.py:812] (4/8) Epoch 21, batch 3700, loss[loss=0.1606, simple_loss=0.2532, pruned_loss=0.03405, over 7318.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2529, pruned_loss=0.03632, over 1413803.00 frames.], batch size: 21, lr: 3.68e-04
2022-05-15 03:07:01,119 INFO [train.py:812] (4/8) Epoch 21, batch 3750, loss[loss=0.1643, simple_loss=0.2615, pruned_loss=0.03359, over 7315.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2524, pruned_loss=0.03642, over 1416602.98 frames.], batch size: 25, lr: 3.68e-04
2022-05-15 03:07:59,607 INFO [train.py:812] (4/8) Epoch 21, batch 3800, loss[loss=0.162, simple_loss=0.2638, pruned_loss=0.03009, over 7187.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2518, pruned_loss=0.03598, over 1418241.18 frames.], batch size: 26, lr: 3.68e-04
2022-05-15 03:08:58,691 INFO [train.py:812] (4/8) Epoch 21, batch 3850, loss[loss=0.1573, simple_loss=0.255, pruned_loss=0.0298, over 7328.00 frames.], tot_loss[loss=0.1618, simple_loss=0.252, pruned_loss=0.0358, over 1418737.84 frames.], batch size: 20, lr: 3.68e-04
2022-05-15 03:09:55,533 INFO [train.py:812] (4/8) Epoch 21, batch 3900, loss[loss=0.1622, simple_loss=0.2539, pruned_loss=0.03523, over 7257.00 frames.], tot_loss[loss=0.162, simple_loss=0.2523, pruned_loss=0.03589, over 1422620.96 frames.], batch size: 19, lr: 3.67e-04
2022-05-15 03:10:53,480 INFO [train.py:812] (4/8) Epoch 21, batch 3950, loss[loss=0.15, simple_loss=0.2363, pruned_loss=0.03188, over 7400.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2529, pruned_loss=0.0363, over 1417218.24 frames.], batch size: 18, lr: 3.67e-04
2022-05-15 03:11:51,916 INFO [train.py:812] (4/8) Epoch 21, batch 4000, loss[loss=0.1323, simple_loss=0.222, pruned_loss=0.02133, over 7359.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2527, pruned_loss=0.03601, over 1421005.74 frames.], batch size: 19, lr: 3.67e-04
2022-05-15 03:12:50,963 INFO [train.py:812] (4/8) Epoch 21, batch 4050, loss[loss=0.208, simple_loss=0.2834, pruned_loss=0.06626, over 5006.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2517, pruned_loss=0.03574, over 1418395.92 frames.], batch size: 52, lr: 3.67e-04
2022-05-15 03:13:49,282 INFO [train.py:812] (4/8) Epoch 21, batch 4100, loss[loss=0.1687, simple_loss=0.2645, pruned_loss=0.03643, over 7213.00 frames.], tot_loss[loss=0.162, simple_loss=0.252, pruned_loss=0.03603, over 1410047.17 frames.], batch size: 21, lr: 3.67e-04
2022-05-15 03:14:46,151 INFO [train.py:812] (4/8) Epoch 21, batch 4150, loss[loss=0.166, simple_loss=0.249, pruned_loss=0.04152, over 7074.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2529, pruned_loss=0.03603, over 1411393.07 frames.], batch size: 18, lr: 3.67e-04
2022-05-15 03:15:43,927 INFO [train.py:812] (4/8) Epoch 21, batch 4200, loss[loss=0.1555, simple_loss=0.2478, pruned_loss=0.03167, over 6789.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2525, pruned_loss=0.03601, over 1410720.10 frames.], batch size: 31, lr: 3.67e-04
2022-05-15 03:16:47,803 INFO [train.py:812] (4/8) Epoch 21, batch 4250, loss[loss=0.1747, simple_loss=0.2711, pruned_loss=0.03917, over 7223.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2512, pruned_loss=0.03551, over 1415448.50 frames.], batch size: 21, lr: 3.67e-04
2022-05-15 03:17:46,898 INFO [train.py:812] (4/8) Epoch 21, batch 4300, loss[loss=0.1813, simple_loss=0.2681, pruned_loss=0.04725, over 7268.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2503, pruned_loss=0.03515, over 1416107.47 frames.], batch size: 24, lr: 3.67e-04
2022-05-15 03:18:45,853 INFO [train.py:812] (4/8) Epoch 21, batch 4350, loss[loss=0.1769, simple_loss=0.2628, pruned_loss=0.04549, over 7224.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2508, pruned_loss=0.03521, over 1415606.22 frames.], batch size: 21, lr: 3.67e-04
2022-05-15 03:19:43,042 INFO [train.py:812] (4/8) Epoch 21, batch 4400, loss[loss=0.1483, simple_loss=0.2302, pruned_loss=0.0332, over 7163.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2509, pruned_loss=0.03517, over 1415569.63 frames.], batch size: 18, lr: 3.66e-04
2022-05-15 03:20:42,008 INFO [train.py:812] (4/8) Epoch 21, batch 4450, loss[loss=0.1317, simple_loss=0.2139, pruned_loss=0.02478, over 6991.00 frames.], tot_loss[loss=0.1607, simple_loss=0.251, pruned_loss=0.03524, over 1407293.23 frames.], batch size: 16, lr: 3.66e-04
2022-05-15 03:21:40,276 INFO [train.py:812] (4/8) Epoch 21, batch 4500, loss[loss=0.1323, simple_loss=0.2122, pruned_loss=0.02615, over 6995.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2516, pruned_loss=0.03525, over 1409692.50 frames.], batch size: 16, lr: 3.66e-04
2022-05-15 03:22:39,955 INFO [train.py:812] (4/8) Epoch 21, batch 4550, loss[loss=0.2044, simple_loss=0.282, pruned_loss=0.06338, over 4744.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2511, pruned_loss=0.03574, over 1394404.66 frames.], batch size: 53, lr: 3.66e-04
2022-05-15 03:23:52,236 INFO [train.py:812] (4/8) Epoch 22, batch 0, loss[loss=0.1542, simple_loss=0.256, pruned_loss=0.02624, over 7311.00 frames.], tot_loss[loss=0.1542, simple_loss=0.256, pruned_loss=0.02624, over 7311.00 frames.], batch size: 25, lr: 3.58e-04
2022-05-15 03:24:50,152 INFO [train.py:812] (4/8) Epoch 22, batch 50, loss[loss=0.1346, simple_loss=0.2262, pruned_loss=0.02151, over 7168.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2511, pruned_loss=0.03478, over 317814.56 frames.], batch size: 18, lr: 3.58e-04
2022-05-15 03:25:49,149 INFO [train.py:812] (4/8) Epoch 22, batch 100, loss[loss=0.1412, simple_loss=0.234, pruned_loss=0.02418, over 7110.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2508, pruned_loss=0.03491, over 564305.61 frames.], batch size: 21, lr: 3.58e-04
2022-05-15 03:26:47,181 INFO [train.py:812] (4/8) Epoch 22, batch 150, loss[loss=0.1655, simple_loss=0.262, pruned_loss=0.03447, over 7322.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2503, pruned_loss=0.03437, over 753738.33 frames.], batch size: 21, lr: 3.58e-04
2022-05-15 03:27:46,007 INFO [train.py:812] (4/8) Epoch 22, batch 200, loss[loss=0.1422, simple_loss=0.2378, pruned_loss=0.02331, over 7347.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2504, pruned_loss=0.03452, over 902215.42 frames.], batch size: 22, lr: 3.58e-04
2022-05-15 03:28:43,578 INFO [train.py:812] (4/8) Epoch 22, batch 250, loss[loss=0.1507, simple_loss=0.2495, pruned_loss=0.02598, over 7257.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2513, pruned_loss=0.03503, over 1016114.72 frames.], batch size: 19, lr: 3.57e-04
2022-05-15 03:29:41,565 INFO [train.py:812] (4/8) Epoch 22, batch 300, loss[loss=0.1657, simple_loss=0.2597, pruned_loss=0.03584, over 7228.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2515, pruned_loss=0.03494, over 1108987.97 frames.], batch size: 20, lr: 3.57e-04
2022-05-15 03:30:39,467 INFO [train.py:812] (4/8) Epoch 22, batch 350, loss[loss=0.1578, simple_loss=0.2498, pruned_loss=0.03288, over 7153.00 frames.], tot_loss[loss=0.1604, simple_loss=0.251, pruned_loss=0.03493, over 1178668.22 frames.], batch size: 19, lr: 3.57e-04
2022-05-15 03:31:38,297 INFO [train.py:812] (4/8) Epoch 22, batch 400, loss[loss=0.1711, simple_loss=0.2694, pruned_loss=0.03644, over 7217.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2508, pruned_loss=0.03449, over 1230638.34 frames.], batch size: 21, lr: 3.57e-04
2022-05-15 03:32:37,212 INFO [train.py:812] (4/8) Epoch 22, batch 450, loss[loss=0.2155, simple_loss=0.3039, pruned_loss=0.06355, over 5170.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2501, pruned_loss=0.03448, over 1274231.42 frames.], batch size: 52, lr: 3.57e-04
2022-05-15 03:33:36,433 INFO [train.py:812] (4/8) Epoch 22, batch 500, loss[loss=0.2008, simple_loss=0.293, pruned_loss=0.05426, over 7304.00 frames.], tot_loss[loss=0.1608, simple_loss=0.252, pruned_loss=0.03479, over 1309520.37 frames.], batch size: 25, lr: 3.57e-04
2022-05-15 03:34:33,234 INFO [train.py:812] (4/8) Epoch 22, batch 550, loss[loss=0.1451, simple_loss=0.2332, pruned_loss=0.02845, over 7433.00 frames.], tot_loss[loss=0.1607, simple_loss=0.252, pruned_loss=0.03472, over 1332473.57 frames.], batch size: 20, lr: 3.57e-04
2022-05-15 03:35:32,154 INFO [train.py:812] (4/8) Epoch 22, batch 600, loss[loss=0.1462, simple_loss=0.2475, pruned_loss=0.02242, over 7339.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2505, pruned_loss=0.03437, over 1353906.04 frames.], batch size: 22, lr: 3.57e-04
2022-05-15 03:36:31,007 INFO [train.py:812] (4/8) Epoch 22, batch 650, loss[loss=0.1743, simple_loss=0.2678, pruned_loss=0.04041, over 7326.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2521, pruned_loss=0.03485, over 1369351.82 frames.], batch size: 22, lr: 3.57e-04
2022-05-15 03:37:30,481 INFO [train.py:812] (4/8) Epoch 22, batch 700, loss[loss=0.2006, simple_loss=0.2935, pruned_loss=0.05388, over 7308.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2522, pruned_loss=0.03527, over 1378375.59 frames.], batch size: 25, lr: 3.57e-04
2022-05-15 03:38:28,393 INFO [train.py:812] (4/8) Epoch 22, batch 750, loss[loss=0.1389, simple_loss=0.2318, pruned_loss=0.02297, over 7156.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2511, pruned_loss=0.03488, over 1387122.80 frames.], batch size: 18, lr: 3.57e-04
2022-05-15 03:39:28,267 INFO [train.py:812] (4/8) Epoch 22, batch 800, loss[loss=0.1697, simple_loss=0.2571, pruned_loss=0.0411, over 7287.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2515, pruned_loss=0.035, over 1399717.84 frames.], batch size: 25, lr: 3.56e-04
2022-05-15 03:40:27,689 INFO [train.py:812] (4/8) Epoch 22, batch 850, loss[loss=0.1627, simple_loss=0.252, pruned_loss=0.03667, over 7409.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2513, pruned_loss=0.03479, over 1405085.93 frames.], batch size: 18, lr: 3.56e-04
2022-05-15 03:41:26,081 INFO [train.py:812] (4/8) Epoch 22, batch 900, loss[loss=0.1412, simple_loss=0.2327, pruned_loss=0.02486, over 6459.00 frames.], tot_loss[loss=0.1603, simple_loss=0.251, pruned_loss=0.03474, over 1410015.42 frames.], batch size: 38, lr: 3.56e-04
2022-05-15 03:42:25,446 INFO [train.py:812] (4/8) Epoch 22, batch 950, loss[loss=0.1574, simple_loss=0.2433, pruned_loss=0.03571, over 7297.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2504, pruned_loss=0.03447, over 1411967.98 frames.], batch size: 18, lr: 3.56e-04
2022-05-15 03:43:24,204 INFO [train.py:812] (4/8) Epoch 22, batch 1000, loss[loss=0.173, simple_loss=0.2624, pruned_loss=0.04177, over 7167.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2518, pruned_loss=0.03528, over 1411855.32 frames.], batch size: 19, lr: 3.56e-04
2022-05-15 03:44:23,459 INFO [train.py:812] (4/8) Epoch 22, batch 1050, loss[loss=0.148, simple_loss=0.2419, pruned_loss=0.02708, over 7325.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2509, pruned_loss=0.03496, over 1415453.18 frames.], batch size: 22, lr: 3.56e-04
2022-05-15 03:45:23,003 INFO [train.py:812] (4/8) Epoch 22, batch 1100, loss[loss=0.191, simple_loss=0.2721, pruned_loss=0.05496, over 6157.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2511, pruned_loss=0.03497, over 1418407.38 frames.], batch size: 37, lr: 3.56e-04
2022-05-15 03:46:20,335 INFO [train.py:812] (4/8) Epoch 22, batch 1150, loss[loss=0.1514, simple_loss=0.2464, pruned_loss=0.0282, over 7270.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2505, pruned_loss=0.03518, over 1421052.27 frames.], batch size: 19, lr: 3.56e-04
2022-05-15 03:47:19,437 INFO [train.py:812] (4/8) Epoch 22, batch 1200, loss[loss=0.1757, simple_loss=0.2755, pruned_loss=0.03794, over 7295.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2507, pruned_loss=0.03531, over 1422125.45 frames.], batch size: 25, lr: 3.56e-04
2022-05-15 03:48:18,941 INFO [train.py:812] (4/8) Epoch 22, batch 1250, loss[loss=0.1198, simple_loss=0.202, pruned_loss=0.01878, over 7004.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2509, pruned_loss=0.03545, over 1421707.76 frames.], batch size: 16, lr: 3.56e-04
2022-05-15 03:49:19,103 INFO [train.py:812] (4/8) Epoch 22, batch 1300, loss[loss=0.1406, simple_loss=0.2399, pruned_loss=0.02062, over 7158.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2501, pruned_loss=0.03502, over 1419914.44 frames.], batch size: 19, lr: 3.56e-04
2022-05-15 03:50:16,168 INFO [train.py:812] (4/8) Epoch 22, batch 1350, loss[loss=0.1857, simple_loss=0.2853, pruned_loss=0.04307, over 7418.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2496, pruned_loss=0.03469, over 1424256.14 frames.], batch size: 21, lr: 3.55e-04
2022-05-15 03:51:15,336 INFO [train.py:812] (4/8) Epoch 22, batch 1400, loss[loss=0.1775, simple_loss=0.2637, pruned_loss=0.04569, over 7210.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2492, pruned_loss=0.03479, over 1420085.06 frames.], batch size: 22, lr: 3.55e-04
2022-05-15 03:52:14,141 INFO [train.py:812] (4/8) Epoch 22, batch 1450, loss[loss=0.1594, simple_loss=0.2484, pruned_loss=0.0352, over 7433.00 frames.], tot_loss[loss=0.1602, simple_loss=0.25, pruned_loss=0.03515, over 1424357.35 frames.], batch size: 20, lr: 3.55e-04
2022-05-15 03:53:13,829 INFO [train.py:812] (4/8) Epoch 22, batch 1500, loss[loss=0.1555, simple_loss=0.25, pruned_loss=0.03055, over 7244.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2503, pruned_loss=0.03532, over 1426551.63 frames.], batch size: 20, lr: 3.55e-04
2022-05-15 03:54:13,337 INFO [train.py:812] (4/8) Epoch 22, batch 1550, loss[loss=0.1724, simple_loss=0.2627, pruned_loss=0.04108, over 7229.00 frames.], tot_loss[loss=0.16, simple_loss=0.2499, pruned_loss=0.03506, over 1428633.89 frames.], batch size: 20, lr: 3.55e-04
2022-05-15 03:55:12,246 INFO [train.py:812] (4/8) Epoch 22, batch 1600, loss[loss=0.1382, simple_loss=0.2144, pruned_loss=0.03107, over 7212.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2494, pruned_loss=0.03443, over 1430096.43 frames.], batch size: 16, lr: 3.55e-04
2022-05-15 03:56:08,990 INFO [train.py:812] (4/8) Epoch 22, batch 1650, loss[loss=0.1677, simple_loss=0.2642, pruned_loss=0.03558, over 6684.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2495, pruned_loss=0.03439, over 1431527.19 frames.], batch size: 31, lr: 3.55e-04
2022-05-15 03:57:06,968 INFO [train.py:812] (4/8) Epoch 22, batch 1700, loss[loss=0.1533, simple_loss=0.2622, pruned_loss=0.02224, over 7339.00 frames.], tot_loss[loss=0.1587, simple_loss=0.249, pruned_loss=0.03419, over 1433578.08 frames.], batch size: 22, lr: 3.55e-04
2022-05-15 03:58:03,875 INFO [train.py:812] (4/8) Epoch 22, batch 1750, loss[loss=0.1605, simple_loss=0.2548, pruned_loss=0.03317, over 7229.00 frames.], tot_loss[loss=0.159, simple_loss=0.2493, pruned_loss=0.03435, over 1433343.07 frames.], batch size: 20, lr: 3.55e-04
2022-05-15 03:59:03,636 INFO [train.py:812] (4/8) Epoch 22, batch 1800, loss[loss=0.1443, simple_loss=0.2277, pruned_loss=0.03045, over 7283.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2489, pruned_loss=0.03451, over 1430848.34 frames.], batch size: 17, lr: 3.55e-04
2022-05-15 04:00:02,104 INFO [train.py:812] (4/8) Epoch 22, batch 1850, loss[loss=0.154, simple_loss=0.2536, pruned_loss=0.02721, over 6332.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2489, pruned_loss=0.0345, over 1427076.72 frames.], batch size: 37, lr: 3.55e-04
2022-05-15 04:01:00,870 INFO [train.py:812] (4/8) Epoch 22, batch 1900, loss[loss=0.1558, simple_loss=0.2472, pruned_loss=0.03224, over 4825.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2487, pruned_loss=0.03426, over 1425466.42 frames.], batch size: 53, lr: 3.54e-04
2022-05-15 04:02:00,141 INFO [train.py:812] (4/8) Epoch 22, batch 1950, loss[loss=0.1468, simple_loss=0.2274, pruned_loss=0.03306, over 7281.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2486, pruned_loss=0.03431, over 1426580.05 frames.], batch size: 17, lr: 3.54e-04
2022-05-15 04:02:59,575 INFO [train.py:812] (4/8) Epoch 22, batch 2000, loss[loss=0.1736, simple_loss=0.2707, pruned_loss=0.03822, over 7324.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2494, pruned_loss=0.03445, over 1428793.07 frames.], batch size: 20, lr: 3.54e-04
2022-05-15 04:03:58,501 INFO [train.py:812] (4/8) Epoch 22, batch 2050, loss[loss=0.1233, simple_loss=0.2059, pruned_loss=0.02042, over 7289.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2499, pruned_loss=0.03469, over 1429181.31 frames.], batch size: 17, lr: 3.54e-04
2022-05-15 04:04:58,106 INFO [train.py:812] (4/8) Epoch 22, batch 2100, loss[loss=0.1259, simple_loss=0.2113, pruned_loss=0.0203, over 7409.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2499, pruned_loss=0.0342, over 1428193.80 frames.], batch size: 18, lr: 3.54e-04
2022-05-15 04:05:56,575 INFO [train.py:812] (4/8) Epoch 22, batch 2150, loss[loss=0.1498, simple_loss=0.2309, pruned_loss=0.03438, over 7171.00 frames.], tot_loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03424, over 1423509.44 frames.], batch size: 18, lr: 3.54e-04
2022-05-15 04:06:54,942 INFO [train.py:812] (4/8) Epoch 22, batch 2200, loss[loss=0.1686, simple_loss=0.2617, pruned_loss=0.03775, over 7118.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2502, pruned_loss=0.03421, over 1426275.49 frames.], batch size: 21, lr: 3.54e-04
2022-05-15 04:07:52,617 INFO [train.py:812] (4/8) Epoch 22, batch 2250, loss[loss=0.1489, simple_loss=0.232, pruned_loss=0.03287, over 6844.00 frames.], tot_loss[loss=0.1591, simple_loss=0.25, pruned_loss=0.03406, over 1423730.81 frames.], batch size: 15, lr: 3.54e-04
2022-05-15 04:08:49,580 INFO [train.py:812] (4/8) Epoch 22, batch 2300, loss[loss=0.1878, simple_loss=0.2662, pruned_loss=0.05475, over 5068.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2504, pruned_loss=0.03431, over 1424937.10 frames.], batch size: 52, lr: 3.54e-04
2022-05-15 04:09:47,977 INFO [train.py:812] (4/8) Epoch 22, batch 2350, loss[loss=0.1652, simple_loss=0.2548, pruned_loss=0.0378, over 6409.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2504, pruned_loss=0.03453, over 1426792.77 frames.], batch size: 37, lr: 3.54e-04
2022-05-15 04:10:57,214 INFO [train.py:812] (4/8) Epoch 22, batch 2400, loss[loss=0.1373, simple_loss=0.2207, pruned_loss=0.02696, over 7134.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2499, pruned_loss=0.03453, over 1427324.21 frames.], batch size: 17, lr: 3.54e-04
2022-05-15 04:11:56,421 INFO [train.py:812] (4/8) Epoch 22, batch 2450, loss[loss=0.1443, simple_loss=0.2277, pruned_loss=0.03041, over 7280.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2503, pruned_loss=0.03455, over 1425693.28 frames.], batch size: 17, lr: 3.54e-04
2022-05-15 04:12:56,114 INFO [train.py:812] (4/8) Epoch 22, batch 2500, loss[loss=0.1592, simple_loss=0.2473, pruned_loss=0.03554, over 7412.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2508, pruned_loss=0.03496, over 1423560.52 frames.], batch size: 21, lr: 3.53e-04
2022-05-15 04:13:55,286 INFO [train.py:812] (4/8) Epoch 22, batch 2550, loss[loss=0.1939, simple_loss=0.2754, pruned_loss=0.05616, over 7445.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2512, pruned_loss=0.0353, over 1423460.05 frames.], batch size: 19, lr: 3.53e-04
2022-05-15 04:14:54,434 INFO [train.py:812] (4/8) Epoch 22, batch 2600, loss[loss=0.1501, simple_loss=0.2345, pruned_loss=0.03289, over 7161.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2518, pruned_loss=0.03521, over 1419629.65 frames.], batch size: 19, lr: 3.53e-04
2022-05-15 04:15:53,315 INFO [train.py:812] (4/8) Epoch 22, batch 2650, loss[loss=0.1314, simple_loss=0.223, pruned_loss=0.01993, over 7258.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2507, pruned_loss=0.03515, over 1423004.45 frames.], batch size: 19, lr: 3.53e-04
2022-05-15 04:16:52,250 INFO [train.py:812] (4/8) Epoch 22, batch 2700, loss[loss=0.1549, simple_loss=0.2302, pruned_loss=0.03977, over 7179.00 frames.], tot_loss[loss=0.1601, simple_loss=0.25, pruned_loss=0.03513, over 1421658.44 frames.], batch size: 18, lr: 3.53e-04
2022-05-15 04:17:51,010 INFO [train.py:812] (4/8) Epoch 22, batch 2750, loss[loss=0.1219, simple_loss=0.2189, pruned_loss=0.01242, over 7060.00 frames.], tot_loss[loss=0.16, simple_loss=0.2504, pruned_loss=0.03486, over 1421577.13 frames.], batch size: 18, lr: 3.53e-04
2022-05-15 04:18:49,824 INFO [train.py:812] (4/8) Epoch 22, batch 2800, loss[loss=0.1333, simple_loss=0.2172, pruned_loss=0.02472, over 7284.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2506, pruned_loss=0.03492, over 1421734.94 frames.], batch size: 18, lr: 3.53e-04
2022-05-15 04:19:48,488 INFO [train.py:812] (4/8) Epoch 22, batch 2850, loss[loss=0.1501, simple_loss=0.2521, pruned_loss=0.02403, over 7167.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2501, pruned_loss=0.03473, over 1419707.96 frames.], batch size: 19, lr: 3.53e-04
2022-05-15 04:20:47,852 INFO [train.py:812] (4/8) Epoch 22, batch 2900, loss[loss=0.15, simple_loss=0.229, pruned_loss=0.03554, over 7154.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2497, pruned_loss=0.03462, over 1421779.18 frames.], batch size: 19, lr: 3.53e-04
2022-05-15 04:21:47,223 INFO [train.py:812] (4/8) Epoch 22, batch 2950, loss[loss=0.1575, simple_loss=0.2477, pruned_loss=0.03365, over 7418.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2503, pruned_loss=0.03465, over 1421695.86 frames.], batch size: 21, lr: 3.53e-04
2022-05-15 04:22:47,049 INFO [train.py:812] (4/8) Epoch 22, batch 3000, loss[loss=0.1412, simple_loss=0.2267, pruned_loss=0.0278, over 7155.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2505, pruned_loss=0.03489, over 1426074.68 frames.], batch size: 18, lr: 3.53e-04
2022-05-15 04:22:47,050 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 04:22:54,482 INFO [train.py:841] (4/8) Epoch 22, validation: loss=0.1529, simple_loss=0.2512, pruned_loss=0.02731, over 698248.00 frames.
2022-05-15 04:23:53,744 INFO [train.py:812] (4/8) Epoch 22, batch 3050, loss[loss=0.1807, simple_loss=0.2786, pruned_loss=0.0414, over 7107.00 frames.], tot_loss[loss=0.16, simple_loss=0.2503, pruned_loss=0.03483, over 1427780.48 frames.], batch size: 28, lr: 3.52e-04
2022-05-15 04:24:53,794 INFO [train.py:812] (4/8) Epoch 22, batch 3100, loss[loss=0.1658, simple_loss=0.2514, pruned_loss=0.04013, over 5148.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2497, pruned_loss=0.035, over 1428166.12 frames.], batch size: 52, lr: 3.52e-04
2022-05-15 04:25:52,324 INFO [train.py:812] (4/8) Epoch 22, batch 3150, loss[loss=0.1888, simple_loss=0.2813, pruned_loss=0.04814, over 7413.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2495, pruned_loss=0.03486, over 1426182.99 frames.], batch size: 21, lr: 3.52e-04
2022-05-15 04:26:51,015 INFO [train.py:812] (4/8) Epoch 22, batch 3200, loss[loss=0.155, simple_loss=0.2472, pruned_loss=0.03139, over 7074.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2494, pruned_loss=0.03469, over 1426876.44 frames.], batch size: 18, lr: 3.52e-04
2022-05-15 04:27:50,211 INFO [train.py:812] (4/8) Epoch 22, batch 3250, loss[loss=0.1398, simple_loss=0.2185, pruned_loss=0.03053, over 7416.00 frames.], tot_loss[loss=0.16, simple_loss=0.2501, pruned_loss=0.03496, over 1428401.71 frames.], batch size: 17, lr: 3.52e-04
2022-05-15 04:28:47,778 INFO [train.py:812] (4/8) Epoch 22, batch 3300, loss[loss=0.1526, simple_loss=0.2461, pruned_loss=0.02962, over 7427.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2516, pruned_loss=0.03506, over 1430210.43 frames.], batch size: 20, lr: 3.52e-04
2022-05-15 04:29:46,918 INFO [train.py:812] (4/8) Epoch 22, batch 3350, loss[loss=0.1636, simple_loss=0.257, pruned_loss=0.03514, over 7360.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2524, pruned_loss=0.03539, over 1428790.11 frames.], batch size: 19, lr: 3.52e-04
2022-05-15 04:30:46,406 INFO [train.py:812] (4/8) Epoch 22, batch 3400, loss[loss=0.1811, simple_loss=0.2555, pruned_loss=0.05339, over 7131.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2525, pruned_loss=0.0355, over 1425179.36 frames.], batch size: 17, lr: 3.52e-04
2022-05-15 04:31:45,546 INFO [train.py:812] (4/8) Epoch 22, batch 3450, loss[loss=0.1546, simple_loss=0.2471, pruned_loss=0.03099, over 7349.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2521, pruned_loss=0.03522, over 1426850.11 frames.], batch size: 22, lr: 3.52e-04
2022-05-15 04:32:45,120 INFO [train.py:812] (4/8) Epoch 22, batch 3500, loss[loss=0.1688, simple_loss=0.2651, pruned_loss=0.03628, over 7341.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2512, pruned_loss=0.03507, over 1429482.95 frames.], batch size: 22, lr: 3.52e-04
2022-05-15 04:33:44,168 INFO [train.py:812] (4/8) Epoch 22, batch 3550, loss[loss=0.1672, simple_loss=0.261, pruned_loss=0.03676, over 6755.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2517, pruned_loss=0.0349, over 1427464.33 frames.], batch size: 31, lr: 3.52e-04
2022-05-15 04:34:43,573 INFO [train.py:812] (4/8) Epoch 22, batch 3600, loss[loss=0.1526, simple_loss=0.2339, pruned_loss=0.03568, over 7302.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2509, pruned_loss=0.03499, over 1422321.02 frames.], batch size: 17, lr: 3.51e-04
2022-05-15 04:35:42,258 INFO [train.py:812] (4/8) Epoch 22, batch 3650, loss[loss=0.1736, simple_loss=0.272, pruned_loss=0.03765, over 7374.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2512, pruned_loss=0.03509, over 1423708.32 frames.], batch size: 23, lr: 3.51e-04
2022-05-15 04:36:47,194 INFO [train.py:812] (4/8) Epoch 22, batch 3700, loss[loss=0.1516, simple_loss=0.2521, pruned_loss=0.02558, over 7221.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2507, pruned_loss=0.03492, over 1426808.61 frames.], batch size: 21, lr: 3.51e-04
2022-05-15 04:37:46,505 INFO [train.py:812] (4/8) Epoch 22, batch 3750, loss[loss=0.1475, simple_loss=0.227, pruned_loss=0.03398, over 6992.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2503, pruned_loss=0.03503, over 1430774.38 frames.], batch size: 16, lr: 3.51e-04
2022-05-15 04:38:46,129 INFO [train.py:812] (4/8) Epoch 22, batch 3800, loss[loss=0.1857, simple_loss=0.2717, pruned_loss=0.04985, over 5236.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2501, pruned_loss=0.03478, over 1425282.37 frames.], batch size: 52, lr: 3.51e-04
2022-05-15 04:39:43,948 INFO [train.py:812] (4/8) Epoch 22, batch 3850, loss[loss=0.168, simple_loss=0.2638, pruned_loss=0.03605, over 7232.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2503, pruned_loss=0.03443, over 1427751.31 frames.], batch size: 20, lr: 3.51e-04
2022-05-15 04:40:43,470 INFO [train.py:812] (4/8) Epoch 22, batch 3900, loss[loss=0.1622, simple_loss=0.2496, pruned_loss=0.03742, over 6413.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2492, pruned_loss=0.03409, over 1427600.40 frames.], batch size: 37, lr: 3.51e-04
2022-05-15 04:41:41,334 INFO [train.py:812] (4/8) Epoch 22, batch 3950, loss[loss=0.1349, simple_loss=0.225, pruned_loss=0.02243, over 7274.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2493, pruned_loss=0.03389, over 1425861.41 frames.], batch size: 17, lr: 3.51e-04
2022-05-15 04:42:39,861 INFO [train.py:812] (4/8) Epoch 22, batch 4000, loss[loss=0.1873, simple_loss=0.2882, pruned_loss=0.04318, over 7325.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2508, pruned_loss=0.03473, over 1425965.88 frames.], batch size: 21, lr: 3.51e-04
2022-05-15 04:43:37,310 INFO [train.py:812] (4/8) Epoch 22, batch 4050, loss[loss=0.1369, simple_loss=0.2265, pruned_loss=0.02363, over 7365.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2499, pruned_loss=0.03438, over 1423900.38 frames.], batch size: 19, lr: 3.51e-04
2022-05-15 04:44:35,623 INFO [train.py:812] (4/8) Epoch 22, batch 4100, loss[loss=0.1523, simple_loss=0.2487, pruned_loss=0.02797, over 7316.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2501, pruned_loss=0.03404, over 1424945.95 frames.], batch size: 20, lr: 3.51e-04
2022-05-15 04:45:34,802 INFO [train.py:812] (4/8) Epoch 22, batch 4150, loss[loss=0.1415, simple_loss=0.2368, pruned_loss=0.02312, over 7076.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2501, pruned_loss=0.03433, over 1420132.87 frames.], batch size: 18, lr: 3.51e-04
2022-05-15 04:46:33,510 INFO [train.py:812] (4/8) Epoch 22, batch 4200, loss[loss=0.1798, simple_loss=0.274, pruned_loss=0.0428, over 7146.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2499, pruned_loss=0.03391, over 1416222.44 frames.], batch size: 20, lr: 3.50e-04
2022-05-15 04:47:30,299 INFO [train.py:812] (4/8) Epoch 22, batch 4250, loss[loss=0.1507, simple_loss=0.2496, pruned_loss=0.02591, over 6704.00 frames.], tot_loss[loss=0.16, simple_loss=0.2507, pruned_loss=0.03463, over 1409837.41 frames.], batch size: 31, lr: 3.50e-04
2022-05-15 04:48:27,304 INFO [train.py:812] (4/8) Epoch 22, batch 4300, loss[loss=0.1577, simple_loss=0.2603, pruned_loss=0.0276, over 7290.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2506, pruned_loss=0.03428, over 1411645.41 frames.], batch size: 24, lr: 3.50e-04
2022-05-15 04:49:26,474 INFO [train.py:812] (4/8) Epoch 22, batch 4350, loss[loss=0.1596, simple_loss=0.262, pruned_loss=0.02858, over 7334.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2504, pruned_loss=0.03409, over 1409175.87 frames.], batch size: 22, lr: 3.50e-04
2022-05-15 04:50:35,270 INFO [train.py:812] (4/8) Epoch 22, batch 4400, loss[loss=0.184, simple_loss=0.2645, pruned_loss=0.05173, over 7120.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2509, pruned_loss=0.03441, over 1403948.80 frames.], batch size: 21, lr: 3.50e-04
2022-05-15 04:51:33,773 INFO [train.py:812] (4/8) Epoch 22, batch 4450, loss[loss=0.1524, simple_loss=0.2469, pruned_loss=0.02894, over 7341.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2522, pruned_loss=0.03481, over 1399789.73 frames.], batch size: 22, lr: 3.50e-04
2022-05-15 04:52:33,294 INFO [train.py:812] (4/8) Epoch 22, batch 4500, loss[loss=0.1748, simple_loss=0.2672, pruned_loss=0.04115, over 7024.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2541, pruned_loss=0.03567, over 1388642.31 frames.], batch size: 28, lr: 3.50e-04
2022-05-15 04:53:50,572 INFO [train.py:812] (4/8) Epoch 22, batch 4550, loss[loss=0.1759, simple_loss=0.2622, pruned_loss=0.04481, over 5309.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2558, pruned_loss=0.03686, over 1347640.55 frames.], batch size: 52, lr: 3.50e-04
2022-05-15 04:55:29,964 INFO [train.py:812] (4/8) Epoch 23, batch 0, loss[loss=0.1415, simple_loss=0.221, pruned_loss=0.031, over 6794.00 frames.], tot_loss[loss=0.1415, simple_loss=0.221, pruned_loss=0.031, over 6794.00 frames.], batch size: 15, lr: 3.42e-04
2022-05-15 04:56:28,542 INFO [train.py:812] (4/8) Epoch 23, batch 50, loss[loss=0.1386, simple_loss=0.2349, pruned_loss=0.02113, over 7163.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2512, pruned_loss=0.03602, over 319812.35 frames.], batch size: 19, lr: 3.42e-04
2022-05-15 04:57:26,788 INFO [train.py:812] (4/8) Epoch 23, batch 100, loss[loss=0.1558, simple_loss=0.2381, pruned_loss=0.03676, over 7281.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2529, pruned_loss=0.03498, over 566250.07 frames.], batch size: 18, lr: 3.42e-04
2022-05-15 04:58:25,155 INFO [train.py:812] (4/8) Epoch 23, batch 150, loss[loss=0.1528, simple_loss=0.2493, pruned_loss=0.02817, over 7297.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2535, pruned_loss=0.03535, over 753072.04 frames.], batch size: 24, lr: 3.42e-04
2022-05-15 04:59:34,121 INFO [train.py:812] (4/8) Epoch 23, batch 200, loss[loss=0.1508, simple_loss=0.2464, pruned_loss=0.02762, over 6502.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2514, pruned_loss=0.03437, over 901996.47 frames.], batch size: 38, lr: 3.42e-04
2022-05-15 05:00:33,216 INFO [train.py:812] (4/8) Epoch 23, batch 250, loss[loss=0.1808, simple_loss=0.2615, pruned_loss=0.04999, over 7229.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2513, pruned_loss=0.03446, over 1017260.81 frames.], batch size: 23, lr: 3.42e-04
2022-05-15 05:01:30,506 INFO [train.py:812] (4/8) Epoch 23, batch 300, loss[loss=0.1577, simple_loss=0.2506, pruned_loss=0.03237, over 7163.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2505, pruned_loss=0.03424, over 1103601.34 frames.], batch size: 19, lr: 3.42e-04
2022-05-15 05:02:29,198 INFO [train.py:812] (4/8) Epoch 23, batch 350, loss[loss=0.1513, simple_loss=0.242, pruned_loss=0.03036, over 7335.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03358, over 1178110.56 frames.], batch size: 22, lr: 3.42e-04
2022-05-15 05:03:27,248 INFO [train.py:812] (4/8) Epoch 23, batch 400, loss[loss=0.1643, simple_loss=0.2612, pruned_loss=0.03368, over 7206.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2497, pruned_loss=0.03346, over 1231907.60 frames.], batch size: 23, lr: 3.42e-04
2022-05-15 05:04:26,527 INFO [train.py:812] (4/8) Epoch 23, batch 450, loss[loss=0.1727, simple_loss=0.2661, pruned_loss=0.03967, over 7279.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2504, pruned_loss=0.03373, over 1272623.67 frames.], batch size: 24, lr: 3.42e-04
2022-05-15 05:05:24,832 INFO [train.py:812] (4/8) Epoch 23, batch 500, loss[loss=0.1602, simple_loss=0.2415, pruned_loss=0.03947, over 7218.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2513, pruned_loss=0.03397, over 1308687.67 frames.], batch size: 16, lr: 3.41e-04
2022-05-15 05:06:21,985 INFO [train.py:812] (4/8) Epoch 23, batch 550, loss[loss=0.1548, simple_loss=0.2434, pruned_loss=0.03308, over 7319.00 frames.], tot_loss[loss=0.1587, simple_loss=0.25, pruned_loss=0.03376, over 1337609.10 frames.], batch size: 24, lr: 3.41e-04
2022-05-15 05:07:20,813 INFO [train.py:812] (4/8) Epoch 23, batch 600, loss[loss=0.1461, simple_loss=0.2413, pruned_loss=0.02545, over 7113.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2501, pruned_loss=0.03387, over 1359697.48 frames.], batch size: 21, lr: 3.41e-04
2022-05-15 05:08:19,867 INFO [train.py:812] (4/8) Epoch 23, batch 650, loss[loss=0.1603, simple_loss=0.2511, pruned_loss=0.03471, over 6847.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2504, pruned_loss=0.03444, over 1374725.13 frames.], batch size: 31, lr: 3.41e-04
2022-05-15 05:09:19,439 INFO [train.py:812] (4/8) Epoch 23, batch 700, loss[loss=0.1849, simple_loss=0.2622, pruned_loss=0.05383, over 5054.00 frames.], tot_loss[loss=0.16, simple_loss=0.251, pruned_loss=0.03452, over 1381787.26 frames.], batch size: 52, lr: 3.41e-04
2022-05-15 05:10:18,456 INFO [train.py:812] (4/8) Epoch 23, batch 750, loss[loss=0.1703, simple_loss=0.2681, pruned_loss=0.03625, over 7193.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2512, pruned_loss=0.03445, over 1393037.52 frames.], batch size: 23, lr: 3.41e-04
2022-05-15 05:11:17,824 INFO [train.py:812] (4/8) Epoch 23, batch 800, loss[loss=0.1401, simple_loss=0.2232, pruned_loss=0.02844, over 7361.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2515, pruned_loss=0.03456, over 1396325.56 frames.], batch size: 19, lr: 3.41e-04
2022-05-15 05:12:15,506 INFO [train.py:812] (4/8) Epoch 23, batch 850, loss[loss=0.1385, simple_loss=0.2283, pruned_loss=0.02434, over 7431.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2509, pruned_loss=0.03451, over 1404688.27 frames.], batch size: 20, lr: 3.41e-04
2022-05-15 05:13:14,536 INFO [train.py:812] (4/8) Epoch 23, batch 900, loss[loss=0.1429, simple_loss=0.2348, pruned_loss=0.02552, over 7154.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2515, pruned_loss=0.03466, over 1408935.04 frames.], batch size: 19, lr: 3.41e-04
2022-05-15 05:14:13,170 INFO [train.py:812] (4/8) Epoch 23, batch 950, loss[loss=0.1795, simple_loss=0.2753, pruned_loss=0.04178, over 7025.00 frames.], tot_loss[loss=0.1598, simple_loss=0.251, pruned_loss=0.03431, over 1411044.40 frames.], batch size: 28, lr: 3.41e-04
2022-05-15 05:15:13,118 INFO [train.py:812] (4/8) Epoch 23, batch 1000, loss[loss=0.1533, simple_loss=0.2422, pruned_loss=0.03224, over 7360.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2504, pruned_loss=0.03392, over 1418039.09 frames.], batch size: 19, lr: 3.41e-04
2022-05-15 05:16:12,063 INFO [train.py:812] (4/8) Epoch 23, batch 1050, loss[loss=0.1969, simple_loss=0.2769, pruned_loss=0.05842, over 5068.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2506, pruned_loss=0.03433, over 1419037.61 frames.], batch size: 52, lr: 3.41e-04
2022-05-15 05:17:10,938 INFO [train.py:812] (4/8) Epoch 23, batch 1100, loss[loss=0.1528, simple_loss=0.2349, pruned_loss=0.03536, over 7283.00 frames.], tot_loss[loss=0.16, simple_loss=0.2511, pruned_loss=0.03445, over 1418904.95 frames.], batch size: 17, lr: 3.40e-04
2022-05-15 05:18:09,890 INFO [train.py:812] (4/8) Epoch 23, batch 1150, loss[loss=0.1502, simple_loss=0.2319, pruned_loss=0.03421, over 7429.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2506, pruned_loss=0.03421, over 1423237.67 frames.], batch size: 20, lr: 3.40e-04
2022-05-15 05:19:09,545 INFO [train.py:812] (4/8) Epoch 23, batch 1200, loss[loss=0.1511, simple_loss=0.2478, pruned_loss=0.0272, over 7292.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2503, pruned_loss=0.03395, over 1422257.10 frames.], batch size: 18, lr: 3.40e-04
2022-05-15 05:20:07,295 INFO [train.py:812] (4/8) Epoch 23, batch 1250, loss[loss=0.1329, simple_loss=0.2142, pruned_loss=0.02582, over 6749.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2492, pruned_loss=0.03378, over 1425468.50 frames.], batch size: 15, lr: 3.40e-04
2022-05-15 05:21:05,551 INFO [train.py:812] (4/8) Epoch 23, batch 1300, loss[loss=0.1683, simple_loss=0.2683, pruned_loss=0.0341, over 7191.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2493, pruned_loss=0.03393, over 1428316.20 frames.], batch size: 23, lr: 3.40e-04
2022-05-15 05:22:03,020 INFO [train.py:812] (4/8) Epoch 23, batch 1350, loss[loss=0.1266, simple_loss=0.2223, pruned_loss=0.01548, over 7274.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2484, pruned_loss=0.03358, over 1428675.50 frames.], batch size: 18, lr: 3.40e-04
2022-05-15 05:23:02,489 INFO [train.py:812] (4/8) Epoch 23, batch 1400, loss[loss=0.1324, simple_loss=0.2238, pruned_loss=0.02053, over 7121.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2483, pruned_loss=0.03332, over 1428149.74 frames.], batch size: 21, lr: 3.40e-04
2022-05-15 05:24:01,073 INFO [train.py:812] (4/8) Epoch 23, batch 1450, loss[loss=0.1409, simple_loss=0.2269, pruned_loss=0.02741, over 7403.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2482, pruned_loss=0.03366, over 1422784.75 frames.], batch size: 18, lr: 3.40e-04
2022-05-15 05:24:59,733 INFO [train.py:812] (4/8) Epoch 23, batch 1500, loss[loss=0.166, simple_loss=0.2596, pruned_loss=0.03614, over 7079.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2475, pruned_loss=0.03363, over 1423579.06 frames.], batch size: 28, lr: 3.40e-04
2022-05-15 05:25:58,346 INFO [train.py:812] (4/8) Epoch 23, batch 1550, loss[loss=0.1604, simple_loss=0.2553, pruned_loss=0.03281, over 7351.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2486, pruned_loss=0.03405, over 1414761.05 frames.], batch size: 19, lr: 3.40e-04
2022-05-15 05:26:57,169 INFO [train.py:812] (4/8) Epoch 23, batch 1600, loss[loss=0.163, simple_loss=0.25, pruned_loss=0.03801, over 7218.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2496, pruned_loss=0.0349, over 1413849.83 frames.], batch size: 21, lr: 3.40e-04
2022-05-15 05:27:55,180 INFO [train.py:812] (4/8) Epoch 23, batch 1650, loss[loss=0.1611, simple_loss=0.2502, pruned_loss=0.03607, over 7393.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2494, pruned_loss=0.03475, over 1417027.29 frames.], batch size: 23, lr: 3.40e-04
2022-05-15 05:28:54,100 INFO [train.py:812] (4/8) Epoch 23, batch 1700, loss[loss=0.1404, simple_loss=0.229, pruned_loss=0.02586, over 7410.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2498, pruned_loss=0.03487, over 1417813.26 frames.], batch size: 18, lr: 3.39e-04
2022-05-15 05:29:50,564 INFO [train.py:812] (4/8) Epoch 23, batch 1750, loss[loss=0.1943, simple_loss=0.2847, pruned_loss=0.05198, over 7181.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2506, pruned_loss=0.03492, over 1416316.36 frames.], batch size: 26, lr: 3.39e-04
2022-05-15 05:30:48,706 INFO [train.py:812] (4/8) Epoch 23, batch 1800, loss[loss=0.2296, simple_loss=0.314, pruned_loss=0.07257, over 5367.00 frames.], tot_loss[loss=0.1608, simple_loss=0.251, pruned_loss=0.03532, over 1412746.66 frames.], batch size: 52, lr: 3.39e-04
2022-05-15 05:31:46,088 INFO [train.py:812] (4/8) Epoch 23, batch 1850, loss[loss=0.1321, simple_loss=0.217, pruned_loss=0.02362, over 7426.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2507, pruned_loss=0.03497, over 1417133.89 frames.], batch size: 20, lr: 3.39e-04
2022-05-15 05:32:44,000 INFO [train.py:812] (4/8) Epoch 23, batch 1900, loss[loss=0.1644, simple_loss=0.2617, pruned_loss=0.03358, over 7142.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2502, pruned_loss=0.03478, over 1420326.60 frames.], batch size: 20, lr: 3.39e-04
2022-05-15 05:33:42,349 INFO [train.py:812] (4/8) Epoch 23, batch 1950, loss[loss=0.1528, simple_loss=0.2494, pruned_loss=0.02811, over 7141.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2502, pruned_loss=0.03474, over 1417717.58 frames.], batch size: 20, lr: 3.39e-04
2022-05-15 05:34:41,197 INFO [train.py:812] (4/8) Epoch 23, batch 2000, loss[loss=0.1661, simple_loss=0.2486, pruned_loss=0.04179, over 7262.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2512, pruned_loss=0.03491, over 1421444.49 frames.], batch size: 19, lr: 3.39e-04
2022-05-15 05:35:40,293 INFO [train.py:812] (4/8) Epoch 23, batch 2050, loss[loss=0.1765, simple_loss=0.2754, pruned_loss=0.03878, over 7239.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2513, pruned_loss=0.03461, over 1425525.65 frames.], batch size: 20, lr: 3.39e-04
2022-05-15 05:36:39,470 INFO [train.py:812] (4/8) Epoch 23, batch 2100, loss[loss=0.1735, simple_loss=0.2671, pruned_loss=0.0399, over 7210.00 frames.], tot_loss[loss=0.1591, simple_loss=0.25, pruned_loss=0.03411, over 1419736.44 frames.], batch size: 23, lr: 3.39e-04
2022-05-15 05:37:37,955 INFO [train.py:812] (4/8) Epoch 23, batch 2150, loss[loss=0.1381, simple_loss=0.2335, pruned_loss=0.02134, over 7160.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2499, pruned_loss=0.03421, over 1420969.35 frames.], batch size: 19, lr: 3.39e-04
2022-05-15 05:38:37,636 INFO [train.py:812] (4/8) Epoch 23, batch 2200, loss[loss=0.1462, simple_loss=0.247, pruned_loss=0.02269, over 7158.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2501, pruned_loss=0.0345, over 1416043.87 frames.], batch size: 20, lr: 3.39e-04
2022-05-15 05:39:36,695 INFO [train.py:812] (4/8) Epoch 23, batch 2250, loss[loss=0.1684, simple_loss=0.2501, pruned_loss=0.04338, over 7161.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2497, pruned_loss=0.03411, over 1412206.43 frames.], batch size: 19, lr: 3.39e-04
2022-05-15 05:40:35,585 INFO [train.py:812] (4/8) Epoch 23, batch 2300, loss[loss=0.175, simple_loss=0.2703, pruned_loss=0.03983, over 7325.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2489, pruned_loss=0.03405, over 1413895.95 frames.], batch size: 21, lr: 3.38e-04
2022-05-15 05:41:34,384 INFO [train.py:812] (4/8) Epoch 23, batch 2350, loss[loss=0.1461, simple_loss=0.2532, pruned_loss=0.01946, over 7330.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2493, pruned_loss=0.0338, over 1416602.51 frames.], batch size: 22, lr: 3.38e-04
2022-05-15 05:42:33,221 INFO [train.py:812] (4/8) Epoch 23, batch 2400, loss[loss=0.1671, simple_loss=0.2617, pruned_loss=0.03629, over 7290.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2503, pruned_loss=0.03395, over 1419119.12 frames.], batch size: 24, lr: 3.38e-04
2022-05-15 05:43:31,225 INFO [train.py:812] (4/8) Epoch 23, batch 2450, loss[loss=0.1849, simple_loss=0.2708, pruned_loss=0.04945, over 7187.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2514, pruned_loss=0.03438, over 1423105.56 frames.], batch size: 22, lr: 3.38e-04
2022-05-15 05:44:30,332 INFO [train.py:812] (4/8) Epoch 23, batch 2500, loss[loss=0.1527, simple_loss=0.2429, pruned_loss=0.03123, over 6350.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2493, pruned_loss=0.03376, over 1421016.12 frames.], batch size: 37, lr: 3.38e-04
2022-05-15 05:45:29,324 INFO [train.py:812] (4/8) Epoch 23, batch 2550, loss[loss=0.1663, simple_loss=0.2586, pruned_loss=0.03696, over 7374.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2493, pruned_loss=0.03343, over 1421905.46 frames.], batch size: 23, lr: 3.38e-04
2022-05-15 05:46:26,773 INFO [train.py:812] (4/8) Epoch 23, batch 2600, loss[loss=0.1578, simple_loss=0.2487, pruned_loss=0.03347, over 7342.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2493, pruned_loss=0.03387, over 1425964.76 frames.], batch size: 22, lr: 3.38e-04
2022-05-15 05:47:25,316 INFO [train.py:812] (4/8) Epoch 23, batch 2650, loss[loss=0.1586, simple_loss=0.2533, pruned_loss=0.03197, over 7285.00 frames.], tot_loss[loss=0.158, simple_loss=0.2487, pruned_loss=0.03368, over 1422777.04 frames.], batch size: 25, lr: 3.38e-04
2022-05-15 05:48:25,328 INFO [train.py:812] (4/8) Epoch 23, batch 2700, loss[loss=0.14, simple_loss=0.2313, pruned_loss=0.0243, over 7161.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2491, pruned_loss=0.0339, over 1423119.58 frames.], batch size: 19, lr: 3.38e-04
2022-05-15 05:49:24,352 INFO [train.py:812] (4/8) Epoch 23, batch 2750, loss[loss=0.1505, simple_loss=0.2399, pruned_loss=0.03056, over 7172.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2492, pruned_loss=0.03446, over 1420919.63 frames.], batch size: 18, lr: 3.38e-04
2022-05-15 05:50:23,651 INFO [train.py:812] (4/8) Epoch 23, batch 2800, loss[loss=0.1513, simple_loss=0.2365, pruned_loss=0.03306, over 7171.00 frames.], tot_loss[loss=0.159, simple_loss=0.2493, pruned_loss=0.0344, over 1420135.01 frames.], batch size: 18, lr: 3.38e-04
2022-05-15 05:51:22,634 INFO [train.py:812] (4/8) Epoch 23, batch 2850, loss[loss=0.1821, simple_loss=0.2795, pruned_loss=0.04237, over 7101.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2486, pruned_loss=0.03402, over 1421824.29 frames.], batch size: 28, lr: 3.38e-04
2022-05-15 05:52:22,315 INFO [train.py:812] (4/8) Epoch 23, batch 2900, loss[loss=0.1668, simple_loss=0.2522, pruned_loss=0.04066, over 7327.00 frames.], tot_loss[loss=0.1585, simple_loss=0.249, pruned_loss=0.03396, over 1423441.96 frames.], batch size: 25, lr: 3.37e-04
2022-05-15 05:53:20,354 INFO [train.py:812] (4/8) Epoch 23, batch 2950, loss[loss=0.1618, simple_loss=0.2573, pruned_loss=0.03314, over 7198.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2494, pruned_loss=0.03412, over 1424430.46 frames.], batch size: 22, lr: 3.37e-04
2022-05-15 05:54:18,726 INFO [train.py:812] (4/8) Epoch 23, batch 3000, loss[loss=0.1318, simple_loss=0.2111, pruned_loss=0.02629, over 7002.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2498, pruned_loss=0.03427, over 1423324.35 frames.], batch size: 16, lr: 3.37e-04
2022-05-15 05:54:18,727 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 05:54:28,115 INFO [train.py:841] (4/8) Epoch 23, validation: loss=0.153, simple_loss=0.251, pruned_loss=0.02752, over 698248.00 frames.
2022-05-15 05:55:26,689 INFO [train.py:812] (4/8) Epoch 23, batch 3050, loss[loss=0.1477, simple_loss=0.23, pruned_loss=0.03276, over 7151.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2498, pruned_loss=0.03418, over 1426208.56 frames.], batch size: 19, lr: 3.37e-04
2022-05-15 05:56:31,542 INFO [train.py:812] (4/8) Epoch 23, batch 3100, loss[loss=0.1386, simple_loss=0.2334, pruned_loss=0.02194, over 7232.00 frames.], tot_loss[loss=0.1586, simple_loss=0.249, pruned_loss=0.03411, over 1425767.69 frames.], batch size: 20, lr: 3.37e-04
2022-05-15 05:57:30,938 INFO [train.py:812] (4/8) Epoch 23, batch 3150, loss[loss=0.1426, simple_loss=0.2268, pruned_loss=0.02913, over 7324.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2483, pruned_loss=0.03395, over 1427194.70 frames.], batch size: 20, lr: 3.37e-04
2022-05-15 05:58:30,532 INFO [train.py:812] (4/8) Epoch 23, batch 3200, loss[loss=0.1612, simple_loss=0.255, pruned_loss=0.03371, over 7110.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2487, pruned_loss=0.03408, over 1428227.07 frames.], batch size: 21, lr: 3.37e-04
2022-05-15 05:59:29,507 INFO [train.py:812] (4/8) Epoch 23, batch 3250, loss[loss=0.1553, simple_loss=0.2532, pruned_loss=0.02872, over 6371.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2501, pruned_loss=0.03446, over 1422072.79 frames.], batch size: 38, lr: 3.37e-04
2022-05-15 06:00:29,699 INFO [train.py:812] (4/8) Epoch 23, batch 3300, loss[loss=0.1718, simple_loss=0.2573, pruned_loss=0.04315, over 7322.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2505, pruned_loss=0.03434, over 1422739.92 frames.], batch size: 24, lr: 3.37e-04
2022-05-15 06:01:29,032 INFO [train.py:812] (4/8) Epoch 23, batch 3350, loss[loss=0.1594, simple_loss=0.2599, pruned_loss=0.02942, over 7146.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2493, pruned_loss=0.034, over 1427025.68 frames.], batch size: 26, lr: 3.37e-04
2022-05-15 06:02:28,580 INFO [train.py:812] (4/8) Epoch 23, batch 3400, loss[loss=0.1451, simple_loss=0.2383, pruned_loss=0.02594, over 7157.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2487, pruned_loss=0.03394, over 1427899.71 frames.], batch size: 19, lr: 3.37e-04
2022-05-15 06:03:27,803 INFO [train.py:812] (4/8) Epoch 23, batch 3450, loss[loss=0.1489, simple_loss=0.2327, pruned_loss=0.03262, over 7296.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2473, pruned_loss=0.03325, over 1429907.22 frames.], batch size: 16, lr: 3.37e-04
2022-05-15 06:04:27,368 INFO [train.py:812] (4/8) Epoch 23, batch 3500, loss[loss=0.1284, simple_loss=0.2112, pruned_loss=0.02282, over 6816.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2476, pruned_loss=0.03341, over 1430635.51 frames.], batch size: 15, lr: 3.37e-04
2022-05-15 06:05:25,897 INFO [train.py:812] (4/8) Epoch 23, batch 3550, loss[loss=0.1399, simple_loss=0.2173, pruned_loss=0.03132, over 7417.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2473, pruned_loss=0.03327, over 1430084.87 frames.], batch size: 18, lr: 3.36e-04
2022-05-15 06:06:25,041 INFO [train.py:812] (4/8) Epoch 23, batch 3600, loss[loss=0.1435, simple_loss=0.2272, pruned_loss=0.02985, over 7286.00 frames.], tot_loss[loss=0.1575, simple_loss=0.248, pruned_loss=0.03346, over 1431418.61 frames.], batch size: 17, lr: 3.36e-04
2022-05-15 06:07:24,129 INFO [train.py:812] (4/8) Epoch 23, batch 3650, loss[loss=0.1814, simple_loss=0.2675, pruned_loss=0.04762, over 6506.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2485, pruned_loss=0.03366, over 1431623.75 frames.], batch size: 37, lr: 3.36e-04
2022-05-15 06:08:33,464 INFO [train.py:812] (4/8) Epoch 23, batch 3700, loss[loss=0.1671, simple_loss=0.2692, pruned_loss=0.03256, over 7153.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2484, pruned_loss=0.03344, over 1430165.91 frames.], batch size: 19, lr: 3.36e-04
2022-05-15 06:09:32,127 INFO [train.py:812] (4/8) Epoch 23, batch 3750, loss[loss=0.1382, simple_loss=0.2193, pruned_loss=0.02851, over 7277.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2485, pruned_loss=0.03325, over 1427968.25 frames.], batch size: 17, lr: 3.36e-04
2022-05-15 06:10:31,415 INFO [train.py:812] (4/8) Epoch 23, batch 3800, loss[loss=0.1736, simple_loss=0.2635, pruned_loss=0.04185, over 7382.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2487, pruned_loss=0.03342, over 1429831.14 frames.], batch size: 23, lr: 3.36e-04
2022-05-15 06:11:30,124 INFO [train.py:812] (4/8) Epoch 23, batch 3850, loss[loss=0.1733, simple_loss=0.264, pruned_loss=0.04131, over 7073.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2482, pruned_loss=0.03349, over 1430366.77 frames.], batch size: 28, lr: 3.36e-04
2022-05-15 06:12:28,297 INFO [train.py:812] (4/8) Epoch 23, batch 3900, loss[loss=0.1707, simple_loss=0.2604, pruned_loss=0.0405, over 7111.00 frames.], tot_loss[loss=0.159, simple_loss=0.2494, pruned_loss=0.03433, over 1430897.80 frames.], batch size: 21, lr: 3.36e-04
2022-05-15 06:13:25,766 INFO [train.py:812] (4/8) Epoch 23, batch 3950, loss[loss=0.1613, simple_loss=0.2513, pruned_loss=0.03566, over 7160.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2499, pruned_loss=0.03419, over 1430174.28 frames.], batch size: 19, lr: 3.36e-04
2022-05-15 06:14:22,995 INFO [train.py:812] (4/8) Epoch 23, batch 4000, loss[loss=0.1416, simple_loss=0.2344, pruned_loss=0.02438, over 7283.00 frames.], tot_loss[loss=0.1582, simple_loss=0.249, pruned_loss=0.03371, over 1427166.79 frames.], batch size: 17, lr: 3.36e-04
2022-05-15 06:15:21,474 INFO [train.py:812] (4/8) Epoch 23, batch 4050, loss[loss=0.1399, simple_loss=0.2214, pruned_loss=0.02922, over 6817.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2506, pruned_loss=0.03461, over 1422096.71 frames.], batch size: 15, lr: 3.36e-04
2022-05-15 06:16:21,795 INFO [train.py:812] (4/8) Epoch 23, batch 4100, loss[loss=0.1317, simple_loss=0.2124, pruned_loss=0.0255, over 6785.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2502, pruned_loss=0.03463, over 1419262.98 frames.], batch size: 15, lr: 3.36e-04
2022-05-15 06:17:19,467 INFO [train.py:812] (4/8) Epoch 23, batch 4150, loss[loss=0.1441, simple_loss=0.2375, pruned_loss=0.02533, over 7327.00 frames.], tot_loss[loss=0.1602, simple_loss=0.251, pruned_loss=0.03476, over 1418515.35 frames.], batch size: 21, lr: 3.35e-04
2022-05-15 06:18:18,884 INFO [train.py:812] (4/8) Epoch 23, batch 4200, loss[loss=0.127, simple_loss=0.2064, pruned_loss=0.02375, over 7009.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2517, pruned_loss=0.03491, over 1422776.29 frames.], batch size: 16, lr: 3.35e-04
2022-05-15 06:19:17,847 INFO [train.py:812] (4/8) Epoch 23, batch 4250, loss[loss=0.1484, simple_loss=0.2428, pruned_loss=0.02704, over 7241.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2515, pruned_loss=0.03474, over 1424243.99 frames.], batch size: 20, lr: 3.35e-04
2022-05-15 06:20:16,267 INFO [train.py:812] (4/8) Epoch 23, batch 4300, loss[loss=0.1563, simple_loss=0.2379, pruned_loss=0.03733, over 7165.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2502, pruned_loss=0.03463, over 1421204.45 frames.], batch size: 18, lr: 3.35e-04
2022-05-15 06:21:15,794 INFO [train.py:812] (4/8) Epoch 23, batch 4350, loss[loss=0.1487, simple_loss=0.2265, pruned_loss=0.03539, over 7225.00 frames.], tot_loss[loss=0.1587, simple_loss=0.249, pruned_loss=0.0342, over 1422914.81 frames.], batch size: 16, lr: 3.35e-04
2022-05-15 06:22:15,641 INFO [train.py:812] (4/8) Epoch 23, batch 4400, loss[loss=0.1489, simple_loss=0.2391, pruned_loss=0.02936, over 7067.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2488, pruned_loss=0.0341, over 1420980.42 frames.], batch size: 18, lr: 3.35e-04
2022-05-15 06:23:14,861 INFO [train.py:812] (4/8) Epoch 23, batch 4450, loss[loss=0.2235, simple_loss=0.2984, pruned_loss=0.07433, over 4924.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2493, pruned_loss=0.0344, over 1415039.73 frames.], batch size: 52, lr: 3.35e-04
2022-05-15 06:24:12,956 INFO [train.py:812] (4/8) Epoch 23, batch 4500, loss[loss=0.1429, simple_loss=0.2265, pruned_loss=0.02959, over 7066.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2496, pruned_loss=0.03407, over 1413779.82 frames.], batch size: 18, lr: 3.35e-04
2022-05-15 06:25:11,010 INFO [train.py:812] (4/8) Epoch 23, batch 4550, loss[loss=0.1635, simple_loss=0.2443, pruned_loss=0.04131, over 5091.00 frames.], tot_loss[loss=0.1618, simple_loss=0.252, pruned_loss=0.03579, over 1354652.23 frames.], batch size: 52, lr: 3.35e-04
2022-05-15 06:26:16,426 INFO [train.py:812] (4/8) Epoch 24, batch 0, loss[loss=0.1412, simple_loss=0.2275, pruned_loss=0.02747, over 6778.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2275, pruned_loss=0.02747, over 6778.00 frames.], batch size: 15, lr: 3.28e-04
2022-05-15 06:27:14,053 INFO [train.py:812] (4/8) Epoch 24, batch 50, loss[loss=0.1308, simple_loss=0.2159, pruned_loss=0.02283, over 7275.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2464, pruned_loss=0.03148, over 316728.80 frames.], batch size: 17, lr: 3.28e-04
2022-05-15 06:28:13,405 INFO [train.py:812] (4/8) Epoch 24, batch 100, loss[loss=0.181, simple_loss=0.2846, pruned_loss=0.0387, over 7328.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2476, pruned_loss=0.03227, over 567391.81 frames.], batch size: 20, lr: 3.28e-04
2022-05-15 06:29:11,074 INFO [train.py:812] (4/8) Epoch 24, batch 150, loss[loss=0.17, simple_loss=0.2654, pruned_loss=0.0373, over 7377.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2503, pruned_loss=0.03336, over 753268.96 frames.], batch size: 23, lr: 3.28e-04
2022-05-15 06:30:10,084 INFO [train.py:812] (4/8) Epoch 24, batch 200, loss[loss=0.1804, simple_loss=0.2717, pruned_loss=0.04452, over 7212.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2488, pruned_loss=0.03305, over 904089.04 frames.], batch size: 22, lr: 3.28e-04
2022-05-15 06:31:07,642 INFO [train.py:812] (4/8) Epoch 24, batch 250, loss[loss=0.1495, simple_loss=0.2483, pruned_loss=0.02539, over 7416.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2488, pruned_loss=0.03317, over 1016621.35 frames.], batch size: 21, lr: 3.28e-04
2022-05-15 06:32:07,186 INFO [train.py:812] (4/8) Epoch 24, batch 300, loss[loss=0.1456, simple_loss=0.2433, pruned_loss=0.02392, over 7140.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2484, pruned_loss=0.0331, over 1107664.52 frames.], batch size: 20, lr: 3.27e-04
2022-05-15 06:33:03,997 INFO [train.py:812] (4/8) Epoch 24, batch 350, loss[loss=0.1553, simple_loss=0.2504, pruned_loss=0.03009, over 7284.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2477, pruned_loss=0.03272, over 1179376.63 frames.], batch size: 25, lr: 3.27e-04
2022-05-15 06:34:01,080 INFO [train.py:812] (4/8) Epoch 24, batch 400, loss[loss=0.1614, simple_loss=0.2513, pruned_loss=0.03574, over 7303.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2467, pruned_loss=0.03282, over 1230676.75 frames.], batch size: 24, lr: 3.27e-04
2022-05-15 06:34:58,897 INFO [train.py:812] (4/8) Epoch 24, batch 450, loss[loss=0.1562, simple_loss=0.2519, pruned_loss=0.03027, over 7140.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2475, pruned_loss=0.03297, over 1276638.54 frames.], batch size: 20, lr: 3.27e-04
2022-05-15 06:35:57,369 INFO [train.py:812] (4/8) Epoch 24, batch 500, loss[loss=0.1292, simple_loss=0.2217, pruned_loss=0.01837, over 7361.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2478, pruned_loss=0.0329, over 1308378.03 frames.], batch size: 19, lr: 3.27e-04
2022-05-15 06:36:55,887 INFO [train.py:812] (4/8) Epoch 24, batch 550, loss[loss=0.1764, simple_loss=0.2749, pruned_loss=0.03893, over 7214.00 frames.], tot_loss[loss=0.1571, simple_loss=0.248, pruned_loss=0.03312, over 1336359.55 frames.], batch size: 22, lr: 3.27e-04
2022-05-15 06:37:55,367 INFO [train.py:812] (4/8) Epoch 24, batch 600, loss[loss=0.1522, simple_loss=0.2359, pruned_loss=0.0343, over 7361.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2468, pruned_loss=0.03275, over 1354178.23 frames.], batch size: 19, lr: 3.27e-04
2022-05-15 06:38:54,598 INFO [train.py:812] (4/8) Epoch 24, batch 650, loss[loss=0.1809, simple_loss=0.2654, pruned_loss=0.04826, over 7361.00 frames.], tot_loss[loss=0.157, simple_loss=0.2477, pruned_loss=0.03319, over 1365925.03 frames.], batch size: 19, lr: 3.27e-04
2022-05-15 06:39:54,722 INFO [train.py:812] (4/8) Epoch 24, batch 700, loss[loss=0.1827, simple_loss=0.2741, pruned_loss=0.04566, over 7170.00 frames.], tot_loss[loss=0.156, simple_loss=0.2464, pruned_loss=0.03282, over 1382236.68 frames.], batch size: 26, lr: 3.27e-04
2022-05-15 06:40:53,830 INFO [train.py:812] (4/8) Epoch 24, batch 750, loss[loss=0.1435, simple_loss=0.2295, pruned_loss=0.02878, over 6987.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2473, pruned_loss=0.03275, over 1392120.20 frames.], batch size: 16, lr: 3.27e-04
2022-05-15 06:41:53,037 INFO [train.py:812] (4/8) Epoch 24, batch 800, loss[loss=0.1503, simple_loss=0.2405, pruned_loss=0.03004, over 7258.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03257, over 1399087.20 frames.], batch size: 19, lr: 3.27e-04
2022-05-15 06:42:52,227 INFO [train.py:812] (4/8) Epoch 24, batch 850, loss[loss=0.1554, simple_loss=0.2545, pruned_loss=0.0282, over 6957.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2468, pruned_loss=0.0321, over 1405053.57 frames.], batch size: 32, lr: 3.27e-04
2022-05-15 06:43:51,472 INFO [train.py:812] (4/8) Epoch 24, batch 900, loss[loss=0.1481, simple_loss=0.2443, pruned_loss=0.02596, over 7437.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.0317, over 1410862.82 frames.], batch size: 20, lr: 3.27e-04
2022-05-15 06:44:50,517 INFO [train.py:812] (4/8) Epoch 24, batch 950, loss[loss=0.1604, simple_loss=0.2501, pruned_loss=0.03538, over 6338.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2464, pruned_loss=0.03194, over 1415433.19 frames.], batch size: 37, lr: 3.26e-04
2022-05-15 06:45:49,539 INFO [train.py:812] (4/8) Epoch 24, batch 1000, loss[loss=0.1659, simple_loss=0.2657, pruned_loss=0.0331, over 7315.00 frames.], tot_loss[loss=0.156, simple_loss=0.2471, pruned_loss=0.03239, over 1416778.01 frames.], batch size: 21, lr: 3.26e-04
2022-05-15 06:46:47,308 INFO [train.py:812] (4/8) Epoch 24, batch 1050, loss[loss=0.1338, simple_loss=0.2326, pruned_loss=0.0175, over 7230.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2483, pruned_loss=0.0331, over 1410203.27 frames.], batch size: 20, lr: 3.26e-04
2022-05-15 06:47:46,418 INFO [train.py:812] (4/8) Epoch 24, batch 1100, loss[loss=0.1672, simple_loss=0.2614, pruned_loss=0.03647, over 7142.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2481, pruned_loss=0.0329, over 1409906.03 frames.], batch size: 20, lr: 3.26e-04
2022-05-15 06:48:44,901 INFO [train.py:812] (4/8) Epoch 24, batch 1150, loss[loss=0.1679, simple_loss=0.2534, pruned_loss=0.04114, over 6278.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2478, pruned_loss=0.03288, over 1413403.53 frames.], batch size: 37, lr: 3.26e-04
2022-05-15 06:49:42,950 INFO [train.py:812] (4/8) Epoch 24, batch 1200, loss[loss=0.1441, simple_loss=0.2352, pruned_loss=0.02647, over 7176.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03221, over 1415796.50 frames.], batch size: 18, lr: 3.26e-04
2022-05-15 06:50:50,713 INFO [train.py:812] (4/8) Epoch 24, batch 1250, loss[loss=0.1402, simple_loss=0.2302, pruned_loss=0.02508, over 7329.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2467, pruned_loss=0.03257, over 1417169.87 frames.], batch size: 20, lr: 3.26e-04
2022-05-15 06:51:49,901 INFO [train.py:812] (4/8) Epoch 24, batch 1300, loss[loss=0.1502, simple_loss=0.2496, pruned_loss=0.02536, over 6772.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2474, pruned_loss=0.03309, over 1418825.06 frames.], batch size: 31, lr: 3.26e-04
2022-05-15 06:52:48,835 INFO [train.py:812] (4/8) Epoch 24, batch 1350, loss[loss=0.1568, simple_loss=0.24, pruned_loss=0.03678, over 7415.00 frames.], tot_loss[loss=0.158, simple_loss=0.2485, pruned_loss=0.03372, over 1425050.81 frames.], batch size: 18, lr: 3.26e-04
2022-05-15 06:53:46,292 INFO [train.py:812] (4/8) Epoch 24, batch 1400, loss[loss=0.1661, simple_loss=0.2584, pruned_loss=0.03687, over 7191.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2489, pruned_loss=0.0341, over 1423827.57 frames.], batch size: 26, lr: 3.26e-04
2022-05-15 06:55:13,451 INFO [train.py:812] (4/8) Epoch 24, batch 1450, loss[loss=0.1465, simple_loss=0.2435, pruned_loss=0.02473, over 7142.00 frames.], tot_loss[loss=0.1583, simple_loss=0.249, pruned_loss=0.03385, over 1422021.36 frames.], batch size: 20, lr: 3.26e-04
2022-05-15 06:56:21,949 INFO [train.py:812] (4/8) Epoch 24, batch 1500, loss[loss=0.163, simple_loss=0.2563, pruned_loss=0.03485, over 7139.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2485, pruned_loss=0.03359, over 1421040.76 frames.], batch size: 20, lr: 3.26e-04
2022-05-15 06:57:21,244 INFO [train.py:812] (4/8) Epoch 24, batch 1550, loss[loss=0.1714, simple_loss=0.2732, pruned_loss=0.03476, over 6722.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2481, pruned_loss=0.03377, over 1421270.47 frames.], batch size: 31, lr: 3.26e-04
2022-05-15 06:58:39,392 INFO [train.py:812] (4/8) Epoch 24, batch 1600, loss[loss=0.1657, simple_loss=0.2544, pruned_loss=0.03845, over 7336.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2491, pruned_loss=0.03413, over 1422903.37 frames.], batch size: 20, lr: 3.25e-04
2022-05-15 06:59:37,742 INFO [train.py:812] (4/8) Epoch 24, batch 1650, loss[loss=0.1507, simple_loss=0.2342, pruned_loss=0.03356, over 6789.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2496, pruned_loss=0.03389, over 1414694.45 frames.], batch size: 15, lr: 3.25e-04
2022-05-15 07:00:36,792 INFO [train.py:812] (4/8) Epoch 24, batch 1700, loss[loss=0.1689, simple_loss=0.2729, pruned_loss=0.03243, over 7331.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2504, pruned_loss=0.03394, over 1418144.89 frames.], batch size: 21, lr: 3.25e-04
2022-05-15 07:01:34,460 INFO [train.py:812] (4/8) Epoch 24, batch 1750, loss[loss=0.1356, simple_loss=0.2227, pruned_loss=0.0242, over 7056.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2504, pruned_loss=0.03402, over 1420038.70 frames.], batch size: 18, lr: 3.25e-04
2022-05-15 07:02:33,275 INFO [train.py:812] (4/8) Epoch 24, batch 1800, loss[loss=0.158, simple_loss=0.2517, pruned_loss=0.03213, over 7331.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2494, pruned_loss=0.03348, over 1420075.99 frames.], batch size: 22, lr: 3.25e-04
2022-05-15 07:03:31,326 INFO [train.py:812] (4/8) Epoch 24, batch 1850, loss[loss=0.1587, simple_loss=0.2495, pruned_loss=0.03398, over 7278.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2493, pruned_loss=0.03364, over 1423609.06 frames.], batch size: 24, lr: 3.25e-04
2022-05-15 07:04:30,223 INFO [train.py:812] (4/8) Epoch 24, batch 1900, loss[loss=0.1687, simple_loss=0.2609, pruned_loss=0.03827, over 7022.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2495, pruned_loss=0.03368, over 1421846.77 frames.], batch size: 28, lr: 3.25e-04
2022-05-15 07:05:29,097 INFO [train.py:812] (4/8) Epoch 24, batch 1950, loss[loss=0.169, simple_loss=0.2729, pruned_loss=0.03258, over 7107.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2499, pruned_loss=0.03351, over 1423554.75 frames.], batch size: 21, lr: 3.25e-04
2022-05-15 07:06:27,365 INFO [train.py:812] (4/8) Epoch 24, batch 2000, loss[loss=0.1747, simple_loss=0.2542, pruned_loss=0.04765, over 5038.00 frames.], tot_loss[loss=0.159, simple_loss=0.2507, pruned_loss=0.0336, over 1422049.90 frames.], batch size: 52, lr: 3.25e-04
2022-05-15 07:07:25,811 INFO [train.py:812] (4/8) Epoch 24, batch 2050, loss[loss=0.1576, simple_loss=0.2468, pruned_loss=0.03415, over 7429.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2512, pruned_loss=0.03411, over 1422076.78 frames.], batch size: 20, lr: 3.25e-04
2022-05-15 07:08:23,660 INFO [train.py:812] (4/8) Epoch 24, batch 2100, loss[loss=0.14, simple_loss=0.2273, pruned_loss=0.02632, over 7009.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2501, pruned_loss=0.03354, over 1423518.67 frames.], batch size: 16, lr: 3.25e-04
2022-05-15 07:09:22,549 INFO [train.py:812] (4/8) Epoch 24, batch 2150, loss[loss=0.1794, simple_loss=0.2619, pruned_loss=0.04851, over 5271.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03364, over 1420898.51 frames.], batch size: 52, lr: 3.25e-04
2022-05-15 07:10:21,850 INFO [train.py:812] (4/8) Epoch 24, batch 2200, loss[loss=0.1385, simple_loss=0.2219, pruned_loss=0.02755, over 7142.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2488, pruned_loss=0.03341, over 1420475.44 frames.], batch size: 17, lr: 3.25e-04
2022-05-15 07:11:20,859 INFO [train.py:812] (4/8) Epoch 24, batch 2250, loss[loss=0.1539, simple_loss=0.2542, pruned_loss=0.02675, over 7331.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2496, pruned_loss=0.03372, over 1410138.95 frames.], batch size: 25, lr: 3.24e-04
2022-05-15 07:12:19,954 INFO [train.py:812] (4/8) Epoch 24, batch 2300, loss[loss=0.1573, simple_loss=0.2477, pruned_loss=0.03345, over 7259.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2489, pruned_loss=0.03339, over 1416648.80 frames.], batch size: 17, lr: 3.24e-04
2022-05-15 07:13:18,781 INFO [train.py:812] (4/8) Epoch 24, batch 2350, loss[loss=0.1595, simple_loss=0.2567, pruned_loss=0.03108, over 7327.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2493, pruned_loss=0.03324, over 1418304.17 frames.], batch size: 22, lr: 3.24e-04
2022-05-15 07:14:18,394 INFO [train.py:812] (4/8) Epoch 24, batch 2400, loss[loss=0.1217, simple_loss=0.2094, pruned_loss=0.01704, over 6808.00 frames.], tot_loss[loss=0.158, simple_loss=0.2497, pruned_loss=0.03314, over 1421898.48 frames.], batch size: 15, lr: 3.24e-04
2022-05-15 07:15:15,759 INFO [train.py:812] (4/8) Epoch 24, batch 2450, loss[loss=0.1791, simple_loss=0.2712, pruned_loss=0.04349, over 7233.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2491, pruned_loss=0.03337, over 1418715.91 frames.], batch size: 20, lr: 3.24e-04
2022-05-15 07:16:21,378 INFO [train.py:812] (4/8) Epoch 24, batch 2500, loss[loss=0.1405, simple_loss=0.2323, pruned_loss=0.0243, over 7311.00 frames.], tot_loss[loss=0.157, simple_loss=0.2482, pruned_loss=0.03287, over 1418969.34 frames.], batch size: 21, lr: 3.24e-04
2022-05-15 07:17:19,928 INFO [train.py:812] (4/8) Epoch 24, batch 2550, loss[loss=0.1711, simple_loss=0.2525, pruned_loss=0.04487, over 5014.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.03258, over 1415440.15 frames.], batch size: 54, lr: 3.24e-04
2022-05-15 07:18:18,697 INFO [train.py:812] (4/8) Epoch 24, batch 2600, loss[loss=0.1436, simple_loss=0.2326, pruned_loss=0.02731, over 7278.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2487, pruned_loss=0.0328, over 1418736.49 frames.], batch size: 18, lr: 3.24e-04
2022-05-15 07:19:17,315 INFO [train.py:812] (4/8) Epoch 24, batch 2650, loss[loss=0.1621, simple_loss=0.2502, pruned_loss=0.03701, over 7312.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2487, pruned_loss=0.03273, over 1417147.38 frames.], batch size: 21, lr: 3.24e-04
2022-05-15 07:20:16,527 INFO [train.py:812] (4/8) Epoch 24, batch 2700, loss[loss=0.18, simple_loss=0.2786, pruned_loss=0.04074, over 7334.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2497, pruned_loss=0.03344, over 1421843.50 frames.], batch size: 22, lr: 3.24e-04
2022-05-15 07:21:15,978 INFO [train.py:812] (4/8) Epoch 24, batch 2750, loss[loss=0.1511, simple_loss=0.2408, pruned_loss=0.03074, over 7419.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2486, pruned_loss=0.03287, over 1424837.19 frames.], batch size: 21, lr: 3.24e-04
2022-05-15 07:22:15,051 INFO [train.py:812] (4/8) Epoch 24, batch 2800, loss[loss=0.1472, simple_loss=0.249, pruned_loss=0.02266, over 7246.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2501, pruned_loss=0.03352, over 1421867.50 frames.], batch size: 20, lr: 3.24e-04
2022-05-15 07:23:13,166 INFO [train.py:812] (4/8) Epoch 24, batch 2850, loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03088, over 7366.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2509, pruned_loss=0.03393, over 1422102.97 frames.], batch size: 19, lr: 3.24e-04
2022-05-15 07:24:12,089 INFO [train.py:812] (4/8) Epoch 24, batch 2900, loss[loss=0.1767, simple_loss=0.2681, pruned_loss=0.04268, over 7314.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2508, pruned_loss=0.03392, over 1422744.96 frames.], batch size: 25, lr: 3.24e-04
2022-05-15 07:25:09,865 INFO [train.py:812] (4/8) Epoch 24, batch 2950, loss[loss=0.1627, simple_loss=0.2338, pruned_loss=0.04581, over 7285.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2502, pruned_loss=0.03348, over 1426450.77 frames.], batch size: 17, lr: 3.23e-04
2022-05-15 07:26:08,042 INFO [train.py:812] (4/8) Epoch 24, batch 3000, loss[loss=0.1689, simple_loss=0.2639, pruned_loss=0.03695, over 7123.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2511, pruned_loss=0.03385, over 1422212.70 frames.], batch size: 21, lr: 3.23e-04
2022-05-15 07:26:08,043 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 07:26:15,602 INFO [train.py:841] (4/8) 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] (4/8) Epoch 24, batch 3050, loss[loss=0.1488, simple_loss=0.2356, pruned_loss=0.03103, over 7289.00 frames.], tot_loss[loss=0.159, simple_loss=0.2503, pruned_loss=0.03388, over 1417544.15 frames.], batch size: 18, lr: 3.23e-04
2022-05-15 07:28:13,638 INFO [train.py:812] (4/8) Epoch 24, batch 3100, loss[loss=0.1462, simple_loss=0.2474, pruned_loss=0.02251, over 6705.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2497, pruned_loss=0.03401, over 1420861.62 frames.], batch size: 31, lr: 3.23e-04
2022-05-15 07:29:12,197 INFO [train.py:812] (4/8) Epoch 24, batch 3150, loss[loss=0.1305, simple_loss=0.2171, pruned_loss=0.02195, over 7014.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03355, over 1421744.92 frames.], batch size: 16, lr: 3.23e-04
2022-05-15 07:30:11,686 INFO [train.py:812] (4/8) Epoch 24, batch 3200, loss[loss=0.1618, simple_loss=0.2567, pruned_loss=0.03347, over 7318.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03352, over 1425990.67 frames.], batch size: 21, lr: 3.23e-04
2022-05-15 07:31:10,165 INFO [train.py:812] (4/8) Epoch 24, batch 3250, loss[loss=0.1498, simple_loss=0.2373, pruned_loss=0.03119, over 7161.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2493, pruned_loss=0.03352, over 1427929.13 frames.], batch size: 18, lr: 3.23e-04
2022-05-15 07:32:09,045 INFO [train.py:812] (4/8) Epoch 24, batch 3300, loss[loss=0.1986, simple_loss=0.2968, pruned_loss=0.0502, over 7274.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2502, pruned_loss=0.03365, over 1427677.27 frames.], batch size: 24, lr: 3.23e-04
2022-05-15 07:33:06,612 INFO [train.py:812] (4/8) Epoch 24, batch 3350, loss[loss=0.1634, simple_loss=0.2528, pruned_loss=0.03705, over 7300.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2503, pruned_loss=0.03374, over 1423974.63 frames.], batch size: 24, lr: 3.23e-04
2022-05-15 07:34:04,975 INFO [train.py:812] (4/8) Epoch 24, batch 3400, loss[loss=0.1299, simple_loss=0.2129, pruned_loss=0.02342, over 7358.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2505, pruned_loss=0.03387, over 1427699.34 frames.], batch size: 19, lr: 3.23e-04
2022-05-15 07:35:03,129 INFO [train.py:812] (4/8) Epoch 24, batch 3450, loss[loss=0.1729, simple_loss=0.2684, pruned_loss=0.03873, over 7316.00 frames.], tot_loss[loss=0.1595, simple_loss=0.251, pruned_loss=0.03397, over 1423351.31 frames.], batch size: 22, lr: 3.23e-04
2022-05-15 07:36:01,795 INFO [train.py:812] (4/8) Epoch 24, batch 3500, loss[loss=0.126, simple_loss=0.2124, pruned_loss=0.01979, over 6847.00 frames.], tot_loss[loss=0.1579, simple_loss=0.249, pruned_loss=0.03334, over 1421814.00 frames.], batch size: 15, lr: 3.23e-04
2022-05-15 07:37:00,364 INFO [train.py:812] (4/8) Epoch 24, batch 3550, loss[loss=0.1639, simple_loss=0.2558, pruned_loss=0.03598, over 7110.00 frames.], tot_loss[loss=0.158, simple_loss=0.2493, pruned_loss=0.03336, over 1423261.38 frames.], batch size: 21, lr: 3.23e-04
2022-05-15 07:38:00,111 INFO [train.py:812] (4/8) Epoch 24, batch 3600, loss[loss=0.1519, simple_loss=0.2349, pruned_loss=0.03443, over 7055.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2494, pruned_loss=0.03338, over 1422381.77 frames.], batch size: 18, lr: 3.22e-04
2022-05-15 07:38:57,461 INFO [train.py:812] (4/8) Epoch 24, batch 3650, loss[loss=0.145, simple_loss=0.2275, pruned_loss=0.03128, over 7354.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2501, pruned_loss=0.03382, over 1423953.36 frames.], batch size: 19, lr: 3.22e-04
2022-05-15 07:39:55,863 INFO [train.py:812] (4/8) Epoch 24, batch 3700, loss[loss=0.1466, simple_loss=0.247, pruned_loss=0.02311, over 6373.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2499, pruned_loss=0.03361, over 1420976.64 frames.], batch size: 38, lr: 3.22e-04
2022-05-15 07:40:52,810 INFO [train.py:812] (4/8) Epoch 24, batch 3750, loss[loss=0.1686, simple_loss=0.2547, pruned_loss=0.04128, over 7277.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2502, pruned_loss=0.0336, over 1422053.08 frames.], batch size: 18, lr: 3.22e-04
2022-05-15 07:41:51,838 INFO [train.py:812] (4/8) Epoch 24, batch 3800, loss[loss=0.1436, simple_loss=0.2356, pruned_loss=0.02579, over 7429.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2496, pruned_loss=0.03336, over 1423838.13 frames.], batch size: 20, lr: 3.22e-04
2022-05-15 07:42:51,164 INFO [train.py:812] (4/8) Epoch 24, batch 3850, loss[loss=0.1845, simple_loss=0.2698, pruned_loss=0.04963, over 5202.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2502, pruned_loss=0.03384, over 1419763.21 frames.], batch size: 52, lr: 3.22e-04
2022-05-15 07:43:50,681 INFO [train.py:812] (4/8) Epoch 24, batch 3900, loss[loss=0.1591, simple_loss=0.2553, pruned_loss=0.03144, over 6674.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2498, pruned_loss=0.03394, over 1416808.18 frames.], batch size: 31, lr: 3.22e-04
2022-05-15 07:44:49,671 INFO [train.py:812] (4/8) Epoch 24, batch 3950, loss[loss=0.1422, simple_loss=0.2254, pruned_loss=0.02952, over 7128.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2502, pruned_loss=0.03399, over 1416955.13 frames.], batch size: 17, lr: 3.22e-04
2022-05-15 07:45:48,713 INFO [train.py:812] (4/8) Epoch 24, batch 4000, loss[loss=0.187, simple_loss=0.2791, pruned_loss=0.04747, over 7202.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2509, pruned_loss=0.03421, over 1415211.34 frames.], batch size: 22, lr: 3.22e-04
2022-05-15 07:46:47,067 INFO [train.py:812] (4/8) Epoch 24, batch 4050, loss[loss=0.1876, simple_loss=0.2759, pruned_loss=0.04965, over 4837.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2505, pruned_loss=0.03382, over 1416061.60 frames.], batch size: 54, lr: 3.22e-04
2022-05-15 07:47:46,725 INFO [train.py:812] (4/8) Epoch 24, batch 4100, loss[loss=0.1328, simple_loss=0.2173, pruned_loss=0.02413, over 7279.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2503, pruned_loss=0.03394, over 1416673.89 frames.], batch size: 18, lr: 3.22e-04
2022-05-15 07:48:45,770 INFO [train.py:812] (4/8) Epoch 24, batch 4150, loss[loss=0.1408, simple_loss=0.2192, pruned_loss=0.03117, over 6997.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2502, pruned_loss=0.03424, over 1418886.92 frames.], batch size: 16, lr: 3.22e-04
2022-05-15 07:49:44,871 INFO [train.py:812] (4/8) Epoch 24, batch 4200, loss[loss=0.1563, simple_loss=0.2337, pruned_loss=0.03944, over 7266.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2508, pruned_loss=0.03427, over 1419680.68 frames.], batch size: 18, lr: 3.22e-04
2022-05-15 07:50:44,112 INFO [train.py:812] (4/8) Epoch 24, batch 4250, loss[loss=0.2128, simple_loss=0.3032, pruned_loss=0.06123, over 7382.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2504, pruned_loss=0.03418, over 1417729.94 frames.], batch size: 23, lr: 3.22e-04
2022-05-15 07:51:43,368 INFO [train.py:812] (4/8) Epoch 24, batch 4300, loss[loss=0.1432, simple_loss=0.221, pruned_loss=0.03265, over 6795.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2492, pruned_loss=0.03384, over 1416790.45 frames.], batch size: 15, lr: 3.21e-04
2022-05-15 07:52:41,816 INFO [train.py:812] (4/8) Epoch 24, batch 4350, loss[loss=0.1663, simple_loss=0.2595, pruned_loss=0.03657, over 6767.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2497, pruned_loss=0.03397, over 1414024.61 frames.], batch size: 31, lr: 3.21e-04
2022-05-15 07:53:40,607 INFO [train.py:812] (4/8) Epoch 24, batch 4400, loss[loss=0.1707, simple_loss=0.2695, pruned_loss=0.03597, over 6219.00 frames.], tot_loss[loss=0.16, simple_loss=0.2507, pruned_loss=0.03462, over 1408087.29 frames.], batch size: 37, lr: 3.21e-04
2022-05-15 07:54:38,518 INFO [train.py:812] (4/8) Epoch 24, batch 4450, loss[loss=0.1483, simple_loss=0.2542, pruned_loss=0.02122, over 6458.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2495, pruned_loss=0.0338, over 1410156.38 frames.], batch size: 38, lr: 3.21e-04
2022-05-15 07:55:37,559 INFO [train.py:812] (4/8) Epoch 24, batch 4500, loss[loss=0.166, simple_loss=0.2606, pruned_loss=0.03571, over 6351.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2504, pruned_loss=0.03412, over 1397825.98 frames.], batch size: 37, lr: 3.21e-04
2022-05-15 07:56:36,607 INFO [train.py:812] (4/8) Epoch 24, batch 4550, loss[loss=0.1634, simple_loss=0.2638, pruned_loss=0.03157, over 7294.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2507, pruned_loss=0.03454, over 1386589.21 frames.], batch size: 24, lr: 3.21e-04
2022-05-15 07:57:47,758 INFO [train.py:812] (4/8) Epoch 25, batch 0, loss[loss=0.1676, simple_loss=0.2644, pruned_loss=0.03543, over 7068.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2644, pruned_loss=0.03543, over 7068.00 frames.], batch size: 18, lr: 3.15e-04
2022-05-15 07:58:47,073 INFO [train.py:812] (4/8) Epoch 25, batch 50, loss[loss=0.1373, simple_loss=0.2254, pruned_loss=0.02464, over 7259.00 frames.], tot_loss[loss=0.1607, simple_loss=0.252, pruned_loss=0.0347, over 321874.34 frames.], batch size: 19, lr: 3.15e-04
2022-05-15 07:59:46,722 INFO [train.py:812] (4/8) Epoch 25, batch 100, loss[loss=0.1503, simple_loss=0.2406, pruned_loss=0.02997, over 7324.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2499, pruned_loss=0.03434, over 569961.46 frames.], batch size: 20, lr: 3.15e-04
2022-05-15 08:00:45,691 INFO [train.py:812] (4/8) Epoch 25, batch 150, loss[loss=0.1599, simple_loss=0.2528, pruned_loss=0.03345, over 7315.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2507, pruned_loss=0.03433, over 761240.26 frames.], batch size: 21, lr: 3.14e-04
2022-05-15 08:01:45,483 INFO [train.py:812] (4/8) Epoch 25, batch 200, loss[loss=0.1225, simple_loss=0.2089, pruned_loss=0.01805, over 7228.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2495, pruned_loss=0.03396, over 906700.74 frames.], batch size: 16, lr: 3.14e-04
2022-05-15 08:02:44,395 INFO [train.py:812] (4/8) Epoch 25, batch 250, loss[loss=0.1573, simple_loss=0.2593, pruned_loss=0.02764, over 7237.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2497, pruned_loss=0.03373, over 1018577.70 frames.], batch size: 20, lr: 3.14e-04
2022-05-15 08:03:43,893 INFO [train.py:812] (4/8) Epoch 25, batch 300, loss[loss=0.1644, simple_loss=0.2484, pruned_loss=0.04024, over 7149.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2497, pruned_loss=0.03359, over 1112860.31 frames.], batch size: 19, lr: 3.14e-04
2022-05-15 08:04:42,714 INFO [train.py:812] (4/8) Epoch 25, batch 350, loss[loss=0.1421, simple_loss=0.2399, pruned_loss=0.02218, over 7193.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2494, pruned_loss=0.03385, over 1182565.13 frames.], batch size: 23, lr: 3.14e-04
2022-05-15 08:05:50,921 INFO [train.py:812] (4/8) Epoch 25, batch 400, loss[loss=0.2111, simple_loss=0.3043, pruned_loss=0.05894, over 7233.00 frames.], tot_loss[loss=0.1576, simple_loss=0.249, pruned_loss=0.03315, over 1236671.98 frames.], batch size: 20, lr: 3.14e-04
2022-05-15 08:06:49,138 INFO [train.py:812] (4/8) Epoch 25, batch 450, loss[loss=0.1622, simple_loss=0.2528, pruned_loss=0.03582, over 7076.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2484, pruned_loss=0.03333, over 1277870.09 frames.], batch size: 28, lr: 3.14e-04
2022-05-15 08:07:48,545 INFO [train.py:812] (4/8) Epoch 25, batch 500, loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.02863, over 7164.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2484, pruned_loss=0.03334, over 1313362.17 frames.], batch size: 18, lr: 3.14e-04
2022-05-15 08:08:47,657 INFO [train.py:812] (4/8) Epoch 25, batch 550, loss[loss=0.1441, simple_loss=0.2313, pruned_loss=0.02841, over 7173.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03348, over 1340089.45 frames.], batch size: 18, lr: 3.14e-04
2022-05-15 08:09:45,624 INFO [train.py:812] (4/8) Epoch 25, batch 600, loss[loss=0.1713, simple_loss=0.2546, pruned_loss=0.04397, over 7189.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2493, pruned_loss=0.03383, over 1359395.27 frames.], batch size: 23, lr: 3.14e-04
2022-05-15 08:10:45,005 INFO [train.py:812] (4/8) Epoch 25, batch 650, loss[loss=0.1221, simple_loss=0.2073, pruned_loss=0.01849, over 7305.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2484, pruned_loss=0.03362, over 1371568.14 frames.], batch size: 17, lr: 3.14e-04
2022-05-15 08:11:43,789 INFO [train.py:812] (4/8) Epoch 25, batch 700, loss[loss=0.1262, simple_loss=0.2082, pruned_loss=0.02205, over 6839.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2489, pruned_loss=0.03396, over 1388087.83 frames.], batch size: 15, lr: 3.14e-04
2022-05-15 08:12:42,957 INFO [train.py:812] (4/8) Epoch 25, batch 750, loss[loss=0.1554, simple_loss=0.2373, pruned_loss=0.0368, over 7237.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2491, pruned_loss=0.03393, over 1399026.56 frames.], batch size: 20, lr: 3.14e-04
2022-05-15 08:13:42,688 INFO [train.py:812] (4/8) Epoch 25, batch 800, loss[loss=0.1753, simple_loss=0.2658, pruned_loss=0.04242, over 7415.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2497, pruned_loss=0.03443, over 1405689.75 frames.], batch size: 21, lr: 3.14e-04
2022-05-15 08:14:42,183 INFO [train.py:812] (4/8) Epoch 25, batch 850, loss[loss=0.1634, simple_loss=0.2605, pruned_loss=0.0332, over 7321.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2487, pruned_loss=0.03382, over 1407646.18 frames.], batch size: 21, lr: 3.13e-04
2022-05-15 08:15:39,806 INFO [train.py:812] (4/8) Epoch 25, batch 900, loss[loss=0.1888, simple_loss=0.2921, pruned_loss=0.0428, over 7359.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2491, pruned_loss=0.03389, over 1409883.65 frames.], batch size: 25, lr: 3.13e-04
2022-05-15 08:16:38,342 INFO [train.py:812] (4/8) Epoch 25, batch 950, loss[loss=0.1945, simple_loss=0.2776, pruned_loss=0.05565, over 5055.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2489, pruned_loss=0.03387, over 1405575.44 frames.], batch size: 52, lr: 3.13e-04
2022-05-15 08:17:38,345 INFO [train.py:812] (4/8) Epoch 25, batch 1000, loss[loss=0.1684, simple_loss=0.2516, pruned_loss=0.04256, over 7413.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2486, pruned_loss=0.0334, over 1411983.47 frames.], batch size: 21, lr: 3.13e-04
2022-05-15 08:18:37,737 INFO [train.py:812] (4/8) Epoch 25, batch 1050, loss[loss=0.1556, simple_loss=0.2484, pruned_loss=0.03137, over 7310.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2491, pruned_loss=0.03331, over 1418692.69 frames.], batch size: 20, lr: 3.13e-04
2022-05-15 08:19:35,300 INFO [train.py:812] (4/8) Epoch 25, batch 1100, loss[loss=0.1572, simple_loss=0.2608, pruned_loss=0.02674, over 7345.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2479, pruned_loss=0.03329, over 1421484.40 frames.], batch size: 22, lr: 3.13e-04
2022-05-15 08:20:32,125 INFO [train.py:812] (4/8) Epoch 25, batch 1150, loss[loss=0.166, simple_loss=0.2651, pruned_loss=0.0334, over 7206.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2483, pruned_loss=0.03322, over 1425083.24 frames.], batch size: 23, lr: 3.13e-04
2022-05-15 08:21:31,792 INFO [train.py:812] (4/8) Epoch 25, batch 1200, loss[loss=0.192, simple_loss=0.2794, pruned_loss=0.05236, over 7358.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2483, pruned_loss=0.03323, over 1424918.22 frames.], batch size: 23, lr: 3.13e-04
2022-05-15 08:22:29,881 INFO [train.py:812] (4/8) Epoch 25, batch 1250, loss[loss=0.1471, simple_loss=0.2453, pruned_loss=0.02452, over 7151.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2475, pruned_loss=0.03291, over 1423083.57 frames.], batch size: 20, lr: 3.13e-04
2022-05-15 08:23:28,196 INFO [train.py:812] (4/8) Epoch 25, batch 1300, loss[loss=0.1531, simple_loss=0.2328, pruned_loss=0.03676, over 6823.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2476, pruned_loss=0.03305, over 1421999.95 frames.], batch size: 15, lr: 3.13e-04
2022-05-15 08:24:27,540 INFO [train.py:812] (4/8) Epoch 25, batch 1350, loss[loss=0.1561, simple_loss=0.2553, pruned_loss=0.02843, over 6424.00 frames.], tot_loss[loss=0.157, simple_loss=0.2479, pruned_loss=0.033, over 1423012.51 frames.], batch size: 38, lr: 3.13e-04
2022-05-15 08:25:26,990 INFO [train.py:812] (4/8) Epoch 25, batch 1400, loss[loss=0.135, simple_loss=0.2257, pruned_loss=0.02211, over 7271.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2485, pruned_loss=0.03328, over 1427801.73 frames.], batch size: 17, lr: 3.13e-04
2022-05-15 08:26:25,996 INFO [train.py:812] (4/8) Epoch 25, batch 1450, loss[loss=0.1655, simple_loss=0.2638, pruned_loss=0.03356, over 7145.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2484, pruned_loss=0.03346, over 1423406.80 frames.], batch size: 20, lr: 3.13e-04
2022-05-15 08:27:24,398 INFO [train.py:812] (4/8) Epoch 25, batch 1500, loss[loss=0.1715, simple_loss=0.2698, pruned_loss=0.03664, over 6688.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2484, pruned_loss=0.03338, over 1422119.57 frames.], batch size: 31, lr: 3.13e-04
2022-05-15 08:28:23,103 INFO [train.py:812] (4/8) Epoch 25, batch 1550, loss[loss=0.1713, simple_loss=0.2511, pruned_loss=0.04575, over 7290.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2492, pruned_loss=0.03369, over 1422943.68 frames.], batch size: 18, lr: 3.12e-04
2022-05-15 08:29:22,781 INFO [train.py:812] (4/8) Epoch 25, batch 1600, loss[loss=0.168, simple_loss=0.2458, pruned_loss=0.04511, over 7219.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2491, pruned_loss=0.03374, over 1421580.29 frames.], batch size: 16, lr: 3.12e-04
2022-05-15 08:30:21,921 INFO [train.py:812] (4/8) Epoch 25, batch 1650, loss[loss=0.1498, simple_loss=0.2384, pruned_loss=0.03065, over 7227.00 frames.], tot_loss[loss=0.158, simple_loss=0.2485, pruned_loss=0.03376, over 1422650.07 frames.], batch size: 21, lr: 3.12e-04
2022-05-15 08:31:21,075 INFO [train.py:812] (4/8) Epoch 25, batch 1700, loss[loss=0.1891, simple_loss=0.2786, pruned_loss=0.0498, over 7379.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2483, pruned_loss=0.03373, over 1421314.11 frames.], batch size: 23, lr: 3.12e-04
2022-05-15 08:32:19,162 INFO [train.py:812] (4/8) Epoch 25, batch 1750, loss[loss=0.1347, simple_loss=0.2185, pruned_loss=0.02547, over 7148.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2481, pruned_loss=0.03337, over 1422970.39 frames.], batch size: 17, lr: 3.12e-04
2022-05-15 08:33:18,566 INFO [train.py:812] (4/8) Epoch 25, batch 1800, loss[loss=0.1385, simple_loss=0.2257, pruned_loss=0.02567, over 7013.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.0326, over 1422443.04 frames.], batch size: 16, lr: 3.12e-04
2022-05-15 08:34:17,250 INFO [train.py:812] (4/8) Epoch 25, batch 1850, loss[loss=0.1565, simple_loss=0.2394, pruned_loss=0.0368, over 7243.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2475, pruned_loss=0.03284, over 1419560.66 frames.], batch size: 16, lr: 3.12e-04
2022-05-15 08:35:20,958 INFO [train.py:812] (4/8) Epoch 25, batch 1900, loss[loss=0.1831, simple_loss=0.2721, pruned_loss=0.04709, over 7274.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03323, over 1421102.02 frames.], batch size: 25, lr: 3.12e-04
2022-05-15 08:36:19,549 INFO [train.py:812] (4/8) Epoch 25, batch 1950, loss[loss=0.1365, simple_loss=0.2327, pruned_loss=0.02016, over 7255.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2479, pruned_loss=0.03316, over 1423188.45 frames.], batch size: 19, lr: 3.12e-04
2022-05-15 08:37:18,257 INFO [train.py:812] (4/8) Epoch 25, batch 2000, loss[loss=0.152, simple_loss=0.2508, pruned_loss=0.02665, over 7161.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2479, pruned_loss=0.03293, over 1424391.04 frames.], batch size: 18, lr: 3.12e-04
2022-05-15 08:38:16,612 INFO [train.py:812] (4/8) Epoch 25, batch 2050, loss[loss=0.1982, simple_loss=0.2937, pruned_loss=0.05139, over 7332.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2477, pruned_loss=0.03309, over 1428588.12 frames.], batch size: 21, lr: 3.12e-04
2022-05-15 08:39:15,899 INFO [train.py:812] (4/8) Epoch 25, batch 2100, loss[loss=0.1486, simple_loss=0.2372, pruned_loss=0.02999, over 7255.00 frames.], tot_loss[loss=0.157, simple_loss=0.2479, pruned_loss=0.03304, over 1424881.26 frames.], batch size: 19, lr: 3.12e-04
2022-05-15 08:40:13,581 INFO [train.py:812] (4/8) Epoch 25, batch 2150, loss[loss=0.1504, simple_loss=0.2396, pruned_loss=0.03053, over 7421.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2483, pruned_loss=0.03299, over 1423383.87 frames.], batch size: 20, lr: 3.12e-04
2022-05-15 08:41:13,383 INFO [train.py:812] (4/8) Epoch 25, batch 2200, loss[loss=0.1375, simple_loss=0.2233, pruned_loss=0.02591, over 7231.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2474, pruned_loss=0.03245, over 1422231.28 frames.], batch size: 16, lr: 3.12e-04
2022-05-15 08:42:11,779 INFO [train.py:812] (4/8) Epoch 25, batch 2250, loss[loss=0.1492, simple_loss=0.2402, pruned_loss=0.02908, over 7070.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2474, pruned_loss=0.0329, over 1418238.03 frames.], batch size: 18, lr: 3.12e-04
2022-05-15 08:43:09,215 INFO [train.py:812] (4/8) Epoch 25, batch 2300, loss[loss=0.1302, simple_loss=0.2178, pruned_loss=0.0213, over 7195.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2469, pruned_loss=0.03266, over 1419557.54 frames.], batch size: 16, lr: 3.11e-04
2022-05-15 08:44:06,012 INFO [train.py:812] (4/8) Epoch 25, batch 2350, loss[loss=0.1494, simple_loss=0.2482, pruned_loss=0.02527, over 7308.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2467, pruned_loss=0.03249, over 1420253.41 frames.], batch size: 21, lr: 3.11e-04
2022-05-15 08:45:05,373 INFO [train.py:812] (4/8) Epoch 25, batch 2400, loss[loss=0.1627, simple_loss=0.2509, pruned_loss=0.03725, over 7353.00 frames.], tot_loss[loss=0.1572, simple_loss=0.248, pruned_loss=0.0332, over 1424732.38 frames.], batch size: 19, lr: 3.11e-04
2022-05-15 08:46:04,717 INFO [train.py:812] (4/8) Epoch 25, batch 2450, loss[loss=0.12, simple_loss=0.2112, pruned_loss=0.01434, over 7135.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2476, pruned_loss=0.03276, over 1423844.21 frames.], batch size: 17, lr: 3.11e-04
2022-05-15 08:47:04,379 INFO [train.py:812] (4/8) Epoch 25, batch 2500, loss[loss=0.1581, simple_loss=0.2565, pruned_loss=0.02989, over 7403.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.03252, over 1423652.04 frames.], batch size: 21, lr: 3.11e-04
2022-05-15 08:48:03,392 INFO [train.py:812] (4/8) Epoch 25, batch 2550, loss[loss=0.1658, simple_loss=0.2531, pruned_loss=0.03925, over 7414.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2485, pruned_loss=0.03303, over 1424403.58 frames.], batch size: 20, lr: 3.11e-04
2022-05-15 08:49:03,055 INFO [train.py:812] (4/8) Epoch 25, batch 2600, loss[loss=0.1573, simple_loss=0.2366, pruned_loss=0.03894, over 7137.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2483, pruned_loss=0.03315, over 1421928.88 frames.], batch size: 17, lr: 3.11e-04
2022-05-15 08:50:01,840 INFO [train.py:812] (4/8) Epoch 25, batch 2650, loss[loss=0.1532, simple_loss=0.2439, pruned_loss=0.03122, over 7208.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2493, pruned_loss=0.03347, over 1424023.53 frames.], batch size: 22, lr: 3.11e-04
2022-05-15 08:51:09,486 INFO [train.py:812] (4/8) Epoch 25, batch 2700, loss[loss=0.1515, simple_loss=0.2386, pruned_loss=0.03225, over 7060.00 frames.], tot_loss[loss=0.157, simple_loss=0.2484, pruned_loss=0.03284, over 1426405.56 frames.], batch size: 18, lr: 3.11e-04
2022-05-15 08:52:06,911 INFO [train.py:812] (4/8) Epoch 25, batch 2750, loss[loss=0.1556, simple_loss=0.2568, pruned_loss=0.02718, over 7137.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2478, pruned_loss=0.03282, over 1421406.97 frames.], batch size: 20, lr: 3.11e-04
2022-05-15 08:53:06,510 INFO [train.py:812] (4/8) Epoch 25, batch 2800, loss[loss=0.1397, simple_loss=0.2285, pruned_loss=0.02546, over 7257.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2473, pruned_loss=0.03255, over 1422160.41 frames.], batch size: 19, lr: 3.11e-04
2022-05-15 08:54:05,458 INFO [train.py:812] (4/8) Epoch 25, batch 2850, loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.03273, over 7433.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2476, pruned_loss=0.03257, over 1420313.64 frames.], batch size: 20, lr: 3.11e-04
2022-05-15 08:55:04,576 INFO [train.py:812] (4/8) Epoch 25, batch 2900, loss[loss=0.156, simple_loss=0.2541, pruned_loss=0.02895, over 7213.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2487, pruned_loss=0.03275, over 1420937.35 frames.], batch size: 23, lr: 3.11e-04
2022-05-15 08:56:02,084 INFO [train.py:812] (4/8) Epoch 25, batch 2950, loss[loss=0.1533, simple_loss=0.2571, pruned_loss=0.02472, over 7108.00 frames.], tot_loss[loss=0.157, simple_loss=0.2487, pruned_loss=0.03265, over 1425981.02 frames.], batch size: 21, lr: 3.11e-04
2022-05-15 08:57:29,015 INFO [train.py:812] (4/8) Epoch 25, batch 3000, loss[loss=0.1553, simple_loss=0.2476, pruned_loss=0.03154, over 6639.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03267, over 1428572.35 frames.], batch size: 31, lr: 3.10e-04
2022-05-15 08:57:29,016 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 08:57:46,643 INFO [train.py:841] (4/8) Epoch 25, validation: loss=0.1532, simple_loss=0.2507, pruned_loss=0.02787, over 698248.00 frames.
2022-05-15 08:58:45,934 INFO [train.py:812] (4/8) Epoch 25, batch 3050, loss[loss=0.154, simple_loss=0.2547, pruned_loss=0.02668, over 7102.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03226, over 1429137.27 frames.], batch size: 21, lr: 3.10e-04
2022-05-15 08:59:53,863 INFO [train.py:812] (4/8) Epoch 25, batch 3100, loss[loss=0.1399, simple_loss=0.2167, pruned_loss=0.03157, over 6773.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2469, pruned_loss=0.03228, over 1428856.33 frames.], batch size: 15, lr: 3.10e-04
2022-05-15 09:01:01,452 INFO [train.py:812] (4/8) Epoch 25, batch 3150, loss[loss=0.14, simple_loss=0.2291, pruned_loss=0.02548, over 7262.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.0326, over 1430260.97 frames.], batch size: 19, lr: 3.10e-04
2022-05-15 09:02:01,445 INFO [train.py:812] (4/8) Epoch 25, batch 3200, loss[loss=0.1602, simple_loss=0.2465, pruned_loss=0.03698, over 5288.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2471, pruned_loss=0.03255, over 1429585.25 frames.], batch size: 53, lr: 3.10e-04
2022-05-15 09:03:00,344 INFO [train.py:812] (4/8) Epoch 25, batch 3250, loss[loss=0.1721, simple_loss=0.2602, pruned_loss=0.04201, over 7232.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03292, over 1426652.14 frames.], batch size: 20, lr: 3.10e-04
2022-05-15 09:03:59,274 INFO [train.py:812] (4/8) Epoch 25, batch 3300, loss[loss=0.1443, simple_loss=0.2336, pruned_loss=0.02753, over 7164.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2483, pruned_loss=0.03336, over 1425933.37 frames.], batch size: 19, lr: 3.10e-04
2022-05-15 09:04:58,425 INFO [train.py:812] (4/8) Epoch 25, batch 3350, loss[loss=0.1574, simple_loss=0.2516, pruned_loss=0.03158, over 7270.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2484, pruned_loss=0.03326, over 1422035.61 frames.], batch size: 19, lr: 3.10e-04
2022-05-15 09:05:57,555 INFO [train.py:812] (4/8) Epoch 25, batch 3400, loss[loss=0.1566, simple_loss=0.2372, pruned_loss=0.03796, over 7291.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2477, pruned_loss=0.03294, over 1424115.55 frames.], batch size: 17, lr: 3.10e-04
2022-05-15 09:06:55,960 INFO [train.py:812] (4/8) Epoch 25, batch 3450, loss[loss=0.1474, simple_loss=0.2452, pruned_loss=0.02478, over 7216.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2486, pruned_loss=0.03341, over 1420636.38 frames.], batch size: 21, lr: 3.10e-04
2022-05-15 09:07:54,087 INFO [train.py:812] (4/8) Epoch 25, batch 3500, loss[loss=0.1448, simple_loss=0.2309, pruned_loss=0.02933, over 7139.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2488, pruned_loss=0.03343, over 1422554.74 frames.], batch size: 17, lr: 3.10e-04
2022-05-15 09:08:53,542 INFO [train.py:812] (4/8) Epoch 25, batch 3550, loss[loss=0.1559, simple_loss=0.2424, pruned_loss=0.03468, over 7340.00 frames.], tot_loss[loss=0.1579, simple_loss=0.249, pruned_loss=0.03338, over 1423418.02 frames.], batch size: 20, lr: 3.10e-04
2022-05-15 09:09:52,741 INFO [train.py:812] (4/8) Epoch 25, batch 3600, loss[loss=0.1592, simple_loss=0.2575, pruned_loss=0.0305, over 7203.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2489, pruned_loss=0.0331, over 1421868.06 frames.], batch size: 23, lr: 3.10e-04
2022-05-15 09:10:51,694 INFO [train.py:812] (4/8) Epoch 25, batch 3650, loss[loss=0.1774, simple_loss=0.2617, pruned_loss=0.04653, over 6685.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2483, pruned_loss=0.03308, over 1418929.90 frames.], batch size: 38, lr: 3.10e-04
2022-05-15 09:11:51,257 INFO [train.py:812] (4/8) Epoch 25, batch 3700, loss[loss=0.1644, simple_loss=0.2518, pruned_loss=0.03846, over 7428.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2471, pruned_loss=0.03239, over 1421756.74 frames.], batch size: 20, lr: 3.10e-04
2022-05-15 09:12:50,498 INFO [train.py:812] (4/8) Epoch 25, batch 3750, loss[loss=0.171, simple_loss=0.2611, pruned_loss=0.04042, over 7381.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2469, pruned_loss=0.03274, over 1424089.32 frames.], batch size: 23, lr: 3.09e-04
2022-05-15 09:13:50,121 INFO [train.py:812] (4/8) Epoch 25, batch 3800, loss[loss=0.174, simple_loss=0.2645, pruned_loss=0.04176, over 5070.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2469, pruned_loss=0.03287, over 1422679.95 frames.], batch size: 52, lr: 3.09e-04
2022-05-15 09:14:48,002 INFO [train.py:812] (4/8) Epoch 25, batch 3850, loss[loss=0.1483, simple_loss=0.2317, pruned_loss=0.03242, over 7270.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2477, pruned_loss=0.03309, over 1421831.69 frames.], batch size: 18, lr: 3.09e-04
2022-05-15 09:15:47,060 INFO [train.py:812] (4/8) Epoch 25, batch 3900, loss[loss=0.1619, simple_loss=0.2453, pruned_loss=0.03922, over 7260.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2485, pruned_loss=0.03327, over 1421392.71 frames.], batch size: 19, lr: 3.09e-04
2022-05-15 09:16:44,713 INFO [train.py:812] (4/8) Epoch 25, batch 3950, loss[loss=0.1312, simple_loss=0.2129, pruned_loss=0.02476, over 7419.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2483, pruned_loss=0.03297, over 1423421.79 frames.], batch size: 18, lr: 3.09e-04
2022-05-15 09:17:43,596 INFO [train.py:812] (4/8) Epoch 25, batch 4000, loss[loss=0.1687, simple_loss=0.2677, pruned_loss=0.03478, over 7316.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2486, pruned_loss=0.03301, over 1422727.37 frames.], batch size: 21, lr: 3.09e-04
2022-05-15 09:18:42,640 INFO [train.py:812] (4/8) Epoch 25, batch 4050, loss[loss=0.1414, simple_loss=0.2475, pruned_loss=0.01761, over 7424.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2479, pruned_loss=0.03271, over 1420977.08 frames.], batch size: 20, lr: 3.09e-04
2022-05-15 09:19:41,936 INFO [train.py:812] (4/8) Epoch 25, batch 4100, loss[loss=0.1638, simple_loss=0.2625, pruned_loss=0.03255, over 6353.00 frames.], tot_loss[loss=0.1567, simple_loss=0.248, pruned_loss=0.03274, over 1421921.94 frames.], batch size: 37, lr: 3.09e-04
2022-05-15 09:20:41,040 INFO [train.py:812] (4/8) Epoch 25, batch 4150, loss[loss=0.1728, simple_loss=0.2582, pruned_loss=0.04368, over 7224.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2478, pruned_loss=0.03264, over 1418162.91 frames.], batch size: 21, lr: 3.09e-04
2022-05-15 09:21:39,845 INFO [train.py:812] (4/8) Epoch 25, batch 4200, loss[loss=0.1702, simple_loss=0.2673, pruned_loss=0.03657, over 7208.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2502, pruned_loss=0.03351, over 1420363.09 frames.], batch size: 23, lr: 3.09e-04
2022-05-15 09:22:38,431 INFO [train.py:812] (4/8) Epoch 25, batch 4250, loss[loss=0.1448, simple_loss=0.2355, pruned_loss=0.02707, over 6179.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2494, pruned_loss=0.03339, over 1414616.24 frames.], batch size: 37, lr: 3.09e-04
2022-05-15 09:23:37,026 INFO [train.py:812] (4/8) Epoch 25, batch 4300, loss[loss=0.1484, simple_loss=0.2379, pruned_loss=0.02951, over 7152.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2486, pruned_loss=0.03349, over 1413903.06 frames.], batch size: 19, lr: 3.09e-04
2022-05-15 09:24:36,168 INFO [train.py:812] (4/8) Epoch 25, batch 4350, loss[loss=0.1743, simple_loss=0.2671, pruned_loss=0.04068, over 7302.00 frames.], tot_loss[loss=0.157, simple_loss=0.2476, pruned_loss=0.03315, over 1414369.52 frames.], batch size: 25, lr: 3.09e-04
2022-05-15 09:25:35,375 INFO [train.py:812] (4/8) Epoch 25, batch 4400, loss[loss=0.1579, simple_loss=0.2485, pruned_loss=0.03367, over 7291.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2484, pruned_loss=0.0332, over 1413120.05 frames.], batch size: 24, lr: 3.09e-04
2022-05-15 09:26:34,031 INFO [train.py:812] (4/8) Epoch 25, batch 4450, loss[loss=0.1668, simple_loss=0.26, pruned_loss=0.0368, over 7320.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2493, pruned_loss=0.03344, over 1404052.92 frames.], batch size: 25, lr: 3.09e-04
2022-05-15 09:27:33,029 INFO [train.py:812] (4/8) Epoch 25, batch 4500, loss[loss=0.1779, simple_loss=0.2629, pruned_loss=0.04651, over 5420.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2506, pruned_loss=0.03389, over 1389661.68 frames.], batch size: 52, lr: 3.08e-04
2022-05-15 09:28:30,319 INFO [train.py:812] (4/8) Epoch 25, batch 4550, loss[loss=0.2107, simple_loss=0.284, pruned_loss=0.06869, over 5137.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2523, pruned_loss=0.03458, over 1351727.19 frames.], batch size: 53, lr: 3.08e-04
2022-05-15 09:29:36,562 INFO [train.py:812] (4/8) Epoch 26, batch 0, loss[loss=0.1825, simple_loss=0.2825, pruned_loss=0.04125, over 7221.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2825, pruned_loss=0.04125, over 7221.00 frames.], batch size: 21, lr: 3.02e-04
2022-05-15 09:30:35,850 INFO [train.py:812] (4/8) Epoch 26, batch 50, loss[loss=0.1664, simple_loss=0.2603, pruned_loss=0.03622, over 7319.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2438, pruned_loss=0.03073, over 322033.49 frames.], batch size: 21, lr: 3.02e-04
2022-05-15 09:31:35,518 INFO [train.py:812] (4/8) Epoch 26, batch 100, loss[loss=0.1899, simple_loss=0.269, pruned_loss=0.05541, over 5451.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.03149, over 566782.34 frames.], batch size: 52, lr: 3.02e-04
2022-05-15 09:32:35,332 INFO [train.py:812] (4/8) Epoch 26, batch 150, loss[loss=0.1416, simple_loss=0.2282, pruned_loss=0.02747, over 7280.00 frames.], tot_loss[loss=0.157, simple_loss=0.2484, pruned_loss=0.03283, over 760588.48 frames.], batch size: 17, lr: 3.02e-04
2022-05-15 09:33:34,912 INFO [train.py:812] (4/8) Epoch 26, batch 200, loss[loss=0.1664, simple_loss=0.2683, pruned_loss=0.03224, over 7387.00 frames.], tot_loss[loss=0.1553, simple_loss=0.247, pruned_loss=0.03185, over 907331.77 frames.], batch size: 23, lr: 3.02e-04
2022-05-15 09:34:32,551 INFO [train.py:812] (4/8) Epoch 26, batch 250, loss[loss=0.1681, simple_loss=0.2584, pruned_loss=0.0389, over 7211.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2474, pruned_loss=0.03195, over 1019144.80 frames.], batch size: 22, lr: 3.02e-04
2022-05-15 09:35:31,871 INFO [train.py:812] (4/8) Epoch 26, batch 300, loss[loss=0.1532, simple_loss=0.2437, pruned_loss=0.03137, over 7324.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2485, pruned_loss=0.03203, over 1105157.46 frames.], batch size: 20, lr: 3.02e-04
2022-05-15 09:36:29,843 INFO [train.py:812] (4/8) Epoch 26, batch 350, loss[loss=0.1568, simple_loss=0.2444, pruned_loss=0.03456, over 7170.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2471, pruned_loss=0.03187, over 1174738.48 frames.], batch size: 18, lr: 3.02e-04
2022-05-15 09:37:29,641 INFO [train.py:812] (4/8) Epoch 26, batch 400, loss[loss=0.1343, simple_loss=0.2097, pruned_loss=0.02944, over 7408.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2473, pruned_loss=0.03189, over 1232076.70 frames.], batch size: 18, lr: 3.02e-04
2022-05-15 09:38:28,205 INFO [train.py:812] (4/8) Epoch 26, batch 450, loss[loss=0.1537, simple_loss=0.2504, pruned_loss=0.02847, over 7398.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2469, pruned_loss=0.03208, over 1273276.97 frames.], batch size: 21, lr: 3.02e-04
2022-05-15 09:39:25,644 INFO [train.py:812] (4/8) Epoch 26, batch 500, loss[loss=0.1647, simple_loss=0.2552, pruned_loss=0.03712, over 7388.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2479, pruned_loss=0.03242, over 1302012.98 frames.], batch size: 23, lr: 3.02e-04
2022-05-15 09:40:22,336 INFO [train.py:812] (4/8) Epoch 26, batch 550, loss[loss=0.1729, simple_loss=0.2741, pruned_loss=0.03583, over 7227.00 frames.], tot_loss[loss=0.1557, simple_loss=0.247, pruned_loss=0.03223, over 1327455.15 frames.], batch size: 20, lr: 3.02e-04
2022-05-15 09:41:20,611 INFO [train.py:812] (4/8) Epoch 26, batch 600, loss[loss=0.1579, simple_loss=0.2575, pruned_loss=0.02919, over 7076.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2471, pruned_loss=0.03241, over 1345851.64 frames.], batch size: 28, lr: 3.02e-04
2022-05-15 09:42:19,342 INFO [train.py:812] (4/8) Epoch 26, batch 650, loss[loss=0.1345, simple_loss=0.2241, pruned_loss=0.02246, over 7335.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2469, pruned_loss=0.03279, over 1360106.34 frames.], batch size: 20, lr: 3.02e-04
2022-05-15 09:43:17,903 INFO [train.py:812] (4/8) Epoch 26, batch 700, loss[loss=0.1485, simple_loss=0.2557, pruned_loss=0.02067, over 7147.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2459, pruned_loss=0.03229, over 1373854.50 frames.], batch size: 20, lr: 3.02e-04
2022-05-15 09:44:17,493 INFO [train.py:812] (4/8) Epoch 26, batch 750, loss[loss=0.1378, simple_loss=0.2266, pruned_loss=0.0245, over 7444.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2463, pruned_loss=0.03212, over 1389504.60 frames.], batch size: 20, lr: 3.01e-04
2022-05-15 09:45:17,289 INFO [train.py:812] (4/8) Epoch 26, batch 800, loss[loss=0.1889, simple_loss=0.2832, pruned_loss=0.04733, over 6712.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2474, pruned_loss=0.03244, over 1394941.21 frames.], batch size: 31, lr: 3.01e-04
2022-05-15 09:46:14,834 INFO [train.py:812] (4/8) Epoch 26, batch 850, loss[loss=0.1679, simple_loss=0.2634, pruned_loss=0.03616, over 7109.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2481, pruned_loss=0.03263, over 1406017.71 frames.], batch size: 21, lr: 3.01e-04
2022-05-15 09:47:13,168 INFO [train.py:812] (4/8) Epoch 26, batch 900, loss[loss=0.1301, simple_loss=0.2119, pruned_loss=0.0242, over 6817.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2479, pruned_loss=0.03295, over 1406538.16 frames.], batch size: 15, lr: 3.01e-04
2022-05-15 09:48:12,079 INFO [train.py:812] (4/8) Epoch 26, batch 950, loss[loss=0.1191, simple_loss=0.2042, pruned_loss=0.01705, over 7285.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2468, pruned_loss=0.03233, over 1413129.31 frames.], batch size: 17, lr: 3.01e-04
2022-05-15 09:49:11,024 INFO [train.py:812] (4/8) Epoch 26, batch 1000, loss[loss=0.1696, simple_loss=0.2586, pruned_loss=0.0403, over 7111.00 frames.], tot_loss[loss=0.156, simple_loss=0.247, pruned_loss=0.03252, over 1412305.39 frames.], batch size: 21, lr: 3.01e-04
2022-05-15 09:50:10,505 INFO [train.py:812] (4/8) Epoch 26, batch 1050, loss[loss=0.2078, simple_loss=0.2843, pruned_loss=0.0657, over 5187.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2476, pruned_loss=0.03262, over 1413866.44 frames.], batch size: 52, lr: 3.01e-04
2022-05-15 09:51:08,589 INFO [train.py:812] (4/8) Epoch 26, batch 1100, loss[loss=0.1565, simple_loss=0.2531, pruned_loss=0.02997, over 7125.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2483, pruned_loss=0.03263, over 1414312.96 frames.], batch size: 21, lr: 3.01e-04
2022-05-15 09:52:08,149 INFO [train.py:812] (4/8) Epoch 26, batch 1150, loss[loss=0.1692, simple_loss=0.2683, pruned_loss=0.03501, over 7373.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2481, pruned_loss=0.03235, over 1418168.98 frames.], batch size: 23, lr: 3.01e-04
2022-05-15 09:53:08,267 INFO [train.py:812] (4/8) Epoch 26, batch 1200, loss[loss=0.1323, simple_loss=0.214, pruned_loss=0.02532, over 7139.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2479, pruned_loss=0.03258, over 1422716.03 frames.], batch size: 17, lr: 3.01e-04
2022-05-15 09:54:07,368 INFO [train.py:812] (4/8) Epoch 26, batch 1250, loss[loss=0.1644, simple_loss=0.2533, pruned_loss=0.03776, over 7312.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2481, pruned_loss=0.03283, over 1424783.10 frames.], batch size: 21, lr: 3.01e-04
2022-05-15 09:55:11,136 INFO [train.py:812] (4/8) Epoch 26, batch 1300, loss[loss=0.1476, simple_loss=0.235, pruned_loss=0.03013, over 7422.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2476, pruned_loss=0.03238, over 1427994.63 frames.], batch size: 20, lr: 3.01e-04
2022-05-15 09:56:09,545 INFO [train.py:812] (4/8) Epoch 26, batch 1350, loss[loss=0.1679, simple_loss=0.261, pruned_loss=0.03743, over 7316.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2478, pruned_loss=0.03223, over 1427870.30 frames.], batch size: 21, lr: 3.01e-04
2022-05-15 09:57:07,830 INFO [train.py:812] (4/8) Epoch 26, batch 1400, loss[loss=0.1765, simple_loss=0.2701, pruned_loss=0.04147, over 7330.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2486, pruned_loss=0.03274, over 1428756.55 frames.], batch size: 22, lr: 3.01e-04
2022-05-15 09:58:05,647 INFO [train.py:812] (4/8) Epoch 26, batch 1450, loss[loss=0.1409, simple_loss=0.228, pruned_loss=0.02688, over 6981.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03254, over 1430086.42 frames.], batch size: 16, lr: 3.01e-04
2022-05-15 09:59:03,792 INFO [train.py:812] (4/8) Epoch 26, batch 1500, loss[loss=0.1461, simple_loss=0.2438, pruned_loss=0.02421, over 7214.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2482, pruned_loss=0.03273, over 1428156.38 frames.], batch size: 21, lr: 3.00e-04
2022-05-15 10:00:02,493 INFO [train.py:812] (4/8) Epoch 26, batch 1550, loss[loss=0.1371, simple_loss=0.2196, pruned_loss=0.02733, over 7118.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2481, pruned_loss=0.03264, over 1427185.14 frames.], batch size: 17, lr: 3.00e-04
2022-05-15 10:01:01,523 INFO [train.py:812] (4/8) Epoch 26, batch 1600, loss[loss=0.1705, simple_loss=0.2643, pruned_loss=0.03835, over 7133.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2489, pruned_loss=0.03295, over 1424080.83 frames.], batch size: 20, lr: 3.00e-04
2022-05-15 10:02:00,519 INFO [train.py:812] (4/8) Epoch 26, batch 1650, loss[loss=0.1615, simple_loss=0.2479, pruned_loss=0.03757, over 7050.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2468, pruned_loss=0.03214, over 1425475.48 frames.], batch size: 28, lr: 3.00e-04
2022-05-15 10:02:59,719 INFO [train.py:812] (4/8) Epoch 26, batch 1700, loss[loss=0.1649, simple_loss=0.2604, pruned_loss=0.03472, over 7329.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03206, over 1425639.82 frames.], batch size: 21, lr: 3.00e-04
2022-05-15 10:04:07,538 INFO [train.py:812] (4/8) Epoch 26, batch 1750, loss[loss=0.1191, simple_loss=0.2059, pruned_loss=0.01616, over 7144.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2477, pruned_loss=0.03227, over 1424760.09 frames.], batch size: 17, lr: 3.00e-04
2022-05-15 10:05:06,530 INFO [train.py:812] (4/8) Epoch 26, batch 1800, loss[loss=0.1743, simple_loss=0.2579, pruned_loss=0.04537, over 7149.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2479, pruned_loss=0.03267, over 1421667.40 frames.], batch size: 20, lr: 3.00e-04
2022-05-15 10:06:05,260 INFO [train.py:812] (4/8) Epoch 26, batch 1850, loss[loss=0.1573, simple_loss=0.2566, pruned_loss=0.02902, over 7427.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2484, pruned_loss=0.033, over 1422572.06 frames.], batch size: 20, lr: 3.00e-04
2022-05-15 10:07:04,822 INFO [train.py:812] (4/8) Epoch 26, batch 1900, loss[loss=0.1619, simple_loss=0.2407, pruned_loss=0.04148, over 7135.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2484, pruned_loss=0.03266, over 1423538.44 frames.], batch size: 17, lr: 3.00e-04
2022-05-15 10:08:02,586 INFO [train.py:812] (4/8) Epoch 26, batch 1950, loss[loss=0.1763, simple_loss=0.265, pruned_loss=0.04377, over 4972.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03257, over 1421382.56 frames.], batch size: 52, lr: 3.00e-04
2022-05-15 10:09:00,915 INFO [train.py:812] (4/8) Epoch 26, batch 2000, loss[loss=0.1487, simple_loss=0.2386, pruned_loss=0.02933, over 7157.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2486, pruned_loss=0.03284, over 1417543.46 frames.], batch size: 19, lr: 3.00e-04
2022-05-15 10:10:00,121 INFO [train.py:812] (4/8) Epoch 26, batch 2050, loss[loss=0.1976, simple_loss=0.2879, pruned_loss=0.05359, over 7318.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2479, pruned_loss=0.03275, over 1419140.71 frames.], batch size: 20, lr: 3.00e-04
2022-05-15 10:10:59,279 INFO [train.py:812] (4/8) Epoch 26, batch 2100, loss[loss=0.1732, simple_loss=0.2558, pruned_loss=0.04529, over 7214.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2487, pruned_loss=0.03288, over 1418371.00 frames.], batch size: 22, lr: 3.00e-04
2022-05-15 10:11:58,146 INFO [train.py:812] (4/8) Epoch 26, batch 2150, loss[loss=0.1483, simple_loss=0.2294, pruned_loss=0.03359, over 7163.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2495, pruned_loss=0.03319, over 1420600.09 frames.], batch size: 18, lr: 3.00e-04
2022-05-15 10:12:57,683 INFO [train.py:812] (4/8) Epoch 26, batch 2200, loss[loss=0.1619, simple_loss=0.2585, pruned_loss=0.03262, over 7077.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2493, pruned_loss=0.03272, over 1422691.06 frames.], batch size: 28, lr: 3.00e-04
2022-05-15 10:13:56,441 INFO [train.py:812] (4/8) Epoch 26, batch 2250, loss[loss=0.156, simple_loss=0.2453, pruned_loss=0.0334, over 7377.00 frames.], tot_loss[loss=0.1562, simple_loss=0.248, pruned_loss=0.03227, over 1424595.72 frames.], batch size: 23, lr: 3.00e-04
2022-05-15 10:14:54,804 INFO [train.py:812] (4/8) Epoch 26, batch 2300, loss[loss=0.1377, simple_loss=0.2272, pruned_loss=0.02411, over 7065.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2487, pruned_loss=0.03242, over 1424713.67 frames.], batch size: 18, lr: 2.99e-04
2022-05-15 10:15:54,090 INFO [train.py:812] (4/8) Epoch 26, batch 2350, loss[loss=0.1367, simple_loss=0.2313, pruned_loss=0.02104, over 7252.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2474, pruned_loss=0.03243, over 1425148.72 frames.], batch size: 19, lr: 2.99e-04
2022-05-15 10:16:53,714 INFO [train.py:812] (4/8) Epoch 26, batch 2400, loss[loss=0.2063, simple_loss=0.2972, pruned_loss=0.05771, over 7387.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2472, pruned_loss=0.0326, over 1422665.92 frames.], batch size: 23, lr: 2.99e-04
2022-05-15 10:17:52,714 INFO [train.py:812] (4/8) Epoch 26, batch 2450, loss[loss=0.1554, simple_loss=0.2462, pruned_loss=0.03229, over 6790.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2478, pruned_loss=0.03288, over 1420620.22 frames.], batch size: 31, lr: 2.99e-04
2022-05-15 10:18:50,829 INFO [train.py:812] (4/8) Epoch 26, batch 2500, loss[loss=0.1668, simple_loss=0.2699, pruned_loss=0.0318, over 7362.00 frames.], tot_loss[loss=0.1562, simple_loss=0.247, pruned_loss=0.03271, over 1421810.90 frames.], batch size: 19, lr: 2.99e-04
2022-05-15 10:19:48,014 INFO [train.py:812] (4/8) Epoch 26, batch 2550, loss[loss=0.1443, simple_loss=0.2284, pruned_loss=0.03005, over 7413.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03288, over 1424769.80 frames.], batch size: 18, lr: 2.99e-04
2022-05-15 10:20:46,863 INFO [train.py:812] (4/8) Epoch 26, batch 2600, loss[loss=0.1505, simple_loss=0.2492, pruned_loss=0.02587, over 7159.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2476, pruned_loss=0.03284, over 1422876.99 frames.], batch size: 19, lr: 2.99e-04
2022-05-15 10:21:44,645 INFO [train.py:812] (4/8) Epoch 26, batch 2650, loss[loss=0.1785, simple_loss=0.2704, pruned_loss=0.0433, over 7107.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2481, pruned_loss=0.03309, over 1419284.59 frames.], batch size: 28, lr: 2.99e-04
2022-05-15 10:22:43,731 INFO [train.py:812] (4/8) Epoch 26, batch 2700, loss[loss=0.1447, simple_loss=0.2329, pruned_loss=0.02823, over 7261.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03269, over 1419946.07 frames.], batch size: 19, lr: 2.99e-04
2022-05-15 10:23:42,368 INFO [train.py:812] (4/8) Epoch 26, batch 2750, loss[loss=0.1599, simple_loss=0.2664, pruned_loss=0.0267, over 7277.00 frames.], tot_loss[loss=0.157, simple_loss=0.2481, pruned_loss=0.03296, over 1412986.25 frames.], batch size: 25, lr: 2.99e-04
2022-05-15 10:24:40,497 INFO [train.py:812] (4/8) Epoch 26, batch 2800, loss[loss=0.1537, simple_loss=0.2486, pruned_loss=0.02942, over 7265.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2473, pruned_loss=0.03286, over 1415600.40 frames.], batch size: 18, lr: 2.99e-04
2022-05-15 10:25:38,072 INFO [train.py:812] (4/8) Epoch 26, batch 2850, loss[loss=0.15, simple_loss=0.2468, pruned_loss=0.02662, over 7416.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2469, pruned_loss=0.0328, over 1410600.29 frames.], batch size: 21, lr: 2.99e-04
2022-05-15 10:26:37,769 INFO [train.py:812] (4/8) Epoch 26, batch 2900, loss[loss=0.1559, simple_loss=0.2579, pruned_loss=0.027, over 7145.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2465, pruned_loss=0.03236, over 1416953.03 frames.], batch size: 20, lr: 2.99e-04
2022-05-15 10:27:35,283 INFO [train.py:812] (4/8) Epoch 26, batch 2950, loss[loss=0.1435, simple_loss=0.2457, pruned_loss=0.02061, over 7328.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2477, pruned_loss=0.03269, over 1417628.81 frames.], batch size: 20, lr: 2.99e-04
2022-05-15 10:28:33,139 INFO [train.py:812] (4/8) Epoch 26, batch 3000, loss[loss=0.1516, simple_loss=0.2354, pruned_loss=0.03391, over 6474.00 frames.], tot_loss[loss=0.1565, simple_loss=0.248, pruned_loss=0.03251, over 1421992.01 frames.], batch size: 38, lr: 2.99e-04
2022-05-15 10:28:33,140 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 10:28:40,784 INFO [train.py:841] (4/8) Epoch 26, validation: loss=0.1534, simple_loss=0.2507, pruned_loss=0.02805, over 698248.00 frames.
2022-05-15 10:29:38,765 INFO [train.py:812] (4/8) Epoch 26, batch 3050, loss[loss=0.1434, simple_loss=0.2393, pruned_loss=0.02371, over 7343.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2489, pruned_loss=0.03259, over 1421804.94 frames.], batch size: 22, lr: 2.99e-04
2022-05-15 10:30:38,722 INFO [train.py:812] (4/8) Epoch 26, batch 3100, loss[loss=0.166, simple_loss=0.2526, pruned_loss=0.0397, over 7251.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2488, pruned_loss=0.03277, over 1418672.03 frames.], batch size: 19, lr: 2.98e-04
2022-05-15 10:31:36,299 INFO [train.py:812] (4/8) Epoch 26, batch 3150, loss[loss=0.15, simple_loss=0.2303, pruned_loss=0.03481, over 7131.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2485, pruned_loss=0.03318, over 1417896.39 frames.], batch size: 17, lr: 2.98e-04
2022-05-15 10:32:35,707 INFO [train.py:812] (4/8) Epoch 26, batch 3200, loss[loss=0.1403, simple_loss=0.2346, pruned_loss=0.02293, over 7150.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2486, pruned_loss=0.03319, over 1421173.57 frames.], batch size: 19, lr: 2.98e-04
2022-05-15 10:33:35,057 INFO [train.py:812] (4/8) Epoch 26, batch 3250, loss[loss=0.1496, simple_loss=0.2362, pruned_loss=0.03145, over 7276.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2474, pruned_loss=0.03318, over 1424395.31 frames.], batch size: 18, lr: 2.98e-04
2022-05-15 10:34:33,017 INFO [train.py:812] (4/8) Epoch 26, batch 3300, loss[loss=0.1672, simple_loss=0.2691, pruned_loss=0.03265, over 7157.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03284, over 1417668.94 frames.], batch size: 26, lr: 2.98e-04
2022-05-15 10:35:31,817 INFO [train.py:812] (4/8) Epoch 26, batch 3350, loss[loss=0.1647, simple_loss=0.262, pruned_loss=0.03374, over 7309.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2485, pruned_loss=0.03301, over 1413971.96 frames.], batch size: 21, lr: 2.98e-04
2022-05-15 10:36:31,840 INFO [train.py:812] (4/8) Epoch 26, batch 3400, loss[loss=0.1825, simple_loss=0.2643, pruned_loss=0.05035, over 6407.00 frames.], tot_loss[loss=0.156, simple_loss=0.247, pruned_loss=0.03254, over 1418817.48 frames.], batch size: 38, lr: 2.98e-04
2022-05-15 10:37:30,433 INFO [train.py:812] (4/8) Epoch 26, batch 3450, loss[loss=0.1477, simple_loss=0.2367, pruned_loss=0.02936, over 7162.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2467, pruned_loss=0.03232, over 1418674.11 frames.], batch size: 18, lr: 2.98e-04
2022-05-15 10:38:29,755 INFO [train.py:812] (4/8) Epoch 26, batch 3500, loss[loss=0.1691, simple_loss=0.2597, pruned_loss=0.03927, over 7378.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.03264, over 1417308.02 frames.], batch size: 23, lr: 2.98e-04
2022-05-15 10:39:28,314 INFO [train.py:812] (4/8) Epoch 26, batch 3550, loss[loss=0.1664, simple_loss=0.2575, pruned_loss=0.03763, over 7405.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2468, pruned_loss=0.03222, over 1420223.56 frames.], batch size: 21, lr: 2.98e-04
2022-05-15 10:40:26,268 INFO [train.py:812] (4/8) Epoch 26, batch 3600, loss[loss=0.1707, simple_loss=0.2661, pruned_loss=0.03763, over 7199.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2474, pruned_loss=0.03242, over 1425375.12 frames.], batch size: 23, lr: 2.98e-04
2022-05-15 10:41:25,807 INFO [train.py:812] (4/8) Epoch 26, batch 3650, loss[loss=0.1387, simple_loss=0.2291, pruned_loss=0.02414, over 7263.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2479, pruned_loss=0.03254, over 1427155.21 frames.], batch size: 19, lr: 2.98e-04
2022-05-15 10:42:23,890 INFO [train.py:812] (4/8) Epoch 26, batch 3700, loss[loss=0.1525, simple_loss=0.2403, pruned_loss=0.0324, over 7061.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03265, over 1424644.90 frames.], batch size: 18, lr: 2.98e-04
2022-05-15 10:43:22,970 INFO [train.py:812] (4/8) Epoch 26, batch 3750, loss[loss=0.1571, simple_loss=0.2456, pruned_loss=0.03432, over 7158.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2476, pruned_loss=0.0324, over 1423072.53 frames.], batch size: 19, lr: 2.98e-04
2022-05-15 10:44:21,253 INFO [train.py:812] (4/8) Epoch 26, batch 3800, loss[loss=0.1501, simple_loss=0.2457, pruned_loss=0.02727, over 6460.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2472, pruned_loss=0.03232, over 1420388.83 frames.], batch size: 38, lr: 2.98e-04
2022-05-15 10:45:20,415 INFO [train.py:812] (4/8) Epoch 26, batch 3850, loss[loss=0.1474, simple_loss=0.2452, pruned_loss=0.02477, over 7141.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03229, over 1418364.83 frames.], batch size: 20, lr: 2.97e-04
2022-05-15 10:46:19,972 INFO [train.py:812] (4/8) Epoch 26, batch 3900, loss[loss=0.1419, simple_loss=0.2337, pruned_loss=0.02502, over 7407.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2482, pruned_loss=0.03258, over 1420600.05 frames.], batch size: 18, lr: 2.97e-04
2022-05-15 10:47:17,425 INFO [train.py:812] (4/8) Epoch 26, batch 3950, loss[loss=0.1508, simple_loss=0.2483, pruned_loss=0.0267, over 7237.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2474, pruned_loss=0.03254, over 1425493.11 frames.], batch size: 20, lr: 2.97e-04
2022-05-15 10:48:16,826 INFO [train.py:812] (4/8) Epoch 26, batch 4000, loss[loss=0.141, simple_loss=0.2322, pruned_loss=0.02491, over 7430.00 frames.], tot_loss[loss=0.1562, simple_loss=0.247, pruned_loss=0.03268, over 1418664.54 frames.], batch size: 20, lr: 2.97e-04
2022-05-15 10:49:15,500 INFO [train.py:812] (4/8) Epoch 26, batch 4050, loss[loss=0.1628, simple_loss=0.2601, pruned_loss=0.03273, over 7400.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2474, pruned_loss=0.03267, over 1420163.75 frames.], batch size: 21, lr: 2.97e-04
2022-05-15 10:50:14,951 INFO [train.py:812] (4/8) Epoch 26, batch 4100, loss[loss=0.1439, simple_loss=0.2378, pruned_loss=0.02502, over 7417.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03283, over 1417679.07 frames.], batch size: 21, lr: 2.97e-04
2022-05-15 10:51:14,795 INFO [train.py:812] (4/8) Epoch 26, batch 4150, loss[loss=0.149, simple_loss=0.2434, pruned_loss=0.02731, over 7255.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2473, pruned_loss=0.03249, over 1422760.87 frames.], batch size: 19, lr: 2.97e-04
2022-05-15 10:52:13,194 INFO [train.py:812] (4/8) Epoch 26, batch 4200, loss[loss=0.1607, simple_loss=0.2593, pruned_loss=0.03104, over 7041.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2476, pruned_loss=0.03257, over 1418869.14 frames.], batch size: 28, lr: 2.97e-04
2022-05-15 10:53:19,319 INFO [train.py:812] (4/8) Epoch 26, batch 4250, loss[loss=0.1393, simple_loss=0.2261, pruned_loss=0.02622, over 7157.00 frames.], tot_loss[loss=0.1559, simple_loss=0.247, pruned_loss=0.03239, over 1418393.75 frames.], batch size: 18, lr: 2.97e-04
2022-05-15 10:54:17,961 INFO [train.py:812] (4/8) Epoch 26, batch 4300, loss[loss=0.2294, simple_loss=0.3155, pruned_loss=0.07167, over 7163.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2477, pruned_loss=0.0328, over 1422355.69 frames.], batch size: 26, lr: 2.97e-04
2022-05-15 10:55:15,847 INFO [train.py:812] (4/8) Epoch 26, batch 4350, loss[loss=0.1452, simple_loss=0.2337, pruned_loss=0.02842, over 7245.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2481, pruned_loss=0.03299, over 1415550.84 frames.], batch size: 20, lr: 2.97e-04
2022-05-15 10:56:15,067 INFO [train.py:812] (4/8) Epoch 26, batch 4400, loss[loss=0.138, simple_loss=0.2178, pruned_loss=0.02913, over 7061.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2488, pruned_loss=0.03301, over 1416050.32 frames.], batch size: 18, lr: 2.97e-04
2022-05-15 10:57:23,161 INFO [train.py:812] (4/8) Epoch 26, batch 4450, loss[loss=0.1904, simple_loss=0.2676, pruned_loss=0.0566, over 7314.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2488, pruned_loss=0.03301, over 1414868.07 frames.], batch size: 24, lr: 2.97e-04
2022-05-15 10:58:40,622 INFO [train.py:812] (4/8) Epoch 26, batch 4500, loss[loss=0.1489, simple_loss=0.2361, pruned_loss=0.03087, over 7321.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2486, pruned_loss=0.03328, over 1398624.87 frames.], batch size: 20, lr: 2.97e-04
2022-05-15 10:59:48,369 INFO [train.py:812] (4/8) Epoch 26, batch 4550, loss[loss=0.1714, simple_loss=0.2593, pruned_loss=0.04176, over 5126.00 frames.], tot_loss[loss=0.1581, simple_loss=0.249, pruned_loss=0.03355, over 1388352.60 frames.], batch size: 53, lr: 2.97e-04
2022-05-15 11:01:05,805 INFO [train.py:812] (4/8) Epoch 27, batch 0, loss[loss=0.1545, simple_loss=0.2445, pruned_loss=0.03228, over 7169.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2445, pruned_loss=0.03228, over 7169.00 frames.], batch size: 18, lr: 2.91e-04
2022-05-15 11:02:14,196 INFO [train.py:812] (4/8) Epoch 27, batch 50, loss[loss=0.1351, simple_loss=0.2113, pruned_loss=0.02945, over 7279.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2456, pruned_loss=0.03292, over 319095.51 frames.], batch size: 17, lr: 2.91e-04
2022-05-15 11:03:12,407 INFO [train.py:812] (4/8) Epoch 27, batch 100, loss[loss=0.1393, simple_loss=0.2166, pruned_loss=0.03104, over 7280.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2455, pruned_loss=0.03196, over 562074.72 frames.], batch size: 17, lr: 2.91e-04
2022-05-15 11:04:11,554 INFO [train.py:812] (4/8) Epoch 27, batch 150, loss[loss=0.1344, simple_loss=0.2364, pruned_loss=0.01623, over 6317.00 frames.], tot_loss[loss=0.156, simple_loss=0.2468, pruned_loss=0.03259, over 750393.47 frames.], batch size: 37, lr: 2.91e-04
2022-05-15 11:05:08,309 INFO [train.py:812] (4/8) Epoch 27, batch 200, loss[loss=0.1558, simple_loss=0.247, pruned_loss=0.03228, over 7137.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2469, pruned_loss=0.03278, over 893659.22 frames.], batch size: 26, lr: 2.91e-04
2022-05-15 11:06:06,626 INFO [train.py:812] (4/8) Epoch 27, batch 250, loss[loss=0.1396, simple_loss=0.2437, pruned_loss=0.01779, over 6623.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2481, pruned_loss=0.03335, over 1005362.79 frames.], batch size: 38, lr: 2.91e-04
2022-05-15 11:07:05,729 INFO [train.py:812] (4/8) Epoch 27, batch 300, loss[loss=0.1536, simple_loss=0.253, pruned_loss=0.02715, over 6441.00 frames.], tot_loss[loss=0.157, simple_loss=0.2484, pruned_loss=0.0328, over 1099965.80 frames.], batch size: 37, lr: 2.91e-04
2022-05-15 11:08:04,239 INFO [train.py:812] (4/8) Epoch 27, batch 350, loss[loss=0.1763, simple_loss=0.2664, pruned_loss=0.0431, over 6654.00 frames.], tot_loss[loss=0.1562, simple_loss=0.247, pruned_loss=0.0327, over 1167534.73 frames.], batch size: 31, lr: 2.91e-04
2022-05-15 11:09:03,270 INFO [train.py:812] (4/8) Epoch 27, batch 400, loss[loss=0.1518, simple_loss=0.2484, pruned_loss=0.02762, over 7141.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2478, pruned_loss=0.03281, over 1227671.16 frames.], batch size: 20, lr: 2.91e-04
2022-05-15 11:10:01,853 INFO [train.py:812] (4/8) Epoch 27, batch 450, loss[loss=0.1633, simple_loss=0.2469, pruned_loss=0.03987, over 7232.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2479, pruned_loss=0.03242, over 1275298.22 frames.], batch size: 20, lr: 2.91e-04
2022-05-15 11:10:59,675 INFO [train.py:812] (4/8) Epoch 27, batch 500, loss[loss=0.1833, simple_loss=0.2769, pruned_loss=0.04479, over 4892.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03226, over 1307089.22 frames.], batch size: 52, lr: 2.91e-04
2022-05-15 11:11:59,504 INFO [train.py:812] (4/8) Epoch 27, batch 550, loss[loss=0.1463, simple_loss=0.245, pruned_loss=0.02378, over 7199.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2481, pruned_loss=0.03253, over 1332300.81 frames.], batch size: 22, lr: 2.90e-04
2022-05-15 11:12:58,976 INFO [train.py:812] (4/8) Epoch 27, batch 600, loss[loss=0.1307, simple_loss=0.2188, pruned_loss=0.02129, over 7250.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2481, pruned_loss=0.03247, over 1355362.59 frames.], batch size: 19, lr: 2.90e-04
2022-05-15 11:13:58,665 INFO [train.py:812] (4/8) Epoch 27, batch 650, loss[loss=0.126, simple_loss=0.2088, pruned_loss=0.02159, over 7278.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2479, pruned_loss=0.03236, over 1372433.52 frames.], batch size: 18, lr: 2.90e-04
2022-05-15 11:14:57,634 INFO [train.py:812] (4/8) Epoch 27, batch 700, loss[loss=0.1632, simple_loss=0.2669, pruned_loss=0.02972, over 7117.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2477, pruned_loss=0.03229, over 1381353.62 frames.], batch size: 21, lr: 2.90e-04
2022-05-15 11:16:01,093 INFO [train.py:812] (4/8) Epoch 27, batch 750, loss[loss=0.1579, simple_loss=0.251, pruned_loss=0.03239, over 7144.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2475, pruned_loss=0.03196, over 1390285.91 frames.], batch size: 20, lr: 2.90e-04
2022-05-15 11:17:00,047 INFO [train.py:812] (4/8) Epoch 27, batch 800, loss[loss=0.136, simple_loss=0.2206, pruned_loss=0.02568, over 7232.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03224, over 1396086.73 frames.], batch size: 20, lr: 2.90e-04
2022-05-15 11:17:59,355 INFO [train.py:812] (4/8) Epoch 27, batch 850, loss[loss=0.1888, simple_loss=0.2718, pruned_loss=0.05287, over 5233.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2486, pruned_loss=0.0323, over 1398715.23 frames.], batch size: 52, lr: 2.90e-04
2022-05-15 11:18:57,705 INFO [train.py:812] (4/8) Epoch 27, batch 900, loss[loss=0.1409, simple_loss=0.2241, pruned_loss=0.02882, over 7405.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2475, pruned_loss=0.03221, over 1408238.06 frames.], batch size: 18, lr: 2.90e-04
2022-05-15 11:19:56,352 INFO [train.py:812] (4/8) Epoch 27, batch 950, loss[loss=0.1459, simple_loss=0.2338, pruned_loss=0.029, over 6835.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2478, pruned_loss=0.03239, over 1409274.05 frames.], batch size: 15, lr: 2.90e-04
2022-05-15 11:20:55,291 INFO [train.py:812] (4/8) Epoch 27, batch 1000, loss[loss=0.1598, simple_loss=0.2576, pruned_loss=0.03095, over 7297.00 frames.], tot_loss[loss=0.157, simple_loss=0.2486, pruned_loss=0.03271, over 1412789.86 frames.], batch size: 24, lr: 2.90e-04
2022-05-15 11:21:53,182 INFO [train.py:812] (4/8) Epoch 27, batch 1050, loss[loss=0.1641, simple_loss=0.2592, pruned_loss=0.03443, over 7210.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2482, pruned_loss=0.03238, over 1418044.95 frames.], batch size: 23, lr: 2.90e-04
2022-05-15 11:22:52,381 INFO [train.py:812] (4/8) Epoch 27, batch 1100, loss[loss=0.1642, simple_loss=0.243, pruned_loss=0.04268, over 7197.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03223, over 1421690.14 frames.], batch size: 22, lr: 2.90e-04
2022-05-15 11:23:52,080 INFO [train.py:812] (4/8) Epoch 27, batch 1150, loss[loss=0.1255, simple_loss=0.2127, pruned_loss=0.01921, over 7159.00 frames.], tot_loss[loss=0.1556, simple_loss=0.247, pruned_loss=0.03208, over 1423590.98 frames.], batch size: 19, lr: 2.90e-04
2022-05-15 11:24:50,278 INFO [train.py:812] (4/8) Epoch 27, batch 1200, loss[loss=0.169, simple_loss=0.2624, pruned_loss=0.03773, over 7277.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2474, pruned_loss=0.03251, over 1427318.40 frames.], batch size: 24, lr: 2.90e-04
2022-05-15 11:25:49,800 INFO [train.py:812] (4/8) Epoch 27, batch 1250, loss[loss=0.1663, simple_loss=0.2557, pruned_loss=0.0385, over 6556.00 frames.], tot_loss[loss=0.155, simple_loss=0.2462, pruned_loss=0.0319, over 1427887.29 frames.], batch size: 38, lr: 2.90e-04
2022-05-15 11:26:48,361 INFO [train.py:812] (4/8) Epoch 27, batch 1300, loss[loss=0.1364, simple_loss=0.2251, pruned_loss=0.02384, over 7272.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2464, pruned_loss=0.03199, over 1424383.87 frames.], batch size: 18, lr: 2.90e-04
2022-05-15 11:27:46,497 INFO [train.py:812] (4/8) Epoch 27, batch 1350, loss[loss=0.1293, simple_loss=0.2141, pruned_loss=0.02227, over 7416.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2452, pruned_loss=0.03173, over 1427408.95 frames.], batch size: 18, lr: 2.89e-04
2022-05-15 11:28:44,275 INFO [train.py:812] (4/8) Epoch 27, batch 1400, loss[loss=0.16, simple_loss=0.2484, pruned_loss=0.03578, over 7189.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2449, pruned_loss=0.03177, over 1419380.58 frames.], batch size: 23, lr: 2.89e-04
2022-05-15 11:29:43,172 INFO [train.py:812] (4/8) Epoch 27, batch 1450, loss[loss=0.1358, simple_loss=0.225, pruned_loss=0.02328, over 7276.00 frames.], tot_loss[loss=0.1554, simple_loss=0.246, pruned_loss=0.0324, over 1420931.90 frames.], batch size: 18, lr: 2.89e-04
2022-05-15 11:30:41,591 INFO [train.py:812] (4/8) Epoch 27, batch 1500, loss[loss=0.1837, simple_loss=0.2582, pruned_loss=0.05463, over 5008.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2463, pruned_loss=0.03246, over 1417046.25 frames.], batch size: 52, lr: 2.89e-04
2022-05-15 11:31:41,143 INFO [train.py:812] (4/8) Epoch 27, batch 1550, loss[loss=0.1516, simple_loss=0.2551, pruned_loss=0.02409, over 7119.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2465, pruned_loss=0.03243, over 1420229.76 frames.], batch size: 21, lr: 2.89e-04
2022-05-15 11:32:40,460 INFO [train.py:812] (4/8) Epoch 27, batch 1600, loss[loss=0.1522, simple_loss=0.2377, pruned_loss=0.0334, over 7261.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2456, pruned_loss=0.03249, over 1423711.53 frames.], batch size: 19, lr: 2.89e-04
2022-05-15 11:33:39,620 INFO [train.py:812] (4/8) Epoch 27, batch 1650, loss[loss=0.1751, simple_loss=0.2738, pruned_loss=0.03818, over 7207.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2459, pruned_loss=0.03222, over 1427505.60 frames.], batch size: 26, lr: 2.89e-04
2022-05-15 11:34:37,984 INFO [train.py:812] (4/8) Epoch 27, batch 1700, loss[loss=0.1478, simple_loss=0.2455, pruned_loss=0.02507, over 7328.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2457, pruned_loss=0.03179, over 1429114.56 frames.], batch size: 22, lr: 2.89e-04
2022-05-15 11:35:35,783 INFO [train.py:812] (4/8) Epoch 27, batch 1750, loss[loss=0.2013, simple_loss=0.284, pruned_loss=0.05931, over 7113.00 frames.], tot_loss[loss=0.155, simple_loss=0.246, pruned_loss=0.03198, over 1429731.37 frames.], batch size: 26, lr: 2.89e-04
2022-05-15 11:36:34,352 INFO [train.py:812] (4/8) Epoch 27, batch 1800, loss[loss=0.1372, simple_loss=0.2338, pruned_loss=0.02034, over 7120.00 frames.], tot_loss[loss=0.1552, simple_loss=0.246, pruned_loss=0.03221, over 1427058.65 frames.], batch size: 21, lr: 2.89e-04
2022-05-15 11:37:32,438 INFO [train.py:812] (4/8) Epoch 27, batch 1850, loss[loss=0.1957, simple_loss=0.2815, pruned_loss=0.05497, over 4791.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2463, pruned_loss=0.0322, over 1427370.32 frames.], batch size: 53, lr: 2.89e-04
2022-05-15 11:38:30,740 INFO [train.py:812] (4/8) Epoch 27, batch 1900, loss[loss=0.15, simple_loss=0.2407, pruned_loss=0.02965, over 7362.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2451, pruned_loss=0.03189, over 1426342.74 frames.], batch size: 19, lr: 2.89e-04
2022-05-15 11:39:30,046 INFO [train.py:812] (4/8) Epoch 27, batch 1950, loss[loss=0.1552, simple_loss=0.249, pruned_loss=0.03071, over 6546.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2458, pruned_loss=0.03197, over 1423702.17 frames.], batch size: 37, lr: 2.89e-04
2022-05-15 11:40:29,352 INFO [train.py:812] (4/8) Epoch 27, batch 2000, loss[loss=0.1443, simple_loss=0.2465, pruned_loss=0.02106, over 6690.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2449, pruned_loss=0.0318, over 1422342.53 frames.], batch size: 31, lr: 2.89e-04
2022-05-15 11:41:28,623 INFO [train.py:812] (4/8) Epoch 27, batch 2050, loss[loss=0.1423, simple_loss=0.244, pruned_loss=0.02028, over 7165.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03202, over 1425840.93 frames.], batch size: 26, lr: 2.89e-04
2022-05-15 11:42:27,677 INFO [train.py:812] (4/8) Epoch 27, batch 2100, loss[loss=0.1733, simple_loss=0.2713, pruned_loss=0.03767, over 7211.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2469, pruned_loss=0.03266, over 1423716.75 frames.], batch size: 22, lr: 2.89e-04
2022-05-15 11:43:25,344 INFO [train.py:812] (4/8) Epoch 27, batch 2150, loss[loss=0.1546, simple_loss=0.2464, pruned_loss=0.03137, over 7333.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2478, pruned_loss=0.03277, over 1427079.06 frames.], batch size: 25, lr: 2.89e-04
2022-05-15 11:44:23,712 INFO [train.py:812] (4/8) Epoch 27, batch 2200, loss[loss=0.1721, simple_loss=0.2645, pruned_loss=0.03985, over 7231.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2475, pruned_loss=0.03257, over 1425359.49 frames.], batch size: 20, lr: 2.88e-04
2022-05-15 11:45:23,024 INFO [train.py:812] (4/8) Epoch 27, batch 2250, loss[loss=0.1423, simple_loss=0.2285, pruned_loss=0.02801, over 7430.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2474, pruned_loss=0.03252, over 1430970.16 frames.], batch size: 17, lr: 2.88e-04
2022-05-15 11:46:21,533 INFO [train.py:812] (4/8) Epoch 27, batch 2300, loss[loss=0.136, simple_loss=0.2297, pruned_loss=0.02118, over 7137.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2475, pruned_loss=0.03243, over 1432471.51 frames.], batch size: 17, lr: 2.88e-04
2022-05-15 11:47:19,553 INFO [train.py:812] (4/8) Epoch 27, batch 2350, loss[loss=0.1514, simple_loss=0.2501, pruned_loss=0.02635, over 7156.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2481, pruned_loss=0.03268, over 1430741.40 frames.], batch size: 20, lr: 2.88e-04
2022-05-15 11:48:16,533 INFO [train.py:812] (4/8) Epoch 27, batch 2400, loss[loss=0.1742, simple_loss=0.2673, pruned_loss=0.04055, over 7293.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2483, pruned_loss=0.03266, over 1431970.19 frames.], batch size: 24, lr: 2.88e-04
2022-05-15 11:49:16,165 INFO [train.py:812] (4/8) Epoch 27, batch 2450, loss[loss=0.1876, simple_loss=0.273, pruned_loss=0.05113, over 7238.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2481, pruned_loss=0.0326, over 1435537.97 frames.], batch size: 20, lr: 2.88e-04
2022-05-15 11:50:15,242 INFO [train.py:812] (4/8) Epoch 27, batch 2500, loss[loss=0.1787, simple_loss=0.269, pruned_loss=0.04423, over 7224.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2478, pruned_loss=0.03254, over 1437246.84 frames.], batch size: 21, lr: 2.88e-04
2022-05-15 11:51:13,618 INFO [train.py:812] (4/8) Epoch 27, batch 2550, loss[loss=0.1493, simple_loss=0.2531, pruned_loss=0.02278, over 6838.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2471, pruned_loss=0.03183, over 1434178.21 frames.], batch size: 31, lr: 2.88e-04
2022-05-15 11:52:12,744 INFO [train.py:812] (4/8) Epoch 27, batch 2600, loss[loss=0.1429, simple_loss=0.2292, pruned_loss=0.02835, over 6819.00 frames.], tot_loss[loss=0.1552, simple_loss=0.247, pruned_loss=0.03167, over 1434282.55 frames.], batch size: 15, lr: 2.88e-04
2022-05-15 11:53:12,242 INFO [train.py:812] (4/8) Epoch 27, batch 2650, loss[loss=0.1669, simple_loss=0.2689, pruned_loss=0.0324, over 7279.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2472, pruned_loss=0.03177, over 1430845.07 frames.], batch size: 24, lr: 2.88e-04
2022-05-15 11:54:11,603 INFO [train.py:812] (4/8) Epoch 27, batch 2700, loss[loss=0.1565, simple_loss=0.2551, pruned_loss=0.02897, over 7344.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2474, pruned_loss=0.0316, over 1428605.03 frames.], batch size: 22, lr: 2.88e-04
2022-05-15 11:55:10,409 INFO [train.py:812] (4/8) Epoch 27, batch 2750, loss[loss=0.1487, simple_loss=0.2412, pruned_loss=0.02814, over 7165.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2466, pruned_loss=0.03121, over 1427752.70 frames.], batch size: 19, lr: 2.88e-04
2022-05-15 11:56:08,582 INFO [train.py:812] (4/8) Epoch 27, batch 2800, loss[loss=0.1547, simple_loss=0.243, pruned_loss=0.03315, over 7302.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2466, pruned_loss=0.03136, over 1427546.40 frames.], batch size: 25, lr: 2.88e-04
2022-05-15 11:57:08,016 INFO [train.py:812] (4/8) Epoch 27, batch 2850, loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02826, over 7257.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2464, pruned_loss=0.03124, over 1426387.53 frames.], batch size: 19, lr: 2.88e-04
2022-05-15 11:58:06,921 INFO [train.py:812] (4/8) Epoch 27, batch 2900, loss[loss=0.137, simple_loss=0.2225, pruned_loss=0.02575, over 7162.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2462, pruned_loss=0.03128, over 1425700.66 frames.], batch size: 19, lr: 2.88e-04
2022-05-15 11:59:06,488 INFO [train.py:812] (4/8) Epoch 27, batch 2950, loss[loss=0.1529, simple_loss=0.2489, pruned_loss=0.02841, over 7114.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2458, pruned_loss=0.03102, over 1419691.69 frames.], batch size: 21, lr: 2.88e-04
2022-05-15 12:00:05,429 INFO [train.py:812] (4/8) Epoch 27, batch 3000, loss[loss=0.1749, simple_loss=0.2689, pruned_loss=0.04044, over 7410.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2462, pruned_loss=0.03117, over 1419697.19 frames.], batch size: 21, lr: 2.88e-04
2022-05-15 12:00:05,431 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 12:00:12,947 INFO [train.py:841] (4/8) Epoch 27, validation: loss=0.1528, simple_loss=0.25, pruned_loss=0.02785, over 698248.00 frames.
2022-05-15 12:01:11,835 INFO [train.py:812] (4/8) Epoch 27, batch 3050, loss[loss=0.1832, simple_loss=0.2885, pruned_loss=0.03896, over 7109.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2458, pruned_loss=0.03152, over 1411680.95 frames.], batch size: 21, lr: 2.87e-04
2022-05-15 12:02:10,773 INFO [train.py:812] (4/8) Epoch 27, batch 3100, loss[loss=0.1498, simple_loss=0.2402, pruned_loss=0.02968, over 7313.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2471, pruned_loss=0.03198, over 1417704.40 frames.], batch size: 21, lr: 2.87e-04
2022-05-15 12:03:20,249 INFO [train.py:812] (4/8) Epoch 27, batch 3150, loss[loss=0.1551, simple_loss=0.2474, pruned_loss=0.03146, over 7208.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2477, pruned_loss=0.03235, over 1417672.80 frames.], batch size: 22, lr: 2.87e-04
2022-05-15 12:04:19,263 INFO [train.py:812] (4/8) Epoch 27, batch 3200, loss[loss=0.1737, simple_loss=0.2657, pruned_loss=0.0408, over 7206.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2478, pruned_loss=0.03228, over 1420638.32 frames.], batch size: 23, lr: 2.87e-04
2022-05-15 12:05:18,866 INFO [train.py:812] (4/8) Epoch 27, batch 3250, loss[loss=0.1666, simple_loss=0.2667, pruned_loss=0.03325, over 6515.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2482, pruned_loss=0.03242, over 1421405.60 frames.], batch size: 38, lr: 2.87e-04
2022-05-15 12:06:17,728 INFO [train.py:812] (4/8) Epoch 27, batch 3300, loss[loss=0.1567, simple_loss=0.2468, pruned_loss=0.03329, over 6814.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2478, pruned_loss=0.03237, over 1420618.12 frames.], batch size: 31, lr: 2.87e-04
2022-05-15 12:07:17,058 INFO [train.py:812] (4/8) Epoch 27, batch 3350, loss[loss=0.1571, simple_loss=0.2566, pruned_loss=0.02879, over 7331.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2494, pruned_loss=0.03308, over 1421070.46 frames.], batch size: 22, lr: 2.87e-04
2022-05-15 12:08:16,174 INFO [train.py:812] (4/8) Epoch 27, batch 3400, loss[loss=0.1751, simple_loss=0.2675, pruned_loss=0.0413, over 7147.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2495, pruned_loss=0.03308, over 1418355.60 frames.], batch size: 20, lr: 2.87e-04
2022-05-15 12:09:14,982 INFO [train.py:812] (4/8) Epoch 27, batch 3450, loss[loss=0.1499, simple_loss=0.2422, pruned_loss=0.02877, over 7338.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2496, pruned_loss=0.0328, over 1421367.36 frames.], batch size: 22, lr: 2.87e-04
2022-05-15 12:10:13,338 INFO [train.py:812] (4/8) Epoch 27, batch 3500, loss[loss=0.1264, simple_loss=0.2144, pruned_loss=0.01924, over 6779.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2485, pruned_loss=0.0325, over 1423478.10 frames.], batch size: 15, lr: 2.87e-04
2022-05-15 12:11:13,075 INFO [train.py:812] (4/8) Epoch 27, batch 3550, loss[loss=0.1585, simple_loss=0.2457, pruned_loss=0.03561, over 5118.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2477, pruned_loss=0.03188, over 1416902.05 frames.], batch size: 52, lr: 2.87e-04
2022-05-15 12:12:10,925 INFO [train.py:812] (4/8) Epoch 27, batch 3600, loss[loss=0.1357, simple_loss=0.2315, pruned_loss=0.01993, over 7150.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2478, pruned_loss=0.03163, over 1414182.25 frames.], batch size: 19, lr: 2.87e-04
2022-05-15 12:13:10,316 INFO [train.py:812] (4/8) Epoch 27, batch 3650, loss[loss=0.1382, simple_loss=0.2226, pruned_loss=0.02686, over 7061.00 frames.], tot_loss[loss=0.1559, simple_loss=0.248, pruned_loss=0.03191, over 1413725.68 frames.], batch size: 18, lr: 2.87e-04
2022-05-15 12:14:09,329 INFO [train.py:812] (4/8) Epoch 27, batch 3700, loss[loss=0.1359, simple_loss=0.2207, pruned_loss=0.0255, over 7293.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2476, pruned_loss=0.03203, over 1413037.73 frames.], batch size: 18, lr: 2.87e-04
2022-05-15 12:15:08,333 INFO [train.py:812] (4/8) Epoch 27, batch 3750, loss[loss=0.1936, simple_loss=0.2803, pruned_loss=0.05349, over 7224.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2467, pruned_loss=0.03214, over 1416691.97 frames.], batch size: 21, lr: 2.87e-04
2022-05-15 12:16:08,058 INFO [train.py:812] (4/8) Epoch 27, batch 3800, loss[loss=0.1464, simple_loss=0.2355, pruned_loss=0.02865, over 7328.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2453, pruned_loss=0.03154, over 1420875.97 frames.], batch size: 20, lr: 2.87e-04
2022-05-15 12:17:07,772 INFO [train.py:812] (4/8) Epoch 27, batch 3850, loss[loss=0.1415, simple_loss=0.2295, pruned_loss=0.02671, over 7426.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03209, over 1413623.94 frames.], batch size: 18, lr: 2.87e-04
2022-05-15 12:18:06,242 INFO [train.py:812] (4/8) Epoch 27, batch 3900, loss[loss=0.1703, simple_loss=0.2646, pruned_loss=0.03802, over 7027.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2473, pruned_loss=0.03221, over 1414799.55 frames.], batch size: 28, lr: 2.86e-04
2022-05-15 12:19:04,970 INFO [train.py:812] (4/8) Epoch 27, batch 3950, loss[loss=0.1732, simple_loss=0.2639, pruned_loss=0.04124, over 7346.00 frames.], tot_loss[loss=0.156, simple_loss=0.2473, pruned_loss=0.03239, over 1419206.12 frames.], batch size: 19, lr: 2.86e-04
2022-05-15 12:20:04,218 INFO [train.py:812] (4/8) Epoch 27, batch 4000, loss[loss=0.1634, simple_loss=0.2479, pruned_loss=0.03946, over 7122.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2457, pruned_loss=0.03179, over 1424342.31 frames.], batch size: 28, lr: 2.86e-04
2022-05-15 12:21:04,114 INFO [train.py:812] (4/8) Epoch 27, batch 4050, loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02859, over 7339.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03167, over 1425356.91 frames.], batch size: 20, lr: 2.86e-04
2022-05-15 12:22:03,546 INFO [train.py:812] (4/8) Epoch 27, batch 4100, loss[loss=0.1414, simple_loss=0.2417, pruned_loss=0.02053, over 7323.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03135, over 1423401.36 frames.], batch size: 20, lr: 2.86e-04
2022-05-15 12:23:02,356 INFO [train.py:812] (4/8) Epoch 27, batch 4150, loss[loss=0.1423, simple_loss=0.2367, pruned_loss=0.02394, over 7114.00 frames.], tot_loss[loss=0.154, simple_loss=0.2454, pruned_loss=0.0313, over 1420772.70 frames.], batch size: 21, lr: 2.86e-04
2022-05-15 12:23:59,498 INFO [train.py:812] (4/8) Epoch 27, batch 4200, loss[loss=0.1422, simple_loss=0.2481, pruned_loss=0.01814, over 7322.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2453, pruned_loss=0.03125, over 1422020.84 frames.], batch size: 22, lr: 2.86e-04
2022-05-15 12:24:57,511 INFO [train.py:812] (4/8) Epoch 27, batch 4250, loss[loss=0.1574, simple_loss=0.2467, pruned_loss=0.03404, over 7409.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2465, pruned_loss=0.0316, over 1414883.50 frames.], batch size: 21, lr: 2.86e-04
2022-05-15 12:25:55,497 INFO [train.py:812] (4/8) Epoch 27, batch 4300, loss[loss=0.1592, simple_loss=0.2479, pruned_loss=0.03525, over 6720.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2474, pruned_loss=0.03191, over 1414051.75 frames.], batch size: 31, lr: 2.86e-04
2022-05-15 12:26:54,775 INFO [train.py:812] (4/8) Epoch 27, batch 4350, loss[loss=0.1436, simple_loss=0.2227, pruned_loss=0.03224, over 7002.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2474, pruned_loss=0.03213, over 1413547.10 frames.], batch size: 16, lr: 2.86e-04
2022-05-15 12:27:53,340 INFO [train.py:812] (4/8) Epoch 27, batch 4400, loss[loss=0.139, simple_loss=0.2329, pruned_loss=0.02255, over 6304.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2475, pruned_loss=0.03245, over 1400213.17 frames.], batch size: 37, lr: 2.86e-04
2022-05-15 12:28:51,270 INFO [train.py:812] (4/8) Epoch 27, batch 4450, loss[loss=0.1535, simple_loss=0.2506, pruned_loss=0.02823, over 7340.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2474, pruned_loss=0.03278, over 1397602.21 frames.], batch size: 22, lr: 2.86e-04
2022-05-15 12:29:50,409 INFO [train.py:812] (4/8) Epoch 27, batch 4500, loss[loss=0.1677, simple_loss=0.2577, pruned_loss=0.03881, over 7163.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2478, pruned_loss=0.03317, over 1387762.45 frames.], batch size: 18, lr: 2.86e-04
2022-05-15 12:30:49,289 INFO [train.py:812] (4/8) Epoch 27, batch 4550, loss[loss=0.2038, simple_loss=0.2774, pruned_loss=0.06506, over 4754.00 frames.], tot_loss[loss=0.1567, simple_loss=0.247, pruned_loss=0.03326, over 1369727.33 frames.], batch size: 52, lr: 2.86e-04
2022-05-15 12:32:00,086 INFO [train.py:812] (4/8) Epoch 28, batch 0, loss[loss=0.1369, simple_loss=0.2262, pruned_loss=0.02382, over 7260.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2262, pruned_loss=0.02382, over 7260.00 frames.], batch size: 19, lr: 2.81e-04
2022-05-15 12:32:59,362 INFO [train.py:812] (4/8) Epoch 28, batch 50, loss[loss=0.1645, simple_loss=0.2469, pruned_loss=0.04112, over 7252.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2459, pruned_loss=0.03159, over 321685.06 frames.], batch size: 19, lr: 2.81e-04
2022-05-15 12:33:58,534 INFO [train.py:812] (4/8) Epoch 28, batch 100, loss[loss=0.1416, simple_loss=0.239, pruned_loss=0.02212, over 7142.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2451, pruned_loss=0.03087, over 565208.32 frames.], batch size: 20, lr: 2.80e-04
2022-05-15 12:35:03,229 INFO [train.py:812] (4/8) Epoch 28, batch 150, loss[loss=0.1409, simple_loss=0.235, pruned_loss=0.02341, over 6432.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2461, pruned_loss=0.03085, over 753782.76 frames.], batch size: 37, lr: 2.80e-04
2022-05-15 12:36:01,539 INFO [train.py:812] (4/8) Epoch 28, batch 200, loss[loss=0.1688, simple_loss=0.2669, pruned_loss=0.03534, over 7200.00 frames.], tot_loss[loss=0.1548, simple_loss=0.247, pruned_loss=0.03132, over 900121.44 frames.], batch size: 23, lr: 2.80e-04
2022-05-15 12:36:59,620 INFO [train.py:812] (4/8) Epoch 28, batch 250, loss[loss=0.1769, simple_loss=0.2718, pruned_loss=0.04104, over 7315.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2468, pruned_loss=0.03121, over 1015713.48 frames.], batch size: 24, lr: 2.80e-04
2022-05-15 12:37:58,310 INFO [train.py:812] (4/8) Epoch 28, batch 300, loss[loss=0.1533, simple_loss=0.2393, pruned_loss=0.03361, over 6782.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2469, pruned_loss=0.0313, over 1105210.16 frames.], batch size: 31, lr: 2.80e-04
2022-05-15 12:38:57,247 INFO [train.py:812] (4/8) Epoch 28, batch 350, loss[loss=0.1571, simple_loss=0.2451, pruned_loss=0.03448, over 7157.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2457, pruned_loss=0.03069, over 1177704.34 frames.], batch size: 19, lr: 2.80e-04
2022-05-15 12:39:55,227 INFO [train.py:812] (4/8) Epoch 28, batch 400, loss[loss=0.1492, simple_loss=0.241, pruned_loss=0.02876, over 7133.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2465, pruned_loss=0.03141, over 1234284.87 frames.], batch size: 17, lr: 2.80e-04
2022-05-15 12:40:54,511 INFO [train.py:812] (4/8) Epoch 28, batch 450, loss[loss=0.164, simple_loss=0.2537, pruned_loss=0.03717, over 7301.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.03197, over 1271433.48 frames.], batch size: 25, lr: 2.80e-04
2022-05-15 12:41:53,061 INFO [train.py:812] (4/8) Epoch 28, batch 500, loss[loss=0.1555, simple_loss=0.2533, pruned_loss=0.02883, over 7308.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2461, pruned_loss=0.03142, over 1308771.09 frames.], batch size: 21, lr: 2.80e-04
2022-05-15 12:42:52,284 INFO [train.py:812] (4/8) Epoch 28, batch 550, loss[loss=0.1726, simple_loss=0.251, pruned_loss=0.04706, over 7068.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2458, pruned_loss=0.03148, over 1331262.45 frames.], batch size: 18, lr: 2.80e-04
2022-05-15 12:43:51,388 INFO [train.py:812] (4/8) Epoch 28, batch 600, loss[loss=0.1405, simple_loss=0.2307, pruned_loss=0.02517, over 7338.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2462, pruned_loss=0.03144, over 1349916.80 frames.], batch size: 20, lr: 2.80e-04
2022-05-15 12:44:49,182 INFO [train.py:812] (4/8) Epoch 28, batch 650, loss[loss=0.1828, simple_loss=0.2773, pruned_loss=0.04413, over 7078.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2462, pruned_loss=0.0314, over 1367098.81 frames.], batch size: 28, lr: 2.80e-04
2022-05-15 12:45:47,938 INFO [train.py:812] (4/8) Epoch 28, batch 700, loss[loss=0.1272, simple_loss=0.2169, pruned_loss=0.01879, over 7069.00 frames.], tot_loss[loss=0.1543, simple_loss=0.246, pruned_loss=0.03129, over 1380986.31 frames.], batch size: 18, lr: 2.80e-04
2022-05-15 12:46:48,082 INFO [train.py:812] (4/8) Epoch 28, batch 750, loss[loss=0.1545, simple_loss=0.2539, pruned_loss=0.02757, over 7221.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2451, pruned_loss=0.03117, over 1392033.21 frames.], batch size: 21, lr: 2.80e-04
2022-05-15 12:47:47,179 INFO [train.py:812] (4/8) Epoch 28, batch 800, loss[loss=0.155, simple_loss=0.254, pruned_loss=0.02796, over 7129.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2457, pruned_loss=0.03109, over 1398600.07 frames.], batch size: 28, lr: 2.80e-04
2022-05-15 12:48:46,804 INFO [train.py:812] (4/8) Epoch 28, batch 850, loss[loss=0.1686, simple_loss=0.2679, pruned_loss=0.03466, over 7329.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2454, pruned_loss=0.03085, over 1406258.37 frames.], batch size: 25, lr: 2.80e-04
2022-05-15 12:49:45,701 INFO [train.py:812] (4/8) Epoch 28, batch 900, loss[loss=0.1395, simple_loss=0.221, pruned_loss=0.02898, over 7003.00 frames.], tot_loss[loss=0.1541, simple_loss=0.246, pruned_loss=0.03104, over 1407530.96 frames.], batch size: 16, lr: 2.80e-04
2022-05-15 12:50:44,997 INFO [train.py:812] (4/8) Epoch 28, batch 950, loss[loss=0.136, simple_loss=0.2262, pruned_loss=0.02289, over 7154.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2459, pruned_loss=0.03133, over 1410284.78 frames.], batch size: 18, lr: 2.80e-04
2022-05-15 12:51:43,943 INFO [train.py:812] (4/8) Epoch 28, batch 1000, loss[loss=0.1653, simple_loss=0.2606, pruned_loss=0.03502, over 7435.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2463, pruned_loss=0.03147, over 1415789.44 frames.], batch size: 20, lr: 2.79e-04
2022-05-15 12:52:42,476 INFO [train.py:812] (4/8) Epoch 28, batch 1050, loss[loss=0.1501, simple_loss=0.2409, pruned_loss=0.02965, over 7413.00 frames.], tot_loss[loss=0.155, simple_loss=0.2466, pruned_loss=0.03174, over 1416326.90 frames.], batch size: 21, lr: 2.79e-04
2022-05-15 12:53:50,425 INFO [train.py:812] (4/8) Epoch 28, batch 1100, loss[loss=0.1475, simple_loss=0.2277, pruned_loss=0.0337, over 7063.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2463, pruned_loss=0.03133, over 1414776.58 frames.], batch size: 18, lr: 2.79e-04
2022-05-15 12:54:49,776 INFO [train.py:812] (4/8) Epoch 28, batch 1150, loss[loss=0.1574, simple_loss=0.2553, pruned_loss=0.0297, over 7187.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2465, pruned_loss=0.03153, over 1420667.18 frames.], batch size: 23, lr: 2.79e-04
2022-05-15 12:55:48,173 INFO [train.py:812] (4/8) Epoch 28, batch 1200, loss[loss=0.1562, simple_loss=0.2452, pruned_loss=0.03353, over 7149.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2464, pruned_loss=0.03144, over 1424538.12 frames.], batch size: 17, lr: 2.79e-04
2022-05-15 12:56:47,572 INFO [train.py:812] (4/8) Epoch 28, batch 1250, loss[loss=0.1531, simple_loss=0.2339, pruned_loss=0.03612, over 7126.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2465, pruned_loss=0.0314, over 1422355.39 frames.], batch size: 17, lr: 2.79e-04
2022-05-15 12:57:56,212 INFO [train.py:812] (4/8) Epoch 28, batch 1300, loss[loss=0.1456, simple_loss=0.2381, pruned_loss=0.02655, over 7289.00 frames.], tot_loss[loss=0.1551, simple_loss=0.247, pruned_loss=0.03158, over 1418876.07 frames.], batch size: 18, lr: 2.79e-04
2022-05-15 12:58:55,628 INFO [train.py:812] (4/8) Epoch 28, batch 1350, loss[loss=0.1526, simple_loss=0.2359, pruned_loss=0.03464, over 7360.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03203, over 1418808.28 frames.], batch size: 19, lr: 2.79e-04
2022-05-15 13:00:02,713 INFO [train.py:812] (4/8) Epoch 28, batch 1400, loss[loss=0.1433, simple_loss=0.2357, pruned_loss=0.0254, over 7067.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2463, pruned_loss=0.03207, over 1418871.26 frames.], batch size: 18, lr: 2.79e-04
2022-05-15 13:01:30,486 INFO [train.py:812] (4/8) Epoch 28, batch 1450, loss[loss=0.1449, simple_loss=0.237, pruned_loss=0.02643, over 7331.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2447, pruned_loss=0.03172, over 1421633.74 frames.], batch size: 20, lr: 2.79e-04
2022-05-15 13:02:27,763 INFO [train.py:812] (4/8) Epoch 28, batch 1500, loss[loss=0.1528, simple_loss=0.2633, pruned_loss=0.02117, over 7107.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2456, pruned_loss=0.03156, over 1423656.85 frames.], batch size: 21, lr: 2.79e-04
2022-05-15 13:03:25,150 INFO [train.py:812] (4/8) Epoch 28, batch 1550, loss[loss=0.1222, simple_loss=0.2159, pruned_loss=0.01421, over 6795.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2464, pruned_loss=0.03194, over 1420586.46 frames.], batch size: 15, lr: 2.79e-04
2022-05-15 13:04:33,683 INFO [train.py:812] (4/8) Epoch 28, batch 1600, loss[loss=0.1869, simple_loss=0.2754, pruned_loss=0.04917, over 7425.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2459, pruned_loss=0.03183, over 1424605.98 frames.], batch size: 21, lr: 2.79e-04
2022-05-15 13:05:32,118 INFO [train.py:812] (4/8) Epoch 28, batch 1650, loss[loss=0.1397, simple_loss=0.2158, pruned_loss=0.03174, over 7059.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2452, pruned_loss=0.03146, over 1425661.27 frames.], batch size: 18, lr: 2.79e-04
2022-05-15 13:06:30,573 INFO [train.py:812] (4/8) Epoch 28, batch 1700, loss[loss=0.1355, simple_loss=0.2202, pruned_loss=0.02541, over 7355.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2462, pruned_loss=0.03152, over 1427201.81 frames.], batch size: 19, lr: 2.79e-04
2022-05-15 13:07:29,481 INFO [train.py:812] (4/8) Epoch 28, batch 1750, loss[loss=0.157, simple_loss=0.2495, pruned_loss=0.03219, over 6811.00 frames.], tot_loss[loss=0.155, simple_loss=0.2462, pruned_loss=0.03188, over 1428367.68 frames.], batch size: 31, lr: 2.79e-04
2022-05-15 13:08:28,865 INFO [train.py:812] (4/8) Epoch 28, batch 1800, loss[loss=0.1624, simple_loss=0.2606, pruned_loss=0.0321, over 7221.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2466, pruned_loss=0.03203, over 1427104.31 frames.], batch size: 20, lr: 2.79e-04
2022-05-15 13:09:27,169 INFO [train.py:812] (4/8) Epoch 28, batch 1850, loss[loss=0.1297, simple_loss=0.2236, pruned_loss=0.01787, over 7169.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2459, pruned_loss=0.03149, over 1429872.25 frames.], batch size: 19, lr: 2.79e-04
2022-05-15 13:10:26,328 INFO [train.py:812] (4/8) Epoch 28, batch 1900, loss[loss=0.187, simple_loss=0.2693, pruned_loss=0.05234, over 7279.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2458, pruned_loss=0.03155, over 1430372.42 frames.], batch size: 17, lr: 2.78e-04
2022-05-15 13:11:24,510 INFO [train.py:812] (4/8) Epoch 28, batch 1950, loss[loss=0.1702, simple_loss=0.2684, pruned_loss=0.03596, over 6555.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2458, pruned_loss=0.03148, over 1425337.47 frames.], batch size: 37, lr: 2.78e-04
2022-05-15 13:12:23,343 INFO [train.py:812] (4/8) Epoch 28, batch 2000, loss[loss=0.141, simple_loss=0.2376, pruned_loss=0.02219, over 7219.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2455, pruned_loss=0.03086, over 1424314.99 frames.], batch size: 21, lr: 2.78e-04
2022-05-15 13:13:21,542 INFO [train.py:812] (4/8) Epoch 28, batch 2050, loss[loss=0.1553, simple_loss=0.2462, pruned_loss=0.03217, over 7214.00 frames.], tot_loss[loss=0.1551, simple_loss=0.247, pruned_loss=0.03161, over 1423047.61 frames.], batch size: 23, lr: 2.78e-04
2022-05-15 13:14:21,005 INFO [train.py:812] (4/8) Epoch 28, batch 2100, loss[loss=0.1632, simple_loss=0.256, pruned_loss=0.03517, over 7281.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2461, pruned_loss=0.03133, over 1423319.63 frames.], batch size: 25, lr: 2.78e-04
2022-05-15 13:15:20,656 INFO [train.py:812] (4/8) Epoch 28, batch 2150, loss[loss=0.1553, simple_loss=0.2319, pruned_loss=0.03933, over 7116.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2469, pruned_loss=0.03165, over 1422164.58 frames.], batch size: 17, lr: 2.78e-04
2022-05-15 13:16:19,069 INFO [train.py:812] (4/8) Epoch 28, batch 2200, loss[loss=0.1459, simple_loss=0.2453, pruned_loss=0.02325, over 7314.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2467, pruned_loss=0.03146, over 1421428.31 frames.], batch size: 24, lr: 2.78e-04
2022-05-15 13:17:18,176 INFO [train.py:812] (4/8) Epoch 28, batch 2250, loss[loss=0.1615, simple_loss=0.2483, pruned_loss=0.03739, over 7341.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2465, pruned_loss=0.03135, over 1424321.80 frames.], batch size: 22, lr: 2.78e-04
2022-05-15 13:18:16,762 INFO [train.py:812] (4/8) Epoch 28, batch 2300, loss[loss=0.1555, simple_loss=0.2488, pruned_loss=0.03112, over 7141.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.0316, over 1421299.03 frames.], batch size: 20, lr: 2.78e-04
2022-05-15 13:19:16,299 INFO [train.py:812] (4/8) Epoch 28, batch 2350, loss[loss=0.1563, simple_loss=0.2545, pruned_loss=0.02907, over 7159.00 frames.], tot_loss[loss=0.155, simple_loss=0.2464, pruned_loss=0.03179, over 1419657.10 frames.], batch size: 19, lr: 2.78e-04
2022-05-15 13:20:14,242 INFO [train.py:812] (4/8) Epoch 28, batch 2400, loss[loss=0.1917, simple_loss=0.279, pruned_loss=0.05221, over 7206.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03222, over 1422651.57 frames.], batch size: 23, lr: 2.78e-04
2022-05-15 13:21:14,083 INFO [train.py:812] (4/8) Epoch 28, batch 2450, loss[loss=0.1562, simple_loss=0.2599, pruned_loss=0.0263, over 6333.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2465, pruned_loss=0.03158, over 1422913.35 frames.], batch size: 37, lr: 2.78e-04
2022-05-15 13:22:13,030 INFO [train.py:812] (4/8) Epoch 28, batch 2500, loss[loss=0.1529, simple_loss=0.2343, pruned_loss=0.03572, over 7273.00 frames.], tot_loss[loss=0.155, simple_loss=0.2465, pruned_loss=0.03175, over 1420504.06 frames.], batch size: 16, lr: 2.78e-04
2022-05-15 13:23:12,410 INFO [train.py:812] (4/8) Epoch 28, batch 2550, loss[loss=0.1364, simple_loss=0.2321, pruned_loss=0.0203, over 7261.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.0316, over 1421714.88 frames.], batch size: 19, lr: 2.78e-04
2022-05-15 13:24:10,669 INFO [train.py:812] (4/8) Epoch 28, batch 2600, loss[loss=0.1538, simple_loss=0.2534, pruned_loss=0.0271, over 7231.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2457, pruned_loss=0.03109, over 1421698.61 frames.], batch size: 20, lr: 2.78e-04
2022-05-15 13:25:09,883 INFO [train.py:812] (4/8) Epoch 28, batch 2650, loss[loss=0.1382, simple_loss=0.2244, pruned_loss=0.02606, over 7021.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2468, pruned_loss=0.0315, over 1420534.42 frames.], batch size: 16, lr: 2.78e-04
2022-05-15 13:26:08,942 INFO [train.py:812] (4/8) Epoch 28, batch 2700, loss[loss=0.1534, simple_loss=0.2564, pruned_loss=0.02517, over 7320.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2466, pruned_loss=0.03132, over 1422563.36 frames.], batch size: 21, lr: 2.78e-04
2022-05-15 13:27:07,538 INFO [train.py:812] (4/8) Epoch 28, batch 2750, loss[loss=0.1271, simple_loss=0.2164, pruned_loss=0.01887, over 7234.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2477, pruned_loss=0.03185, over 1420475.47 frames.], batch size: 19, lr: 2.78e-04
2022-05-15 13:28:05,904 INFO [train.py:812] (4/8) Epoch 28, batch 2800, loss[loss=0.1479, simple_loss=0.2356, pruned_loss=0.03013, over 7236.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2474, pruned_loss=0.03172, over 1416809.69 frames.], batch size: 20, lr: 2.77e-04
2022-05-15 13:29:05,088 INFO [train.py:812] (4/8) Epoch 28, batch 2850, loss[loss=0.132, simple_loss=0.2199, pruned_loss=0.02203, over 7141.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2469, pruned_loss=0.03168, over 1421173.48 frames.], batch size: 17, lr: 2.77e-04
2022-05-15 13:30:03,003 INFO [train.py:812] (4/8) Epoch 28, batch 2900, loss[loss=0.1765, simple_loss=0.279, pruned_loss=0.03696, over 7311.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2473, pruned_loss=0.03172, over 1420281.89 frames.], batch size: 25, lr: 2.77e-04
2022-05-15 13:31:01,403 INFO [train.py:812] (4/8) Epoch 28, batch 2950, loss[loss=0.1466, simple_loss=0.2338, pruned_loss=0.02969, over 7203.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2475, pruned_loss=0.03161, over 1423096.40 frames.], batch size: 23, lr: 2.77e-04
2022-05-15 13:32:00,613 INFO [train.py:812] (4/8) Epoch 28, batch 3000, loss[loss=0.1857, simple_loss=0.2743, pruned_loss=0.0485, over 7060.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2472, pruned_loss=0.0317, over 1424923.31 frames.], batch size: 28, lr: 2.77e-04
2022-05-15 13:32:00,614 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 13:32:08,091 INFO [train.py:841] (4/8) Epoch 28, validation: loss=0.1523, simple_loss=0.2496, pruned_loss=0.02748, over 698248.00 frames.
2022-05-15 13:33:05,905 INFO [train.py:812] (4/8) Epoch 28, batch 3050, loss[loss=0.1402, simple_loss=0.2172, pruned_loss=0.03161, over 7132.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2469, pruned_loss=0.03174, over 1426246.62 frames.], batch size: 17, lr: 2.77e-04
2022-05-15 13:34:04,042 INFO [train.py:812] (4/8) Epoch 28, batch 3100, loss[loss=0.1595, simple_loss=0.2518, pruned_loss=0.03361, over 7368.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2458, pruned_loss=0.03122, over 1424650.02 frames.], batch size: 23, lr: 2.77e-04
2022-05-15 13:35:03,615 INFO [train.py:812] (4/8) Epoch 28, batch 3150, loss[loss=0.1324, simple_loss=0.2114, pruned_loss=0.02671, over 7402.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2459, pruned_loss=0.03164, over 1423439.17 frames.], batch size: 18, lr: 2.77e-04
2022-05-15 13:36:02,618 INFO [train.py:812] (4/8) Epoch 28, batch 3200, loss[loss=0.1618, simple_loss=0.2566, pruned_loss=0.03346, over 7318.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2463, pruned_loss=0.03162, over 1424173.71 frames.], batch size: 21, lr: 2.77e-04
2022-05-15 13:37:02,639 INFO [train.py:812] (4/8) Epoch 28, batch 3250, loss[loss=0.1688, simple_loss=0.2573, pruned_loss=0.04013, over 7171.00 frames.], tot_loss[loss=0.155, simple_loss=0.2463, pruned_loss=0.03185, over 1424100.15 frames.], batch size: 18, lr: 2.77e-04
2022-05-15 13:37:59,648 INFO [train.py:812] (4/8) Epoch 28, batch 3300, loss[loss=0.1339, simple_loss=0.2144, pruned_loss=0.02672, over 6993.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2465, pruned_loss=0.03188, over 1423382.42 frames.], batch size: 16, lr: 2.77e-04
2022-05-15 13:38:57,847 INFO [train.py:812] (4/8) Epoch 28, batch 3350, loss[loss=0.1581, simple_loss=0.2523, pruned_loss=0.03195, over 7359.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03174, over 1420970.86 frames.], batch size: 23, lr: 2.77e-04
2022-05-15 13:39:56,933 INFO [train.py:812] (4/8) Epoch 28, batch 3400, loss[loss=0.1666, simple_loss=0.2638, pruned_loss=0.03466, over 7321.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.0319, over 1422409.75 frames.], batch size: 20, lr: 2.77e-04
2022-05-15 13:40:56,434 INFO [train.py:812] (4/8) Epoch 28, batch 3450, loss[loss=0.1661, simple_loss=0.2583, pruned_loss=0.03692, over 7210.00 frames.], tot_loss[loss=0.155, simple_loss=0.2465, pruned_loss=0.03174, over 1423621.13 frames.], batch size: 22, lr: 2.77e-04
2022-05-15 13:41:55,467 INFO [train.py:812] (4/8) Epoch 28, batch 3500, loss[loss=0.1409, simple_loss=0.2341, pruned_loss=0.02388, over 7061.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.03154, over 1422570.81 frames.], batch size: 18, lr: 2.77e-04
2022-05-15 13:42:54,601 INFO [train.py:812] (4/8) Epoch 28, batch 3550, loss[loss=0.1562, simple_loss=0.2512, pruned_loss=0.03061, over 7322.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2463, pruned_loss=0.03135, over 1423651.49 frames.], batch size: 22, lr: 2.77e-04
2022-05-15 13:43:53,656 INFO [train.py:812] (4/8) Epoch 28, batch 3600, loss[loss=0.1395, simple_loss=0.2282, pruned_loss=0.02537, over 7070.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2472, pruned_loss=0.03174, over 1423552.17 frames.], batch size: 18, lr: 2.77e-04
2022-05-15 13:44:53,072 INFO [train.py:812] (4/8) Epoch 28, batch 3650, loss[loss=0.1852, simple_loss=0.2768, pruned_loss=0.04683, over 7407.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2462, pruned_loss=0.03133, over 1423027.71 frames.], batch size: 21, lr: 2.77e-04
2022-05-15 13:45:51,493 INFO [train.py:812] (4/8) Epoch 28, batch 3700, loss[loss=0.1514, simple_loss=0.2457, pruned_loss=0.02854, over 7440.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2463, pruned_loss=0.03138, over 1423084.16 frames.], batch size: 20, lr: 2.77e-04
2022-05-15 13:46:50,233 INFO [train.py:812] (4/8) Epoch 28, batch 3750, loss[loss=0.1977, simple_loss=0.2801, pruned_loss=0.05764, over 5007.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.03153, over 1419896.60 frames.], batch size: 52, lr: 2.76e-04
2022-05-15 13:47:49,325 INFO [train.py:812] (4/8) Epoch 28, batch 3800, loss[loss=0.143, simple_loss=0.2232, pruned_loss=0.03136, over 7273.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2465, pruned_loss=0.03131, over 1422519.41 frames.], batch size: 17, lr: 2.76e-04
2022-05-15 13:48:48,426 INFO [train.py:812] (4/8) Epoch 28, batch 3850, loss[loss=0.1642, simple_loss=0.2585, pruned_loss=0.03494, over 7160.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2466, pruned_loss=0.03148, over 1426019.45 frames.], batch size: 19, lr: 2.76e-04
2022-05-15 13:49:47,457 INFO [train.py:812] (4/8) Epoch 28, batch 3900, loss[loss=0.1488, simple_loss=0.2421, pruned_loss=0.02775, over 7201.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2462, pruned_loss=0.03131, over 1424595.34 frames.], batch size: 22, lr: 2.76e-04
2022-05-15 13:50:47,235 INFO [train.py:812] (4/8) Epoch 28, batch 3950, loss[loss=0.1713, simple_loss=0.2675, pruned_loss=0.03753, over 7204.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2457, pruned_loss=0.03081, over 1426376.28 frames.], batch size: 22, lr: 2.76e-04
2022-05-15 13:51:46,170 INFO [train.py:812] (4/8) Epoch 28, batch 4000, loss[loss=0.1601, simple_loss=0.2581, pruned_loss=0.031, over 6765.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2447, pruned_loss=0.0309, over 1423063.50 frames.], batch size: 31, lr: 2.76e-04
2022-05-15 13:52:45,722 INFO [train.py:812] (4/8) Epoch 28, batch 4050, loss[loss=0.1848, simple_loss=0.2711, pruned_loss=0.04925, over 4786.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2466, pruned_loss=0.03178, over 1416451.30 frames.], batch size: 52, lr: 2.76e-04
2022-05-15 13:53:44,805 INFO [train.py:812] (4/8) Epoch 28, batch 4100, loss[loss=0.1299, simple_loss=0.2085, pruned_loss=0.02568, over 7120.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2466, pruned_loss=0.03238, over 1418196.70 frames.], batch size: 17, lr: 2.76e-04
2022-05-15 13:54:49,274 INFO [train.py:812] (4/8) Epoch 28, batch 4150, loss[loss=0.1469, simple_loss=0.2392, pruned_loss=0.02734, over 7154.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03252, over 1423242.69 frames.], batch size: 19, lr: 2.76e-04
2022-05-15 13:55:47,964 INFO [train.py:812] (4/8) Epoch 28, batch 4200, loss[loss=0.1555, simple_loss=0.2538, pruned_loss=0.02863, over 5258.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2478, pruned_loss=0.03259, over 1417990.09 frames.], batch size: 52, lr: 2.76e-04
2022-05-15 13:56:46,297 INFO [train.py:812] (4/8) Epoch 28, batch 4250, loss[loss=0.1512, simple_loss=0.2382, pruned_loss=0.03212, over 7057.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2469, pruned_loss=0.03221, over 1416278.65 frames.], batch size: 18, lr: 2.76e-04
2022-05-15 13:57:45,187 INFO [train.py:812] (4/8) Epoch 28, batch 4300, loss[loss=0.1482, simple_loss=0.2305, pruned_loss=0.03288, over 7142.00 frames.], tot_loss[loss=0.155, simple_loss=0.2462, pruned_loss=0.03186, over 1417901.14 frames.], batch size: 17, lr: 2.76e-04
2022-05-15 13:58:44,137 INFO [train.py:812] (4/8) Epoch 28, batch 4350, loss[loss=0.1726, simple_loss=0.2643, pruned_loss=0.04044, over 7214.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.03161, over 1417619.14 frames.], batch size: 21, lr: 2.76e-04
2022-05-15 13:59:42,366 INFO [train.py:812] (4/8) Epoch 28, batch 4400, loss[loss=0.1504, simple_loss=0.2453, pruned_loss=0.0278, over 6405.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2465, pruned_loss=0.03163, over 1409732.99 frames.], batch size: 37, lr: 2.76e-04
2022-05-15 14:00:51,464 INFO [train.py:812] (4/8) Epoch 28, batch 4450, loss[loss=0.1659, simple_loss=0.2428, pruned_loss=0.0445, over 7244.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2467, pruned_loss=0.03207, over 1402780.97 frames.], batch size: 16, lr: 2.76e-04
2022-05-15 14:01:50,406 INFO [train.py:812] (4/8) Epoch 28, batch 4500, loss[loss=0.1677, simple_loss=0.2736, pruned_loss=0.03087, over 7214.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03205, over 1390587.74 frames.], batch size: 21, lr: 2.76e-04
2022-05-15 14:02:49,652 INFO [train.py:812] (4/8) Epoch 28, batch 4550, loss[loss=0.1458, simple_loss=0.2514, pruned_loss=0.02007, over 6295.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2482, pruned_loss=0.03302, over 1359042.69 frames.], batch size: 37, lr: 2.76e-04
2022-05-15 14:04:01,561 INFO [train.py:812] (4/8) Epoch 29, batch 0, loss[loss=0.1551, simple_loss=0.2484, pruned_loss=0.03095, over 7088.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2484, pruned_loss=0.03095, over 7088.00 frames.], batch size: 28, lr: 2.71e-04
2022-05-15 14:05:00,866 INFO [train.py:812] (4/8) Epoch 29, batch 50, loss[loss=0.1733, simple_loss=0.262, pruned_loss=0.04231, over 7290.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2481, pruned_loss=0.03271, over 323729.87 frames.], batch size: 24, lr: 2.71e-04
2022-05-15 14:05:59,926 INFO [train.py:812] (4/8) Epoch 29, batch 100, loss[loss=0.1789, simple_loss=0.268, pruned_loss=0.04489, over 7317.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2455, pruned_loss=0.0318, over 569664.10 frames.], batch size: 21, lr: 2.71e-04
2022-05-15 14:06:58,559 INFO [train.py:812] (4/8) Epoch 29, batch 150, loss[loss=0.1491, simple_loss=0.2373, pruned_loss=0.03049, over 7246.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.03158, over 760289.67 frames.], batch size: 20, lr: 2.71e-04
2022-05-15 14:07:56,836 INFO [train.py:812] (4/8) Epoch 29, batch 200, loss[loss=0.1518, simple_loss=0.2399, pruned_loss=0.0319, over 7063.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2448, pruned_loss=0.03093, over 908963.08 frames.], batch size: 18, lr: 2.71e-04
2022-05-15 14:08:56,090 INFO [train.py:812] (4/8) Epoch 29, batch 250, loss[loss=0.1708, simple_loss=0.2606, pruned_loss=0.04054, over 4876.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2451, pruned_loss=0.03118, over 1019693.45 frames.], batch size: 53, lr: 2.71e-04
2022-05-15 14:09:54,909 INFO [train.py:812] (4/8) Epoch 29, batch 300, loss[loss=0.1621, simple_loss=0.2562, pruned_loss=0.03401, over 7164.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2461, pruned_loss=0.03135, over 1109020.22 frames.], batch size: 18, lr: 2.70e-04
2022-05-15 14:10:53,108 INFO [train.py:812] (4/8) Epoch 29, batch 350, loss[loss=0.1342, simple_loss=0.223, pruned_loss=0.02274, over 7070.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2461, pruned_loss=0.03109, over 1180313.51 frames.], batch size: 18, lr: 2.70e-04
2022-05-15 14:11:51,406 INFO [train.py:812] (4/8) Epoch 29, batch 400, loss[loss=0.1499, simple_loss=0.2583, pruned_loss=0.02077, over 7141.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2464, pruned_loss=0.03111, over 1235358.18 frames.], batch size: 20, lr: 2.70e-04
2022-05-15 14:12:49,829 INFO [train.py:812] (4/8) Epoch 29, batch 450, loss[loss=0.1498, simple_loss=0.2558, pruned_loss=0.02186, over 7129.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2464, pruned_loss=0.03138, over 1280907.78 frames.], batch size: 21, lr: 2.70e-04
2022-05-15 14:13:47,252 INFO [train.py:812] (4/8) Epoch 29, batch 500, loss[loss=0.1899, simple_loss=0.2765, pruned_loss=0.05167, over 4646.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03169, over 1308677.27 frames.], batch size: 52, lr: 2.70e-04
2022-05-15 14:14:46,083 INFO [train.py:812] (4/8) Epoch 29, batch 550, loss[loss=0.1442, simple_loss=0.25, pruned_loss=0.0192, over 7227.00 frames.], tot_loss[loss=0.1553, simple_loss=0.247, pruned_loss=0.03185, over 1331344.43 frames.], batch size: 21, lr: 2.70e-04
2022-05-15 14:15:44,275 INFO [train.py:812] (4/8) Epoch 29, batch 600, loss[loss=0.1397, simple_loss=0.2341, pruned_loss=0.02261, over 7253.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2457, pruned_loss=0.03133, over 1349363.94 frames.], batch size: 19, lr: 2.70e-04
2022-05-15 14:16:43,617 INFO [train.py:812] (4/8) Epoch 29, batch 650, loss[loss=0.1547, simple_loss=0.2467, pruned_loss=0.03131, over 7459.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2455, pruned_loss=0.0313, over 1368121.09 frames.], batch size: 19, lr: 2.70e-04
2022-05-15 14:17:43,338 INFO [train.py:812] (4/8) Epoch 29, batch 700, loss[loss=0.1715, simple_loss=0.2506, pruned_loss=0.04623, over 5390.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2461, pruned_loss=0.03141, over 1376414.61 frames.], batch size: 53, lr: 2.70e-04
2022-05-15 14:18:41,549 INFO [train.py:812] (4/8) Epoch 29, batch 750, loss[loss=0.1325, simple_loss=0.2251, pruned_loss=0.01996, over 7443.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2456, pruned_loss=0.03115, over 1382946.14 frames.], batch size: 20, lr: 2.70e-04
2022-05-15 14:19:40,301 INFO [train.py:812] (4/8) Epoch 29, batch 800, loss[loss=0.1581, simple_loss=0.2502, pruned_loss=0.03302, over 7111.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2458, pruned_loss=0.03117, over 1388079.93 frames.], batch size: 21, lr: 2.70e-04
2022-05-15 14:20:39,291 INFO [train.py:812] (4/8) Epoch 29, batch 850, loss[loss=0.1679, simple_loss=0.2631, pruned_loss=0.03638, over 6259.00 frames.], tot_loss[loss=0.1544, simple_loss=0.246, pruned_loss=0.03138, over 1392618.83 frames.], batch size: 37, lr: 2.70e-04
2022-05-15 14:21:38,042 INFO [train.py:812] (4/8) Epoch 29, batch 900, loss[loss=0.1568, simple_loss=0.2529, pruned_loss=0.03038, over 6785.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.03113, over 1399100.19 frames.], batch size: 31, lr: 2.70e-04
2022-05-15 14:22:37,045 INFO [train.py:812] (4/8) Epoch 29, batch 950, loss[loss=0.1575, simple_loss=0.2576, pruned_loss=0.02863, over 7211.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2458, pruned_loss=0.03156, over 1408384.88 frames.], batch size: 22, lr: 2.70e-04
2022-05-15 14:23:36,641 INFO [train.py:812] (4/8) Epoch 29, batch 1000, loss[loss=0.134, simple_loss=0.212, pruned_loss=0.02804, over 6845.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2447, pruned_loss=0.03122, over 1414438.69 frames.], batch size: 15, lr: 2.70e-04
2022-05-15 14:24:36,149 INFO [train.py:812] (4/8) Epoch 29, batch 1050, loss[loss=0.1613, simple_loss=0.262, pruned_loss=0.03028, over 7402.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2454, pruned_loss=0.03114, over 1420028.61 frames.], batch size: 21, lr: 2.70e-04
2022-05-15 14:25:35,349 INFO [train.py:812] (4/8) Epoch 29, batch 1100, loss[loss=0.1339, simple_loss=0.2202, pruned_loss=0.02377, over 7285.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03117, over 1422454.53 frames.], batch size: 17, lr: 2.70e-04
2022-05-15 14:26:34,888 INFO [train.py:812] (4/8) Epoch 29, batch 1150, loss[loss=0.1488, simple_loss=0.2409, pruned_loss=0.0283, over 7133.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2455, pruned_loss=0.03149, over 1421159.38 frames.], batch size: 28, lr: 2.70e-04
2022-05-15 14:27:33,681 INFO [train.py:812] (4/8) Epoch 29, batch 1200, loss[loss=0.1538, simple_loss=0.2516, pruned_loss=0.02798, over 7131.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2469, pruned_loss=0.03159, over 1423442.86 frames.], batch size: 28, lr: 2.70e-04
2022-05-15 14:28:32,566 INFO [train.py:812] (4/8) Epoch 29, batch 1250, loss[loss=0.1838, simple_loss=0.2605, pruned_loss=0.05359, over 7204.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2465, pruned_loss=0.03168, over 1417039.95 frames.], batch size: 22, lr: 2.70e-04
2022-05-15 14:29:29,500 INFO [train.py:812] (4/8) Epoch 29, batch 1300, loss[loss=0.1704, simple_loss=0.2709, pruned_loss=0.03495, over 7147.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2464, pruned_loss=0.03165, over 1419147.51 frames.], batch size: 20, lr: 2.69e-04
2022-05-15 14:30:28,433 INFO [train.py:812] (4/8) Epoch 29, batch 1350, loss[loss=0.1568, simple_loss=0.2559, pruned_loss=0.02886, over 7114.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.03093, over 1425409.77 frames.], batch size: 21, lr: 2.69e-04
2022-05-15 14:31:27,378 INFO [train.py:812] (4/8) Epoch 29, batch 1400, loss[loss=0.1283, simple_loss=0.2179, pruned_loss=0.0194, over 7258.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2463, pruned_loss=0.03131, over 1426794.11 frames.], batch size: 17, lr: 2.69e-04
2022-05-15 14:32:26,335 INFO [train.py:812] (4/8) Epoch 29, batch 1450, loss[loss=0.1667, simple_loss=0.2562, pruned_loss=0.03855, over 7269.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2461, pruned_loss=0.03133, over 1430774.22 frames.], batch size: 24, lr: 2.69e-04
2022-05-15 14:33:24,396 INFO [train.py:812] (4/8) Epoch 29, batch 1500, loss[loss=0.1518, simple_loss=0.2464, pruned_loss=0.02863, over 7322.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2465, pruned_loss=0.03127, over 1427494.87 frames.], batch size: 20, lr: 2.69e-04
2022-05-15 14:34:23,840 INFO [train.py:812] (4/8) Epoch 29, batch 1550, loss[loss=0.153, simple_loss=0.2502, pruned_loss=0.02788, over 7222.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2467, pruned_loss=0.03117, over 1428606.71 frames.], batch size: 21, lr: 2.69e-04
2022-05-15 14:35:22,643 INFO [train.py:812] (4/8) Epoch 29, batch 1600, loss[loss=0.1409, simple_loss=0.2265, pruned_loss=0.02764, over 6819.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2468, pruned_loss=0.03095, over 1425885.98 frames.], batch size: 15, lr: 2.69e-04
2022-05-15 14:36:22,714 INFO [train.py:812] (4/8) Epoch 29, batch 1650, loss[loss=0.1424, simple_loss=0.2327, pruned_loss=0.0261, over 6834.00 frames.], tot_loss[loss=0.153, simple_loss=0.2451, pruned_loss=0.03049, over 1427437.58 frames.], batch size: 15, lr: 2.69e-04
2022-05-15 14:37:22,122 INFO [train.py:812] (4/8) Epoch 29, batch 1700, loss[loss=0.1357, simple_loss=0.2245, pruned_loss=0.02341, over 7274.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03078, over 1430184.25 frames.], batch size: 19, lr: 2.69e-04
2022-05-15 14:38:21,736 INFO [train.py:812] (4/8) Epoch 29, batch 1750, loss[loss=0.1517, simple_loss=0.247, pruned_loss=0.02813, over 7123.00 frames.], tot_loss[loss=0.1531, simple_loss=0.245, pruned_loss=0.03063, over 1432574.09 frames.], batch size: 21, lr: 2.69e-04
2022-05-15 14:39:20,866 INFO [train.py:812] (4/8) Epoch 29, batch 1800, loss[loss=0.1298, simple_loss=0.2064, pruned_loss=0.02658, over 7000.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03073, over 1422785.18 frames.], batch size: 16, lr: 2.69e-04
2022-05-15 14:40:20,286 INFO [train.py:812] (4/8) Epoch 29, batch 1850, loss[loss=0.1371, simple_loss=0.2251, pruned_loss=0.02454, over 7420.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2457, pruned_loss=0.03122, over 1425164.62 frames.], batch size: 18, lr: 2.69e-04
2022-05-15 14:41:18,744 INFO [train.py:812] (4/8) Epoch 29, batch 1900, loss[loss=0.169, simple_loss=0.2563, pruned_loss=0.04091, over 7223.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2451, pruned_loss=0.0311, over 1425650.85 frames.], batch size: 26, lr: 2.69e-04
2022-05-15 14:42:17,741 INFO [train.py:812] (4/8) Epoch 29, batch 1950, loss[loss=0.1591, simple_loss=0.2575, pruned_loss=0.03039, over 7309.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2448, pruned_loss=0.03082, over 1427969.72 frames.], batch size: 25, lr: 2.69e-04
2022-05-15 14:43:16,663 INFO [train.py:812] (4/8) Epoch 29, batch 2000, loss[loss=0.1721, simple_loss=0.261, pruned_loss=0.04159, over 7181.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2448, pruned_loss=0.03087, over 1431081.78 frames.], batch size: 23, lr: 2.69e-04
2022-05-15 14:44:14,140 INFO [train.py:812] (4/8) Epoch 29, batch 2050, loss[loss=0.1614, simple_loss=0.2561, pruned_loss=0.03338, over 7314.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2449, pruned_loss=0.03115, over 1424440.51 frames.], batch size: 21, lr: 2.69e-04
2022-05-15 14:45:11,932 INFO [train.py:812] (4/8) Epoch 29, batch 2100, loss[loss=0.1506, simple_loss=0.2456, pruned_loss=0.02778, over 7283.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2447, pruned_loss=0.03096, over 1426973.36 frames.], batch size: 25, lr: 2.69e-04
2022-05-15 14:46:11,712 INFO [train.py:812] (4/8) Epoch 29, batch 2150, loss[loss=0.1513, simple_loss=0.2541, pruned_loss=0.02426, over 7228.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2451, pruned_loss=0.03099, over 1427990.85 frames.], batch size: 21, lr: 2.69e-04
2022-05-15 14:47:09,930 INFO [train.py:812] (4/8) Epoch 29, batch 2200, loss[loss=0.1541, simple_loss=0.2522, pruned_loss=0.02796, over 7307.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2451, pruned_loss=0.03055, over 1422174.01 frames.], batch size: 25, lr: 2.69e-04
2022-05-15 14:48:08,318 INFO [train.py:812] (4/8) Epoch 29, batch 2250, loss[loss=0.1598, simple_loss=0.255, pruned_loss=0.03233, over 7107.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03075, over 1425652.83 frames.], batch size: 21, lr: 2.68e-04
2022-05-15 14:49:05,773 INFO [train.py:812] (4/8) Epoch 29, batch 2300, loss[loss=0.1492, simple_loss=0.2557, pruned_loss=0.02131, over 7276.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.03082, over 1427020.93 frames.], batch size: 24, lr: 2.68e-04
2022-05-15 14:50:03,896 INFO [train.py:812] (4/8) Epoch 29, batch 2350, loss[loss=0.1765, simple_loss=0.2676, pruned_loss=0.04274, over 7062.00 frames.], tot_loss[loss=0.1531, simple_loss=0.245, pruned_loss=0.03065, over 1424369.71 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 14:51:02,207 INFO [train.py:812] (4/8) Epoch 29, batch 2400, loss[loss=0.1394, simple_loss=0.2329, pruned_loss=0.023, over 7357.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2441, pruned_loss=0.03023, over 1426195.61 frames.], batch size: 19, lr: 2.68e-04
2022-05-15 14:51:59,594 INFO [train.py:812] (4/8) Epoch 29, batch 2450, loss[loss=0.1413, simple_loss=0.2358, pruned_loss=0.02337, over 7112.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03078, over 1416451.48 frames.], batch size: 21, lr: 2.68e-04
2022-05-15 14:52:57,614 INFO [train.py:812] (4/8) Epoch 29, batch 2500, loss[loss=0.1574, simple_loss=0.2402, pruned_loss=0.03727, over 7419.00 frames.], tot_loss[loss=0.153, simple_loss=0.2443, pruned_loss=0.03087, over 1419691.18 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 14:53:56,712 INFO [train.py:812] (4/8) Epoch 29, batch 2550, loss[loss=0.144, simple_loss=0.233, pruned_loss=0.0275, over 7152.00 frames.], tot_loss[loss=0.153, simple_loss=0.2443, pruned_loss=0.03083, over 1416920.70 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 14:54:55,314 INFO [train.py:812] (4/8) Epoch 29, batch 2600, loss[loss=0.1616, simple_loss=0.2563, pruned_loss=0.03346, over 7203.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2441, pruned_loss=0.03113, over 1415042.08 frames.], batch size: 23, lr: 2.68e-04
2022-05-15 14:56:04,286 INFO [train.py:812] (4/8) Epoch 29, batch 2650, loss[loss=0.1528, simple_loss=0.2402, pruned_loss=0.03276, over 7418.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2442, pruned_loss=0.03122, over 1418102.68 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 14:57:02,548 INFO [train.py:812] (4/8) Epoch 29, batch 2700, loss[loss=0.1599, simple_loss=0.2479, pruned_loss=0.03589, over 4967.00 frames.], tot_loss[loss=0.153, simple_loss=0.2436, pruned_loss=0.0312, over 1417990.29 frames.], batch size: 53, lr: 2.68e-04
2022-05-15 14:58:00,033 INFO [train.py:812] (4/8) Epoch 29, batch 2750, loss[loss=0.1784, simple_loss=0.2779, pruned_loss=0.03947, over 7313.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2446, pruned_loss=0.03156, over 1413647.84 frames.], batch size: 21, lr: 2.68e-04
2022-05-15 14:59:07,976 INFO [train.py:812] (4/8) Epoch 29, batch 2800, loss[loss=0.1375, simple_loss=0.2375, pruned_loss=0.0188, over 7334.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2453, pruned_loss=0.03126, over 1416845.16 frames.], batch size: 22, lr: 2.68e-04
2022-05-15 15:00:06,478 INFO [train.py:812] (4/8) Epoch 29, batch 2850, loss[loss=0.1504, simple_loss=0.2372, pruned_loss=0.03181, over 7251.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2453, pruned_loss=0.03129, over 1418001.04 frames.], batch size: 19, lr: 2.68e-04
2022-05-15 15:01:14,247 INFO [train.py:812] (4/8) Epoch 29, batch 2900, loss[loss=0.1509, simple_loss=0.2259, pruned_loss=0.03794, over 7257.00 frames.], tot_loss[loss=0.154, simple_loss=0.2452, pruned_loss=0.03134, over 1417683.63 frames.], batch size: 17, lr: 2.68e-04
2022-05-15 15:02:42,656 INFO [train.py:812] (4/8) Epoch 29, batch 2950, loss[loss=0.1143, simple_loss=0.1992, pruned_loss=0.01465, over 7138.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2444, pruned_loss=0.0313, over 1418443.57 frames.], batch size: 17, lr: 2.68e-04
2022-05-15 15:03:40,344 INFO [train.py:812] (4/8) Epoch 29, batch 3000, loss[loss=0.1457, simple_loss=0.2414, pruned_loss=0.02503, over 7239.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2448, pruned_loss=0.03086, over 1419514.56 frames.], batch size: 20, lr: 2.68e-04
2022-05-15 15:03:40,345 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 15:03:47,851 INFO [train.py:841] (4/8) Epoch 29, validation: loss=0.153, simple_loss=0.2498, pruned_loss=0.02809, over 698248.00 frames.
2022-05-15 15:04:46,873 INFO [train.py:812] (4/8) Epoch 29, batch 3050, loss[loss=0.1305, simple_loss=0.2188, pruned_loss=0.02107, over 7159.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2445, pruned_loss=0.03109, over 1422340.50 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 15:05:54,527 INFO [train.py:812] (4/8) Epoch 29, batch 3100, loss[loss=0.1399, simple_loss=0.2222, pruned_loss=0.02886, over 7282.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2443, pruned_loss=0.03113, over 1419576.73 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 15:06:53,598 INFO [train.py:812] (4/8) Epoch 29, batch 3150, loss[loss=0.1692, simple_loss=0.2681, pruned_loss=0.03515, over 7210.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2451, pruned_loss=0.03136, over 1423735.23 frames.], batch size: 21, lr: 2.68e-04
2022-05-15 15:07:52,380 INFO [train.py:812] (4/8) Epoch 29, batch 3200, loss[loss=0.1675, simple_loss=0.2604, pruned_loss=0.03728, over 7121.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2449, pruned_loss=0.03121, over 1423954.81 frames.], batch size: 21, lr: 2.68e-04
2022-05-15 15:08:52,067 INFO [train.py:812] (4/8) Epoch 29, batch 3250, loss[loss=0.16, simple_loss=0.2405, pruned_loss=0.03982, over 6809.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2446, pruned_loss=0.03114, over 1422951.72 frames.], batch size: 15, lr: 2.67e-04
2022-05-15 15:09:50,369 INFO [train.py:812] (4/8) Epoch 29, batch 3300, loss[loss=0.1492, simple_loss=0.2518, pruned_loss=0.0233, over 7213.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2464, pruned_loss=0.03175, over 1422344.96 frames.], batch size: 21, lr: 2.67e-04
2022-05-15 15:10:48,355 INFO [train.py:812] (4/8) Epoch 29, batch 3350, loss[loss=0.1738, simple_loss=0.2625, pruned_loss=0.04257, over 7015.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2459, pruned_loss=0.03166, over 1419575.25 frames.], batch size: 28, lr: 2.67e-04
2022-05-15 15:11:47,204 INFO [train.py:812] (4/8) Epoch 29, batch 3400, loss[loss=0.137, simple_loss=0.2216, pruned_loss=0.02617, over 7063.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03166, over 1418615.47 frames.], batch size: 18, lr: 2.67e-04
2022-05-15 15:12:46,915 INFO [train.py:812] (4/8) Epoch 29, batch 3450, loss[loss=0.1279, simple_loss=0.2161, pruned_loss=0.01986, over 7276.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2458, pruned_loss=0.03136, over 1420958.64 frames.], batch size: 17, lr: 2.67e-04
2022-05-15 15:13:45,911 INFO [train.py:812] (4/8) Epoch 29, batch 3500, loss[loss=0.1404, simple_loss=0.2377, pruned_loss=0.02154, over 6841.00 frames.], tot_loss[loss=0.153, simple_loss=0.2448, pruned_loss=0.03061, over 1420129.66 frames.], batch size: 31, lr: 2.67e-04
2022-05-15 15:14:51,719 INFO [train.py:812] (4/8) Epoch 29, batch 3550, loss[loss=0.1305, simple_loss=0.2136, pruned_loss=0.02369, over 7290.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2446, pruned_loss=0.03083, over 1423753.25 frames.], batch size: 18, lr: 2.67e-04
2022-05-15 15:15:51,036 INFO [train.py:812] (4/8) Epoch 29, batch 3600, loss[loss=0.1443, simple_loss=0.2302, pruned_loss=0.02919, over 6814.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2451, pruned_loss=0.03116, over 1424104.64 frames.], batch size: 15, lr: 2.67e-04
2022-05-15 15:16:50,757 INFO [train.py:812] (4/8) Epoch 29, batch 3650, loss[loss=0.174, simple_loss=0.2632, pruned_loss=0.04241, over 7339.00 frames.], tot_loss[loss=0.154, simple_loss=0.2452, pruned_loss=0.0314, over 1427375.59 frames.], batch size: 22, lr: 2.67e-04
2022-05-15 15:17:49,910 INFO [train.py:812] (4/8) Epoch 29, batch 3700, loss[loss=0.1829, simple_loss=0.2729, pruned_loss=0.04643, over 7200.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2454, pruned_loss=0.0316, over 1428316.27 frames.], batch size: 23, lr: 2.67e-04
2022-05-15 15:18:49,047 INFO [train.py:812] (4/8) Epoch 29, batch 3750, loss[loss=0.1841, simple_loss=0.2791, pruned_loss=0.04458, over 4892.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2455, pruned_loss=0.0314, over 1427374.48 frames.], batch size: 52, lr: 2.67e-04
2022-05-15 15:19:48,071 INFO [train.py:812] (4/8) Epoch 29, batch 3800, loss[loss=0.1387, simple_loss=0.2365, pruned_loss=0.02041, over 7431.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2455, pruned_loss=0.03136, over 1428048.87 frames.], batch size: 20, lr: 2.67e-04
2022-05-15 15:20:46,937 INFO [train.py:812] (4/8) Epoch 29, batch 3850, loss[loss=0.1778, simple_loss=0.2755, pruned_loss=0.04, over 7377.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2459, pruned_loss=0.03175, over 1428527.95 frames.], batch size: 23, lr: 2.67e-04
2022-05-15 15:21:44,962 INFO [train.py:812] (4/8) Epoch 29, batch 3900, loss[loss=0.1609, simple_loss=0.2503, pruned_loss=0.03572, over 7287.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2465, pruned_loss=0.03189, over 1431047.94 frames.], batch size: 24, lr: 2.67e-04
2022-05-15 15:22:44,169 INFO [train.py:812] (4/8) Epoch 29, batch 3950, loss[loss=0.1409, simple_loss=0.2299, pruned_loss=0.0259, over 7407.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2478, pruned_loss=0.03181, over 1432099.17 frames.], batch size: 18, lr: 2.67e-04
2022-05-15 15:23:43,017 INFO [train.py:812] (4/8) Epoch 29, batch 4000, loss[loss=0.1649, simple_loss=0.2625, pruned_loss=0.03368, over 7336.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2477, pruned_loss=0.03179, over 1431389.53 frames.], batch size: 22, lr: 2.67e-04
2022-05-15 15:24:42,290 INFO [train.py:812] (4/8) Epoch 29, batch 4050, loss[loss=0.135, simple_loss=0.225, pruned_loss=0.02255, over 7280.00 frames.], tot_loss[loss=0.156, simple_loss=0.2483, pruned_loss=0.0318, over 1430052.23 frames.], batch size: 17, lr: 2.67e-04
2022-05-15 15:25:40,975 INFO [train.py:812] (4/8) Epoch 29, batch 4100, loss[loss=0.1672, simple_loss=0.2655, pruned_loss=0.03447, over 7340.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2479, pruned_loss=0.03147, over 1430077.62 frames.], batch size: 22, lr: 2.67e-04
2022-05-15 15:26:40,404 INFO [train.py:812] (4/8) Epoch 29, batch 4150, loss[loss=0.1576, simple_loss=0.2546, pruned_loss=0.03032, over 7313.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2472, pruned_loss=0.03146, over 1423407.06 frames.], batch size: 21, lr: 2.67e-04
2022-05-15 15:27:39,253 INFO [train.py:812] (4/8) Epoch 29, batch 4200, loss[loss=0.1341, simple_loss=0.2247, pruned_loss=0.02173, over 7270.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2474, pruned_loss=0.03167, over 1420674.51 frames.], batch size: 19, lr: 2.66e-04
2022-05-15 15:28:38,674 INFO [train.py:812] (4/8) Epoch 29, batch 4250, loss[loss=0.159, simple_loss=0.2505, pruned_loss=0.03372, over 6761.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2463, pruned_loss=0.03119, over 1421150.00 frames.], batch size: 31, lr: 2.66e-04
2022-05-15 15:29:36,731 INFO [train.py:812] (4/8) Epoch 29, batch 4300, loss[loss=0.1491, simple_loss=0.2397, pruned_loss=0.02925, over 7172.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.03075, over 1417143.40 frames.], batch size: 18, lr: 2.66e-04
2022-05-15 15:30:35,688 INFO [train.py:812] (4/8) Epoch 29, batch 4350, loss[loss=0.1486, simple_loss=0.2467, pruned_loss=0.02524, over 7323.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2444, pruned_loss=0.03065, over 1418729.48 frames.], batch size: 21, lr: 2.66e-04
2022-05-15 15:31:34,531 INFO [train.py:812] (4/8) Epoch 29, batch 4400, loss[loss=0.1885, simple_loss=0.2813, pruned_loss=0.04785, over 7288.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03122, over 1410914.75 frames.], batch size: 24, lr: 2.66e-04
2022-05-15 15:32:33,470 INFO [train.py:812] (4/8) Epoch 29, batch 4450, loss[loss=0.1572, simple_loss=0.242, pruned_loss=0.03627, over 6459.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03119, over 1402458.26 frames.], batch size: 38, lr: 2.66e-04
2022-05-15 15:33:31,923 INFO [train.py:812] (4/8) Epoch 29, batch 4500, loss[loss=0.1765, simple_loss=0.2695, pruned_loss=0.04179, over 7217.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2461, pruned_loss=0.03167, over 1379920.45 frames.], batch size: 22, lr: 2.66e-04
2022-05-15 15:34:29,706 INFO [train.py:812] (4/8) Epoch 29, batch 4550, loss[loss=0.1501, simple_loss=0.2384, pruned_loss=0.03092, over 5127.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2478, pruned_loss=0.03241, over 1361342.91 frames.], batch size: 53, lr: 2.66e-04
2022-05-15 15:35:40,750 INFO [train.py:812] (4/8) Epoch 30, batch 0, loss[loss=0.1413, simple_loss=0.2335, pruned_loss=0.0245, over 7328.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2335, pruned_loss=0.0245, over 7328.00 frames.], batch size: 20, lr: 2.62e-04
2022-05-15 15:36:39,955 INFO [train.py:812] (4/8) Epoch 30, batch 50, loss[loss=0.1351, simple_loss=0.2311, pruned_loss=0.01952, over 7262.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2442, pruned_loss=0.02965, over 324155.40 frames.], batch size: 18, lr: 2.62e-04
2022-05-15 15:37:39,034 INFO [train.py:812] (4/8) Epoch 30, batch 100, loss[loss=0.1424, simple_loss=0.2267, pruned_loss=0.02908, over 7271.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03082, over 572277.78 frames.], batch size: 17, lr: 2.62e-04
2022-05-15 15:38:38,756 INFO [train.py:812] (4/8) Epoch 30, batch 150, loss[loss=0.1658, simple_loss=0.2622, pruned_loss=0.03468, over 7312.00 frames.], tot_loss[loss=0.1535, simple_loss=0.245, pruned_loss=0.031, over 750052.66 frames.], batch size: 24, lr: 2.62e-04
2022-05-15 15:39:36,194 INFO [train.py:812] (4/8) Epoch 30, batch 200, loss[loss=0.1507, simple_loss=0.2403, pruned_loss=0.03056, over 7365.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2445, pruned_loss=0.03091, over 899513.15 frames.], batch size: 19, lr: 2.61e-04
2022-05-15 15:40:35,792 INFO [train.py:812] (4/8) Epoch 30, batch 250, loss[loss=0.1413, simple_loss=0.2309, pruned_loss=0.02581, over 6773.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.03089, over 1015493.24 frames.], batch size: 15, lr: 2.61e-04
2022-05-15 15:41:34,906 INFO [train.py:812] (4/8) Epoch 30, batch 300, loss[loss=0.148, simple_loss=0.2363, pruned_loss=0.02983, over 7272.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2473, pruned_loss=0.03201, over 1107385.25 frames.], batch size: 18, lr: 2.61e-04
2022-05-15 15:42:33,924 INFO [train.py:812] (4/8) Epoch 30, batch 350, loss[loss=0.135, simple_loss=0.2254, pruned_loss=0.02226, over 7327.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2456, pruned_loss=0.03108, over 1180192.57 frames.], batch size: 20, lr: 2.61e-04
2022-05-15 15:43:32,167 INFO [train.py:812] (4/8) Epoch 30, batch 400, loss[loss=0.1565, simple_loss=0.2549, pruned_loss=0.02906, over 7288.00 frames.], tot_loss[loss=0.154, simple_loss=0.2461, pruned_loss=0.03097, over 1236496.55 frames.], batch size: 24, lr: 2.61e-04
2022-05-15 15:44:30,923 INFO [train.py:812] (4/8) Epoch 30, batch 450, loss[loss=0.149, simple_loss=0.2404, pruned_loss=0.02887, over 7421.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2445, pruned_loss=0.03068, over 1278461.30 frames.], batch size: 21, lr: 2.61e-04
2022-05-15 15:45:28,631 INFO [train.py:812] (4/8) Epoch 30, batch 500, loss[loss=0.1366, simple_loss=0.2339, pruned_loss=0.01958, over 7319.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2442, pruned_loss=0.03034, over 1307124.10 frames.], batch size: 20, lr: 2.61e-04
2022-05-15 15:46:27,337 INFO [train.py:812] (4/8) Epoch 30, batch 550, loss[loss=0.1661, simple_loss=0.2589, pruned_loss=0.03662, over 7292.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2451, pruned_loss=0.03077, over 1335188.74 frames.], batch size: 24, lr: 2.61e-04
2022-05-15 15:47:24,867 INFO [train.py:812] (4/8) Epoch 30, batch 600, loss[loss=0.1529, simple_loss=0.2407, pruned_loss=0.0325, over 7175.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03081, over 1351069.38 frames.], batch size: 22, lr: 2.61e-04
2022-05-15 15:48:22,460 INFO [train.py:812] (4/8) Epoch 30, batch 650, loss[loss=0.1527, simple_loss=0.2372, pruned_loss=0.03413, over 7070.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2448, pruned_loss=0.03092, over 1366098.67 frames.], batch size: 18, lr: 2.61e-04
2022-05-15 15:49:20,310 INFO [train.py:812] (4/8) Epoch 30, batch 700, loss[loss=0.1459, simple_loss=0.2363, pruned_loss=0.02778, over 7317.00 frames.], tot_loss[loss=0.1542, simple_loss=0.246, pruned_loss=0.03124, over 1375272.56 frames.], batch size: 20, lr: 2.61e-04
2022-05-15 15:50:18,872 INFO [train.py:812] (4/8) Epoch 30, batch 750, loss[loss=0.1568, simple_loss=0.2423, pruned_loss=0.03569, over 7236.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2463, pruned_loss=0.03152, over 1381902.96 frames.], batch size: 20, lr: 2.61e-04
2022-05-15 15:51:17,434 INFO [train.py:812] (4/8) Epoch 30, batch 800, loss[loss=0.1438, simple_loss=0.2352, pruned_loss=0.02614, over 7340.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.03112, over 1387825.66 frames.], batch size: 22, lr: 2.61e-04
2022-05-15 15:52:16,555 INFO [train.py:812] (4/8) Epoch 30, batch 850, loss[loss=0.1488, simple_loss=0.2485, pruned_loss=0.02459, over 7055.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2444, pruned_loss=0.03096, over 1396268.05 frames.], batch size: 18, lr: 2.61e-04
2022-05-15 15:53:14,196 INFO [train.py:812] (4/8) Epoch 30, batch 900, loss[loss=0.1626, simple_loss=0.2496, pruned_loss=0.03775, over 7213.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2449, pruned_loss=0.03108, over 1399545.88 frames.], batch size: 21, lr: 2.61e-04
2022-05-15 15:54:13,187 INFO [train.py:812] (4/8) Epoch 30, batch 950, loss[loss=0.1554, simple_loss=0.2535, pruned_loss=0.0286, over 7442.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2453, pruned_loss=0.03126, over 1405996.25 frames.], batch size: 22, lr: 2.61e-04
2022-05-15 15:55:11,577 INFO [train.py:812] (4/8) Epoch 30, batch 1000, loss[loss=0.1664, simple_loss=0.2535, pruned_loss=0.03961, over 7147.00 frames.], tot_loss[loss=0.1543, simple_loss=0.246, pruned_loss=0.03126, over 1410474.11 frames.], batch size: 20, lr: 2.61e-04
2022-05-15 15:56:10,080 INFO [train.py:812] (4/8) Epoch 30, batch 1050, loss[loss=0.1253, simple_loss=0.2093, pruned_loss=0.02063, over 7292.00 frames.], tot_loss[loss=0.154, simple_loss=0.2458, pruned_loss=0.03112, over 1407395.06 frames.], batch size: 18, lr: 2.61e-04
2022-05-15 15:57:08,267 INFO [train.py:812] (4/8) Epoch 30, batch 1100, loss[loss=0.1619, simple_loss=0.2571, pruned_loss=0.03338, over 7322.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2473, pruned_loss=0.03155, over 1416760.59 frames.], batch size: 21, lr: 2.61e-04
2022-05-15 15:58:07,685 INFO [train.py:812] (4/8) Epoch 30, batch 1150, loss[loss=0.1462, simple_loss=0.2221, pruned_loss=0.03511, over 7006.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2469, pruned_loss=0.03143, over 1417718.75 frames.], batch size: 16, lr: 2.61e-04
2022-05-15 15:59:06,101 INFO [train.py:812] (4/8) Epoch 30, batch 1200, loss[loss=0.1436, simple_loss=0.2313, pruned_loss=0.02791, over 7141.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2462, pruned_loss=0.03099, over 1422466.17 frames.], batch size: 19, lr: 2.61e-04
2022-05-15 16:00:14,956 INFO [train.py:812] (4/8) Epoch 30, batch 1250, loss[loss=0.1801, simple_loss=0.2713, pruned_loss=0.04445, over 4956.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2457, pruned_loss=0.03131, over 1417935.62 frames.], batch size: 52, lr: 2.60e-04
2022-05-15 16:01:13,728 INFO [train.py:812] (4/8) Epoch 30, batch 1300, loss[loss=0.1577, simple_loss=0.2454, pruned_loss=0.03502, over 7338.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2456, pruned_loss=0.03111, over 1419032.60 frames.], batch size: 22, lr: 2.60e-04
2022-05-15 16:02:13,400 INFO [train.py:812] (4/8) Epoch 30, batch 1350, loss[loss=0.1553, simple_loss=0.2448, pruned_loss=0.03293, over 6701.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2461, pruned_loss=0.03143, over 1419669.16 frames.], batch size: 38, lr: 2.60e-04
2022-05-15 16:03:12,428 INFO [train.py:812] (4/8) Epoch 30, batch 1400, loss[loss=0.1478, simple_loss=0.2352, pruned_loss=0.03014, over 6861.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2455, pruned_loss=0.03141, over 1420012.71 frames.], batch size: 15, lr: 2.60e-04
2022-05-15 16:04:10,789 INFO [train.py:812] (4/8) Epoch 30, batch 1450, loss[loss=0.1536, simple_loss=0.2506, pruned_loss=0.0283, over 7102.00 frames.], tot_loss[loss=0.154, simple_loss=0.2454, pruned_loss=0.03126, over 1418136.16 frames.], batch size: 21, lr: 2.60e-04
2022-05-15 16:05:09,048 INFO [train.py:812] (4/8) Epoch 30, batch 1500, loss[loss=0.1367, simple_loss=0.2316, pruned_loss=0.02085, over 7261.00 frames.], tot_loss[loss=0.154, simple_loss=0.2458, pruned_loss=0.03112, over 1417000.17 frames.], batch size: 19, lr: 2.60e-04
2022-05-15 16:06:06,406 INFO [train.py:812] (4/8) Epoch 30, batch 1550, loss[loss=0.1732, simple_loss=0.257, pruned_loss=0.04466, over 7219.00 frames.], tot_loss[loss=0.1541, simple_loss=0.246, pruned_loss=0.03107, over 1418252.69 frames.], batch size: 23, lr: 2.60e-04
2022-05-15 16:07:03,151 INFO [train.py:812] (4/8) Epoch 30, batch 1600, loss[loss=0.1611, simple_loss=0.2529, pruned_loss=0.03461, over 7322.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2465, pruned_loss=0.03129, over 1419789.83 frames.], batch size: 21, lr: 2.60e-04
2022-05-15 16:08:02,733 INFO [train.py:812] (4/8) Epoch 30, batch 1650, loss[loss=0.1744, simple_loss=0.2714, pruned_loss=0.03871, over 7166.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2457, pruned_loss=0.03089, over 1424067.16 frames.], batch size: 26, lr: 2.60e-04
2022-05-15 16:09:00,137 INFO [train.py:812] (4/8) Epoch 30, batch 1700, loss[loss=0.1734, simple_loss=0.2697, pruned_loss=0.03857, over 7143.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2458, pruned_loss=0.03082, over 1426125.21 frames.], batch size: 17, lr: 2.60e-04
2022-05-15 16:09:58,749 INFO [train.py:812] (4/8) Epoch 30, batch 1750, loss[loss=0.1492, simple_loss=0.2515, pruned_loss=0.02342, over 7149.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2454, pruned_loss=0.03062, over 1421751.57 frames.], batch size: 20, lr: 2.60e-04
2022-05-15 16:10:56,861 INFO [train.py:812] (4/8) Epoch 30, batch 1800, loss[loss=0.2169, simple_loss=0.2994, pruned_loss=0.06724, over 4938.00 frames.], tot_loss[loss=0.1542, simple_loss=0.246, pruned_loss=0.03122, over 1418941.88 frames.], batch size: 52, lr: 2.60e-04
2022-05-15 16:11:55,155 INFO [train.py:812] (4/8) Epoch 30, batch 1850, loss[loss=0.177, simple_loss=0.271, pruned_loss=0.0415, over 7116.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2462, pruned_loss=0.03123, over 1423527.42 frames.], batch size: 21, lr: 2.60e-04
2022-05-15 16:12:53,270 INFO [train.py:812] (4/8) Epoch 30, batch 1900, loss[loss=0.1346, simple_loss=0.2164, pruned_loss=0.02644, over 7228.00 frames.], tot_loss[loss=0.1544, simple_loss=0.246, pruned_loss=0.03136, over 1426016.65 frames.], batch size: 16, lr: 2.60e-04
2022-05-15 16:13:52,790 INFO [train.py:812] (4/8) Epoch 30, batch 1950, loss[loss=0.1274, simple_loss=0.2091, pruned_loss=0.02289, over 7268.00 frames.], tot_loss[loss=0.154, simple_loss=0.2456, pruned_loss=0.03126, over 1428148.56 frames.], batch size: 17, lr: 2.60e-04
2022-05-15 16:14:51,459 INFO [train.py:812] (4/8) Epoch 30, batch 2000, loss[loss=0.1293, simple_loss=0.2361, pruned_loss=0.01127, over 7342.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2456, pruned_loss=0.03099, over 1430623.42 frames.], batch size: 22, lr: 2.60e-04
2022-05-15 16:15:50,925 INFO [train.py:812] (4/8) Epoch 30, batch 2050, loss[loss=0.1871, simple_loss=0.2775, pruned_loss=0.0484, over 7211.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2453, pruned_loss=0.03066, over 1430929.81 frames.], batch size: 23, lr: 2.60e-04
2022-05-15 16:16:49,866 INFO [train.py:812] (4/8) Epoch 30, batch 2100, loss[loss=0.1469, simple_loss=0.2549, pruned_loss=0.01944, over 7145.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2454, pruned_loss=0.03063, over 1430883.84 frames.], batch size: 20, lr: 2.60e-04
2022-05-15 16:17:48,136 INFO [train.py:812] (4/8) Epoch 30, batch 2150, loss[loss=0.1643, simple_loss=0.2472, pruned_loss=0.04068, over 7116.00 frames.], tot_loss[loss=0.153, simple_loss=0.2451, pruned_loss=0.03049, over 1430061.62 frames.], batch size: 17, lr: 2.60e-04
2022-05-15 16:18:47,070 INFO [train.py:812] (4/8) Epoch 30, batch 2200, loss[loss=0.1673, simple_loss=0.2582, pruned_loss=0.03814, over 7298.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2448, pruned_loss=0.03046, over 1424345.23 frames.], batch size: 24, lr: 2.60e-04
2022-05-15 16:19:45,895 INFO [train.py:812] (4/8) Epoch 30, batch 2250, loss[loss=0.1699, simple_loss=0.2617, pruned_loss=0.03904, over 7235.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2453, pruned_loss=0.03092, over 1422542.89 frames.], batch size: 26, lr: 2.59e-04
2022-05-15 16:20:43,590 INFO [train.py:812] (4/8) Epoch 30, batch 2300, loss[loss=0.1234, simple_loss=0.2187, pruned_loss=0.01404, over 7327.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2457, pruned_loss=0.03069, over 1419779.32 frames.], batch size: 20, lr: 2.59e-04
2022-05-15 16:21:42,628 INFO [train.py:812] (4/8) Epoch 30, batch 2350, loss[loss=0.174, simple_loss=0.2715, pruned_loss=0.03822, over 7341.00 frames.], tot_loss[loss=0.153, simple_loss=0.2451, pruned_loss=0.03049, over 1421019.46 frames.], batch size: 22, lr: 2.59e-04
2022-05-15 16:22:41,687 INFO [train.py:812] (4/8) Epoch 30, batch 2400, loss[loss=0.1544, simple_loss=0.2535, pruned_loss=0.02768, over 7323.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2457, pruned_loss=0.03074, over 1422827.24 frames.], batch size: 25, lr: 2.59e-04
2022-05-15 16:23:41,332 INFO [train.py:812] (4/8) Epoch 30, batch 2450, loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.02998, over 7133.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03016, over 1427487.60 frames.], batch size: 20, lr: 2.59e-04
2022-05-15 16:24:39,658 INFO [train.py:812] (4/8) Epoch 30, batch 2500, loss[loss=0.1398, simple_loss=0.224, pruned_loss=0.0278, over 6808.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.02992, over 1430763.27 frames.], batch size: 15, lr: 2.59e-04
2022-05-15 16:25:38,970 INFO [train.py:812] (4/8) Epoch 30, batch 2550, loss[loss=0.1282, simple_loss=0.2131, pruned_loss=0.02165, over 7415.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02993, over 1427433.36 frames.], batch size: 18, lr: 2.59e-04
2022-05-15 16:26:37,725 INFO [train.py:812] (4/8) Epoch 30, batch 2600, loss[loss=0.147, simple_loss=0.2404, pruned_loss=0.02684, over 7114.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02983, over 1426745.51 frames.], batch size: 21, lr: 2.59e-04
2022-05-15 16:27:37,239 INFO [train.py:812] (4/8) Epoch 30, batch 2650, loss[loss=0.1428, simple_loss=0.2294, pruned_loss=0.02815, over 7155.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2436, pruned_loss=0.03008, over 1428624.13 frames.], batch size: 17, lr: 2.59e-04
2022-05-15 16:28:36,177 INFO [train.py:812] (4/8) Epoch 30, batch 2700, loss[loss=0.1372, simple_loss=0.2352, pruned_loss=0.01958, over 7123.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2444, pruned_loss=0.03035, over 1429527.56 frames.], batch size: 21, lr: 2.59e-04
2022-05-15 16:29:34,401 INFO [train.py:812] (4/8) Epoch 30, batch 2750, loss[loss=0.1685, simple_loss=0.255, pruned_loss=0.04101, over 7229.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2452, pruned_loss=0.03064, over 1425234.62 frames.], batch size: 20, lr: 2.59e-04
2022-05-15 16:30:32,051 INFO [train.py:812] (4/8) Epoch 30, batch 2800, loss[loss=0.142, simple_loss=0.2414, pruned_loss=0.02127, over 7346.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2454, pruned_loss=0.03079, over 1425314.21 frames.], batch size: 22, lr: 2.59e-04
2022-05-15 16:31:31,638 INFO [train.py:812] (4/8) Epoch 30, batch 2850, loss[loss=0.1661, simple_loss=0.2577, pruned_loss=0.03724, over 7227.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2449, pruned_loss=0.0309, over 1419414.57 frames.], batch size: 20, lr: 2.59e-04
2022-05-15 16:32:29,827 INFO [train.py:812] (4/8) Epoch 30, batch 2900, loss[loss=0.127, simple_loss=0.2138, pruned_loss=0.02009, over 7000.00 frames.], tot_loss[loss=0.1528, simple_loss=0.244, pruned_loss=0.03078, over 1421955.13 frames.], batch size: 16, lr: 2.59e-04
2022-05-15 16:33:36,390 INFO [train.py:812] (4/8) Epoch 30, batch 2950, loss[loss=0.1449, simple_loss=0.2443, pruned_loss=0.02275, over 6455.00 frames.], tot_loss[loss=0.152, simple_loss=0.2432, pruned_loss=0.03037, over 1423389.81 frames.], batch size: 38, lr: 2.59e-04
2022-05-15 16:34:35,500 INFO [train.py:812] (4/8) Epoch 30, batch 3000, loss[loss=0.1327, simple_loss=0.2318, pruned_loss=0.01676, over 7106.00 frames.], tot_loss[loss=0.152, simple_loss=0.2432, pruned_loss=0.03036, over 1425643.16 frames.], batch size: 21, lr: 2.59e-04
2022-05-15 16:34:35,501 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 16:34:43,057 INFO [train.py:841] (4/8) Epoch 30, validation: loss=0.1528, simple_loss=0.2494, pruned_loss=0.02809, over 698248.00 frames.
2022-05-15 16:35:41,824 INFO [train.py:812] (4/8) Epoch 30, batch 3050, loss[loss=0.1654, simple_loss=0.263, pruned_loss=0.0339, over 7121.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.03055, over 1427111.34 frames.], batch size: 21, lr: 2.59e-04
2022-05-15 16:36:40,855 INFO [train.py:812] (4/8) Epoch 30, batch 3100, loss[loss=0.1644, simple_loss=0.2605, pruned_loss=0.03415, over 7410.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03068, over 1427576.46 frames.], batch size: 21, lr: 2.59e-04
2022-05-15 16:37:40,501 INFO [train.py:812] (4/8) Epoch 30, batch 3150, loss[loss=0.1717, simple_loss=0.2518, pruned_loss=0.04584, over 7157.00 frames.], tot_loss[loss=0.1525, simple_loss=0.244, pruned_loss=0.03049, over 1422688.14 frames.], batch size: 18, lr: 2.59e-04
2022-05-15 16:38:39,685 INFO [train.py:812] (4/8) Epoch 30, batch 3200, loss[loss=0.1657, simple_loss=0.2584, pruned_loss=0.03645, over 7265.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2434, pruned_loss=0.03044, over 1425925.77 frames.], batch size: 19, lr: 2.59e-04
2022-05-15 16:39:38,878 INFO [train.py:812] (4/8) Epoch 30, batch 3250, loss[loss=0.1639, simple_loss=0.2642, pruned_loss=0.03184, over 7060.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2436, pruned_loss=0.0305, over 1421167.34 frames.], batch size: 28, lr: 2.59e-04
2022-05-15 16:40:36,549 INFO [train.py:812] (4/8) Epoch 30, batch 3300, loss[loss=0.1379, simple_loss=0.2389, pruned_loss=0.01843, over 7337.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2436, pruned_loss=0.0304, over 1424157.38 frames.], batch size: 20, lr: 2.58e-04
2022-05-15 16:41:35,377 INFO [train.py:812] (4/8) Epoch 30, batch 3350, loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03217, over 7281.00 frames.], tot_loss[loss=0.152, simple_loss=0.2433, pruned_loss=0.03038, over 1428281.76 frames.], batch size: 17, lr: 2.58e-04
2022-05-15 16:42:33,352 INFO [train.py:812] (4/8) Epoch 30, batch 3400, loss[loss=0.1711, simple_loss=0.2527, pruned_loss=0.04478, over 5279.00 frames.], tot_loss[loss=0.1516, simple_loss=0.243, pruned_loss=0.03011, over 1424950.18 frames.], batch size: 52, lr: 2.58e-04
2022-05-15 16:43:31,882 INFO [train.py:812] (4/8) Epoch 30, batch 3450, loss[loss=0.1718, simple_loss=0.2702, pruned_loss=0.03669, over 7291.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2435, pruned_loss=0.03062, over 1420905.69 frames.], batch size: 24, lr: 2.58e-04
2022-05-15 16:44:30,303 INFO [train.py:812] (4/8) Epoch 30, batch 3500, loss[loss=0.1929, simple_loss=0.2978, pruned_loss=0.04403, over 7207.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2446, pruned_loss=0.03083, over 1423381.07 frames.], batch size: 26, lr: 2.58e-04
2022-05-15 16:45:29,361 INFO [train.py:812] (4/8) Epoch 30, batch 3550, loss[loss=0.148, simple_loss=0.2321, pruned_loss=0.03196, over 7169.00 frames.], tot_loss[loss=0.1523, simple_loss=0.244, pruned_loss=0.03025, over 1423198.89 frames.], batch size: 18, lr: 2.58e-04
2022-05-15 16:46:28,174 INFO [train.py:812] (4/8) Epoch 30, batch 3600, loss[loss=0.1428, simple_loss=0.2338, pruned_loss=0.02587, over 7263.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.0301, over 1427276.24 frames.], batch size: 19, lr: 2.58e-04
2022-05-15 16:47:27,377 INFO [train.py:812] (4/8) Epoch 30, batch 3650, loss[loss=0.1644, simple_loss=0.2588, pruned_loss=0.03503, over 6749.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2446, pruned_loss=0.03053, over 1428797.83 frames.], batch size: 31, lr: 2.58e-04
2022-05-15 16:48:25,020 INFO [train.py:812] (4/8) Epoch 30, batch 3700, loss[loss=0.1305, simple_loss=0.2182, pruned_loss=0.0214, over 7275.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2448, pruned_loss=0.03053, over 1429471.84 frames.], batch size: 17, lr: 2.58e-04
2022-05-15 16:49:23,815 INFO [train.py:812] (4/8) Epoch 30, batch 3750, loss[loss=0.1594, simple_loss=0.2695, pruned_loss=0.02466, over 7087.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2455, pruned_loss=0.03052, over 1432182.03 frames.], batch size: 28, lr: 2.58e-04
2022-05-15 16:50:21,258 INFO [train.py:812] (4/8) Epoch 30, batch 3800, loss[loss=0.1744, simple_loss=0.273, pruned_loss=0.03789, over 7219.00 frames.], tot_loss[loss=0.154, simple_loss=0.2462, pruned_loss=0.03089, over 1425106.63 frames.], batch size: 22, lr: 2.58e-04
2022-05-15 16:51:18,888 INFO [train.py:812] (4/8) Epoch 30, batch 3850, loss[loss=0.1393, simple_loss=0.2176, pruned_loss=0.03048, over 6778.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.03019, over 1425841.26 frames.], batch size: 15, lr: 2.58e-04
2022-05-15 16:52:16,802 INFO [train.py:812] (4/8) Epoch 30, batch 3900, loss[loss=0.1284, simple_loss=0.2128, pruned_loss=0.02198, over 7145.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.03055, over 1425958.27 frames.], batch size: 17, lr: 2.58e-04
2022-05-15 16:53:15,077 INFO [train.py:812] (4/8) Epoch 30, batch 3950, loss[loss=0.1587, simple_loss=0.264, pruned_loss=0.02676, over 7383.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2463, pruned_loss=0.03095, over 1420774.28 frames.], batch size: 23, lr: 2.58e-04
2022-05-15 16:54:13,800 INFO [train.py:812] (4/8) Epoch 30, batch 4000, loss[loss=0.1544, simple_loss=0.2516, pruned_loss=0.02862, over 7301.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2471, pruned_loss=0.03123, over 1418599.98 frames.], batch size: 25, lr: 2.58e-04
2022-05-15 16:55:12,880 INFO [train.py:812] (4/8) Epoch 30, batch 4050, loss[loss=0.1594, simple_loss=0.2592, pruned_loss=0.02986, over 7044.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2465, pruned_loss=0.03138, over 1419188.67 frames.], batch size: 28, lr: 2.58e-04
2022-05-15 16:56:10,888 INFO [train.py:812] (4/8) Epoch 30, batch 4100, loss[loss=0.1715, simple_loss=0.271, pruned_loss=0.036, over 7317.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.03158, over 1420740.51 frames.], batch size: 21, lr: 2.58e-04
2022-05-15 16:57:19,274 INFO [train.py:812] (4/8) Epoch 30, batch 4150, loss[loss=0.1546, simple_loss=0.2487, pruned_loss=0.03027, over 7228.00 frames.], tot_loss[loss=0.154, simple_loss=0.2455, pruned_loss=0.03124, over 1420852.04 frames.], batch size: 21, lr: 2.58e-04
2022-05-15 16:58:17,927 INFO [train.py:812] (4/8) Epoch 30, batch 4200, loss[loss=0.1373, simple_loss=0.2316, pruned_loss=0.02149, over 7416.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2456, pruned_loss=0.03129, over 1421696.84 frames.], batch size: 20, lr: 2.58e-04
2022-05-15 16:59:24,885 INFO [train.py:812] (4/8) Epoch 30, batch 4250, loss[loss=0.1562, simple_loss=0.2563, pruned_loss=0.02805, over 7371.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2473, pruned_loss=0.03157, over 1415638.79 frames.], batch size: 23, lr: 2.58e-04
2022-05-15 17:00:23,129 INFO [train.py:812] (4/8) Epoch 30, batch 4300, loss[loss=0.1343, simple_loss=0.2163, pruned_loss=0.02615, over 7303.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2464, pruned_loss=0.03131, over 1419265.30 frames.], batch size: 17, lr: 2.58e-04
2022-05-15 17:01:31,704 INFO [train.py:812] (4/8) Epoch 30, batch 4350, loss[loss=0.1531, simple_loss=0.2442, pruned_loss=0.03099, over 7242.00 frames.], tot_loss[loss=0.1545, simple_loss=0.246, pruned_loss=0.03155, over 1421597.60 frames.], batch size: 20, lr: 2.58e-04
2022-05-15 17:02:30,815 INFO [train.py:812] (4/8) Epoch 30, batch 4400, loss[loss=0.1576, simple_loss=0.2521, pruned_loss=0.03157, over 7234.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.03085, over 1417828.76 frames.], batch size: 20, lr: 2.57e-04
2022-05-15 17:03:47,891 INFO [train.py:812] (4/8) Epoch 30, batch 4450, loss[loss=0.1532, simple_loss=0.2471, pruned_loss=0.02966, over 6185.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2443, pruned_loss=0.03055, over 1412237.69 frames.], batch size: 37, lr: 2.57e-04
2022-05-15 17:04:54,633 INFO [train.py:812] (4/8) Epoch 30, batch 4500, loss[loss=0.2049, simple_loss=0.2812, pruned_loss=0.06429, over 5165.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03085, over 1397055.23 frames.], batch size: 52, lr: 2.57e-04
2022-05-15 17:05:52,213 INFO [train.py:812] (4/8) Epoch 30, batch 4550, loss[loss=0.176, simple_loss=0.256, pruned_loss=0.04795, over 5033.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2472, pruned_loss=0.03185, over 1357056.87 frames.], batch size: 53, lr: 2.57e-04
2022-05-15 17:07:08,081 INFO [train.py:812] (4/8) Epoch 31, batch 0, loss[loss=0.1254, simple_loss=0.2105, pruned_loss=0.02019, over 7329.00 frames.], tot_loss[loss=0.1254, simple_loss=0.2105, pruned_loss=0.02019, over 7329.00 frames.], batch size: 20, lr: 2.53e-04
2022-05-15 17:08:07,415 INFO [train.py:812] (4/8) Epoch 31, batch 50, loss[loss=0.1498, simple_loss=0.248, pruned_loss=0.02578, over 7264.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2465, pruned_loss=0.03195, over 316384.33 frames.], batch size: 19, lr: 2.53e-04
2022-05-15 17:09:06,198 INFO [train.py:812] (4/8) Epoch 31, batch 100, loss[loss=0.1623, simple_loss=0.2576, pruned_loss=0.03355, over 7390.00 frames.], tot_loss[loss=0.155, simple_loss=0.2466, pruned_loss=0.03164, over 560676.50 frames.], batch size: 23, lr: 2.53e-04
2022-05-15 17:10:05,003 INFO [train.py:812] (4/8) Epoch 31, batch 150, loss[loss=0.1476, simple_loss=0.2476, pruned_loss=0.02377, over 7203.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2461, pruned_loss=0.03207, over 755563.67 frames.], batch size: 22, lr: 2.53e-04
2022-05-15 17:11:03,894 INFO [train.py:812] (4/8) Epoch 31, batch 200, loss[loss=0.1905, simple_loss=0.2682, pruned_loss=0.05636, over 5378.00 frames.], tot_loss[loss=0.1541, simple_loss=0.245, pruned_loss=0.03166, over 901112.20 frames.], batch size: 52, lr: 2.53e-04
2022-05-15 17:12:02,400 INFO [train.py:812] (4/8) Epoch 31, batch 250, loss[loss=0.1521, simple_loss=0.2469, pruned_loss=0.02866, over 7304.00 frames.], tot_loss[loss=0.155, simple_loss=0.2467, pruned_loss=0.03165, over 1015909.04 frames.], batch size: 25, lr: 2.53e-04
2022-05-15 17:13:01,769 INFO [train.py:812] (4/8) Epoch 31, batch 300, loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02994, over 7320.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2466, pruned_loss=0.03158, over 1108251.26 frames.], batch size: 21, lr: 2.53e-04
2022-05-15 17:13:59,729 INFO [train.py:812] (4/8) Epoch 31, batch 350, loss[loss=0.1627, simple_loss=0.2546, pruned_loss=0.03537, over 7167.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2465, pruned_loss=0.03171, over 1175595.04 frames.], batch size: 18, lr: 2.53e-04
2022-05-15 17:14:57,263 INFO [train.py:812] (4/8) Epoch 31, batch 400, loss[loss=0.1533, simple_loss=0.2531, pruned_loss=0.02669, over 7219.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2464, pruned_loss=0.03161, over 1226631.51 frames.], batch size: 21, lr: 2.53e-04
2022-05-15 17:15:56,104 INFO [train.py:812] (4/8) Epoch 31, batch 450, loss[loss=0.1704, simple_loss=0.2607, pruned_loss=0.04005, over 7173.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2473, pruned_loss=0.03167, over 1268039.61 frames.], batch size: 26, lr: 2.53e-04
2022-05-15 17:16:55,571 INFO [train.py:812] (4/8) Epoch 31, batch 500, loss[loss=0.1233, simple_loss=0.2093, pruned_loss=0.01864, over 7275.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2461, pruned_loss=0.03125, over 1302524.38 frames.], batch size: 17, lr: 2.53e-04
2022-05-15 17:17:54,445 INFO [train.py:812] (4/8) Epoch 31, batch 550, loss[loss=0.1481, simple_loss=0.2467, pruned_loss=0.02477, over 7413.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2466, pruned_loss=0.03123, over 1329249.19 frames.], batch size: 21, lr: 2.53e-04
2022-05-15 17:18:53,062 INFO [train.py:812] (4/8) Epoch 31, batch 600, loss[loss=0.1504, simple_loss=0.2312, pruned_loss=0.03477, over 7075.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2472, pruned_loss=0.03134, over 1348392.77 frames.], batch size: 18, lr: 2.53e-04
2022-05-15 17:19:50,590 INFO [train.py:812] (4/8) Epoch 31, batch 650, loss[loss=0.1693, simple_loss=0.2573, pruned_loss=0.04065, over 7151.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2464, pruned_loss=0.03109, over 1369595.77 frames.], batch size: 20, lr: 2.53e-04
2022-05-15 17:20:49,367 INFO [train.py:812] (4/8) Epoch 31, batch 700, loss[loss=0.1209, simple_loss=0.2056, pruned_loss=0.01816, over 7208.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2459, pruned_loss=0.03093, over 1379978.14 frames.], batch size: 16, lr: 2.52e-04
2022-05-15 17:21:47,385 INFO [train.py:812] (4/8) Epoch 31, batch 750, loss[loss=0.1612, simple_loss=0.2476, pruned_loss=0.03735, over 7244.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2455, pruned_loss=0.03074, over 1387339.69 frames.], batch size: 20, lr: 2.52e-04
2022-05-15 17:22:46,127 INFO [train.py:812] (4/8) Epoch 31, batch 800, loss[loss=0.1331, simple_loss=0.2263, pruned_loss=0.01997, over 7321.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2457, pruned_loss=0.03096, over 1395216.46 frames.], batch size: 20, lr: 2.52e-04
2022-05-15 17:23:44,748 INFO [train.py:812] (4/8) Epoch 31, batch 850, loss[loss=0.1603, simple_loss=0.2508, pruned_loss=0.03487, over 7415.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03016, over 1399920.61 frames.], batch size: 20, lr: 2.52e-04
2022-05-15 17:24:43,304 INFO [train.py:812] (4/8) Epoch 31, batch 900, loss[loss=0.1257, simple_loss=0.2098, pruned_loss=0.02076, over 7232.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2433, pruned_loss=0.03005, over 1404753.59 frames.], batch size: 16, lr: 2.52e-04
2022-05-15 17:25:42,286 INFO [train.py:812] (4/8) Epoch 31, batch 950, loss[loss=0.1418, simple_loss=0.2377, pruned_loss=0.02294, over 7037.00 frames.], tot_loss[loss=0.152, simple_loss=0.2434, pruned_loss=0.03035, over 1406330.23 frames.], batch size: 28, lr: 2.52e-04
2022-05-15 17:26:41,337 INFO [train.py:812] (4/8) Epoch 31, batch 1000, loss[loss=0.1425, simple_loss=0.2417, pruned_loss=0.02167, over 7334.00 frames.], tot_loss[loss=0.152, simple_loss=0.2435, pruned_loss=0.0302, over 1409005.11 frames.], batch size: 22, lr: 2.52e-04
2022-05-15 17:27:40,601 INFO [train.py:812] (4/8) Epoch 31, batch 1050, loss[loss=0.1485, simple_loss=0.2481, pruned_loss=0.02445, over 7043.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2439, pruned_loss=0.03026, over 1410565.85 frames.], batch size: 28, lr: 2.52e-04
2022-05-15 17:28:39,410 INFO [train.py:812] (4/8) Epoch 31, batch 1100, loss[loss=0.1536, simple_loss=0.2475, pruned_loss=0.02981, over 7067.00 frames.], tot_loss[loss=0.1522, simple_loss=0.244, pruned_loss=0.03015, over 1415875.52 frames.], batch size: 18, lr: 2.52e-04
2022-05-15 17:29:38,123 INFO [train.py:812] (4/8) Epoch 31, batch 1150, loss[loss=0.1403, simple_loss=0.2272, pruned_loss=0.02666, over 7061.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2429, pruned_loss=0.02999, over 1417531.00 frames.], batch size: 18, lr: 2.52e-04
2022-05-15 17:30:36,862 INFO [train.py:812] (4/8) Epoch 31, batch 1200, loss[loss=0.1904, simple_loss=0.2826, pruned_loss=0.04904, over 7202.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2431, pruned_loss=0.03003, over 1418856.08 frames.], batch size: 22, lr: 2.52e-04
2022-05-15 17:31:36,148 INFO [train.py:812] (4/8) Epoch 31, batch 1250, loss[loss=0.1411, simple_loss=0.2301, pruned_loss=0.02606, over 7404.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2436, pruned_loss=0.03012, over 1417872.76 frames.], batch size: 18, lr: 2.52e-04
2022-05-15 17:32:35,755 INFO [train.py:812] (4/8) Epoch 31, batch 1300, loss[loss=0.1602, simple_loss=0.2541, pruned_loss=0.03318, over 7199.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2435, pruned_loss=0.03017, over 1417924.42 frames.], batch size: 26, lr: 2.52e-04
2022-05-15 17:33:34,082 INFO [train.py:812] (4/8) Epoch 31, batch 1350, loss[loss=0.1369, simple_loss=0.2275, pruned_loss=0.02315, over 7137.00 frames.], tot_loss[loss=0.1531, simple_loss=0.245, pruned_loss=0.03058, over 1415250.54 frames.], batch size: 17, lr: 2.52e-04
2022-05-15 17:34:32,634 INFO [train.py:812] (4/8) Epoch 31, batch 1400, loss[loss=0.1741, simple_loss=0.2695, pruned_loss=0.03936, over 7334.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2451, pruned_loss=0.03055, over 1419399.83 frames.], batch size: 22, lr: 2.52e-04
2022-05-15 17:35:31,415 INFO [train.py:812] (4/8) Epoch 31, batch 1450, loss[loss=0.1492, simple_loss=0.2418, pruned_loss=0.02832, over 7141.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2455, pruned_loss=0.03088, over 1420722.93 frames.], batch size: 20, lr: 2.52e-04
2022-05-15 17:36:30,345 INFO [train.py:812] (4/8) Epoch 31, batch 1500, loss[loss=0.1531, simple_loss=0.2457, pruned_loss=0.03024, over 7292.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2463, pruned_loss=0.03099, over 1426329.87 frames.], batch size: 25, lr: 2.52e-04
2022-05-15 17:37:27,930 INFO [train.py:812] (4/8) Epoch 31, batch 1550, loss[loss=0.1496, simple_loss=0.2473, pruned_loss=0.02591, over 7342.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03074, over 1427973.60 frames.], batch size: 25, lr: 2.52e-04
2022-05-15 17:38:27,309 INFO [train.py:812] (4/8) Epoch 31, batch 1600, loss[loss=0.1365, simple_loss=0.2284, pruned_loss=0.02226, over 7255.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2439, pruned_loss=0.03043, over 1428579.31 frames.], batch size: 19, lr: 2.52e-04
2022-05-15 17:39:26,046 INFO [train.py:812] (4/8) Epoch 31, batch 1650, loss[loss=0.1378, simple_loss=0.2339, pruned_loss=0.02085, over 7124.00 frames.], tot_loss[loss=0.153, simple_loss=0.2449, pruned_loss=0.03055, over 1428857.99 frames.], batch size: 21, lr: 2.52e-04
2022-05-15 17:40:24,539 INFO [train.py:812] (4/8) Epoch 31, batch 1700, loss[loss=0.1687, simple_loss=0.2672, pruned_loss=0.03511, over 7281.00 frames.], tot_loss[loss=0.152, simple_loss=0.2435, pruned_loss=0.03023, over 1425336.28 frames.], batch size: 24, lr: 2.52e-04
2022-05-15 17:41:22,582 INFO [train.py:812] (4/8) Epoch 31, batch 1750, loss[loss=0.1677, simple_loss=0.2566, pruned_loss=0.03938, over 7372.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03011, over 1427676.08 frames.], batch size: 23, lr: 2.52e-04
2022-05-15 17:42:21,639 INFO [train.py:812] (4/8) Epoch 31, batch 1800, loss[loss=0.117, simple_loss=0.2025, pruned_loss=0.01576, over 7429.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.03009, over 1423244.44 frames.], batch size: 20, lr: 2.51e-04
2022-05-15 17:43:20,029 INFO [train.py:812] (4/8) Epoch 31, batch 1850, loss[loss=0.1371, simple_loss=0.2221, pruned_loss=0.02603, over 7144.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.03038, over 1422223.31 frames.], batch size: 17, lr: 2.51e-04
2022-05-15 17:44:19,012 INFO [train.py:812] (4/8) Epoch 31, batch 1900, loss[loss=0.1472, simple_loss=0.2308, pruned_loss=0.03182, over 7322.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2439, pruned_loss=0.03026, over 1425443.80 frames.], batch size: 20, lr: 2.51e-04
2022-05-15 17:45:17,772 INFO [train.py:812] (4/8) Epoch 31, batch 1950, loss[loss=0.1556, simple_loss=0.2568, pruned_loss=0.02716, over 7368.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2437, pruned_loss=0.02997, over 1424641.72 frames.], batch size: 23, lr: 2.51e-04
2022-05-15 17:46:16,477 INFO [train.py:812] (4/8) Epoch 31, batch 2000, loss[loss=0.1532, simple_loss=0.2509, pruned_loss=0.02776, over 7164.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2424, pruned_loss=0.02947, over 1426441.15 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 17:47:15,231 INFO [train.py:812] (4/8) Epoch 31, batch 2050, loss[loss=0.1824, simple_loss=0.2602, pruned_loss=0.05231, over 7200.00 frames.], tot_loss[loss=0.1508, simple_loss=0.242, pruned_loss=0.02981, over 1423970.64 frames.], batch size: 22, lr: 2.51e-04
2022-05-15 17:48:13,817 INFO [train.py:812] (4/8) Epoch 31, batch 2100, loss[loss=0.1716, simple_loss=0.2611, pruned_loss=0.04109, over 7163.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2438, pruned_loss=0.03029, over 1422560.40 frames.], batch size: 19, lr: 2.51e-04
2022-05-15 17:49:12,918 INFO [train.py:812] (4/8) Epoch 31, batch 2150, loss[loss=0.1433, simple_loss=0.2404, pruned_loss=0.02313, over 7167.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2425, pruned_loss=0.0296, over 1426266.72 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 17:50:11,064 INFO [train.py:812] (4/8) Epoch 31, batch 2200, loss[loss=0.151, simple_loss=0.24, pruned_loss=0.03097, over 7064.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02982, over 1427799.22 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 17:51:08,602 INFO [train.py:812] (4/8) Epoch 31, batch 2250, loss[loss=0.1863, simple_loss=0.2952, pruned_loss=0.03873, over 7189.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2443, pruned_loss=0.02994, over 1427275.53 frames.], batch size: 23, lr: 2.51e-04
2022-05-15 17:52:08,125 INFO [train.py:812] (4/8) Epoch 31, batch 2300, loss[loss=0.1455, simple_loss=0.2339, pruned_loss=0.02853, over 7259.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.03001, over 1430066.33 frames.], batch size: 19, lr: 2.51e-04
2022-05-15 17:53:06,339 INFO [train.py:812] (4/8) Epoch 31, batch 2350, loss[loss=0.1509, simple_loss=0.2433, pruned_loss=0.02923, over 7064.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.03023, over 1429707.33 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 17:54:10,965 INFO [train.py:812] (4/8) Epoch 31, batch 2400, loss[loss=0.1734, simple_loss=0.2615, pruned_loss=0.04262, over 7222.00 frames.], tot_loss[loss=0.1532, simple_loss=0.245, pruned_loss=0.03069, over 1428720.77 frames.], batch size: 21, lr: 2.51e-04
2022-05-15 17:55:08,408 INFO [train.py:812] (4/8) Epoch 31, batch 2450, loss[loss=0.155, simple_loss=0.2565, pruned_loss=0.02675, over 7213.00 frames.], tot_loss[loss=0.153, simple_loss=0.2452, pruned_loss=0.03039, over 1423968.24 frames.], batch size: 21, lr: 2.51e-04
2022-05-15 17:56:07,150 INFO [train.py:812] (4/8) Epoch 31, batch 2500, loss[loss=0.1596, simple_loss=0.2526, pruned_loss=0.03325, over 7354.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2449, pruned_loss=0.03028, over 1426559.93 frames.], batch size: 22, lr: 2.51e-04
2022-05-15 17:57:05,833 INFO [train.py:812] (4/8) Epoch 31, batch 2550, loss[loss=0.1614, simple_loss=0.2567, pruned_loss=0.0331, over 7181.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2447, pruned_loss=0.03003, over 1428365.66 frames.], batch size: 23, lr: 2.51e-04
2022-05-15 17:58:14,117 INFO [train.py:812] (4/8) Epoch 31, batch 2600, loss[loss=0.1391, simple_loss=0.2157, pruned_loss=0.03127, over 7421.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03015, over 1427852.75 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 17:59:11,563 INFO [train.py:812] (4/8) Epoch 31, batch 2650, loss[loss=0.1752, simple_loss=0.2711, pruned_loss=0.03966, over 7409.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2449, pruned_loss=0.03045, over 1425068.89 frames.], batch size: 21, lr: 2.51e-04
2022-05-15 18:00:10,468 INFO [train.py:812] (4/8) Epoch 31, batch 2700, loss[loss=0.1682, simple_loss=0.2592, pruned_loss=0.03858, over 7265.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2445, pruned_loss=0.03026, over 1418951.21 frames.], batch size: 25, lr: 2.51e-04
2022-05-15 18:01:09,686 INFO [train.py:812] (4/8) Epoch 31, batch 2750, loss[loss=0.1506, simple_loss=0.254, pruned_loss=0.02358, over 7138.00 frames.], tot_loss[loss=0.152, simple_loss=0.2443, pruned_loss=0.02986, over 1419667.13 frames.], batch size: 20, lr: 2.51e-04
2022-05-15 18:02:08,956 INFO [train.py:812] (4/8) Epoch 31, batch 2800, loss[loss=0.1491, simple_loss=0.2425, pruned_loss=0.0279, over 7168.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03027, over 1421893.73 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 18:03:06,862 INFO [train.py:812] (4/8) Epoch 31, batch 2850, loss[loss=0.1963, simple_loss=0.2884, pruned_loss=0.0521, over 7204.00 frames.], tot_loss[loss=0.1528, simple_loss=0.245, pruned_loss=0.03025, over 1418892.65 frames.], batch size: 22, lr: 2.51e-04
2022-05-15 18:04:06,694 INFO [train.py:812] (4/8) Epoch 31, batch 2900, loss[loss=0.1499, simple_loss=0.2465, pruned_loss=0.02659, over 7118.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03072, over 1422524.28 frames.], batch size: 21, lr: 2.51e-04
2022-05-15 18:05:04,898 INFO [train.py:812] (4/8) Epoch 31, batch 2950, loss[loss=0.1506, simple_loss=0.2439, pruned_loss=0.0287, over 7265.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2455, pruned_loss=0.03073, over 1421503.71 frames.], batch size: 19, lr: 2.50e-04
2022-05-15 18:06:03,447 INFO [train.py:812] (4/8) Epoch 31, batch 3000, loss[loss=0.1337, simple_loss=0.23, pruned_loss=0.01871, over 7334.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2451, pruned_loss=0.03079, over 1421390.35 frames.], batch size: 20, lr: 2.50e-04
2022-05-15 18:06:03,448 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 18:06:10,972 INFO [train.py:841] (4/8) Epoch 31, validation: loss=0.1541, simple_loss=0.25, pruned_loss=0.02913, over 698248.00 frames.
2022-05-15 18:07:09,525 INFO [train.py:812] (4/8) Epoch 31, batch 3050, loss[loss=0.1299, simple_loss=0.2235, pruned_loss=0.01812, over 6976.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.03058, over 1421426.56 frames.], batch size: 16, lr: 2.50e-04
2022-05-15 18:08:09,165 INFO [train.py:812] (4/8) Epoch 31, batch 3100, loss[loss=0.1505, simple_loss=0.2412, pruned_loss=0.02984, over 7275.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.0304, over 1425846.44 frames.], batch size: 25, lr: 2.50e-04
2022-05-15 18:09:08,143 INFO [train.py:812] (4/8) Epoch 31, batch 3150, loss[loss=0.1373, simple_loss=0.2225, pruned_loss=0.02605, over 7004.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2444, pruned_loss=0.03066, over 1424820.54 frames.], batch size: 16, lr: 2.50e-04
2022-05-15 18:10:05,066 INFO [train.py:812] (4/8) Epoch 31, batch 3200, loss[loss=0.1793, simple_loss=0.2834, pruned_loss=0.03765, over 7195.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03072, over 1415641.93 frames.], batch size: 23, lr: 2.50e-04
2022-05-15 18:11:03,077 INFO [train.py:812] (4/8) Epoch 31, batch 3250, loss[loss=0.1676, simple_loss=0.2767, pruned_loss=0.02926, over 7143.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2454, pruned_loss=0.03082, over 1414483.78 frames.], batch size: 20, lr: 2.50e-04
2022-05-15 18:12:02,660 INFO [train.py:812] (4/8) Epoch 31, batch 3300, loss[loss=0.1226, simple_loss=0.1995, pruned_loss=0.02283, over 7284.00 frames.], tot_loss[loss=0.153, simple_loss=0.2449, pruned_loss=0.03055, over 1422071.28 frames.], batch size: 17, lr: 2.50e-04
2022-05-15 18:13:01,589 INFO [train.py:812] (4/8) Epoch 31, batch 3350, loss[loss=0.1463, simple_loss=0.2342, pruned_loss=0.0292, over 7205.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2445, pruned_loss=0.03027, over 1421372.38 frames.], batch size: 21, lr: 2.50e-04
2022-05-15 18:14:00,866 INFO [train.py:812] (4/8) Epoch 31, batch 3400, loss[loss=0.1641, simple_loss=0.2669, pruned_loss=0.03069, over 7269.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.03002, over 1420386.28 frames.], batch size: 25, lr: 2.50e-04
2022-05-15 18:14:57,865 INFO [train.py:812] (4/8) Epoch 31, batch 3450, loss[loss=0.1593, simple_loss=0.2529, pruned_loss=0.03288, over 6585.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2443, pruned_loss=0.03018, over 1424678.48 frames.], batch size: 38, lr: 2.50e-04
2022-05-15 18:15:56,024 INFO [train.py:812] (4/8) Epoch 31, batch 3500, loss[loss=0.1869, simple_loss=0.2829, pruned_loss=0.04549, over 7370.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.03009, over 1426738.05 frames.], batch size: 23, lr: 2.50e-04
2022-05-15 18:16:54,986 INFO [train.py:812] (4/8) Epoch 31, batch 3550, loss[loss=0.1625, simple_loss=0.251, pruned_loss=0.03699, over 7428.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2442, pruned_loss=0.03025, over 1428099.28 frames.], batch size: 20, lr: 2.50e-04
2022-05-15 18:17:52,444 INFO [train.py:812] (4/8) Epoch 31, batch 3600, loss[loss=0.1762, simple_loss=0.2799, pruned_loss=0.03621, over 7271.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2449, pruned_loss=0.03064, over 1423310.35 frames.], batch size: 24, lr: 2.50e-04
2022-05-15 18:18:51,245 INFO [train.py:812] (4/8) Epoch 31, batch 3650, loss[loss=0.1488, simple_loss=0.2339, pruned_loss=0.0318, over 7155.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2454, pruned_loss=0.03092, over 1422287.87 frames.], batch size: 17, lr: 2.50e-04
2022-05-15 18:19:50,489 INFO [train.py:812] (4/8) Epoch 31, batch 3700, loss[loss=0.1318, simple_loss=0.2172, pruned_loss=0.02327, over 7284.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2447, pruned_loss=0.03055, over 1425041.60 frames.], batch size: 17, lr: 2.50e-04
2022-05-15 18:20:49,307 INFO [train.py:812] (4/8) Epoch 31, batch 3750, loss[loss=0.1428, simple_loss=0.232, pruned_loss=0.02679, over 7255.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2447, pruned_loss=0.03085, over 1422919.93 frames.], batch size: 19, lr: 2.50e-04
2022-05-15 18:21:49,294 INFO [train.py:812] (4/8) Epoch 31, batch 3800, loss[loss=0.1482, simple_loss=0.2313, pruned_loss=0.03255, over 7275.00 frames.], tot_loss[loss=0.1527, simple_loss=0.244, pruned_loss=0.03068, over 1425741.20 frames.], batch size: 18, lr: 2.50e-04
2022-05-15 18:22:47,393 INFO [train.py:812] (4/8) Epoch 31, batch 3850, loss[loss=0.1379, simple_loss=0.2317, pruned_loss=0.02205, over 7055.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2441, pruned_loss=0.0307, over 1424918.44 frames.], batch size: 18, lr: 2.50e-04
2022-05-15 18:23:45,719 INFO [train.py:812] (4/8) Epoch 31, batch 3900, loss[loss=0.1583, simple_loss=0.2522, pruned_loss=0.03221, over 7310.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2434, pruned_loss=0.03023, over 1428906.23 frames.], batch size: 24, lr: 2.50e-04
2022-05-15 18:24:43,604 INFO [train.py:812] (4/8) Epoch 31, batch 3950, loss[loss=0.1476, simple_loss=0.2375, pruned_loss=0.02885, over 7359.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2431, pruned_loss=0.0301, over 1428385.24 frames.], batch size: 19, lr: 2.50e-04
2022-05-15 18:25:41,727 INFO [train.py:812] (4/8) Epoch 31, batch 4000, loss[loss=0.1451, simple_loss=0.2282, pruned_loss=0.03104, over 7163.00 frames.], tot_loss[loss=0.152, simple_loss=0.2436, pruned_loss=0.03019, over 1426181.64 frames.], batch size: 18, lr: 2.50e-04
2022-05-15 18:26:41,003 INFO [train.py:812] (4/8) Epoch 31, batch 4050, loss[loss=0.1842, simple_loss=0.286, pruned_loss=0.04115, over 7279.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2446, pruned_loss=0.03045, over 1425731.81 frames.], batch size: 24, lr: 2.49e-04
2022-05-15 18:27:40,598 INFO [train.py:812] (4/8) Epoch 31, batch 4100, loss[loss=0.148, simple_loss=0.2455, pruned_loss=0.0253, over 7155.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2448, pruned_loss=0.03039, over 1427673.80 frames.], batch size: 19, lr: 2.49e-04
2022-05-15 18:28:39,537 INFO [train.py:812] (4/8) Epoch 31, batch 4150, loss[loss=0.1762, simple_loss=0.2716, pruned_loss=0.04043, over 7107.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03013, over 1428884.46 frames.], batch size: 21, lr: 2.49e-04
2022-05-15 18:29:38,561 INFO [train.py:812] (4/8) Epoch 31, batch 4200, loss[loss=0.1465, simple_loss=0.2226, pruned_loss=0.0352, over 6752.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.03015, over 1430807.29 frames.], batch size: 15, lr: 2.49e-04
2022-05-15 18:30:36,491 INFO [train.py:812] (4/8) Epoch 31, batch 4250, loss[loss=0.1834, simple_loss=0.272, pruned_loss=0.04741, over 7150.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2449, pruned_loss=0.03031, over 1427201.97 frames.], batch size: 26, lr: 2.49e-04
2022-05-15 18:31:35,782 INFO [train.py:812] (4/8) Epoch 31, batch 4300, loss[loss=0.1486, simple_loss=0.2455, pruned_loss=0.02588, over 7292.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2437, pruned_loss=0.03001, over 1429885.01 frames.], batch size: 24, lr: 2.49e-04
2022-05-15 18:32:33,436 INFO [train.py:812] (4/8) Epoch 31, batch 4350, loss[loss=0.1716, simple_loss=0.2689, pruned_loss=0.03711, over 7124.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.03005, over 1420648.93 frames.], batch size: 21, lr: 2.49e-04
2022-05-15 18:33:32,245 INFO [train.py:812] (4/8) Epoch 31, batch 4400, loss[loss=0.1619, simple_loss=0.263, pruned_loss=0.03038, over 7107.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2441, pruned_loss=0.02974, over 1411234.07 frames.], batch size: 21, lr: 2.49e-04
2022-05-15 18:34:30,882 INFO [train.py:812] (4/8) Epoch 31, batch 4450, loss[loss=0.1635, simple_loss=0.2551, pruned_loss=0.03594, over 6429.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2444, pruned_loss=0.03009, over 1410189.70 frames.], batch size: 37, lr: 2.49e-04
2022-05-15 18:35:30,065 INFO [train.py:812] (4/8) Epoch 31, batch 4500, loss[loss=0.1487, simple_loss=0.2535, pruned_loss=0.02193, over 6322.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2456, pruned_loss=0.03104, over 1385238.33 frames.], batch size: 37, lr: 2.49e-04
2022-05-15 18:36:28,941 INFO [train.py:812] (4/8) Epoch 31, batch 4550, loss[loss=0.1745, simple_loss=0.2583, pruned_loss=0.04538, over 5159.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2471, pruned_loss=0.03175, over 1355648.89 frames.], batch size: 52, lr: 2.49e-04
2022-05-15 18:37:36,646 INFO [train.py:812] (4/8) Epoch 32, batch 0, loss[loss=0.1628, simple_loss=0.2608, pruned_loss=0.03238, over 4966.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2608, pruned_loss=0.03238, over 4966.00 frames.], batch size: 52, lr: 2.45e-04
2022-05-15 18:38:34,881 INFO [train.py:812] (4/8) Epoch 32, batch 50, loss[loss=0.1746, simple_loss=0.2768, pruned_loss=0.03621, over 6411.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2483, pruned_loss=0.03093, over 319555.49 frames.], batch size: 37, lr: 2.45e-04
2022-05-15 18:39:33,408 INFO [train.py:812] (4/8) Epoch 32, batch 100, loss[loss=0.1799, simple_loss=0.2738, pruned_loss=0.04299, over 7320.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2467, pruned_loss=0.03116, over 565951.27 frames.], batch size: 25, lr: 2.45e-04
2022-05-15 18:40:32,475 INFO [train.py:812] (4/8) Epoch 32, batch 150, loss[loss=0.1639, simple_loss=0.2635, pruned_loss=0.03212, over 7127.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2456, pruned_loss=0.03055, over 757837.90 frames.], batch size: 26, lr: 2.45e-04
2022-05-15 18:41:31,068 INFO [train.py:812] (4/8) Epoch 32, batch 200, loss[loss=0.1463, simple_loss=0.2358, pruned_loss=0.02839, over 7008.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2444, pruned_loss=0.03012, over 902333.12 frames.], batch size: 16, lr: 2.45e-04
2022-05-15 18:42:29,430 INFO [train.py:812] (4/8) Epoch 32, batch 250, loss[loss=0.153, simple_loss=0.2459, pruned_loss=0.03004, over 7311.00 frames.], tot_loss[loss=0.1529, simple_loss=0.245, pruned_loss=0.03036, over 1022295.18 frames.], batch size: 24, lr: 2.45e-04
2022-05-15 18:43:28,936 INFO [train.py:812] (4/8) Epoch 32, batch 300, loss[loss=0.1858, simple_loss=0.274, pruned_loss=0.04883, over 7314.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2458, pruned_loss=0.03031, over 1112995.79 frames.], batch size: 24, lr: 2.45e-04
2022-05-15 18:44:28,378 INFO [train.py:812] (4/8) Epoch 32, batch 350, loss[loss=0.1445, simple_loss=0.2374, pruned_loss=0.02586, over 7048.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2452, pruned_loss=0.03054, over 1181049.98 frames.], batch size: 28, lr: 2.45e-04
2022-05-15 18:45:27,078 INFO [train.py:812] (4/8) Epoch 32, batch 400, loss[loss=0.1615, simple_loss=0.2584, pruned_loss=0.03232, over 7196.00 frames.], tot_loss[loss=0.153, simple_loss=0.2453, pruned_loss=0.03041, over 1236382.95 frames.], batch size: 26, lr: 2.45e-04
2022-05-15 18:46:25,921 INFO [train.py:812] (4/8) Epoch 32, batch 450, loss[loss=0.1582, simple_loss=0.252, pruned_loss=0.03217, over 7321.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03017, over 1276951.17 frames.], batch size: 21, lr: 2.45e-04
2022-05-15 18:47:25,085 INFO [train.py:812] (4/8) Epoch 32, batch 500, loss[loss=0.1401, simple_loss=0.2427, pruned_loss=0.01873, over 7339.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2434, pruned_loss=0.02992, over 1313347.27 frames.], batch size: 22, lr: 2.45e-04
2022-05-15 18:48:23,111 INFO [train.py:812] (4/8) Epoch 32, batch 550, loss[loss=0.1695, simple_loss=0.2656, pruned_loss=0.03665, over 7321.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03016, over 1341251.00 frames.], batch size: 22, lr: 2.45e-04
2022-05-15 18:49:22,851 INFO [train.py:812] (4/8) Epoch 32, batch 600, loss[loss=0.1259, simple_loss=0.2102, pruned_loss=0.02081, over 7138.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2438, pruned_loss=0.03023, over 1363764.35 frames.], batch size: 17, lr: 2.45e-04
2022-05-15 18:50:21,227 INFO [train.py:812] (4/8) Epoch 32, batch 650, loss[loss=0.1243, simple_loss=0.2109, pruned_loss=0.01885, over 7003.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02964, over 1379637.12 frames.], batch size: 16, lr: 2.45e-04
2022-05-15 18:51:18,841 INFO [train.py:812] (4/8) Epoch 32, batch 700, loss[loss=0.1529, simple_loss=0.2406, pruned_loss=0.03254, over 7188.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02984, over 1387907.03 frames.], batch size: 23, lr: 2.45e-04
2022-05-15 18:52:17,788 INFO [train.py:812] (4/8) Epoch 32, batch 750, loss[loss=0.1396, simple_loss=0.2413, pruned_loss=0.0189, over 7109.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.0302, over 1396513.49 frames.], batch size: 21, lr: 2.44e-04
2022-05-15 18:53:17,319 INFO [train.py:812] (4/8) Epoch 32, batch 800, loss[loss=0.1385, simple_loss=0.2267, pruned_loss=0.02511, over 7264.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2448, pruned_loss=0.03038, over 1401117.27 frames.], batch size: 18, lr: 2.44e-04
2022-05-15 18:54:15,848 INFO [train.py:812] (4/8) Epoch 32, batch 850, loss[loss=0.1672, simple_loss=0.2612, pruned_loss=0.03662, over 7287.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2452, pruned_loss=0.03064, over 1408641.70 frames.], batch size: 25, lr: 2.44e-04
2022-05-15 18:55:14,229 INFO [train.py:812] (4/8) Epoch 32, batch 900, loss[loss=0.1616, simple_loss=0.2608, pruned_loss=0.03117, over 7338.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2459, pruned_loss=0.03043, over 1411196.63 frames.], batch size: 22, lr: 2.44e-04
2022-05-15 18:56:22,089 INFO [train.py:812] (4/8) Epoch 32, batch 950, loss[loss=0.1242, simple_loss=0.2066, pruned_loss=0.02093, over 6823.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03017, over 1412030.83 frames.], batch size: 15, lr: 2.44e-04
2022-05-15 18:57:31,056 INFO [train.py:812] (4/8) Epoch 32, batch 1000, loss[loss=0.1374, simple_loss=0.2312, pruned_loss=0.02184, over 7426.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2441, pruned_loss=0.02981, over 1415581.06 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 18:58:30,371 INFO [train.py:812] (4/8) Epoch 32, batch 1050, loss[loss=0.143, simple_loss=0.2421, pruned_loss=0.02197, over 7229.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.02941, over 1420165.99 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 18:59:29,291 INFO [train.py:812] (4/8) Epoch 32, batch 1100, loss[loss=0.1921, simple_loss=0.2834, pruned_loss=0.05041, over 7226.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02978, over 1418422.47 frames.], batch size: 22, lr: 2.44e-04
2022-05-15 19:00:36,749 INFO [train.py:812] (4/8) Epoch 32, batch 1150, loss[loss=0.1424, simple_loss=0.2251, pruned_loss=0.02982, over 7151.00 frames.], tot_loss[loss=0.153, simple_loss=0.2448, pruned_loss=0.03061, over 1422022.14 frames.], batch size: 17, lr: 2.44e-04
2022-05-15 19:01:36,500 INFO [train.py:812] (4/8) Epoch 32, batch 1200, loss[loss=0.1559, simple_loss=0.2574, pruned_loss=0.02723, over 7411.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2447, pruned_loss=0.03037, over 1424374.20 frames.], batch size: 21, lr: 2.44e-04
2022-05-15 19:02:45,182 INFO [train.py:812] (4/8) Epoch 32, batch 1250, loss[loss=0.1433, simple_loss=0.2495, pruned_loss=0.01853, over 7197.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03076, over 1418370.15 frames.], batch size: 23, lr: 2.44e-04
2022-05-15 19:03:53,737 INFO [train.py:812] (4/8) Epoch 32, batch 1300, loss[loss=0.1557, simple_loss=0.2608, pruned_loss=0.02534, over 7145.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2459, pruned_loss=0.03089, over 1423758.09 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 19:05:00,954 INFO [train.py:812] (4/8) Epoch 32, batch 1350, loss[loss=0.1403, simple_loss=0.2384, pruned_loss=0.02114, over 7333.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2455, pruned_loss=0.03073, over 1421760.00 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 19:05:59,750 INFO [train.py:812] (4/8) Epoch 32, batch 1400, loss[loss=0.1554, simple_loss=0.2521, pruned_loss=0.02938, over 7233.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.03041, over 1422149.87 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 19:06:57,262 INFO [train.py:812] (4/8) Epoch 32, batch 1450, loss[loss=0.1554, simple_loss=0.2473, pruned_loss=0.03173, over 7330.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.03078, over 1423836.30 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 19:08:05,685 INFO [train.py:812] (4/8) Epoch 32, batch 1500, loss[loss=0.1753, simple_loss=0.2547, pruned_loss=0.04802, over 5161.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2441, pruned_loss=0.03023, over 1422802.87 frames.], batch size: 53, lr: 2.44e-04
2022-05-15 19:09:04,139 INFO [train.py:812] (4/8) Epoch 32, batch 1550, loss[loss=0.1387, simple_loss=0.2236, pruned_loss=0.02693, over 7426.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.02998, over 1421349.62 frames.], batch size: 18, lr: 2.44e-04
2022-05-15 19:10:03,432 INFO [train.py:812] (4/8) Epoch 32, batch 1600, loss[loss=0.1755, simple_loss=0.2581, pruned_loss=0.0465, over 7194.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03044, over 1417673.79 frames.], batch size: 23, lr: 2.44e-04
2022-05-15 19:11:01,511 INFO [train.py:812] (4/8) Epoch 32, batch 1650, loss[loss=0.1547, simple_loss=0.2412, pruned_loss=0.03407, over 7423.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03078, over 1416874.45 frames.], batch size: 21, lr: 2.44e-04
2022-05-15 19:12:00,715 INFO [train.py:812] (4/8) Epoch 32, batch 1700, loss[loss=0.1607, simple_loss=0.26, pruned_loss=0.03076, over 7109.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03086, over 1412010.85 frames.], batch size: 21, lr: 2.44e-04
2022-05-15 19:12:59,708 INFO [train.py:812] (4/8) Epoch 32, batch 1750, loss[loss=0.1866, simple_loss=0.2645, pruned_loss=0.05436, over 5102.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.03052, over 1408957.37 frames.], batch size: 52, lr: 2.44e-04
2022-05-15 19:14:04,616 INFO [train.py:812] (4/8) Epoch 32, batch 1800, loss[loss=0.1528, simple_loss=0.248, pruned_loss=0.02878, over 7229.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2451, pruned_loss=0.03082, over 1410448.86 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 19:15:03,155 INFO [train.py:812] (4/8) Epoch 32, batch 1850, loss[loss=0.126, simple_loss=0.2086, pruned_loss=0.02175, over 6994.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2454, pruned_loss=0.03092, over 1405914.55 frames.], batch size: 16, lr: 2.44e-04
2022-05-15 19:16:02,095 INFO [train.py:812] (4/8) Epoch 32, batch 1900, loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02908, over 7351.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2445, pruned_loss=0.03067, over 1411717.05 frames.], batch size: 19, lr: 2.44e-04
2022-05-15 19:17:00,603 INFO [train.py:812] (4/8) Epoch 32, batch 1950, loss[loss=0.148, simple_loss=0.2323, pruned_loss=0.03184, over 7361.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2441, pruned_loss=0.03022, over 1417706.00 frames.], batch size: 19, lr: 2.43e-04
2022-05-15 19:18:00,431 INFO [train.py:812] (4/8) Epoch 32, batch 2000, loss[loss=0.1299, simple_loss=0.2144, pruned_loss=0.02267, over 7279.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2438, pruned_loss=0.02985, over 1419014.15 frames.], batch size: 18, lr: 2.43e-04
2022-05-15 19:18:57,522 INFO [train.py:812] (4/8) Epoch 32, batch 2050, loss[loss=0.1572, simple_loss=0.2544, pruned_loss=0.02995, over 7150.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2437, pruned_loss=0.02975, over 1416279.73 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:19:56,215 INFO [train.py:812] (4/8) Epoch 32, batch 2100, loss[loss=0.1369, simple_loss=0.2168, pruned_loss=0.02845, over 7190.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2457, pruned_loss=0.03047, over 1416818.69 frames.], batch size: 16, lr: 2.43e-04
2022-05-15 19:20:54,974 INFO [train.py:812] (4/8) Epoch 32, batch 2150, loss[loss=0.1596, simple_loss=0.2661, pruned_loss=0.02654, over 7221.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2467, pruned_loss=0.0308, over 1420833.07 frames.], batch size: 21, lr: 2.43e-04
2022-05-15 19:21:53,683 INFO [train.py:812] (4/8) Epoch 32, batch 2200, loss[loss=0.1727, simple_loss=0.2687, pruned_loss=0.03829, over 7205.00 frames.], tot_loss[loss=0.153, simple_loss=0.2452, pruned_loss=0.03039, over 1423320.85 frames.], batch size: 26, lr: 2.43e-04
2022-05-15 19:22:52,760 INFO [train.py:812] (4/8) Epoch 32, batch 2250, loss[loss=0.1496, simple_loss=0.2276, pruned_loss=0.03577, over 7068.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03025, over 1424844.21 frames.], batch size: 18, lr: 2.43e-04
2022-05-15 19:23:52,312 INFO [train.py:812] (4/8) Epoch 32, batch 2300, loss[loss=0.1652, simple_loss=0.2721, pruned_loss=0.02912, over 7341.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2444, pruned_loss=0.03039, over 1422210.30 frames.], batch size: 22, lr: 2.43e-04
2022-05-15 19:24:49,717 INFO [train.py:812] (4/8) Epoch 32, batch 2350, loss[loss=0.1551, simple_loss=0.2393, pruned_loss=0.03546, over 7288.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.0303, over 1425471.76 frames.], batch size: 17, lr: 2.43e-04
2022-05-15 19:25:48,469 INFO [train.py:812] (4/8) Epoch 32, batch 2400, loss[loss=0.1613, simple_loss=0.2544, pruned_loss=0.03412, over 7321.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2455, pruned_loss=0.03044, over 1420430.33 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:26:47,736 INFO [train.py:812] (4/8) Epoch 32, batch 2450, loss[loss=0.1606, simple_loss=0.2637, pruned_loss=0.02871, over 7197.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2448, pruned_loss=0.03041, over 1421683.60 frames.], batch size: 26, lr: 2.43e-04
2022-05-15 19:27:46,275 INFO [train.py:812] (4/8) Epoch 32, batch 2500, loss[loss=0.139, simple_loss=0.221, pruned_loss=0.02848, over 7276.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03014, over 1424678.06 frames.], batch size: 17, lr: 2.43e-04
2022-05-15 19:28:44,155 INFO [train.py:812] (4/8) Epoch 32, batch 2550, loss[loss=0.1479, simple_loss=0.2518, pruned_loss=0.02204, over 7325.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.02999, over 1421824.32 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:29:41,350 INFO [train.py:812] (4/8) Epoch 32, batch 2600, loss[loss=0.1358, simple_loss=0.222, pruned_loss=0.02483, over 7133.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2443, pruned_loss=0.03032, over 1420407.58 frames.], batch size: 17, lr: 2.43e-04
2022-05-15 19:30:39,829 INFO [train.py:812] (4/8) Epoch 32, batch 2650, loss[loss=0.1601, simple_loss=0.253, pruned_loss=0.03364, over 7160.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03025, over 1422654.56 frames.], batch size: 26, lr: 2.43e-04
2022-05-15 19:31:39,432 INFO [train.py:812] (4/8) Epoch 32, batch 2700, loss[loss=0.1429, simple_loss=0.2373, pruned_loss=0.02427, over 7314.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2444, pruned_loss=0.03026, over 1421924.65 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:32:37,300 INFO [train.py:812] (4/8) Epoch 32, batch 2750, loss[loss=0.1712, simple_loss=0.2678, pruned_loss=0.03729, over 7067.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.03002, over 1425169.76 frames.], batch size: 28, lr: 2.43e-04
2022-05-15 19:33:35,478 INFO [train.py:812] (4/8) Epoch 32, batch 2800, loss[loss=0.1271, simple_loss=0.216, pruned_loss=0.01914, over 7405.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2439, pruned_loss=0.02985, over 1424339.04 frames.], batch size: 18, lr: 2.43e-04
2022-05-15 19:34:34,367 INFO [train.py:812] (4/8) Epoch 32, batch 2850, loss[loss=0.1491, simple_loss=0.2554, pruned_loss=0.02139, over 6343.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02965, over 1421368.94 frames.], batch size: 37, lr: 2.43e-04
2022-05-15 19:35:32,679 INFO [train.py:812] (4/8) Epoch 32, batch 2900, loss[loss=0.1572, simple_loss=0.2588, pruned_loss=0.02775, over 7232.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2448, pruned_loss=0.03, over 1426015.93 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:36:30,945 INFO [train.py:812] (4/8) Epoch 32, batch 2950, loss[loss=0.1611, simple_loss=0.2636, pruned_loss=0.02933, over 7176.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2454, pruned_loss=0.03017, over 1418536.17 frames.], batch size: 23, lr: 2.43e-04
2022-05-15 19:37:29,684 INFO [train.py:812] (4/8) Epoch 32, batch 3000, loss[loss=0.1678, simple_loss=0.2689, pruned_loss=0.03332, over 7438.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2463, pruned_loss=0.03058, over 1419785.61 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:37:29,685 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 19:37:37,095 INFO [train.py:841] (4/8) Epoch 32, validation: loss=0.1532, simple_loss=0.2494, pruned_loss=0.02852, over 698248.00 frames.
2022-05-15 19:38:35,487 INFO [train.py:812] (4/8) Epoch 32, batch 3050, loss[loss=0.1717, simple_loss=0.2648, pruned_loss=0.03935, over 7322.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2455, pruned_loss=0.03051, over 1423182.20 frames.], batch size: 25, lr: 2.43e-04
2022-05-15 19:39:34,750 INFO [train.py:812] (4/8) Epoch 32, batch 3100, loss[loss=0.1565, simple_loss=0.2553, pruned_loss=0.02887, over 7113.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2454, pruned_loss=0.03084, over 1425925.46 frames.], batch size: 28, lr: 2.42e-04
2022-05-15 19:40:34,128 INFO [train.py:812] (4/8) Epoch 32, batch 3150, loss[loss=0.1212, simple_loss=0.2004, pruned_loss=0.02097, over 7258.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2445, pruned_loss=0.03066, over 1423798.98 frames.], batch size: 17, lr: 2.42e-04
2022-05-15 19:41:32,535 INFO [train.py:812] (4/8) Epoch 32, batch 3200, loss[loss=0.1382, simple_loss=0.2393, pruned_loss=0.01853, over 7107.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.03055, over 1425896.66 frames.], batch size: 21, lr: 2.42e-04
2022-05-15 19:42:31,658 INFO [train.py:812] (4/8) Epoch 32, batch 3250, loss[loss=0.1611, simple_loss=0.2478, pruned_loss=0.03725, over 7342.00 frames.], tot_loss[loss=0.1531, simple_loss=0.245, pruned_loss=0.03061, over 1427038.52 frames.], batch size: 22, lr: 2.42e-04
2022-05-15 19:43:31,268 INFO [train.py:812] (4/8) Epoch 32, batch 3300, loss[loss=0.1549, simple_loss=0.2556, pruned_loss=0.02706, over 7427.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2444, pruned_loss=0.03039, over 1423742.33 frames.], batch size: 20, lr: 2.42e-04
2022-05-15 19:44:30,458 INFO [train.py:812] (4/8) Epoch 32, batch 3350, loss[loss=0.1608, simple_loss=0.2494, pruned_loss=0.03613, over 7315.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2431, pruned_loss=0.03013, over 1425555.86 frames.], batch size: 21, lr: 2.42e-04
2022-05-15 19:45:29,638 INFO [train.py:812] (4/8) Epoch 32, batch 3400, loss[loss=0.1372, simple_loss=0.2316, pruned_loss=0.02139, over 7333.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.0306, over 1422017.18 frames.], batch size: 20, lr: 2.42e-04
2022-05-15 19:46:27,578 INFO [train.py:812] (4/8) Epoch 32, batch 3450, loss[loss=0.1811, simple_loss=0.2762, pruned_loss=0.043, over 7209.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03081, over 1424828.65 frames.], batch size: 22, lr: 2.42e-04
2022-05-15 19:47:26,350 INFO [train.py:812] (4/8) Epoch 32, batch 3500, loss[loss=0.1726, simple_loss=0.2608, pruned_loss=0.04217, over 7285.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2443, pruned_loss=0.03017, over 1428490.27 frames.], batch size: 24, lr: 2.42e-04
2022-05-15 19:48:25,231 INFO [train.py:812] (4/8) Epoch 32, batch 3550, loss[loss=0.1527, simple_loss=0.2512, pruned_loss=0.02706, over 7394.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2432, pruned_loss=0.02991, over 1431331.14 frames.], batch size: 23, lr: 2.42e-04
2022-05-15 19:49:24,694 INFO [train.py:812] (4/8) Epoch 32, batch 3600, loss[loss=0.1535, simple_loss=0.2486, pruned_loss=0.0292, over 6301.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2429, pruned_loss=0.02993, over 1428812.24 frames.], batch size: 37, lr: 2.42e-04
2022-05-15 19:50:24,033 INFO [train.py:812] (4/8) Epoch 32, batch 3650, loss[loss=0.163, simple_loss=0.2554, pruned_loss=0.03525, over 7230.00 frames.], tot_loss[loss=0.152, simple_loss=0.2437, pruned_loss=0.03017, over 1428257.33 frames.], batch size: 20, lr: 2.42e-04
2022-05-15 19:51:24,139 INFO [train.py:812] (4/8) Epoch 32, batch 3700, loss[loss=0.1488, simple_loss=0.2199, pruned_loss=0.03881, over 7138.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2432, pruned_loss=0.03015, over 1430530.31 frames.], batch size: 17, lr: 2.42e-04
2022-05-15 19:52:22,803 INFO [train.py:812] (4/8) Epoch 32, batch 3750, loss[loss=0.1744, simple_loss=0.2663, pruned_loss=0.04128, over 7189.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2433, pruned_loss=0.03028, over 1424568.01 frames.], batch size: 23, lr: 2.42e-04
2022-05-15 19:53:21,635 INFO [train.py:812] (4/8) Epoch 32, batch 3800, loss[loss=0.1415, simple_loss=0.2373, pruned_loss=0.0229, over 7388.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2434, pruned_loss=0.0299, over 1425915.70 frames.], batch size: 23, lr: 2.42e-04
2022-05-15 19:54:19,356 INFO [train.py:812] (4/8) Epoch 32, batch 3850, loss[loss=0.1552, simple_loss=0.2562, pruned_loss=0.02715, over 7428.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2428, pruned_loss=0.02974, over 1428472.28 frames.], batch size: 20, lr: 2.42e-04
2022-05-15 19:55:27,968 INFO [train.py:812] (4/8) Epoch 32, batch 3900, loss[loss=0.1448, simple_loss=0.233, pruned_loss=0.02832, over 7166.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02996, over 1429256.89 frames.], batch size: 18, lr: 2.42e-04
2022-05-15 19:56:25,348 INFO [train.py:812] (4/8) Epoch 32, batch 3950, loss[loss=0.1525, simple_loss=0.2556, pruned_loss=0.02469, over 7224.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.03024, over 1424312.34 frames.], batch size: 21, lr: 2.42e-04
2022-05-15 19:57:24,496 INFO [train.py:812] (4/8) Epoch 32, batch 4000, loss[loss=0.1468, simple_loss=0.233, pruned_loss=0.03035, over 7409.00 frames.], tot_loss[loss=0.1522, simple_loss=0.244, pruned_loss=0.03014, over 1422315.02 frames.], batch size: 18, lr: 2.42e-04
2022-05-15 19:58:22,821 INFO [train.py:812] (4/8) Epoch 32, batch 4050, loss[loss=0.1514, simple_loss=0.2614, pruned_loss=0.02072, over 7367.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2441, pruned_loss=0.03028, over 1419681.06 frames.], batch size: 23, lr: 2.42e-04
2022-05-15 19:59:20,908 INFO [train.py:812] (4/8) Epoch 32, batch 4100, loss[loss=0.1641, simple_loss=0.2593, pruned_loss=0.0344, over 7209.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2452, pruned_loss=0.03064, over 1418074.97 frames.], batch size: 22, lr: 2.42e-04
2022-05-15 20:00:19,820 INFO [train.py:812] (4/8) Epoch 32, batch 4150, loss[loss=0.1721, simple_loss=0.2709, pruned_loss=0.03661, over 7220.00 frames.], tot_loss[loss=0.1529, simple_loss=0.245, pruned_loss=0.03036, over 1422511.46 frames.], batch size: 21, lr: 2.42e-04
2022-05-15 20:01:19,549 INFO [train.py:812] (4/8) Epoch 32, batch 4200, loss[loss=0.1245, simple_loss=0.2188, pruned_loss=0.01509, over 7327.00 frames.], tot_loss[loss=0.1515, simple_loss=0.243, pruned_loss=0.02998, over 1422040.15 frames.], batch size: 20, lr: 2.42e-04
2022-05-15 20:02:17,844 INFO [train.py:812] (4/8) Epoch 32, batch 4250, loss[loss=0.1576, simple_loss=0.2418, pruned_loss=0.03671, over 7255.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2432, pruned_loss=0.03021, over 1421050.91 frames.], batch size: 19, lr: 2.42e-04
2022-05-15 20:03:17,426 INFO [train.py:812] (4/8) Epoch 32, batch 4300, loss[loss=0.1383, simple_loss=0.2303, pruned_loss=0.02318, over 7416.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2427, pruned_loss=0.02996, over 1420808.01 frames.], batch size: 18, lr: 2.42e-04
2022-05-15 20:04:16,089 INFO [train.py:812] (4/8) Epoch 32, batch 4350, loss[loss=0.1321, simple_loss=0.2188, pruned_loss=0.02277, over 7174.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2436, pruned_loss=0.03028, over 1420217.08 frames.], batch size: 18, lr: 2.41e-04
2022-05-15 20:05:14,968 INFO [train.py:812] (4/8) Epoch 32, batch 4400, loss[loss=0.1449, simple_loss=0.2373, pruned_loss=0.02627, over 7331.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03073, over 1406356.00 frames.], batch size: 25, lr: 2.41e-04
2022-05-15 20:06:12,564 INFO [train.py:812] (4/8) Epoch 32, batch 4450, loss[loss=0.1491, simple_loss=0.2346, pruned_loss=0.03178, over 7268.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2448, pruned_loss=0.03091, over 1404037.73 frames.], batch size: 16, lr: 2.41e-04
2022-05-15 20:07:11,387 INFO [train.py:812] (4/8) Epoch 32, batch 4500, loss[loss=0.1426, simple_loss=0.2376, pruned_loss=0.02377, over 6734.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2449, pruned_loss=0.03091, over 1395258.86 frames.], batch size: 31, lr: 2.41e-04
2022-05-15 20:08:09,914 INFO [train.py:812] (4/8) Epoch 32, batch 4550, loss[loss=0.1801, simple_loss=0.2625, pruned_loss=0.04884, over 4807.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2453, pruned_loss=0.03179, over 1358182.56 frames.], batch size: 52, lr: 2.41e-04
2022-05-15 20:09:17,617 INFO [train.py:812] (4/8) Epoch 33, batch 0, loss[loss=0.1435, simple_loss=0.2338, pruned_loss=0.02664, over 6752.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2338, pruned_loss=0.02664, over 6752.00 frames.], batch size: 31, lr: 2.38e-04
2022-05-15 20:10:15,660 INFO [train.py:812] (4/8) Epoch 33, batch 50, loss[loss=0.1614, simple_loss=0.2428, pruned_loss=0.04001, over 5344.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2448, pruned_loss=0.03001, over 314555.03 frames.], batch size: 52, lr: 2.38e-04
2022-05-15 20:11:14,529 INFO [train.py:812] (4/8) Epoch 33, batch 100, loss[loss=0.1645, simple_loss=0.2592, pruned_loss=0.03491, over 6537.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.03083, over 559836.77 frames.], batch size: 38, lr: 2.38e-04
2022-05-15 20:12:13,179 INFO [train.py:812] (4/8) Epoch 33, batch 150, loss[loss=0.1707, simple_loss=0.2658, pruned_loss=0.03778, over 7218.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2457, pruned_loss=0.03051, over 751469.26 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:13:12,834 INFO [train.py:812] (4/8) Epoch 33, batch 200, loss[loss=0.1436, simple_loss=0.2297, pruned_loss=0.02869, over 7015.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2449, pruned_loss=0.03078, over 893961.58 frames.], batch size: 16, lr: 2.37e-04
2022-05-15 20:14:10,197 INFO [train.py:812] (4/8) Epoch 33, batch 250, loss[loss=0.134, simple_loss=0.2277, pruned_loss=0.02017, over 7222.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03083, over 1009119.59 frames.], batch size: 20, lr: 2.37e-04
2022-05-15 20:15:08,985 INFO [train.py:812] (4/8) Epoch 33, batch 300, loss[loss=0.1852, simple_loss=0.285, pruned_loss=0.04266, over 6749.00 frames.], tot_loss[loss=0.1538, simple_loss=0.246, pruned_loss=0.03082, over 1092877.00 frames.], batch size: 31, lr: 2.37e-04
2022-05-15 20:16:07,544 INFO [train.py:812] (4/8) Epoch 33, batch 350, loss[loss=0.1237, simple_loss=0.2172, pruned_loss=0.01512, over 7413.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.0309, over 1164120.52 frames.], batch size: 18, lr: 2.37e-04
2022-05-15 20:17:07,048 INFO [train.py:812] (4/8) Epoch 33, batch 400, loss[loss=0.1417, simple_loss=0.2245, pruned_loss=0.02946, over 7431.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03041, over 1220736.18 frames.], batch size: 20, lr: 2.37e-04
2022-05-15 20:18:06,475 INFO [train.py:812] (4/8) Epoch 33, batch 450, loss[loss=0.1573, simple_loss=0.2523, pruned_loss=0.03118, over 6716.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03014, over 1262875.72 frames.], batch size: 31, lr: 2.37e-04
2022-05-15 20:19:06,089 INFO [train.py:812] (4/8) Epoch 33, batch 500, loss[loss=0.143, simple_loss=0.2448, pruned_loss=0.02063, over 7210.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03013, over 1300960.09 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:20:04,297 INFO [train.py:812] (4/8) Epoch 33, batch 550, loss[loss=0.1387, simple_loss=0.2374, pruned_loss=0.01998, over 7308.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2461, pruned_loss=0.0304, over 1329458.80 frames.], batch size: 21, lr: 2.37e-04
2022-05-15 20:21:03,129 INFO [train.py:812] (4/8) Epoch 33, batch 600, loss[loss=0.1648, simple_loss=0.2505, pruned_loss=0.03958, over 7300.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2457, pruned_loss=0.0305, over 1347460.60 frames.], batch size: 24, lr: 2.37e-04
2022-05-15 20:22:00,732 INFO [train.py:812] (4/8) Epoch 33, batch 650, loss[loss=0.1628, simple_loss=0.2612, pruned_loss=0.03221, over 7188.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2456, pruned_loss=0.03027, over 1364589.79 frames.], batch size: 26, lr: 2.37e-04
2022-05-15 20:23:00,274 INFO [train.py:812] (4/8) Epoch 33, batch 700, loss[loss=0.143, simple_loss=0.2205, pruned_loss=0.03279, over 7151.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2461, pruned_loss=0.0305, over 1375225.16 frames.], batch size: 17, lr: 2.37e-04
2022-05-15 20:23:58,672 INFO [train.py:812] (4/8) Epoch 33, batch 750, loss[loss=0.134, simple_loss=0.2339, pruned_loss=0.01706, over 7218.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2456, pruned_loss=0.0304, over 1381171.96 frames.], batch size: 21, lr: 2.37e-04
2022-05-15 20:24:57,941 INFO [train.py:812] (4/8) Epoch 33, batch 800, loss[loss=0.1644, simple_loss=0.2567, pruned_loss=0.03602, over 7441.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2452, pruned_loss=0.03054, over 1392454.41 frames.], batch size: 20, lr: 2.37e-04
2022-05-15 20:25:55,922 INFO [train.py:812] (4/8) Epoch 33, batch 850, loss[loss=0.1516, simple_loss=0.2493, pruned_loss=0.02694, over 7382.00 frames.], tot_loss[loss=0.153, simple_loss=0.2453, pruned_loss=0.0304, over 1399514.03 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:26:54,547 INFO [train.py:812] (4/8) Epoch 33, batch 900, loss[loss=0.1805, simple_loss=0.2691, pruned_loss=0.04594, over 7183.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.0302, over 1408882.89 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:27:51,772 INFO [train.py:812] (4/8) Epoch 33, batch 950, loss[loss=0.1384, simple_loss=0.2292, pruned_loss=0.0238, over 7429.00 frames.], tot_loss[loss=0.153, simple_loss=0.245, pruned_loss=0.03046, over 1414424.03 frames.], batch size: 20, lr: 2.37e-04
2022-05-15 20:28:51,354 INFO [train.py:812] (4/8) Epoch 33, batch 1000, loss[loss=0.1614, simple_loss=0.2635, pruned_loss=0.02966, over 7229.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03036, over 1414408.87 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:29:49,409 INFO [train.py:812] (4/8) Epoch 33, batch 1050, loss[loss=0.1411, simple_loss=0.2295, pruned_loss=0.02632, over 7147.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2448, pruned_loss=0.03019, over 1413522.17 frames.], batch size: 28, lr: 2.37e-04
2022-05-15 20:30:48,564 INFO [train.py:812] (4/8) Epoch 33, batch 1100, loss[loss=0.1651, simple_loss=0.2537, pruned_loss=0.03822, over 7291.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03031, over 1418175.37 frames.], batch size: 24, lr: 2.37e-04
2022-05-15 20:31:47,038 INFO [train.py:812] (4/8) Epoch 33, batch 1150, loss[loss=0.1397, simple_loss=0.2419, pruned_loss=0.01874, over 7216.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2446, pruned_loss=0.02993, over 1419588.01 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:32:51,450 INFO [train.py:812] (4/8) Epoch 33, batch 1200, loss[loss=0.1729, simple_loss=0.2674, pruned_loss=0.03917, over 7193.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2447, pruned_loss=0.02977, over 1422547.27 frames.], batch size: 26, lr: 2.37e-04
2022-05-15 20:33:50,447 INFO [train.py:812] (4/8) Epoch 33, batch 1250, loss[loss=0.146, simple_loss=0.246, pruned_loss=0.02296, over 6500.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2446, pruned_loss=0.02984, over 1420991.14 frames.], batch size: 38, lr: 2.37e-04
2022-05-15 20:34:50,217 INFO [train.py:812] (4/8) Epoch 33, batch 1300, loss[loss=0.1535, simple_loss=0.2543, pruned_loss=0.02638, over 7226.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2443, pruned_loss=0.02997, over 1421428.21 frames.], batch size: 21, lr: 2.37e-04
2022-05-15 20:35:49,526 INFO [train.py:812] (4/8) Epoch 33, batch 1350, loss[loss=0.1409, simple_loss=0.2286, pruned_loss=0.0266, over 7267.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2443, pruned_loss=0.03001, over 1421485.63 frames.], batch size: 17, lr: 2.37e-04
2022-05-15 20:36:48,930 INFO [train.py:812] (4/8) Epoch 33, batch 1400, loss[loss=0.1352, simple_loss=0.2301, pruned_loss=0.02013, over 7140.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2442, pruned_loss=0.03009, over 1422254.54 frames.], batch size: 20, lr: 2.36e-04
2022-05-15 20:37:47,490 INFO [train.py:812] (4/8) Epoch 33, batch 1450, loss[loss=0.1429, simple_loss=0.2453, pruned_loss=0.02024, over 6548.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02991, over 1424630.78 frames.], batch size: 31, lr: 2.36e-04
2022-05-15 20:38:46,332 INFO [train.py:812] (4/8) Epoch 33, batch 1500, loss[loss=0.1772, simple_loss=0.2572, pruned_loss=0.04859, over 4747.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2456, pruned_loss=0.03076, over 1422028.86 frames.], batch size: 53, lr: 2.36e-04
2022-05-15 20:39:44,945 INFO [train.py:812] (4/8) Epoch 33, batch 1550, loss[loss=0.1298, simple_loss=0.2355, pruned_loss=0.01202, over 7212.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2455, pruned_loss=0.03078, over 1418553.61 frames.], batch size: 21, lr: 2.36e-04
2022-05-15 20:40:43,839 INFO [train.py:812] (4/8) Epoch 33, batch 1600, loss[loss=0.1532, simple_loss=0.2532, pruned_loss=0.02662, over 7414.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2446, pruned_loss=0.03054, over 1421004.34 frames.], batch size: 21, lr: 2.36e-04
2022-05-15 20:41:42,719 INFO [train.py:812] (4/8) Epoch 33, batch 1650, loss[loss=0.1497, simple_loss=0.2446, pruned_loss=0.0274, over 7214.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2439, pruned_loss=0.03035, over 1421134.56 frames.], batch size: 21, lr: 2.36e-04
2022-05-15 20:42:41,759 INFO [train.py:812] (4/8) Epoch 33, batch 1700, loss[loss=0.1681, simple_loss=0.265, pruned_loss=0.03559, over 7270.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03007, over 1422662.84 frames.], batch size: 24, lr: 2.36e-04
2022-05-15 20:43:40,829 INFO [train.py:812] (4/8) Epoch 33, batch 1750, loss[loss=0.1692, simple_loss=0.2514, pruned_loss=0.04351, over 7032.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2454, pruned_loss=0.0306, over 1415521.30 frames.], batch size: 28, lr: 2.36e-04
2022-05-15 20:44:40,002 INFO [train.py:812] (4/8) Epoch 33, batch 1800, loss[loss=0.1392, simple_loss=0.2305, pruned_loss=0.02394, over 7266.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2449, pruned_loss=0.03046, over 1419091.77 frames.], batch size: 19, lr: 2.36e-04
2022-05-15 20:45:38,887 INFO [train.py:812] (4/8) Epoch 33, batch 1850, loss[loss=0.1534, simple_loss=0.2403, pruned_loss=0.03325, over 7312.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03079, over 1422223.53 frames.], batch size: 21, lr: 2.36e-04
2022-05-15 20:46:37,355 INFO [train.py:812] (4/8) Epoch 33, batch 1900, loss[loss=0.1613, simple_loss=0.2533, pruned_loss=0.03468, over 7379.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2442, pruned_loss=0.03028, over 1425316.79 frames.], batch size: 23, lr: 2.36e-04
2022-05-15 20:47:35,955 INFO [train.py:812] (4/8) Epoch 33, batch 1950, loss[loss=0.1445, simple_loss=0.2419, pruned_loss=0.02355, over 7262.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.0301, over 1423869.99 frames.], batch size: 24, lr: 2.36e-04
2022-05-15 20:48:34,900 INFO [train.py:812] (4/8) Epoch 33, batch 2000, loss[loss=0.1551, simple_loss=0.2598, pruned_loss=0.02519, over 6524.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2443, pruned_loss=0.02995, over 1425892.96 frames.], batch size: 38, lr: 2.36e-04
2022-05-15 20:49:32,706 INFO [train.py:812] (4/8) Epoch 33, batch 2050, loss[loss=0.1467, simple_loss=0.2343, pruned_loss=0.0295, over 7153.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.02976, over 1427135.84 frames.], batch size: 18, lr: 2.36e-04
2022-05-15 20:50:32,331 INFO [train.py:812] (4/8) Epoch 33, batch 2100, loss[loss=0.1392, simple_loss=0.2202, pruned_loss=0.02912, over 7161.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02959, over 1428263.75 frames.], batch size: 19, lr: 2.36e-04
2022-05-15 20:51:30,241 INFO [train.py:812] (4/8) Epoch 33, batch 2150, loss[loss=0.1248, simple_loss=0.2104, pruned_loss=0.01959, over 7414.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2435, pruned_loss=0.02985, over 1428416.38 frames.], batch size: 18, lr: 2.36e-04
2022-05-15 20:52:28,370 INFO [train.py:812] (4/8) Epoch 33, batch 2200, loss[loss=0.196, simple_loss=0.2847, pruned_loss=0.05366, over 5100.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2437, pruned_loss=0.03005, over 1422708.58 frames.], batch size: 52, lr: 2.36e-04
2022-05-15 20:53:26,613 INFO [train.py:812] (4/8) Epoch 33, batch 2250, loss[loss=0.1613, simple_loss=0.2526, pruned_loss=0.03501, over 7182.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2432, pruned_loss=0.02999, over 1420379.89 frames.], batch size: 26, lr: 2.36e-04
2022-05-15 20:54:25,536 INFO [train.py:812] (4/8) Epoch 33, batch 2300, loss[loss=0.1714, simple_loss=0.255, pruned_loss=0.04396, over 7212.00 frames.], tot_loss[loss=0.152, simple_loss=0.243, pruned_loss=0.03048, over 1417957.41 frames.], batch size: 22, lr: 2.36e-04
2022-05-15 20:55:24,370 INFO [train.py:812] (4/8) Epoch 33, batch 2350, loss[loss=0.1424, simple_loss=0.2244, pruned_loss=0.03023, over 6787.00 frames.], tot_loss[loss=0.1511, simple_loss=0.242, pruned_loss=0.03007, over 1420932.21 frames.], batch size: 15, lr: 2.36e-04
2022-05-15 20:56:23,038 INFO [train.py:812] (4/8) Epoch 33, batch 2400, loss[loss=0.1486, simple_loss=0.2415, pruned_loss=0.02786, over 7429.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2418, pruned_loss=0.02981, over 1422868.41 frames.], batch size: 20, lr: 2.36e-04
2022-05-15 20:57:40,442 INFO [train.py:812] (4/8) Epoch 33, batch 2450, loss[loss=0.1371, simple_loss=0.2303, pruned_loss=0.02191, over 7258.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2424, pruned_loss=0.02985, over 1424971.93 frames.], batch size: 19, lr: 2.36e-04
2022-05-15 20:58:40,017 INFO [train.py:812] (4/8) Epoch 33, batch 2500, loss[loss=0.164, simple_loss=0.2596, pruned_loss=0.03423, over 7316.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2423, pruned_loss=0.02994, over 1427050.31 frames.], batch size: 21, lr: 2.36e-04
2022-05-15 20:59:48,297 INFO [train.py:812] (4/8) Epoch 33, batch 2550, loss[loss=0.1542, simple_loss=0.2453, pruned_loss=0.03154, over 7370.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2416, pruned_loss=0.0298, over 1427310.45 frames.], batch size: 23, lr: 2.36e-04
2022-05-15 21:00:46,747 INFO [train.py:812] (4/8) Epoch 33, batch 2600, loss[loss=0.1896, simple_loss=0.2871, pruned_loss=0.04602, over 7204.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2424, pruned_loss=0.03031, over 1427714.52 frames.], batch size: 23, lr: 2.36e-04
2022-05-15 21:01:44,981 INFO [train.py:812] (4/8) Epoch 33, batch 2650, loss[loss=0.1466, simple_loss=0.2247, pruned_loss=0.03424, over 7259.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2433, pruned_loss=0.03051, over 1423247.71 frames.], batch size: 16, lr: 2.35e-04
2022-05-15 21:02:52,790 INFO [train.py:812] (4/8) Epoch 33, batch 2700, loss[loss=0.1489, simple_loss=0.2449, pruned_loss=0.02641, over 7430.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2428, pruned_loss=0.02999, over 1424323.92 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:04:10,609 INFO [train.py:812] (4/8) Epoch 33, batch 2750, loss[loss=0.1224, simple_loss=0.2151, pruned_loss=0.01481, over 7285.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2432, pruned_loss=0.03015, over 1425079.59 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:05:09,529 INFO [train.py:812] (4/8) Epoch 33, batch 2800, loss[loss=0.147, simple_loss=0.2436, pruned_loss=0.0252, over 7198.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2423, pruned_loss=0.02971, over 1424312.03 frames.], batch size: 23, lr: 2.35e-04
2022-05-15 21:06:07,219 INFO [train.py:812] (4/8) Epoch 33, batch 2850, loss[loss=0.1443, simple_loss=0.239, pruned_loss=0.02476, over 7320.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2419, pruned_loss=0.02942, over 1425601.27 frames.], batch size: 21, lr: 2.35e-04
2022-05-15 21:07:06,366 INFO [train.py:812] (4/8) Epoch 33, batch 2900, loss[loss=0.1547, simple_loss=0.2496, pruned_loss=0.0299, over 7300.00 frames.], tot_loss[loss=0.1504, simple_loss=0.242, pruned_loss=0.0294, over 1425714.62 frames.], batch size: 25, lr: 2.35e-04
2022-05-15 21:08:04,492 INFO [train.py:812] (4/8) Epoch 33, batch 2950, loss[loss=0.153, simple_loss=0.2453, pruned_loss=0.03037, over 7420.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02951, over 1427798.97 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:09:12,203 INFO [train.py:812] (4/8) Epoch 33, batch 3000, loss[loss=0.1206, simple_loss=0.2054, pruned_loss=0.01786, over 7056.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.0293, over 1426687.78 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:09:12,204 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 21:09:19,691 INFO [train.py:841] (4/8) Epoch 33, validation: loss=0.1535, simple_loss=0.2493, pruned_loss=0.02886, over 698248.00 frames.
2022-05-15 21:10:18,078 INFO [train.py:812] (4/8) Epoch 33, batch 3050, loss[loss=0.1616, simple_loss=0.2571, pruned_loss=0.03308, over 6412.00 frames.], tot_loss[loss=0.1502, simple_loss=0.242, pruned_loss=0.02916, over 1422204.30 frames.], batch size: 37, lr: 2.35e-04
2022-05-15 21:11:15,938 INFO [train.py:812] (4/8) Epoch 33, batch 3100, loss[loss=0.1597, simple_loss=0.2657, pruned_loss=0.02687, over 7397.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2427, pruned_loss=0.02933, over 1422909.44 frames.], batch size: 23, lr: 2.35e-04
2022-05-15 21:12:14,893 INFO [train.py:812] (4/8) Epoch 33, batch 3150, loss[loss=0.1287, simple_loss=0.2144, pruned_loss=0.02153, over 7068.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2421, pruned_loss=0.02953, over 1420986.16 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:13:13,032 INFO [train.py:812] (4/8) Epoch 33, batch 3200, loss[loss=0.1355, simple_loss=0.2219, pruned_loss=0.02456, over 7234.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2423, pruned_loss=0.02968, over 1421865.13 frames.], batch size: 16, lr: 2.35e-04
2022-05-15 21:14:11,711 INFO [train.py:812] (4/8) Epoch 33, batch 3250, loss[loss=0.1489, simple_loss=0.2344, pruned_loss=0.03171, over 7282.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2428, pruned_loss=0.02987, over 1419705.57 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:15:11,681 INFO [train.py:812] (4/8) Epoch 33, batch 3300, loss[loss=0.1607, simple_loss=0.2523, pruned_loss=0.0345, over 7231.00 frames.], tot_loss[loss=0.151, simple_loss=0.2424, pruned_loss=0.02982, over 1424062.33 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:16:10,457 INFO [train.py:812] (4/8) Epoch 33, batch 3350, loss[loss=0.1361, simple_loss=0.2313, pruned_loss=0.02041, over 7325.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2421, pruned_loss=0.02953, over 1428099.09 frames.], batch size: 21, lr: 2.35e-04
2022-05-15 21:17:09,955 INFO [train.py:812] (4/8) Epoch 33, batch 3400, loss[loss=0.1469, simple_loss=0.2277, pruned_loss=0.03308, over 7286.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2422, pruned_loss=0.0298, over 1427819.23 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:18:09,762 INFO [train.py:812] (4/8) Epoch 33, batch 3450, loss[loss=0.1274, simple_loss=0.2203, pruned_loss=0.01724, over 7321.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2429, pruned_loss=0.02989, over 1431505.87 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:19:07,584 INFO [train.py:812] (4/8) Epoch 33, batch 3500, loss[loss=0.1806, simple_loss=0.2717, pruned_loss=0.04476, over 7377.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.03063, over 1428390.61 frames.], batch size: 23, lr: 2.35e-04
2022-05-15 21:20:05,736 INFO [train.py:812] (4/8) Epoch 33, batch 3550, loss[loss=0.1432, simple_loss=0.2271, pruned_loss=0.02968, over 7415.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2438, pruned_loss=0.03042, over 1427172.61 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:21:04,476 INFO [train.py:812] (4/8) Epoch 33, batch 3600, loss[loss=0.1224, simple_loss=0.2112, pruned_loss=0.01678, over 7320.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2433, pruned_loss=0.03023, over 1424306.58 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:22:03,607 INFO [train.py:812] (4/8) Epoch 33, batch 3650, loss[loss=0.1559, simple_loss=0.2434, pruned_loss=0.03416, over 7332.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2428, pruned_loss=0.02979, over 1424573.73 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:23:02,539 INFO [train.py:812] (4/8) Epoch 33, batch 3700, loss[loss=0.1337, simple_loss=0.2173, pruned_loss=0.02509, over 7274.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03009, over 1427467.54 frames.], batch size: 17, lr: 2.35e-04
2022-05-15 21:24:01,176 INFO [train.py:812] (4/8) Epoch 33, batch 3750, loss[loss=0.1571, simple_loss=0.2463, pruned_loss=0.03399, over 7221.00 frames.], tot_loss[loss=0.152, simple_loss=0.2434, pruned_loss=0.03027, over 1427560.84 frames.], batch size: 21, lr: 2.35e-04
2022-05-15 21:25:00,737 INFO [train.py:812] (4/8) Epoch 33, batch 3800, loss[loss=0.1621, simple_loss=0.2663, pruned_loss=0.02898, over 7188.00 frames.], tot_loss[loss=0.1518, simple_loss=0.243, pruned_loss=0.03031, over 1428182.53 frames.], batch size: 23, lr: 2.35e-04
2022-05-15 21:25:58,520 INFO [train.py:812] (4/8) Epoch 33, batch 3850, loss[loss=0.1604, simple_loss=0.2625, pruned_loss=0.02921, over 7327.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2432, pruned_loss=0.03032, over 1428889.14 frames.], batch size: 21, lr: 2.35e-04
2022-05-15 21:26:57,083 INFO [train.py:812] (4/8) Epoch 33, batch 3900, loss[loss=0.1467, simple_loss=0.2304, pruned_loss=0.03151, over 6808.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.03035, over 1428827.13 frames.], batch size: 15, lr: 2.35e-04
2022-05-15 21:27:55,716 INFO [train.py:812] (4/8) Epoch 33, batch 3950, loss[loss=0.1406, simple_loss=0.2336, pruned_loss=0.02383, over 7396.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2446, pruned_loss=0.03036, over 1431341.94 frames.], batch size: 18, lr: 2.34e-04
2022-05-15 21:28:55,478 INFO [train.py:812] (4/8) Epoch 33, batch 4000, loss[loss=0.1496, simple_loss=0.2499, pruned_loss=0.02466, over 6189.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2436, pruned_loss=0.03002, over 1431761.85 frames.], batch size: 38, lr: 2.34e-04
2022-05-15 21:29:54,335 INFO [train.py:812] (4/8) Epoch 33, batch 4050, loss[loss=0.1451, simple_loss=0.2303, pruned_loss=0.02993, over 7283.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.02994, over 1428755.11 frames.], batch size: 18, lr: 2.34e-04
2022-05-15 21:30:52,675 INFO [train.py:812] (4/8) Epoch 33, batch 4100, loss[loss=0.1514, simple_loss=0.2477, pruned_loss=0.02758, over 7192.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.0301, over 1423969.10 frames.], batch size: 26, lr: 2.34e-04
2022-05-15 21:31:50,561 INFO [train.py:812] (4/8) Epoch 33, batch 4150, loss[loss=0.1405, simple_loss=0.2233, pruned_loss=0.0289, over 6776.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03012, over 1423460.40 frames.], batch size: 15, lr: 2.34e-04
2022-05-15 21:32:49,110 INFO [train.py:812] (4/8) Epoch 33, batch 4200, loss[loss=0.1412, simple_loss=0.2356, pruned_loss=0.02336, over 7265.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2433, pruned_loss=0.0299, over 1421313.19 frames.], batch size: 19, lr: 2.34e-04
2022-05-15 21:33:48,269 INFO [train.py:812] (4/8) Epoch 33, batch 4250, loss[loss=0.1536, simple_loss=0.2498, pruned_loss=0.0287, over 7427.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2433, pruned_loss=0.02979, over 1421734.68 frames.], batch size: 20, lr: 2.34e-04
2022-05-15 21:34:46,558 INFO [train.py:812] (4/8) Epoch 33, batch 4300, loss[loss=0.149, simple_loss=0.2447, pruned_loss=0.02669, over 6800.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2428, pruned_loss=0.02989, over 1420014.48 frames.], batch size: 31, lr: 2.34e-04
2022-05-15 21:35:44,812 INFO [train.py:812] (4/8) Epoch 33, batch 4350, loss[loss=0.1358, simple_loss=0.2401, pruned_loss=0.01579, over 7210.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2421, pruned_loss=0.02948, over 1415199.70 frames.], batch size: 21, lr: 2.34e-04
2022-05-15 21:36:43,623 INFO [train.py:812] (4/8) Epoch 33, batch 4400, loss[loss=0.141, simple_loss=0.238, pruned_loss=0.02202, over 7144.00 frames.], tot_loss[loss=0.1505, simple_loss=0.242, pruned_loss=0.0295, over 1414438.79 frames.], batch size: 20, lr: 2.34e-04
2022-05-15 21:37:42,035 INFO [train.py:812] (4/8) Epoch 33, batch 4450, loss[loss=0.1523, simple_loss=0.2528, pruned_loss=0.02592, over 7337.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2427, pruned_loss=0.02991, over 1407734.82 frames.], batch size: 22, lr: 2.34e-04
2022-05-15 21:38:41,153 INFO [train.py:812] (4/8) Epoch 33, batch 4500, loss[loss=0.1522, simple_loss=0.2473, pruned_loss=0.02852, over 7142.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.0297, over 1397746.78 frames.], batch size: 20, lr: 2.34e-04
2022-05-15 21:39:39,857 INFO [train.py:812] (4/8) Epoch 33, batch 4550, loss[loss=0.1734, simple_loss=0.2561, pruned_loss=0.04534, over 5352.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2433, pruned_loss=0.02982, over 1376617.59 frames.], batch size: 52, lr: 2.34e-04
2022-05-15 21:40:52,134 INFO [train.py:812] (4/8) Epoch 34, batch 0, loss[loss=0.1546, simple_loss=0.2392, pruned_loss=0.03498, over 7433.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2392, pruned_loss=0.03498, over 7433.00 frames.], batch size: 20, lr: 2.31e-04
2022-05-15 21:41:51,335 INFO [train.py:812] (4/8) Epoch 34, batch 50, loss[loss=0.1504, simple_loss=0.2526, pruned_loss=0.02416, over 7125.00 frames.], tot_loss[loss=0.148, simple_loss=0.2399, pruned_loss=0.02808, over 325050.57 frames.], batch size: 28, lr: 2.30e-04
2022-05-15 21:42:51,065 INFO [train.py:812] (4/8) Epoch 34, batch 100, loss[loss=0.1473, simple_loss=0.2524, pruned_loss=0.02116, over 7109.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2452, pruned_loss=0.0303, over 566833.15 frames.], batch size: 21, lr: 2.30e-04
2022-05-15 21:43:50,314 INFO [train.py:812] (4/8) Epoch 34, batch 150, loss[loss=0.1475, simple_loss=0.2408, pruned_loss=0.02708, over 7062.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2427, pruned_loss=0.03022, over 755737.81 frames.], batch size: 18, lr: 2.30e-04
2022-05-15 21:44:49,645 INFO [train.py:812] (4/8) Epoch 34, batch 200, loss[loss=0.1352, simple_loss=0.2229, pruned_loss=0.02369, over 7270.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2427, pruned_loss=0.03021, over 905554.75 frames.], batch size: 17, lr: 2.30e-04
2022-05-15 21:45:48,787 INFO [train.py:812] (4/8) Epoch 34, batch 250, loss[loss=0.1547, simple_loss=0.2493, pruned_loss=0.03003, over 4793.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2426, pruned_loss=0.02988, over 1012041.31 frames.], batch size: 52, lr: 2.30e-04
2022-05-15 21:46:48,765 INFO [train.py:812] (4/8) Epoch 34, batch 300, loss[loss=0.1502, simple_loss=0.243, pruned_loss=0.02867, over 7362.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2441, pruned_loss=0.03066, over 1102665.62 frames.], batch size: 23, lr: 2.30e-04
2022-05-15 21:47:46,245 INFO [train.py:812] (4/8) Epoch 34, batch 350, loss[loss=0.1182, simple_loss=0.2136, pruned_loss=0.01142, over 7174.00 frames.], tot_loss[loss=0.1536, simple_loss=0.245, pruned_loss=0.03103, over 1167737.06 frames.], batch size: 17, lr: 2.30e-04
2022-05-15 21:48:46,232 INFO [train.py:812] (4/8) Epoch 34, batch 400, loss[loss=0.1672, simple_loss=0.2588, pruned_loss=0.0378, over 7415.00 frames.], tot_loss[loss=0.1526, simple_loss=0.244, pruned_loss=0.03058, over 1228510.68 frames.], batch size: 21, lr: 2.30e-04
2022-05-15 21:49:44,747 INFO [train.py:812] (4/8) Epoch 34, batch 450, loss[loss=0.137, simple_loss=0.2188, pruned_loss=0.02759, over 7399.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2441, pruned_loss=0.03059, over 1273177.17 frames.], batch size: 18, lr: 2.30e-04
2022-05-15 21:50:44,152 INFO [train.py:812] (4/8) Epoch 34, batch 500, loss[loss=0.1477, simple_loss=0.245, pruned_loss=0.02524, over 7305.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2441, pruned_loss=0.03037, over 1306496.85 frames.], batch size: 24, lr: 2.30e-04
2022-05-15 21:51:42,509 INFO [train.py:812] (4/8) Epoch 34, batch 550, loss[loss=0.1584, simple_loss=0.2531, pruned_loss=0.0318, over 6468.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2441, pruned_loss=0.03058, over 1329628.50 frames.], batch size: 37, lr: 2.30e-04
2022-05-15 21:52:57,381 INFO [train.py:812] (4/8) Epoch 34, batch 600, loss[loss=0.1589, simple_loss=0.2564, pruned_loss=0.03068, over 7299.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2445, pruned_loss=0.03028, over 1352511.41 frames.], batch size: 25, lr: 2.30e-04
2022-05-15 21:53:55,940 INFO [train.py:812] (4/8) Epoch 34, batch 650, loss[loss=0.1453, simple_loss=0.2264, pruned_loss=0.03205, over 7173.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2448, pruned_loss=0.03053, over 1370579.15 frames.], batch size: 18, lr: 2.30e-04
2022-05-15 21:54:54,867 INFO [train.py:812] (4/8) Epoch 34, batch 700, loss[loss=0.1306, simple_loss=0.2138, pruned_loss=0.02369, over 7140.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2437, pruned_loss=0.03032, over 1377888.91 frames.], batch size: 17, lr: 2.30e-04
2022-05-15 21:55:51,397 INFO [train.py:812] (4/8) Epoch 34, batch 750, loss[loss=0.1755, simple_loss=0.2719, pruned_loss=0.03953, over 7165.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2442, pruned_loss=0.03006, over 1389072.09 frames.], batch size: 23, lr: 2.30e-04
2022-05-15 21:56:50,465 INFO [train.py:812] (4/8) Epoch 34, batch 800, loss[loss=0.122, simple_loss=0.2061, pruned_loss=0.01893, over 7271.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2447, pruned_loss=0.0299, over 1394622.73 frames.], batch size: 18, lr: 2.30e-04
2022-05-15 21:57:49,849 INFO [train.py:812] (4/8) Epoch 34, batch 850, loss[loss=0.1508, simple_loss=0.2437, pruned_loss=0.029, over 6547.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2443, pruned_loss=0.0302, over 1404614.73 frames.], batch size: 38, lr: 2.30e-04
2022-05-15 21:58:48,161 INFO [train.py:812] (4/8) Epoch 34, batch 900, loss[loss=0.2185, simple_loss=0.2939, pruned_loss=0.07155, over 5014.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2431, pruned_loss=0.02987, over 1409326.05 frames.], batch size: 52, lr: 2.30e-04
2022-05-15 21:59:45,335 INFO [train.py:812] (4/8) Epoch 34, batch 950, loss[loss=0.1437, simple_loss=0.2342, pruned_loss=0.02656, over 7277.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2429, pruned_loss=0.02983, over 1408010.97 frames.], batch size: 18, lr: 2.30e-04
2022-05-15 22:00:43,723 INFO [train.py:812] (4/8) Epoch 34, batch 1000, loss[loss=0.1498, simple_loss=0.2404, pruned_loss=0.02963, over 7431.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.02924, over 1409872.27 frames.], batch size: 20, lr: 2.30e-04
2022-05-15 22:01:41,766 INFO [train.py:812] (4/8) Epoch 34, batch 1050, loss[loss=0.145, simple_loss=0.2333, pruned_loss=0.02839, over 7150.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02908, over 1415841.51 frames.], batch size: 19, lr: 2.30e-04
2022-05-15 22:02:40,798 INFO [train.py:812] (4/8) Epoch 34, batch 1100, loss[loss=0.1533, simple_loss=0.2507, pruned_loss=0.02797, over 6571.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02895, over 1413821.34 frames.], batch size: 38, lr: 2.30e-04
2022-05-15 22:03:39,420 INFO [train.py:812] (4/8) Epoch 34, batch 1150, loss[loss=0.1461, simple_loss=0.2414, pruned_loss=0.02538, over 7420.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02918, over 1416872.54 frames.], batch size: 20, lr: 2.30e-04
2022-05-15 22:04:38,154 INFO [train.py:812] (4/8) Epoch 34, batch 1200, loss[loss=0.1623, simple_loss=0.2574, pruned_loss=0.03366, over 7194.00 frames.], tot_loss[loss=0.151, simple_loss=0.2426, pruned_loss=0.02968, over 1420973.43 frames.], batch size: 23, lr: 2.30e-04
2022-05-15 22:05:35,713 INFO [train.py:812] (4/8) Epoch 34, batch 1250, loss[loss=0.1492, simple_loss=0.2538, pruned_loss=0.02229, over 7353.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.0296, over 1419273.64 frames.], batch size: 22, lr: 2.30e-04
2022-05-15 22:06:34,736 INFO [train.py:812] (4/8) Epoch 34, batch 1300, loss[loss=0.1498, simple_loss=0.2414, pruned_loss=0.02909, over 7171.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.02949, over 1418977.78 frames.], batch size: 26, lr: 2.30e-04
2022-05-15 22:07:33,215 INFO [train.py:812] (4/8) Epoch 34, batch 1350, loss[loss=0.1575, simple_loss=0.2546, pruned_loss=0.0302, over 7218.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2421, pruned_loss=0.02948, over 1419877.12 frames.], batch size: 21, lr: 2.29e-04
2022-05-15 22:08:32,212 INFO [train.py:812] (4/8) Epoch 34, batch 1400, loss[loss=0.1432, simple_loss=0.2345, pruned_loss=0.02595, over 7261.00 frames.], tot_loss[loss=0.1496, simple_loss=0.241, pruned_loss=0.02912, over 1422952.04 frames.], batch size: 19, lr: 2.29e-04
2022-05-15 22:09:31,083 INFO [train.py:812] (4/8) Epoch 34, batch 1450, loss[loss=0.1551, simple_loss=0.2474, pruned_loss=0.03143, over 7417.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2412, pruned_loss=0.0292, over 1426396.97 frames.], batch size: 21, lr: 2.29e-04
2022-05-15 22:10:29,327 INFO [train.py:812] (4/8) Epoch 34, batch 1500, loss[loss=0.1816, simple_loss=0.2762, pruned_loss=0.0435, over 7393.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2423, pruned_loss=0.02956, over 1424765.53 frames.], batch size: 23, lr: 2.29e-04
2022-05-15 22:11:28,567 INFO [train.py:812] (4/8) Epoch 34, batch 1550, loss[loss=0.1497, simple_loss=0.2398, pruned_loss=0.0298, over 7306.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2428, pruned_loss=0.02991, over 1422098.96 frames.], batch size: 24, lr: 2.29e-04
2022-05-15 22:12:27,928 INFO [train.py:812] (4/8) Epoch 34, batch 1600, loss[loss=0.1309, simple_loss=0.2276, pruned_loss=0.01709, over 7332.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2434, pruned_loss=0.02985, over 1422770.38 frames.], batch size: 20, lr: 2.29e-04
2022-05-15 22:13:26,012 INFO [train.py:812] (4/8) Epoch 34, batch 1650, loss[loss=0.1497, simple_loss=0.2462, pruned_loss=0.0266, over 7218.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2442, pruned_loss=0.03006, over 1422477.18 frames.], batch size: 22, lr: 2.29e-04
2022-05-15 22:14:25,171 INFO [train.py:812] (4/8) Epoch 34, batch 1700, loss[loss=0.1525, simple_loss=0.2443, pruned_loss=0.03038, over 7392.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02967, over 1426387.06 frames.], batch size: 23, lr: 2.29e-04
2022-05-15 22:15:24,023 INFO [train.py:812] (4/8) Epoch 34, batch 1750, loss[loss=0.1513, simple_loss=0.2465, pruned_loss=0.02801, over 7078.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2431, pruned_loss=0.02966, over 1421681.60 frames.], batch size: 28, lr: 2.29e-04
2022-05-15 22:16:22,623 INFO [train.py:812] (4/8) Epoch 34, batch 1800, loss[loss=0.1329, simple_loss=0.2178, pruned_loss=0.02402, over 7286.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2427, pruned_loss=0.02923, over 1423014.02 frames.], batch size: 17, lr: 2.29e-04
2022-05-15 22:17:21,602 INFO [train.py:812] (4/8) Epoch 34, batch 1850, loss[loss=0.1628, simple_loss=0.2591, pruned_loss=0.03321, over 7316.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02944, over 1415489.62 frames.], batch size: 21, lr: 2.29e-04
2022-05-15 22:18:20,749 INFO [train.py:812] (4/8) Epoch 34, batch 1900, loss[loss=0.1455, simple_loss=0.246, pruned_loss=0.02245, over 6793.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.02948, over 1411100.17 frames.], batch size: 31, lr: 2.29e-04
2022-05-15 22:19:17,933 INFO [train.py:812] (4/8) Epoch 34, batch 1950, loss[loss=0.1493, simple_loss=0.2331, pruned_loss=0.03279, over 6980.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2436, pruned_loss=0.03013, over 1417278.59 frames.], batch size: 16, lr: 2.29e-04
2022-05-15 22:20:16,774 INFO [train.py:812] (4/8) Epoch 34, batch 2000, loss[loss=0.1404, simple_loss=0.2275, pruned_loss=0.02665, over 7405.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2431, pruned_loss=0.0299, over 1421545.26 frames.], batch size: 18, lr: 2.29e-04
2022-05-15 22:21:15,737 INFO [train.py:812] (4/8) Epoch 34, batch 2050, loss[loss=0.1615, simple_loss=0.2594, pruned_loss=0.0318, over 7206.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2431, pruned_loss=0.02993, over 1420758.86 frames.], batch size: 26, lr: 2.29e-04
2022-05-15 22:22:14,732 INFO [train.py:812] (4/8) Epoch 34, batch 2100, loss[loss=0.1726, simple_loss=0.2616, pruned_loss=0.04178, over 7217.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02966, over 1423552.53 frames.], batch size: 23, lr: 2.29e-04
2022-05-15 22:23:12,296 INFO [train.py:812] (4/8) Epoch 34, batch 2150, loss[loss=0.1859, simple_loss=0.2679, pruned_loss=0.05192, over 7297.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02977, over 1422981.08 frames.], batch size: 24, lr: 2.29e-04
2022-05-15 22:24:11,547 INFO [train.py:812] (4/8) Epoch 34, batch 2200, loss[loss=0.1371, simple_loss=0.2386, pruned_loss=0.01777, over 7314.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2443, pruned_loss=0.02972, over 1426024.43 frames.], batch size: 21, lr: 2.29e-04
2022-05-15 22:25:10,885 INFO [train.py:812] (4/8) Epoch 34, batch 2250, loss[loss=0.1427, simple_loss=0.224, pruned_loss=0.03069, over 7285.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2446, pruned_loss=0.03001, over 1423090.74 frames.], batch size: 18, lr: 2.29e-04
2022-05-15 22:26:09,579 INFO [train.py:812] (4/8) Epoch 34, batch 2300, loss[loss=0.1371, simple_loss=0.2236, pruned_loss=0.02535, over 7152.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2447, pruned_loss=0.02994, over 1423890.79 frames.], batch size: 19, lr: 2.29e-04
2022-05-15 22:27:07,999 INFO [train.py:812] (4/8) Epoch 34, batch 2350, loss[loss=0.1214, simple_loss=0.2142, pruned_loss=0.01429, over 7154.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.02939, over 1425028.86 frames.], batch size: 19, lr: 2.29e-04
2022-05-15 22:28:06,472 INFO [train.py:812] (4/8) Epoch 34, batch 2400, loss[loss=0.1471, simple_loss=0.2388, pruned_loss=0.02771, over 7374.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2431, pruned_loss=0.02964, over 1426068.11 frames.], batch size: 23, lr: 2.29e-04
2022-05-15 22:29:04,655 INFO [train.py:812] (4/8) Epoch 34, batch 2450, loss[loss=0.1517, simple_loss=0.242, pruned_loss=0.03071, over 7217.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02954, over 1421071.61 frames.], batch size: 21, lr: 2.29e-04
2022-05-15 22:30:04,440 INFO [train.py:812] (4/8) Epoch 34, batch 2500, loss[loss=0.1232, simple_loss=0.206, pruned_loss=0.02015, over 7008.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02943, over 1419379.44 frames.], batch size: 16, lr: 2.29e-04
2022-05-15 22:31:02,276 INFO [train.py:812] (4/8) Epoch 34, batch 2550, loss[loss=0.1448, simple_loss=0.2437, pruned_loss=0.02294, over 7337.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02948, over 1421008.14 frames.], batch size: 22, lr: 2.29e-04
2022-05-15 22:32:00,056 INFO [train.py:812] (4/8) Epoch 34, batch 2600, loss[loss=0.1441, simple_loss=0.2315, pruned_loss=0.02833, over 7060.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02959, over 1419797.16 frames.], batch size: 18, lr: 2.29e-04
2022-05-15 22:32:58,091 INFO [train.py:812] (4/8) Epoch 34, batch 2650, loss[loss=0.1489, simple_loss=0.249, pruned_loss=0.02442, over 7339.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.0296, over 1420557.40 frames.], batch size: 22, lr: 2.29e-04
2022-05-15 22:33:56,978 INFO [train.py:812] (4/8) Epoch 34, batch 2700, loss[loss=0.1353, simple_loss=0.2173, pruned_loss=0.02666, over 7285.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02918, over 1425225.98 frames.], batch size: 18, lr: 2.28e-04
2022-05-15 22:34:55,313 INFO [train.py:812] (4/8) Epoch 34, batch 2750, loss[loss=0.1504, simple_loss=0.247, pruned_loss=0.02693, over 7316.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02972, over 1423561.37 frames.], batch size: 21, lr: 2.28e-04
2022-05-15 22:35:54,064 INFO [train.py:812] (4/8) Epoch 34, batch 2800, loss[loss=0.1372, simple_loss=0.2192, pruned_loss=0.02759, over 7403.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2437, pruned_loss=0.02947, over 1428919.30 frames.], batch size: 18, lr: 2.28e-04
2022-05-15 22:36:52,786 INFO [train.py:812] (4/8) Epoch 34, batch 2850, loss[loss=0.1728, simple_loss=0.2668, pruned_loss=0.03938, over 7223.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2438, pruned_loss=0.02937, over 1430197.74 frames.], batch size: 23, lr: 2.28e-04
2022-05-15 22:37:50,509 INFO [train.py:812] (4/8) Epoch 34, batch 2900, loss[loss=0.1554, simple_loss=0.2497, pruned_loss=0.03054, over 7151.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02905, over 1426590.21 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:38:49,628 INFO [train.py:812] (4/8) Epoch 34, batch 2950, loss[loss=0.1667, simple_loss=0.2611, pruned_loss=0.03617, over 7145.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2425, pruned_loss=0.02911, over 1426351.88 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:39:49,332 INFO [train.py:812] (4/8) Epoch 34, batch 3000, loss[loss=0.16, simple_loss=0.2446, pruned_loss=0.03773, over 7349.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2426, pruned_loss=0.02895, over 1427518.06 frames.], batch size: 19, lr: 2.28e-04
2022-05-15 22:39:49,333 INFO [train.py:832] (4/8) Computing validation loss
2022-05-15 22:39:56,836 INFO [train.py:841] (4/8) Epoch 34, validation: loss=0.1534, simple_loss=0.2492, pruned_loss=0.02878, over 698248.00 frames.
2022-05-15 22:40:55,238 INFO [train.py:812] (4/8) Epoch 34, batch 3050, loss[loss=0.177, simple_loss=0.2647, pruned_loss=0.04466, over 7355.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2435, pruned_loss=0.0292, over 1427744.45 frames.], batch size: 19, lr: 2.28e-04
2022-05-15 22:41:53,724 INFO [train.py:812] (4/8) Epoch 34, batch 3100, loss[loss=0.1359, simple_loss=0.2229, pruned_loss=0.02446, over 7256.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2437, pruned_loss=0.02924, over 1430157.30 frames.], batch size: 16, lr: 2.28e-04
2022-05-15 22:42:52,705 INFO [train.py:812] (4/8) Epoch 34, batch 3150, loss[loss=0.1165, simple_loss=0.1997, pruned_loss=0.01667, over 7288.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02912, over 1430164.57 frames.], batch size: 17, lr: 2.28e-04
2022-05-15 22:43:51,467 INFO [train.py:812] (4/8) Epoch 34, batch 3200, loss[loss=0.168, simple_loss=0.2593, pruned_loss=0.0383, over 5094.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2434, pruned_loss=0.02923, over 1425912.75 frames.], batch size: 52, lr: 2.28e-04
2022-05-15 22:44:49,462 INFO [train.py:812] (4/8) Epoch 34, batch 3250, loss[loss=0.151, simple_loss=0.2492, pruned_loss=0.0264, over 7123.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.0293, over 1423291.26 frames.], batch size: 17, lr: 2.28e-04
2022-05-15 22:45:48,020 INFO [train.py:812] (4/8) Epoch 34, batch 3300, loss[loss=0.1649, simple_loss=0.2663, pruned_loss=0.03176, over 7026.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02972, over 1419634.30 frames.], batch size: 28, lr: 2.28e-04
2022-05-15 22:46:47,344 INFO [train.py:812] (4/8) Epoch 34, batch 3350, loss[loss=0.1473, simple_loss=0.2503, pruned_loss=0.02216, over 7145.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.02929, over 1421909.46 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:47:45,299 INFO [train.py:812] (4/8) Epoch 34, batch 3400, loss[loss=0.1424, simple_loss=0.2418, pruned_loss=0.02154, over 7193.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2415, pruned_loss=0.029, over 1422452.87 frames.], batch size: 23, lr: 2.28e-04
2022-05-15 22:48:43,916 INFO [train.py:812] (4/8) Epoch 34, batch 3450, loss[loss=0.1495, simple_loss=0.2398, pruned_loss=0.0296, over 6996.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2418, pruned_loss=0.02935, over 1427849.20 frames.], batch size: 16, lr: 2.28e-04
2022-05-15 22:49:41,447 INFO [train.py:812] (4/8) Epoch 34, batch 3500, loss[loss=0.1532, simple_loss=0.2349, pruned_loss=0.03575, over 7214.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02937, over 1429425.18 frames.], batch size: 23, lr: 2.28e-04
2022-05-15 22:50:38,745 INFO [train.py:812] (4/8) Epoch 34, batch 3550, loss[loss=0.1178, simple_loss=0.2035, pruned_loss=0.01607, over 7300.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02854, over 1431406.63 frames.], batch size: 17, lr: 2.28e-04
2022-05-15 22:51:37,809 INFO [train.py:812] (4/8) Epoch 34, batch 3600, loss[loss=0.1587, simple_loss=0.2556, pruned_loss=0.0309, over 7320.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02887, over 1432964.14 frames.], batch size: 21, lr: 2.28e-04
2022-05-15 22:52:35,096 INFO [train.py:812] (4/8) Epoch 34, batch 3650, loss[loss=0.1399, simple_loss=0.2337, pruned_loss=0.02305, over 6432.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02897, over 1428072.97 frames.], batch size: 38, lr: 2.28e-04
2022-05-15 22:53:34,819 INFO [train.py:812] (4/8) Epoch 34, batch 3700, loss[loss=0.1513, simple_loss=0.2455, pruned_loss=0.0286, over 7231.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2414, pruned_loss=0.02856, over 1425139.18 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:54:33,390 INFO [train.py:812] (4/8) Epoch 34, batch 3750, loss[loss=0.1525, simple_loss=0.2583, pruned_loss=0.02335, over 7280.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2413, pruned_loss=0.0289, over 1422816.79 frames.], batch size: 24, lr: 2.28e-04
2022-05-15 22:55:32,407 INFO [train.py:812] (4/8) Epoch 34, batch 3800, loss[loss=0.1545, simple_loss=0.2514, pruned_loss=0.02881, over 7142.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02897, over 1426270.56 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:56:31,649 INFO [train.py:812] (4/8) Epoch 34, batch 3850, loss[loss=0.1796, simple_loss=0.2645, pruned_loss=0.04732, over 7200.00 frames.], tot_loss[loss=0.15, simple_loss=0.2417, pruned_loss=0.02913, over 1427754.18 frames.], batch size: 23, lr: 2.28e-04
2022-05-15 22:57:28,734 INFO [train.py:812] (4/8) Epoch 34, batch 3900, loss[loss=0.1657, simple_loss=0.259, pruned_loss=0.0362, over 7205.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2422, pruned_loss=0.02927, over 1426667.48 frames.], batch size: 23, lr: 2.28e-04
2022-05-15 22:58:46,460 INFO [train.py:812] (4/8) Epoch 34, batch 3950, loss[loss=0.1492, simple_loss=0.2429, pruned_loss=0.02781, over 7323.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2431, pruned_loss=0.02961, over 1423594.41 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:59:45,597 INFO [train.py:812] (4/8) Epoch 34, batch 4000, loss[loss=0.1543, simple_loss=0.2373, pruned_loss=0.03569, over 7074.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02986, over 1424539.68 frames.], batch size: 18, lr: 2.28e-04
2022-05-15 23:00:53,099 INFO [train.py:812] (4/8) Epoch 34, batch 4050, loss[loss=0.1444, simple_loss=0.2363, pruned_loss=0.02624, over 7198.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2441, pruned_loss=0.02978, over 1419349.85 frames.], batch size: 26, lr: 2.27e-04
2022-05-15 23:01:51,481 INFO [train.py:812] (4/8) Epoch 34, batch 4100, loss[loss=0.1617, simple_loss=0.2611, pruned_loss=0.03112, over 6203.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.02969, over 1419794.14 frames.], batch size: 37, lr: 2.27e-04
2022-05-15 23:02:49,389 INFO [train.py:812] (4/8) Epoch 34, batch 4150, loss[loss=0.1441, simple_loss=0.2253, pruned_loss=0.03144, over 7428.00 frames.], tot_loss[loss=0.1517, simple_loss=0.244, pruned_loss=0.02969, over 1418317.79 frames.], batch size: 18, lr: 2.27e-04
2022-05-15 23:03:57,835 INFO [train.py:812] (4/8) Epoch 34, batch 4200, loss[loss=0.1718, simple_loss=0.2729, pruned_loss=0.03535, over 7229.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2441, pruned_loss=0.02977, over 1420561.36 frames.], batch size: 20, lr: 2.27e-04
2022-05-15 23:05:06,371 INFO [train.py:812] (4/8) Epoch 34, batch 4250, loss[loss=0.1501, simple_loss=0.2425, pruned_loss=0.0288, over 7141.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2447, pruned_loss=0.03004, over 1420297.37 frames.], batch size: 17, lr: 2.27e-04
2022-05-15 23:06:05,066 INFO [train.py:812] (4/8) Epoch 34, batch 4300, loss[loss=0.1303, simple_loss=0.2124, pruned_loss=0.02409, over 6976.00 frames.], tot_loss[loss=0.152, simple_loss=0.2443, pruned_loss=0.02983, over 1420610.19 frames.], batch size: 16, lr: 2.27e-04
2022-05-15 23:07:13,202 INFO [train.py:812] (4/8) Epoch 34, batch 4350, loss[loss=0.1533, simple_loss=0.2317, pruned_loss=0.0375, over 7193.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2457, pruned_loss=0.03049, over 1416527.33 frames.], batch size: 16, lr: 2.27e-04
2022-05-15 23:08:12,772 INFO [train.py:812] (4/8) Epoch 34, batch 4400, loss[loss=0.1263, simple_loss=0.2197, pruned_loss=0.01641, over 7153.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2438, pruned_loss=0.02975, over 1417769.32 frames.], batch size: 18, lr: 2.27e-04
2022-05-15 23:09:11,168 INFO [train.py:812] (4/8) Epoch 34, batch 4450, loss[loss=0.1652, simple_loss=0.2656, pruned_loss=0.03242, over 7196.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.03008, over 1402768.51 frames.], batch size: 23, lr: 2.27e-04
2022-05-15 23:10:19,474 INFO [train.py:812] (4/8) Epoch 34, batch 4500, loss[loss=0.202, simple_loss=0.2905, pruned_loss=0.05674, over 4679.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2436, pruned_loss=0.03011, over 1393564.21 frames.], batch size: 53, lr: 2.27e-04
2022-05-15 23:11:16,026 INFO [train.py:812] (4/8) Epoch 34, batch 4550, loss[loss=0.163, simple_loss=0.2519, pruned_loss=0.03702, over 4813.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2457, pruned_loss=0.0307, over 1352783.96 frames.], batch size: 53, lr: 2.27e-04
2022-05-15 23:12:20,549 INFO [train.py:812] (4/8) Epoch 35, batch 0, loss[loss=0.1653, simple_loss=0.2663, pruned_loss=0.03211, over 7232.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2663, pruned_loss=0.03211, over 7232.00 frames.], batch size: 20, lr: 2.24e-04
2022-05-15 23:13:24,534 INFO [train.py:812] (4/8) Epoch 35, batch 50, loss[loss=0.1509, simple_loss=0.2464, pruned_loss=0.02767, over 7302.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2459, pruned_loss=0.03166, over 317609.43 frames.], batch size: 24, lr: 2.24e-04
2022-05-15 23:14:23,048 INFO [train.py:812] (4/8) Epoch 35, batch 100, loss[loss=0.1601, simple_loss=0.2614, pruned_loss=0.02945, over 7176.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2432, pruned_loss=0.02997, over 566986.02 frames.], batch size: 26, lr: 2.24e-04
2022-05-15 23:15:22,490 INFO [train.py:812] (4/8) Epoch 35, batch 150, loss[loss=0.1642, simple_loss=0.2588, pruned_loss=0.03486, over 7381.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2443, pruned_loss=0.0299, over 760141.60 frames.], batch size: 23, lr: 2.24e-04
2022-05-15 23:16:21,271 INFO [train.py:812] (4/8) Epoch 35, batch 200, loss[loss=0.1485, simple_loss=0.2389, pruned_loss=0.02907, over 7062.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2438, pruned_loss=0.02977, over 909183.09 frames.], batch size: 18, lr: 2.24e-04
2022-05-15 23:17:21,139 INFO [train.py:812] (4/8) Epoch 35, batch 250, loss[loss=0.1341, simple_loss=0.2252, pruned_loss=0.02144, over 7235.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2437, pruned_loss=0.02986, over 1026448.56 frames.], batch size: 20, lr: 2.24e-04
2022-05-15 23:18:18,840 INFO [train.py:812] (4/8) Epoch 35, batch 300, loss[loss=0.1387, simple_loss=0.227, pruned_loss=0.02522, over 7157.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2426, pruned_loss=0.02975, over 1113077.40 frames.], batch size: 19, lr: 2.24e-04
2022-05-15 23:19:18,457 INFO [train.py:812] (4/8) Epoch 35, batch 350, loss[loss=0.1501, simple_loss=0.2493, pruned_loss=0.02542, over 7206.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2416, pruned_loss=0.02942, over 1184970.46 frames.], batch size: 23, lr: 2.24e-04
2022-05-15 23:20:16,882 INFO [train.py:812] (4/8) Epoch 35, batch 400, loss[loss=0.1743, simple_loss=0.2597, pruned_loss=0.04443, over 7322.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.02936, over 1239013.62 frames.], batch size: 20, lr: 2.24e-04
2022-05-15 23:21:15,057 INFO [train.py:812] (4/8) Epoch 35, batch 450, loss[loss=0.1797, simple_loss=0.2854, pruned_loss=0.03699, over 6692.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.02923, over 1283434.70 frames.], batch size: 31, lr: 2.24e-04
2022-05-15 23:22:13,112 INFO [train.py:812] (4/8) Epoch 35, batch 500, loss[loss=0.1381, simple_loss=0.2316, pruned_loss=0.02236, over 7327.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2425, pruned_loss=0.0294, over 1312781.49 frames.], batch size: 20, lr: 2.23e-04
2022-05-15 23:23:12,694 INFO [train.py:812] (4/8) Epoch 35, batch 550, loss[loss=0.1211, simple_loss=0.2029, pruned_loss=0.01961, over 7076.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2417, pruned_loss=0.02903, over 1334020.10 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:24:10,902 INFO [train.py:812] (4/8) Epoch 35, batch 600, loss[loss=0.1407, simple_loss=0.2313, pruned_loss=0.0251, over 7333.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2419, pruned_loss=0.02918, over 1353136.20 frames.], batch size: 22, lr: 2.23e-04
2022-05-15 23:25:10,092 INFO [train.py:812] (4/8) Epoch 35, batch 650, loss[loss=0.1315, simple_loss=0.2262, pruned_loss=0.01843, over 7163.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.02918, over 1372177.76 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:26:08,926 INFO [train.py:812] (4/8) Epoch 35, batch 700, loss[loss=0.1505, simple_loss=0.241, pruned_loss=0.03002, over 7293.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02931, over 1386662.09 frames.], batch size: 17, lr: 2.23e-04
2022-05-15 23:27:08,860 INFO [train.py:812] (4/8) Epoch 35, batch 750, loss[loss=0.1556, simple_loss=0.2439, pruned_loss=0.03372, over 7258.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2419, pruned_loss=0.0294, over 1393978.82 frames.], batch size: 19, lr: 2.23e-04
2022-05-15 23:28:07,093 INFO [train.py:812] (4/8) Epoch 35, batch 800, loss[loss=0.1644, simple_loss=0.2644, pruned_loss=0.03221, over 7223.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2423, pruned_loss=0.02944, over 1403165.37 frames.], batch size: 21, lr: 2.23e-04
2022-05-15 23:29:06,745 INFO [train.py:812] (4/8) Epoch 35, batch 850, loss[loss=0.1598, simple_loss=0.2585, pruned_loss=0.03057, over 7282.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2427, pruned_loss=0.0294, over 1403054.09 frames.], batch size: 24, lr: 2.23e-04
2022-05-15 23:30:05,625 INFO [train.py:812] (4/8) Epoch 35, batch 900, loss[loss=0.1813, simple_loss=0.2613, pruned_loss=0.0506, over 5108.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02906, over 1406376.64 frames.], batch size: 52, lr: 2.23e-04
2022-05-15 23:31:04,512 INFO [train.py:812] (4/8) Epoch 35, batch 950, loss[loss=0.1382, simple_loss=0.2243, pruned_loss=0.02603, over 7262.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2417, pruned_loss=0.02894, over 1410518.06 frames.], batch size: 19, lr: 2.23e-04
2022-05-15 23:32:02,593 INFO [train.py:812] (4/8) Epoch 35, batch 1000, loss[loss=0.1688, simple_loss=0.2668, pruned_loss=0.03536, over 6750.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.02942, over 1412099.13 frames.], batch size: 31, lr: 2.23e-04
2022-05-15 23:33:01,221 INFO [train.py:812] (4/8) Epoch 35, batch 1050, loss[loss=0.1692, simple_loss=0.2722, pruned_loss=0.03308, over 7411.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02921, over 1416320.73 frames.], batch size: 21, lr: 2.23e-04
2022-05-15 23:33:59,697 INFO [train.py:812] (4/8) Epoch 35, batch 1100, loss[loss=0.154, simple_loss=0.2407, pruned_loss=0.03369, over 7350.00 frames.], tot_loss[loss=0.1499, simple_loss=0.242, pruned_loss=0.0289, over 1420019.24 frames.], batch size: 19, lr: 2.23e-04
2022-05-15 23:34:58,671 INFO [train.py:812] (4/8) Epoch 35, batch 1150, loss[loss=0.1522, simple_loss=0.2445, pruned_loss=0.02997, over 7205.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.0289, over 1421797.22 frames.], batch size: 23, lr: 2.23e-04
2022-05-15 23:35:56,584 INFO [train.py:812] (4/8) Epoch 35, batch 1200, loss[loss=0.1353, simple_loss=0.2188, pruned_loss=0.02589, over 7274.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02884, over 1425766.54 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:36:55,000 INFO [train.py:812] (4/8) Epoch 35, batch 1250, loss[loss=0.1719, simple_loss=0.286, pruned_loss=0.02892, over 7329.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02877, over 1425077.70 frames.], batch size: 22, lr: 2.23e-04
2022-05-15 23:37:53,439 INFO [train.py:812] (4/8) Epoch 35, batch 1300, loss[loss=0.146, simple_loss=0.2402, pruned_loss=0.02597, over 7014.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2432, pruned_loss=0.02924, over 1421230.40 frames.], batch size: 28, lr: 2.23e-04
2022-05-15 23:38:52,780 INFO [train.py:812] (4/8) Epoch 35, batch 1350, loss[loss=0.1533, simple_loss=0.2537, pruned_loss=0.02651, over 7047.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02932, over 1423852.12 frames.], batch size: 28, lr: 2.23e-04
2022-05-15 23:39:51,265 INFO [train.py:812] (4/8) Epoch 35, batch 1400, loss[loss=0.126, simple_loss=0.2164, pruned_loss=0.01785, over 7315.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02964, over 1421153.25 frames.], batch size: 20, lr: 2.23e-04
2022-05-15 23:40:50,641 INFO [train.py:812] (4/8) Epoch 35, batch 1450, loss[loss=0.1559, simple_loss=0.249, pruned_loss=0.0314, over 7265.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2433, pruned_loss=0.03001, over 1418456.49 frames.], batch size: 19, lr: 2.23e-04
2022-05-15 23:41:50,033 INFO [train.py:812] (4/8) Epoch 35, batch 1500, loss[loss=0.1434, simple_loss=0.2272, pruned_loss=0.02978, over 7132.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02981, over 1419596.01 frames.], batch size: 17, lr: 2.23e-04
2022-05-15 23:42:48,887 INFO [train.py:812] (4/8) Epoch 35, batch 1550, loss[loss=0.1914, simple_loss=0.2988, pruned_loss=0.04205, over 7226.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2438, pruned_loss=0.02955, over 1420037.11 frames.], batch size: 21, lr: 2.23e-04
2022-05-15 23:43:47,277 INFO [train.py:812] (4/8) Epoch 35, batch 1600, loss[loss=0.152, simple_loss=0.2584, pruned_loss=0.02284, over 7119.00 frames.], tot_loss[loss=0.1505, simple_loss=0.243, pruned_loss=0.02904, over 1422217.46 frames.], batch size: 28, lr: 2.23e-04
2022-05-15 23:44:46,445 INFO [train.py:812] (4/8) Epoch 35, batch 1650, loss[loss=0.159, simple_loss=0.2371, pruned_loss=0.04043, over 7402.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02897, over 1426649.49 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:45:45,299 INFO [train.py:812] (4/8) Epoch 35, batch 1700, loss[loss=0.1864, simple_loss=0.2685, pruned_loss=0.05222, over 5277.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02901, over 1426258.12 frames.], batch size: 52, lr: 2.23e-04
2022-05-15 23:46:45,282 INFO [train.py:812] (4/8) Epoch 35, batch 1750, loss[loss=0.1366, simple_loss=0.2287, pruned_loss=0.02225, over 7164.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02857, over 1425872.33 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:47:44,625 INFO [train.py:812] (4/8) Epoch 35, batch 1800, loss[loss=0.1587, simple_loss=0.2543, pruned_loss=0.03153, over 7277.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2405, pruned_loss=0.02837, over 1429587.24 frames.], batch size: 25, lr: 2.23e-04
2022-05-15 23:48:43,683 INFO [train.py:812] (4/8) Epoch 35, batch 1850, loss[loss=0.1551, simple_loss=0.243, pruned_loss=0.0336, over 7061.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2405, pruned_loss=0.02854, over 1426174.91 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:49:42,139 INFO [train.py:812] (4/8) Epoch 35, batch 1900, loss[loss=0.1468, simple_loss=0.2441, pruned_loss=0.02475, over 7383.00 frames.], tot_loss[loss=0.1493, simple_loss=0.241, pruned_loss=0.0288, over 1426426.39 frames.], batch size: 23, lr: 2.22e-04
2022-05-15 23:50:50,963 INFO [train.py:812] (4/8) Epoch 35, batch 1950, loss[loss=0.1397, simple_loss=0.2247, pruned_loss=0.02731, over 7142.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2412, pruned_loss=0.02885, over 1424957.55 frames.], batch size: 18, lr: 2.22e-04
2022-05-15 23:51:48,107 INFO [train.py:812] (4/8) Epoch 35, batch 2000, loss[loss=0.1356, simple_loss=0.236, pruned_loss=0.01759, over 6639.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2423, pruned_loss=0.02937, over 1420848.22 frames.], batch size: 38, lr: 2.22e-04
2022-05-15 23:52:46,854 INFO [train.py:812] (4/8) Epoch 35, batch 2050, loss[loss=0.1418, simple_loss=0.2385, pruned_loss=0.0225, over 7115.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02941, over 1422348.26 frames.], batch size: 21, lr: 2.22e-04
2022-05-15 23:53:45,615 INFO [train.py:812] (4/8) Epoch 35, batch 2100, loss[loss=0.1613, simple_loss=0.2549, pruned_loss=0.03389, over 7426.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02957, over 1425153.49 frames.], batch size: 21, lr: 2.22e-04
2022-05-15 23:54:43,310 INFO [train.py:812] (4/8) Epoch 35, batch 2150, loss[loss=0.156, simple_loss=0.2478, pruned_loss=0.03214, over 6200.00 frames.], tot_loss[loss=0.151, simple_loss=0.2436, pruned_loss=0.0292, over 1427858.34 frames.], batch size: 37, lr: 2.22e-04
2022-05-15 23:55:40,412 INFO [train.py:812] (4/8) Epoch 35, batch 2200, loss[loss=0.1443, simple_loss=0.2401, pruned_loss=0.02428, over 7434.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.02924, over 1424560.27 frames.], batch size: 20, lr: 2.22e-04
2022-05-15 23:56:39,586 INFO [train.py:812] (4/8) Epoch 35, batch 2250, loss[loss=0.1405, simple_loss=0.22, pruned_loss=0.03047, over 7276.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2429, pruned_loss=0.02891, over 1422343.78 frames.], batch size: 18, lr: 2.22e-04
2022-05-15 23:57:38,203 INFO [train.py:812] (4/8) Epoch 35, batch 2300, loss[loss=0.1655, simple_loss=0.2586, pruned_loss=0.0362, over 7166.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02936, over 1418655.86 frames.], batch size: 26, lr: 2.22e-04
2022-05-15 23:58:36,529 INFO [train.py:812] (4/8) Epoch 35, batch 2350, loss[loss=0.1548, simple_loss=0.2616, pruned_loss=0.02399, over 7123.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2433, pruned_loss=0.02912, over 1416666.82 frames.], batch size: 28, lr: 2.22e-04
2022-05-15 23:59:34,365 INFO [train.py:812] (4/8) Epoch 35, batch 2400, loss[loss=0.1158, simple_loss=0.1998, pruned_loss=0.0159, over 7009.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2428, pruned_loss=0.0289, over 1422368.34 frames.], batch size: 16, lr: 2.22e-04
2022-05-16 00:00:32,007 INFO [train.py:812] (4/8) Epoch 35, batch 2450, loss[loss=0.1469, simple_loss=0.237, pruned_loss=0.02839, over 7429.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2421, pruned_loss=0.02872, over 1422597.99 frames.], batch size: 20, lr: 2.22e-04
2022-05-16 00:01:31,447 INFO [train.py:812] (4/8) Epoch 35, batch 2500, loss[loss=0.1766, simple_loss=0.2682, pruned_loss=0.04244, over 6515.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2415, pruned_loss=0.02869, over 1423951.32 frames.], batch size: 38, lr: 2.22e-04
2022-05-16 00:02:30,465 INFO [train.py:812] (4/8) Epoch 35, batch 2550, loss[loss=0.1554, simple_loss=0.2559, pruned_loss=0.02743, over 7106.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2425, pruned_loss=0.02884, over 1423997.38 frames.], batch size: 21, lr: 2.22e-04
2022-05-16 00:03:28,742 INFO [train.py:812] (4/8) Epoch 35, batch 2600, loss[loss=0.1869, simple_loss=0.2764, pruned_loss=0.04866, over 7198.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.0288, over 1424306.42 frames.], batch size: 22, lr: 2.22e-04
2022-05-16 00:04:26,537 INFO [train.py:812] (4/8) Epoch 35, batch 2650, loss[loss=0.1836, simple_loss=0.2723, pruned_loss=0.04742, over 7190.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2423, pruned_loss=0.02937, over 1422743.91 frames.], batch size: 23, lr: 2.22e-04
2022-05-16 00:05:25,225 INFO [train.py:812] (4/8) Epoch 35, batch 2700, loss[loss=0.1727, simple_loss=0.2622, pruned_loss=0.04163, over 7112.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02941, over 1424543.98 frames.], batch size: 21, lr: 2.22e-04
2022-05-16 00:06:24,239 INFO [train.py:812] (4/8) Epoch 35, batch 2750, loss[loss=0.1439, simple_loss=0.2365, pruned_loss=0.02565, over 7318.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02954, over 1424180.39 frames.], batch size: 21, lr: 2.22e-04
2022-05-16 00:07:23,140 INFO [train.py:812] (4/8) Epoch 35, batch 2800, loss[loss=0.1398, simple_loss=0.2292, pruned_loss=0.02518, over 7332.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.0298, over 1425189.81 frames.], batch size: 20, lr: 2.22e-04
2022-05-16 00:08:20,731 INFO [train.py:812] (4/8) Epoch 35, batch 2850, loss[loss=0.1598, simple_loss=0.2549, pruned_loss=0.03237, over 7155.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2444, pruned_loss=0.03006, over 1423835.40 frames.], batch size: 19, lr: 2.22e-04
2022-05-16 00:09:20,167 INFO [train.py:812] (4/8) Epoch 35, batch 2900, loss[loss=0.1463, simple_loss=0.2394, pruned_loss=0.02658, over 6387.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.02979, over 1422609.11 frames.], batch size: 38, lr: 2.22e-04
2022-05-16 00:10:18,321 INFO [train.py:812] (4/8) Epoch 35, batch 2950, loss[loss=0.1405, simple_loss=0.2174, pruned_loss=0.03177, over 6822.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2443, pruned_loss=0.02999, over 1416405.17 frames.], batch size: 15, lr: 2.22e-04
2022-05-16 00:11:17,559 INFO [train.py:812] (4/8) Epoch 35, batch 3000, loss[loss=0.1936, simple_loss=0.2752, pruned_loss=0.05599, over 7379.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02979, over 1420575.04 frames.], batch size: 23, lr: 2.22e-04
2022-05-16 00:11:17,560 INFO [train.py:832] (4/8) Computing validation loss
2022-05-16 00:11:25,088 INFO [train.py:841] (4/8) Epoch 35, validation: loss=0.1528, simple_loss=0.2485, pruned_loss=0.02851, over 698248.00 frames.
2022-05-16 00:12:24,403 INFO [train.py:812] (4/8) Epoch 35, batch 3050, loss[loss=0.1444, simple_loss=0.2395, pruned_loss=0.02463, over 7241.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2433, pruned_loss=0.02921, over 1423424.54 frames.], batch size: 20, lr: 2.22e-04
2022-05-16 00:13:22,722 INFO [train.py:812] (4/8) Epoch 35, batch 3100, loss[loss=0.1685, simple_loss=0.2523, pruned_loss=0.04234, over 7377.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2433, pruned_loss=0.02955, over 1420598.32 frames.], batch size: 23, lr: 2.22e-04
2022-05-16 00:14:22,593 INFO [train.py:812] (4/8) Epoch 35, batch 3150, loss[loss=0.1679, simple_loss=0.2615, pruned_loss=0.03718, over 7211.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02944, over 1424147.70 frames.], batch size: 22, lr: 2.22e-04
2022-05-16 00:15:21,759 INFO [train.py:812] (4/8) Epoch 35, batch 3200, loss[loss=0.1493, simple_loss=0.243, pruned_loss=0.02774, over 7222.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2433, pruned_loss=0.02923, over 1428167.00 frames.], batch size: 22, lr: 2.22e-04
2022-05-16 00:16:21,594 INFO [train.py:812] (4/8) Epoch 35, batch 3250, loss[loss=0.1422, simple_loss=0.2282, pruned_loss=0.02806, over 7438.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02937, over 1427125.30 frames.], batch size: 20, lr: 2.22e-04
2022-05-16 00:17:21,159 INFO [train.py:812] (4/8) Epoch 35, batch 3300, loss[loss=0.1486, simple_loss=0.2394, pruned_loss=0.02891, over 7437.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2439, pruned_loss=0.02967, over 1428718.65 frames.], batch size: 20, lr: 2.22e-04
2022-05-16 00:18:19,927 INFO [train.py:812] (4/8) Epoch 35, batch 3350, loss[loss=0.1508, simple_loss=0.2448, pruned_loss=0.02839, over 7432.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2436, pruned_loss=0.02934, over 1431931.98 frames.], batch size: 20, lr: 2.21e-04
2022-05-16 00:19:17,058 INFO [train.py:812] (4/8) Epoch 35, batch 3400, loss[loss=0.1274, simple_loss=0.2243, pruned_loss=0.01523, over 7282.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02914, over 1429043.47 frames.], batch size: 18, lr: 2.21e-04
2022-05-16 00:20:15,917 INFO [train.py:812] (4/8) Epoch 35, batch 3450, loss[loss=0.1279, simple_loss=0.2114, pruned_loss=0.02226, over 7014.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02911, over 1431565.93 frames.], batch size: 16, lr: 2.21e-04
2022-05-16 00:21:14,738 INFO [train.py:812] (4/8) Epoch 35, batch 3500, loss[loss=0.1764, simple_loss=0.2625, pruned_loss=0.04517, over 7336.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2424, pruned_loss=0.02887, over 1429957.10 frames.], batch size: 22, lr: 2.21e-04
2022-05-16 00:22:12,835 INFO [train.py:812] (4/8) Epoch 35, batch 3550, loss[loss=0.1476, simple_loss=0.2483, pruned_loss=0.02345, over 6768.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2418, pruned_loss=0.02883, over 1422442.45 frames.], batch size: 31, lr: 2.21e-04
2022-05-16 00:23:10,734 INFO [train.py:812] (4/8) Epoch 35, batch 3600, loss[loss=0.1787, simple_loss=0.267, pruned_loss=0.04515, over 7206.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02882, over 1421001.24 frames.], batch size: 22, lr: 2.21e-04
2022-05-16 00:24:08,625 INFO [train.py:812] (4/8) Epoch 35, batch 3650, loss[loss=0.1609, simple_loss=0.2502, pruned_loss=0.03577, over 7315.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.02886, over 1422019.27 frames.], batch size: 25, lr: 2.21e-04
2022-05-16 00:25:06,957 INFO [train.py:812] (4/8) Epoch 35, batch 3700, loss[loss=0.1434, simple_loss=0.2447, pruned_loss=0.02099, over 6457.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.0288, over 1420738.19 frames.], batch size: 37, lr: 2.21e-04
2022-05-16 00:26:05,696 INFO [train.py:812] (4/8) Epoch 35, batch 3750, loss[loss=0.1976, simple_loss=0.281, pruned_loss=0.05712, over 4977.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02897, over 1418062.55 frames.], batch size: 52, lr: 2.21e-04
2022-05-16 00:27:04,274 INFO [train.py:812] (4/8) Epoch 35, batch 3800, loss[loss=0.1652, simple_loss=0.2621, pruned_loss=0.03414, over 6767.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2428, pruned_loss=0.02888, over 1418857.66 frames.], batch size: 31, lr: 2.21e-04
2022-05-16 00:28:02,106 INFO [train.py:812] (4/8) Epoch 35, batch 3850, loss[loss=0.1751, simple_loss=0.2649, pruned_loss=0.04259, over 7289.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02909, over 1422123.18 frames.], batch size: 24, lr: 2.21e-04
2022-05-16 00:29:00,965 INFO [train.py:812] (4/8) Epoch 35, batch 3900, loss[loss=0.1412, simple_loss=0.224, pruned_loss=0.02922, over 6787.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2437, pruned_loss=0.02907, over 1418075.36 frames.], batch size: 15, lr: 2.21e-04
2022-05-16 00:30:00,065 INFO [train.py:812] (4/8) Epoch 35, batch 3950, loss[loss=0.1462, simple_loss=0.2223, pruned_loss=0.03507, over 7137.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2435, pruned_loss=0.02913, over 1419690.62 frames.], batch size: 17, lr: 2.21e-04
2022-05-16 00:30:58,309 INFO [train.py:812] (4/8) Epoch 35, batch 4000, loss[loss=0.1359, simple_loss=0.2152, pruned_loss=0.0283, over 7001.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.02931, over 1419038.17 frames.], batch size: 16, lr: 2.21e-04
2022-05-16 00:32:02,096 INFO [train.py:812] (4/8) Epoch 35, batch 4050, loss[loss=0.1534, simple_loss=0.2566, pruned_loss=0.02514, over 6298.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02908, over 1422131.06 frames.], batch size: 37, lr: 2.21e-04
2022-05-16 00:33:00,888 INFO [train.py:812] (4/8) Epoch 35, batch 4100, loss[loss=0.1423, simple_loss=0.2363, pruned_loss=0.02418, over 7214.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.02876, over 1426685.77 frames.], batch size: 21, lr: 2.21e-04
2022-05-16 00:33:59,518 INFO [train.py:812] (4/8) Epoch 35, batch 4150, loss[loss=0.1437, simple_loss=0.2346, pruned_loss=0.02638, over 7316.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02875, over 1424724.60 frames.], batch size: 21, lr: 2.21e-04
2022-05-16 00:34:58,349 INFO [train.py:812] (4/8) Epoch 35, batch 4200, loss[loss=0.1473, simple_loss=0.2453, pruned_loss=0.02467, over 7319.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2429, pruned_loss=0.02906, over 1423134.36 frames.], batch size: 21, lr: 2.21e-04
2022-05-16 00:35:57,139 INFO [train.py:812] (4/8) Epoch 35, batch 4250, loss[loss=0.1276, simple_loss=0.2139, pruned_loss=0.02069, over 7284.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2418, pruned_loss=0.02862, over 1427770.31 frames.], batch size: 17, lr: 2.21e-04
2022-05-16 00:36:55,267 INFO [train.py:812] (4/8) Epoch 35, batch 4300, loss[loss=0.16, simple_loss=0.2642, pruned_loss=0.02794, over 7151.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02882, over 1419024.69 frames.], batch size: 26, lr: 2.21e-04
2022-05-16 00:37:53,246 INFO [train.py:812] (4/8) Epoch 35, batch 4350, loss[loss=0.1498, simple_loss=0.249, pruned_loss=0.02527, over 7281.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.02925, over 1414507.56 frames.], batch size: 24, lr: 2.21e-04
2022-05-16 00:38:52,040 INFO [train.py:812] (4/8) Epoch 35, batch 4400, loss[loss=0.1379, simple_loss=0.2355, pruned_loss=0.02015, over 7166.00 frames.], tot_loss[loss=0.151, simple_loss=0.2432, pruned_loss=0.02939, over 1408857.65 frames.], batch size: 19, lr: 2.21e-04
2022-05-16 00:39:50,152 INFO [train.py:812] (4/8) Epoch 35, batch 4450, loss[loss=0.1469, simple_loss=0.2455, pruned_loss=0.02418, over 6831.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02966, over 1393963.81 frames.], batch size: 31, lr: 2.21e-04
2022-05-16 00:40:48,511 INFO [train.py:812] (4/8) Epoch 35, batch 4500, loss[loss=0.1708, simple_loss=0.262, pruned_loss=0.03978, over 7187.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03031, over 1380886.18 frames.], batch size: 26, lr: 2.21e-04
2022-05-16 00:41:45,667 INFO [train.py:812] (4/8) Epoch 35, batch 4550, loss[loss=0.162, simple_loss=0.2519, pruned_loss=0.03609, over 4875.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2467, pruned_loss=0.03126, over 1355457.40 frames.], batch size: 53, lr: 2.21e-04
2022-05-16 00:42:50,923 INFO [train.py:812] (4/8) Epoch 36, batch 0, loss[loss=0.134, simple_loss=0.2291, pruned_loss=0.01945, over 7342.00 frames.], tot_loss[loss=0.134, simple_loss=0.2291, pruned_loss=0.01945, over 7342.00 frames.], batch size: 20, lr: 2.18e-04
2022-05-16 00:43:50,521 INFO [train.py:812] (4/8) Epoch 36, batch 50, loss[loss=0.1483, simple_loss=0.2391, pruned_loss=0.02881, over 7418.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2408, pruned_loss=0.02939, over 316325.16 frames.], batch size: 20, lr: 2.18e-04
2022-05-16 00:44:48,785 INFO [train.py:812] (4/8) Epoch 36, batch 100, loss[loss=0.1724, simple_loss=0.2591, pruned_loss=0.04284, over 4849.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2407, pruned_loss=0.02803, over 561351.72 frames.], batch size: 52, lr: 2.17e-04
2022-05-16 00:45:47,238 INFO [train.py:812] (4/8) Epoch 36, batch 150, loss[loss=0.1264, simple_loss=0.2211, pruned_loss=0.01582, over 7234.00 frames.], tot_loss[loss=0.1484, simple_loss=0.24, pruned_loss=0.02837, over 750116.94 frames.], batch size: 20, lr: 2.17e-04
2022-05-16 00:46:46,335 INFO [train.py:812] (4/8) Epoch 36, batch 200, loss[loss=0.1429, simple_loss=0.2429, pruned_loss=0.02145, over 7317.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02881, over 900273.30 frames.], batch size: 21, lr: 2.17e-04
2022-05-16 00:47:45,335 INFO [train.py:812] (4/8) Epoch 36, batch 250, loss[loss=0.1261, simple_loss=0.2128, pruned_loss=0.01966, over 7151.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2404, pruned_loss=0.02853, over 1020133.80 frames.], batch size: 19, lr: 2.17e-04
2022-05-16 00:48:43,650 INFO [train.py:812] (4/8) Epoch 36, batch 300, loss[loss=0.1527, simple_loss=0.2499, pruned_loss=0.02774, over 7183.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2414, pruned_loss=0.02868, over 1105227.55 frames.], batch size: 26, lr: 2.17e-04
2022-05-16 00:49:42,221 INFO [train.py:812] (4/8) Epoch 36, batch 350, loss[loss=0.1557, simple_loss=0.2513, pruned_loss=0.03006, over 6707.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2417, pruned_loss=0.02843, over 1174549.64 frames.], batch size: 31, lr: 2.17e-04
2022-05-16 00:50:40,200 INFO [train.py:812] (4/8) Epoch 36, batch 400, loss[loss=0.1918, simple_loss=0.2829, pruned_loss=0.05035, over 7203.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.0291, over 1230995.24 frames.], batch size: 22, lr: 2.17e-04
2022-05-16 00:51:39,745 INFO [train.py:812] (4/8) Epoch 36, batch 450, loss[loss=0.1573, simple_loss=0.2554, pruned_loss=0.02962, over 7157.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2437, pruned_loss=0.02948, over 1278783.08 frames.], batch size: 26, lr: 2.17e-04
2022-05-16 00:52:38,607 INFO [train.py:812] (4/8) Epoch 36, batch 500, loss[loss=0.172, simple_loss=0.2655, pruned_loss=0.03924, over 7187.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2447, pruned_loss=0.02931, over 1310802.81 frames.], batch size: 23, lr: 2.17e-04
2022-05-16 00:53:37,434 INFO [train.py:812] (4/8) Epoch 36, batch 550, loss[loss=0.1365, simple_loss=0.2255, pruned_loss=0.02377, over 7437.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2451, pruned_loss=0.02951, over 1336699.17 frames.], batch size: 20, lr: 2.17e-04
2022-05-16 00:54:35,754 INFO [train.py:812] (4/8) Epoch 36, batch 600, loss[loss=0.1653, simple_loss=0.2492, pruned_loss=0.04076, over 7222.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2433, pruned_loss=0.02915, over 1359055.77 frames.], batch size: 23, lr: 2.17e-04
2022-05-16 00:55:34,860 INFO [train.py:812] (4/8) Epoch 36, batch 650, loss[loss=0.1148, simple_loss=0.2117, pruned_loss=0.008944, over 7160.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.02919, over 1373512.06 frames.], batch size: 19, lr: 2.17e-04
2022-05-16 00:56:33,802 INFO [train.py:812] (4/8) Epoch 36, batch 700, loss[loss=0.1422, simple_loss=0.2335, pruned_loss=0.02548, over 7252.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02915, over 1385518.38 frames.], batch size: 19, lr: 2.17e-04
2022-05-16 00:57:42,576 INFO [train.py:812] (4/8) Epoch 36, batch 750, loss[loss=0.1494, simple_loss=0.2451, pruned_loss=0.02684, over 7329.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.02931, over 1385569.30 frames.], batch size: 20, lr: 2.17e-04
2022-05-16 00:58:59,878 INFO [train.py:812] (4/8) Epoch 36, batch 800, loss[loss=0.1409, simple_loss=0.2399, pruned_loss=0.02092, over 7415.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.0291, over 1393639.66 frames.], batch size: 21, lr: 2.17e-04
2022-05-16 00:59:58,242 INFO [train.py:812] (4/8) Epoch 36, batch 850, loss[loss=0.1519, simple_loss=0.2537, pruned_loss=0.02499, over 7226.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02915, over 1394699.21 frames.], batch size: 21, lr: 2.17e-04
2022-05-16 01:00:57,362 INFO [train.py:812] (4/8) Epoch 36, batch 900, loss[loss=0.1437, simple_loss=0.2423, pruned_loss=0.02254, over 6875.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2422, pruned_loss=0.02878, over 1401564.73 frames.], batch size: 31, lr: 2.17e-04
2022-05-16 01:01:55,212 INFO [train.py:812] (4/8) Epoch 36, batch 950, loss[loss=0.132, simple_loss=0.2142, pruned_loss=0.02487, over 6988.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2427, pruned_loss=0.029, over 1404981.42 frames.], batch size: 16, lr: 2.17e-04
2022-05-16 01:03:03,139 INFO [train.py:812] (4/8) Epoch 36, batch 1000, loss[loss=0.135, simple_loss=0.2245, pruned_loss=0.02278, over 7285.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2421, pruned_loss=0.02856, over 1406859.15 frames.], batch size: 17, lr: 2.17e-04
2022-05-16 01:04:02,114 INFO [train.py:812] (4/8) Epoch 36, batch 1050, loss[loss=0.1409, simple_loss=0.2343, pruned_loss=0.02375, over 7361.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2418, pruned_loss=0.02886, over 1406818.28 frames.], batch size: 19, lr: 2.17e-04
2022-05-16 01:05:09,919 INFO [train.py:812] (4/8) Epoch 36, batch 1100, loss[loss=0.1557, simple_loss=0.2539, pruned_loss=0.02879, over 7202.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02918, over 1407406.51 frames.], batch size: 22, lr: 2.17e-04
2022-05-16 01:06:19,095 INFO [train.py:812] (4/8) Epoch 36, batch 1150, loss[loss=0.1599, simple_loss=0.2553, pruned_loss=0.03226, over 7295.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02891, over 1413235.05 frames.], batch size: 24, lr: 2.17e-04
2022-05-16 01:07:18,007 INFO [train.py:812] (4/8) Epoch 36, batch 1200, loss[loss=0.1357, simple_loss=0.2147, pruned_loss=0.02838, over 7273.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02958, over 1409998.85 frames.], batch size: 17, lr: 2.17e-04
2022-05-16 01:08:16,992 INFO [train.py:812] (4/8) Epoch 36, batch 1250, loss[loss=0.149, simple_loss=0.2334, pruned_loss=0.03231, over 6987.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02928, over 1410861.40 frames.], batch size: 16, lr: 2.17e-04
2022-05-16 01:09:23,826 INFO [train.py:812] (4/8) Epoch 36, batch 1300, loss[loss=0.1282, simple_loss=0.2218, pruned_loss=0.01727, over 7130.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.02944, over 1414874.18 frames.], batch size: 17, lr: 2.17e-04
2022-05-16 01:10:23,386 INFO [train.py:812] (4/8) Epoch 36, batch 1350, loss[loss=0.1401, simple_loss=0.2266, pruned_loss=0.02674, over 7264.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.02917, over 1419601.68 frames.], batch size: 19, lr: 2.17e-04
2022-05-16 01:11:21,657 INFO [train.py:812] (4/8) Epoch 36, batch 1400, loss[loss=0.1481, simple_loss=0.2364, pruned_loss=0.02994, over 6985.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.02949, over 1418127.43 frames.], batch size: 16, lr: 2.17e-04
2022-05-16 01:12:20,390 INFO [train.py:812] (4/8) Epoch 36, batch 1450, loss[loss=0.1418, simple_loss=0.2276, pruned_loss=0.02803, over 6781.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02922, over 1414818.79 frames.], batch size: 15, lr: 2.17e-04
2022-05-16 01:13:19,146 INFO [train.py:812] (4/8) Epoch 36, batch 1500, loss[loss=0.1467, simple_loss=0.2466, pruned_loss=0.02335, over 7322.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02905, over 1418819.08 frames.], batch size: 21, lr: 2.17e-04
2022-05-16 01:14:17,134 INFO [train.py:812] (4/8) Epoch 36, batch 1550, loss[loss=0.1638, simple_loss=0.26, pruned_loss=0.03385, over 7235.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2439, pruned_loss=0.02938, over 1420675.69 frames.], batch size: 20, lr: 2.17e-04
2022-05-16 01:15:14,895 INFO [train.py:812] (4/8) Epoch 36, batch 1600, loss[loss=0.1729, simple_loss=0.2648, pruned_loss=0.04051, over 7388.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02912, over 1420247.71 frames.], batch size: 23, lr: 2.16e-04
2022-05-16 01:16:13,259 INFO [train.py:812] (4/8) Epoch 36, batch 1650, loss[loss=0.142, simple_loss=0.2274, pruned_loss=0.0283, over 7169.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02913, over 1421081.74 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:17:10,692 INFO [train.py:812] (4/8) Epoch 36, batch 1700, loss[loss=0.1448, simple_loss=0.245, pruned_loss=0.02225, over 7273.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2438, pruned_loss=0.02921, over 1423622.99 frames.], batch size: 25, lr: 2.16e-04
2022-05-16 01:18:09,646 INFO [train.py:812] (4/8) Epoch 36, batch 1750, loss[loss=0.1576, simple_loss=0.2454, pruned_loss=0.03494, over 7270.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2439, pruned_loss=0.02921, over 1419340.96 frames.], batch size: 18, lr: 2.16e-04
2022-05-16 01:19:07,111 INFO [train.py:812] (4/8) Epoch 36, batch 1800, loss[loss=0.1615, simple_loss=0.2493, pruned_loss=0.03687, over 7192.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2443, pruned_loss=0.02947, over 1422057.79 frames.], batch size: 23, lr: 2.16e-04
2022-05-16 01:20:05,565 INFO [train.py:812] (4/8) Epoch 36, batch 1850, loss[loss=0.1411, simple_loss=0.2419, pruned_loss=0.02013, over 7116.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2438, pruned_loss=0.02929, over 1424994.82 frames.], batch size: 21, lr: 2.16e-04
2022-05-16 01:21:04,168 INFO [train.py:812] (4/8) Epoch 36, batch 1900, loss[loss=0.1528, simple_loss=0.247, pruned_loss=0.02933, over 6786.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2441, pruned_loss=0.02966, over 1425446.73 frames.], batch size: 31, lr: 2.16e-04
2022-05-16 01:22:03,015 INFO [train.py:812] (4/8) Epoch 36, batch 1950, loss[loss=0.1386, simple_loss=0.2336, pruned_loss=0.02185, over 7243.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.02948, over 1423293.01 frames.], batch size: 20, lr: 2.16e-04
2022-05-16 01:23:01,525 INFO [train.py:812] (4/8) Epoch 36, batch 2000, loss[loss=0.1289, simple_loss=0.2116, pruned_loss=0.02313, over 6996.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2436, pruned_loss=0.02939, over 1420878.04 frames.], batch size: 16, lr: 2.16e-04
2022-05-16 01:24:00,266 INFO [train.py:812] (4/8) Epoch 36, batch 2050, loss[loss=0.193, simple_loss=0.2857, pruned_loss=0.05014, over 7319.00 frames.], tot_loss[loss=0.1513, simple_loss=0.244, pruned_loss=0.02931, over 1425305.88 frames.], batch size: 21, lr: 2.16e-04
2022-05-16 01:24:59,299 INFO [train.py:812] (4/8) Epoch 36, batch 2100, loss[loss=0.16, simple_loss=0.2539, pruned_loss=0.03305, over 7415.00 frames.], tot_loss[loss=0.151, simple_loss=0.2435, pruned_loss=0.02924, over 1423875.44 frames.], batch size: 21, lr: 2.16e-04
2022-05-16 01:25:59,145 INFO [train.py:812] (4/8) Epoch 36, batch 2150, loss[loss=0.1429, simple_loss=0.2345, pruned_loss=0.02568, over 7268.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2427, pruned_loss=0.02889, over 1426009.01 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:26:58,701 INFO [train.py:812] (4/8) Epoch 36, batch 2200, loss[loss=0.1556, simple_loss=0.2407, pruned_loss=0.03518, over 7415.00 frames.], tot_loss[loss=0.1502, simple_loss=0.243, pruned_loss=0.02871, over 1425471.76 frames.], batch size: 18, lr: 2.16e-04
2022-05-16 01:27:57,345 INFO [train.py:812] (4/8) Epoch 36, batch 2250, loss[loss=0.1403, simple_loss=0.2455, pruned_loss=0.01752, over 7331.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2433, pruned_loss=0.02874, over 1422199.39 frames.], batch size: 22, lr: 2.16e-04
2022-05-16 01:28:55,642 INFO [train.py:812] (4/8) Epoch 36, batch 2300, loss[loss=0.1327, simple_loss=0.2168, pruned_loss=0.02434, over 7134.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02865, over 1425587.06 frames.], batch size: 17, lr: 2.16e-04
2022-05-16 01:29:55,114 INFO [train.py:812] (4/8) Epoch 36, batch 2350, loss[loss=0.1908, simple_loss=0.2685, pruned_loss=0.05655, over 5179.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02881, over 1424314.51 frames.], batch size: 52, lr: 2.16e-04
2022-05-16 01:30:54,432 INFO [train.py:812] (4/8) Epoch 36, batch 2400, loss[loss=0.1444, simple_loss=0.2329, pruned_loss=0.02796, over 7408.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02872, over 1426987.09 frames.], batch size: 18, lr: 2.16e-04
2022-05-16 01:31:54,049 INFO [train.py:812] (4/8) Epoch 36, batch 2450, loss[loss=0.1695, simple_loss=0.2585, pruned_loss=0.04029, over 7155.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2422, pruned_loss=0.02893, over 1422288.90 frames.], batch size: 18, lr: 2.16e-04
2022-05-16 01:32:52,234 INFO [train.py:812] (4/8) Epoch 36, batch 2500, loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03173, over 7147.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02877, over 1426366.79 frames.], batch size: 20, lr: 2.16e-04
2022-05-16 01:33:51,369 INFO [train.py:812] (4/8) Epoch 36, batch 2550, loss[loss=0.1534, simple_loss=0.2436, pruned_loss=0.03159, over 7361.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02888, over 1422478.08 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:34:50,039 INFO [train.py:812] (4/8) Epoch 36, batch 2600, loss[loss=0.1354, simple_loss=0.2312, pruned_loss=0.01976, over 7164.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02903, over 1423453.32 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:35:48,586 INFO [train.py:812] (4/8) Epoch 36, batch 2650, loss[loss=0.2057, simple_loss=0.2943, pruned_loss=0.05854, over 5492.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02919, over 1422395.22 frames.], batch size: 52, lr: 2.16e-04
2022-05-16 01:36:46,989 INFO [train.py:812] (4/8) Epoch 36, batch 2700, loss[loss=0.1443, simple_loss=0.2376, pruned_loss=0.02546, over 7323.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02916, over 1423380.33 frames.], batch size: 21, lr: 2.16e-04
2022-05-16 01:37:45,805 INFO [train.py:812] (4/8) Epoch 36, batch 2750, loss[loss=0.1526, simple_loss=0.2526, pruned_loss=0.02624, over 7124.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02938, over 1425661.16 frames.], batch size: 21, lr: 2.16e-04
2022-05-16 01:38:44,974 INFO [train.py:812] (4/8) Epoch 36, batch 2800, loss[loss=0.17, simple_loss=0.2718, pruned_loss=0.03412, over 7197.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2417, pruned_loss=0.02903, over 1426980.75 frames.], batch size: 22, lr: 2.16e-04
2022-05-16 01:39:44,897 INFO [train.py:812] (4/8) Epoch 36, batch 2850, loss[loss=0.1188, simple_loss=0.2028, pruned_loss=0.01745, over 7258.00 frames.], tot_loss[loss=0.15, simple_loss=0.2416, pruned_loss=0.02922, over 1427615.03 frames.], batch size: 17, lr: 2.16e-04
2022-05-16 01:40:43,904 INFO [train.py:812] (4/8) Epoch 36, batch 2900, loss[loss=0.1446, simple_loss=0.2341, pruned_loss=0.02756, over 7259.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2408, pruned_loss=0.02904, over 1426364.42 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:41:42,646 INFO [train.py:812] (4/8) Epoch 36, batch 2950, loss[loss=0.1312, simple_loss=0.2275, pruned_loss=0.01739, over 7171.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2416, pruned_loss=0.02901, over 1424668.69 frames.], batch size: 18, lr: 2.16e-04
2022-05-16 01:42:41,194 INFO [train.py:812] (4/8) Epoch 36, batch 3000, loss[loss=0.134, simple_loss=0.2156, pruned_loss=0.02618, over 7160.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02984, over 1421977.73 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:42:41,195 INFO [train.py:832] (4/8) Computing validation loss
2022-05-16 01:42:48,527 INFO [train.py:841] (4/8) Epoch 36, validation: loss=0.1533, simple_loss=0.2487, pruned_loss=0.02893, over 698248.00 frames.
2022-05-16 01:43:48,424 INFO [train.py:812] (4/8) Epoch 36, batch 3050, loss[loss=0.1521, simple_loss=0.2415, pruned_loss=0.03136, over 7304.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2434, pruned_loss=0.02946, over 1424929.50 frames.], batch size: 24, lr: 2.16e-04
2022-05-16 01:44:47,700 INFO [train.py:812] (4/8) Epoch 36, batch 3100, loss[loss=0.1844, simple_loss=0.2697, pruned_loss=0.04954, over 7298.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2438, pruned_loss=0.0294, over 1429244.62 frames.], batch size: 25, lr: 2.15e-04
2022-05-16 01:45:47,532 INFO [train.py:812] (4/8) Epoch 36, batch 3150, loss[loss=0.1684, simple_loss=0.2565, pruned_loss=0.04014, over 7379.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2435, pruned_loss=0.02977, over 1427328.30 frames.], batch size: 23, lr: 2.15e-04
2022-05-16 01:46:46,138 INFO [train.py:812] (4/8) Epoch 36, batch 3200, loss[loss=0.1345, simple_loss=0.2183, pruned_loss=0.02536, over 7127.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2433, pruned_loss=0.02985, over 1421393.17 frames.], batch size: 17, lr: 2.15e-04
2022-05-16 01:47:45,913 INFO [train.py:812] (4/8) Epoch 36, batch 3250, loss[loss=0.1533, simple_loss=0.2441, pruned_loss=0.03122, over 5210.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02961, over 1419032.08 frames.], batch size: 52, lr: 2.15e-04
2022-05-16 01:48:53,221 INFO [train.py:812] (4/8) Epoch 36, batch 3300, loss[loss=0.1649, simple_loss=0.2587, pruned_loss=0.03556, over 7208.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2437, pruned_loss=0.02967, over 1422208.08 frames.], batch size: 23, lr: 2.15e-04
2022-05-16 01:49:52,245 INFO [train.py:812] (4/8) Epoch 36, batch 3350, loss[loss=0.1511, simple_loss=0.247, pruned_loss=0.02759, over 7195.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.02968, over 1426303.85 frames.], batch size: 23, lr: 2.15e-04
2022-05-16 01:50:50,250 INFO [train.py:812] (4/8) Epoch 36, batch 3400, loss[loss=0.1313, simple_loss=0.2212, pruned_loss=0.02072, over 7255.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.0296, over 1424646.40 frames.], batch size: 19, lr: 2.15e-04
2022-05-16 01:51:53,847 INFO [train.py:812] (4/8) Epoch 36, batch 3450, loss[loss=0.1266, simple_loss=0.2032, pruned_loss=0.02501, over 7281.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.02939, over 1422208.25 frames.], batch size: 17, lr: 2.15e-04
2022-05-16 01:52:52,271 INFO [train.py:812] (4/8) Epoch 36, batch 3500, loss[loss=0.1811, simple_loss=0.277, pruned_loss=0.04254, over 7406.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02938, over 1419327.70 frames.], batch size: 21, lr: 2.15e-04
2022-05-16 01:53:50,960 INFO [train.py:812] (4/8) Epoch 36, batch 3550, loss[loss=0.16, simple_loss=0.251, pruned_loss=0.03451, over 7045.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.02947, over 1423017.64 frames.], batch size: 28, lr: 2.15e-04
2022-05-16 01:54:49,013 INFO [train.py:812] (4/8) Epoch 36, batch 3600, loss[loss=0.1624, simple_loss=0.2521, pruned_loss=0.03638, over 7269.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.0291, over 1421465.12 frames.], batch size: 25, lr: 2.15e-04
2022-05-16 01:55:48,166 INFO [train.py:812] (4/8) Epoch 36, batch 3650, loss[loss=0.1773, simple_loss=0.2701, pruned_loss=0.04221, over 7275.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2423, pruned_loss=0.0291, over 1423396.03 frames.], batch size: 24, lr: 2.15e-04
2022-05-16 01:56:46,027 INFO [train.py:812] (4/8) Epoch 36, batch 3700, loss[loss=0.1599, simple_loss=0.2587, pruned_loss=0.03055, over 7117.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02888, over 1426299.28 frames.], batch size: 21, lr: 2.15e-04
2022-05-16 01:57:44,751 INFO [train.py:812] (4/8) Epoch 36, batch 3750, loss[loss=0.145, simple_loss=0.2401, pruned_loss=0.02491, over 7332.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2412, pruned_loss=0.02846, over 1425906.16 frames.], batch size: 22, lr: 2.15e-04
2022-05-16 01:58:43,595 INFO [train.py:812] (4/8) Epoch 36, batch 3800, loss[loss=0.135, simple_loss=0.2211, pruned_loss=0.02439, over 7362.00 frames.], tot_loss[loss=0.1504, simple_loss=0.243, pruned_loss=0.02885, over 1427733.25 frames.], batch size: 19, lr: 2.15e-04
2022-05-16 01:59:42,780 INFO [train.py:812] (4/8) Epoch 36, batch 3850, loss[loss=0.1321, simple_loss=0.2101, pruned_loss=0.02709, over 7008.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2433, pruned_loss=0.02898, over 1423550.36 frames.], batch size: 16, lr: 2.15e-04
2022-05-16 02:00:41,787 INFO [train.py:812] (4/8) Epoch 36, batch 3900, loss[loss=0.1542, simple_loss=0.2501, pruned_loss=0.02912, over 7221.00 frames.], tot_loss[loss=0.151, simple_loss=0.2434, pruned_loss=0.02933, over 1425801.41 frames.], batch size: 23, lr: 2.15e-04
2022-05-16 02:01:40,064 INFO [train.py:812] (4/8) Epoch 36, batch 3950, loss[loss=0.1543, simple_loss=0.2473, pruned_loss=0.03064, over 6669.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2443, pruned_loss=0.02949, over 1423888.12 frames.], batch size: 31, lr: 2.15e-04
2022-05-16 02:02:38,548 INFO [train.py:812] (4/8) Epoch 36, batch 4000, loss[loss=0.1454, simple_loss=0.2438, pruned_loss=0.02354, over 6967.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2445, pruned_loss=0.02964, over 1424141.82 frames.], batch size: 28, lr: 2.15e-04
2022-05-16 02:03:36,278 INFO [train.py:812] (4/8) Epoch 36, batch 4050, loss[loss=0.1616, simple_loss=0.2542, pruned_loss=0.03448, over 7222.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2438, pruned_loss=0.02916, over 1426587.06 frames.], batch size: 21, lr: 2.15e-04
2022-05-16 02:04:34,900 INFO [train.py:812] (4/8) Epoch 36, batch 4100, loss[loss=0.1248, simple_loss=0.2124, pruned_loss=0.01858, over 7115.00 frames.], tot_loss[loss=0.151, simple_loss=0.2436, pruned_loss=0.02917, over 1426780.35 frames.], batch size: 17, lr: 2.15e-04
2022-05-16 02:05:34,475 INFO [train.py:812] (4/8) Epoch 36, batch 4150, loss[loss=0.1667, simple_loss=0.2603, pruned_loss=0.03654, over 7201.00 frames.], tot_loss[loss=0.15, simple_loss=0.2425, pruned_loss=0.02879, over 1418572.48 frames.], batch size: 23, lr: 2.15e-04
2022-05-16 02:06:32,901 INFO [train.py:812] (4/8) Epoch 36, batch 4200, loss[loss=0.1424, simple_loss=0.2371, pruned_loss=0.0238, over 7239.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.02879, over 1416900.28 frames.], batch size: 20, lr: 2.15e-04
2022-05-16 02:07:31,853 INFO [train.py:812] (4/8) Epoch 36, batch 4250, loss[loss=0.1611, simple_loss=0.2513, pruned_loss=0.03548, over 7208.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02872, over 1416010.60 frames.], batch size: 22, lr: 2.15e-04
2022-05-16 02:08:31,007 INFO [train.py:812] (4/8) Epoch 36, batch 4300, loss[loss=0.1746, simple_loss=0.2562, pruned_loss=0.04653, over 7205.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2419, pruned_loss=0.0291, over 1412192.90 frames.], batch size: 22, lr: 2.15e-04
2022-05-16 02:09:30,583 INFO [train.py:812] (4/8) Epoch 36, batch 4350, loss[loss=0.1585, simple_loss=0.2425, pruned_loss=0.03723, over 7422.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2403, pruned_loss=0.02866, over 1410070.94 frames.], batch size: 20, lr: 2.15e-04
2022-05-16 02:10:29,641 INFO [train.py:812] (4/8) Epoch 36, batch 4400, loss[loss=0.1371, simple_loss=0.2281, pruned_loss=0.02304, over 7376.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2397, pruned_loss=0.02843, over 1414386.78 frames.], batch size: 19, lr: 2.15e-04
2022-05-16 02:11:29,748 INFO [train.py:812] (4/8) Epoch 36, batch 4450, loss[loss=0.1268, simple_loss=0.2248, pruned_loss=0.01441, over 7213.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2394, pruned_loss=0.02842, over 1405497.87 frames.], batch size: 21, lr: 2.15e-04
2022-05-16 02:12:28,157 INFO [train.py:812] (4/8) Epoch 36, batch 4500, loss[loss=0.1549, simple_loss=0.2545, pruned_loss=0.02763, over 7221.00 frames.], tot_loss[loss=0.148, simple_loss=0.2394, pruned_loss=0.02825, over 1393493.35 frames.], batch size: 21, lr: 2.15e-04
2022-05-16 02:13:26,415 INFO [train.py:812] (4/8) Epoch 36, batch 4550, loss[loss=0.1496, simple_loss=0.2468, pruned_loss=0.02626, over 7267.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2405, pruned_loss=0.02944, over 1355723.04 frames.], batch size: 19, lr: 2.15e-04
2022-05-16 02:14:35,970 INFO [train.py:812] (4/8) Epoch 37, batch 0, loss[loss=0.1589, simple_loss=0.2688, pruned_loss=0.02457, over 7351.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2688, pruned_loss=0.02457, over 7351.00 frames.], batch size: 22, lr: 2.12e-04
2022-05-16 02:15:35,004 INFO [train.py:812] (4/8) Epoch 37, batch 50, loss[loss=0.1391, simple_loss=0.236, pruned_loss=0.02106, over 7071.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2453, pruned_loss=0.02995, over 320858.64 frames.], batch size: 18, lr: 2.12e-04
2022-05-16 02:16:33,784 INFO [train.py:812] (4/8) Epoch 37, batch 100, loss[loss=0.1406, simple_loss=0.2331, pruned_loss=0.02407, over 7323.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2435, pruned_loss=0.02896, over 566414.79 frames.], batch size: 20, lr: 2.12e-04
2022-05-16 02:17:32,749 INFO [train.py:812] (4/8) Epoch 37, batch 150, loss[loss=0.1275, simple_loss=0.2193, pruned_loss=0.01788, over 7015.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2439, pruned_loss=0.02942, over 754204.41 frames.], batch size: 28, lr: 2.11e-04
2022-05-16 02:18:31,114 INFO [train.py:812] (4/8) Epoch 37, batch 200, loss[loss=0.147, simple_loss=0.246, pruned_loss=0.02396, over 7311.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2465, pruned_loss=0.0302, over 905432.47 frames.], batch size: 21, lr: 2.11e-04
2022-05-16 02:19:29,653 INFO [train.py:812] (4/8) Epoch 37, batch 250, loss[loss=0.1659, simple_loss=0.2481, pruned_loss=0.04184, over 7246.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2455, pruned_loss=0.02997, over 1016321.20 frames.], batch size: 19, lr: 2.11e-04
2022-05-16 02:20:28,586 INFO [train.py:812] (4/8) Epoch 37, batch 300, loss[loss=0.1588, simple_loss=0.2608, pruned_loss=0.02844, over 7330.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.02997, over 1103478.58 frames.], batch size: 22, lr: 2.11e-04
2022-05-16 02:21:27,132 INFO [train.py:812] (4/8) Epoch 37, batch 350, loss[loss=0.1164, simple_loss=0.203, pruned_loss=0.01496, over 7162.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2441, pruned_loss=0.02965, over 1172220.42 frames.], batch size: 18, lr: 2.11e-04
2022-05-16 02:22:25,671 INFO [train.py:812] (4/8) Epoch 37, batch 400, loss[loss=0.144, simple_loss=0.237, pruned_loss=0.02551, over 7230.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2437, pruned_loss=0.02936, over 1231622.69 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:23:24,547 INFO [train.py:812] (4/8) Epoch 37, batch 450, loss[loss=0.1585, simple_loss=0.2598, pruned_loss=0.02861, over 7146.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2445, pruned_loss=0.0294, over 1275945.12 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:24:21,850 INFO [train.py:812] (4/8) Epoch 37, batch 500, loss[loss=0.1489, simple_loss=0.2539, pruned_loss=0.02195, over 7233.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2442, pruned_loss=0.02922, over 1306077.48 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:25:21,118 INFO [train.py:812] (4/8) Epoch 37, batch 550, loss[loss=0.1575, simple_loss=0.2471, pruned_loss=0.03392, over 7071.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2445, pruned_loss=0.02934, over 1322656.88 frames.], batch size: 18, lr: 2.11e-04
2022-05-16 02:26:19,461 INFO [train.py:812] (4/8) Epoch 37, batch 600, loss[loss=0.158, simple_loss=0.25, pruned_loss=0.03299, over 7442.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2436, pruned_loss=0.02947, over 1347723.96 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:27:18,103 INFO [train.py:812] (4/8) Epoch 37, batch 650, loss[loss=0.1247, simple_loss=0.2102, pruned_loss=0.01959, over 7131.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2413, pruned_loss=0.02894, over 1367193.52 frames.], batch size: 17, lr: 2.11e-04
2022-05-16 02:28:16,755 INFO [train.py:812] (4/8) Epoch 37, batch 700, loss[loss=0.1551, simple_loss=0.2506, pruned_loss=0.02974, over 7231.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.02882, over 1380256.28 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:29:16,768 INFO [train.py:812] (4/8) Epoch 37, batch 750, loss[loss=0.1451, simple_loss=0.229, pruned_loss=0.03055, over 7157.00 frames.], tot_loss[loss=0.149, simple_loss=0.2408, pruned_loss=0.02855, over 1388824.04 frames.], batch size: 19, lr: 2.11e-04
2022-05-16 02:30:15,266 INFO [train.py:812] (4/8) Epoch 37, batch 800, loss[loss=0.1496, simple_loss=0.2265, pruned_loss=0.03629, over 7395.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2408, pruned_loss=0.02873, over 1398808.80 frames.], batch size: 18, lr: 2.11e-04
2022-05-16 02:31:14,067 INFO [train.py:812] (4/8) Epoch 37, batch 850, loss[loss=0.147, simple_loss=0.2295, pruned_loss=0.03222, over 7265.00 frames.], tot_loss[loss=0.1489, simple_loss=0.241, pruned_loss=0.02844, over 1398469.95 frames.], batch size: 19, lr: 2.11e-04
2022-05-16 02:32:12,867 INFO [train.py:812] (4/8) Epoch 37, batch 900, loss[loss=0.1336, simple_loss=0.219, pruned_loss=0.02412, over 7061.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2407, pruned_loss=0.02828, over 1407072.60 frames.], batch size: 18, lr: 2.11e-04
2022-05-16 02:33:11,835 INFO [train.py:812] (4/8) Epoch 37, batch 950, loss[loss=0.138, simple_loss=0.2137, pruned_loss=0.03113, over 7314.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2401, pruned_loss=0.02827, over 1410362.11 frames.], batch size: 17, lr: 2.11e-04
2022-05-16 02:34:09,800 INFO [train.py:812] (4/8) Epoch 37, batch 1000, loss[loss=0.1812, simple_loss=0.2805, pruned_loss=0.04096, over 6669.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.0289, over 1413303.24 frames.], batch size: 31, lr: 2.11e-04
2022-05-16 02:35:08,665 INFO [train.py:812] (4/8) Epoch 37, batch 1050, loss[loss=0.1709, simple_loss=0.266, pruned_loss=0.03785, over 7358.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.0293, over 1417574.63 frames.], batch size: 23, lr: 2.11e-04
2022-05-16 02:36:07,864 INFO [train.py:812] (4/8) Epoch 37, batch 1100, loss[loss=0.1737, simple_loss=0.2739, pruned_loss=0.03677, over 7218.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2421, pruned_loss=0.02934, over 1418507.36 frames.], batch size: 21, lr: 2.11e-04
2022-05-16 02:37:06,625 INFO [train.py:812] (4/8) Epoch 37, batch 1150, loss[loss=0.2048, simple_loss=0.2691, pruned_loss=0.07024, over 4888.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2419, pruned_loss=0.02919, over 1417587.27 frames.], batch size: 52, lr: 2.11e-04
2022-05-16 02:38:04,300 INFO [train.py:812] (4/8) Epoch 37, batch 1200, loss[loss=0.1481, simple_loss=0.2439, pruned_loss=0.02614, over 7153.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02949, over 1420168.44 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:39:03,401 INFO [train.py:812] (4/8) Epoch 37, batch 1250, loss[loss=0.1534, simple_loss=0.2493, pruned_loss=0.02881, over 7205.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2437, pruned_loss=0.02947, over 1420090.02 frames.], batch size: 22, lr: 2.11e-04
2022-05-16 02:40:01,878 INFO [train.py:812] (4/8) Epoch 37, batch 1300, loss[loss=0.1371, simple_loss=0.2206, pruned_loss=0.02675, over 7128.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2441, pruned_loss=0.02955, over 1422485.84 frames.], batch size: 17, lr: 2.11e-04
2022-05-16 02:41:00,882 INFO [train.py:812] (4/8) Epoch 37, batch 1350, loss[loss=0.139, simple_loss=0.2331, pruned_loss=0.0225, over 7064.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02955, over 1418235.73 frames.], batch size: 18, lr: 2.11e-04
2022-05-16 02:41:59,968 INFO [train.py:812] (4/8) Epoch 37, batch 1400, loss[loss=0.1463, simple_loss=0.2331, pruned_loss=0.02977, over 7020.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02916, over 1418556.91 frames.], batch size: 16, lr: 2.11e-04
2022-05-16 02:42:58,496 INFO [train.py:812] (4/8) Epoch 37, batch 1450, loss[loss=0.1539, simple_loss=0.2473, pruned_loss=0.03025, over 7296.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.02887, over 1420165.49 frames.], batch size: 24, lr: 2.11e-04
2022-05-16 02:43:56,639 INFO [train.py:812] (4/8) Epoch 37, batch 1500, loss[loss=0.1701, simple_loss=0.2715, pruned_loss=0.03441, over 7309.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02944, over 1416562.04 frames.], batch size: 24, lr: 2.11e-04
2022-05-16 02:44:55,820 INFO [train.py:812] (4/8) Epoch 37, batch 1550, loss[loss=0.1577, simple_loss=0.2574, pruned_loss=0.02899, over 6805.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2439, pruned_loss=0.0297, over 1410269.33 frames.], batch size: 31, lr: 2.11e-04
2022-05-16 02:45:54,004 INFO [train.py:812] (4/8) Epoch 37, batch 1600, loss[loss=0.1795, simple_loss=0.2748, pruned_loss=0.04212, over 7382.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2427, pruned_loss=0.02953, over 1410192.12 frames.], batch size: 23, lr: 2.11e-04
2022-05-16 02:46:52,090 INFO [train.py:812] (4/8) Epoch 37, batch 1650, loss[loss=0.1743, simple_loss=0.2717, pruned_loss=0.03848, over 7197.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02889, over 1414104.54 frames.], batch size: 22, lr: 2.11e-04
2022-05-16 02:47:50,668 INFO [train.py:812] (4/8) Epoch 37, batch 1700, loss[loss=0.1285, simple_loss=0.2155, pruned_loss=0.02072, over 7153.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2425, pruned_loss=0.02914, over 1412789.86 frames.], batch size: 19, lr: 2.11e-04
2022-05-16 02:48:48,768 INFO [train.py:812] (4/8) Epoch 37, batch 1750, loss[loss=0.144, simple_loss=0.2347, pruned_loss=0.02662, over 7353.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2424, pruned_loss=0.02912, over 1407534.61 frames.], batch size: 19, lr: 2.10e-04
2022-05-16 02:49:47,207 INFO [train.py:812] (4/8) Epoch 37, batch 1800, loss[loss=0.1462, simple_loss=0.235, pruned_loss=0.02874, over 7296.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2429, pruned_loss=0.02907, over 1410530.87 frames.], batch size: 24, lr: 2.10e-04
2022-05-16 02:50:46,351 INFO [train.py:812] (4/8) Epoch 37, batch 1850, loss[loss=0.1433, simple_loss=0.233, pruned_loss=0.02682, over 7260.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2424, pruned_loss=0.02909, over 1411649.66 frames.], batch size: 19, lr: 2.10e-04
2022-05-16 02:51:45,053 INFO [train.py:812] (4/8) Epoch 37, batch 1900, loss[loss=0.1711, simple_loss=0.2578, pruned_loss=0.04222, over 6737.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.02914, over 1417237.99 frames.], batch size: 31, lr: 2.10e-04
2022-05-16 02:52:44,048 INFO [train.py:812] (4/8) Epoch 37, batch 1950, loss[loss=0.1684, simple_loss=0.2636, pruned_loss=0.03655, over 7229.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02911, over 1420356.69 frames.], batch size: 21, lr: 2.10e-04
2022-05-16 02:53:42,347 INFO [train.py:812] (4/8) Epoch 37, batch 2000, loss[loss=0.1605, simple_loss=0.2622, pruned_loss=0.02936, over 7429.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02893, over 1416779.33 frames.], batch size: 21, lr: 2.10e-04
2022-05-16 02:54:41,774 INFO [train.py:812] (4/8) Epoch 37, batch 2050, loss[loss=0.1559, simple_loss=0.2485, pruned_loss=0.03165, over 7235.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2419, pruned_loss=0.02868, over 1419820.76 frames.], batch size: 20, lr: 2.10e-04
2022-05-16 02:55:38,643 INFO [train.py:812] (4/8) Epoch 37, batch 2100, loss[loss=0.1515, simple_loss=0.2542, pruned_loss=0.02438, over 7148.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02903, over 1420274.33 frames.], batch size: 20, lr: 2.10e-04
2022-05-16 02:56:46,827 INFO [train.py:812] (4/8) Epoch 37, batch 2150, loss[loss=0.1328, simple_loss=0.2376, pruned_loss=0.01405, over 7416.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02901, over 1417452.83 frames.], batch size: 21, lr: 2.10e-04
2022-05-16 02:57:45,105 INFO [train.py:812] (4/8) Epoch 37, batch 2200, loss[loss=0.1518, simple_loss=0.2457, pruned_loss=0.02902, over 7259.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.02889, over 1418710.40 frames.], batch size: 19, lr: 2.10e-04
2022-05-16 02:58:53,448 INFO [train.py:812] (4/8) Epoch 37, batch 2250, loss[loss=0.1606, simple_loss=0.2647, pruned_loss=0.0282, over 7141.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2427, pruned_loss=0.02894, over 1419482.59 frames.], batch size: 20, lr: 2.10e-04
2022-05-16 03:00:01,348 INFO [train.py:812] (4/8) Epoch 37, batch 2300, loss[loss=0.1408, simple_loss=0.2426, pruned_loss=0.01951, over 7217.00 frames.], tot_loss[loss=0.15, simple_loss=0.2425, pruned_loss=0.02873, over 1419298.60 frames.], batch size: 23, lr: 2.10e-04
2022-05-16 03:01:01,013 INFO [train.py:812] (4/8) Epoch 37, batch 2350, loss[loss=0.1319, simple_loss=0.2185, pruned_loss=0.02267, over 7295.00 frames.], tot_loss[loss=0.1504, simple_loss=0.243, pruned_loss=0.02887, over 1413239.45 frames.], batch size: 17, lr: 2.10e-04
2022-05-16 03:01:59,220 INFO [train.py:812] (4/8) Epoch 37, batch 2400, loss[loss=0.1608, simple_loss=0.2528, pruned_loss=0.03438, over 7292.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02885, over 1419845.59 frames.], batch size: 25, lr: 2.10e-04
2022-05-16 03:02:57,118 INFO [train.py:812] (4/8) Epoch 37, batch 2450, loss[loss=0.1726, simple_loss=0.2669, pruned_loss=0.03919, over 7213.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2424, pruned_loss=0.02863, over 1425230.39 frames.], batch size: 26, lr: 2.10e-04
2022-05-16 03:04:04,661 INFO [train.py:812] (4/8) Epoch 37, batch 2500, loss[loss=0.1623, simple_loss=0.2566, pruned_loss=0.034, over 7164.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02856, over 1427810.12 frames.], batch size: 19, lr: 2.10e-04
2022-05-16 03:05:04,385 INFO [train.py:812] (4/8) Epoch 37, batch 2550, loss[loss=0.15, simple_loss=0.2384, pruned_loss=0.03084, over 7287.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02882, over 1428543.36 frames.], batch size: 24, lr: 2.10e-04
2022-05-16 03:06:02,646 INFO [train.py:812] (4/8) Epoch 37, batch 2600, loss[loss=0.1438, simple_loss=0.235, pruned_loss=0.02627, over 7213.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.0287, over 1424943.15 frames.], batch size: 16, lr: 2.10e-04
2022-05-16 03:07:21,590 INFO [train.py:812] (4/8) Epoch 37, batch 2650, loss[loss=0.1529, simple_loss=0.2439, pruned_loss=0.03091, over 7202.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02868, over 1429018.12 frames.], batch size: 22, lr: 2.10e-04
2022-05-16 03:08:19,645 INFO [train.py:812] (4/8) Epoch 37, batch 2700, loss[loss=0.1646, simple_loss=0.2579, pruned_loss=0.03569, over 6239.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02857, over 1424744.01 frames.], batch size: 37, lr: 2.10e-04
2022-05-16 03:09:18,861 INFO [train.py:812] (4/8) Epoch 37, batch 2750, loss[loss=0.1637, simple_loss=0.249, pruned_loss=0.03925, over 5092.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2422, pruned_loss=0.02862, over 1425140.23 frames.], batch size: 54, lr: 2.10e-04
2022-05-16 03:10:16,998 INFO [train.py:812] (4/8) Epoch 37, batch 2800, loss[loss=0.1332, simple_loss=0.2203, pruned_loss=0.02301, over 7282.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2415, pruned_loss=0.02871, over 1429839.69 frames.], batch size: 18, lr: 2.10e-04
2022-05-16 03:11:34,303 INFO [train.py:812] (4/8) Epoch 37, batch 2850, loss[loss=0.1493, simple_loss=0.2466, pruned_loss=0.02601, over 6300.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2418, pruned_loss=0.02873, over 1428322.13 frames.], batch size: 37, lr: 2.10e-04
2022-05-16 03:12:32,634 INFO [train.py:812] (4/8) Epoch 37, batch 2900, loss[loss=0.1319, simple_loss=0.2148, pruned_loss=0.02448, over 7006.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2412, pruned_loss=0.02827, over 1429039.48 frames.], batch size: 16, lr: 2.10e-04
2022-05-16 03:13:31,849 INFO [train.py:812] (4/8) Epoch 37, batch 2950, loss[loss=0.1413, simple_loss=0.2324, pruned_loss=0.02509, over 7424.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02839, over 1425975.48 frames.], batch size: 20, lr: 2.10e-04
2022-05-16 03:14:30,575 INFO [train.py:812] (4/8) Epoch 37, batch 3000, loss[loss=0.1362, simple_loss=0.2368, pruned_loss=0.01782, over 7229.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.0287, over 1422306.13 frames.], batch size: 21, lr: 2.10e-04
2022-05-16 03:14:30,576 INFO [train.py:832] (4/8) Computing validation loss
2022-05-16 03:14:38,087 INFO [train.py:841] (4/8) Epoch 37, validation: loss=0.1539, simple_loss=0.2491, pruned_loss=0.02931, over 698248.00 frames.
2022-05-16 03:15:37,667 INFO [train.py:812] (4/8) Epoch 37, batch 3050, loss[loss=0.1507, simple_loss=0.2264, pruned_loss=0.0375, over 6770.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.0292, over 1420288.04 frames.], batch size: 15, lr: 2.10e-04
2022-05-16 03:16:36,461 INFO [train.py:812] (4/8) Epoch 37, batch 3100, loss[loss=0.1343, simple_loss=0.2197, pruned_loss=0.02447, over 7067.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2422, pruned_loss=0.02921, over 1419394.57 frames.], batch size: 18, lr: 2.10e-04
2022-05-16 03:17:34,871 INFO [train.py:812] (4/8) Epoch 37, batch 3150, loss[loss=0.1347, simple_loss=0.2256, pruned_loss=0.02188, over 7008.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2416, pruned_loss=0.02938, over 1419076.55 frames.], batch size: 16, lr: 2.10e-04
2022-05-16 03:18:33,957 INFO [train.py:812] (4/8) Epoch 37, batch 3200, loss[loss=0.1535, simple_loss=0.2419, pruned_loss=0.03259, over 5183.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2414, pruned_loss=0.02922, over 1419882.65 frames.], batch size: 52, lr: 2.10e-04
2022-05-16 03:19:33,519 INFO [train.py:812] (4/8) Epoch 37, batch 3250, loss[loss=0.1554, simple_loss=0.2454, pruned_loss=0.0327, over 7208.00 frames.], tot_loss[loss=0.1505, simple_loss=0.242, pruned_loss=0.02953, over 1420100.33 frames.], batch size: 22, lr: 2.10e-04
2022-05-16 03:20:31,427 INFO [train.py:812] (4/8) Epoch 37, batch 3300, loss[loss=0.1486, simple_loss=0.2544, pruned_loss=0.02138, over 7428.00 frames.], tot_loss[loss=0.151, simple_loss=0.2424, pruned_loss=0.02981, over 1417618.45 frames.], batch size: 21, lr: 2.10e-04
2022-05-16 03:21:29,312 INFO [train.py:812] (4/8) Epoch 37, batch 3350, loss[loss=0.168, simple_loss=0.2646, pruned_loss=0.03569, over 7361.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.03002, over 1413838.13 frames.], batch size: 23, lr: 2.09e-04
2022-05-16 03:22:27,822 INFO [train.py:812] (4/8) Epoch 37, batch 3400, loss[loss=0.128, simple_loss=0.2124, pruned_loss=0.0218, over 7133.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2439, pruned_loss=0.0295, over 1418119.87 frames.], batch size: 17, lr: 2.09e-04
2022-05-16 03:23:27,192 INFO [train.py:812] (4/8) Epoch 37, batch 3450, loss[loss=0.1425, simple_loss=0.2187, pruned_loss=0.03313, over 7293.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02902, over 1421696.92 frames.], batch size: 17, lr: 2.09e-04
2022-05-16 03:24:25,217 INFO [train.py:812] (4/8) Epoch 37, batch 3500, loss[loss=0.1376, simple_loss=0.2274, pruned_loss=0.02387, over 7352.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2421, pruned_loss=0.02871, over 1418988.32 frames.], batch size: 19, lr: 2.09e-04
2022-05-16 03:25:24,376 INFO [train.py:812] (4/8) Epoch 37, batch 3550, loss[loss=0.1294, simple_loss=0.2133, pruned_loss=0.02273, over 6787.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2411, pruned_loss=0.02824, over 1415229.92 frames.], batch size: 15, lr: 2.09e-04
2022-05-16 03:26:23,186 INFO [train.py:812] (4/8) Epoch 37, batch 3600, loss[loss=0.1269, simple_loss=0.2096, pruned_loss=0.02214, over 6999.00 frames.], tot_loss[loss=0.148, simple_loss=0.2403, pruned_loss=0.0279, over 1421164.86 frames.], batch size: 16, lr: 2.09e-04
2022-05-16 03:27:22,044 INFO [train.py:812] (4/8) Epoch 37, batch 3650, loss[loss=0.1451, simple_loss=0.2389, pruned_loss=0.02566, over 7154.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2406, pruned_loss=0.02814, over 1423714.34 frames.], batch size: 19, lr: 2.09e-04
2022-05-16 03:28:20,577 INFO [train.py:812] (4/8) Epoch 37, batch 3700, loss[loss=0.142, simple_loss=0.2403, pruned_loss=0.02187, over 7234.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2407, pruned_loss=0.0282, over 1426574.83 frames.], batch size: 20, lr: 2.09e-04
2022-05-16 03:29:19,676 INFO [train.py:812] (4/8) Epoch 37, batch 3750, loss[loss=0.1582, simple_loss=0.2536, pruned_loss=0.03144, over 7305.00 frames.], tot_loss[loss=0.1494, simple_loss=0.242, pruned_loss=0.02845, over 1423142.49 frames.], batch size: 24, lr: 2.09e-04
2022-05-16 03:30:17,096 INFO [train.py:812] (4/8) Epoch 37, batch 3800, loss[loss=0.1167, simple_loss=0.2051, pruned_loss=0.01418, over 7281.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2412, pruned_loss=0.02828, over 1425015.75 frames.], batch size: 17, lr: 2.09e-04
2022-05-16 03:31:15,862 INFO [train.py:812] (4/8) Epoch 37, batch 3850, loss[loss=0.1582, simple_loss=0.2465, pruned_loss=0.03497, over 5062.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2407, pruned_loss=0.02813, over 1423691.48 frames.], batch size: 55, lr: 2.09e-04
2022-05-16 03:32:12,582 INFO [train.py:812] (4/8) Epoch 37, batch 3900, loss[loss=0.1648, simple_loss=0.2554, pruned_loss=0.03711, over 7323.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2408, pruned_loss=0.02832, over 1425448.46 frames.], batch size: 20, lr: 2.09e-04
2022-05-16 03:33:11,480 INFO [train.py:812] (4/8) Epoch 37, batch 3950, loss[loss=0.133, simple_loss=0.2256, pruned_loss=0.02015, over 7287.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2413, pruned_loss=0.02844, over 1426334.39 frames.], batch size: 18, lr: 2.09e-04
2022-05-16 03:34:09,789 INFO [train.py:812] (4/8) Epoch 37, batch 4000, loss[loss=0.1474, simple_loss=0.244, pruned_loss=0.02541, over 7151.00 frames.], tot_loss[loss=0.1489, simple_loss=0.241, pruned_loss=0.02842, over 1426664.84 frames.], batch size: 20, lr: 2.09e-04
2022-05-16 03:35:09,211 INFO [train.py:812] (4/8) Epoch 37, batch 4050, loss[loss=0.1332, simple_loss=0.2248, pruned_loss=0.02082, over 7143.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2407, pruned_loss=0.02819, over 1426018.53 frames.], batch size: 20, lr: 2.09e-04
2022-05-16 03:36:06,890 INFO [train.py:812] (4/8) Epoch 37, batch 4100, loss[loss=0.1871, simple_loss=0.2779, pruned_loss=0.04812, over 7308.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02836, over 1423775.41 frames.], batch size: 25, lr: 2.09e-04
2022-05-16 03:37:05,680 INFO [train.py:812] (4/8) Epoch 37, batch 4150, loss[loss=0.1298, simple_loss=0.2298, pruned_loss=0.01486, over 7224.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2406, pruned_loss=0.02793, over 1425936.69 frames.], batch size: 21, lr: 2.09e-04
2022-05-16 03:38:02,984 INFO [train.py:812] (4/8) Epoch 37, batch 4200, loss[loss=0.1511, simple_loss=0.2505, pruned_loss=0.02581, over 7340.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2401, pruned_loss=0.02779, over 1428273.78 frames.], batch size: 22, lr: 2.09e-04
2022-05-16 03:39:02,455 INFO [train.py:812] (4/8) Epoch 37, batch 4250, loss[loss=0.1634, simple_loss=0.2536, pruned_loss=0.03659, over 7214.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2401, pruned_loss=0.02761, over 1431237.56 frames.], batch size: 22, lr: 2.09e-04
2022-05-16 03:40:00,858 INFO [train.py:812] (4/8) Epoch 37, batch 4300, loss[loss=0.1415, simple_loss=0.2266, pruned_loss=0.02817, over 7331.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2405, pruned_loss=0.02807, over 1425582.24 frames.], batch size: 20, lr: 2.09e-04
2022-05-16 03:41:00,629 INFO [train.py:812] (4/8) Epoch 37, batch 4350, loss[loss=0.1554, simple_loss=0.2497, pruned_loss=0.03056, over 7341.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2401, pruned_loss=0.0277, over 1430570.82 frames.], batch size: 22, lr: 2.09e-04
2022-05-16 03:41:59,223 INFO [train.py:812] (4/8) Epoch 37, batch 4400, loss[loss=0.1613, simple_loss=0.2623, pruned_loss=0.03016, over 7333.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2402, pruned_loss=0.02762, over 1422135.45 frames.], batch size: 22, lr: 2.09e-04
2022-05-16 03:42:59,064 INFO [train.py:812] (4/8) Epoch 37, batch 4450, loss[loss=0.1306, simple_loss=0.2209, pruned_loss=0.02017, over 7420.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2409, pruned_loss=0.02791, over 1421331.58 frames.], batch size: 18, lr: 2.09e-04
2022-05-16 03:43:58,019 INFO [train.py:812] (4/8) Epoch 37, batch 4500, loss[loss=0.1378, simple_loss=0.2293, pruned_loss=0.02315, over 7280.00 frames.], tot_loss[loss=0.1485, simple_loss=0.241, pruned_loss=0.02801, over 1416576.10 frames.], batch size: 18, lr: 2.09e-04
2022-05-16 03:44:56,297 INFO [train.py:812] (4/8) Epoch 37, batch 4550, loss[loss=0.1615, simple_loss=0.2519, pruned_loss=0.03554, over 6534.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2426, pruned_loss=0.02854, over 1392779.34 frames.], batch size: 38, lr: 2.09e-04
2022-05-16 03:46:01,494 INFO [train.py:812] (4/8) Epoch 38, batch 0, loss[loss=0.1346, simple_loss=0.2324, pruned_loss=0.01838, over 7361.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2324, pruned_loss=0.01838, over 7361.00 frames.], batch size: 19, lr: 2.06e-04
2022-05-16 03:47:10,797 INFO [train.py:812] (4/8) Epoch 38, batch 50, loss[loss=0.1473, simple_loss=0.247, pruned_loss=0.02385, over 6419.00 frames.], tot_loss[loss=0.15, simple_loss=0.2428, pruned_loss=0.02859, over 322538.22 frames.], batch size: 38, lr: 2.06e-04
2022-05-16 03:48:09,443 INFO [train.py:812] (4/8) Epoch 38, batch 100, loss[loss=0.1405, simple_loss=0.2355, pruned_loss=0.02276, over 7272.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2456, pruned_loss=0.02899, over 560122.35 frames.], batch size: 19, lr: 2.06e-04
2022-05-16 03:49:08,236 INFO [train.py:812] (4/8) Epoch 38, batch 150, loss[loss=0.1718, simple_loss=0.2626, pruned_loss=0.04045, over 7377.00 frames.], tot_loss[loss=0.152, simple_loss=0.2453, pruned_loss=0.02938, over 747987.31 frames.], batch size: 23, lr: 2.06e-04
2022-05-16 03:50:07,476 INFO [train.py:812] (4/8) Epoch 38, batch 200, loss[loss=0.1818, simple_loss=0.2686, pruned_loss=0.0475, over 7419.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02918, over 896617.31 frames.], batch size: 21, lr: 2.06e-04
2022-05-16 03:51:06,655 INFO [train.py:812] (4/8) Epoch 38, batch 250, loss[loss=0.1541, simple_loss=0.2357, pruned_loss=0.03623, over 7357.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02882, over 1014822.75 frames.], batch size: 19, lr: 2.06e-04
2022-05-16 03:52:05,100 INFO [train.py:812] (4/8) Epoch 38, batch 300, loss[loss=0.1353, simple_loss=0.227, pruned_loss=0.02178, over 7227.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02916, over 1105939.34 frames.], batch size: 20, lr: 2.06e-04
2022-05-16 03:53:04,669 INFO [train.py:812] (4/8) Epoch 38, batch 350, loss[loss=0.136, simple_loss=0.232, pruned_loss=0.01998, over 7263.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02912, over 1172964.90 frames.], batch size: 19, lr: 2.06e-04
2022-05-16 03:54:02,522 INFO [train.py:812] (4/8) Epoch 38, batch 400, loss[loss=0.1419, simple_loss=0.2251, pruned_loss=0.02934, over 7275.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.02914, over 1232977.21 frames.], batch size: 17, lr: 2.06e-04
2022-05-16 03:55:02,015 INFO [train.py:812] (4/8) Epoch 38, batch 450, loss[loss=0.1616, simple_loss=0.2572, pruned_loss=0.03298, over 7110.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02908, over 1276160.89 frames.], batch size: 21, lr: 2.06e-04
2022-05-16 03:56:00,721 INFO [train.py:812] (4/8) Epoch 38, batch 500, loss[loss=0.1236, simple_loss=0.209, pruned_loss=0.01912, over 7279.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2408, pruned_loss=0.02869, over 1312086.02 frames.], batch size: 18, lr: 2.06e-04
2022-05-16 03:56:58,593 INFO [train.py:812] (4/8) Epoch 38, batch 550, loss[loss=0.1335, simple_loss=0.2242, pruned_loss=0.02139, over 7328.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2412, pruned_loss=0.02882, over 1336190.69 frames.], batch size: 20, lr: 2.06e-04
2022-05-16 03:57:56,245 INFO [train.py:812] (4/8) Epoch 38, batch 600, loss[loss=0.169, simple_loss=0.2602, pruned_loss=0.03887, over 7382.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2434, pruned_loss=0.02925, over 1357628.33 frames.], batch size: 23, lr: 2.06e-04
2022-05-16 03:58:54,202 INFO [train.py:812] (4/8) Epoch 38, batch 650, loss[loss=0.1655, simple_loss=0.262, pruned_loss=0.03453, over 7332.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2433, pruned_loss=0.02896, over 1374312.38 frames.], batch size: 22, lr: 2.06e-04
2022-05-16 03:59:53,355 INFO [train.py:812] (4/8) Epoch 38, batch 700, loss[loss=0.1637, simple_loss=0.2487, pruned_loss=0.03932, over 7170.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2427, pruned_loss=0.02874, over 1386451.07 frames.], batch size: 18, lr: 2.06e-04
2022-05-16 04:00:52,138 INFO [train.py:812] (4/8) Epoch 38, batch 750, loss[loss=0.1725, simple_loss=0.2641, pruned_loss=0.04042, over 7378.00 frames.], tot_loss[loss=0.15, simple_loss=0.2425, pruned_loss=0.02878, over 1400858.93 frames.], batch size: 23, lr: 2.05e-04
2022-05-16 04:01:50,326 INFO [train.py:812] (4/8) Epoch 38, batch 800, loss[loss=0.1294, simple_loss=0.216, pruned_loss=0.02142, over 7413.00 frames.], tot_loss[loss=0.15, simple_loss=0.2427, pruned_loss=0.0287, over 1408545.76 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:02:49,130 INFO [train.py:812] (4/8) Epoch 38, batch 850, loss[loss=0.1434, simple_loss=0.2268, pruned_loss=0.02999, over 7343.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2427, pruned_loss=0.02833, over 1411137.54 frames.], batch size: 19, lr: 2.05e-04
2022-05-16 04:03:47,718 INFO [train.py:812] (4/8) Epoch 38, batch 900, loss[loss=0.1394, simple_loss=0.2332, pruned_loss=0.02278, over 7295.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2416, pruned_loss=0.02794, over 1413026.70 frames.], batch size: 24, lr: 2.05e-04
2022-05-16 04:04:46,212 INFO [train.py:812] (4/8) Epoch 38, batch 950, loss[loss=0.1341, simple_loss=0.2222, pruned_loss=0.02302, over 7279.00 frames.], tot_loss[loss=0.15, simple_loss=0.2425, pruned_loss=0.02874, over 1418634.94 frames.], batch size: 19, lr: 2.05e-04
2022-05-16 04:05:44,617 INFO [train.py:812] (4/8) Epoch 38, batch 1000, loss[loss=0.168, simple_loss=0.2652, pruned_loss=0.03542, over 7212.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02882, over 1420786.22 frames.], batch size: 22, lr: 2.05e-04
2022-05-16 04:06:43,934 INFO [train.py:812] (4/8) Epoch 38, batch 1050, loss[loss=0.1657, simple_loss=0.2596, pruned_loss=0.03593, over 7339.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2433, pruned_loss=0.02903, over 1422043.73 frames.], batch size: 20, lr: 2.05e-04
2022-05-16 04:07:41,758 INFO [train.py:812] (4/8) Epoch 38, batch 1100, loss[loss=0.1254, simple_loss=0.213, pruned_loss=0.01891, over 6771.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2436, pruned_loss=0.0289, over 1424802.13 frames.], batch size: 15, lr: 2.05e-04
2022-05-16 04:08:41,053 INFO [train.py:812] (4/8) Epoch 38, batch 1150, loss[loss=0.1281, simple_loss=0.2144, pruned_loss=0.02092, over 7276.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2434, pruned_loss=0.02856, over 1421918.92 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:09:40,642 INFO [train.py:812] (4/8) Epoch 38, batch 1200, loss[loss=0.1499, simple_loss=0.2513, pruned_loss=0.02425, over 7203.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2433, pruned_loss=0.02851, over 1424172.62 frames.], batch size: 26, lr: 2.05e-04
2022-05-16 04:10:39,705 INFO [train.py:812] (4/8) Epoch 38, batch 1250, loss[loss=0.1387, simple_loss=0.2449, pruned_loss=0.01626, over 6476.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2427, pruned_loss=0.02858, over 1427719.41 frames.], batch size: 38, lr: 2.05e-04
2022-05-16 04:11:38,484 INFO [train.py:812] (4/8) Epoch 38, batch 1300, loss[loss=0.1273, simple_loss=0.2169, pruned_loss=0.01882, over 7259.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2434, pruned_loss=0.02878, over 1427717.41 frames.], batch size: 17, lr: 2.05e-04
2022-05-16 04:12:36,177 INFO [train.py:812] (4/8) Epoch 38, batch 1350, loss[loss=0.135, simple_loss=0.2282, pruned_loss=0.02094, over 7114.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2425, pruned_loss=0.02886, over 1420964.30 frames.], batch size: 21, lr: 2.05e-04
2022-05-16 04:13:33,885 INFO [train.py:812] (4/8) Epoch 38, batch 1400, loss[loss=0.1523, simple_loss=0.249, pruned_loss=0.02778, over 7282.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02932, over 1421191.94 frames.], batch size: 24, lr: 2.05e-04
2022-05-16 04:14:32,882 INFO [train.py:812] (4/8) Epoch 38, batch 1450, loss[loss=0.1638, simple_loss=0.2578, pruned_loss=0.03496, over 7223.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2434, pruned_loss=0.0295, over 1425250.24 frames.], batch size: 22, lr: 2.05e-04
2022-05-16 04:15:31,398 INFO [train.py:812] (4/8) Epoch 38, batch 1500, loss[loss=0.1367, simple_loss=0.2333, pruned_loss=0.02002, over 7279.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2436, pruned_loss=0.02957, over 1425164.55 frames.], batch size: 25, lr: 2.05e-04
2022-05-16 04:16:30,122 INFO [train.py:812] (4/8) Epoch 38, batch 1550, loss[loss=0.1313, simple_loss=0.2234, pruned_loss=0.01962, over 7235.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2433, pruned_loss=0.02927, over 1422445.24 frames.], batch size: 20, lr: 2.05e-04
2022-05-16 04:17:27,396 INFO [train.py:812] (4/8) Epoch 38, batch 1600, loss[loss=0.1444, simple_loss=0.2329, pruned_loss=0.028, over 7268.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2439, pruned_loss=0.02938, over 1425617.17 frames.], batch size: 19, lr: 2.05e-04
2022-05-16 04:18:25,554 INFO [train.py:812] (4/8) Epoch 38, batch 1650, loss[loss=0.1771, simple_loss=0.2865, pruned_loss=0.03387, over 7069.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2438, pruned_loss=0.0294, over 1424775.28 frames.], batch size: 28, lr: 2.05e-04
2022-05-16 04:19:24,095 INFO [train.py:812] (4/8) Epoch 38, batch 1700, loss[loss=0.1365, simple_loss=0.2144, pruned_loss=0.02927, over 7174.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02918, over 1423185.33 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:20:24,538 INFO [train.py:812] (4/8) Epoch 38, batch 1750, loss[loss=0.1672, simple_loss=0.2541, pruned_loss=0.04012, over 5230.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02905, over 1422289.61 frames.], batch size: 54, lr: 2.05e-04
2022-05-16 04:21:23,206 INFO [train.py:812] (4/8) Epoch 38, batch 1800, loss[loss=0.1632, simple_loss=0.2679, pruned_loss=0.02921, over 7322.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02901, over 1419031.14 frames.], batch size: 20, lr: 2.05e-04
2022-05-16 04:22:21,144 INFO [train.py:812] (4/8) Epoch 38, batch 1850, loss[loss=0.1385, simple_loss=0.2261, pruned_loss=0.02548, over 7277.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02903, over 1421221.54 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:23:20,145 INFO [train.py:812] (4/8) Epoch 38, batch 1900, loss[loss=0.1331, simple_loss=0.2162, pruned_loss=0.02502, over 6808.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2431, pruned_loss=0.02908, over 1424243.44 frames.], batch size: 15, lr: 2.05e-04
2022-05-16 04:24:18,766 INFO [train.py:812] (4/8) Epoch 38, batch 1950, loss[loss=0.1311, simple_loss=0.219, pruned_loss=0.0216, over 7243.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2436, pruned_loss=0.02904, over 1427060.90 frames.], batch size: 19, lr: 2.05e-04
2022-05-16 04:25:17,623 INFO [train.py:812] (4/8) Epoch 38, batch 2000, loss[loss=0.1476, simple_loss=0.2225, pruned_loss=0.03641, over 7412.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2427, pruned_loss=0.02877, over 1427436.20 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:26:16,384 INFO [train.py:812] (4/8) Epoch 38, batch 2050, loss[loss=0.1252, simple_loss=0.2133, pruned_loss=0.01859, over 7263.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.02878, over 1424227.88 frames.], batch size: 19, lr: 2.05e-04
2022-05-16 04:27:14,057 INFO [train.py:812] (4/8) Epoch 38, batch 2100, loss[loss=0.1552, simple_loss=0.2483, pruned_loss=0.03109, over 7171.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2437, pruned_loss=0.02909, over 1418507.34 frames.], batch size: 26, lr: 2.05e-04
2022-05-16 04:28:12,419 INFO [train.py:812] (4/8) Epoch 38, batch 2150, loss[loss=0.1423, simple_loss=0.2304, pruned_loss=0.02707, over 7073.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2434, pruned_loss=0.02884, over 1418455.05 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:29:11,070 INFO [train.py:812] (4/8) Epoch 38, batch 2200, loss[loss=0.1407, simple_loss=0.2299, pruned_loss=0.02575, over 7059.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2442, pruned_loss=0.02921, over 1419679.13 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:30:15,102 INFO [train.py:812] (4/8) Epoch 38, batch 2250, loss[loss=0.1343, simple_loss=0.2311, pruned_loss=0.0187, over 6300.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2444, pruned_loss=0.02928, over 1418749.94 frames.], batch size: 38, lr: 2.05e-04
2022-05-16 04:31:14,140 INFO [train.py:812] (4/8) Epoch 38, batch 2300, loss[loss=0.166, simple_loss=0.2499, pruned_loss=0.04106, over 7058.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2442, pruned_loss=0.02924, over 1422400.77 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:32:13,338 INFO [train.py:812] (4/8) Epoch 38, batch 2350, loss[loss=0.148, simple_loss=0.2422, pruned_loss=0.02689, over 7335.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2435, pruned_loss=0.02918, over 1420082.73 frames.], batch size: 20, lr: 2.05e-04
2022-05-16 04:33:12,145 INFO [train.py:812] (4/8) Epoch 38, batch 2400, loss[loss=0.1506, simple_loss=0.2311, pruned_loss=0.03503, over 7398.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.02884, over 1424304.09 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:34:10,723 INFO [train.py:812] (4/8) Epoch 38, batch 2450, loss[loss=0.1581, simple_loss=0.2521, pruned_loss=0.03202, over 7322.00 frames.], tot_loss[loss=0.1505, simple_loss=0.243, pruned_loss=0.02894, over 1425927.29 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:35:08,797 INFO [train.py:812] (4/8) Epoch 38, batch 2500, loss[loss=0.1357, simple_loss=0.2265, pruned_loss=0.02245, over 7168.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2423, pruned_loss=0.02871, over 1425601.50 frames.], batch size: 18, lr: 2.04e-04
2022-05-16 04:36:06,687 INFO [train.py:812] (4/8) Epoch 38, batch 2550, loss[loss=0.1442, simple_loss=0.229, pruned_loss=0.02972, over 7179.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2417, pruned_loss=0.02844, over 1423488.20 frames.], batch size: 18, lr: 2.04e-04
2022-05-16 04:37:05,283 INFO [train.py:812] (4/8) Epoch 38, batch 2600, loss[loss=0.1471, simple_loss=0.2468, pruned_loss=0.02371, over 7435.00 frames.], tot_loss[loss=0.1486, simple_loss=0.241, pruned_loss=0.02807, over 1422594.87 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:38:03,422 INFO [train.py:812] (4/8) Epoch 38, batch 2650, loss[loss=0.1579, simple_loss=0.2527, pruned_loss=0.0316, over 7211.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2413, pruned_loss=0.02812, over 1424324.95 frames.], batch size: 23, lr: 2.04e-04
2022-05-16 04:39:01,033 INFO [train.py:812] (4/8) Epoch 38, batch 2700, loss[loss=0.1341, simple_loss=0.2265, pruned_loss=0.02085, over 7232.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2405, pruned_loss=0.02785, over 1425192.07 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:39:59,842 INFO [train.py:812] (4/8) Epoch 38, batch 2750, loss[loss=0.1506, simple_loss=0.2381, pruned_loss=0.0315, over 7360.00 frames.], tot_loss[loss=0.1485, simple_loss=0.241, pruned_loss=0.02801, over 1426712.87 frames.], batch size: 19, lr: 2.04e-04
2022-05-16 04:40:57,548 INFO [train.py:812] (4/8) Epoch 38, batch 2800, loss[loss=0.153, simple_loss=0.2415, pruned_loss=0.03227, over 7279.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2403, pruned_loss=0.02774, over 1425055.77 frames.], batch size: 24, lr: 2.04e-04
2022-05-16 04:41:55,564 INFO [train.py:812] (4/8) Epoch 38, batch 2850, loss[loss=0.1465, simple_loss=0.2484, pruned_loss=0.02233, over 7419.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2404, pruned_loss=0.02786, over 1425196.36 frames.], batch size: 21, lr: 2.04e-04
2022-05-16 04:42:54,118 INFO [train.py:812] (4/8) Epoch 38, batch 2900, loss[loss=0.1698, simple_loss=0.2386, pruned_loss=0.05047, over 7132.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2404, pruned_loss=0.02812, over 1425382.33 frames.], batch size: 17, lr: 2.04e-04
2022-05-16 04:43:53,033 INFO [train.py:812] (4/8) Epoch 38, batch 2950, loss[loss=0.1138, simple_loss=0.2016, pruned_loss=0.01301, over 7394.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2407, pruned_loss=0.02788, over 1430366.51 frames.], batch size: 18, lr: 2.04e-04
2022-05-16 04:44:52,017 INFO [train.py:812] (4/8) Epoch 38, batch 3000, loss[loss=0.1721, simple_loss=0.2604, pruned_loss=0.04193, over 7205.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2414, pruned_loss=0.02823, over 1429496.39 frames.], batch size: 23, lr: 2.04e-04
2022-05-16 04:44:52,018 INFO [train.py:832] (4/8) Computing validation loss
2022-05-16 04:44:59,416 INFO [train.py:841] (4/8) Epoch 38, validation: loss=0.1532, simple_loss=0.2484, pruned_loss=0.02898, over 698248.00 frames.
2022-05-16 04:45:58,535 INFO [train.py:812] (4/8) Epoch 38, batch 3050, loss[loss=0.1516, simple_loss=0.2378, pruned_loss=0.03272, over 7168.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2421, pruned_loss=0.02843, over 1429960.60 frames.], batch size: 18, lr: 2.04e-04
2022-05-16 04:46:56,204 INFO [train.py:812] (4/8) Epoch 38, batch 3100, loss[loss=0.1588, simple_loss=0.2567, pruned_loss=0.03046, over 7215.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.0287, over 1422760.95 frames.], batch size: 22, lr: 2.04e-04
2022-05-16 04:47:54,544 INFO [train.py:812] (4/8) Epoch 38, batch 3150, loss[loss=0.1948, simple_loss=0.277, pruned_loss=0.05626, over 7379.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02899, over 1421482.26 frames.], batch size: 23, lr: 2.04e-04
2022-05-16 04:48:52,457 INFO [train.py:812] (4/8) Epoch 38, batch 3200, loss[loss=0.1412, simple_loss=0.2392, pruned_loss=0.02159, over 7106.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2422, pruned_loss=0.02917, over 1426006.23 frames.], batch size: 21, lr: 2.04e-04
2022-05-16 04:49:51,337 INFO [train.py:812] (4/8) Epoch 38, batch 3250, loss[loss=0.135, simple_loss=0.2247, pruned_loss=0.02272, over 7274.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02893, over 1426438.04 frames.], batch size: 18, lr: 2.04e-04
2022-05-16 04:50:49,204 INFO [train.py:812] (4/8) Epoch 38, batch 3300, loss[loss=0.1507, simple_loss=0.2531, pruned_loss=0.02415, over 7235.00 frames.], tot_loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.02867, over 1426023.66 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:51:47,401 INFO [train.py:812] (4/8) Epoch 38, batch 3350, loss[loss=0.1581, simple_loss=0.2473, pruned_loss=0.03439, over 7181.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02877, over 1427190.85 frames.], batch size: 22, lr: 2.04e-04
2022-05-16 04:52:45,594 INFO [train.py:812] (4/8) Epoch 38, batch 3400, loss[loss=0.1566, simple_loss=0.2461, pruned_loss=0.03357, over 6784.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2428, pruned_loss=0.02877, over 1430814.90 frames.], batch size: 31, lr: 2.04e-04
2022-05-16 04:53:45,203 INFO [train.py:812] (4/8) Epoch 38, batch 3450, loss[loss=0.1386, simple_loss=0.2317, pruned_loss=0.02275, over 7439.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2427, pruned_loss=0.02892, over 1432616.30 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:54:43,564 INFO [train.py:812] (4/8) Epoch 38, batch 3500, loss[loss=0.1461, simple_loss=0.2355, pruned_loss=0.02833, over 7230.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02888, over 1430474.34 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:55:41,797 INFO [train.py:812] (4/8) Epoch 38, batch 3550, loss[loss=0.1374, simple_loss=0.2414, pruned_loss=0.01669, over 7144.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2432, pruned_loss=0.02903, over 1430821.89 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:56:49,632 INFO [train.py:812] (4/8) Epoch 38, batch 3600, loss[loss=0.1527, simple_loss=0.2508, pruned_loss=0.02728, over 6678.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.02892, over 1429322.27 frames.], batch size: 31, lr: 2.04e-04
2022-05-16 04:57:48,375 INFO [train.py:812] (4/8) Epoch 38, batch 3650, loss[loss=0.173, simple_loss=0.2565, pruned_loss=0.04481, over 7120.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02919, over 1431987.46 frames.], batch size: 28, lr: 2.04e-04
2022-05-16 04:58:46,160 INFO [train.py:812] (4/8) Epoch 38, batch 3700, loss[loss=0.1737, simple_loss=0.2724, pruned_loss=0.03748, over 7285.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02907, over 1423280.13 frames.], batch size: 24, lr: 2.04e-04
2022-05-16 05:00:03,395 INFO [train.py:812] (4/8) Epoch 38, batch 3750, loss[loss=0.1409, simple_loss=0.2402, pruned_loss=0.02082, over 7162.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2428, pruned_loss=0.02907, over 1418271.14 frames.], batch size: 19, lr: 2.04e-04
2022-05-16 05:01:01,783 INFO [train.py:812] (4/8) Epoch 38, batch 3800, loss[loss=0.1578, simple_loss=0.2521, pruned_loss=0.03174, over 7384.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02886, over 1418542.81 frames.], batch size: 23, lr: 2.04e-04
2022-05-16 05:02:01,305 INFO [train.py:812] (4/8) Epoch 38, batch 3850, loss[loss=0.1488, simple_loss=0.2353, pruned_loss=0.03115, over 7109.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2412, pruned_loss=0.02853, over 1420572.89 frames.], batch size: 21, lr: 2.04e-04
2022-05-16 05:03:01,099 INFO [train.py:812] (4/8) Epoch 38, batch 3900, loss[loss=0.1358, simple_loss=0.2351, pruned_loss=0.0183, over 7329.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2404, pruned_loss=0.02843, over 1422671.18 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 05:03:59,298 INFO [train.py:812] (4/8) Epoch 38, batch 3950, loss[loss=0.1617, simple_loss=0.2529, pruned_loss=0.03525, over 7190.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2405, pruned_loss=0.02864, over 1417849.56 frames.], batch size: 22, lr: 2.04e-04
2022-05-16 05:04:56,835 INFO [train.py:812] (4/8) Epoch 38, batch 4000, loss[loss=0.1306, simple_loss=0.2195, pruned_loss=0.02081, over 7148.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2402, pruned_loss=0.02861, over 1417685.90 frames.], batch size: 19, lr: 2.04e-04
2022-05-16 05:06:06,115 INFO [train.py:812] (4/8) Epoch 38, batch 4050, loss[loss=0.1375, simple_loss=0.2281, pruned_loss=0.02343, over 7293.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2401, pruned_loss=0.02837, over 1410683.66 frames.], batch size: 17, lr: 2.04e-04
2022-05-16 05:07:14,548 INFO [train.py:812] (4/8) Epoch 38, batch 4100, loss[loss=0.1387, simple_loss=0.2418, pruned_loss=0.01781, over 7219.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2413, pruned_loss=0.02866, over 1412939.86 frames.], batch size: 21, lr: 2.04e-04
2022-05-16 05:08:13,931 INFO [train.py:812] (4/8) Epoch 38, batch 4150, loss[loss=0.1635, simple_loss=0.2499, pruned_loss=0.03854, over 7261.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2402, pruned_loss=0.02841, over 1412915.59 frames.], batch size: 19, lr: 2.03e-04
2022-05-16 05:09:21,218 INFO [train.py:812] (4/8) Epoch 38, batch 4200, loss[loss=0.148, simple_loss=0.2395, pruned_loss=0.02819, over 7301.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2397, pruned_loss=0.02784, over 1413949.40 frames.], batch size: 24, lr: 2.03e-04
2022-05-16 05:10:29,485 INFO [train.py:812] (4/8) Epoch 38, batch 4250, loss[loss=0.1291, simple_loss=0.2241, pruned_loss=0.01704, over 7229.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2403, pruned_loss=0.02804, over 1414174.04 frames.], batch size: 20, lr: 2.03e-04
2022-05-16 05:11:27,935 INFO [train.py:812] (4/8) Epoch 38, batch 4300, loss[loss=0.1859, simple_loss=0.2784, pruned_loss=0.04666, over 5236.00 frames.], tot_loss[loss=0.1474, simple_loss=0.239, pruned_loss=0.02786, over 1411922.68 frames.], batch size: 53, lr: 2.03e-04
2022-05-16 05:12:26,581 INFO [train.py:812] (4/8) Epoch 38, batch 4350, loss[loss=0.1391, simple_loss=0.2188, pruned_loss=0.02968, over 6985.00 frames.], tot_loss[loss=0.1467, simple_loss=0.238, pruned_loss=0.02767, over 1413930.34 frames.], batch size: 16, lr: 2.03e-04
2022-05-16 05:13:26,090 INFO [train.py:812] (4/8) Epoch 38, batch 4400, loss[loss=0.1416, simple_loss=0.2313, pruned_loss=0.02594, over 6797.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2382, pruned_loss=0.02766, over 1414479.08 frames.], batch size: 15, lr: 2.03e-04
2022-05-16 05:14:25,868 INFO [train.py:812] (4/8) Epoch 38, batch 4450, loss[loss=0.1342, simple_loss=0.2251, pruned_loss=0.02166, over 6798.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2377, pruned_loss=0.02775, over 1405851.06 frames.], batch size: 15, lr: 2.03e-04
2022-05-16 05:15:24,214 INFO [train.py:812] (4/8) Epoch 38, batch 4500, loss[loss=0.1394, simple_loss=0.2296, pruned_loss=0.0246, over 6505.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2382, pruned_loss=0.02839, over 1380332.80 frames.], batch size: 38, lr: 2.03e-04
2022-05-16 05:16:23,031 INFO [train.py:812] (4/8) Epoch 38, batch 4550, loss[loss=0.1494, simple_loss=0.2391, pruned_loss=0.02987, over 4717.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2378, pruned_loss=0.02864, over 1354254.13 frames.], batch size: 52, lr: 2.03e-04
2022-05-16 05:17:28,550 INFO [train.py:812] (4/8) Epoch 39, batch 0, loss[loss=0.1467, simple_loss=0.2441, pruned_loss=0.02464, over 7265.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2441, pruned_loss=0.02464, over 7265.00 frames.], batch size: 19, lr: 2.01e-04
2022-05-16 05:18:26,906 INFO [train.py:812] (4/8) Epoch 39, batch 50, loss[loss=0.1503, simple_loss=0.2533, pruned_loss=0.02363, over 7149.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2436, pruned_loss=0.02804, over 320035.83 frames.], batch size: 20, lr: 2.01e-04
2022-05-16 05:19:25,801 INFO [train.py:812] (4/8) Epoch 39, batch 100, loss[loss=0.1504, simple_loss=0.2478, pruned_loss=0.02655, over 6864.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2423, pruned_loss=0.02737, over 565903.69 frames.], batch size: 31, lr: 2.01e-04
2022-05-16 05:20:24,080 INFO [train.py:812] (4/8) Epoch 39, batch 150, loss[loss=0.1361, simple_loss=0.2304, pruned_loss=0.02088, over 7159.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2403, pruned_loss=0.02776, over 754395.03 frames.], batch size: 18, lr: 2.01e-04
2022-05-16 05:21:22,518 INFO [train.py:812] (4/8) Epoch 39, batch 200, loss[loss=0.1461, simple_loss=0.2357, pruned_loss=0.0282, over 7436.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2411, pruned_loss=0.02798, over 901765.01 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:22:20,453 INFO [train.py:812] (4/8) Epoch 39, batch 250, loss[loss=0.1469, simple_loss=0.2416, pruned_loss=0.02609, over 6386.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02827, over 1017341.98 frames.], batch size: 38, lr: 2.00e-04
2022-05-16 05:23:19,091 INFO [train.py:812] (4/8) Epoch 39, batch 300, loss[loss=0.1453, simple_loss=0.239, pruned_loss=0.02577, over 7433.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2411, pruned_loss=0.02806, over 1112670.01 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:24:17,710 INFO [train.py:812] (4/8) Epoch 39, batch 350, loss[loss=0.1415, simple_loss=0.2405, pruned_loss=0.02127, over 7272.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2406, pruned_loss=0.02804, over 1179446.53 frames.], batch size: 24, lr: 2.00e-04
2022-05-16 05:25:17,168 INFO [train.py:812] (4/8) Epoch 39, batch 400, loss[loss=0.1527, simple_loss=0.2535, pruned_loss=0.02589, over 7212.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2409, pruned_loss=0.02809, over 1229376.67 frames.], batch size: 21, lr: 2.00e-04
2022-05-16 05:26:16,281 INFO [train.py:812] (4/8) Epoch 39, batch 450, loss[loss=0.1815, simple_loss=0.2758, pruned_loss=0.04356, over 7195.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2411, pruned_loss=0.02829, over 1274809.47 frames.], batch size: 23, lr: 2.00e-04
2022-05-16 05:27:15,059 INFO [train.py:812] (4/8) Epoch 39, batch 500, loss[loss=0.1362, simple_loss=0.242, pruned_loss=0.01519, over 7142.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02882, over 1301890.51 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:28:14,643 INFO [train.py:812] (4/8) Epoch 39, batch 550, loss[loss=0.1449, simple_loss=0.2341, pruned_loss=0.0278, over 7435.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2415, pruned_loss=0.02878, over 1327561.12 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:29:14,822 INFO [train.py:812] (4/8) Epoch 39, batch 600, loss[loss=0.1378, simple_loss=0.2304, pruned_loss=0.02263, over 7159.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2409, pruned_loss=0.02834, over 1345876.64 frames.], batch size: 18, lr: 2.00e-04
2022-05-16 05:30:14,577 INFO [train.py:812] (4/8) Epoch 39, batch 650, loss[loss=0.1215, simple_loss=0.2045, pruned_loss=0.01925, over 7284.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2408, pruned_loss=0.02803, over 1365815.38 frames.], batch size: 17, lr: 2.00e-04
2022-05-16 05:31:13,692 INFO [train.py:812] (4/8) Epoch 39, batch 700, loss[loss=0.1481, simple_loss=0.2354, pruned_loss=0.03037, over 6821.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2398, pruned_loss=0.02789, over 1378543.43 frames.], batch size: 15, lr: 2.00e-04
2022-05-16 05:32:12,656 INFO [train.py:812] (4/8) Epoch 39, batch 750, loss[loss=0.1631, simple_loss=0.2612, pruned_loss=0.03255, over 6273.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2401, pruned_loss=0.0277, over 1386917.15 frames.], batch size: 37, lr: 2.00e-04
2022-05-16 05:33:12,264 INFO [train.py:812] (4/8) Epoch 39, batch 800, loss[loss=0.1487, simple_loss=0.2452, pruned_loss=0.02614, over 7231.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2403, pruned_loss=0.02769, over 1399535.20 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:34:10,583 INFO [train.py:812] (4/8) Epoch 39, batch 850, loss[loss=0.1524, simple_loss=0.2526, pruned_loss=0.0261, over 7120.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2389, pruned_loss=0.02713, over 1405114.16 frames.], batch size: 28, lr: 2.00e-04
2022-05-16 05:35:08,790 INFO [train.py:812] (4/8) Epoch 39, batch 900, loss[loss=0.1566, simple_loss=0.2546, pruned_loss=0.02926, over 7420.00 frames.], tot_loss[loss=0.1476, simple_loss=0.24, pruned_loss=0.02763, over 1402946.51 frames.], batch size: 21, lr: 2.00e-04
2022-05-16 05:36:07,917 INFO [train.py:812] (4/8) Epoch 39, batch 950, loss[loss=0.1366, simple_loss=0.2174, pruned_loss=0.02795, over 7135.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2411, pruned_loss=0.02798, over 1404291.37 frames.], batch size: 17, lr: 2.00e-04
2022-05-16 05:37:07,612 INFO [train.py:812] (4/8) Epoch 39, batch 1000, loss[loss=0.1517, simple_loss=0.2505, pruned_loss=0.02644, over 7360.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02821, over 1407408.04 frames.], batch size: 19, lr: 2.00e-04
2022-05-16 05:38:06,540 INFO [train.py:812] (4/8) Epoch 39, batch 1050, loss[loss=0.139, simple_loss=0.2364, pruned_loss=0.02077, over 6992.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2413, pruned_loss=0.02846, over 1410721.33 frames.], batch size: 32, lr: 2.00e-04
2022-05-16 05:39:05,053 INFO [train.py:812] (4/8) Epoch 39, batch 1100, loss[loss=0.169, simple_loss=0.2593, pruned_loss=0.03932, over 7381.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2409, pruned_loss=0.02836, over 1415986.45 frames.], batch size: 23, lr: 2.00e-04
2022-05-16 05:40:03,849 INFO [train.py:812] (4/8) Epoch 39, batch 1150, loss[loss=0.1452, simple_loss=0.2301, pruned_loss=0.03019, over 7276.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2403, pruned_loss=0.02822, over 1419845.69 frames.], batch size: 18, lr: 2.00e-04
2022-05-16 05:41:02,328 INFO [train.py:812] (4/8) Epoch 39, batch 1200, loss[loss=0.1392, simple_loss=0.2348, pruned_loss=0.02174, over 6833.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2405, pruned_loss=0.02807, over 1421747.70 frames.], batch size: 31, lr: 2.00e-04
2022-05-16 05:42:00,509 INFO [train.py:812] (4/8) Epoch 39, batch 1250, loss[loss=0.1531, simple_loss=0.25, pruned_loss=0.02808, over 7429.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2407, pruned_loss=0.02828, over 1421529.55 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:42:59,391 INFO [train.py:812] (4/8) Epoch 39, batch 1300, loss[loss=0.1311, simple_loss=0.2197, pruned_loss=0.02123, over 7258.00 frames.], tot_loss[loss=0.149, simple_loss=0.241, pruned_loss=0.02856, over 1425000.98 frames.], batch size: 17, lr: 2.00e-04
2022-05-16 05:43:56,600 INFO [train.py:812] (4/8) Epoch 39, batch 1350, loss[loss=0.1494, simple_loss=0.2521, pruned_loss=0.02335, over 7335.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2413, pruned_loss=0.02843, over 1424725.93 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:45:05,779 INFO [train.py:812] (4/8) Epoch 39, batch 1400, loss[loss=0.1298, simple_loss=0.2222, pruned_loss=0.01867, over 7168.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2416, pruned_loss=0.02868, over 1423016.68 frames.], batch size: 19, lr: 2.00e-04
2022-05-16 05:46:03,945 INFO [train.py:812] (4/8) Epoch 39, batch 1450, loss[loss=0.1492, simple_loss=0.2491, pruned_loss=0.02465, over 7277.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.0288, over 1423596.53 frames.], batch size: 25, lr: 2.00e-04
2022-05-16 05:47:01,542 INFO [train.py:812] (4/8) Epoch 39, batch 1500, loss[loss=0.174, simple_loss=0.277, pruned_loss=0.03549, over 7114.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2425, pruned_loss=0.02864, over 1422487.70 frames.], batch size: 21, lr: 2.00e-04
2022-05-16 05:48:00,121 INFO [train.py:812] (4/8) Epoch 39, batch 1550, loss[loss=0.1404, simple_loss=0.2374, pruned_loss=0.0217, over 7197.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.02819, over 1423286.36 frames.], batch size: 22, lr: 2.00e-04
2022-05-16 05:48:59,841 INFO [train.py:812] (4/8) Epoch 39, batch 1600, loss[loss=0.1627, simple_loss=0.2638, pruned_loss=0.03078, over 6725.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2409, pruned_loss=0.02788, over 1425301.87 frames.], batch size: 31, lr: 2.00e-04
2022-05-16 05:49:57,808 INFO [train.py:812] (4/8) Epoch 39, batch 1650, loss[loss=0.1502, simple_loss=0.2502, pruned_loss=0.02507, over 7220.00 frames.], tot_loss[loss=0.1485, simple_loss=0.241, pruned_loss=0.02806, over 1423855.72 frames.], batch size: 21, lr: 2.00e-04
2022-05-16 05:51:01,155 INFO [train.py:812] (4/8) Epoch 39, batch 1700, loss[loss=0.1431, simple_loss=0.2347, pruned_loss=0.02579, over 7032.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2418, pruned_loss=0.02833, over 1425745.74 frames.], batch size: 28, lr: 2.00e-04
2022-05-16 05:51:59,352 INFO [train.py:812] (4/8) Epoch 39, batch 1750, loss[loss=0.1323, simple_loss=0.227, pruned_loss=0.01876, over 7431.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2418, pruned_loss=0.028, over 1425116.99 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:52:58,531 INFO [train.py:812] (4/8) Epoch 39, batch 1800, loss[loss=0.1544, simple_loss=0.2629, pruned_loss=0.02299, over 7204.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2423, pruned_loss=0.02797, over 1422989.56 frames.], batch size: 23, lr: 2.00e-04
2022-05-16 05:53:57,513 INFO [train.py:812] (4/8) Epoch 39, batch 1850, loss[loss=0.153, simple_loss=0.2477, pruned_loss=0.02914, over 7169.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2425, pruned_loss=0.02811, over 1420161.28 frames.], batch size: 19, lr: 2.00e-04
2022-05-16 05:54:55,918 INFO [train.py:812] (4/8) Epoch 39, batch 1900, loss[loss=0.1327, simple_loss=0.2193, pruned_loss=0.02299, over 7298.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2422, pruned_loss=0.02815, over 1423414.47 frames.], batch size: 18, lr: 2.00e-04
2022-05-16 05:55:54,027 INFO [train.py:812] (4/8) Epoch 39, batch 1950, loss[loss=0.1436, simple_loss=0.246, pruned_loss=0.0206, over 7333.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2424, pruned_loss=0.02813, over 1423532.46 frames.], batch size: 21, lr: 1.99e-04
2022-05-16 05:56:52,312 INFO [train.py:812] (4/8) Epoch 39, batch 2000, loss[loss=0.1382, simple_loss=0.2275, pruned_loss=0.02443, over 7258.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2426, pruned_loss=0.02856, over 1423368.83 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 05:57:50,333 INFO [train.py:812] (4/8) Epoch 39, batch 2050, loss[loss=0.1452, simple_loss=0.2352, pruned_loss=0.0276, over 7341.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2429, pruned_loss=0.02868, over 1421999.42 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 05:58:49,533 INFO [train.py:812] (4/8) Epoch 39, batch 2100, loss[loss=0.1234, simple_loss=0.215, pruned_loss=0.01587, over 6762.00 frames.], tot_loss[loss=0.15, simple_loss=0.2425, pruned_loss=0.02876, over 1423585.62 frames.], batch size: 15, lr: 1.99e-04
2022-05-16 05:59:47,691 INFO [train.py:812] (4/8) Epoch 39, batch 2150, loss[loss=0.1404, simple_loss=0.23, pruned_loss=0.02534, over 7254.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02895, over 1421137.77 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:00:46,908 INFO [train.py:812] (4/8) Epoch 39, batch 2200, loss[loss=0.1698, simple_loss=0.2623, pruned_loss=0.03864, over 7224.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2425, pruned_loss=0.02864, over 1421740.64 frames.], batch size: 22, lr: 1.99e-04
2022-05-16 06:01:45,965 INFO [train.py:812] (4/8) Epoch 39, batch 2250, loss[loss=0.1765, simple_loss=0.261, pruned_loss=0.04597, over 7148.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02843, over 1424943.37 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 06:02:45,400 INFO [train.py:812] (4/8) Epoch 39, batch 2300, loss[loss=0.1364, simple_loss=0.2269, pruned_loss=0.02296, over 7168.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02865, over 1424837.88 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:03:45,424 INFO [train.py:812] (4/8) Epoch 39, batch 2350, loss[loss=0.1416, simple_loss=0.2422, pruned_loss=0.02053, over 7238.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2416, pruned_loss=0.02856, over 1426470.13 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 06:04:43,837 INFO [train.py:812] (4/8) Epoch 39, batch 2400, loss[loss=0.139, simple_loss=0.2359, pruned_loss=0.02112, over 7143.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2409, pruned_loss=0.02836, over 1428529.74 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 06:05:41,782 INFO [train.py:812] (4/8) Epoch 39, batch 2450, loss[loss=0.1353, simple_loss=0.2241, pruned_loss=0.02327, over 7404.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2402, pruned_loss=0.02776, over 1429562.32 frames.], batch size: 18, lr: 1.99e-04
2022-05-16 06:06:40,892 INFO [train.py:812] (4/8) Epoch 39, batch 2500, loss[loss=0.1278, simple_loss=0.2179, pruned_loss=0.01881, over 7410.00 frames.], tot_loss[loss=0.1467, simple_loss=0.239, pruned_loss=0.02719, over 1427550.60 frames.], batch size: 18, lr: 1.99e-04
2022-05-16 06:07:38,144 INFO [train.py:812] (4/8) Epoch 39, batch 2550, loss[loss=0.1335, simple_loss=0.2244, pruned_loss=0.02135, over 7419.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2388, pruned_loss=0.0272, over 1432169.04 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 06:08:37,359 INFO [train.py:812] (4/8) Epoch 39, batch 2600, loss[loss=0.1563, simple_loss=0.2506, pruned_loss=0.03099, over 7153.00 frames.], tot_loss[loss=0.1475, simple_loss=0.24, pruned_loss=0.02753, over 1429784.85 frames.], batch size: 26, lr: 1.99e-04
2022-05-16 06:09:36,152 INFO [train.py:812] (4/8) Epoch 39, batch 2650, loss[loss=0.1555, simple_loss=0.2463, pruned_loss=0.03241, over 7050.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2407, pruned_loss=0.02761, over 1430634.77 frames.], batch size: 28, lr: 1.99e-04
2022-05-16 06:10:34,089 INFO [train.py:812] (4/8) Epoch 39, batch 2700, loss[loss=0.1813, simple_loss=0.2715, pruned_loss=0.04555, over 7336.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2407, pruned_loss=0.02786, over 1428823.56 frames.], batch size: 25, lr: 1.99e-04
2022-05-16 06:11:32,685 INFO [train.py:812] (4/8) Epoch 39, batch 2750, loss[loss=0.1395, simple_loss=0.2268, pruned_loss=0.02611, over 7159.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2409, pruned_loss=0.0282, over 1430057.17 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:12:31,345 INFO [train.py:812] (4/8) Epoch 39, batch 2800, loss[loss=0.1459, simple_loss=0.2465, pruned_loss=0.0227, over 7335.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02832, over 1426959.80 frames.], batch size: 22, lr: 1.99e-04
2022-05-16 06:13:29,203 INFO [train.py:812] (4/8) Epoch 39, batch 2850, loss[loss=0.1581, simple_loss=0.2541, pruned_loss=0.03107, over 6365.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02871, over 1426927.47 frames.], batch size: 38, lr: 1.99e-04
2022-05-16 06:14:28,574 INFO [train.py:812] (4/8) Epoch 39, batch 2900, loss[loss=0.1611, simple_loss=0.2607, pruned_loss=0.03075, over 7320.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2424, pruned_loss=0.02867, over 1425059.71 frames.], batch size: 21, lr: 1.99e-04
2022-05-16 06:15:27,566 INFO [train.py:812] (4/8) Epoch 39, batch 2950, loss[loss=0.1403, simple_loss=0.241, pruned_loss=0.01979, over 7331.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2415, pruned_loss=0.02852, over 1427773.00 frames.], batch size: 22, lr: 1.99e-04
2022-05-16 06:16:26,920 INFO [train.py:812] (4/8) Epoch 39, batch 3000, loss[loss=0.1538, simple_loss=0.2431, pruned_loss=0.03225, over 7233.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2427, pruned_loss=0.02882, over 1428814.42 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 06:16:26,921 INFO [train.py:832] (4/8) Computing validation loss
2022-05-16 06:16:34,437 INFO [train.py:841] (4/8) Epoch 39, validation: loss=0.153, simple_loss=0.2484, pruned_loss=0.02885, over 698248.00 frames.
2022-05-16 06:17:33,454 INFO [train.py:812] (4/8) Epoch 39, batch 3050, loss[loss=0.1418, simple_loss=0.2241, pruned_loss=0.02978, over 7136.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02866, over 1425877.37 frames.], batch size: 17, lr: 1.99e-04
2022-05-16 06:18:32,180 INFO [train.py:812] (4/8) Epoch 39, batch 3100, loss[loss=0.1582, simple_loss=0.256, pruned_loss=0.03019, over 6484.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2421, pruned_loss=0.02863, over 1418210.33 frames.], batch size: 38, lr: 1.99e-04
2022-05-16 06:19:30,263 INFO [train.py:812] (4/8) Epoch 39, batch 3150, loss[loss=0.1374, simple_loss=0.2364, pruned_loss=0.01921, over 7396.00 frames.], tot_loss[loss=0.149, simple_loss=0.2415, pruned_loss=0.02824, over 1423252.24 frames.], batch size: 21, lr: 1.99e-04
2022-05-16 06:20:28,880 INFO [train.py:812] (4/8) Epoch 39, batch 3200, loss[loss=0.1494, simple_loss=0.2486, pruned_loss=0.02511, over 6417.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2408, pruned_loss=0.02805, over 1424584.91 frames.], batch size: 38, lr: 1.99e-04
2022-05-16 06:21:26,208 INFO [train.py:812] (4/8) Epoch 39, batch 3250, loss[loss=0.1718, simple_loss=0.2619, pruned_loss=0.04087, over 6288.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2404, pruned_loss=0.02773, over 1424415.78 frames.], batch size: 37, lr: 1.99e-04
2022-05-16 06:22:25,454 INFO [train.py:812] (4/8) Epoch 39, batch 3300, loss[loss=0.1371, simple_loss=0.2375, pruned_loss=0.01829, over 7165.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2402, pruned_loss=0.02768, over 1424455.38 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:23:24,301 INFO [train.py:812] (4/8) Epoch 39, batch 3350, loss[loss=0.1481, simple_loss=0.2326, pruned_loss=0.0318, over 7138.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2397, pruned_loss=0.02739, over 1426955.05 frames.], batch size: 17, lr: 1.99e-04
2022-05-16 06:24:23,013 INFO [train.py:812] (4/8) Epoch 39, batch 3400, loss[loss=0.1533, simple_loss=0.2524, pruned_loss=0.02714, over 7363.00 frames.], tot_loss[loss=0.1477, simple_loss=0.24, pruned_loss=0.02775, over 1426949.32 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:25:22,180 INFO [train.py:812] (4/8) Epoch 39, batch 3450, loss[loss=0.1512, simple_loss=0.253, pruned_loss=0.0247, over 7218.00 frames.], tot_loss[loss=0.148, simple_loss=0.2402, pruned_loss=0.02791, over 1419182.42 frames.], batch size: 23, lr: 1.99e-04
2022-05-16 06:26:21,456 INFO [train.py:812] (4/8) Epoch 39, batch 3500, loss[loss=0.1581, simple_loss=0.2518, pruned_loss=0.03219, over 7159.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2411, pruned_loss=0.02809, over 1421055.33 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:27:20,258 INFO [train.py:812] (4/8) Epoch 39, batch 3550, loss[loss=0.1367, simple_loss=0.2339, pruned_loss=0.01977, over 7350.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2409, pruned_loss=0.02814, over 1423612.76 frames.], batch size: 22, lr: 1.99e-04
2022-05-16 06:28:19,538 INFO [train.py:812] (4/8) Epoch 39, batch 3600, loss[loss=0.1379, simple_loss=0.221, pruned_loss=0.02742, over 7279.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2412, pruned_loss=0.0281, over 1423785.63 frames.], batch size: 18, lr: 1.99e-04
2022-05-16 06:29:17,986 INFO [train.py:812] (4/8) Epoch 39, batch 3650, loss[loss=0.1616, simple_loss=0.2611, pruned_loss=0.03108, over 7009.00 frames.], tot_loss[loss=0.1493, simple_loss=0.242, pruned_loss=0.02835, over 1425014.37 frames.], batch size: 28, lr: 1.99e-04
2022-05-16 06:30:16,890 INFO [train.py:812] (4/8) Epoch 39, batch 3700, loss[loss=0.1379, simple_loss=0.2277, pruned_loss=0.02403, over 6494.00 frames.], tot_loss[loss=0.149, simple_loss=0.2419, pruned_loss=0.02802, over 1421605.47 frames.], batch size: 38, lr: 1.99e-04
2022-05-16 06:31:16,316 INFO [train.py:812] (4/8) Epoch 39, batch 3750, loss[loss=0.1602, simple_loss=0.2506, pruned_loss=0.03492, over 7186.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2413, pruned_loss=0.02804, over 1415413.39 frames.], batch size: 23, lr: 1.98e-04
2022-05-16 06:32:15,551 INFO [train.py:812] (4/8) Epoch 39, batch 3800, loss[loss=0.1525, simple_loss=0.2468, pruned_loss=0.02915, over 7360.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2409, pruned_loss=0.02776, over 1421588.59 frames.], batch size: 19, lr: 1.98e-04
2022-05-16 06:33:12,766 INFO [train.py:812] (4/8) Epoch 39, batch 3850, loss[loss=0.1934, simple_loss=0.2669, pruned_loss=0.05995, over 5018.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2415, pruned_loss=0.02832, over 1419002.06 frames.], batch size: 52, lr: 1.98e-04
2022-05-16 06:34:10,688 INFO [train.py:812] (4/8) Epoch 39, batch 3900, loss[loss=0.1595, simple_loss=0.2497, pruned_loss=0.03466, over 7041.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02827, over 1420521.70 frames.], batch size: 28, lr: 1.98e-04
2022-05-16 06:35:09,072 INFO [train.py:812] (4/8) Epoch 39, batch 3950, loss[loss=0.1581, simple_loss=0.2562, pruned_loss=0.03001, over 7287.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2418, pruned_loss=0.0283, over 1422356.10 frames.], batch size: 25, lr: 1.98e-04
2022-05-16 06:36:07,269 INFO [train.py:812] (4/8) Epoch 39, batch 4000, loss[loss=0.1479, simple_loss=0.2458, pruned_loss=0.02499, over 6758.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2413, pruned_loss=0.028, over 1425625.36 frames.], batch size: 31, lr: 1.98e-04
2022-05-16 06:37:03,582 INFO [train.py:812] (4/8) Epoch 39, batch 4050, loss[loss=0.1558, simple_loss=0.2484, pruned_loss=0.0316, over 6781.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02826, over 1423750.32 frames.], batch size: 31, lr: 1.98e-04
2022-05-16 06:38:02,732 INFO [train.py:812] (4/8) Epoch 39, batch 4100, loss[loss=0.1458, simple_loss=0.2476, pruned_loss=0.022, over 7213.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02838, over 1422206.15 frames.], batch size: 21, lr: 1.98e-04
2022-05-16 06:39:01,692 INFO [train.py:812] (4/8) Epoch 39, batch 4150, loss[loss=0.1573, simple_loss=0.2625, pruned_loss=0.02604, over 7216.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2407, pruned_loss=0.02802, over 1419253.91 frames.], batch size: 21, lr: 1.98e-04
2022-05-16 06:40:00,321 INFO [train.py:812] (4/8) Epoch 39, batch 4200, loss[loss=0.1378, simple_loss=0.2309, pruned_loss=0.0223, over 6791.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2415, pruned_loss=0.02796, over 1419349.59 frames.], batch size: 31, lr: 1.98e-04
2022-05-16 06:40:58,797 INFO [train.py:812] (4/8) Epoch 39, batch 4250, loss[loss=0.152, simple_loss=0.2354, pruned_loss=0.03426, over 7144.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2409, pruned_loss=0.02766, over 1416124.69 frames.], batch size: 17, lr: 1.98e-04
2022-05-16 06:41:58,210 INFO [train.py:812] (4/8) Epoch 39, batch 4300, loss[loss=0.1869, simple_loss=0.2779, pruned_loss=0.04797, over 7299.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2423, pruned_loss=0.02808, over 1417808.57 frames.], batch size: 25, lr: 1.98e-04
2022-05-16 06:42:57,008 INFO [train.py:812] (4/8) Epoch 39, batch 4350, loss[loss=0.1259, simple_loss=0.2169, pruned_loss=0.01749, over 7436.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2423, pruned_loss=0.0283, over 1414611.78 frames.], batch size: 20, lr: 1.98e-04
2022-05-16 06:43:56,258 INFO [train.py:812] (4/8) Epoch 39, batch 4400, loss[loss=0.1436, simple_loss=0.2416, pruned_loss=0.02273, over 7330.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2436, pruned_loss=0.02862, over 1411148.04 frames.], batch size: 22, lr: 1.98e-04
2022-05-16 06:44:54,110 INFO [train.py:812] (4/8) Epoch 39, batch 4450, loss[loss=0.1204, simple_loss=0.2109, pruned_loss=0.0149, over 7011.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2447, pruned_loss=0.02908, over 1398272.30 frames.], batch size: 16, lr: 1.98e-04
2022-05-16 06:45:52,387 INFO [train.py:812] (4/8) Epoch 39, batch 4500, loss[loss=0.1337, simple_loss=0.2276, pruned_loss=0.01994, over 7172.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2446, pruned_loss=0.02901, over 1387670.37 frames.], batch size: 18, lr: 1.98e-04
2022-05-16 06:46:49,732 INFO [train.py:812] (4/8) Epoch 39, batch 4550, loss[loss=0.1809, simple_loss=0.2766, pruned_loss=0.04263, over 5102.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2463, pruned_loss=0.02998, over 1350076.98 frames.], batch size: 52, lr: 1.98e-04
2022-05-16 06:47:54,904 INFO [train.py:812] (4/8) Epoch 40, batch 0, loss[loss=0.1873, simple_loss=0.2855, pruned_loss=0.04461, over 7270.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2855, pruned_loss=0.04461, over 7270.00 frames.], batch size: 24, lr: 1.96e-04
2022-05-16 06:48:53,195 INFO [train.py:812] (4/8) Epoch 40, batch 50, loss[loss=0.1283, simple_loss=0.2178, pruned_loss=0.01935, over 7270.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2463, pruned_loss=0.02958, over 317080.74 frames.], batch size: 17, lr: 1.95e-04
2022-05-16 06:49:52,227 INFO [train.py:812] (4/8) Epoch 40, batch 100, loss[loss=0.151, simple_loss=0.2408, pruned_loss=0.03062, over 7355.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2435, pruned_loss=0.02876, over 562578.41 frames.], batch size: 19, lr: 1.95e-04
2022-05-16 06:50:51,449 INFO [train.py:812] (4/8) Epoch 40, batch 150, loss[loss=0.1577, simple_loss=0.2608, pruned_loss=0.02731, over 7233.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2392, pruned_loss=0.02824, over 754541.86 frames.], batch size: 20, lr: 1.95e-04
2022-05-16 06:51:50,272 INFO [train.py:812] (4/8) Epoch 40, batch 200, loss[loss=0.1341, simple_loss=0.2116, pruned_loss=0.02832, over 7411.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2412, pruned_loss=0.02867, over 903420.33 frames.], batch size: 18, lr: 1.95e-04
2022-05-16 06:52:48,881 INFO [train.py:812] (4/8) Epoch 40, batch 250, loss[loss=0.1468, simple_loss=0.2533, pruned_loss=0.02018, over 7122.00 frames.], tot_loss[loss=0.149, simple_loss=0.2412, pruned_loss=0.02843, over 1016514.75 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 06:53:47,828 INFO [train.py:812] (4/8) Epoch 40, batch 300, loss[loss=0.148, simple_loss=0.2503, pruned_loss=0.02281, over 7277.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02852, over 1107343.11 frames.], batch size: 24, lr: 1.95e-04
2022-05-16 06:54:46,896 INFO [train.py:812] (4/8) Epoch 40, batch 350, loss[loss=0.1287, simple_loss=0.2231, pruned_loss=0.01713, over 7154.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2417, pruned_loss=0.02856, over 1172429.48 frames.], batch size: 20, lr: 1.95e-04
2022-05-16 06:55:45,289 INFO [train.py:812] (4/8) Epoch 40, batch 400, loss[loss=0.1596, simple_loss=0.2514, pruned_loss=0.03384, over 7200.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02826, over 1229830.21 frames.], batch size: 26, lr: 1.95e-04
2022-05-16 06:56:53,571 INFO [train.py:812] (4/8) Epoch 40, batch 450, loss[loss=0.1625, simple_loss=0.2562, pruned_loss=0.03443, over 7301.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2409, pruned_loss=0.028, over 1273803.01 frames.], batch size: 25, lr: 1.95e-04
2022-05-16 06:57:52,469 INFO [train.py:812] (4/8) Epoch 40, batch 500, loss[loss=0.1331, simple_loss=0.2284, pruned_loss=0.01896, over 7325.00 frames.], tot_loss[loss=0.148, simple_loss=0.2404, pruned_loss=0.02781, over 1305284.24 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 06:58:59,591 INFO [train.py:812] (4/8) Epoch 40, batch 550, loss[loss=0.1695, simple_loss=0.2488, pruned_loss=0.04509, over 7235.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02829, over 1327379.97 frames.], batch size: 20, lr: 1.95e-04
2022-05-16 06:59:58,460 INFO [train.py:812] (4/8) Epoch 40, batch 600, loss[loss=0.1391, simple_loss=0.2274, pruned_loss=0.02537, over 7258.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2403, pruned_loss=0.02805, over 1349511.09 frames.], batch size: 19, lr: 1.95e-04
2022-05-16 07:01:07,491 INFO [train.py:812] (4/8) Epoch 40, batch 650, loss[loss=0.15, simple_loss=0.2404, pruned_loss=0.02983, over 7229.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2405, pruned_loss=0.02814, over 1368916.32 frames.], batch size: 20, lr: 1.95e-04
2022-05-16 07:02:07,010 INFO [train.py:812] (4/8) Epoch 40, batch 700, loss[loss=0.1254, simple_loss=0.2064, pruned_loss=0.0222, over 7283.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2409, pruned_loss=0.02814, over 1381842.65 frames.], batch size: 18, lr: 1.95e-04
2022-05-16 07:03:06,187 INFO [train.py:812] (4/8) Epoch 40, batch 750, loss[loss=0.1511, simple_loss=0.2389, pruned_loss=0.03167, over 7359.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2404, pruned_loss=0.02797, over 1387711.32 frames.], batch size: 19, lr: 1.95e-04
2022-05-16 07:04:05,448 INFO [train.py:812] (4/8) Epoch 40, batch 800, loss[loss=0.1507, simple_loss=0.2488, pruned_loss=0.02626, over 7118.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.02828, over 1396549.07 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 07:05:03,701 INFO [train.py:812] (4/8) Epoch 40, batch 850, loss[loss=0.1254, simple_loss=0.2144, pruned_loss=0.01818, over 7127.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2421, pruned_loss=0.02845, over 1403034.20 frames.], batch size: 17, lr: 1.95e-04
2022-05-16 07:06:12,334 INFO [train.py:812] (4/8) Epoch 40, batch 900, loss[loss=0.1611, simple_loss=0.2552, pruned_loss=0.03347, over 7181.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2422, pruned_loss=0.02818, over 1409056.80 frames.], batch size: 23, lr: 1.95e-04
2022-05-16 07:07:10,688 INFO [train.py:812] (4/8) Epoch 40, batch 950, loss[loss=0.1568, simple_loss=0.245, pruned_loss=0.03428, over 5248.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2424, pruned_loss=0.02829, over 1411490.40 frames.], batch size: 52, lr: 1.95e-04
2022-05-16 07:08:20,197 INFO [train.py:812] (4/8) Epoch 40, batch 1000, loss[loss=0.1713, simple_loss=0.27, pruned_loss=0.03628, over 7118.00 frames.], tot_loss[loss=0.149, simple_loss=0.2419, pruned_loss=0.02808, over 1409904.42 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 07:09:19,151 INFO [train.py:812] (4/8) Epoch 40, batch 1050, loss[loss=0.1349, simple_loss=0.2338, pruned_loss=0.01803, over 7219.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2422, pruned_loss=0.02812, over 1408843.80 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 07:10:42,488 INFO [train.py:812] (4/8) Epoch 40, batch 1100, loss[loss=0.1608, simple_loss=0.2523, pruned_loss=0.03466, over 7165.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2419, pruned_loss=0.02821, over 1408508.01 frames.], batch size: 18, lr: 1.95e-04
2022-05-16 07:11:40,919 INFO [train.py:812] (4/8) Epoch 40, batch 1150, loss[loss=0.1613, simple_loss=0.2588, pruned_loss=0.03193, over 6801.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2422, pruned_loss=0.02826, over 1415661.49 frames.], batch size: 31, lr: 1.95e-04
2022-05-16 07:12:38,507 INFO [train.py:812] (4/8) Epoch 40, batch 1200, loss[loss=0.1653, simple_loss=0.2571, pruned_loss=0.0368, over 6389.00 frames.], tot_loss[loss=0.1503, simple_loss=0.243, pruned_loss=0.02879, over 1418449.59 frames.], batch size: 37, lr: 1.95e-04
2022-05-16 07:13:37,114 INFO [train.py:812] (4/8) Epoch 40, batch 1250, loss[loss=0.1635, simple_loss=0.2486, pruned_loss=0.03918, over 7328.00 frames.], tot_loss[loss=0.15, simple_loss=0.2421, pruned_loss=0.02894, over 1422379.59 frames.], batch size: 25, lr: 1.95e-04
2022-05-16 07:14:35,222 INFO [train.py:812] (4/8) Epoch 40, batch 1300, loss[loss=0.1642, simple_loss=0.2661, pruned_loss=0.03116, over 7438.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.0285, over 1422582.85 frames.], batch size: 20, lr: 1.95e-04
2022-05-16 07:15:33,957 INFO [train.py:812] (4/8) Epoch 40, batch 1350, loss[loss=0.1483, simple_loss=0.2446, pruned_loss=0.02602, over 6304.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.02821, over 1421844.47 frames.], batch size: 38, lr: 1.95e-04
2022-05-16 07:16:32,344 INFO [train.py:812] (4/8) Epoch 40, batch 1400, loss[loss=0.1505, simple_loss=0.2476, pruned_loss=0.02674, over 6427.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2417, pruned_loss=0.02808, over 1423743.02 frames.], batch size: 37, lr: 1.95e-04
2022-05-16 07:17:30,661 INFO [train.py:812] (4/8) Epoch 40, batch 1450, loss[loss=0.1827, simple_loss=0.2802, pruned_loss=0.0426, over 7183.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2411, pruned_loss=0.02772, over 1425155.03 frames.], batch size: 23, lr: 1.95e-04
2022-05-16 07:18:29,823 INFO [train.py:812] (4/8) Epoch 40, batch 1500, loss[loss=0.1287, simple_loss=0.2159, pruned_loss=0.02071, over 7134.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2412, pruned_loss=0.0278, over 1425959.79 frames.], batch size: 17, lr: 1.95e-04
2022-05-16 07:19:28,059 INFO [train.py:812] (4/8) Epoch 40, batch 1550, loss[loss=0.1562, simple_loss=0.2505, pruned_loss=0.03098, over 7210.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2402, pruned_loss=0.02772, over 1423651.95 frames.], batch size: 23, lr: 1.95e-04
2022-05-16 07:20:27,065 INFO [train.py:812] (4/8) Epoch 40, batch 1600, loss[loss=0.155, simple_loss=0.2445, pruned_loss=0.03271, over 7091.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2405, pruned_loss=0.02801, over 1426366.89 frames.], batch size: 28, lr: 1.95e-04
2022-05-16 07:21:25,474 INFO [train.py:812] (4/8) Epoch 40, batch 1650, loss[loss=0.1569, simple_loss=0.2528, pruned_loss=0.03051, over 4837.00 frames.], tot_loss[loss=0.1487, simple_loss=0.241, pruned_loss=0.02823, over 1419746.50 frames.], batch size: 52, lr: 1.95e-04
2022-05-16 07:22:23,890 INFO [train.py:812] (4/8) Epoch 40, batch 1700, loss[loss=0.1099, simple_loss=0.1894, pruned_loss=0.01518, over 7407.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2407, pruned_loss=0.02817, over 1413416.22 frames.], batch size: 17, lr: 1.95e-04
2022-05-16 07:23:23,265 INFO [train.py:812] (4/8) Epoch 40, batch 1750, loss[loss=0.1473, simple_loss=0.2307, pruned_loss=0.03191, over 7319.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2405, pruned_loss=0.02808, over 1415537.62 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 07:24:22,409 INFO [train.py:812] (4/8) Epoch 40, batch 1800, loss[loss=0.1592, simple_loss=0.2495, pruned_loss=0.03445, over 7344.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2417, pruned_loss=0.02848, over 1418475.19 frames.], batch size: 22, lr: 1.95e-04
2022-05-16 07:25:21,049 INFO [train.py:812] (4/8) Epoch 40, batch 1850, loss[loss=0.1289, simple_loss=0.2241, pruned_loss=0.01684, over 7067.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2414, pruned_loss=0.0282, over 1421491.69 frames.], batch size: 18, lr: 1.95e-04
2022-05-16 07:26:20,236 INFO [train.py:812] (4/8) Epoch 40, batch 1900, loss[loss=0.1344, simple_loss=0.2246, pruned_loss=0.02214, over 7149.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2415, pruned_loss=0.02834, over 1424958.21 frames.], batch size: 19, lr: 1.94e-04
2022-05-16 07:27:17,898 INFO [train.py:812] (4/8) Epoch 40, batch 1950, loss[loss=0.1748, simple_loss=0.2532, pruned_loss=0.04822, over 4888.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2419, pruned_loss=0.0285, over 1418865.18 frames.], batch size: 53, lr: 1.94e-04
2022-05-16 07:28:16,414 INFO [train.py:812] (4/8) Epoch 40, batch 2000, loss[loss=0.1366, simple_loss=0.2241, pruned_loss=0.02453, over 7064.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02839, over 1422228.92 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:29:15,096 INFO [train.py:812] (4/8) Epoch 40, batch 2050, loss[loss=0.1306, simple_loss=0.2227, pruned_loss=0.01924, over 7425.00 frames.], tot_loss[loss=0.149, simple_loss=0.2413, pruned_loss=0.02828, over 1426150.36 frames.], batch size: 20, lr: 1.94e-04
2022-05-16 07:30:14,384 INFO [train.py:812] (4/8) Epoch 40, batch 2100, loss[loss=0.1363, simple_loss=0.2162, pruned_loss=0.02818, over 7412.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02837, over 1424775.40 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:31:12,651 INFO [train.py:812] (4/8) Epoch 40, batch 2150, loss[loss=0.1551, simple_loss=0.2516, pruned_loss=0.02932, over 7144.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2414, pruned_loss=0.02845, over 1428920.49 frames.], batch size: 20, lr: 1.94e-04
2022-05-16 07:32:11,383 INFO [train.py:812] (4/8) Epoch 40, batch 2200, loss[loss=0.1466, simple_loss=0.2379, pruned_loss=0.02768, over 7236.00 frames.], tot_loss[loss=0.1487, simple_loss=0.241, pruned_loss=0.02827, over 1431622.85 frames.], batch size: 20, lr: 1.94e-04
2022-05-16 07:33:10,322 INFO [train.py:812] (4/8) Epoch 40, batch 2250, loss[loss=0.1644, simple_loss=0.2663, pruned_loss=0.03125, over 7187.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.02848, over 1429346.31 frames.], batch size: 22, lr: 1.94e-04
2022-05-16 07:34:08,374 INFO [train.py:812] (4/8) Epoch 40, batch 2300, loss[loss=0.1419, simple_loss=0.2333, pruned_loss=0.02526, over 7429.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2402, pruned_loss=0.02827, over 1426463.75 frames.], batch size: 20, lr: 1.94e-04
2022-05-16 07:35:07,172 INFO [train.py:812] (4/8) Epoch 40, batch 2350, loss[loss=0.1579, simple_loss=0.2538, pruned_loss=0.03104, over 7334.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2398, pruned_loss=0.02819, over 1425633.13 frames.], batch size: 22, lr: 1.94e-04
2022-05-16 07:36:06,634 INFO [train.py:812] (4/8) Epoch 40, batch 2400, loss[loss=0.172, simple_loss=0.261, pruned_loss=0.04147, over 7202.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2403, pruned_loss=0.02856, over 1425972.57 frames.], batch size: 22, lr: 1.94e-04
2022-05-16 07:37:04,708 INFO [train.py:812] (4/8) Epoch 40, batch 2450, loss[loss=0.1746, simple_loss=0.2624, pruned_loss=0.04344, over 7039.00 frames.], tot_loss[loss=0.1492, simple_loss=0.241, pruned_loss=0.0287, over 1421061.35 frames.], batch size: 28, lr: 1.94e-04
2022-05-16 07:38:03,599 INFO [train.py:812] (4/8) Epoch 40, batch 2500, loss[loss=0.144, simple_loss=0.2312, pruned_loss=0.02836, over 7407.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2402, pruned_loss=0.02808, over 1417986.29 frames.], batch size: 21, lr: 1.94e-04
2022-05-16 07:39:02,627 INFO [train.py:812] (4/8) Epoch 40, batch 2550, loss[loss=0.1731, simple_loss=0.2589, pruned_loss=0.04363, over 7034.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2401, pruned_loss=0.02786, over 1418287.12 frames.], batch size: 28, lr: 1.94e-04
2022-05-16 07:40:02,265 INFO [train.py:812] (4/8) Epoch 40, batch 2600, loss[loss=0.1515, simple_loss=0.2501, pruned_loss=0.02645, over 7331.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2399, pruned_loss=0.02785, over 1418026.70 frames.], batch size: 22, lr: 1.94e-04
2022-05-16 07:40:59,590 INFO [train.py:812] (4/8) Epoch 40, batch 2650, loss[loss=0.1444, simple_loss=0.2358, pruned_loss=0.02648, over 7166.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02826, over 1420205.81 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:42:08,100 INFO [train.py:812] (4/8) Epoch 40, batch 2700, loss[loss=0.1494, simple_loss=0.2457, pruned_loss=0.02657, over 7121.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2412, pruned_loss=0.02827, over 1421787.43 frames.], batch size: 26, lr: 1.94e-04
2022-05-16 07:43:06,189 INFO [train.py:812] (4/8) Epoch 40, batch 2750, loss[loss=0.175, simple_loss=0.2723, pruned_loss=0.03887, over 7286.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2413, pruned_loss=0.02808, over 1425175.77 frames.], batch size: 24, lr: 1.94e-04
2022-05-16 07:44:05,705 INFO [train.py:812] (4/8) Epoch 40, batch 2800, loss[loss=0.1532, simple_loss=0.2498, pruned_loss=0.02828, over 7057.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2425, pruned_loss=0.02862, over 1421539.01 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:45:02,892 INFO [train.py:812] (4/8) Epoch 40, batch 2850, loss[loss=0.1433, simple_loss=0.2369, pruned_loss=0.02485, over 6307.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02855, over 1418633.40 frames.], batch size: 38, lr: 1.94e-04
2022-05-16 07:46:01,101 INFO [train.py:812] (4/8) Epoch 40, batch 2900, loss[loss=0.1519, simple_loss=0.2489, pruned_loss=0.02749, over 7073.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2414, pruned_loss=0.02796, over 1419010.90 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:46:58,669 INFO [train.py:812] (4/8) Epoch 40, batch 2950, loss[loss=0.1583, simple_loss=0.2579, pruned_loss=0.02939, over 7304.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2422, pruned_loss=0.02806, over 1418454.83 frames.], batch size: 24, lr: 1.94e-04
2022-05-16 07:47:56,499 INFO [train.py:812] (4/8) Epoch 40, batch 3000, loss[loss=0.1386, simple_loss=0.2392, pruned_loss=0.01895, over 7324.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2422, pruned_loss=0.02816, over 1413418.54 frames.], batch size: 22, lr: 1.94e-04
2022-05-16 07:47:56,501 INFO [train.py:832] (4/8) Computing validation loss
2022-05-16 07:48:04,108 INFO [train.py:841] (4/8) Epoch 40, validation: loss=0.1534, simple_loss=0.2485, pruned_loss=0.02916, over 698248.00 frames.
2022-05-16 07:49:02,574 INFO [train.py:812] (4/8) Epoch 40, batch 3050, loss[loss=0.1363, simple_loss=0.2317, pruned_loss=0.02048, over 7354.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2419, pruned_loss=0.02826, over 1415661.46 frames.], batch size: 19, lr: 1.94e-04
2022-05-16 07:50:01,837 INFO [train.py:812] (4/8) Epoch 40, batch 3100, loss[loss=0.1742, simple_loss=0.2695, pruned_loss=0.03951, over 7138.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2418, pruned_loss=0.0284, over 1417856.17 frames.], batch size: 26, lr: 1.94e-04
2022-05-16 07:51:00,387 INFO [train.py:812] (4/8) Epoch 40, batch 3150, loss[loss=0.1446, simple_loss=0.2477, pruned_loss=0.02073, over 7151.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02855, over 1421645.44 frames.], batch size: 20, lr: 1.94e-04
2022-05-16 07:51:59,401 INFO [train.py:812] (4/8) Epoch 40, batch 3200, loss[loss=0.1789, simple_loss=0.2663, pruned_loss=0.04574, over 4898.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02847, over 1422528.21 frames.], batch size: 52, lr: 1.94e-04
2022-05-16 07:52:57,278 INFO [train.py:812] (4/8) Epoch 40, batch 3250, loss[loss=0.1869, simple_loss=0.2731, pruned_loss=0.05032, over 7370.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2423, pruned_loss=0.02864, over 1421133.08 frames.], batch size: 23, lr: 1.94e-04
2022-05-16 07:53:57,056 INFO [train.py:812] (4/8) Epoch 40, batch 3300, loss[loss=0.1707, simple_loss=0.2702, pruned_loss=0.03558, over 7125.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.02823, over 1419704.54 frames.], batch size: 21, lr: 1.94e-04
2022-05-16 07:54:55,915 INFO [train.py:812] (4/8) Epoch 40, batch 3350, loss[loss=0.1391, simple_loss=0.2341, pruned_loss=0.02201, over 7119.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2419, pruned_loss=0.02818, over 1418341.05 frames.], batch size: 21, lr: 1.94e-04
2022-05-16 07:55:55,676 INFO [train.py:812] (4/8) Epoch 40, batch 3400, loss[loss=0.1578, simple_loss=0.2494, pruned_loss=0.03306, over 7161.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2409, pruned_loss=0.02812, over 1418411.30 frames.], batch size: 19, lr: 1.94e-04
2022-05-16 07:56:54,701 INFO [train.py:812] (4/8) Epoch 40, batch 3450, loss[loss=0.1289, simple_loss=0.2149, pruned_loss=0.0214, over 7280.00 frames.], tot_loss[loss=0.1488, simple_loss=0.241, pruned_loss=0.02826, over 1417271.46 frames.], batch size: 17, lr: 1.94e-04
2022-05-16 07:57:54,436 INFO [train.py:812] (4/8) Epoch 40, batch 3500, loss[loss=0.1518, simple_loss=0.254, pruned_loss=0.0248, over 7325.00 frames.], tot_loss[loss=0.149, simple_loss=0.2414, pruned_loss=0.02825, over 1418297.55 frames.], batch size: 21, lr: 1.94e-04
2022-05-16 07:58:53,139 INFO [train.py:812] (4/8) Epoch 40, batch 3550, loss[loss=0.1601, simple_loss=0.2424, pruned_loss=0.03891, over 7076.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2406, pruned_loss=0.02803, over 1419001.95 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:59:51,366 INFO [train.py:812] (4/8) Epoch 40, batch 3600, loss[loss=0.166, simple_loss=0.2574, pruned_loss=0.03736, over 5057.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2411, pruned_loss=0.02836, over 1416335.17 frames.], batch size: 52, lr: 1.94e-04
2022-05-16 08:00:51,215 INFO [train.py:812] (4/8) Epoch 40, batch 3650, loss[loss=0.1615, simple_loss=0.2528, pruned_loss=0.03511, over 6486.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2408, pruned_loss=0.02812, over 1418086.18 frames.], batch size: 37, lr: 1.94e-04
2022-05-16 08:01:49,913 INFO [train.py:812] (4/8) Epoch 40, batch 3700, loss[loss=0.1502, simple_loss=0.2262, pruned_loss=0.03706, over 7141.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02858, over 1422235.44 frames.], batch size: 17, lr: 1.94e-04
2022-05-16 08:02:46,988 INFO [train.py:812] (4/8) Epoch 40, batch 3750, loss[loss=0.134, simple_loss=0.2303, pruned_loss=0.01886, over 7346.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02825, over 1418366.31 frames.], batch size: 19, lr: 1.93e-04
2022-05-16 08:03:45,476 INFO [train.py:812] (4/8) Epoch 40, batch 3800, loss[loss=0.1341, simple_loss=0.2198, pruned_loss=0.02418, over 6989.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2418, pruned_loss=0.02818, over 1423573.69 frames.], batch size: 16, lr: 1.93e-04
2022-05-16 08:04:42,350 INFO [train.py:812] (4/8) Epoch 40, batch 3850, loss[loss=0.1386, simple_loss=0.2404, pruned_loss=0.01839, over 7435.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2412, pruned_loss=0.02782, over 1419455.97 frames.], batch size: 21, lr: 1.93e-04
2022-05-16 08:05:41,378 INFO [train.py:812] (4/8) Epoch 40, batch 3900, loss[loss=0.183, simple_loss=0.2808, pruned_loss=0.04257, over 7202.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2416, pruned_loss=0.02797, over 1420367.15 frames.], batch size: 23, lr: 1.93e-04
2022-05-16 08:06:40,239 INFO [train.py:812] (4/8) Epoch 40, batch 3950, loss[loss=0.1281, simple_loss=0.2093, pruned_loss=0.02348, over 7064.00 frames.], tot_loss[loss=0.1486, simple_loss=0.241, pruned_loss=0.02813, over 1416018.97 frames.], batch size: 18, lr: 1.93e-04
2022-05-16 08:07:38,723 INFO [train.py:812] (4/8) Epoch 40, batch 4000, loss[loss=0.1435, simple_loss=0.2221, pruned_loss=0.0325, over 7124.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2421, pruned_loss=0.02858, over 1416122.50 frames.], batch size: 17, lr: 1.93e-04
2022-05-16 08:08:36,089 INFO [train.py:812] (4/8) Epoch 40, batch 4050, loss[loss=0.185, simple_loss=0.2814, pruned_loss=0.04431, over 7207.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2422, pruned_loss=0.02862, over 1421153.60 frames.], batch size: 22, lr: 1.93e-04
2022-05-16 08:09:35,649 INFO [train.py:812] (4/8) Epoch 40, batch 4100, loss[loss=0.1304, simple_loss=0.238, pruned_loss=0.01146, over 7227.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2414, pruned_loss=0.02824, over 1422019.41 frames.], batch size: 20, lr: 1.93e-04
2022-05-16 08:10:34,189 INFO [train.py:812] (4/8) Epoch 40, batch 4150, loss[loss=0.1559, simple_loss=0.2431, pruned_loss=0.0343, over 7276.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02822, over 1424023.04 frames.], batch size: 18, lr: 1.93e-04
2022-05-16 08:11:32,969 INFO [train.py:812] (4/8) Epoch 40, batch 4200, loss[loss=0.1449, simple_loss=0.2398, pruned_loss=0.02496, over 7155.00 frames.], tot_loss[loss=0.149, simple_loss=0.2419, pruned_loss=0.02806, over 1425288.56 frames.], batch size: 18, lr: 1.93e-04
2022-05-16 08:12:31,938 INFO [train.py:812] (4/8) Epoch 40, batch 4250, loss[loss=0.1602, simple_loss=0.2456, pruned_loss=0.03735, over 7305.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2412, pruned_loss=0.02812, over 1419967.88 frames.], batch size: 21, lr: 1.93e-04
2022-05-16 08:13:30,179 INFO [train.py:812] (4/8) Epoch 40, batch 4300, loss[loss=0.1452, simple_loss=0.2303, pruned_loss=0.03002, over 7170.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2411, pruned_loss=0.02815, over 1421465.96 frames.], batch size: 18, lr: 1.93e-04
2022-05-16 08:14:29,513 INFO [train.py:812] (4/8) Epoch 40, batch 4350, loss[loss=0.1651, simple_loss=0.2603, pruned_loss=0.03488, over 7330.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2416, pruned_loss=0.02833, over 1423079.01 frames.], batch size: 20, lr: 1.93e-04
2022-05-16 08:15:29,020 INFO [train.py:812] (4/8) Epoch 40, batch 4400, loss[loss=0.1656, simple_loss=0.2562, pruned_loss=0.03748, over 6686.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2419, pruned_loss=0.02837, over 1422591.98 frames.], batch size: 31, lr: 1.93e-04
2022-05-16 08:16:26,687 INFO [train.py:812] (4/8) Epoch 40, batch 4450, loss[loss=0.1372, simple_loss=0.2302, pruned_loss=0.02213, over 7158.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2423, pruned_loss=0.02827, over 1410385.85 frames.], batch size: 18, lr: 1.93e-04
2022-05-16 08:17:25,848 INFO [train.py:812] (4/8) Epoch 40, batch 4500, loss[loss=0.1584, simple_loss=0.2516, pruned_loss=0.03263, over 7219.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2425, pruned_loss=0.0283, over 1402540.64 frames.], batch size: 21, lr: 1.93e-04
2022-05-16 08:18:25,891 INFO [train.py:812] (4/8) Epoch 40, batch 4550, loss[loss=0.1284, simple_loss=0.2094, pruned_loss=0.02367, over 6817.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2395, pruned_loss=0.02832, over 1395377.89 frames.], batch size: 15, lr: 1.93e-04
2022-05-16 08:19:10,457 INFO [train.py:1030] (4/8) Done!